On Thu, 2010-12-02 at 11:15 -0500, Don Zickus wrote:
Nah, we should actively scan for that during the bring-up and kill
hw-perf when we find an enable bit set, some BIOSes actively use the
PMU, this is something that should be discouraged.
---
arch/x86/kernel/cpu/perf_event.c | 30 +++++++++++++++++++++++++++---
1 files changed, 27 insertions(+), 3 deletions(-)
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 817d2b1..7f92833 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -375,15 +375,40 @@ static void release_pmc_hardware(void) {}
static bool check_hw_exists(void)
{
u64 val, val_new = 0;
- int ret = 0;
+ int i, reg, ret = 0;
val = 0xabcdUL;
ret |= checking_wrmsrl(x86_pmu.perfctr, val);
ret |= rdmsrl_safe(x86_pmu.perfctr, &val_new);
- if (ret || val != val_new)
+ if (ret || val != val_new) {
+ printk(KERN_CONT "Broken PMU hardware detected, software events only.\n");
return false;
+ }
+
+ /*
+ * Check to see if the BIOS enabled any of the counters, if so
+ * complain and bail.
+ */
+ for (i = 0; i < x86_pmu.num_counters; i++) {
+ reg = x86_pmu.eventsel + i;
+ rdmsrl(reg, val);
+ if (val & ARCH_PERFMON_EVENTSEL_ENABLE)
+ goto bios_fail;
+ }
+
+ for (i = 0; i < x86_pmu.num_counters_fixed; i++) {
+ reg = MSR_ARCH_PERFMON_FIXED_CTR_CTRL;
+ rdmsrl(reg, val);
+ if (val & (0x03 << i*4))
+ goto bios_fail;
+ }
return true;
+
+bios_fail:
+ printk(KERN_CONT "Broken BIOS detected, software events only.\n");
+ printk(KERN_ERR FW_BUG "invalid MSR %x=%Lx\n", reg, val);
+ return false;
}
static void reserve_ds_buffers(void);
@@ -1379,7 +1404,6 @@ int __init init_hw_perf_events(void)
/* sanity check that the hardware exists or is emulated */
if (!check_hw_exists()) {
- pr_cont("Broken PMU hardware detected, software events only.\n");
return 0;
}
Something like the below, preferably I'd key that off of SYS_KEXEC, but
looking through the existing notifiers adding a state requires touching
all of them :/
---
kernel/perf_event.c | 21 +++++++++++++++++++++
1 files changed, 21 insertions(+), 0 deletions(-)
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 195393c..7abcd8d 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -21,6 +21,7 @@
#include <linux/dcache.h>
#include <linux/percpu.h>
#include <linux/ptrace.h>
+#include <linux/reboot.h>
#include <linux/vmstat.h>
#include <linux/vmalloc.h>
#include <linux/hardirq.h>
@@ -6383,6 +6384,25 @@ static void perf_event_exit_cpu(int cpu)
static inline void perf_event_exit_cpu(int cpu) { }
#endif
+static int
+perf_reboot(struct notifier_block *notifier, unsigned long val, void *v)
+{
+ /*
+ * XXX this relies on hotplug, does kexec do too?
+ */
+ perf_event_exit_cpu(0);
+ return NOTIFY_OK;
+}
+
+/*
+ * Run the perf reboot notifier at the very last possible moment so that
+ * the generic watchdog code runs as long as possible.
+ */
+static struct notifier_block perf_reboot_notifier = {
+ .notifier_call = perf_reboot,
+ .priority = INT_MIN,
+};
+
static int __cpuinit
perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
{
@@ -6418,6 +6438,7 @@ void __init perf_event_init(void)
perf_pmu_register(&perf_task_clock);
perf_tp_register();
perf_cpu_notifier(perf_cpu_notify);
+ register_reboot_notifier(&perf_reboot_notifier);
ret = init_hw_breakpoint();
WARN(ret, "hw_breakpoint initialization failed with: %d", ret);
--
