It turned out that a performance counter on AMD does not
count at all when the GO or HO bit is set in the control
register and SVM is disabled in EFER.
This patch works around this issue by masking out the HO bit
in the performance counter control register when SVM is not
enabled.
The GO bit is not touched because it is only set when the
user wants to count in guest-mode only. So when SVM is
disabled the counter should not run at all and the
not-counting is the intended behaviour.
Cc: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxx>
Cc: Avi Kivity <avi@xxxxxxxxxx>
Cc: Stephane Eranian <eranian@xxxxxxxxxx>
Cc: David Ahern <dsahern@xxxxxxxxx>
Cc: Gleb Natapov <gleb@xxxxxxxxxx>
Cc: Robert Richter <robert.richter@xxxxxxx>
Cc: stable@xxxxxxxxxxxxxxx # 3.2
Signed-off-by: Joerg Roedel <joerg.roedel@xxxxxxx>
---
arch/x86/include/asm/perf_event.h | 8 +++++++
arch/x86/kernel/cpu/perf_event.h | 6 ++++-
arch/x86/kernel/cpu/perf_event_amd.c | 37 ++++++++++++++++++++++++++++++++-
arch/x86/kvm/svm.c | 5 ++++
4 files changed, 53 insertions(+), 3 deletions(-)
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 096c975e..ffad310 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -242,4 +242,12 @@ static inline void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap)
static inline void perf_events_lapic_init(void) { }
#endif
+#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_AMD)
+extern void amd_pmu_enable_virt(void);
+extern void amd_pmu_disable_virt(void);
+#else /* CONFIG_PERF_EVENTS && CONFIG_CPU_SUP_AMD */
+static inline void amd_pmu_enable_virt(void) { }
+static inline void amd_pmu_disable_virt(void) { }
+#endif /* CONFIG_PERF_EVENTS && CONFIG_CPU_SUP_AMD */
+
#endif /* _ASM_X86_PERF_EVENT_H */
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 8944062..2c581b9 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -148,6 +148,8 @@ struct cpu_hw_events {
* AMD specific bits
*/
struct amd_nb *amd_nb;
+ /* Inverted mask of bits to clear in the perf_ctr ctrl registers */
+ u64 perf_ctr_virt_mask;
void *kfree_on_online;
};
@@ -417,9 +419,11 @@ void x86_pmu_disable_all(void);
static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc,
u64 enable_mask)
{
+ u64 disable_mask = __this_cpu_read(cpu_hw_events.perf_ctr_virt_mask);
+
if (hwc->extra_reg.reg)
wrmsrl(hwc->extra_reg.reg, hwc->extra_reg.config);
- wrmsrl(hwc->config_base, hwc->config | enable_mask);
+ wrmsrl(hwc->config_base, (hwc->config | enable_mask) & ~disable_mask);
}
void x86_pmu_enable_all(int added);
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 0397b23..67250a5 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -1,4 +1,5 @@
#include <linux/perf_event.h>
+#include <linux/export.h>
#include <linux/types.h>
#include <linux/init.h>
#include <linux/slab.h>
@@ -357,7 +358,9 @@ static void amd_pmu_cpu_starting(int cpu)
struct amd_nb *nb;
int i, nb_id;
- if (boot_cpu_data.x86_max_cores < 2)
+ cpuc->perf_ctr_virt_mask = AMD_PERFMON_EVENTSEL_HOSTONLY;
+
+ if (boot_cpu_data.x86_max_cores < 2 || boot_cpu_data.x86 == 0x15)
return;
nb_id = amd_get_nb_id(cpu);
@@ -587,9 +590,9 @@ static __initconst const struct x86_pmu amd_pmu_f15h = {
.put_event_constraints = amd_put_event_constraints,
.cpu_prepare = amd_pmu_cpu_prepare,
- .cpu_starting = amd_pmu_cpu_starting,
.cpu_dead = amd_pmu_cpu_dead,
#endif
+ .cpu_starting = amd_pmu_cpu_starting,
};
__init int amd_pmu_init(void)
@@ -621,3 +624,33 @@ __init int amd_pmu_init(void)
return 0;
}
+
+void amd_pmu_enable_virt(void)
+{
+ struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+ cpuc->perf_ctr_virt_mask = 0;
+
+ /* Reload all events */
+ x86_pmu_disable_all();
+ x86_pmu_enable_all(0);
+}
+EXPORT_SYMBOL_GPL(amd_pmu_enable_virt);
+
+void amd_pmu_disable_virt(void)
+{
+ struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+
+ /*
+ * We only mask out the Host-only bit so that host-only counting works
+ * when SVM is disabled. If someone sets up a guest-only counter when
+ * SVM is disabled the Guest-only bits still gets set and the counter
+ * will not count anything.
+ */
+ cpuc->perf_ctr_virt_mask = AMD_PERFMON_EVENTSEL_HOSTONLY;
+
+ /* Reload all events */
+ x86_pmu_disable_all();
+ x86_pmu_enable_all(0);
+}
+EXPORT_SYMBOL_GPL(amd_pmu_disable_virt);
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 5fa553b..e385214 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -29,6 +29,7 @@
#include <linux/ftrace_event.h>
#include <linux/slab.h>
+#include <asm/perf_event.h>
#include <asm/tlbflush.h>
#include <asm/desc.h>
#include <asm/kvm_para.h>
@@ -575,6 +576,8 @@ static void svm_hardware_disable(void *garbage)
wrmsrl(MSR_AMD64_TSC_RATIO, TSC_RATIO_DEFAULT);
cpu_svm_disable();
+
+ amd_pmu_disable_virt();
}
static int svm_hardware_enable(void *garbage)
@@ -622,6 +625,8 @@ static int svm_hardware_enable(void *garbage)
svm_init_erratum_383();
+ amd_pmu_enable_virt();
+
return 0;
}
--
1.7.5.4
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
