LKML Archive on lore.kernel.org
 help / color / Atom feed
From: tip-bot for Thomas Gleixner <tipbot@zytor.com>
To: linux-tip-commits@vger.kernel.org
Cc: akpm@linux-foundation.org, cmetcalf@mellanox.com,
	linux-kernel@vger.kernel.org, npiggin@gmail.com,
	mingo@kernel.org, peterz@infradead.org, bp@alien8.de,
	uobergfe@redhat.com, tglx@linutronix.de, hpa@zytor.com,
	bigeasy@linutronix.de, dzickus@redhat.com,
	torvalds@linux-foundation.org
Subject: [tip:core/urgent] watchdog/hardlockup/perf: Prevent CPU hotplug deadlock
Date: Thu, 14 Sep 2017 03:43:32 -0700
Message-ID: <tip-941154bd6937a710ae9193a3c733c0029e5ae7b8@git.kernel.org> (raw)
In-Reply-To: <20170912194146.884469246@linutronix.de>

Commit-ID:  941154bd6937a710ae9193a3c733c0029e5ae7b8
Gitweb:     http://git.kernel.org/tip/941154bd6937a710ae9193a3c733c0029e5ae7b8
Author:     Thomas Gleixner <tglx@linutronix.de>
AuthorDate: Tue, 12 Sep 2017 21:37:04 +0200
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Thu, 14 Sep 2017 11:41:05 +0200

watchdog/hardlockup/perf: Prevent CPU hotplug deadlock

The following deadlock is possible in the watchdog hotplug code:

  cpus_write_lock()
    ...
      takedown_cpu()
        smpboot_park_threads()
          smpboot_park_thread()
            kthread_park()
              ->park() := watchdog_disable()
                watchdog_nmi_disable()
                  perf_event_release_kernel();
                    put_event()
                      _free_event()
                        ->destroy() := hw_perf_event_destroy()
                          x86_release_hardware()
                            release_ds_buffers()
                              get_online_cpus()

when a per cpu watchdog perf event is destroyed which drops the last
reference to the PMU hardware. The cleanup code there invokes
get_online_cpus() which instantly deadlocks because the hotplug percpu
rwsem is write locked.

To solve this add a deferring mechanism:

  cpus_write_lock()
			   kthread_park()
			    watchdog_nmi_disable(deferred)
			      perf_event_disable(event);
			      move_event_to_deferred(event);
			   ....
  cpus_write_unlock()
  cleaup_deferred_events()
    perf_event_release_kernel()

This is still properly serialized against concurrent hotplug via the
cpu_add_remove_lock, which is held by the task which initiated the hotplug
event.

This is also used to handle event destruction when the watchdog threads are
parked via other mechanisms than CPU hotplug.

Analyzed-by: Peter Zijlstra <peterz@infradead.org>

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/20170912194146.884469246@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/nmi.h   |  6 ++++++
 kernel/cpu.c          |  6 ++++++
 kernel/watchdog.c     | 25 +++++++++++++++++++++++++
 kernel/watchdog_hld.c | 34 ++++++++++++++++++++++++++++------
 4 files changed, 65 insertions(+), 6 deletions(-)

diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index 7eefe7a..80354e6 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -13,9 +13,11 @@
 #ifdef CONFIG_LOCKUP_DETECTOR
 void lockup_detector_init(void);
 void lockup_detector_soft_poweroff(void);
+void lockup_detector_cleanup(void);
 #else
 static inline void lockup_detector_init(void) { }
 static inline void lockup_detector_soft_poweroff(void) { }
+static inline void lockup_detector_cleanup(void) { }
 #endif
 
 #ifdef CONFIG_SOFTLOCKUP_DETECTOR
@@ -77,9 +79,13 @@ static inline void hardlockup_detector_disable(void) {}
 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_cleanup(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_cleanup(void) { }
 #if !defined(CONFIG_HAVE_NMI_WATCHDOG)
 static inline void arch_touch_nmi_watchdog(void) {}
 #endif
diff --git a/kernel/cpu.c b/kernel/cpu.c
index acf5308..a96b348 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -24,6 +24,7 @@
 #include <linux/lockdep.h>
 #include <linux/tick.h>
 #include <linux/irq.h>
+#include <linux/nmi.h>
 #include <linux/smpboot.h>
 #include <linux/relay.h>
 #include <linux/slab.h>
@@ -734,6 +735,11 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen,
 
 out:
 	cpus_write_unlock();
+	/*
+	 * Do post unplug cleanup. This is still protected against
+	 * concurrent CPU hotplug via cpu_add_remove_lock.
+	 */
+	lockup_detector_cleanup();
 	return ret;
 }
 
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index af00095..dd1fd59 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -109,8 +109,10 @@ int __weak watchdog_nmi_enable(unsigned int cpu)
 {
 	return 0;
 }
+
 void __weak watchdog_nmi_disable(unsigned int cpu)
 {
+	hardlockup_detector_perf_disable();
 }
 
 /*
@@ -193,6 +195,8 @@ __setup("hardlockup_all_cpu_backtrace=", hardlockup_all_cpu_backtrace_setup);
 #endif
 #endif
 
+static void __lockup_detector_cleanup(void);
+
 /*
  * Hard-lockup warnings should be triggered after just a few seconds. Soft-
  * lockups can have false positives under extreme conditions. So we generally
@@ -631,6 +635,24 @@ static void set_sample_period(void)
 }
 #endif /* SOFTLOCKUP */
 
+static void __lockup_detector_cleanup(void)
+{
+	lockdep_assert_held(&watchdog_mutex);
+	hardlockup_detector_perf_cleanup();
+}
+
+/**
+ * lockup_detector_cleanup - Cleanup after cpu hotplug or sysctl changes
+ *
+ * Caller must not hold the cpu hotplug rwsem.
+ */
+void lockup_detector_cleanup(void)
+{
+	mutex_lock(&watchdog_mutex);
+	__lockup_detector_cleanup();
+	mutex_unlock(&watchdog_mutex);
+}
+
 /**
  * lockup_detector_soft_poweroff - Interface to stop lockup detector(s)
  *
@@ -665,6 +687,8 @@ static int proc_watchdog_update(void)
 
 	watchdog_nmi_reconfigure();
 
+	__lockup_detector_cleanup();
+
 	return err;
 
 }
@@ -837,6 +861,7 @@ int proc_watchdog_cpumask(struct ctl_table *table, int write,
 		}
 
 		watchdog_nmi_reconfigure();
+		__lockup_detector_cleanup();
 	}
 
 	mutex_unlock(&watchdog_mutex);
diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c
index 7b60271..94111cc 100644
--- a/kernel/watchdog_hld.c
+++ b/kernel/watchdog_hld.c
@@ -21,6 +21,8 @@
 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;
 static bool hardlockup_detector_disabled;
@@ -239,16 +241,18 @@ out:
 	return 0;
 }
 
-void watchdog_nmi_disable(unsigned int cpu)
+/**
+ * hardlockup_detector_perf_disable - Disable the local event
+ */
+void hardlockup_detector_perf_disable(void)
 {
-	struct perf_event *event = per_cpu(watchdog_ev, cpu);
+	struct perf_event *event = this_cpu_read(watchdog_ev);
 
 	if (event) {
 		perf_event_disable(event);
-		per_cpu(watchdog_ev, cpu) = NULL;
-
-		/* should be in cleanup, but blocks oprofile */
-		perf_event_release_kernel(event);
+		this_cpu_write(watchdog_ev, NULL);
+		this_cpu_write(dead_event, event);
+		cpumask_set_cpu(smp_processor_id(), &dead_events_mask);
 
 		/* watchdog_nmi_enable() expects this to be zero initially. */
 		if (atomic_dec_and_test(&watchdog_cpus))
@@ -257,6 +261,24 @@ void watchdog_nmi_disable(unsigned int cpu)
 }
 
 /**
+ * hardlockup_detector_perf_cleanup - Cleanup disabled events and destroy them
+ *
+ * Called from lockup_detector_cleanup(). Serialized by the caller.
+ */
+void hardlockup_detector_perf_cleanup(void)
+{
+	int cpu;
+
+	for_each_cpu(cpu, &dead_events_mask) {
+		struct perf_event *event = per_cpu(dead_event, cpu);
+
+		per_cpu(dead_event, cpu) = NULL;
+		perf_event_release_kernel(event);
+	}
+	cpumask_clear(&dead_events_mask);
+}
+
+/**
  * hardlockup_detector_perf_stop - Globally stop watchdog events
  *
  * Special interface for x86 to handle the perf HT bug.

  reply index

Thread overview: 77+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-09-12 19:36 [patch V2 00/29] lockup_detector: Cure hotplug deadlocks and replace duct tape Thomas Gleixner
2017-09-12 19:36 ` [patch V2 01/29] hardlockup_detector: Provide interface to stop/restart perf events Thomas Gleixner
2017-09-14 10:40   ` [tip:core/urgent] watchdog/hardlockup: " tip-bot for Peter Zijlstra
2017-09-12 19:36 ` [patch V2 02/29] perf/x86/intel: Sanitize PMU HT bug workaround Thomas Gleixner
2017-09-14 10:40   ` [tip:core/urgent] perf/x86/intel, watchdog/core: " tip-bot for Peter Zijlstra
2017-09-12 19:36 ` [patch V2 03/29] lockup_detector: Provide interface to stop from poweroff() Thomas Gleixner
2017-09-14 10:40   ` [tip:core/urgent] watchdog/core: " tip-bot for Thomas Gleixner
2017-09-12 19:36 ` [patch V2 04/29] parisc: Use lockup_detector_stop() Thomas Gleixner
2017-09-14  8:59   ` Helge Deller
2017-09-14 13:46     ` Don Zickus
2017-09-14 10:41   ` [tip:core/urgent] parisc, watchdog/core: " tip-bot for Thomas Gleixner
2017-09-12 19:36 ` [patch V2 05/29] lockup_detector: Remove broken suspend/resume interfaces Thomas Gleixner
2017-09-14 10:41   ` [tip:core/urgent] watchdog/core: " tip-bot for Thomas Gleixner
2017-09-12 19:37 ` [patch V2 06/29] lockup_detector: Rework cpu hotplug locking Thomas Gleixner
2017-09-14 10:41   ` [tip:core/urgent] watchdog/core: Rework CPU " tip-bot for Thomas Gleixner
2017-09-12 19:37 ` [patch V2 07/29] lockup_detector: Rename watchdog_proc_mutex Thomas Gleixner
2017-09-14 10:42   ` [tip:core/urgent] watchdog/core: " tip-bot for Thomas Gleixner
2017-09-12 19:37 ` [patch V2 08/29] lockup_detector: Mark hardlockup_detector_disable() __init Thomas Gleixner
2017-09-14 10:42   ` [tip:core/urgent] watchdog/core: " tip-bot for Thomas Gleixner
2017-09-12 19:37 ` [patch V2 09/29] lockup_detector/perf: Remove broken self disable on failure Thomas Gleixner
2017-09-14 10:43   ` [tip:core/urgent] watchdog/hardlockup/perf: " tip-bot for Thomas Gleixner
2017-09-12 19:37 ` [patch V2 10/29] lockup_detector/perf: Prevent cpu hotplug deadlock Thomas Gleixner
2017-09-14 10:43   ` tip-bot for Thomas Gleixner [this message]
2017-09-12 19:37 ` [patch V2 11/29] lockup_detector: Remove park_in_progress obfuscation Thomas Gleixner
2017-09-12 19:37 ` [patch V2 12/29] lockup_detector: Cleanup stub functions Thomas Gleixner
2017-09-14 10:44   ` [tip:core/urgent] watchdog/core: Clean up " tip-bot for Thomas Gleixner
2017-09-12 19:37 ` [patch V2 13/29] lockup_detector: Cleanup the ifdef maze Thomas Gleixner
2017-09-14 10:44   ` [tip:core/urgent] watchdog/core: Clean up the #ifdef maze tip-bot for Thomas Gleixner
2017-09-12 19:37 ` [patch V2 14/29] lockup_detector: Split out cpumask write function Thomas Gleixner
2017-09-14 10:45   ` [tip:core/urgent] watchdog/core: " tip-bot for Thomas Gleixner
2017-09-12 19:37 ` [patch V2 15/29] smpboot/threads: Avoid runtime allocation Thomas Gleixner
2017-09-14 10:45   ` [tip:core/urgent] smpboot/threads, watchdog/core: " tip-bot for Thomas Gleixner
2017-09-12 19:37 ` [patch V2 16/29] lockup_detector: Create new thread handling infrastructure Thomas Gleixner
2017-09-14 10:45   ` [tip:core/urgent] watchdog/core: " tip-bot for Thomas Gleixner
2017-09-12 19:37 ` [patch V2 17/29] lockup_detector: Get rid of the thread teardown/setup dance Thomas Gleixner
2017-09-14 10:46   ` [tip:core/urgent] watchdog/core: " tip-bot for Thomas Gleixner
2017-09-12 19:37 ` [patch V2 18/29] lockup_detector: Further simplify sysctl handling Thomas Gleixner
2017-09-14 10:46   ` [tip:core/urgent] watchdog/core: " tip-bot for Thomas Gleixner
2017-09-12 19:37 ` [patch V2 19/29] lockup_detector: Cleanup header mess Thomas Gleixner
2017-09-14 10:47   ` [tip:core/urgent] watchdog/core: Clean up " tip-bot for Thomas Gleixner
2017-09-12 19:37 ` [patch V2 20/29] lockup_detector/sysctl: Get rid of the ifdeffery Thomas Gleixner
2017-09-14 10:47   ` [tip:core/urgent] watchdog/sysctl: Get rid of the #ifdeffery tip-bot for Thomas Gleixner
2017-09-12 19:37 ` [patch V2 21/29] lockup_detector: Cleanup sysctl variable name space Thomas Gleixner
2017-09-14 10:47   ` [tip:core/urgent] watchdog/sysctl: Clean up " tip-bot for Thomas Gleixner
2017-09-12 19:37 ` [patch V2 22/29] lockup_detector: Make watchdog_nmi_reconfigure() two stage Thomas Gleixner
2017-09-14 10:48   ` [tip:core/urgent] watchdog/core, powerpc: " tip-bot for Thomas Gleixner
2017-10-03  0:29   ` [patch V2 22/29] lockup_detector: " Michael Ellerman
2017-10-03  6:50     ` Thomas Gleixner
2017-10-03  7:04       ` Thomas Gleixner
2017-10-03 10:01         ` Nicholas Piggin
2017-10-03 10:56           ` Thomas Gleixner
2017-10-03 11:36       ` Michael Ellerman
2017-10-03 12:13         ` Thomas Gleixner
2017-10-03 13:20           ` Thomas Gleixner
2017-10-03 19:27             ` Thomas Gleixner
2017-10-04  5:53               ` Michael Ellerman
2017-10-05 16:17               ` Don Zickus
2017-09-12 19:37 ` [patch V2 23/29] lockup_detector: Get rid of the racy update loop Thomas Gleixner
2017-09-14 10:48   ` [tip:core/urgent] watchdog/core: " tip-bot for Thomas Gleixner
2017-09-12 19:37 ` [patch V2 24/29] lockup_detector/perf: Implement init time perf validation Thomas Gleixner
2017-09-14 10:48   ` [tip:core/urgent] watchdog/hardlockup/perf: " tip-bot for Thomas Gleixner
2017-09-12 19:37 ` [patch V2 25/29] lockup_detector: Implement init time detection of perf Thomas Gleixner
2017-09-13 18:02   ` Don Zickus
2017-09-13 18:05     ` Thomas Gleixner
2017-09-14  5:27       ` Ingo Molnar
2017-09-14 10:49   ` [tip:core/urgent] watchdog/hardlockup/perf: " tip-bot for Thomas Gleixner
2017-09-12 19:37 ` [patch V2 26/29] lockup_detector/perf: Implement CPU enable replacement Thomas Gleixner
2017-09-14 10:49   ` [tip:core/urgent] watchdog/hardlockup/perf: " tip-bot for Thomas Gleixner
2017-09-12 19:37 ` [patch V2 27/29] lockup_detector: Use new perf CPU enable mechanism Thomas Gleixner
2017-09-14 10:50   ` [tip:core/urgent] watchdog/hardlockup/perf: " tip-bot for Thomas Gleixner
2017-09-12 19:37 ` [patch V2 28/29] lockup_detector/perf: Simplify deferred event destroy Thomas Gleixner
2017-09-14 10:50   ` [tip:core/urgent] watchdog/hardlockup/perf: " tip-bot for Thomas Gleixner
2017-09-12 19:37 ` [patch V2 29/29] lockup_detector: Cleanup hotplug locking mess Thomas Gleixner
2017-09-14 10:50   ` [tip:core/urgent] watchdog/hardlockup: Clean up " tip-bot for Thomas Gleixner
2017-09-13 18:06 ` [patch V2 00/29] lockup_detector: Cure hotplug deadlocks and replace duct tape Don Zickus
2017-09-14  5:27   ` Ingo Molnar
2017-09-14  8:11   ` Thomas Gleixner

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=tip-941154bd6937a710ae9193a3c733c0029e5ae7b8@git.kernel.org \
    --to=tipbot@zytor.com \
    --cc=akpm@linux-foundation.org \
    --cc=bigeasy@linutronix.de \
    --cc=bp@alien8.de \
    --cc=cmetcalf@mellanox.com \
    --cc=dzickus@redhat.com \
    --cc=hpa@zytor.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-tip-commits@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=npiggin@gmail.com \
    --cc=peterz@infradead.org \
    --cc=tglx@linutronix.de \
    --cc=torvalds@linux-foundation.org \
    --cc=uobergfe@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lore.kernel.org/lkml/7 lkml/git/7.git
	git clone --mirror https://lore.kernel.org/lkml/8 lkml/git/8.git
	git clone --mirror https://lore.kernel.org/lkml/9 lkml/git/9.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 lkml lkml/ https://lore.kernel.org/lkml \
		linux-kernel@vger.kernel.org
	public-inbox-index lkml

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-kernel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git