From: Peter Zijlstra <peterz@infradead.org>
To: Shaokun Zhang <zhangshaokun@hisilicon.com>
Cc: Eric Dumazet <eric.dumazet@gmail.com>,
David Miller <davem@davemloft.net>,
netdev@vger.kernel.org, linux-kernel@vger.kernel.org,
jinyuqi@huawei.com, kuznet@ms2.inr.ac.ru,
yoshfuji@linux-ipv6.org, edumazet@google.com,
guoyang2@huawei.com, Will Deacon <will@kernel.org>
Subject: Re: [PATCH] net: optimize cmpxchg in ip_idents_reserve
Date: Fri, 17 Jan 2020 13:32:53 +0100 [thread overview]
Message-ID: <20200117123253.GC14879@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <430496fc-9f26-8cb4-91d8-505fda9af230@hisilicon.com>
On Fri, Jan 17, 2020 at 02:54:03PM +0800, Shaokun Zhang wrote:
> So how about this? ;-)
>
> delta = prandom_u32_max(now - old);
>
> +#ifdef CONFIG_UBSAN
> /* Do not use atomic_add_return() as it makes UBSAN unhappy */
> + old = (u32)atomic_read(p_id);
> do {
> - old = (u32)atomic_read(p_id);
> new = old + delta + segs;
> - } while (atomic_cmpxchg(p_id, old, new) != old);
> + } while (!atomic_try_cmpxchg(p_id, &old, new));
> +#else
> + new = atomic_add_return(segs + delta, p_id);
> +#endif
That's crazy, just accept that UBSAN is taking bonghits and ignore it.
Use atomic_add_return() unconditionally.
next prev parent reply other threads:[~2020-01-17 12:33 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-01-15 3:23 [PATCH] net: optimize cmpxchg in ip_idents_reserve Shaokun Zhang
2020-01-16 12:27 ` David Miller
2020-01-16 14:05 ` Shaokun Zhang
2020-01-16 15:12 ` Eric Dumazet
2020-01-16 15:19 ` Eric Dumazet
2020-01-17 6:54 ` Shaokun Zhang
2020-01-17 12:32 ` Peter Zijlstra [this message]
2020-01-17 16:35 ` Eric Dumazet
2020-01-17 18:03 ` Arvind Sankar
2020-01-17 18:16 ` Eric Dumazet
2020-01-17 18:38 ` Arvind Sankar
2020-01-17 18:48 ` Eric Dumazet
2020-01-20 8:18 ` Peter Zijlstra
2020-05-07 9:12 ` Shaokun Zhang
2020-05-07 13:49 ` Eric Dumazet
2020-01-19 3:46 ` Shaokun Zhang
2020-01-19 4:12 ` Eric Dumazet
2020-01-21 2:40 ` Shaokun Zhang
2020-01-22 8:49 ` Peter Zijlstra
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=20200117123253.GC14879@hirez.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=eric.dumazet@gmail.com \
--cc=guoyang2@huawei.com \
--cc=jinyuqi@huawei.com \
--cc=kuznet@ms2.inr.ac.ru \
--cc=linux-kernel@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=will@kernel.org \
--cc=yoshfuji@linux-ipv6.org \
--cc=zhangshaokun@hisilicon.com \
/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;
as well as URLs for NNTP newsgroup(s).