| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <616f43d534c7c043220d032700ce72e4a7c740aa.camel@linux.intel.com>
Date: Mon, 08 Sep 2025 11:23:01 -0700
From: Tim Chen <tim.c.chen@...ux.intel.com>
To: "Chen, Yu C" <yu.c.chen@...el.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 Mon, 2025-09-08 at 00:28 +0800, Chen, Yu C wrote:
> On 9/6/2025 2:36 AM, Tim Chen wrote:
... snip ...
> > -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))?
Otherwise I will need to pass a flag to sched_record_numa_dist to
choose which distance to use. I am okay either way. Choosing
the current method so it makes sched_record_numa_dist() simpler.
>
> > +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;
> >
> >
... snip ...
> > +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().
Sure, I think that simplifies sched_record_numa_dist().
Tim
Powered by blists - more mailing lists