diff options
| author | Pavel Begunkov <[email protected]> | 2021-08-15 10:40:26 +0100 |
|---|---|---|
| committer | Jens Axboe <[email protected]> | 2021-08-23 13:10:43 -0600 |
| commit | 906c6caaf586180261ea581915e1cf8bc466bd69 (patch) | |
| tree | 362bec352f429aa6711795fa058fd1479b5f0cb8 /lib/test_fortify/write_overflow-memcpy.c | |
| parent | 0756a8691017518ceeca4c083e7a359107186498 (diff) | |
io_uring: optimise io_prep_linked_timeout()
Linked timeout handling during issuing is heavy, it adds extra
instructions and forces to save the next linked timeout before
io_issue_sqe().
Follwing the same reasoning as in refcounting patches, a request can't
be freed by the time it returns from io_issue_sqe(), so now we don't
need to do io_prep_linked_timeout() in advance, and it can be delayed to
colder paths optimising the generic path.
Also, it should also save quite a lot for requests with linked timeouts
and completed inline on timeout spinlocking + hrtimer_start() +
hrtimer_try_to_cancel() and so on.
Signed-off-by: Pavel Begunkov <[email protected]>
Link: https://lore.kernel.org/r/19bfc9a0d26c5c5f1e359f7650afe807ca8ef879.1628981736.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <[email protected]>
Diffstat (limited to 'lib/test_fortify/write_overflow-memcpy.c')
0 files changed, 0 insertions, 0 deletions