[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <87fxus1y6q.fsf@saeurebad.de>
Date: Sat, 15 Mar 2008 04:08:29 +0100
From: Johannes Weiner <hannes@...urebad.de>
To: "Yinghai Lu" <yhlu.kernel@...il.com>
Cc: "KAMEZAWA Hiroyuki" <kamezawa.hiroyu@...fujitsu.com>,
"Andrew Morton" <akpm@...ux-foundation.org>,
"Ingo Molnar" <mingo@...e.hu>, "Andi Kleen" <ak@...e.de>,
"Christoph Lameter" <clameter@....com>,
linux-kernel@...r.kernel.org,
"Yasunori Goto" <y-goto@...fujitsu.com>
Subject: Re: [PATCH] mm: make reserve_bootmem can crossed the nodes
Hi,
"Yinghai Lu" <yhlu.kernel@...il.com> writes:
> On Thu, Mar 13, 2008 at 7:58 PM, Johannes Weiner <hannes@...urebad.de> wrote:
>> Hi,
>>
>>
>> KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com> writes:
>>
>> > Background:
>> > - reserve_bootmem is called for *reserve* memory before bootmem allocator.
>> > - It specifies <address, size>.
>> > - Because <addrees, size> are argments, memory hole in <address, size> is not
>> > problem here.
>> >
>> > Before change,
>> > - reseve_bootmem() only works for Node(0)
>> >
>> > After change
>> > - reserve_bootmem() works on sutiable nodes for <address, size>
>> > - It can spread accross among prural nodes.
>>
>> After the change it will iterate over all nodes, reserving the range
>> `address to address+size' on each of them.
>
> + /* out of range */
> + if (addr >= bdata->node_boot_start && addr < bdata->last_success)
> + return;
>
> out of range will bail out...
Sorry, I did not see that.
Hannes
--
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/
Powered by blists - more mailing lists