Merge tag 'md-next-20230814-resend' into loongarch-next

LoongArch architecture changes for 6.5 (raid5/6 optimization) depend on
the md changes to fix build and work, so merge them to create a base.

11 files changed, 122 insertions, 61 deletions

diff --git a/include/linux/bio.h b/include/linux/bio.h
index 11984ed29cb8..debbd8fcbabb 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -488,7 +488,12 @@ extern void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter,
 extern void bio_copy_data(struct bio *dst, struct bio *src);
 extern void bio_free_pages(struct bio *bio);
 void guard_bio_eod(struct bio *bio);
-void zero_fill_bio(struct bio *bio);
+void zero_fill_bio_iter(struct bio *bio, struct bvec_iter iter);
+
+static inline void zero_fill_bio(struct bio *bio)
+{
+	zero_fill_bio_iter(bio, bio->bi_iter);
+}
 
 static inline void bio_release_pages(struct bio *bio, bool mark_dirty)
 {
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 495ca198775f..958ed7e89b30 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -178,14 +178,10 @@ struct request {
 
 	struct {
 		unsigned int		seq;
-		struct list_head	list;
 		rq_end_io_fn		*saved_end_io;
 	} flush;
 
-	union {
-		struct __call_single_data csd;
-		u64 fifo_time;
-	};
+	u64 fifo_time;
 
 	/*
 	 * completion callback.
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 87d94be7825a..c1421da8d45e 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -538,6 +538,7 @@ struct request_queue {
 #define QUEUE_FLAG_ADD_RANDOM	10	/* Contributes to random pool */
 #define QUEUE_FLAG_SYNCHRONOUS	11	/* always completes in submit context */
 #define QUEUE_FLAG_SAME_FORCE	12	/* force complete on same CPU */
+#define QUEUE_FLAG_HW_WC	18	/* Write back caching supported */
 #define QUEUE_FLAG_INIT_DONE	14	/* queue is initialized */
 #define QUEUE_FLAG_STABLE_WRITES 15	/* don't modify blks until WB is done */
 #define QUEUE_FLAG_POLL		16	/* IO polling enabled if set */
@@ -846,6 +847,7 @@ extern const char *blk_op_str(enum req_op op);
 
 int blk_status_to_errno(blk_status_t status);
 blk_status_t errno_to_blk_status(int errno);
+const char *blk_status_to_str(blk_status_t status);
 
 /* only poll the hardware once, don't continue until a completion was found */
 #define BLK_POLL_ONESHOT		(1 << 0)
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 6cb3e9af78c9..c89ef50d5112 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -16,8 +16,6 @@
 #include <linux/wait.h>
 #include <linux/atomic.h>
 
-#ifdef CONFIG_BLOCK
-
 enum bh_state_bits {
 	BH_Uptodate,	/* Contains valid data */
 	BH_Dirty,	/* Is dirty */
@@ -198,7 +196,6 @@ void set_bh_page(struct buffer_head *bh,
 		struct page *page, unsigned long offset);
 void folio_set_bh(struct buffer_head *bh, struct folio *folio,
 		  unsigned long offset);
-bool try_to_free_buffers(struct folio *);
 struct buffer_head *folio_alloc_buffers(struct folio *folio, unsigned long size,
 					bool retry);
 struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size,
@@ -213,10 +210,6 @@ void end_buffer_async_write(struct buffer_head *bh, int uptodate);
 
 /* Things to do with buffers at mapping->private_list */
 void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode);
-int inode_has_buffers(struct inode *);
-void invalidate_inode_buffers(struct inode *);
-int remove_inode_buffers(struct inode *inode);
-int sync_mapping_buffers(struct address_space *mapping);
 int generic_buffers_fsync_noflush(struct file *file, loff_t start, loff_t end,
 				  bool datasync);
 int generic_buffers_fsync(struct file *file, loff_t start, loff_t end,
@@ -240,9 +233,6 @@ void __bforget(struct buffer_head *);
 void __breadahead(struct block_device *, sector_t block, unsigned int size);
 struct buffer_head *__bread_gfp(struct block_device *,
 				sector_t block, unsigned size, gfp_t gfp);
-void invalidate_bh_lrus(void);
-void invalidate_bh_lrus_cpu(void);
-bool has_bh_in_lru(int cpu, void *dummy);
 struct buffer_head *alloc_buffer_head(gfp_t gfp_flags);
 void free_buffer_head(struct buffer_head * bh);
 void unlock_buffer(struct buffer_head *bh);
@@ -258,8 +248,6 @@ int __bh_read(struct buffer_head *bh, blk_opf_t op_flags, bool wait);
 void __bh_read_batch(int nr, struct buffer_head *bhs[],
 		     blk_opf_t op_flags, bool force_lock);
 
-extern int buffer_heads_over_limit;
-
 /*
  * Generic address_space_operations implementations for buffer_head-backed
  * address_spaces.
@@ -291,18 +279,6 @@ int generic_cont_expand_simple(struct inode *inode, loff_t size);
 int block_commit_write(struct page *page, unsigned from, unsigned to);
 int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
 				get_block_t get_block);
-/* Convert errno to return value from ->page_mkwrite() call */
-static inline vm_fault_t block_page_mkwrite_return(int err)
-{
-	if (err == 0)
-		return VM_FAULT_LOCKED;
-	if (err == -EFAULT || err == -EAGAIN)
-		return VM_FAULT_NOPAGE;
-	if (err == -ENOMEM)
-		return VM_FAULT_OOM;
-	/* -ENOSPC, -EDQUOT, -EIO ... */
-	return VM_FAULT_SIGBUS;
-}
 sector_t generic_block_bmap(struct address_space *, sector_t, get_block_t *);
 int block_truncate_page(struct address_space *, loff_t, get_block_t *);
 
@@ -316,8 +292,6 @@ extern int buffer_migrate_folio_norefs(struct address_space *,
 #define buffer_migrate_folio_norefs NULL
 #endif
 
-void buffer_init(void);
-
 /*
  * inline definitions
  */
@@ -477,7 +451,20 @@ __bread(struct block_device *bdev, sector_t block, unsigned size)
 
 bool block_dirty_folio(struct address_space *mapping, struct folio *folio);
 
-#else /* CONFIG_BLOCK */
+#ifdef CONFIG_BUFFER_HEAD
+
+void buffer_init(void);
+bool try_to_free_buffers(struct folio *folio);
+int inode_has_buffers(struct inode *inode);
+void invalidate_inode_buffers(struct inode *inode);
+int remove_inode_buffers(struct inode *inode);
+int sync_mapping_buffers(struct address_space *mapping);
+void invalidate_bh_lrus(void);
+void invalidate_bh_lrus_cpu(void);
+bool has_bh_in_lru(int cpu, void *dummy);
+extern int buffer_heads_over_limit;
+
+#else /* CONFIG_BUFFER_HEAD */
 
 static inline void buffer_init(void) {}
 static inline bool try_to_free_buffers(struct folio *folio) { return true; }
@@ -485,9 +472,10 @@ static inline int inode_has_buffers(struct inode *inode) { return 0; }
 static inline void invalidate_inode_buffers(struct inode *inode) {}
 static inline int remove_inode_buffers(struct inode *inode) { return 1; }
 static inline int sync_mapping_buffers(struct address_space *mapping) { return 0; }
+static inline void invalidate_bh_lrus(void) {}
 static inline void invalidate_bh_lrus_cpu(void) {}
 static inline bool has_bh_in_lru(int cpu, void *dummy) { return false; }
 #define buffer_heads_over_limit 0
 
-#endif /* CONFIG_BLOCK */
+#endif /* CONFIG_BUFFER_HEAD */
 #endif /* _LINUX_BUFFER_HEAD_H */
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index e2b836c2e119..54f50d34fd9d 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -58,7 +58,11 @@ struct vm_fault;
 #define IOMAP_F_DIRTY		(1U << 1)
 #define IOMAP_F_SHARED		(1U << 2)
 #define IOMAP_F_MERGED		(1U << 3)
+#ifdef CONFIG_BUFFER_HEAD
 #define IOMAP_F_BUFFER_HEAD	(1U << 4)
+#else
+#define IOMAP_F_BUFFER_HEAD	0
+#endif /* CONFIG_BUFFER_HEAD */
 #define IOMAP_F_XATTR		(1U << 5)
 
 /*
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 34f9dba17c1a..c47a08e7dfab 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3403,6 +3403,24 @@ static inline vm_fault_t vmf_error(int err)
 	return VM_FAULT_SIGBUS;
 }
 
+/*
+ * Convert errno to return value for ->page_mkwrite() calls.
+ *
+ * This should eventually be merged with vmf_error() above, but will need a
+ * careful audit of all vmf_error() callers.
+ */
+static inline vm_fault_t vmf_fs_error(int err)
+{
+	if (err == 0)
+		return VM_FAULT_LOCKED;
+	if (err == -EFAULT || err == -EAGAIN)
+		return VM_FAULT_NOPAGE;
+	if (err == -ENOMEM)
+		return VM_FAULT_OOM;
+	/* -ENOSPC, -EDQUOT, -EIO ... */
+	return VM_FAULT_SIGBUS;
+}
+
 struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
 			 unsigned int foll_flags);
 
diff --git a/include/trace/events/block.h b/include/trace/events/block.h
index 40e60c33cc6f..0e128ad51460 100644
--- a/include/trace/events/block.h
+++ b/include/trace/events/block.h
@@ -12,6 +12,7 @@
 
 #define RWBS_LEN	8
 
+#ifdef CONFIG_BUFFER_HEAD
 DECLARE_EVENT_CLASS(block_buffer,
 
 	TP_PROTO(struct buffer_head *bh),
@@ -61,6 +62,7 @@ DEFINE_EVENT(block_buffer, block_dirty_buffer,
 
 	TP_ARGS(bh)
 );
+#endif /* CONFIG_BUFFER_HEAD */
 
 /**
  * block_rq_requeue - place block IO request back on a queue
diff --git a/include/trace/events/kyber.h b/include/trace/events/kyber.h
index bf7533f171ff..9d44781efc1c 100644
--- a/include/trace/events/kyber.h
+++ b/include/trace/events/kyber.h
@@ -31,8 +31,8 @@ TRACE_EVENT(kyber_latency,
 
 	TP_fast_assign(
 		__entry->dev		= dev;
-		strlcpy(__entry->domain, domain, sizeof(__entry->domain));
-		strlcpy(__entry->type, type, sizeof(__entry->type));
+		strscpy(__entry->domain, domain, sizeof(__entry->domain));
+		strscpy(__entry->type, type, sizeof(__entry->type));
 		__entry->percentile	= percentile;
 		__entry->numerator	= numerator;
 		__entry->denominator	= denominator;
@@ -59,7 +59,7 @@ TRACE_EVENT(kyber_adjust,
 
 	TP_fast_assign(
 		__entry->dev		= dev;
-		strlcpy(__entry->domain, domain, sizeof(__entry->domain));
+		strscpy(__entry->domain, domain, sizeof(__entry->domain));
 		__entry->depth		= depth;
 	),
 
@@ -81,7 +81,7 @@ TRACE_EVENT(kyber_throttled,
 
 	TP_fast_assign(
 		__entry->dev		= dev;
-		strlcpy(__entry->domain, domain, sizeof(__entry->domain));
+		strscpy(__entry->domain, domain, sizeof(__entry->domain));
 	),
 
 	TP_printk("%d,%d %s", MAJOR(__entry->dev), MINOR(__entry->dev),
diff --git a/include/trace/events/wbt.h b/include/trace/events/wbt.h
index 9c66e59d859c..4661f0d27062 100644
--- a/include/trace/events/wbt.h
+++ b/include/trace/events/wbt.h
@@ -33,7 +33,7 @@ TRACE_EVENT(wbt_stat,
 	),
 
 	TP_fast_assign(
-		strlcpy(__entry->name, bdi_dev_name(bdi),
+		strscpy(__entry->name, bdi_dev_name(bdi),
 			ARRAY_SIZE(__entry->name));
 		__entry->rmean		= stat[0].mean;
 		__entry->rmin		= stat[0].min;
@@ -68,7 +68,7 @@ TRACE_EVENT(wbt_lat,
 	),
 
 	TP_fast_assign(
-		strlcpy(__entry->name, bdi_dev_name(bdi),
+		strscpy(__entry->name, bdi_dev_name(bdi),
 			ARRAY_SIZE(__entry->name));
 		__entry->lat = div_u64(lat, 1000);
 	),
@@ -105,7 +105,7 @@ TRACE_EVENT(wbt_step,
 	),
 
 	TP_fast_assign(
-		strlcpy(__entry->name, bdi_dev_name(bdi),
+		strscpy(__entry->name, bdi_dev_name(bdi),
 			ARRAY_SIZE(__entry->name));
 		__entry->msg	= msg;
 		__entry->step	= step;
@@ -141,7 +141,7 @@ TRACE_EVENT(wbt_timer,
 	),
 
 	TP_fast_assign(
-		strlcpy(__entry->name, bdi_dev_name(bdi),
+		strscpy(__entry->name, bdi_dev_name(bdi),
 			ARRAY_SIZE(__entry->name));
 		__entry->status		= status;
 		__entry->step		= step;
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/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h
index 4b8558db90e1..2685e53e4752 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 +238,26 @@ 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		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 +278,10 @@ 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 +310,21 @@ 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 +367,13 @@ 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 +385,13 @@ 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