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
  ...

79 files changed, 1254 insertions, 2660 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index 3a3db42fff2a..81f6b37e82c8 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -20079,6 +20079,7 @@ F:	include/linux/property.h
 
 SOFTWARE RAID (Multiple Disks) SUPPORT
 M:	Song Liu <song@kernel.org>
+R:	Yu Kuai <yukuai3@huawei.com>
 L:	linux-raid@vger.kernel.org
 S:	Supported
 Q:	https://patchwork.kernel.org/project/linux-raid/list/
diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index 50206feac577..92ee2697ff39 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -798,7 +798,6 @@ static int ubd_open_dev(struct ubd *ubd_dev)
 		ubd_dev->cow.fd = err;
 	}
 	if (ubd_dev->no_trim == 0) {
-		ubd_dev->queue->limits.discard_granularity = SECTOR_SIZE;
 		blk_queue_max_discard_sectors(ubd_dev->queue, UBD_MAX_REQUEST);
 		blk_queue_max_write_zeroes_sectors(ubd_dev->queue, UBD_MAX_REQUEST);
 	}
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)) {