linux.git/kernel/watchdog.c, branch v6.12.80

watchdog/softlockup: fix sample ring index wrap in need_counting_irqs()

2026-03-04T12:21:54+00:00

[ Upstream commit cafe4074a7221dca2fa954dd1ab0cf99b6318e23 ]

cpustat_tail indexes cpustat_util[], which is a NUM_SAMPLE_PERIODS-sized
ring buffer. need_counting_irqs() currently wraps the index using
NUM_HARDIRQ_REPORT, which only happens to match NUM_SAMPLE_PERIODS.

Use NUM_SAMPLE_PERIODS for the wrap to keep the ring math correct even if
the NUM_HARDIRQ_REPORT or  NUM_SAMPLE_PERIODS changes.

Link: https://lkml.kernel.org/r/tencent_7068189CB6D6689EB353F3D17BF5A5311A07@qq.com
Fixes: e9a9292e2368 ("watchdog/softlockup: Report the most frequent interrupts")
Signed-off-by: Shengming Hu 
Reviewed-by: Petr Mladek 
Cc: Ingo Molnar 
Cc: Mark Brown 
Cc: Thomas Gleixner 
Cc: Zhang Run 
Cc: 
Signed-off-by: Andrew Morton 
Signed-off-by: Sasha Levin

watchdog: fix watchdog may detect false positive of softlockup

2025-06-27T10:11:22+00:00

commit 7123dbbef88cfd9f09e8a7899b0911834600cfa3 upstream.

When updating `watchdog_thresh`, there is a race condition between writing
the new `watchdog_thresh` value and stopping the old watchdog timer.  If
the old timer triggers during this window, it may falsely detect a
softlockup due to the old interval and the new `watchdog_thresh` value
being used.  The problem can be described as follow:

 # We asuume previous watchdog_thresh is 60, so the watchdog timer is
 # coming every 24s.
echo 10 > /proc/sys/kernel/watchdog_thresh (User space)
|
+------>+ update watchdog_thresh (We are in kernel now)
	|
	|	  # using old interval and new `watchdog_thresh`
	+------>+ watchdog hrtimer (irq context: detect softlockup)
		|
		|
	+-------+
	|
	|
	+ softlockup_stop_all

To fix this problem, introduce a shadow variable for `watchdog_thresh`.
The update to the actual `watchdog_thresh` is delayed until after the old
timer is stopped, preventing false positives.

The following testcase may help to understand this problem.

---------------------------------------------
echo RT_RUNTIME_SHARE > /sys/kernel/debug/sched/features
echo -1 > /proc/sys/kernel/sched_rt_runtime_us
echo 0 > /sys/kernel/debug/sched/fair_server/cpu3/runtime
echo 60 > /proc/sys/kernel/watchdog_thresh
taskset -c 3 chrt -r 99 /bin/bash -c "while true;do true; done" &
echo 10 > /proc/sys/kernel/watchdog_thresh &
---------------------------------------------

The test case above first removes the throttling restrictions for
real-time tasks.  It then sets watchdog_thresh to 60 and executes a
real-time task ,a simple while(1) loop, on cpu3.  Consequently, the final
command gets blocked because the presence of this real-time thread
prevents kworker:3 from being selected by the scheduler.  This eventually
triggers a softlockup detection on cpu3 due to watchdog_timer_fn operating
with inconsistent variable - using both the old interval and the updated
watchdog_thresh simultaneously.

[nysal@linux.ibm.com: fix the SOFTLOCKUP_DETECTOR=n case]
  Link: https://lkml.kernel.org/r/20250502111120.282690-1-nysal@linux.ibm.com
Link: https://lkml.kernel.org/r/20250421035021.3507649-1-luogengkun@huaweicloud.com
Signed-off-by: Luo Gengkun 
Signed-off-by: Nysal Jan K.A. 
Cc: Doug Anderson 
Cc: Joel Granados 
Cc: Song Liu 
Cc: Thomas Gleinxer 
Cc: "Nysal Jan K.A." 
Cc: Venkat Rao Bagalkote 
Cc: 
Signed-off-by: Andrew Morton 
Signed-off-by: Greg Kroah-Hartman

watchdog/hardlockup/perf: Fix perf_event memory leak

2025-04-10T12:39:11+00:00

[ Upstream commit d6834d9c990333bfa433bc1816e2417f268eebbe ]

During stress-testing, we found a kmemleak report for perf_event:

  unreferenced object 0xff110001410a33e0 (size 1328):
    comm "kworker/4:11", pid 288, jiffies 4294916004
    hex dump (first 32 bytes):
      b8 be c2 3b 02 00 11 ff 22 01 00 00 00 00 ad de  ...;....".......
      f0 33 0a 41 01 00 11 ff f0 33 0a 41 01 00 11 ff  .3.A.....3.A....
    backtrace (crc 24eb7b3a):
      [<00000000e211b653>] kmem_cache_alloc_node_noprof+0x269/0x2e0
      [<000000009d0985fa>] perf_event_alloc+0x5f/0xcf0
      [<00000000084ad4a2>] perf_event_create_kernel_counter+0x38/0x1b0
      [<00000000fde96401>] hardlockup_detector_event_create+0x50/0xe0
      [<0000000051183158>] watchdog_hardlockup_enable+0x17/0x70
      [<00000000ac89727f>] softlockup_start_fn+0x15/0x40
      ...

Our stress test includes CPU online and offline cycles, and updating the
watchdog configuration.

After reading the code, I found that there may be a race between cleaning up
perf_event after updating watchdog and disabling event when the CPU goes offline:

  CPU0                          CPU1                           CPU2
  (update watchdog)                                            (hotplug offline CPU1)

  ...                                                          _cpu_down(CPU1)
  cpus_read_lock()                                             // waiting for cpu lock
    softlockup_start_all
      smp_call_on_cpu(CPU1)
                                softlockup_start_fn
                                ...
                                  watchdog_hardlockup_enable(CPU1)
                                    perf create E1
                                    watchdog_ev[CPU1] = E1
  cpus_read_unlock()
                                                               cpus_write_lock()
                                                               cpuhp_kick_ap_work(CPU1)
                                cpuhp_thread_fun
                                ...
                                  watchdog_hardlockup_disable(CPU1)
                                    watchdog_ev[CPU1] = NULL
                                    dead_event[CPU1] = E1
  __lockup_detector_cleanup
    for each dead_events_mask
      release each dead_event
      /*
       * CPU1 has not been added to
       * dead_events_mask, then E1
       * will not be released
       */
                                    CPU1 -> dead_events_mask
    cpumask_clear(&dead_events_mask)
    // dead_events_mask is cleared, E1 is leaked

In this case, the leaked perf_event E1 matches the perf_event leak
reported by kmemleak. Due to the low probability of problem recurrence
(only reported once), I added some hack delays in the code:

  static void __lockup_detector_reconfigure(void)
  {
    ...
          watchdog_hardlockup_start();
          cpus_read_unlock();
  +       mdelay(100);
          /*
           * Must be called outside the cpus locked section to prevent
           * recursive locking in the perf code.
    ...
  }

  void watchdog_hardlockup_disable(unsigned int cpu)
  {
    ...
                  perf_event_disable(event);
                  this_cpu_write(watchdog_ev, NULL);
                  this_cpu_write(dead_event, event);
  +               mdelay(100);
                  cpumask_set_cpu(smp_processor_id(), &dead_events_mask);
                  atomic_dec(&watchdog_cpus);
    ...
  }

  void hardlockup_detector_perf_cleanup(void)
  {
    ...
                          perf_event_release_kernel(event);
                  per_cpu(dead_event, cpu) = NULL;
          }
  +       mdelay(100);
          cpumask_clear(&dead_events_mask);
  }

Then, simultaneously performing CPU on/off and switching watchdog, it is
almost certain to reproduce this leak.

The problem here is that releasing perf_event is not within the CPU
hotplug read-write lock. Commit:

  941154bd6937 ("watchdog/hardlockup/perf: Prevent CPU hotplug deadlock")

introduced deferred release to solve the deadlock caused by calling
get_online_cpus() when releasing perf_event. Later, commit:

  efe951d3de91 ("perf/x86: Fix perf,x86,cpuhp deadlock")

removed the get_online_cpus() call on the perf_event release path to solve
another deadlock problem.

Therefore, it is now possible to move the release of perf_event back
into the CPU hotplug read-write lock, and release the event immediately
after disabling it.

Fixes: 941154bd6937 ("watchdog/hardlockup/perf: Prevent CPU hotplug deadlock")
Signed-off-by: Li Huafei 
Signed-off-by: Ingo Molnar 
Cc: Thomas Gleixner 
Cc: Peter Zijlstra 
Link: https://lore.kernel.org/r/20241021193004.308303-1-lihuafei1@huawei.com
Signed-off-by: Sasha Levin

watchdog: handle the ENODEV failure case of lockup_detector_delay_init() separately

2024-09-02T03:43:32+00:00

When watchdog_hardlockup_probe() is being called by
lockup_detector_delay_init(), an error return of -ENODEV will happen
for the arm64 arch when arch_perf_nmi_is_available() returns false. This
means that NMI is not usable by the hard lockup detector and so has to
be disabled. This can be considered a deficiency in that particular
arm64 chip, but there is nothing we can do about it.  That also means
the following error will always be reported when the kernel boot up.

  watchdog: Delayed init of the lockup detector failed: -19

The word "failed" itself has a connotation that there is something
wrong with the kernel which is not really the case here. Handle this
special ENODEV case separately and explain the reason behind disabling
hard lockup detector without causing anxiety for those users who read
the above message and wonder about it.

Link: https://lkml.kernel.org/r/20240802151621.617244-1-longman@redhat.com
Signed-off-by: Waiman Long 
Cc: Douglas Anderson 
Cc: Joel Granados 
Cc: Li Zhe 
Cc: Petr Mladek 
Cc: Thomas Weißschuh 
Signed-off-by: Andrew Morton

sysctl: treewide: constify the ctl_table argument of proc_handlers

2024-07-24T18:59:29+00:00

const qualify the struct ctl_table argument in the proc_handler function
signatures. This is a prerequisite to moving the static ctl_table
structs into .rodata data which will ensure that proc_handler function
pointers cannot be modified.

This patch has been generated by the following coccinelle script:

```
  virtual patch

  @r1@
  identifier ctl, write, buffer, lenp, ppos;
  identifier func !~ "appldata_(timer|interval)_handler|sched_(rt|rr)_handler|rds_tcp_skbuf_handler|proc_sctp_do_(hmac_alg|rto_min|rto_max|udp_port|alpha_beta|auth|probe_interval)";
  @@

  int func(
  - struct ctl_table *ctl
  + const struct ctl_table *ctl
    ,int write, void *buffer, size_t *lenp, loff_t *ppos);

  @r2@
  identifier func, ctl, write, buffer, lenp, ppos;
  @@

  int func(
  - struct ctl_table *ctl
  + const struct ctl_table *ctl
    ,int write, void *buffer, size_t *lenp, loff_t *ppos)
  { ... }

  @r3@
  identifier func;
  @@

  int func(
  - struct ctl_table *
  + const struct ctl_table *
    ,int , void *, size_t *, loff_t *);

  @r4@
  identifier func, ctl;
  @@

  int func(
  - struct ctl_table *ctl
  + const struct ctl_table *ctl
    ,int , void *, size_t *, loff_t *);

  @r5@
  identifier func, write, buffer, lenp, ppos;
  @@

  int func(
  - struct ctl_table *
  + const struct ctl_table *
    ,int write, void *buffer, size_t *lenp, loff_t *ppos);

```

* Code formatting was adjusted in xfs_sysctl.c to comply with code
  conventions. The xfs_stats_clear_proc_handler,
  xfs_panic_mask_proc_handler and xfs_deprecated_dointvec_minmax where
  adjusted.

* The ctl_table argument in proc_watchdog_common was const qualified.
  This is called from a proc_handler itself and is calling back into
  another proc_handler, making it necessary to change it as part of the
  proc_handler migration.

Co-developed-by: Thomas Weißschuh 
Signed-off-by: Thomas Weißschuh 
Co-developed-by: Joel Granados 
Signed-off-by: Joel Granados

Merge tag 'mm-nonmm-stable-2024-05-19-11-56' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

2024-05-19T21:02:03+00:00

Pull non-mm updates from Andrew Morton:
 "Mainly singleton patches, documented in their respective changelogs.
  Notable series include:

   - Some maintenance and performance work for ocfs2 in Heming Zhao's
     series "improve write IO performance when fragmentation is high".

   - Some ocfs2 bugfixes from Su Yue in the series "ocfs2 bugs fixes
     exposed by fstests".

   - kfifo header rework from Andy Shevchenko in the series "kfifo:
     Clean up kfifo.h".

   - GDB script fixes from Florian Rommel in the series "scripts/gdb:
     Fixes for $lx_current and $lx_per_cpu".

   - After much discussion, a coding-style update from Barry Song
     explaining one reason why inline functions are preferred over
     macros. The series is "codingstyle: avoid unused parameters for a
     function-like macro""

* tag 'mm-nonmm-stable-2024-05-19-11-56' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (62 commits)
  fs/proc: fix softlockup in __read_vmcore
  nilfs2: convert BUG_ON() in nilfs_finish_roll_forward() to WARN_ON()
  scripts: checkpatch: check unused parameters for function-like macro
  Documentation: coding-style: ask function-like macros to evaluate parameters
  nilfs2: use __field_struct() for a bitwise field
  selftests/kcmp: remove unused open mode
  nilfs2: remove calls to folio_set_error() and folio_clear_error()
  kernel/watchdog_perf.c: tidy up kerneldoc
  watchdog: allow nmi watchdog to use raw perf event
  watchdog: handle comma separated nmi_watchdog command line
  nilfs2: make superblock data array index computation sparse friendly
  squashfs: remove calls to set the folio error flag
  squashfs: convert squashfs_symlink_read_folio to use folio APIs
  scripts/gdb: fix detection of current CPU in KGDB
  scripts/gdb: make get_thread_info accept pointers
  scripts/gdb: fix parameter handling in $lx_per_cpu
  scripts/gdb: fix failing KGDB detection during probe
  kfifo: don't use "proxy" headers
  media: stih-cec: add missing io.h
  media: rc: add missing io.h
  ...

Merge tag 'sysctl-6.10-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/sysctl/sysctl

2024-05-18T00:31:24+00:00

Pull sysctl updates from Joel Granados:

 - Remove sentinel elements from ctl_table structs in kernel/*

   Removing sentinels in ctl_table arrays reduces the build time size
   and runtime memory consumed by ~64 bytes per array. Removals for
   net/, io_uring/, mm/, ipc/ and security/ are set to go into mainline
   through their respective subsystems making the next release the most
   likely place where the final series that removes the check for
   proc_name == NULL will land.

   This adds to removals already in arch/, drivers/ and fs/.

 - Adjust ctl_table definitions and references to allow constification
     - Remove unused ctl_table function arguments
     - Move non-const elements from ctl_table to ctl_table_header
     - Make ctl_table pointers const in ctl_table_root structure

   Making the static ctl_table structs const will increase safety by
   keeping the pointers to proc_handler functions in .rodata. Though no
   ctl_tables where made const in this PR, the ground work for making
   that possible has started with these changes sent by Thomas
   Weißschuh.

* tag 'sysctl-6.10-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/sysctl/sysctl:
  sysctl: drop now unnecessary out-of-bounds check
  sysctl: move sysctl type to ctl_table_header
  sysctl: drop sysctl_is_perm_empty_ctl_table
  sysctl: treewide: constify argument ctl_table_root::permissions(table)
  sysctl: treewide: drop unused argument ctl_table_root::set_ownership(table)
  bpf: Remove the now superfluous sentinel elements from ctl_table array
  delayacct: Remove the now superfluous sentinel elements from ctl_table array
  kprobes: Remove the now superfluous sentinel elements from ctl_table array
  printk: Remove the now superfluous sentinel elements from ctl_table array
  scheduler: Remove the now superfluous sentinel elements from ctl_table array
  seccomp: Remove the now superfluous sentinel elements from ctl_table array
  timekeeping: Remove the now superfluous sentinel elements from ctl_table array
  ftrace: Remove the now superfluous sentinel elements from ctl_table array
  umh: Remove the now superfluous sentinel elements from ctl_table array
  kernel misc: Remove the now superfluous sentinel elements from ctl_table array

watchdog: allow nmi watchdog to use raw perf event

2024-05-08T15:41:29+00:00

NMI watchdog permanently consumes one hardware counters per CPU on the
system.  For systems that use many hardware counters, this causes more
aggressive time multiplexing of perf events.

OTOH, some CPUs (mostly Intel) support "ref-cycles" event, which is rarely
used.  Add kernel cmdline arg nmi_watchdog=rNNN to configure the watchdog
to use raw event.  For example, on Intel CPUs, we can use "r300" to
configure the watchdog to use ref-cycles event.

If the raw event does not work, fall back to use "cycles".

[akpm@linux-foundation.org: fix kerneldoc]
Link: https://lkml.kernel.org/r/20240430060236.1878002-2-song@kernel.org
Signed-off-by: Song Liu 
Cc: Peter Zijlstra 
Cc: "Matthew Wilcox (Oracle)" 
Signed-off-by: Andrew Morton

watchdog: handle comma separated nmi_watchdog command line

2024-05-08T15:41:28+00:00

Per the document, the kernel can accept comma separated command line like
nmi_watchdog=nopanic,0.  However, the code doesn't really handle it.  Fix
the kernel to handle it properly.

Link: https://lkml.kernel.org/r/20240430060236.1878002-1-song@kernel.org
Signed-off-by: Song Liu 
Cc: Peter Zijlstra 
Signed-off-by: Andrew Morton

kernel misc: Remove the now superfluous sentinel elements from ctl_table array

2024-04-24T07:43:53+00:00

This commit comes at the tail end of a greater effort to remove the
empty elements at the end of the ctl_table arrays (sentinels) which
will reduce the overall build time size of the kernel and run time
memory bloat by ~64 bytes per sentinel (further information Link :
https://lore.kernel.org/all/ZO5Yx5JFogGi%2FcBo@bombadil.infradead.org/)

Remove the sentinel from ctl_table arrays. Reduce by one the values used
to compare the size of the adjusted arrays.

Signed-off-by: Joel Granados