raspi/linux
1
0
Fork 1
mirror of https://github.com/raspberrypi/linux.git synced 2025-12-06 18:09:56 +00:00
Code Issues Projects Releases Wiki Activity

sched/topology: Refinement to topology_span_sane speedup

Browse Source 
Simplify the topology_span_sane code further, removing the need to
allocate an array and gotos used to make sure the array gets freed.

This version is in a separate commit because it could return a
different sanity result than the previous code, but only in odd
circumstances that are not expected to actually occur; for example,
when a CPU is not listed in its own mask.

Signed-off-by: Steve Wahl <steve.wahl@hpe.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Valentin Schneider <vschneid@redhat.com>
Reviewed-by: Madadi Vineeth Reddy <vineethr@linux.ibm.com>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Tested-by: Valentin Schneider <vschneid@redhat.com>
Tested-by: Madadi Vineeth Reddy <vineethr@linux.ibm.com>
Link: https://lore.kernel.org/r/20250304160844.75373-3-steve.wahl@hpe.com
This commit is contained in:
Steve Wahl
2025-03-04 10:08:44 -06:00
committed by Peter Zijlstra
parent f55dac1daf
commit ce29a7da84
1 changed files with 19 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files

52
kernel/sched/topology.c
View File

@@ -2352,17 +2352,12 @@ static struct sched_domain *build_sched_domain(struct sched_domain_topology_leve
static bool topology_span_sane(const struct cpumask *cpu_map) static bool topology_span_sane(const struct cpumask *cpu_map)
{ {
struct sched_domain_topology_level *tl; struct sched_domain_topology_level *tl;
const struct cpumask **masks; struct cpumask *covered, *id_seen;
struct cpumask *covered; int cpu;
int cpu, id;
bool ret = false;
lockdep_assert_held(&sched_domains_mutex); lockdep_assert_held(&sched_domains_mutex);
covered = sched_domains_tmpmask; covered = sched_domains_tmpmask;
id_seen = sched_domains_tmpmask2;
masks = kmalloc_array(nr_cpu_ids, sizeof(struct cpumask *), GFP_KERNEL);
if (!masks)
return ret;
for_each_sd_topology(tl) { for_each_sd_topology(tl) {
@@ -2371,7 +2366,7 @@ static bool topology_span_sane(const struct cpumask *cpu_map)
continue; continue;
cpumask_clear(covered); cpumask_clear(covered);
memset(masks, 0, nr_cpu_ids * sizeof(struct cpumask *)); cpumask_clear(id_seen);
/* /*
* Non-NUMA levels cannot partially overlap - they must be either * Non-NUMA levels cannot partially overlap - they must be either
@@ -2380,36 +2375,27 @@ static bool topology_span_sane(const struct cpumask *cpu_map)
* breaks the linking done for an earlier span. * breaks the linking done for an earlier span.
*/ */
for_each_cpu(cpu, cpu_map) { for_each_cpu(cpu, cpu_map) {
const struct cpumask *tl_cpu_mask = tl->mask(cpu);
int id;
/* lowest bit set in this mask is used as a unique id */ /* lowest bit set in this mask is used as a unique id */
id = cpumask_first(tl->mask(cpu)); id = cpumask_first(tl_cpu_mask);
/* zeroed masks cannot possibly collide */ if (cpumask_test_cpu(id, id_seen)) {
if (id >= nr_cpu_ids) /* First CPU has already been seen, ensure identical spans */
continue; if (!cpumask_equal(tl->mask(id), tl_cpu_mask))
return false;
} else {
/* First CPU hasn't been seen before, ensure it's a completely new span */
if (cpumask_intersects(tl_cpu_mask, covered))
return false;
/* if this mask doesn't collide with what we've already seen */ cpumask_or(covered, covered, tl_cpu_mask);
if (!cpumask_intersects(tl->mask(cpu), covered)) { cpumask_set_cpu(id, id_seen);
/* this failing would be an error in this algorithm */
if (WARN_ON(masks[id]))
goto notsane;
/* record the mask we saw for this id */
masks[id] = tl->mask(cpu);
cpumask_or(covered, tl->mask(cpu), covered);
} else if ((!masks[id]) || !cpumask_equal(masks[id], tl->mask(cpu))) {
/*
* a collision with covered should have exactly matched
* a previously seen mask with the same id
*/
goto notsane;
} }
} }
} }
ret = true; return true;
notsane:
kfree(masks);
return ret;
} }
/* /*