linux-kernel - Re: [PATCH v4 09/13] perf: cs-etm: Update record event to use new Trace ID protocol

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <bbd9ca67-9538-8e0f-28d0-9b73957c8898@arm.com>
Date:   Mon, 5 Sep 2022 12:38:43 +0100
From:   James Clark <james.clark@....com>
To:     Mike Leach <mike.leach@...aro.org>, coresight@...ts.linaro.org,
        linux-arm-kernel@...ts.infradead.org, linux-kernel@...r.kernel.org
Cc:     mathieu.poirier@...aro.org, peterz@...radead.org, mingo@...hat.com,
        acme@...nel.org, linux-perf-users@...r.kernel.org,
        quic_jinlmao@...cinc.com
Subject: Re: [PATCH v4 09/13] perf: cs-etm: Update record event to use new
 Trace ID protocol



On 23/08/2022 10:10, Mike Leach wrote:
> Trace IDs are now dynamically allocated.
> 
> Previously used the static association algorithm that is no longer
> used. The 'cpu * 2 + seed' was outdated and broken for systems with high
> core counts (>46). as it did not scale and was broken for larger
> core counts.
> 
> Trace ID will now be sent in PERF_RECORD_AUX_OUTPUT_HW_ID record.
> 
> Legacy ID algorithm renamed and retained for limited backward
> compatibility use.
> 
> Signed-off-by: Mike Leach <mike.leach@...aro.org>

Reviewed-by: James Clark <james.clark@....com>

> ---
>  tools/include/linux/coresight-pmu.h | 30 +++++++++++++++++------------
>  tools/perf/arch/arm/util/cs-etm.c   | 21 ++++++++++++--------
>  2 files changed, 31 insertions(+), 20 deletions(-)
> 
> diff --git a/tools/include/linux/coresight-pmu.h b/tools/include/linux/coresight-pmu.h
> index db9c7c0abb6a..307f357defe9 100644
> --- a/tools/include/linux/coresight-pmu.h
> +++ b/tools/include/linux/coresight-pmu.h
> @@ -10,11 +10,28 @@
>  #include <linux/bits.h>
>  
>  #define CORESIGHT_ETM_PMU_NAME "cs_etm"
> -#define CORESIGHT_ETM_PMU_SEED  0x10
> +
> +/*
> + * The legacy Trace ID system based on fixed calculation from the cpu
> + * number. This has been replaced by drivers using a dynamic allocation
> + * system - but need to retain the legacy algorithm for backward comparibility
> + * in certain situations:-
> + * a) new perf running on older systems that generate the legacy mapping
> + * b) older tools e.g. simpleperf in Android, that may not update at the same
> + *    time as the kernel.
> + */
> +#define CORESIGHT_LEGACY_CPU_TRACE_ID(cpu)  (0x10 + (cpu * 2))
>  
>  /* CoreSight trace ID is currently the bottom 7 bits of the value */
>  #define CORESIGHT_TRACE_ID_VAL_MASK	GENMASK(6, 0)
>  
> +/*
> + * perf record will set the legacy meta data values as unused initially.
> + * This allows perf report to manage the decoders created when dynamic
> + * allocation in operation.
> + */
> +#define CORESIGHT_TRACE_ID_UNUSED_FLAG	BIT(31)
> +
>  /*
>   * Below are the definition of bit offsets for perf option, and works as
>   * arbitrary values for all ETM versions.
> @@ -39,15 +56,4 @@
>  #define ETM4_CFG_BIT_RETSTK	12
>  #define ETM4_CFG_BIT_VMID_OPT	15
>  
> -static inline int coresight_get_trace_id(int cpu)
> -{
> -	/*
> -	 * A trace ID of value 0 is invalid, so let's start at some
> -	 * random value that fits in 7 bits and go from there.  Since
> -	 * the common convention is to have data trace IDs be I(N) + 1,
> -	 * set instruction trace IDs as a function of the CPU number.
> -	 */
> -	return (CORESIGHT_ETM_PMU_SEED + (cpu * 2));
> -}
> -
>  #endif
> diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
> index 1b54638d53b0..196fe1a77de9 100644
> --- a/tools/perf/arch/arm/util/cs-etm.c
> +++ b/tools/perf/arch/arm/util/cs-etm.c
> @@ -421,13 +421,16 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
>  	evlist__to_front(evlist, cs_etm_evsel);
>  
>  	/*
> -	 * In the case of per-cpu mmaps, we need the CPU on the
> -	 * AUX event.  We also need the contextID in order to be notified
> +	 * get the CPU on the sample - need it to associate trace ID in the
> +	 * AUX_OUTPUT_HW_ID event, and the AUX event for per-cpu mmaps.
> +	 */
> +	evsel__set_sample_bit(cs_etm_evsel, CPU);
> +
> +	/*
> +	 * Also the case of per-cpu mmaps, need the contextID in order to be notified
>  	 * when a context switch happened.
>  	 */
>  	if (!perf_cpu_map__empty(cpus)) {
> -		evsel__set_sample_bit(cs_etm_evsel, CPU);
> -
>  		err = cs_etm_set_option(itr, cs_etm_evsel,
>  					BIT(ETM_OPT_CTXTID) | BIT(ETM_OPT_TS));
>  		if (err)
> @@ -633,8 +636,10 @@ static void cs_etm_save_etmv4_header(__u64 data[], struct auxtrace_record *itr,
>  
>  	/* Get trace configuration register */
>  	data[CS_ETMV4_TRCCONFIGR] = cs_etmv4_get_config(itr);
> -	/* Get traceID from the framework */
> -	data[CS_ETMV4_TRCTRACEIDR] = coresight_get_trace_id(cpu);
> +	/* traceID set to legacy version, in case new perf running on older system */
> +	data[CS_ETMV4_TRCTRACEIDR] =
> +		CORESIGHT_LEGACY_CPU_TRACE_ID(cpu) | CORESIGHT_TRACE_ID_UNUSED_FLAG;
> +
>  	/* Get read-only information from sysFS */
>  	data[CS_ETMV4_TRCIDR0] = cs_etm_get_ro(cs_etm_pmu, cpu,
>  					       metadata_etmv4_ro[CS_ETMV4_TRCIDR0]);
> @@ -681,9 +686,9 @@ static void cs_etm_get_metadata(int cpu, u32 *offset,
>  		magic = __perf_cs_etmv3_magic;
>  		/* Get configuration register */
>  		info->priv[*offset + CS_ETM_ETMCR] = cs_etm_get_config(itr);
> -		/* Get traceID from the framework */
> +		/* traceID set to legacy value in case new perf running on old system */
>  		info->priv[*offset + CS_ETM_ETMTRACEIDR] =
> -						coresight_get_trace_id(cpu);
> +			CORESIGHT_LEGACY_CPU_TRACE_ID(cpu) | CORESIGHT_TRACE_ID_UNUSED_FLAG;
>  		/* Get read-only information from sysFS */
>  		info->priv[*offset + CS_ETM_ETMCCER] =
>  			cs_etm_get_ro(cs_etm_pmu, cpu,