io_uring: optimise completion timeout flushing

io_commit_cqring() might be very hot and we definitely don't want to
touch ->timeout_list there, because 1) it's shared with the submission
side so might lead to cache bouncing and 2) may need to load an extra
cache line, especially for IRQ completions.

We're interested in it at the completion side only when there are
offset-mode timeouts, which are not so popular. Replace
list_empty(->timeout_list) hot path check with a new one-way flag, which
is set when we prepare the first offset-mode timeout.

note: the flag sits in the same line as briefly used after ->rings

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/e4892ec68b71a69f92ffbea4a1499be3ec0d463b.1623709150.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 ecac362913cc9bd40c0c0eb945c10a05d3ec9c04..b27734bc5ca366a8b760ba7d166cac15985c1a58 100644 (file)
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -351,6 +351,7 @@ struct io_ring_ctx {
                unsigned int            drain_next: 1;
                unsigned int            eventfd_async: 1;
                unsigned int            restricted: 1;
+               unsigned int            off_timeout_used: 1;
        } ____cacheline_aligned_in_smp;
 
        /* submission data */
@@ -1318,12 +1319,12 @@ static void io_flush_timeouts(struct io_ring_ctx *ctx)
 {
        u32 seq;
 
-       if (list_empty(&ctx->timeout_list))
+       if (likely(!ctx->off_timeout_used))
                return;
 
        seq = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts);
 
-       do {
+       while (!list_empty(&ctx->timeout_list)) {
                u32 events_needed, events_got;
                struct io_kiocb *req = list_first_entry(&ctx->timeout_list,
                                                struct io_kiocb, timeout.list);
@@ -1345,8 +1346,7 @@ static void io_flush_timeouts(struct io_ring_ctx *ctx)
 
                list_del_init(&req->timeout.list);
                io_kill_timeout(req, 0);
-       } while (!list_empty(&ctx->timeout_list));
-
+       }
        ctx->cq_last_tm_flush = seq;
 }
 
@@ -5651,6 +5651,8 @@ static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe,
                return -EINVAL;
 
        req->timeout.off = off;
+       if (unlikely(off && !req->ctx->off_timeout_used))
+               req->ctx->off_timeout_used = true;
 
        if (!req->async_data && io_alloc_async_data(req))
                return -ENOMEM;