Re: [PATCH] perf/x86: Fix smp_processor_id()-in-preemptible warnings

[K Prateek Nayak <kprateek.nayak@amd.com>]

Hello Huafei,

On 7/29/2024 5:15 PM, Li Huafei wrote:
> The following bug was triggered on a system built with
> CONFIG_DEBUG_PREEMPT=y:
> 
>   # echo p > /proc/sysrq-trigger
> 
>   BUG: using smp_processor_id() in preemptible [00000000] code: sh/117
>   caller is perf_event_print_debug+0x1a/0x4c0
>   CPU: 3 UID: 0 PID: 117 Comm: sh Not tainted 6.11.0-rc1 #109
>   Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014
>   Call Trace:
>    <TASK>
>    dump_stack_lvl+0x4f/0x60
>    check_preemption_disabled+0xc8/0xd0
>    perf_event_print_debug+0x1a/0x4c0
>    __handle_sysrq+0x140/0x180
>    write_sysrq_trigger+0x61/0x70
>    proc_reg_write+0x4e/0x70
>    vfs_write+0xd0/0x430
>    ? handle_mm_fault+0xc8/0x240
>    ksys_write+0x9c/0xd0
>    do_syscall_64+0x96/0x190
>    entry_SYSCALL_64_after_hwframe+0x4b/0x53
> 
> This is because the commit d4b294bf84db ("perf/x86: Hybrid PMU support
> for counters") took smp_processor_id() outside the irq critical section.
> If a preemption occurs in perf_event_print_debug() and the task is
> migrated to another cpu, we may get incorrect pmu debug information.
> Move smp_processor_id() back inside the irq critical section to fix this
> issue.
> 
> Fixes: d4b294bf84db ("perf/x86: Hybrid PMU support for counters")
> Signed-off-by: Li Huafei <lihuafei1@huawei.com>
> ---
>   arch/x86/events/core.c | 19 ++++++++++++-------
>   1 file changed, 12 insertions(+), 7 deletions(-)
> 
> diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
> index 12f2a0c14d33..c0157a5d8296 100644
> --- a/arch/x86/events/core.c
> +++ b/arch/x86/events/core.c
> @@ -1521,19 +1521,24 @@ void perf_event_print_debug(void)
>   {
>   	u64 ctrl, status, overflow, pmc_ctrl, pmc_count, prev_left, fixed;
>   	u64 pebs, debugctl;
> -	int cpu = smp_processor_id();
> -	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
> -	unsigned long *cntr_mask = hybrid(cpuc->pmu, cntr_mask);
> -	unsigned long *fixed_cntr_mask = hybrid(cpuc->pmu, fixed_cntr_mask);
> -	struct event_constraint *pebs_constraints = hybrid(cpuc->pmu, pebs_constraints);
> +	int cpu;
> +	struct cpu_hw_events *cpuc;
> +	unsigned long *cntr_mask, *fixed_cntr_mask;
> +	struct event_constraint *pebs_constraints;
>   	unsigned long flags;
>   	int idx;

nit. "cpu" and "idx" can be defined together and this can be converted
to use revere xmas tree order.

>   
> +	local_irq_save(flags);

Perhaps use "guard(irqsave)();" here since ...

> +
> +	cpu = smp_processor_id();
> +	cpuc = &per_cpu(cpu_hw_events, cpu);
> +	cntr_mask = hybrid(cpuc->pmu, cntr_mask);
> +	fixed_cntr_mask = hybrid(cpuc->pmu, fixed_cntr_mask);
> +	pebs_constraints = hybrid(cpuc->pmu, pebs_constraints);
> +
>   	if (!*(u64 *)cntr_mask)

... a "local_irq_restore(flags)" is required here now before returning
and using the guard can avoid that. Even the flags variable will no
longer be necessary.

Thoughts?

>   		return;
>   
> -	local_irq_save(flags);
> -
>   	if (x86_pmu.version >= 2) {
>   		rdmsrl(MSR_CORE_PERF_GLOBAL_CTRL, ctrl);
>   		rdmsrl(MSR_CORE_PERF_GLOBAL_STATUS, status);

-- 
Thanks and Regards,
Prateek