io_uring: static_key for !IORING_SETUP_NO_SQARRAY

IORING_SETUP_NO_SQARRAY should be preferred and used by default by
liburing, optimise flag checking in io_get_sqe() with a static key.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/c164a48542fbb080115e2377ecf160c758562742.1729264988.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index c0358a8d85d27014a918638c49a416b6bd2ebfa4..fa9d31034c626e74f07ff7d1a27d194adb1a7d38 100644 (file)
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -70,6 +70,7 @@
 #include <linux/io_uring/cmd.h>
 #include <linux/audit.h>
 #include <linux/security.h>
+#include <linux/jump_label.h>
 #include <asm/shmparam.h>
 
 #define CREATE_TRACE_POINTS
@@ -149,6 +150,8 @@ static bool io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
 
 static void io_queue_sqe(struct io_kiocb *req);
 
+static __read_mostly DEFINE_STATIC_KEY_FALSE(io_key_has_sqarray);
+
 struct kmem_cache *req_cachep;
 static struct workqueue_struct *iou_wq __ro_after_init;
 
@@ -2254,7 +2257,8 @@ static bool io_get_sqe(struct io_ring_ctx *ctx, const struct io_uring_sqe **sqe)
        unsigned mask = ctx->sq_entries - 1;
        unsigned head = ctx->cached_sq_head++ & mask;
 
-       if (!(ctx->flags & IORING_SETUP_NO_SQARRAY)) {
+       if (static_branch_unlikely(&io_key_has_sqarray) &&
+           (!(ctx->flags & IORING_SETUP_NO_SQARRAY))) {
                head = READ_ONCE(ctx->sq_array[head]);
                if (unlikely(head >= ctx->sq_entries)) {
                        /* drop invalid entries */
@@ -2758,6 +2762,9 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx)
        }
        io_rings_free(ctx);
 
+       if (!(ctx->flags & IORING_SETUP_NO_SQARRAY))
+               static_branch_dec(&io_key_has_sqarray);
+
        percpu_ref_exit(&ctx->refs);
        free_uid(ctx->user);
        io_req_caches_free(ctx);
@@ -3549,6 +3556,9 @@ static __cold int io_uring_create(unsigned entries, struct io_uring_params *p,
        ctx->clockid = CLOCK_MONOTONIC;
        ctx->clock_offset = 0;
 
+       if (!(ctx->flags & IORING_SETUP_NO_SQARRAY))
+               static_branch_inc(&io_key_has_sqarray);
+
        if ((ctx->flags & IORING_SETUP_DEFER_TASKRUN) &&
            !(ctx->flags & IORING_SETUP_IOPOLL) &&
            !(ctx->flags & IORING_SETUP_SQPOLL))