Merge tag 'io_uring-6.19-20251208' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux

Pull io_uring updates from Jens Axboe:
 "Followup set of fixes for io_uring for this merge window. These are
  either later fixes, or cleanups that don't make sense to defer. This
  pull request contains:

   - Fix for a recent regression in io-wq worker creation

   - Tracing cleanup

   - Use READ_ONCE/WRITE_ONCE consistently for ring mapped kbufs. Mostly
     for documentation purposes, indicating that they are shared with
     userspace

   - Fix for POLL_ADD losing a completion, if the request is updated and
     now is triggerable - eg, if POLLIN is set with the updated, and the
     polled file is readable

   - In conjunction with the above fix, also unify how poll wait queue
     entries are deleted with the head update. We had 3 different spots
     doing both the list deletion and head write, with one of them
     nicely documented. Abstract that into a helper and use it
     consistently

   - Small series from Joanne fixing an issue with buffer cloning, and
     cleaning up the arg validation"

* tag 'io_uring-6.19-20251208' of git://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux:
  io_uring/poll: unify poll waitqueue entry and list removal
  io_uring/kbuf: use WRITE_ONCE() for userspace-shared buffer ring fields
  io_uring/kbuf: use READ_ONCE() for userspace-mapped memory
  io_uring/rsrc: fix lost entries after cloned range
  io_uring/rsrc: rename misleading src_node variable in io_clone_buffers()
  io_uring/rsrc: clean up buffer cloning arg validation
  io_uring/trace: rename io_uring_queue_async_work event "rw" field
  io_uring/io-wq: always retry worker create on ERESTART*
  io_uring/poll: correctly handle io_poll_add() return value on update

1 files changed, 21 insertions, 26 deletions

diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c
index 3765a50329a8..a63474b331bf 100644
--- a/io_uring/rsrc.c
+++ b/io_uring/rsrc.c
@@ -1186,12 +1186,16 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx
 		return -EBUSY;
 
 	nbufs = src_ctx->buf_table.nr;
+	if (!nbufs)
+		return -ENXIO;
 	if (!arg->nr)
 		arg->nr = nbufs;
 	else if (arg->nr > nbufs)
 		return -EINVAL;
 	else if (arg->nr > IORING_MAX_REG_BUFFERS)
 		return -EINVAL;
+	if (check_add_overflow(arg->nr, arg->src_off, &off) || off > nbufs)
+		return -EOVERFLOW;
 	if (check_add_overflow(arg->nr, arg->dst_off, &nbufs))
 		return -EOVERFLOW;
 	if (nbufs > IORING_MAX_REG_BUFFERS)
@@ -1201,31 +1205,16 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx
 	if (ret)
 		return ret;
 
-	/* Fill entries in data from dst that won't overlap with src */
+	/* Copy original dst nodes from before the cloned range */
 	for (i = 0; i < min(arg->dst_off, ctx->buf_table.nr); i++) {
-		struct io_rsrc_node *src_node = ctx->buf_table.nodes[i];
+		struct io_rsrc_node *node = ctx->buf_table.nodes[i];
 
-		if (src_node) {
-			data.nodes[i] = src_node;
-			src_node->refs++;
+		if (node) {
+			data.nodes[i] = node;
+			node->refs++;
 		}
 	}
 
-	ret = -ENXIO;
-	nbufs = src_ctx->buf_table.nr;
-	if (!nbufs)
-		goto out_free;
-	ret = -EINVAL;
-	if (!arg->nr)
-		arg->nr = nbufs;
-	else if (arg->nr > nbufs)
-		goto out_free;
-	ret = -EOVERFLOW;
-	if (check_add_overflow(arg->nr, arg->src_off, &off))
-		goto out_free;
-	if (off > nbufs)
-		goto out_free;
-
 	off = arg->dst_off;
 	i = arg->src_off;
 	nr = arg->nr;
@@ -1238,8 +1227,8 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx
 		} else {
 			dst_node = io_rsrc_node_alloc(ctx, IORING_RSRC_BUFFER);
 			if (!dst_node) {
-				ret = -ENOMEM;
-				goto out_free;
+				io_rsrc_data_free(ctx, &data);
+				return -ENOMEM;
 			}
 
 			refcount_inc(&src_node->buf->refs);
@@ -1249,6 +1238,16 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx
 		i++;
 	}
 
+	/* Copy original dst nodes from after the cloned range */
+	for (i = nbufs; i < ctx->buf_table.nr; i++) {
+		struct io_rsrc_node *node = ctx->buf_table.nodes[i];
+
+		if (node) {
+			data.nodes[i] = node;
+			node->refs++;
+		}
+	}
+
 	/*
 	 * If asked for replace, put the old table. data->nodes[] holds both
 	 * old and new nodes at this point.
@@ -1265,10 +1264,6 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx
 	WARN_ON_ONCE(ctx->buf_table.nr);
 	ctx->buf_table = data;
 	return 0;
-
-out_free:
-	io_rsrc_data_free(ctx, &data);
-	return ret;
 }
 
 /*