Re: [PATCH v3 15/19] perf: Add deferred user callchains

On 28.10.2024 22:48, Josh Poimboeuf wrote:
...
> diff --git a/kernel/events/core.c b/kernel/events/core.c
> index ebf143aa427b..bf97b2fa8a9c 100644
> --- a/kernel/events/core.c
> +++ b/kernel/events/core.c
...
> @@ -6955,6 +6958,53 @@ static void perf_pending_irq(struct irq_work *entry)
>   		perf_swevent_put_recursion_context(rctx);
>   }
>   
> +static void perf_pending_unwind_irq(struct irq_work *entry)
> +{
> +	struct perf_event *event = container_of(entry, struct perf_event, pending_unwind_irq);
> +
> +	if (event->pending_unwind) {
> +		unwind_user_deferred(&perf_unwind_callback_cb, NULL, event);
> +		event->pending_unwind = 0;
> +	}
> +}
> +
> +struct perf_callchain_deferred_event {
> +	struct perf_event_header	header;
> +	u64				ctx_cookie;

This introduces ctx_cookie in the struct used to produce deferred events but misses to do so in the struct used to consume them. This causes the ctx_cookie value to erroneously get interpreted as nr (number of IPs) in perf:

Core was generated by `perf record -F 99 --call-graph fp /opt/binutils-sframe2/bin/objdump --sframe /opt/binutils-sframe2/bin/objdump'.
Program terminated with signal SIGSEGV, Segmentation fault.
#0  __GI_memcpy () at ../sysdeps/s390/memcpy-z900.S:209
209             mvc     0(256,%r1),0(%r3)
[Current thread is 1 (Thread 0x3ff8bb5fe80 (LWP 16554))]
(gdb) bt
#0  __GI_memcpy () at ../sysdeps/s390/memcpy-z900.S:209
#1  0x00000000012ad0ca in sample__merge_deferred_callchain (sample_orig=0x3ffd2ff53c8, sample_callchain=0x3ffd2ff5b18) at util/callchain.c:1853
...
(gdb) p/x sample_callchain->callchain->nr
$2 = 0x489cb

With debug output from perf_event_callchain_deferred() (see below):

DEBUG: perf_event_callchain_deferred: ctx_cookie=0x00000000000489cb, nr=2

> +	u64				nr;
> +	u64				ips[];
> +};
> +
> +static void perf_event_callchain_deferred(struct unwind_stacktrace *trace,
> +					  u64 ctx_cookie, void *_data)
> +{
> +	struct perf_callchain_deferred_event deferred_event;
> +	u64 callchain_context = PERF_CONTEXT_USER;
> +	struct perf_output_handle handle;
> +	struct perf_event *event = _data;
> +	struct perf_sample_data data;
> +	u64 nr = trace->nr + 1 /* callchain_context */;
> +
> +	deferred_event.header.type = PERF_RECORD_CALLCHAIN_DEFERRED;
> +	deferred_event.header.misc = PERF_RECORD_MISC_USER;
> +	deferred_event.header.size = sizeof(deferred_event) + (nr * sizeof(u64));
> +
> +	deferred_event.ctx_cookie = ctx_cookie;
> +	deferred_event.nr = nr;
> +
> +	perf_event_header__init_id(&deferred_event.header, &data, event);

	pr_info_ratelimited("DEBUG: perf_event_callchain_deferred: ctx_cookie=0x%016llx, nr=%llu\n",
		deferred_event.ctx_cookie, deferred_event.nr);

> +
> +	if (perf_output_begin(&handle, &data, event, deferred_event.header.size))
> +		return;
> +
> +	perf_output_put(&handle, deferred_event);
> +	perf_output_put(&handle, callchain_context);
> +	perf_output_copy(&handle, trace->entries, trace->nr * sizeof(u64));
> +	perf_event__output_id_sample(event, &handle, &data);
> +
> +	perf_output_end(&handle);
> +}
> +
>   static void perf_pending_task(struct callback_head *head)
>   {
>   	struct perf_event *event = container_of(head, struct perf_event, pending_task);
...

Regards,
Jens
-- 
Jens Remus
Linux on Z Development (D3303) and z/VSE Support
+49-7031-16-1128 Office
[email protected]

IBM

IBM Deutschland Research & Development GmbH; Vorsitzender des Aufsichtsrats: Wolfgang Wendt; Geschäftsführung: David Faller; Sitz der Gesellschaft: Böblingen; Registergericht: Amtsgericht Stuttgart, HRB 243294
IBM Data Privacy Statement: https://www.ibm.com/privacy/