From: Pavel Begunkov <[email protected]>
To: Jens Axboe <[email protected]>, [email protected]
Subject: [PATCH 03/10] io_uring: dismantle req early and remove need_iter
Date: Sun, 28 Jun 2020 12:52:31 +0300 [thread overview]
Message-ID: <4f56207c1ac5ae6a26f7bb0e4d45fd197d9623de.1593337097.git.asml.silence@gmail.com> (raw)
In-Reply-To: <[email protected]>
Every request in io_req_multi_free() is having ->file, instead of
pointlessly defering and counting reqs with file, dismantle it
on place and save for batch dealloc.
It also saves us from potentially skipping io_cleanup_req(), put_task(),
etc. Never happens though, becacuse ->file is always there.
Signed-off-by: Pavel Begunkov <[email protected]>
---
fs/io_uring.c | 14 +++-----------
1 file changed, 3 insertions(+), 11 deletions(-)
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 28a66e85ef9f..f3c6506e9df1 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -1540,22 +1540,16 @@ static void __io_free_req(struct io_kiocb *req)
struct req_batch {
void *reqs[IO_IOPOLL_BATCH];
int to_free;
- int need_iter;
};
static void io_free_req_many(struct io_ring_ctx *ctx, struct req_batch *rb)
{
if (!rb->to_free)
return;
- if (rb->need_iter) {
- int i;
- for (i = 0; i < rb->to_free; i++)
- io_dismantle_req(rb->reqs[i]);
- }
kmem_cache_free_bulk(req_cachep, rb->to_free, rb->reqs);
percpu_ref_put_many(&ctx->refs, rb->to_free);
- rb->to_free = rb->need_iter = 0;
+ rb->to_free = 0;
}
static bool io_link_cancel_timeout(struct io_kiocb *req)
@@ -1846,9 +1840,7 @@ static inline bool io_req_multi_free(struct req_batch *rb, struct io_kiocb *req)
if ((req->flags & REQ_F_LINK_HEAD) || io_is_fallback_req(req))
return false;
- if (req->file || req->io)
- rb->need_iter++;
-
+ io_dismantle_req(req);
rb->reqs[rb->to_free++] = req;
if (unlikely(rb->to_free == ARRAY_SIZE(rb->reqs)))
io_free_req_many(req->ctx, rb);
@@ -1900,7 +1892,7 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
/* order with ->result store in io_complete_rw_iopoll() */
smp_rmb();
- rb.to_free = rb.need_iter = 0;
+ rb.to_free = 0;
while (!list_empty(done)) {
int cflags = 0;
--
2.24.0
next prev parent reply other threads:[~2020-06-28 9:54 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-06-28 9:52 [PATCH 00/10] some fixing + refactoring batch-free Pavel Begunkov
2020-06-28 9:52 ` [PATCH 01/10] io_uring: fix refs underflow in io_iopoll_queue() Pavel Begunkov
2020-06-28 9:52 ` [PATCH 02/10] io_uring: remove inflight batching in free_many() Pavel Begunkov
2020-06-28 9:52 ` Pavel Begunkov [this message]
2020-06-28 9:52 ` [PATCH 04/10] io_uring: batch-free linked reqs as well Pavel Begunkov
2020-06-28 9:52 ` [PATCH 05/10] io_uring: cosmetic changes for batch free Pavel Begunkov
2020-06-28 9:52 ` [PATCH 06/10] io_uring: kill REQ_F_LINK_NEXT Pavel Begunkov
2020-06-28 9:52 ` [PATCH 07/10] io_uring: clean up req->result setting by rw Pavel Begunkov
2020-06-28 9:52 ` [PATCH 08/10] io_uring: fix missing wake_up io_rw_reissue() Pavel Begunkov
2020-06-28 14:12 ` Jens Axboe
2020-06-28 14:48 ` Pavel Begunkov
2020-06-28 9:52 ` [PATCH 09/10] io_uring: do task_work_run() during iopoll Pavel Begunkov
2020-06-28 9:52 ` [PATCH 10/10] io_uring: fix iopoll -EAGAIN handling Pavel Begunkov
2020-06-28 14:09 ` [PATCH 00/10] some fixing + refactoring batch-free Jens Axboe
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=4f56207c1ac5ae6a26f7bb0e4d45fd197d9623de.1593337097.git.asml.silence@gmail.com \
[email protected] \
[email protected] \
[email protected] \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox