From e873c74132f0c5f1452816cd9bb26208f0bba1e1 Mon Sep 17 00:00:00 2001 From: Shivank Garg Date: Sat, 22 Aug 2026 19:22:05 +0000 Subject: dmaengine: fix use-after-free in dma_chan_put() and dma_release_channel() When dma_device_put() drops the last reference on chan->device->ref, dma_device_release() runs and may free the dma_device along with its channels. dma_chan_put() then still reads chan->device->owner via dma_chan_to_owner() for the trailing module_put(). KASAN catches it: slab-use-after-free in dma_chan_put+0x3e6/0x4c0 Read of size 8 by task insmod/6319 Freed by task 6319: kfree+0x225/0x470 dma_chan_put+0x395/0x4c0 dmaengine_put+0xf8/0x160 Cache the module owner in dma_chan_put() before the put so the trailing module_put() does not need chan->device. Fixes: 8ad342a86359 ("dmaengine: Add reference counting to dma_device struct") Suggested-by: Sashiko Link: https://sashiko.dev/#/patchset/20260518-dmaengine-kref-fix-v1-1-4d6125048fb7@amd.com Reviewed-by: Frank Li Reviewed-by: Logan Gunthorpe Signed-off-by: Shivank Garg Link: https://patch.msgid.link/20260822-dmaengine-kref-fix-v5-3-d4a4ee47d927@amd.com Signed-off-by: Vinod Koul --- 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