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: <CAP-5=fU4Mn0BhgS3n_aUmfamtD77d-VDhnZ1OoiRvXFrGJERCQ@mail.gmail.com>
Date: Tue, 25 Jun 2024 18:34:50 -0700
From: Ian Rogers <irogers@...gle.com>
To: kan.liang@...ux.intel.com
Cc: peterz@...radead.org, mingo@...nel.org, acme@...nel.org, 
	namhyung@...nel.org, adrian.hunter@...el.com, 
	alexander.shishkin@...ux.intel.com, linux-kernel@...r.kernel.org, 
	ak@...ux.intel.com, eranian@...gle.com, 
	Dapeng Mi <dapeng1.mi@...ux.intel.com>
Subject: Re: [PATCH V2 07/13] perf/x86/intel: Support PERFEVTSEL extension

On Tue, Jun 25, 2024 at 11:22 AM <kan.liang@...ux.intel.com> wrote:
>
> From: Kan Liang <kan.liang@...ux.intel.com>
>
> Two new fields (the unit mask2, and the equal flag) are added in the
> IA32_PERFEVTSELx MSRs. They can be enumerated by the CPUID.23H.0.EBX.
>
> Update the config_mask in x86_pmu and x86_hybrid_pmu for the true layout
> of the PERFEVTSEL.
> Expose the new formats into sysfs if they are available. The umask
> extension reuses the same format attr name "umask" as the previous
> umask. Add umask2_show to determine/display the correct format
> for the current machine.
>
> Reviewed-by: Andi Kleen <ak@...ux.intel.com>
> Co-developed-by: Dapeng Mi <dapeng1.mi@...ux.intel.com>
> Signed-off-by: Dapeng Mi <dapeng1.mi@...ux.intel.com>
> Signed-off-by: Kan Liang <kan.liang@...ux.intel.com>
> ---
>  arch/x86/events/intel/core.c      | 69 +++++++++++++++++++++++++++++--
>  arch/x86/include/asm/perf_event.h |  4 ++
>  2 files changed, 69 insertions(+), 4 deletions(-)
>
> diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
> index 23e074fd25e1..9d50e1049e30 100644
> --- a/arch/x86/events/intel/core.c
> +++ b/arch/x86/events/intel/core.c
> @@ -4632,8 +4632,55 @@ PMU_FORMAT_ATTR(pc,      "config:19"     );
>  PMU_FORMAT_ATTR(any,   "config:21"     ); /* v3 + */
>  PMU_FORMAT_ATTR(inv,   "config:23"     );
>  PMU_FORMAT_ATTR(cmask, "config:24-31"  );
> -PMU_FORMAT_ATTR(in_tx,  "config:32");
> -PMU_FORMAT_ATTR(in_tx_cp, "config:33");
> +PMU_FORMAT_ATTR(in_tx,  "config:32"    );
> +PMU_FORMAT_ATTR(in_tx_cp, "config:33"  );

nit: It seems unfortunate these 2 lines change for the sake of spaces
before the ')'. Perhaps leave unchanged.

Thanks,
Ian

> +PMU_FORMAT_ATTR(eq,    "config:36"     ); /* v6 + */
> +
> +static ssize_t umask2_show(struct device *dev,
> +                          struct device_attribute *attr,
> +                          char *page)
> +{
> +       u64 mask = hybrid(dev_get_drvdata(dev), config_mask) & ARCH_PERFMON_EVENTSEL_UMASK2;
> +
> +       if (mask == ARCH_PERFMON_EVENTSEL_UMASK2)
> +               return sprintf(page, "config:8-15,40-47\n");
> +
> +       /* Roll back to the old format if umask2 is not supported. */
> +       return sprintf(page, "config:8-15\n");
> +}
> +
> +static struct device_attribute format_attr_umask2  =
> +               __ATTR(umask, 0444, umask2_show, NULL);
> +
> +static struct attribute *format_evtsel_ext_attrs[] = {
> +       &format_attr_umask2.attr,
> +       &format_attr_eq.attr,
> +       NULL
> +};
> +
> +static umode_t
> +evtsel_ext_is_visible(struct kobject *kobj, struct attribute *attr, int i)
> +{
> +       struct device *dev = kobj_to_dev(kobj);
> +       u64 mask;
> +
> +       /*
> +        * The umask and umask2 have different formats but share the
> +        * same attr name. In update mode, the previous value of the
> +        * umask is unconditionally removed before is_visible. If
> +        * umask2 format is not enumerated, it's impossible to roll
> +        * back to the old format.
> +        * Does the check in umask2_show rather than is_visible.
> +        */
> +       if (i == 0)
> +               return attr->mode;
> +
> +       mask = hybrid(dev_get_drvdata(dev), config_mask);
> +       if (i == 1)
> +               return (mask & ARCH_PERFMON_EVENTSEL_EQ) ? attr->mode : 0;
> +
> +       return 0;
> +}
>
>  static struct attribute *intel_arch_formats_attr[] = {
>         &format_attr_event.attr,
> @@ -4786,8 +4833,14 @@ static inline bool intel_pmu_broken_perf_cap(void)
>
>  static void update_pmu_cap(struct x86_hybrid_pmu *pmu)
>  {
> -       unsigned int sub_bitmaps = cpuid_eax(ARCH_PERFMON_EXT_LEAF);
> -       unsigned int eax, ebx, ecx, edx;
> +       unsigned int sub_bitmaps, eax, ebx, ecx, edx;
> +
> +       cpuid(ARCH_PERFMON_EXT_LEAF, &sub_bitmaps, &ebx, &ecx, &edx);
> +
> +       if (ebx & ARCH_PERFMON_EXT_UMASK2)
> +               pmu->config_mask |= ARCH_PERFMON_EVENTSEL_UMASK2;
> +       if (ebx & ARCH_PERFMON_EXT_EQ)
> +               pmu->config_mask |= ARCH_PERFMON_EVENTSEL_EQ;
>
>         if (sub_bitmaps & ARCH_PERFMON_NUM_COUNTER_LEAF_BIT) {
>                 cpuid_count(ARCH_PERFMON_EXT_LEAF, ARCH_PERFMON_NUM_COUNTER_LEAF,
> @@ -5810,6 +5863,12 @@ static struct attribute_group group_format_extra_skl = {
>         .is_visible = exra_is_visible,
>  };
>
> +static struct attribute_group group_format_evtsel_ext = {
> +       .name       = "format",
> +       .attrs      = format_evtsel_ext_attrs,
> +       .is_visible = evtsel_ext_is_visible,
> +};
> +
>  static struct attribute_group group_default = {
>         .attrs      = intel_pmu_attrs,
>         .is_visible = default_is_visible,
> @@ -5823,6 +5882,7 @@ static const struct attribute_group *attr_update[] = {
>         &group_caps_lbr,
>         &group_format_extra,
>         &group_format_extra_skl,
> +       &group_format_evtsel_ext,
>         &group_default,
>         NULL,
>  };
> @@ -6042,6 +6102,7 @@ static const struct attribute_group *hybrid_attr_update[] = {
>         &group_caps_gen,
>         &group_caps_lbr,
>         &hybrid_group_format_extra,
> +       &group_format_evtsel_ext,
>         &group_default,
>         &hybrid_group_cpus,
>         NULL,
> diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
> index 400c909b8658..91b73571412f 100644
> --- a/arch/x86/include/asm/perf_event.h
> +++ b/arch/x86/include/asm/perf_event.h
> @@ -32,6 +32,8 @@
>  #define ARCH_PERFMON_EVENTSEL_INV                      (1ULL << 23)
>  #define ARCH_PERFMON_EVENTSEL_CMASK                    0xFF000000ULL
>  #define ARCH_PERFMON_EVENTSEL_BR_CNTR                  (1ULL << 35)
> +#define ARCH_PERFMON_EVENTSEL_EQ                       (1ULL << 36)
> +#define ARCH_PERFMON_EVENTSEL_UMASK2                   (0xFFULL << 40)
>
>  #define INTEL_FIXED_BITS_MASK                          0xFULL
>  #define INTEL_FIXED_BITS_STRIDE                        4
> @@ -185,6 +187,8 @@ union cpuid10_edx {
>   * detection/enumeration details:
>   */
>  #define ARCH_PERFMON_EXT_LEAF                  0x00000023
> +#define ARCH_PERFMON_EXT_UMASK2                        0x1
> +#define ARCH_PERFMON_EXT_EQ                    0x2
>  #define ARCH_PERFMON_NUM_COUNTER_LEAF_BIT      0x1
>  #define ARCH_PERFMON_NUM_COUNTER_LEAF          0x1
>
> --
> 2.35.1
>

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ