Merge tag 'for-6.6/block-2023-08-28' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:
 "Pretty quiet round for this release. This contains:

   - Add support for zoned storage to ublk (Andreas, Ming)

   - Series improving performance for drivers that mark themselves as
     needing a blocking context for issue (Bart)

   - Cleanup the flush logic (Chengming)

   - sed opal keyring support (Greg)

   - Fixes and improvements to the integrity support (Jinyoung)

   - Add some exports for bcachefs that we can hopefully delete again in
     the future (Kent)

   - deadline throttling fix (Zhiguo)

   - Series allowing building the kernel without buffer_head support
     (Christoph)

   - Sanitize the bio page adding flow (Christoph)

   - Write back cache fixes (Christoph)

   - MD updates via Song:
      - Fix perf regression for raid0 large sequential writes (Jan)
      - Fix split bio iostat for raid0 (David)
      - Various raid1 fixes (Heinz, Xueshi)
      - raid6test build fixes (WANG)
      - Deprecate bitmap file support (Christoph)
      - Fix deadlock with md sync thread (Yu)
      - Refactor md io accounting (Yu)
      - Various non-urgent fixes (Li, Yu, Jack)

   - Various fixes and cleanups (Arnd, Azeem, Chengming, Damien, Li,
     Ming, Nitesh, Ruan, Tejun, Thomas, Xu)"

* tag 'for-6.6/block-2023-08-28' of git://git.kernel.dk/linux: (113 commits)
  block: use strscpy() to instead of strncpy()
  block: sed-opal: keyring support for SED keys
  block: sed-opal: Implement IOC_OPAL_REVERT_LSP
  block: sed-opal: Implement IOC_OPAL_DISCOVERY
  blk-mq: prealloc tags when increase tagset nr_hw_queues
  blk-mq: delete redundant tagset map update when fallback
  blk-mq: fix tags leak when shrink nr_hw_queues
  ublk: zoned: support REQ_OP_ZONE_RESET_ALL
  md: raid0: account for split bio in iostat accounting
  md/raid0: Fix performance regression for large sequential writes
  md/raid0: Factor out helper for mapping and submitting a bio
  md raid1: allow writebehind to work on any leg device set WriteMostly
  md/raid1: hold the barrier until handle_read_error() finishes
  md/raid1: free the r1bio before waiting for blocked rdev
  md/raid1: call free_r1bio() before allow_barrier() in raid_end_bio_io()
  blk-cgroup: Fix NULL deref caused by blkg_policy_data being installed before init
  drivers/rnbd: restore sysfs interface to rnbd-client
  md/raid5-cache: fix null-ptr-deref for r5l_flush_stripe_to_raid()
  raid6: test: only check for Altivec if building on powerpc hosts
  raid6: test: make sure all intermediate and artifact files are .gitignored
  ...

3 files changed, 90 insertions, 20 deletions

diff --git a/include/uapi/linux/ioprio.h b/include/uapi/linux/ioprio.h
index 99440b2e8c35..bee2bdb0eedb 100644
--- a/include/uapi/linux/ioprio.h
+++ b/include/uapi/linux/ioprio.h
@@ -107,20 +107,21 @@ enum {
 /*
  * Return an I/O priority value based on a class, a level and a hint.
  */
-static __always_inline __u16 ioprio_value(int class, int level, int hint)
+static __always_inline __u16 ioprio_value(int prioclass, int priolevel,
+					  int priohint)
 {
-	if (IOPRIO_BAD_VALUE(class, IOPRIO_NR_CLASSES) ||
-	    IOPRIO_BAD_VALUE(level, IOPRIO_NR_LEVELS) ||
-	    IOPRIO_BAD_VALUE(hint, IOPRIO_NR_HINTS))
+	if (IOPRIO_BAD_VALUE(prioclass, IOPRIO_NR_CLASSES) ||
+	    IOPRIO_BAD_VALUE(priolevel, IOPRIO_NR_LEVELS) ||
+	    IOPRIO_BAD_VALUE(priohint, IOPRIO_NR_HINTS))
 		return IOPRIO_CLASS_INVALID << IOPRIO_CLASS_SHIFT;
 
-	return (class << IOPRIO_CLASS_SHIFT) |
-		(hint << IOPRIO_HINT_SHIFT) | level;
+	return (prioclass << IOPRIO_CLASS_SHIFT) |
+		(priohint << IOPRIO_HINT_SHIFT) | priolevel;
 }
 
-#define IOPRIO_PRIO_VALUE(class, level)			\
-	ioprio_value(class, level, IOPRIO_HINT_NONE)
-#define IOPRIO_PRIO_VALUE_HINT(class, level, hint)	\
-	ioprio_value(class, level, hint)
+#define IOPRIO_PRIO_VALUE(prioclass, priolevel)			\
+	ioprio_value(prioclass, priolevel, IOPRIO_HINT_NONE)
+#define IOPRIO_PRIO_VALUE_HINT(prioclass, priolevel, priohint)	\
+	ioprio_value(prioclass, priolevel, priohint)
 
 #endif /* _UAPI_LINUX_IOPRIO_H */
diff --git a/include/uapi/linux/sed-opal.h b/include/uapi/linux/sed-opal.h
index dc2efd345133..d3994b7716bc 100644
--- a/include/uapi/linux/sed-opal.h
+++ b/include/uapi/linux/sed-opal.h
@@ -49,13 +49,23 @@ enum opal_lock_flags {
 	OPAL_SAVE_FOR_LOCK = 0x01,
 };
 
+enum opal_key_type {
+	OPAL_INCLUDED = 0,	/* key[] is the key */
+	OPAL_KEYRING,		/* key is in keyring */
+};
+
 struct opal_key {
 	__u8 lr;
 	__u8 key_len;
-	__u8 __align[6];
+	__u8 key_type;
+	__u8 __align[5];
 	__u8 key[OPAL_KEY_MAX];
 };
 
+enum opal_revert_lsp_opts {
+	OPAL_PRESERVE = 0x01,
+};
+
 struct opal_lr_act {
 	struct opal_key key;
 	__u32 sum;
@@ -173,6 +183,17 @@ struct opal_geometry {
 	__u8  __align[3];
 };
 
+struct opal_discovery {
+	__u64 data;
+	__u64 size;
+};
+
+struct opal_revert_lsp {
+	struct opal_key key;
+	__u32 options;
+	__u32 __pad;
+};
+
 #define IOC_OPAL_SAVE		    _IOW('p', 220, struct opal_lock_unlock)
 #define IOC_OPAL_LOCK_UNLOCK	    _IOW('p', 221, struct opal_lock_unlock)
 #define IOC_OPAL_TAKE_OWNERSHIP	    _IOW('p', 222, struct opal_key)
@@ -192,5 +213,7 @@ struct opal_geometry {
 #define IOC_OPAL_GET_STATUS         _IOR('p', 236, struct opal_status)
 #define IOC_OPAL_GET_LR_STATUS      _IOW('p', 237, struct opal_lr_status)
 #define IOC_OPAL_GET_GEOMETRY       _IOR('p', 238, struct opal_geometry)
+#define IOC_OPAL_DISCOVERY          _IOW('p', 239, struct opal_discovery)
+#define IOC_OPAL_REVERT_LSP         _IOW('p', 240, struct opal_revert_lsp)
 
 #endif /* _UAPI_SED_OPAL_H */
diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h
index 4b8558db90e1..b9cfc5c96268 100644
--- a/include/uapi/linux/ublk_cmd.h
+++ b/include/uapi/linux/ublk_cmd.h
@@ -176,6 +176,12 @@
 /* Copy between request and user buffer by pread()/pwrite() */
 #define UBLK_F_USER_COPY	(1UL << 7)
 
+/*
+ * User space sets this flag when setting up the device to request zoned storage support. Kernel may
+ * deny the request by returning an error.
+ */
+#define UBLK_F_ZONED (1ULL << 8)
+
 /* device state */
 #define UBLK_S_DEV_DEAD	0
 #define UBLK_S_DEV_LIVE	1
@@ -232,9 +238,27 @@ struct ublksrv_ctrl_dev_info {
 #define		UBLK_IO_OP_READ		0
 #define		UBLK_IO_OP_WRITE		1
 #define		UBLK_IO_OP_FLUSH		2
-#define		UBLK_IO_OP_DISCARD	3
-#define		UBLK_IO_OP_WRITE_SAME	4
-#define		UBLK_IO_OP_WRITE_ZEROES	5
+#define		UBLK_IO_OP_DISCARD		3
+#define		UBLK_IO_OP_WRITE_SAME		4
+#define		UBLK_IO_OP_WRITE_ZEROES		5
+#define		UBLK_IO_OP_ZONE_OPEN		10
+#define		UBLK_IO_OP_ZONE_CLOSE		11
+#define		UBLK_IO_OP_ZONE_FINISH		12
+#define		UBLK_IO_OP_ZONE_APPEND		13
+#define		UBLK_IO_OP_ZONE_RESET_ALL	14
+#define		UBLK_IO_OP_ZONE_RESET		15
+/*
+ * Construct a zone report. The report request is carried in `struct
+ * ublksrv_io_desc`. The `start_sector` field must be the first sector of a zone
+ * and shall indicate the first zone of the report. The `nr_zones` shall
+ * indicate how many zones should be reported at most. The report shall be
+ * delivered as a `struct blk_zone` array. To report fewer zones than requested,
+ * zero the last entry of the returned array.
+ *
+ * Related definitions(blk_zone, blk_zone_cond, blk_zone_type, ...) in
+ * include/uapi/linux/blkzoned.h are part of ublk UAPI.
+ */
+#define		UBLK_IO_OP_REPORT_ZONES		18
 
 #define		UBLK_IO_F_FAILFAST_DEV		(1U << 8)
 #define		UBLK_IO_F_FAILFAST_TRANSPORT	(1U << 9)
@@ -255,7 +279,10 @@ struct ublksrv_io_desc {
 	/* op: bit 0-7, flags: bit 8-31 */
 	__u32		op_flags;
 
-	__u32		nr_sectors;
+	union {
+		__u32		nr_sectors;
+		__u32		nr_zones; /* for UBLK_IO_OP_REPORT_ZONES */
+	};
 
 	/* start sector for this io */
 	__u64		start_sector;
@@ -284,11 +311,21 @@ struct ublksrv_io_cmd {
 	/* io result, it is valid for COMMIT* command only */
 	__s32	result;
 
-	/*
-	 * userspace buffer address in ublksrv daemon process, valid for
-	 * FETCH* command only
-	 */
-	__u64	addr;
+	union {
+		/*
+		 * userspace buffer address in ublksrv daemon process, valid for
+		 * FETCH* command only
+		 *
+		 * `addr` should not be used when UBLK_F_USER_COPY is enabled,
+		 * because userspace handles data copy by pread()/pwrite() over
+		 * /dev/ublkcN. But in case of UBLK_F_ZONED, this union is
+		 * re-used to pass back the allocated LBA for
+		 * UBLK_IO_OP_ZONE_APPEND which actually depends on
+		 * UBLK_F_USER_COPY
+		 */
+		__u64	addr;
+		__u64	zone_append_lba;
+	};
 };
 
 struct ublk_param_basic {
@@ -331,6 +368,13 @@ struct ublk_param_devt {
 	__u32   disk_minor;
 };
 
+struct ublk_param_zoned {
+	__u32	max_open_zones;
+	__u32	max_active_zones;
+	__u32	max_zone_append_sectors;
+	__u8	reserved[20];
+};
+
 struct ublk_params {
 	/*
 	 * Total length of parameters, userspace has to set 'len' for both
@@ -342,11 +386,13 @@ struct ublk_params {
 #define UBLK_PARAM_TYPE_BASIC           (1 << 0)
 #define UBLK_PARAM_TYPE_DISCARD         (1 << 1)
 #define UBLK_PARAM_TYPE_DEVT            (1 << 2)
+#define UBLK_PARAM_TYPE_ZONED           (1 << 3)
 	__u32	types;			/* types of parameter included */
 
 	struct ublk_param_basic		basic;
 	struct ublk_param_discard	discard;
 	struct ublk_param_devt		devt;
+	struct ublk_param_zoned	zoned;
 };
 
 #endif