Merge tag 'for-6.9/block-20240310' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - MD pull requests via Song:
      - Cleanup redundant checks (Yu Kuai)
      - Remove deprecated headers (Marc Zyngier, Song Liu)
      - Concurrency fixes (Li Lingfeng)
      - Memory leak fix (Li Nan)
      - Refactor raid1 read_balance (Yu Kuai, Paul Luse)
      - Clean up and fix for md_ioctl (Li Nan)
      - Other small fixes (Gui-Dong Han, Heming Zhao)
      - MD atomic limits (Christoph)

 - NVMe pull request via Keith:
      - RDMA target enhancements (Max)
      - Fabrics fixes (Max, Guixin, Hannes)
      - Atomic queue_limits usage (Christoph)
      - Const use for class_register (Ricardo)
      - Identification error handling fixes (Shin'ichiro, Keith)

 - Improvement and cleanup for cached request handling (Christoph)

 - Moving towards atomic queue limits. Core changes and driver bits so
   far (Christoph)

 - Fix UAF issues in aoeblk (Chun-Yi)

 - Zoned fix and cleanups (Damien)

 - s390 dasd cleanups and fixes (Jan, Miroslav)

 - Block issue timestamp caching (me)

 - noio scope guarding for zoned IO (Johannes)

 - block/nvme PI improvements (Kanchan)

 - Ability to terminate long running discard loop (Keith)

 - bdev revalidation fix (Li)

 - Get rid of old nr_queues hack for kdump kernels (Ming)

 - Support for async deletion of ublk (Ming)

 - Improve IRQ bio recycling (Pavel)

 - Factor in CPU capacity for remote vs local completion (Qais)

 - Add shared_tags configfs entry for null_blk (Shin'ichiro

 - Fix for a regression in page refcounts introduced by the folio
   unification (Tony)

 - Misc fixes and cleanups (Arnd, Colin, John, Kunwu, Li, Navid,
   Ricardo, Roman, Tang, Uwe)

* tag 'for-6.9/block-20240310' of git://git.kernel.dk/linux: (221 commits)
  block: partitions: only define function mac_fix_string for CONFIG_PPC_PMAC
  block/swim: Convert to platform remove callback returning void
  cdrom: gdrom: Convert to platform remove callback returning void
  block: remove disk_stack_limits
  md: remove mddev->queue
  md: don't initialize queue limits
  md/raid10: use the atomic queue limit update APIs
  md/raid5: use the atomic queue limit update APIs
  md/raid1: use the atomic queue limit update APIs
  md/raid0: use the atomic queue limit update APIs
  md: add queue limit helpers
  md: add a mddev_is_dm helper
  md: add a mddev_add_trace_msg helper
  md: add a mddev_trace_remap helper
  bcache: move calculation of stripe_size and io_opt into bcache_device_init
  virtio_blk: Do not use disk_set_max_open/active_zones()
  aoe: fix the potential use-after-free problem in aoecmd_cfg_pkts
  block: move capacity validation to blkpg_do_ioctl()
  block: prevent division by zero in blk_rq_stat_sum()
  drbd: atomically update queue limits in drbd_reconsider_queue_parameters
  ...

9 files changed, 81 insertions, 63 deletions

diff --git a/include/linux/blk-integrity.h b/include/linux/blk-integrity.h
index 378b2459efe2..e253e7bd0d17 100644
--- a/include/linux/blk-integrity.h
+++ b/include/linux/blk-integrity.h
@@ -20,6 +20,7 @@ struct blk_integrity_iter {
 	unsigned int		data_size;
 	unsigned short		interval;
 	unsigned char		tuple_size;
+	unsigned char		pi_offset;
 	const char		*disk_name;
 };
 
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 492b0128b5d9..d3d8fd8e229b 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -684,17 +684,19 @@ enum {
 
 #define BLK_MQ_NO_HCTX_IDX	(-1U)
 
-struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, void *queuedata,
+struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set,
+		struct queue_limits *lim, void *queuedata,
 		struct lock_class_key *lkclass);
-#define blk_mq_alloc_disk(set, queuedata)				\
+#define blk_mq_alloc_disk(set, lim, queuedata)				\
 ({									\
 	static struct lock_class_key __key;				\
 									\
-	__blk_mq_alloc_disk(set, queuedata, &__key);			\
+	__blk_mq_alloc_disk(set, lim, queuedata, &__key);		\
 })
 struct gendisk *blk_mq_alloc_disk_for_queue(struct request_queue *q,
 		struct lock_class_key *lkclass);
-struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *);
+struct request_queue *blk_mq_alloc_queue(struct blk_mq_tag_set *set,
+		struct queue_limits *lim, void *queuedata);
 int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 		struct request_queue *q);
 void blk_mq_destroy_queue(struct request_queue *);
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 12d87cef2c03..cb1526ec44b5 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -207,52 +207,10 @@ static inline bool blk_path_error(blk_status_t error)
 	return true;
 }
 
-/*
- * From most significant bit:
- * 1 bit: reserved for other usage, see below
- * 12 bits: original size of bio
- * 51 bits: issue time of bio
- */
-#define BIO_ISSUE_RES_BITS      1
-#define BIO_ISSUE_SIZE_BITS     12
-#define BIO_ISSUE_RES_SHIFT     (64 - BIO_ISSUE_RES_BITS)
-#define BIO_ISSUE_SIZE_SHIFT    (BIO_ISSUE_RES_SHIFT - BIO_ISSUE_SIZE_BITS)
-#define BIO_ISSUE_TIME_MASK     ((1ULL << BIO_ISSUE_SIZE_SHIFT) - 1)
-#define BIO_ISSUE_SIZE_MASK     \
-	(((1ULL << BIO_ISSUE_SIZE_BITS) - 1) << BIO_ISSUE_SIZE_SHIFT)
-#define BIO_ISSUE_RES_MASK      (~((1ULL << BIO_ISSUE_RES_SHIFT) - 1))
-
-/* Reserved bit for blk-throtl */
-#define BIO_ISSUE_THROTL_SKIP_LATENCY (1ULL << 63)
-
 struct bio_issue {
 	u64 value;
 };
 
-static inline u64 __bio_issue_time(u64 time)
-{
-	return time & BIO_ISSUE_TIME_MASK;
-}
-
-static inline u64 bio_issue_time(struct bio_issue *issue)
-{
-	return __bio_issue_time(issue->value);
-}
-
-static inline sector_t bio_issue_size(struct bio_issue *issue)
-{
-	return ((issue->value & BIO_ISSUE_SIZE_MASK) >> BIO_ISSUE_SIZE_SHIFT);
-}
-
-static inline void bio_issue_init(struct bio_issue *issue,
-				       sector_t size)
-{
-	size &= (1ULL << BIO_ISSUE_SIZE_BITS) - 1;
-	issue->value = ((issue->value & BIO_ISSUE_RES_MASK) |
-			(ktime_get_ns() & BIO_ISSUE_TIME_MASK) |
-			((u64)size << BIO_ISSUE_SIZE_SHIFT));
-}
-
 typedef __u32 __bitwise blk_opf_t;
 
 typedef unsigned int blk_qc_t;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 2f5dbde23094..f9b87c39cab0 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -43,7 +43,7 @@ struct blk_crypto_profile;
 
 extern const struct device_type disk_type;
 extern const struct device_type part_type;
-extern struct class block_class;
+extern const struct class block_class;
 
 /*
  * Maximum number of blkcg policies allowed to be registered concurrently.
@@ -109,6 +109,7 @@ struct blk_integrity {
 	const struct blk_integrity_profile	*profile;
 	unsigned char				flags;
 	unsigned char				tuple_size;
+	unsigned char				pi_offset;
 	unsigned char				interval_exp;
 	unsigned char				tag_size;
 };
@@ -190,8 +191,6 @@ struct gendisk {
 	 * blk_mq_unfreeze_queue().
 	 */
 	unsigned int		nr_zones;
-	unsigned int		max_open_zones;
-	unsigned int		max_active_zones;
 	unsigned long		*conv_zones_bitmap;
 	unsigned long		*seq_zones_wlock;
 #endif /* CONFIG_BLK_DEV_ZONED */
@@ -293,6 +292,7 @@ struct queue_limits {
 	unsigned int		io_opt;
 	unsigned int		max_discard_sectors;
 	unsigned int		max_hw_discard_sectors;
+	unsigned int		max_user_discard_sectors;
 	unsigned int		max_secure_erase_sectors;
 	unsigned int		max_write_zeroes_sectors;
 	unsigned int		max_zone_append_sectors;
@@ -308,6 +308,8 @@ struct queue_limits {
 	unsigned char		discard_misaligned;
 	unsigned char		raid_partial_stripes_expensive;
 	bool			zoned;
+	unsigned int		max_open_zones;
+	unsigned int		max_active_zones;
 
 	/*
 	 * Drivers that set dma_alignment to less than 511 must be prepared to
@@ -326,7 +328,7 @@ void disk_set_zoned(struct gendisk *disk);
 int blkdev_report_zones(struct block_device *bdev, sector_t sector,
 		unsigned int nr_zones, report_zones_cb cb, void *data);
 int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op,
-		sector_t sectors, sector_t nr_sectors, gfp_t gfp_mask);
+		sector_t sectors, sector_t nr_sectors);
 int blk_revalidate_disk_zones(struct gendisk *disk,
 		void (*update_driver_data)(struct gendisk *disk));
 
@@ -474,6 +476,7 @@ struct request_queue {
 
 	struct mutex		sysfs_lock;
 	struct mutex		sysfs_dir_lock;
+	struct mutex		limits_lock;
 
 	/*
 	 * for reusing dead hctx instance in case of updating
@@ -640,23 +643,23 @@ static inline bool disk_zone_is_seq(struct gendisk *disk, sector_t sector)
 static inline void disk_set_max_open_zones(struct gendisk *disk,
 		unsigned int max_open_zones)
 {
-	disk->max_open_zones = max_open_zones;
+	disk->queue->limits.max_open_zones = max_open_zones;
 }
 
 static inline void disk_set_max_active_zones(struct gendisk *disk,
 		unsigned int max_active_zones)
 {
-	disk->max_active_zones = max_active_zones;
+	disk->queue->limits.max_active_zones = max_active_zones;
 }
 
 static inline unsigned int bdev_max_open_zones(struct block_device *bdev)
 {
-	return bdev->bd_disk->max_open_zones;
+	return bdev->bd_disk->queue->limits.max_open_zones;
 }
 
 static inline unsigned int bdev_max_active_zones(struct block_device *bdev)
 {
-	return bdev->bd_disk->max_active_zones;
+	return bdev->bd_disk->queue->limits.max_active_zones;
 }
 
 #else /* CONFIG_BLK_DEV_ZONED */
@@ -764,22 +767,26 @@ static inline u64 sb_bdev_nr_blocks(struct super_block *sb)
 int bdev_disk_changed(struct gendisk *disk, bool invalidate);
 
 void put_disk(struct gendisk *disk);
-struct gendisk *__blk_alloc_disk(int node, struct lock_class_key *lkclass);
+struct gendisk *__blk_alloc_disk(struct queue_limits *lim, int node,
+		struct lock_class_key *lkclass);
 
 /**
  * blk_alloc_disk - allocate a gendisk structure
+ * @lim: queue limits to be used for this disk.
  * @node_id: numa node to allocate on
  *
  * Allocate and pre-initialize a gendisk structure for use with BIO based
  * drivers.
  *
+ * Returns an ERR_PTR on error, else the allocated disk.
+ *
  * Context: can sleep
  */
-#define blk_alloc_disk(node_id)						\
+#define blk_alloc_disk(lim, node_id)					\
 ({									\
 	static struct lock_class_key __key;				\
 									\
-	__blk_alloc_disk(node_id, &__key);				\
+	__blk_alloc_disk(lim, node_id, &__key);				\
 })
 
 int __register_blkdev(unsigned int major, const char *name,
@@ -862,6 +869,29 @@ static inline unsigned int blk_chunk_sectors_left(sector_t offset,
 	return chunk_sectors - (offset & (chunk_sectors - 1));
 }
 
+/**
+ * queue_limits_start_update - start an atomic update of queue limits
+ * @q:		queue to update
+ *
+ * This functions starts an atomic update of the queue limits.  It takes a lock
+ * to prevent other updates and returns a snapshot of the current limits that
+ * 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.
+ */
+static inline struct queue_limits
+queue_limits_start_update(struct request_queue *q)
+	__acquires(q->limits_lock)
+{
+	mutex_lock(&q->limits_lock);
+	return q->limits;
+}
+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);
+
 /*
  * Access functions for manipulating queue properties
  */
@@ -895,8 +925,8 @@ extern void blk_set_queue_depth(struct request_queue *q, unsigned int depth);
 extern void blk_set_stacking_limits(struct queue_limits *lim);
 extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 			    sector_t offset);
-extern void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
-			      sector_t offset);
+void queue_limits_stack_bdev(struct queue_limits *t, struct block_device *bdev,
+		sector_t offset, const char *pfx);
 extern void blk_queue_update_dma_pad(struct request_queue *, unsigned int);
 extern void blk_queue_segment_boundary(struct request_queue *, unsigned long);
 extern void blk_queue_virt_boundary(struct request_queue *, unsigned long);
@@ -943,6 +973,7 @@ struct blk_plug {
 
 	/* if ios_left is > 1, we can batch tag/rq allocations */
 	struct request *cached_rq;
+	u64 cur_ktime;
 	unsigned short nr_ios;
 
 	unsigned short rq_count;
@@ -973,6 +1004,18 @@ static inline void blk_flush_plug(struct blk_plug *plug, bool async)
 		__blk_flush_plug(plug, async);
 }
 
+/*
+ * tsk == current here
+ */
+static inline void blk_plug_invalidate_ts(struct task_struct *tsk)
+{
+	struct blk_plug *plug = tsk->plug;
+
+	if (plug)
+		plug->cur_ktime = 0;
+	current->flags &= ~PF_BLOCK_TS;
+}
+
 int blkdev_issue_flush(struct block_device *bdev);
 long nr_blockdev_pages(void);
 #else /* CONFIG_BLOCK */
@@ -996,6 +1039,10 @@ static inline void blk_flush_plug(struct blk_plug *plug, bool async)
 {
 }
 
+static inline void blk_plug_invalidate_ts(struct task_struct *tsk)
+{
+}
+
 static inline int blkdev_issue_flush(struct block_device *bdev)
 {
 	return 0;
diff --git a/include/linux/nvme-rdma.h b/include/linux/nvme-rdma.h
index 4dd7e6fe92fb..eb2f04d636c8 100644
--- a/include/linux/nvme-rdma.h
+++ b/include/linux/nvme-rdma.h
@@ -6,7 +6,11 @@
 #ifndef _LINUX_NVME_RDMA_H
 #define _LINUX_NVME_RDMA_H
 
-#define NVME_RDMA_MAX_QUEUE_SIZE	128
+#define NVME_RDMA_IP_PORT		4420
+
+#define NVME_RDMA_MAX_QUEUE_SIZE 256
+#define NVME_RDMA_MAX_METADATA_QUEUE_SIZE 128
+#define NVME_RDMA_DEFAULT_QUEUE_SIZE 128
 
 enum nvme_rdma_cm_fmt {
 	NVME_RDMA_CM_FMT_1_0 = 0x0,
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 3ef4053ea950..425573202295 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -23,8 +23,6 @@
 
 #define NVME_DISC_SUBSYS_NAME	"nqn.2014-08.org.nvmexpress.discovery"
 
-#define NVME_RDMA_IP_PORT	4420
-
 #define NVME_NSID_ALL		0xffffffff
 
 enum nvme_subsys_type {
diff --git a/include/linux/sched.h b/include/linux/sched.h
index ffe8f618ab86..15b7cb478d16 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1642,7 +1642,7 @@ extern struct pid *cad_pid;
 #define PF_NO_SETAFFINITY	0x04000000	/* Userland is not allowed to meddle with cpus_mask */
 #define PF_MCE_EARLY		0x08000000      /* Early kill for mce process policy */
 #define PF_MEMALLOC_PIN		0x10000000	/* Allocation context constrained to zones which allow long term pinning. */
-#define PF__HOLE__20000000	0x20000000
+#define PF_BLOCK_TS		0x20000000	/* plug has ts that needs updating */
 #define PF__HOLE__40000000	0x40000000
 #define PF_SUSPEND_TASK		0x80000000      /* This thread called freeze_processes() and should not be frozen */
 
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index a6e04b4a21d7..11e0e00e0bb9 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -176,6 +176,7 @@ extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
 cpumask_var_t *alloc_sched_domains(unsigned int ndoms);
 void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms);
 
+bool cpus_equal_capacity(int this_cpu, int that_cpu);
 bool cpus_share_cache(int this_cpu, int that_cpu);
 bool cpus_share_resources(int this_cpu, int that_cpu);
 
@@ -226,6 +227,11 @@ partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
 {
 }
 
+static inline bool cpus_equal_capacity(int this_cpu, int that_cpu)
+{
+	return true;
+}
+
 static inline bool cpus_share_cache(int this_cpu, int that_cpu)
 {
 	return true;
diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h
index b9cfc5c96268..c8dc5f8ea699 100644
--- a/include/uapi/linux/ublk_cmd.h
+++ b/include/uapi/linux/ublk_cmd.h
@@ -49,6 +49,8 @@
 	_IOR('u', UBLK_CMD_GET_DEV_INFO2, struct ublksrv_ctrl_cmd)
 #define UBLK_U_CMD_GET_FEATURES	\
 	_IOR('u', 0x13, struct ublksrv_ctrl_cmd)
+#define UBLK_U_CMD_DEL_DEV_ASYNC	\
+	_IOR('u', 0x14, struct ublksrv_ctrl_cmd)
 
 /*
  * 64bits are enough now, and it should be easy to extend in case of