Merge tag 'for-6.8/block-2024-01-08' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:
 "Pretty quiet round this time around. This contains:

   - NVMe updates via Keith:
        - nvme fabrics spec updates (Guixin, Max)
        - nvme target udpates (Guixin, Evan)
        - nvme attribute refactoring (Daniel)
        - nvme-fc numa fix (Keith)

   - MD updates via Song:
        - Fix/Cleanup RCU usage from conf->disks[i].rdev (Yu Kuai)
        - Fix raid5 hang issue (Junxiao Bi)
        - Add Yu Kuai as Reviewer of the md subsystem
        - Remove deprecated flavors (Song Liu)
        - raid1 read error check support (Li Nan)
        - Better handle events off-by-1 case (Alex Lyakas)

   - Efficiency improvements for passthrough (Kundan)

   - Support for mapping integrity data directly (Keith)

   - Zoned write fix (Damien)

   - rnbd fixes (Kees, Santosh, Supriti)

   - Default to a sane discard size granularity (Christoph)

   - Make the default max transfer size naming less confusing
     (Christoph)

   - Remove support for deprecated host aware zoned model (Christoph)

   - Misc fixes (me, Li, Matthew, Min, Ming, Randy, liyouhong, Daniel,
     Bart, Christoph)"

* tag 'for-6.8/block-2024-01-08' of git://git.kernel.dk/linux: (78 commits)
  block: Treat sequential write preferred zone type as invalid
  block: remove disk_clear_zoned
  sd: remove the !ZBC && blk_queue_is_zoned case in sd_read_block_characteristics
  drivers/block/xen-blkback/common.h: Fix spelling typo in comment
  blk-cgroup: fix rcu lockdep warning in blkg_lookup()
  blk-cgroup: don't use removal safe list iterators
  block: floor the discard granularity to the physical block size
  mtd_blkdevs: use the default discard granularity
  bcache: use the default discard granularity
  zram: use the default discard granularity
  null_blk: use the default discard granularity
  nbd: use the default discard granularity
  ubd: use the default discard granularity
  block: default the discard granularity to sector size
  bcache: discard_granularity should not be smaller than a sector
  block: remove two comments in bio_split_discard
  block: rename and document BLK_DEF_MAX_SECTORS
  loop: don't abuse BLK_DEF_MAX_SECTORS
  aoe: don't abuse BLK_DEF_MAX_SECTORS
  null_blk: don't cap max_hw_sectors to BLK_DEF_MAX_SECTORS
  ...

17 files changed, 320 insertions, 185 deletions

diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index ec8ac8cf6e1b..feef615e2c9c 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -69,15 +69,15 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio,
 
 	memset(bip, 0, sizeof(*bip));
 
+	/* always report as many vecs as asked explicitly, not inline vecs */
+	bip->bip_max_vcnt = nr_vecs;
 	if (nr_vecs > inline_vecs) {
-		bip->bip_max_vcnt = nr_vecs;
 		bip->bip_vec = bvec_alloc(&bs->bvec_integrity_pool,
 					  &bip->bip_max_vcnt, gfp_mask);
 		if (!bip->bip_vec)
 			goto err;
 	} else {
 		bip->bip_vec = bip->bip_inline_vecs;
-		bip->bip_max_vcnt = inline_vecs;
 	}
 
 	bip->bip_bio = bio;
@@ -91,6 +91,47 @@ err:
 }
 EXPORT_SYMBOL(bio_integrity_alloc);
 
+static void bio_integrity_unpin_bvec(struct bio_vec *bv, int nr_vecs,
+				     bool dirty)
+{
+	int i;
+
+	for (i = 0; i < nr_vecs; i++) {
+		if (dirty && !PageCompound(bv[i].bv_page))
+			set_page_dirty_lock(bv[i].bv_page);
+		unpin_user_page(bv[i].bv_page);
+	}
+}
+
+static void bio_integrity_uncopy_user(struct bio_integrity_payload *bip)
+{
+	unsigned short nr_vecs = bip->bip_max_vcnt - 1;
+	struct bio_vec *copy = &bip->bip_vec[1];
+	size_t bytes = bip->bip_iter.bi_size;
+	struct iov_iter iter;
+	int ret;
+
+	iov_iter_bvec(&iter, ITER_DEST, copy, nr_vecs, bytes);
+	ret = copy_to_iter(bvec_virt(bip->bip_vec), bytes, &iter);
+	WARN_ON_ONCE(ret != bytes);
+
+	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
@@ -105,6 +146,8 @@ void bio_integrity_free(struct bio *bio)
 
 	if (bip->bip_flags & BIP_BLOCK_INTEGRITY)
 		kfree(bvec_virt(bip->bip_vec));
+	else if (bip->bip_flags & BIP_INTEGRITY_USER)
+		bio_integrity_unmap_user(bip);
 
 	__bio_integrity_free(bs, bip);
 	bio->bi_integrity = NULL;
@@ -160,6 +203,177 @@ int bio_integrity_add_page(struct bio *bio, struct page *page,
 }
 EXPORT_SYMBOL(bio_integrity_add_page);
 
+static int bio_integrity_copy_user(struct bio *bio, struct bio_vec *bvec,
+				   int nr_vecs, unsigned int len,
+				   unsigned int direction, u32 seed)
+{
+	bool write = direction == ITER_SOURCE;
+	struct bio_integrity_payload *bip;
+	struct iov_iter iter;
+	void *buf;
+	int ret;
+
+	buf = kmalloc(len, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	if (write) {
+		iov_iter_bvec(&iter, direction, bvec, nr_vecs, len);
+		if (!copy_from_iter_full(buf, len, &iter)) {
+			ret = -EFAULT;
+			goto free_buf;
+		}
+
+		bip = bio_integrity_alloc(bio, GFP_KERNEL, 1);
+	} else {
+		memset(buf, 0, len);
+
+		/*
+		 * We need to preserve the original bvec and the number of vecs
+		 * in it for completion handling
+		 */
+		bip = bio_integrity_alloc(bio, GFP_KERNEL, nr_vecs + 1);
+	}
+
+	if (IS_ERR(bip)) {
+		ret = PTR_ERR(bip);
+		goto free_buf;
+	}
+
+	if (write)
+		bio_integrity_unpin_bvec(bvec, nr_vecs, false);
+	else
+		memcpy(&bip->bip_vec[1], bvec, nr_vecs * sizeof(*bvec));
+
+	ret = bio_integrity_add_page(bio, virt_to_page(buf), len,
+				     offset_in_page(buf));
+	if (ret != len) {
+		ret = -ENOMEM;
+		goto free_bip;
+	}
+
+	bip->bip_flags |= BIP_INTEGRITY_USER | BIP_COPY_USER;
+	bip->bip_iter.bi_sector = seed;
+	return 0;
+free_bip:
+	bio_integrity_free(bio);
+free_buf:
+	kfree(buf);
+	return ret;
+}
+
+static int bio_integrity_init_user(struct bio *bio, struct bio_vec *bvec,
+				   int nr_vecs, unsigned int len, u32 seed)
+{
+	struct bio_integrity_payload *bip;
+
+	bip = bio_integrity_alloc(bio, GFP_KERNEL, nr_vecs);
+	if (IS_ERR(bip))
+		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;
+	return 0;
+}
+
+static unsigned int bvec_from_pages(struct bio_vec *bvec, struct page **pages,
+				    int nr_vecs, ssize_t bytes, ssize_t offset)
+{
+	unsigned int nr_bvecs = 0;
+	int i, j;
+
+	for (i = 0; i < nr_vecs; i = j) {
+		size_t size = min_t(size_t, bytes, PAGE_SIZE - offset);
+		struct folio *folio = page_folio(pages[i]);
+
+		bytes -= size;
+		for (j = i + 1; j < nr_vecs; j++) {
+			size_t next = min_t(size_t, PAGE_SIZE, bytes);
+
+			if (page_folio(pages[j]) != folio ||
+			    pages[j] != pages[j - 1] + 1)
+				break;
+			unpin_user_page(pages[j]);
+			size += next;
+			bytes -= next;
+		}
+
+		bvec_set_page(&bvec[nr_bvecs], pages[i], size, offset);
+		offset = 0;
+		nr_bvecs++;
+	}
+
+	return nr_bvecs;
+}
+
+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);
+	struct page *stack_pages[UIO_FASTIOV], **pages = stack_pages;
+	struct bio_vec stack_vec[UIO_FASTIOV], *bvec = stack_vec;
+	unsigned int direction, nr_bvecs;
+	struct iov_iter iter;
+	int ret, nr_vecs;
+	size_t offset;
+	bool copy;
+
+	if (bio_integrity(bio))
+		return -EINVAL;
+	if (bytes >> SECTOR_SHIFT > queue_max_hw_sectors(q))
+		return -E2BIG;
+
+	if (bio_data_dir(bio) == READ)
+		direction = ITER_DEST;
+	else
+		direction = ITER_SOURCE;
+
+	iov_iter_ubuf(&iter, direction, ubuf, bytes);
+	nr_vecs = iov_iter_npages(&iter, BIO_MAX_VECS + 1);
+	if (nr_vecs > BIO_MAX_VECS)
+		return -E2BIG;
+	if (nr_vecs > UIO_FASTIOV) {
+		bvec = kcalloc(sizeof(*bvec), nr_vecs, GFP_KERNEL);
+		if (!bvec)
+			return -ENOMEM;
+		pages = NULL;
+	}
+
+	copy = !iov_iter_is_aligned(&iter, align, align);
+	ret = iov_iter_extract_pages(&iter, &pages, bytes, nr_vecs, 0, &offset);
+	if (unlikely(ret < 0))
+		goto free_bvec;
+
+	nr_bvecs = bvec_from_pages(bvec, pages, nr_vecs, bytes, offset);
+	if (pages != stack_pages)
+		kvfree(pages);
+	if (nr_bvecs > queue_max_integrity_segments(q))
+		copy = true;
+
+	if (copy)
+		ret = bio_integrity_copy_user(bio, bvec, nr_bvecs, bytes,
+					      direction, seed);
+	else
+		ret = bio_integrity_init_user(bio, bvec, nr_bvecs, bytes, seed);
+	if (ret)
+		goto release_pages;
+	if (bvec != stack_vec)
+		kfree(bvec);
+
+	return 0;
+
+release_pages:
+	bio_integrity_unpin_bvec(bvec, nr_bvecs, false);
+free_bvec:
+	if (bvec != stack_vec)
+		kfree(bvec);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(bio_integrity_map_user);
+
 /**
  * bio_integrity_process - Process integrity metadata for a bio
  * @bio:	bio to generate/verify integrity metadata for
diff --git a/block/bio.c b/block/bio.c
index 816d412c06e9..b9642a41f286 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -944,7 +944,7 @@ bool bvec_try_merge_hw_page(struct request_queue *q, struct bio_vec *bv,
 
 	if ((addr1 | mask) != (addr2 | mask))
 		return false;
-	if (bv->bv_len + len > queue_max_segment_size(q))
+	if (len > queue_max_segment_size(q) - bv->bv_len)
 		return false;
 	return bvec_try_merge_page(bv, page, len, offset, same_page);
 }
@@ -966,10 +966,13 @@ int bio_add_hw_page(struct request_queue *q, struct bio *bio,
 		struct page *page, unsigned int len, unsigned int offset,
 		unsigned int max_sectors, bool *same_page)
 {
+	unsigned int max_size = max_sectors << SECTOR_SHIFT;
+
 	if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)))
 		return 0;
 
-	if (((bio->bi_iter.bi_size + len) >> SECTOR_SHIFT) > max_sectors)
+	len = min3(len, max_size, queue_max_segment_size(q));
+	if (len > max_size - bio->bi_iter.bi_size)
 		return 0;
 
 	if (bio->bi_vcnt > 0) {
@@ -1145,13 +1148,22 @@ EXPORT_SYMBOL(bio_add_folio);
 
 void __bio_release_pages(struct bio *bio, bool mark_dirty)
 {
-	struct bvec_iter_all iter_all;
-	struct bio_vec *bvec;
+	struct folio_iter fi;
 
-	bio_for_each_segment_all(bvec, bio, iter_all) {
-		if (mark_dirty && !PageCompound(bvec->bv_page))
-			set_page_dirty_lock(bvec->bv_page);
-		bio_release_page(bio, bvec->bv_page);
+	bio_for_each_folio_all(fi, bio) {
+		struct page *page;
+		size_t done = 0;
+
+		if (mark_dirty) {
+			folio_lock(fi.folio);
+			folio_mark_dirty(fi.folio);
+			folio_unlock(fi.folio);
+		}
+		page = folio_page(fi.folio, fi.offset / PAGE_SIZE);
+		do {
+			bio_release_page(bio, page++);
+			done += PAGE_SIZE;
+		} while (done < fi.length);
 	}
 }
 EXPORT_SYMBOL_GPL(__bio_release_pages);
@@ -1439,18 +1451,12 @@ EXPORT_SYMBOL(bio_free_pages);
  * bio_set_pages_dirty() and bio_check_pages_dirty() are support functions
  * for performing direct-IO in BIOs.
  *
- * The problem is that we cannot run set_page_dirty() from interrupt context
+ * The problem is that we cannot run folio_mark_dirty() from interrupt context
  * because the required locks are not interrupt-safe.  So what we can do is to
  * mark the pages dirty _before_ performing IO.  And in interrupt context,
  * check that the pages are still dirty.   If so, fine.  If not, redirty them
  * in process context.
  *
- * We special-case compound pages here: normally this means reads into hugetlb
- * pages.  The logic in here doesn't really work right for compound pages
- * because the VM does not uniformly chase down the head page in all cases.
- * But dirtiness of compound pages is pretty meaningless anyway: the VM doesn't
- * handle them at all.  So we skip compound pages here at an early stage.
- *
  * Note that this code is very hard to test under normal circumstances because
  * direct-io pins the pages with get_user_pages().  This makes
  * is_page_cache_freeable return false, and the VM will not clean the pages.
@@ -1466,12 +1472,12 @@ EXPORT_SYMBOL(bio_free_pages);
  */
 void bio_set_pages_dirty(struct bio *bio)
 {
-	struct bio_vec *bvec;
-	struct bvec_iter_all iter_all;
+	struct folio_iter fi;
 
-	bio_for_each_segment_all(bvec, bio, iter_all) {
-		if (!PageCompound(bvec->bv_page))
-			set_page_dirty_lock(bvec->bv_page);
+	bio_for_each_folio_all(fi, bio) {
+		folio_lock(fi.folio);
+		folio_mark_dirty(fi.folio);
+		folio_unlock(fi.folio);
 	}
 }
 EXPORT_SYMBOL_GPL(bio_set_pages_dirty);
@@ -1515,12 +1521,11 @@ static void bio_dirty_fn(struct work_struct *work)
 
 void bio_check_pages_dirty(struct bio *bio)
 {
-	struct bio_vec *bvec;
+	struct folio_iter fi;
 	unsigned long flags;
-	struct bvec_iter_all iter_all;
 
-	bio_for_each_segment_all(bvec, bio, iter_all) {
-		if (!PageDirty(bvec->bv_page) && !PageCompound(bvec->bv_page))
+	bio_for_each_folio_all(fi, bio) {
+		if (!folio_test_dirty(fi.folio))
 			goto defer;
 	}
 
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 4b48c2c44098..e303fd317313 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -575,13 +575,13 @@ static void blkg_destroy(struct blkcg_gq *blkg)
 static void blkg_destroy_all(struct gendisk *disk)
 {
 	struct request_queue *q = disk->queue;
-	struct blkcg_gq *blkg, *n;
+	struct blkcg_gq *blkg;
 	int count = BLKG_DESTROY_BATCH_SIZE;
 	int i;
 
 restart:
 	spin_lock_irq(&q->queue_lock);
-	list_for_each_entry_safe(blkg, n, &q->blkg_list, q_node) {
+	list_for_each_entry(blkg, &q->blkg_list, q_node) {
 		struct blkcg *blkcg = blkg->blkcg;
 
 		if (hlist_unhashed(&blkg->blkcg_node))
@@ -2064,6 +2064,9 @@ void bio_associate_blkg(struct bio *bio)
 {
 	struct cgroup_subsys_state *css;
 
+	if (blk_op_is_passthrough(bio->bi_opf))
+		return;
+
 	rcu_read_lock();
 
 	if (bio->bi_blkg)
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index fd482439afbc..b927a4a0ad03 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -252,7 +252,8 @@ static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg,
 	if (blkcg == &blkcg_root)
 		return q->root_blkg;
 
-	blkg = rcu_dereference(blkcg->blkg_hint);
+	blkg = rcu_dereference_check(blkcg->blkg_hint,
+			lockdep_is_held(&q->queue_lock));
 	if (blkg && blkg->q == q)
 		return blkg;
 
diff --git a/block/blk-core.c b/block/blk-core.c
index 2eca76ccf4ee..11342af420d0 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -772,6 +772,15 @@ void submit_bio_noacct(struct bio *bio)
 		bio_clear_polled(bio);
 
 	switch (bio_op(bio)) {
+	case REQ_OP_READ:
+	case REQ_OP_WRITE:
+		break;
+	case REQ_OP_FLUSH:
+		/*
+		 * REQ_OP_FLUSH can't be submitted through bios, it is only
+		 * synthetized in struct request by the flush state machine.
+		 */
+		goto not_supported;
 	case REQ_OP_DISCARD:
 		if (!bdev_max_discard_sectors(bdev))
 			goto not_supported;
@@ -785,6 +794,10 @@ void submit_bio_noacct(struct bio *bio)
 		if (status != BLK_STS_OK)
 			goto end_io;
 		break;
+	case REQ_OP_WRITE_ZEROES:
+		if (!q->limits.max_write_zeroes_sectors)
+			goto not_supported;
+		break;
 	case REQ_OP_ZONE_RESET:
 	case REQ_OP_ZONE_OPEN:
 	case REQ_OP_ZONE_CLOSE:
@@ -796,12 +809,15 @@ void submit_bio_noacct(struct bio *bio)
 		if (!bdev_is_zoned(bio->bi_bdev) || !blk_queue_zone_resetall(q))
 			goto not_supported;
 		break;
-	case REQ_OP_WRITE_ZEROES:
-		if (!q->limits.max_write_zeroes_sectors)
-			goto not_supported;
-		break;
+	case REQ_OP_DRV_IN:
+	case REQ_OP_DRV_OUT:
+		/*
+		 * Driver private operations are only used with passthrough
+		 * requests.
+		 */
+		fallthrough;
 	default:
-		break;
+		goto not_supported;
 	}
 
 	if (blk_throtl_bio(bio))
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 65e75efa9bd3..2d470cf2173e 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -115,17 +115,13 @@ static struct bio *bio_split_discard(struct bio *bio,
 
 	*nsegs = 1;
 
-	/* Zero-sector (unknown) and one-sector granularities are the same.  */
 	granularity = max(lim->discard_granularity >> 9, 1U);
 
 	max_discard_sectors =
 		min(lim->max_discard_sectors, bio_allowed_max_sectors(lim));
 	max_discard_sectors -= max_discard_sectors % granularity;
-
-	if (unlikely(!max_discard_sectors)) {
-		/* XXX: warn */
+	if (unlikely(!max_discard_sectors))
 		return NULL;
-	}
 
 	if (bio_sectors(bio) <= max_discard_sectors)
 		return NULL;
diff --git a/block/blk-mq.c b/block/blk-mq.c
index ac18f802c027..c11c97afa0bc 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1248,7 +1248,8 @@ void blk_mq_start_request(struct request *rq)
 
 	trace_block_rq_issue(rq);
 
-	if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) {
+	if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags) &&
+	    !blk_rq_is_passthrough(rq)) {
 		rq->io_start_time_ns = ktime_get_ns();
 		rq->stats_sectors = blk_rq_sectors(rq);
 		rq->rq_flags |= RQF_STATS;
diff --git a/block/blk-rq-qos.h b/block/blk-rq-qos.h
index f48ee150d667..37245c97ee61 100644
--- a/block/blk-rq-qos.h
+++ b/block/blk-rq-qos.h
@@ -118,7 +118,7 @@ static inline void rq_qos_cleanup(struct request_queue *q, struct bio *bio)
 
 static inline void rq_qos_done(struct request_queue *q, struct request *rq)
 {
-	if (q->rq_qos)
+	if (q->rq_qos && !blk_rq_is_passthrough(rq))
 		__rq_qos_done(q->rq_qos, rq);
 }
 
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 0046b447268f..06ea91e51b8b 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -48,7 +48,7 @@ void blk_set_default_limits(struct queue_limits *lim)
 	lim->max_discard_sectors = 0;
 	lim->max_hw_discard_sectors = 0;
 	lim->max_secure_erase_sectors = 0;
-	lim->discard_granularity = 0;
+	lim->discard_granularity = 512;
 	lim->discard_alignment = 0;
 	lim->discard_misaligned = 0;
 	lim->logical_block_size = lim->physical_block_size = lim->io_min = 512;
@@ -56,7 +56,7 @@ void blk_set_default_limits(struct queue_limits *lim)
 	lim->alignment_offset = 0;
 	lim->io_opt = 0;
 	lim->misaligned = 0;
-	lim->zoned = BLK_ZONED_NONE;
+	lim->zoned = false;
 	lim->zone_write_granularity = 0;
 	lim->dma_alignment = 511;
 }
@@ -127,8 +127,7 @@ void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_secto
 
 	if ((max_hw_sectors << 9) < PAGE_SIZE) {
 		max_hw_sectors = 1 << (PAGE_SHIFT - 9);
-		printk(KERN_INFO "%s: set to minimum %d\n",
-		       __func__, max_hw_sectors);
+		pr_info("%s: set to minimum %u\n", __func__, max_hw_sectors);
 	}
 
 	max_hw_sectors = round_down(max_hw_sectors,
@@ -140,7 +139,7 @@ void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_secto
 	if (limits->max_user_sectors)
 		max_sectors = min(max_sectors, limits->max_user_sectors);
 	else
-		max_sectors = min(max_sectors, BLK_DEF_MAX_SECTORS);
+		max_sectors = min(max_sectors, BLK_DEF_MAX_SECTORS_CAP);
 
 	max_sectors = round_down(max_sectors,
 				 limits->logical_block_size >> SECTOR_SHIFT);
@@ -248,8 +247,7 @@ void blk_queue_max_segments(struct request_queue *q, unsigned short max_segments
 {
 	if (!max_segments) {
 		max_segments = 1;
-		printk(KERN_INFO "%s: set to minimum %d\n",
-		       __func__, max_segments);
+		pr_info("%s: set to minimum %u\n", __func__, max_segments);
 	}
 
 	q->limits.max_segments = max_segments;
@@ -285,8 +283,7 @@ void blk_queue_max_segment_size(struct request_queue *q, unsigned int max_size)
 {
 	if (max_size < PAGE_SIZE) {
 		max_size = PAGE_SIZE;
-		printk(KERN_INFO "%s: set to minimum %d\n",
-		       __func__, max_size);
+		pr_info("%s: set to minimum %u\n", __func__, max_size);
 	}
 
 	/* see blk_queue_virt_boundary() for the explanation */
@@ -312,6 +309,9 @@ void blk_queue_logical_block_size(struct request_queue *q, unsigned int size)
 
 	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;
 
@@ -342,6 +342,9 @@ void blk_queue_physical_block_size(struct request_queue *q, unsigned int 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;
 }
@@ -740,8 +743,7 @@ void blk_queue_segment_boundary(struct request_queue *q, unsigned long mask)
 {
 	if (mask < PAGE_SIZE - 1) {
 		mask = PAGE_SIZE - 1;
-		printk(KERN_INFO "%s: set to minimum %lx\n",
-		       __func__, mask);
+		pr_info("%s: set to minimum %lx\n", __func__, mask);
 	}
 
 	q->limits.seg_boundary_mask = mask;
@@ -841,8 +843,6 @@ void blk_queue_write_cache(struct request_queue *q, bool wc, bool fua)
 		blk_queue_flag_set(QUEUE_FLAG_FUA, q);
 	else
 		blk_queue_flag_clear(QUEUE_FLAG_FUA, q);
-
-	wbt_set_write_cache(q, test_bit(QUEUE_FLAG_WC, &q->queue_flags));
 }
 EXPORT_SYMBOL_GPL(blk_queue_write_cache);
 
@@ -884,81 +884,22 @@ bool blk_queue_can_use_dma_map_merging(struct request_queue *q,
 }
 EXPORT_SYMBOL_GPL(blk_queue_can_use_dma_map_merging);
 
-static bool disk_has_partitions(struct gendisk *disk)
-{
-	unsigned long idx;
-	struct block_device *part;
-	bool ret = false;
-
-	rcu_read_lock();
-	xa_for_each(&disk->part_tbl, idx, part) {
-		if (bdev_is_partition(part)) {
-			ret = true;
-			break;
-		}
-	}
-	rcu_read_unlock();
-
-	return ret;
-}
-
 /**
- * disk_set_zoned - configure the zoned model for a disk
- * @disk:	the gendisk of the queue to configure
- * @model:	the zoned model to set
- *
- * Set the zoned model of @disk to @model.
- *
- * When @model is BLK_ZONED_HM (host managed), this should be called only
- * if zoned block device support is enabled (CONFIG_BLK_DEV_ZONED option).
- * If @model specifies BLK_ZONED_HA (host aware), the effective model used
- * depends on CONFIG_BLK_DEV_ZONED settings and on the existence of partitions
- * on the disk.
+ * disk_set_zoned - inidicate a zoned device
+ * @disk:	gendisk to configure
  */
-void disk_set_zoned(struct gendisk *disk, enum blk_zoned_model model)
+void disk_set_zoned(struct gendisk *disk)
 {
 	struct request_queue *q = disk->queue;
-	unsigned int old_model = q->limits.zoned;
-
-	switch (model) {
-	case BLK_ZONED_HM:
-		/*
-		 * Host managed devices are supported only if
-		 * CONFIG_BLK_DEV_ZONED is enabled.
-		 */
-		WARN_ON_ONCE(!IS_ENABLED(CONFIG_BLK_DEV_ZONED));
-		break;
-	case BLK_ZONED_HA:
-		/*
-		 * Host aware devices can be treated either as regular block
-		 * devices (similar to drive managed devices) or as zoned block
-		 * devices to take advantage of the zone command set, similarly
-		 * to host managed devices. We try the latter if there are no
-		 * partitions and zoned block device support is enabled, else
-		 * we do nothing special as far as the block layer is concerned.
-		 */
-		if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED) ||
-		    disk_has_partitions(disk))
-			model = BLK_ZONED_NONE;
-		break;
-	case BLK_ZONED_NONE:
-	default:
-		if (WARN_ON_ONCE(model != BLK_ZONED_NONE))
-			model = BLK_ZONED_NONE;
-		break;
-	}
 
-	q->limits.zoned = model;
-	if (model != BLK_ZONED_NONE) {
-		/*
-		 * Set the zone write granularity to the device logical block
-		 * size by default. The driver can change this value if needed.
-		 */
-		blk_queue_zone_write_granularity(q,
-						queue_logical_block_size(q));
-	} else if (old_model != BLK_ZONED_NONE) {
-		disk_clear_zone_settings(disk);
-	}
+	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);
 
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 0b2d04766324..6b2429cad81a 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -241,7 +241,7 @@ queue_max_sectors_store(struct request_queue *q, const char *page, size_t count)
 	if (max_sectors_kb == 0) {
 		q->limits.max_user_sectors = 0;
 		max_sectors_kb = min(max_hw_sectors_kb,
-				     BLK_DEF_MAX_SECTORS >> 1);
+				     BLK_DEF_MAX_SECTORS_CAP >> 1);
 	} else {
 		if (max_sectors_kb > max_hw_sectors_kb ||
 		    max_sectors_kb < page_kb)
@@ -309,14 +309,9 @@ QUEUE_SYSFS_BIT_FNS(stable_writes, STABLE_WRITES, 0);
 
 static ssize_t queue_zoned_show(struct request_queue *q, char *page)
 {
-	switch (blk_queue_zoned_model(q)) {
-	case BLK_ZONED_HA:
-		return sprintf(page, "host-aware\n");
-	case BLK_ZONED_HM:
+	if (blk_queue_is_zoned(q))
 		return sprintf(page, "host-managed\n");
-	default:
-		return sprintf(page, "none\n");
-	}
+	return sprintf(page, "none\n");
 }
 
 static ssize_t queue_nr_zones_show(struct request_queue *q, char *page)
diff --git a/block/blk-wbt.c b/block/blk-wbt.c
index 0bb613139bec..5ba3cd574eac 100644
--- a/block/blk-wbt.c
+++ b/block/blk-wbt.c
@@ -84,8 +84,6 @@ struct rq_wb {
 	u64 sync_issue;
 	void *sync_cookie;
 
-	unsigned int wc;
-
 	unsigned long last_issue;		/* last non-throttled issue */
 	unsigned long last_comp;		/* last non-throttled comp */
 	unsigned long min_lat_nsec;
@@ -207,7 +205,8 @@ static void wbt_rqw_done(struct rq_wb *rwb, struct rq_wait *rqw,
 	 */
 	if (wb_acct & WBT_DISCARD)
 		limit = rwb->wb_background;
-	else if (rwb->wc && !wb_recent_wait(rwb))
+	else if (test_bit(QUEUE_FLAG_WC, &rwb->rqos.disk->queue->queue_flags) &&
+	         !wb_recent_wait(rwb))
 		limit = 0;
 	else
 		limit = rwb->wb_normal;
@@ -699,13 +698,6 @@ static void wbt_requeue(struct rq_qos *rqos, struct request *rq)
 	}
 }
 
-void wbt_set_write_cache(struct request_queue *q, bool write_cache_on)
-{
-	struct rq_qos *rqos = wbt_rq_qos(q);
-	if (rqos)
-		RQWB(rqos)->wc = write_cache_on;
-}
-
 /*
  * Enable wbt if defaults are configured that way
  */
@@ -918,7 +910,6 @@ int wbt_init(struct gendisk *disk)
 	rwb->last_comp = rwb->last_issue = jiffies;
 	rwb->win_nsec = RWB_WINDOW_NSEC;
 	rwb->enable_state = WBT_STATE_ON_DEFAULT;
-	rwb->wc = test_bit(QUEUE_FLAG_WC, &q->queue_flags);
 	rwb->rq_depth.default_depth = RWB_DEF_DEPTH;
 	rwb->min_lat_nsec = wbt_default_latency_nsec(q);
 	rwb->rq_depth.queue_depth = blk_queue_depth(q);
diff --git a/block/blk-wbt.h b/block/blk-wbt.h
index 8a029e138f7a..e5fc653b9b76 100644
--- a/block/blk-wbt.h
+++ b/block/blk-wbt.h
@@ -12,8 +12,6 @@ u64 wbt_get_min_lat(struct request_queue *q);
 void wbt_set_min_lat(struct request_queue *q, u64 val);
 bool wbt_disabled(struct request_queue *);
 
-void wbt_set_write_cache(struct request_queue *, bool);
-
 u64 wbt_default_latency_nsec(struct request_queue *);
 
 #else
@@ -24,9 +22,6 @@ static inline void wbt_disable_default(struct gendisk *disk)
 static inline void wbt_enable_default(struct gendisk *disk)
 {
 }
-static inline void wbt_set_write_cache(struct request_queue *q, bool wc)
-{
-}
 
 #endif /* CONFIG_BLK_WBT */
 
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 619ee41a51cc..d343e5756a9c 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -498,7 +498,6 @@ static int blk_revalidate_zone_cb(struct blk_zone *zone, unsigned int idx,
 		set_bit(idx, args->conv_zones_bitmap);
 		break;
 	case BLK_ZONE_TYPE_SEQWRITE_REQ:
-	case BLK_ZONE_TYPE_SEQWRITE_PREF:
 		if (!args->seq_zones_wlock) {
 			args->seq_zones_wlock =
 				blk_alloc_zone_bitmap(q->node, args->nr_zones);
@@ -506,6 +505,7 @@ static int blk_revalidate_zone_cb(struct blk_zone *zone, unsigned int idx,
 				return -ENOMEM;
 		}
 		break;
+	case BLK_ZONE_TYPE_SEQWRITE_PREF:
 	default:
 		pr_warn("%s: Invalid zone type 0x%x at sectors %llu\n",
 			disk->disk_name, (int)zone->type, zone->start);
@@ -615,22 +615,3 @@ int blk_revalidate_disk_zones(struct gendisk *disk,
 	return ret;
 }
 EXPORT_SYMBOL_GPL(blk_revalidate_disk_zones);
-
-void disk_clear_zone_settings(struct gendisk *disk)
-{
-	struct request_queue *q = disk->queue;
-
-	blk_mq_freeze_queue(q);
-
-	disk_free_zone_bitmaps(disk);
-	blk_queue_flag_clear(QUEUE_FLAG_ZONE_RESETALL, q);
-	q->required_elevator_features &= ~ELEVATOR_F_ZBD_SEQ_WRITE;
-	disk->nr_zones = 0;
-	disk->max_open_zones = 0;
-	disk->max_active_zones = 0;
-	q->limits.chunk_sectors = 0;
-	q->limits.zone_write_granularity = 0;
-	q->limits.max_zone_append_sectors = 0;
-
-	blk_mq_unfreeze_queue(q);
-}
diff --git a/block/blk.h b/block/blk.h
index 08a358bc0919..1ef920f72e0f 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -395,14 +395,12 @@ static inline struct bio *blk_queue_bounce(struct bio *bio,
 
 #ifdef CONFIG_BLK_DEV_ZONED
 void disk_free_zone_bitmaps(struct gendisk *disk);
-void disk_clear_zone_settings(struct gendisk *disk);
 int blkdev_report_zones_ioctl(struct block_device *bdev, unsigned int cmd,
 		unsigned long arg);
 int blkdev_zone_mgmt_ioctl(struct block_device *bdev, blk_mode_t mode,
 		unsigned int cmd, unsigned long arg);
 #else /* CONFIG_BLK_DEV_ZONED */
 static inline void disk_free_zone_bitmaps(struct gendisk *disk) {}
-static inline void disk_clear_zone_settings(struct gendisk *disk) {}
 static inline int blkdev_report_zones_ioctl(struct block_device *bdev,
 		unsigned int cmd, unsigned long arg)
 {
diff --git a/block/genhd.c b/block/genhd.c
index c9d06f72c587..d74fb5b4ae68 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -432,7 +432,9 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk,
 				DISK_MAX_PARTS);
 			disk->minors = DISK_MAX_PARTS;
 		}
-		if (disk->first_minor + disk->minors > MINORMASK + 1)
+		if (disk->first_minor > MINORMASK ||
+		    disk->minors > MINORMASK + 1 ||
+		    disk->first_minor + disk->minors > MINORMASK + 1)
 			goto out_exit_elevator;
 	} else {
 		if (WARN_ON(disk->minors))
@@ -542,6 +544,7 @@ out_put_holder_dir:
 	kobject_put(disk->part0->bd_holder_dir);
 out_del_block_link:
 	sysfs_remove_link(block_depr, dev_name(ddev));
+	pm_runtime_set_memalloc_noio(ddev, false);
 out_device_del:
 	device_del(ddev);
 out_free_ext_minor:
diff --git a/block/ioctl.c b/block/ioctl.c
index 4160f4e6bd5b..9c73a763ef88 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -18,7 +18,7 @@ static int blkpg_do_ioctl(struct block_device *bdev,
 {
 	struct gendisk *disk = bdev->bd_disk;
 	struct blkpg_partition p;
-	long long start, length;
+	sector_t start, length;
 
 	if (disk->flags & GENHD_FL_NO_PART)
 		return -EINVAL;
@@ -35,14 +35,17 @@ static int blkpg_do_ioctl(struct block_device *bdev,
 	if (op == BLKPG_DEL_PARTITION)
 		return bdev_del_partition(disk, p.pno);
 
+	if (p.start < 0 || p.length <= 0 || p.start + p.length < 0)
+		return -EINVAL;
+	/* Check that the partition is aligned to the block size */
+	if (!IS_ALIGNED(p.start | p.length, bdev_logical_block_size(bdev)))
+		return -EINVAL;
+
 	start = p.start >> SECTOR_SHIFT;
 	length = p.length >> SECTOR_SHIFT;
 
 	switch (op) {
 	case BLKPG_ADD_PARTITION:
-		/* check if partition is aligned to blocksize */
-		if (p.start & (bdev_logical_block_size(bdev) - 1))
-			return -EINVAL;
 		return bdev_add_partition(disk, p.pno, start, length);
 	case BLKPG_RESIZE_PARTITION:
 		return bdev_resize_partition(disk, p.pno, start, length);
diff --git a/block/partitions/core.c b/block/partitions/core.c
index f47ffcfdfcec..e6ac73617f3e 100644
--- a/block/partitions/core.c
+++ b/block/partitions/core.c
@@ -305,18 +305,10 @@ static struct block_device *add_partition(struct gendisk *disk, int partno,
 	 * Partitions are not supported on zoned block devices that are used as
 	 * such.
 	 */
-	switch (disk->queue->limits.zoned) {
-	case BLK_ZONED_HM:
+	if (bdev_is_zoned(disk->part0)) {
 		pr_warn("%s: partitions not supported on host managed zoned block device\n",
 			disk->disk_name);
 		return ERR_PTR(-ENXIO);
-	case BLK_ZONED_HA:
-		pr_info("%s: disabling host aware zoned block device support due to partitions\n",
-			disk->disk_name);
-		disk_set_zoned(disk, BLK_ZONED_NONE);
-		break;
-	case BLK_ZONED_NONE:
-		break;
 	}
 
 	if (xa_load(&disk->part_tbl, partno))
@@ -613,7 +605,7 @@ static int blk_add_partitions(struct gendisk *disk)
 	/*
 	 * Partitions are not supported on host managed zoned block devices.
 	 */
-	if (disk->queue->limits.zoned == BLK_ZONED_HM) {
+	if (bdev_is_zoned(disk->part0)) {
 		pr_warn("%s: ignoring partition table on host managed zoned block device\n",
 			disk->disk_name);
 		ret = 0;