[Top][All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Qemu-devel] [patch] performance counters from inside of Qemu
From: |
Vince Weaver |
Subject: |
[Qemu-devel] [patch] performance counters from inside of Qemu |
Date: |
Thu, 4 Nov 2010 15:20:43 -0400 (EDT) |
User-agent: |
Alpine 2.02 (DEB 1266 2009-07-14) |
Hello
The following patch enables simulated perf event support inside of Qemu
for x86_64 systems. It enables support for the AMD performance MSRs enough
to return values for the "retired_instructions" (both user and kernel) and
"cpu_clk_unhalted" events.
This is mostly a proof of concept, I'm not sure if anyone is interested in
this. It could in theory be useful for tracking down performance problems
from iside of Qemu using existing tools.
The main missing component is lack of interrupts on counter overflow.
This is possible to implement, I just haven't.
The eventual goal of my group is to enable performance counter support
inside of KVM, but I was experimenting using Qemu first.
Usage:
* Apply the patch
* Boot into Qemu, using a kernel using 2.6.32 or newer.
Use the "-cpu phenom" option to select an AMD machine.
* Use the "perf" utility (or other method of accessing perf counters,
such as PAPI) as you normally would.
Sample output using a benchmark that is exactly 1 million instructions
(it counts more due to kernel overhead):
address@hidden:~$ perf stat ./million
Performance counter stats for './million':
9.147038 task-clock-msecs # 0.635 CPUs
0 context-switches # 0.000 M/sec
0 CPU-migrations # 0.000 M/sec
2 page-faults # 0.000 M/sec
24990915 cycles # 2732.132 M/sec
1070162 instructions # 0.043 IPC
0 cache-references # 0.000 M/sec
0 cache-misses # 0.000 M/sec
0.014401652 seconds time elapsed
address@hidden:~$ exit
diff --git a/target-i386/cpu.h b/target-i386/cpu.h
index 2440d65..aac0efd 100644
--- a/target-i386/cpu.h
+++ b/target-i386/cpu.h
@@ -341,6 +341,16 @@
#define MSR_KERNELGSBASE 0xc0000102
#define MSR_TSC_AUX 0xc0000103
+#define MSR_PERFEVTSEL0 0xc0010000
+#define MSR_PERFEVTSEL1 0xc0010001
+#define MSR_PERFEVTSEL2 0xc0010002
+#define MSR_PERFEVTSEL3 0xc0010003
+
+#define MSR_PERFCTR0 0xc0010004
+#define MSR_PERFCTR1 0xc0010005
+#define MSR_PERFCTR2 0xc0010006
+#define MSR_PERFCTR3 0xc0010007
+
#define MSR_VM_HSAVE_PA 0xc0010117
/* cpuid_features bits */
diff --git a/target-i386/helper.c b/target-i386/helper.c
index 26ea1e5..f2aa2d7 100644
--- a/target-i386/helper.c
+++ b/target-i386/helper.c
@@ -31,6 +31,20 @@
//#define DEBUG_MMU
+long long global_ins_count[3] = {0,0,0};
+
+void helper_insn_count(unsigned int cpl);
+
+void helper_insn_count(unsigned int cpl) {
+ if (cpl==0) {
+ global_ins_count[1]++;
+ }
+ else if (cpl==3) {
+ global_ins_count[0]++;
+ }
+ /* FIXME -- handle overflow interrupts */
+}
+
/* NOTE: must be called outside the CPU execute loop */
void cpu_reset(CPUX86State *env)
{
diff --git a/target-i386/helper.h b/target-i386/helper.h
index 6b518ad..6739007 100644
--- a/target-i386/helper.h
+++ b/target-i386/helper.h
@@ -1,5 +1,7 @@
#include "def-helper.h"
+DEF_HELPER_1(insn_count, void, i32)
+
DEF_HELPER_FLAGS_1(cc_compute_all, TCG_CALL_PURE, i32, int)
DEF_HELPER_FLAGS_1(cc_compute_c, TCG_CALL_PURE, i32, int)
diff --git a/target-i386/op_helper.c b/target-i386/op_helper.c
index 43fbd0c..a80d875 100644
--- a/target-i386/op_helper.c
+++ b/target-i386/op_helper.c
@@ -3005,6 +3005,24 @@ void helper_rdmsr(void)
{
}
#else
+
+extern long long global_ins_count[3];
+
+static uint64_t perf_msrs[8];
+
+static struct counter_info_t {
+ int enabled;
+ long long last_value;
+ int umask;
+ int emask;
+ int os;
+ int usr;
+} counter_info[4];
+
+#define PERF_ENABLED 1ULL<<22
+#define PERF_USR 1ULL<<16
+#define PERF_OS 1ULL<<17
+
void helper_wrmsr(void)
{
uint64_t val;
@@ -3126,6 +3144,88 @@ void helper_wrmsr(void)
case MSR_TSC_AUX:
env->tsc_aux = val;
break;
+ case MSR_PERFEVTSEL0:
+ case MSR_PERFEVTSEL1:
+ case MSR_PERFEVTSEL2:
+ case MSR_PERFEVTSEL3:
+ {
+ int enable;
+ int umask,emask,usr,os;
+ int counter=(int)ECX&0x7;
+
+ emask=val&0xff;
+ umask=(val>>8)&0xff;
+ enable=!!(val&PERF_ENABLED);
+ usr=!!(val&PERF_USR);
+ os=!!(val&PERF_OS);
+
+ if (enable) {
+ counter_info[counter].emask=emask;
+ counter_info[counter].umask=umask;
+ counter_info[counter].enabled=1;
+ counter_info[counter].last_value=0;
+
+ /* retired instructions */
+ if (emask==0xc0) {
+ if (usr) {
+ counter_info[counter].last_value+=global_ins_count[0];
+ }
+ counter_info[counter].usr=usr;
+
+ if (os) {
+ counter_info[counter].last_value+=global_ins_count[1];
+ }
+ counter_info[counter].os=os;
+ }
+ /* cycles */
+ else if (emask==0x76) {
+ counter_info[counter].last_value=
+ (cpu_get_tsc(env)+env->tsc_offset);
+ }
+ else {
+ }
+
+ }
+ else {
+ if (counter_info[counter].enabled) {
+ long long new_count=0;
+
+ /* retired isntructions */
+ if (counter_info[counter].emask==0xc0) {
+ if (counter_info[counter].usr) {
+ new_count+=global_ins_count[0];
+ }
+ if (counter_info[counter].os) {
+ new_count+=global_ins_count[1];
+ }
+
+ perf_msrs[(ECX&0x7)+4]+=new_count-
+ counter_info[counter].last_value;
+ }
+ /* cycles */
+ else if (counter_info[counter].emask==0x76) {
+ new_count=(cpu_get_tsc(env)+env->tsc_offset);
+ perf_msrs[(ECX&0x7)+4]+=new_count-
+ counter_info[counter].last_value;
+ }
+ else {
+ }
+ }
+
+ counter_info[counter].enabled=0;
+
+ }
+ }
+ perf_msrs[ECX&0x7]=val;
+ break;
+
+ case MSR_PERFCTR0:
+ case MSR_PERFCTR1:
+ case MSR_PERFCTR2:
+ case MSR_PERFCTR3:
+ perf_msrs[ECX&0x7]=val;
+ break;
+
default:
if ((uint32_t)ECX >= MSR_MC0_CTL
&& (uint32_t)ECX < MSR_MC0_CTL + (4 * env->mcg_cap & 0xff)) {
@@ -3259,6 +3359,49 @@ void helper_rdmsr(void)
case MSR_MCG_STATUS:
val = env->mcg_status;
break;
+ case MSR_PERFEVTSEL0:
+ case MSR_PERFEVTSEL1:
+ case MSR_PERFEVTSEL2:
+ case MSR_PERFEVTSEL3:
+ val=perf_msrs[ECX&0x7];
+ break;
+
+ case MSR_PERFCTR0:
+ case MSR_PERFCTR1:
+ case MSR_PERFCTR2:
+ case MSR_PERFCTR3:
+ {
+ int counter=(ECX&0x7)-4;
+ long long value=0;
+
+ if ( counter_info[counter].enabled ) {
+
+ /* retired instructions */
+ if (counter_info[counter].emask==0xc0) {
+ if (counter_info[counter].usr) {
+ value+=global_ins_count[0];
+ }
+ if (counter_info[counter].os) {
+ value+=global_ins_count[1];
+ }
+ val=perf_msrs[ECX&0x7]+
+ (value-counter_info[counter].last_value);
+ }
+ /* cycles */
+ else if (counter_info[counter].emask==0x76) {
+ val=perf_msrs[ECX&0x7]+
+ ((cpu_get_tsc(env)+env->tsc_offset)-
+ counter_info[counter].last_value);
+
+ }
+ else {
+ val=perf_msrs[ECX&0x7];
+ }
+ } else { /* counter was disabled */
+ val=perf_msrs[ECX&0x7];
+ }
+ }
+ break;
default:
if ((uint32_t)ECX >= MSR_MC0_CTL
&& (uint32_t)ECX < MSR_MC0_CTL + (4 * env->mcg_cap & 0xff)) {
diff --git a/target-i386/translate.c b/target-i386/translate.c
index 7b6e3c2..1d8f95e 100644
--- a/target-i386/translate.c
+++ b/target-i386/translate.c
@@ -4215,6 +4215,15 @@ static target_ulong disas_insn(DisasContext *s,
target_ulong pc_start)
if (prefixes & PREFIX_LOCK)
gen_helper_lock();
+ {
+ /* vmw */
+ TCGv const1;
+
+ const1 = tcg_const_i32(s->cpl);
+ gen_helper_insn_count(const1);
+ tcg_temp_free(const1);
+ }
+
/* now check op code */
reswitch:
switch(b) {
- [Qemu-devel] [patch] performance counters from inside of Qemu,
Vince Weaver <=