From 3a2c4d55e32ad65efebdb6de44eef3bfa08bb49d Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Wed, 2 Sep 2026 15:31:14 -0700 Subject: treewide: refresh kmalloc_obj() conversions This is another run of the Coccinelle script for converting kmalloc() family of allocations to kmalloc_obj() via the existing rules in scripts/coccinelle/api/kmalloc_objs.cocci This catches both the set of kmalloc() uses added since the first kmalloc_obj() conversions in v7.0 and adds a large group missed in the first pass due to Coccinelle not interacting well with the cleanup.h scoped_...() family of macros[1]. I worked around this with spatch's "--macro-file" argument to a file with all the scoped_...() macros mapped to Coccinelle's YACFE_ITERATOR[2] as that was the closest viable control flow indicator I could find. Build tested allmodconfig on x86, arm64, arm, loongarch, mips, powerpc, riscv, and s390 with no new warnings. Link: https://lore.kernel.org/lkml/202609021314.8A9C0B8@keescook/ [1] Link: https://github.com/coccinelle/coccinelle/blob/master/standard.h [2] Signed-off-by: Kees Cook --- tools/perf/util/affinity.c | 103 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 103 insertions(+) create mode 100644 tools/perf/util/affinity.c (limited to 'tools/perf/util/affinity.c') diff --git a/tools/perf/util/affinity.c b/tools/perf/util/affinity.c new file mode 100644 index 000000000..6c64b5f69 --- /dev/null +++ b/tools/perf/util/affinity.c @@ -0,0 +1,103 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Manage affinity to optimize IPIs inside the kernel perf API. */ +#define _GNU_SOURCE 1 +#include +#include +#include +#include +#include +#include "perf.h" +#include "cpumap.h" +#include "affinity.h" + +static int get_cpu_set_size(void) +{ + int sz = cpu__max_cpu().cpu + 8 - 1; + /* + * sched_getaffinity doesn't like masks smaller than the kernel. + * Hopefully that's big enough. + */ + if (sz < 4096) + sz = 4096; + return sz / 8; +} + +int affinity__setup(struct affinity *a) +{ + int cpu_set_size = get_cpu_set_size(); + + a->orig_cpus = bitmap_zalloc(cpu_set_size * 8); + if (!a->orig_cpus) + return -1; + sched_getaffinity(0, cpu_set_size, (cpu_set_t *)a->orig_cpus); + a->sched_cpus = bitmap_zalloc(cpu_set_size * 8); + if (!a->sched_cpus) { + zfree(&a->orig_cpus); + return -1; + } + bitmap_zero((unsigned long *)a->sched_cpus, cpu_set_size); + a->changed = false; + return 0; +} + +/* + * perf_event_open does an IPI internally to the target CPU. + * It is more efficient to change perf's affinity to the target + * CPU and then set up all events on that CPU, so we amortize + * CPU communication. + */ +void affinity__set(struct affinity *a, int cpu) +{ + int cpu_set_size = get_cpu_set_size(); + + /* + * Return: + * - if cpu is -1 + * - restrict out of bound access to sched_cpus + */ + if (cpu == -1 || ((cpu >= (cpu_set_size * 8)))) + return; + + a->changed = true; + __set_bit(cpu, a->sched_cpus); + /* + * We ignore errors because affinity is just an optimization. + * This could happen for example with isolated CPUs or cpusets. + * In this case the IPIs inside the kernel's perf API still work. + */ + sched_setaffinity(0, cpu_set_size, (cpu_set_t *)a->sched_cpus); + __clear_bit(cpu, a->sched_cpus); +} + +static void __affinity__cleanup(struct affinity *a) +{ + int cpu_set_size = get_cpu_set_size(); + + if (a->changed) + sched_setaffinity(0, cpu_set_size, (cpu_set_t *)a->orig_cpus); + zfree(&a->sched_cpus); + zfree(&a->orig_cpus); +} + +void affinity__cleanup(struct affinity *a) +{ + if (a != NULL) + __affinity__cleanup(a); +} + +void cpu_map__set_affinity(const struct perf_cpu_map *cpumap) +{ + int cpu_set_size = get_cpu_set_size(); + unsigned long *cpuset = bitmap_zalloc(cpu_set_size * 8); + struct perf_cpu cpu; + unsigned int idx; + + if (!cpuset) + return; + + perf_cpu_map__for_each_cpu_skip_any(cpu, idx, cpumap) + __set_bit(cpu.cpu, cpuset); + + sched_setaffinity(0, cpu_set_size, (cpu_set_t *)cpuset); + zfree(&cpuset); +} -- cgit v1.3.1