From 861d034ee814917a83bd5de4b26e3b8336ddeeb8 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Thu, 19 Aug 2010 13:31:43 +0200
Subject: [PATCH 1/2] sched: Fix rq->clock synchronization when migrating tasks
sched_fork() -- we do task placement in ->task_fork_fair() ensure we
update_rq_clock() so we work with current time. We leave the vruntime
in relative state, so the time delay until wake_up_new_task() doesn't
matter.
wake_up_new_task() -- Since task_fork_fair() left p->vruntime in
relative state we can safely migrate, the activate_task() on the
remote rq will call update_rq_clock() and causes the clock to be
synced (enough).
Tested-by: Jack Daniel <wanders.thirst@gmail.com>
Tested-by: Philby John <pjohn@mvista.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1281002322.1923.1708.camel@laptop>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
kernel/sched_fair.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 806d1b227a21..ab661ebc4895 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -3752,6 +3752,8 @@ static void task_fork_fair(struct task_struct *p)
raw_spin_lock_irqsave(&rq->lock, flags);
+ update_rq_clock(rq);
+
if (unlikely(task_cpu(p) != this_cpu))
__set_task_cpu(p, this_cpu);
From cd7240c0b900eb6d690ccee088a6c9b46dae815a Mon Sep 17 00:00:00 2001
From: Suresh Siddha <suresh.b.siddha@intel.com>
Date: Thu, 19 Aug 2010 17:03:38 -0700
Subject: [PATCH 2/2] 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 | 2 ++
arch/x86/kernel/tsc.c | 38 ++++++++++++++++++++++++++++++++++++++
arch/x86/power/cpu.c | 2 ++
3 files changed, 42 insertions(+)
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index c0427295e8f5..1ca132fc0d03 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/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 */
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index ce8e50239332..d632934cb638 100644
--- a/arch/x86/kernel/tsc.c
+++ b/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
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index e7e8c5f54956..87bb35e34ef1 100644
--- a/arch/x86/power/cpu.c
+++ b/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);