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

Pull io_uring updates from Jens Axboe:

 - Unify how task_work cancelations are detected, placing it in the
   task_work running state rather than needing to check the task state

 - Series cleaning up and moving the cancelation code to where it
   belongs, in cancel.c

 - Cleanup of waitid and futex argument handling

 - Add support for mixed sized SQEs. 6.18 added support for mixed sized
   CQEs, improving flexibility and efficiency of workloads that need big
   CQEs. This adds similar support for SQEs, where the occasional need
   for a 128b SQE doesn't necessitate having all SQEs be 128b in size

 - Introduce zcrx and SQ/CQ layout queries. The former returns what zcrx
   features are available. And both return the ring size information to
   help with allocation size calculation for user provided rings like
   IORING_SETUP_NO_MMAP and IORING_MEM_REGION_TYPE_USER

 - Zcrx updates for 6.19. It includes a bunch of small patches,
   IORING_REGISTER_ZCRX_CTRL and RQ flushing and David's work on sharing
   zcrx b/w multiple io_uring instances

 - Series cleaning up ring initializations, notable deduplicating ring
   size and offset calculations. It also moves most of the checking
   before doing any allocations, making the code simpler

 - Add support for getsockname and getpeername, which is mostly a
   trivial hookup after a bit of refactoring on the networking side

 - Various fixes and cleanups

* tag 'for-6.19/io_uring-20251201' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux: (68 commits)
  io_uring: Introduce getsockname io_uring cmd
  socket: Split out a getsockname helper for io_uring
  socket: Unify getsockname and getpeername implementation
  io_uring/query: drop unused io_handle_query_entry() ctx arg
  io_uring/kbuf: remove obsolete buf_nr_pages and update comments
  io_uring/register: use correct location for io_rings_layout
  io_uring/zcrx: share an ifq between rings
  io_uring/zcrx: add io_fill_zcrx_offsets()
  io_uring/zcrx: export zcrx via a file
  io_uring/zcrx: move io_zcrx_scrub() and dependencies up
  io_uring/zcrx: count zcrx users
  io_uring/zcrx: add sync refill queue flushing
  io_uring/zcrx: introduce IORING_REGISTER_ZCRX_CTRL
  io_uring/zcrx: elide passing msg flags
  io_uring/zcrx: use folio_nr_pages() instead of shift operation
  io_uring/zcrx: convert to use netmem_desc
  io_uring/query: introduce rings info query
  io_uring/query: introduce zcrx query
  io_uring: move cq/sq user offset init around
  io_uring: pre-calculate scq layout
  ...

Author: torvalds

block/ioctl.c

@@ -769,14 +769,16 @@ struct blk_iou_cmd {
 	bool nowait;
 };
 
-static void blk_cmd_complete(struct io_uring_cmd *cmd, unsigned int issue_flags)
+static void blk_cmd_complete(struct io_tw_req tw_req, io_tw_token_t tw)
 {
+	struct io_uring_cmd *cmd = io_uring_cmd_from_tw(tw_req);
 	struct blk_iou_cmd *bic = io_uring_cmd_to_pdu(cmd, struct blk_iou_cmd);
 
 	if (bic->res == -EAGAIN && bic->nowait)
 		io_uring_cmd_issue_blocking(cmd);
 	else
-		io_uring_cmd_done(cmd, bic->res, issue_flags);
+		io_uring_cmd_done(cmd, bic->res,
+				  IO_URING_CMD_TASK_WORK_ISSUE_FLAGS);
 }
 
 static void bio_cmd_bio_end_io(struct bio *bio)

drivers/block/ublk_drv.c

@@ -1302,10 +1302,9 @@ static bool ublk_start_io(const struct ublk_queue *ubq, struct request *req,
 	return true;
 }
 
-static void ublk_dispatch_req(struct ublk_queue *ubq,
-			      struct request *req,
-			      unsigned int issue_flags)
+static void ublk_dispatch_req(struct ublk_queue *ubq, struct request *req)
 {
+	unsigned int issue_flags = IO_URING_CMD_TASK_WORK_ISSUE_FLAGS;
 	int tag = req->tag;
 	struct ublk_io *io = &ubq->ios[tag];
 
@@ -1348,13 +1347,13 @@ static void ublk_dispatch_req(struct ublk_queue *ubq,
 		ublk_complete_io_cmd(io, req, UBLK_IO_RES_OK, issue_flags);
 }
 
-static void ublk_cmd_tw_cb(struct io_uring_cmd *cmd,
-			   unsigned int issue_flags)
+static void ublk_cmd_tw_cb(struct io_tw_req tw_req, io_tw_token_t tw)
 {
+	struct io_uring_cmd *cmd = io_uring_cmd_from_tw(tw_req);
 	struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd);
 	struct ublk_queue *ubq = pdu->ubq;
 
-	ublk_dispatch_req(ubq, pdu->req, issue_flags);
+	ublk_dispatch_req(ubq, pdu->req);
 }
 
 static void ublk_queue_cmd(struct ublk_queue *ubq, struct request *rq)
@@ -1366,17 +1365,17 @@ static void ublk_queue_cmd(struct ublk_queue *ubq, struct request *rq)
 	io_uring_cmd_complete_in_task(cmd, ublk_cmd_tw_cb);
 }
 
-static void ublk_cmd_list_tw_cb(struct io_uring_cmd *cmd,
-		unsigned int issue_flags)
+static void ublk_cmd_list_tw_cb(struct io_tw_req tw_req, io_tw_token_t tw)
 {
+	struct io_uring_cmd *cmd = io_uring_cmd_from_tw(tw_req);
 	struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd);
 	struct request *rq = pdu->req_list;
 	struct request *next;
 
 	do {
 		next = rq->rq_next;
 		rq->rq_next = NULL;
-		ublk_dispatch_req(rq->mq_hctx->driver_data, rq, issue_flags);
+		ublk_dispatch_req(rq->mq_hctx->driver_data, rq);
 		rq = next;
 	} while (rq);
 }
@@ -2523,9 +2522,10 @@ static inline struct request *__ublk_check_and_get_req(struct ublk_device *ub,
 	return NULL;
 }
 
-static void ublk_ch_uring_cmd_cb(struct io_uring_cmd *cmd,
-		unsigned int issue_flags)
+static void ublk_ch_uring_cmd_cb(struct io_tw_req tw_req, io_tw_token_t tw)
 {
+	unsigned int issue_flags = IO_URING_CMD_TASK_WORK_ISSUE_FLAGS;
+	struct io_uring_cmd *cmd = io_uring_cmd_from_tw(tw_req);
 	int ret = ublk_ch_uring_cmd_local(cmd, issue_flags);
 
 	if (ret != -EIOCBQUEUED)

drivers/nvme/host/ioctl.c

@@ -398,14 +398,15 @@ static inline struct nvme_uring_cmd_pdu *nvme_uring_cmd_pdu(
 	return io_uring_cmd_to_pdu(ioucmd, struct nvme_uring_cmd_pdu);
 }
 
-static void nvme_uring_task_cb(struct io_uring_cmd *ioucmd,
-			       unsigned issue_flags)
+static void nvme_uring_task_cb(struct io_tw_req tw_req, io_tw_token_t tw)
 {
+	struct io_uring_cmd *ioucmd = io_uring_cmd_from_tw(tw_req);
 	struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd);
 
 	if (pdu->bio)
 		blk_rq_unmap_user(pdu->bio);
-	io_uring_cmd_done32(ioucmd, pdu->status, pdu->result, issue_flags);
+	io_uring_cmd_done32(ioucmd, pdu->status, pdu->result,
+			    IO_URING_CMD_TASK_WORK_ISSUE_FLAGS);
 }
 
 static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req,

fs/btrfs/ioctl.c

@@ -4632,8 +4632,9 @@ struct io_btrfs_cmd {
 	struct btrfs_uring_priv *priv;
 };
 
-static void btrfs_uring_read_finished(struct io_uring_cmd *cmd, unsigned int issue_flags)
+static void btrfs_uring_read_finished(struct io_tw_req tw_req, io_tw_token_t tw)
 {
+	struct io_uring_cmd *cmd = io_uring_cmd_from_tw(tw_req);
 	struct io_btrfs_cmd *bc = io_uring_cmd_to_pdu(cmd, struct io_btrfs_cmd);
 	struct btrfs_uring_priv *priv = bc->priv;
 	struct btrfs_inode *inode = BTRFS_I(file_inode(priv->iocb.ki_filp));
@@ -4678,7 +4679,7 @@ static void btrfs_uring_read_finished(struct io_uring_cmd *cmd, unsigned int iss
 	btrfs_unlock_extent(io_tree, priv->start, priv->lockend, &priv->cached_state);
 	btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED);
 
-	io_uring_cmd_done(cmd, ret, issue_flags);
+	io_uring_cmd_done(cmd, ret, IO_URING_CMD_TASK_WORK_ISSUE_FLAGS);
 	add_rchar(current, ret);
 
 	for (index = 0; index < priv->nr_pages; index++)

fs/fuse/dev_uring.c

@@ -1209,14 +1209,15 @@ static void fuse_uring_send(struct fuse_ring_ent *ent, struct io_uring_cmd *cmd,
  * User buffers are not mapped yet - the application does not have permission
  * to write to it - this has to be executed in ring task context.
  */
-static void fuse_uring_send_in_task(struct io_uring_cmd *cmd,
-				    unsigned int issue_flags)
+static void fuse_uring_send_in_task(struct io_tw_req tw_req, io_tw_token_t tw)
 {
+	unsigned int issue_flags = IO_URING_CMD_TASK_WORK_ISSUE_FLAGS;
+	struct io_uring_cmd *cmd = io_uring_cmd_from_tw(tw_req);
 	struct fuse_ring_ent *ent = uring_cmd_to_ring_ent(cmd);
 	struct fuse_ring_queue *queue = ent->queue;
 	int err;
 
-	if (!(issue_flags & IO_URING_F_TASK_DEAD)) {
+	if (!tw.cancel) {
 		err = fuse_uring_prepare_send(ent, ent->fuse_req);
 		if (err) {
 			fuse_uring_next_fuse_req(ent, queue, issue_flags);

include/linux/io_uring/cmd.h

@@ -11,17 +11,13 @@
 /* io_uring_cmd is being issued again */
 #define IORING_URING_CMD_REISSUE	(1U << 31)
 
-typedef void (*io_uring_cmd_tw_t)(struct io_uring_cmd *cmd,
-				  unsigned issue_flags);
-
 struct io_uring_cmd {
 	struct file	*file;
 	const struct io_uring_sqe *sqe;
-	/* callback to defer completions to task context */
-	io_uring_cmd_tw_t task_work_cb;
 	u32		cmd_op;
 	u32		flags;
 	u8		pdu[32]; /* available inline for free use */
+	u8		unused[8];
 };
 
 static inline const void *io_uring_sqe_cmd(const struct io_uring_sqe *sqe)
@@ -60,7 +56,7 @@ void __io_uring_cmd_done(struct io_uring_cmd *cmd, s32 ret, u64 res2,
 			 unsigned issue_flags, bool is_cqe32);
 
 void __io_uring_cmd_do_in_task(struct io_uring_cmd *ioucmd,
-			    io_uring_cmd_tw_t task_work_cb,
+			    io_req_tw_func_t task_work_cb,
 			    unsigned flags);
 
 /*
@@ -109,7 +105,7 @@ static inline void __io_uring_cmd_done(struct io_uring_cmd *cmd, s32 ret,
 {
 }
 static inline void __io_uring_cmd_do_in_task(struct io_uring_cmd *ioucmd,
-			    io_uring_cmd_tw_t task_work_cb, unsigned flags)
+			    io_req_tw_func_t task_work_cb, unsigned flags)
 {
 }
 static inline void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd,
@@ -132,15 +128,23 @@ static inline bool io_uring_mshot_cmd_post_cqe(struct io_uring_cmd *ioucmd,
 }
 #endif
 
+static inline struct io_uring_cmd *io_uring_cmd_from_tw(struct io_tw_req tw_req)
+{
+	return io_kiocb_to_cmd(tw_req.req, struct io_uring_cmd);
+}
+
+/* task_work executor checks the deferred list completion */
+#define IO_URING_CMD_TASK_WORK_ISSUE_FLAGS IO_URING_F_COMPLETE_DEFER
+
 /* users must follow the IOU_F_TWQ_LAZY_WAKE semantics */
 static inline void io_uring_cmd_do_in_task_lazy(struct io_uring_cmd *ioucmd,
-			io_uring_cmd_tw_t task_work_cb)
+			io_req_tw_func_t task_work_cb)
 {
 	__io_uring_cmd_do_in_task(ioucmd, task_work_cb, IOU_F_TWQ_LAZY_WAKE);
 }
 
 static inline void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd,
-			io_uring_cmd_tw_t task_work_cb)
+			io_req_tw_func_t task_work_cb)
 {
 	__io_uring_cmd_do_in_task(ioucmd, task_work_cb, 0);
 }

include/linux/io_uring_types.h

@@ -39,7 +39,6 @@ enum io_uring_cmd_flags {
 	/* set when uring wants to cancel a previously issued command */
 	IO_URING_F_CANCEL		= (1 << 11),
 	IO_URING_F_COMPAT		= (1 << 12),
-	IO_URING_F_TASK_DEAD		= (1 << 13),
 };
 
 struct io_wq_work_node {
@@ -328,8 +327,8 @@ struct io_ring_ctx {
 
 		/*
 		 * Modifications are protected by ->uring_lock and ->mmap_lock.
-		 * The flags, buf_pages and buf_nr_pages fields should be stable
-		 * once published.
+		 * The buffer list's io mapped region should be stable once
+		 * published.
 		 */
 		struct xarray		io_bl_xa;
 
@@ -474,6 +473,7 @@ struct io_ring_ctx {
  * ONLY core io_uring.c should instantiate this struct.
  */
 struct io_tw_state {
+	bool cancel;
 };
 /* Alias to use in code that doesn't instantiate struct io_tw_state */
 typedef struct io_tw_state io_tw_token_t;
@@ -614,7 +614,11 @@ enum {
 	REQ_F_SQE_COPIED	= IO_REQ_FLAG(REQ_F_SQE_COPIED_BIT),
 };
 
-typedef void (*io_req_tw_func_t)(struct io_kiocb *req, io_tw_token_t tw);
+struct io_tw_req {
+	struct io_kiocb *req;
+};
+
+typedef void (*io_req_tw_func_t)(struct io_tw_req tw_req, io_tw_token_t tw);
 
 struct io_task_work {
 	struct llist_node		node;

include/linux/netdevice.h

@@ -3417,6 +3417,7 @@ struct net_device *dev_get_by_index(struct net *net, int ifindex);
 struct net_device *__dev_get_by_index(struct net *net, int ifindex);
 struct net_device *netdev_get_by_index(struct net *net, int ifindex,
 				       netdevice_tracker *tracker, gfp_t gfp);
+struct net_device *netdev_get_by_index_lock(struct net *net, int ifindex);
 struct net_device *netdev_get_by_name(struct net *net, const char *name,
 				      netdevice_tracker *tracker, gfp_t gfp);
 struct net_device *netdev_get_by_flags_rcu(struct net *net, netdevice_tracker *tracker,

include/linux/socket.h

@@ -468,10 +468,10 @@ extern int __sys_connect(int fd, struct sockaddr __user *uservaddr,
 			 int addrlen);
 extern int __sys_listen(int fd, int backlog);
 extern int __sys_listen_socket(struct socket *sock, int backlog);
+extern int do_getsockname(struct socket *sock, int peer,
+			  struct sockaddr __user *usockaddr, int __user *usockaddr_len);
 extern int __sys_getsockname(int fd, struct sockaddr __user *usockaddr,
-			     int __user *usockaddr_len);
-extern int __sys_getpeername(int fd, struct sockaddr __user *usockaddr,
-			     int __user *usockaddr_len);
+			     int __user *usockaddr_len, int peer);
 extern int __sys_socketpair(int family, int type, int protocol,
 			    int __user *usockvec);
 extern int __sys_shutdown_sock(struct socket *sock, int how);

include/uapi/linux/io_uring.h

@@ -231,6 +231,12 @@ enum io_uring_sqe_flags_bit {
  */
 #define IORING_SETUP_CQE_MIXED		(1U << 18)
 
+/*
+ * Allow both 64b and 128b SQEs. If a 128b SQE is posted, it will have
+ * a 128b opcode.
+ */
+#define IORING_SETUP_SQE_MIXED		(1U << 19)
+
 enum io_uring_op {
 	IORING_OP_NOP,
 	IORING_OP_READV,
@@ -295,6 +301,8 @@ enum io_uring_op {
 	IORING_OP_READV_FIXED,
 	IORING_OP_WRITEV_FIXED,
 	IORING_OP_PIPE,
+	IORING_OP_NOP128,
+	IORING_OP_URING_CMD128,
 
 	/* this goes last, obviously */
 	IORING_OP_LAST,
@@ -689,6 +697,9 @@ enum io_uring_register_op {
 	/* query various aspects of io_uring, see linux/io_uring/query.h */
 	IORING_REGISTER_QUERY			= 35,
 
+	/* auxiliary zcrx configuration, see enum zcrx_ctrl_op */
+	IORING_REGISTER_ZCRX_CTRL		= 36,
+
 	/* this goes last */
 	IORING_REGISTER_LAST,
 
@@ -998,6 +1009,7 @@ enum io_uring_socket_op {
 	SOCKET_URING_OP_GETSOCKOPT,
 	SOCKET_URING_OP_SETSOCKOPT,
 	SOCKET_URING_OP_TX_TIMESTAMP,
+	SOCKET_URING_OP_GETSOCKNAME,
 };
 
 /*
@@ -1052,6 +1064,10 @@ struct io_uring_zcrx_area_reg {
 	__u64	__resv2[2];
 };
 
+enum zcrx_reg_flags {
+	ZCRX_REG_IMPORT	= 1,
+};
+
 /*
  * Argument for IORING_REGISTER_ZCRX_IFQ
  */
@@ -1070,6 +1086,33 @@ struct io_uring_zcrx_ifq_reg {
 	__u64	__resv[3];
 };
 
+enum zcrx_ctrl_op {
+	ZCRX_CTRL_FLUSH_RQ,
+	ZCRX_CTRL_EXPORT,
+
+	__ZCRX_CTRL_LAST,
+};
+
+struct zcrx_ctrl_flush_rq {
+	__u64		__resv[6];
+};
+
+struct zcrx_ctrl_export {
+	__u32		zcrx_fd;
+	__u32 		__resv1[11];
+};
+
+struct zcrx_ctrl {
+	__u32	zcrx_id;
+	__u32	op; /* see enum zcrx_ctrl_op */
+	__u64	__resv[2];
+
+	union {
+		struct zcrx_ctrl_export		zc_export;
+		struct zcrx_ctrl_flush_rq	zc_flush;
+	};
+};
+
 #ifdef __cplusplus
 }
 #endif