Merge tag 'for-6.12/block-20240913' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - MD changes via Song:
      - md-bitmap refactoring (Yu Kuai)
      - raid5 performance optimization (Artur Paszkiewicz)
      - Other small fixes (Yu Kuai, Chen Ni)
      - Add a sysfs entry 'new_level' (Xiao Ni)
      - Improve information reported in /proc/mdstat (Mateusz Kusiak)

 - NVMe changes via Keith:
      - Asynchronous namespace scanning (Stuart)
      - TCP TLS updates (Hannes)
      - RDMA queue controller validation (Niklas)
      - Align field names to the spec (Anuj)
      - Metadata support validation (Puranjay)
      - A syntax cleanup (Shen)
      - Fix a Kconfig linking error (Arnd)
      - New queue-depth quirk (Keith)

 - Add missing unplug trace event (Keith)

 - blk-iocost fixes (Colin, Konstantin)

 - t10-pi modular removal and fixes (Alexey)

 - Fix for potential BLKSECDISCARD overflow (Alexey)

 - bio splitting cleanups and fixes (Christoph)

 - Deal with folios rather than rather than pages, speeding up how the
   block layer handles bigger IOs (Kundan)

 - Use spinlocks rather than bit spinlocks in zram (Sebastian, Mike)

 - Reduce zoned device overhead in ublk (Ming)

 - Add and use sendpages_ok() for drbd and nvme-tcp (Ofir)

 - Fix regression in partition error pointer checking (Riyan)

 - Add support for write zeroes and rotational status in nbd (Wouter)

 - Add Yu Kuai as new BFQ maintainer. The scheduler has been
   unmaintained for quite a while.

 - Various sets of fixes for BFQ (Yu Kuai)

 - Misc fixes and cleanups (Alvaro, Christophe, Li, Md Haris, Mikhail,
   Yang)

* tag 'for-6.12/block-20240913' of git://git.kernel.dk/linux: (120 commits)
  nvme-pci: qdepth 1 quirk
  block: fix potential invalid pointer dereference in blk_add_partition
  blk_iocost: make read-only static array vrate_adj_pct const
  block: unpin user pages belonging to a folio at once
  mm: release number of pages of a folio
  block: introduce folio awareness and add a bigger size from folio
  block: Added folio-ized version of bio_add_hw_page()
  block, bfq: factor out a helper to split bfqq in bfq_init_rq()
  block, bfq: remove local variable 'bfqq_already_existing' in bfq_init_rq()
  block, bfq: remove local variable 'split' in bfq_init_rq()
  block, bfq: remove bfq_log_bfqg()
  block, bfq: merge bfq_release_process_ref() into bfq_put_cooperator()
  block, bfq: fix procress reference leakage for bfqq in merge chain
  block, bfq: fix uaf for accessing waker_bfqq after splitting
  blk-throttle: support prioritized processing of metadata
  blk-throttle: remove last_low_overflow_time
  drbd: Add NULL check for net_conf to prevent dereference in state validation
  nvme-tcp: fix link failure for TCP auth
  blk-mq: add missing unplug trace event
  mtip32xx: Remove redundant null pointer checks in mtip_hw_debugfs_init()
  ...

1 files changed, 56 insertions, 18 deletions

diff --git a/block/blk.h b/block/blk.h
index e180863f918b..86affb583eb6 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -331,33 +331,67 @@ ssize_t part_timeout_show(struct device *, struct device_attribute *, char *);
 ssize_t part_timeout_store(struct device *, struct device_attribute *,
 				const char *, size_t);
 
-static inline bool bio_may_exceed_limits(struct bio *bio,
-					 const struct queue_limits *lim)
+struct bio *bio_split_discard(struct bio *bio, const struct queue_limits *lim,
+		unsigned *nsegs);
+struct bio *bio_split_write_zeroes(struct bio *bio,
+		const struct queue_limits *lim, unsigned *nsegs);
+struct bio *bio_split_rw(struct bio *bio, const struct queue_limits *lim,
+		unsigned *nr_segs);
+struct bio *bio_split_zone_append(struct bio *bio,
+		const struct queue_limits *lim, unsigned *nr_segs);
+
+/*
+ * All drivers must accept single-segments bios that are smaller than PAGE_SIZE.
+ *
+ * This is a quick and dirty check that relies on the fact that bi_io_vec[0] is
+ * always valid if a bio has data.  The check might lead to occasional false
+ * positives when bios are cloned, but compared to the performance impact of
+ * cloned bios themselves the loop below doesn't matter anyway.
+ */
+static inline bool bio_may_need_split(struct bio *bio,
+		const struct queue_limits *lim)
+{
+	return lim->chunk_sectors || bio->bi_vcnt != 1 ||
+		bio->bi_io_vec->bv_len + bio->bi_io_vec->bv_offset > PAGE_SIZE;
+}
+
+/**
+ * __bio_split_to_limits - split a bio to fit the queue limits
+ * @bio:     bio to be split
+ * @lim:     queue limits to split based on
+ * @nr_segs: returns the number of segments in the returned bio
+ *
+ * Check if @bio needs splitting based on the queue limits, and if so split off
+ * a bio fitting the limits from the beginning of @bio and return it.  @bio is
+ * shortened to the remainder and re-submitted.
+ *
+ * The split bio is allocated from @q->bio_split, which is provided by the
+ * block layer.
+ */
+static inline struct bio *__bio_split_to_limits(struct bio *bio,
+		const struct queue_limits *lim, unsigned int *nr_segs)
 {
 	switch (bio_op(bio)) {
+	case REQ_OP_READ:
+	case REQ_OP_WRITE:
+		if (bio_may_need_split(bio, lim))
+			return bio_split_rw(bio, lim, nr_segs);
+		*nr_segs = 1;
+		return bio;
+	case REQ_OP_ZONE_APPEND:
+		return bio_split_zone_append(bio, lim, nr_segs);
 	case REQ_OP_DISCARD:
 	case REQ_OP_SECURE_ERASE:
+		return bio_split_discard(bio, lim, nr_segs);
 	case REQ_OP_WRITE_ZEROES:
-		return true; /* non-trivial splitting decisions */
+		return bio_split_write_zeroes(bio, lim, nr_segs);
 	default:
-		break;
+		/* other operations can't be split */
+		*nr_segs = 0;
+		return bio;
 	}
-
-	/*
-	 * All drivers must accept single-segments bios that are <= PAGE_SIZE.
-	 * This is a quick and dirty check that relies on the fact that
-	 * bi_io_vec[0] is always valid if a bio has data.  The check might
-	 * lead to occasional false negatives when bios are cloned, but compared
-	 * to the performance impact of cloned bios themselves the loop below
-	 * doesn't matter anyway.
-	 */
-	return lim->chunk_sectors || bio->bi_vcnt != 1 ||
-		bio->bi_io_vec->bv_len + bio->bi_io_vec->bv_offset > PAGE_SIZE;
 }
 
-struct bio *__bio_split_to_limits(struct bio *bio,
-				  const struct queue_limits *lim,
-				  unsigned int *nr_segs);
 int ll_back_merge_fn(struct request *req, struct bio *bio,
 		unsigned int nr_segs);
 bool blk_attempt_req_merge(struct request_queue *q, struct request *rq,
@@ -540,6 +574,10 @@ 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);
 
+int bio_add_hw_folio(struct request_queue *q, struct bio *bio,
+		struct folio *folio, size_t len, size_t offset,
+		unsigned int max_sectors, bool *same_page);
+
 /*
  * Clean up a page appropriately, where the page may be pinned, may have a
  * ref taken on it or neither.