[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: TLB flush optimization on s/390.

To: "Martin Schwidefsky" <schwidefsky@de.ibm.com>
Subject: Re: TLB flush optimization on s/390.
From: "David S. Miller" <davem@redhat.com>
Date: Fri, 10 Oct 2003 01:50:18 -0700
Cc: akpm@osdl.org, linux-arch@vger.kernel.org, linux-mm@kvack.org,willy@debian.org
Fake-Sender: owner-linux-mm@kvack.org
In-Reply-To: <OFF67143AC.941FD14C-ONC1256DBB.002D6C6B-C1256DBB.002DCC69@de.ibm.com>
Original-Recipient: rfc822;linux-mm-archive@humbolt.geo.uu.nl
References: <OFF67143AC.941FD14C-ONC1256DBB.002D6C6B-C1256DBB.002DCC69@de.ibm.com>
Sender: Rik van Riel <riel@nl.linux.org>

On Fri, 10 Oct 2003 10:20:14 +0200
"Martin Schwidefsky" <schwidefsky@de.ibm.com> wrote:

> Would you care to explain why this is a problem? It's a static function
> that gets folded into another static function. I added additional arguments
> to copy_one_pte and to avoid to make move_one_page slower I though to
> inline it would be a good idea.

On at least x86 and sparc it makes it so that GCC cannot allocate
enough registers and it has to reload several values to the
stack.

In general when the functions are huge it never makes sense to
inline them even if only used in one place.
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"aart@kvack.org"> aart@kvack.org </a>

Follow-Ups:
- Re: TLB flush optimization on s/390.
  - From: Andi Kleen <ak@suse.de>

References:
- Re: TLB flush optimization on s/390.
  - From: "Martin Schwidefsky" <schwidefsky@de.ibm.com>

Prev by Date: Re: TLB flush optimization on s/390.
Next by Date: Re: TLB flush optimization on s/390.
Prev by thread: Re: TLB flush optimization on s/390.
Next by thread: Re: TLB flush optimization on s/390.
Index(es):
- Date
- Thread