@@ -1117,7 +1117,7 @@ static void io_req_local_work_add(struct io_kiocb *req)
__io_cqring_wake(ctx);
}
-static inline void __io_req_task_work_add(struct io_kiocb *req, bool allow_local)
+void __io_req_task_work_add(struct io_kiocb *req, bool allow_local)
{
struct io_uring_task *tctx = req->task->io_uring;
struct io_ring_ctx *ctx = req->ctx;
@@ -1149,11 +1149,6 @@ static inline void __io_req_task_work_add(struct io_kiocb *req, bool allow_local
}
}
-void io_req_task_work_add(struct io_kiocb *req)
-{
- __io_req_task_work_add(req, true);
-}
-
static void __cold io_move_task_work_from_local(struct io_ring_ctx *ctx)
{
struct llist_node *node;
@@ -48,9 +48,9 @@ static inline bool io_req_ffs_set(struct io_kiocb *req)
return req->flags & REQ_F_FIXED_FILE;
}
+void __io_req_task_work_add(struct io_kiocb *req, bool allow_local);
bool io_is_uring_fops(struct file *file);
bool io_alloc_async_data(struct io_kiocb *req);
-void io_req_task_work_add(struct io_kiocb *req);
void io_req_tw_post_queue(struct io_kiocb *req, s32 res, u32 cflags);
void io_req_task_queue(struct io_kiocb *req);
void io_queue_iowq(struct io_kiocb *req, bool *dont_use);
@@ -80,6 +80,11 @@ bool __io_alloc_req_refill(struct io_ring_ctx *ctx);
bool io_match_task_safe(struct io_kiocb *head, struct task_struct *task,
bool cancel_all);
+static inline void io_req_task_work_add(struct io_kiocb *req)
+{
+ __io_req_task_work_add(req, true);
+}
+
#define io_for_each_link(pos, head) \
for (pos = (head); pos; pos = pos->link)
__io_req_task_work_add() is huge but marked inline, that makes compilers to generate lots of garbage. Inline the wrapper caller io_req_task_work_add() instead. before and after: text data bss dec hex filename 47347 16248 8 63603 f873 io_uring/io_uring.o text data bss dec hex filename 45303 16248 8 61559 f077 io_uring/io_uring.o Signed-off-by: Pavel Begunkov <asml.silence@gmail.com> --- io_uring/io_uring.c | 7 +------ io_uring/io_uring.h | 7 ++++++- 2 files changed, 7 insertions(+), 7 deletions(-)