Merge branch 'for-next' of https://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux.git

7 files changed, 125 insertions, 20 deletions

diff --git a/include/linux/bio-integrity.h b/include/linux/bio-integrity.h
index 0ea2a8bf7efb..a954c97be0b3 100644
--- a/include/linux/bio-integrity.h
+++ b/include/linux/bio-integrity.h
@@ -151,7 +151,6 @@ void bio_integrity_setup_default(struct bio *bio);
 unsigned int fs_bio_integrity_alloc(struct bio *bio);
 void fs_bio_integrity_free(struct bio *bio);
 void fs_bio_integrity_generate(struct bio *bio);
-int fs_bio_integrity_verify(struct bio *bio, sector_t sector,
-		unsigned int size);
+int fs_bio_integrity_verify(struct bio *bio, struct bvec_iter *data_iter);
 
 #endif /* _LINUX_BIO_INTEGRITY_H */
diff --git a/include/linux/bio.h b/include/linux/bio.h
index bb3235497e67..75f8086351c0 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -256,6 +256,12 @@ static inline struct folio *bio_first_folio_all(struct bio *bio)
 	return page_folio(bio_first_page_all(bio));
 }
 
+static inline struct bio_vec *bio_last_bvec_all(struct bio *bio)
+{
+	WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED));
+	return &bio->bi_io_vec[bio->bi_vcnt - 1];
+}
+
 /**
  * struct folio_iter - State for iterating all folios in a bio.
  * @folio: The current folio we're iterating.  NULL after the last folio.
@@ -479,6 +485,7 @@ static inline void bio_init_inline(struct bio *bio, struct block_device *bdev,
 extern void bio_uninit(struct bio *);
 void bio_reset(struct bio *bio, struct block_device *bdev, blk_opf_t opf);
 void bio_reuse(struct bio *bio, blk_opf_t opf);
+void bio_prepare_reissue(struct bio *bio, struct block_device *bdev);
 void bio_chain(struct bio *, struct bio *);
 void bio_await(struct bio *bio, void *priv,
 	       void (*submit)(struct bio *bio, void *priv));
@@ -516,16 +523,18 @@ int bdev_rw_virt(struct block_device *bdev, sector_t sector, void *data,
 		size_t len, enum req_op op);
 
 int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter,
-		unsigned mem_align_mask, unsigned len_align_mask);
+		unsigned maxlen, unsigned mem_align_mask,
+		unsigned len_align_mask);
 
 bool bio_iov_iter_set(struct bio *bio, const struct iov_iter *iter);
 void __bio_release_pages(struct bio *bio, bool mark_dirty);
 extern void bio_set_pages_dirty(struct bio *bio);
 extern void bio_check_pages_dirty(struct bio *bio);
 
-int bio_iov_iter_bounce(struct bio *bio, struct iov_iter *iter, size_t maxlen,
-		size_t minsize);
-void bio_iov_iter_unbounce(struct bio *bio, bool is_error, bool mark_dirty);
+int bio_alloc_bounce_folios(struct bio *bio, size_t total_len, size_t minsize);
+void bio_free_folios(struct bio *bio);
+int bio_iov_iter_bounce_write(struct bio *bio, struct iov_iter *iter,
+		size_t maxlen, size_t minsize);
 
 extern void bio_copy_data(struct bio *dst, struct bio *src);
 extern void bio_free_pages(struct bio *bio);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 4f7905c3412b..d003a9d2d1f6 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -191,14 +191,17 @@ struct gendisk {
 #ifdef CONFIG_BLK_DEV_ZONED
 	/*
 	 * Zoned block device information. Reads of this information must be
-	 * protected with blk_queue_enter() / blk_queue_exit(). Modifying this
-	 * information is only allowed while no requests are being processed.
-	 * See also blk_mq_freeze_queue() and blk_mq_unfreeze_queue().
+	 * protected with blk_queue_enter() / blk_queue_exit() or by holding a
+	 * lock on zone_revalidate_mutex. blk_revalidate_disk_zones() may modify
+	 * this information while no requests are being processed (disk queue
+	 * frozen with blk_mq_freeze_queue()) and while holding a lock on
+	 * zone_revalidate_mutex.
 	 */
+	struct mutex		zone_revalidate_mutex;
 	unsigned int		nr_zones;
 	unsigned int		zone_capacity;
 	unsigned int		last_zone_capacity;
-	u8 __rcu		*zones_cond;
+	u8 __rcu		*zones_state;
 	unsigned int		zone_wplugs_hash_bits;
 	atomic_t		nr_zone_wplugs;
 	spinlock_t		zone_wplugs_hash_lock;
@@ -1816,9 +1819,11 @@ static inline int bio_split_rw_at(struct bio *bio,
  */
 static inline unsigned int max_integrity_io_size(struct queue_limits *lim)
 {
-	return min_t(unsigned int, lim->max_segment_size,
-		(BLK_INTEGRITY_MAX_SIZE / lim->integrity.metadata_size) <<
-			lim->integrity.interval_exp);
+	u64 max_intervals;
+
+	max_intervals = BLK_INTEGRITY_MAX_SIZE / lim->integrity.metadata_size;
+	return min_t(u64, lim->max_segment_size,
+		max_intervals << lim->integrity.interval_exp);
 }
 
 #define DEFINE_IO_COMP_BATCH(name)	struct io_comp_batch name = { }
diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index d1aa4edfc2a5..505caa99c621 100644
--- a/include/linux/io_uring.h
+++ b/include/linux/io_uring.h
@@ -2,10 +2,42 @@
 #ifndef _LINUX_IO_URING_H
 #define _LINUX_IO_URING_H
 
+#include <linux/io_uring_types.h>
 #include <linux/sched.h>
 #include <linux/xarray.h>
 #include <uapi/linux/io_uring.h>
 
+static inline void req_set_fail(struct io_kiocb *req)
+{
+	req->flags |= REQ_F_FAIL;
+	if (req->flags & REQ_F_CQE_SKIP) {
+		req->flags &= ~REQ_F_CQE_SKIP;
+		req->flags |= REQ_F_SKIP_LINK_CQES;
+	}
+}
+
+static inline void io_req_set_res(struct io_kiocb *req, s32 res, u32 cflags)
+{
+	req->cqe.res = res;
+	req->cqe.flags = cflags;
+}
+
+static inline u32 ctx_cqe32_flags(struct io_ring_ctx *ctx)
+{
+	if (ctx->flags & IORING_SETUP_CQE_MIXED)
+		return IORING_CQE_F_32;
+	return 0;
+}
+
+static inline void io_req_set_res32(struct io_kiocb *req, s32 res, u32 cflags,
+				    __u64 extra1, __u64 extra2)
+{
+	req->cqe.res = res;
+	req->cqe.flags = cflags | ctx_cqe32_flags(req->ctx);
+	req->big_cqe.extra1 = extra1;
+	req->big_cqe.extra2 = extra2;
+}
+
 #if defined(CONFIG_IO_URING)
 void __io_uring_cancel(bool cancel_all);
 void __io_uring_free(struct task_struct *tsk);
diff --git a/include/linux/io_uring/cmd.h b/include/linux/io_uring/cmd.h
index 42801f0b6456..e18d4af62e1a 100644
--- a/include/linux/io_uring/cmd.h
+++ b/include/linux/io_uring/cmd.h
@@ -3,6 +3,7 @@
 #define _LINUX_IO_URING_CMD_H
 
 #include <uapi/linux/io_uring.h>
+#include <linux/io_uring.h>
 #include <linux/io_uring_types.h>
 #include <linux/blk-mq.h>
 
@@ -41,6 +42,24 @@ static inline void io_uring_cmd_private_sz_check(size_t cmd_sz)
 	((pdu_type *)&(cmd)->pdu) \
 )
 
+static inline void io_uring_cmd_set_res(struct io_uring_cmd *cmd, s32 ret)
+{
+	struct io_kiocb *req = cmd_to_io_kiocb(cmd);
+
+	if (ret < 0)
+		req_set_fail(req);
+	io_req_set_res(req, ret, 0);
+}
+
+static inline void io_uring_cmd_set_res32(struct io_uring_cmd *cmd, s32 ret, u64 res2)
+{
+	struct io_kiocb *req = cmd_to_io_kiocb(cmd);
+
+	if (ret < 0)
+		req_set_fail(req);
+	io_req_set_res32(req, ret, 0, res2, 0);
+}
+
 #if defined(CONFIG_IO_URING)
 int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
 			      struct iov_iter *iter,
@@ -56,11 +75,12 @@ int io_uring_cmd_import_fixed_vec(struct io_uring_cmd *ioucmd,
  * Completes the request, i.e. posts an io_uring CQE and deallocates @ioucmd
  * and the corresponding io_uring request.
  *
+ * io_uring_cmd_set_res()/io_uring_cmd_set_res32() must be called first.
+ *
  * Note: the caller should never hard code @issue_flags and is only allowed
  * to pass the mask provided by the core io_uring code.
  */
-void __io_uring_cmd_done(struct io_uring_cmd *cmd, s32 ret, u64 res2,
-			 unsigned issue_flags, bool is_cqe32);
+void __io_uring_cmd_done(struct io_uring_cmd *, unsigned issue_flags);
 
 void __io_uring_cmd_do_in_task(struct io_uring_cmd *ioucmd,
 			    io_req_tw_func_t task_work_cb,
@@ -116,8 +136,8 @@ static inline int io_uring_cmd_import_fixed_vec(struct io_uring_cmd *ioucmd,
 {
 	return -EOPNOTSUPP;
 }
-static inline void __io_uring_cmd_done(struct io_uring_cmd *cmd, s32 ret,
-		u64 ret2, unsigned issue_flags, bool is_cqe32)
+static inline void __io_uring_cmd_done(struct io_uring_cmd *cmd,
+				       unsigned issue_flags)
 {
 }
 static inline void __io_uring_cmd_do_in_task(struct io_uring_cmd *ioucmd,
@@ -205,13 +225,15 @@ static inline void *io_uring_cmd_ctx_handle(struct io_uring_cmd *cmd)
 static inline void io_uring_cmd_done(struct io_uring_cmd *ioucmd, s32 ret,
 				     unsigned issue_flags)
 {
-	return __io_uring_cmd_done(ioucmd, ret, 0, issue_flags, false);
+	io_uring_cmd_set_res(ioucmd, ret);
+	__io_uring_cmd_done(ioucmd, issue_flags);
 }
 
 static inline void io_uring_cmd_done32(struct io_uring_cmd *ioucmd, s32 ret,
 				       u64 res2, unsigned issue_flags)
 {
-	return __io_uring_cmd_done(ioucmd, ret, res2, issue_flags, true);
+	io_uring_cmd_set_res32(ioucmd, ret, res2);
+	__io_uring_cmd_done(ioucmd, issue_flags);
 }
 
 #endif /* _LINUX_IO_URING_CMD_H */
diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index 39629ee77b91..90fea94ad202 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -522,6 +522,8 @@ struct io_ring_ctx {
 
 	/* protected by ->completion_lock */
 	unsigned			nr_req_allocated;
+	/* pending SEND_ZC notifications, protected by ->uring_lock */
+	unsigned			nr_notifs;
 
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	struct list_head	napi_list;	/* track busy poll napi_id */
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index bc7ae6327dbf..59718f73c15a 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -483,13 +483,35 @@ sector_t iomap_bmap(struct address_space *mapping, sector_t bno,
 #define IOMAP_IOEND_BOUNDARY		(1U << 2)
 /* is direct I/O */
 #define IOMAP_IOEND_DIRECT		(1U << 3)
+/* generate integrity (PI) information */
+#ifdef CONFIG_BLK_DEV_INTEGRITY
+#define IOMAP_IOEND_INTEGRITY		(1U << 4)
+#else
+#define IOMAP_IOEND_INTEGRITY		0
+#endif /* CONFIG_BLK_DEV_INTEGRITY */
 
 /*
  * Flags that if set on either ioend prevent the merge of two ioends.
  * (IOMAP_IOEND_BOUNDARY also prevents merges, but only one-way)
  */
 #define IOMAP_IOEND_NOMERGE_FLAGS \
-	(IOMAP_IOEND_SHARED | IOMAP_IOEND_UNWRITTEN | IOMAP_IOEND_DIRECT)
+	(IOMAP_IOEND_SHARED | IOMAP_IOEND_UNWRITTEN | IOMAP_IOEND_DIRECT | \
+	 IOMAP_IOEND_INTEGRITY)
+
+/* ioend flags directly implied by iomap flags */
+static inline u16 iomap_ioend_flags(const struct iomap *iomap)
+{
+	unsigned int flags = 0;
+
+	if (iomap->type == IOMAP_UNWRITTEN)
+		flags |= IOMAP_IOEND_UNWRITTEN;
+	if (iomap->flags & IOMAP_F_SHARED)
+		flags |= IOMAP_IOEND_SHARED;
+	if (iomap->flags & IOMAP_F_INTEGRITY)
+		flags |= IOMAP_IOEND_INTEGRITY;
+
+	return flags;
+}
 
 /*
  * Structure for writeback I/O completions.
@@ -500,6 +522,7 @@ sector_t iomap_bmap(struct address_space *mapping, sector_t bno,
 struct iomap_ioend {
 	struct list_head	io_list;	/* next ioend in chain */
 	u16			io_flags;	/* IOMAP_IOEND_* */
+	u32			io_bvec_offset;	/* offset into first bvec */
 	struct inode		*io_inode;	/* file being written to */
 	size_t			io_size;	/* size of the extent */
 	atomic_t		io_remaining;	/* completetion defer count */
@@ -517,6 +540,13 @@ static inline struct iomap_ioend *iomap_ioend_from_bio(struct bio *bio)
 	return container_of(bio, struct iomap_ioend, io_bio);
 }
 
+#define BVEC_ITER_IOEND(_ioend)				\
+{							\
+	.bi_sector	= (_ioend)->io_sector,		\
+	.bi_size	= (_ioend)->io_size,		\
+	.bi_offset	= (_ioend)->io_bvec_offset,	\
+}
+
 struct iomap_writeback_ops {
 	/*
 	 * Performs writeback on the passed in range
@@ -565,6 +595,7 @@ void iomap_finish_ioends(struct iomap_ioend *ioend, int error);
 void iomap_ioend_try_merge(struct iomap_ioend *ioend,
 		struct list_head *more_ioends);
 void iomap_sort_ioends(struct list_head *ioend_list);
+int iomap_ioend_integrity_verify(struct iomap_ioend *ioend);
 ssize_t iomap_add_to_ioend(struct iomap_writepage_ctx *wpc, struct folio *folio,
 		loff_t pos, loff_t end_pos, unsigned int dirty_len);
 int iomap_ioend_writeback_submit(struct iomap_writepage_ctx *wpc, int error);
@@ -577,6 +608,11 @@ void iomap_finish_folio_write(struct inode *inode, struct folio *folio,
 int iomap_writeback_folio(struct iomap_writepage_ctx *wpc, struct folio *folio);
 int iomap_writepages(struct iomap_writepage_ctx *wpc);
 
+void iomap_bounce_read(struct iomap_ioend *orig_ioend, unsigned int minsize,
+		void (*submit_ioend)(struct iomap_ioend *ioend));
+void iomap_bounce_read_end_io(struct iomap_ioend *ioend, struct bio *orig_bio,
+		int error);
+
 struct iomap_read_folio_ctx {
 	const struct iomap_read_ops *ops;
 	struct folio		*cur_folio;