io_uring: move multishot cqe cache in ctx

We cache multishot CQEs before flushing them to the CQ in
submit_state.cqe. It's a 16 entry cache totalling 256 bytes in the
middle of the io_submit_state structure. Move it out of there, it
should help with CPU caches for the submission state, and shouldn't
affect cached CQEs.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/dbe1f39c043ee23da918836be44fcec252ce6711.1692916914.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index 5de5dff..01bdbc2 100644 (file)
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -176,7 +176,6 @@ struct io_submit_state {
        unsigned short          submit_nr;
        unsigned int            cqes_count;
        struct blk_plug         plug;
-       struct io_uring_cqe     cqes[16];
 };
 
 struct io_ev_fd {
@@ -307,6 +306,8 @@ struct io_ring_ctx {
                unsigned                cq_last_tm_flush;
        } ____cacheline_aligned_in_smp;
 
+       struct io_uring_cqe     completion_cqes[16];
+
        /* IRQ completion list, under ->completion_lock */
        struct io_wq_work_list  locked_free_list;
        unsigned int            locked_free_nr;

diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index a6eea39..8859985 100644 (file)
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -880,7 +880,7 @@ static void __io_flush_post_cqes(struct io_ring_ctx *ctx)
 
        lockdep_assert_held(&ctx->uring_lock);
        for (i = 0; i < state->cqes_count; i++) {
-               struct io_uring_cqe *cqe = &state->cqes[i];
+               struct io_uring_cqe *cqe = &ctx->completion_cqes[i];
 
                if (!io_fill_cqe_aux(ctx, cqe->user_data, cqe->res, cqe->flags)) {
                        if (ctx->task_complete) {
@@ -931,7 +931,7 @@ bool io_fill_cqe_req_aux(struct io_kiocb *req, bool defer, s32 res, u32 cflags)
 
        lockdep_assert_held(&ctx->uring_lock);
 
-       if (ctx->submit_state.cqes_count == ARRAY_SIZE(ctx->submit_state.cqes)) {
+       if (ctx->submit_state.cqes_count == ARRAY_SIZE(ctx->completion_cqes)) {
                __io_cq_lock(ctx);
                __io_flush_post_cqes(ctx);
                /* no need to flush - flush is deferred */
@@ -945,7 +945,7 @@ bool io_fill_cqe_req_aux(struct io_kiocb *req, bool defer, s32 res, u32 cflags)
        if (test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq))
                return false;
 
-       cqe = &ctx->submit_state.cqes[ctx->submit_state.cqes_count++];
+       cqe = &ctx->completion_cqes[ctx->submit_state.cqes_count++];
        cqe->user_data = user_data;
        cqe->res = res;
        cqe->flags = cflags;