powerpc/perf: Fix data source encodings for L2.1 and L3.1 accesses

Fix the data source encodings to represent L2.1/L3.1(another core's
L2/L3 on the same node) accesses properly for power10 and older
plaforms.

Add new macros(LEVEL/REM) which can be used to add mem_lvl_num and remote
field data inside perf_mem_data_src structure.

Result in power9 system with patch changes:

localhost:~/linux/tools/perf # ./perf mem report | grep Remote
     0.01%             1  252           Remote core, same node L3 or L3 hit  [.] 0x0000000000002dd0                producer_consumer   [.] 0x00007fff7f25eb90
anon               HitM          N/A                     No       N/A        0              0
     0.01%             1  220           Remote core, same node L3 or L3 hit  [.] 0x0000000000002dd0                producer_consumer   [.] 0x00007fff77776d90
anon               HitM          N/A                     No       N/A        0              0
     0.01%             1  220           Remote core, same node L3 or L3 hit  [.] 0x0000000000002dd0                producer_consumer   [.] 0x00007fff817d9410
anon               HitM          N/A                     No       N/A        0              0

Fixes: 79e96f8f930d ("powerpc/perf: Export memory hierarchy info to user space")
Signed-off-by: Kajol Jain <kjain@linux.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20211006140654.298352-5-kjain@linux.ibm.com

diff --git a/arch/powerpc/perf/isa207-common.c b/arch/powerpc/perf/isa207-common.c
index f92bf5f6b74f144ab612987779f79cb9b067776c..7ea873ab2e6f09a68cd17ec27a2b6bcebadb676e 100644 (file)
--- a/arch/powerpc/perf/isa207-common.c
+++ b/arch/powerpc/perf/isa207-common.c
@@ -238,11 +238,27 @@ static inline u64 isa207_find_source(u64 idx, u32 sub_idx)
                ret |= P(SNOOP, HIT);
                break;
        case 5:
-               ret = PH(LVL, REM_CCE1);
-               if ((sub_idx == 0) || (sub_idx == 2) || (sub_idx == 4))
-                       ret |= P(SNOOP, HIT);
-               else if ((sub_idx == 1) || (sub_idx == 3) || (sub_idx == 5))
-                       ret |= P(SNOOP, HITM);
+               if (cpu_has_feature(CPU_FTR_ARCH_31)) {
+                       ret = REM | P(HOPS, 0);
+
+                       if (sub_idx == 0 || sub_idx == 4)
+                               ret |= PH(LVL, L2) | LEVEL(L2) | P(SNOOP, HIT);
+                       else if (sub_idx == 1 || sub_idx == 5)
+                               ret |= PH(LVL, L2) | LEVEL(L2) | P(SNOOP, HITM);
+                       else if (sub_idx == 2 || sub_idx == 6)
+                               ret |= PH(LVL, L3) | LEVEL(L3) | P(SNOOP, HIT);
+                       else if (sub_idx == 3 || sub_idx == 7)
+                               ret |= PH(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM);
+               } else {
+                       if (sub_idx == 0)
+                               ret = PH(LVL, L2) | LEVEL(L2) | REM | P(SNOOP, HIT) | P(HOPS, 0);
+                       else if (sub_idx == 1)
+                               ret = PH(LVL, L2) | LEVEL(L2) | REM | P(SNOOP, HITM) | P(HOPS, 0);
+                       else if (sub_idx == 2 || sub_idx == 4)
+                               ret = PH(LVL, L3) | LEVEL(L3) | REM | P(SNOOP, HIT) | P(HOPS, 0);
+                       else if (sub_idx == 3 || sub_idx == 5)
+                               ret = PH(LVL, L3) | LEVEL(L3) | REM | P(SNOOP, HITM) | P(HOPS, 0);
+               }
                break;
        case 6:
                ret = PH(LVL, REM_CCE2);

diff --git a/arch/powerpc/perf/isa207-common.h b/arch/powerpc/perf/isa207-common.h
index 4a2cbc3dc047b817b2884c40894f766f52d3de63..ff122603989bdc131606672e524cb3d3064c0e57 100644 (file)
--- a/arch/powerpc/perf/isa207-common.h
+++ b/arch/powerpc/perf/isa207-common.h
@@ -273,6 +273,8 @@
 #define P(a, b)                                PERF_MEM_S(a, b)
 #define PH(a, b)                       (P(LVL, HIT) | P(a, b))
 #define PM(a, b)                       (P(LVL, MISS) | P(a, b))
+#define LEVEL(x)                       P(LVLNUM, x)
+#define REM                            P(REMOTE, REMOTE)
 
 int isa207_get_constraint(u64 event, unsigned long *maskp, unsigned long *valp, u64 event_config1);
 int isa207_compute_mmcr(u64 event[], int n_ev,