Running local task_work requires taking uring_lock, for submit + wait we
can try to run them right after submit while we still hold the lock and
save one lock/unlokc pair. The optimisation was implemented in the first
local tw patches but got dropped for simplicity.
Suggested-by: Dylan Yudaken <dylany@xxxxxx>
Signed-off-by: Pavel Begunkov <asml.silence@xxxxxxxxx>
---
io_uring/io_uring.c | 12 ++++++++++--
io_uring/io_uring.h | 7 +++++++
2 files changed, 17 insertions(+), 2 deletions(-)
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 355fc1f3083d..b092473eca1d 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -3224,8 +3224,16 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
mutex_unlock(&ctx->uring_lock);
goto out;
}
- if ((flags & IORING_ENTER_GETEVENTS) && ctx->syscall_iopoll)
- goto iopoll_locked;
+ if (flags & IORING_ENTER_GETEVENTS) {
+ if (ctx->syscall_iopoll)
+ goto iopoll_locked;
+ /*
+ * Ignore errors, we'll soon call io_cqring_wait() and
+ * it should handle ownership problems if any.
+ */
+ if (ctx->flags & IORING_SETUP_DEFER_TASKRUN)
+ (void)io_run_local_work_locked(ctx);
+ }
mutex_unlock(&ctx->uring_lock);
}
diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h
index e733d31f31d2..8504bc1f3839 100644
--- a/io_uring/io_uring.h
+++ b/io_uring/io_uring.h
@@ -275,6 +275,13 @@ static inline int io_run_task_work_ctx(struct io_ring_ctx *ctx)
return ret;
}
+static inline int io_run_local_work_locked(struct io_ring_ctx *ctx)
+{
+ if (llist_empty(&ctx->work_llist))
+ return 0;
+ return __io_run_local_work(ctx, true);
+}
+
static inline void io_tw_lock(struct io_ring_ctx *ctx, bool *locked)
{
if (!*locked) {
--
2.37.3
