This serves two purposes:
- We now have the last cacheline mostly unused for generic workloads,
instead of having to pull in the poll refs explicitly for workloads
that rely on poll arming.
- It shrinks the io_kiocb from 232 to 224 bytes.
Signed-off-by: Jens Axboe <axboe@xxxxxxxxx>
---
diff --git a/fs/io_uring.c b/fs/io_uring.c
index b17cf54653df..fa4e2cb47e56 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -908,6 +908,7 @@ struct io_kiocb {
/* used by request caches, completion batching and iopoll */
struct io_wq_work_node comp_list;
atomic_t refs;
+ atomic_t poll_refs;
struct io_kiocb *link;
struct io_task_work io_task_work;
/* for polled requests, i.e. IORING_OP_POLL_ADD and async armed poll */
@@ -916,12 +917,11 @@ struct io_kiocb {
struct async_poll *apoll;
/* opcode allocated if it needs to store data for async defer */
void *async_data;
- struct io_wq_work work;
/* custom credentials, valid IFF REQ_F_CREDS is set */
- const struct cred *creds;
/* stores selected buf, valid IFF REQ_F_BUFFER_SELECTED is set */
struct io_buffer *kbuf;
- atomic_t poll_refs;
+ const struct cred *creds;
+ struct io_wq_work work;
};
struct io_tctx_node {
--
Jens Axboe
