perf/x86/intel/lbr: Unify the stored format of LBR information

Current LBR information in the structure x86_perf_task_context is stored
in a different format from the PEBS LBR record and Architecture LBR,
which prevents the sharing of the common codes.

Use the format of the PEBS LBR record as a unified format. Use a generic
name lbr_entry to replace pebs_lbr_entry.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/1593780569-62993-11-git-send-email-kan.liang@linux.intel.com

diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index dc43cc1..86848c5 100644 (file)
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -954,7 +954,7 @@ static void adaptive_pebs_record_size_update(void)
        if (pebs_data_cfg & PEBS_DATACFG_XMMS)
                sz += sizeof(struct pebs_xmm);
        if (pebs_data_cfg & PEBS_DATACFG_LBRS)
-               sz += x86_pmu.lbr_nr * sizeof(struct pebs_lbr_entry);
+               sz += x86_pmu.lbr_nr * sizeof(struct lbr_entry);
 
        cpuc->pebs_record_size = sz;
 }
@@ -1595,10 +1595,10 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
        }
 
        if (format_size & PEBS_DATACFG_LBRS) {
-               struct pebs_lbr *lbr = next_record;
+               struct lbr_entry *lbr = next_record;
                int num_lbr = ((format_size >> PEBS_DATACFG_LBR_SHIFT)
                                        & 0xff) + 1;
-               next_record = next_record + num_lbr*sizeof(struct pebs_lbr_entry);
+               next_record = next_record + num_lbr * sizeof(struct lbr_entry);
 
                if (has_branch_stack(event)) {
                        intel_pmu_store_pebs_lbrs(lbr);

diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 7742562..b8baaf1 100644 (file)
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -372,11 +372,11 @@ void intel_pmu_lbr_restore(void *ctx)
        mask = x86_pmu.lbr_nr - 1;
        for (i = 0; i < task_ctx->valid_lbrs; i++) {
                lbr_idx = (tos - i) & mask;
-               wrlbr_from(lbr_idx, task_ctx->lbr_from[i]);
-               wrlbr_to  (lbr_idx, task_ctx->lbr_to[i]);
+               wrlbr_from(lbr_idx, task_ctx->lbr[i].from);
+               wrlbr_to(lbr_idx, task_ctx->lbr[i].to);
 
                if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
-                       wrmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
+                       wrmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr[i].info);
        }
 
        for (; i < x86_pmu.lbr_nr; i++) {
@@ -440,10 +440,10 @@ void intel_pmu_lbr_save(void *ctx)
                from = rdlbr_from(lbr_idx);
                if (!from)
                        break;
-               task_ctx->lbr_from[i] = from;
-               task_ctx->lbr_to[i]   = rdlbr_to(lbr_idx);
+               task_ctx->lbr[i].from = from;
+               task_ctx->lbr[i].to = rdlbr_to(lbr_idx);
                if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
-                       rdmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
+                       rdmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr[i].info);
        }
        task_ctx->valid_lbrs = i;
        task_ctx->tos = tos;
@@ -1179,7 +1179,7 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc)
        }
 }
 
-void intel_pmu_store_pebs_lbrs(struct pebs_lbr *lbr)
+void intel_pmu_store_pebs_lbrs(struct lbr_entry *lbr)
 {
        struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
        int i;
@@ -1193,11 +1193,11 @@ void intel_pmu_store_pebs_lbrs(struct pebs_lbr *lbr)
                cpuc->lbr_stack.hw_idx = intel_pmu_lbr_tos();
 
        for (i = 0; i < x86_pmu.lbr_nr; i++) {
-               u64 info = lbr->lbr[i].info;
+               u64 info = lbr[i].info;
                struct perf_branch_entry *e = &cpuc->lbr_entries[i];
 
-               e->from         = lbr->lbr[i].from;
-               e->to           = lbr->lbr[i].to;
+               e->from         = lbr[i].from;
+               e->to           = lbr[i].to;
                e->mispred      = !!(info & LBR_INFO_MISPRED);
                e->predicted    = !(info & LBR_INFO_MISPRED);
                e->in_tx        = !!(info & LBR_INFO_IN_TX);

diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index ba89e56..aaa426d 100644 (file)
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -765,13 +765,11 @@ struct x86_perf_task_context_opt {
 };
 
 struct x86_perf_task_context {
-       u64 lbr_from[MAX_LBR_ENTRIES];
-       u64 lbr_to[MAX_LBR_ENTRIES];
-       u64 lbr_info[MAX_LBR_ENTRIES];
        u64 lbr_sel;
        int tos;
        int valid_lbrs;
        struct x86_perf_task_context_opt opt;
+       struct lbr_entry lbr[MAX_LBR_ENTRIES];
 };
 
 #define x86_add_quirk(func_)                                           \
@@ -1092,7 +1090,7 @@ void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in);
 
 void intel_pmu_auto_reload_read(struct perf_event *event);
 
-void intel_pmu_store_pebs_lbrs(struct pebs_lbr *lbr);
+void intel_pmu_store_pebs_lbrs(struct lbr_entry *lbr);
 
 void intel_ds_init(void);
 

diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 9ffce7d..2e29558 100644 (file)
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -282,14 +282,10 @@ struct pebs_xmm {
        u64 xmm[16*2];  /* two entries for each register */
 };
 
-struct pebs_lbr_entry {
+struct lbr_entry {
        u64 from, to, info;
 };
 
-struct pebs_lbr {
-       struct pebs_lbr_entry lbr[0]; /* Variable length */
-};
-
 /*
  * IBS cpuid feature detection
  */