perf/x86: Fix data source encoding issues for load latency/precise store

This patch fixes issues introuduce by Andi's previous patch 'Revamp PEBS'
series.

This patch fixes the following:

 - precise_store_data_hsw() encode the mem op type whenever we can
 - precise_store_data_hsw set the default data source correctly

 - 0 is not a valid init value for data source. Define PERF_MEM_NA as the
   default value

This bug was actually introduced by

    commit 722e76e60f2775c21b087ff12c5e678cf0ebcaaf
    Author: Stephane Eranian <eranian@google.com>
    Date:   Thu May 15 17:56:44 2014 +0200

        fix Haswell precise store data source encoding

Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1407785233-32193-4-git-send-email-eranian@google.com
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: ak@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index a9b60f32064fa24a9e4b179da0ddb04f0b5f24c2..67919ce0f76aa868fcaa059871494ef2810c674f 100644 (file)
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -113,9 +113,12 @@ static u64 precise_store_data_hsw(struct perf_event *event, u64 status)
        union perf_mem_data_src dse;
        u64 cfg = event->hw.config & INTEL_ARCH_EVENT_MASK;
 
-       dse.val = 0;
-       dse.mem_op = PERF_MEM_OP_NA;
-       dse.mem_lvl = PERF_MEM_LVL_NA;
+       dse.val = PERF_MEM_NA;
+
+       if (event->hw.flags & PERF_X86_EVENT_PEBS_ST_HSW)
+               dse.mem_op = PERF_MEM_OP_STORE;
+       else if (event->hw.flags & PERF_X86_EVENT_PEBS_LD_HSW)
+               dse.mem_op = PERF_MEM_OP_LOAD;
 
        /*
         * L1 info only valid for following events:
@@ -126,7 +129,7 @@ static u64 precise_store_data_hsw(struct perf_event *event, u64 status)
         * MEM_UOPS_RETIRED.ALL_STORES
         */
        if (cfg != 0x12d0 && cfg != 0x22d0 && cfg != 0x42d0 && cfg != 0x82d0)
-               return dse.mem_lvl;
+               return dse.val;
 
        if (status & 1)
                dse.mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_HIT;

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index ef5b62bdb103c7fbbc80397b6bf8a67ba88f2ce6..f0a1036b191198cbffdc07d66fc05e74a05c5af2 100644 (file)
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -608,6 +608,13 @@ struct perf_sample_data {
        u64                             txn;
 };
 
+/* default value for data source */
+#define PERF_MEM_NA (PERF_MEM_S(OP, NA)   |\
+                   PERF_MEM_S(LVL, NA)   |\
+                   PERF_MEM_S(SNOOP, NA) |\
+                   PERF_MEM_S(LOCK, NA)  |\
+                   PERF_MEM_S(TLB, NA))
+
 static inline void perf_sample_data_init(struct perf_sample_data *data,
                                         u64 addr, u64 period)
 {
@@ -620,7 +627,7 @@ static inline void perf_sample_data_init(struct perf_sample_data *data,
        data->regs_user.regs = NULL;
        data->stack_user_size = 0;
        data->weight = 0;
-       data->data_src.val = 0;
+       data->data_src.val = PERF_MEM_NA;
        data->txn = 0;
 }