linux-kernel - Re: AIM7 40% regression with 2.6.26-rc1

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]

Message-Id: <20080506110752.ca54623f.akpm@linux-foundation.org>
Date:	Tue, 6 May 2008 11:07:52 -0700
From:	Andrew Morton <akpm@...ux-foundation.org>
To:	Ingo Molnar <mingo@...e.hu>
Cc:	matthew@....cx, bfields@...i.umich.edu,
	yanmin_zhang@...ux.intel.com, linux-kernel@...r.kernel.org,
	viro@....linux.org.uk, torvalds@...ux-foundation.org,
	linux-fsdevel@...r.kernel.org
Subject: Re: AIM7 40% regression with 2.6.26-rc1

On Tue, 6 May 2008 19:49:54 +0200
Ingo Molnar <mingo@...e.hu> wrote:

> 
> * Matthew Wilcox <matthew@....cx> wrote:
> 
> > > down(), down_interruptible() and down_try() should use 
> > > spin_lock_irq(), not irqsave.
> > 
> > We talked about this ... the BKL actually requires that you be able to 
> > acquire it with interrupts disabled. [...]
> 
> hm, where does it require it, besides the early bootup code? (which 
> should just be fixed)

Yeah, the early bootup code.  The kernel does accidental lock_kernel()s in
various places and if that renables interrupts then powerpc goeth crunch.

Matthew, that seemingly-unneeded irqsave in lib/semaphore.c is a prime site
for /* one of these things */, no?

> down_trylock() is OK as irqsave/irqrestore for legacy reasons, but that 
> is fundamentally atomic anyway.

yes, trylock should be made irq-safe.

> > > up() seems to be doing wake-one, FIFO which is nice.  Did the 
> > > implementation which we just removed also do that?  Was it perhaps 
> > > accidentally doing LIFO or something like that?
> > 
> > That's a question for someone who knows x86 assembler, I think.
> 
> the assembly is mostly just for the fastpath - and a 40% regression 
> cannot be about fastpath differences. In the old code the scheduling 
> happens in lib/semaphore-sleeper.c, and from the looks of it it appears 
> to be a proper FIFO as well. (plus this small wakeup weirdness it has)
> 
> i reviewed the new code in kernel/semaphore.c as well and can see 
> nothing bad in it - it does proper wake-up, FIFO queueing, like the 
> mutex code.
> 

There's the weird wakeup in down() which I understood for about five
minutes five years ago.  Perhaps that accidentally sped something up.
Oh well, more investigation needed..
--
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/