lkml.org 
[lkml]   [2021]   [Dec]   [10]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
    Patch in this message
    /
    From
    Subject[PATCH v11 06/17] x86/perf/core: Add pebs_capable to store valid PEBS_COUNTER_MASK value
    Date
    From: "Peter Zijlstra (Intel)" <peterz@infradead.org>

    From: "Peter Zijlstra (Intel)" <peterz@infradead.org>

    The value of pebs_counter_mask will be accessed frequently
    for repeated use in the intel_guest_get_msrs(). So it can be
    optimized instead of endlessly mucking about with branches.

    Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
    ---
    arch/x86/events/intel/core.c | 14 ++++++--------
    arch/x86/events/perf_event.h | 1 +
    2 files changed, 7 insertions(+), 8 deletions(-)

    diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
    index 6721ccd9067b..c886e360698c 100644
    --- a/arch/x86/events/intel/core.c
    +++ b/arch/x86/events/intel/core.c
    @@ -2911,10 +2911,7 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
    * counters from the GLOBAL_STATUS mask and we always process PEBS
    * events via drain_pebs().
    */
    - if (x86_pmu.flags & PMU_FL_PEBS_ALL)
    - status &= ~cpuc->pebs_enabled;
    - else
    - status &= ~(cpuc->pebs_enabled & PEBS_COUNTER_MASK);
    + status &= ~(cpuc->pebs_enabled & x86_pmu.pebs_capable);

    /*
    * PEBS overflow sets bit 62 in the global status register
    @@ -3963,10 +3960,7 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr, void *data)
    arr[0].msr = MSR_CORE_PERF_GLOBAL_CTRL;
    arr[0].host = intel_ctrl & ~cpuc->intel_ctrl_guest_mask;
    arr[0].guest = intel_ctrl & ~cpuc->intel_ctrl_host_mask;
    - if (x86_pmu.flags & PMU_FL_PEBS_ALL)
    - arr[0].guest &= ~cpuc->pebs_enabled;
    - else
    - arr[0].guest &= ~(cpuc->pebs_enabled & PEBS_COUNTER_MASK);
    + arr[0].guest &= ~(cpuc->pebs_enabled & x86_pmu.pebs_capable);
    *nr = 1;

    if (x86_pmu.pebs && x86_pmu.pebs_no_isolation) {
    @@ -5657,6 +5651,7 @@ __init int intel_pmu_init(void)
    x86_pmu.events_mask_len = eax.split.mask_length;

    x86_pmu.max_pebs_events = min_t(unsigned, MAX_PEBS_EVENTS, x86_pmu.num_counters);
    + x86_pmu.pebs_capable = PEBS_COUNTER_MASK;

    /*
    * Quirk: v2 perfmon does not report fixed-purpose events, so
    @@ -5841,6 +5836,7 @@ __init int intel_pmu_init(void)
    x86_pmu.pebs_aliases = NULL;
    x86_pmu.pebs_prec_dist = true;
    x86_pmu.lbr_pt_coexist = true;
    + x86_pmu.pebs_capable = ~0ULL;
    x86_pmu.flags |= PMU_FL_HAS_RSP_1;
    x86_pmu.flags |= PMU_FL_PEBS_ALL;
    x86_pmu.get_event_constraints = glp_get_event_constraints;
    @@ -6198,6 +6194,7 @@ __init int intel_pmu_init(void)
    x86_pmu.pebs_aliases = NULL;
    x86_pmu.pebs_prec_dist = true;
    x86_pmu.pebs_block = true;
    + x86_pmu.pebs_capable = ~0ULL;
    x86_pmu.flags |= PMU_FL_HAS_RSP_1;
    x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
    x86_pmu.flags |= PMU_FL_PEBS_ALL;
    @@ -6240,6 +6237,7 @@ __init int intel_pmu_init(void)
    x86_pmu.pebs_aliases = NULL;
    x86_pmu.pebs_prec_dist = true;
    x86_pmu.pebs_block = true;
    + x86_pmu.pebs_capable = ~0ULL;
    x86_pmu.flags |= PMU_FL_HAS_RSP_1;
    x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
    x86_pmu.flags |= PMU_FL_PEBS_ALL;
    diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
    index 21f84cc6a827..28ca0ada1616 100644
    --- a/arch/x86/events/perf_event.h
    +++ b/arch/x86/events/perf_event.h
    @@ -824,6 +824,7 @@ struct x86_pmu {
    void (*pebs_aliases)(struct perf_event *event);
    unsigned long large_pebs_flags;
    u64 rtm_abort_event;
    + u64 pebs_capable;

    /*
    * Intel LBR
    --
    2.33.1
    \
     
     \ /
      Last update: 2021-12-10 14:37    [W:4.233 / U:0.012 seconds]
    ©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site