x86, tsc, sched: Recompute cyc2ns_offset's during resume from sleep states

TSC's get reset after suspend/resume (even on cpu's with invariant TSC
which runs at a constant rate across ACPI P-, C- and T-states). And in
some systems BIOS seem to reinit TSC to arbitrary large value (still
sync'd across cpu's) during resume.

This leads to a scenario of scheduler rq->clock (sched_clock_cpu()) less
than rq->age_stamp (introduced in 2.6.32). This leads to a big value
returned by scale_rt_power() and the resulting big group power set by the
update_group_power() is causing improper load balancing between busy and
idle cpu's after suspend/resume.

This resulted in multi-threaded workloads (like kernel-compilation) go
slower after suspend/resume cycle on core i5 laptops.

Fix this by recomputing cyc2ns_offset's during resume, so that
sched_clock() continues from the point where it was left off during
suspend.

Reported-by: Florian Pritz <flo@xssn.at>
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: <stable@kernel.org> # [v2.6.32+]
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1282262618.2675.24.camel@sbsiddha-MOBL3.sc.intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

arch/x86/include/asm/tsc.h

@@ -59,5 +59,7 @@ extern void check_tsc_sync_source(int cpu);
 extern void check_tsc_sync_target(void);
 
 extern int notsc_setup(char *);
+extern void save_sched_clock_state(void);
+extern void restore_sched_clock_state(void);
 
 #endif /* _ASM_X86_TSC_H */

arch/x86/kernel/tsc.c

@@ -626,6 +626,44 @@ static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu)
 	local_irq_restore(flags);
 }
 
+static unsigned long long cyc2ns_suspend;
+
+void save_sched_clock_state(void)
+{
+	if (!sched_clock_stable)
+		return;
+
+	cyc2ns_suspend = sched_clock();
+}
+
+/*
+ * Even on processors with invariant TSC, TSC gets reset in some the
+ * ACPI system sleep states. And in some systems BIOS seem to reinit TSC to
+ * arbitrary value (still sync'd across cpu's) during resume from such sleep
+ * states. To cope up with this, recompute the cyc2ns_offset for each cpu so
+ * that sched_clock() continues from the point where it was left off during
+ * suspend.
+ */
+void restore_sched_clock_state(void)
+{
+	unsigned long long offset;
+	unsigned long flags;
+	int cpu;
+
+	if (!sched_clock_stable)
+		return;
+
+	local_irq_save(flags);
+
+	get_cpu_var(cyc2ns_offset) = 0;
+	offset = cyc2ns_suspend - sched_clock();
+
+	for_each_possible_cpu(cpu)
+		per_cpu(cyc2ns_offset, cpu) = offset;
+
+	local_irq_restore(flags);
+}
+
 #ifdef CONFIG_CPU_FREQ
 
 /* Frequency scaling support. Adjust the TSC based timer when the cpu frequency

arch/x86/power/cpu.c

@@ -113,6 +113,7 @@ static void __save_processor_state(struct saved_context *ctxt)
 void save_processor_state(void)
 {
 	__save_processor_state(&saved_context);
+	save_sched_clock_state();
 }
 #ifdef CONFIG_X86_32
 EXPORT_SYMBOL(save_processor_state);
@@ -229,6 +230,7 @@ static void __restore_processor_state(struct saved_context *ctxt)
 void restore_processor_state(void)
 {
 	__restore_processor_state(&saved_context);
+	restore_sched_clock_state();
 }
 #ifdef CONFIG_X86_32
 EXPORT_SYMBOL(restore_processor_state);