Merge tag 'for-6.14/block-20250118' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - NVMe pull requests via Keith:
      - Target support for PCI-Endpoint transport (Damien)
      - TCP IO queue spreading fixes (Sagi, Chaitanya)
      - Target handling for "limited retry" flags (Guixen)
      - Poll type fix (Yongsoo)
      - Xarray storage error handling (Keisuke)
      - Host memory buffer free size fix on error (Francis)

 - MD pull requests via Song:
      - Reintroduce md-linear (Yu Kuai)
      - md-bitmap refactor and fix (Yu Kuai)
      - Replace kmap_atomic with kmap_local_page (David Reaver)

 - Quite a few queue freeze and debugfs deadlock fixes

   Ming introduced lockdep support for this in the 6.13 kernel, and it
   has (unsurprisingly) uncovered quite a few issues

 - Use const attributes for IO schedulers

 - Remove bio ioprio wrappers

 - Fixes for stacked device atomic write support

 - Refactor queue affinity helpers, in preparation for better supporting
   isolated CPUs

 - Cleanups of loop O_DIRECT handling

 - Cleanup of BLK_MQ_F_* flags

 - Add rotational support for null_blk

 - Various fixes and cleanups

* tag 'for-6.14/block-20250118' of git://git.kernel.dk/linux: (106 commits)
  block: Don't trim an atomic write
  block: Add common atomic writes enable flag
  md/md-linear: Fix a NULL vs IS_ERR() bug in linear_add()
  block: limit disk max sectors to (LLONG_MAX >> 9)
  block: Change blk_stack_atomic_writes_limits() unit_min check
  block: Ensure start sector is aligned for stacking atomic writes
  blk-mq: Move more error handling into blk_mq_submit_bio()
  block: Reorder the request allocation code in blk_mq_submit_bio()
  nvme: fix bogus kzalloc() return check in nvme_init_effects_log()
  md/md-bitmap: move bitmap_{start, end}write to md upper layer
  md/raid5: implement pers->bitmap_sector()
  md: add a new callback pers->bitmap_sector()
  md/md-bitmap: remove the last parameter for bimtap_ops->endwrite()
  md/md-bitmap: factor behind write counters out from bitmap_{start/end}write()
  md: Replace deprecated kmap_atomic() with kmap_local_page()
  md: reintroduce md-linear
  partitions: ldm: remove the initial kernel-doc notation
  blk-cgroup: rwstat: fix kernel-doc warnings in header file
  blk-cgroup: fix kernel-doc warnings in header file
  nbd: fix partial sending
  ...

12 files changed, 87 insertions, 77 deletions

diff --git a/include/linux/bio.h b/include/linux/bio.h
index 7a1b3b1a8fed..4b79bf50f4f0 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -19,9 +19,6 @@ static inline unsigned int bio_max_segs(unsigned int nr_segs)
 	return min(nr_segs, BIO_MAX_VECS);
 }
 
-#define bio_prio(bio)			(bio)->bi_ioprio
-#define bio_set_prio(bio, prio)		((bio)->bi_ioprio = prio)
-
 #define bio_iter_iovec(bio, iter)				\
 	bvec_iter_bvec((bio)->bi_io_vec, (iter))
 
@@ -416,8 +413,6 @@ int __must_check bio_add_page(struct bio *bio, struct page *page, unsigned len,
 			      unsigned off);
 bool __must_check bio_add_folio(struct bio *bio, struct folio *folio,
 				size_t len, size_t off);
-extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *,
-			   unsigned int, unsigned int);
 void __bio_add_page(struct bio *bio, struct page *page,
 		unsigned int len, unsigned int off);
 void bio_add_folio_nofail(struct bio *bio, struct folio *folio, size_t len,
diff --git a/include/linux/blk-mq-pci.h b/include/linux/blk-mq-pci.h
deleted file mode 100644
index ca544e1d3508..000000000000
--- a/include/linux/blk-mq-pci.h
+++ /dev/null
@@ -1,11 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LINUX_BLK_MQ_PCI_H
-#define _LINUX_BLK_MQ_PCI_H
-
-struct blk_mq_queue_map;
-struct pci_dev;
-
-void blk_mq_pci_map_queues(struct blk_mq_queue_map *qmap, struct pci_dev *pdev,
-			   int offset);
-
-#endif /* _LINUX_BLK_MQ_PCI_H */
diff --git a/include/linux/blk-mq-virtio.h b/include/linux/blk-mq-virtio.h
deleted file mode 100644
index 13226e9b22dd..000000000000
--- a/include/linux/blk-mq-virtio.h
+++ /dev/null
@@ -1,11 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LINUX_BLK_MQ_VIRTIO_H
-#define _LINUX_BLK_MQ_VIRTIO_H
-
-struct blk_mq_queue_map;
-struct virtio_device;
-
-void blk_mq_virtio_map_queues(struct blk_mq_queue_map *qmap,
-		struct virtio_device *vdev, int first_vec);
-
-#endif /* _LINUX_BLK_MQ_VIRTIO_H */
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index c596e0e4cb75..a0a9007cc1e3 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -296,13 +296,6 @@ enum blk_eh_timer_return {
 	BLK_EH_RESET_TIMER,
 };
 
-/* Keep alloc_policy_name[] in sync with the definitions below */
-enum {
-	BLK_TAG_ALLOC_FIFO,	/* allocate starting from 0 */
-	BLK_TAG_ALLOC_RR,	/* allocate starting from last allocated tag */
-	BLK_TAG_ALLOC_MAX
-};
-
 /**
  * struct blk_mq_hw_ctx - State for a hardware queue facing the hardware
  * block device
@@ -668,7 +661,6 @@ struct blk_mq_ops {
 
 /* Keep hctx_flag_name[] in sync with the definitions below */
 enum {
-	BLK_MQ_F_SHOULD_MERGE	= 1 << 0,
 	BLK_MQ_F_TAG_QUEUE_SHARED = 1 << 1,
 	/*
 	 * Set when this device requires underlying blk-mq device for
@@ -677,23 +669,20 @@ enum {
 	BLK_MQ_F_STACKING	= 1 << 2,
 	BLK_MQ_F_TAG_HCTX_SHARED = 1 << 3,
 	BLK_MQ_F_BLOCKING	= 1 << 4,
-	/* Do not allow an I/O scheduler to be configured. */
-	BLK_MQ_F_NO_SCHED	= 1 << 5,
+
+	/*
+	 * Alloc tags on a round-robin base instead of the first available one.
+	 */
+	BLK_MQ_F_TAG_RR		= 1 << 5,
 
 	/*
 	 * Select 'none' during queue registration in case of a single hwq
 	 * or shared hwqs instead of 'mq-deadline'.
 	 */
 	BLK_MQ_F_NO_SCHED_BY_DEFAULT	= 1 << 6,
-	BLK_MQ_F_ALLOC_POLICY_START_BIT = 7,
-	BLK_MQ_F_ALLOC_POLICY_BITS = 1,
+
+	BLK_MQ_F_MAX = 1 << 7,
 };
-#define BLK_MQ_FLAG_TO_ALLOC_POLICY(flags) \
-	((flags >> BLK_MQ_F_ALLOC_POLICY_START_BIT) & \
-		((1 << BLK_MQ_F_ALLOC_POLICY_BITS) - 1))
-#define BLK_ALLOC_POLICY_TO_MQ_FLAG(policy) \
-	((policy & ((1 << BLK_MQ_F_ALLOC_POLICY_BITS) - 1)) \
-		<< BLK_MQ_F_ALLOC_POLICY_START_BIT)
 
 #define BLK_MQ_MAX_DEPTH	(10240)
 #define BLK_MQ_NO_HCTX_IDX	(-1U)
@@ -921,6 +910,8 @@ void blk_mq_unfreeze_queue_non_owner(struct request_queue *q);
 void blk_freeze_queue_start_non_owner(struct request_queue *q);
 
 void blk_mq_map_queues(struct blk_mq_queue_map *qmap);
+void blk_mq_map_hw_queues(struct blk_mq_queue_map *qmap,
+			  struct device *dev, unsigned int offset);
 void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues);
 
 void blk_mq_quiesce_queue_nowait(struct request_queue *q);
@@ -977,14 +968,6 @@ static inline void blk_mq_cleanup_rq(struct request *rq)
 		rq->q->mq_ops->cleanup_rq(rq);
 }
 
-static inline void blk_rq_bio_prep(struct request *rq, struct bio *bio,
-		unsigned int nr_segs)
-{
-	rq->nr_phys_segments = nr_segs;
-	rq->__data_len = bio->bi_iter.bi_size;
-	rq->bio = rq->biotail = bio;
-}
-
 void blk_mq_hctx_set_fq_lock_class(struct blk_mq_hw_ctx *hctx,
 		struct lock_class_key *key);
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 378d3a1a22fc..76f0a4e7c2e5 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -331,8 +331,8 @@ typedef unsigned int __bitwise blk_features_t;
 #define BLK_FEAT_RAID_PARTIAL_STRIPES_EXPENSIVE \
 	((__force blk_features_t)(1u << 15))
 
-/* stacked device can/does support atomic writes */
-#define BLK_FEAT_ATOMIC_WRITES_STACKED \
+/* atomic writes enabled */
+#define BLK_FEAT_ATOMIC_WRITES \
 	((__force blk_features_t)(1u << 16))
 
 /*
@@ -581,6 +581,12 @@ struct request_queue {
 #ifdef CONFIG_LOCKDEP
 	struct task_struct	*mq_freeze_owner;
 	int			mq_freeze_owner_depth;
+	/*
+	 * Records disk & queue state in current context, used in unfreeze
+	 * queue
+	 */
+	bool			mq_freeze_disk_dead;
+	bool			mq_freeze_queue_dying;
 #endif
 	wait_queue_head_t	mq_freeze_wq;
 	/*
@@ -938,8 +944,7 @@ static inline unsigned int blk_boundary_sectors_left(sector_t offset,
  * the caller can modify.  The caller must call queue_limits_commit_update()
  * to finish the update.
  *
- * Context: process context.  The caller must have frozen the queue or ensured
- * that there is outstanding I/O by other means.
+ * Context: process context.
  */
 static inline struct queue_limits
 queue_limits_start_update(struct request_queue *q)
@@ -947,6 +952,8 @@ queue_limits_start_update(struct request_queue *q)
 	mutex_lock(&q->limits_lock);
 	return q->limits;
 }
+int queue_limits_commit_update_frozen(struct request_queue *q,
+		struct queue_limits *lim);
 int queue_limits_commit_update(struct request_queue *q,
 		struct queue_limits *lim);
 int queue_limits_set(struct request_queue *q, struct queue_limits *lim);
@@ -1699,6 +1706,15 @@ struct io_comp_batch {
 	void (*complete)(struct io_comp_batch *);
 };
 
+static inline bool blk_atomic_write_start_sect_aligned(sector_t sector,
+						struct queue_limits *limits)
+{
+	unsigned int alignment = max(limits->atomic_write_hw_unit_min,
+				limits->atomic_write_hw_boundary);
+
+	return IS_ALIGNED(sector, alignment >> SECTOR_SHIFT);
+}
+
 static inline bool bdev_can_atomic_write(struct block_device *bdev)
 {
 	struct request_queue *bd_queue = bdev->bd_queue;
@@ -1707,15 +1723,9 @@ static inline bool bdev_can_atomic_write(struct block_device *bdev)
 	if (!limits->atomic_write_unit_min)
 		return false;
 
-	if (bdev_is_partition(bdev)) {
-		sector_t bd_start_sect = bdev->bd_start_sect;
-		unsigned int alignment =
-			max(limits->atomic_write_unit_min,
-			    limits->atomic_write_hw_boundary);
-
-		if (!IS_ALIGNED(bd_start_sect, alignment >> SECTOR_SHIFT))
-			return false;
-	}
+	if (bdev_is_partition(bdev))
+		return blk_atomic_write_start_sect_aligned(bdev->bd_start_sect,
+							limits);
 
 	return true;
 }
diff --git a/include/linux/bvec.h b/include/linux/bvec.h
index f41c7f0ef91e..ba8f52d48b94 100644
--- a/include/linux/bvec.h
+++ b/include/linux/bvec.h
@@ -286,12 +286,7 @@ static inline void *bvec_virt(struct bio_vec *bvec)
  */
 static inline phys_addr_t bvec_phys(const struct bio_vec *bvec)
 {
-	/*
-	 * Note this open codes page_to_phys because page_to_phys is defined in
-	 * <asm/io.h>, which we don't want to pull in here.  If it ever moves to
-	 * a sensible place we should start using it.
-	 */
-	return PFN_PHYS(page_to_pfn(bvec->bv_page)) + bvec->bv_offset;
+	return page_to_phys(bvec->bv_page) + bvec->bv_offset;
 }
 
 #endif /* __LINUX_BVEC_H */
diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h
index cdc4757217f9..b18658bce2c3 100644
--- a/include/linux/device/bus.h
+++ b/include/linux/device/bus.h
@@ -48,6 +48,7 @@ struct fwnode_handle;
  *		will never get called until they do.
  * @remove:	Called when a device removed from this bus.
  * @shutdown:	Called at shut-down time to quiesce the device.
+ * @irq_get_affinity:	Get IRQ affinity mask for the device on this bus.
  *
  * @online:	Called to put the device back online (after offlining it).
  * @offline:	Called to put the device offline for hot-removal. May fail.
@@ -87,6 +88,8 @@ struct bus_type {
 	void (*sync_state)(struct device *dev);
 	void (*remove)(struct device *dev);
 	void (*shutdown)(struct device *dev);
+	const struct cpumask *(*irq_get_affinity)(struct device *dev,
+			unsigned int irq_vec);
 
 	int (*online)(struct device *dev);
 	int (*offline)(struct device *dev);
diff --git a/include/linux/libata.h b/include/linux/libata.h
index c1a85d46eba6..be5183d75736 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -1467,13 +1467,13 @@ extern const struct attribute_group *ata_common_sdev_groups[];
 #define ATA_SUBBASE_SHT(drv_name)				\
 	__ATA_BASE_SHT(drv_name),				\
 	.can_queue		= ATA_DEF_QUEUE,		\
-	.tag_alloc_policy	= BLK_TAG_ALLOC_RR,		\
+	.tag_alloc_policy_rr	= true,				\
 	.device_configure	= ata_scsi_device_configure
 
 #define ATA_SUBBASE_SHT_QD(drv_name, drv_qd)			\
 	__ATA_BASE_SHT(drv_name),				\
 	.can_queue		= drv_qd,			\
-	.tag_alloc_policy	= BLK_TAG_ALLOC_RR,		\
+	.tag_alloc_policy_rr	= true,				\
 	.device_configure	= ata_scsi_device_configure
 
 #define ATA_BASE_SHT(drv_name)					\
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 13377dde4527..fe3b60818fdc 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -64,6 +64,7 @@ enum {
 
 /* Transport Type codes for Discovery Log Page entry TRTYPE field */
 enum {
+	NVMF_TRTYPE_PCI		= 0,	/* PCI */
 	NVMF_TRTYPE_RDMA	= 1,	/* RDMA */
 	NVMF_TRTYPE_FC		= 2,	/* Fibre Channel */
 	NVMF_TRTYPE_TCP		= 3,	/* TCP/IP */
@@ -275,6 +276,7 @@ enum nvme_ctrl_attr {
 	NVME_CTRL_ATTR_HID_128_BIT	= (1 << 0),
 	NVME_CTRL_ATTR_TBKAS		= (1 << 6),
 	NVME_CTRL_ATTR_ELBAS		= (1 << 15),
+	NVME_CTRL_ATTR_RHII		= (1 << 18),
 };
 
 struct nvme_id_ctrl {
@@ -1896,6 +1898,46 @@ static inline bool nvme_is_fabrics(const struct nvme_command *cmd)
 	return cmd->common.opcode == nvme_fabrics_command;
 }
 
+#ifdef CONFIG_NVME_VERBOSE_ERRORS
+const char *nvme_get_error_status_str(u16 status);
+const char *nvme_get_opcode_str(u8 opcode);
+const char *nvme_get_admin_opcode_str(u8 opcode);
+const char *nvme_get_fabrics_opcode_str(u8 opcode);
+#else /* CONFIG_NVME_VERBOSE_ERRORS */
+static inline const char *nvme_get_error_status_str(u16 status)
+{
+	return "I/O Error";
+}
+static inline const char *nvme_get_opcode_str(u8 opcode)
+{
+	return "I/O Cmd";
+}
+static inline const char *nvme_get_admin_opcode_str(u8 opcode)
+{
+	return "Admin Cmd";
+}
+
+static inline const char *nvme_get_fabrics_opcode_str(u8 opcode)
+{
+	return "Fabrics Cmd";
+}
+#endif /* CONFIG_NVME_VERBOSE_ERRORS */
+
+static inline const char *nvme_opcode_str(int qid, u8 opcode)
+{
+	return qid ? nvme_get_opcode_str(opcode) :
+		nvme_get_admin_opcode_str(opcode);
+}
+
+static inline const char *nvme_fabrics_opcode_str(
+		int qid, const struct nvme_command *cmd)
+{
+	if (nvme_is_fabrics(cmd))
+		return nvme_get_fabrics_opcode_str(cmd->fabrics.fctype);
+
+	return nvme_opcode_str(qid, cmd->common.opcode);
+}
+
 struct nvme_error_slot {
 	__le64		error_count;
 	__le16		sqid;
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index 2b4ab0369ffb..02823d6af37d 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -438,8 +438,10 @@ struct scsi_host_template {
 	 */
 	short cmd_per_lun;
 
-	/* If use block layer to manage tags, this is tag allocation policy */
-	int tag_alloc_policy;
+	/*
+	 * Allocate tags starting from last allocated tag.
+	 */
+	bool tag_alloc_policy_rr : 1;
 
 	/*
 	 * Track QUEUE_FULL events and reduce queue depth on demand.
diff --git a/include/uapi/linux/raid/md_p.h b/include/uapi/linux/raid/md_p.h
index 5a43c23f53bf..ff47b6f0ba0f 100644
--- a/include/uapi/linux/raid/md_p.h
+++ b/include/uapi/linux/raid/md_p.h
@@ -233,7 +233,7 @@ struct mdp_superblock_1 {
 	char	set_name[32];	/* set and interpreted by user-space */
 
 	__le64	ctime;		/* lo 40 bits are seconds, top 24 are microseconds or 0*/
-	__le32	level;		/* 0,1,4,5 */
+	__le32	level;		/* 0,1,4,5, -1 (linear) */
 	__le32	layout;		/* only for raid5 and raid10 currently */
 	__le64	size;		/* used size of component devices, in 512byte sectors */
 
diff --git a/include/uapi/linux/raid/md_u.h b/include/uapi/linux/raid/md_u.h
index 7be89a4906e7..a893010735fb 100644
--- a/include/uapi/linux/raid/md_u.h
+++ b/include/uapi/linux/raid/md_u.h
@@ -103,6 +103,8 @@ typedef struct mdu_array_info_s {
 
 } mdu_array_info_t;
 
+#define LEVEL_LINEAR		(-1)
+
 /* we need a value for 'no level specified' and 0
  * means 'raid0', so we need something else.  This is
  * for internal use only