Merge tag 'io_uring-7.0-20260320' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux

Pull io_uring fixes from Jens Axboe:

 - A bit of a work-around for AF_UNIX recv multishot, as the in-kernel
   implementation doesn't properly signal EOF. We'll likely rework this
   one going forward, but the fix is sufficient for now

 - Two fixes for incrementally consumed buffers, for non-pollable files
   and for 0 byte reads

* tag 'io_uring-7.0-20260320' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux:
  io_uring/kbuf: propagate BUF_MORE through early buffer commit path
  io_uring/kbuf: fix missing BUF_MORE for incremental buffers at EOF
  io_uring/poll: fix multishot recv missing EOF on wakeup race

3 files changed, 21 insertions, 5 deletions

diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index dd1420bfcb73..214fdbd49052 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -541,6 +541,7 @@ enum {
 	REQ_F_BL_NO_RECYCLE_BIT,
 	REQ_F_BUFFERS_COMMIT_BIT,
 	REQ_F_BUF_NODE_BIT,
+	REQ_F_BUF_MORE_BIT,
 	REQ_F_HAS_METADATA_BIT,
 	REQ_F_IMPORT_BUFFER_BIT,
 	REQ_F_SQE_COPIED_BIT,
@@ -626,6 +627,8 @@ 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),
+	/* incremental buffer consumption, more space available */
+	REQ_F_BUF_MORE		= IO_REQ_FLAG(REQ_F_BUF_MORE_BIT),
 	/* request has read/write metadata assigned */
 	REQ_F_HAS_METADATA	= IO_REQ_FLAG(REQ_F_HAS_METADATA_BIT),
 	/*
diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c
index 26813b0f1dfd..5257b3aad395 100644
--- a/io_uring/kbuf.c
+++ b/io_uring/kbuf.c
@@ -34,6 +34,10 @@ struct io_provide_buf {
 
 static bool io_kbuf_inc_commit(struct io_buffer_list *bl, int len)
 {
+	/* No data consumed, return false early to avoid consuming the buffer */
+	if (!len)
+		return false;
+
 	while (len) {
 		struct io_uring_buf *buf;
 		u32 buf_len, this_len;
@@ -212,7 +216,8 @@ static struct io_br_sel io_ring_buffer_select(struct io_kiocb *req, size_t *len,
 	sel.addr = u64_to_user_ptr(READ_ONCE(buf->addr));
 
 	if (io_should_commit(req, issue_flags)) {
-		io_kbuf_commit(req, sel.buf_list, *len, 1);
+		if (!io_kbuf_commit(req, sel.buf_list, *len, 1))
+			req->flags |= REQ_F_BUF_MORE;
 		sel.buf_list = NULL;
 	}
 	return sel;
@@ -345,7 +350,8 @@ int io_buffers_select(struct io_kiocb *req, struct buf_sel_arg *arg,
 		 */
 		if (ret > 0) {
 			req->flags |= REQ_F_BUFFERS_COMMIT | REQ_F_BL_NO_RECYCLE;
-			io_kbuf_commit(req, sel->buf_list, arg->out_len, ret);
+			if (!io_kbuf_commit(req, sel->buf_list, arg->out_len, ret))
+				req->flags |= REQ_F_BUF_MORE;
 		}
 	} else {
 		ret = io_provided_buffers_select(req, &arg->out_len, sel->buf_list, arg->iovs);
@@ -391,8 +397,10 @@ static inline bool __io_put_kbuf_ring(struct io_kiocb *req,
 
 	if (bl)
 		ret = io_kbuf_commit(req, bl, len, nr);
+	if (ret && (req->flags & REQ_F_BUF_MORE))
+		ret = false;
 
-	req->flags &= ~REQ_F_BUFFER_RING;
+	req->flags &= ~(REQ_F_BUFFER_RING | REQ_F_BUF_MORE);
 	return ret;
 }
 
diff --git a/io_uring/poll.c b/io_uring/poll.c
index b671b84657d9..2e9ee47d74bf 100644
--- a/io_uring/poll.c
+++ b/io_uring/poll.c
@@ -272,6 +272,7 @@ static int io_poll_check_events(struct io_kiocb *req, io_tw_token_t tw)
 				atomic_andnot(IO_POLL_RETRY_FLAG, &req->poll_refs);
 				v &= ~IO_POLL_RETRY_FLAG;
 			}
+			v &= IO_POLL_REF_MASK;
 		}
 
 		/* the mask was stashed in __io_poll_execute */
@@ -304,8 +305,13 @@ static int io_poll_check_events(struct io_kiocb *req, io_tw_token_t tw)
 				return IOU_POLL_REMOVE_POLL_USE_RES;
 			}
 		} else {
-			int ret = io_poll_issue(req, tw);
+			int ret;
 
+			/* multiple refs and HUP, ensure we loop once more */
+			if ((req->cqe.res & (POLLHUP | POLLRDHUP)) && v != 1)
+				v--;
+
+			ret = io_poll_issue(req, tw);
 			if (ret == IOU_COMPLETE)
 				return IOU_POLL_REMOVE_POLL_USE_RES;
 			else if (ret == IOU_REQUEUE)
@@ -321,7 +327,6 @@ static int io_poll_check_events(struct io_kiocb *req, io_tw_token_t tw)
 		 * Release all references, retry if someone tried to restart
 		 * task_work while we were executing it.
 		 */
-		v &= IO_POLL_REF_MASK;
 	} while (atomic_sub_return(v, &req->poll_refs) & IO_POLL_REF_MASK);
 
 	io_napi_add(req);