From: Martin Josefsson <gandalf@wlug.westbo.se> To: Bart De Schuymer <bdschuym@pandora.be> Cc: "David S. Miller" <davem@davemloft.net>, shemminger@osdl.org, dwmw2@infradead.org, ak@suse.de, snort2004@mail.ru, bridge@osdl.org, netdev@oss.sgi.com, Rusty Russell <rusty@rustcorp.com.au> Subject: Re: [PATCH/RFC] Reduce call chain length in netfilter (was: Re: do_IRQ: stack overflow: 872..) Date: Sun, 23 Jan 2005 00:22:33 +0100 [thread overview] Message-ID: <1106436153.20995.42.camel@tux.rsn.bth.se> (raw) In-Reply-To: <1106433059.4486.11.camel@localhost.localdomain> [-- Attachment #1: Type: text/plain, Size: 1557 bytes --] On Sat, 2005-01-22 at 23:30 +0100, Bart De Schuymer wrote: Hi Bart > @@ -138,23 +139,34 @@ void nf_log_packet(int pf, > /* This is gross, but inline doesn't cut it for avoiding the function > call in fast path: gcc doesn't inline (needs value tracking?). --RR */ > #ifdef CONFIG_NETFILTER_DEBUG > -#define NF_HOOK(pf, hook, skb, indev, outdev, okfn) \ > - nf_hook_slow((pf), (hook), (skb), (indev), (outdev), (okfn), INT_MIN) > -#define NF_HOOK_THRESH nf_hook_slow > +#define NF_HOOK(pf, hook, skb, indev, outdev, okfn) \ > +({int __ret = 0; \ > +if (!nf_hook_slow(pf, hook, &(skb), indev, outdev, okfn, INT_MIN, &__ret); \ > + __ret = (okfn)(skb); \ > +__ret;}) > +#define NF_HOOK_THRESH(pf, hook, skb, indev, outdev, okfn, thresh) \ > +({int __ret = 0; \ > +if (!nf_hook_slow(pf, hook, &(skb), indev, outdev, okfn, thresh, &__ret); \ > + __ret = (okfn)(skb); \ > +__ret;}) > #else I guess you never testcompiled with CONFIG_NETFILTER_DEBUG set :) The if-statements above needs to have ; replaced with ) > + if (verdict > NF_MAX_VERDICT) { > + NFDEBUG("Evil return from %p(%u).\n", > + elem->hook, hook); > + continue; > + } Maybe add unlikely() around the test? Otherwise the changes look sane. The reoganisation of things in nf_hook_slow() shouldn't cause any performance changes, I tried to benchmark various variations of that code some time ago but the result of the changes were more or less in the noise. -- /Martin [-- Attachment #2: This is a digitally signed message part --] [-- Type: application/pgp-signature, Size: 189 bytes --]
WARNING: multiple messages have this Message-ID (diff)
From: Martin Josefsson <gandalf@wlug.westbo.se> To: Bart De Schuymer <bdschuym@pandora.be> Cc: netdev@oss.sgi.com, bridge@osdl.org, snort2004@mail.ru, Rusty Russell <rusty@rustcorp.com.au>, dwmw2@infradead.org, "David S. Miller" <davem@davemloft.net>, shemminger@osdl.org, ak@suse.de Subject: [Bridge] Re: [PATCH/RFC] Reduce call chain length in netfilter (was: Re: do_IRQ: stack overflow: 872..) Date: Sun, 23 Jan 2005 00:22:33 +0100 [thread overview] Message-ID: <1106436153.20995.42.camel@tux.rsn.bth.se> (raw) In-Reply-To: <1106433059.4486.11.camel@localhost.localdomain> [-- Attachment #1: Type: text/plain, Size: 1557 bytes --] On Sat, 2005-01-22 at 23:30 +0100, Bart De Schuymer wrote: Hi Bart > @@ -138,23 +139,34 @@ void nf_log_packet(int pf, > /* This is gross, but inline doesn't cut it for avoiding the function > call in fast path: gcc doesn't inline (needs value tracking?). --RR */ > #ifdef CONFIG_NETFILTER_DEBUG > -#define NF_HOOK(pf, hook, skb, indev, outdev, okfn) \ > - nf_hook_slow((pf), (hook), (skb), (indev), (outdev), (okfn), INT_MIN) > -#define NF_HOOK_THRESH nf_hook_slow > +#define NF_HOOK(pf, hook, skb, indev, outdev, okfn) \ > +({int __ret = 0; \ > +if (!nf_hook_slow(pf, hook, &(skb), indev, outdev, okfn, INT_MIN, &__ret); \ > + __ret = (okfn)(skb); \ > +__ret;}) > +#define NF_HOOK_THRESH(pf, hook, skb, indev, outdev, okfn, thresh) \ > +({int __ret = 0; \ > +if (!nf_hook_slow(pf, hook, &(skb), indev, outdev, okfn, thresh, &__ret); \ > + __ret = (okfn)(skb); \ > +__ret;}) > #else I guess you never testcompiled with CONFIG_NETFILTER_DEBUG set :) The if-statements above needs to have ; replaced with ) > + if (verdict > NF_MAX_VERDICT) { > + NFDEBUG("Evil return from %p(%u).\n", > + elem->hook, hook); > + continue; > + } Maybe add unlikely() around the test? Otherwise the changes look sane. The reoganisation of things in nf_hook_slow() shouldn't cause any performance changes, I tried to benchmark various variations of that code some time ago but the result of the changes were more or less in the noise. -- /Martin [-- Attachment #2: This is a digitally signed message part --] [-- Type: application/pgp-signature, Size: 189 bytes --]
next prev parent reply other threads:[~2005-01-22 23:22 UTC|newest] Thread overview: 52+ messages / expand[flat|nested] mbox.gz Atom feed top [not found] <1131604877.20041218092730@mail.ru.suse.lists.linux.kernel> 2004-12-18 7:50 ` do_IRQ: stack overflow: 872 Andi Kleen 2004-12-18 11:12 ` Bart De Schuymer 2004-12-18 11:14 ` Andi Kleen 2004-12-18 11:51 ` Bart De Schuymer 2004-12-18 13:53 ` Andi Kleen 2004-12-18 16:07 ` Re[2]: " Crazy AMD K7 2004-12-18 16:46 ` Bart De Schuymer 2005-01-07 17:05 ` David Woodhouse 2005-01-07 18:00 ` Stephen Hemminger 2005-01-07 18:00 ` [Bridge] " Stephen Hemminger 2005-01-07 18:06 ` David Woodhouse 2005-01-07 18:06 ` [Bridge] " David Woodhouse 2005-01-07 21:27 ` Bart De Schuymer 2005-01-07 21:27 ` [Bridge] " Bart De Schuymer 2005-01-18 21:57 ` David S. Miller 2005-01-18 21:57 ` [Bridge] " David S. Miller 2005-01-22 22:30 ` [PATCH/RFC] Reduce call chain length in netfilter (was: Re: do_IRQ: stack overflow: 872..) Bart De Schuymer 2005-01-22 22:30 ` [Bridge] " Bart De Schuymer 2005-01-22 23:22 ` Martin Josefsson [this message] 2005-01-22 23:22 ` [Bridge] " Martin Josefsson 2005-01-23 12:40 ` Bart De Schuymer 2005-01-23 12:40 ` [Bridge] " Bart De Schuymer 2005-01-23 16:08 ` Martin Josefsson 2005-01-23 16:08 ` [Bridge] " Martin Josefsson 2005-01-26 6:05 ` David S. Miller 2005-01-26 6:05 ` [Bridge] " David S. Miller 2005-01-26 9:08 ` Bart De Schuymer 2005-01-26 9:08 ` [Bridge] " Bart De Schuymer 2005-01-26 23:49 ` [PATCH/RFC] Reduce call chain length in netfilter Patrick McHardy 2005-01-26 23:49 ` [Bridge] " Patrick McHardy 2005-01-27 7:18 ` David S. Miller 2005-01-27 7:18 ` [Bridge] " David S. Miller 2005-01-27 17:50 ` Patrick McHardy 2005-01-27 17:50 ` [Bridge] " Patrick McHardy 2005-01-27 19:47 ` David S. Miller 2005-01-27 19:47 ` [Bridge] " David S. Miller 2005-01-27 21:16 ` Bart De Schuymer 2005-01-27 21:16 ` [Bridge] " Bart De Schuymer 2005-01-27 22:48 ` Patrick McHardy 2005-01-27 22:48 ` [Bridge] " Patrick McHardy 2005-01-27 23:24 ` David S. Miller 2005-01-27 23:24 ` [Bridge] " David S. Miller 2005-01-28 0:08 ` Patrick McHardy 2005-01-28 0:08 ` [Bridge] " Patrick McHardy 2005-01-28 0:29 ` Rusty Russell 2005-01-28 0:29 ` [Bridge] " Rusty Russell 2005-01-28 1:10 ` David S. Miller 2005-01-28 1:10 ` [Bridge] " David S. Miller 2005-01-28 1:32 ` Rusty Russell 2005-01-28 1:32 ` [Bridge] " Rusty Russell 2005-01-28 1:35 ` Patrick McHardy 2005-01-28 1:35 ` [Bridge] " Patrick McHardy
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=1106436153.20995.42.camel@tux.rsn.bth.se \ --to=gandalf@wlug.westbo.se \ --cc=ak@suse.de \ --cc=bdschuym@pandora.be \ --cc=bridge@osdl.org \ --cc=davem@davemloft.net \ --cc=dwmw2@infradead.org \ --cc=netdev@oss.sgi.com \ --cc=rusty@rustcorp.com.au \ --cc=shemminger@osdl.org \ --cc=snort2004@mail.ru \ /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: linkBe 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.