On 11/24/22 5:14 PM, Dylan Yudaken wrote:
I think changing the tests to use the public API is probably better
than exporting this function. I don't believe it has much general use?
But there is no public API that does the same thing. I'll mark it
as static and create a copy of that function in iopoll.c (in v2).
Something like this, what do you think?
src/queue.c | 2 +-
test/iopoll.c | 33 ++++++++++++++++++++++++++++++++-
2 files changed, 33 insertions(+), 2 deletions(-)
diff --git a/src/queue.c b/src/queue.c
index feea0ad..b784b10 100644
--- a/src/queue.c
+++ b/src/queue.c
@@ -201,7 +201,7 @@ again:
* Sync internal state with kernel ring state on the SQ side. Returns the
* number of pending items in the SQ ring, for the shared ring.
*/
-unsigned __io_uring_flush_sq(struct io_uring *ring)
+static unsigned __io_uring_flush_sq(struct io_uring *ring)
{
struct io_uring_sq *sq = &ring->sq;
unsigned tail = sq->sqe_tail;
diff --git a/test/iopoll.c b/test/iopoll.c
index 20f91c7..5edd5c3 100644
--- a/test/iopoll.c
+++ b/test/iopoll.c
@@ -201,7 +201,38 @@ err:
return 1;
}
-extern unsigned __io_uring_flush_sq(struct io_uring *ring);
+/*
+ * Sync internal state with kernel ring state on the SQ side. Returns the
+ * number of pending items in the SQ ring, for the shared ring.
+ */
+static unsigned __io_uring_flush_sq(struct io_uring *ring)
+{
+ struct io_uring_sq *sq = &ring->sq;
+ unsigned tail = sq->sqe_tail;
+
+ if (sq->sqe_head != tail) {
+ sq->sqe_head = tail;
+ /*
+ * Ensure kernel sees the SQE updates before the tail update.
+ */
+ if (!(ring->flags & IORING_SETUP_SQPOLL))
+ IO_URING_WRITE_ONCE(*sq->ktail, tail);
+ else
+ io_uring_smp_store_release(sq->ktail, tail);
+ }
+ /*
+ * This _may_ look problematic, as we're not supposed to be reading
+ * SQ->head without acquire semantics. When we're in SQPOLL mode, the
+ * kernel submitter could be updating this right now. For non-SQPOLL,
+ * task itself does it, and there's no potential race. But even for
+ * SQPOLL, the load is going to be potentially out-of-date the very
+ * instant it's done, regardless or whether or not it's done
+ * atomically. Worst case, we're going to be over-estimating what
+ * we can submit. The point is, we need to be able to deal with this
+ * situation regardless of any perceived atomicity.
+ */
+ return tail - *sq->khead;
+}
/*
* if we are polling io_uring_submit needs to always enter the
--
Ammar Faizi
