Merge tag 'v6.11-rc1' into for-6.12

Linux 6.11-rc1

35 files changed, 1217 insertions, 1471 deletions

diff --git a/block/Kconfig b/block/Kconfig
index dc12af58dbae..5b623b876d3b 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -62,6 +62,8 @@ config BLK_DEV_BSGLIB
 
 config BLK_DEV_INTEGRITY
 	bool "Block layer data integrity support"
+	select CRC_T10DIF
+	select CRC64_ROCKSOFT
 	help
 	Some storage devices allow extra information to be
 	stored/retrieved to help protect the data.  The block layer
@@ -72,12 +74,6 @@ config BLK_DEV_INTEGRITY
 	T10/SCSI Data Integrity Field or the T13/ATA External Path
 	Protection.  If in doubt, say N.
 
-config BLK_DEV_INTEGRITY_T10
-	tristate
-	depends on BLK_DEV_INTEGRITY
-	select CRC_T10DIF
-	select CRC64_ROCKSOFT
-
 config BLK_DEV_WRITE_MOUNTED
 	bool "Allow writing to mounted block devices"
 	default y
diff --git a/block/Makefile b/block/Makefile
index 168150b9c510..ddfd21c1a9ff 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -26,8 +26,7 @@ obj-$(CONFIG_MQ_IOSCHED_KYBER)	+= kyber-iosched.o
 bfq-y				:= bfq-iosched.o bfq-wf2q.o bfq-cgroup.o
 obj-$(CONFIG_IOSCHED_BFQ)	+= bfq.o
 
-obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o blk-integrity.o
-obj-$(CONFIG_BLK_DEV_INTEGRITY_T10)	+= t10-pi.o
+obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o blk-integrity.o t10-pi.o
 obj-$(CONFIG_BLK_MQ_PCI)	+= blk-mq-pci.o
 obj-$(CONFIG_BLK_MQ_VIRTIO)	+= blk-mq-virtio.o
 obj-$(CONFIG_BLK_DEV_ZONED)	+= blk-zoned.o
diff --git a/block/bdev.c b/block/bdev.c
index 353677ac49b3..c5507b6f63b8 100644
--- a/block/bdev.c
+++ b/block/bdev.c
@@ -385,7 +385,7 @@ static struct file_system_type bd_type = {
 };
 
 struct super_block *blockdev_superblock __ro_after_init;
-struct vfsmount *blockdev_mnt __ro_after_init;
+static struct vfsmount *blockdev_mnt __ro_after_init;
 EXPORT_SYMBOL_GPL(blockdev_superblock);
 
 void __init bdev_cache_init(void)
@@ -1260,23 +1260,42 @@ void sync_bdevs(bool wait)
 }
 
 /*
- * Handle STATX_DIOALIGN for block devices.
- *
- * Note that the inode passed to this is the inode of a block device node file,
- * not the block device's internal inode.  Therefore it is *not* valid to use
- * I_BDEV() here; the block device has to be looked up by i_rdev instead.
+ * Handle STATX_{DIOALIGN, WRITE_ATOMIC} for block devices.
  */
-void bdev_statx_dioalign(struct inode *inode, struct kstat *stat)
+void bdev_statx(struct path *path, struct kstat *stat,
+		u32 request_mask)
 {
+	struct inode *backing_inode;
 	struct block_device *bdev;
 
-	bdev = blkdev_get_no_open(inode->i_rdev);
+	if (!(request_mask & (STATX_DIOALIGN | STATX_WRITE_ATOMIC)))
+		return;
+
+	backing_inode = d_backing_inode(path->dentry);
+
+	/*
+	 * Note that backing_inode is the inode of a block device node file,
+	 * not the block device's internal inode.  Therefore it is *not* valid
+	 * to use I_BDEV() here; the block device has to be looked up by i_rdev
+	 * instead.
+	 */
+	bdev = blkdev_get_no_open(backing_inode->i_rdev);
 	if (!bdev)
 		return;
 
-	stat->dio_mem_align = bdev_dma_alignment(bdev) + 1;
-	stat->dio_offset_align = bdev_logical_block_size(bdev);
-	stat->result_mask |= STATX_DIOALIGN;
+	if (request_mask & STATX_DIOALIGN) {
+		stat->dio_mem_align = bdev_dma_alignment(bdev) + 1;
+		stat->dio_offset_align = bdev_logical_block_size(bdev);
+		stat->result_mask |= STATX_DIOALIGN;
+	}
+
+	if (request_mask & STATX_WRITE_ATOMIC && bdev_can_atomic_write(bdev)) {
+		struct request_queue *bd_queue = bdev->bd_queue;
+
+		generic_fill_statx_atomic_writes(stat,
+			queue_atomic_write_unit_min_bytes(bd_queue),
+			queue_atomic_write_unit_max_bytes(bd_queue));
+	}
 
 	blkdev_put_no_open(bdev);
 }
diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
index d442ee358fc2..b758693697c0 100644
--- a/block/bfq-cgroup.c
+++ b/block/bfq-cgroup.c
@@ -797,57 +797,6 @@ void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio)
 	 */
 	bfq_link_bfqg(bfqd, bfqg);
 	__bfq_bic_change_cgroup(bfqd, bic, bfqg);
-	/*
-	 * Update blkg_path for bfq_log_* functions. We cache this
-	 * path, and update it here, for the following
-	 * reasons. Operations on blkg objects in blk-cgroup are
-	 * protected with the request_queue lock, and not with the
-	 * lock that protects the instances of this scheduler
-	 * (bfqd->lock). This exposes BFQ to the following sort of
-	 * race.
-	 *
-	 * The blkg_lookup performed in bfq_get_queue, protected
-	 * through rcu, may happen to return the address of a copy of
-	 * the original blkg. If this is the case, then the
-	 * bfqg_and_blkg_get performed in bfq_get_queue, to pin down
-	 * the blkg, is useless: it does not prevent blk-cgroup code
-	 * from destroying both the original blkg and all objects
-	 * directly or indirectly referred by the copy of the
-	 * blkg.
-	 *
-	 * On the bright side, destroy operations on a blkg invoke, as
-	 * a first step, hooks of the scheduler associated with the
-	 * blkg. And these hooks are executed with bfqd->lock held for
-	 * BFQ. As a consequence, for any blkg associated with the
-	 * request queue this instance of the scheduler is attached
-	 * to, we are guaranteed that such a blkg is not destroyed, and
-	 * that all the pointers it contains are consistent, while we
-	 * are holding bfqd->lock. A blkg_lookup performed with
-	 * bfqd->lock held then returns a fully consistent blkg, which
-	 * remains consistent until this lock is held.
-	 *
-	 * Thanks to the last fact, and to the fact that: (1) bfqg has
-	 * been obtained through a blkg_lookup in the above
-	 * assignment, and (2) bfqd->lock is being held, here we can
-	 * safely use the policy data for the involved blkg (i.e., the
-	 * field bfqg->pd) to get to the blkg associated with bfqg,
-	 * and then we can safely use any field of blkg. After we
-	 * release bfqd->lock, even just getting blkg through this
-	 * bfqg may cause dangling references to be traversed, as
-	 * bfqg->pd may not exist any more.
-	 *
-	 * In view of the above facts, here we cache, in the bfqg, any
-	 * blkg data we may need for this bic, and for its associated
-	 * bfq_queue. As of now, we need to cache only the path of the
-	 * blkg, which is used in the bfq_log_* functions.
-	 *
-	 * Finally, note that bfqg itself needs to be protected from
-	 * destruction on the blkg_free of the original blkg (which
-	 * invokes bfq_pd_free). We use an additional private
-	 * refcounter for bfqg, to let it disappear only after no
-	 * bfq_queue refers to it any longer.
-	 */
-	blkg_path(bfqg_to_blkg(bfqg), bfqg->blkg_path, sizeof(bfqg->blkg_path));
 	bic->blkcg_serial_nr = serial_nr;
 }
 
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 4b88a54a9b76..36a4998c4b37 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -5463,40 +5463,42 @@ static void bfq_exit_icq_bfqq(struct bfq_io_cq *bic, bool is_sync,
 	}
 }
 
+static void _bfq_exit_icq(struct bfq_io_cq *bic, unsigned int num_actuators)
+{
+	struct bfq_iocq_bfqq_data *bfqq_data = bic->bfqq_data;
+	unsigned int act_idx;
+
+	for (act_idx = 0; act_idx < num_actuators; act_idx++) {
+		if (bfqq_data[act_idx].stable_merge_bfqq)
+			bfq_put_stable_ref(bfqq_data[act_idx].stable_merge_bfqq);
+
+		bfq_exit_icq_bfqq(bic, true, act_idx);
+		bfq_exit_icq_bfqq(bic, false, act_idx);
+	}
+}
+
 static void bfq_exit_icq(struct io_cq *icq)
 {
 	struct bfq_io_cq *bic = icq_to_bic(icq);
 	struct bfq_data *bfqd = bic_to_bfqd(bic);
 	unsigned long flags;
-	unsigned int act_idx;
+
 	/*
 	 * If bfqd and thus bfqd->num_actuators is not available any
 	 * longer, then cycle over all possible per-actuator bfqqs in
 	 * next loop. We rely on bic being zeroed on creation, and
 	 * therefore on its unused per-actuator fields being NULL.
-	 */
-	unsigned int num_actuators = BFQ_MAX_ACTUATORS;
-	struct bfq_iocq_bfqq_data *bfqq_data = bic->bfqq_data;
-
-	/*
+	 *
 	 * bfqd is NULL if scheduler already exited, and in that case
 	 * this is the last time these queues are accessed.
 	 */
 	if (bfqd) {
 		spin_lock_irqsave(&bfqd->lock, flags);
-		num_actuators = bfqd->num_actuators;
-	}
-
-	for (act_idx = 0; act_idx < num_actuators; act_idx++) {
-		if (bfqq_data[act_idx].stable_merge_bfqq)
-			bfq_put_stable_ref(bfqq_data[act_idx].stable_merge_bfqq);
-
-		bfq_exit_icq_bfqq(bic, true, act_idx);
-		bfq_exit_icq_bfqq(bic, false, act_idx);
-	}
-
-	if (bfqd)
+		_bfq_exit_icq(bic, bfqd->num_actuators);
 		spin_unlock_irqrestore(&bfqd->lock, flags);
+	} else {
+		_bfq_exit_icq(bic, BFQ_MAX_ACTUATORS);
+	}
 }
 
 /*
diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
index 467e8cfc41a2..08ddf2cfae5b 100644
--- a/block/bfq-iosched.h
+++ b/block/bfq-iosched.h
@@ -1003,9 +1003,6 @@ struct bfq_group {
 	/* must be the first member */
 	struct blkg_policy_data pd;
 
-	/* cached path for this blkg (see comments in bfq_bic_update_cgroup) */
-	char blkg_path[128];
-
 	/* reference counter (see comments in bfq_bic_update_cgroup) */
 	refcount_t ref;
 
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index 2e3e8e04961e..8d1fb38f745f 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -22,9 +22,17 @@ void blk_flush_integrity(void)
 	flush_workqueue(kintegrityd_wq);
 }
 
-static void __bio_integrity_free(struct bio_set *bs,
-				 struct bio_integrity_payload *bip)
+/**
+ * bio_integrity_free - Free bio integrity payload
+ * @bio:	bio containing bip to be freed
+ *
+ * Description: Free the integrity portion of a bio.
+ */
+void bio_integrity_free(struct bio *bio)
 {
+	struct bio_integrity_payload *bip = bio_integrity(bio);
+	struct bio_set *bs = bio->bi_pool;
+
 	if (bs && mempool_initialized(&bs->bio_integrity_pool)) {
 		if (bip->bip_vec)
 			bvec_free(&bs->bvec_integrity_pool, bip->bip_vec,
@@ -33,6 +41,8 @@ static void __bio_integrity_free(struct bio_set *bs,
 	} else {
 		kfree(bip);
 	}
+	bio->bi_integrity = NULL;
+	bio->bi_opf &= ~REQ_INTEGRITY;
 }
 
 /**
@@ -76,7 +86,7 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
 					  &bip->bip_max_vcnt, gfp_mask);
 		if (!bip->bip_vec)
 			goto err;
-	} else {
+	} else if (nr_vecs) {
 		bip->bip_vec = bip->bip_inline_vecs;
 	}
 
@@ -86,7 +96,10 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
 
 	return bip;
 err:
-	__bio_integrity_free(bs, bip);
+	if (bs && mempool_initialized(&bs->bio_integrity_pool))
+		mempool_free(bip, &bs->bio_integrity_pool);
+	else
+		kfree(bip);
 	return ERR_PTR(-ENOMEM);
 }
 EXPORT_SYMBOL(bio_integrity_alloc);
@@ -118,40 +131,25 @@ static void bio_integrity_uncopy_user(struct bio_integrity_payload *bip)
 	bio_integrity_unpin_bvec(copy, nr_vecs, true);
 }
 
-static void bio_integrity_unmap_user(struct bio_integrity_payload *bip)
-{
-	bool dirty = bio_data_dir(bip->bip_bio) == READ;
-
-	if (bip->bip_flags & BIP_COPY_USER) {
-		if (dirty)
-			bio_integrity_uncopy_user(bip);
-		kfree(bvec_virt(bip->bip_vec));
-		return;
-	}
-
-	bio_integrity_unpin_bvec(bip->bip_vec, bip->bip_max_vcnt, dirty);
-}
-
 /**
- * bio_integrity_free - Free bio integrity payload
- * @bio:	bio containing bip to be freed
+ * bio_integrity_unmap_user - Unmap user integrity payload
+ * @bio:	bio containing bip to be unmapped
  *
- * Description: Used to free the integrity portion of a bio. Usually
- * called from bio_free().
+ * Unmap the user mapped integrity portion of a bio.
  */
-void bio_integrity_free(struct bio *bio)
+void bio_integrity_unmap_user(struct bio *bio)
 {
 	struct bio_integrity_payload *bip = bio_integrity(bio);
-	struct bio_set *bs = bio->bi_pool;
 
-	if (bip->bip_flags & BIP_BLOCK_INTEGRITY)
+	if (bip->bip_flags & BIP_COPY_USER) {
+		if (bio_data_dir(bio) == READ)
+			bio_integrity_uncopy_user(bip);
 		kfree(bvec_virt(bip->bip_vec));
-	else if (bip->bip_flags & BIP_INTEGRITY_USER)
-		bio_integrity_unmap_user(bip);
+		return;
+	}
 
-	__bio_integrity_free(bs, bip);
-	bio->bi_integrity = NULL;
-	bio->bi_opf &= ~REQ_INTEGRITY;
+	bio_integrity_unpin_bvec(bip->bip_vec, bip->bip_max_vcnt,
+			bio_data_dir(bio) == READ);
 }
 
 /**
@@ -252,8 +250,9 @@ static int bio_integrity_copy_user(struct bio *bio, struct bio_vec *bvec,
 		goto free_bip;
 	}
 
-	bip->bip_flags |= BIP_INTEGRITY_USER | BIP_COPY_USER;
+	bip->bip_flags |= BIP_COPY_USER;
 	bip->bip_iter.bi_sector = seed;
+	bip->bip_vcnt = nr_vecs;
 	return 0;
 free_bip:
 	bio_integrity_free(bio);
@@ -272,9 +271,9 @@ static int bio_integrity_init_user(struct bio *bio, struct bio_vec *bvec,
 		return PTR_ERR(bip);
 
 	memcpy(bip->bip_vec, bvec, nr_vecs * sizeof(*bvec));
-	bip->bip_flags |= BIP_INTEGRITY_USER;
 	bip->bip_iter.bi_sector = seed;
 	bip->bip_iter.bi_size = len;
+	bip->bip_vcnt = nr_vecs;
 	return 0;
 }
 
@@ -312,7 +311,7 @@ int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t bytes,
 			   u32 seed)
 {
 	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
-	unsigned int align = q->dma_pad_mask | queue_dma_alignment(q);
+	unsigned int align = blk_lim_dma_alignment_and_pad(&q->limits);
 	struct page *stack_pages[UIO_FASTIOV], **pages = stack_pages;
 	struct bio_vec stack_vec[UIO_FASTIOV], *bvec = stack_vec;
 	unsigned int direction, nr_bvecs;
@@ -375,44 +374,6 @@ free_bvec:
 EXPORT_SYMBOL_GPL(bio_integrity_map_user);
 
 /**
- * bio_integrity_process - Process integrity metadata for a bio
- * @bio:	bio to generate/verify integrity metadata for
- * @proc_iter:  iterator to process
- * @proc_fn:	Pointer to the relevant processing function
- */
-static blk_status_t bio_integrity_process(struct bio *bio,
-		struct bvec_iter *proc_iter, integrity_processing_fn *proc_fn)
-{
-	struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk);
-	struct blk_integrity_iter iter;
-	struct bvec_iter bviter;
-	struct bio_vec bv;
-	struct bio_integrity_payload *bip = bio_integrity(bio);
-	blk_status_t ret = BLK_STS_OK;
-
-	iter.disk_name = bio->bi_bdev->bd_disk->disk_name;
-	iter.interval = 1 << bi->interval_exp;
-	iter.tuple_size = bi->tuple_size;
-	iter.seed = proc_iter->bi_sector;
-	iter.prot_buf = bvec_virt(bip->bip_vec);
-	iter.pi_offset = bi->pi_offset;
-
-	__bio_for_each_segment(bv, bio, bviter, *proc_iter) {
-		void *kaddr = bvec_kmap_local(&bv);
-
-		iter.data_buf = kaddr;
-		iter.data_size = bv.bv_len;
-		ret = proc_fn(&iter);
-		kunmap_local(kaddr);
-
-		if (ret)
-			break;
-
-	}
-	return ret;
-}
-
-/**
  * bio_integrity_prep - Prepare bio for integrity I/O
  * @bio:	bio to prepare
  *
@@ -428,17 +389,13 @@ bool bio_integrity_prep(struct bio *bio)
 {
 	struct bio_integrity_payload *bip;
 	struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk);
+	unsigned int len;
 	void *buf;
-	unsigned long start, end;
-	unsigned int len, nr_pages;
-	unsigned int bytes, offset, i;
+	gfp_t gfp = GFP_NOIO;
 
 	if (!bi)
 		return true;
 
-	if (bio_op(bio) != REQ_OP_READ && bio_op(bio) != REQ_OP_WRITE)
-		return true;
-
 	if (!bio_sectors(bio))
 		return true;
 
@@ -446,32 +403,36 @@ bool bio_integrity_prep(struct bio *bio)
 	if (bio_integrity(bio))
 		return true;
 
-	if (bio_data_dir(bio) == READ) {
-		if (!bi->profile->verify_fn ||
-		    !(bi->flags & BLK_INTEGRITY_VERIFY))
+	switch (bio_op(bio)) {
+	case REQ_OP_READ:
+		if (bi->flags & BLK_INTEGRITY_NOVERIFY)
 			return true;
-	} else {
-		if (!bi->profile->generate_fn ||
-		    !(bi->flags & BLK_INTEGRITY_GENERATE))
+		break;
+	case REQ_OP_WRITE:
+		if (bi->flags & BLK_INTEGRITY_NOGENERATE)
 			return true;
+
+		/*
+		 * Zero the memory allocated to not leak uninitialized kernel
+		 * memory to disk for non-integrity metadata where nothing else
+		 * initializes the memory.
+		 */
+		if (bi->csum_type == BLK_INTEGRITY_CSUM_NONE)
+			gfp |= __GFP_ZERO;
+		break;
+	default:
+		return true;
 	}
 
 	/* Allocate kernel buffer for protection data */
 	len = bio_integrity_bytes(bi, bio_sectors(bio));
-	buf = kmalloc(len, GFP_NOIO);
+	buf = kmalloc(len, gfp);
 	if (unlikely(buf == NULL)) {
-		printk(KERN_ERR "could not allocate integrity buffer\n");
 		goto err_end_io;
 	}
 
-	end = (((unsigned long) buf) + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
-	start = ((unsigned long) buf) >> PAGE_SHIFT;
-	nr_pages = end - start;
-
-	/* Allocate bio integrity payload and integrity vectors */
-	bip = bio_integrity_alloc(bio, GFP_NOIO, nr_pages);
+	bip = bio_integrity_alloc(bio, GFP_NOIO, 1);
 	if (IS_ERR(bip)) {
-		printk(KERN_ERR "could not allocate data integrity bioset\n");
 		kfree(buf);
 		goto err_end_io;
 	}
@@ -479,35 +440,20 @@ bool bio_integrity_prep(struct bio *bio)
 	bip->bip_flags |= BIP_BLOCK_INTEGRITY;
 	bip_set_seed(bip, bio->bi_iter.bi_sector);
 
-	if (bi->flags & BLK_INTEGRITY_IP_CHECKSUM)
+	if (bi->csum_type == BLK_INTEGRITY_CSUM_IP)
 		bip->bip_flags |= BIP_IP_CHECKSUM;
 
-	/* Map it */
-	offset = offset_in_page(buf);
-	for (i = 0; i < nr_pages && len > 0; i++) {
-		bytes = PAGE_SIZE - offset;
-
-		if (bytes > len)
-			bytes = len;
-
-		if (bio_integrity_add_page(bio, virt_to_page(buf),
-					   bytes, offset) < bytes) {
-			printk(KERN_ERR "could not attach integrity payload\n");
-			goto err_end_io;
-		}
-
-		buf += bytes;
-		len -= bytes;
-		offset = 0;
+	if (bio_integrity_add_page(bio, virt_to_page(buf), len,
+			offset_in_page(buf)) < len) {
+		printk(KERN_ERR "could not attach integrity payload\n");
+		goto err_end_io;
 	}
 
 	/* Auto-generate integrity metadata if this is a write */
-	if (bio_data_dir(bio) == WRITE) {
-		bio_integrity_process(bio, &bio->bi_iter,
-				      bi->profile->generate_fn);
-	} else {
+	if (bio_data_dir(bio) == WRITE)
+		blk_integrity_generate(bio);
+	else
 		bip->bio_iter = bio->bi_iter;
-	}
 	return true;
 
 err_end_io:
@@ -530,15 +476,10 @@ static void bio_integrity_verify_fn(struct work_struct *work)
 	struct bio_integrity_payload *bip =
 		container_of(work, struct bio_integrity_payload, bip_work);
 	struct bio *bio = bip->bip_bio;
-	struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk);
 
-	/*
-	 * At the moment verify is called bio's iterator was advanced
-	 * during split and completion, we need to rewind iterator to
-	 * it's original position.
-	 */
-	bio->bi_status = bio_integrity_process(bio, &bip->bio_iter,
-						bi->profile->verify_fn);
+	blk_integrity_verify(bio);
+
+	kfree(bvec_virt(bip->bip_vec));
 	bio_integrity_free(bio);
 	bio_endio(bio);
 }
@@ -559,13 +500,13 @@ bool __bio_integrity_endio(struct bio *bio)
 	struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk);
 	struct bio_integrity_payload *bip = bio_integrity(bio);
 
-	if (bio_op(bio) == REQ_OP_READ && !bio->bi_status &&
-	    (bip->bip_flags & BIP_BLOCK_INTEGRITY) && bi->profile->verify_fn) {
+	if (bio_op(bio) == REQ_OP_READ && !bio->bi_status && bi->csum_type) {
 		INIT_WORK(&bip->bip_work, bio_integrity_verify_fn);
 		queue_work(kintegrityd_wq, &bip->bip_work);
 		return false;
 	}
 
+	kfree(bvec_virt(bip->bip_vec));
 	bio_integrity_free(bio);
 	return true;
 }
@@ -620,14 +561,11 @@ int bio_integrity_clone(struct bio *bio, struct bio *bio_src,
 
 	BUG_ON(bip_src == NULL);
 
-	bip = bio_integrity_alloc(bio, gfp_mask, bip_src->bip_vcnt);
+	bip = bio_integrity_alloc(bio, gfp_mask, 0);
 	if (IS_ERR(bip))
 		return PTR_ERR(bip);
 
-	memcpy(bip->bip_vec, bip_src->bip_vec,
-	       bip_src->bip_vcnt * sizeof(struct bio_vec));
-
-	bip->bip_vcnt = bip_src->bip_vcnt;
+	bip->bip_vec = bip_src->bip_vec;
 	bip->bip_iter = bip_src->bip_iter;
 	bip->bip_flags = bip_src->bip_flags & ~BIP_BLOCK_INTEGRITY;
 
diff --git a/block/bio.c b/block/bio.c
index e9e809a63c59..c4053d49679a 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -4,7 +4,7 @@
  */
 #include <linux/mm.h>
 #include <linux/swap.h>
-#include <linux/bio.h>
+#include <linux/bio-integrity.h>
 #include <linux/blkdev.h>
 #include <linux/uio.h>
 #include <linux/iocontext.h>
@@ -953,7 +953,7 @@ bool bvec_try_merge_hw_page(struct request_queue *q, struct bio_vec *bv,
 		bool *same_page)
 {
 	unsigned long mask = queue_segment_boundary(q);
-	phys_addr_t addr1 = page_to_phys(bv->bv_page) + bv->bv_offset;
+	phys_addr_t addr1 = bvec_phys(bv);
 	phys_addr_t addr2 = page_to_phys(page) + offset + len - 1;
 
 	if ((addr1 | mask) != (addr2 | mask))
@@ -1630,8 +1630,18 @@ again:
 		goto again;
 	}
 
-	/* release cgroup info */
-	bio_uninit(bio);
+#ifdef CONFIG_BLK_CGROUP
+	/*
+	 * Release cgroup info.  We shouldn't have to do this here, but quite
+	 * a few callers of bio_init fail to call bio_uninit, so we cover up
+	 * for that here at least for now.
+	 */
+	if (bio->bi_blkg) {
+		blkg_put(bio->bi_blkg);
+		bio->bi_blkg = NULL;
+	}
+#endif
+
 	if (bio->bi_end_io)
 		bio->bi_end_io(bio);
 }
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 37e6cc91d576..69e70964398c 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -2182,12 +2182,13 @@ void blk_cgroup_bio_start(struct bio *bio)
 
 bool blk_cgroup_congested(void)
 {
-	struct cgroup_subsys_state *css;
+	struct blkcg *blkcg;
 	bool ret = false;
 
 	rcu_read_lock();
-	for (css = blkcg_css(); css; css = css->parent) {
-		if (atomic_read(&css->cgroup->congestion_count)) {
+	for (blkcg = css_to_blkcg(blkcg_css()); blkcg;
+	     blkcg = blkcg_parent(blkcg)) {
+		if (atomic_read(&blkcg->congestion_count)) {
 			ret = true;
 			break;
 		}
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index 90b3959d88cf..864fad4a850b 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -95,6 +95,8 @@ struct blkcg {
 	struct cgroup_subsys_state	css;
 	spinlock_t			lock;
 	refcount_t			online_pin;
+	/* If there is block congestion on this cgroup. */
+	atomic_t			congestion_count;
 
 	struct radix_tree_root		blkg_tree;
 	struct blkcg_gq	__rcu		*blkg_hint;
@@ -301,19 +303,6 @@ static inline struct blkcg *cpd_to_blkcg(struct blkcg_policy_data *cpd)
 }
 
 /**
- * blkg_path - format cgroup path of blkg
- * @blkg: blkg of interest
- * @buf: target buffer
- * @buflen: target buffer length
- *
- * Format the path of the cgroup of @blkg into @buf.
- */
-static inline int blkg_path(struct blkcg_gq *blkg, char *buf, int buflen)
-{
-	return cgroup_path(blkg->blkcg->css.cgroup, buf, buflen);
-}
-
-/**
  * blkg_get - get a blkg reference
  * @blkg: blkg to get
  *
@@ -387,7 +376,7 @@ static inline void blkcg_use_delay(struct blkcg_gq *blkg)
 	if (WARN_ON_ONCE(atomic_read(&blkg->use_delay) < 0))
 		return;
 	if (atomic_add_return(1, &blkg->use_delay) == 1)
-		atomic_inc(&blkg->blkcg->css.cgroup->congestion_count);
+		atomic_inc(&blkg->blkcg->congestion_count);
 }
 
 static inline int blkcg_unuse_delay(struct blkcg_gq *blkg)
@@ -412,7 +401,7 @@ static inline int blkcg_unuse_delay(struct blkcg_gq *blkg)
 	if (old == 0)
 		return 0;
 	if (old == 1)
-		atomic_dec(&blkg->blkcg->css.cgroup->congestion_count);
+		atomic_dec(&blkg->blkcg->congestion_count);
 	return 1;
 }
 
@@ -431,7 +420,7 @@ static inline void blkcg_set_delay(struct blkcg_gq *blkg, u64 delay)
 
 	/* We only want 1 person setting the congestion count for this blkg. */
 	if (!old && atomic_try_cmpxchg(&blkg->use_delay, &old, -1))
-		atomic_inc(&blkg->blkcg->css.cgroup->congestion_count);
+		atomic_inc(&blkg->blkcg->congestion_count);
 
 	atomic64_set(&blkg->delay_nsec, delay);
 }
@@ -448,7 +437,7 @@ static inline void blkcg_clear_delay(struct blkcg_gq *blkg)
 
 	/* We only want 1 person clearing the congestion count for this blkg. */
 	if (old && atomic_try_cmpxchg(&blkg->use_delay, &old, 0))
-		atomic_dec(&blkg->blkcg->css.cgroup->congestion_count);
+		atomic_dec(&blkg->blkcg->congestion_count);
 }
 
 /**
diff --git a/block/blk-core.c b/block/blk-core.c
index 82c3ae22d76d..1217c2cd66dd 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -94,20 +94,6 @@ void blk_queue_flag_clear(unsigned int flag, struct request_queue *q)
 }
 EXPORT_SYMBOL(blk_queue_flag_clear);
 
-/**
- * blk_queue_flag_test_and_set - atomically test and set a queue flag
- * @flag: flag to be set
- * @q: request queue
- *
- * Returns the previous value of @flag - 0 if the flag was not set and 1 if
- * the flag was already set.
- */
-bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q)
-{
-	return test_and_set_bit(flag, &q->queue_flags);
-}
-EXPORT_SYMBOL_GPL(blk_queue_flag_test_and_set);
-
 #define REQ_OP_NAME(name) [REQ_OP_##name] = #name
 static const char *const blk_op_name[] = {
 	REQ_OP_NAME(READ),
@@ -174,6 +160,8 @@ static const struct {
 	/* Command duration limit device-side timeout */
 	[BLK_STS_DURATION_LIMIT]	= { -ETIME, "duration limit exceeded" },
 
+	[BLK_STS_INVAL]		= { -EINVAL,	"invalid" },
+
 	/* everything else not covered above: */
 	[BLK_STS_IOERR]		= { -EIO,	"I/O" },
 };
@@ -739,6 +727,18 @@ void submit_bio_noacct_nocheck(struct bio *bio)
 		__submit_bio_noacct(bio);
 }
 
+static blk_status_t blk_validate_atomic_write_op_size(struct request_queue *q,
+						 struct bio *bio)
+{
+	if (bio->bi_iter.bi_size > queue_atomic_write_unit_max_bytes(q))
+		return BLK_STS_INVAL;
+
+	if (bio->bi_iter.bi_size % queue_atomic_write_unit_min_bytes(q))
+		return BLK_STS_INVAL;
+
+	return BLK_STS_OK;
+}
+
 /**
  * submit_bio_noacct - re-submit a bio to the block device layer for I/O
  * @bio:  The bio describing the location in memory and on the device.
@@ -782,7 +782,7 @@ void submit_bio_noacct(struct bio *bio)
 		if (WARN_ON_ONCE(bio_op(bio) != REQ_OP_WRITE &&
 				 bio_op(bio) != REQ_OP_ZONE_APPEND))
 			goto end_io;
-		if (!test_bit(QUEUE_FLAG_WC, &q->queue_flags)) {
+		if (!bdev_write_cache(bdev)) {
 			bio->bi_opf &= ~(REQ_PREFLUSH | REQ_FUA);
 			if (!bio_sectors(bio)) {
 				status = BLK_STS_OK;
@@ -791,12 +791,20 @@ void submit_bio_noacct(struct bio *bio)
 		}
 	}
 
-	if (!test_bit(QUEUE_FLAG_POLL, &q->queue_flags))
+	if (!(q->limits.features & BLK_FEAT_POLL) &&
+			(bio->bi_opf & REQ_POLLED)) {
 		bio_clear_polled(bio);
+		goto not_supported;
+	}
 
 	switch (bio_op(bio)) {
 	case REQ_OP_READ:
 	case REQ_OP_WRITE:
+		if (bio->bi_opf & REQ_ATOMIC) {
+			status = blk_validate_atomic_write_op_size(q, bio);
+			if (status != BLK_STS_OK)
+				goto end_io;
+		}
 		break;
 	case REQ_OP_FLUSH:
 		/*
@@ -825,11 +833,8 @@ void submit_bio_noacct(struct bio *bio)
 	case REQ_OP_ZONE_OPEN:
 	case REQ_OP_ZONE_CLOSE:
 	case REQ_OP_ZONE_FINISH:
-		if (!bdev_is_zoned(bio->bi_bdev))
-			goto not_supported;
-		break;
 	case REQ_OP_ZONE_RESET_ALL:
-		if (!bdev_is_zoned(bio->bi_bdev) || !blk_queue_zone_resetall(q))
+		if (!bdev_is_zoned(bio->bi_bdev))
 			goto not_supported;
 		break;
 	case REQ_OP_DRV_IN:
@@ -915,8 +920,7 @@ int bio_poll(struct bio *bio, struct io_comp_batch *iob, unsigned int flags)
 		return 0;
 
 	q = bdev_get_queue(bdev);
-	if (cookie == BLK_QC_T_NONE ||
-	    !test_bit(QUEUE_FLAG_POLL, &q->queue_flags))
+	if (cookie == BLK_QC_T_NONE || !(q->limits.features & BLK_FEAT_POLL))
 		return 0;
 
 	blk_flush_plug(current->plug, false);
diff --git a/block/blk-flush.c b/block/blk-flush.c
index c17cf8ed8113..a72e2a83d075 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -100,23 +100,6 @@ blk_get_flush_queue(struct request_queue *q, struct blk_mq_ctx *ctx)
 	return blk_mq_map_queue(q, REQ_OP_FLUSH, ctx)->fq;
 }
 
-static unsigned int blk_flush_policy(unsigned long fflags, struct request *rq)
-{
-	unsigned int policy = 0;
-
-	if (blk_rq_sectors(rq))
-		policy |= REQ_FSEQ_DATA;
-
-	if (fflags & (1UL << QUEUE_FLAG_WC)) {
-		if (rq->cmd_flags & REQ_PREFLUSH)
-			policy |= REQ_FSEQ_PREFLUSH;
-		if (!(fflags & (1UL << QUEUE_FLAG_FUA)) &&
-		    (rq->cmd_flags & REQ_FUA))
-			policy |= REQ_FSEQ_POSTFLUSH;
-	}
-	return policy;
-}
-
 static unsigned int blk_flush_cur_seq(struct request *rq)
 {
 	return 1 << ffz(rq->flush.seq);
@@ -185,7 +168,7 @@ static void blk_flush_complete_seq(struct request *rq,
 		/* queue for flush */
 		if (list_empty(pending))
 			fq->flush_pending_since = jiffies;
-		list_move_tail(&rq->queuelist, pending);
+		list_add_tail(&rq->queuelist, pending);
 		break;
 
 	case REQ_FSEQ_DATA:
@@ -263,6 +246,7 @@ static enum rq_end_io_ret flush_end_io(struct request *flush_rq,
 		unsigned int seq = blk_flush_cur_seq(rq);
 
 		BUG_ON(seq != REQ_FSEQ_PREFLUSH && seq != REQ_FSEQ_POSTFLUSH);
+		list_del_init(&rq->queuelist);
 		blk_flush_complete_seq(rq, fq, seq, error);
 	}
 
@@ -398,19 +382,32 @@ static void blk_rq_init_flush(struct request *rq)
 bool blk_insert_flush(struct request *rq)
 {
 	struct request_queue *q = rq->q;
-	unsigned long fflags = q->queue_flags;	/* may change, cache */
-	unsigned int policy = blk_flush_policy(fflags, rq);
 	struct blk_flush_queue *fq = blk_get_flush_queue(q, rq->mq_ctx);
+	bool supports_fua = q->limits.features & BLK_FEAT_FUA;
+	unsigned int policy = 0;
 
 	/* FLUSH/FUA request must never be merged */
 	WARN_ON_ONCE(rq->bio != rq->biotail);
 
+	if (blk_rq_sectors(rq))
+		policy |= REQ_FSEQ_DATA;
+
+	/*
+	 * Check which flushes we need to sequence for this operation.
+	 */
+	if (blk_queue_write_cache(q)) {
+		if (rq->cmd_flags & REQ_PREFLUSH)
+			policy |= REQ_FSEQ_PREFLUSH;
+		if ((rq->cmd_flags & REQ_FUA) && !supports_fua)
+			policy |= REQ_FSEQ_POSTFLUSH;
+	}
+
 	/*
 	 * @policy now records what operations need to be done.  Adjust
 	 * REQ_PREFLUSH and FUA for the driver.
 	 */
 	rq->cmd_flags &= ~REQ_PREFLUSH;
-	if (!(fflags & (1UL << QUEUE_FLAG_FUA)))
+	if (!supports_fua)
 		rq->cmd_flags &= ~REQ_FUA;
 
 	/*
diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index ccbeb6dfa87a..010decc892ea 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -107,60 +107,6 @@ new_segment:
 }
 EXPORT_SYMBOL(blk_rq_map_integrity_sg);
 
-/**
- * blk_integrity_compare - Compare integrity profile of two disks
- * @gd1:	Disk to compare
- * @gd2:	Disk to compare
- *
- * Description: Meta-devices like DM and MD need to verify that all
- * sub-devices use the same integrity format before advertising to
- * upper layers that they can send/receive integrity metadata.  This
- * function can be used to check whether two gendisk devices have
- * compatible integrity formats.
- */
-int blk_integrity_compare(struct gendisk *gd1, struct gendisk *gd2)
-{
-	struct blk_integrity *b1 = &gd1->queue->integrity;
-	struct blk_integrity *b2 = &gd2->queue->integrity;
-
-	if (!b1->profile && !b2->profile)
-		return 0;
-
-	if (!b1->profile || !b2->profile)
-		return -1;
-
-	if (b1->interval_exp != b2->interval_exp) {
-		pr_err("%s: %s/%s protection interval %u != %u\n",
-		       __func__, gd1->disk_name, gd2->disk_name,
-		       1 << b1->interval_exp, 1 << b2->interval_exp);
-		return -1;
-	}
-
-	if (b1->tuple_size != b2->tuple_size) {
-		pr_err("%s: %s/%s tuple sz %u != %u\n", __func__,
-		       gd1->disk_name, gd2->disk_name,
-		       b1->tuple_size, b2->tuple_size);
-		return -1;
-	}
-
-	if (b1->tag_size && b2->tag_size && (b1->tag_size != b2->tag_size)) {
-		pr_err("%s: %s/%s tag sz %u != %u\n", __func__,
-		       gd1->disk_name, gd2->disk_name,
-		       b1->tag_size, b2->tag_size);
-		return -1;
-	}
-
-	if (b1->profile != b2->profile) {
-		pr_err("%s: %s/%s type %s != %s\n", __func__,
-		       gd1->disk_name, gd2->disk_name,
-		       b1->profile->name, b2->profile->name);
-		return -1;
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL(blk_integrity_compare);
-
 bool blk_integrity_merge_rq(struct request_queue *q, struct request *req,
 			    struct request *next)
 {
@@ -214,7 +160,64 @@ bool blk_integrity_merge_bio(struct request_queue *q, struct request *req,
 
 static inline struct blk_integrity *dev_to_bi(struct device *dev)
 {
-	return &dev_to_disk(dev)->queue->integrity;
+	return &dev_to_disk(dev)->queue->limits.integrity;
+}
+
+const char *blk_integrity_profile_name(struct blk_integrity *bi)
+{
+	switch (bi->csum_type) {
+	case BLK_INTEGRITY_CSUM_IP:
+		if (bi->flags & BLK_INTEGRITY_REF_TAG)
+			return "T10-DIF-TYPE1-IP";
+		return "T10-DIF-TYPE3-IP";
+	case BLK_INTEGRITY_CSUM_CRC:
+		if (bi->flags & BLK_INTEGRITY_REF_TAG)
+			return "T10-DIF-TYPE1-CRC";
+		return "T10-DIF-TYPE3-CRC";
+	case BLK_INTEGRITY_CSUM_CRC64:
+		if (bi->flags & BLK_INTEGRITY_REF_TAG)
+			return "EXT-DIF-TYPE1-CRC64";
+		return "EXT-DIF-TYPE3-CRC64";
+	case BLK_INTEGRITY_CSUM_NONE:
+		break;
+	}
+
+	return "nop";
+}
+EXPORT_SYMBOL_GPL(blk_integrity_profile_name);
+
+static ssize_t flag_store(struct device *dev, const char *page, size_t count,
+		unsigned char flag)
+{
+	struct request_queue *q = dev_to_disk(dev)->queue;
+	struct queue_limits lim;
+	unsigned long val;
+	int err;
+
+	err = kstrtoul(page, 10, &val);
+	if (err)
+		return err;
+
+	/* note that the flags are inverted vs the values in the sysfs files */
+	lim = queue_limits_start_update(q);
+	if (val)
+		lim.integrity.flags &= ~flag;
+	else
+		lim.integrity.flags |= flag;
+
+	blk_mq_freeze_queue(q);
+	err = queue_limits_commit_update(q, &lim);
+	blk_mq_unfreeze_queue(q);
+	if (err)
+		return err;
+	return count;
+}
+
+static ssize_t flag_show(struct device *dev, char *page, unsigned char flag)
+{
+	struct blk_integrity *bi = dev_to_bi(dev);
+
+	return sysfs_emit(page, "%d\n", !(bi->flags & flag));
 }
 
 static ssize_t format_show(struct device *dev, struct device_attribute *attr,
@@ -222,9 +225,9 @@ static ssize_t format_show(struct device *dev, struct device_attribute *attr,
 {
 	struct blk_integrity *bi = dev_to_bi(dev);
 
-	if (bi->profile && bi->profile->name)
-		return sysfs_emit(page, "%s\n", bi->profile->name);
-	return sysfs_emit(page, "none\n");
+	if (!bi->tuple_size)
+		return sysfs_emit(page, "none\n");
+	return sysfs_emit(page, "%s\n", blk_integrity_profile_name(bi));
 }
 
 static ssize_t tag_size_show(struct device *dev, struct device_attribute *attr,
@@ -249,49 +252,26 @@ static ssize_t read_verify_store(struct device *dev,
 				 struct device_attribute *attr,
 				 const char *page, size_t count)
 {
-	struct blk_integrity *bi = dev_to_bi(dev);
-	char *p = (char *) page;
-	unsigned long val = simple_strtoul(p, &p, 10);
-
-	if (val)
-		bi->flags |= BLK_INTEGRITY_VERIFY;
-	else
-		bi->flags &= ~BLK_INTEGRITY_VERIFY;
-
-	return count;
+	return flag_store(dev, page, count, BLK_INTEGRITY_NOVERIFY);
 }
 
 static ssize_t read_verify_show(struct device *dev,
 				struct device_attribute *attr, char *page)
 {
-	struct blk_integrity *bi = dev_to_bi(dev);
-
-	return sysfs_emit(page, "%d\n", !!(bi->flags & BLK_INTEGRITY_VERIFY));
+	return flag_show(dev, page, BLK_INTEGRITY_NOVERIFY);
 }
 
 static ssize_t write_generate_store(struct device *dev,
 				    struct device_attribute *attr,
 				    const char *page, size_t count)
 {
-	struct blk_integrity *bi = dev_to_bi(dev);
-
-	char *p = (char *) page;
-	unsigned long val = simple_strtoul(p, &p, 10);
-
-	if (val)
-		bi->flags |= BLK_INTEGRITY_GENERATE;
-	else
-		bi->flags &= ~BLK_INTEGRITY_GENERATE;
-
-	return count;
+	return flag_store(dev, page, count, BLK_INTEGRITY_NOGENERATE);
 }
 
 static ssize_t write_generate_show(struct device *dev,
 				   struct device_attribute *attr, char *page)
 {
-	struct blk_integrity *bi = dev_to_bi(dev);
-
-	return sysfs_emit(page, "%d\n", !!(bi->flags & BLK_INTEGRITY_GENERATE));
+	return flag_show(dev, page, BLK_INTEGRITY_NOGENERATE);
 }
 
 static ssize_t device_is_integrity_capable_show(struct device *dev,
@@ -325,81 +305,3 @@ const struct attribute_group blk_integrity_attr_group = {
 	.name = "integrity",
 	.attrs = integrity_attrs,
 };
-
-static blk_status_t blk_integrity_nop_fn(struct blk_integrity_iter *iter)
-{
-	return BLK_STS_OK;
-}
-
-static void blk_integrity_nop_prepare(struct request *rq)
-{
-}
-
-static void blk_integrity_nop_complete(struct request *rq,
-		unsigned int nr_bytes)
-{
-}
-
-static const struct blk_integrity_profile nop_profile = {
-	.name = "nop",
-	.generate_fn = blk_integrity_nop_fn,
-	.verify_fn = blk_integrity_nop_fn,
-	.prepare_fn = blk_integrity_nop_prepare,
-	.complete_fn = blk_integrity_nop_complete,
-};
-
-/**
- * blk_integrity_register - Register a gendisk as being integrity-capable
- * @disk:	struct gendisk pointer to make integrity-aware
- * @template:	block integrity profile to register
- *
- * Description: When a device needs to advertise itself as being able to
- * send/receive integrity metadata it must use this function to register
- * the capability with the block layer. The template is a blk_integrity
- * struct with values appropriate for the underlying hardware. See
- * Documentation/block/data-integrity.rst.
- */
-void blk_integrity_register(struct gendisk *disk, struct blk_integrity *template)
-{
-	struct blk_integrity *bi = &disk->queue->integrity;
-
-	bi->flags = BLK_INTEGRITY_VERIFY | BLK_INTEGRITY_GENERATE |
-		template->flags;
-	bi->interval_exp = template->interval_exp ? :
-		ilog2(queue_logical_block_size(disk->queue));
-	bi->profile = template->profile ? template->profile : &nop_profile;
-	bi->tuple_size = template->tuple_size;
-	bi->tag_size = template->tag_size;
-	bi->pi_offset = template->pi_offset;
-
-	blk_queue_flag_set(QUEUE_FLAG_STABLE_WRITES, disk->queue);
-
-#ifdef CONFIG_BLK_INLINE_ENCRYPTION
-	if (disk->queue->crypto_profile) {
-		pr_warn("blk-integrity: Integrity and hardware inline encryption are not supported together. Disabling hardware inline encryption.\n");
-		disk->queue->crypto_profile = NULL;
-	}
-#endif
-}
-EXPORT_SYMBOL(blk_integrity_register);
-
-/**
- * blk_integrity_unregister - Unregister block integrity profile
- * @disk:	disk whose integrity profile to unregister
- *
- * Description: This function unregisters the integrity capability from
- * a block device.
- */
-void blk_integrity_unregister(struct gendisk *disk)
-{
-	struct blk_integrity *bi = &disk->queue->integrity;
-
-	if (!bi->profile)
-		return;
-
-	/* ensure all bios are off the integrity workqueue */
-	blk_flush_integrity();
-	blk_queue_flag_clear(QUEUE_FLAG_STABLE_WRITES, disk->queue);
-	memset(bi, 0, sizeof(*bi));
-}
-EXPORT_SYMBOL(blk_integrity_unregister);
diff --git a/block/blk-lib.c b/block/blk-lib.c
index 442da9dad042..9f735efa6c94 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -103,38 +103,71 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 }
 EXPORT_SYMBOL(blkdev_issue_discard);
 
-static int __blkdev_issue_write_zeroes(struct block_device *bdev,
-		sector_t sector, sector_t nr_sects, gfp_t gfp_mask,
-		struct bio **biop, unsigned flags)
+static sector_t bio_write_zeroes_limit(struct block_device *bdev)
 {
-	struct bio *bio = *biop;
-	unsigned int max_sectors;
-
-	if (bdev_read_only(bdev))
-		return -EPERM;
-
-	/* Ensure that max_sectors doesn't overflow bi_size */
-	max_sectors = bdev_write_zeroes_sectors(bdev);
+	sector_t bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1;
 
-	if (max_sectors == 0)
-		return -EOPNOTSUPP;
+	return min(bdev_write_zeroes_sectors(bdev),
+		(UINT_MAX >> SECTOR_SHIFT) & ~bs_mask);
+}
 
+static void __blkdev_issue_write_zeroes(struct block_device *bdev,
+		sector_t sector, sector_t nr_sects, gfp_t gfp_mask,
+		struct bio **biop, unsigned flags)
+{
 	while (nr_sects) {
-		unsigned int len = min_t(sector_t, nr_sects, max_sectors);
+		unsigned int len = min_t(sector_t, nr_sects,
+				bio_write_zeroes_limit(bdev));
+		struct bio *bio;
+
+		if ((flags & BLKDEV_ZERO_KILLABLE) &&
+		    fatal_signal_pending(current))
+			break;
 
-		bio = blk_next_bio(bio, bdev, 0, REQ_OP_WRITE_ZEROES, gfp_mask);
+		bio = bio_alloc(bdev, 0, REQ_OP_WRITE_ZEROES, gfp_mask);
 		bio->bi_iter.bi_sector = sector;
 		if (flags & BLKDEV_ZERO_NOUNMAP)
 			bio->bi_opf |= REQ_NOUNMAP;
 
 		bio->bi_iter.bi_size = len << SECTOR_SHIFT;
+		*biop = bio_chain_and_submit(*biop, bio);
+
 		nr_sects -= len;
 		sector += len;
 		cond_resched();
 	}
+}
 
-	*biop = bio;
-	return 0;
+static int blkdev_issue_write_zeroes(struct block_device *bdev, sector_t sector,
+		sector_t nr_sects, gfp_t gfp, unsigned flags)
+{
+	struct bio *bio = NULL;
+	struct blk_plug plug;
+	int ret = 0;
+
+	blk_start_plug(&plug);
+	__blkdev_issue_write_zeroes(bdev, sector, nr_sects, gfp, &bio, flags);
+	if (bio) {
+		if ((flags & BLKDEV_ZERO_KILLABLE) &&
+		    fatal_signal_pending(current)) {
+			bio_await_chain(bio);
+			blk_finish_plug(&plug);
+			return -EINTR;
+		}
+		ret = submit_bio_wait(bio);
+		bio_put(bio);
+	}
+	blk_finish_plug(&plug);
+
+	/*
+	 * For some devices there is no non-destructive way to verify whether
+	 * WRITE ZEROES is actually supported.  These will clear the capability
+	 * on an I/O error, in which case we'll turn any error into
+	 * "not supported" here.
+	 */
+	if (ret && !bdev_write_zeroes_sectors(bdev))
+		return -EOPNOTSUPP;
+	return ret;
 }
 
 /*
@@ -150,35 +183,63 @@ static unsigned int __blkdev_sectors_to_bio_pages(sector_t nr_sects)
 	return min(pages, (sector_t)BIO_MAX_VECS);
 }
 
-static int __blkdev_issue_zero_pages(struct block_device *bdev,
+static void __blkdev_issue_zero_pages(struct block_device *bdev,
 		sector_t sector, sector_t nr_sects, gfp_t gfp_mask,
-		struct bio **biop)
+		struct bio **biop, unsigned int flags)
 {
-	struct bio *bio = *biop;
-	int bi_size = 0;
-	unsigned int sz;
-
-	if (bdev_read_only(bdev))
-		return -EPERM;
+	while (nr_sects) {
+		unsigned int nr_vecs = __blkdev_sectors_to_bio_pages(nr_sects);
+		struct bio *bio;
 
-	while (nr_sects != 0) {
-		bio = blk_next_bio(bio, bdev, __blkdev_sectors_to_bio_pages(nr_sects),
-				   REQ_OP_WRITE, gfp_mask);
+		bio = bio_alloc(bdev, nr_vecs, REQ_OP_WRITE, gfp_mask);
 		bio->bi_iter.bi_sector = sector;
 
-		while (nr_sects != 0) {
-			sz = min((sector_t) PAGE_SIZE, nr_sects << 9);
-			bi_size = bio_add_page(bio, ZERO_PAGE(0), sz, 0);
-			nr_sects -= bi_size >> 9;
-			sector += bi_size >> 9;
-			if (bi_size < sz)
+		if ((flags & BLKDEV_ZERO_KILLABLE) &&
+		    fatal_signal_pending(current))
+			break;
+
+		do {
+			unsigned int len, added;
+
+			len = min_t(sector_t,
+				PAGE_SIZE, nr_sects << SECTOR_SHIFT);
+			added = bio_add_page(bio, ZERO_PAGE(0), len, 0);
+			if (added < len)
 				break;
-		}
+			nr_sects -= added >> SECTOR_SHIFT;
+			sector += added >> SECTOR_SHIFT;
+		} while (nr_sects);
+
+		*biop = bio_chain_and_submit(*biop, bio);
 		cond_resched();
 	}
+}
 
-	*biop = bio;
-	return 0;
+static int blkdev_issue_zero_pages(struct block_device *bdev, sector_t sector,
+		sector_t nr_sects, gfp_t gfp, unsigned flags)
+{
+	struct bio *bio = NULL;
+	struct blk_plug plug;
+	int ret = 0;
+
+	if (flags & BLKDEV_ZERO_NOFALLBACK)
+		return -EOPNOTSUPP;
+
+	blk_start_plug(&plug);
+	__blkdev_issue_zero_pages(bdev, sector, nr_sects, gfp, &bio, flags);
+	if (bio) {
+		if ((flags & BLKDEV_ZERO_KILLABLE) &&
+		    fatal_signal_pending(current)) {
+			bio_await_chain(bio);
+			blk_finish_plug(&plug);
+			return -EINTR;
+		}
+		ret = submit_bio_wait(bio);
+		bio_put(bio);
+	}
+	blk_finish_plug(&plug);
+
+	return ret;
 }
 
 /**
@@ -204,20 +265,19 @@ int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp_mask, struct bio **biop,
 		unsigned flags)
 {
-	int ret;
-	sector_t bs_mask;
-
-	bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1;
-	if ((sector | nr_sects) & bs_mask)
-		return -EINVAL;
-
-	ret = __blkdev_issue_write_zeroes(bdev, sector, nr_sects, gfp_mask,
-			biop, flags);
-	if (ret != -EOPNOTSUPP || (flags & BLKDEV_ZERO_NOFALLBACK))
-		return ret;
+	if (bdev_read_only(bdev))
+		return -EPERM;
 
-	return __blkdev_issue_zero_pages(bdev, sector, nr_sects, gfp_mask,
-					 biop);
+	if (bdev_write_zeroes_sectors(bdev)) {
+		__blkdev_issue_write_zeroes(bdev, sector, nr_sects,
+				gfp_mask, biop, flags);
+	} else {
+		if (flags & BLKDEV_ZERO_NOFALLBACK)
+			return -EOPNOTSUPP;
+		__blkdev_issue_zero_pages(bdev, sector, nr_sects, gfp_mask,
+				biop, flags);
+	}
+	return 0;
 }
 EXPORT_SYMBOL(__blkdev_issue_zeroout);
 
@@ -237,51 +297,21 @@ EXPORT_SYMBOL(__blkdev_issue_zeroout);
 int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp_mask, unsigned flags)
 {
-	int ret = 0;
-	sector_t bs_mask;
-	struct bio *bio;
-	struct blk_plug plug;
-	bool try_write_zeroes = !!bdev_write_zeroes_sectors(bdev);
+	int ret;
 
-	bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1;
-	if ((sector | nr_sects) & bs_mask)
+	if ((sector | nr_sects) & ((bdev_logical_block_size(bdev) >> 9) - 1))
 		return -EINVAL;
+	if (bdev_read_only(bdev))
+		return -EPERM;
 
-retry:
-	bio = NULL;
-	blk_start_plug(&plug);
-	if (try_write_zeroes) {
-		ret = __blkdev_issue_write_zeroes(bdev, sector, nr_sects,
-						  gfp_mask, &bio, flags);
-	} else if (!(flags & BLKDEV_ZERO_NOFALLBACK)) {
-		ret = __blkdev_issue_zero_pages(bdev, sector, nr_sects,
-						gfp_mask, &bio);
-	} else {
-		/* No zeroing offload support */
-		ret = -EOPNOTSUPP;
-	}
-	if (ret == 0 && bio) {
-		ret = submit_bio_wait(bio);
-		bio_put(bio);
-	}
-	blk_finish_plug(&plug);
-	if (ret && try_write_zeroes) {
-		if (!(flags & BLKDEV_ZERO_NOFALLBACK)) {
-			try_write_zeroes = false;
-			goto retry;
-		}
-		if (!bdev_write_zeroes_sectors(bdev)) {
-			/*
-			 * Zeroing offload support was indicated, but the
-			 * device reported ILLEGAL REQUEST (for some devices
-			 * there is no non-destructive way to verify whether
-			 * WRITE ZEROES is actually supported).
-			 */
-			ret = -EOPNOTSUPP;
-		}
+	if (bdev_write_zeroes_sectors(bdev)) {
+		ret = blkdev_issue_write_zeroes(bdev, sector, nr_sects,
+				gfp_mask, flags);
+		if (ret != -EOPNOTSUPP)
+			return ret;
 	}
 
-	return ret;
+	return blkdev_issue_zero_pages(bdev, sector, nr_sects, gfp_mask, flags);
 }
 EXPORT_SYMBOL(blkdev_issue_zeroout);
 
diff --git a/block/blk-map.c b/block/blk-map.c
index 71210cdb3442..0e1167b23934 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -634,7 +634,7 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
 			const struct iov_iter *iter, gfp_t gfp_mask)
 {
 	bool copy = false, map_bvec = false;
-	unsigned long align = q->dma_pad_mask | queue_dma_alignment(q);
+	unsigned long align = blk_lim_dma_alignment_and_pad(&q->limits);
 	struct bio *bio = NULL;
 	struct iov_iter i;
 	int ret = -EINVAL;
@@ -757,6 +757,9 @@ int blk_rq_unmap_user(struct bio *bio)
 			bio_release_pages(bio, bio_data_dir(bio) == READ);
 		}
 
+		if (bio_integrity(bio))
+			bio_integrity_unmap_user(bio);
+
 		next_bio = bio;
 		bio = bio->bi_next;
 		blk_mq_map_bio_put(next_bio);
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 8534c35e0497..de5281bcadc5 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -154,6 +154,19 @@ static struct bio *bio_split_write_zeroes(struct bio *bio,
 	return bio_split(bio, lim->max_write_zeroes_sectors, GFP_NOIO, bs);
 }
 
+static inline unsigned int blk_boundary_sectors(const struct queue_limits *lim,
+						bool is_atomic)
+{
+	/*
+	 * chunk_sectors must be a multiple of atomic_write_boundary_sectors if
+	 * both non-zero.
+	 */
+	if (is_atomic && lim->atomic_write_boundary_sectors)
+		return lim->atomic_write_boundary_sectors;
+
+	return lim->chunk_sectors;
+}
+
 /*
  * Return the maximum number of sectors from the start of a bio that may be
  * submitted as a single request to a block device. If enough sectors remain,
@@ -167,12 +180,23 @@ static inline unsigned get_max_io_size(struct bio *bio,
 {
 	unsigned pbs = lim->physical_block_size >> SECTOR_SHIFT;
 	unsigned lbs = lim->logical_block_size >> SECTOR_SHIFT;
-	unsigned max_sectors = lim->max_sectors, start, end;
+	bool is_atomic = bio->bi_opf & REQ_ATOMIC;
+	unsigned boundary_sectors = blk_boundary_sectors(lim, is_atomic);
+	unsigned max_sectors, start, end;
 
-	if (lim->chunk_sectors) {
+	/*
+	 * We ignore lim->max_sectors for atomic writes because it may less
+	 * than the actual bio size, which we cannot tolerate.
+	 */
+	if (is_atomic)
+		max_sectors = lim->atomic_write_max_sectors;
+	else
+		max_sectors = lim->max_sectors;
+
+	if (boundary_sectors) {
 		max_sectors = min(max_sectors,
-			blk_chunk_sectors_left(bio->bi_iter.bi_sector,
-					       lim->chunk_sectors));
+			blk_boundary_sectors_left(bio->bi_iter.bi_sector,
+					      boundary_sectors));
 	}
 
 	start = bio->bi_iter.bi_sector & (pbs - 1);
@@ -185,23 +209,22 @@ static inline unsigned get_max_io_size(struct bio *bio,
 /**
  * get_max_segment_size() - maximum number of bytes to add as a single segment
  * @lim: Request queue limits.
- * @start_page: See below.
- * @offset: Offset from @start_page where to add a segment.
+ * @paddr: address of the range to add
+ * @len: maximum length available to add at @paddr
  *
- * Returns the maximum number of bytes that can be added as a single segment.
+ * Returns the maximum number of bytes of the range starting at @paddr that can
+ * be added to a single segment.
  */
 static inline unsigned get_max_segment_size(const struct queue_limits *lim,
-		struct page *start_page, unsigned long offset)
+		phys_addr_t paddr, unsigned int len)
 {
-	unsigned long mask = lim->seg_boundary_mask;
-
-	offset = mask & (page_to_phys(start_page) + offset);
-
 	/*
 	 * Prevent an overflow if mask = ULONG_MAX and offset = 0 by adding 1
 	 * after having calculated the minimum.
 	 */
-	return min(mask - offset, (unsigned long)lim->max_segment_size - 1) + 1;
+	return min_t(unsigned long, len,
+		min(lim->seg_boundary_mask - (lim->seg_boundary_mask & paddr),
+		    (unsigned long)lim->max_segment_size - 1) + 1);
 }
 
 /**
@@ -234,9 +257,7 @@ static bool bvec_split_segs(const struct queue_limits *lim,
 	unsigned seg_size = 0;
 
 	while (len && *nsegs < max_segs) {
-		seg_size = get_max_segment_size(lim, bv->bv_page,
-						bv->bv_offset + total_len);
-		seg_size = min(seg_size, len);
+		seg_size = get_max_segment_size(lim, bvec_phys(bv) + total_len, len);
 
 		(*nsegs)++;
 		total_len += seg_size;
@@ -305,6 +326,11 @@ struct bio *bio_split_rw(struct bio *bio, const struct queue_limits *lim,
 	*segs = nsegs;
 	return NULL;
 split:
+	if (bio->bi_opf & REQ_ATOMIC) {
+		bio->bi_status = BLK_STS_INVAL;
+		bio_endio(bio);
+		return ERR_PTR(-EINVAL);
+	}
 	/*
 	 * We can't sanely support splitting for a REQ_NOWAIT bio. End it
 	 * with EAGAIN if splitting is required and return an error pointer.
@@ -465,8 +491,8 @@ static unsigned blk_bvec_map_sg(struct request_queue *q,
 
 	while (nbytes > 0) {
 		unsigned offset = bvec->bv_offset + total;
-		unsigned len = min(get_max_segment_size(&q->limits,
-				   bvec->bv_page, offset), nbytes);
+		unsigned len = get_max_segment_size(&q->limits,
+				bvec_phys(bvec) + total, nbytes);
 		struct page *page = bvec->bv_page;
 
 		/*
@@ -588,18 +614,22 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq,
 						  sector_t offset)
 {
 	struct request_queue *q = rq->q;
-	unsigned int max_sectors;
+	struct queue_limits *lim = &q->limits;
+	unsigned int max_sectors, boundary_sectors;
+	bool is_atomic = rq->cmd_flags & REQ_ATOMIC;
 
 	if (blk_rq_is_passthrough(rq))
 		return q->limits.max_hw_sectors;
 
-	max_sectors = blk_queue_get_max_sectors(q, req_op(rq));
-	if (!q->limits.chunk_sectors ||
+	boundary_sectors = blk_boundary_sectors(lim, is_atomic);
+	max_sectors = blk_queue_get_max_sectors(rq);
+
+	if (!boundary_sectors ||
 	    req_op(rq) == REQ_OP_DISCARD ||
 	    req_op(rq) == REQ_OP_SECURE_ERASE)
 		return max_sectors;
 	return min(max_sectors,
-		   blk_chunk_sectors_left(offset, q->limits.chunk_sectors));
+		   blk_boundary_sectors_left(offset, boundary_sectors));
 }
 
 static inline int ll_new_hw_segment(struct request *req, struct bio *bio,
@@ -797,6 +827,18 @@ static enum elv_merge blk_try_req_merge(struct request *req,
 	return ELEVATOR_NO_MERGE;
 }
 
+static bool blk_atomic_write_mergeable_rq_bio(struct request *rq,
+					      struct bio *bio)
+{
+	return (rq->cmd_flags & REQ_ATOMIC) == (bio->bi_opf & REQ_ATOMIC);
+}
+
+static bool blk_atomic_write_mergeable_rqs(struct request *rq,
+					   struct request *next)
+{
+	return (rq->cmd_flags & REQ_ATOMIC) == (next->cmd_flags & REQ_ATOMIC);
+}
+
 /*
  * For non-mq, this has to be called with the request spinlock acquired.
  * For mq with scheduling, the appropriate queue wide lock should be held.
@@ -820,6 +862,9 @@ static struct request *attempt_merge(struct request_queue *q,
 	if (req->ioprio != next->ioprio)
 		return NULL;
 
+	if (!blk_atomic_write_mergeable_rqs(req, next))
+		return NULL;
+
 	/*
 	 * If we are allowed to merge, then append bio list
 	 * from next to rq and release next. merge_requests_fn
@@ -951,6 +996,9 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio)
 	if (rq->ioprio != bio_prio(bio))
 		return false;
 
+	if (blk_atomic_write_mergeable_rq_bio(rq, bio) == false)
+		return false;
+
 	return true;
 }
 
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 770c0c2b72fa..5463697a8442 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -5,6 +5,7 @@
 
 #include <linux/kernel.h>
 #include <linux/blkdev.h>
+#include <linux/build_bug.h>
 #include <linux/debugfs.h>
 
 #include "blk.h"
@@ -79,33 +80,19 @@ static int queue_pm_only_show(void *data, struct seq_file *m)
 
 #define QUEUE_FLAG_NAME(name) [QUEUE_FLAG_##name] = #name
 static const char *const blk_queue_flag_name[] = {
-	QUEUE_FLAG_NAME(STOPPED),
 	QUEUE_FLAG_NAME(DYING),
 	QUEUE_FLAG_NAME(NOMERGES),
 	QUEUE_FLAG_NAME(SAME_COMP),
 	QUEUE_FLAG_NAME(FAIL_IO),
-	QUEUE_FLAG_NAME(NONROT),
-	QUEUE_FLAG_NAME(IO_STAT),
 	QUEUE_FLAG_NAME(NOXMERGES),
-	QUEUE_FLAG_NAME(ADD_RANDOM),
-	QUEUE_FLAG_NAME(SYNCHRONOUS),
 	QUEUE_FLAG_NAME(SAME_FORCE),
 	QUEUE_FLAG_NAME(INIT_DONE),
-	QUEUE_FLAG_NAME(STABLE_WRITES),
-	QUEUE_FLAG_NAME(POLL),
-	QUEUE_FLAG_NAME(WC),
-	QUEUE_FLAG_NAME(FUA),
-	QUEUE_FLAG_NAME(DAX),
 	QUEUE_FLAG_NAME(STATS),
 	QUEUE_FLAG_NAME(REGISTERED),
 	QUEUE_FLAG_NAME(QUIESCED),
-	QUEUE_FLAG_NAME(PCI_P2PDMA),
-	QUEUE_FLAG_NAME(ZONE_RESETALL),
 	QUEUE_FLAG_NAME(RQ_ALLOC_TIME),
 	QUEUE_FLAG_NAME(HCTX_ACTIVE),
-	QUEUE_FLAG_NAME(NOWAIT),
 	QUEUE_FLAG_NAME(SQ_SCHED),
-	QUEUE_FLAG_NAME(SKIP_TAGSET_QUIESCE),
 };
 #undef QUEUE_FLAG_NAME
 
@@ -113,6 +100,7 @@ static int queue_state_show(void *data, struct seq_file *m)
 {
 	struct request_queue *q = data;
 
+	BUILD_BUG_ON(ARRAY_SIZE(blk_queue_flag_name) != QUEUE_FLAG_MAX);
 	blk_flags_show(m, q->queue_flags, blk_queue_flag_name,
 		       ARRAY_SIZE(blk_queue_flag_name));
 	seq_puts(m, "\n");
@@ -177,6 +165,7 @@ static int hctx_state_show(void *data, struct seq_file *m)
 {
 	struct blk_mq_hw_ctx *hctx = data;
 
+	BUILD_BUG_ON(ARRAY_SIZE(hctx_state_name) != BLK_MQ_S_MAX);
 	blk_flags_show(m, hctx->state, hctx_state_name,
 		       ARRAY_SIZE(hctx_state_name));
 	seq_puts(m, "\n");
@@ -194,10 +183,11 @@ static const char *const alloc_policy_name[] = {
 static const char *const hctx_flag_name[] = {
 	HCTX_FLAG_NAME(SHOULD_MERGE),
 	HCTX_FLAG_NAME(TAG_QUEUE_SHARED),
-	HCTX_FLAG_NAME(BLOCKING),
-	HCTX_FLAG_NAME(NO_SCHED),
 	HCTX_FLAG_NAME(STACKING),
 	HCTX_FLAG_NAME(TAG_HCTX_SHARED),
+	HCTX_FLAG_NAME(BLOCKING),
+	HCTX_FLAG_NAME(NO_SCHED),
+	HCTX_FLAG_NAME(NO_SCHED_BY_DEFAULT),
 };
 #undef HCTX_FLAG_NAME
 
@@ -206,6 +196,10 @@ static int hctx_flags_show(void *data, struct seq_file *m)
 	struct blk_mq_hw_ctx *hctx = data;
 	const int alloc_policy = BLK_MQ_FLAG_TO_ALLOC_POLICY(hctx->flags);
 
+	BUILD_BUG_ON(ARRAY_SIZE(hctx_flag_name) !=
+			BLK_MQ_F_ALLOC_POLICY_START_BIT);
+	BUILD_BUG_ON(ARRAY_SIZE(alloc_policy_name) != BLK_TAG_ALLOC_MAX);
+
 	seq_puts(m, "alloc_policy=");
 	if (alloc_policy < ARRAY_SIZE(alloc_policy_name) &&
 	    alloc_policy_name[alloc_policy])
@@ -236,12 +230,17 @@ static const char *const cmd_flag_name[] = {
 	CMD_FLAG_NAME(RAHEAD),
 	CMD_FLAG_NAME(BACKGROUND),
 	CMD_FLAG_NAME(NOWAIT),
-	CMD_FLAG_NAME(NOUNMAP),
 	CMD_FLAG_NAME(POLLED),
+	CMD_FLAG_NAME(ALLOC_CACHE),
+	CMD_FLAG_NAME(SWAP),
+	CMD_FLAG_NAME(DRV),
+	CMD_FLAG_NAME(FS_PRIVATE),
+	CMD_FLAG_NAME(ATOMIC),
+	CMD_FLAG_NAME(NOUNMAP),
 };
 #undef CMD_FLAG_NAME
 
-#define RQF_NAME(name) [ilog2((__force u32)RQF_##name)] = #name
+#define RQF_NAME(name) [__RQF_##name] = #name
 static const char *const rqf_name[] = {
 	RQF_NAME(STARTED),
 	RQF_NAME(FLUSH_SEQ),
@@ -256,6 +255,7 @@ static const char *const rqf_name[] = {
 	RQF_NAME(HASHED),
 	RQF_NAME(STATS),
 	RQF_NAME(SPECIAL_PAYLOAD),
+	RQF_NAME(ZONE_WRITE_PLUGGING),
 	RQF_NAME(TIMED_OUT),
 	RQF_NAME(RESV),
 };
@@ -281,6 +281,9 @@ int __blk_mq_debugfs_rq_show(struct seq_file *m, struct request *rq)
 	const enum req_op op = req_op(rq);
 	const char *op_str = blk_op_str(op);
 
+	BUILD_BUG_ON(ARRAY_SIZE(cmd_flag_name) != __REQ_NR_BITS);
+	BUILD_BUG_ON(ARRAY_SIZE(rqf_name) != __RQF_BITS);
+
 	seq_printf(m, "%p {.op=", rq);
 	if (strcmp(op_str, "UNKNOWN") == 0)
 		seq_printf(m, "%u", op);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 3b4df8e5ac9e..e3c3c0c21b55 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -448,6 +448,10 @@ static struct request *__blk_mq_alloc_requests(struct blk_mq_alloc_data *data)
 	if (data->cmd_flags & REQ_NOWAIT)
 		data->flags |= BLK_MQ_REQ_NOWAIT;
 
+retry:
+	data->ctx = blk_mq_get_ctx(q);
+	data->hctx = blk_mq_map_queue(q, data->cmd_flags, data->ctx);
+
 	if (q->elevator) {
 		/*
 		 * All requests use scheduler tags when an I/O scheduler is
@@ -469,13 +473,9 @@ static struct request *__blk_mq_alloc_requests(struct blk_mq_alloc_data *data)
 			if (ops->limit_depth)
 				ops->limit_depth(data->cmd_flags, data);
 		}
-	}
-
-retry:
-	data->ctx = blk_mq_get_ctx(q);
-	data->hctx = blk_mq_map_queue(q, data->cmd_flags, data->ctx);
-	if (!(data->rq_flags & RQF_SCHED_TAGS))
+	} else {
 		blk_mq_tag_busy(data->hctx);
+	}
 
 	if (data->flags & BLK_MQ_REQ_RESERVED)
 		data->rq_flags |= RQF_RESV;
@@ -804,10 +804,8 @@ static void blk_complete_request(struct request *req)
 	if (!bio)
 		return;
 
-#ifdef CONFIG_BLK_DEV_INTEGRITY
 	if (blk_integrity_rq(req) && req_op(req) == REQ_OP_READ)
-		req->q->integrity.profile->complete_fn(req, total_bytes);
-#endif
+		blk_integrity_complete(req, total_bytes);
 
 	/*
 	 * Upper layers may call blk_crypto_evict_key() anytime after the last
@@ -875,11 +873,9 @@ bool blk_update_request(struct request *req, blk_status_t error,
 	if (!req->bio)
 		return false;
 
-#ifdef CONFIG_BLK_DEV_INTEGRITY
 	if (blk_integrity_rq(req) && req_op(req) == REQ_OP_READ &&
 	    error == BLK_STS_OK)
-		req->q->integrity.profile->complete_fn(req, nr_bytes);
-#endif
+		blk_integrity_complete(req, nr_bytes);
 
 	/*
 	 * Upper layers may call blk_crypto_evict_key() anytime after the last
@@ -1264,10 +1260,9 @@ void blk_mq_start_request(struct request *rq)
 	WRITE_ONCE(rq->state, MQ_RQ_IN_FLIGHT);
 	rq->mq_hctx->tags->rqs[rq->tag] = rq;
 
-#ifdef CONFIG_BLK_DEV_INTEGRITY
 	if (blk_integrity_rq(rq) && req_op(rq) == REQ_OP_WRITE)
-		q->integrity.profile->prepare_fn(rq);
-#endif
+		blk_integrity_prepare(rq);
+
 	if (rq->bio && rq->bio->bi_opf & REQ_POLLED)
 	        WRITE_ONCE(rq->bio->bi_cookie, rq->mq_hctx->queue_num);
 }
@@ -2914,6 +2909,17 @@ static void blk_mq_use_cached_rq(struct request *rq, struct blk_plug *plug,
 	INIT_LIST_HEAD(&rq->queuelist);
 }
 
+static bool bio_unaligned(const struct bio *bio, struct request_queue *q)
+{
+	unsigned int bs_mask = queue_logical_block_size(q) - 1;
+
+	/* .bi_sector of any zero sized bio need to be initialized */
+	if ((bio->bi_iter.bi_size & bs_mask) ||
+	    ((bio->bi_iter.bi_sector << SECTOR_SHIFT) & bs_mask))
+		return true;
+	return false;
+}
+
 /**
  * blk_mq_submit_bio - Create and send a request to block device.
  * @bio: Bio pointer.
@@ -2966,6 +2972,15 @@ void blk_mq_submit_bio(struct bio *bio)
 			return;
 	}
 
+	/*
+	 * Device reconfiguration may change logical block size, so alignment
+	 * check has to be done with queue usage counter held
+	 */
+	if (unlikely(bio_unaligned(bio, q))) {
+		bio_io_error(bio);
+		goto queue_exit;
+	}
+
 	if (unlikely(bio_may_exceed_limits(bio, &q->limits))) {
 		bio = __bio_split_to_limits(bio, &q->limits, &nr_segs);
 		if (!bio)
@@ -3041,7 +3056,7 @@ queue_exit:
 blk_status_t blk_insert_cloned_request(struct request *rq)
 {
 	struct request_queue *q = rq->q;
-	unsigned int max_sectors = blk_queue_get_max_sectors(q, req_op(rq));
+	unsigned int max_sectors = blk_queue_get_max_sectors(rq);
 	unsigned int max_segments = blk_rq_get_max_segments(rq);
 	blk_status_t ret;
 
@@ -4114,6 +4129,12 @@ void blk_mq_release(struct request_queue *q)
 	blk_mq_sysfs_deinit(q);
 }
 
+static bool blk_mq_can_poll(struct blk_mq_tag_set *set)
+{
+	return set->nr_maps > HCTX_TYPE_POLL &&
+		set->map[HCTX_TYPE_POLL].nr_queues;
+}
+
 struct request_queue *blk_mq_alloc_queue(struct blk_mq_tag_set *set,
 		struct queue_limits *lim, void *queuedata)
 {
@@ -4121,7 +4142,13 @@ struct request_queue *blk_mq_alloc_queue(struct blk_mq_tag_set *set,
 	struct request_queue *q;
 	int ret;
 
-	q = blk_alloc_queue(lim ? lim : &default_lim, set->numa_node);
+	if (!lim)
+		lim = &default_lim;
+	lim->features |= BLK_FEAT_IO_STAT | BLK_FEAT_NOWAIT;
+	if (blk_mq_can_poll(set))
+		lim->features |= BLK_FEAT_POLL;
+
+	q = blk_alloc_queue(lim, set->numa_node);
 	if (IS_ERR(q))
 		return q;
 	q->queuedata = queuedata;
@@ -4274,17 +4301,6 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set,
 	mutex_unlock(&q->sysfs_lock);
 }
 
-static void blk_mq_update_poll_flag(struct request_queue *q)
-{
-	struct blk_mq_tag_set *set = q->tag_set;
-
-	if (set->nr_maps > HCTX_TYPE_POLL &&
-	    set->map[HCTX_TYPE_POLL].nr_queues)
-		blk_queue_flag_set(QUEUE_FLAG_POLL, q);
-	else
-		blk_queue_flag_clear(QUEUE_FLAG_POLL, q);
-}
-
 int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 		struct request_queue *q)
 {
@@ -4312,7 +4328,6 @@ int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 	q->tag_set = set;
 
 	q->queue_flags |= QUEUE_FLAG_MQ_DEFAULT;
-	blk_mq_update_poll_flag(q);
 
 	INIT_DELAYED_WORK(&q->requeue_work, blk_mq_requeue_work);
 	INIT_LIST_HEAD(&q->flush_list);
@@ -4636,13 +4651,15 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr)
 	int ret;
 	unsigned long i;
 
+	if (WARN_ON_ONCE(!q->mq_freeze_depth))
+		return -EINVAL;
+
 	if (!set)
 		return -EINVAL;
 
 	if (q->nr_requests == nr)
 		return 0;
 
-	blk_mq_freeze_queue(q);
 	blk_mq_quiesce_queue(q);
 
 	ret = 0;
@@ -4676,7 +4693,6 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr)
 	}
 
 	blk_mq_unquiesce_queue(q);
-	blk_mq_unfreeze_queue(q);
 
 	return ret;
 }
@@ -4798,8 +4814,10 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set,
 fallback:
 	blk_mq_update_queue_map(set);
 	list_for_each_entry(q, &set->tag_list, tag_set_list) {
+		struct queue_limits lim;
+
 		blk_mq_realloc_hw_ctxs(set, q);
-		blk_mq_update_poll_flag(q);
+
 		if (q->nr_hw_queues != set->nr_hw_queues) {
 			int i = prev_nr_hw_queues;
 
@@ -4811,6 +4829,13 @@ fallback:
 			set->nr_hw_queues = prev_nr_hw_queues;
 			goto fallback;
 		}
+		lim = queue_limits_start_update(q);
+		if (blk_mq_can_poll(set))
+			lim.features |= BLK_FEAT_POLL;
+		else
+			lim.features &= ~BLK_FEAT_POLL;
+		if (queue_limits_commit_update(q, &lim) < 0)
+			pr_warn("updating the poll flag failed\n");
 		blk_mq_map_swqueue(q);
 	}
 
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 260beea8e332..3bd43b10032f 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -36,6 +36,8 @@ enum {
 	BLK_MQ_TAG_MAX		= BLK_MQ_NO_TAG - 1,
 };
 
+#define BLK_MQ_CPU_WORK_BATCH	(8)
+
 typedef unsigned int __bitwise blk_insert_t;
 #define BLK_MQ_INSERT_AT_HEAD		((__force blk_insert_t)0x01)
 
diff --git a/block/blk-settings.c b/block/blk-settings.c
index effeb9a639bb..cd8a8eabc9a5 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -6,7 +6,7 @@
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/bio.h>
-#include <linux/blkdev.h>
+#include <linux/blk-integrity.h>
 #include <linux/pagemap.h>
 #include <linux/backing-dev-defs.h>
 #include <linux/gcd.h>
@@ -55,7 +55,7 @@ void blk_set_stacking_limits(struct queue_limits *lim)
 }
 EXPORT_SYMBOL(blk_set_stacking_limits);
 
-static void blk_apply_bdi_limits(struct backing_dev_info *bdi,
+void blk_apply_bdi_limits(struct backing_dev_info *bdi,
 		struct queue_limits *lim)
 {
 	/*
@@ -68,7 +68,7 @@ static void blk_apply_bdi_limits(struct backing_dev_info *bdi,
 
 static int blk_validate_zoned_limits(struct queue_limits *lim)
 {
-	if (!lim->zoned) {
+	if (!(lim->features & BLK_FEAT_ZONED)) {
 		if (WARN_ON_ONCE(lim->max_open_zones) ||
 		    WARN_ON_ONCE(lim->max_active_zones) ||
 		    WARN_ON_ONCE(lim->zone_write_granularity) ||
@@ -80,6 +80,14 @@ static int blk_validate_zoned_limits(struct queue_limits *lim)
 	if (WARN_ON_ONCE(!IS_ENABLED(CONFIG_BLK_DEV_ZONED)))
 		return -EINVAL;
 
+	/*
+	 * Given that active zones include open zones, the maximum number of
+	 * open zones cannot be larger than the maximum number of active zones.
+	 */
+	if (lim->max_active_zones &&
+	    lim->max_open_zones > lim->max_active_zones)
+		return -EINVAL;
+
 	if (lim->zone_write_granularity < lim->logical_block_size)
 		lim->zone_write_granularity = lim->logical_block_size;
 
@@ -97,6 +105,120 @@ static int blk_validate_zoned_limits(struct queue_limits *lim)
 	return 0;
 }
 
+static int blk_validate_integrity_limits(struct queue_limits *lim)
+{
+	struct blk_integrity *bi = &lim->integrity;
+
+	if (!bi->tuple_size) {
+		if (bi->csum_type != BLK_INTEGRITY_CSUM_NONE ||
+		    bi->tag_size || ((bi->flags & BLK_INTEGRITY_REF_TAG))) {
+			pr_warn("invalid PI settings.\n");
+			return -EINVAL;
+		}
+		return 0;
+	}
+
+	if (!IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY)) {
+		pr_warn("integrity support disabled.\n");
+		return -EINVAL;
+	}
+
+	if (bi->csum_type == BLK_INTEGRITY_CSUM_NONE &&
+	    (bi->flags & BLK_INTEGRITY_REF_TAG)) {
+		pr_warn("ref tag not support without checksum.\n");
+		return -EINVAL;
+	}
+
+	if (!bi->interval_exp)
+		bi->interval_exp = ilog2(lim->logical_block_size);
+
+	return 0;
+}
+
+/*
+ * Returns max guaranteed bytes which we can fit in a bio.
+ *
+ * We request that an atomic_write is ITER_UBUF iov_iter (so a single vector),
+ * so we assume that we can fit in at least PAGE_SIZE in a segment, apart from
+ * the first and last segments.
+ */
+static unsigned int blk_queue_max_guaranteed_bio(struct queue_limits *lim)
+{
+	unsigned int max_segments = min(BIO_MAX_VECS, lim->max_segments);
+	unsigned int length;
+
+	length = min(max_segments, 2) * lim->logical_block_size;
+	if (max_segments > 2)
+		length += (max_segments - 2) * PAGE_SIZE;
+
+	return length;
+}
+
+static void blk_atomic_writes_update_limits(struct queue_limits *lim)
+{
+	unsigned int unit_limit = min(lim->max_hw_sectors << SECTOR_SHIFT,
+					blk_queue_max_guaranteed_bio(lim));
+
+	unit_limit = rounddown_pow_of_two(unit_limit);
+
+	lim->atomic_write_max_sectors =
+		min(lim->atomic_write_hw_max >> SECTOR_SHIFT,
+			lim->max_hw_sectors);
+	lim->atomic_write_unit_min =
+		min(lim->atomic_write_hw_unit_min, unit_limit);
+	lim->atomic_write_unit_max =
+		min(lim->atomic_write_hw_unit_max, unit_limit);
+	lim->atomic_write_boundary_sectors =
+		lim->atomic_write_hw_boundary >> SECTOR_SHIFT;
+}
+
+static void blk_validate_atomic_write_limits(struct queue_limits *lim)
+{
+	unsigned int boundary_sectors;
+
+	if (!lim->atomic_write_hw_max)
+		goto unsupported;
+
+	boundary_sectors = lim->atomic_write_hw_boundary >> SECTOR_SHIFT;
+
+	if (boundary_sectors) {
+		/*
+		 * A feature of boundary support is that it disallows bios to
+		 * be merged which would result in a merged request which
+		 * crosses either a chunk sector or atomic write HW boundary,
+		 * even though chunk sectors may be just set for performance.
+		 * For simplicity, disallow atomic writes for a chunk sector
+		 * which is non-zero and smaller than atomic write HW boundary.
+		 * Furthermore, chunk sectors must be a multiple of atomic
+		 * write HW boundary. Otherwise boundary support becomes
+		 * complicated.
+		 * Devices which do not conform to these rules can be dealt
+		 * with if and when they show up.
+		 */
+		if (WARN_ON_ONCE(lim->chunk_sectors % boundary_sectors))
+			goto unsupported;
+
+		/*
+		 * The boundary size just needs to be a multiple of unit_max
+		 * (and not necessarily a power-of-2), so this following check
+		 * could be relaxed in future.
+		 * Furthermore, if needed, unit_max could even be reduced so
+		 * that it is compliant with a !power-of-2 boundary.
+		 */
+		if (!is_power_of_2(boundary_sectors))
+			goto unsupported;
+	}
+
+	blk_atomic_writes_update_limits(lim);
+	return;
+
+unsupported:
+	lim->atomic_write_max_sectors = 0;
+	lim->atomic_write_boundary_sectors = 0;
+	lim->atomic_write_unit_min = 0;
+	lim->atomic_write_unit_max = 0;
+}
+
 /*
  * Check that the limits in lim are valid, initialize defaults for unset
  * values, and cap values based on others where needed.
@@ -105,6 +227,7 @@ static int blk_validate_limits(struct queue_limits *lim)
 {
 	unsigned int max_hw_sectors;
 	unsigned int logical_block_sectors;
+	int err;
 
 	/*
 	 * Unless otherwise specified, default to 512 byte logical blocks and a
@@ -112,6 +235,10 @@ static int blk_validate_limits(struct queue_limits *lim)
 	 */
 	if (!lim->logical_block_size)
 		lim->logical_block_size = SECTOR_SIZE;
+	else if (blk_validate_block_size(lim->logical_block_size)) {
+		pr_warn("Invalid logical block size (%d)\n", lim->logical_block_size);
+		return -EINVAL;
+	}
 	if (lim->physical_block_size < lim->logical_block_size)
 		lim->physical_block_size = lim->logical_block_size;
 
@@ -153,6 +280,12 @@ static int blk_validate_limits(struct queue_limits *lim)
 		if (lim->max_user_sectors < PAGE_SIZE / SECTOR_SIZE)
 			return -EINVAL;
 		lim->max_sectors = min(max_hw_sectors, lim->max_user_sectors);
+	} else if (lim->io_opt > (BLK_DEF_MAX_SECTORS_CAP << SECTOR_SHIFT)) {
+		lim->max_sectors =
+			min(max_hw_sectors, lim->io_opt >> SECTOR_SHIFT);
+	} else if (lim->io_min > (BLK_DEF_MAX_SECTORS_CAP << SECTOR_SHIFT)) {
+		lim->max_sectors =
+			min(max_hw_sectors, lim->io_min >> SECTOR_SHIFT);
 	} else {
 		lim->max_sectors = min(max_hw_sectors, BLK_DEF_MAX_SECTORS_CAP);
 	}
@@ -220,9 +353,17 @@ static int blk_validate_limits(struct queue_limits *lim)
 
 	if (lim->alignment_offset) {
 		lim->alignment_offset &= (lim->physical_block_size - 1);
-		lim->misaligned = 0;
+		lim->flags &= ~BLK_FLAG_MISALIGNED;
 	}
 
+	if (!(lim->features & BLK_FEAT_WRITE_CACHE))
+		lim->features &= ~BLK_FEAT_FUA;
+
+	blk_validate_atomic_write_limits(lim);
+
+	err = blk_validate_integrity_limits(lim);
+	if (err)
+		return err;
 	return blk_validate_zoned_limits(lim);
 }
 
@@ -254,15 +395,25 @@ int blk_set_default_limits(struct queue_limits *lim)
  */
 int queue_limits_commit_update(struct request_queue *q,
 		struct queue_limits *lim)
-	__releases(q->limits_lock)
 {
-	int error = blk_validate_limits(lim);
+	int error;
 
-	if (!error) {
-		q->limits = *lim;
-		if (q->disk)
-			blk_apply_bdi_limits(q->disk->bdi, lim);
+	error = blk_validate_limits(lim);
+	if (error)
+		goto out_unlock;
+
+#ifdef CONFIG_BLK_INLINE_ENCRYPTION
+	if (q->crypto_profile && lim->integrity.tag_size) {
+		pr_warn("blk-integrity: Integrity and hardware inline encryption are not supported together.\n");
+		error = -EINVAL;
+		goto out_unlock;
 	}
+#endif
+
+	q->limits = *lim;
+	if (q->disk)
+		blk_apply_bdi_limits(q->disk->bdi, lim);
+out_unlock:
 	mutex_unlock(&q->limits_lock);
 	return error;
 }
@@ -287,204 +438,6 @@ int queue_limits_set(struct request_queue *q, struct queue_limits *lim)
 EXPORT_SYMBOL_GPL(queue_limits_set);
 
 /**
- * blk_queue_chunk_sectors - set size of the chunk for this queue
- * @q:  the request queue for the device
- * @chunk_sectors:  chunk sectors in the usual 512b unit
- *
- * Description:
- *    If a driver doesn't want IOs to cross a given chunk size, it can set
- *    this limit and prevent merging across chunks. Note that the block layer
- *    must accept a page worth of data at any offset. So if the crossing of
- *    chunks is a hard limitation in the driver, it must still be prepared
- *    to split single page bios.
- **/
-void blk_queue_chunk_sectors(struct request_queue *q, unsigned int chunk_sectors)
-{
-	q->limits.chunk_sectors = chunk_sectors;
-}
-EXPORT_SYMBOL(blk_queue_chunk_sectors);
-
-/**
- * blk_queue_max_discard_sectors - set max sectors for a single discard
- * @q:  the request queue for the device
- * @max_discard_sectors: maximum number of sectors to discard
- **/
-void blk_queue_max_discard_sectors(struct request_queue *q,
-		unsigned int max_discard_sectors)
-{
-	struct queue_limits *lim = &q->limits;
-
-	lim->max_hw_discard_sectors = max_discard_sectors;
-	lim->max_discard_sectors =
-		min(max_discard_sectors, lim->max_user_discard_sectors);
-}
-EXPORT_SYMBOL(blk_queue_max_discard_sectors);
-
-/**
- * blk_queue_max_secure_erase_sectors - set max sectors for a secure erase
- * @q:  the request queue for the device
- * @max_sectors: maximum number of sectors to secure_erase
- **/
-void blk_queue_max_secure_erase_sectors(struct request_queue *q,
-		unsigned int max_sectors)
-{
-	q->limits.max_secure_erase_sectors = max_sectors;
-}
-EXPORT_SYMBOL(blk_queue_max_secure_erase_sectors);
-
-/**
- * blk_queue_max_write_zeroes_sectors - set max sectors for a single
- *                                      write zeroes
- * @q:  the request queue for the device
- * @max_write_zeroes_sectors: maximum number of sectors to write per command
- **/
-void blk_queue_max_write_zeroes_sectors(struct request_queue *q,
-		unsigned int max_write_zeroes_sectors)
-{
-	q->limits.max_write_zeroes_sectors = max_write_zeroes_sectors;
-}
-EXPORT_SYMBOL(blk_queue_max_write_zeroes_sectors);
-
-/**
- * blk_queue_max_zone_append_sectors - set max sectors for a single zone append
- * @q:  the request queue for the device
- * @max_zone_append_sectors: maximum number of sectors to write per command
- *
- * Sets the maximum number of sectors allowed for zone append commands. If
- * Specifying 0 for @max_zone_append_sectors indicates that the queue does
- * not natively support zone append operations and that the block layer must
- * emulate these operations using regular writes.
- **/
-void blk_queue_max_zone_append_sectors(struct request_queue *q,
-		unsigned int max_zone_append_sectors)
-{
-	unsigned int max_sectors = 0;
-
-	if (WARN_ON(!blk_queue_is_zoned(q)))
-		return;
-
-	if (max_zone_append_sectors) {
-		max_sectors = min(q->limits.max_hw_sectors,
-				  max_zone_append_sectors);
-		max_sectors = min(q->limits.chunk_sectors, max_sectors);
-
-		/*
-		 * Signal eventual driver bugs resulting in the max_zone_append
-		 * sectors limit being 0 due to the chunk_sectors limit (zone
-		 * size) not set or the max_hw_sectors limit not set.
-		 */
-		WARN_ON_ONCE(!max_sectors);
-	}
-
-	q->limits.max_zone_append_sectors = max_sectors;
-}
-EXPORT_SYMBOL_GPL(blk_queue_max_zone_append_sectors);
-
-/**
- * blk_queue_logical_block_size - set logical block size for the queue
- * @q:  the request queue for the device
- * @size:  the logical block size, in bytes
- *
- * Description:
- *   This should be set to the lowest possible block size that the
- *   storage device can address.  The default of 512 covers most
- *   hardware.
- **/
-void blk_queue_logical_block_size(struct request_queue *q, unsigned int size)
-{
-	struct queue_limits *limits = &q->limits;
-
-	limits->logical_block_size = size;
-
-	if (limits->discard_granularity < limits->logical_block_size)
-		limits->discard_granularity = limits->logical_block_size;
-
-	if (limits->physical_block_size < size)
-		limits->physical_block_size = size;
-
-	if (limits->io_min < limits->physical_block_size)
-		limits->io_min = limits->physical_block_size;
-
-	limits->max_hw_sectors =
-		round_down(limits->max_hw_sectors, size >> SECTOR_SHIFT);
-	limits->max_sectors =
-		round_down(limits->max_sectors, size >> SECTOR_SHIFT);
-}
-EXPORT_SYMBOL(blk_queue_logical_block_size);
-
-/**
- * blk_queue_physical_block_size - set physical block size for the queue
- * @q:  the request queue for the device
- * @size:  the physical block size, in bytes
- *
- * Description:
- *   This should be set to the lowest possible sector size that the
- *   hardware can operate on without reverting to read-modify-write
- *   operations.
- */
-void blk_queue_physical_block_size(struct request_queue *q, unsigned int size)
-{
-	q->limits.physical_block_size = size;
-
-	if (q->limits.physical_block_size < q->limits.logical_block_size)
-		q->limits.physical_block_size = q->limits.logical_block_size;
-
-	if (q->limits.discard_granularity < q->limits.physical_block_size)
-		q->limits.discard_granularity = q->limits.physical_block_size;
-
-	if (q->limits.io_min < q->limits.physical_block_size)
-		q->limits.io_min = q->limits.physical_block_size;
-}
-EXPORT_SYMBOL(blk_queue_physical_block_size);
-
-/**
- * blk_queue_zone_write_granularity - set zone write granularity for the queue
- * @q:  the request queue for the zoned device
- * @size:  the zone write granularity size, in bytes
- *
- * Description:
- *   This should be set to the lowest possible size allowing to write in
- *   sequential zones of a zoned block device.
- */
-void blk_queue_zone_write_granularity(struct request_queue *q,
-				      unsigned int size)
-{
-	if (WARN_ON_ONCE(!blk_queue_is_zoned(q)))
-		return;
-
-	q->limits.zone_write_granularity = size;
-
-	if (q->limits.zone_write_granularity < q->limits.logical_block_size)
-		q->limits.zone_write_granularity = q->limits.logical_block_size;
-}
-EXPORT_SYMBOL_GPL(blk_queue_zone_write_granularity);
-
-/**
- * blk_queue_alignment_offset - set physical block alignment offset
- * @q:	the request queue for the device
- * @offset: alignment offset in bytes
- *
- * Description:
- *   Some devices are naturally misaligned to compensate for things like
- *   the legacy DOS partition table 63-sector offset.  Low-level drivers
- *   should call this function for devices whose first sector is not
- *   naturally aligned.
- */
-void blk_queue_alignment_offset(struct request_queue *q, unsigned int offset)
-{
-	q->limits.alignment_offset =
-		offset & (q->limits.physical_block_size - 1);
-	q->limits.misaligned = 0;
-}
-EXPORT_SYMBOL(blk_queue_alignment_offset);
-
-void disk_update_readahead(struct gendisk *disk)
-{
-	blk_apply_bdi_limits(disk->bdi, &disk->queue->limits);
-}
-EXPORT_SYMBOL_GPL(disk_update_readahead);
-
-/**
  * blk_limits_io_min - set minimum request size for a device
  * @limits: the queue limits
  * @min:  smallest I/O size in bytes
@@ -508,26 +461,6 @@ void blk_limits_io_min(struct queue_limits *limits, unsigned int min)
 EXPORT_SYMBOL(blk_limits_io_min);
 
 /**
- * blk_queue_io_min - set minimum request size for the queue
- * @q:	the request queue for the device
- * @min:  smallest I/O size in bytes
- *
- * Description:
- *   Storage devices may report a granularity or preferred minimum I/O
- *   size which is the smallest request the device can perform without
- *   incurring a performance penalty.  For disk drives this is often the
- *   physical block size.  For RAID arrays it is often the stripe chunk
- *   size.  A properly aligned multiple of minimum_io_size is the
- *   preferred request size for workloads where a high number of I/O
- *   operations is desired.
- */
-void blk_queue_io_min(struct request_queue *q, unsigned int min)
-{
-	blk_limits_io_min(&q->limits, min);
-}
-EXPORT_SYMBOL(blk_queue_io_min);
-
-/**
  * blk_limits_io_opt - set optimal request size for a device
  * @limits: the queue limits
  * @opt:  smallest I/O size in bytes
@@ -614,6 +547,21 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 {
 	unsigned int top, bottom, alignment, ret = 0;
 
+	t->features |= (b->features & BLK_FEAT_INHERIT_MASK);
+
+	/*
+	 * BLK_FEAT_NOWAIT and BLK_FEAT_POLL need to be supported both by the
+	 * stacking driver and all underlying devices.  The stacking driver sets
+	 * the flags before stacking the limits, and this will clear the flags
+	 * if any of the underlying devices does not support it.
+	 */
+	if (!(b->features & BLK_FEAT_NOWAIT))
+		t->features &= ~BLK_FEAT_NOWAIT;
+	if (!(b->features & BLK_FEAT_POLL))
+		t->features &= ~BLK_FEAT_POLL;
+
+	t->flags |= (b->flags & BLK_FLAG_MISALIGNED);
+
 	t->max_sectors = min_not_zero(t->max_sectors, b->max_sectors);
 	t->max_user_sectors = min_not_zero(t->max_user_sectors,
 			b->max_user_sectors);
@@ -623,7 +571,6 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 					b->max_write_zeroes_sectors);
 	t->max_zone_append_sectors = min(queue_limits_max_zone_append_sectors(t),
 					 queue_limits_max_zone_append_sectors(b));
-	t->bounce = max(t->bounce, b->bounce);
 
 	t->seg_boundary_mask = min_not_zero(t->seg_boundary_mask,
 					    b->seg_boundary_mask);
@@ -639,8 +586,6 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 	t->max_segment_size = min_not_zero(t->max_segment_size,
 					   b->max_segment_size);
 
-	t->misaligned |= b->misaligned;
-
 	alignment = queue_limit_alignment_offset(b, start);
 
 	/* Bottom device has different alignment.  Check that it is
@@ -654,7 +599,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 
 		/* Verify that top and bottom intervals line up */
 		if (max(top, bottom) % min(top, bottom)) {
-			t->misaligned = 1;
+			t->flags |= BLK_FLAG_MISALIGNED;
 			ret = -1;
 		}
 	}
@@ -676,42 +621,38 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 	/* Physical block size a multiple of the logical block size? */
 	if (t->physical_block_size & (t->logical_block_size - 1)) {
 		t->physical_block_size = t->logical_block_size;
-		t->misaligned = 1;
+		t->flags |= BLK_FLAG_MISALIGNED;
 		ret = -1;
 	}
 
 	/* Minimum I/O a multiple of the physical block size? */
 	if (t->io_min & (t->physical_block_size - 1)) {
 		t->io_min = t->physical_block_size;
-		t->misaligned = 1;
+		t->flags |= BLK_FLAG_MISALIGNED;
 		ret = -1;
 	}
 
 	/* Optimal I/O a multiple of the physical block size? */
 	if (t->io_opt & (t->physical_block_size - 1)) {
 		t->io_opt = 0;
-		t->misaligned = 1;
+		t->flags |= BLK_FLAG_MISALIGNED;
 		ret = -1;
 	}
 
 	/* chunk_sectors a multiple of the physical block size? */
 	if ((t->chunk_sectors << 9) & (t->physical_block_size - 1)) {
 		t->chunk_sectors = 0;
-		t->misaligned = 1;
+		t->flags |= BLK_FLAG_MISALIGNED;
 		ret = -1;
 	}
 
-	t->raid_partial_stripes_expensive =
-		max(t->raid_partial_stripes_expensive,
-		    b->raid_partial_stripes_expensive);
-
 	/* Find lowest common alignment_offset */
 	t->alignment_offset = lcm_not_zero(t->alignment_offset, alignment)
 		% max(t->physical_block_size, t->io_min);
 
 	/* Verify that new alignment_offset is on a logical block boundary */
 	if (t->alignment_offset & (t->logical_block_size - 1)) {
-		t->misaligned = 1;
+		t->flags |= BLK_FLAG_MISALIGNED;
 		ret = -1;
 	}
 
@@ -723,16 +664,6 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 	if (b->discard_granularity) {
 		alignment = queue_limit_discard_alignment(b, start);
 
-		if (t->discard_granularity != 0 &&
-		    t->discard_alignment != alignment) {
-			top = t->discard_granularity + t->discard_alignment;
-			bottom = b->discard_granularity + alignment;
-
-			/* Verify that top and bottom intervals line up */
-			if ((max(top, bottom) % min(top, bottom)) != 0)
-				t->discard_misaligned = 1;
-		}
-
 		t->max_discard_sectors = min_not_zero(t->max_discard_sectors,
 						      b->max_discard_sectors);
 		t->max_hw_discard_sectors = min_not_zero(t->max_hw_discard_sectors,
@@ -746,8 +677,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 						   b->max_secure_erase_sectors);
 	t->zone_write_granularity = max(t->zone_write_granularity,
 					b->zone_write_granularity);
-	t->zoned = max(t->zoned, b->zoned);
-	if (!t->zoned) {
+	if (!(t->features & BLK_FEAT_ZONED)) {
 		t->zone_write_granularity = 0;
 		t->max_zone_append_sectors = 0;
 	}
@@ -781,21 +711,65 @@ void queue_limits_stack_bdev(struct queue_limits *t, struct block_device *bdev,
 EXPORT_SYMBOL_GPL(queue_limits_stack_bdev);
 
 /**
- * blk_queue_update_dma_pad - update pad mask
- * @q:     the request queue for the device
- * @mask:  pad mask
+ * queue_limits_stack_integrity - stack integrity profile
+ * @t: target queue limits
+ * @b: base queue limits
  *
- * Update dma pad mask.
+ * Check if the integrity profile in the @b can be stacked into the
+ * target @t.  Stacking is possible if either:
  *
- * Appending pad buffer to a request modifies the last entry of a
- * scatter list such that it includes the pad buffer.
- **/
-void blk_queue_update_dma_pad(struct request_queue *q, unsigned int mask)
-{
-	if (mask > q->dma_pad_mask)
-		q->dma_pad_mask = mask;
+ *   a) does not have any integrity information stacked into it yet
+ *   b) the integrity profile in @b is identical to the one in @t
+ *
+ * If @b can be stacked into @t, return %true.  Else return %false and clear the
+ * integrity information in @t.
+ */
+bool queue_limits_stack_integrity(struct queue_limits *t,
+		struct queue_limits *b)
+{
+	struct blk_integrity *ti = &t->integrity;
+	struct blk_integrity *bi = &b->integrity;
+
+	if (!IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY))
+		return true;
+
+	if (!ti->tuple_size) {
+		/* inherit the settings from the first underlying device */
+		if (!(ti->flags & BLK_INTEGRITY_STACKED)) {
+			ti->flags = BLK_INTEGRITY_DEVICE_CAPABLE |
+				(bi->flags & BLK_INTEGRITY_REF_TAG);
+			ti->csum_type = bi->csum_type;
+			ti->tuple_size = bi->tuple_size;
+			ti->pi_offset = bi->pi_offset;
+			ti->interval_exp = bi->interval_exp;
+			ti->tag_size = bi->tag_size;
+			goto done;
+		}
+		if (!bi->tuple_size)
+			goto done;
+	}
+
+	if (ti->tuple_size != bi->tuple_size)
+		goto incompatible;
+	if (ti->interval_exp != bi->interval_exp)
+		goto incompatible;
+	if (ti->tag_size != bi->tag_size)
+		goto incompatible;
+	if (ti->csum_type != bi->csum_type)
+		goto incompatible;
+	if ((ti->flags & BLK_INTEGRITY_REF_TAG) !=
+	    (bi->flags & BLK_INTEGRITY_REF_TAG))
+		goto incompatible;
+
+done:
+	ti->flags |= BLK_INTEGRITY_STACKED;
+	return true;
+
+incompatible:
+	memset(ti, 0, sizeof(*ti));
+	return false;
 }
-EXPORT_SYMBOL(blk_queue_update_dma_pad);
+EXPORT_SYMBOL_GPL(queue_limits_stack_integrity);
 
 /**
  * blk_set_queue_depth - tell the block layer about the device queue depth
@@ -810,54 +784,11 @@ void blk_set_queue_depth(struct request_queue *q, unsigned int depth)
 }
 EXPORT_SYMBOL(blk_set_queue_depth);
 
-/**
- * blk_queue_write_cache - configure queue's write cache
- * @q:		the request queue for the device
- * @wc:		write back cache on or off
- * @fua:	device supports FUA writes, if true
- *
- * Tell the block layer about the write cache of @q.
- */
-void blk_queue_write_cache(struct request_queue *q, bool wc, bool fua)
-{
-	if (wc) {
-		blk_queue_flag_set(QUEUE_FLAG_HW_WC, q);
-		blk_queue_flag_set(QUEUE_FLAG_WC, q);
-	} else {
-		blk_queue_flag_clear(QUEUE_FLAG_HW_WC, q);
-		blk_queue_flag_clear(QUEUE_FLAG_WC, q);
-	}
-	if (fua)
-		blk_queue_flag_set(QUEUE_FLAG_FUA, q);
-	else
-		blk_queue_flag_clear(QUEUE_FLAG_FUA, q);
-}
-EXPORT_SYMBOL_GPL(blk_queue_write_cache);
-
-/**
- * disk_set_zoned - inidicate a zoned device
- * @disk:	gendisk to configure
- */
-void disk_set_zoned(struct gendisk *disk)
-{
-	struct request_queue *q = disk->queue;
-
-	WARN_ON_ONCE(!IS_ENABLED(CONFIG_BLK_DEV_ZONED));
-
-	/*
-	 * Set the zone write granularity to the device logical block
-	 * size by default. The driver can change this value if needed.
-	 */
-	q->limits.zoned = true;
-	blk_queue_zone_write_granularity(q, queue_logical_block_size(q));
-}
-EXPORT_SYMBOL_GPL(disk_set_zoned);
-
 int bdev_alignment_offset(struct block_device *bdev)
 {
 	struct request_queue *q = bdev_get_queue(bdev);
 
-	if (q->limits.misaligned)
+	if (q->limits.flags & BLK_FLAG_MISALIGNED)
 		return -1;
 	if (bdev_is_partition(bdev))
 		return queue_limit_alignment_offset(&q->limits,
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index f0f9314ab65c..60116d13cb80 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -22,8 +22,8 @@
 
 struct queue_sysfs_entry {
 	struct attribute attr;
-	ssize_t (*show)(struct request_queue *, char *);
-	ssize_t (*store)(struct request_queue *, const char *, size_t);
+	ssize_t (*show)(struct gendisk *disk, char *page);
+	ssize_t (*store)(struct gendisk *disk, const char *page, size_t count);
 };
 
 static ssize_t
@@ -47,18 +47,18 @@ queue_var_store(unsigned long *var, const char *page, size_t count)
 	return count;
 }
 
-static ssize_t queue_requests_show(struct request_queue *q, char *page)
+static ssize_t queue_requests_show(struct gendisk *disk, char *page)
 {
-	return queue_var_show(q->nr_requests, page);
+	return queue_var_show(disk->queue->nr_requests, page);
 }
 
 static ssize_t
-queue_requests_store(struct request_queue *q, const char *page, size_t count)
+queue_requests_store(struct gendisk *disk, const char *page, size_t count)
 {
 	unsigned long nr;
 	int ret, err;
 
-	if (!queue_is_mq(q))
+	if (!queue_is_mq(disk->queue))
 		return -EINVAL;
 
 	ret = queue_var_store(&nr, page, count);
@@ -68,111 +68,91 @@ queue_requests_store(struct request_queue *q, const char *page, size_t count)
 	if (nr < BLKDEV_MIN_RQ)
 		nr = BLKDEV_MIN_RQ;
 
-	err = blk_mq_update_nr_requests(q, nr);
+	err = blk_mq_update_nr_requests(disk->queue, nr);
 	if (err)
 		return err;
 
 	return ret;
 }
 
-static ssize_t queue_ra_show(struct request_queue *q, char *page)
+static ssize_t queue_ra_show(struct gendisk *disk, char *page)
 {
-	unsigned long ra_kb;
-
-	if (!q->disk)
-		return -EINVAL;
-	ra_kb = q->disk->bdi->ra_pages << (PAGE_SHIFT - 10);
-	return queue_var_show(ra_kb, page);
+	return queue_var_show(disk->bdi->ra_pages << (PAGE_SHIFT - 10), page);
 }
 
 static ssize_t
-queue_ra_store(struct request_queue *q, const char *page, size_t count)
+queue_ra_store(struct gendisk *disk, const char *page, size_t count)
 {
 	unsigned long ra_kb;
 	ssize_t ret;
 
-	if (!q->disk)
-		return -EINVAL;
 	ret = queue_var_store(&ra_kb, page, count);
 	if (ret < 0)
 		return ret;
-	q->disk->bdi->ra_pages = ra_kb >> (PAGE_SHIFT - 10);
+	disk->bdi->ra_pages = ra_kb >> (PAGE_SHIFT - 10);
 	return ret;
 }
 
-static ssize_t queue_max_sectors_show(struct request_queue *q, char *page)
-{
-	int max_sectors_kb = queue_max_sectors(q) >> 1;
-
-	return queue_var_show(max_sectors_kb, page);
-}
-
-static ssize_t queue_max_segments_show(struct request_queue *q, char *page)
-{
-	return queue_var_show(queue_max_segments(q), page);
-}
-
-static ssize_t queue_max_discard_segments_show(struct request_queue *q,
-		char *page)
-{
-	return queue_var_show(queue_max_discard_segments(q), page);
-}
-
-static ssize_t queue_max_integrity_segments_show(struct request_queue *q, char *page)
-{
-	return queue_var_show(q->limits.max_integrity_segments, page);
-}
-
-static ssize_t queue_max_segment_size_show(struct request_queue *q, char *page)
-{
-	return queue_var_show(queue_max_segment_size(q), page);
-}
-
-static ssize_t queue_logical_block_size_show(struct request_queue *q, char *page)
-{
-	return queue_var_show(queue_logical_block_size(q), page);
-}
-
-static ssize_t queue_physical_block_size_show(struct request_queue *q, char *page)
-{
-	return queue_var_show(queue_physical_block_size(q), page);
-}
-
-static ssize_t queue_chunk_sectors_show(struct request_queue *q, char *page)
-{
-	return queue_var_show(q->limits.chunk_sectors, page);
-}
-
-static ssize_t queue_io_min_show(struct request_queue *q, char *page)
-{
-	return queue_var_show(queue_io_min(q), page);
+#define QUEUE_SYSFS_LIMIT_SHOW(_field)					\
+static ssize_t queue_##_field##_show(struct gendisk *disk, char *page)	\
+{									\
+	return queue_var_show(disk->queue->limits._field, page);	\
+}
+
+QUEUE_SYSFS_LIMIT_SHOW(max_segments)
+QUEUE_SYSFS_LIMIT_SHOW(max_discard_segments)
+QUEUE_SYSFS_LIMIT_SHOW(max_integrity_segments)
+QUEUE_SYSFS_LIMIT_SHOW(max_segment_size)
+QUEUE_SYSFS_LIMIT_SHOW(logical_block_size)
+QUEUE_SYSFS_LIMIT_SHOW(physical_block_size)
+QUEUE_SYSFS_LIMIT_SHOW(chunk_sectors)
+QUEUE_SYSFS_LIMIT_SHOW(io_min)
+QUEUE_SYSFS_LIMIT_SHOW(io_opt)
+QUEUE_SYSFS_LIMIT_SHOW(discard_granularity)
+QUEUE_SYSFS_LIMIT_SHOW(zone_write_granularity)
+QUEUE_SYSFS_LIMIT_SHOW(virt_boundary_mask)
+QUEUE_SYSFS_LIMIT_SHOW(dma_alignment)
+QUEUE_SYSFS_LIMIT_SHOW(max_open_zones)
+QUEUE_SYSFS_LIMIT_SHOW(max_active_zones)
+QUEUE_SYSFS_LIMIT_SHOW(atomic_write_unit_min)
+QUEUE_SYSFS_LIMIT_SHOW(atomic_write_unit_max)
+
+#define QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(_field)			\
+static ssize_t queue_##_field##_show(struct gendisk *disk, char *page)	\
+{									\
+	return sprintf(page, "%llu\n",					\
+		(unsigned long long)disk->queue->limits._field <<	\
+			SECTOR_SHIFT);					\
 }
 
-static ssize_t queue_io_opt_show(struct request_queue *q, char *page)
-{
-	return queue_var_show(queue_io_opt(q), page);
-}
+QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(max_discard_sectors)
+QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(max_hw_discard_sectors)
+QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(max_write_zeroes_sectors)
+QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(atomic_write_max_sectors)
+QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(atomic_write_boundary_sectors)
 
-static ssize_t queue_discard_granularity_show(struct request_queue *q, char *page)
-{
-	return queue_var_show(q->limits.discard_granularity, page);
+#define QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_KB(_field)			\
+static ssize_t queue_##_field##_show(struct gendisk *disk, char *page)	\
+{									\
+	return queue_var_show(disk->queue->limits._field >> 1, page);	\
 }
 
-static ssize_t queue_discard_max_hw_show(struct request_queue *q, char *page)
-{
+QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_KB(max_sectors)
+QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_KB(max_hw_sectors)
 
-	return sprintf(page, "%llu\n",
-		(unsigned long long)q->limits.max_hw_discard_sectors << 9);
+#define QUEUE_SYSFS_SHOW_CONST(_name, _val)				\
+static ssize_t queue_##_name##_show(struct gendisk *disk, char *page)	\
+{									\
+	return sprintf(page, "%d\n", _val);				\
 }
 
-static ssize_t queue_discard_max_show(struct request_queue *q, char *page)
-{
-	return sprintf(page, "%llu\n",
-		       (unsigned long long)q->limits.max_discard_sectors << 9);
-}
+/* deprecated fields */
+QUEUE_SYSFS_SHOW_CONST(discard_zeroes_data, 0)
+QUEUE_SYSFS_SHOW_CONST(write_same_max, 0)
+QUEUE_SYSFS_SHOW_CONST(poll_delay, -1)
 
-static ssize_t queue_discard_max_store(struct request_queue *q,
-				       const char *page, size_t count)
+static ssize_t queue_max_discard_sectors_store(struct gendisk *disk,
+		const char *page, size_t count)
 {
 	unsigned long max_discard_bytes;
 	struct queue_limits lim;
@@ -183,54 +163,34 @@ static ssize_t queue_discard_max_store(struct request_queue *q,
 	if (ret < 0)
 		return ret;
 
-	if (max_discard_bytes & (q->limits.discard_granularity - 1))
+	if (max_discard_bytes & (disk->queue->limits.discard_granularity - 1))
 		return -EINVAL;
 
 	if ((max_discard_bytes >> SECTOR_SHIFT) > UINT_MAX)
 		return -EINVAL;
 
-	blk_mq_freeze_queue(q);
-	lim = queue_limits_start_update(q);
+	lim = queue_limits_start_update(disk->queue);
 	lim.max_user_discard_sectors = max_discard_bytes >> SECTOR_SHIFT;
-	err = queue_limits_commit_update(q, &lim);
-	blk_mq_unfreeze_queue(q);
-
+	err = queue_limits_commit_update(disk->queue, &lim);
 	if (err)
 		return err;
 	return ret;
 }
 
-static ssize_t queue_discard_zeroes_data_show(struct request_queue *q, char *page)
-{
-	return queue_var_show(0, page);
-}
-
-static ssize_t queue_write_same_max_show(struct request_queue *q, char *page)
-{
-	return queue_var_show(0, page);
-}
-
-static ssize_t queue_write_zeroes_max_show(struct request_queue *q, char *page)
+/*
+ * For zone append queue_max_zone_append_sectors does not just return the
+ * underlying queue limits, but actually contains a calculation.  Because of
+ * that we can't simply use QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES here.
+ */
+static ssize_t queue_zone_append_max_show(struct gendisk *disk, char *page)
 {
 	return sprintf(page, "%llu\n",
-		(unsigned long long)q->limits.max_write_zeroes_sectors << 9);
-}
-
-static ssize_t queue_zone_write_granularity_show(struct request_queue *q,
-						 char *page)
-{
-	return queue_var_show(queue_zone_write_granularity(q), page);
-}
-
-static ssize_t queue_zone_append_max_show(struct request_queue *q, char *page)
-{
-	unsigned long long max_sectors = queue_max_zone_append_sectors(q);
-
-	return sprintf(page, "%llu\n", max_sectors << SECTOR_SHIFT);
+		(u64)queue_max_zone_append_sectors(disk->queue) <<
+			SECTOR_SHIFT);
 }
 
 static ssize_t
-queue_max_sectors_store(struct request_queue *q, const char *page, size_t count)
+queue_max_sectors_store(struct gendisk *disk, const char *page, size_t count)
 {
 	unsigned long max_sectors_kb;
 	struct queue_limits lim;
@@ -241,94 +201,83 @@ queue_max_sectors_store(struct request_queue *q, const char *page, size_t count)
 	if (ret < 0)
 		return ret;
 
-	blk_mq_freeze_queue(q);
-	lim = queue_limits_start_update(q);
+	lim = queue_limits_start_update(disk->queue);
 	lim.max_user_sectors = max_sectors_kb << 1;
-	err = queue_limits_commit_update(q, &lim);
-	blk_mq_unfreeze_queue(q);
+	err = queue_limits_commit_update(disk->queue, &lim);
 	if (err)
 		return err;
 	return ret;
 }
 
-static ssize_t queue_max_hw_sectors_show(struct request_queue *q, char *page)
+static ssize_t queue_feature_store(struct gendisk *disk, const char *page,
+		size_t count, blk_features_t feature)
 {
-	int max_hw_sectors_kb = queue_max_hw_sectors(q) >> 1;
-
-	return queue_var_show(max_hw_sectors_kb, page);
-}
+	struct queue_limits lim;
+	unsigned long val;
+	ssize_t ret;
 
-static ssize_t queue_virt_boundary_mask_show(struct request_queue *q, char *page)
-{
-	return queue_var_show(q->limits.virt_boundary_mask, page);
-}
+	ret = queue_var_store(&val, page, count);
+	if (ret < 0)
+		return ret;
 
-static ssize_t queue_dma_alignment_show(struct request_queue *q, char *page)
-{
-	return queue_var_show(queue_dma_alignment(q), page);
+	lim = queue_limits_start_update(disk->queue);
+	if (val)
+		lim.features |= feature;
+	else
+		lim.features &= ~feature;
+	ret = queue_limits_commit_update(disk->queue, &lim);
+	if (ret)
+		return ret;
+	return count;
 }
 
-#define QUEUE_SYSFS_BIT_FNS(name, flag, neg)				\
-static ssize_t								\
-queue_##name##_show(struct request_queue *q, char *page)		\
+#define QUEUE_SYSFS_FEATURE(_name, _feature)				\
+static ssize_t queue_##_name##_show(struct gendisk *disk, char *page)	\
 {									\
-	int bit;							\
-	bit = test_bit(QUEUE_FLAG_##flag, &q->queue_flags);		\
-	return queue_var_show(neg ? !bit : bit, page);			\
+	return sprintf(page, "%u\n",					\
+		!!(disk->queue->limits.features & _feature));		\
 }									\
-static ssize_t								\
-queue_##name##_store(struct request_queue *q, const char *page, size_t count) \
+static ssize_t queue_##_name##_store(struct gendisk *disk,		\
+		const char *page, size_t count)				\
 {									\
-	unsigned long val;						\
-	ssize_t ret;							\
-	ret = queue_var_store(&val, page, count);			\
-	if (ret < 0)							\
-		 return ret;						\
-	if (neg)							\
-		val = !val;						\
-									\
-	if (val)							\
-		blk_queue_flag_set(QUEUE_FLAG_##flag, q);		\
-	else								\
-		blk_queue_flag_clear(QUEUE_FLAG_##flag, q);		\
-	return ret;							\
-}
-
-QUEUE_SYSFS_BIT_FNS(nonrot, NONROT, 1);
-QUEUE_SYSFS_BIT_FNS(random, ADD_RANDOM, 0);
-QUEUE_SYSFS_BIT_FNS(iostats, IO_STAT, 0);
-QUEUE_SYSFS_BIT_FNS(stable_writes, STABLE_WRITES, 0);
-#undef QUEUE_SYSFS_BIT_FNS
-
-static ssize_t queue_zoned_show(struct request_queue *q, char *page)
-{
-	if (blk_queue_is_zoned(q))
-		return sprintf(page, "host-managed\n");
-	return sprintf(page, "none\n");
+	return queue_feature_store(disk, page, count, _feature);	\
 }
 
-static ssize_t queue_nr_zones_show(struct request_queue *q, char *page)
-{
-	return queue_var_show(disk_nr_zones(q->disk), page);
+QUEUE_SYSFS_FEATURE(rotational, BLK_FEAT_ROTATIONAL)
+QUEUE_SYSFS_FEATURE(add_random, BLK_FEAT_ADD_RANDOM)
+QUEUE_SYSFS_FEATURE(iostats, BLK_FEAT_IO_STAT)
+QUEUE_SYSFS_FEATURE(stable_writes, BLK_FEAT_STABLE_WRITES);
+
+#define QUEUE_SYSFS_FEATURE_SHOW(_name, _feature)			\
+static ssize_t queue_##_name##_show(struct gendisk *disk, char *page)	\
+{									\
+	return sprintf(page, "%u\n",					\
+		!!(disk->queue->limits.features & _feature));		\
 }
 
-static ssize_t queue_max_open_zones_show(struct request_queue *q, char *page)
+QUEUE_SYSFS_FEATURE_SHOW(poll, BLK_FEAT_POLL);
+QUEUE_SYSFS_FEATURE_SHOW(fua, BLK_FEAT_FUA);
+QUEUE_SYSFS_FEATURE_SHOW(dax, BLK_FEAT_DAX);
+
+static ssize_t queue_zoned_show(struct gendisk *disk, char *page)
 {
-	return queue_var_show(bdev_max_open_zones(q->disk->part0), page);
+	if (blk_queue_is_zoned(disk->queue))
+		return sprintf(page, "host-managed\n");
+	return sprintf(page, "none\n");
 }
 
-static ssize_t queue_max_active_zones_show(struct request_queue *q, char *page)
+static ssize_t queue_nr_zones_show(struct gendisk *disk, char *page)
 {
-	return queue_var_show(bdev_max_active_zones(q->disk->part0), page);
+	return queue_var_show(disk_nr_zones(disk), page);
 }
 
-static ssize_t queue_nomerges_show(struct request_queue *q, char *page)
+static ssize_t queue_nomerges_show(struct gendisk *disk, char *page)
 {
-	return queue_var_show((blk_queue_nomerges(q) << 1) |
-			       blk_queue_noxmerges(q), page);
+	return queue_var_show((blk_queue_nomerges(disk->queue) << 1) |
+			       blk_queue_noxmerges(disk->queue), page);
 }
 
-static ssize_t queue_nomerges_store(struct request_queue *q, const char *page,
+static ssize_t queue_nomerges_store(struct gendisk *disk, const char *page,
 				    size_t count)
 {
 	unsigned long nm;
@@ -337,29 +286,30 @@ static ssize_t queue_nomerges_store(struct request_queue *q, const char *page,
 	if (ret < 0)
 		return ret;
 
-	blk_queue_flag_clear(QUEUE_FLAG_NOMERGES, q);
-	blk_queue_flag_clear(QUEUE_FLAG_NOXMERGES, q);
+	blk_queue_flag_clear(QUEUE_FLAG_NOMERGES, disk->queue);
+	blk_queue_flag_clear(QUEUE_FLAG_NOXMERGES, disk->queue);
 	if (nm == 2)
-		blk_queue_flag_set(QUEUE_FLAG_NOMERGES, q);
+		blk_queue_flag_set(QUEUE_FLAG_NOMERGES, disk->queue);
 	else if (nm)
-		blk_queue_flag_set(QUEUE_FLAG_NOXMERGES, q);
+		blk_queue_flag_set(QUEUE_FLAG_NOXMERGES, disk->queue);
 
 	return ret;
 }
 
-static ssize_t queue_rq_affinity_show(struct request_queue *q, char *page)
+static ssize_t queue_rq_affinity_show(struct gendisk *disk, char *page)
 {
-	bool set = test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags);
-	bool force = test_bit(QUEUE_FLAG_SAME_FORCE, &q->queue_flags);
+	bool set = test_bit(QUEUE_FLAG_SAME_COMP, &disk->queue->queue_flags);
+	bool force = test_bit(QUEUE_FLAG_SAME_FORCE, &disk->queue->queue_flags);
 
 	return queue_var_show(set << force, page);
 }
 
 static ssize_t
-queue_rq_affinity_store(struct request_queue *q, const char *page, size_t count)
+queue_rq_affinity_store(struct gendisk *disk, const char *page, size_t count)
 {
 	ssize_t ret = -EINVAL;
 #ifdef CONFIG_SMP
+	struct request_queue *q = disk->queue;
 	unsigned long val;
 
 	ret = queue_var_store(&val, page, count);
@@ -380,38 +330,28 @@ queue_rq_affinity_store(struct request_queue *q, const char *page, size_t count)
 	return ret;
 }
 
-static ssize_t queue_poll_delay_show(struct request_queue *q, char *page)
-{
-	return sprintf(page, "%d\n", -1);
-}
-
-static ssize_t queue_poll_delay_store(struct request_queue *q, const char *page,
+static ssize_t queue_poll_delay_store(struct gendisk *disk, const char *page,
 				size_t count)
 {
 	return count;
 }
 
-static ssize_t queue_poll_show(struct request_queue *q, char *page)
-{
-	return queue_var_show(test_bit(QUEUE_FLAG_POLL, &q->queue_flags), page);
-}
-
-static ssize_t queue_poll_store(struct request_queue *q, const char *page,
+static ssize_t queue_poll_store(struct gendisk *disk, const char *page,
 				size_t count)
 {
-	if (!test_bit(QUEUE_FLAG_POLL, &q->queue_flags))
+	if (!(disk->queue->limits.features & BLK_FEAT_POLL))
 		return -EINVAL;
 	pr_info_ratelimited("writes to the poll attribute are ignored.\n");
 	pr_info_ratelimited("please use driver specific parameters instead.\n");
 	return count;
 }
 
-static ssize_t queue_io_timeout_show(struct request_queue *q, char *page)
+static ssize_t queue_io_timeout_show(struct gendisk *disk, char *page)
 {
-	return sprintf(page, "%u\n", jiffies_to_msecs(q->rq_timeout));
+	return sprintf(page, "%u\n", jiffies_to_msecs(disk->queue->rq_timeout));
 }
 
-static ssize_t queue_io_timeout_store(struct request_queue *q, const char *page,
+static ssize_t queue_io_timeout_store(struct gendisk *disk, const char *page,
 				  size_t count)
 {
 	unsigned int val;
@@ -421,46 +361,45 @@ static ssize_t queue_io_timeout_store(struct request_queue *q, const char *page,
 	if (err || val == 0)
 		return -EINVAL;
 
-	blk_queue_rq_timeout(q, msecs_to_jiffies(val));
+	blk_queue_rq_timeout(disk->queue, msecs_to_jiffies(val));
 
 	return count;
 }
 
-static ssize_t queue_wc_show(struct request_queue *q, char *page)
+static ssize_t queue_wc_show(struct gendisk *disk, char *page)
 {
-	if (test_bit(QUEUE_FLAG_WC, &q->queue_flags))
+	if (blk_queue_write_cache(disk->queue))
 		return sprintf(page, "write back\n");
-
 	return sprintf(page, "write through\n");
 }
 
-static ssize_t queue_wc_store(struct request_queue *q, const char *page,
+static ssize_t queue_wc_store(struct gendisk *disk, const char *page,
 			      size_t count)
 {
+	struct queue_limits lim;
+	bool disable;
+	int err;
+
 	if (!strncmp(page, "write back", 10)) {
-		if (!test_bit(QUEUE_FLAG_HW_WC, &q->queue_flags))
-			return -EINVAL;
-		blk_queue_flag_set(QUEUE_FLAG_WC, q);
+		disable = false;
 	} else if (!strncmp(page, "write through", 13) ||
-		 !strncmp(page, "none", 4)) {
-		blk_queue_flag_clear(QUEUE_FLAG_WC, q);
+		   !strncmp(page, "none", 4)) {
+		disable = true;
 	} else {
 		return -EINVAL;
 	}
 
+	lim = queue_limits_start_update(disk->queue);
+	if (disable)
+		lim.flags |= BLK_FLAG_WRITE_CACHE_DISABLED;
+	else
+		lim.flags &= ~BLK_FLAG_WRITE_CACHE_DISABLED;
+	err = queue_limits_commit_update(disk->queue, &lim);
+	if (err)
+		return err;
 	return count;
 }
 
-static ssize_t queue_fua_show(struct request_queue *q, char *page)
-{
-	return sprintf(page, "%u\n", test_bit(QUEUE_FLAG_FUA, &q->queue_flags));
-}
-
-static ssize_t queue_dax_show(struct request_queue *q, char *page)
-{
-	return queue_var_show(blk_queue_dax(q), page);
-}
-
 #define QUEUE_RO_ENTRY(_prefix, _name)			\
 static struct queue_sysfs_entry _prefix##_entry = {	\
 	.attr	= { .name = _name, .mode = 0444 },	\
@@ -491,12 +430,18 @@ QUEUE_RO_ENTRY(queue_io_opt, "optimal_io_size");
 
 QUEUE_RO_ENTRY(queue_max_discard_segments, "max_discard_segments");
 QUEUE_RO_ENTRY(queue_discard_granularity, "discard_granularity");
-QUEUE_RO_ENTRY(queue_discard_max_hw, "discard_max_hw_bytes");
-QUEUE_RW_ENTRY(queue_discard_max, "discard_max_bytes");
+QUEUE_RO_ENTRY(queue_max_hw_discard_sectors, "discard_max_hw_bytes");
+QUEUE_RW_ENTRY(queue_max_discard_sectors, "discard_max_bytes");
 QUEUE_RO_ENTRY(queue_discard_zeroes_data, "discard_zeroes_data");
 
+QUEUE_RO_ENTRY(queue_atomic_write_max_sectors, "atomic_write_max_bytes");
+QUEUE_RO_ENTRY(queue_atomic_write_boundary_sectors,
+		"atomic_write_boundary_bytes");
+QUEUE_RO_ENTRY(queue_atomic_write_unit_max, "atomic_write_unit_max_bytes");
+QUEUE_RO_ENTRY(queue_atomic_write_unit_min, "atomic_write_unit_min_bytes");
+
 QUEUE_RO_ENTRY(queue_write_same_max, "write_same_max_bytes");
-QUEUE_RO_ENTRY(queue_write_zeroes_max, "write_zeroes_max_bytes");
+QUEUE_RO_ENTRY(queue_max_write_zeroes_sectors, "write_zeroes_max_bytes");
 QUEUE_RO_ENTRY(queue_zone_append_max, "zone_append_max_bytes");
 QUEUE_RO_ENTRY(queue_zone_write_granularity, "zone_write_granularity");
 
@@ -522,9 +467,9 @@ static struct queue_sysfs_entry queue_hw_sector_size_entry = {
 	.show = queue_logical_block_size_show,
 };
 
-QUEUE_RW_ENTRY(queue_nonrot, "rotational");
+QUEUE_RW_ENTRY(queue_rotational, "rotational");
 QUEUE_RW_ENTRY(queue_iostats, "iostats");
-QUEUE_RW_ENTRY(queue_random, "add_random");
+QUEUE_RW_ENTRY(queue_add_random, "add_random");
 QUEUE_RW_ENTRY(queue_stable_writes, "stable_writes");
 
 #ifdef CONFIG_BLK_WBT
@@ -541,20 +486,22 @@ static ssize_t queue_var_store64(s64 *var, const char *page)
 	return 0;
 }
 
-static ssize_t queue_wb_lat_show(struct request_queue *q, char *page)
+static ssize_t queue_wb_lat_show(struct gendisk *disk, char *page)
 {
-	if (!wbt_rq_qos(q))
+	if (!wbt_rq_qos(disk->queue))
 		return -EINVAL;
 
-	if (wbt_disabled(q))
+	if (wbt_disabled(disk->queue))
 		return sprintf(page, "0\n");
 
-	return sprintf(page, "%llu\n", div_u64(wbt_get_min_lat(q), 1000));
+	return sprintf(page, "%llu\n",
+		div_u64(wbt_get_min_lat(disk->queue), 1000));
 }
 
-static ssize_t queue_wb_lat_store(struct request_queue *q, const char *page,
+static ssize_t queue_wb_lat_store(struct gendisk *disk, const char *page,
 				  size_t count)
 {
+	struct request_queue *q = disk->queue;
 	struct rq_qos *rqos;
 	ssize_t ret;
 	s64 val;
@@ -567,7 +514,7 @@ static ssize_t queue_wb_lat_store(struct request_queue *q, const char *page,
 
 	rqos = wbt_rq_qos(q);
 	if (!rqos) {
-		ret = wbt_init(q->disk);
+		ret = wbt_init(disk);
 		if (ret)
 			return ret;
 	}
@@ -585,13 +532,11 @@ static ssize_t queue_wb_lat_store(struct request_queue *q, const char *page,
 	 * ends up either enabling or disabling wbt completely. We can't
 	 * have IO inflight if that happens.
 	 */
-	blk_mq_freeze_queue(q);
 	blk_mq_quiesce_queue(q);
 
 	wbt_set_min_lat(q, val);
 
 	blk_mq_unquiesce_queue(q);
-	blk_mq_unfreeze_queue(q);
 
 	return count;
 }
@@ -615,14 +560,18 @@ static struct attribute *queue_attrs[] = {
 	&queue_io_min_entry.attr,
 	&queue_io_opt_entry.attr,
 	&queue_discard_granularity_entry.attr,
-	&queue_discard_max_entry.attr,
-	&queue_discard_max_hw_entry.attr,
+	&queue_max_discard_sectors_entry.attr,
+	&queue_max_hw_discard_sectors_entry.attr,
 	&queue_discard_zeroes_data_entry.attr,
+	&queue_atomic_write_max_sectors_entry.attr,
+	&queue_atomic_write_boundary_sectors_entry.attr,
+	&queue_atomic_write_unit_min_entry.attr,
+	&queue_atomic_write_unit_max_entry.attr,
 	&queue_write_same_max_entry.attr,
-	&queue_write_zeroes_max_entry.attr,
+	&queue_max_write_zeroes_sectors_entry.attr,
 	&queue_zone_append_max_entry.attr,
 	&queue_zone_write_granularity_entry.attr,
-	&queue_nonrot_entry.attr,
+	&queue_rotational_entry.attr,
 	&queue_zoned_entry.attr,
 	&queue_nr_zones_entry.attr,
 	&queue_max_open_zones_entry.attr,
@@ -630,7 +579,7 @@ static struct attribute *queue_attrs[] = {
 	&queue_nomerges_entry.attr,
 	&queue_iostats_entry.attr,
 	&queue_stable_writes_entry.attr,
-	&queue_random_entry.attr,
+	&queue_add_random_entry.attr,
 	&queue_poll_entry.attr,
 	&queue_wc_entry.attr,
 	&queue_fua_entry.attr,
@@ -699,14 +648,13 @@ queue_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
 {
 	struct queue_sysfs_entry *entry = to_queue(attr);
 	struct gendisk *disk = container_of(kobj, struct gendisk, queue_kobj);
-	struct request_queue *q = disk->queue;
 	ssize_t res;
 
 	if (!entry->show)
 		return -EIO;
-	mutex_lock(&q->sysfs_lock);
-	res = entry->show(q, page);
-	mutex_unlock(&q->sysfs_lock);
+	mutex_lock(&disk->queue->sysfs_lock);
+	res = entry->show(disk, page);
+	mutex_unlock(&disk->queue->sysfs_lock);
 	return res;
 }
 
@@ -722,9 +670,11 @@ queue_attr_store(struct kobject *kobj, struct attribute *attr,
 	if (!entry->store)
 		return -EIO;
 
+	blk_mq_freeze_queue(q);
 	mutex_lock(&q->sysfs_lock);
-	res = entry->store(q, page, length);
+	res = entry->store(disk, page, length);
 	mutex_unlock(&q->sysfs_lock);
+	blk_mq_unfreeze_queue(q);
 	return res;
 }
 
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index c1bf73f8c75d..dc6140fa3de0 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -704,6 +704,9 @@ static unsigned long tg_within_iops_limit(struct throtl_grp *tg, struct bio *bio
 
 	/* Calc approx time to dispatch */
 	jiffy_wait = jiffy_elapsed_rnd - jiffy_elapsed;
+
+	/* make sure at least one io can be dispatched after waiting */
+	jiffy_wait = max(jiffy_wait, HZ / iops_limit + 1);
 	return jiffy_wait;
 }
 
diff --git a/block/blk-wbt.c b/block/blk-wbt.c
index 64472134dd26..6dfc659d22e2 100644
--- a/block/blk-wbt.c
+++ b/block/blk-wbt.c
@@ -37,7 +37,7 @@
 enum wbt_flags {
 	WBT_TRACKED		= 1,	/* write, tracked for throttling */
 	WBT_READ		= 2,	/* read */
-	WBT_KSWAPD		= 4,	/* write, from kswapd */
+	WBT_SWAP		= 4,	/* write, from swap_writepage() */
 	WBT_DISCARD		= 8,	/* discard */
 
 	WBT_NR_BITS		= 4,	/* number of bits */
@@ -45,7 +45,7 @@ enum wbt_flags {
 
 enum {
 	WBT_RWQ_BG		= 0,
-	WBT_RWQ_KSWAPD,
+	WBT_RWQ_SWAP,
 	WBT_RWQ_DISCARD,
 	WBT_NUM_RWQ,
 };
@@ -172,8 +172,8 @@ static bool wb_recent_wait(struct rq_wb *rwb)
 static inline struct rq_wait *get_rq_wait(struct rq_wb *rwb,
 					  enum wbt_flags wb_acct)
 {
-	if (wb_acct & WBT_KSWAPD)
-		return &rwb->rq_wait[WBT_RWQ_KSWAPD];
+	if (wb_acct & WBT_SWAP)
+		return &rwb->rq_wait[WBT_RWQ_SWAP];
 	else if (wb_acct & WBT_DISCARD)
 		return &rwb->rq_wait[WBT_RWQ_DISCARD];
 
@@ -206,8 +206,8 @@ static void wbt_rqw_done(struct rq_wb *rwb, struct rq_wait *rqw,
 	 */
 	if (wb_acct & WBT_DISCARD)
 		limit = rwb->wb_background;
-	else if (test_bit(QUEUE_FLAG_WC, &rwb->rqos.disk->queue->queue_flags) &&
-	         !wb_recent_wait(rwb))
+	else if (blk_queue_write_cache(rwb->rqos.disk->queue) &&
+		 !wb_recent_wait(rwb))
 		limit = 0;
 	else
 		limit = rwb->wb_normal;
@@ -528,7 +528,7 @@ static bool close_io(struct rq_wb *rwb)
 		time_before(now, rwb->last_comp + HZ / 10);
 }
 
-#define REQ_HIPRIO	(REQ_SYNC | REQ_META | REQ_PRIO)
+#define REQ_HIPRIO	(REQ_SYNC | REQ_META | REQ_PRIO | REQ_SWAP)
 
 static inline unsigned int get_limit(struct rq_wb *rwb, blk_opf_t opf)
 {
@@ -539,13 +539,13 @@ static inline unsigned int get_limit(struct rq_wb *rwb, blk_opf_t opf)
 
 	/*
 	 * At this point we know it's a buffered write. If this is
-	 * kswapd trying to free memory, or REQ_SYNC is set, then
+	 * swap trying to free memory, or REQ_SYNC is set, then
 	 * it's WB_SYNC_ALL writeback, and we'll use the max limit for
 	 * that. If the write is marked as a background write, then use
 	 * the idle limit, or go to normal if we haven't had competing
 	 * IO for a bit.
 	 */
-	if ((opf & REQ_HIPRIO) || wb_recent_wait(rwb) || current_is_kswapd())
+	if ((opf & REQ_HIPRIO) || wb_recent_wait(rwb))
 		limit = rwb->rq_depth.max_depth;
 	else if ((opf & REQ_BACKGROUND) || close_io(rwb)) {
 		/*
@@ -622,8 +622,8 @@ static enum wbt_flags bio_to_wbt_flags(struct rq_wb *rwb, struct bio *bio)
 	if (bio_op(bio) == REQ_OP_READ) {
 		flags = WBT_READ;
 	} else if (wbt_should_throttle(bio)) {
-		if (current_is_kswapd())
-			flags |= WBT_KSWAPD;
+		if (bio->bi_opf & REQ_SWAP)
+			flags |= WBT_SWAP;
 		if (bio_op(bio) == REQ_OP_DISCARD)
 			flags |= WBT_DISCARD;
 		flags |= WBT_TRACKED;
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 52abebf56027..af19296fa50d 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -116,24 +116,6 @@ const char *blk_zone_cond_str(enum blk_zone_cond zone_cond)
 EXPORT_SYMBOL_GPL(blk_zone_cond_str);
 
 /**
- * bdev_nr_zones - Get number of zones
- * @bdev:	Target device
- *
- * Return the total number of zones of a zoned block device.  For a block
- * device without zone capabilities, the number of zones is always 0.
- */
-unsigned int bdev_nr_zones(struct block_device *bdev)
-{
-	sector_t zone_sectors = bdev_zone_sectors(bdev);
-
-	if (!bdev_is_zoned(bdev))
-		return 0;
-	return (bdev_nr_sectors(bdev) + zone_sectors - 1) >>
-		ilog2(zone_sectors);
-}
-EXPORT_SYMBOL_GPL(bdev_nr_zones);
-
-/**
  * blkdev_report_zones - Get zones information
  * @bdev:	Target block device
  * @sector:	Sector from which to report zones
@@ -168,77 +150,6 @@ int blkdev_report_zones(struct block_device *bdev, sector_t sector,
 }
 EXPORT_SYMBOL_GPL(blkdev_report_zones);
 
-static inline unsigned long *blk_alloc_zone_bitmap(int node,
-						   unsigned int nr_zones)
-{
-	return kcalloc_node(BITS_TO_LONGS(nr_zones), sizeof(unsigned long),
-			    GFP_NOIO, node);
-}
-
-static int blk_zone_need_reset_cb(struct blk_zone *zone, unsigned int idx,
-				  void *data)
-{
-	/*
-	 * For an all-zones reset, ignore conventional, empty, read-only
-	 * and offline zones.
-	 */
-	switch (zone->cond) {
-	case BLK_ZONE_COND_NOT_WP:
-	case BLK_ZONE_COND_EMPTY:
-	case BLK_ZONE_COND_READONLY:
-	case BLK_ZONE_COND_OFFLINE:
-		return 0;
-	default:
-		set_bit(idx, (unsigned long *)data);
-		return 0;
-	}
-}
-
-static int blkdev_zone_reset_all_emulated(struct block_device *bdev)
-{
-	struct gendisk *disk = bdev->bd_disk;
-	sector_t capacity = bdev_nr_sectors(bdev);
-	sector_t zone_sectors = bdev_zone_sectors(bdev);
-	unsigned long *need_reset;
-	struct bio *bio = NULL;
-	sector_t sector = 0;
-	int ret;
-
-	need_reset = blk_alloc_zone_bitmap(disk->queue->node, disk->nr_zones);
-	if (!need_reset)
-		return -ENOMEM;
-
-	ret = disk->fops->report_zones(disk, 0, disk->nr_zones,
-				       blk_zone_need_reset_cb, need_reset);
-	if (ret < 0)
-		goto out_free_need_reset;
-
-	ret = 0;
-	while (sector < capacity) {
-		if (!test_bit(disk_zone_no(disk, sector), need_reset)) {
-			sector += zone_sectors;
-			continue;
-		}
-
-		bio = blk_next_bio(bio, bdev, 0, REQ_OP_ZONE_RESET | REQ_SYNC,
-				   GFP_KERNEL);
-		bio->bi_iter.bi_sector = sector;
-		sector += zone_sectors;
-
-		/* This may take a while, so be nice to others */
-		cond_resched();
-	}
-
-	if (bio) {
-		ret = submit_bio_wait(bio);
-		bio_put(bio);
-	}
-
-out_free_need_reset:
-	kfree(need_reset);
-	return ret;
-}
-
 static int blkdev_zone_reset_all(struct block_device *bdev)
 {
 	struct bio bio;
@@ -265,7 +176,6 @@ static int blkdev_zone_reset_all(struct block_device *bdev)
 int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op,
 		     sector_t sector, sector_t nr_sectors)
 {
-	struct request_queue *q = bdev_get_queue(bdev);
 	sector_t zone_sectors = bdev_zone_sectors(bdev);
 	sector_t capacity = bdev_nr_sectors(bdev);
 	sector_t end_sector = sector + nr_sectors;
@@ -293,16 +203,11 @@ int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op,
 		return -EINVAL;
 
 	/*
-	 * In the case of a zone reset operation over all zones,
-	 * REQ_OP_ZONE_RESET_ALL can be used with devices supporting this
-	 * command. For other devices, we emulate this command behavior by
-	 * identifying the zones needing a reset.
+	 * In the case of a zone reset operation over all zones, use
+	 * REQ_OP_ZONE_RESET_ALL.
 	 */
-	if (op == REQ_OP_ZONE_RESET && sector == 0 && nr_sectors == capacity) {
-		if (!blk_queue_zone_resetall(q))
-			return blkdev_zone_reset_all_emulated(bdev);
+	if (op == REQ_OP_ZONE_RESET && sector == 0 && nr_sectors == capacity)
 		return blkdev_zone_reset_all(bdev);
-	}
 
 	while (sector < end_sector) {
 		bio = blk_next_bio(bio, bdev, 0, op | REQ_SYNC, GFP_KERNEL);
@@ -1552,6 +1457,9 @@ static void disk_destroy_zone_wplugs_hash_table(struct gendisk *disk)
 
 void disk_free_zone_resources(struct gendisk *disk)
 {
+	if (!disk->zone_wplugs_pool)
+		return;
+
 	cancel_work_sync(&disk->zone_wplugs_work);
 
 	if (disk->zone_wplugs_wq) {
@@ -1570,7 +1478,7 @@ void disk_free_zone_resources(struct gendisk *disk)
 	mempool_destroy(disk->zone_wplugs_pool);
 	disk->zone_wplugs_pool = NULL;
 
-	kfree(disk->conv_zones_bitmap);
+	bitmap_free(disk->conv_zones_bitmap);
 	disk->conv_zones_bitmap = NULL;
 	disk->zone_capacity = 0;
 	disk->last_zone_capacity = 0;
@@ -1647,8 +1555,22 @@ static int disk_update_zone_resources(struct gendisk *disk,
 		return -ENODEV;
 	}
 
+	lim = queue_limits_start_update(q);
+
+	/*
+	 * Some devices can advertize zone resource limits that are larger than
+	 * the number of sequential zones of the zoned block device, e.g. a
+	 * small ZNS namespace. For such case, assume that the zoned device has
+	 * no zone resource limits.
+	 */
+	nr_seq_zones = disk->nr_zones - nr_conv_zones;
+	if (lim.max_open_zones >= nr_seq_zones)
+		lim.max_open_zones = 0;
+	if (lim.max_active_zones >= nr_seq_zones)
+		lim.max_active_zones = 0;
+
 	if (!disk->zone_wplugs_pool)
-		return 0;
+		goto commit;
 
 	/*
 	 * If the device has no limit on the maximum number of open and active
@@ -1657,9 +1579,6 @@ static int disk_update_zone_resources(struct gendisk *disk,
 	 * dynamic zone write plug allocation when simultaneously writing to
 	 * more zones than the size of the mempool.
 	 */
-	lim = queue_limits_start_update(q);
-
-	nr_seq_zones = disk->nr_zones - nr_conv_zones;
 	pool_size = max(lim.max_open_zones, lim.max_active_zones);
 	if (!pool_size)
 		pool_size = min(BLK_ZONE_WPLUG_DEFAULT_POOL_SIZE, nr_seq_zones);
@@ -1673,6 +1592,7 @@ static int disk_update_zone_resources(struct gendisk *disk,
 			lim.max_open_zones = 0;
 	}
 
+commit:
 	return queue_limits_commit_update(q, &lim);
 }
 
@@ -1680,7 +1600,6 @@ static int blk_revalidate_conv_zone(struct blk_zone *zone, unsigned int idx,
 				    struct blk_revalidate_zone_args *args)
 {
 	struct gendisk *disk = args->disk;
-	struct request_queue *q = disk->queue;
 
 	if (zone->capacity != zone->len) {
 		pr_warn("%s: Invalid conventional zone capacity\n",
@@ -1696,7 +1615,7 @@ static int blk_revalidate_conv_zone(struct blk_zone *zone, unsigned int idx,
 
 	if (!args->conv_zones_bitmap) {
 		args->conv_zones_bitmap =
-			blk_alloc_zone_bitmap(q->node, args->nr_zones);
+			bitmap_zalloc(args->nr_zones, GFP_NOIO);
 		if (!args->conv_zones_bitmap)
 			return -ENOMEM;
 	}
diff --git a/block/blk.h b/block/blk.h
index 189bc25beb50..e180863f918b 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -2,6 +2,7 @@
 #ifndef BLK_INTERNAL_H
 #define BLK_INTERNAL_H
 
+#include <linux/bio-integrity.h>
 #include <linux/blk-crypto.h>
 #include <linux/memblock.h>	/* for max_pfn/max_low_pfn */
 #include <linux/sched/sysctl.h>
@@ -98,8 +99,8 @@ static inline bool biovec_phys_mergeable(struct request_queue *q,
 		struct bio_vec *vec1, struct bio_vec *vec2)
 {
 	unsigned long mask = queue_segment_boundary(q);
-	phys_addr_t addr1 = page_to_phys(vec1->bv_page) + vec1->bv_offset;
-	phys_addr_t addr2 = page_to_phys(vec2->bv_page) + vec2->bv_offset;
+	phys_addr_t addr1 = bvec_phys(vec1);
+	phys_addr_t addr2 = bvec_phys(vec2);
 
 	/*
 	 * Merging adjacent physical pages may not work correctly under KMSAN
@@ -181,9 +182,11 @@ static inline unsigned int blk_rq_get_max_segments(struct request *rq)
 	return queue_max_segments(rq->q);
 }
 
-static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q,
-						     enum req_op op)
+static inline unsigned int blk_queue_get_max_sectors(struct request *rq)
 {
+	struct request_queue *q = rq->q;
+	enum req_op op = req_op(rq);
+
 	if (unlikely(op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE))
 		return min(q->limits.max_discard_sectors,
 			   UINT_MAX >> SECTOR_SHIFT);
@@ -191,16 +194,28 @@ static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q,
 	if (unlikely(op == REQ_OP_WRITE_ZEROES))
 		return q->limits.max_write_zeroes_sectors;
 
+	if (rq->cmd_flags & REQ_ATOMIC)
+		return q->limits.atomic_write_max_sectors;
+
 	return q->limits.max_sectors;
 }
 
 #ifdef CONFIG_BLK_DEV_INTEGRITY
 void blk_flush_integrity(void);
-bool __bio_integrity_endio(struct bio *);
 void bio_integrity_free(struct bio *bio);
+
+/*
+ * Integrity payloads can either be owned by the submitter, in which case
+ * bio_uninit will free them, or owned and generated by the block layer,
+ * in which case we'll verify them here (for reads) and free them before
+ * the bio is handed back to the submitted.
+ */
+bool __bio_integrity_endio(struct bio *bio);
 static inline bool bio_integrity_endio(struct bio *bio)
 {
-	if (bio_integrity(bio))
+	struct bio_integrity_payload *bip = bio_integrity(bio);
+
+	if (bip && (bip->bip_flags & BIP_BLOCK_INTEGRITY))
 		return __bio_integrity_endio(bio);
 	return true;
 }
@@ -352,6 +367,8 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio);
 enum elv_merge blk_try_merge(struct request *rq, struct bio *bio);
 
 int blk_set_default_limits(struct queue_limits *lim);
+void blk_apply_bdi_limits(struct backing_dev_info *bdi,
+		struct queue_limits *lim);
 int blk_dev_init(void);
 
 /*
@@ -393,7 +410,7 @@ struct bio *__blk_queue_bounce(struct bio *bio, struct request_queue *q);
 static inline bool blk_queue_may_bounce(struct request_queue *q)
 {
 	return IS_ENABLED(CONFIG_BOUNCE) &&
-		q->limits.bounce == BLK_BOUNCE_HIGH &&
+		(q->limits.features & BLK_FEAT_BOUNCE_HIGH) &&
 		max_low_pfn >= max_pfn;
 }
 
@@ -673,4 +690,9 @@ int bdev_open(struct block_device *bdev, blk_mode_t mode, void *holder,
 	      const struct blk_holder_ops *hops, struct file *bdev_file);
 int bdev_permission(dev_t dev, blk_mode_t mode, void *holder);
 
+void blk_integrity_generate(struct bio *bio);
+void blk_integrity_verify(struct bio *bio);
+void blk_integrity_prepare(struct request *rq);
+void blk_integrity_complete(struct request *rq, unsigned int nr_bytes);
+
 #endif /* BLK_INTERNAL_H */
diff --git a/block/bounce.c b/block/bounce.c
index d6a5219f29dd..0d898cd5ec49 100644
--- a/block/bounce.c
+++ b/block/bounce.c
@@ -10,7 +10,7 @@
 #include <linux/export.h>
 #include <linux/swap.h>
 #include <linux/gfp.h>
-#include <linux/bio.h>
+#include <linux/bio-integrity.h>
 #include <linux/pagemap.h>
 #include <linux/mempool.h>
 #include <linux/blkdev.h>
diff --git a/block/bsg-lib.c b/block/bsg-lib.c
index ee738d129a9f..32da4a4429ce 100644
--- a/block/bsg-lib.c
+++ b/block/bsg-lib.c
@@ -385,13 +385,12 @@ struct request_queue *bsg_setup_queue(struct device *dev, const char *name,
 	if (blk_mq_alloc_tag_set(set))
 		goto out_tag_set;
 
-	q = blk_mq_alloc_queue(set, lim, NULL);
+	q = blk_mq_alloc_queue(set, lim, dev);
 	if (IS_ERR(q)) {
 		ret = PTR_ERR(q);
 		goto out_queue;
 	}
 
-	q->queuedata = dev;
 	blk_queue_rq_timeout(q, BLK_DEFAULT_SG_TIMEOUT);
 
 	bset->bd = bsg_register_queue(q, dev, name, bsg_transport_sg_io_fn);
diff --git a/block/elevator.c b/block/elevator.c
index f64ebd726e58..f13d552a32c8 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -709,24 +709,25 @@ static int elevator_change(struct request_queue *q, const char *elevator_name)
 	return ret;
 }
 
-ssize_t elv_iosched_store(struct request_queue *q, const char *buf,
+ssize_t elv_iosched_store(struct gendisk *disk, const char *buf,
 			  size_t count)
 {
 	char elevator_name[ELV_NAME_MAX];
 	int ret;
 
-	if (!elv_support_iosched(q))
+	if (!elv_support_iosched(disk->queue))
 		return count;
 
 	strscpy(elevator_name, buf, sizeof(elevator_name));
-	ret = elevator_change(q, strstrip(elevator_name));
+	ret = elevator_change(disk->queue, strstrip(elevator_name));
 	if (!ret)
 		return count;
 	return ret;
 }
 
-ssize_t elv_iosched_show(struct request_queue *q, char *name)
+ssize_t elv_iosched_show(struct gendisk *disk, char *name)
 {
+	struct request_queue *q = disk->queue;
 	struct elevator_queue *eq = q->elevator;
 	struct elevator_type *cur = NULL, *e;
 	int len = 0;
diff --git a/block/elevator.h b/block/elevator.h
index e9a050a96e53..3fe18e1a8692 100644
--- a/block/elevator.h
+++ b/block/elevator.h
@@ -147,8 +147,8 @@ extern void elv_unregister(struct elevator_type *);
 /*
  * io scheduler sysfs switching
  */
-extern ssize_t elv_iosched_show(struct request_queue *, char *);
-extern ssize_t elv_iosched_store(struct request_queue *, const char *, size_t);
+ssize_t elv_iosched_show(struct gendisk *disk, char *page);
+ssize_t elv_iosched_store(struct gendisk *disk, const char *page, size_t count);
 
 extern bool elv_bio_merge_ok(struct request *, struct bio *);
 extern struct elevator_queue *elevator_alloc(struct request_queue *,
diff --git a/block/fops.c b/block/fops.c
index 376265935714..9825c1713a49 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -34,9 +34,12 @@ static blk_opf_t dio_bio_write_op(struct kiocb *iocb)
 	return opf;
 }
 
-static bool blkdev_dio_unaligned(struct block_device *bdev, loff_t pos,
-			      struct iov_iter *iter)
+static bool blkdev_dio_invalid(struct block_device *bdev, loff_t pos,
+				struct iov_iter *iter, bool is_atomic)
 {
+	if (is_atomic && !generic_atomic_write_valid(iter, pos))
+		return true;
+
 	return pos & (bdev_logical_block_size(bdev) - 1) ||
 		!bdev_iter_is_aligned(bdev, iter);
 }
@@ -72,6 +75,8 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb,
 	bio.bi_iter.bi_sector = pos >> SECTOR_SHIFT;
 	bio.bi_write_hint = file_inode(iocb->ki_filp)->i_write_hint;
 	bio.bi_ioprio = iocb->ki_ioprio;
+	if (iocb->ki_flags & IOCB_ATOMIC)
+		bio.bi_opf |= REQ_ATOMIC;
 
 	ret = bio_iov_iter_get_pages(&bio, iter);
 	if (unlikely(ret))
@@ -343,6 +348,9 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb,
 		task_io_account_write(bio->bi_iter.bi_size);
 	}
 
+	if (iocb->ki_flags & IOCB_ATOMIC)
+		bio->bi_opf |= REQ_ATOMIC;
+
 	if (iocb->ki_flags & IOCB_NOWAIT)
 		bio->bi_opf |= REQ_NOWAIT;
 
@@ -359,12 +367,13 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb,
 static ssize_t blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 {
 	struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host);
+	bool is_atomic = iocb->ki_flags & IOCB_ATOMIC;
 	unsigned int nr_pages;
 
 	if (!iov_iter_count(iter))
 		return 0;
 
-	if (blkdev_dio_unaligned(bdev, iocb->ki_pos, iter))
+	if (blkdev_dio_invalid(bdev, iocb->ki_pos, iter, is_atomic))
 		return -EINVAL;
 
 	nr_pages = bio_iov_vecs_to_alloc(iter, BIO_MAX_VECS + 1);
@@ -373,6 +382,8 @@ static ssize_t blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 			return __blkdev_direct_IO_simple(iocb, iter, bdev,
 							nr_pages);
 		return __blkdev_direct_IO_async(iocb, iter, bdev, nr_pages);
+	} else if (is_atomic) {
+		return -EINVAL;
 	}
 	return __blkdev_direct_IO(iocb, iter, bdev, bio_max_segs(nr_pages));
 }
@@ -383,10 +394,11 @@ static int blkdev_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 	struct block_device *bdev = I_BDEV(inode);
 	loff_t isize = i_size_read(inode);
 
-	iomap->bdev = bdev;
-	iomap->offset = ALIGN_DOWN(offset, bdev_logical_block_size(bdev));
 	if (offset >= isize)
 		return -EIO;
+
+	iomap->bdev = bdev;
+	iomap->offset = ALIGN_DOWN(offset, bdev_logical_block_size(bdev));
 	iomap->type = IOMAP_MAPPED;
 	iomap->addr = iomap->offset;
 	iomap->length = isize - iomap->offset;
@@ -612,6 +624,9 @@ static int blkdev_open(struct inode *inode, struct file *filp)
 	if (!bdev)
 		return -ENXIO;
 
+	if (bdev_can_atomic_write(bdev) && filp->f_flags & O_DIRECT)
+		filp->f_mode |= FMODE_CAN_ATOMIC_WRITE;
+
 	ret = bdev_open(bdev, mode, filp->private_data, NULL, filp);
 	if (ret)
 		blkdev_put_no_open(bdev);
diff --git a/block/genhd.c b/block/genhd.c
index 8f1f3c6b4d67..1c05dd4c6980 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -524,7 +524,7 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk,
 		disk->part0->bd_dev = MKDEV(disk->major, disk->first_minor);
 	}
 
-	disk_update_readahead(disk);
+	blk_apply_bdi_limits(disk->bdi, &disk->queue->limits);
 	disk_add_events(disk);
 	set_bit(GD_ADDED, &disk->state);
 	return 0;
@@ -663,12 +663,12 @@ void del_gendisk(struct gendisk *disk)
 	 */
 	if (!test_bit(GD_DEAD, &disk->state))
 		blk_report_disk_dead(disk, false);
-	__blk_mark_disk_dead(disk);
 
 	/*
 	 * Drop all partitions now that the disk is marked dead.
 	 */
 	mutex_lock(&disk->open_mutex);
+	__blk_mark_disk_dead(disk);
 	xa_for_each_start(&disk->part_tbl, idx, part, 1)
 		drop_partition(part);
 	mutex_unlock(&disk->open_mutex);
diff --git a/block/ioctl.c b/block/ioctl.c
index d570e1695896..e8e4a4190f18 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -224,7 +224,7 @@ static int blk_ioctl_zeroout(struct block_device *bdev, blk_mode_t mode,
 		goto fail;
 
 	err = blkdev_issue_zeroout(bdev, start >> 9, len >> 9, GFP_KERNEL,
-				   BLKDEV_ZERO_NOUNMAP);
+				   BLKDEV_ZERO_NOUNMAP | BLKDEV_ZERO_KILLABLE);
 
 fail:
 	filemap_invalidate_unlock(bdev->bd_mapping);
diff --git a/block/mq-deadline.c b/block/mq-deadline.c
index 94eede4fb9eb..acdc28756d9d 100644
--- a/block/mq-deadline.c
+++ b/block/mq-deadline.c
@@ -488,6 +488,20 @@ unlock:
 }
 
 /*
+ * 'depth' is a number in the range 1..INT_MAX representing a number of
+ * requests. Scale it with a factor (1 << bt->sb.shift) / q->nr_requests since
+ * 1..(1 << bt->sb.shift) is the range expected by sbitmap_get_shallow().
+ * Values larger than q->nr_requests have the same effect as q->nr_requests.
+ */
+static int dd_to_word_depth(struct blk_mq_hw_ctx *hctx, unsigned int qdepth)
+{
+	struct sbitmap_queue *bt = &hctx->sched_tags->bitmap_tags;
+	const unsigned int nrr = hctx->queue->nr_requests;
+
+	return ((qdepth << bt->sb.shift) + nrr - 1) / nrr;
+}
+
+/*
  * Called by __blk_mq_alloc_request(). The shallow_depth value set by this
  * function is used by __blk_mq_get_tag().
  */
@@ -503,7 +517,7 @@ static void dd_limit_depth(blk_opf_t opf, struct blk_mq_alloc_data *data)
 	 * Throttle asynchronous requests and writes such that these requests
 	 * do not block the allocation of synchronous requests.
 	 */
-	data->shallow_depth = dd->async_depth;
+	data->shallow_depth = dd_to_word_depth(data->hctx, dd->async_depth);
 }
 
 /* Called by blk_mq_update_nr_requests(). */
@@ -513,9 +527,9 @@ static void dd_depth_updated(struct blk_mq_hw_ctx *hctx)
 	struct deadline_data *dd = q->elevator->elevator_data;
 	struct blk_mq_tags *tags = hctx->sched_tags;
 
-	dd->async_depth = max(1UL, 3 * q->nr_requests / 4);
+	dd->async_depth = q->nr_requests;
 
-	sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, dd->async_depth);
+	sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, 1);
 }
 
 /* Called by blk_mq_init_hctx() and blk_mq_init_sched(). */
diff --git a/block/sed-opal.c b/block/sed-opal.c
index 14fe0fef811c..598fd3e7fcc8 100644
--- a/block/sed-opal.c
+++ b/block/sed-opal.c
@@ -314,7 +314,7 @@ static int read_sed_opal_key(const char *key_name, u_char *buffer, int buflen)
 			      &key_type_user, key_name, true);
 
 	if (IS_ERR(kref))
-		ret = PTR_ERR(kref);
+		return PTR_ERR(kref);
 
 	key = key_ref_to_ptr(kref);
 	down_read(&key->sem);
diff --git a/block/t10-pi.c b/block/t10-pi.c
index f4cc91156da1..425e2836f3e1 100644
--- a/block/t10-pi.c
+++ b/block/t10-pi.c
@@ -11,17 +11,23 @@
 #include <linux/module.h>
 #include <net/checksum.h>
 #include <asm/unaligned.h>
+#include "blk.h"
+
+struct blk_integrity_iter {
+	void			*prot_buf;
+	void			*data_buf;
+	sector_t		seed;
+	unsigned int		data_size;
+	unsigned short		interval;
+	const char		*disk_name;
+};
 
-typedef __be16 (csum_fn) (__be16, void *, unsigned int);
-
-static __be16 t10_pi_crc_fn(__be16 crc, void *data, unsigned int len)
-{
-	return cpu_to_be16(crc_t10dif_update(be16_to_cpu(crc), data, len));
-}
-
-static __be16 t10_pi_ip_fn(__be16 csum, void *data, unsigned int len)
+static __be16 t10_pi_csum(__be16 csum, void *data, unsigned int len,
+		unsigned char csum_type)
 {
-	return (__force __be16)ip_compute_csum(data, len);
+	if (csum_type == BLK_INTEGRITY_CSUM_IP)
+		return (__force __be16)ip_compute_csum(data, len);
+	return cpu_to_be16(crc_t10dif_update(be16_to_cpu(csum), data, len));
 }
 
 /*
@@ -29,48 +35,44 @@ static __be16 t10_pi_ip_fn(__be16 csum, void *data, unsigned int len)
  * 16 bit app tag, 32 bit reference tag. Type 3 does not define the ref
  * tag.
  */
-static blk_status_t t10_pi_generate(struct blk_integrity_iter *iter,
-		csum_fn *fn, enum t10_dif_type type)
+static void t10_pi_generate(struct blk_integrity_iter *iter,
+		struct blk_integrity *bi)
 {
-	u8 offset = iter->pi_offset;
+	u8 offset = bi->pi_offset;
 	unsigned int i;
 
 	for (i = 0 ; i < iter->data_size ; i += iter->interval) {
 		struct t10_pi_tuple *pi = iter->prot_buf + offset;
 
-		pi->guard_tag = fn(0, iter->data_buf, iter->interval);
+		pi->guard_tag = t10_pi_csum(0, iter->data_buf, iter->interval,
+				bi->csum_type);
 		if (offset)
-			pi->guard_tag = fn(pi->guard_tag, iter->prot_buf,
-					   offset);
+			pi->guard_tag = t10_pi_csum(pi->guard_tag,
+					iter->prot_buf, offset, bi->csum_type);
 		pi->app_tag = 0;
 
-		if (type == T10_PI_TYPE1_PROTECTION)
+		if (bi->flags & BLK_INTEGRITY_REF_TAG)
 			pi->ref_tag = cpu_to_be32(lower_32_bits(iter->seed));
 		else
 			pi->ref_tag = 0;
 
 		iter->data_buf += iter->interval;
-		iter->prot_buf += iter->tuple_size;
+		iter->prot_buf += bi->tuple_size;
 		iter->seed++;
 	}
-
-	return BLK_STS_OK;
 }
 
 static blk_status_t t10_pi_verify(struct blk_integrity_iter *iter,
-		csum_fn *fn, enum t10_dif_type type)
+		struct blk_integrity *bi)
 {
-	u8 offset = iter->pi_offset;
+	u8 offset = bi->pi_offset;
 	unsigned int i;
 
-	BUG_ON(type == T10_PI_TYPE0_PROTECTION);
-
 	for (i = 0 ; i < iter->data_size ; i += iter->interval) {
 		struct t10_pi_tuple *pi = iter->prot_buf + offset;
 		__be16 csum;
 
-		if (type == T10_PI_TYPE1_PROTECTION ||
-		    type == T10_PI_TYPE2_PROTECTION) {
+		if (bi->flags & BLK_INTEGRITY_REF_TAG) {
 			if (pi->app_tag == T10_PI_APP_ESCAPE)
 				goto next;
 
@@ -82,15 +84,17 @@ static blk_status_t t10_pi_verify(struct blk_integrity_iter *iter,
 				       iter->seed, be32_to_cpu(pi->ref_tag));
 				return BLK_STS_PROTECTION;
 			}
-		} else if (type == T10_PI_TYPE3_PROTECTION) {
+		} else {
 			if (pi->app_tag == T10_PI_APP_ESCAPE &&
 			    pi->ref_tag == T10_PI_REF_ESCAPE)
 				goto next;
 		}
 
-		csum = fn(0, iter->data_buf, iter->interval);
+		csum = t10_pi_csum(0, iter->data_buf, iter->interval,
+				bi->csum_type);
 		if (offset)
-			csum = fn(csum, iter->prot_buf, offset);
+			csum = t10_pi_csum(csum, iter->prot_buf, offset,
+					bi->csum_type);
 
 		if (pi->guard_tag != csum) {
 			pr_err("%s: guard tag error at sector %llu " \
@@ -102,33 +106,13 @@ static blk_status_t t10_pi_verify(struct blk_integrity_iter *iter,
 
 next:
 		iter->data_buf += iter->interval;
-		iter->prot_buf += iter->tuple_size;
+		iter->prot_buf += bi->tuple_size;
 		iter->seed++;
 	}
 
 	return BLK_STS_OK;
 }
 
-static blk_status_t t10_pi_type1_generate_crc(struct blk_integrity_iter *iter)
-{
-	return t10_pi_generate(iter, t10_pi_crc_fn, T10_PI_TYPE1_PROTECTION);
-}
-
-static blk_status_t t10_pi_type1_generate_ip(struct blk_integrity_iter *iter)
-{
-	return t10_pi_generate(iter, t10_pi_ip_fn, T10_PI_TYPE1_PROTECTION);
-}
-
-static blk_status_t t10_pi_type1_verify_crc(struct blk_integrity_iter *iter)
-{
-	return t10_pi_verify(iter, t10_pi_crc_fn, T10_PI_TYPE1_PROTECTION);
-}
-
-static blk_status_t t10_pi_type1_verify_ip(struct blk_integrity_iter *iter)
-{
-	return t10_pi_verify(iter, t10_pi_ip_fn, T10_PI_TYPE1_PROTECTION);
-}
-
 /**
  * t10_pi_type1_prepare - prepare PI prior submitting request to device
  * @rq:              request with PI that should be prepared
@@ -141,7 +125,7 @@ static blk_status_t t10_pi_type1_verify_ip(struct blk_integrity_iter *iter)
  */
 static void t10_pi_type1_prepare(struct request *rq)
 {
-	struct blk_integrity *bi = &rq->q->integrity;
+	struct blk_integrity *bi = &rq->q->limits.integrity;
 	const int tuple_sz = bi->tuple_size;
 	u32 ref_tag = t10_pi_ref_tag(rq);
 	u8 offset = bi->pi_offset;
@@ -192,7 +176,7 @@ static void t10_pi_type1_prepare(struct request *rq)
  */
 static void t10_pi_type1_complete(struct request *rq, unsigned int nr_bytes)
 {
-	struct blk_integrity *bi = &rq->q->integrity;
+	struct blk_integrity *bi = &rq->q->limits.integrity;
 	unsigned intervals = nr_bytes >> bi->interval_exp;
 	const int tuple_sz = bi->tuple_size;
 	u32 ref_tag = t10_pi_ref_tag(rq);
@@ -225,81 +209,15 @@ static void t10_pi_type1_complete(struct request *rq, unsigned int nr_bytes)
 	}
 }
 
-static blk_status_t t10_pi_type3_generate_crc(struct blk_integrity_iter *iter)
-{
-	return t10_pi_generate(iter, t10_pi_crc_fn, T10_PI_TYPE3_PROTECTION);
-}
-
-static blk_status_t t10_pi_type3_generate_ip(struct blk_integrity_iter *iter)
-{
-	return t10_pi_generate(iter, t10_pi_ip_fn, T10_PI_TYPE3_PROTECTION);
-}
-
-static blk_status_t t10_pi_type3_verify_crc(struct blk_integrity_iter *iter)
-{
-	return t10_pi_verify(iter, t10_pi_crc_fn, T10_PI_TYPE3_PROTECTION);
-}
-
-static blk_status_t t10_pi_type3_verify_ip(struct blk_integrity_iter *iter)
-{
-	return t10_pi_verify(iter, t10_pi_ip_fn, T10_PI_TYPE3_PROTECTION);
-}
-
-/* Type 3 does not have a reference tag so no remapping is required. */
-static void t10_pi_type3_prepare(struct request *rq)
-{
-}
-
-/* Type 3 does not have a reference tag so no remapping is required. */
-static void t10_pi_type3_complete(struct request *rq, unsigned int nr_bytes)
-{
-}
-
-const struct blk_integrity_profile t10_pi_type1_crc = {
-	.name			= "T10-DIF-TYPE1-CRC",
-	.generate_fn		= t10_pi_type1_generate_crc,
-	.verify_fn		= t10_pi_type1_verify_crc,
-	.prepare_fn		= t10_pi_type1_prepare,
-	.complete_fn		= t10_pi_type1_complete,
-};
-EXPORT_SYMBOL(t10_pi_type1_crc);
-
-const struct blk_integrity_profile t10_pi_type1_ip = {
-	.name			= "T10-DIF-TYPE1-IP",
-	.generate_fn		= t10_pi_type1_generate_ip,
-	.verify_fn		= t10_pi_type1_verify_ip,
-	.prepare_fn		= t10_pi_type1_prepare,
-	.complete_fn		= t10_pi_type1_complete,
-};
-EXPORT_SYMBOL(t10_pi_type1_ip);
-
-const struct blk_integrity_profile t10_pi_type3_crc = {
-	.name			= "T10-DIF-TYPE3-CRC",
-	.generate_fn		= t10_pi_type3_generate_crc,
-	.verify_fn		= t10_pi_type3_verify_crc,
-	.prepare_fn		= t10_pi_type3_prepare,
-	.complete_fn		= t10_pi_type3_complete,
-};
-EXPORT_SYMBOL(t10_pi_type3_crc);
-
-const struct blk_integrity_profile t10_pi_type3_ip = {
-	.name			= "T10-DIF-TYPE3-IP",
-	.generate_fn		= t10_pi_type3_generate_ip,
-	.verify_fn		= t10_pi_type3_verify_ip,
-	.prepare_fn		= t10_pi_type3_prepare,
-	.complete_fn		= t10_pi_type3_complete,
-};
-EXPORT_SYMBOL(t10_pi_type3_ip);
-
 static __be64 ext_pi_crc64(u64 crc, void *data, unsigned int len)
 {
 	return cpu_to_be64(crc64_rocksoft_update(crc, data, len));
 }
 
-static blk_status_t ext_pi_crc64_generate(struct blk_integrity_iter *iter,
-					enum t10_dif_type type)
+static void ext_pi_crc64_generate(struct blk_integrity_iter *iter,
+		struct blk_integrity *bi)
 {
-	u8 offset = iter->pi_offset;
+	u8 offset = bi->pi_offset;
 	unsigned int i;
 
 	for (i = 0 ; i < iter->data_size ; i += iter->interval) {
@@ -311,17 +229,15 @@ static blk_status_t ext_pi_crc64_generate(struct blk_integrity_iter *iter,
 					iter->prot_buf, offset);
 		pi->app_tag = 0;
 
-		if (type == T10_PI_TYPE1_PROTECTION)
+		if (bi->flags & BLK_INTEGRITY_REF_TAG)
 			put_unaligned_be48(iter->seed, pi->ref_tag);
 		else
 			put_unaligned_be48(0ULL, pi->ref_tag);
 
 		iter->data_buf += iter->interval;
-		iter->prot_buf += iter->tuple_size;
+		iter->prot_buf += bi->tuple_size;
 		iter->seed++;
 	}
-
-	return BLK_STS_OK;
 }
 
 static bool ext_pi_ref_escape(u8 *ref_tag)
@@ -332,9 +248,9 @@ static bool ext_pi_ref_escape(u8 *ref_tag)
 }
 
 static blk_status_t ext_pi_crc64_verify(struct blk_integrity_iter *iter,
-				      enum t10_dif_type type)
+		struct blk_integrity *bi)
 {
-	u8 offset = iter->pi_offset;
+	u8 offset = bi->pi_offset;
 	unsigned int i;
 
 	for (i = 0; i < iter->data_size; i += iter->interval) {
@@ -342,7 +258,7 @@ static blk_status_t ext_pi_crc64_verify(struct blk_integrity_iter *iter,
 		u64 ref, seed;
 		__be64 csum;
 
-		if (type == T10_PI_TYPE1_PROTECTION) {
+		if (bi->flags & BLK_INTEGRITY_REF_TAG) {
 			if (pi->app_tag == T10_PI_APP_ESCAPE)
 				goto next;
 
@@ -353,7 +269,7 @@ static blk_status_t ext_pi_crc64_verify(struct blk_integrity_iter *iter,
 					iter->disk_name, seed, ref);
 				return BLK_STS_PROTECTION;
 			}
-		} else if (type == T10_PI_TYPE3_PROTECTION) {
+		} else {
 			if (pi->app_tag == T10_PI_APP_ESCAPE &&
 			    ext_pi_ref_escape(pi->ref_tag))
 				goto next;
@@ -374,26 +290,16 @@ static blk_status_t ext_pi_crc64_verify(struct blk_integrity_iter *iter,
 
 next:
 		iter->data_buf += iter->interval;
-		iter->prot_buf += iter->tuple_size;
+		iter->prot_buf += bi->tuple_size;
 		iter->seed++;
 	}
 
 	return BLK_STS_OK;
 }
 
-static blk_status_t ext_pi_type1_verify_crc64(struct blk_integrity_iter *iter)
-{
-	return ext_pi_crc64_verify(iter, T10_PI_TYPE1_PROTECTION);
-}
-
-static blk_status_t ext_pi_type1_generate_crc64(struct blk_integrity_iter *iter)
-{
-	return ext_pi_crc64_generate(iter, T10_PI_TYPE1_PROTECTION);
-}
-
 static void ext_pi_type1_prepare(struct request *rq)
 {
-	struct blk_integrity *bi = &rq->q->integrity;
+	struct blk_integrity *bi = &rq->q->limits.integrity;
 	const int tuple_sz = bi->tuple_size;
 	u64 ref_tag = ext_pi_ref_tag(rq);
 	u8 offset = bi->pi_offset;
@@ -433,7 +339,7 @@ static void ext_pi_type1_prepare(struct request *rq)
 
 static void ext_pi_type1_complete(struct request *rq, unsigned int nr_bytes)
 {
-	struct blk_integrity *bi = &rq->q->integrity;
+	struct blk_integrity *bi = &rq->q->limits.integrity;
 	unsigned intervals = nr_bytes >> bi->interval_exp;
 	const int tuple_sz = bi->tuple_size;
 	u64 ref_tag = ext_pi_ref_tag(rq);
@@ -467,33 +373,105 @@ static void ext_pi_type1_complete(struct request *rq, unsigned int nr_bytes)
 	}
 }
 
-static blk_status_t ext_pi_type3_verify_crc64(struct blk_integrity_iter *iter)
+void blk_integrity_generate(struct bio *bio)
 {
-	return ext_pi_crc64_verify(iter, T10_PI_TYPE3_PROTECTION);
+	struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk);
+	struct bio_integrity_payload *bip = bio_integrity(bio);
+	struct blk_integrity_iter iter;
+	struct bvec_iter bviter;
+	struct bio_vec bv;
+
+	iter.disk_name = bio->bi_bdev->bd_disk->disk_name;
+	iter.interval = 1 << bi->interval_exp;
+	iter.seed = bio->bi_iter.bi_sector;
+	iter.prot_buf = bvec_virt(bip->bip_vec);
+	bio_for_each_segment(bv, bio, bviter) {
+		void *kaddr = bvec_kmap_local(&bv);
+
+		iter.data_buf = kaddr;
+		iter.data_size = bv.bv_len;
+		switch (bi->csum_type) {
+		case BLK_INTEGRITY_CSUM_CRC64:
+			ext_pi_crc64_generate(&iter, bi);
+			break;
+		case BLK_INTEGRITY_CSUM_CRC:
+		case BLK_INTEGRITY_CSUM_IP:
+			t10_pi_generate(&iter, bi);
+			break;
+		default:
+			break;
+		}
+		kunmap_local(kaddr);
+	}
 }
 
-static blk_status_t ext_pi_type3_generate_crc64(struct blk_integrity_iter *iter)
+void blk_integrity_verify(struct bio *bio)
 {
-	return ext_pi_crc64_generate(iter, T10_PI_TYPE3_PROTECTION);
+	struct blk_integrity *bi = blk_get_integrity(bio->bi_bdev->bd_disk);
+	struct bio_integrity_payload *bip = bio_integrity(bio);
+	struct blk_integrity_iter iter;
+	struct bvec_iter bviter;
+	struct bio_vec bv;
+
+	/*
+	 * At the moment verify is called bi_iter has been advanced during split
+	 * and completion, so use the copy created during submission here.
+	 */
+	iter.disk_name = bio->bi_bdev->bd_disk->disk_name;
+	iter.interval = 1 << bi->interval_exp;
+	iter.seed = bip->bio_iter.bi_sector;
+	iter.prot_buf = bvec_virt(bip->bip_vec);
+	__bio_for_each_segment(bv, bio, bviter, bip->bio_iter) {
+		void *kaddr = bvec_kmap_local(&bv);
+		blk_status_t ret = BLK_STS_OK;
+
+		iter.data_buf = kaddr;
+		iter.data_size = bv.bv_len;
+		switch (bi->csum_type) {
+		case BLK_INTEGRITY_CSUM_CRC64:
+			ret = ext_pi_crc64_verify(&iter, bi);
+			break;
+		case BLK_INTEGRITY_CSUM_CRC:
+		case BLK_INTEGRITY_CSUM_IP:
+			ret = t10_pi_verify(&iter, bi);
+			break;
+		default:
+			break;
+		}
+		kunmap_local(kaddr);
+
+		if (ret) {
+			bio->bi_status = ret;
+			return;
+		}
+	}
 }
 
-const struct blk_integrity_profile ext_pi_type1_crc64 = {
-	.name			= "EXT-DIF-TYPE1-CRC64",
-	.generate_fn		= ext_pi_type1_generate_crc64,
-	.verify_fn		= ext_pi_type1_verify_crc64,
-	.prepare_fn		= ext_pi_type1_prepare,
-	.complete_fn		= ext_pi_type1_complete,
-};
-EXPORT_SYMBOL_GPL(ext_pi_type1_crc64);
-
-const struct blk_integrity_profile ext_pi_type3_crc64 = {
-	.name			= "EXT-DIF-TYPE3-CRC64",
-	.generate_fn		= ext_pi_type3_generate_crc64,
-	.verify_fn		= ext_pi_type3_verify_crc64,
-	.prepare_fn		= t10_pi_type3_prepare,
-	.complete_fn		= t10_pi_type3_complete,
-};
-EXPORT_SYMBOL_GPL(ext_pi_type3_crc64);
+void blk_integrity_prepare(struct request *rq)
+{
+	struct blk_integrity *bi = &rq->q->limits.integrity;
+
+	if (!(bi->flags & BLK_INTEGRITY_REF_TAG))
+		return;
+
+	if (bi->csum_type == BLK_INTEGRITY_CSUM_CRC64)
+		ext_pi_type1_prepare(rq);
+	else
+		t10_pi_type1_prepare(rq);
+}
+
+void blk_integrity_complete(struct request *rq, unsigned int nr_bytes)
+{
+	struct blk_integrity *bi = &rq->q->limits.integrity;
+
+	if (!(bi->flags & BLK_INTEGRITY_REF_TAG))
+		return;
+
+	if (bi->csum_type == BLK_INTEGRITY_CSUM_CRC64)
+		ext_pi_type1_complete(rq, nr_bytes);
+	else
+		t10_pi_type1_complete(rq, nr_bytes);
+}
 
 MODULE_DESCRIPTION("T10 Protection Information module");
 MODULE_LICENSE("GPL");