Merge tag 'for-6.16/block-20250523' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - ublk updates:
      - Add support for updating the size of a ublk instance
      - Zero-copy improvements
      - Auto-registering of buffers for zero-copy
      - Series simplifying and improving GET_DATA and request lookup
      - Series adding quiesce support
      - Lots of selftests additions
      - Various cleanups

 - NVMe updates via Christoph:
      - add per-node DMA pools and use them for PRP/SGL allocations
        (Caleb Sander Mateos, Keith Busch)
      - nvme-fcloop refcounting fixes (Daniel Wagner)
      - support delayed removal of the multipath node and optionally
        support the multipath node for private namespaces (Nilay Shroff)
      - support shared CQs in the PCI endpoint target code (Wilfred
        Mallawa)
      - support admin-queue only authentication (Hannes Reinecke)
      - use the crc32c library instead of the crypto API (Eric Biggers)
      - misc cleanups (Christoph Hellwig, Marcelo Moreira, Hannes
        Reinecke, Leon Romanovsky, Gustavo A. R. Silva)

 - MD updates via Yu:
      - Fix that normal IO can be starved by sync IO, found by mkfs on
        newly created large raid5, with some clean up patches for bdev
        inflight counters

 - Clean up brd, getting rid of atomic kmaps and bvec poking

 - Add loop driver specifically for zoned IO testing

 - Eliminate blk-rq-qos calls with a static key, if not enabled

 - Improve hctx locking for when a plug has IO for multiple queues
   pending

 - Remove block layer bouncing support, which in turn means we can
   remove the per-node bounce stat as well

 - Improve blk-throttle support

 - Improve delay support for blk-throttle

 - Improve brd discard support

 - Unify IO scheduler switching. This should also fix a bunch of lockdep
   warnings we've been seeing, after enabling lockdep support for queue
   freezing/unfreezeing

 - Add support for block write streams via FDP (flexible data placement)
   on NVMe

 - Add a bunch of block helpers, facilitating the removal of a bunch of
   duplicated boilerplate code

 - Remove obsolete BLK_MQ pci and virtio Kconfig options

 - Add atomic/untorn write support to blktrace

 - Various little cleanups and fixes

* tag 'for-6.16/block-20250523' of git://git.kernel.dk/linux: (186 commits)
  selftests: ublk: add test for UBLK_F_QUIESCE
  ublk: add feature UBLK_F_QUIESCE
  selftests: ublk: add test case for UBLK_U_CMD_UPDATE_SIZE
  traceevent/block: Add REQ_ATOMIC flag to block trace events
  ublk: run auto buf unregisgering in same io_ring_ctx with registering
  io_uring: add helper io_uring_cmd_ctx_handle()
  ublk: remove io argument from ublk_auto_buf_reg_fallback()
  ublk: handle ublk_set_auto_buf_reg() failure correctly in ublk_fetch()
  selftests: ublk: add test for covering UBLK_AUTO_BUF_REG_FALLBACK
  selftests: ublk: support UBLK_F_AUTO_BUF_REG
  ublk: support UBLK_AUTO_BUF_REG_FALLBACK
  ublk: register buffer to local io_uring with provided buf index via UBLK_F_AUTO_BUF_REG
  ublk: prepare for supporting to register request buffer automatically
  ublk: convert to refcount_t
  selftests: ublk: make IO & device removal test more stressful
  nvme: rename nvme_mpath_shutdown_disk to nvme_mpath_remove_disk
  nvme: introduce multipath_always_on module param
  nvme-multipath: introduce delayed removal of the multipath head node
  nvme-pci: derive and better document max segments limits
  nvme-pci: use struct_size for allocation struct nvme_dev
  ...

1 files changed, 19 insertions, 5 deletions

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 9a1f0ee40b56..332b56f323d9 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -182,7 +182,6 @@ struct gendisk {
 	struct list_head slave_bdevs;
 #endif
 	struct timer_rand_state *random;
-	atomic_t sync_io;		/* RAID */
 	struct disk_events *ev;
 
 #ifdef CONFIG_BLK_DEV_ZONED
@@ -218,6 +217,8 @@ struct gendisk {
 	 * devices that do not have multiple independent access ranges.
 	 */
 	struct blk_independent_access_ranges *ia_ranges;
+
+	struct mutex rqos_state_mutex;	/* rqos state change mutex */
 };
 
 /**
@@ -331,9 +332,6 @@ typedef unsigned int __bitwise blk_features_t;
 /* skip this queue in blk_mq_(un)quiesce_tagset */
 #define BLK_FEAT_SKIP_TAGSET_QUIESCE	((__force blk_features_t)(1u << 13))
 
-/* bounce all highmem pages */
-#define BLK_FEAT_BOUNCE_HIGH		((__force blk_features_t)(1u << 14))
-
 /* undocumented magic for bcache */
 #define BLK_FEAT_RAID_PARTIAL_STRIPES_EXPENSIVE \
 	((__force blk_features_t)(1u << 15))
@@ -347,7 +345,7 @@ typedef unsigned int __bitwise blk_features_t;
  */
 #define BLK_FEAT_INHERIT_MASK \
 	(BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA | BLK_FEAT_ROTATIONAL | \
-	 BLK_FEAT_STABLE_WRITES | BLK_FEAT_ZONED | BLK_FEAT_BOUNCE_HIGH | \
+	 BLK_FEAT_STABLE_WRITES | BLK_FEAT_ZONED | \
 	 BLK_FEAT_RAID_PARTIAL_STRIPES_EXPENSIVE)
 
 /* internal flags in queue_limits.flags */
@@ -405,6 +403,9 @@ struct queue_limits {
 	unsigned short		max_integrity_segments;
 	unsigned short		max_discard_segments;
 
+	unsigned short		max_write_streams;
+	unsigned int		write_stream_granularity;
+
 	unsigned int		max_open_zones;
 	unsigned int		max_active_zones;
 
@@ -644,6 +645,8 @@ enum {
 	QUEUE_FLAG_RQ_ALLOC_TIME,	/* record rq->alloc_time_ns */
 	QUEUE_FLAG_HCTX_ACTIVE,		/* at least one blk-mq hctx is active */
 	QUEUE_FLAG_SQ_SCHED,		/* single queue style io dispatch */
+	QUEUE_FLAG_DISABLE_WBT_DEF,	/* for sched to disable/enable wbt */
+	QUEUE_FLAG_NO_ELV_SWITCH,	/* can't switch elevator any more */
 	QUEUE_FLAG_MAX
 };
 
@@ -679,6 +682,10 @@ void blk_queue_flag_clear(unsigned int flag, struct request_queue *q);
 #define blk_queue_sq_sched(q)	test_bit(QUEUE_FLAG_SQ_SCHED, &(q)->queue_flags)
 #define blk_queue_skip_tagset_quiesce(q) \
 	((q)->limits.features & BLK_FEAT_SKIP_TAGSET_QUIESCE)
+#define blk_queue_disable_wbt(q)	\
+	test_bit(QUEUE_FLAG_DISABLE_WBT_DEF, &(q)->queue_flags)
+#define blk_queue_no_elv_switch(q)	\
+	test_bit(QUEUE_FLAG_NO_ELV_SWITCH, &(q)->queue_flags)
 
 extern void blk_set_pm_only(struct request_queue *q);
 extern void blk_clear_pm_only(struct request_queue *q);
@@ -1288,6 +1295,13 @@ static inline unsigned int bdev_max_segments(struct block_device *bdev)
 	return queue_max_segments(bdev_get_queue(bdev));
 }
 
+static inline unsigned short bdev_max_write_streams(struct block_device *bdev)
+{
+	if (bdev_is_partition(bdev))
+		return 0;
+	return bdev_limits(bdev)->max_write_streams;
+}
+
 static inline unsigned queue_logical_block_size(const struct request_queue *q)
 {
 	return q->limits.logical_block_size;