This small series follows up to patch discussion related
to $subject patch series which is now in linux-next at:
- introduce watchdog_park_threads() and watchdog_unpark_threads()
https://git.kernel.org/cgit/linux/kernel/git/next/linux-next.git/commit/kernel/watchdog.c?id=89f536017155c7f76c8a620e6aed03809e53cd4c
- introduce watchdog_suspend() and watchdog_resume()
https://git.kernel.org/cgit/linux/kernel/git/next/linux-next.git/commit/kernel/watchdog.c?id=e0dd9ee3ecf3394e93343cf9542d8ca1b54eca08
- use park/unpark functions in update_watchdog_all_cpus()
https://git.kernel.org/cgit/linux/kernel/git/next/linux-next.git/commit/kernel/watchdog.c?id=eef1a759acfb98766fef20afca9e06f014299e3f
- use suspend/resume interface in fixup_ht_bug()
https://git.kernel.org/cgit/linux/kernel/git/next/linux-next.git/commit/kernel/watchdog.c?id=77592a82363dd508ce3dbe4eaaa2c6c45b966ebb
Changes based on patch discussion:
- Patch 1/2: rename watchdog_{suspend|resume}, add comment blocks
http://marc.info/?l=linux-kernel&m=143844050610220&w=2
http://marc.info/?l=linux-kernel&m=143876224114821&w=2
- Patch 2/2: use pr_debug() instead of pr_info()
http://marc.info/?l=linux-kernel&m=143869949229461&w=2
Ulrich Obergfell (2):
watchdog: rename watchdog_suspend() and watchdog_resume()
watchdog: use pr_debug() in fixup_ht_bug() failure path
arch/x86/kernel/cpu/perf_event_intel.c | 6 +++---
include/linux/nmi.h | 8 ++++----
kernel/watchdog.c | 26 ++++++++++++++++++++++----
3 files changed, 29 insertions(+), 11 deletions(-)
--
1.7.11.7
Rename watchdog_suspend() to lockup_detector_suspend() and
watchdog_resume() to lockup_detector_resume() to avoid
confusion with the watchdog subsystem and to be consistent
with the existing name lockup_detector_init().
Also provide comment blocks to explain the watchdog_running
and watchdog_suspended variables and their relationship.
Signed-off-by: Ulrich Obergfell <[email protected]>
---
arch/x86/kernel/cpu/perf_event_intel.c | 4 ++--
include/linux/nmi.h | 8 ++++----
kernel/watchdog.c | 26 ++++++++++++++++++++++----
3 files changed, 28 insertions(+), 10 deletions(-)
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index d4e1b0c..0357bf7 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -3368,7 +3368,7 @@ static __init int fixup_ht_bug(void)
return 0;
}
- if (watchdog_suspend() != 0) {
+ if (lockup_detector_suspend() != 0) {
pr_info("failed to disable PMU erratum BJ122, BV98, HSD29 workaround\n");
return 0;
}
@@ -3379,7 +3379,7 @@ static __init int fixup_ht_bug(void)
x86_pmu.commit_scheduling = NULL;
x86_pmu.stop_scheduling = NULL;
- watchdog_resume();
+ lockup_detector_resume();
get_online_cpus();
diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index 46e28e9e..78488e0 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -84,15 +84,15 @@ extern int proc_watchdog_thresh(struct ctl_table *, int ,
void __user *, size_t *, loff_t *);
extern int proc_watchdog_cpumask(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
-extern int watchdog_suspend(void);
-extern void watchdog_resume(void);
+extern int lockup_detector_suspend(void);
+extern void lockup_detector_resume(void);
#else
-static inline int watchdog_suspend(void)
+static inline int lockup_detector_suspend(void)
{
return 0;
}
-static inline void watchdog_resume(void)
+static inline void lockup_detector_resume(void)
{
}
#endif
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 69666f4..64ed1c3 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -67,8 +67,26 @@ unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask);
#define for_each_watchdog_cpu(cpu) \
for_each_cpu_and((cpu), cpu_online_mask, &watchdog_cpumask)
-static int __read_mostly watchdog_suspended;
+/*
+ * The 'watchdog_running' variable is set to 1 when the watchdog threads
+ * are registered/started and is set to 0 when the watchdog threads are
+ * unregistered/stopped, so it is an indicator whether the threads exist.
+ */
static int __read_mostly watchdog_running;
+/*
+ * If a subsystem has a need to deactivate the watchdog temporarily, it
+ * can use the suspend/resume interface to achieve this. The content of
+ * the 'watchdog_suspended' variable reflects this state. Existing threads
+ * are parked/unparked by the lockup_detector_{suspend|resume} functions
+ * (see comment blocks pertaining to those functions for further details).
+ *
+ * 'watchdog_suspended' also prevents threads from being registered/started
+ * or unregistered/stopped via parameters in /proc/sys/kernel, so the state
+ * of 'watchdog_running' cannot change while the watchdog is deactivated
+ * temporarily (see related code in 'proc' handlers).
+ */
+static int __read_mostly watchdog_suspended;
+
static u64 __read_mostly sample_period;
static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts);
@@ -669,7 +687,7 @@ static void watchdog_unpark_threads(void)
/*
* Suspend the hard and soft lockup detector by parking the watchdog threads.
*/
-int watchdog_suspend(void)
+int lockup_detector_suspend(void)
{
int ret = 0;
@@ -679,7 +697,7 @@ int watchdog_suspend(void)
* the 'watchdog_suspended' variable). If the watchdog threads are
* running, the first caller takes care that they will be parked.
* The state of 'watchdog_running' cannot change while a suspend
- * request is active (see related changes in 'proc' handlers).
+ * request is active (see related code in 'proc' handlers).
*/
if (watchdog_running && !watchdog_suspended)
ret = watchdog_park_threads();
@@ -695,7 +713,7 @@ int watchdog_suspend(void)
/*
* Resume the hard and soft lockup detector by unparking the watchdog threads.
*/
-void watchdog_resume(void)
+void lockup_detector_resume(void)
{
mutex_lock(&watchdog_proc_mutex);
--
1.7.11.7
Signed-off-by: Ulrich Obergfell <[email protected]>
---
arch/x86/kernel/cpu/perf_event_intel.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 0357bf7..abb25c3 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -3369,7 +3369,7 @@ static __init int fixup_ht_bug(void)
}
if (lockup_detector_suspend() != 0) {
- pr_info("failed to disable PMU erratum BJ122, BV98, HSD29 workaround\n");
+ pr_debug("failed to disable PMU erratum BJ122, BV98, HSD29 workaround\n");
return 0;
}
--
1.7.11.7
On Fri 2015-08-07 11:58 +0200, Ulrich Obergfell wrote:
> Rename watchdog_suspend() to lockup_detector_suspend() and
> watchdog_resume() to lockup_detector_resume() to avoid
> confusion with the watchdog subsystem and to be consistent
> with the existing name lockup_detector_init().
>
> Also provide comment blocks to explain the watchdog_running
> and watchdog_suspended variables and their relationship.
>
> Signed-off-by: Ulrich Obergfell <[email protected]>
> ---
> arch/x86/kernel/cpu/perf_event_intel.c | 4 ++--
> include/linux/nmi.h | 8 ++++----
> kernel/watchdog.c | 26 ++++++++++++++++++++++----
> 3 files changed, 28 insertions(+), 10 deletions(-)
>
> diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
> index d4e1b0c..0357bf7 100644
> --- a/arch/x86/kernel/cpu/perf_event_intel.c
> +++ b/arch/x86/kernel/cpu/perf_event_intel.c
> @@ -3368,7 +3368,7 @@ static __init int fixup_ht_bug(void)
> return 0;
> }
>
> - if (watchdog_suspend() != 0) {
> + if (lockup_detector_suspend() != 0) {
> pr_info("failed to disable PMU erratum BJ122, BV98, HSD29 workaround\n");
> return 0;
> }
> @@ -3379,7 +3379,7 @@ static __init int fixup_ht_bug(void)
> x86_pmu.commit_scheduling = NULL;
> x86_pmu.stop_scheduling = NULL;
>
> - watchdog_resume();
> + lockup_detector_resume();
>
> get_online_cpus();
>
> diff --git a/include/linux/nmi.h b/include/linux/nmi.h
> index 46e28e9e..78488e0 100644
> --- a/include/linux/nmi.h
> +++ b/include/linux/nmi.h
> @@ -84,15 +84,15 @@ extern int proc_watchdog_thresh(struct ctl_table *, int ,
> void __user *, size_t *, loff_t *);
> extern int proc_watchdog_cpumask(struct ctl_table *, int,
> void __user *, size_t *, loff_t *);
> -extern int watchdog_suspend(void);
> -extern void watchdog_resume(void);
> +extern int lockup_detector_suspend(void);
> +extern void lockup_detector_resume(void);
> #else
> -static inline int watchdog_suspend(void)
> +static inline int lockup_detector_suspend(void)
> {
> return 0;
> }
>
> -static inline void watchdog_resume(void)
> +static inline void lockup_detector_resume(void)
> {
> }
> #endif
> diff --git a/kernel/watchdog.c b/kernel/watchdog.c
> index 69666f4..64ed1c3 100644
> --- a/kernel/watchdog.c
> +++ b/kernel/watchdog.c
> @@ -67,8 +67,26 @@ unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask);
> #define for_each_watchdog_cpu(cpu) \
> for_each_cpu_and((cpu), cpu_online_mask, &watchdog_cpumask)
>
> -static int __read_mostly watchdog_suspended;
> +/*
> + * The 'watchdog_running' variable is set to 1 when the watchdog threads
> + * are registered/started and is set to 0 when the watchdog threads are
> + * unregistered/stopped, so it is an indicator whether the threads exist.
> + */
> static int __read_mostly watchdog_running;
> +/*
> + * If a subsystem has a need to deactivate the watchdog temporarily, it
> + * can use the suspend/resume interface to achieve this. The content of
> + * the 'watchdog_suspended' variable reflects this state. Existing threads
> + * are parked/unparked by the lockup_detector_{suspend|resume} functions
> + * (see comment blocks pertaining to those functions for further details).
> + *
> + * 'watchdog_suspended' also prevents threads from being registered/started
> + * or unregistered/stopped via parameters in /proc/sys/kernel, so the state
> + * of 'watchdog_running' cannot change while the watchdog is deactivated
> + * temporarily (see related code in 'proc' handlers).
> + */
> +static int __read_mostly watchdog_suspended;
> +
> static u64 __read_mostly sample_period;
>
> static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts);
> @@ -669,7 +687,7 @@ static void watchdog_unpark_threads(void)
> /*
> * Suspend the hard and soft lockup detector by parking the watchdog threads.
> */
> -int watchdog_suspend(void)
> +int lockup_detector_suspend(void)
> {
> int ret = 0;
>
> @@ -679,7 +697,7 @@ int watchdog_suspend(void)
> * the 'watchdog_suspended' variable). If the watchdog threads are
> * running, the first caller takes care that they will be parked.
> * The state of 'watchdog_running' cannot change while a suspend
> - * request is active (see related changes in 'proc' handlers).
> + * request is active (see related code in 'proc' handlers).
> */
> if (watchdog_running && !watchdog_suspended)
> ret = watchdog_park_threads();
> @@ -695,7 +713,7 @@ int watchdog_suspend(void)
> /*
> * Resume the hard and soft lockup detector by unparking the watchdog threads.
> */
> -void watchdog_resume(void)
> +void lockup_detector_resume(void)
> {
> mutex_lock(&watchdog_proc_mutex);
>
Reviewed-by: Aaron Tomlin <[email protected]>
--
Aaron Tomlin
On Fri 2015-08-07 11:58 +0200, Ulrich Obergfell wrote:
>
> Signed-off-by: Ulrich Obergfell <[email protected]>
> ---
> arch/x86/kernel/cpu/perf_event_intel.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
> index 0357bf7..abb25c3 100644
> --- a/arch/x86/kernel/cpu/perf_event_intel.c
> +++ b/arch/x86/kernel/cpu/perf_event_intel.c
> @@ -3369,7 +3369,7 @@ static __init int fixup_ht_bug(void)
> }
>
> if (lockup_detector_suspend() != 0) {
> - pr_info("failed to disable PMU erratum BJ122, BV98, HSD29 workaround\n");
> + pr_debug("failed to disable PMU erratum BJ122, BV98, HSD29 workaround\n");
> return 0;
> }
>
Reviewed-by: Aaron Tomlin <[email protected]>
--
Aaron Tomlin