Re: [PATCH] zone_reclaim cpus_empty needs a real variable

[Christoph Lameter]

On Fri, 20 Jan 2006, Andy Whitcroft wrote:

> zone_reclaim cpus_empty needs a real variable

Maybe we also need to add a new variable for

zone->zone_pgdat->node_id 

Its used multiple times 

> 
> On some architectures cpus_empty() attempts to take the address
> of the mask.  Consequently we must store the result of the
> node_to_cpumask() before applying it.
> 
> Signed-off-by: Andy Whitcroft <apw@xxxxxxxxxxxx>
> ---
>  vmscan.c |    7 +++++--
>  1 file changed, 5 insertions(+), 2 deletions(-)
> diff -upN reference/mm/vmscan.c current/mm/vmscan.c
> --- reference/mm/vmscan.c
> +++ current/mm/vmscan.c
> @@ -1836,18 +1836,21 @@ int zone_reclaim(struct zone *zone, gfp_
>  	struct task_struct *p = current;
>  	struct reclaim_state reclaim_state;
>  	struct scan_control sc;
> +	cpumask_t mask;
>  
>  	if (time_before(jiffies,
>  		zone->last_unsuccessful_zone_reclaim + ZONE_RECLAIM_INTERVAL))
>  			return 0;
>  
>  	if (!(gfp_mask & __GFP_WAIT) ||
> -		(!cpus_empty(node_to_cpumask(zone->zone_pgdat->node_id)) &&
> -			 zone->zone_pgdat->node_id != numa_node_id()) ||
>  		zone->all_unreclaimable ||
>  		atomic_read(&zone->reclaim_in_progress) > 0)
>  			return 0;
>  
> +	mask = node_to_cpumask(zone->zone_pgdat->node_id);
> +	if (!cpus_empty(mask) && zone->zone_pgdat->node_id != numa_node_id())
> +		return 0;
> +
>  	sc.may_writepage = 0;
>  	sc.may_swap = 0;
>  	sc.nr_scanned = 0;
> -
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@xxxxxxxxxxxxxxx
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at  http://www.tux.org/lkml/
> 
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/