perf tools: Make Power7 events available for perf
Power7 supports over 530 different perf events but only a small subset
of these can be specified by name, for the remaining events, we must
specify them by their raw code:
perf stat -e r2003c <application>
This patch makes all the POWER7 events available in sysfs. So we can
instead specify these as:
perf stat -e 'cpu/PM_CMPLU_STALL_DFU/' <application>
where PM_CMPLU_STALL_DFU is the r2003c in previous example.
Before this patch is applied, the size of power7-pmu.o is:
$ size arch/powerpc/perf/power7-pmu.o
text data bss dec hex filename
3073 2720 0 5793 16a1 arch/powerpc/perf/power7-pmu.o
and after the patch is applied, it is:
$ size arch/powerpc/perf/power7-pmu.o
text data bss dec hex filename
15950 31112 0 47062 b7d6 arch/powerpc/perf/power7-pmu.o
For the run time overhead, I use two scripts, one is "event_name.sh",
which contains 50 event names, it looks like:
# ./perf record -e 'cpu/PM_CMPLU_STALL_DFU/' -e ..... /bin/sleep 1
the other one is named "event_code.sh" which use corresponding events
raw
code instead of events names, it looks like:
# ./perf record -e r2003c -e ...... /bin/sleep 1
below is the result.
Using events name:
[root@localhost perf]# time ./event_name.sh
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.002 MB perf.data (~102 samples) ]
real 0m1.192s
user 0m0.028s
sys 0m0.106s
Using events raw code:
[root@localhost perf]# time ./event_code.sh
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.003 MB perf.data (~112 samples) ]
real 0m1.198s
user 0m0.028s
sys 0m0.105s
Signed-off-by: Runzhen Wang <runzhen@linux.vnet.ibm.com>
Acked-by: Michael Ellerman <michael@ellerman.id.au>
Cc: icycoder@gmail.com
Cc: linuxppc-dev@lists.ozlabs.org
Cc: Michael Ellerman <michael@ellerman.id.au>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Runzhen Wang <runzhew@clemson.edu>
Cc: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Cc: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/1372407297-6996-3-git-send-email-runzhen@linux.vnet.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
diff --git a/arch/powerpc/perf/power7-pmu.c b/arch/powerpc/perf/power7-pmu.c
index d1821b8..56c67bc 100644
--- a/arch/powerpc/perf/power7-pmu.c
+++ b/arch/powerpc/perf/power7-pmu.c
@@ -53,37 +53,13 @@
/*
* Power7 event codes.
*/
-#define PME_PM_CYC 0x1e
-#define PME_PM_GCT_NOSLOT_CYC 0x100f8
-#define PME_PM_CMPLU_STALL 0x4000a
-#define PME_PM_INST_CMPL 0x2
-#define PME_PM_LD_REF_L1 0xc880
-#define PME_PM_LD_MISS_L1 0x400f0
-#define PME_PM_BRU_FIN 0x10068
-#define PME_PM_BR_MPRED 0x400f6
+#define EVENT(_name, _code) \
+ PME_##_name = _code,
-#define PME_PM_CMPLU_STALL_FXU 0x20014
-#define PME_PM_CMPLU_STALL_DIV 0x40014
-#define PME_PM_CMPLU_STALL_SCALAR 0x40012
-#define PME_PM_CMPLU_STALL_SCALAR_LONG 0x20018
-#define PME_PM_CMPLU_STALL_VECTOR 0x2001c
-#define PME_PM_CMPLU_STALL_VECTOR_LONG 0x4004a
-#define PME_PM_CMPLU_STALL_LSU 0x20012
-#define PME_PM_CMPLU_STALL_REJECT 0x40016
-#define PME_PM_CMPLU_STALL_ERAT_MISS 0x40018
-#define PME_PM_CMPLU_STALL_DCACHE_MISS 0x20016
-#define PME_PM_CMPLU_STALL_STORE 0x2004a
-#define PME_PM_CMPLU_STALL_THRD 0x1001c
-#define PME_PM_CMPLU_STALL_IFU 0x4004c
-#define PME_PM_CMPLU_STALL_BRU 0x4004e
-#define PME_PM_GCT_NOSLOT_IC_MISS 0x2001a
-#define PME_PM_GCT_NOSLOT_BR_MPRED 0x4001a
-#define PME_PM_GCT_NOSLOT_BR_MPRED_IC_MISS 0x4001c
-#define PME_PM_GRP_CMPL 0x30004
-#define PME_PM_1PLUS_PPC_CMPL 0x100f2
-#define PME_PM_CMPLU_STALL_DFU 0x2003c
-#define PME_PM_RUN_CYC 0x200f4
-#define PME_PM_RUN_INST_CMPL 0x400fa
+enum {
+#include "power7-events-list.h"
+};
+#undef EVENT
/*
* Layout of constraint bits:
@@ -398,96 +374,36 @@
};
-GENERIC_EVENT_ATTR(cpu-cycles, CYC);
-GENERIC_EVENT_ATTR(stalled-cycles-frontend, GCT_NOSLOT_CYC);
-GENERIC_EVENT_ATTR(stalled-cycles-backend, CMPLU_STALL);
-GENERIC_EVENT_ATTR(instructions, INST_CMPL);
-GENERIC_EVENT_ATTR(cache-references, LD_REF_L1);
-GENERIC_EVENT_ATTR(cache-misses, LD_MISS_L1);
-GENERIC_EVENT_ATTR(branch-instructions, BRU_FIN);
-GENERIC_EVENT_ATTR(branch-misses, BR_MPRED);
+GENERIC_EVENT_ATTR(cpu-cycles, PM_CYC);
+GENERIC_EVENT_ATTR(stalled-cycles-frontend, PM_GCT_NOSLOT_CYC);
+GENERIC_EVENT_ATTR(stalled-cycles-backend, PM_CMPLU_STALL);
+GENERIC_EVENT_ATTR(instructions, PM_INST_CMPL);
+GENERIC_EVENT_ATTR(cache-references, PM_LD_REF_L1);
+GENERIC_EVENT_ATTR(cache-misses, PM_LD_MISS_L1);
+GENERIC_EVENT_ATTR(branch-instructions, PM_BRU_FIN);
+GENERIC_EVENT_ATTR(branch-misses, PM_BR_MPRED);
-POWER_EVENT_ATTR(CYC, CYC);
-POWER_EVENT_ATTR(GCT_NOSLOT_CYC, GCT_NOSLOT_CYC);
-POWER_EVENT_ATTR(CMPLU_STALL, CMPLU_STALL);
-POWER_EVENT_ATTR(INST_CMPL, INST_CMPL);
-POWER_EVENT_ATTR(LD_REF_L1, LD_REF_L1);
-POWER_EVENT_ATTR(LD_MISS_L1, LD_MISS_L1);
-POWER_EVENT_ATTR(BRU_FIN, BRU_FIN)
-POWER_EVENT_ATTR(BR_MPRED, BR_MPRED);
+#define EVENT(_name, _code) POWER_EVENT_ATTR(_name, _name);
+#include "power7-events-list.h"
+#undef EVENT
-POWER_EVENT_ATTR(CMPLU_STALL_FXU, CMPLU_STALL_FXU);
-POWER_EVENT_ATTR(CMPLU_STALL_DIV, CMPLU_STALL_DIV);
-POWER_EVENT_ATTR(CMPLU_STALL_SCALAR, CMPLU_STALL_SCALAR);
-POWER_EVENT_ATTR(CMPLU_STALL_SCALAR_LONG, CMPLU_STALL_SCALAR_LONG);
-POWER_EVENT_ATTR(CMPLU_STALL_VECTOR, CMPLU_STALL_VECTOR);
-POWER_EVENT_ATTR(CMPLU_STALL_VECTOR_LONG, CMPLU_STALL_VECTOR_LONG);
-POWER_EVENT_ATTR(CMPLU_STALL_LSU, CMPLU_STALL_LSU);
-POWER_EVENT_ATTR(CMPLU_STALL_REJECT, CMPLU_STALL_REJECT);
-
-POWER_EVENT_ATTR(CMPLU_STALL_ERAT_MISS, CMPLU_STALL_ERAT_MISS);
-POWER_EVENT_ATTR(CMPLU_STALL_DCACHE_MISS, CMPLU_STALL_DCACHE_MISS);
-POWER_EVENT_ATTR(CMPLU_STALL_STORE, CMPLU_STALL_STORE);
-POWER_EVENT_ATTR(CMPLU_STALL_THRD, CMPLU_STALL_THRD);
-POWER_EVENT_ATTR(CMPLU_STALL_IFU, CMPLU_STALL_IFU);
-POWER_EVENT_ATTR(CMPLU_STALL_BRU, CMPLU_STALL_BRU);
-POWER_EVENT_ATTR(GCT_NOSLOT_IC_MISS, GCT_NOSLOT_IC_MISS);
-
-POWER_EVENT_ATTR(GCT_NOSLOT_BR_MPRED, GCT_NOSLOT_BR_MPRED);
-POWER_EVENT_ATTR(GCT_NOSLOT_BR_MPRED_IC_MISS, GCT_NOSLOT_BR_MPRED_IC_MISS);
-POWER_EVENT_ATTR(GRP_CMPL, GRP_CMPL);
-POWER_EVENT_ATTR(1PLUS_PPC_CMPL, 1PLUS_PPC_CMPL);
-POWER_EVENT_ATTR(CMPLU_STALL_DFU, CMPLU_STALL_DFU);
-POWER_EVENT_ATTR(RUN_CYC, RUN_CYC);
-POWER_EVENT_ATTR(RUN_INST_CMPL, RUN_INST_CMPL);
+#define EVENT(_name, _code) POWER_EVENT_PTR(_name),
static struct attribute *power7_events_attr[] = {
- GENERIC_EVENT_PTR(CYC),
- GENERIC_EVENT_PTR(GCT_NOSLOT_CYC),
- GENERIC_EVENT_PTR(CMPLU_STALL),
- GENERIC_EVENT_PTR(INST_CMPL),
- GENERIC_EVENT_PTR(LD_REF_L1),
- GENERIC_EVENT_PTR(LD_MISS_L1),
- GENERIC_EVENT_PTR(BRU_FIN),
- GENERIC_EVENT_PTR(BR_MPRED),
+ GENERIC_EVENT_PTR(PM_CYC),
+ GENERIC_EVENT_PTR(PM_GCT_NOSLOT_CYC),
+ GENERIC_EVENT_PTR(PM_CMPLU_STALL),
+ GENERIC_EVENT_PTR(PM_INST_CMPL),
+ GENERIC_EVENT_PTR(PM_LD_REF_L1),
+ GENERIC_EVENT_PTR(PM_LD_MISS_L1),
+ GENERIC_EVENT_PTR(PM_BRU_FIN),
+ GENERIC_EVENT_PTR(PM_BR_MPRED),
- POWER_EVENT_PTR(CYC),
- POWER_EVENT_PTR(GCT_NOSLOT_CYC),
- POWER_EVENT_PTR(CMPLU_STALL),
- POWER_EVENT_PTR(INST_CMPL),
- POWER_EVENT_PTR(LD_REF_L1),
- POWER_EVENT_PTR(LD_MISS_L1),
- POWER_EVENT_PTR(BRU_FIN),
- POWER_EVENT_PTR(BR_MPRED),
-
- POWER_EVENT_PTR(CMPLU_STALL_FXU),
- POWER_EVENT_PTR(CMPLU_STALL_DIV),
- POWER_EVENT_PTR(CMPLU_STALL_SCALAR),
- POWER_EVENT_PTR(CMPLU_STALL_SCALAR_LONG),
- POWER_EVENT_PTR(CMPLU_STALL_VECTOR),
- POWER_EVENT_PTR(CMPLU_STALL_VECTOR_LONG),
- POWER_EVENT_PTR(CMPLU_STALL_LSU),
- POWER_EVENT_PTR(CMPLU_STALL_REJECT),
-
- POWER_EVENT_PTR(CMPLU_STALL_ERAT_MISS),
- POWER_EVENT_PTR(CMPLU_STALL_DCACHE_MISS),
- POWER_EVENT_PTR(CMPLU_STALL_STORE),
- POWER_EVENT_PTR(CMPLU_STALL_THRD),
- POWER_EVENT_PTR(CMPLU_STALL_IFU),
- POWER_EVENT_PTR(CMPLU_STALL_BRU),
- POWER_EVENT_PTR(GCT_NOSLOT_IC_MISS),
- POWER_EVENT_PTR(GCT_NOSLOT_BR_MPRED),
-
- POWER_EVENT_PTR(GCT_NOSLOT_BR_MPRED_IC_MISS),
- POWER_EVENT_PTR(GRP_CMPL),
- POWER_EVENT_PTR(1PLUS_PPC_CMPL),
- POWER_EVENT_PTR(CMPLU_STALL_DFU),
- POWER_EVENT_PTR(RUN_CYC),
- POWER_EVENT_PTR(RUN_INST_CMPL),
+ #include "power7-events-list.h"
+ #undef EVENT
NULL
};
-
static struct attribute_group power7_pmu_events_group = {
.name = "events",
.attrs = power7_events_attr,