On Mon, Apr 12, 2010 at 11:38 AM, Minchan Kim <minchan.kim@xxxxxxxxx> wrote:
> Hi, Bob.
>
> On Sat, Apr 10, 2010 at 8:49 PM, Bob Liu <lliubbo@xxxxxxxxx> wrote:
>> Add alloc_pages_exact_node() to allocate pages from exact
>> node.
>>
>> Signed-off-by: Bob Liu <lliubbo@xxxxxxxxx>
>> ---
>> arch/powerpc/platforms/cell/ras.c | 4 ++--
>> include/linux/gfp.h | 7 +++++++
>> mm/mempolicy.c | 2 +-
>> mm/migrate.c | 3 +--
>> 4 files changed, 11 insertions(+), 5 deletions(-)
>>
>> diff --git a/arch/powerpc/platforms/cell/ras.c b/arch/powerpc/platforms/cell/ras.c
>> index 6d32594..93a5afd 100644
>> --- a/arch/powerpc/platforms/cell/ras.c
>> +++ b/arch/powerpc/platforms/cell/ras.c
>> @@ -123,8 +123,8 @@ static int __init cbe_ptcal_enable_on_node(int nid, int order)
>>
>> area->nid = nid;
>> area->order = order;
>> - area->pages = alloc_pages_from_valid_node(area->nid,
>> - GFP_KERNEL | GFP_THISNODE, area->order);
>> + area->pages = alloc_pages_exact_node(area->nid, GFP_KERNEL,
>> + area->order);
>>
>> if (!area->pages) {
>> printk(KERN_WARNING "%s: no page on node %d\n",
>> diff --git a/include/linux/gfp.h b/include/linux/gfp.h
>> index c94f2ed..70cf2ae 100644
>> --- a/include/linux/gfp.h
>> +++ b/include/linux/gfp.h
>> @@ -296,6 +296,13 @@ static inline struct page *alloc_pages_from_valid_node(int nid, gfp_t gfp_mask,
>> return __alloc_pages(gfp_mask, order, node_zonelist(nid, gfp_mask));
>> }
>>
>> +static inline struct page *alloc_pages_exact_node(int nid, gfp_t gfp_mask,
>> + unsigned int order)
>> +{
>> + return alloc_pages_from_valid_node(nid, gfp_mask | GFP_THISNODE,
>> + order);
>> +}
>> +
>> #ifdef CONFIG_NUMA
>> extern struct page *alloc_pages_current(gfp_t gfp_mask, unsigned order);
>>
>> diff --git a/mm/mempolicy.c b/mm/mempolicy.c
>> index 6838cd8..08f40a2 100644
>> --- a/mm/mempolicy.c
>> +++ b/mm/mempolicy.c
>> @@ -842,7 +842,7 @@ static void migrate_page_add(struct page *page, struct list_head *pagelist,
>>
>> static struct page *new_node_page(struct page *page, unsigned long node, int **x)
>> {
>> - return alloc_pages_from_valid_node(node, GFP_HIGHUSER_MOVABLE, 0);
>> + return alloc_pages_exact_node(node, GFP_HIGHUSER_MOVABLE, 0);
>> }
>
> It's behavior change. Please, write down why you want to change
> behavior in log.
> Although I knew it, you need to explain it for others and git log,
>
Hm, ok.
I will add the log later. Thank you for your suggestion.
--
Regards,
--Bob
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxxx For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href