diff options
Diffstat (limited to 'lib/group_cpus.c')
| -rw-r--r-- | lib/group_cpus.c | 47 |
1 files changed, 32 insertions, 15 deletions
diff --git a/lib/group_cpus.c b/lib/group_cpus.c index aa3f6815bb12..6d08ac05f371 100644 --- a/lib/group_cpus.c +++ b/lib/group_cpus.c @@ -332,9 +332,11 @@ static int __group_cpus_evenly(unsigned int startgrp, unsigned int numgrps, /** * group_cpus_evenly - Group all CPUs evenly per NUMA/CPU locality * @numgrps: number of groups + * @nummasks: number of initialized cpumasks * * Return: cpumask array if successful, NULL otherwise. And each element - * includes CPUs assigned to this group + * includes CPUs assigned to this group. nummasks contains the number + * of initialized masks which can be less than numgrps. * * Try to put close CPUs from viewpoint of CPU and NUMA locality into * same group, and run two-stage grouping: @@ -344,7 +346,7 @@ static int __group_cpus_evenly(unsigned int startgrp, unsigned int numgrps, * We guarantee in the resulted grouping that all CPUs are covered, and * no same CPU is assigned to multiple groups */ -struct cpumask *group_cpus_evenly(unsigned int numgrps) +struct cpumask *group_cpus_evenly(unsigned int numgrps, unsigned int *nummasks) { unsigned int curgrp = 0, nr_present = 0, nr_others = 0; cpumask_var_t *node_to_cpumask; @@ -352,6 +354,9 @@ struct cpumask *group_cpus_evenly(unsigned int numgrps) int ret = -ENOMEM; struct cpumask *masks = NULL; + if (numgrps == 0) + return NULL; + if (!zalloc_cpumask_var(&nmsk, GFP_KERNEL)) return NULL; @@ -366,15 +371,27 @@ struct cpumask *group_cpus_evenly(unsigned int numgrps) if (!masks) goto fail_node_to_cpumask; - /* Stabilize the cpumasks */ - cpus_read_lock(); build_node_to_cpumask(node_to_cpumask); + /* + * Make a local cache of 'cpu_present_mask', so the two stages + * spread can observe consistent 'cpu_present_mask' without holding + * cpu hotplug lock, then we can reduce deadlock risk with cpu + * hotplug code. + * + * Here CPU hotplug may happen when reading `cpu_present_mask`, and + * we can live with the case because it only affects that hotplug + * CPU is handled in the 1st or 2nd stage, and either way is correct + * from API user viewpoint since 2-stage spread is sort of + * optimization. + */ + cpumask_copy(npresmsk, data_race(cpu_present_mask)); + /* grouping present CPUs first */ ret = __group_cpus_evenly(curgrp, numgrps, node_to_cpumask, - cpu_present_mask, nmsk, masks); + npresmsk, nmsk, masks); if (ret < 0) - goto fail_build_affinity; + goto fail_node_to_cpumask; nr_present = ret; /* @@ -387,18 +404,12 @@ struct cpumask *group_cpus_evenly(unsigned int numgrps) curgrp = 0; else curgrp = nr_present; - cpumask_andnot(npresmsk, cpu_possible_mask, cpu_present_mask); + cpumask_andnot(npresmsk, cpu_possible_mask, npresmsk); ret = __group_cpus_evenly(curgrp, numgrps, node_to_cpumask, npresmsk, nmsk, masks); if (ret >= 0) nr_others = ret; - fail_build_affinity: - cpus_read_unlock(); - - if (ret >= 0) - WARN_ON(nr_present + nr_others < numgrps); - fail_node_to_cpumask: free_node_to_cpumask(node_to_cpumask); @@ -411,18 +422,24 @@ struct cpumask *group_cpus_evenly(unsigned int numgrps) kfree(masks); return NULL; } + *nummasks = min(nr_present + nr_others, numgrps); return masks; } #else /* CONFIG_SMP */ -struct cpumask *group_cpus_evenly(unsigned int numgrps) +struct cpumask *group_cpus_evenly(unsigned int numgrps, unsigned int *nummasks) { - struct cpumask *masks = kcalloc(numgrps, sizeof(*masks), GFP_KERNEL); + struct cpumask *masks; + if (numgrps == 0) + return NULL; + + masks = kcalloc(numgrps, sizeof(*masks), GFP_KERNEL); if (!masks) return NULL; /* assign all CPUs(cpu 0) to the 1st group only */ cpumask_copy(&masks[0], cpu_possible_mask); + *nummasks = 1; return masks; } #endif /* CONFIG_SMP */ |