Re: [2.6.24 regression][BUGFIX] numactl --interleave=all doesn'tworks on memoryless node.

[David Rientjes]

On Tue, 5 Feb 2008, Lee Schermerhorn wrote:

> Index: Linux/mm/mempolicy.c
> ===================================================================
> --- Linux.orig/mm/mempolicy.c	2008-02-05 11:25:17.000000000 -0500
> +++ Linux/mm/mempolicy.c	2008-02-05 16:03:11.000000000 -0500
> @@ -131,7 +131,7 @@ static int mpol_check_policy(int mode, n
>  			return -EINVAL;
>  		break;
>  	}
> - 	return nodes_subset(*nodes, node_states[N_HIGH_MEMORY]) ? 0 : -EINVAL;
> + 	return 0;
>  }
>  
>  /* Generate a custom zonelist for the BIND policy. */

This change will be necessary when the nodemask passed from the syscall is 
saved in the struct mempolicy as the intent of the application as well.

> @@ -188,8 +188,6 @@ static struct mempolicy *mpol_new(int mo
>  	switch (mode) {
>  	case MPOL_INTERLEAVE:
>  		policy->v.nodes = *nodes;
> -		nodes_and(policy->v.nodes, policy->v.nodes,
> -					node_states[N_HIGH_MEMORY]);
>  		if (nodes_weight(policy->v.nodes) == 0) {
>  			kmem_cache_free(policy_cache, policy);
>  			return ERR_PTR(-EINVAL);
> @@ -426,9 +424,13 @@ static int contextualize_policy(int mode
>  	if (!nodes)
>  		return 0;
>  
> +	/*
> +	 * Restrict the nodes to the allowed nodes in the cpuset.
> +	 * This is guaranteed to be a subset of nodes with memory.
> +	 */
>  	cpuset_update_task_memory_state();
> -	if (!cpuset_nodes_subset_current_mems_allowed(*nodes))
> -		return -EINVAL;
> +	nodes_and(*nodes, *nodes, cpuset_current_mems_allowed);
> +
>  	return mpol_check_policy(mode, nodes);
>  }
>  

I would defer the intersection until later because contextualize_policy() 
is called before mpol_new() so we have no struct mempolicy to save the 
intent in.  It doesn't matter for the sake of this change, I know, but you 
could move this intersection to mpol_new() and give us an opportunity to 
store the user's nodemask in the mempolicy with a one-line change and get 
the same desired result.

You can now remove cpuset_nodes_subset_current_mems_allowed() from 
linux/cpuset.h.

> @@ -797,7 +799,7 @@ static long do_mbind(unsigned long start
>  	if (end == start)
>  		return 0;
>  
> -	if (mpol_check_policy(mode, nmask))
> +	if (contextualize_policy(mode, nmask))
>  		return -EINVAL;
>  
>  	new = mpol_new(mode, nmask);
> @@ -915,10 +917,6 @@ asmlinkage long sys_mbind(unsigned long 
>  	err = get_nodes(&nodes, nmask, maxnode);
>  	if (err)
>  		return err;
> -#ifdef CONFIG_CPUSETS
> -	/* Restrict the nodes to the allowed nodes in the cpuset */
> -	nodes_and(nodes, nodes, current->mems_allowed);
> -#endif
>  	return do_mbind(start, len, mode, &nodes, flags);
>  }
>  

Looks good, thanks for doing this.
--
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/