Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1731174 > unrolled thread

[patch V2 00/29] lockup_detector: Cure hotplug deadlocks and replace duct tape

Back to article view | Back to linux.kernel

Contents

  [patch V2 00/29] lockup_detector: Cure hotplug deadlocks and replace  duct tape Thomas Gleixner <tglx@linutronix.de> - 2017-09-12 21:50 +0200
    [patch V2 14/29] lockup_detector: Split out cpumask write function Thomas Gleixner <tglx@linutronix.de> - 2017-09-12 21:50 +0200
      [tip:core/urgent] watchdog/core: Split out cpumask write function tip-bot for Thomas Gleixner <tipbot@zytor.com> - 2017-09-14 13:00 +0200
    [patch V2 05/29] lockup_detector: Remove broken suspend/resume  interfaces Thomas Gleixner <tglx@linutronix.de> - 2017-09-12 21:50 +0200
      [tip:core/urgent] watchdog/core: Remove broken suspend/resume  interfaces tip-bot for Thomas Gleixner <tipbot@zytor.com> - 2017-09-14 12:50 +0200
    [patch V2 16/29] lockup_detector: Create new thread handling  infrastructure Thomas Gleixner <tglx@linutronix.de> - 2017-09-12 21:50 +0200
      [tip:core/urgent] watchdog/core: Create new thread handling  infrastructure tip-bot for Thomas Gleixner <tipbot@zytor.com> - 2017-09-14 13:00 +0200
    [patch V2 01/29] hardlockup_detector: Provide interface to  stop/restart perf events Thomas Gleixner <tglx@linutronix.de> - 2017-09-12 21:50 +0200
      [tip:core/urgent] watchdog/hardlockup: Provide interface to  stop/restart perf events tip-bot for Peter Zijlstra <tipbot@zytor.com> - 2017-09-14 12:50 +0200
    [patch V2 26/29] lockup_detector/perf: Implement CPU enable  replacement Thomas Gleixner <tglx@linutronix.de> - 2017-09-12 22:00 +0200
      [tip:core/urgent] watchdog/hardlockup/perf: Implement CPU enable  replacement tip-bot for Thomas Gleixner <tipbot@zytor.com> - 2017-09-14 13:00 +0200
    [patch V2 06/29] lockup_detector: Rework cpu hotplug locking Thomas Gleixner <tglx@linutronix.de> - 2017-09-12 22:00 +0200
      [tip:core/urgent] watchdog/core: Rework CPU hotplug locking tip-bot for Thomas Gleixner <tipbot@zytor.com> - 2017-09-14 12:50 +0200
    [patch V2 28/29] lockup_detector/perf: Simplify deferred event destroy Thomas Gleixner <tglx@linutronix.de> - 2017-09-12 22:00 +0200
      [tip:core/urgent] watchdog/hardlockup/perf: Simplify deferred event  destroy tip-bot for Thomas Gleixner <tipbot@zytor.com> - 2017-09-14 13:00 +0200
    [patch V2 04/29] parisc: Use lockup_detector_stop() Thomas Gleixner <tglx@linutronix.de> - 2017-09-12 22:00 +0200
      Re: [patch V2 04/29] parisc: Use lockup_detector_stop() Helge Deller <deller@gmx.de> - 2017-09-14 11:10 +0200
        Re: [patch V2 04/29] parisc: Use lockup_detector_stop() Don Zickus <dzickus@redhat.com> - 2017-09-14 15:50 +0200
      [tip:core/urgent] parisc, watchdog/core: Use lockup_detector_stop() tip-bot for Thomas Gleixner <tipbot@zytor.com> - 2017-09-14 12:50 +0200
    [patch V2 17/29] lockup_detector: Get rid of the thread  teardown/setup dance Thomas Gleixner <tglx@linutronix.de> - 2017-09-12 22:00 +0200
      [tip:core/urgent] watchdog/core: Get rid of the thread  teardown/setup dance tip-bot for Thomas Gleixner <tipbot@zytor.com> - 2017-09-14 13:00 +0200
    [patch V2 03/29] lockup_detector: Provide interface to stop from  poweroff() Thomas Gleixner <tglx@linutronix.de> - 2017-09-12 22:00 +0200
      [tip:core/urgent] watchdog/core: Provide interface to stop from  poweroff() tip-bot for Thomas Gleixner <tipbot@zytor.com> - 2017-09-14 12:50 +0200
    [patch V2 10/29] lockup_detector/perf: Prevent cpu hotplug deadlock Thomas Gleixner <tglx@linutronix.de> - 2017-09-12 22:00 +0200
      [tip:core/urgent] watchdog/hardlockup/perf: Prevent CPU hotplug  deadlock tip-bot for Thomas Gleixner <tipbot@zytor.com> - 2017-09-14 12:50 +0200
    [patch V2 13/29] lockup_detector: Cleanup the ifdef maze Thomas Gleixner <tglx@linutronix.de> - 2017-09-12 22:00 +0200
      [tip:core/urgent] watchdog/core: Clean up the #ifdef maze tip-bot for Thomas Gleixner <tipbot@zytor.com> - 2017-09-14 13:00 +0200
    [patch V2 29/29] lockup_detector: Cleanup hotplug locking mess Thomas Gleixner <tglx@linutronix.de> - 2017-09-12 22:00 +0200
      [tip:core/urgent] watchdog/hardlockup: Clean up hotplug locking  mess tip-bot for Thomas Gleixner <tipbot@zytor.com> - 2017-09-14 13:00 +0200
    [patch V2 09/29] lockup_detector/perf: Remove broken self disable on  failure Thomas Gleixner <tglx@linutronix.de> - 2017-09-12 22:00 +0200
      [tip:core/urgent] watchdog/hardlockup/perf: Remove broken self  disable on failure tip-bot for Thomas Gleixner <tipbot@zytor.com> - 2017-09-14 12:50 +0200
    [patch V2 08/29] lockup_detector: Mark hardlockup_detector_disable()  __init Thomas Gleixner <tglx@linutronix.de> - 2017-09-12 22:00 +0200
      [tip:core/urgent] watchdog/core: Mark hardlockup_detector_disable()  __init tip-bot for Thomas Gleixner <tipbot@zytor.com> - 2017-09-14 12:50 +0200
    [patch V2 18/29] lockup_detector: Further simplify sysctl handling Thomas Gleixner <tglx@linutronix.de> - 2017-09-12 22:00 +0200
      [tip:core/urgent] watchdog/core: Further simplify sysctl handling tip-bot for Thomas Gleixner <tipbot@zytor.com> - 2017-09-14 13:00 +0200
    [patch V2 12/29] lockup_detector: Cleanup stub functions Thomas Gleixner <tglx@linutronix.de> - 2017-09-12 22:00 +0200
      [tip:core/urgent] watchdog/core: Clean up stub functions tip-bot for Thomas Gleixner <tipbot@zytor.com> - 2017-09-14 13:00 +0200
    [patch V2 15/29] smpboot/threads: Avoid runtime allocation Thomas Gleixner <tglx@linutronix.de> - 2017-09-12 22:00 +0200
      [tip:core/urgent] smpboot/threads, watchdog/core: Avoid runtime  allocation tip-bot for Thomas Gleixner <tipbot@zytor.com> - 2017-09-14 13:00 +0200
    [patch V2 20/29] lockup_detector/sysctl: Get rid of the ifdeffery Thomas Gleixner <tglx@linutronix.de> - 2017-09-12 22:00 +0200
      [tip:core/urgent] watchdog/sysctl: Get rid of the #ifdeffery tip-bot for Thomas Gleixner <tipbot@zytor.com> - 2017-09-14 13:00 +0200
    [patch V2 27/29] lockup_detector: Use new perf CPU enable mechanism Thomas Gleixner <tglx@linutronix.de> - 2017-09-12 22:00 +0200
      [tip:core/urgent] watchdog/hardlockup/perf: Use new perf CPU enable  mechanism tip-bot for Thomas Gleixner <tipbot@zytor.com> - 2017-09-14 13:00 +0200
    [patch V2 24/29] lockup_detector/perf: Implement init time perf  validation Thomas Gleixner <tglx@linutronix.de> - 2017-09-12 22:00 +0200
      [tip:core/urgent] watchdog/hardlockup/perf: Implement init time  perf validation tip-bot for Thomas Gleixner <tipbot@zytor.com> - 2017-09-14 13:00 +0200
    [patch V2 19/29] lockup_detector: Cleanup header mess Thomas Gleixner <tglx@linutronix.de> - 2017-09-12 22:00 +0200
      [tip:core/urgent] watchdog/core: Clean up header mess tip-bot for Thomas Gleixner <tipbot@zytor.com> - 2017-09-14 13:00 +0200
    [patch V2 22/29] lockup_detector: Make watchdog_nmi_reconfigure() two  stage Thomas Gleixner <tglx@linutronix.de> - 2017-09-12 22:00 +0200
      [tip:core/urgent] watchdog/core, powerpc: Make  watchdog_nmi_reconfigure() two stage tip-bot for Thomas Gleixner <tipbot@zytor.com> - 2017-09-14 13:00 +0200
    [patch V2 25/29] lockup_detector: Implement init time detection of  perf Thomas Gleixner <tglx@linutronix.de> - 2017-09-12 22:00 +0200
      Re: [patch V2 25/29] lockup_detector: Implement init time detection  of perf Don Zickus <dzickus@redhat.com> - 2017-09-13 20:10 +0200
        Re: [patch V2 25/29] lockup_detector: Implement init time detection  of perf Thomas Gleixner <tglx@linutronix.de> - 2017-09-13 20:10 +0200
          Re: [patch V2 25/29] lockup_detector: Implement init time detection  of perf Ingo Molnar <mingo@kernel.org> - 2017-09-14 07:30 +0200
      [tip:core/urgent] watchdog/hardlockup/perf: Implement init time  detection of perf tip-bot for Thomas Gleixner <tipbot@zytor.com> - 2017-09-14 13:00 +0200
    [patch V2 23/29] lockup_detector: Get rid of the racy update loop Thomas Gleixner <tglx@linutronix.de> - 2017-09-12 22:00 +0200
      [tip:core/urgent] watchdog/core: Get rid of the racy update loop tip-bot for Thomas Gleixner <tipbot@zytor.com> - 2017-09-14 13:00 +0200
    Re: [patch V2 00/29] lockup_detector: Cure hotplug deadlocks and  replace duct tape Don Zickus <dzickus@redhat.com> - 2017-09-13 20:10 +0200
      Re: [patch V2 00/29] lockup_detector: Cure hotplug deadlocks and  replace duct tape Ingo Molnar <mingo@kernel.org> - 2017-09-14 07:30 +0200
      Re: [patch V2 00/29] lockup_detector: Cure hotplug deadlocks and  replace duct tape Thomas Gleixner <tglx@linutronix.de> - 2017-09-14 10:20 +0200

Page 1 of 3  [1] 2 3  Next page →

#1731174 — [patch V2 00/29] lockup_detector: Cure hotplug deadlocks and replace duct tape

The lockup detector is broken is several ways:

    - It's deadlock prone vs. CPU hotplug in various ways. Some of these
      are due to recursive cpus_read_lock() others are due to
      cpus_read_lock() from CPU hotplug callbacks which immediately lock
      the machine because cpus are write locked.

    - The handling of the cpu hotplug threads happens sideways to the
      smpboot thread infrastructure, which is racy and pointless

    - The handling of the user space sysctl interface is a complete
      trainwreck as it fiddles directly with variables which can be
      modified or evaluated by the running watchdogs.

    - The perf event initialization is a trainwreck as it tries to create
      perf events over and over even if perf is not functional (no
      hardware, ....). To avoid excessive dmesg spam it contains magic
      printk ratelimiting along with either wrong or useless messages.

    - The code structure is horrible as ifdef sections are scattered all
      over the place which makes it unreadable

    - There is more wreckage, but see the changelogs for the ugly details.

The following series sanitizes the facility and addresses the problems.

Changes since V1:

    - Wrapped the perf specific calls into the weak watchdog_nmi_*
      functions

    - Fixed the compile error pointed out by Don

    - Fixed the reconfiguration parameter inconsistency which broke
      powerpc

    - Picked up the updated version of patch 11/29

Delta patch below.

Thanks,

        tglx
---
Diffstat for the series:

 arch/parisc/kernel/process.c   |    2 
 arch/powerpc/kernel/watchdog.c |   22 -
 arch/x86/events/intel/core.c   |   11 
 include/linux/nmi.h            |  121 +++----
 include/linux/smpboot.h        |    4 
 kernel/cpu.c                   |    6 
 kernel/smpboot.c               |   22 -
 kernel/sysctl.c                |   22 -
 kernel/watchdog.c              |  633 ++++++++++++++---------------------------
 kernel/watchdog_hld.c          |  193 ++++++------
 10 files changed, 434 insertions(+), 602 deletions(-)

Delta patch vs. V1
8<------------------------
--- a/arch/powerpc/kernel/watchdog.c
+++ b/arch/powerpc/kernel/watchdog.c
@@ -355,12 +355,12 @@ static void watchdog_calc_timeouts(void)
 	wd_timer_period_ms = watchdog_thresh * 1000 * 2 / 5;
 }
 
-void watchdog_nmi_reconfigure(bool stop)
+void watchdog_nmi_reconfigure(bool run)
 {
 	int cpu;
 
 	cpus_read_lock();
-	if (stop) {
+	if (!run) {
 		for_each_cpu(cpu, &wd_cpus_enabled)
 			stop_wd_on_cpu(cpu);
 	} else {
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -102,7 +102,7 @@ static inline void hardlockup_detector_p
 static inline void hardlockup_detector_perf_enable(void) { }
 static inline void hardlockup_detector_perf_cleanup(void) { }
 # if !defined(CONFIG_HAVE_NMI_WATCHDOG)
-static int hardlockup_detector_perf_init(void) { return -ENODEV; }
+static inline int hardlockup_detector_perf_init(void) { return -ENODEV; }
 static inline void arch_touch_nmi_watchdog(void) {}
 # else
 static int hardlockup_detector_perf_init(void) { return 0; }
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -105,18 +105,32 @@ static int __init hardlockup_all_cpu_bac
  * softlockup watchdog threads start and stop. The arch must select the
  * SOFTLOCKUP_DETECTOR Kconfig.
  */
-int __weak watchdog_nmi_enable(unsigned int cpu) { return 0; }
-void __weak watchdog_nmi_disable(unsigned int cpu) { }
+int __weak watchdog_nmi_enable(unsigned int cpu)
+{
+	hardlockup_detector_perf_enable();
+	return 0;
+}
+
+void __weak watchdog_nmi_disable(unsigned int cpu)
+{
+	hardlockup_detector_perf_disable();
+}
+
+/* Return 0, if a NMI watchdog is available. Error code otherwise */
+int __weak __init void watchdog_nmi_probe(void)
+{
+	return hardlockup_detector_perf_init();
+}
 
 /**
  * watchdog_nmi_reconfigure - Optional function to reconfigure NMI watchdogs
- * @stop:	If true stop the watchdogs on all enabled CPUs
- *		If false start the watchdogs on all enabled CPUs
+ * @run:	If false stop the watchdogs on all enabled CPUs
+ *		If true start the watchdogs on all enabled CPUs
  *
  * The core call order is:
- * watchdog_nmi_reconfigure(true);
- * update_variables();
  * watchdog_nmi_reconfigure(false);
+ * update_variables();
+ * watchdog_nmi_reconfigure(true);
  *
  * The second call which starts the watchdogs again guarantees that the
  * following variables are stable across the call.
@@ -126,13 +140,13 @@ void __weak watchdog_nmi_disable(unsigne
  *
  * After the call the variables can be changed again.
  */
-void __weak watchdog_nmi_reconfigure(bool stop) { }
+void __weak watchdog_nmi_reconfigure(bool run) { }
 
 /**
  * lockup_detector_update_enable - Update the sysctl enable bit
  *
  * Caller needs to make sure that the NMI/perf watchdogs are off, so this
- * can't race with hardlockup_detector_disable().
+ * can't race with watchdog_nmi_disable().
  */
 static void lockup_detector_update_enable(void)
 {
@@ -453,8 +467,7 @@ static void watchdog_enable(unsigned int
 	__touch_watchdog();
 	/* Enable the perf event */
 	if (watchdog_enabled & NMI_WATCHDOG_ENABLED)
-		hardlockup_detector_perf_enable();
-	watchdog_nmi_enable(cpu);
+		watchdog_nmi_enable(cpu);
 
 	watchdog_set_prio(SCHED_FIFO, MAX_RT_PRIO - 1);
 }
@@ -469,7 +482,6 @@ static void watchdog_disable(unsigned in
 	 * between disabling the timer and disabling the perf event causes
 	 * the perf NMI to detect a false positive.
 	 */
-	hardlockup_detector_perf_disable();
 	watchdog_nmi_disable(cpu);
 	hrtimer_cancel(hrtimer);
 }
@@ -745,12 +757,6 @@ int proc_watchdog_cpumask(struct ctl_tab
 }
 #endif /* CONFIG_SYSCTL */
 
-static __init void detect_nmi_watchdog(void)
-{
-	if (!hardlockup_detector_perf_init())
-		nmi_watchdog_available = true;
-}
-
 void __init lockup_detector_init(void)
 {
 #ifdef CONFIG_NO_HZ_FULL
@@ -763,6 +769,7 @@ void __init lockup_detector_init(void)
 	cpumask_copy(&watchdog_cpumask, cpu_possible_mask);
 #endif
 
-	detect_nmi_watchdog();
+	if (!watchdog_nmi_probe())
+		nmi_watchdog_available = true;
 	softlockup_init_threads();
 }

[toc] | [next] | [standalone]

#1731175 — [patch V2 14/29] lockup_detector: Split out cpumask write function

Split the write part of the cpumask proc handler out into a separate helper
to avoid deep indentation. This also reduces the patch complexity in the
following cleanups.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Chris Metcalf <cmetcalf@mellanox.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sebastian Siewior <bigeasy@linutronix.de>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Ulrich Obergfell <uobergfe@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/20170831073054.098896932@linutronix.de

---
 kernel/watchdog.c |   40 +++++++++++++++++++++-------------------
 1 file changed, 21 insertions(+), 19 deletions(-)

--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -792,10 +792,29 @@ static int watchdog_update_cpus(void)
 	if (IS_ENABLED(CONFIG_SOFTLOCKUP_DETECTOR)) {
 		return smpboot_update_cpumask_percpu_thread(&watchdog_threads,
 							    &watchdog_cpumask);
+		__lockup_detector_cleanup();
 	}
 	return 0;
 }
 
+static void proc_watchdog_cpumask_update(void)
+{
+	/* Remove impossible cpus to keep sysctl output clean. */
+	cpumask_and(&watchdog_cpumask, &watchdog_cpumask, cpu_possible_mask);
+
+	if (watchdog_running) {
+		/*
+		 * Failure would be due to being unable to allocate a
+		 * temporary cpumask, so we are likely not in a position to
+		 * do much else to make things better.
+		 */
+		if (watchdog_update_cpus() != 0)
+			pr_err("cpumask update failed\n");
+	}
+
+	watchdog_nmi_reconfigure();
+}
+
 /*
  * The cpumask is the mask of possible cpus that the watchdog can run
  * on, not the mask of cpus it is actually running on.  This allows the
@@ -811,30 +830,13 @@ int proc_watchdog_cpumask(struct ctl_tab
 	mutex_lock(&watchdog_mutex);
 
 	err = proc_do_large_bitmap(table, write, buffer, lenp, ppos);
-	if (!err && write) {
-		/* Remove impossible cpus to keep sysctl output cleaner. */
-		cpumask_and(&watchdog_cpumask, &watchdog_cpumask,
-			    cpu_possible_mask);
-
-		if (watchdog_running) {
-			/*
-			 * Failure would be due to being unable to allocate
-			 * a temporary cpumask, so we are likely not in a
-			 * position to do much else to make things better.
-			 */
-			if (watchdog_update_cpus() != 0)
-				pr_err("cpumask update failed\n");
-		}
-
-		watchdog_nmi_reconfigure();
-		__lockup_detector_cleanup();
-	}
+	if (!err && write)
+		proc_watchdog_cpumask_update();
 
 	mutex_unlock(&watchdog_mutex);
 	cpu_hotplug_enable();
 	return err;
 }
-
 #endif /* CONFIG_SYSCTL */
 
 void __init lockup_detector_init(void)

[toc] | [prev] | [next] | [standalone]

#1732194 — [tip:core/urgent] watchdog/core: Split out cpumask write function

Commit-ID:  05ba3de74a3f499dcaa37b186220aaf174c95a4b
Gitweb:     http://git.kernel.org/tip/05ba3de74a3f499dcaa37b186220aaf174c95a4b
Author:     Thomas Gleixner <tglx@linutronix.de>
AuthorDate: Tue, 12 Sep 2017 21:37:08 +0200
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Thu, 14 Sep 2017 11:41:06 +0200

watchdog/core: Split out cpumask write function

Split the write part of the cpumask proc handler out into a separate helper
to avoid deep indentation. This also reduces the patch complexity in the
following cleanups.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Don Zickus <dzickus@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Chris Metcalf <cmetcalf@mellanox.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sebastian Siewior <bigeasy@linutronix.de>
Cc: Ulrich Obergfell <uobergfe@redhat.com>
Link: http://lkml.kernel.org/r/20170912194147.218075991@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/watchdog.c | 40 +++++++++++++++++++++-------------------
 1 file changed, 21 insertions(+), 19 deletions(-)

diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index a9bdfde..cedf45a 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -792,10 +792,29 @@ static int watchdog_update_cpus(void)
 	if (IS_ENABLED(CONFIG_SOFTLOCKUP_DETECTOR)) {
 		return smpboot_update_cpumask_percpu_thread(&watchdog_threads,
 							    &watchdog_cpumask);
+		__lockup_detector_cleanup();
 	}
 	return 0;
 }
 
+static void proc_watchdog_cpumask_update(void)
+{
+	/* Remove impossible cpus to keep sysctl output clean. */
+	cpumask_and(&watchdog_cpumask, &watchdog_cpumask, cpu_possible_mask);
+
+	if (watchdog_running) {
+		/*
+		 * Failure would be due to being unable to allocate a
+		 * temporary cpumask, so we are likely not in a position to
+		 * do much else to make things better.
+		 */
+		if (watchdog_update_cpus() != 0)
+			pr_err("cpumask update failed\n");
+	}
+
+	watchdog_nmi_reconfigure();
+}
+
 /*
  * The cpumask is the mask of possible cpus that the watchdog can run
  * on, not the mask of cpus it is actually running on.  This allows the
@@ -811,30 +830,13 @@ int proc_watchdog_cpumask(struct ctl_table *table, int write,
 	mutex_lock(&watchdog_mutex);
 
 	err = proc_do_large_bitmap(table, write, buffer, lenp, ppos);
-	if (!err && write) {
-		/* Remove impossible cpus to keep sysctl output cleaner. */
-		cpumask_and(&watchdog_cpumask, &watchdog_cpumask,
-			    cpu_possible_mask);
-
-		if (watchdog_running) {
-			/*
-			 * Failure would be due to being unable to allocate
-			 * a temporary cpumask, so we are likely not in a
-			 * position to do much else to make things better.
-			 */
-			if (watchdog_update_cpus() != 0)
-				pr_err("cpumask update failed\n");
-		}
-
-		watchdog_nmi_reconfigure();
-		__lockup_detector_cleanup();
-	}
+	if (!err && write)
+		proc_watchdog_cpumask_update();
 
 	mutex_unlock(&watchdog_mutex);
 	cpu_hotplug_enable();
 	return err;
 }
-
 #endif /* CONFIG_SYSCTL */
 
 void __init lockup_detector_init(void)

[toc] | [prev] | [next] | [standalone]

#1731176 — [patch V2 05/29] lockup_detector: Remove broken suspend/resume interfaces

This interface has several issues:

 - It's causing recursive locking of the hotplug lock.

 - It's complete overkill to teardown all threads and then recreate them

The same can be achieved with the simple hardlockup_detector_perf_stop /
restart() interfaces. The abuse from the busy looping poweroff() loop of
PARISC has been solved as well.

Remove the cruft.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Chris Metcalf <cmetcalf@mellanox.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sebastian Siewior <bigeasy@linutronix.de>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Ulrich Obergfell <uobergfe@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/20170831073053.359128818@linutronix.de

---
 arch/powerpc/kernel/watchdog.c |    3 -
 include/linux/nmi.h            |   12 -----
 kernel/watchdog.c              |   89 -----------------------------------------
 3 files changed, 1 insertion(+), 103 deletions(-)

--- a/arch/powerpc/kernel/watchdog.c
+++ b/arch/powerpc/kernel/watchdog.c
@@ -310,9 +310,6 @@ static int start_wd_on_cpu(unsigned int
 	if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED))
 		return 0;
 
-	if (watchdog_suspended)
-		return 0;
-
 	if (!cpumask_test_cpu(cpu, &watchdog_cpumask))
 		return 0;
 
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -164,7 +164,6 @@ extern int watchdog_thresh;
 extern unsigned long watchdog_enabled;
 extern struct cpumask watchdog_cpumask;
 extern unsigned long *watchdog_cpumask_bits;
-extern int __read_mostly watchdog_suspended;
 #ifdef CONFIG_SMP
 extern int sysctl_softlockup_all_cpu_backtrace;
 extern int sysctl_hardlockup_all_cpu_backtrace;
@@ -192,17 +191,6 @@ extern int proc_watchdog_thresh(struct c
 				void __user *, size_t *, loff_t *);
 extern int proc_watchdog_cpumask(struct ctl_table *, int,
 				 void __user *, size_t *, loff_t *);
-extern int lockup_detector_suspend(void);
-extern void lockup_detector_resume(void);
-#else
-static inline int lockup_detector_suspend(void)
-{
-	return 0;
-}
-
-static inline void lockup_detector_resume(void)
-{
-}
 #endif
 
 #ifdef CONFIG_HAVE_ACPI_APEI_NMI
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -97,19 +97,6 @@ unsigned long *watchdog_cpumask_bits = c
  * 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).
- */
-int __read_mostly watchdog_suspended;
 
 /*
  * These functions can be overridden if an architecture implements its
@@ -136,7 +123,6 @@ void __weak watchdog_nmi_disable(unsigne
  * - watchdog_cpumask
  * - sysctl_hardlockup_all_cpu_backtrace
  * - hardlockup_panic
- * - watchdog_suspended
  */
 void __weak watchdog_nmi_reconfigure(void)
 {
@@ -672,61 +658,6 @@ void lockup_detector_soft_poweroff(void)
 	watchdog_enabled = 0;
 }
 
-/*
- * Suspend the hard and soft lockup detector by parking the watchdog threads.
- */
-int lockup_detector_suspend(void)
-{
-	int ret = 0;
-
-	get_online_cpus();
-	mutex_lock(&watchdog_proc_mutex);
-	/*
-	 * Multiple suspend requests can be active in parallel (counted by
-	 * 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 code in 'proc' handlers).
-	 */
-	if (watchdog_running && !watchdog_suspended)
-		ret = watchdog_park_threads();
-
-	if (ret == 0)
-		watchdog_suspended++;
-	else {
-		watchdog_disable_all_cpus();
-		pr_err("Failed to suspend lockup detectors, disabled\n");
-		watchdog_enabled = 0;
-	}
-
-	watchdog_nmi_reconfigure();
-
-	mutex_unlock(&watchdog_proc_mutex);
-
-	return ret;
-}
-
-/*
- * Resume the hard and soft lockup detector by unparking the watchdog threads.
- */
-void lockup_detector_resume(void)
-{
-	mutex_lock(&watchdog_proc_mutex);
-
-	watchdog_suspended--;
-	/*
-	 * The watchdog threads are unparked if they were previously running
-	 * and if there is no more active suspend request.
-	 */
-	if (watchdog_running && !watchdog_suspended)
-		watchdog_unpark_threads();
-
-	watchdog_nmi_reconfigure();
-
-	mutex_unlock(&watchdog_proc_mutex);
-	put_online_cpus();
-}
-
 #ifdef CONFIG_SYSCTL
 
 /*
@@ -775,12 +706,6 @@ static int proc_watchdog_common(int whic
 	get_online_cpus();
 	mutex_lock(&watchdog_proc_mutex);
 
-	if (watchdog_suspended) {
-		/* no parameter changes allowed while watchdog is suspended */
-		err = -EAGAIN;
-		goto out;
-	}
-
 	/*
 	 * If the parameter is being read return the state of the corresponding
 	 * bit(s) in 'watchdog_enabled', else update 'watchdog_enabled' and the
@@ -872,12 +797,6 @@ int proc_watchdog_thresh(struct ctl_tabl
 	get_online_cpus();
 	mutex_lock(&watchdog_proc_mutex);
 
-	if (watchdog_suspended) {
-		/* no parameter changes allowed while watchdog is suspended */
-		err = -EAGAIN;
-		goto out;
-	}
-
 	old = ACCESS_ONCE(watchdog_thresh);
 	err = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 
@@ -917,12 +836,6 @@ int proc_watchdog_cpumask(struct ctl_tab
 	get_online_cpus();
 	mutex_lock(&watchdog_proc_mutex);
 
-	if (watchdog_suspended) {
-		/* no parameter changes allowed while watchdog is suspended */
-		err = -EAGAIN;
-		goto out;
-	}
-
 	err = proc_do_large_bitmap(table, write, buffer, lenp, ppos);
 	if (!err && write) {
 		/* Remove impossible cpus to keep sysctl output cleaner. */
@@ -941,7 +854,7 @@ int proc_watchdog_cpumask(struct ctl_tab
 
 		watchdog_nmi_reconfigure();
 	}
-out:
+
 	mutex_unlock(&watchdog_proc_mutex);
 	put_online_cpus();
 	return err;

[toc] | [prev] | [next] | [standalone]

#1732185 — [tip:core/urgent] watchdog/core: Remove broken suspend/resume interfaces

Commit-ID:  5490125d77a43016b26f629d4b485e2c62172551
Gitweb:     http://git.kernel.org/tip/5490125d77a43016b26f629d4b485e2c62172551
Author:     Thomas Gleixner <tglx@linutronix.de>
AuthorDate: Tue, 12 Sep 2017 21:36:59 +0200
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Thu, 14 Sep 2017 11:41:04 +0200

watchdog/core: Remove broken suspend/resume interfaces

This interface has several issues:

 - It's causing recursive locking of the hotplug lock.

 - It's complete overkill to teardown all threads and then recreate them

The same can be achieved with the simple hardlockup_detector_perf_stop /
restart() interfaces. The abuse from the busy looping poweroff() loop of
PARISC has been solved as well.

Remove the cruft.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Don Zickus <dzickus@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Chris Metcalf <cmetcalf@mellanox.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sebastian Siewior <bigeasy@linutronix.de>
Cc: Ulrich Obergfell <uobergfe@redhat.com>
Link: http://lkml.kernel.org/r/20170912194146.487537732@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/powerpc/kernel/watchdog.c |  3 --
 include/linux/nmi.h            | 12 ------
 kernel/watchdog.c              | 89 +-----------------------------------------
 3 files changed, 1 insertion(+), 103 deletions(-)

diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c
index 2f6eadd..5ded171 100644
--- a/arch/powerpc/kernel/watchdog.c
+++ b/arch/powerpc/kernel/watchdog.c
@@ -310,9 +310,6 @@ static int start_wd_on_cpu(unsigned int cpu)
 	if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED))
 		return 0;
 
-	if (watchdog_suspended)
-		return 0;
-
 	if (!cpumask_test_cpu(cpu, &watchdog_cpumask))
 		return 0;
 
diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index 85bb268b..7eefe7a 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -164,7 +164,6 @@ extern int watchdog_thresh;
 extern unsigned long watchdog_enabled;
 extern struct cpumask watchdog_cpumask;
 extern unsigned long *watchdog_cpumask_bits;
-extern int __read_mostly watchdog_suspended;
 #ifdef CONFIG_SMP
 extern int sysctl_softlockup_all_cpu_backtrace;
 extern int sysctl_hardlockup_all_cpu_backtrace;
@@ -192,17 +191,6 @@ 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 lockup_detector_suspend(void);
-extern void lockup_detector_resume(void);
-#else
-static inline int lockup_detector_suspend(void)
-{
-	return 0;
-}
-
-static inline void lockup_detector_resume(void)
-{
-}
 #endif
 
 #ifdef CONFIG_HAVE_ACPI_APEI_NMI
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index f23e373..b2d4675 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -97,19 +97,6 @@ unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask);
  * 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).
- */
-int __read_mostly watchdog_suspended;
 
 /*
  * These functions can be overridden if an architecture implements its
@@ -136,7 +123,6 @@ void __weak watchdog_nmi_disable(unsigned int cpu)
  * - watchdog_cpumask
  * - sysctl_hardlockup_all_cpu_backtrace
  * - hardlockup_panic
- * - watchdog_suspended
  */
 void __weak watchdog_nmi_reconfigure(void)
 {
@@ -672,61 +658,6 @@ void lockup_detector_soft_poweroff(void)
 	watchdog_enabled = 0;
 }
 
-/*
- * Suspend the hard and soft lockup detector by parking the watchdog threads.
- */
-int lockup_detector_suspend(void)
-{
-	int ret = 0;
-
-	get_online_cpus();
-	mutex_lock(&watchdog_proc_mutex);
-	/*
-	 * Multiple suspend requests can be active in parallel (counted by
-	 * 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 code in 'proc' handlers).
-	 */
-	if (watchdog_running && !watchdog_suspended)
-		ret = watchdog_park_threads();
-
-	if (ret == 0)
-		watchdog_suspended++;
-	else {
-		watchdog_disable_all_cpus();
-		pr_err("Failed to suspend lockup detectors, disabled\n");
-		watchdog_enabled = 0;
-	}
-
-	watchdog_nmi_reconfigure();
-
-	mutex_unlock(&watchdog_proc_mutex);
-
-	return ret;
-}
-
-/*
- * Resume the hard and soft lockup detector by unparking the watchdog threads.
- */
-void lockup_detector_resume(void)
-{
-	mutex_lock(&watchdog_proc_mutex);
-
-	watchdog_suspended--;
-	/*
-	 * The watchdog threads are unparked if they were previously running
-	 * and if there is no more active suspend request.
-	 */
-	if (watchdog_running && !watchdog_suspended)
-		watchdog_unpark_threads();
-
-	watchdog_nmi_reconfigure();
-
-	mutex_unlock(&watchdog_proc_mutex);
-	put_online_cpus();
-}
-
 #ifdef CONFIG_SYSCTL
 
 /*
@@ -775,12 +706,6 @@ static int proc_watchdog_common(int which, struct ctl_table *table, int write,
 	get_online_cpus();
 	mutex_lock(&watchdog_proc_mutex);
 
-	if (watchdog_suspended) {
-		/* no parameter changes allowed while watchdog is suspended */
-		err = -EAGAIN;
-		goto out;
-	}
-
 	/*
 	 * If the parameter is being read return the state of the corresponding
 	 * bit(s) in 'watchdog_enabled', else update 'watchdog_enabled' and the
@@ -872,12 +797,6 @@ int proc_watchdog_thresh(struct ctl_table *table, int write,
 	get_online_cpus();
 	mutex_lock(&watchdog_proc_mutex);
 
-	if (watchdog_suspended) {
-		/* no parameter changes allowed while watchdog is suspended */
-		err = -EAGAIN;
-		goto out;
-	}
-
 	old = ACCESS_ONCE(watchdog_thresh);
 	err = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 
@@ -917,12 +836,6 @@ int proc_watchdog_cpumask(struct ctl_table *table, int write,
 	get_online_cpus();
 	mutex_lock(&watchdog_proc_mutex);
 
-	if (watchdog_suspended) {
-		/* no parameter changes allowed while watchdog is suspended */
-		err = -EAGAIN;
-		goto out;
-	}
-
 	err = proc_do_large_bitmap(table, write, buffer, lenp, ppos);
 	if (!err && write) {
 		/* Remove impossible cpus to keep sysctl output cleaner. */
@@ -941,7 +854,7 @@ int proc_watchdog_cpumask(struct ctl_table *table, int write,
 
 		watchdog_nmi_reconfigure();
 	}
-out:
+
 	mutex_unlock(&watchdog_proc_mutex);
 	put_online_cpus();
 	return err;

[toc] | [prev] | [next] | [standalone]

#1731177 — [patch V2 16/29] lockup_detector: Create new thread handling infrastructure

The lockup detector reconfiguration tears down all watchdog threads when
the watchdog is disabled and sets them up again when its enabled.

That's a pointless exercise. The watchdog threads are not consuming an
insane amount of resources, so it's enough to set them up at init time and
keep them in parked position when the watchdog is disabled and unpark them
when it is reenabled. The smpboot thread infrastructure takes care of
keeping the force parked threads in place even across cpu hotplug.

Another horrible mechanism are the open coded park/unpark loops which are
used for reconfiguration of the watchdog. The smpboot infrastructure allows
exactly the same via smpboot_update_cpumask_thread_percpu(), which is cpu
hotplug safe. Using that instead of the open coded loops allows to get rid
of the hotplug locking mess in the watchdog code.

Implement a clean infrastructure which allows to replace the open coded
nonsense.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Chris Metcalf <cmetcalf@mellanox.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sebastian Siewior <bigeasy@linutronix.de>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Ulrich Obergfell <uobergfe@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/20170831073054.260048944@linutronix.de

---
 kernel/watchdog.c |   75 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 75 insertions(+)

--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -139,6 +139,9 @@ unsigned int __read_mostly softlockup_pa
 			CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE;
 int __read_mostly soft_watchdog_enabled;
 
+struct cpumask watchdog_allowed_mask __read_mostly;
+static bool softlockup_threads_initialized __read_mostly;
+
 static u64 __read_mostly sample_period;
 
 static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts);
@@ -584,12 +587,84 @@ static void watchdog_disable_all_cpus(vo
 	}
 }
 
+static void softlockup_update_smpboot_threads(void)
+{
+	lockdep_assert_held(&watchdog_mutex);
+
+	if (!softlockup_threads_initialized)
+		return;
+
+	smpboot_update_cpumask_percpu_thread(&watchdog_threads,
+					     &watchdog_allowed_mask);
+	__lockup_detector_cleanup();
+}
+
+/* Temporarily park all watchdog threads */
+static void softlockup_park_all_threads(void)
+{
+	cpumask_clear(&watchdog_allowed_mask);
+	softlockup_update_smpboot_threads();
+}
+
+/*
+ * Park threads which are not longer enabled and unpark threads which have
+ * been newly enabled.
+ */
+static void softlockup_update_threads(void)
+{
+	cpumask_copy(&watchdog_allowed_mask, &watchdog_cpumask);
+	softlockup_update_smpboot_threads();
+}
+
+static void softlockup_reconfigure_threads(bool enabled)
+{
+	softlockup_park_all_threads();
+	set_sample_period();
+	if (enabled)
+		softlockup_update_threads();
+}
+
+/*
+ * Create the watchdog thread infrastructure.
+ *
+ * The threads are not unparked as watchdog_allowed_mask is empty.  When
+ * the threads are sucessfully initialized, take the proper locks and
+ * unpark the threads in the watchdog_cpumask if the watchdog is enabled.
+ */
+static __init void softlockup_init_threads(void)
+{
+	int ret;
+
+	/*
+	 * If sysctl is off and watchdog got disabled on the command line,
+	 * nothing to do here.
+	 */
+	if (!IS_ENABLED(CONFIG_SYSCTL) &&
+	    !(watchdog_enabled && watchdog_thresh))
+		return;
+
+	ret = smpboot_register_percpu_thread_cpumask(&watchdog_threads,
+						     &watchdog_allowed_mask);
+	if (ret) {
+		pr_err("Failed to initialize soft lockup detector threads\n");
+		return;
+	}
+
+	mutex_lock(&watchdog_mutex);
+	softlockup_threads_initialized = true;
+	softlockup_reconfigure_threads(watchdog_enabled && watchdog_thresh);
+	mutex_unlock(&watchdog_mutex);
+}
+
 #else /* CONFIG_SOFTLOCKUP_DETECTOR */
 static inline int watchdog_park_threads(void) { return 0; }
 static inline void watchdog_unpark_threads(void) { }
 static inline int watchdog_enable_all_cpus(void) { return 0; }
 static inline void watchdog_disable_all_cpus(void) { }
 static inline void set_sample_period(void) { }
+static inline void softlockup_init_threads(void) { }
+static inline void softlockup_update_threads(void) { }
+static inline void softlockup_reconfigure_threads(bool enabled) { }
 #endif /* !CONFIG_SOFTLOCKUP_DETECTOR */
 
 static void __lockup_detector_cleanup(void)

[toc] | [prev] | [next] | [standalone]

#1732208 — [tip:core/urgent] watchdog/core: Create new thread handling infrastructure

Commit-ID:  2eb2527f847d1bd8d8fb9db1e8139db5d6eddb36
Gitweb:     http://git.kernel.org/tip/2eb2527f847d1bd8d8fb9db1e8139db5d6eddb36
Author:     Thomas Gleixner <tglx@linutronix.de>
AuthorDate: Tue, 12 Sep 2017 21:37:10 +0200
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Thu, 14 Sep 2017 11:41:06 +0200

watchdog/core: Create new thread handling infrastructure

The lockup detector reconfiguration tears down all watchdog threads when
the watchdog is disabled and sets them up again when its enabled.

That's a pointless exercise. The watchdog threads are not consuming an
insane amount of resources, so it's enough to set them up at init time and
keep them in parked position when the watchdog is disabled and unpark them
when it is reenabled. The smpboot thread infrastructure takes care of
keeping the force parked threads in place even across cpu hotplug.

Another horrible mechanism are the open coded park/unpark loops which are
used for reconfiguration of the watchdog. The smpboot infrastructure allows
exactly the same via smpboot_update_cpumask_thread_percpu(), which is cpu
hotplug safe. Using that instead of the open coded loops allows to get rid
of the hotplug locking mess in the watchdog code.

Implement a clean infrastructure which allows to replace the open coded
nonsense.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Don Zickus <dzickus@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Chris Metcalf <cmetcalf@mellanox.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sebastian Siewior <bigeasy@linutronix.de>
Cc: Ulrich Obergfell <uobergfe@redhat.com>
Link: http://lkml.kernel.org/r/20170912194147.377182587@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/watchdog.c | 75 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 75 insertions(+)

diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 8935a3a..b355183 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -139,6 +139,9 @@ unsigned int __read_mostly softlockup_panic =
 			CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE;
 int __read_mostly soft_watchdog_enabled;
 
+struct cpumask watchdog_allowed_mask __read_mostly;
+static bool softlockup_threads_initialized __read_mostly;
+
 static u64 __read_mostly sample_period;
 
 static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts);
@@ -584,12 +587,84 @@ static void watchdog_disable_all_cpus(void)
 	}
 }
 
+static void softlockup_update_smpboot_threads(void)
+{
+	lockdep_assert_held(&watchdog_mutex);
+
+	if (!softlockup_threads_initialized)
+		return;
+
+	smpboot_update_cpumask_percpu_thread(&watchdog_threads,
+					     &watchdog_allowed_mask);
+	__lockup_detector_cleanup();
+}
+
+/* Temporarily park all watchdog threads */
+static void softlockup_park_all_threads(void)
+{
+	cpumask_clear(&watchdog_allowed_mask);
+	softlockup_update_smpboot_threads();
+}
+
+/*
+ * Park threads which are not longer enabled and unpark threads which have
+ * been newly enabled.
+ */
+static void softlockup_update_threads(void)
+{
+	cpumask_copy(&watchdog_allowed_mask, &watchdog_cpumask);
+	softlockup_update_smpboot_threads();
+}
+
+static void softlockup_reconfigure_threads(bool enabled)
+{
+	softlockup_park_all_threads();
+	set_sample_period();
+	if (enabled)
+		softlockup_update_threads();
+}
+
+/*
+ * Create the watchdog thread infrastructure.
+ *
+ * The threads are not unparked as watchdog_allowed_mask is empty.  When
+ * the threads are sucessfully initialized, take the proper locks and
+ * unpark the threads in the watchdog_cpumask if the watchdog is enabled.
+ */
+static __init void softlockup_init_threads(void)
+{
+	int ret;
+
+	/*
+	 * If sysctl is off and watchdog got disabled on the command line,
+	 * nothing to do here.
+	 */
+	if (!IS_ENABLED(CONFIG_SYSCTL) &&
+	    !(watchdog_enabled && watchdog_thresh))
+		return;
+
+	ret = smpboot_register_percpu_thread_cpumask(&watchdog_threads,
+						     &watchdog_allowed_mask);
+	if (ret) {
+		pr_err("Failed to initialize soft lockup detector threads\n");
+		return;
+	}
+
+	mutex_lock(&watchdog_mutex);
+	softlockup_threads_initialized = true;
+	softlockup_reconfigure_threads(watchdog_enabled && watchdog_thresh);
+	mutex_unlock(&watchdog_mutex);
+}
+
 #else /* CONFIG_SOFTLOCKUP_DETECTOR */
 static inline int watchdog_park_threads(void) { return 0; }
 static inline void watchdog_unpark_threads(void) { }
 static inline int watchdog_enable_all_cpus(void) { return 0; }
 static inline void watchdog_disable_all_cpus(void) { }
 static inline void set_sample_period(void) { }
+static inline void softlockup_init_threads(void) { }
+static inline void softlockup_update_threads(void) { }
+static inline void softlockup_reconfigure_threads(bool enabled) { }
 #endif /* !CONFIG_SOFTLOCKUP_DETECTOR */
 
 static void __lockup_detector_cleanup(void)

[toc] | [prev] | [next] | [standalone]

#1731178 — [patch V2 01/29] hardlockup_detector: Provide interface to stop/restart perf events

From: Peter Zijlstra <peterz@infradead.org>

Provide an interface to stop and restart perf NMI watchdog events on all
CPUs. This is only usable during init and especially for handling the perf
HT bug on Intel machines. It's safe to use it this way as nothing can
start/stop the NMI watchdog in parallel.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Chris Metcalf <cmetcalf@mellanox.com>
Cc: Sebastian Siewior <bigeasy@linutronix.de>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Ulrich Obergfell <uobergfe@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/20170831073053.022580726@linutronix.de

---
 include/linux/nmi.h   |    4 ++++
 kernel/watchdog_hld.c |   41 +++++++++++++++++++++++++++++++++++++++++
 2 files changed, 45 insertions(+)

--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -75,7 +75,11 @@ static inline void hardlockup_detector_d
 
 #if defined(CONFIG_HARDLOCKUP_DETECTOR_PERF)
 extern void arch_touch_nmi_watchdog(void);
+extern void hardlockup_detector_perf_stop(void);
+extern void hardlockup_detector_perf_restart(void);
 #else
+static inline void hardlockup_detector_perf_stop(void) { }
+static inline void hardlockup_detector_perf_restart(void) { }
 #if !defined(CONFIG_HAVE_NMI_WATCHDOG)
 static inline void arch_touch_nmi_watchdog(void) {}
 #endif
--- a/kernel/watchdog_hld.c
+++ b/kernel/watchdog_hld.c
@@ -261,3 +261,44 @@ void watchdog_nmi_disable(unsigned int c
 			firstcpu_err = 0;
 	}
 }
+
+/**
+ * hardlockup_detector_perf_stop - Globally stop watchdog events
+ *
+ * Special interface for x86 to handle the perf HT bug.
+ */
+void __init hardlockup_detector_perf_stop(void)
+{
+	int cpu;
+
+	lockdep_assert_cpus_held();
+
+	for_each_online_cpu(cpu) {
+		struct perf_event *event = per_cpu(watchdog_ev, cpu);
+
+		if (event)
+			perf_event_disable(event);
+	}
+}
+
+/**
+ * hardlockup_detector_perf_restart - Globally restart watchdog events
+ *
+ * Special interface for x86 to handle the perf HT bug.
+ */
+void __init hardlockup_detector_perf_restart(void)
+{
+	int cpu;
+
+	lockdep_assert_cpus_held();
+
+	if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED))
+		return;
+
+	for_each_online_cpu(cpu) {
+		struct perf_event *event = per_cpu(watchdog_ev, cpu);
+
+		if (event)
+			perf_event_enable(event);
+	}
+}

[toc] | [prev] | [next] | [standalone]

#1732186 — [tip:core/urgent] watchdog/hardlockup: Provide interface to stop/restart perf events

Commit-ID:  d0b6e0a8ef24b1b07078ababe5d91bcdf4f4264a
Gitweb:     http://git.kernel.org/tip/d0b6e0a8ef24b1b07078ababe5d91bcdf4f4264a
Author:     Peter Zijlstra <peterz@infradead.org>
AuthorDate: Tue, 12 Sep 2017 21:36:55 +0200
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Thu, 14 Sep 2017 11:41:03 +0200

watchdog/hardlockup: Provide interface to stop/restart perf events

Provide an interface to stop and restart perf NMI watchdog events on all
CPUs. This is only usable during init and especially for handling the perf
HT bug on Intel machines. It's safe to use it this way as nothing can
start/stop the NMI watchdog in parallel.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Don Zickus <dzickus@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Chris Metcalf <cmetcalf@mellanox.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Sebastian Siewior <bigeasy@linutronix.de>
Cc: Ulrich Obergfell <uobergfe@redhat.com>
Link: http://lkml.kernel.org/r/20170912194146.167649596@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/nmi.h   |  4 ++++
 kernel/watchdog_hld.c | 41 +++++++++++++++++++++++++++++++++++++++++
 2 files changed, 45 insertions(+)

diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index a36abe2..b24d4a5 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -75,7 +75,11 @@ static inline void hardlockup_detector_disable(void) {}
 
 #if defined(CONFIG_HARDLOCKUP_DETECTOR_PERF)
 extern void arch_touch_nmi_watchdog(void);
+extern void hardlockup_detector_perf_stop(void);
+extern void hardlockup_detector_perf_restart(void);
 #else
+static inline void hardlockup_detector_perf_stop(void) { }
+static inline void hardlockup_detector_perf_restart(void) { }
 #if !defined(CONFIG_HAVE_NMI_WATCHDOG)
 static inline void arch_touch_nmi_watchdog(void) {}
 #endif
diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c
index 3a09ea1..c9586eb 100644
--- a/kernel/watchdog_hld.c
+++ b/kernel/watchdog_hld.c
@@ -261,3 +261,44 @@ void watchdog_nmi_disable(unsigned int cpu)
 			firstcpu_err = 0;
 	}
 }
+
+/**
+ * hardlockup_detector_perf_stop - Globally stop watchdog events
+ *
+ * Special interface for x86 to handle the perf HT bug.
+ */
+void __init hardlockup_detector_perf_stop(void)
+{
+	int cpu;
+
+	lockdep_assert_cpus_held();
+
+	for_each_online_cpu(cpu) {
+		struct perf_event *event = per_cpu(watchdog_ev, cpu);
+
+		if (event)
+			perf_event_disable(event);
+	}
+}
+
+/**
+ * hardlockup_detector_perf_restart - Globally restart watchdog events
+ *
+ * Special interface for x86 to handle the perf HT bug.
+ */
+void __init hardlockup_detector_perf_restart(void)
+{
+	int cpu;
+
+	lockdep_assert_cpus_held();
+
+	if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED))
+		return;
+
+	for_each_online_cpu(cpu) {
+		struct perf_event *event = per_cpu(watchdog_ev, cpu);
+
+		if (event)
+			perf_event_enable(event);
+	}
+}

[toc] | [prev] | [next] | [standalone]

#1731181 — [patch V2 26/29] lockup_detector/perf: Implement CPU enable replacement

watchdog_nmi_enable() is an unparseable mess, Provide a clean perf specific
implementation, which will be used when the existing setup/teardown mess is
replaced.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Chris Metcalf <cmetcalf@mellanox.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sebastian Siewior <bigeasy@linutronix.de>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Ulrich Obergfell <uobergfe@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/20170831073055.081402493@linutronix.de

---
 include/linux/nmi.h   |    2 ++
 kernel/watchdog_hld.c |   11 +++++++++++
 2 files changed, 13 insertions(+)

--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -92,12 +92,14 @@ extern void arch_touch_nmi_watchdog(void
 extern void hardlockup_detector_perf_stop(void);
 extern void hardlockup_detector_perf_restart(void);
 extern void hardlockup_detector_perf_disable(void);
+extern void hardlockup_detector_perf_enable(void);
 extern void hardlockup_detector_perf_cleanup(void);
 extern int hardlockup_detector_perf_init(void);
 #else
 static inline void hardlockup_detector_perf_stop(void) { }
 static inline void hardlockup_detector_perf_restart(void) { }
 static inline void hardlockup_detector_perf_disable(void) { }
+static inline void hardlockup_detector_perf_enable(void) { }
 static inline void hardlockup_detector_perf_cleanup(void) { }
 # if !defined(CONFIG_HAVE_NMI_WATCHDOG)
 static inline int hardlockup_detector_perf_init(void) { return -ENODEV; }
--- a/kernel/watchdog_hld.c
+++ b/kernel/watchdog_hld.c
@@ -260,6 +260,17 @@ static int hardlockup_detector_event_cre
 }
 
 /**
+ * hardlockup_detector_perf_enable - Enable the local event
+ */
+void hardlockup_detector_perf_enable(void)
+{
+	if (hardlockup_detector_event_create())
+		return;
+
+	perf_event_enable(this_cpu_read(watchdog_ev));
+}
+
+/**
  * hardlockup_detector_perf_disable - Disable the local event
  */
 void hardlockup_detector_perf_disable(void)

[toc] | [prev] | [next] | [standalone]

#1732198 — [tip:core/urgent] watchdog/hardlockup/perf: Implement CPU enable replacement

Commit-ID:  2a1b8ee4f5665b4291e43e4a25d964c3eb2f4c32
Gitweb:     http://git.kernel.org/tip/2a1b8ee4f5665b4291e43e4a25d964c3eb2f4c32
Author:     Thomas Gleixner <tglx@linutronix.de>
AuthorDate: Tue, 12 Sep 2017 21:37:20 +0200
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Thu, 14 Sep 2017 11:41:08 +0200

watchdog/hardlockup/perf: Implement CPU enable replacement

watchdog_nmi_enable() is an unparseable mess, Provide a clean perf specific
implementation, which will be used when the existing setup/teardown mess is
replaced.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Don Zickus <dzickus@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Chris Metcalf <cmetcalf@mellanox.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sebastian Siewior <bigeasy@linutronix.de>
Cc: Ulrich Obergfell <uobergfe@redhat.com>
Link: http://lkml.kernel.org/r/20170912194148.180215498@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/nmi.h   |  2 ++
 kernel/watchdog_hld.c | 11 +++++++++++
 2 files changed, 13 insertions(+)

diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index 72c62a8..89ba8b2 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -92,12 +92,14 @@ extern void arch_touch_nmi_watchdog(void);
 extern void hardlockup_detector_perf_stop(void);
 extern void hardlockup_detector_perf_restart(void);
 extern void hardlockup_detector_perf_disable(void);
+extern void hardlockup_detector_perf_enable(void);
 extern void hardlockup_detector_perf_cleanup(void);
 extern int hardlockup_detector_perf_init(void);
 #else
 static inline void hardlockup_detector_perf_stop(void) { }
 static inline void hardlockup_detector_perf_restart(void) { }
 static inline void hardlockup_detector_perf_disable(void) { }
+static inline void hardlockup_detector_perf_enable(void) { }
 static inline void hardlockup_detector_perf_cleanup(void) { }
 # if !defined(CONFIG_HAVE_NMI_WATCHDOG)
 static inline int hardlockup_detector_perf_init(void) { return -ENODEV; }
diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c
index f7e752e..99a3f22 100644
--- a/kernel/watchdog_hld.c
+++ b/kernel/watchdog_hld.c
@@ -260,6 +260,17 @@ static int hardlockup_detector_event_create(void)
 }
 
 /**
+ * hardlockup_detector_perf_enable - Enable the local event
+ */
+void hardlockup_detector_perf_enable(void)
+{
+	if (hardlockup_detector_event_create())
+		return;
+
+	perf_event_enable(this_cpu_read(watchdog_ev));
+}
+
+/**
  * hardlockup_detector_perf_disable - Disable the local event
  */
 void hardlockup_detector_perf_disable(void)

[toc] | [prev] | [next] | [standalone]

#1731183 — [patch V2 06/29] lockup_detector: Rework cpu hotplug locking

The watchdog proc interface causes extensive recursive locking of the cpu
hotplug percpu rwsem, which is deadlock prone.

Replace the get/put_online_cpus() pairs with cpu_hotplug_disable()/enable()
calls for now. Later patches will remove that requirement completely.

Reported-by: Borislav Petkov <bp@alien8.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Chris Metcalf <cmetcalf@mellanox.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sebastian Siewior <bigeasy@linutronix.de>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Ulrich Obergfell <uobergfe@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/20170831073053.437818037@linutronix.de

---
 kernel/watchdog.c |   12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -703,7 +703,7 @@ static int proc_watchdog_common(int whic
 	int err, old, new;
 	int *watchdog_param = (int *)table->data;
 
-	get_online_cpus();
+	cpu_hotplug_disable();
 	mutex_lock(&watchdog_proc_mutex);
 
 	/*
@@ -752,7 +752,7 @@ static int proc_watchdog_common(int whic
 	}
 out:
 	mutex_unlock(&watchdog_proc_mutex);
-	put_online_cpus();
+	cpu_hotplug_enable();
 	return err;
 }
 
@@ -794,7 +794,7 @@ int proc_watchdog_thresh(struct ctl_tabl
 {
 	int err, old, new;
 
-	get_online_cpus();
+	cpu_hotplug_disable();
 	mutex_lock(&watchdog_proc_mutex);
 
 	old = ACCESS_ONCE(watchdog_thresh);
@@ -818,7 +818,7 @@ int proc_watchdog_thresh(struct ctl_tabl
 	}
 out:
 	mutex_unlock(&watchdog_proc_mutex);
-	put_online_cpus();
+	cpu_hotplug_enable();
 	return err;
 }
 
@@ -833,7 +833,7 @@ int proc_watchdog_cpumask(struct ctl_tab
 {
 	int err;
 
-	get_online_cpus();
+	cpu_hotplug_disable();
 	mutex_lock(&watchdog_proc_mutex);
 
 	err = proc_do_large_bitmap(table, write, buffer, lenp, ppos);
@@ -856,7 +856,7 @@ int proc_watchdog_cpumask(struct ctl_tab
 	}
 
 	mutex_unlock(&watchdog_proc_mutex);
-	put_online_cpus();
+	cpu_hotplug_enable();
 	return err;
 }
 

[toc] | [prev] | [next] | [standalone]

#1732189 — [tip:core/urgent] watchdog/core: Rework CPU hotplug locking

Commit-ID:  b7a349819d4b9b5db64e523351e66a79a758eaa5
Gitweb:     http://git.kernel.org/tip/b7a349819d4b9b5db64e523351e66a79a758eaa5
Author:     Thomas Gleixner <tglx@linutronix.de>
AuthorDate: Tue, 12 Sep 2017 21:37:00 +0200
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Thu, 14 Sep 2017 11:41:04 +0200

watchdog/core: Rework CPU hotplug locking

The watchdog proc interface causes extensive recursive locking of the CPU
hotplug percpu rwsem, which is deadlock prone.

Replace the get/put_online_cpus() pairs with cpu_hotplug_disable()/enable()
calls for now. Later patches will remove that requirement completely.

Reported-by: Borislav Petkov <bp@alien8.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Don Zickus <dzickus@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Chris Metcalf <cmetcalf@mellanox.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sebastian Siewior <bigeasy@linutronix.de>
Cc: Ulrich Obergfell <uobergfe@redhat.com>
Link: http://lkml.kernel.org/r/20170912194146.568079057@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/watchdog.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index b2d4675..cd79f64 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -703,7 +703,7 @@ static int proc_watchdog_common(int which, struct ctl_table *table, int write,
 	int err, old, new;
 	int *watchdog_param = (int *)table->data;
 
-	get_online_cpus();
+	cpu_hotplug_disable();
 	mutex_lock(&watchdog_proc_mutex);
 
 	/*
@@ -752,7 +752,7 @@ static int proc_watchdog_common(int which, struct ctl_table *table, int write,
 	}
 out:
 	mutex_unlock(&watchdog_proc_mutex);
-	put_online_cpus();
+	cpu_hotplug_enable();
 	return err;
 }
 
@@ -794,7 +794,7 @@ int proc_watchdog_thresh(struct ctl_table *table, int write,
 {
 	int err, old, new;
 
-	get_online_cpus();
+	cpu_hotplug_disable();
 	mutex_lock(&watchdog_proc_mutex);
 
 	old = ACCESS_ONCE(watchdog_thresh);
@@ -818,7 +818,7 @@ int proc_watchdog_thresh(struct ctl_table *table, int write,
 	}
 out:
 	mutex_unlock(&watchdog_proc_mutex);
-	put_online_cpus();
+	cpu_hotplug_enable();
 	return err;
 }
 
@@ -833,7 +833,7 @@ int proc_watchdog_cpumask(struct ctl_table *table, int write,
 {
 	int err;
 
-	get_online_cpus();
+	cpu_hotplug_disable();
 	mutex_lock(&watchdog_proc_mutex);
 
 	err = proc_do_large_bitmap(table, write, buffer, lenp, ppos);
@@ -856,7 +856,7 @@ int proc_watchdog_cpumask(struct ctl_table *table, int write,
 	}
 
 	mutex_unlock(&watchdog_proc_mutex);
-	put_online_cpus();
+	cpu_hotplug_enable();
 	return err;
 }
 

[toc] | [prev] | [next] | [standalone]

#1731184 — [patch V2 28/29] lockup_detector/perf: Simplify deferred event destroy

Now that all functionality is properly serialized against CPU hotplug,
remove the extra per cpu storage which holds the disabled events for
cleanup. The core makes sure that cleanup happens before new events are
created.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Chris Metcalf <cmetcalf@mellanox.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sebastian Siewior <bigeasy@linutronix.de>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Ulrich Obergfell <uobergfe@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/20170831073055.251195167@linutronix.de

---
 kernel/watchdog_hld.c |    7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

--- a/kernel/watchdog_hld.c
+++ b/kernel/watchdog_hld.c
@@ -21,7 +21,6 @@
 static DEFINE_PER_CPU(bool, hard_watchdog_warn);
 static DEFINE_PER_CPU(bool, watchdog_nmi_touch);
 static DEFINE_PER_CPU(struct perf_event *, watchdog_ev);
-static DEFINE_PER_CPU(struct perf_event *, dead_event);
 static struct cpumask dead_events_mask;
 
 static unsigned long hardlockup_allcpu_dumped;
@@ -204,8 +203,6 @@ void hardlockup_detector_perf_disable(vo
 
 	if (event) {
 		perf_event_disable(event);
-		this_cpu_write(watchdog_ev, NULL);
-		this_cpu_write(dead_event, event);
 		cpumask_set_cpu(smp_processor_id(), &dead_events_mask);
 		watchdog_cpus--;
 	}
@@ -221,9 +218,9 @@ void hardlockup_detector_perf_cleanup(vo
 	int cpu;
 
 	for_each_cpu(cpu, &dead_events_mask) {
-		struct perf_event *event = per_cpu(dead_event, cpu);
+		struct perf_event *event = per_cpu(watchdog_ev, cpu);
 
-		per_cpu(dead_event, cpu) = NULL;
+		per_cpu(watchdog_ev, cpu) = NULL;
 		perf_event_release_kernel(event);
 	}
 	cpumask_clear(&dead_events_mask);

[toc] | [prev] | [next] | [standalone]

#1732200 — [tip:core/urgent] watchdog/hardlockup/perf: Simplify deferred event destroy

Commit-ID:  a33d44843d4574ec05bec39527d8a87b7af2072c
Gitweb:     http://git.kernel.org/tip/a33d44843d4574ec05bec39527d8a87b7af2072c
Author:     Thomas Gleixner <tglx@linutronix.de>
AuthorDate: Tue, 12 Sep 2017 21:37:22 +0200
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Thu, 14 Sep 2017 11:41:08 +0200

watchdog/hardlockup/perf: Simplify deferred event destroy

Now that all functionality is properly serialized against CPU hotplug,
remove the extra per cpu storage which holds the disabled events for
cleanup. The core makes sure that cleanup happens before new events are
created.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Don Zickus <dzickus@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Chris Metcalf <cmetcalf@mellanox.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sebastian Siewior <bigeasy@linutronix.de>
Cc: Ulrich Obergfell <uobergfe@redhat.com>
Link: http://lkml.kernel.org/r/20170912194148.340708074@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/watchdog_hld.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c
index 509bb6b..b293115 100644
--- a/kernel/watchdog_hld.c
+++ b/kernel/watchdog_hld.c
@@ -21,7 +21,6 @@
 static DEFINE_PER_CPU(bool, hard_watchdog_warn);
 static DEFINE_PER_CPU(bool, watchdog_nmi_touch);
 static DEFINE_PER_CPU(struct perf_event *, watchdog_ev);
-static DEFINE_PER_CPU(struct perf_event *, dead_event);
 static struct cpumask dead_events_mask;
 
 static unsigned long hardlockup_allcpu_dumped;
@@ -204,8 +203,6 @@ void hardlockup_detector_perf_disable(void)
 
 	if (event) {
 		perf_event_disable(event);
-		this_cpu_write(watchdog_ev, NULL);
-		this_cpu_write(dead_event, event);
 		cpumask_set_cpu(smp_processor_id(), &dead_events_mask);
 		watchdog_cpus--;
 	}
@@ -221,9 +218,9 @@ void hardlockup_detector_perf_cleanup(void)
 	int cpu;
 
 	for_each_cpu(cpu, &dead_events_mask) {
-		struct perf_event *event = per_cpu(dead_event, cpu);
+		struct perf_event *event = per_cpu(watchdog_ev, cpu);
 
-		per_cpu(dead_event, cpu) = NULL;
+		per_cpu(watchdog_ev, cpu) = NULL;
 		perf_event_release_kernel(event);
 	}
 	cpumask_clear(&dead_events_mask);

[toc] | [prev] | [next] | [standalone]

#1731186 — [patch V2 04/29] parisc: Use lockup_detector_stop()

The broken lockup_detector_suspend/resume() interface is going away. Use
the new lockup_detector_soft_poweroff() interface to stop the watchdog from
the busy looping power off routine.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Chris Metcalf <cmetcalf@mellanox.com>
Cc: linux-parisc@vger.kernel.org
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sebastian Siewior <bigeasy@linutronix.de>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Ulrich Obergfell <uobergfe@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Helge Deller <deller@gmx.de>
Link: http://lkml.kernel.org/r/20170831073053.281414373@linutronix.de

---
 arch/parisc/kernel/process.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -146,7 +146,7 @@ void machine_power_off(void)
 
 	/* prevent soft lockup/stalled CPU messages for endless loop. */
 	rcu_sysrq_start();
-	lockup_detector_suspend();
+	lockup_detector_soft_poweroff();
 	for (;;);
 }
 

[toc] | [prev] | [next] | [standalone]

#1732119 — Re: [patch V2 04/29] parisc: Use lockup_detector_stop()

* Thomas Gleixner <tglx@linutronix.de>:
> The broken lockup_detector_suspend/resume() interface is going away. Use
> the new lockup_detector_soft_poweroff() interface to stop the watchdog from
> the busy looping power off routine.
> 
> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
> Cc: Don Zickus <dzickus@redhat.com>
> Cc: Chris Metcalf <cmetcalf@mellanox.com>
> Cc: linux-parisc@vger.kernel.org
> Cc: Peter Zijlstra <peterz@infradead.org>
> Cc: Sebastian Siewior <bigeasy@linutronix.de>
> Cc: Nicholas Piggin <npiggin@gmail.com>
> Cc: Ulrich Obergfell <uobergfe@redhat.com>
> Cc: Borislav Petkov <bp@alien8.de>
> Cc: Andrew Morton <akpm@linux-foundation.org>
> Cc: Helge Deller <deller@gmx.de>
> Link: http://lkml.kernel.org/r/20170831073053.281414373@linutronix.de
> 
> ---
>  arch/parisc/kernel/process.c |    2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> --- a/arch/parisc/kernel/process.c
> +++ b/arch/parisc/kernel/process.c
> @@ -146,7 +146,7 @@ void machine_power_off(void)
>  
>  	/* prevent soft lockup/stalled CPU messages for endless loop. */
>  	rcu_sysrq_start();
> -	lockup_detector_suspend();
> +	lockup_detector_soft_poweroff();
>  	for (;;);
>  }

Thomas, thanks for cleaning that up.  
You may add to patches 03/04:
Acked-by: Helge Deller <deller@gmx.de>


On a side-note, there is sadly no general function like
	turn_off_all_kind_of_runtime_hang_detectors()
which turns off *all* detectors at once (including soft lockup detector).
I've seen another detector complaing at runtime that we were hanging
here. I would need to dig up more info if you are interested...

Helge

[toc] | [prev] | [next] | [standalone]

#1732278 — Re: [patch V2 04/29] parisc: Use lockup_detector_stop()

On Thu, Sep 14, 2017 at 10:59:17AM +0200, Helge Deller wrote:
> * Thomas Gleixner <tglx@linutronix.de>:
> > The broken lockup_detector_suspend/resume() interface is going away. Use
> > the new lockup_detector_soft_poweroff() interface to stop the watchdog from
> > the busy looping power off routine.
> > 
> > Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
> > Cc: Don Zickus <dzickus@redhat.com>
> > Cc: Chris Metcalf <cmetcalf@mellanox.com>
> > Cc: linux-parisc@vger.kernel.org
> > Cc: Peter Zijlstra <peterz@infradead.org>
> > Cc: Sebastian Siewior <bigeasy@linutronix.de>
> > Cc: Nicholas Piggin <npiggin@gmail.com>
> > Cc: Ulrich Obergfell <uobergfe@redhat.com>
> > Cc: Borislav Petkov <bp@alien8.de>
> > Cc: Andrew Morton <akpm@linux-foundation.org>
> > Cc: Helge Deller <deller@gmx.de>
> > Link: http://lkml.kernel.org/r/20170831073053.281414373@linutronix.de
> > 
> > ---
> >  arch/parisc/kernel/process.c |    2 +-
> >  1 file changed, 1 insertion(+), 1 deletion(-)
> > 
> > --- a/arch/parisc/kernel/process.c
> > +++ b/arch/parisc/kernel/process.c
> > @@ -146,7 +146,7 @@ void machine_power_off(void)
> >  
> >  	/* prevent soft lockup/stalled CPU messages for endless loop. */
> >  	rcu_sysrq_start();
> > -	lockup_detector_suspend();
> > +	lockup_detector_soft_poweroff();
> >  	for (;;);
> >  }
> 
> Thomas, thanks for cleaning that up.  
> You may add to patches 03/04:
> Acked-by: Helge Deller <deller@gmx.de>
> 
> 
> On a side-note, there is sadly no general function like
> 	turn_off_all_kind_of_runtime_hang_detectors()
> which turns off *all* detectors at once (including soft lockup detector).
> I've seen another detector complaing at runtime that we were hanging
> here. I would need to dig up more info if you are interested...

There are numerous detectors I have seen over the years: rcu, clocksource,
hard/soft, hang, fs, network, wq?, etc..  I am not sure it is easy to put
them all in one place or makes sense.

I know working with the kvm folks, when they swap back in, the real clock
can do a massive jump forward and causes a flood of warnings such that they
had to 'touch' all of them before running the vm again.

Cheers,
Don

[toc] | [prev] | [next] | [standalone]

#1732188 — [tip:core/urgent] parisc, watchdog/core: Use lockup_detector_stop()

Commit-ID:  47bb4baf7df43ac8bbc51c24022466972ba29ef1
Gitweb:     http://git.kernel.org/tip/47bb4baf7df43ac8bbc51c24022466972ba29ef1
Author:     Thomas Gleixner <tglx@linutronix.de>
AuthorDate: Tue, 12 Sep 2017 21:36:58 +0200
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Thu, 14 Sep 2017 11:41:03 +0200

parisc, watchdog/core: Use lockup_detector_stop()

The broken lockup_detector_suspend/resume() interface is going away. Use
the new lockup_detector_soft_poweroff() interface to stop the watchdog from
the busy looping power off routine.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Don Zickus <dzickus@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Chris Metcalf <cmetcalf@mellanox.com>
Cc: Helge Deller <deller@gmx.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sebastian Siewior <bigeasy@linutronix.de>
Cc: Ulrich Obergfell <uobergfe@redhat.com>
Cc: linux-parisc@vger.kernel.org
Link: http://lkml.kernel.org/r/20170912194146.407385557@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/parisc/kernel/process.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c
index a45a67d..30f9239 100644
--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -146,7 +146,7 @@ void machine_power_off(void)
 
 	/* prevent soft lockup/stalled CPU messages for endless loop. */
 	rcu_sysrq_start();
-	lockup_detector_suspend();
+	lockup_detector_soft_poweroff();
 	for (;;);
 }
 

[toc] | [prev] | [next] | [standalone]

#1731187 — [patch V2 17/29] lockup_detector: Get rid of the thread teardown/setup dance

The lockup detector reconfiguration tears down all watchdog threads when
the watchdog is disabled and sets them up again when its enabled.

That's a pointless exercise. The watchdog threads are not consuming an
insane amount of resources, so it's enough to set them up at init time and
keep them in parked position when the watchdog is disabled and unpark them
when it is reenabled. The smpboot thread infrastructure takes care of
keeping the force parked threads in place even across cpu hotplug.

Aside of that the code implements the park/unpark facility of smp hotplug
threads on its own, which is even more pointless. We have functionality in
the smpboot thread code to do so.

Use the new thread management functions and get rid of the unholy mess.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Chris Metcalf <cmetcalf@mellanox.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sebastian Siewior <bigeasy@linutronix.de>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Ulrich Obergfell <uobergfe@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/20170831073054.346816852@linutronix.de

---
 kernel/watchdog.c |  190 +++++-------------------------------------------------
 1 file changed, 19 insertions(+), 171 deletions(-)

--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -92,13 +92,6 @@ struct cpumask watchdog_cpumask __read_m
 unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask);
 
 /*
- * 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;
-
-/*
  * These functions can be overridden if an architecture implements its
  * own hardlockup detector.
  *
@@ -130,10 +123,6 @@ void __weak watchdog_nmi_reconfigure(voi
 
 #ifdef CONFIG_SOFTLOCKUP_DETECTOR
 
-/* Helper for online, unparked cpus. */
-#define for_each_watchdog_cpu(cpu) \
-	for_each_cpu_and((cpu), cpu_online_mask, &watchdog_cpumask)
-
 /* Global variables, exported for sysctl */
 unsigned int __read_mostly softlockup_panic =
 			CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE;
@@ -259,11 +248,15 @@ void touch_all_softlockup_watchdogs(void
 	int cpu;
 
 	/*
-	 * this is done lockless
-	 * do we care if a 0 races with a timestamp?
-	 * all it means is the softlock check starts one cycle later
+	 * watchdog_mutex cannpt be taken here, as this might be called
+	 * from (soft)interrupt context, so the access to
+	 * watchdog_allowed_cpumask might race with a concurrent update.
+	 *
+	 * The watchdog time stamp can race against a concurrent real
+	 * update as well, the only side effect might be a cycle delay for
+	 * the softlockup check.
 	 */
-	for_each_watchdog_cpu(cpu)
+	for_each_cpu(cpu, &watchdog_allowed_mask)
 		per_cpu(watchdog_touch_ts, cpu) = 0;
 	wq_watchdog_touch(-1);
 }
@@ -303,9 +296,6 @@ static void watchdog_interrupt_count(voi
 	__this_cpu_inc(hrtimer_interrupts);
 }
 
-static int watchdog_enable_all_cpus(void);
-static void watchdog_disable_all_cpus(void);
-
 /* watchdog kicker functions */
 static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 {
@@ -498,95 +488,6 @@ static struct smp_hotplug_thread watchdo
 	.unpark			= watchdog_enable,
 };
 
-/*
- * park all watchdog threads that are specified in 'watchdog_cpumask'
- *
- * This function returns an error if kthread_park() of a watchdog thread
- * fails. In this situation, the watchdog threads of some CPUs can already
- * be parked and the watchdog threads of other CPUs can still be runnable.
- * Callers are expected to handle this special condition as appropriate in
- * their context.
- *
- * This function may only be called in a context that is protected against
- * races with CPU hotplug - for example, via get_online_cpus().
- */
-static int watchdog_park_threads(void)
-{
-	int cpu, ret = 0;
-
-	for_each_watchdog_cpu(cpu) {
-		ret = kthread_park(per_cpu(softlockup_watchdog, cpu));
-		if (ret)
-			break;
-	}
-	return ret;
-}
-
-/*
- * unpark all watchdog threads that are specified in 'watchdog_cpumask'
- *
- * This function may only be called in a context that is protected against
- * races with CPU hotplug - for example, via get_online_cpus().
- */
-static void watchdog_unpark_threads(void)
-{
-	int cpu;
-
-	for_each_watchdog_cpu(cpu)
-		kthread_unpark(per_cpu(softlockup_watchdog, cpu));
-}
-
-static int update_watchdog_all_cpus(void)
-{
-	int ret;
-
-	ret = watchdog_park_threads();
-	if (ret)
-		return ret;
-
-	watchdog_unpark_threads();
-
-	return 0;
-}
-
-static int watchdog_enable_all_cpus(void)
-{
-	int err = 0;
-
-	if (!watchdog_running) {
-		err = smpboot_register_percpu_thread_cpumask(&watchdog_threads,
-							     &watchdog_cpumask);
-		if (err)
-			pr_err("Failed to create watchdog threads, disabled\n");
-		else
-			watchdog_running = 1;
-	} else {
-		/*
-		 * Enable/disable the lockup detectors or
-		 * change the sample period 'on the fly'.
-		 */
-		err = update_watchdog_all_cpus();
-
-		if (err) {
-			watchdog_disable_all_cpus();
-			pr_err("Failed to update lockup detectors, disabled\n");
-		}
-	}
-
-	if (err)
-		watchdog_enabled = 0;
-
-	return err;
-}
-
-static void watchdog_disable_all_cpus(void)
-{
-	if (watchdog_running) {
-		watchdog_running = 0;
-		smpboot_unregister_percpu_thread(&watchdog_threads);
-	}
-}
-
 static void softlockup_update_smpboot_threads(void)
 {
 	lockdep_assert_held(&watchdog_mutex);
@@ -661,7 +562,6 @@ static inline int watchdog_park_threads(
 static inline void watchdog_unpark_threads(void) { }
 static inline int watchdog_enable_all_cpus(void) { return 0; }
 static inline void watchdog_disable_all_cpus(void) { }
-static inline void set_sample_period(void) { }
 static inline void softlockup_init_threads(void) { }
 static inline void softlockup_update_threads(void) { }
 static inline void softlockup_reconfigure_threads(bool enabled) { }
@@ -701,28 +601,10 @@ void lockup_detector_soft_poweroff(void)
 /*
  * Update the run state of the lockup detectors.
  */
-static int proc_watchdog_update(void)
+static void proc_watchdog_update(void)
 {
-	int err = 0;
-
-	/*
-	 * Watchdog threads won't be started if they are already active.
-	 * The 'watchdog_running' variable in watchdog_*_all_cpus() takes
-	 * care of this. If those threads are already active, the sample
-	 * period will be updated and the lockup detectors will be enabled
-	 * or disabled 'on the fly'.
-	 */
-	if (watchdog_enabled && watchdog_thresh)
-		err = watchdog_enable_all_cpus();
-	else
-		watchdog_disable_all_cpus();
-
+	softlockup_reconfigure_threads(watchdog_enabled && watchdog_thresh);
 	watchdog_nmi_reconfigure();
-
-	__lockup_detector_cleanup();
-
-	return err;
-
 }
 
 /*
@@ -778,17 +660,8 @@ static int proc_watchdog_common(int whic
 				new = old & ~which;
 		} while (cmpxchg(&watchdog_enabled, old, new) != old);
 
-		/*
-		 * Update the run state of the lockup detectors. There is _no_
-		 * need to check the value returned by proc_watchdog_update()
-		 * and to restore the previous value of 'watchdog_enabled' as
-		 * both lockup detectors are disabled if proc_watchdog_update()
-		 * returns an error.
-		 */
-		if (old == new)
-			goto out;
-
-		err = proc_watchdog_update();
+		if (old != new)
+			proc_watchdog_update();
 	}
 out:
 	mutex_unlock(&watchdog_mutex);
@@ -832,50 +705,28 @@ int proc_soft_watchdog(struct ctl_table
 int proc_watchdog_thresh(struct ctl_table *table, int write,
 			 void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-	int err, old, new;
+	int err, old;
 
 	cpu_hotplug_disable();
 	mutex_lock(&watchdog_mutex);
 
-	old = ACCESS_ONCE(watchdog_thresh);
+	old = READ_ONCE(watchdog_thresh);
 	err = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 
-	if (err || !write)
-		goto out;
+	if (!err && write && old != READ_ONCE(watchdog_thresh))
+		proc_watchdog_update();
 
-	/*
-	 * Update the sample period. Restore on failure.
-	 */
-	new = ACCESS_ONCE(watchdog_thresh);
-	if (old == new)
-		goto out;
-
-	set_sample_period();
-	err = proc_watchdog_update();
-	if (err) {
-		watchdog_thresh = old;
-		set_sample_period();
-	}
-out:
 	mutex_unlock(&watchdog_mutex);
 	cpu_hotplug_enable();
 	return err;
 }
 
-static void watchdog_update_cpus(void)
-{
-	if (IS_ENABLED(CONFIG_SOFTLOCKUP_DETECTOR) && watchdog_running) {
-		smpboot_update_cpumask_percpu_thread(&watchdog_threads,
-						     &watchdog_cpumask);
-		__lockup_detector_cleanup();
-	}
-}
-
 static void proc_watchdog_cpumask_update(void)
 {
 	/* Remove impossible cpus to keep sysctl output clean. */
 	cpumask_and(&watchdog_cpumask, &watchdog_cpumask, cpu_possible_mask);
-	watchdog_update_cpus();
+
+	softlockup_update_threads();
 	watchdog_nmi_reconfigure();
 }
 
@@ -905,8 +756,6 @@ int proc_watchdog_cpumask(struct ctl_tab
 
 void __init lockup_detector_init(void)
 {
-	set_sample_period();
-
 #ifdef CONFIG_NO_HZ_FULL
 	if (tick_nohz_full_enabled()) {
 		pr_info("Disabling watchdog on nohz_full cores by default\n");
@@ -917,6 +766,5 @@ void __init lockup_detector_init(void)
 	cpumask_copy(&watchdog_cpumask, cpu_possible_mask);
 #endif
 
-	if (watchdog_enabled)
-		watchdog_enable_all_cpus();
+	softlockup_init_threads();
 }

[toc] | [prev] | [next] | [standalone]

Page 1 of 3  [1] 2 3  Next page →

Back to top | Article view | linux.kernel

csiph-web