#include <linux/sysdev.h>
#include <linux/sysctl.h>
#include <linux/percpu.h>
+#include <linux/dmi.h>
#include <asm/smp.h>
#include <asm/nmi.h>
#include <asm/kdebug.h>
+#include <asm/intel_arch_perfmon.h>
#include "mach_traps.h"
*/
#define NMI_MAX_COUNTER_BITS 66
-/*
- * lapic_nmi_owner tracks the ownership of the lapic NMI hardware:
- * - it may be reserved by some other driver, or not
- * - when not reserved by some other driver, it may be used for
- * the NMI watchdog, or not
- *
- * This is maintained separately from nmi_active because the NMI
- * watchdog may also be driven from the I/O APIC timer.
- */
-static DEFINE_SPINLOCK(lapic_nmi_owner_lock);
-static unsigned int lapic_nmi_owner;
-#define LAPIC_NMI_WATCHDOG (1<<0)
-#define LAPIC_NMI_RESERVED (1<<1)
-
/* nmi_active:
* >0: the lapic NMI watchdog is active, but can be disabled
* <0: the lapic NMI watchdog has not been set up, and cannot
static DEFINE_PER_CPU(struct nmi_watchdog_ctlblk, nmi_watchdog_ctlblk);
/* local prototypes */
-static void stop_apic_nmi_watchdog(void *unused);
static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu);
extern void show_registers(struct pt_regs *regs);
case X86_VENDOR_AMD:
return (msr - MSR_K7_PERFCTR0);
case X86_VENDOR_INTEL:
+ if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON))
+ return (msr - MSR_ARCH_PERFMON_PERFCTR0);
+
switch (boot_cpu_data.x86) {
case 6:
return (msr - MSR_P6_PERFCTR0);
case X86_VENDOR_AMD:
return (msr - MSR_K7_EVNTSEL0);
case X86_VENDOR_INTEL:
+ if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON))
+ return (msr - MSR_ARCH_PERFMON_EVENTSEL0);
+
switch (boot_cpu_data.x86) {
case 6:
return (msr - MSR_P6_EVNTSEL0);
case X86_VENDOR_AMD:
return ((boot_cpu_data.x86 == 15) || (boot_cpu_data.x86 == 6));
case X86_VENDOR_INTEL:
- return ((boot_cpu_data.x86 == 15) || (boot_cpu_data.x86 == 6));
+ if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON))
+ return 1;
+ else
+ return ((boot_cpu_data.x86 == 15) || (boot_cpu_data.x86 == 6));
}
return 0;
}
unsigned int *prev_nmi_count;
int cpu;
+ /* Enable NMI watchdog for newer systems.
+ Actually it should be safe for most systems before 2004 too except
+ for some IBM systems that corrupt registers when NMI happens
+ during SMM. Unfortunately we don't have more exact information
+ on these and use this coarse check. */
+ if (nmi_watchdog == NMI_DEFAULT && dmi_get_year(DMI_BIOS_DATE) >= 2004)
+ nmi_watchdog = NMI_LOCAL_APIC;
+
if ((nmi_watchdog == NMI_NONE) || (nmi_watchdog == NMI_DEFAULT))
return 0;
/* now that we know it works we can reduce NMI frequency to
something more reasonable; makes a difference in some configs */
- if (nmi_watchdog == NMI_LOCAL_APIC)
+ if (nmi_watchdog == NMI_LOCAL_APIC) {
+ struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
+
nmi_hz = 1;
+ /*
+ * On Intel CPUs with ARCH_PERFMON only 32 bits in the counter
+ * are writable, with higher bits sign extending from bit 31.
+ * So, we can only program the counter with 31 bit values and
+ * 32nd bit should be 1, for 33.. to be 1.
+ * Find the appropriate nmi_hz
+ */
+ if (wd->perfctr_msr == MSR_ARCH_PERFMON_PERFCTR0 &&
+ ((u64)cpu_khz * 1000) > 0x7fffffffULL) {
+ u64 count = (u64)cpu_khz * 1000;
+ do_div(count, 0x7fffffffUL);
+ nmi_hz = count + 1;
+ }
+ }
kfree(prev_nmi_count);
return 0;
touch_nmi_watchdog();
}
-int reserve_lapic_nmi(void)
-{
- unsigned int old_owner;
-
- spin_lock(&lapic_nmi_owner_lock);
- old_owner = lapic_nmi_owner;
- lapic_nmi_owner |= LAPIC_NMI_RESERVED;
- spin_unlock(&lapic_nmi_owner_lock);
- if (old_owner & LAPIC_NMI_RESERVED)
- return -EBUSY;
- if (old_owner & LAPIC_NMI_WATCHDOG)
- disable_lapic_nmi_watchdog();
- return 0;
-}
-
-void release_lapic_nmi(void)
-{
- unsigned int new_owner;
-
- spin_lock(&lapic_nmi_owner_lock);
- new_owner = lapic_nmi_owner & ~LAPIC_NMI_RESERVED;
- lapic_nmi_owner = new_owner;
- spin_unlock(&lapic_nmi_owner_lock);
- if (new_owner & LAPIC_NMI_WATCHDOG)
- enable_lapic_nmi_watchdog();
-}
-
void disable_timer_nmi_watchdog(void)
{
BUG_ON(nmi_watchdog != NMI_IO_APIC);
static int lapic_nmi_suspend(struct sys_device *dev, pm_message_t state)
{
+ /* only CPU0 goes here, other CPUs should be offline */
nmi_pm_active = atomic_read(&nmi_active);
- disable_lapic_nmi_watchdog();
+ stop_apic_nmi_watchdog(NULL);
+ BUG_ON(atomic_read(&nmi_active) != 0);
return 0;
}
static int lapic_nmi_resume(struct sys_device *dev)
{
- if (nmi_pm_active > 0)
- enable_lapic_nmi_watchdog();
+ /* only CPU0 goes here, other CPUs should be offline */
+ if (nmi_pm_active > 0) {
+ setup_apic_nmi_watchdog(NULL);
+ touch_nmi_watchdog();
+ }
return 0;
}
release_perfctr_nmi(wd->perfctr_msr);
}
+#define ARCH_PERFMON_NMI_EVENT_SEL ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL
+#define ARCH_PERFMON_NMI_EVENT_UMASK ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK
+
+static int setup_intel_arch_watchdog(void)
+{
+ unsigned int ebx;
+ union cpuid10_eax eax;
+ unsigned int unused;
+ unsigned int perfctr_msr, evntsel_msr;
+ unsigned int evntsel;
+ struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
+
+ /*
+ * Check whether the Architectural PerfMon supports
+ * Unhalted Core Cycles Event or not.
+ * NOTE: Corresponding bit = 0 in ebx indicates event present.
+ */
+ cpuid(10, &(eax.full), &ebx, &unused, &unused);
+ if ((eax.split.mask_length < (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX+1)) ||
+ (ebx & ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT))
+ goto fail;
+
+ perfctr_msr = MSR_ARCH_PERFMON_PERFCTR0;
+ evntsel_msr = MSR_ARCH_PERFMON_EVENTSEL0;
+
+ if (!reserve_perfctr_nmi(perfctr_msr))
+ goto fail;
+
+ if (!reserve_evntsel_nmi(evntsel_msr))
+ goto fail1;
+
+ wrmsrl(perfctr_msr, 0UL);
+
+ evntsel = ARCH_PERFMON_EVENTSEL_INT
+ | ARCH_PERFMON_EVENTSEL_OS
+ | ARCH_PERFMON_EVENTSEL_USR
+ | ARCH_PERFMON_NMI_EVENT_SEL
+ | ARCH_PERFMON_NMI_EVENT_UMASK;
+
+ /* setup the timer */
+ wrmsr(evntsel_msr, evntsel, 0);
+ write_watchdog_counter(perfctr_msr, "INTEL_ARCH_PERFCTR0");
+ apic_write(APIC_LVTPC, APIC_DM_NMI);
+ evntsel |= ARCH_PERFMON_EVENTSEL0_ENABLE;
+ wrmsr(evntsel_msr, evntsel, 0);
+
+ wd->perfctr_msr = perfctr_msr;
+ wd->evntsel_msr = evntsel_msr;
+ wd->cccr_msr = 0; //unused
+ wd->check_bit = 1ULL << (eax.split.bit_width - 1);
+ return 1;
+fail1:
+ release_perfctr_nmi(perfctr_msr);
+fail:
+ return 0;
+}
+
+static void stop_intel_arch_watchdog(void)
+{
+ unsigned int ebx;
+ union cpuid10_eax eax;
+ unsigned int unused;
+ struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
+
+ /*
+ * Check whether the Architectural PerfMon supports
+ * Unhalted Core Cycles Event or not.
+ * NOTE: Corresponding bit = 0 in ebx indicates event present.
+ */
+ cpuid(10, &(eax.full), &ebx, &unused, &unused);
+ if ((eax.split.mask_length < (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX+1)) ||
+ (ebx & ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT))
+ return;
+
+ wrmsr(wd->evntsel_msr, 0, 0);
+ release_evntsel_nmi(wd->evntsel_msr);
+ release_perfctr_nmi(wd->perfctr_msr);
+}
+
void setup_apic_nmi_watchdog (void *unused)
{
+ struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
+
/* only support LOCAL and IO APICs for now */
if ((nmi_watchdog != NMI_LOCAL_APIC) &&
(nmi_watchdog != NMI_IO_APIC))
return;
+ if (wd->enabled == 1)
+ return;
+
+ /* cheap hack to support suspend/resume */
+ /* if cpu0 is not active neither should the other cpus */
+ if ((smp_processor_id() != 0) && (atomic_read(&nmi_active) <= 0))
+ return;
+
if (nmi_watchdog == NMI_LOCAL_APIC) {
switch (boot_cpu_data.x86_vendor) {
case X86_VENDOR_AMD:
return;
break;
case X86_VENDOR_INTEL:
+ if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) {
+ if (!setup_intel_arch_watchdog())
+ return;
+ break;
+ }
switch (boot_cpu_data.x86) {
case 6:
if (boot_cpu_data.x86_model > 0xd)
return;
}
}
- __get_cpu_var(nmi_watchdog_ctlblk.enabled) = 1;
+ wd->enabled = 1;
atomic_inc(&nmi_active);
}
-static void stop_apic_nmi_watchdog(void *unused)
+void stop_apic_nmi_watchdog(void *unused)
{
+ struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
+
/* only support LOCAL and IO APICs for now */
if ((nmi_watchdog != NMI_LOCAL_APIC) &&
(nmi_watchdog != NMI_IO_APIC))
return;
+ if (wd->enabled == 0)
+ return;
+
if (nmi_watchdog == NMI_LOCAL_APIC) {
switch (boot_cpu_data.x86_vendor) {
case X86_VENDOR_AMD:
stop_k7_watchdog();
break;
case X86_VENDOR_INTEL:
+ if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) {
+ stop_intel_arch_watchdog();
+ break;
+ }
switch (boot_cpu_data.x86) {
case 6:
if (boot_cpu_data.x86_model > 0xd)
return;
}
}
- __get_cpu_var(nmi_watchdog_ctlblk.enabled) = 0;
+ wd->enabled = 0;
atomic_dec(&nmi_active);
}
extern void die_nmi(struct pt_regs *, const char *msg);
-void nmi_watchdog_tick (struct pt_regs * regs, unsigned reason)
+int nmi_watchdog_tick (struct pt_regs * regs, unsigned reason)
{
/*
int cpu = smp_processor_id();
struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
u64 dummy;
+ int rc=0;
/* check for other users first */
if (notify_die(DIE_NMI, "nmi", regs, reason, 2, SIGINT)
== NOTIFY_STOP) {
+ rc = 1;
touched = 1;
}
wrmsrl(wd->cccr_msr, dummy);
apic_write(APIC_LVTPC, APIC_DM_NMI);
}
- else if (wd->perfctr_msr == MSR_P6_PERFCTR0) {
- /* Only P6 based Pentium M need to re-unmask
+ else if (wd->perfctr_msr == MSR_P6_PERFCTR0 ||
+ wd->perfctr_msr == MSR_ARCH_PERFMON_PERFCTR0) {
+ /* P6 based Pentium M need to re-unmask
* the apic vector but it doesn't hurt
- * other P6 variant */
+ * other P6 variant.
+ * ArchPerfom/Core Duo also needs this */
apic_write(APIC_LVTPC, APIC_DM_NMI);
}
/* start the cycle over again */
write_watchdog_counter(wd->perfctr_msr, NULL);
- }
+ rc = 1;
+ } else if (nmi_watchdog == NMI_IO_APIC) {
+ /* don't know how to accurately check for this.
+ * just assume it was a watchdog timer interrupt
+ * This matches the old behaviour.
+ */
+ rc = 1;
+ } else
+ printk(KERN_WARNING "Unknown enabled NMI hardware?!\n");
}
done:
- return;
+ return rc;
+}
+
+int do_nmi_callback(struct pt_regs * regs, int cpu)
+{
+#ifdef CONFIG_SYSCTL
+ if (unknown_nmi_panic)
+ return unknown_nmi_panic_callback(regs, cpu);
+#endif
+ return 0;
}
#ifdef CONFIG_SYSCTL
unsigned char reason = get_nmi_reason();
char buf[64];
- if (!(reason & 0xc0)) {
- sprintf(buf, "NMI received for unknown reason %02x\n", reason);
- die_nmi(regs, buf);
- }
+ sprintf(buf, "NMI received for unknown reason %02x\n", reason);
+ die_nmi(regs, buf);
return 0;
}
/*
- * proc handler for /proc/sys/kernel/unknown_nmi_panic
+ * proc handler for /proc/sys/kernel/nmi
*/
-int proc_unknown_nmi_panic(ctl_table *table, int write, struct file *file,
+int proc_nmi_enabled(struct ctl_table *table, int write, struct file *file,
void __user *buffer, size_t *length, loff_t *ppos)
{
int old_state;
- old_state = unknown_nmi_panic;
+ nmi_watchdog_enabled = (atomic_read(&nmi_active) > 0) ? 1 : 0;
+ old_state = nmi_watchdog_enabled;
proc_dointvec(table, write, file, buffer, length, ppos);
- if (!!old_state == !!unknown_nmi_panic)
+ if (!!old_state == !!nmi_watchdog_enabled)
return 0;
- if (unknown_nmi_panic) {
- if (reserve_lapic_nmi() < 0) {
- unknown_nmi_panic = 0;
- return -EBUSY;
- } else {
- set_nmi_callback(unknown_nmi_panic_callback);
- }
+ if (atomic_read(&nmi_active) < 0) {
+ printk( KERN_WARNING "NMI watchdog is permanently disabled\n");
+ return -EIO;
+ }
+
+ if (nmi_watchdog == NMI_DEFAULT) {
+ if (nmi_known_cpu() > 0)
+ nmi_watchdog = NMI_LOCAL_APIC;
+ else
+ nmi_watchdog = NMI_IO_APIC;
+ }
+
+ if (nmi_watchdog == NMI_LOCAL_APIC) {
+ if (nmi_watchdog_enabled)
+ enable_lapic_nmi_watchdog();
+ else
+ disable_lapic_nmi_watchdog();
} else {
- release_lapic_nmi();
- unset_nmi_callback();
+ printk( KERN_WARNING
+ "NMI watchdog doesn't know what hardware to touch\n");
+ return -EIO;
}
return 0;
}
EXPORT_SYMBOL(release_perfctr_nmi);
EXPORT_SYMBOL(reserve_evntsel_nmi);
EXPORT_SYMBOL(release_evntsel_nmi);
-EXPORT_SYMBOL(reserve_lapic_nmi);
-EXPORT_SYMBOL(release_lapic_nmi);
EXPORT_SYMBOL(disable_timer_nmi_watchdog);
EXPORT_SYMBOL(enable_timer_nmi_watchdog);