perf_counter: Add P6 PMU support
Add basic P6 PMU support. The P6 uses the EVNTSEL0 EN bit to enable/disable both its counters. We use this for the global enable/disable, and clear all config bits (except EN) to disable individual counters. Actual ia32 hardware doesn't support lfence, so use a locked op without side-effect to implement a full barrier. perf stat and perf record seem to function correctly. [a.p.zijlstra@chello.nl: cleanups and complete the enable/disable code] Signed-off-by: Vince Weaver <vince@deater.net> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <Pine.LNX.4.64.0907081718450.2715@pianoman.cluster.toy> Signed-off-by: Ingo Molnar <mingo@elte.hu>
This commit is contained in:
Vince Weaver
Ingo Molnar
parent
9590b7ba3f
commit
11d1578f94
|
|
@ -65,6 +65,44 @@ static DEFINE_PER_CPU(struct cpu_hw_counters, cpu_hw_counters) = {
|
|||
.enabled = 1,
|
||||
};
|
||||
|
||||
/*
|
||||
* Not sure about some of these
|
||||
*/
|
||||
static const u64 p6_perfmon_event_map[] =
|
||||
{
|
||||
[PERF_COUNT_HW_CPU_CYCLES] = 0x0079,
|
||||
[PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0,
|
||||
[PERF_COUNT_HW_CACHE_REFERENCES] = 0x0000,
|
||||
[PERF_COUNT_HW_CACHE_MISSES] = 0x0000,
|
||||
[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c4,
|
||||
[PERF_COUNT_HW_BRANCH_MISSES] = 0x00c5,
|
||||
[PERF_COUNT_HW_BUS_CYCLES] = 0x0062,
|
||||
};
|
||||
|
||||
static u64 p6_pmu_event_map(int event)
|
||||
{
|
||||
return p6_perfmon_event_map[event];
|
||||
}
|
||||
|
||||
static u64 p6_pmu_raw_event(u64 event)
|
||||
{
|
||||
#define P6_EVNTSEL_EVENT_MASK 0x000000FFULL
|
||||
#define P6_EVNTSEL_UNIT_MASK 0x0000FF00ULL
|
||||
#define P6_EVNTSEL_EDGE_MASK 0x00040000ULL
|
||||
#define P6_EVNTSEL_INV_MASK 0x00800000ULL
|
||||
#define P6_EVNTSEL_COUNTER_MASK 0xFF000000ULL
|
||||
|
||||
#define P6_EVNTSEL_MASK \
|
||||
(P6_EVNTSEL_EVENT_MASK | \
|
||||
P6_EVNTSEL_UNIT_MASK | \
|
||||
P6_EVNTSEL_EDGE_MASK | \
|
||||
P6_EVNTSEL_INV_MASK | \
|
||||
P6_EVNTSEL_COUNTER_MASK)
|
||||
|
||||
return event & P6_EVNTSEL_MASK;
|
||||
}
|
||||
|
||||
|
||||
/*
|
||||
* Intel PerfMon v3. Used on Core2 and later.
|
||||
*/
|
||||
|
|
@ -726,6 +764,23 @@ static int __hw_perf_counter_init(struct perf_counter *counter)
|
|||
return 0;
|
||||
}
|
||||
|
||||
static void p6_pmu_disable_all(void)
|
||||
{
|
||||
struct cpu_hw_counters *cpuc = &__get_cpu_var(cpu_hw_counters);
|
||||
unsigned long val;
|
||||
|
||||
if (!cpuc->enabled)
|
||||
return;
|
||||
|
||||
cpuc->enabled = 0;
|
||||
barrier();
|
||||
|
||||
/* p6 only has one enable register */
|
||||
rdmsrl(MSR_P6_EVNTSEL0, val);
|
||||
val &= ~ARCH_PERFMON_EVENTSEL0_ENABLE;
|
||||
wrmsrl(MSR_P6_EVNTSEL0, val);
|
||||
}
|
||||
|
||||
static void intel_pmu_disable_all(void)
|
||||
{
|
||||
wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0);
|
||||
|
|
@ -767,6 +822,23 @@ void hw_perf_disable(void)
|
|||
return x86_pmu.disable_all();
|
||||
}
|
||||
|
||||
static void p6_pmu_enable_all(void)
|
||||
{
|
||||
struct cpu_hw_counters *cpuc = &__get_cpu_var(cpu_hw_counters);
|
||||
unsigned long val;
|
||||
|
||||
if (cpuc->enabled)
|
||||
return;
|
||||
|
||||
cpuc->enabled = 1;
|
||||
barrier();
|
||||
|
||||
/* p6 only has one enable register */
|
||||
rdmsrl(MSR_P6_EVNTSEL0, val);
|
||||
val |= ARCH_PERFMON_EVENTSEL0_ENABLE;
|
||||
wrmsrl(MSR_P6_EVNTSEL0, val);
|
||||
}
|
||||
|
||||
static void intel_pmu_enable_all(void)
|
||||
{
|
||||
wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, x86_pmu.intel_ctrl);
|
||||
|
|
@ -819,16 +891,13 @@ static inline void intel_pmu_ack_status(u64 ack)
|
|||
|
||||
static inline void x86_pmu_enable_counter(struct hw_perf_counter *hwc, int idx)
|
||||
{
|
||||
int err;
|
||||
err = checking_wrmsrl(hwc->config_base + idx,
|
||||
(void)checking_wrmsrl(hwc->config_base + idx,
|
||||
hwc->config | ARCH_PERFMON_EVENTSEL0_ENABLE);
|
||||
}
|
||||
|
||||
static inline void x86_pmu_disable_counter(struct hw_perf_counter *hwc, int idx)
|
||||
{
|
||||
int err;
|
||||
err = checking_wrmsrl(hwc->config_base + idx,
|
||||
hwc->config);
|
||||
(void)checking_wrmsrl(hwc->config_base + idx, hwc->config);
|
||||
}
|
||||
|
||||
static inline void
|
||||
|
|
@ -836,13 +905,24 @@ intel_pmu_disable_fixed(struct hw_perf_counter *hwc, int __idx)
|
|||
{
|
||||
int idx = __idx - X86_PMC_IDX_FIXED;
|
||||
u64 ctrl_val, mask;
|
||||
int err;
|
||||
|
||||
mask = 0xfULL << (idx * 4);
|
||||
|
||||
rdmsrl(hwc->config_base, ctrl_val);
|
||||
ctrl_val &= ~mask;
|
||||
err = checking_wrmsrl(hwc->config_base, ctrl_val);
|
||||
(void)checking_wrmsrl(hwc->config_base, ctrl_val);
|
||||
}
|
||||
|
||||
static inline void
|
||||
p6_pmu_disable_counter(struct hw_perf_counter *hwc, int idx)
|
||||
{
|
||||
struct cpu_hw_counters *cpuc = &__get_cpu_var(cpu_hw_counters);
|
||||
unsigned long val = ARCH_PERFMON_EVENTSEL0_ENABLE;
|
||||
|
||||
if (!cpuc->enabled)
|
||||
val = 0;
|
||||
|
||||
(void)checking_wrmsrl(hwc->config_base + idx, val);
|
||||
}
|
||||
|
||||
static inline void
|
||||
|
|
@ -943,6 +1023,17 @@ intel_pmu_enable_fixed(struct hw_perf_counter *hwc, int __idx)
|
|||
err = checking_wrmsrl(hwc->config_base, ctrl_val);
|
||||
}
|
||||
|
||||
static void p6_pmu_enable_counter(struct hw_perf_counter *hwc, int idx)
|
||||
{
|
||||
struct cpu_hw_counters *cpuc = &__get_cpu_var(cpu_hw_counters);
|
||||
|
||||
if (cpuc->enabled)
|
||||
x86_pmu_enable_counter(hwc, idx);
|
||||
else
|
||||
x86_pmu_disable_counter(hwc, idx);
|
||||
}
|
||||
|
||||
|
||||
static void intel_pmu_enable_counter(struct hw_perf_counter *hwc, int idx)
|
||||
{
|
||||
if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
|
||||
|
|
@ -1176,6 +1267,49 @@ static void intel_pmu_reset(void)
|
|||
local_irq_restore(flags);
|
||||
}
|
||||
|
||||
static int p6_pmu_handle_irq(struct pt_regs *regs)
|
||||
{
|
||||
struct perf_sample_data data;
|
||||
struct cpu_hw_counters *cpuc;
|
||||
struct perf_counter *counter;
|
||||
struct hw_perf_counter *hwc;
|
||||
int idx, handled = 0;
|
||||
u64 val;
|
||||
|
||||
data.regs = regs;
|
||||
data.addr = 0;
|
||||
|
||||
cpuc = &__get_cpu_var(cpu_hw_counters);
|
||||
|
||||
for (idx = 0; idx < x86_pmu.num_counters; idx++) {
|
||||
if (!test_bit(idx, cpuc->active_mask))
|
||||
continue;
|
||||
|
||||
counter = cpuc->counters[idx];
|
||||
hwc = &counter->hw;
|
||||
|
||||
val = x86_perf_counter_update(counter, hwc, idx);
|
||||
if (val & (1ULL << (x86_pmu.counter_bits - 1)))
|
||||
continue;
|
||||
|
||||
/*
|
||||
* counter overflow
|
||||
*/
|
||||
handled = 1;
|
||||
data.period = counter->hw.last_period;
|
||||
|
||||
if (!x86_perf_counter_set_period(counter, hwc, idx))
|
||||
continue;
|
||||
|
||||
if (perf_counter_overflow(counter, 1, &data))
|
||||
p6_pmu_disable_counter(hwc, idx);
|
||||
}
|
||||
|
||||
if (handled)
|
||||
inc_irq_stat(apic_perf_irqs);
|
||||
|
||||
return handled;
|
||||
}
|
||||
|
||||
/*
|
||||
* This handler is triggered by the local APIC, so the APIC IRQ handling
|
||||
|
|
@ -1185,14 +1319,13 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
|
|||
{
|
||||
struct perf_sample_data data;
|
||||
struct cpu_hw_counters *cpuc;
|
||||
int bit, cpu, loops;
|
||||
int bit, loops;
|
||||
u64 ack, status;
|
||||
|
||||
data.regs = regs;
|
||||
data.addr = 0;
|
||||
|
||||
cpu = smp_processor_id();
|
||||
cpuc = &per_cpu(cpu_hw_counters, cpu);
|
||||
cpuc = &__get_cpu_var(cpu_hw_counters);
|
||||
|
||||
perf_disable();
|
||||
status = intel_pmu_get_status();
|
||||
|
|
@ -1249,14 +1382,13 @@ static int amd_pmu_handle_irq(struct pt_regs *regs)
|
|||
struct cpu_hw_counters *cpuc;
|
||||
struct perf_counter *counter;
|
||||
struct hw_perf_counter *hwc;
|
||||
int cpu, idx, handled = 0;
|
||||
int idx, handled = 0;
|
||||
u64 val;
|
||||
|
||||
data.regs = regs;
|
||||
data.addr = 0;
|
||||
|
||||
cpu = smp_processor_id();
|
||||
cpuc = &per_cpu(cpu_hw_counters, cpu);
|
||||
cpuc = &__get_cpu_var(cpu_hw_counters);
|
||||
|
||||
for (idx = 0; idx < x86_pmu.num_counters; idx++) {
|
||||
if (!test_bit(idx, cpuc->active_mask))
|
||||
|
|
@ -1353,6 +1485,32 @@ static __read_mostly struct notifier_block perf_counter_nmi_notifier = {
|
|||
.priority = 1
|
||||
};
|
||||
|
||||
static struct x86_pmu p6_pmu = {
|
||||
.name = "p6",
|
||||
.handle_irq = p6_pmu_handle_irq,
|
||||
.disable_all = p6_pmu_disable_all,
|
||||
.enable_all = p6_pmu_enable_all,
|
||||
.enable = p6_pmu_enable_counter,
|
||||
.disable = p6_pmu_disable_counter,
|
||||
.eventsel = MSR_P6_EVNTSEL0,
|
||||
.perfctr = MSR_P6_PERFCTR0,
|
||||
.event_map = p6_pmu_event_map,
|
||||
.raw_event = p6_pmu_raw_event,
|
||||
.max_events = ARRAY_SIZE(p6_perfmon_event_map),
|
||||
.max_period = (1ULL << 31) - 1,
|
||||
.version = 0,
|
||||
.num_counters = 2,
|
||||
/*
|
||||
* Counters have 40 bits implemented. However they are designed such
|
||||
* that bits [32-39] are sign extensions of bit 31. As such the
|
||||
* effective width of a counter for P6-like PMU is 32 bits only.
|
||||
*
|
||||
* See IA-32 Intel Architecture Software developer manual Vol 3B
|
||||
*/
|
||||
.counter_bits = 32,
|
||||
.counter_mask = (1ULL << 32) - 1,
|
||||
};
|
||||
|
||||
static struct x86_pmu intel_pmu = {
|
||||
.name = "Intel",
|
||||
.handle_irq = intel_pmu_handle_irq,
|
||||
|
|
@ -1392,6 +1550,41 @@ static struct x86_pmu amd_pmu = {
|
|||
.max_period = (1ULL << 47) - 1,
|
||||
};
|
||||
|
||||
static int p6_pmu_init(void)
|
||||
{
|
||||
int high, low;
|
||||
|
||||
switch (boot_cpu_data.x86_model) {
|
||||
case 1:
|
||||
case 3: /* Pentium Pro */
|
||||
case 5:
|
||||
case 6: /* Pentium II */
|
||||
case 7:
|
||||
case 8:
|
||||
case 11: /* Pentium III */
|
||||
break;
|
||||
case 9:
|
||||
case 13:
|
||||
/* for Pentium M, we need to check if PMU exist */
|
||||
rdmsr(MSR_IA32_MISC_ENABLE, low, high);
|
||||
if (low & MSR_IA32_MISC_ENABLE_EMON)
|
||||
break;
|
||||
default:
|
||||
pr_cont("unsupported p6 CPU model %d ",
|
||||
boot_cpu_data.x86_model);
|
||||
return -ENODEV;
|
||||
}
|
||||
|
||||
if (!cpu_has_apic) {
|
||||
pr_info("no Local APIC, try rebooting with lapic");
|
||||
return -ENODEV;
|
||||
}
|
||||
|
||||
x86_pmu = p6_pmu;
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
static int intel_pmu_init(void)
|
||||
{
|
||||
union cpuid10_edx edx;
|
||||
|
|
@ -1400,8 +1593,14 @@ static int intel_pmu_init(void)
|
|||
unsigned int ebx;
|
||||
int version;
|
||||
|
||||
if (!cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON))
|
||||
if (!cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) {
|
||||
/* check for P6 processor family */
|
||||
if (boot_cpu_data.x86 == 6) {
|
||||
return p6_pmu_init();
|
||||
} else {
|
||||
return -ENODEV;
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
* Check whether the Architectural PerfMon supports
|
||||
|
|
|
|||
|
|
@ -1,7 +1,13 @@
|
|||
#ifndef _PERF_PERF_H
|
||||
#define _PERF_PERF_H
|
||||
|
||||
#if defined(__x86_64__) || defined(__i386__)
|
||||
#if defined(__i386__)
|
||||
#include "../../arch/x86/include/asm/unistd.h"
|
||||
#define rmb() asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
|
||||
#define cpu_relax() asm volatile("rep; nop" ::: "memory");
|
||||
#endif
|
||||
|
||||
#if defined(__x86_64__)
|
||||
#include "../../arch/x86/include/asm/unistd.h"
|
||||
#define rmb() asm volatile("lfence" ::: "memory")
|
||||
#define cpu_relax() asm volatile("rep; nop" ::: "memory");
|
||||
|
|
|
|||
Loading…
Reference in New Issue