#include <asm/nmi.h>
#include <asm/msr.h>
#include <asm/apic.h>
-
+
#include "op_counter.h"
#include "op_x86_model.h"
-static struct op_x86_model_spec const * model;
-static struct op_msrs cpu_msrs[NR_CPUS];
-static unsigned long saved_lvtpc[NR_CPUS];
+static struct op_x86_model_spec const *model;
+static DEFINE_PER_CPU(struct op_msrs, cpu_msrs);
+static DEFINE_PER_CPU(unsigned long, saved_lvtpc);
static int nmi_start(void);
static void nmi_stop(void);
return 0;
}
-
static int nmi_resume(struct sys_device *dev)
{
if (nmi_enabled == 1)
return 0;
}
-
static struct sysdev_class oprofile_sysclass = {
- set_kset_name("oprofile"),
+ .name = "oprofile",
.resume = nmi_resume,
.suspend = nmi_suspend,
};
-
static struct sys_device device_oprofile = {
.id = 0,
.cls = &oprofile_sysclass,
};
-
static int __init init_sysfs(void)
{
int error;
- if (!(error = sysdev_class_register(&oprofile_sysclass)))
+
+ error = sysdev_class_register(&oprofile_sysclass);
+ if (!error)
error = sysdev_register(&device_oprofile);
return error;
}
-
static void exit_sysfs(void)
{
sysdev_unregister(&device_oprofile);
int ret = NOTIFY_DONE;
int cpu = smp_processor_id();
- switch(val) {
+ switch (val) {
case DIE_NMI:
- if (model->check_ctrs(args->regs, &cpu_msrs[cpu]))
+ if (model->check_ctrs(args->regs, &per_cpu(cpu_msrs, cpu)))
ret = NOTIFY_STOP;
break;
default:
return ret;
}
-static void nmi_cpu_save_registers(struct op_msrs * msrs)
+static void nmi_cpu_save_registers(struct op_msrs *msrs)
{
unsigned int const nr_ctrs = model->num_counters;
- unsigned int const nr_ctrls = model->num_controls;
- struct op_msr * counters = msrs->counters;
- struct op_msr * controls = msrs->controls;
+ unsigned int const nr_ctrls = model->num_controls;
+ struct op_msr *counters = msrs->counters;
+ struct op_msr *controls = msrs->controls;
unsigned int i;
for (i = 0; i < nr_ctrs; ++i) {
- if (counters[i].addr){
+ if (counters[i].addr) {
rdmsr(counters[i].addr,
counters[i].saved.low,
counters[i].saved.high);
}
}
-
+
for (i = 0; i < nr_ctrls; ++i) {
- if (controls[i].addr){
+ if (controls[i].addr) {
rdmsr(controls[i].addr,
controls[i].saved.low,
controls[i].saved.high);
}
}
-
-static void nmi_save_registers(void * dummy)
+static void nmi_save_registers(void *dummy)
{
int cpu = smp_processor_id();
- struct op_msrs * msrs = &cpu_msrs[cpu];
+ struct op_msrs *msrs = &per_cpu(cpu_msrs, cpu);
nmi_cpu_save_registers(msrs);
}
-
static void free_msrs(void)
{
int i;
for_each_possible_cpu(i) {
- kfree(cpu_msrs[i].counters);
- cpu_msrs[i].counters = NULL;
- kfree(cpu_msrs[i].controls);
- cpu_msrs[i].controls = NULL;
+ kfree(per_cpu(cpu_msrs, i).counters);
+ per_cpu(cpu_msrs, i).counters = NULL;
+ kfree(per_cpu(cpu_msrs, i).controls);
+ per_cpu(cpu_msrs, i).controls = NULL;
}
}
-
static int allocate_msrs(void)
{
int success = 1;
int i;
for_each_possible_cpu(i) {
- cpu_msrs[i].counters = kmalloc(counters_size, GFP_KERNEL);
- if (!cpu_msrs[i].counters) {
+ per_cpu(cpu_msrs, i).counters = kmalloc(counters_size,
+ GFP_KERNEL);
+ if (!per_cpu(cpu_msrs, i).counters) {
success = 0;
break;
}
- cpu_msrs[i].controls = kmalloc(controls_size, GFP_KERNEL);
- if (!cpu_msrs[i].controls) {
+ per_cpu(cpu_msrs, i).controls = kmalloc(controls_size,
+ GFP_KERNEL);
+ if (!per_cpu(cpu_msrs, i).controls) {
success = 0;
break;
}
return success;
}
-
-static void nmi_cpu_setup(void * dummy)
+static void nmi_cpu_setup(void *dummy)
{
int cpu = smp_processor_id();
- struct op_msrs * msrs = &cpu_msrs[cpu];
+ struct op_msrs *msrs = &per_cpu(cpu_msrs, cpu);
spin_lock(&oprofilefs_lock);
model->setup_ctrs(msrs);
spin_unlock(&oprofilefs_lock);
- saved_lvtpc[cpu] = apic_read(APIC_LVTPC);
+ per_cpu(saved_lvtpc, cpu) = apic_read(APIC_LVTPC);
apic_write(APIC_LVTPC, APIC_DM_NMI);
}
static int nmi_setup(void)
{
- int err=0;
+ int err = 0;
int cpu;
if (!allocate_msrs())
return -ENOMEM;
- if ((err = register_die_notifier(&profile_exceptions_nb))){
+ err = register_die_notifier(&profile_exceptions_nb);
+ if (err) {
free_msrs();
return err;
}
*/
/* Assume saved/restored counters are the same on all CPUs */
- model->fill_in_addresses(&cpu_msrs[0]);
- for_each_possible_cpu (cpu) {
+ model->fill_in_addresses(&per_cpu(cpu_msrs, 0));
+ for_each_possible_cpu(cpu) {
if (cpu != 0) {
- memcpy(cpu_msrs[cpu].counters, cpu_msrs[0].counters,
+ memcpy(per_cpu(cpu_msrs, cpu).counters,
+ per_cpu(cpu_msrs, 0).counters,
sizeof(struct op_msr) * model->num_counters);
- memcpy(cpu_msrs[cpu].controls, cpu_msrs[0].controls,
+ memcpy(per_cpu(cpu_msrs, cpu).controls,
+ per_cpu(cpu_msrs, 0).controls,
sizeof(struct op_msr) * model->num_controls);
}
return 0;
}
-
-static void nmi_restore_registers(struct op_msrs * msrs)
+static void nmi_restore_registers(struct op_msrs *msrs)
{
unsigned int const nr_ctrs = model->num_counters;
- unsigned int const nr_ctrls = model->num_controls;
- struct op_msr * counters = msrs->counters;
- struct op_msr * controls = msrs->controls;
+ unsigned int const nr_ctrls = model->num_controls;
+ struct op_msr *counters = msrs->counters;
+ struct op_msr *controls = msrs->controls;
unsigned int i;
for (i = 0; i < nr_ctrls; ++i) {
- if (controls[i].addr){
+ if (controls[i].addr) {
wrmsr(controls[i].addr,
controls[i].saved.low,
controls[i].saved.high);
}
}
-
+
for (i = 0; i < nr_ctrs; ++i) {
- if (counters[i].addr){
+ if (counters[i].addr) {
wrmsr(counters[i].addr,
counters[i].saved.low,
counters[i].saved.high);
}
}
}
-
-static void nmi_cpu_shutdown(void * dummy)
+static void nmi_cpu_shutdown(void *dummy)
{
unsigned int v;
int cpu = smp_processor_id();
- struct op_msrs * msrs = &cpu_msrs[cpu];
-
+ struct op_msrs *msrs = &__get_cpu_var(cpu_msrs);
+
/* restoring APIC_LVTPC can trigger an apic error because the delivery
* mode and vector nr combination can be illegal. That's by design: on
* power on apic lvt contain a zero vector nr which are legal only for
*/
v = apic_read(APIC_LVTERR);
apic_write(APIC_LVTERR, v | APIC_LVT_MASKED);
- apic_write(APIC_LVTPC, saved_lvtpc[cpu]);
+ apic_write(APIC_LVTPC, per_cpu(saved_lvtpc, cpu));
apic_write(APIC_LVTERR, v);
nmi_restore_registers(msrs);
}
-
static void nmi_shutdown(void)
{
+ struct op_msrs *msrs = &get_cpu_var(cpu_msrs);
nmi_enabled = 0;
on_each_cpu(nmi_cpu_shutdown, NULL, 0, 1);
unregister_die_notifier(&profile_exceptions_nb);
- model->shutdown(cpu_msrs);
+ model->shutdown(msrs);
free_msrs();
+ put_cpu_var(cpu_msrs);
}
-
-static void nmi_cpu_start(void * dummy)
+static void nmi_cpu_start(void *dummy)
{
- struct op_msrs const * msrs = &cpu_msrs[smp_processor_id()];
+ struct op_msrs const *msrs = &__get_cpu_var(cpu_msrs);
model->start(msrs);
}
-
static int nmi_start(void)
{
on_each_cpu(nmi_cpu_start, NULL, 0, 1);
return 0;
}
-
-
-static void nmi_cpu_stop(void * dummy)
+
+static void nmi_cpu_stop(void *dummy)
{
- struct op_msrs const * msrs = &cpu_msrs[smp_processor_id()];
+ struct op_msrs const *msrs = &__get_cpu_var(cpu_msrs);
model->stop(msrs);
}
-
-
+
static void nmi_stop(void)
{
on_each_cpu(nmi_cpu_stop, NULL, 0, 1);
}
-
struct op_counter_config counter_config[OP_MAX_COUNTER];
-static int nmi_create_files(struct super_block * sb, struct dentry * root)
+static int nmi_create_files(struct super_block *sb, struct dentry *root)
{
unsigned int i;
for (i = 0; i < model->num_counters; ++i) {
- struct dentry * dir;
+ struct dentry *dir;
char buf[4];
-
- /* quick little hack to _not_ expose a counter if it is not
+
+ /* quick little hack to _not_ expose a counter if it is not
* available for use. This should protect userspace app.
* NOTE: assumes 1:1 mapping here (that counters are organized
* sequentially in their struct assignment).
snprintf(buf, sizeof(buf), "%d", i);
dir = oprofilefs_mkdir(sb, root, buf);
- oprofilefs_create_ulong(sb, dir, "enabled", &counter_config[i].enabled);
- oprofilefs_create_ulong(sb, dir, "event", &counter_config[i].event);
- oprofilefs_create_ulong(sb, dir, "count", &counter_config[i].count);
- oprofilefs_create_ulong(sb, dir, "unit_mask", &counter_config[i].unit_mask);
- oprofilefs_create_ulong(sb, dir, "kernel", &counter_config[i].kernel);
- oprofilefs_create_ulong(sb, dir, "user", &counter_config[i].user);
+ oprofilefs_create_ulong(sb, dir, "enabled", &counter_config[i].enabled);
+ oprofilefs_create_ulong(sb, dir, "event", &counter_config[i].event);
+ oprofilefs_create_ulong(sb, dir, "count", &counter_config[i].count);
+ oprofilefs_create_ulong(sb, dir, "unit_mask", &counter_config[i].unit_mask);
+ oprofilefs_create_ulong(sb, dir, "kernel", &counter_config[i].kernel);
+ oprofilefs_create_ulong(sb, dir, "user", &counter_config[i].user);
}
return 0;
}
-
+
static int p4force;
module_param(p4force, int, 0);
-
-static int __init p4_init(char ** cpu_type)
+
+static int __init p4_init(char **cpu_type)
{
__u8 cpu_model = boot_cpu_data.x86_model;
return 1;
#else
switch (smp_num_siblings) {
- case 1:
- *cpu_type = "i386/p4";
- model = &op_p4_spec;
- return 1;
-
- case 2:
- *cpu_type = "i386/p4-ht";
- model = &op_p4_ht2_spec;
- return 1;
+ case 1:
+ *cpu_type = "i386/p4";
+ model = &op_p4_spec;
+ return 1;
+
+ case 2:
+ *cpu_type = "i386/p4-ht";
+ model = &op_p4_ht2_spec;
+ return 1;
}
#endif
return 0;
}
-
-static int __init ppro_init(char ** cpu_type)
+static int __init ppro_init(char **cpu_type)
{
__u8 cpu_model = boot_cpu_data.x86_model;
if (!cpu_has_apic)
return -ENODEV;
-
+
switch (vendor) {
- case X86_VENDOR_AMD:
- /* Needs to be at least an Athlon (or hammer in 32bit mode) */
+ case X86_VENDOR_AMD:
+ /* Needs to be at least an Athlon (or hammer in 32bit mode) */
- switch (family) {
- default:
+ switch (family) {
+ default:
+ return -ENODEV;
+ case 6:
+ model = &op_athlon_spec;
+ cpu_type = "i386/athlon";
+ break;
+ case 0xf:
+ model = &op_athlon_spec;
+ /* Actually it could be i386/hammer too, but give
+ user space an consistent name. */
+ cpu_type = "x86-64/hammer";
+ break;
+ case 0x10:
+ model = &op_athlon_spec;
+ cpu_type = "x86-64/family10";
+ break;
+ }
+ break;
+
+ case X86_VENDOR_INTEL:
+ switch (family) {
+ /* Pentium IV */
+ case 0xf:
+ if (!p4_init(&cpu_type))
return -ENODEV;
- case 6:
- model = &op_athlon_spec;
- cpu_type = "i386/athlon";
- break;
- case 0xf:
- model = &op_athlon_spec;
- /* Actually it could be i386/hammer too, but give
- user space an consistent name. */
- cpu_type = "x86-64/hammer";
- break;
- case 0x10:
- model = &op_athlon_spec;
- cpu_type = "x86-64/family10";
- break;
- }
break;
-
- case X86_VENDOR_INTEL:
- switch (family) {
- /* Pentium IV */
- case 0xf:
- if (!p4_init(&cpu_type))
- return -ENODEV;
- break;
-
- /* A P6-class processor */
- case 6:
- if (!ppro_init(&cpu_type))
- return -ENODEV;
- break;
-
- default:
- return -ENODEV;
- }
+
+ /* A P6-class processor */
+ case 6:
+ if (!ppro_init(&cpu_type))
+ return -ENODEV;
break;
default:
return -ENODEV;
+ }
+ break;
+
+ default:
+ return -ENODEV;
}
init_sysfs();
return 0;
}
-
void op_nmi_exit(void)
{
if (using_nmi)