io_uring: optimise io_commit_cqring()

In most cases io_commit_cqring() is just an smp_store_release(), and
it's hot enough, especially for IRQ rw, to want it to save on a function
call. Mark it inline and extract a non-inlined slow path doing drain
and timeout flushing. The inlined part is pretty slim to not cause
binary bloating.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/7350f8b6b92caa50a48a80be39909f0d83eddd93.1623772051.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/fs/io_uring.c b/fs/io_uring.c
index f63fc79..16156a6 100644 (file)
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1344,14 +1344,18 @@ static void io_flush_timeouts(struct io_ring_ctx *ctx)
        ctx->cq_last_tm_flush = seq;
 }
 
-static void io_commit_cqring(struct io_ring_ctx *ctx)
+static void __io_commit_cqring_flush(struct io_ring_ctx *ctx)
 {
-       if (unlikely(ctx->off_timeout_used || ctx->drain_active)) {
-               if (ctx->off_timeout_used)
-                       io_flush_timeouts(ctx);
-               if (ctx->drain_active)
-                       io_queue_deferred(ctx);
-       }
+       if (ctx->off_timeout_used)
+               io_flush_timeouts(ctx);
+       if (ctx->drain_active)
+               io_queue_deferred(ctx);
+}
+
+static inline void io_commit_cqring(struct io_ring_ctx *ctx)
+{
+       if (unlikely(ctx->off_timeout_used || ctx->drain_active))
+               __io_commit_cqring_flush(ctx);
        /* order cqe stores with ring update */
        smp_store_release(&ctx->rings->cq.tail, ctx->cached_cq_tail);
 }