linux-kernel - Re: [PATCH 1/6] perf/amd/ibs: Add support for L3 miss filtering

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] [thread-next>] [day] [month] [year] [list]

Message-ID: <20220426100707.GP2731@worktop.programming.kicks-ass.net>
Date:   Tue, 26 Apr 2022 12:07:07 +0200
From:   Peter Zijlstra <peterz@...radead.org>
To:     Ravi Bangoria <ravi.bangoria@....com>
Cc:     acme@...nel.org, mingo@...hat.com, mark.rutland@....com,
        jolsa@...nel.org, namhyung@...nel.org, tglx@...utronix.de,
        bp@...en8.de, irogers@...gle.com, yao.jin@...ux.intel.com,
        james.clark@....com, leo.yan@...aro.org, kan.liang@...ux.intel.com,
        ak@...ux.intel.com, eranian@...gle.com, like.xu.linux@...il.com,
        x86@...nel.org, linux-perf-users@...r.kernel.org,
        linux-kernel@...r.kernel.org, sandipan.das@....com,
        ananth.narayan@....com, kim.phillips@....com, rrichter@....com,
        santosh.shukla@....com
Subject: Re: [PATCH 1/6] perf/amd/ibs: Add support for L3 miss filtering

On Mon, Apr 25, 2022 at 10:13:18AM +0530, Ravi Bangoria wrote:
> IBS L3 miss filtering works by tagging an instruction on IBS counter
> overflow and generating an NMI if the tagged instruction causes an L3
> miss. Samples without an L3 miss are discarded and counter is reset
> with random value (between 1-15 for fetch pmu and 1-127 for op pmu).
> This helps in reducing sampling overhead when user is interested only
> in such samples. One of the use case of such filtered samples is to
> feed data to page-migration daemon in tiered memory systems.
> 
> Add support for L3 miss filtering in IBS driver via new pmu attribute
> "l3missonly". Example usage:
> 
>   # perf record -a -e ibs_op/l3missonly=1/ --raw-samples sleep 5
> 
> Signed-off-by: Ravi Bangoria <ravi.bangoria@....com>
> ---
>  arch/x86/events/amd/ibs.c         | 42 ++++++++++++++++++++++---------
>  arch/x86/include/asm/perf_event.h |  3 +++
>  2 files changed, 33 insertions(+), 12 deletions(-)
> 
> diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
> index 9739019d4b67..a5303d62060c 100644
> --- a/arch/x86/events/amd/ibs.c
> +++ b/arch/x86/events/amd/ibs.c
> @@ -520,16 +520,12 @@ static void perf_ibs_read(struct perf_event *event) { }
>  
>  PMU_FORMAT_ATTR(rand_en,	"config:57");
>  PMU_FORMAT_ATTR(cnt_ctl,	"config:19");
> +PMU_EVENT_ATTR_STRING(l3missonly, fetch_l3missonly, "config:59");
> +PMU_EVENT_ATTR_STRING(l3missonly, op_l3missonly, "config:16");
>  
> -static struct attribute *ibs_fetch_format_attrs[] = {
> -	&format_attr_rand_en.attr,
> -	NULL,
> -};
> -
> -static struct attribute *ibs_op_format_attrs[] = {
> -	NULL,	/* &format_attr_cnt_ctl.attr if IBS_CAPS_OPCNT */
> -	NULL,
> -};
> +/* size = nr attrs plus NULL at the end */
> +static struct attribute *ibs_fetch_format_attrs[3];
> +static struct attribute *ibs_op_format_attrs[3];
>  
>  static struct perf_ibs perf_ibs_fetch = {
>  	.pmu = {
> @@ -759,9 +755,9 @@ static __init int perf_ibs_pmu_init(struct perf_ibs *perf_ibs, char *name)
>  	return ret;
>  }
>  
> -static __init void perf_event_ibs_init(void)
> +static __init void perf_ibs_fetch_prepare(void)
>  {
> -	struct attribute **attr = ibs_op_format_attrs;
> +	struct attribute **format_attrs = perf_ibs_fetch.format_attrs;
>  
>  	/*
>  	 * Some chips fail to reset the fetch count when it is written; instead
> @@ -773,11 +769,22 @@ static __init void perf_event_ibs_init(void)
>  	if (boot_cpu_data.x86 == 0x19 && boot_cpu_data.x86_model < 0x10)
>  		perf_ibs_fetch.fetch_ignore_if_zero_rip = 1;
>  
> +	*format_attrs++ = &format_attr_rand_en.attr;
> +	if (ibs_caps & IBS_CAPS_ZEN4IBSEXTENSIONS) {
> +		perf_ibs_fetch.config_mask |= IBS_FETCH_L3MISSONLY;
> +		*format_attrs++ = &fetch_l3missonly.attr.attr;
> +	}
> +
>  	perf_ibs_pmu_init(&perf_ibs_fetch, "ibs_fetch");
> +}
> +
> +static __init void perf_ibs_op_prepare(void)
> +{
> +	struct attribute **format_attrs = perf_ibs_op.format_attrs;
>  
>  	if (ibs_caps & IBS_CAPS_OPCNT) {
>  		perf_ibs_op.config_mask |= IBS_OP_CNT_CTL;
> -		*attr++ = &format_attr_cnt_ctl.attr;
> +		*format_attrs++ = &format_attr_cnt_ctl.attr;
>  	}
>  
>  	if (ibs_caps & IBS_CAPS_OPCNTEXT) {
> @@ -786,7 +793,18 @@ static __init void perf_event_ibs_init(void)
>  		perf_ibs_op.cnt_mask    |= IBS_OP_MAX_CNT_EXT_MASK;
>  	}
>  
> +	if (ibs_caps & IBS_CAPS_ZEN4IBSEXTENSIONS) {
> +		perf_ibs_op.config_mask |= IBS_OP_L3MISSONLY;
> +		*format_attrs++ = &op_l3missonly.attr.attr;
> +	}
> +
>  	perf_ibs_pmu_init(&perf_ibs_op, "ibs_op");
> +}

Right, so Greg told us to stop doing silly things like this and use
.is_visible, also see commits like:

  b7c9b3927337 ("perf/x86/intel: Use ->is_visible callback for default group")

There's quite a bit of that in the intel driver and some in the x86
core code too. Please have a look.