@@ -24,6 +24,13 @@ struct async_poll {
struct io_poll *double_poll;
};
+static inline void io_poll_multishot_retry(struct io_kiocb *req,
+ unsigned int issue_flags)
+{
+ if (issue_flags & IO_URING_F_MULTISHOT)
+ atomic_inc(&req->poll_refs);
+}
+
int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe);
int io_poll_add(struct io_kiocb *req, unsigned int issue_flags);
@@ -18,6 +18,7 @@
#include "opdef.h"
#include "kbuf.h"
#include "rsrc.h"
+#include "poll.h"
#include "rw.h"
struct io_rw {
@@ -962,8 +963,15 @@ int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags)
if (io_fill_cqe_req_aux(req,
issue_flags & IO_URING_F_COMPLETE_DEFER,
ret, cflags | IORING_CQE_F_MORE)) {
- if (issue_flags & IO_URING_F_MULTISHOT)
+ if (issue_flags & IO_URING_F_MULTISHOT) {
+ /*
+ * Force retry, as we might have more data to
+ * be read and otherwise it won't get retried
+ * until (if ever) another poll is triggered.
+ */
+ io_poll_multishot_retry(req, issue_flags);
return IOU_ISSUE_SKIP_COMPLETE;
+ }
return -EAGAIN;
}
}
io_read_mshot() always relies on poll triggering retries, and this works fine as long as we do a retry per size of the buffer being read. The buffer size is given by the size of the buffer(s) in the given buffer group ID. But if we're reading less than what is available, then we don't always get to read everything that is available. For example, if the buffers available are 32 bytes and we have 64 bytes to read, then we'll correctly read the first 32 bytes and then wait for another poll trigger before we attempt the next read. This next poll trigger may never happen, in which case we just sit forever and never make progress, or it may trigger at some point in the future, and now we're just delivering the available data much later than we should have. io_read_mshot() could do retries itself, but that is wasteful as we'll be going through all of __io_read() again, and most likely in vain. Rather than do that, bump our poll reference count and have io_poll_check_events() do one more loop and check with vfs_poll() if we have more data to read. If we do, io_read_mshot() will get invoked again directly and we'll read the next chunk. io_poll_multishot_retry() must only get called from inside io_poll_issue(), which is our multishot retry handler, as we know we already "own" the request at this point. Cc: stable@vger.kernel.org Link: https://github.com/axboe/liburing/issues/1041 Fixes: fc68fcda0491 ("io_uring/rw: add support for IORING_OP_READ_MULTISHOT") Signed-off-by: Jens Axboe <axboe@kernel.dk> --- Wrote and committed a test case for this as well, find it here: https://git.kernel.dk/cgit/liburing/commit/?id=a8277668275e9d9bf60aa45622584a6a92039608