This patch fixes a kernel crash when using precise sampling (PEBS)
after a suspend/resume. Turns out the CPU notifier code is not invoked
on CPU0 (BP). Therefore, the DS_AREA (used by PEBS) is not restored properly
by the kernel and keeps it power-on/resume value of 0 causing any PEBS
measurement to crash when running on CPU0.
The workaround is to add a hook in the actual resume code to restore
the DS Area MSR value. It is invoked for all CPUS. So for all but CPU0,
the DS_AREA will be restored twice but this is harmless.
Reported-by: Linus Torvalds <torva...@linux-foundation.org>
Signed-off-by: Stephane Eranian <eran...@google.com>
---
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c
b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 826054a..0e9bdd3 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -729,3 +729,11 @@ void intel_ds_init(void)
}
}
}
+
+void perf_restore_debug_store(void)
+{
+ if (!x86_pmu.bts && !x86_pmu.pebs)
+ return;
+
+ init_debug_store_on_cpu(smp_processor_id());
+}
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 120cee1..3c68768 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -11,6 +11,7 @@
#include <linux/suspend.h>
#include <linux/export.h>
#include <linux/smp.h>
+#include <linux/perf_event.h>
#include <asm/pgtable.h>
#include <asm/proto.h>
@@ -228,6 +229,7 @@ static void __restore_processor_state(struct saved_context
*ctxt)
do_fpu_end();
x86_platform.restore_sched_clock_state();
mtrr_bp_restore();
+ perf_restore_debug_store();
}
/* Needed by apm.c */
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 8737e1c..746be3b 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -742,6 +742,7 @@ extern void perf_event_enable(struct perf_event *event);
extern void perf_event_disable(struct perf_event *event);
extern int __perf_event_disable(void *info);
extern void perf_event_task_tick(void);
+extern void perf_restore_debug_store(void);
#else
static inline void
perf_event_task_sched_in(struct task_struct *prev,
@@ -781,6 +782,7 @@ static inline void perf_event_enable(struct perf_event
*event) { }
static inline void perf_event_disable(struct perf_event *event)
{ }
static inline int __perf_event_disable(void *info) {
return -1; }
static inline void perf_event_task_tick(void) { }
+static inline void perf_restore_debug_store(void) { }
#endif
#define perf_output_put(handle, x) perf_output_copy((handle), &(x), sizeof(x))
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
