[PATCH] x86 tsc: avoid system instability in hibernation

[PATCH] x86 tsc: avoid system instability in hibernation

[Atharva Tiwari]

System instability are seen during resume from hibernation when system
is under heavy CPU load. This is due to the lack of update of sched
clock data, and the scheduler would then think that heavy CPU hog
tasks need more time in CPU, causing the system to freeze
during the unfreezing of tasks.

Signed-off-by: Atharva Tiwari <evepolonium@gmail.com>
---
 arch/x86/kernel/tsc.c       | 27 +++++++++++++++++++++++++++
 include/linux/sched/clock.h |  5 ++++-
 kernel/sched/clock.c        |  4 ++--
 3 files changed, 33 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 67aeaba4ba9c..28a5c3ff2e90 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -15,6 +15,7 @@
 #include <linux/timex.h>
 #include <linux/static_key.h>
 #include <linux/static_call.h>
+#include <linux/suspend.h>
 
 #include <asm/hpet.h>
 #include <asm/timer.h>
@@ -1599,3 +1600,29 @@ unsigned long calibrate_delay_is_known(void)
 	return 0;
 }
 #endif
+static int tsc_pm_notifier(struct notifier_block *notifier,
+			unsigned long pm_event, void *unused)
+{
+	switch (pm_event) {
+	case PM_HIBERNATION_PREPARE:
+		clear_sched_clock_stable();
+		break;
+	case PM_POST_HIBERNATION:
+		if (!check_tsc_unstable())
+			set_sched_clock_stable();
+		break;
+	}
+	
+	return 0;
+};
+
+static struct notifier_block tsc_pm_notifier_block = {
+	.notifier_call = tsc_pm_notifier,
+}
+
+static int tsc_setup_pm_notifier(void)
+{
+       return register_pm_notifier(&tsc_pm_notifier_block);
+}
+
+subsys_initcall(tsc_setup_pm_notifier);
diff --git a/include/linux/sched/clock.h b/include/linux/sched/clock.h
index 196f0ca351a2..69efc280f14c 100644
--- a/include/linux/sched/clock.h
+++ b/include/linux/sched/clock.h
@@ -40,7 +40,9 @@ static inline void sched_clock_tick(void)
 static inline void clear_sched_clock_stable(void)
 {
 }
-
+static inline void set_sched_clock_stable(void)
+{
+}
 static inline void sched_clock_idle_sleep_event(void)
 {
 }
@@ -65,6 +67,7 @@ static __always_inline u64 local_clock(void)
 }
 #else
 extern int sched_clock_stable(void);
+extern void set_sched_clock_stable(void);
 extern void clear_sched_clock_stable(void);
 
 /*
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index a09655b48140..efe8f2b69657 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -114,7 +114,7 @@ notrace static void __scd_stamp(struct sched_clock_data *scd)
 	scd->tick_raw = sched_clock();
 }
 
-notrace static void __set_sched_clock_stable(void)
+notrace void set_sched_clock_stable(void)
 {
 	struct sched_clock_data *scd;
 
@@ -234,7 +234,7 @@ static int __init sched_clock_init_late(void)
 	smp_mb(); /* matches {set,clear}_sched_clock_stable() */
 
 	if (__sched_clock_stable_early)
-		__set_sched_clock_stable();
+		set_sched_clock_stable();
 
 	return 0;
 }
-- 
2.43.0

Re: [PATCH] x86 tsc: avoid system instability in hibernation

[Peter Zijlstra]

On Tue, Dec 10, 2024 at 11:54:18AM +0530, Atharva Tiwari wrote:
> System instability are seen during resume from hibernation when system
> is under heavy CPU load. This is due to the lack of update of sched
> clock data, and the scheduler would then think that heavy CPU hog
> tasks need more time in CPU, causing the system to freeze
> during the unfreezing of tasks.

Please tell me more.. what crazy things are happening?

[PATCH] x86 tsc: avoid system instability in hibernation

[Atharva Tiwari]

System instability are seen during resume from hibernation when system is under heavy CPU load. this is caused by the lack of update of sched clock data

Signed-off-by: Atharva Tiwari <evepolonium@gmail.com>
---
 arch/x86/kernel/tsc.c       | 27 +++++++++++++++++++++++++++
 include/linux/sched/clock.h |  5 ++++-
 kernel/sched/clock.c        |  4 ++--
 3 files changed, 33 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 67aeaba4ba9c..28a5c3ff2e90 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -15,6 +15,7 @@
 #include <linux/timex.h>
 #include <linux/static_key.h>
 #include <linux/static_call.h>
+#include <linux/suspend.h>
 
 #include <asm/hpet.h>
 #include <asm/timer.h>
@@ -1599,3 +1600,29 @@ unsigned long calibrate_delay_is_known(void)
 	return 0;
 }
 #endif
+static int tsc_pm_notifier(struct notifier_block *notifier,
+			unsigned long pm_event, void *unused)
+{
+	switch (pm_event) {
+	case PM_HIBERNATION_PREPARE:
+		clear_sched_clock_stable();
+		break;
+	case PM_POST_HIBERNATION:
+		if (!check_tsc_unstable())
+			set_sched_clock_stable();
+		break;
+	}
+	
+	return 0;
+};
+
+static struct notifier_block tsc_pm_notifier_block = {
+	.notifier_call = tsc_pm_notifier,
+}
+
+static int tsc_setup_pm_notifier(void)
+{
+       return register_pm_notifier(&tsc_pm_notifier_block);
+}
+
+subsys_initcall(tsc_setup_pm_notifier);
diff --git a/include/linux/sched/clock.h b/include/linux/sched/clock.h
index 196f0ca351a2..69efc280f14c 100644
--- a/include/linux/sched/clock.h
+++ b/include/linux/sched/clock.h
@@ -40,7 +40,9 @@ static inline void sched_clock_tick(void)
 static inline void clear_sched_clock_stable(void)
 {
 }
-
+static inline void set_sched_clock_stable(void)
+{
+}
 static inline void sched_clock_idle_sleep_event(void)
 {
 }
@@ -65,6 +67,7 @@ static __always_inline u64 local_clock(void)
 }
 #else
 extern int sched_clock_stable(void);
+extern void set_sched_clock_stable(void);
 extern void clear_sched_clock_stable(void);
 
 /*
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index a09655b48140..efe8f2b69657 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -114,7 +114,7 @@ notrace static void __scd_stamp(struct sched_clock_data *scd)
 	scd->tick_raw = sched_clock();
 }
 
-notrace static void __set_sched_clock_stable(void)
+notrace void set_sched_clock_stable(void)
 {
 	struct sched_clock_data *scd;
 
@@ -234,7 +234,7 @@ static int __init sched_clock_init_late(void)
 	smp_mb(); /* matches {set,clear}_sched_clock_stable() */
 
 	if (__sched_clock_stable_early)
-		__set_sched_clock_stable();
+		set_sched_clock_stable();
 
 	return 0;
 }
-- 
2.43.0

Re: [PATCH] x86 tsc: avoid system instability in hibernation

[kernel test robot]

Hi Atharva,

kernel test robot noticed the following build errors:

[auto build test ERROR on tip/master]
[also build test ERROR on tip/sched/core linus/master tip/auto-latest tip/x86/core v6.13-rc3 next-20241217]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Atharva-Tiwari/x86-tsc-avoid-system-instability-in-hibernation/20241210-214059
base:   tip/master
patch link:    https://lore.kernel.org/r/20241210133930.1195-1-evepolonium%40gmail.com
patch subject: [PATCH] x86 tsc: avoid system instability in hibernation
config: x86_64-kexec (https://download.01.org/0day-ci/archive/20241217/202412172141.6wHjHpsF-lkp@intel.com/config)
compiler: clang version 19.1.3 (https://github.com/llvm/llvm-project ab51eccf88f5321e7c60591c5546b254b6afab99)
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20241217/202412172141.6wHjHpsF-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202412172141.6wHjHpsF-lkp@intel.com/

All errors (new ones prefixed by >>):

   In file included from arch/x86/kernel/tsc.c:18:
   In file included from include/linux/suspend.h:5:
   In file included from include/linux/swap.h:9:
   In file included from include/linux/memcontrol.h:21:
   In file included from include/linux/mm.h:2223:
   include/linux/vmstat.h:504:43: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum numa_stat_item') [-Wenum-enum-conversion]
     504 |         return vmstat_text[NR_VM_ZONE_STAT_ITEMS +
         |                            ~~~~~~~~~~~~~~~~~~~~~ ^
     505 |                            item];
         |                            ~~~~
   include/linux/vmstat.h:511:43: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum numa_stat_item') [-Wenum-enum-conversion]
     511 |         return vmstat_text[NR_VM_ZONE_STAT_ITEMS +
         |                            ~~~~~~~~~~~~~~~~~~~~~ ^
     512 |                            NR_VM_NUMA_EVENT_ITEMS +
         |                            ~~~~~~~~~~~~~~~~~~~~~~
   include/linux/vmstat.h:518:36: warning: arithmetic between different enumeration types ('enum node_stat_item' and 'enum lru_list') [-Wenum-enum-conversion]
     518 |         return node_stat_name(NR_LRU_BASE + lru) + 3; // skip "nr_"
         |                               ~~~~~~~~~~~ ^ ~~~
   include/linux/vmstat.h:524:43: warning: arithmetic between different enumeration types ('enum zone_stat_item' and 'enum numa_stat_item') [-Wenum-enum-conversion]
     524 |         return vmstat_text[NR_VM_ZONE_STAT_ITEMS +
         |                            ~~~~~~~~~~~~~~~~~~~~~ ^
     525 |                            NR_VM_NUMA_EVENT_ITEMS +
         |                            ~~~~~~~~~~~~~~~~~~~~~~
>> arch/x86/kernel/tsc.c:1621:2: error: expected ';' after top level declarator
    1621 | }
         |  ^
         |  ;
   4 warnings and 1 error generated.


vim +1621 arch/x86/kernel/tsc.c

  1618	
  1619	static struct notifier_block tsc_pm_notifier_block = {
  1620		.notifier_call = tsc_pm_notifier,
> 1621	}
  1622	

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki