From: David Mosberger <davidm@napali.hpl.hp.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
Message-ID: <16077.6500.502815.97688@napali.hpl.hp.com>
Date: Thu, 22 May 2003 11:39:32 -0700
To: Rusty Russell <rusty@rustcorp.com.au>
Cc: Andrew Morton <akpm@digeo.com>, Ravikiran G Thirumalai <kiran@in.ibm.com>,
       Dipankar Sarma <dipankar@in.ibm.com>, linux-kernel@vger.kernel.org,
       David Mosberger-Tang <davidm@hpl.hp.com>
Subject: Re: [PATCH] per-cpu support inside modules (minimal)
In-Reply-To: <20030522100511.751E02C0F1@lists.samba.org>
References: <20030522100511.751E02C0F1@lists.samba.org>
Reply-To: davidm@hpl.hp.com
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 937
Lines: 27


  Rusty> OK, this does the *minimum* required to support
  Rusty> DEFINE_PER_CPU inside modules.  If we decide to change
  Rusty> kmalloc_percpu later, great, we can turf this out.

  Rusty> Basically, overallocates the amount of per-cpu data at boot
  Rusty> to at least PERCPU_ENOUGH_ROOM if CONFIG_MODULES=y
  Rusty> (arch-specific by default 16k: I have only 5700 bytes of
  Rusty> percpu data in my kernel here, so makes sense), and a special
  Rusty> allocator in module.c dishes it out.

  Rusty> Comments welcome!

Looks good to me.  For ia64, I guess I'll want to add a

	#define PERCPU_ENOUGH_ROOM	PERCPU_PAGE_SIZE

somewhere, but that doesn't sound so hard. ;-)

Thanks!

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