summary refs log tree commit diff
path: root/arch/powerpc/perf
diff options
context:
space:
mode:
authorKajol Jain <kjain@linux.ibm.com>2021-12-06 14:47:48 +0530
committerMichael Ellerman <mpe@ellerman.id.au>2021-12-16 21:31:44 +1100
commit4a20ee106154ac1765dea97932faad29f0ba57fc (patch)
treedb44976d6cb7674740d6887be2bd2fe8aa4e46e6 /arch/powerpc/perf
parentcb1c4aba055f928ffae0c868e8dfe08eeab302e7 (diff)
downloadlinux-4a20ee106154ac1765dea97932faad29f0ba57fc.tar.gz
powerpc/perf: Add encodings to represent data based on newer composite PERF_MEM_LVLNUM* fields
The code represent data coming from L1/L2/L3 cache hits based on
PERF_MEM_LVL_* namespace, which is in the process of deprecation in
the favour of newer composite PERF_MEM_{LVLNUM_,REMOTE_,SNOOPX_,HOPS_}
fields.

Add data source encodings to represent L1/L2/L3 cache hits based on
newer composite PERF_MEM_{LVLNUM_,REMOTE_,SNOOPX_,HOPS_} fields for
power10 and older platforms

Result in power9 system without patch changes:

localhost:# ./perf mem report --sort="mem,sym,dso" --stdio
 # Overhead       Samples  Memory access             Symbol                             Shared Object
 # ........  ............  ........................  .................................  ................
 #
    29.51%             1  L2 hit                    [k] perf_event_exec                [kernel.vmlinux]
    27.05%             1  L1 hit                    [k] perf_ctx_unlock                [kernel.vmlinux]
    13.93%             1  L1 hit                    [k] vtime_delta                    [kernel.vmlinux]
    13.11%             1  L1 hit                    [k] prepend_path.isra.11           [kernel.vmlinux]
     8.20%             1  L1 hit                    [.] 00000038.plt_call.__GI_strlen  libc-2.28.so
     8.20%             1  L1 hit                    [k] perf_event_interrupt           [kernel.vmlinux]

Result in power9 system with patch changes:

localhost:# ./perf mem report --sort="mem,sym,dso" --stdio
 # Overhead       Samples  Memory access             Symbol                      Shared Object
 # ........  ............  ........................  ..........................  ................
 #
    36.63%             1  L2 or L2 hit              [k] perf_event_exec         [kernel.vmlinux]
    25.50%             1  L1 or L1 hit              [k] vtime_delta             [kernel.vmlinux]
    13.12%             1  L1 or L1 hit              [k] unmap_region            [kernel.vmlinux]
    12.62%             1  L1 or L1 hit              [k] perf_sample_event_took  [kernel.vmlinux]
     6.93%             1  L1 or L1 hit              [k] perf_ctx_unlock         [kernel.vmlinux]
     5.20%             1  L1 or L1 hit              [.] __memcpy_power7         libc-2.28.so

Signed-off-by: Kajol Jain <kjain@linux.ibm.com>
Reviewed-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20211206091749.87585-4-kjain@linux.ibm.com

Diffstat (limited to 'arch/powerpc/perf')
-rw-r--r--arch/powerpc/perf/isa207-common.c6
1 files changed, 3 insertions, 3 deletions
diff --git a/arch/powerpc/perf/isa207-common.c b/arch/powerpc/perf/isa207-common.c
index 7ea873ab2e6f..6c6bc8b7d887 100644
--- a/arch/powerpc/perf/isa207-common.c
+++ b/arch/powerpc/perf/isa207-common.c
@@ -220,13 +220,13 @@ static inline u64 isa207_find_source(u64 idx, u32 sub_idx)
 		/* Nothing to do */
 		break;
 	case 1:
-		ret = PH(LVL, L1);
+		ret = PH(LVL, L1) | LEVEL(L1) | P(SNOOP, HIT);
 		break;
 	case 2:
-		ret = PH(LVL, L2);
+		ret = PH(LVL, L2) | LEVEL(L2) | P(SNOOP, HIT);
 		break;
 	case 3:
-		ret = PH(LVL, L3);
+		ret = PH(LVL, L3) | LEVEL(L3) | P(SNOOP, HIT);
 		break;
 	case 4:
 		if (sub_idx <= 1)