diff mbox series

[2/2] io_uring/rsrc: allow cloning with node replacements

Message ID 20241030165556.64918-3-axboe@kernel.dk (mailing list archive)
State New
Headers show
Series Add support for cloning partial buffer sets | expand

Commit Message

Jens Axboe Oct. 30, 2024, 4:54 p.m. UTC
Currently cloning a buffer table will fail if the destination already has
a table. But it should be possible to use it to replace existing elements.
Add a IORING_REGISTER_DST_REPLACE cloning flag, which if set, will allow
the destination to already having a buffer table. If that is the case,
then entries designated by offset + nr buffers will be replaced if they
already exist.

Note that it's allowed to use IORING_REGISTER_DST_REPLACE and not have
an existing table, in which case it'll work just like not having the
flag set and an empty table - it'll just assign the newly created table
for that case.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/uapi/linux/io_uring.h |  3 ++-
 io_uring/rsrc.c               | 24 ++++++++++++++++++++----
 2 files changed, 22 insertions(+), 5 deletions(-)
diff mbox series

Patch

diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index cc8dbe78c126..ce58c4590de6 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -713,7 +713,8 @@  struct io_uring_clock_register {
 };
 
 enum {
-	IORING_REGISTER_SRC_REGISTERED = 1,
+	IORING_REGISTER_SRC_REGISTERED	= (1U << 0),
+	IORING_REGISTER_DST_REPLACE	= (1U << 1),
 };
 
 struct io_uring_clone_buffers {
diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c
index 4c149dc42fd7..9829c51105ed 100644
--- a/io_uring/rsrc.c
+++ b/io_uring/rsrc.c
@@ -990,9 +990,25 @@  static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx
 	/* Have a ref on the bufs now, drop src lock and re-grab our own lock */
 	mutex_unlock(&src_ctx->uring_lock);
 	mutex_lock(&ctx->uring_lock);
-	if (!ctx->buf_table.nr) {
+
+	/*
+	 * Not replacing, or replacing an empty table. Just install the
+	 * new table.
+	 */
+	if (!(arg->flags & IORING_REGISTER_DST_REPLACE) || !ctx->buf_table.nr) {
 		ctx->buf_table = data;
 		return 0;
+	} else if (arg->flags & IORING_REGISTER_DST_REPLACE) {
+		/* put nodes in overlapping spots, if any */
+		for (i = arg->src_off; i < arg->nr; i++) {
+			if (data.nodes[i] == rsrc_empty_node)
+				continue;
+			io_reset_rsrc_node(&ctx->buf_table, i);
+			ctx->buf_table.nodes[i] = data.nodes[i];
+			data.nodes[i] = NULL;
+		}
+		io_rsrc_data_free(&data);
+		return 0;
 	}
 
 	mutex_unlock(&ctx->uring_lock);
@@ -1026,12 +1042,12 @@  int io_register_clone_buffers(struct io_ring_ctx *ctx, void __user *arg)
 	struct file *file;
 	int ret;
 
-	if (ctx->buf_table.nr)
-		return -EBUSY;
 	if (copy_from_user(&buf, arg, sizeof(buf)))
 		return -EFAULT;
-	if (buf.flags & ~IORING_REGISTER_SRC_REGISTERED)
+	if (buf.flags & ~(IORING_REGISTER_SRC_REGISTERED|IORING_REGISTER_DST_REPLACE))
 		return -EINVAL;
+	if (!(buf.flags & IORING_REGISTER_DST_REPLACE) && ctx->buf_table.nr)
+		return -EBUSY;
 	if (memchr_inv(buf.pad, 0, sizeof(buf.pad)))
 		return -EINVAL;