Merge tag 'for-6.14/io_uring-20250119' of git://git.kernel.dk/linux

Pull io_uring updates from Jens Axboe:
 "Not a lot in terms of features this time around, mostly just cleanups
  and code consolidation:

   - Support for PI meta data read/write via io_uring, with NVMe and
     SCSI covered

   - Cleanup the per-op structure caching, making it consistent across
     various command types

   - Consolidate the various user mapped features into a concept called
     regions, making the various users of that consistent

   - Various cleanups and fixes"

* tag 'for-6.14/io_uring-20250119' of git://git.kernel.dk/linux: (56 commits)
  io_uring/fdinfo: fix io_uring_show_fdinfo() misuse of ->d_iname
  io_uring: reuse io_should_terminate_tw() for cmds
  io_uring: Factor out a function to parse restrictions
  io_uring/rsrc: require cloned buffers to share accounting contexts
  io_uring: simplify the SQPOLL thread check when cancelling requests
  io_uring: expose read/write attribute capability
  io_uring/rw: don't gate retry on completion context
  io_uring/rw: handle -EAGAIN retry at IO completion time
  io_uring/rw: use io_rw_recycle() from cleanup path
  io_uring/rsrc: simplify the bvec iter count calculation
  io_uring: ensure io_queue_deferred() is out-of-line
  io_uring/rw: always clear ->bytes_done on io_async_rw setup
  io_uring/rw: use NULL for rw->free_iovec assigment
  io_uring/rw: don't mask in f_iocb_flags
  io_uring/msg_ring: Drop custom destructor
  io_uring: Move old async data allocation helper to header
  io_uring/rw: Allocate async data through helper
  io_uring/net: Allocate msghdr async data through helper
  io_uring/uring_cmd: Allocate async data through generic helper
  io_uring/poll: Allocate apoll with generic alloc_cache helper
  ...

6 files changed, 68 insertions, 19 deletions

diff --git a/include/linux/bio-integrity.h b/include/linux/bio-integrity.h
index dbf0f74c1529..802f52e38efd 100644
--- a/include/linux/bio-integrity.h
+++ b/include/linux/bio-integrity.h
@@ -7,10 +7,12 @@
 enum bip_flags {
 	BIP_BLOCK_INTEGRITY	= 1 << 0, /* block layer owns integrity data */
 	BIP_MAPPED_INTEGRITY	= 1 << 1, /* ref tag has been remapped */
-	BIP_CTRL_NOCHECK	= 1 << 2, /* disable HBA integrity checking */
-	BIP_DISK_NOCHECK	= 1 << 3, /* disable disk integrity checking */
-	BIP_IP_CHECKSUM		= 1 << 4, /* IP checksum */
-	BIP_COPY_USER		= 1 << 5, /* Kernel bounce buffer in use */
+	BIP_DISK_NOCHECK	= 1 << 2, /* disable disk integrity checking */
+	BIP_IP_CHECKSUM		= 1 << 3, /* IP checksum */
+	BIP_COPY_USER		= 1 << 4, /* Kernel bounce buffer in use */
+	BIP_CHECK_GUARD		= 1 << 5, /* guard check */
+	BIP_CHECK_REFTAG	= 1 << 6, /* reftag check */
+	BIP_CHECK_APPTAG	= 1 << 7, /* apptag check */
 };
 
 struct bio_integrity_payload {
@@ -21,6 +23,7 @@ struct bio_integrity_payload {
 	unsigned short		bip_vcnt;	/* # of integrity bio_vecs */
 	unsigned short		bip_max_vcnt;	/* integrity bio_vec slots */
 	unsigned short		bip_flags;	/* control flags */
+	u16			app_tag;	/* application tag value */
 
 	struct bvec_iter	bio_iter;	/* for rewinding parent bio */
 
@@ -30,6 +33,9 @@ struct bio_integrity_payload {
 	struct bio_vec		bip_inline_vecs[];/* embedded bvec array */
 };
 
+#define BIP_CLONE_FLAGS (BIP_MAPPED_INTEGRITY | BIP_IP_CHECKSUM | \
+			 BIP_CHECK_GUARD | BIP_CHECK_REFTAG | BIP_CHECK_APPTAG)
+
 #ifdef CONFIG_BLK_DEV_INTEGRITY
 
 #define bip_for_each_vec(bvl, bip, iter)				\
@@ -72,7 +78,8 @@ struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio, gfp_t gfp,
 		unsigned int nr);
 int bio_integrity_add_page(struct bio *bio, struct page *page, unsigned int len,
 		unsigned int offset);
-int bio_integrity_map_user(struct bio *bio, void __user *ubuf, ssize_t len);
+int bio_integrity_map_user(struct bio *bio, struct iov_iter *iter);
+int bio_integrity_map_iter(struct bio *bio, struct uio_meta *meta);
 void bio_integrity_unmap_user(struct bio *bio);
 bool bio_integrity_prep(struct bio *bio);
 void bio_integrity_advance(struct bio *bio, unsigned int bytes_done);
@@ -98,8 +105,12 @@ static inline void bioset_integrity_free(struct bio_set *bs)
 {
 }
 
-static inline int bio_integrity_map_user(struct bio *bio, void __user *ubuf,
-					 ssize_t len)
+static inline int bio_integrity_map_user(struct bio *bio, struct iov_iter *iter)
+{
+	return -EINVAL;
+}
+
+static inline int bio_integrity_map_iter(struct bio *bio, struct uio_meta *meta)
 {
 	return -EINVAL;
 }
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 2b8447f53200..a4af70367f8a 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -349,6 +349,7 @@ struct readahead_control;
 #define IOCB_DIO_CALLER_COMP	(1 << 22)
 /* kiocb is a read or write operation submitted by fs/aio.c. */
 #define IOCB_AIO_RW		(1 << 23)
+#define IOCB_HAS_METADATA	(1 << 24)
 
 /* for use in trace events */
 #define TRACE_IOCB_STRINGS \
diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index fd4cdb0860a2..623d8e798a11 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -78,8 +78,9 @@ struct io_hash_table {
 
 struct io_mapped_region {
 	struct page		**pages;
-	void			*vmap_ptr;
-	size_t			nr_pages;
+	void			*ptr;
+	unsigned		nr_pages;
+	unsigned		flags;
 };
 
 /*
@@ -293,6 +294,11 @@ struct io_ring_ctx {
 
 		struct io_submit_state	submit_state;
 
+		/*
+		 * Modifications are protected by ->uring_lock and ->mmap_lock.
+		 * The flags, buf_pages and buf_nr_pages fields should be stable
+		 * once published.
+		 */
 		struct xarray		io_bl_xa;
 
 		struct io_hash_table	cancel_table;
@@ -424,17 +430,10 @@ struct io_ring_ctx {
 	 * side will need to grab this lock, to prevent either side from
 	 * being run concurrently with the other.
 	 */
-	struct mutex			resize_lock;
-
-	/*
-	 * If IORING_SETUP_NO_MMAP is used, then the below holds
-	 * the gup'ed pages for the two rings, and the sqes.
-	 */
-	unsigned short			n_ring_pages;
-	unsigned short			n_sqe_pages;
-	struct page			**ring_pages;
-	struct page			**sqe_pages;
+	struct mutex			mmap_lock;
 
+	struct io_mapped_region		sq_region;
+	struct io_mapped_region		ring_region;
 	/* used for optimised request parameter and wait argument passing  */
 	struct io_mapped_region		param_region;
 };
@@ -481,6 +480,7 @@ enum {
 	REQ_F_BL_NO_RECYCLE_BIT,
 	REQ_F_BUFFERS_COMMIT_BIT,
 	REQ_F_BUF_NODE_BIT,
+	REQ_F_HAS_METADATA_BIT,
 
 	/* not a real bit, just to check we're not overflowing the space */
 	__REQ_F_LAST_BIT,
@@ -561,6 +561,8 @@ enum {
 	REQ_F_BUFFERS_COMMIT	= IO_REQ_FLAG(REQ_F_BUFFERS_COMMIT_BIT),
 	/* buf node is valid */
 	REQ_F_BUF_NODE		= IO_REQ_FLAG(REQ_F_BUF_NODE_BIT),
+	/* request has read/write metadata assigned */
+	REQ_F_HAS_METADATA	= IO_REQ_FLAG(REQ_F_HAS_METADATA_BIT),
 };
 
 typedef void (*io_req_tw_func_t)(struct io_kiocb *req, struct io_tw_state *ts);
diff --git a/include/linux/uio.h b/include/linux/uio.h
index 853f9de5aa05..8ada84e85447 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -82,6 +82,15 @@ struct iov_iter {
 	};
 };
 
+typedef __u16 uio_meta_flags_t;
+
+struct uio_meta {
+	uio_meta_flags_t	flags;
+	u16			app_tag;
+	u64			seed;
+	struct iov_iter		iter;
+};
+
 static inline const struct iovec *iter_iov(const struct iov_iter *iter)
 {
 	if (iter->iter_type == ITER_UBUF)
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index 56a4f93a08f4..2bbe00cf1248 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -40,6 +40,15 @@
 #define BLOCK_SIZE_BITS 10
 #define BLOCK_SIZE (1<<BLOCK_SIZE_BITS)
 
+/* flags for integrity meta */
+#define IO_INTEGRITY_CHK_GUARD		(1U << 0) /* enforce guard check */
+#define IO_INTEGRITY_CHK_REFTAG		(1U << 1) /* enforce ref check */
+#define IO_INTEGRITY_CHK_APPTAG		(1U << 2) /* enforce app check */
+
+#define IO_INTEGRITY_VALID_FLAGS (IO_INTEGRITY_CHK_GUARD | \
+				  IO_INTEGRITY_CHK_REFTAG | \
+				  IO_INTEGRITY_CHK_APPTAG)
+
 #define SEEK_SET	0	/* seek relative to beginning of file */
 #define SEEK_CUR	1	/* seek relative to current file position */
 #define SEEK_END	2	/* seek relative to end of file */
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index aac9a4f8fa9a..e11c82638527 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -98,6 +98,10 @@ struct io_uring_sqe {
 			__u64	addr3;
 			__u64	__pad2[1];
 		};
+		struct {
+			__u64	attr_ptr; /* pointer to attribute information */
+			__u64	attr_type_mask; /* bit mask of attributes */
+		};
 		__u64	optval;
 		/*
 		 * If the ring is initialized with IORING_SETUP_SQE128, then
@@ -107,6 +111,18 @@ struct io_uring_sqe {
 	};
 };
 
+/* sqe->attr_type_mask flags */
+#define IORING_RW_ATTR_FLAG_PI	(1U << 0)
+/* PI attribute information */
+struct io_uring_attr_pi {
+		__u16	flags;
+		__u16	app_tag;
+		__u32	len;
+		__u64	addr;
+		__u64	seed;
+		__u64	rsvd;
+};
+
 /*
  * If sqe->file_index is set to this for opcodes that instantiate a new
  * direct descriptor (like openat/openat2/accept), then io_uring will allocate
@@ -561,6 +577,7 @@ struct io_uring_params {
 #define IORING_FEAT_REG_REG_RING	(1U << 13)
 #define IORING_FEAT_RECVSEND_BUNDLE	(1U << 14)
 #define IORING_FEAT_MIN_TIMEOUT		(1U << 15)
+#define IORING_FEAT_RW_ATTR		(1U << 16)
 
 /*
  * io_uring_register(2) opcodes and arguments