Hello,
On Mon, Aug 10, 2020 at 3:22 PM Alexander Gordeev
<agord...@linux.ibm.com> wrote:
>
> It is currently assumed that each node contains at most
> nr_cpus/nr_nodes CPUs and node CPU ranges do not overlap.
> That assumption is generally incorrect as there are archs
> where a CPU number does not depend on to its node number.
>
> This update removes the described assumption by simply calling
> numa_node_to_cpus() interface and using the returned mask for
> binding CPUs to nodes. It also tightens a cpumask allocation
> failure check a bit.
>
> Cc: Satheesh Rajendran <sathn...@linux.vnet.ibm.com>
> Cc: Srikar Dronamraju <sri...@linux.vnet.ibm.com>
> Cc: Naveen N. Rao <naveen.n....@linux.vnet.ibm.com>
> Cc: Balamuruhan S <bal...@linux.vnet.ibm.com>
> Cc: Peter Zijlstra <pet...@infradead.org>
> Cc: Ingo Molnar <mi...@redhat.com>
> Cc: Arnaldo Carvalho de Melo <a...@kernel.org>
> Cc: Mark Rutland <mark.rutl...@arm.com>
> Cc: Alexander Shishkin <alexander.shish...@linux.intel.com>
> Cc: Jiri Olsa <jo...@redhat.com>
> Cc: Namhyung Kim <namhy...@kernel.org>
> Signed-off-by: Alexander Gordeev <agord...@linux.ibm.com>
> ---
> tools/perf/bench/numa.c | 27 +++++++++++++--------------
> 1 file changed, 13 insertions(+), 14 deletions(-)
>
> diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c
> index 5797253..23e224e 100644
> --- a/tools/perf/bench/numa.c
> +++ b/tools/perf/bench/numa.c
> @@ -247,12 +247,13 @@ static int is_node_present(int node)
> */
> static bool node_has_cpus(int node)
> {
> - struct bitmask *cpu = numa_allocate_cpumask();
> + struct bitmask *cpumask = numa_allocate_cpumask();
> unsigned int i;
>
> - if (cpu && !numa_node_to_cpus(node, cpu)) {
> - for (i = 0; i < cpu->size; i++) {
> - if (numa_bitmask_isbitset(cpu, i))
> + BUG_ON(!cpumask);
> + if (!numa_node_to_cpus(node, cpumask)) {
> + for (i = 0; i < cpumask->size; i++) {
> + if (numa_bitmask_isbitset(cpumask, i))
> return true;
> }
> }
> @@ -288,14 +289,10 @@ static cpu_set_t bind_to_cpu(int target_cpu)
>
> static cpu_set_t bind_to_node(int target_node)
> {
> - int cpus_per_node = g->p.nr_cpus / nr_numa_nodes();
> cpu_set_t orig_mask, mask;
> int cpu;
> int ret;
>
> - BUG_ON(cpus_per_node * nr_numa_nodes() != g->p.nr_cpus);
> - BUG_ON(!cpus_per_node);
> -
> ret = sched_getaffinity(0, sizeof(orig_mask), &orig_mask);
> BUG_ON(ret);
>
> @@ -305,13 +302,15 @@ static cpu_set_t bind_to_node(int target_node)
> for (cpu = 0; cpu < g->p.nr_cpus; cpu++)
> CPU_SET(cpu, &mask);
> } else {
> - int cpu_start = (target_node + 0) * cpus_per_node;
> - int cpu_stop = (target_node + 1) * cpus_per_node;
> -
> - BUG_ON(cpu_stop > g->p.nr_cpus);
> + struct bitmask *cpumask = numa_allocate_cpumask();
>
> - for (cpu = cpu_start; cpu < cpu_stop; cpu++)
> - CPU_SET(cpu, &mask);
> + BUG_ON(!cpumask);
> + if (!numa_node_to_cpus(target_node, cpumask)) {
> + for (cpu = 0; cpu < (int)cpumask->size; cpu++) {
> + if (numa_bitmask_isbitset(cpumask, cpu))
> + CPU_SET(cpu, &mask);
> + }
> + }
It seems you need to call numa_free_cpumask() for both functions.
Thanks
Namhyung
> }
>
> ret = sched_setaffinity(0, sizeof(mask), &mask);
> --
> 1.8.3.1
>
