From: Eric Dumazet <eric.dumazet@gmail.com>
To: Willem de Bruijn <willemb@google.com>
Cc: netdev@vger.kernel.org, davem@davemloft.net, stephen@networkplumber.org
Subject: Re: [PATCH net-next v2] rps: selective flow shedding during softnet overflow
Date: Mon, 22 Apr 2013 15:30:08 -0700 [thread overview]
Message-ID: <1366669808.16391.90.camel@edumazet-glaptop> (raw)
In-Reply-To: <1366663561-12305-1-git-send-email-willemb@google.com>
On Mon, 2013-04-22 at 16:46 -0400, Willem de Bruijn wrote:
> + len = sizeof(*cur) + netdev_flow_limit_table_len;
[1]
> + mutex_lock(&flow_limit_update_mutex);
[2]
> + for_each_possible_cpu(i) {
> + sd = &per_cpu(softnet_data, i);
> + cur = rcu_dereference_protected(sd->flow_limit,
> + lockdep_is_held(flow_limit_update_mutex));
> + if (cur && !cpumask_test_cpu(i, mask)) {
> + RCU_INIT_POINTER(sd->flow_limit, NULL);
> + synchronize_rcu();
> + kfree(cur);
> + } else if (!cur && cpumask_test_cpu(i, mask)) {
> + cur = kzalloc(len, GFP_KERNEL);
> + cur->num_buckets = netdev_flow_limit_table_len;
[3]
Its a bit tricky, but the value of netdev_flow_limit_table_len could
change between [1] and [3]
So you should read its value once, or protect the whole thing using
mutex_lock(&flow_limit_update_mutex) in sysctl code ( and move [1] after
[2])
next prev parent reply other threads:[~2013-04-22 22:30 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-04-19 17:46 [PATCH] rps: selective flow shedding during softnet overflow Willem de Bruijn
2013-04-19 17:58 ` Eric Dumazet
2013-04-22 20:40 ` Willem de Bruijn
2013-04-22 20:46 ` [PATCH net-next v2] " Willem de Bruijn
2013-04-22 22:30 ` Eric Dumazet [this message]
2013-04-23 18:45 ` Willem de Bruijn
2013-04-23 18:46 ` [PATCH net-next v3] " Willem de Bruijn
2013-04-23 19:18 ` Eric Dumazet
2013-04-23 20:30 ` Willem de Bruijn
2013-04-23 20:31 ` [PATCH net-next v4] " Willem de Bruijn
2013-04-23 21:23 ` Stephen Hemminger
2013-04-23 21:37 ` Willem de Bruijn
2013-04-23 21:37 ` Eric Dumazet
2013-04-23 21:52 ` Stephen Hemminger
2013-04-23 22:34 ` David Miller
2013-04-24 0:09 ` Eric Dumazet
2013-04-24 0:37 ` [PATCH net-next v5] " Willem de Bruijn
2013-04-24 1:07 ` Eric Dumazet
2013-04-25 8:20 ` David Miller
2013-05-20 14:02 ` [PATCH net-next v6] " Willem de Bruijn
2013-05-20 16:00 ` Eric Dumazet
2013-05-20 16:08 ` Willem de Bruijn
2013-05-20 20:48 ` David Miller
2013-04-24 1:25 ` [PATCH net-next v4] " Jamal Hadi Salim
2013-04-24 1:32 ` Eric Dumazet
2013-04-24 1:44 ` Jamal Hadi Salim
2013-04-24 2:11 ` Eric Dumazet
2013-04-24 13:00 ` Jamal Hadi Salim
2013-04-24 14:41 ` Eric Dumazet
2013-04-23 22:33 ` David Miller
2013-04-23 21:34 ` Eric Dumazet
2013-04-23 22:41 ` David Miller
2013-04-23 23:11 ` Eric Dumazet
2013-04-23 23:15 ` David Miller
2013-04-23 23:26 ` Eric Dumazet
2013-04-24 0:03 ` Stephen Hemminger
2013-04-24 0:00 ` Willem de Bruijn
2013-04-23 20:46 ` [PATCH net-next v3] " Eric Dumazet
2013-04-19 19:03 ` [PATCH] " Stephen Hemminger
2013-04-19 19:21 ` Eric Dumazet
2013-04-19 20:11 ` Willem de Bruijn
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=1366669808.16391.90.camel@edumazet-glaptop \
--to=eric.dumazet@gmail.com \
--cc=davem@davemloft.net \
--cc=netdev@vger.kernel.org \
--cc=stephen@networkplumber.org \
--cc=willemb@google.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.