Merge tag 'for-6.16/io_uring-20250523' of git://git.kernel.dk/linux

Pull io_uring updates from Jens Axboe:

 - Avoid indirect function calls in io-wq for executing and freeing
   work.

   The design of io-wq is such that it can be a generic mechanism, but
   as it's just used by io_uring now, may as well avoid these indirect
   calls

 - Clean up registered buffers for networking

 - Add support for IORING_OP_PIPE. Pretty straight forward, allows
   creating pipes with io_uring, particularly useful for having these be
   instantiated as direct descriptors

 - Clean up the coalescing support fore registered buffers

 - Add support for multiple interface queues for zero-copy rx
   networking. As this feature was merged for 6.15 it supported just a
   single ifq per ring

 - Clean up the eventfd support

 - Add dma-buf support to zero-copy rx

 - Clean up and improving the request draining support

 - Clean up provided buffer support, most notably with an eye toward
   making the legacy support less intrusive

 - Minor fdinfo cleanups, dropping support for dumping what credentials
   are registered

 - Improve support for overflow CQE handling, getting rid of GFP_ATOMIC
   for allocating overflow entries where possible

 - Improve detection of cases where io-wq doesn't need to spawn a new
   worker unnecessarily

 - Various little cleanups

* tag 'for-6.16/io_uring-20250523' of git://git.kernel.dk/linux: (59 commits)
  io_uring/cmd: warn on reg buf imports by ineligible cmds
  io_uring/io-wq: only create a new worker if it can make progress
  io_uring/io-wq: ignore non-busy worker going to sleep
  io_uring/io-wq: move hash helpers to the top
  trace/io_uring: fix io_uring_local_work_run ctx documentation
  io_uring: finish IOU_OK -> IOU_COMPLETE transition
  io_uring: add new helpers for posting overflows
  io_uring: pass in struct io_big_cqe to io_alloc_ocqe()
  io_uring: make io_alloc_ocqe() take a struct io_cqe pointer
  io_uring: split alloc and add of overflow
  io_uring: open code io_req_cqe_overflow()
  io_uring/fdinfo: get rid of dumping credentials
  io_uring/fdinfo: only compile if CONFIG_PROC_FS is set
  io_uring/kbuf: unify legacy buf provision and removal
  io_uring/kbuf: refactor __io_remove_buffers
  io_uring/kbuf: don't compute size twice on prep
  io_uring/kbuf: drop extra vars in io_register_pbuf_ring
  io_uring/kbuf: use mem_is_zero()
  io_uring/kbuf: account ring io_buffer_list memory
  io_uring: drain based on allocates reqs
  ...

1 files changed, 25 insertions, 37 deletions

diff --git a/io_uring/net.c b/io_uring/net.c
index 27f37fa2ef79..d13f3e8f6c72 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -18,7 +18,6 @@
 #include "rsrc.h"
 #include "zcrx.h"
 
-#if defined(CONFIG_NET)
 struct io_shutdown {
 	struct file			*file;
 	int				how;
@@ -129,7 +128,7 @@ int io_shutdown(struct io_kiocb *req, unsigned int issue_flags)
 
 	ret = __sys_shutdown_sock(sock, shutdown->how);
 	io_req_set_res(req, ret, 0);
-	return IOU_OK;
+	return IOU_COMPLETE;
 }
 
 static bool io_net_retry(struct socket *sock, int flags)
@@ -190,7 +189,6 @@ static inline void io_mshot_prep_retry(struct io_kiocb *req,
 	sr->done_io = 0;
 	sr->retry = false;
 	sr->len = 0; /* get from the provided buffer */
-	req->buf_index = sr->buf_group;
 }
 
 static int io_net_import_vec(struct io_kiocb *req, struct io_async_msghdr *iomsg,
@@ -359,15 +357,13 @@ static int io_send_setup(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		kmsg->msg.msg_name = &kmsg->addr;
 		kmsg->msg.msg_namelen = addr_len;
 	}
-	if (sr->flags & IORING_RECVSEND_FIXED_BUF)
+	if (sr->flags & IORING_RECVSEND_FIXED_BUF) {
+		req->flags |= REQ_F_IMPORT_BUFFER;
 		return 0;
-	if (!io_do_buffer_select(req)) {
-		ret = import_ubuf(ITER_SOURCE, sr->buf, sr->len,
-				  &kmsg->msg.msg_iter);
-		if (unlikely(ret < 0))
-			return ret;
 	}
-	return 0;
+	if (req->flags & REQ_F_BUFFER_SELECT)
+		return 0;
+	return import_ubuf(ITER_SOURCE, sr->buf, sr->len, &kmsg->msg.msg_iter);
 }
 
 static int io_sendmsg_setup(struct io_kiocb *req, const struct io_uring_sqe *sqe)
@@ -409,13 +405,12 @@ int io_sendmsg_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	sr->msg_flags = READ_ONCE(sqe->msg_flags) | MSG_NOSIGNAL;
 	if (sr->msg_flags & MSG_DONTWAIT)
 		req->flags |= REQ_F_NOWAIT;
+	if (req->flags & REQ_F_BUFFER_SELECT)
+		sr->buf_group = req->buf_index;
 	if (sr->flags & IORING_RECVSEND_BUNDLE) {
 		if (req->opcode == IORING_OP_SENDMSG)
 			return -EINVAL;
-		if (!(req->flags & REQ_F_BUFFER_SELECT))
-			return -EINVAL;
 		sr->msg_flags |= MSG_WAITALL;
-		sr->buf_group = req->buf_index;
 		req->buf_list = NULL;
 		req->flags |= REQ_F_MULTISHOT;
 	}
@@ -507,7 +502,7 @@ static inline bool io_send_finish(struct io_kiocb *req, int *ret,
 	/* Otherwise stop bundle and use the current result. */
 finish:
 	io_req_set_res(req, *ret, cflags);
-	*ret = IOU_OK;
+	*ret = IOU_COMPLETE;
 	return true;
 }
 
@@ -558,7 +553,7 @@ int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags)
 	else if (sr->done_io)
 		ret = sr->done_io;
 	io_req_set_res(req, ret, 0);
-	return IOU_OK;
+	return IOU_COMPLETE;
 }
 
 static int io_send_select_buffer(struct io_kiocb *req, unsigned int issue_flags,
@@ -571,6 +566,7 @@ static int io_send_select_buffer(struct io_kiocb *req, unsigned int issue_flags,
 		.iovs = &kmsg->fast_iov,
 		.max_len = min_not_zero(sr->len, INT_MAX),
 		.nr_iovs = 1,
+		.buf_group = sr->buf_group,
 	};
 
 	if (kmsg->vec.iovec) {
@@ -723,7 +719,6 @@ static int io_recvmsg_prep_setup(struct io_kiocb *req)
 {
 	struct io_sr_msg *sr = io_kiocb_to_cmd(req, struct io_sr_msg);
 	struct io_async_msghdr *kmsg;
-	int ret;
 
 	kmsg = io_msg_alloc_async(req);
 	if (unlikely(!kmsg))
@@ -739,13 +734,10 @@ static int io_recvmsg_prep_setup(struct io_kiocb *req)
 		kmsg->msg.msg_iocb = NULL;
 		kmsg->msg.msg_ubuf = NULL;
 
-		if (!io_do_buffer_select(req)) {
-			ret = import_ubuf(ITER_DEST, sr->buf, sr->len,
-					  &kmsg->msg.msg_iter);
-			if (unlikely(ret))
-				return ret;
-		}
-		return 0;
+		if (req->flags & REQ_F_BUFFER_SELECT)
+			return 0;
+		return import_ubuf(ITER_DEST, sr->buf, sr->len,
+				   &kmsg->msg.msg_iter);
 	}
 
 	return io_recvmsg_copy_hdr(req, kmsg);
@@ -991,7 +983,7 @@ retry_multishot:
 		void __user *buf;
 		size_t len = sr->len;
 
-		buf = io_buffer_select(req, &len, issue_flags);
+		buf = io_buffer_select(req, &len, sr->buf_group, issue_flags);
 		if (!buf)
 			return -ENOBUFS;
 
@@ -1069,6 +1061,7 @@ static int io_recv_buf_select(struct io_kiocb *req, struct io_async_msghdr *kmsg
 			.iovs = &kmsg->fast_iov,
 			.nr_iovs = 1,
 			.mode = KBUF_MODE_EXPAND,
+			.buf_group = sr->buf_group,
 		};
 
 		if (kmsg->vec.iovec) {
@@ -1101,7 +1094,7 @@ static int io_recv_buf_select(struct io_kiocb *req, struct io_async_msghdr *kmsg
 		void __user *buf;
 
 		*len = sr->len;
-		buf = io_buffer_select(req, len, issue_flags);
+		buf = io_buffer_select(req, len, sr->buf_group, issue_flags);
 		if (!buf)
 			return -ENOBUFS;
 		sr->buf = buf;
@@ -1197,16 +1190,14 @@ int io_recvzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	struct io_recvzc *zc = io_kiocb_to_cmd(req, struct io_recvzc);
 	unsigned ifq_idx;
 
-	if (unlikely(sqe->file_index || sqe->addr2 || sqe->addr ||
-		     sqe->addr3))
+	if (unlikely(sqe->addr2 || sqe->addr || sqe->addr3))
 		return -EINVAL;
 
 	ifq_idx = READ_ONCE(sqe->zcrx_ifq_idx);
-	if (ifq_idx != 0)
-		return -EINVAL;
-	zc->ifq = req->ctx->ifq;
+	zc->ifq = xa_load(&req->ctx->zcrx_ctxs, ifq_idx);
 	if (!zc->ifq)
 		return -EINVAL;
+
 	zc->len = READ_ONCE(sqe->len);
 	zc->flags = READ_ONCE(sqe->ioprio);
 	zc->msg_flags = READ_ONCE(sqe->msg_flags);
@@ -1327,8 +1318,6 @@ int io_send_zc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 		return -ENOMEM;
 
 	if (req->opcode == IORING_OP_SEND_ZC) {
-		if (zc->flags & IORING_RECVSEND_FIXED_BUF)
-			req->flags |= REQ_F_IMPORT_BUFFER;
 		ret = io_send_setup(req, sqe);
 	} else {
 		if (unlikely(sqe->addr2 || sqe->file_index))
@@ -1476,7 +1465,7 @@ int io_send_zc(struct io_kiocb *req, unsigned int issue_flags)
 		io_req_msg_cleanup(req, 0);
 	}
 	io_req_set_res(req, ret, IORING_CQE_F_MORE);
-	return IOU_OK;
+	return IOU_COMPLETE;
 }
 
 int io_sendmsg_zc(struct io_kiocb *req, unsigned int issue_flags)
@@ -1547,7 +1536,7 @@ int io_sendmsg_zc(struct io_kiocb *req, unsigned int issue_flags)
 		io_req_msg_cleanup(req, 0);
 	}
 	io_req_set_res(req, ret, IORING_CQE_F_MORE);
-	return IOU_OK;
+	return IOU_COMPLETE;
 }
 
 void io_sendrecv_fail(struct io_kiocb *req)
@@ -1711,7 +1700,7 @@ int io_socket(struct io_kiocb *req, unsigned int issue_flags)
 					    sock->file_slot);
 	}
 	io_req_set_res(req, ret, 0);
-	return IOU_OK;
+	return IOU_COMPLETE;
 }
 
 int io_connect_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
@@ -1778,7 +1767,7 @@ out:
 		req_set_fail(req);
 	io_req_msg_cleanup(req, issue_flags);
 	io_req_set_res(req, ret, 0);
-	return IOU_OK;
+	return IOU_COMPLETE;
 }
 
 int io_bind_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
@@ -1852,4 +1841,3 @@ void io_netmsg_cache_free(const void *entry)
 	io_vec_free(&kmsg->vec);
 	kfree(kmsg);
 }
-#endif