[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <07938684-0010-4510-9350-0f6d9a83461b@intel.com>
Date: Mon, 8 Sep 2025 00:28:53 +0800
From: "Chen, Yu C" <yu.c.chen@...el.com>
To: Tim Chen <tim.c.chen@...ux.intel.com>
CC: Juri Lelli <juri.lelli@...hat.com>, Dietmar Eggemann
<dietmar.eggemann@....com>, Ben Segall <bsegall@...gle.com>, Mel Gorman
<mgorman@...e.de>, Valentin Schneider <vschneid@...hat.com>, Tim Chen
<tim.c.chen@...el.com>, Vincent Guittot <vincent.guittot@...aro.org>, "Libo
Chen" <libo.chen@...cle.com>, Abel Wu <wuyun.abel@...edance.com>, Len Brown
<len.brown@...el.com>, <linux-kernel@...r.kernel.org>, K Prateek Nayak
<kprateek.nayak@....com>, "Gautham R . Shenoy" <gautham.shenoy@....com>,
"Zhao Liu" <zhao1.liu@...el.com>, Vinicius Costa Gomes
<vinicius.gomes@...el.com>, Arjan Van De Ven <arjan.van.de.ven@...el.com>,
Peter Zijlstra <peterz@...radead.org>, Ingo Molnar <mingo@...hat.com>
Subject: Re: [PATCH v2 1/2] sched: Create architecture specific sched domain
distances
On 9/6/2025 2:36 AM, Tim Chen wrote:
> Allow architecture specific sched domain NUMA distances that can be
> modified from NUMA node distances for the purpose of building NUMA
> sched domains.
>
> The actual NUMA distances are kept separately. This allows for NUMA
> domain levels modification when building sched domains for specific
> architectures.
>
> Consolidate the recording of unique NUMA distances in an array to
> sched_record_numa_dist() so the function can be reused to record NUMA
> distances when the NUMA distance metric is changed.
>
> No functional change if there's no arch specific NUMA distances
> are being defined.
>
> Co-developed-by: Vinicius Costa Gomes <vinicius.gomes@...el.com>
> Signed-off-by: Tim Chen <tim.c.chen@...ux.intel.com>
> ---
> include/linux/sched/topology.h | 2 +
> kernel/sched/topology.c | 118 ++++++++++++++++++++++++++++-----
> 2 files changed, 103 insertions(+), 17 deletions(-)
>
> diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
> index 5263746b63e8..4f58e78ca52e 100644
> --- a/include/linux/sched/topology.h
> +++ b/include/linux/sched/topology.h
> @@ -59,6 +59,8 @@ static inline int cpu_numa_flags(void)
> #endif
>
> extern int arch_asym_cpu_priority(int cpu);
> +extern int arch_sched_node_distance(int from, int to);
> +extern int sched_avg_remote_numa_distance;
>
> struct sched_domain_attr {
> int relax_domain_level;
> diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
> index 977e133bb8a4..1f08dfef2ea5 100644
> --- a/kernel/sched/topology.c
> +++ b/kernel/sched/topology.c
> @@ -1591,10 +1591,13 @@ static void claim_allocations(int cpu, struct sched_domain *sd)
> enum numa_topology_type sched_numa_topology_type;
>
> static int sched_domains_numa_levels;
> +static int sched_numa_node_levels;
> static int sched_domains_curr_level;
>
> int sched_max_numa_distance;
> +int sched_avg_remote_numa_distance;
> static int *sched_domains_numa_distance;
> +static int *sched_numa_node_distance;
> static struct cpumask ***sched_domains_numa_masks;
> #endif /* CONFIG_NUMA */
>
> @@ -1808,10 +1811,10 @@ bool find_numa_distance(int distance)
> return true;
>
> rcu_read_lock();
> - distances = rcu_dereference(sched_domains_numa_distance);
> + distances = rcu_dereference(sched_numa_node_distance);
> if (!distances)
> goto unlock;
> - for (i = 0; i < sched_domains_numa_levels; i++) {
> + for (i = 0; i < sched_numa_node_levels; i++) {
> if (distances[i] == distance) {
> found = true;
> break;
> @@ -1887,14 +1890,29 @@ static void init_numa_topology_type(int offline_node)
>
> #define NR_DISTANCE_VALUES (1 << DISTANCE_BITS)
>
> -void sched_init_numa(int offline_node)
> +/*
> + * Architecture could simplify NUMA distance, to avoid
> + * creating too many NUMA levels.
> + */
> +int __weak arch_sched_node_distance(int from, int to)
> +{
> + return node_distance(from, to);
> +}
> +
> +static int numa_node_dist(int i, int j)
> +{
> + return node_distance(i, j);
> +}
> +
numa_node_dist() seems to be used only once by
sched_record_numa_dist(), would it be possible to
use node_distance() directly
sched_record_numa_dist(offline_node, node_distance, &distances,
&max_dist, &nr_node_levels))?
> +static int sched_record_numa_dist(int offline_node, int (*n_dist)(int, int),
> + int **dist, int *maximum_dist, int *levels)
> +
> {
> - struct sched_domain_topology_level *tl;
> unsigned long *distance_map;
> int nr_levels = 0;
> int i, j;
> int *distances;
> - struct cpumask ***masks;
> + int max_dist = 0;
>
> /*
> * O(nr_nodes^2) de-duplicating selection sort -- in order to find the
> @@ -1902,17 +1920,20 @@ void sched_init_numa(int offline_node)
> */
> distance_map = bitmap_alloc(NR_DISTANCE_VALUES, GFP_KERNEL);
> if (!distance_map)
> - return;
> + return -ENOMEM;
>
> bitmap_zero(distance_map, NR_DISTANCE_VALUES);
> for_each_cpu_node_but(i, offline_node) {
> for_each_cpu_node_but(j, offline_node) {
> - int distance = node_distance(i, j);
> + int distance = n_dist(i, j);
> +
> + if (distance > max_dist)
> + max_dist = distance;
>
> if (distance < LOCAL_DISTANCE || distance >= NR_DISTANCE_VALUES) {
> sched_numa_warn("Invalid distance value range");
> bitmap_free(distance_map);
> - return;
> + return -EINVAL;
> }
>
> bitmap_set(distance_map, distance, 1);
> @@ -1927,17 +1948,70 @@ void sched_init_numa(int offline_node)
> distances = kcalloc(nr_levels, sizeof(int), GFP_KERNEL);
> if (!distances) {
> bitmap_free(distance_map);
> - return;
> + return -ENOMEM;
> }
> -
> for (i = 0, j = 0; i < nr_levels; i++, j++) {
> j = find_next_bit(distance_map, NR_DISTANCE_VALUES, j);
> distances[i] = j;
> }
> - rcu_assign_pointer(sched_domains_numa_distance, distances);
> + *dist = distances;
> + if (levels)
> + *levels = nr_levels;
> +
> + if (maximum_dist)
> + *maximum_dist = max_dist;
>
> bitmap_free(distance_map);
>
> + return 0;
> +}
> +
> +static int avg_remote_numa_distance(int offline_node)
> +{
> + int i, j;
> + int distance, nr_remote = 0, total_distance = 0;
> +
> + for_each_cpu_node_but(i, offline_node) {
> + for_each_cpu_node_but(j, offline_node) {
> + distance = node_distance(i, j);
> +
> + if (distance >= REMOTE_DISTANCE) {
> + nr_remote++;
> + total_distance += distance;
> + }
> + }
> + }
> + if (nr_remote)
> + return total_distance / nr_remote;
> + else
> + return REMOTE_DISTANCE;
> +}
> +
> +void sched_init_numa(int offline_node)
> +{
> + struct sched_domain_topology_level *tl;
> + int nr_levels, nr_node_levels;
> + int i, j;
> + int *distances, *domain_distances;
> + int max_dist;
> + struct cpumask ***masks;
> +
> + if (sched_record_numa_dist(offline_node, numa_node_dist, &distances,
> + &max_dist, &nr_node_levels))
> + return;
> +
> + WRITE_ONCE(sched_avg_remote_numa_distance,
> + avg_remote_numa_distance(offline_node));
> +
> + if (sched_record_numa_dist(offline_node,
> + arch_sched_node_distance, &domain_distances,
> + NULL, &nr_levels)) {
> + kfree(distances);
> + return;
> + }
> + rcu_assign_pointer(sched_numa_node_distance, distances);
> + WRITE_ONCE(sched_numa_node_levels, nr_node_levels);
> +
> /*
> * 'nr_levels' contains the number of unique distances
> *
> @@ -1954,6 +2028,8 @@ void sched_init_numa(int offline_node)
> *
> * We reset it to 'nr_levels' at the end of this function.
> */
> + rcu_assign_pointer(sched_domains_numa_distance, domain_distances);
> +
> sched_domains_numa_levels = 0;
>
> masks = kzalloc(sizeof(void *) * nr_levels, GFP_KERNEL);
> @@ -1979,10 +2055,13 @@ void sched_init_numa(int offline_node)
> masks[i][j] = mask;
>
> for_each_cpu_node_but(k, offline_node) {
> - if (sched_debug() && (node_distance(j, k) != node_distance(k, j)))
> + if (sched_debug() &&
> + (arch_sched_node_distance(j, k) !=
> + arch_sched_node_distance(k, j)))
> sched_numa_warn("Node-distance not symmetric");
>
> - if (node_distance(j, k) > sched_domains_numa_distance[i])
> + if (arch_sched_node_distance(j, k) >
> + sched_domains_numa_distance[i])
> continue;
>
> cpumask_or(mask, mask, cpumask_of_node(k));
> @@ -2022,7 +2101,7 @@ void sched_init_numa(int offline_node)
> sched_domain_topology = tl;
>
> sched_domains_numa_levels = nr_levels;
> - WRITE_ONCE(sched_max_numa_distance, sched_domains_numa_distance[nr_levels - 1]);
> + WRITE_ONCE(sched_max_numa_distance, max_dist);
>
Would it be possible to use
WRITE_ONCE(sched_max_numa_distance, distance[nr_node_levels - 1]);
so we can simplify the code by removing the introduced 'max_dist'
both in sched_record_numa_dist() and sched_init_numa().
thanks,
Chenyu
> init_numa_topology_type(offline_node);
> }
> @@ -2030,14 +2109,18 @@ void sched_init_numa(int offline_node)
>
> static void sched_reset_numa(void)
> {
> - int nr_levels, *distances;
> + int nr_levels, *distances, *dom_distances;
> struct cpumask ***masks;
>
> nr_levels = sched_domains_numa_levels;
> + sched_numa_node_levels = 0;
> sched_domains_numa_levels = 0;
> sched_max_numa_distance = 0;
> + sched_avg_remote_numa_distance = 0;
> sched_numa_topology_type = NUMA_DIRECT;
> - distances = sched_domains_numa_distance;
> + distances = sched_numa_node_distance;
> + dom_distances = sched_domains_numa_distance;
> + rcu_assign_pointer(sched_numa_node_distance, NULL);
> rcu_assign_pointer(sched_domains_numa_distance, NULL);
> masks = sched_domains_numa_masks;
> rcu_assign_pointer(sched_domains_numa_masks, NULL);
> @@ -2054,6 +2137,7 @@ static void sched_reset_numa(void)
> kfree(masks[i]);
> }
> kfree(masks);
> + kfree(dom_distances);
> }
> if (sched_domain_topology_saved) {
> kfree(sched_domain_topology);
> @@ -2092,7 +2176,7 @@ void sched_domains_numa_masks_set(unsigned int cpu)
> continue;
>
> /* Set ourselves in the remote node's masks */
> - if (node_distance(j, node) <= sched_domains_numa_distance[i])
> + if (arch_sched_node_distance(j, node) <= sched_domains_numa_distance[i])
> cpumask_set_cpu(cpu, sched_domains_numa_masks[i][j]);
> }
> }
Powered by blists - more mailing lists