mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-30 10:06:43 +07:00
64aee2a965
Regardless of which events form a group, it does not make sense for the
events to target different tasks and/or CPUs, as this leaves the group
inconsistent and impossible to schedule. The core perf code assumes that
these are consistent across (successfully intialised) groups.
Core perf code only verifies this when moving SW events into a HW
context. Thus, we can violate this requirement for pure SW groups and
pure HW groups, unless the relevant PMU driver happens to perform this
verification itself. These mismatched groups subsequently wreak havoc
elsewhere.
For example, we handle watchpoints as SW events, and reserve watchpoint
HW on a per-CPU basis at pmu::event_init() time to ensure that any event
that is initialised is guaranteed to have a slot at pmu::add() time.
However, the core code only checks the group leader's cpu filter (via
event_filter_match()), and can thus install follower events onto CPUs
violating thier (mismatched) CPU filters, potentially installing them
into a CPU without sufficient reserved slots.
This can be triggered with the below test case, resulting in warnings
from arch backends.
#define _GNU_SOURCE
#include <linux/hw_breakpoint.h>
#include <linux/perf_event.h>
#include <sched.h>
#include <stdio.h>
#include <sys/prctl.h>
#include <sys/syscall.h>
#include <unistd.h>
static int perf_event_open(struct perf_event_attr *attr, pid_t pid, int cpu,
int group_fd, unsigned long flags)
{
return syscall(__NR_perf_event_open, attr, pid, cpu, group_fd, flags);
}
char watched_char;
struct perf_event_attr wp_attr = {
.type = PERF_TYPE_BREAKPOINT,
.bp_type = HW_BREAKPOINT_RW,
.bp_addr = (unsigned long)&watched_char,
.bp_len = 1,
.size = sizeof(wp_attr),
};
int main(int argc, char *argv[])
{
int leader, ret;
cpu_set_t cpus;
/*
* Force use of CPU0 to ensure our CPU0-bound events get scheduled.
*/
CPU_ZERO(&cpus);
CPU_SET(0, &cpus);
ret = sched_setaffinity(0, sizeof(cpus), &cpus);
if (ret) {
printf("Unable to set cpu affinity\n");
return 1;
}
/* open leader event, bound to this task, CPU0 only */
leader = perf_event_open(&wp_attr, 0, 0, -1, 0);
if (leader < 0) {
printf("Couldn't open leader: %d\n", leader);
return 1;
}
/*
* Open a follower event that is bound to the same task, but a
* different CPU. This means that the group should never be possible to
* schedule.
*/
ret = perf_event_open(&wp_attr, 0, 1, leader, 0);
if (ret < 0) {
printf("Couldn't open mismatched follower: %d\n", ret);
return 1;
} else {
printf("Opened leader/follower with mismastched CPUs\n");
}
/*
* Open as many independent events as we can, all bound to the same
* task, CPU0 only.
*/
do {
ret = perf_event_open(&wp_attr, 0, 0, -1, 0);
} while (ret >= 0);
/*
* Force enable/disble all events to trigger the erronoeous
* installation of the follower event.
*/
printf("Opened all events. Toggling..\n");
for (;;) {
prctl(PR_TASK_PERF_EVENTS_DISABLE, 0, 0, 0, 0);
prctl(PR_TASK_PERF_EVENTS_ENABLE, 0, 0, 0, 0);
}
return 0;
}
Fix this by validating this requirement regardless of whether we're
moving events.
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Zhou Chengming <zhouchengming1@huawei.com>
Cc: stable@vger.kernel.org
Link: http://lkml.kernel.org/r/1498142498-15758-1-git-send-email-mark.rutland@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
||
|---|---|---|
| .. | ||
| bpf | ||
| cgroup | ||
| configs | ||
| debug | ||
| events | ||
| gcov | ||
| irq | ||
| livepatch | ||
| locking | ||
| power | ||
| printk | ||
| rcu | ||
| sched | ||
| time | ||
| trace | ||
| .gitignore | ||
| acct.c | ||
| async.c | ||
| audit_fsnotify.c | ||
| audit_tree.c | ||
| audit_watch.c | ||
| audit.c | ||
| audit.h | ||
| auditfilter.c | ||
| auditsc.c | ||
| backtracetest.c | ||
| bounds.c | ||
| capability.c | ||
| compat.c | ||
| configs.c | ||
| context_tracking.c | ||
| cpu_pm.c | ||
| cpu.c | ||
| crash_core.c | ||
| crash_dump.c | ||
| cred.c | ||
| delayacct.c | ||
| dma.c | ||
| elfcore.c | ||
| exec_domain.c | ||
| exit.c | ||
| extable.c | ||
| fork.c | ||
| freezer.c | ||
| futex_compat.c | ||
| futex.c | ||
| groups.c | ||
| hung_task.c | ||
| irq_work.c | ||
| jump_label.c | ||
| kallsyms.c | ||
| kcmp.c | ||
| Kconfig.freezer | ||
| Kconfig.hz | ||
| Kconfig.locks | ||
| Kconfig.preempt | ||
| kcov.c | ||
| kexec_core.c | ||
| kexec_file.c | ||
| kexec_internal.h | ||
| kexec.c | ||
| kmod.c | ||
| kprobes.c | ||
| ksysfs.c | ||
| kthread.c | ||
| latencytop.c | ||
| Makefile | ||
| membarrier.c | ||
| memremap.c | ||
| module_signing.c | ||
| module-internal.h | ||
| module.c | ||
| notifier.c | ||
| nsproxy.c | ||
| padata.c | ||
| panic.c | ||
| params.c | ||
| pid_namespace.c | ||
| pid.c | ||
| profile.c | ||
| ptrace.c | ||
| range.c | ||
| reboot.c | ||
| relay.c | ||
| resource.c | ||
| seccomp.c | ||
| signal.c | ||
| smp.c | ||
| smpboot.c | ||
| smpboot.h | ||
| softirq.c | ||
| stacktrace.c | ||
| stop_machine.c | ||
| sys_ni.c | ||
| sys.c | ||
| sysctl_binary.c | ||
| sysctl.c | ||
| task_work.c | ||
| taskstats.c | ||
| test_kprobes.c | ||
| torture.c | ||
| tracepoint.c | ||
| tsacct.c | ||
| ucount.c | ||
| uid16.c | ||
| up.c | ||
| user_namespace.c | ||
| user-return-notifier.c | ||
| user.c | ||
| utsname_sysctl.c | ||
| utsname.c | ||
| watchdog_hld.c | ||
| watchdog.c | ||
| workqueue_internal.h | ||
| workqueue.c | ||