diff mbox series

[v5,4/6] kernel/watchdog: Adapt the watchdog_hld interface for async model

Message ID 20220613135956.15711-5-lecopzer.chen@mediatek.com (mailing list archive)
State New, archived
Headers show
Series Support hld delayed init based on Pseudo-NMI for | expand

Commit Message

Lecopzer Chen June 13, 2022, 1:59 p.m. UTC 
When lockup_detector_init()->watchdog_nmi_probe(), PMU may be not ready
yet. E.g. on arm64, PMU is not ready until
device_initcall(armv8_pmu_driver_init).  And it is deeply integrated
with the driver model and cpuhp. Hence it is hard to push this
initialization before smp_init().

But it is easy to take an opposite approach and try to initialize
the watchdog once again later.
The delayed probe is called using workqueues. It need to allocate
memory and must be proceed in a normal context.
The delayed probe is able to use if watchdog_nmi_probe() returns
non-zero which means the return code returned when PMU is not ready yet.

Provide an API - retry_lockup_detector_init() for anyone who needs
to delayed init lockup detector if they had ever failed at
lockup_detector_init().

The original assumption is: nobody should use delayed probe after
lockup_detector_check() which has __init attribute.
That is, anyone uses this API must call between lockup_detector_init()
and lockup_detector_check(), and the caller must have __init attribute

Reviewed-by: Petr Mladek <pmladek@suse.com>
Co-developed-by: Pingfan Liu <kernelfans@gmail.com>
Signed-off-by: Pingfan Liu <kernelfans@gmail.com>
Signed-off-by: Lecopzer Chen <lecopzer.chen@mediatek.com>
Suggested-by: Petr Mladek <pmladek@suse.com>
---
 include/linux/nmi.h |  2 ++
 kernel/watchdog.c   | 67 ++++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 68 insertions(+), 1 deletion(-)

Comments

kernel test robot June 14, 2022, 5:57 a.m. UTC | #1 
Hi Lecopzer,

Thank you for the patch! Yet something to improve:

[auto build test ERROR on arm64/for-next/core]
[also build test ERROR on arm/for-next kvmarm/next soc/for-next linus/master v5.19-rc2 next-20220610]
[cannot apply to xilinx-xlnx/master]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]

url:    https://github.com/intel-lab-lkp/linux/commits/Lecopzer-Chen/Support-hld-delayed-init-based-on-Pseudo-NMI-for/20220614-021318
base:   https://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux.git for-next/core
config: sparc64-randconfig-r026-20220613 (https://download.01.org/0day-ci/archive/20220614/202206141348.e7aqnN0q-lkp@intel.com/config)
compiler: sparc64-linux-gcc (GCC) 11.3.0
reproduce (this is a W=1 build):
        wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
        chmod +x ~/bin/make.cross
        # https://github.com/intel-lab-lkp/linux/commit/7df94eb967160312b005f9d8a29b558beec2d5a7
        git remote add linux-review https://github.com/intel-lab-lkp/linux
        git fetch --no-tags linux-review Lecopzer-Chen/Support-hld-delayed-init-based-on-Pseudo-NMI-for/20220614-021318
        git checkout 7df94eb967160312b005f9d8a29b558beec2d5a7
        # save the config file
        mkdir build_dir && cp config build_dir/.config
        COMPILER_INSTALL_PATH=$HOME/0day COMPILER=gcc-11.3.0 make.cross W=1 O=build_dir ARCH=sparc64 SHELL=/bin/bash

If you fix the issue, kindly add following tag where applicable
Reported-by: kernel test robot <lkp@intel.com>

All errors (new ones prefixed by >>):

   kernel/watchdog.c: In function 'lockup_detector_init':
>> kernel/watchdog.c:915:17: error: 'allow_lockup_detector_init_retry' undeclared (first use in this function); did you mean 'retry_lockup_detector_init'?
     915 |                 allow_lockup_detector_init_retry = true;
         |                 ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
         |                 retry_lockup_detector_init
   kernel/watchdog.c:915:17: note: each undeclared identifier is reported only once for each function it appears in


vim +915 kernel/watchdog.c

   903	
   904	void __init lockup_detector_init(void)
   905	{
   906		if (tick_nohz_full_enabled())
   907			pr_info("Disabling watchdog on nohz_full cores by default\n");
   908	
   909		cpumask_copy(&watchdog_cpumask,
   910			     housekeeping_cpumask(HK_TYPE_TIMER));
   911	
   912		if (!watchdog_nmi_probe())
   913			nmi_watchdog_available = true;
   914		else
 > 915			allow_lockup_detector_init_retry = true;
kernel test robot June 14, 2022, 6:18 a.m. UTC | #2 
Hi Lecopzer,

Thank you for the patch! Yet something to improve:

[auto build test ERROR on arm64/for-next/core]
[also build test ERROR on arm/for-next kvmarm/next soc/for-next]
[cannot apply to xilinx-xlnx/master]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]

url:    https://github.com/intel-lab-lkp/linux/commits/Lecopzer-Chen/Support-hld-delayed-init-based-on-Pseudo-NMI-for/20220614-021318
base:   https://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux.git for-next/core
config: hexagon-randconfig-r024-20220613 (https://download.01.org/0day-ci/archive/20220614/202206141412.PeVDy6qk-lkp@intel.com/config)
compiler: clang version 15.0.0 (https://github.com/llvm/llvm-project d378268ead93c85803c270277f0243737b536ae7)
reproduce (this is a W=1 build):
        wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
        chmod +x ~/bin/make.cross
        # https://github.com/intel-lab-lkp/linux/commit/7df94eb967160312b005f9d8a29b558beec2d5a7
        git remote add linux-review https://github.com/intel-lab-lkp/linux
        git fetch --no-tags linux-review Lecopzer-Chen/Support-hld-delayed-init-based-on-Pseudo-NMI-for/20220614-021318
        git checkout 7df94eb967160312b005f9d8a29b558beec2d5a7
        # save the config file
        mkdir build_dir && cp config build_dir/.config
        COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang make.cross W=1 O=build_dir ARCH=hexagon SHELL=/bin/bash

If you fix the issue, kindly add following tag where applicable
Reported-by: kernel test robot <lkp@intel.com>

All errors (new ones prefixed by >>):

>> kernel/watchdog.c:915:3: error: use of undeclared identifier 'allow_lockup_detector_init_retry'
                   allow_lockup_detector_init_retry = true;
                   ^
   1 error generated.


vim +/allow_lockup_detector_init_retry +915 kernel/watchdog.c

   903	
   904	void __init lockup_detector_init(void)
   905	{
   906		if (tick_nohz_full_enabled())
   907			pr_info("Disabling watchdog on nohz_full cores by default\n");
   908	
   909		cpumask_copy(&watchdog_cpumask,
   910			     housekeeping_cpumask(HK_TYPE_TIMER));
   911	
   912		if (!watchdog_nmi_probe())
   913			nmi_watchdog_available = true;
   914		else
 > 915			allow_lockup_detector_init_retry = true;
diff mbox series

Patch

diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index b7bcd63c36b4..10f2a305fe0d 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -118,6 +118,8 @@  static inline int hardlockup_detector_perf_init(void) { return 0; }
 
 void watchdog_nmi_stop(void);
 void watchdog_nmi_start(void);
+
+void retry_lockup_detector_init(void);
 int watchdog_nmi_probe(void);
 void watchdog_nmi_enable(unsigned int cpu);
 void watchdog_nmi_disable(unsigned int cpu);
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 458737bc4e35..654a193bcbaa 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -103,7 +103,13 @@  void __weak watchdog_nmi_disable(unsigned int cpu)
 	hardlockup_detector_perf_disable();
 }
 
-/* Return 0, if a NMI watchdog is available. Error code otherwise */
+/*
+ * Arch specific API.
+ *
+ * Return 0 when NMI watchdog is available, negative value otherwise.
+ * Note that the negative value means that a delayed probe might
+ * succeed later.
+ */
 int __weak __init watchdog_nmi_probe(void)
 {
 	return hardlockup_detector_perf_init();
@@ -835,6 +841,62 @@  static struct ctl_table watchdog_sysctls[] = {
 	{}
 };
 
+static void __init lockup_detector_delay_init(struct work_struct *work);
+static bool allow_lockup_detector_init_retry __initdata;
+
+static struct work_struct detector_work __initdata =
+		__WORK_INITIALIZER(detector_work, lockup_detector_delay_init);
+
+static void __init lockup_detector_delay_init(struct work_struct *work)
+{
+	int ret;
+
+	ret = watchdog_nmi_probe();
+	if (ret) {
+		pr_info("Delayed init of the lockup detector failed: %d\n", ret);
+		pr_info("Perf NMI watchdog permanently disabled\n");
+		return;
+	}
+
+	allow_lockup_detector_init_retry = false;
+
+	nmi_watchdog_available = true;
+	lockup_detector_setup();
+}
+
+/*
+ * retry_lockup_detector_init - retry init lockup detector if possible.
+ *
+ * Retry hardlockup detector init. It is useful when it requires some
+ * functionality that has to be initialized later on a particular
+ * platform.
+ */
+void __init retry_lockup_detector_init(void)
+{
+	/* Must be called before late init calls */
+	if (!allow_lockup_detector_init_retry)
+		return;
+
+	schedule_work(&detector_work);
+}
+
+/*
+ * Ensure that optional delayed hardlockup init is proceed before
+ * the init code and memory is freed.
+ */
+static int __init lockup_detector_check(void)
+{
+	/* Prevent any later retry. */
+	allow_lockup_detector_init_retry = false;
+
+	/* Make sure no work is pending. */
+	flush_work(&detector_work);
+
+	return 0;
+
+}
+late_initcall_sync(lockup_detector_check);
+
 static void __init watchdog_sysctl_init(void)
 {
 	register_sysctl_init("kernel", watchdog_sysctls);
@@ -853,6 +915,9 @@  void __init lockup_detector_init(void)
 
 	if (!watchdog_nmi_probe())
 		nmi_watchdog_available = true;
+	else
+		allow_lockup_detector_init_retry = true;
+
 	lockup_detector_setup();
 	watchdog_sysctl_init();
 }