Re: [PATCH 2/7] perf, x86: Basic Haswell LBR call stack support

[Stephane Eranian]

On Tue, Jun 25, 2013 at 10:47 AM, Yan, Zheng <zheng.z.yan@xxxxxxxxx> wrote:
> From: "Yan, Zheng" <zheng.z.yan@xxxxxxxxx>
>
> The new HSW call stack feature provides a facility such that
> unfiltered call data will be collected as normal, but as return
> instructions are executed the last captured branch record is
> popped from the LBR stack. Thus, branch information relative to
> leaf functions will not be captured, while preserving the call
> stack information of the main line execution path.
>
> Signed-off-by: Yan, Zheng <zheng.z.yan@xxxxxxxxx>
> ---
>  arch/x86/kernel/cpu/perf_event.h           |  7 ++-
>  arch/x86/kernel/cpu/perf_event_intel.c     |  2 +-
>  arch/x86/kernel/cpu/perf_event_intel_lbr.c | 89 ++++++++++++++++++++++--------
>  3 files changed, 74 insertions(+), 24 deletions(-)
>
> diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
> index a74d554..e14c963 100644
> --- a/arch/x86/kernel/cpu/perf_event.h
> +++ b/arch/x86/kernel/cpu/perf_event.h
> @@ -448,7 +448,10 @@ struct x86_pmu {
>  };
>
>  enum {
> -       PERF_SAMPLE_BRANCH_SELECT_MAP_SIZE = PERF_SAMPLE_BRANCH_MAX_SHIFT,
> +       PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT = PERF_SAMPLE_BRANCH_MAX_SHIFT,
> +       PERF_SAMPLE_BRANCH_SELECT_MAP_SIZE,
> +
> +       PERF_SAMPLE_BRANCH_CALL_STACK = 1U << PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT,
>  };
>
>  #define x86_add_quirk(func_)                                           \
> @@ -681,6 +684,8 @@ void intel_pmu_lbr_init_atom(void);
>
>  void intel_pmu_lbr_init_snb(void);
>
> +void intel_pmu_lbr_init_hsw(void);
> +
>  int intel_pmu_setup_lbr_filter(struct perf_event *event);
>
>  int p4_pmu_init(void);
> diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
> index a6eccf1..3e92a68 100644
> --- a/arch/x86/kernel/cpu/perf_event_intel.c
> +++ b/arch/x86/kernel/cpu/perf_event_intel.c
> @@ -2276,7 +2276,7 @@ __init int intel_pmu_init(void)
>                 memcpy(hw_cache_event_ids, snb_hw_cache_event_ids, sizeof(hw_cache_event_ids));
>                 memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
>
> -               intel_pmu_lbr_init_snb();
> +               intel_pmu_lbr_init_hsw();
>
>                 x86_pmu.event_constraints = intel_hsw_event_constraints;
>                 x86_pmu.pebs_constraints = intel_hsw_pebs_event_constraints;
> diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
> index a72e9e9..2136320 100644
> --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
> +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
> @@ -39,6 +39,7 @@ static enum {
>  #define LBR_IND_JMP_BIT                6 /* do not capture indirect jumps */
>  #define LBR_REL_JMP_BIT                7 /* do not capture relative jumps */
>  #define LBR_FAR_BIT            8 /* do not capture far branches */
> +#define LBR_CALL_STACK_BIT     9 /* enable call stack */
>
>  #define LBR_KERNEL     (1 << LBR_KERNEL_BIT)
>  #define LBR_USER       (1 << LBR_USER_BIT)
> @@ -49,6 +50,7 @@ static enum {
>  #define LBR_REL_JMP    (1 << LBR_REL_JMP_BIT)
>  #define LBR_IND_JMP    (1 << LBR_IND_JMP_BIT)
>  #define LBR_FAR                (1 << LBR_FAR_BIT)
> +#define LBR_CALL_STACK (1 << LBR_CALL_STACK_BIT)
>
>  #define LBR_PLM (LBR_KERNEL | LBR_USER)
>
> @@ -74,24 +76,25 @@ static enum {
>   * x86control flow changes include branches, interrupts, traps, faults
>   */
>  enum {
> -       X86_BR_NONE     = 0,      /* unknown */
> -
> -       X86_BR_USER     = 1 << 0, /* branch target is user */
> -       X86_BR_KERNEL   = 1 << 1, /* branch target is kernel */
> -
> -       X86_BR_CALL     = 1 << 2, /* call */
> -       X86_BR_RET      = 1 << 3, /* return */
> -       X86_BR_SYSCALL  = 1 << 4, /* syscall */
> -       X86_BR_SYSRET   = 1 << 5, /* syscall return */
> -       X86_BR_INT      = 1 << 6, /* sw interrupt */
> -       X86_BR_IRET     = 1 << 7, /* return from interrupt */
> -       X86_BR_JCC      = 1 << 8, /* conditional */
> -       X86_BR_JMP      = 1 << 9, /* jump */
> -       X86_BR_IRQ      = 1 << 10,/* hw interrupt or trap or fault */
> -       X86_BR_IND_CALL = 1 << 11,/* indirect calls */
> -       X86_BR_ABORT    = 1 << 12,/* transaction abort */
> -       X86_BR_IN_TX    = 1 << 13,/* in transaction */
> -       X86_BR_NO_TX    = 1 << 14,/* not in transaction */
> +       X86_BR_NONE             = 0,      /* unknown */
> +
> +       X86_BR_USER             = 1 << 0, /* branch target is user */
> +       X86_BR_KERNEL           = 1 << 1, /* branch target is kernel */
> +
> +       X86_BR_CALL             = 1 << 2, /* call */
> +       X86_BR_RET              = 1 << 3, /* return */
> +       X86_BR_SYSCALL          = 1 << 4, /* syscall */
> +       X86_BR_SYSRET           = 1 << 5, /* syscall return */
> +       X86_BR_INT              = 1 << 6, /* sw interrupt */
> +       X86_BR_IRET             = 1 << 7, /* return from interrupt */
> +       X86_BR_JCC              = 1 << 8, /* conditional */
> +       X86_BR_JMP              = 1 << 9, /* jump */
> +       X86_BR_IRQ              = 1 << 10,/* hw interrupt or trap or fault */
> +       X86_BR_IND_CALL         = 1 << 11,/* indirect calls */
> +       X86_BR_ABORT            = 1 << 12,/* transaction abort */
> +       X86_BR_IN_TX            = 1 << 13,/* in transaction */
> +       X86_BR_NO_TX            = 1 << 14,/* not in transaction */
> +       X86_BR_CALL_STACK       = 1 << 15,/* call stack */
>  };
>
>  #define X86_BR_PLM (X86_BR_USER | X86_BR_KERNEL)
> @@ -135,7 +138,10 @@ static void __intel_pmu_lbr_enable(void)
>                 wrmsrl(MSR_LBR_SELECT, cpuc->lbr_sel->config);
>
>         rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
> -       debugctl |= (DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
> +       debugctl |= DEBUGCTLMSR_LBR;
> +       /* LBR callstack does not work well with FREEZE_LBRS_ON_PMI */
> +       if (!cpuc->lbr_sel || !(cpuc->lbr_sel->config & LBR_CALL_STACK))
> +               debugctl |= DEBUGCTLMSR_FREEZE_LBRS_ON_PMI;
>         wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
>  }
Is that a bug or a known limitation here?

In either case for HSW, this means the call-stack mode is only useful when
measuring user level code and MUST be enforced that way by the kernel.
In other words, callstack can ONLY be associated with events measuring
ONLY at the user level. Otherwise you lose correlation with counter overflow.

Don't see the code to enforce this restriction in this patch. Maybe it
is elsewhere.

>
> @@ -333,7 +339,7 @@ void intel_pmu_lbr_read(void)
>   * - in case there is no HW filter
>   * - in case the HW filter has errata or limitations
>   */
> -static void intel_pmu_setup_sw_lbr_filter(struct perf_event *event)
> +static int intel_pmu_setup_sw_lbr_filter(struct perf_event *event)
>  {
>         u64 br_type = event->attr.branch_sample_type;
>         int mask = 0;
> @@ -367,11 +373,21 @@ static void intel_pmu_setup_sw_lbr_filter(struct perf_event *event)
>         if (br_type & PERF_SAMPLE_BRANCH_NO_TX)
>                 mask |= X86_BR_NO_TX;
>
> +       if (br_type & PERF_SAMPLE_BRANCH_CALL_STACK) {
> +               if (!x86_pmu.lbr_sel_map)
> +                       return -EOPNOTSUPP;
> +               if (mask & ~(X86_BR_USER | X86_BR_KERNEL))
> +                       return -EINVAL;
> +               mask |= X86_BR_CALL | X86_BR_IND_CALL | X86_BR_RET |
> +                       X86_BR_CALL_STACK;
> +       }
> +
>         /*
>          * stash actual user request into reg, it may
>          * be used by fixup code for some CPU
>          */
>         event->hw.branch_reg.reg = mask;
> +       return 0;
>  }
>
>  /*
> @@ -401,7 +417,7 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event)
>         reg->idx = EXTRA_REG_LBR;
>
>         /* LBR_SELECT operates in suppress mode so invert mask */
> -       reg->config = ~mask & x86_pmu.lbr_sel_mask;
> +       reg->config = mask ^ x86_pmu.lbr_sel_mask;
>
>         return 0;
>  }
> @@ -419,7 +435,9 @@ int intel_pmu_setup_lbr_filter(struct perf_event *event)
>         /*
>          * setup SW LBR filter
>          */
> -       intel_pmu_setup_sw_lbr_filter(event);
> +       ret = intel_pmu_setup_sw_lbr_filter(event);
> +       if (ret)
> +               return ret;
>
>         /*
>          * setup HW LBR filter, if any
> @@ -674,6 +692,19 @@ static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_SELECT_MAP_SIZE] = {
>         [PERF_SAMPLE_BRANCH_IND_CALL_SHIFT]     = LBR_IND_CALL,
>  };
>
> +static const int hsw_lbr_sel_map[PERF_SAMPLE_BRANCH_SELECT_MAP_SIZE] = {
> +       [PERF_SAMPLE_BRANCH_ANY_SHIFT]          = LBR_ANY,
> +       [PERF_SAMPLE_BRANCH_USER_SHIFT]         = LBR_USER,
> +       [PERF_SAMPLE_BRANCH_KERNEL_SHIFT]       = LBR_KERNEL,
> +       [PERF_SAMPLE_BRANCH_HV_SHIFT]           = LBR_IGN,
> +       [PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT]   = LBR_RETURN | LBR_FAR,
> +       [PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT]     = LBR_REL_CALL | LBR_IND_CALL
> +                                               | LBR_FAR,
> +       [PERF_SAMPLE_BRANCH_IND_CALL_SHIFT]     = LBR_IND_CALL,
> +       [PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT]   = LBR_REL_CALL | LBR_IND_CALL
> +                                               | LBR_RETURN | LBR_CALL_STACK,
> +};
> +
>  /* core */
>  void intel_pmu_lbr_init_core(void)
>  {
> @@ -730,6 +761,20 @@ void intel_pmu_lbr_init_snb(void)
>         pr_cont("16-deep LBR, ");
>  }
>
> +/* haswell */
> +void intel_pmu_lbr_init_hsw(void)
> +{
> +       x86_pmu.lbr_nr   = 16;
> +       x86_pmu.lbr_tos  = MSR_LBR_TOS;
> +       x86_pmu.lbr_from = MSR_LBR_NHM_FROM;
> +       x86_pmu.lbr_to   = MSR_LBR_NHM_TO;
> +
> +       x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
> +       x86_pmu.lbr_sel_map  = hsw_lbr_sel_map;
> +
> +       pr_cont("16-deep LBR, ");
> +}
> +
>  /* atom */
>  void intel_pmu_lbr_init_atom(void)
>  {
> --
> 1.8.1.4
>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/