Merge tag 'for-6.6/block-2023-08-28' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:
 "Pretty quiet round for this release. This contains:

   - Add support for zoned storage to ublk (Andreas, Ming)

   - Series improving performance for drivers that mark themselves as
     needing a blocking context for issue (Bart)

   - Cleanup the flush logic (Chengming)

   - sed opal keyring support (Greg)

   - Fixes and improvements to the integrity support (Jinyoung)

   - Add some exports for bcachefs that we can hopefully delete again in
     the future (Kent)

   - deadline throttling fix (Zhiguo)

   - Series allowing building the kernel without buffer_head support
     (Christoph)

   - Sanitize the bio page adding flow (Christoph)

   - Write back cache fixes (Christoph)

   - MD updates via Song:
      - Fix perf regression for raid0 large sequential writes (Jan)
      - Fix split bio iostat for raid0 (David)
      - Various raid1 fixes (Heinz, Xueshi)
      - raid6test build fixes (WANG)
      - Deprecate bitmap file support (Christoph)
      - Fix deadlock with md sync thread (Yu)
      - Refactor md io accounting (Yu)
      - Various non-urgent fixes (Li, Yu, Jack)

   - Various fixes and cleanups (Arnd, Azeem, Chengming, Damien, Li,
     Ming, Nitesh, Ruan, Tejun, Thomas, Xu)"

* tag 'for-6.6/block-2023-08-28' of git://git.kernel.dk/linux: (113 commits)
  block: use strscpy() to instead of strncpy()
  block: sed-opal: keyring support for SED keys
  block: sed-opal: Implement IOC_OPAL_REVERT_LSP
  block: sed-opal: Implement IOC_OPAL_DISCOVERY
  blk-mq: prealloc tags when increase tagset nr_hw_queues
  blk-mq: delete redundant tagset map update when fallback
  blk-mq: fix tags leak when shrink nr_hw_queues
  ublk: zoned: support REQ_OP_ZONE_RESET_ALL
  md: raid0: account for split bio in iostat accounting
  md/raid0: Fix performance regression for large sequential writes
  md/raid0: Factor out helper for mapping and submitting a bio
  md raid1: allow writebehind to work on any leg device set WriteMostly
  md/raid1: hold the barrier until handle_read_error() finishes
  md/raid1: free the r1bio before waiting for blocked rdev
  md/raid1: call free_r1bio() before allow_barrier() in raid_end_bio_io()
  blk-cgroup: Fix NULL deref caused by blkg_policy_data being installed before init
  drivers/rnbd: restore sysfs interface to rnbd-client
  md/raid5-cache: fix null-ptr-deref for r5l_flush_stripe_to_raid()
  raid6: test: only check for Altivec if building on powerpc hosts
  raid6: test: make sure all intermediate and artifact files are .gitignored
  ...

101 files changed, 1683 insertions, 844 deletions

diff --git a/block/Kconfig b/block/Kconfig
index 86122e459fe0..f1364d1c0d93 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -5,6 +5,7 @@
 menuconfig BLOCK
        bool "Enable the block layer" if EXPERT
        default y
+       select FS_IOMAP
        select SBITMAP
        help
 	 Provide block layer support for the kernel.
@@ -183,6 +184,8 @@ config BLK_DEBUG_FS_ZONED
 
 config BLK_SED_OPAL
 	bool "Logic for interfacing with Opal enabled SEDs"
+	depends on KEYS
+	select PSERIES_PLPKS if PPC_PSERIES
 	help
 	Builds Logic for interfacing with Opal enabled controllers.
 	Enabling this option enables users to setup/unlock/lock
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index 4533eb491661..ec8ac8cf6e1b 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -123,20 +123,38 @@ void bio_integrity_free(struct bio *bio)
 int bio_integrity_add_page(struct bio *bio, struct page *page,
 			   unsigned int len, unsigned int offset)
 {
+	struct request_queue *q = bdev_get_queue(bio->bi_bdev);
 	struct bio_integrity_payload *bip = bio_integrity(bio);
 
-	if (bip->bip_vcnt >= bip->bip_max_vcnt) {
-		printk(KERN_ERR "%s: bip_vec full\n", __func__);
+	if (((bip->bip_iter.bi_size + len) >> SECTOR_SHIFT) >
+	    queue_max_hw_sectors(q))
 		return 0;
-	}
 
-	if (bip->bip_vcnt &&
-	    bvec_gap_to_prev(&bdev_get_queue(bio->bi_bdev)->limits,
-			     &bip->bip_vec[bip->bip_vcnt - 1], offset))
-		return 0;
+	if (bip->bip_vcnt > 0) {
+		struct bio_vec *bv = &bip->bip_vec[bip->bip_vcnt - 1];
+		bool same_page = false;
+
+		if (bvec_try_merge_hw_page(q, bv, page, len, offset,
+					   &same_page)) {
+			bip->bip_iter.bi_size += len;
+			return len;
+		}
+
+		if (bip->bip_vcnt >=
+		    min(bip->bip_max_vcnt, queue_max_integrity_segments(q)))
+			return 0;
+
+		/*
+		 * If the queue doesn't support SG gaps and adding this segment
+		 * would create a gap, disallow it.
+		 */
+		if (bvec_gap_to_prev(&q->limits, bv, offset))
+			return 0;
+	}
 
 	bvec_set_page(&bip->bip_vec[bip->bip_vcnt], page, len, offset);
 	bip->bip_vcnt++;
+	bip->bip_iter.bi_size += len;
 
 	return len;
 }
@@ -199,8 +217,6 @@ bool bio_integrity_prep(struct bio *bio)
 	unsigned long start, end;
 	unsigned int len, nr_pages;
 	unsigned int bytes, offset, i;
-	unsigned int intervals;
-	blk_status_t status;
 
 	if (!bi)
 		return true;
@@ -224,12 +240,10 @@ bool bio_integrity_prep(struct bio *bio)
 		    !(bi->flags & BLK_INTEGRITY_GENERATE))
 			return true;
 	}
-	intervals = bio_integrity_intervals(bi, bio_sectors(bio));
 
 	/* Allocate kernel buffer for protection data */
-	len = intervals * bi->tuple_size;
+	len = bio_integrity_bytes(bi, bio_sectors(bio));
 	buf = kmalloc(len, GFP_NOIO);
-	status = BLK_STS_RESOURCE;
 	if (unlikely(buf == NULL)) {
 		printk(KERN_ERR "could not allocate integrity buffer\n");
 		goto err_end_io;
@@ -244,12 +258,10 @@ bool bio_integrity_prep(struct bio *bio)
 	if (IS_ERR(bip)) {
 		printk(KERN_ERR "could not allocate data integrity bioset\n");
 		kfree(buf);
-		status = BLK_STS_RESOURCE;
 		goto err_end_io;
 	}
 
 	bip->bip_flags |= BIP_BLOCK_INTEGRITY;
-	bip->bip_iter.bi_size = len;
 	bip_set_seed(bip, bio->bi_iter.bi_sector);
 
 	if (bi->flags & BLK_INTEGRITY_IP_CHECKSUM)
@@ -257,28 +269,18 @@ bool bio_integrity_prep(struct bio *bio)
 
 	/* Map it */
 	offset = offset_in_page(buf);
-	for (i = 0 ; i < nr_pages ; i++) {
-		int ret;
+	for (i = 0; i < nr_pages && len > 0; i++) {
 		bytes = PAGE_SIZE - offset;
 
-		if (len <= 0)
-			break;
-
 		if (bytes > len)
 			bytes = len;
 
-		ret = bio_integrity_add_page(bio, virt_to_page(buf),
-					     bytes, offset);
-
-		if (ret == 0) {
+		if (bio_integrity_add_page(bio, virt_to_page(buf),
+					   bytes, offset) < bytes) {
 			printk(KERN_ERR "could not attach integrity payload\n");
-			status = BLK_STS_RESOURCE;
 			goto err_end_io;
 		}
 
-		if (ret < bytes)
-			break;
-
 		buf += bytes;
 		len -= bytes;
 		offset = 0;
@@ -294,10 +296,9 @@ bool bio_integrity_prep(struct bio *bio)
 	return true;
 
 err_end_io:
-	bio->bi_status = status;
+	bio->bi_status = BLK_STS_RESOURCE;
 	bio_endio(bio);
 	return false;
-
 }
 EXPORT_SYMBOL(bio_integrity_prep);
 
diff --git a/block/bio.c b/block/bio.c
index 8672179213b9..816d412c06e9 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -606,15 +606,15 @@ struct bio *bio_kmalloc(unsigned short nr_vecs, gfp_t gfp_mask)
 }
 EXPORT_SYMBOL(bio_kmalloc);
 
-void zero_fill_bio(struct bio *bio)
+void zero_fill_bio_iter(struct bio *bio, struct bvec_iter start)
 {
 	struct bio_vec bv;
 	struct bvec_iter iter;
 
-	bio_for_each_segment(bv, bio, iter)
+	__bio_for_each_segment(bv, bio, iter, start)
 		memzero_bvec(&bv);
 }
-EXPORT_SYMBOL(zero_fill_bio);
+EXPORT_SYMBOL(zero_fill_bio_iter);
 
 /**
  * bio_truncate - truncate the bio to small size of @new_size
@@ -903,9 +903,8 @@ static inline bool bio_full(struct bio *bio, unsigned len)
 	return false;
 }
 
-static inline bool page_is_mergeable(const struct bio_vec *bv,
-		struct page *page, unsigned int len, unsigned int off,
-		bool *same_page)
+static bool bvec_try_merge_page(struct bio_vec *bv, struct page *page,
+		unsigned int len, unsigned int off, bool *same_page)
 {
 	size_t bv_end = bv->bv_offset + bv->bv_len;
 	phys_addr_t vec_end_addr = page_to_phys(bv->bv_page) + bv_end - 1;
@@ -919,49 +918,15 @@ static inline bool page_is_mergeable(const struct bio_vec *bv,
 		return false;
 
 	*same_page = ((vec_end_addr & PAGE_MASK) == page_addr);
-	if (*same_page)
-		return true;
-	else if (IS_ENABLED(CONFIG_KMSAN))
-		return false;
-	return (bv->bv_page + bv_end / PAGE_SIZE) == (page + off / PAGE_SIZE);
-}
-
-/**
- * __bio_try_merge_page - try appending data to an existing bvec.
- * @bio: destination bio
- * @page: start page to add
- * @len: length of the data to add
- * @off: offset of the data relative to @page
- * @same_page: return if the segment has been merged inside the same page
- *
- * Try to add the data at @page + @off to the last bvec of @bio.  This is a
- * useful optimisation for file systems with a block size smaller than the
- * page size.
- *
- * Warn if (@len, @off) crosses pages in case that @same_page is true.
- *
- * Return %true on success or %false on failure.
- */
-static bool __bio_try_merge_page(struct bio *bio, struct page *page,
-		unsigned int len, unsigned int off, bool *same_page)
-{
-	if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)))
-		return false;
-
-	if (bio->bi_vcnt > 0) {
-		struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
-
-		if (page_is_mergeable(bv, page, len, off, same_page)) {
-			if (bio->bi_iter.bi_size > UINT_MAX - len) {
-				*same_page = false;
-				return false;
-			}
-			bv->bv_len += len;
-			bio->bi_iter.bi_size += len;
-			return true;
-		}
+	if (!*same_page) {
+		if (IS_ENABLED(CONFIG_KMSAN))
+			return false;
+		if (bv->bv_page + bv_end / PAGE_SIZE != page + off / PAGE_SIZE)
+			return false;
 	}
-	return false;
+
+	bv->bv_len += len;
+	return true;
 }
 
 /*
@@ -969,11 +934,10 @@ static bool __bio_try_merge_page(struct bio *bio, struct page *page,
  * size limit.  This is not for normal read/write bios, but for passthrough
  * or Zone Append operations that we can't split.
  */
-static bool bio_try_merge_hw_seg(struct request_queue *q, struct bio *bio,
-				 struct page *page, unsigned len,
-				 unsigned offset, bool *same_page)
+bool bvec_try_merge_hw_page(struct request_queue *q, struct bio_vec *bv,
+		struct page *page, unsigned len, unsigned offset,
+		bool *same_page)
 {
-	struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
 	unsigned long mask = queu