Re: [PATCH] mm/mempolicy: refcount the weighted interleave state instead of copying it

On Sun, Aug 23, 2026 at 10:41:17PM -0400, Gregory Price wrote:
> @@ -2632,7 +2654,7 @@ static unsigned long alloc_pages_bulk_weighted_interleave(gfp_t gfp,
>  	unsigned long nr_allocated = 0;
>  	unsigned long rounds;
>  	unsigned long node_pages, delta;
> -	u8 *weights, weight;
> +	u8 *table, weight;
>  	unsigned int weight_total = 0;
>  	unsigned long rem_pages = nr_pages;
>  	nodemask_t nodes;
> @@ -2676,25 +2698,12 @@ static unsigned long alloc_pages_bulk_weighted_interleave(gfp_t gfp,
>  	me->il_weight = 0;
>  	prev_node = node;
>  
> -	/* create a local copy of node weights to operate on outside rcu */
> -	weights = kzalloc(nr_node_ids, GFP_KERNEL);
> -	if (!weights)
> -		return total_allocated;
> -
> -	rcu_read_lock();
> -	state = rcu_dereference(wi_state);
> -	if (state) {
> -		memcpy(weights, state->iw_table, nr_node_ids * sizeof(u8));
> -		rcu_read_unlock();
> -	} else {
> -		rcu_read_unlock();
> -		for (i = 0; i < nr_node_ids; i++)
> -			weights[i] = 1;
> -	}
> +	state = wi_state_get();
> +	table = state ? state->iw_table : NULL;
>  
>  	/* calculate total, detect system default usage */
>  	for_each_node_mask(node, nodes)
> -		weight_total += weights[node];
> +		weight_total += table ? table[node] : 1;
>  
>  	/*
>  	 * Calculate rounds/partial rounds to minimize __alloc_pages_bulk calls.
> @@ -2706,10 +2715,10 @@ static unsigned long alloc_pages_bulk_weighted_interleave(gfp_t gfp,
>  	rounds = rem_pages / weight_total;
>  	delta = rem_pages % weight_total;
>  	resume_node = next_node_in(prev_node, nodes);
> -	resume_weight = weights[resume_node];
> +	resume_weight = table ? table[resume_node] : 1;
>  	for (i = 0; i < nnodes; i++) {
>  		node = next_node_in(prev_node, nodes);
> -		weight = weights[node];
> +		weight = table ? table[node] : 1;
>  		node_pages = weight * rounds;
>  		/* If a delta exists, add this node's portion of the delta */
>  		if (delta > weight) {
> @@ -2735,7 +2744,7 @@ static unsigned long alloc_pages_bulk_weighted_interleave(gfp_t gfp,
>  	}
>  	me->il_prev = resume_node;
>  	me->il_weight = resume_weight;
> -	kfree(weights);
> +	wi_state_put(state);
>  	return total_allocated;
>  }
>  

Bit of a shame to take/put a refcount on every memory allocation.  That
seems like it might hurt (even being on a different cacheline).  Would
it make more sense to use SRCU for this?