[Fwd: [Ltt-dev] MIPS atomic operations, "sync"]

[Fwd: [Ltt-dev] MIPS atomic operations, "sync"]

[Sergei Shtylyov]

Forwarding to the correct mail list...

-------- Original Message --------
Subject: [Ltt-dev] MIPS atomic operations, "sync"
Date: Fri, 10 Nov 2006 13:36:53 -0500
From: Mathieu Desnoyers <compudj@krystal.dyndns.org>
To: lkml@vger.kernel.org, ltt-dev@shafik.org

Hi,

I am currently creating a "LOCK" prefix free and memory barrier free version
of atomic.h to fulfill my tracer (LTTng) needs, which is to atomically update
per-cpu data and have a minimal performance loss.

I just came across the MIPS atomic.h and system.h implementations in 2.6.18
which brings a question :

Why are the primitives in include/asm-mips/atomic.h using the "sync"
instruction even in the UP case ? system.h cmpxchg only uses the sync in the
SMP case.

Mathieu


OpenPGP public key:              http://krystal.dyndns.org:8080/key/compudj.gpg
Key fingerprint:     8CD5 52C3 8E3C 4140 715F  BA06 3F25 A8FE 3BAE 9A68
_______________________________________________
Ltt-dev mailing list
Ltt-dev@listserv.shafik.org
http://listserv.shafik.org/mailman/listinfo/ltt-dev

RE: [Fwd: [Ltt-dev] MIPS atomic operations, "sync"]

[Kaz Kylheku]

Sergei Shtylyov wrote:
> I just came across the MIPS atomic.h and system.h 
> implementations in 2.6.18
> which brings a question :
> 
> Why are the primitives in include/asm-mips/atomic.h using the "sync"
> instruction even in the UP case ? system.h cmpxchg only uses 
> the sync in the
> SMP case.

There was just a discussion about this in the mailing list. Check the
archive.

Ralf Baechle mentioned that he has a patch to remove the syncs from
uniprocessor code, so that would seem to answer your question.

Thread subject line: "Sync operation in atomic_add_return()".

RE: [Fwd: [Ltt-dev] MIPS atomic operations, "sync"]

[Kaz Kylheku]

Sergei Shtylyov wrote:
> I just came across the MIPS atomic.h and system.h 
> implementations in 2.6.18
> which brings a question :
> 
> Why are the primitives in include/asm-mips/atomic.h using the "sync"
> instruction even in the UP case ? system.h cmpxchg only uses 
> the sync in the
> SMP case.

There was just a discussion about this in the mailing list. Check the
archive.

Ralf Baechle mentioned that he has a patch to remove the syncs from
uniprocessor code, so that would seem to answer your question.

Thread subject line: "Sync operation in atomic_add_return()".