Merge tag 'for-6.19/block-20251201' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux

Pull block updates from Jens Axboe:

 - Fix head insertion for mq-deadline, a regression from when priority
   support was added

 - Series simplifying and improving the ublk user copy code

 - Various ublk related cleanups

 - Fixup REQ_NOWAIT handling in loop/zloop, clearing NOWAIT when the
   request is punted to a thread for handling

 - Merge and then later revert loop dio nowait support, as it ended up
   causing excessive stack usage for when the inline issue code needs to
   dip back into the full file system code

 - Improve auto integrity code, making it less deadlock prone

 - Speedup polled IO handling, but manually managing the hctx lookups

 - Fixes for blk-throttle for SSD devices

 - Small series with fixes for the S390 dasd driver

 - Add support for caching zones, avoiding unnecessary report zone
   queries

 - MD pull requests via Yu:
      - fix null-ptr-dereference regression for dm-raid0
      - fix IO hang for raid5 when array is broken with IO inflight
      - remove legacy 1s delay to speed up system shutdown
      - change maintainer's email address
      - data can be lost if array is created with different lbs devices,
        fix this problem and record lbs of the array in metadata
      - fix rcu protection for md_thread
      - fix mddev kobject lifetime regression
      - enable atomic writes for md-linear
      - some cleanups

 - bcache updates via Coly
      - remove useless discard and cache device code
      - improve usage of per-cpu workqueues

 - Reorganize the IO scheduler switching code, fixing some lockdep
   reports as well

 - Improve the block layer P2P DMA support

 - Add support to the block tracing code for zoned devices

 - Segment calculation improves, and memory alignment flexibility
   improvements

 - Set of prep and cleanups patches for ublk batching support. The
   actual batching hasn't been added yet, but helps shrink down the
   workload of getting that patchset ready for 6.20

 - Fix for how the ps3 block driver handles segments offsets

 - Improve how block plugging handles batch tag allocations

 - nbd fixes for use-after-free of the configuration on device clear/put

 - Set of improvements and fixes for zloop

 - Add Damien as maintainer of the block zoned device code handling

 - Various other fixes and cleanups

* tag 'for-6.19/block-20251201' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux: (162 commits)
  block/rnbd: correct all kernel-doc complaints
  blk-mq: use queue_hctx in blk_mq_map_queue_type
  md: remove legacy 1s delay in md_notify_reboot
  md/raid5: fix IO hang when array is broken with IO inflight
  md: warn about updating super block failure
  md/raid0: fix NULL pointer dereference in create_strip_zones() for dm-raid
  sbitmap: fix all kernel-doc warnings
  ublk: add helper of __ublk_fetch()
  ublk: pass const pointer to ublk_queue_is_zoned()
  ublk: refactor auto buffer register in ublk_dispatch_req()
  ublk: add `union ublk_io_buf` with improved naming
  ublk: add parameter `struct io_uring_cmd *` to ublk_prep_auto_buf_reg()
  kfifo: add kfifo_alloc_node() helper for NUMA awareness
  blk-mq: fix potential uaf for 'queue_hw_ctx'
  blk-mq: use array manage hctx map instead of xarray
  ublk: prevent invalid access with DEBUG
  s390/dasd: Use scnprintf() instead of sprintf()
  s390/dasd: Move device name formatting into separate function
  s390/dasd: Remove unnecessary debugfs_create() return checks
  s390/dasd: Fix gendisk parent after copy pair swap
  ...

4 files changed, 98 insertions, 9 deletions

diff --git a/include/uapi/linux/blktrace_api.h b/include/uapi/linux/blktrace_api.h
index 1bfb635e309b..7c092d9f3aa4 100644
--- a/include/uapi/linux/blktrace_api.h
+++ b/include/uapi/linux/blktrace_api.h
@@ -26,11 +26,22 @@ enum blktrace_cat {
 	BLK_TC_DRV_DATA	= 1 << 14,	/* binary per-driver data */
 	BLK_TC_FUA	= 1 << 15,	/* fua requests */
 
-	BLK_TC_END	= 1 << 15,	/* we've run out of bits! */
+	BLK_TC_END_V1	= 1 << 15,	/* we've run out of bits! */
+
+	BLK_TC_ZONE_APPEND	= 1ull << 16,  	/* zone append */
+	BLK_TC_ZONE_RESET	= 1ull << 17,	/* zone reset */
+	BLK_TC_ZONE_RESET_ALL	= 1ull << 18,	/* zone reset all */
+	BLK_TC_ZONE_FINISH	= 1ull << 19,	/* zone finish */
+	BLK_TC_ZONE_OPEN	= 1ull << 20,	/* zone open */
+	BLK_TC_ZONE_CLOSE	= 1ull << 21,	/* zone close */
+
+	BLK_TC_WRITE_ZEROES	= 1ull << 22,	/* write-zeroes */
+
+	BLK_TC_END_V2		= 1ull << 22,
 };
 
 #define BLK_TC_SHIFT		(16)
-#define BLK_TC_ACT(act)		((act) << BLK_TC_SHIFT)
+#define BLK_TC_ACT(act)		((u64)(act) << BLK_TC_SHIFT)
 
 /*
  * Basic trace actions
@@ -53,6 +64,8 @@ enum blktrace_act {
 	__BLK_TA_REMAP,			/* bio was remapped */
 	__BLK_TA_ABORT,			/* request aborted */
 	__BLK_TA_DRV_DATA,		/* driver-specific binary data */
+	__BLK_TA_ZONE_PLUG,		/* zone write plug was plugged */
+	__BLK_TA_ZONE_UNPLUG,		/* zone write plug was unplugged */
 	__BLK_TA_CGROUP = 1 << 8,	/* from a cgroup*/
 };
 
@@ -88,12 +101,19 @@ enum blktrace_notify {
 #define BLK_TA_ABORT		(__BLK_TA_ABORT | BLK_TC_ACT(BLK_TC_QUEUE))
 #define BLK_TA_DRV_DATA	(__BLK_TA_DRV_DATA | BLK_TC_ACT(BLK_TC_DRV_DATA))
 
+#define BLK_TA_ZONE_APPEND	(__BLK_TA_COMPLETE |\
+				 BLK_TC_ACT(BLK_TC_ZONE_APPEND))
+#define BLK_TA_ZONE_PLUG	(__BLK_TA_ZONE_PLUG | BLK_TC_ACT(BLK_TC_QUEUE))
+#define BLK_TA_ZONE_UNPLUG	(__BLK_TA_ZONE_UNPLUG |\
+				 BLK_TC_ACT(BLK_TC_QUEUE))
+
 #define BLK_TN_PROCESS		(__BLK_TN_PROCESS | BLK_TC_ACT(BLK_TC_NOTIFY))
 #define BLK_TN_TIMESTAMP	(__BLK_TN_TIMESTAMP | BLK_TC_ACT(BLK_TC_NOTIFY))
 #define BLK_TN_MESSAGE		(__BLK_TN_MESSAGE | BLK_TC_ACT(BLK_TC_NOTIFY))
 
 #define BLK_IO_TRACE_MAGIC	0x65617400
 #define BLK_IO_TRACE_VERSION	0x07
+#define BLK_IO_TRACE2_VERSION	0x08
 
 /*
  * The trace itself
@@ -113,6 +133,21 @@ struct blk_io_trace {
 	/* cgroup id will be stored here if exists */
 };
 
+struct blk_io_trace2 {
+	__u32 magic;		/* MAGIC << 8 | BLK_IO_TRACE2_VERSION */
+	__u32 sequence;		/* event number */
+	__u64 time;		/* in nanoseconds */
+	__u64 sector;		/* disk offset */
+	__u32 bytes;		/* transfer length */
+	__u32 pid;		/* who did it */
+	__u64 action;		/* what happened */
+	__u32 device;		/* device number */
+	__u32 cpu;		/* on what cpu did it happen */
+	__u16 error;		/* completion error */
+	__u16 pdu_len;		/* length of data after this trace */
+	__u8 pad[12];
+	/* cgroup id will be stored here if it exists */
+};
 /*
  * The remap event
  */
@@ -129,6 +164,7 @@ enum {
 };
 
 #define BLKTRACE_BDEV_SIZE	32
+#define BLKTRACE_BDEV_SIZE2	64
 
 /*
  * User setup structure passed with BLKTRACESETUP
@@ -143,4 +179,19 @@ struct blk_user_trace_setup {
 	__u32 pid;
 };
 
+/*
+ * User setup structure passed with BLKTRACESETUP2
+ */
+struct blk_user_trace_setup2 {
+	char name[BLKTRACE_BDEV_SIZE2];		/* output */
+	__u64 act_mask;				/* input */
+	__u32 buf_size;				/* input */
+	__u32 buf_nr;				/* input */
+	__u64 start_lba;
+	__u64 end_lba;
+	__u32 pid;
+	__u32 flags;		/* currently unused */
+	__u64 reserved[11];
+};
+
 #endif /* _UAPIBLKTRACE_H */
diff --git a/include/uapi/linux/blkzoned.h b/include/uapi/linux/blkzoned.h
index f85743ef6e7d..e33f02703350 100644
--- a/include/uapi/linux/blkzoned.h
+++ b/include/uapi/linux/blkzoned.h
@@ -48,6 +48,8 @@ enum blk_zone_type {
  *                      FINISH ZONE command.
  * @BLK_ZONE_COND_READONLY: The zone is read-only.
  * @BLK_ZONE_COND_OFFLINE: The zone is offline (sectors cannot be read/written).
+ * @BLK_ZONE_COND_ACTIVE: The zone is either implicitly open, explicitly open,
+ *			  or closed.
  *
  * The Zone Condition state machine in the ZBC/ZAC standards maps the above
  * deinitions as:
@@ -61,6 +63,13 @@ enum blk_zone_type {
  *
  * Conditions 0x5 to 0xC are reserved by the current ZBC/ZAC spec and should
  * be considered invalid.
+ *
+ * The condition BLK_ZONE_COND_ACTIVE is used only with cached zone reports.
+ * It is used to report any of the BLK_ZONE_COND_IMP_OPEN,
+ * BLK_ZONE_COND_EXP_OPEN and BLK_ZONE_COND_CLOSED conditions. Conversely, a
+ * regular zone report will never report a zone condition using
+ * BLK_ZONE_COND_ACTIVE and instead use the conditions BLK_ZONE_COND_IMP_OPEN,
+ * BLK_ZONE_COND_EXP_OPEN or BLK_ZONE_COND_CLOSED as reported by the device.
  */
 enum blk_zone_cond {
 	BLK_ZONE_COND_NOT_WP	= 0x0,
@@ -71,15 +80,27 @@ enum blk_zone_cond {
 	BLK_ZONE_COND_READONLY	= 0xD,
 	BLK_ZONE_COND_FULL	= 0xE,
 	BLK_ZONE_COND_OFFLINE	= 0xF,
+
+	BLK_ZONE_COND_ACTIVE	= 0xFF,
 };
 
 /**
  * enum blk_zone_report_flags - Feature flags of reported zone descriptors.
  *
- * @BLK_ZONE_REP_CAPACITY: Zone descriptor has capacity field.
+ * @BLK_ZONE_REP_CAPACITY: Output only. Indicates that zone descriptors in a
+ *			   zone report have a valid capacity field.
+ * @BLK_ZONE_REP_CACHED: Input only. Indicates that the zone report should be
+ *			 generated using cached zone information. In this case,
+ *			 the implicit open, explicit open and closed zone
+ *			 conditions are all reported with the
+ *			 BLK_ZONE_COND_ACTIVE condition.
  */
 enum blk_zone_report_flags {
-	BLK_ZONE_REP_CAPACITY	= (1 << 0),
+	/* Output flags */
+	BLK_ZONE_REP_CAPACITY	= (1U << 0),
+
+	/* Input flags */
+	BLK_ZONE_REP_CACHED	= (1U << 31),
 };
 
 /**
@@ -122,6 +143,10 @@ struct blk_zone {
  * @sector: starting sector of report
  * @nr_zones: IN maximum / OUT actual
  * @flags: one or more flags as defined by enum blk_zone_report_flags.
+ * @flags: one or more flags as defined by enum blk_zone_report_flags.
+ *	   With BLKREPORTZONE, this field is ignored as an input and is valid
+ *	   only as an output. Using BLKREPORTZONEV2, this field is used as both
+ *	   input and output.
  * @zones: Space to hold @nr_zones @zones entries on reply.
  *
  * The array of at most @nr_zones must follow this structure in memory.
@@ -148,9 +173,19 @@ struct blk_zone_range {
 /**
  * Zoned block device ioctl's:
  *
- * @BLKREPORTZONE: Get zone information. Takes a zone report as argument.
- *                 The zone report will start from the zone containing the
- *                 sector specified in the report request structure.
+ * @BLKREPORTZONE: Get zone information from a zoned device. Takes a zone report
+ *		   as argument. The zone report will start from the zone
+ *		   containing the sector specified in struct blk_zone_report.
+ *		   The flags field of struct blk_zone_report is used as an
+ *		   output only and ignored as an input.
+ *		   DEPRECATED, use BLKREPORTZONEV2 instead.
+ * @BLKREPORTZONEV2: Same as @BLKREPORTZONE but uses the flags field of
+ *		     struct blk_zone_report as an input, allowing to get a zone
+ *		     report using cached zone information if the flag
+ *		     BLK_ZONE_REP_CACHED is set. In such case, the zone report
+ *		     may include zones with the condition @BLK_ZONE_COND_ACTIVE
+ *		     (c.f. the description of this condition above for more
+ *		     details).
  * @BLKRESETZONE: Reset the write pointer of the zones in the specified
  *                sector range. The sector range must be zone aligned.
  * @BLKGETZONESZ: Get the device zone size in number of 512 B sectors.
@@ -169,5 +204,6 @@ struct blk_zone_range {
 #define BLKOPENZONE	_IOW(0x12, 134, struct blk_zone_range)
 #define BLKCLOSEZONE	_IOW(0x12, 135, struct blk_zone_range)
 #define BLKFINISHZONE	_IOW(0x12, 136, struct blk_zone_range)
+#define BLKREPORTZONEV2	_IOWR(0x12, 142, struct blk_zone_report)
 
 #endif /* _UAPI_BLKZONED_H */
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index beb4c2d1e41c..66ca526cf786 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -298,8 +298,9 @@ struct file_attr {
 #define BLKROTATIONAL _IO(0x12,126)
 #define BLKZEROOUT _IO(0x12,127)
 #define BLKGETDISKSEQ _IOR(0x12,128,__u64)
-/* 130-136 are used by zoned block device ioctls (uapi/linux/blkzoned.h) */
+/* 130-136 and 142 are used by zoned block device ioctls (uapi/linux/blkzoned.h) */
 /* 137-141 are used by blk-crypto ioctls (uapi/linux/blk-crypto.h) */
+#define BLKTRACESETUP2 _IOWR(0x12, 142, struct blk_user_trace_setup2)
 
 #define BMAP_IOCTL 1		/* obsolete - kept for compatibility */
 #define FIBMAP	   _IO(0x00,1)	/* bmap access */
diff --git a/include/uapi/linux/raid/md_p.h b/include/uapi/linux/raid/md_p.h
index ac74133a4768..310068bb2a1d 100644
--- a/include/uapi/linux/raid/md_p.h
+++ b/include/uapi/linux/raid/md_p.h
@@ -291,7 +291,8 @@ struct mdp_superblock_1 {
 	__le64	resync_offset;	/* data before this offset (from data_offset) known to be in sync */
 	__le32	sb_csum;	/* checksum up to devs[max_dev] */
 	__le32	max_dev;	/* size of devs[] array to consider */
-	__u8	pad3[64-32];	/* set to 0 when writing */
+	__le32  logical_block_size;	/* same as q->limits->logical_block_size */
+	__u8	pad3[64-36];	/* set to 0 when writing */
 
 	/* device state information. Indexed by dev_number.
 	 * 2 bytes per device