[PATCH] io_uring: read/readv must commit ring mapped buffers upfront

[Jens Axboe <axboe@kernel.dk>]

For recv/recvmsg, IO either completes immediately or gets queued for a
retry. This isn't the case for read/readv, if eg a normal file or a block
device is used. Here, an operation can get queued with the block layer.
If this happens, ring mapped buffers must get committed immediately to
avoid that the next read can consume the same buffer.

Add an io_op_def flag for this, buffer_ring_commit. If set, when a mapped
buffer is selected, it is immediately committed.

Fixes: c7fb19428d67 ("io_uring: add support for ring mapped supplied buffers")
Signed-off-by: Jens Axboe <axboe@kernel.dk>

---

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 5d479428d8e5..05703bcf73fd 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1098,6 +1098,8 @@ struct io_op_def {
 	unsigned		poll_exclusive : 1;
 	/* op supports buffer selection */
 	unsigned		buffer_select : 1;
+	/* op needs immediate commit of ring mapped buffers */
+	unsigned		buffer_ring_commit : 1;
 	/* do prep async if is going to be punted */
 	unsigned		needs_async_setup : 1;
 	/* opcode is not supported by this kernel */
@@ -1122,6 +1124,7 @@ static const struct io_op_def io_op_defs[] = {
 		.unbound_nonreg_file	= 1,
 		.pollin			= 1,
 		.buffer_select		= 1,
+		.buffer_ring_commit	= 1,
 		.needs_async_setup	= 1,
 		.plug			= 1,
 		.audit_skip		= 1,
@@ -1239,6 +1242,7 @@ static const struct io_op_def io_op_defs[] = {
 		.unbound_nonreg_file	= 1,
 		.pollin			= 1,
 		.buffer_select		= 1,
+		.buffer_ring_commit	= 1,
 		.plug			= 1,
 		.audit_skip		= 1,
 		.ioprio			= 1,
@@ -3836,7 +3840,8 @@ static void __user *io_ring_buffer_select(struct io_kiocb *req, size_t *len,
 	req->buf_list = bl;
 	req->buf_index = buf->bid;
 
-	if (issue_flags & IO_URING_F_UNLOCKED) {
+	if (issue_flags & IO_URING_F_UNLOCKED ||
+	    io_op_defs[req->opcode].buffer_ring_commit) {
 		/*
 		 * If we came in unlocked, we have no choice but to consume the
 		 * buffer here. This does mean it'll be pinned until the IO

-- 
Jens Axboe