Re: [PATCH 1/7] perf, x86: Reduce lbr_sel_map size

["Yan, Zheng" <zheng.z.yan@intel.com>]

On 06/25/2013 08:33 PM, Stephane Eranian wrote:
> On Tue, Jun 25, 2013 at 10:47 AM, Yan, Zheng <zheng.z.yan@intel.com> wrote:
>> From: "Yan, Zheng" <zheng.z.yan@intel.com>
>>
>> The index of lbr_sel_map is bit value of perf branch_sample_type.
>> We can reduce lbr_sel_map size by using bit shift as index.
>>
>> Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
>> ---
>>  arch/x86/kernel/cpu/perf_event.h           |  4 +++
>>  arch/x86/kernel/cpu/perf_event_intel_lbr.c | 50 ++++++++++++++----------------
>>  include/uapi/linux/perf_event.h            | 42 +++++++++++++++++--------
>>  3 files changed, 56 insertions(+), 40 deletions(-)
>>
>> diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
>> index 108dc75..a74d554 100644
>> --- a/arch/x86/kernel/cpu/perf_event.h
>> +++ b/arch/x86/kernel/cpu/perf_event.h
>> @@ -447,6 +447,10 @@ struct x86_pmu {
>>         struct perf_guest_switch_msr *(*guest_get_msrs)(int *nr);
>>  };
>>
>> +enum {
>> +       PERF_SAMPLE_BRANCH_SELECT_MAP_SIZE = PERF_SAMPLE_BRANCH_MAX_SHIFT,
>> +};
>> +
>>  #define x86_add_quirk(func_)                                           \
>>  do {                                                                   \
>>         static struct x86_pmu_quirk __quirk __initdata = {              \
>> diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
>> index d5be06a..a72e9e9 100644
>> --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
>> +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
>> @@ -69,10 +69,6 @@ static enum {
>>  #define LBR_FROM_FLAG_IN_TX    (1ULL << 62)
>>  #define LBR_FROM_FLAG_ABORT    (1ULL << 61)
>>
>> -#define for_each_branch_sample_type(x) \
>> -       for ((x) = PERF_SAMPLE_BRANCH_USER; \
>> -            (x) < PERF_SAMPLE_BRANCH_MAX; (x) <<= 1)
>> -
>>  /*
>>   * x86control flow change classification
>>   * x86control flow changes include branches, interrupts, traps, faults
>> @@ -387,14 +383,14 @@ static int intel_pmu_setup_hw_lbr_filter(struct perf_event *event)
>>  {
>>         struct hw_perf_event_extra *reg;
>>         u64 br_type = event->attr.branch_sample_type;
>> -       u64 mask = 0, m;
>> -       u64 v;
>> +       u64 mask = 0, v;
>> +       int i;
>>
>> -       for_each_branch_sample_type(m) {
>> -               if (!(br_type & m))
>> +       for (i = 0; i < PERF_SAMPLE_BRANCH_SELECT_MAP_SIZE; i++) {
>> +               if (!(br_type & (1U << i)))
> 
> Needs to be 1ULL to avoid bug later on. br_type is u64.

thanks, will fix.

> 
>>                         continue;
>>
>> -               v = x86_pmu.lbr_sel_map[m];
>> +               v = x86_pmu.lbr_sel_map[i];
>>                 if (v == LBR_NOT_SUPP)
>>                         return -EOPNOTSUPP;
>>
>> @@ -649,33 +645,33 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc)
>>  /*
>>   * Map interface branch filters onto LBR filters
>>   */
>> -static const int nhm_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX] = {
>> -       [PERF_SAMPLE_BRANCH_ANY]        = LBR_ANY,
>> -       [PERF_SAMPLE_BRANCH_USER]       = LBR_USER,
>> -       [PERF_SAMPLE_BRANCH_KERNEL]     = LBR_KERNEL,
>> -       [PERF_SAMPLE_BRANCH_HV]         = LBR_IGN,
>> -       [PERF_SAMPLE_BRANCH_ANY_RETURN] = LBR_RETURN | LBR_REL_JMP
>> -                                       | LBR_IND_JMP | LBR_FAR,
>> +static const int nhm_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_REL_JMP
>> +                                               | LBR_IND_JMP | LBR_FAR,
>>         /*
>>          * NHM/WSM erratum: must include REL_JMP+IND_JMP to get CALL branches
>>          */
>> -       [PERF_SAMPLE_BRANCH_ANY_CALL] =
>> +       [PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT] =
>>          LBR_REL_CALL | LBR_IND_CALL | LBR_REL_JMP | LBR_IND_JMP | LBR_FAR,
>>         /*
>>          * NHM/WSM erratum: must include IND_JMP to capture IND_CALL
>>          */
>> -       [PERF_SAMPLE_BRANCH_IND_CALL] = LBR_IND_CALL | LBR_IND_JMP,
>> +       [PERF_SAMPLE_BRANCH_IND_CALL_SHIFT] = LBR_IND_CALL | LBR_IND_JMP,
>>  };
>>
> I think it would ease formatting readability
> if the indexes could be constructed from a simple macro:
> #define BR_SHIFT(a) \
>   PERF_SAMPLE_##a##_SHIFT
> 
> #define BR_SMPL(a) \
>    PERF_SAMPLE_##a


#define BR_SHIFT(a) PERF_SAMPLE_##a##_SHIFT

static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_SELECT_MAP_SIZE] = {
	[BR_SHIFT(ANY)]			= LBR_ANY,
	[BR_SHIFT(USER)]		= LBR_USER,
	[BR_SHIFT(KERNEL)		= LBR_KERNEL,
	[BR_SHIFT(HV)]			= LBR_IGN,
	[BR_SHIFT(ANY_RETURN)]		= LBR_RETURN | LBR_FAR,
	[BR_SHIFT(ANY_CALL)]		= LBR_REL_CALL | LBR_IND_CALL | LBR_FAR,
	[BR_SHIFT(CALL_STACK)]		= LBR_IND_CALL,
};

the code looks strange, I don't think it has better readability. 

Regards
Yan, Zheng



> 
>> -static const int snb_lbr_sel_map[PERF_SAMPLE_BRANCH_MAX] = {
>> -       [PERF_SAMPLE_BRANCH_ANY]        = LBR_ANY,
>> -       [PERF_SAMPLE_BRANCH_USER]       = LBR_USER,
>> -       [PERF_SAMPLE_BRANCH_KERNEL]     = LBR_KERNEL,
>> -       [PERF_SAMPLE_BRANCH_HV]         = LBR_IGN,
>> -       [PERF_SAMPLE_BRANCH_ANY_RETURN] = LBR_RETURN | LBR_FAR,
>> -       [PERF_SAMPLE_BRANCH_ANY_CALL]   = LBR_REL_CALL | LBR_IND_CALL
>> -                                       | LBR_FAR,
>> -       [PERF_SAMPLE_BRANCH_IND_CALL]   = LBR_IND_CALL,
>> +static const int snb_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,
>>  };
>>
>>  /* core */
>> diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
>> index 0b1df41..2ec219e 100644
>> --- a/include/uapi/linux/perf_event.h
>> +++ b/include/uapi/linux/perf_event.h
>> @@ -148,20 +148,36 @@ enum perf_event_sample_format {
>>   * The branch types can be combined, however BRANCH_ANY covers all types
>>   * of branches and therefore it supersedes all the other types.
>>   */
>> +enum perf_branch_sample_type_shift {
>> +       PERF_SAMPLE_BRANCH_USER_SHIFT           = 0, /* user branches */
>> +       PERF_SAMPLE_BRANCH_KERNEL_SHIFT         = 1, /* kernel branches */
>> +       PERF_SAMPLE_BRANCH_HV_SHIFT             = 2, /* hypervisor branches */
>> +
>> +       PERF_SAMPLE_BRANCH_ANY_SHIFT            = 3, /* any branch types */
>> +       PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT       = 4, /* any call branch */
>> +       PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT     = 5, /* any return branch */
>> +       PERF_SAMPLE_BRANCH_IND_CALL_SHIFT       = 6, /* indirect calls */
>> +       PERF_SAMPLE_BRANCH_ABORT_TX_SHIFT       = 7, /* transaction aborts */
>> +       PERF_SAMPLE_BRANCH_IN_TX_SHIFT          = 8, /* in transaction */
>> +       PERF_SAMPLE_BRANCH_NO_TX_SHIFT          = 9, /* not in transaction */
>> +
>> +       PERF_SAMPLE_BRANCH_MAX_SHIFT            /* non-ABI */
>> +};
>> +
>>  enum perf_branch_sample_type {
>> -       PERF_SAMPLE_BRANCH_USER         = 1U << 0, /* user branches */
>> -       PERF_SAMPLE_BRANCH_KERNEL       = 1U << 1, /* kernel branches */
>> -       PERF_SAMPLE_BRANCH_HV           = 1U << 2, /* hypervisor branches */
>> -
>> -       PERF_SAMPLE_BRANCH_ANY          = 1U << 3, /* any branch types */
>> -       PERF_SAMPLE_BRANCH_ANY_CALL     = 1U << 4, /* any call branch */
>> -       PERF_SAMPLE_BRANCH_ANY_RETURN   = 1U << 5, /* any return branch */
>> -       PERF_SAMPLE_BRANCH_IND_CALL     = 1U << 6, /* indirect calls */
>> -       PERF_SAMPLE_BRANCH_ABORT_TX     = 1U << 7, /* transaction aborts */
>> -       PERF_SAMPLE_BRANCH_IN_TX        = 1U << 8, /* in transaction */
>> -       PERF_SAMPLE_BRANCH_NO_TX        = 1U << 9, /* not in transaction */
>> -
>> -       PERF_SAMPLE_BRANCH_MAX          = 1U << 10, /* non-ABI */
>> +       PERF_SAMPLE_BRANCH_USER         = 1U << PERF_SAMPLE_BRANCH_USER_SHIFT,
>> +       PERF_SAMPLE_BRANCH_KERNEL       = 1U << PERF_SAMPLE_BRANCH_KERNEL_SHIFT,
>> +       PERF_SAMPLE_BRANCH_HV           = 1U << PERF_SAMPLE_BRANCH_HV_SHIFT,
>> +
>> +       PERF_SAMPLE_BRANCH_ANY          = 1U << PERF_SAMPLE_BRANCH_ANY_SHIFT,
>> +       PERF_SAMPLE_BRANCH_ANY_CALL     = 1U << PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT,
>> +       PERF_SAMPLE_BRANCH_ANY_RETURN   = 1U << PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT,
>> +       PERF_SAMPLE_BRANCH_IND_CALL     = 1U << PERF_SAMPLE_BRANCH_IND_CALL_SHIFT,
>> +       PERF_SAMPLE_BRANCH_ABORT_TX     = 1U << PERF_SAMPLE_BRANCH_ABORT_TX_SHIFT,
>> +       PERF_SAMPLE_BRANCH_IN_TX        = 1U << PERF_SAMPLE_BRANCH_IN_TX_SHIFT,
>> +       PERF_SAMPLE_BRANCH_NO_TX        = 1U << PERF_SAMPLE_BRANCH_NO_TX_SHIFT,
>> +
>> +       PERF_SAMPLE_BRANCH_MAX          = 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT,
>>  };
>>
>>  #define PERF_SAMPLE_BRANCH_PLM_ALL \
>> --
>> 1.8.1.4
>>