linux-kernel - Re: [PATCH UPDATED] percpu: use dynamic percpu allocator as the default percpu allocator

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:	Thu, 2 Apr 2009 04:10:24 +0200
From:	Ingo Molnar <mingo@...e.hu>
To:	Matthew Wilcox <matthew@....cx>
Cc:	Linus Torvalds <torvalds@...ux-foundation.org>,
	Christoph Lameter <cl@...ux.com>, Tejun Heo <tj@...nel.org>,
	Martin Schwidefsky <schwidefsky@...ibm.com>,
	rusty@...tcorp.com.au, tglx@...utronix.de, x86@...nel.org,
	linux-kernel@...r.kernel.org, hpa@...or.com,
	Paul Mundt <lethal@...ux-sh.org>, rmk@....linux.org.uk,
	starvik@...s.com, ralf@...ux-mips.org, davem@...emloft.net,
	cooloney@...nel.org, kyle@...artin.ca, grundler@...isc-linux.org,
	takata@...ux-m32r.org, benh@...nel.crashing.org, rth@...ddle.net,
	ink@...assic.park.msu.ru, heiko.carstens@...ibm.com,
	Nick Piggin <npiggin@...e.de>,
	Peter Zijlstra <a.p.zijlstra@...llo.nl>
Subject: Re: [PATCH UPDATED] percpu: use dynamic percpu allocator as the
	default percpu allocator

* Matthew Wilcox <matthew@....cx> wrote:

> On Thu, Apr 02, 2009 at 12:32:41AM +0200, Ingo Molnar wrote:
> > And free_percpu(NULL) does this:
> > 
> > void free_percpu(void *ptr)
> > {
> >         void *addr = __pcpu_ptr_to_addr(ptr);
> >         struct pcpu_chunk *chunk;
> >         unsigned long flags;
> >         int off;
> > 
> >         if (!ptr)
> >                 return;
> 
> Why don't we rewrite this as:
> 
> -	void *addr = __pcpu_ptr_to_addr(ptr);
> +	void *addr;
> ...
> 	if (!ptr)
> 		return;
> 	addr = __pcpu_ptr_to_addr(ptr);
> 
> if kfree(NULL) is really that important, we should avoid doing this
> extra work, not just rely on the variable being cache-hot.

Yes, of course we can fix that, the NULL fastpath needs no access to 
anything but the call parameter.

Note that my argument was different though: that assumptions about 
variable correlation are very hard to track and validate, and that 
IMHO we should be using __read_mostly generously (we know _that_ 
attribute with a rather high likelyhood), and we should group the 
remaining variables together, starting at a cacheline aligned 
address.

A sub-argument was that the boundary between global variables from 
different .o files should perhaps not be 'merged' together (on SMP), 
because the sharing effects are not maintainable: an example of 
badness is the sb_lock false cacheline sharing that Christoph's 
patch triggered (randomly).

A sub-sub argument was that perhaps we should not split .data and 
.bss variables into separate sections - it doubles the chance of 
false cacheline sharing and spreads the cacheline footprint.

	Ingo
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/