Date:   Tue, 21 Dec 2021 10:32:50 +0100
From:   Jiri Olsa <jolsa@redhat.com>
To:     German Gomez <german.gomez@arm.com>
Cc:     linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org,
        acme@kernel.org, Alexandre Truong <alexandre.truong@arm.com>,
        John Garry <john.garry@huawei.com>,
        Will Deacon <will@kernel.org>,
        Mathieu Poirier <mathieu.poirier@linaro.org>,
        Leo Yan <leo.yan@linaro.org>,
        Mark Rutland <mark.rutland@arm.com>,
        Alexander Shishkin <alexander.shishkin@linux.intel.com>,
        Namhyung Kim <namhyung@kernel.org>,
        linux-arm-kernel@lists.infradead.org
Subject: Re: [PATCH v5 6/6] perf arm64: inject missing frames if perf-record
 used "--call-graph=fp"
Message-ID: <YcGfQr43ChIgtacC@krava>
References: <20211217154521.80603-1-german.gomez@arm.com>
 <20211217154521.80603-7-german.gomez@arm.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20211217154521.80603-7-german.gomez@arm.com>
Precedence: bulk

On Fri, Dec 17, 2021 at 03:45:20PM +0000, German Gomez wrote:

SNIP

> +}
> +
> +u64 get_leaf_frame_caller_aarch64(struct perf_sample *sample, struct thread *thread, int usr_idx)
> +{
> +	int ret;
> +	struct entries entries = {};
> +	struct regs_dump old_regs = sample->user_regs;
> +
> +	if (!get_leaf_frame_caller_enabled(sample))
> +		return 0;
> +
> +	/*
> +	 * If PC and SP are not recorded, get the value of PC from the stack
> +	 * and set its mask. SP is not used when doing the unwinding but it
> +	 * still needs to be set to prevent failures.
> +	 */
> +
> +	if (!(sample->user_regs.mask & SMPL_REG_MASK(PERF_REG_ARM64_PC))) {
> +		sample->user_regs.cache_mask |= SMPL_REG_MASK(PERF_REG_ARM64_PC);
> +		sample->user_regs.cache_regs[PERF_REG_ARM64_PC] = sample->callchain->ips[usr_idx+1];
> +	}
> +
> +	if (!(sample->user_regs.mask & SMPL_REG_MASK(PERF_REG_ARM64_SP))) {
> +		sample->user_regs.cache_mask |= SMPL_REG_MASK(PERF_REG_ARM64_SP);
> +		sample->user_regs.cache_regs[PERF_REG_ARM64_SP] = 0;
> +	}
> +
> +	ret = unwind__get_entries(add_entry, &entries, thread, sample, 2);

just curious, did you try this with both unwinders libunwind/libdw?

any chance you could add arm specific test for this?

otherwise it looks good to me

Acked-by: Jiri Olsa <jolsa@kernel.org>

thanks,
jirka


> +	sample->user_regs = old_regs;
> +
> +	if (ret || entries.length != 2)
> +		return ret;
> +
> +	return callchain_param.order == ORDER_CALLER ? entries.stack[0] : entries.stack[1];
> +}
> diff --git a/tools/perf/util/arm64-frame-pointer-unwind-support.h b/tools/perf/util/arm64-frame-pointer-unwind-support.h
> new file mode 100644
> index 000000000000..32af9ce94398
> --- /dev/null
> +++ b/tools/perf/util/arm64-frame-pointer-unwind-support.h
> @@ -0,0 +1,10 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +#ifndef __PERF_ARM_FRAME_POINTER_UNWIND_SUPPORT_H
> +#define __PERF_ARM_FRAME_POINTER_UNWIND_SUPPORT_H
> +
> +#include "event.h"
> +#include "thread.h"
> +
> +u64 get_leaf_frame_caller_aarch64(struct perf_sample *sample, struct thread *thread, int user_idx);
> +
> +#endif /* __PERF_ARM_FRAME_POINTER_UNWIND_SUPPORT_H */
> diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
> index 3eddad009f78..a00fd6796b35 100644
> --- a/tools/perf/util/machine.c
> +++ b/tools/perf/util/machine.c
> @@ -34,6 +34,7 @@
>  #include "bpf-event.h"
>  #include <internal/lib.h> // page_size
>  #include "cgroup.h"
> +#include "arm64-frame-pointer-unwind-support.h"
>  
>  #include <linux/ctype.h>
>  #include <symbol/kallsyms.h>
> @@ -2710,10 +2711,13 @@ static int find_prev_cpumode(struct ip_callchain *chain, struct thread *thread,
>  	return err;
>  }
>  
> -static u64 get_leaf_frame_caller(struct perf_sample *sample __maybe_unused,
> -		struct thread *thread __maybe_unused, int usr_idx __maybe_unused)
> +static u64 get_leaf_frame_caller(struct perf_sample *sample,
> +		struct thread *thread, int usr_idx)
>  {
> -	return 0;
> +	if (machine__normalize_is(thread->maps->machine, "arm64"))
> +		return get_leaf_frame_caller_aarch64(sample, thread, usr_idx);
> +	else
> +		return 0;
>  }
>  
>  static int thread__resolve_callchain_sample(struct thread *thread,
> @@ -3114,14 +3118,19 @@ int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
>  }
>  
>  /*
> - * Compares the raw arch string. N.B. see instead perf_env__arch() if a
> - * normalized arch is needed.
> + * Compares the raw arch string. N.B. see instead perf_env__arch() or
> + * machine__normalize_is() if a normalized arch is needed.
>   */
>  bool machine__is(struct machine *machine, const char *arch)
>  {
>  	return machine && !strcmp(perf_env__raw_arch(machine->env), arch);
>  }
>  
> +bool machine__normalize_is(struct machine *machine, const char *arch)
> +{
> +	return machine && !strcmp(perf_env__arch(machine->env), arch);
> +}
> +
>  int machine__nr_cpus_avail(struct machine *machine)
>  {
>  	return machine ? perf_env__nr_cpus_avail(machine->env) : 0;
> diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
> index a143087eeb47..665535153411 100644
> --- a/tools/perf/util/machine.h
> +++ b/tools/perf/util/machine.h
> @@ -208,6 +208,7 @@ static inline bool machine__is_host(struct machine *machine)
>  }
>  
>  bool machine__is(struct machine *machine, const char *arch);
> +bool machine__normalize_is(struct machine *machine, const char *arch);
>  int machine__nr_cpus_avail(struct machine *machine);
>  
>  struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid);
> -- 
> 2.25.1
>