Re: [PATCH v2 2/2] mm/page_alloc: refactor build_node_zonelist() out of build_zonelists()

[Zi Yan]

On Fri Sep 11, 2026 at 11:04 PM EDT, Gregory Price wrote:
> Extract per-node fallback-list construction into build_node_zonelist().
> Build each selected node directly into the destination zonelist so no
> intermediate node_order array or node count is needed. Print the fallback
> order as each node is added.
>
> This lets us build new zonelists from candidate nodemasks instead of just
> the default N_MEMORY node state list.
>
> No functional change: build_zonelists() builds and prints the same FALLBACK
> list over N_MEMORY with node_load updates as before.
>
> Signed-off-by: Gregory Price <gourry@xxxxxxxxxx>
> ---
>  mm/page_alloc.c | 63 ++++++++++++++++++-------------------------------
>  1 file changed, 23 insertions(+), 40 deletions(-)
>
> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
> index 7efce139d562..d1888d5630e0 100644
> --- a/mm/page_alloc.c
> +++ b/mm/page_alloc.c
> @@ -5857,31 +5857,6 @@ int find_next_best_node_in(int node, nodemask_t *used_node_mask,
>  }
>  
>  
> -/*
> - * Build zonelists ordered by node and zones within node.
> - * This results in maximum locality--normal zone overflows into local
> - * DMA zone, if any--but risks exhausting DMA zone.
> - */
> -static void build_zonelists_in_node_order(pg_data_t *pgdat, int *node_order,
> -		unsigned nr_nodes)
> -{
> -	struct zoneref *zonerefs;
> -	int i;
> -
> -	zonerefs = pgdat->node_zonelists[ZONELIST_FALLBACK]._zonerefs;
> -
> -	for (i = 0; i < nr_nodes; i++) {
> -		int nr_zones;
> -
> -		pg_data_t *node = NODE_DATA(node_order[i]);
> -
> -		nr_zones = build_zonerefs_node(node, zonerefs);
> -		zonerefs += nr_zones;
> -	}
> -	zonerefs->zone = NULL;
> -	zonerefs->zone_idx = 0;
> -}
> -
>  /*
>   * Build __GFP_THISNODE zonelists
>   */
> @@ -5897,20 +5872,24 @@ static void build_thisnode_zonelists(pg_data_t *pgdat)
>  	zonerefs->zone_idx = 0;
>  }
>  
> -static void build_zonelists(pg_data_t *pgdat)
> +/*
> + * Build one zonelist ordered by node and zones within node. This results in
> + * maximum locality--normal zone overflows into local DMA zone, if any--but
> + * risks exhausting DMA zone.
> + */
> +static void build_node_zonelist(pg_data_t *pgdat, const nodemask_t *candidates,
> +				int zlidx)
>  {
> -	static int node_order[MAX_NUMNODES];
> -	int node, nr_nodes = 0;
> +	struct zoneref *zonerefs = pgdat->node_zonelists[zlidx]._zonerefs;

Why does build_node_zonelist() need to have a new zlidx instead of using
ZONELIST_FALLBACK like build_zonelists_in_node_order() did?

>  	nodemask_t used_mask = NODE_MASK_NONE;
> -	int local_node, prev_node;
> +	int local_node = pgdat->node_id;
> +	int prev_node = local_node;
> +	int node;
>  
> -	/* NUMA-aware ordering of nodes */
> -	local_node = pgdat->node_id;
> -	prev_node = local_node;
> +	pr_info("Fallback order for Node %d: ", local_node);
>  
> -	memset(node_order, 0, sizeof(node_order));
>  	while ((node = find_next_best_node_in(local_node, &used_mask,
> -					      &node_states[N_MEMORY])) >= 0) {
> +					      candidates)) >= 0) {
>  		/*
>  		 * We don't want to pressure a particular node.
>  		 * So adding penalty to the first node in same
> @@ -5920,18 +5899,22 @@ static void build_zonelists(pg_data_t *pgdat)
>  		    node_distance(local_node, prev_node))
>  			node_load[node] += 1;
>  
> -		node_order[nr_nodes++] = node;
> +		zonerefs += build_zonerefs_node(NODE_DATA(node), zonerefs);
> +		pr_cont("%d ", node);
>  		prev_node = node;
>  	}
>  
> -	build_zonelists_in_node_order(pgdat, node_order, nr_nodes);
> -	build_thisnode_zonelists(pgdat);
> -	pr_info("Fallback order for Node %d: ", local_node);
> -	for (node = 0; node < nr_nodes; node++)
> -		pr_cont("%d ", node_order[node]);
> +	zonerefs->zone = NULL;
> +	zonerefs->zone_idx = 0;
>  	pr_cont("\n");
>  }
>  
> +static void build_zonelists(pg_data_t *pgdat)
> +{
> +	build_node_zonelist(pgdat, &node_states[N_MEMORY], ZONELIST_FALLBACK);
> +	build_thisnode_zonelists(pgdat);

If build_thisnode_zonelists() means ZONELIST_NOFALLBACK, why
cannot build_node_zonelist() imply ZONELIST_FALLBACK?

> +}
> +
>  #ifdef CONFIG_HAVE_MEMORYLESS_NODES
>  /*
>   * Return node id of node used for "local" allocations.


-- 
Best Regards,
Yan, Zi