Merge tag 'mm-nonmm-stable-2023-06-24-19-23' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull non-mm updates from Andrew Morton:

 - Arnd Bergmann has fixed a bunch of -Wmissing-prototypes in top-level
   directories

 - Douglas Anderson has added a new "buddy" mode to the hardlockup
   detector. It permits the detector to work on architectures which
   cannot provide the required interrupts, by having CPUs periodically
   perform checks on other CPUs

 - Zhen Lei has enhanced kexec's ability to support two crash regions

 - Petr Mladek has done a lot of cleanup on the hard lockup detector's
   Kconfig entries

 - And the usual bunch of singleton patches in various places

* tag 'mm-nonmm-stable-2023-06-24-19-23' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (72 commits)
  kernel/time/posix-stubs.c: remove duplicated include
  ocfs2: remove redundant assignment to variable bit_off
  watchdog/hardlockup: fix typo in config HARDLOCKUP_DETECTOR_PREFER_BUDDY
  powerpc: move arch_trigger_cpumask_backtrace from nmi.h to irq.h
  devres: show which resource was invalid in __devm_ioremap_resource()
  watchdog/hardlockup: define HARDLOCKUP_DETECTOR_ARCH
  watchdog/sparc64: define HARDLOCKUP_DETECTOR_SPARC64
  watchdog/hardlockup: make HAVE_NMI_WATCHDOG sparc64-specific
  watchdog/hardlockup: declare arch_touch_nmi_watchdog() only in linux/nmi.h
  watchdog/hardlockup: make the config checks more straightforward
  watchdog/hardlockup: sort hardlockup detector related config values a logical way
  watchdog/hardlockup: move SMP barriers from common code to buddy code
  watchdog/buddy: simplify the dependency for HARDLOCKUP_DETECTOR_PREFER_BUDDY
  watchdog/buddy: don't copy the cpumask in watchdog_next_cpu()
  watchdog/buddy: cleanup how watchdog_buddy_check_hardlockup() is called
  watchdog/hardlockup: remove softlockup comment in touch_nmi_watchdog()
  watchdog/hardlockup: in watchdog_hardlockup_check() use cpumask_copy()
  watchdog/hardlockup: don't use raw_cpu_ptr() in watchdog_hardlockup_kick()
  watchdog/hardlockup: HAVE_NMI_WATCHDOG must implement watchdog_hardlockup_probe()
  watchdog/hardlockup: keep kernel.nmi_watchdog sysctl as 0444 if probe fails
  ...

kernel/Makefile

@@ -91,7 +91,8 @@ obj-$(CONFIG_FAIL_FUNCTION) += fail_function.o
 obj-$(CONFIG_KGDB) += debug/
 obj-$(CONFIG_DETECT_HUNG_TASK) += hung_task.o
 obj-$(CONFIG_LOCKUP_DETECTOR) += watchdog.o
-obj-$(CONFIG_HARDLOCKUP_DETECTOR_PERF) += watchdog_hld.o
+obj-$(CONFIG_HARDLOCKUP_DETECTOR_BUDDY) += watchdog_buddy.o
+obj-$(CONFIG_HARDLOCKUP_DETECTOR_PERF) += watchdog_perf.o
 obj-$(CONFIG_SECCOMP) += seccomp.o
 obj-$(CONFIG_RELAY) += relay.o
 obj-$(CONFIG_SYSCTL) += utsname_sysctl.o

kernel/fork.c

@@ -252,23 +252,19 @@ static int memcg_charge_kernel_stack(struct vm_struct *vm)
 {
 	int i;
 	int ret;
+	int nr_charged = 0;
 
-	BUILD_BUG_ON(IS_ENABLED(CONFIG_VMAP_STACK) && PAGE_SIZE % 1024 != 0);
 	BUG_ON(vm->nr_pages != THREAD_SIZE / PAGE_SIZE);
 
 	for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) {
 		ret = memcg_kmem_charge_page(vm->pages[i], GFP_KERNEL, 0);
 		if (ret)
 			goto err;
+		nr_charged++;
 	}
 	return 0;
 err:
-	/*
-	 * If memcg_kmem_charge_page() fails, page's memory cgroup pointer is
-	 * NULL, and memcg_kmem_uncharge_page() in free_thread_stack() will
-	 * ignore this page.
-	 */
-	for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++)
+	for (i = 0; i < nr_charged; i++)
 		memcg_kmem_uncharge_page(vm->pages[i], 0);
 	return ret;
 }

kernel/kcov.c

@@ -279,7 +279,7 @@ void notrace __sanitizer_cov_trace_cmp4(u32 arg1, u32 arg2)
 }
 EXPORT_SYMBOL(__sanitizer_cov_trace_cmp4);
 
-void notrace __sanitizer_cov_trace_cmp8(u64 arg1, u64 arg2)
+void notrace __sanitizer_cov_trace_cmp8(kcov_u64 arg1, kcov_u64 arg2)
 {
 	write_comp_data(KCOV_CMP_SIZE(3), arg1, arg2, _RET_IP_);
 }
@@ -306,16 +306,17 @@ void notrace __sanitizer_cov_trace_const_cmp4(u32 arg1, u32 arg2)
 }
 EXPORT_SYMBOL(__sanitizer_cov_trace_const_cmp4);
 
-void notrace __sanitizer_cov_trace_const_cmp8(u64 arg1, u64 arg2)
+void notrace __sanitizer_cov_trace_const_cmp8(kcov_u64 arg1, kcov_u64 arg2)
 {
 	write_comp_data(KCOV_CMP_SIZE(3) | KCOV_CMP_CONST, arg1, arg2,
 			_RET_IP_);
 }
 EXPORT_SYMBOL(__sanitizer_cov_trace_const_cmp8);
 
-void notrace __sanitizer_cov_trace_switch(u64 val, u64 *cases)
+void notrace __sanitizer_cov_trace_switch(kcov_u64 val, void *arg)
 {
 	u64 i;
+	u64 *cases = arg;
 	u64 count = cases[0];
 	u64 size = cases[1];
 	u64 type = KCOV_CMP_CONST;

kernel/kexec_core.c

@@ -1091,6 +1091,11 @@ __bpf_kfunc void crash_kexec(struct pt_regs *regs)
 	}
 }
 
+static inline resource_size_t crash_resource_size(const struct resource *res)
+{
+	return !res->end ? 0 : resource_size(res);
+}
+
 ssize_t crash_get_memory_size(void)
 {
 	ssize_t size = 0;
@@ -1098,19 +1103,45 @@ ssize_t crash_get_memory_size(void)
 	if (!kexec_trylock())
 		return -EBUSY;
 
-	if (crashk_res.end != crashk_res.start)
-		size = resource_size(&crashk_res);
+	size += crash_resource_size(&crashk_res);
+	size += crash_resource_size(&crashk_low_res);
 
 	kexec_unlock();
 	return size;
 }
 
+static int __crash_shrink_memory(struct resource *old_res,
+				 unsigned long new_size)
+{
+	struct resource *ram_res;
+
+	ram_res = kzalloc(sizeof(*ram_res), GFP_KERNEL);
+	if (!ram_res)
+		return -ENOMEM;
+
+	ram_res->start = old_res->start + new_size;
+	ram_res->end   = old_res->end;
+	ram_res->flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM;
+	ram_res->name  = "System RAM";
+
+	if (!new_size) {
+		release_resource(old_res);
+		old_res->start = 0;
+		old_res->end   = 0;
+	} else {
+		crashk_res.end = ram_res->start - 1;
+	}
+
+	crash_free_reserved_phys_range(ram_res->start, ram_res->end);
+	insert_resource(&iomem_resource, ram_res);
+
+	return 0;
+}
+
 int crash_shrink_memory(unsigned long new_size)
 {
 	int ret = 0;
-	unsigned long start, end;
-	unsigned long old_size;
-	struct resource *ram_res;
+	unsigned long old_size, low_size;
 
 	if (!kexec_trylock())
 		return -EBUSY;
@@ -1119,36 +1150,42 @@ int crash_shrink_memory(unsigned long new_size)
 		ret = -ENOENT;
 		goto unlock;
 	}
-	start = crashk_res.start;
-	end = crashk_res.end;
-	old_size = (end == 0) ? 0 : end - start + 1;
+
+	low_size = crash_resource_size(&crashk_low_res);
+	old_size = crash_resource_size(&crashk_res) + low_size;
+	new_size = roundup(new_size, KEXEC_CRASH_MEM_ALIGN);
 	if (new_size >= old_size) {
 		ret = (new_size == old_size) ? 0 : -EINVAL;
 		goto unlock;
 	}
 
-	ram_res = kzalloc(sizeof(*ram_res), GFP_KERNEL);
-	if (!ram_res) {
-		ret = -ENOMEM;
-		goto unlock;
+	/*
+	 * (low_size > new_size) implies that low_size is greater than zero.
+	 * This also means that if low_size is zero, the else branch is taken.
+	 *
+	 * If low_size is greater than 0, (low_size > new_size) indicates that
+	 * crashk_low_res also needs to be shrunken. Otherwise, only crashk_res
+	 * needs to be shrunken.
+	 */
+	if (low_size > new_size) {
+		ret = __crash_shrink_memory(&crashk_res, 0);
+		if (ret)
+			goto unlock;
+
+		ret = __crash_shrink_memory(&crashk_low_res, new_size);
+	} else {
+		ret = __crash_shrink_memory(&crashk_res, new_size - low_size);
 	}
 
-	start = roundup(start, KEXEC_CRASH_MEM_ALIGN);
-	end = roundup(start + new_size, KEXEC_CRASH_MEM_ALIGN);
-
-	crash_free_reserved_phys_range(end, crashk_res.end);
-
-	if ((start == end) && (crashk_res.parent != NULL))
-		release_resource(&crashk_res);
-
-	ram_res->start = end;
-	ram_res->end = crashk_res.end;
-	ram_res->flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM;
-	ram_res->name = "System RAM";
-
-	crashk_res.end = end - 1;
-
-	insert_resource(&iomem_resource, ram_res);
+	/* Swap crashk_res and crashk_low_res if needed */
+	if (!crashk_res.end && crashk_low_res.end) {
+		crashk_res.start = crashk_low_res.start;
+		crashk_res.end   = crashk_low_res.end;
+		release_resource(&crashk_low_res);
+		crashk_low_res.start = 0;
+		crashk_low_res.end   = 0;
+		insert_resource(&iomem_resource, &crashk_res);
+	}
 
 unlock:
 	kexec_unlock();

kernel/kexec_file.c

@@ -867,6 +867,7 @@ static int kexec_purgatory_setup_sechdrs(struct purgatory_info *pi,
 {
 	unsigned long bss_addr;
 	unsigned long offset;
+	size_t sechdrs_size;
 	Elf_Shdr *sechdrs;
 	int i;
 
@@ -874,11 +875,11 @@ static int kexec_purgatory_setup_sechdrs(struct purgatory_info *pi,
 	 * The section headers in kexec_purgatory are read-only. In order to
 	 * have them modifiable make a temporary copy.
 	 */
-	sechdrs = vzalloc(array_size(sizeof(Elf_Shdr), pi->ehdr->e_shnum));
+	sechdrs_size = array_size(sizeof(Elf_Shdr), pi->ehdr->e_shnum);
+	sechdrs = vzalloc(sechdrs_size);
 	if (!sechdrs)
 		return -ENOMEM;
-	memcpy(sechdrs, (void *)pi->ehdr + pi->ehdr->e_shoff,
-	       pi->ehdr->e_shnum * sizeof(Elf_Shdr));
+	memcpy(sechdrs, (void *)pi->ehdr + pi->ehdr->e_shoff, sechdrs_size);
 	pi->sechdrs = sechdrs;
 
 	offset = 0;

kernel/kthread.c

@@ -322,10 +322,10 @@ void __noreturn kthread_exit(long result)
  * @comp: Completion to complete
  * @code: The integer value to return to kthread_stop().
  *
- * If present complete @comp and the reuturn code to kthread_stop().
+ * If present, complete @comp and then return code to kthread_stop().
  *
  * A kernel thread whose module may be removed after the completion of
- * @comp can use this function exit safely.
+ * @comp can use this function to exit safely.
  *
  * Does not return.
  */

kernel/locking/lock_events.h

@@ -57,4 +57,8 @@ static inline void __lockevent_add(enum lock_events event, int inc)
 #define lockevent_cond_inc(ev, c)
 
 #endif /* CONFIG_LOCK_EVENT_COUNTS */
+
+ssize_t lockevent_read(struct file *file, char __user *user_buf,
+		       size_t count, loff_t *ppos);
+
 #endif /* __LOCKING_LOCK_EVENTS_H */

kernel/panic.c

@@ -684,6 +684,7 @@ void __warn(const char *file, int line, void *caller, unsigned taint,
 	add_taint(taint, LOCKDEP_STILL_OK);
 }
 
+#ifdef CONFIG_BUG
 #ifndef __WARN_FLAGS
 void warn_slowpath_fmt(const char *file, int line, unsigned taint,
 		       const char *fmt, ...)
@@ -722,8 +723,6 @@ void __warn_printk(const char *fmt, ...)
 EXPORT_SYMBOL(__warn_printk);
 #endif
 
-#ifdef CONFIG_BUG
-
 /* Support resetting WARN*_ONCE state */
 
 static int clear_warn_once_set(void *data, u64 val)

kernel/watchdog.c

@@ -29,20 +29,18 @@
 
 static DEFINE_MUTEX(watchdog_mutex);
 
-#if defined(CONFIG_HARDLOCKUP_DETECTOR) || defined(CONFIG_HAVE_NMI_WATCHDOG)
-# define WATCHDOG_DEFAULT	(SOFT_WATCHDOG_ENABLED | NMI_WATCHDOG_ENABLED)
-# define NMI_WATCHDOG_DEFAULT	1
+#if defined(CONFIG_HARDLOCKUP_DETECTOR) || defined(CONFIG_HARDLOCKUP_DETECTOR_SPARC64)
+# define WATCHDOG_HARDLOCKUP_DEFAULT	1
 #else
-# define WATCHDOG_DEFAULT	(SOFT_WATCHDOG_ENABLED)
-# define NMI_WATCHDOG_DEFAULT	0
+# define WATCHDOG_HARDLOCKUP_DEFAULT	0
 #endif
 
 unsigned long __read_mostly watchdog_enabled;
 int __read_mostly watchdog_user_enabled = 1;
-int __read_mostly nmi_watchdog_user_enabled = NMI_WATCHDOG_DEFAULT;
-int __read_mostly soft_watchdog_user_enabled = 1;
+static int __read_mostly watchdog_hardlockup_user_enabled = WATCHDOG_HARDLOCKUP_DEFAULT;
+static int __read_mostly watchdog_softlockup_user_enabled = 1;
 int __read_mostly watchdog_thresh = 10;
-static int __read_mostly nmi_watchdog_available;
+static int __read_mostly watchdog_hardlockup_available;
 
 struct cpumask watchdog_cpumask __read_mostly;
 unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask);
@@ -68,7 +66,7 @@ unsigned int __read_mostly hardlockup_panic =
  */
 void __init hardlockup_detector_disable(void)
 {
-	nmi_watchdog_user_enabled = 0;
+	watchdog_hardlockup_user_enabled = 0;
 }
 
 static int __init hardlockup_panic_setup(char *str)
@@ -78,54 +76,163 @@ static int __init hardlockup_panic_setup(char *str)
 	else if (!strncmp(str, "nopanic", 7))
 		hardlockup_panic = 0;
 	else if (!strncmp(str, "0", 1))
-		nmi_watchdog_user_enabled = 0;
+		watchdog_hardlockup_user_enabled = 0;
 	else if (!strncmp(str, "1", 1))
-		nmi_watchdog_user_enabled = 1;
+		watchdog_hardlockup_user_enabled = 1;
 	return 1;
 }
 __setup("nmi_watchdog=", hardlockup_panic_setup);
 
 #endif /* CONFIG_HARDLOCKUP_DETECTOR */
 
+#if defined(CONFIG_HARDLOCKUP_DETECTOR_COUNTS_HRTIMER)
+
+static DEFINE_PER_CPU(atomic_t, hrtimer_interrupts);
+static DEFINE_PER_CPU(int, hrtimer_interrupts_saved);
+static DEFINE_PER_CPU(bool, watchdog_hardlockup_warned);
+static DEFINE_PER_CPU(bool, watchdog_hardlockup_touched);
+static unsigned long watchdog_hardlockup_all_cpu_dumped;
+
+notrace void arch_touch_nmi_watchdog(void)
+{
+	/*
+	 * Using __raw here because some code paths have
+	 * preemption enabled.  If preemption is enabled
+	 * then interrupts should be enabled too, in which
+	 * case we shouldn't have to worry about the watchdog
+	 * going off.
+	 */
+	raw_cpu_write(watchdog_hardlockup_touched, true);
+}
+EXPORT_SYMBOL(arch_touch_nmi_watchdog);
+
+void watchdog_hardlockup_touch_cpu(unsigned int cpu)
+{
+	per_cpu(watchdog_hardlockup_touched, cpu) = true;
+}
+
+static bool is_hardlockup(unsigned int cpu)
+{
+	int hrint = atomic_read(&per_cpu(hrtimer_interrupts, cpu));
+
+	if (per_cpu(hrtimer_interrupts_saved, cpu) == hrint)
+		return true;
+
+	/*
+	 * NOTE: we don't need any fancy atomic_t or READ_ONCE/WRITE_ONCE
+	 * for hrtimer_interrupts_saved. hrtimer_interrupts_saved is
+	 * written/read by a single CPU.
+	 */
+	per_cpu(hrtimer_interrupts_saved, cpu) = hrint;
+
+	return false;
+}
+
+static void watchdog_hardlockup_kick(void)
+{
+	int new_interrupts;
+
+	new_interrupts = atomic_inc_return(this_cpu_ptr(&hrtimer_interrupts));
+	watchdog_buddy_check_hardlockup(new_interrupts);
+}
+
+void watchdog_hardlockup_check(unsigned int cpu, struct pt_regs *regs)
+{
+	if (per_cpu(watchdog_hardlockup_touched, cpu)) {
+		per_cpu(watchdog_hardlockup_touched, cpu) = false;
+		return;
+	}
+
+	/*
+	 * Check for a hardlockup by making sure the CPU's timer
+	 * interrupt is incrementing. The timer interrupt should have
+	 * fired multiple times before we overflow'd. If it hasn't
+	 * then this is a good indication the cpu is stuck
+	 */
+	if (is_hardlockup(cpu)) {
+		unsigned int this_cpu = smp_processor_id();
+		struct cpumask backtrace_mask;
+
+		cpumask_copy(&backtrace_mask, cpu_online_mask);
+
+		/* Only print hardlockups once. */
+		if (per_cpu(watchdog_hardlockup_warned, cpu))
+			return;
+
+		pr_emerg("Watchdog detected hard LOCKUP on cpu %d\n", cpu);
+		print_modules();
+		print_irqtrace_events(current);
+		if (cpu == this_cpu) {
+			if (regs)
+				show_regs(regs);
+			else
+				dump_stack();
+			cpumask_clear_cpu(cpu, &backtrace_mask);
+		} else {
+			if (trigger_single_cpu_backtrace(cpu))
+				cpumask_clear_cpu(cpu, &backtrace_mask);
+		}
+
+		/*
+		 * Perform multi-CPU dump only once to avoid multiple
+		 * hardlockups generating interleaving traces
+		 */
+		if (sysctl_hardlockup_all_cpu_backtrace &&
+		    !test_and_set_bit(0, &watchdog_hardlockup_all_cpu_dumped))
+			trigger_cpumask_backtrace(&backtrace_mask);
+
+		if (hardlockup_panic)
+			nmi_panic(regs, "Hard LOCKUP");
+
+		per_cpu(watchdog_hardlockup_warned, cpu) = true;
+	} else {
+		per_cpu(watchdog_hardlockup_warned, cpu) = false;
+	}
+}
+
+#else /* CONFIG_HARDLOCKUP_DETECTOR_COUNTS_HRTIMER */
+
+static inline void watchdog_hardlockup_kick(void) { }
+
+#endif /* !CONFIG_HARDLOCKUP_DETECTOR_COUNTS_HRTIMER */
+
 /*
- * These functions can be overridden if an architecture implements its
- * own hardlockup detector.
+ * These functions can be overridden based on the configured hardlockdup detector.
  *
- * watchdog_nmi_enable/disable can be implemented to start and stop when
- * softlockup watchdog start and stop. The arch must select the
+ * watchdog_hardlockup_enable/disable can be implemented to start and stop when
+ * softlockup watchdog start and stop. The detector must select the
  * SOFTLOCKUP_DETECTOR Kconfig.
  */
-int __weak watchdog_nmi_enable(unsigned int cpu)
-{
-	hardlockup_detector_perf_enable();
-	return 0;
-}
+void __weak watchdog_hardlockup_enable(unsigned int cpu) { }
 
-void __weak watchdog_nmi_disable(unsigned int cpu)
-{
-	hardlockup_detector_perf_disable();
-}
+void __weak watchdog_hardlockup_disable(unsigned int cpu) { }
 
-/* Return 0, if a NMI watchdog is available. Error code otherwise */
-int __weak __init watchdog_nmi_probe(void)
+/*
+ * Watchdog-detector specific API.
+ *
+ * Return 0 when hardlockup watchdog is available, negative value otherwise.
+ * Note that the negative value means that a delayed probe might
+ * succeed later.
+ */
+int __weak __init watchdog_hardlockup_probe(void)
 {
-	return hardlockup_detector_perf_init();
+	return -ENODEV;
 }
 
 /**
- * watchdog_nmi_stop - Stop the watchdog for reconfiguration
+ * watchdog_hardlockup_stop - Stop the watchdog for reconfiguration
  *
  * The reconfiguration steps are:
- * watchdog_nmi_stop();
+ * watchdog_hardlockup_stop();
  * update_variables();
- * watchdog_nmi_start();
+ * watchdog_hardlockup_start();
  */
-void __weak watchdog_nmi_stop(void) { }
+void __weak watchdog_hardlockup_stop(void) { }
 
 /**
- * watchdog_nmi_start - Start the watchdog after reconfiguration
+ * watchdog_hardlockup_start - Start the watchdog after reconfiguration
  *
- * Counterpart to watchdog_nmi_stop().
+ * Counterpart to watchdog_hardlockup_stop().
  *
  * The following variables have been updated in update_variables() and
  * contain the currently valid configuration:
@@ -133,23 +240,23 @@ void __weak watchdog_nmi_stop(void) { }
  * - watchdog_thresh
  * - watchdog_cpumask
  */
-void __weak watchdog_nmi_start(void) { }
+void __weak watchdog_hardlockup_start(void) { }
 
 /**
  * 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 watchdog_nmi_disable().
+ * Caller needs to make sure that the hard watchdogs are off, so this
+ * can't race with watchdog_hardlockup_disable().
  */
 static void lockup_detector_update_enable(void)
 {
 	watchdog_enabled = 0;
 	if (!watchdog_user_enabled)
 		return;
-	if (nmi_watchdog_available && nmi_watchdog_user_enabled)
-		watchdog_enabled |= NMI_WATCHDOG_ENABLED;
-	if (soft_watchdog_user_enabled)
-		watchdog_enabled |= SOFT_WATCHDOG_ENABLED;
+	if (watchdog_hardlockup_available && watchdog_hardlockup_user_enabled)
+		watchdog_enabled |= WATCHDOG_HARDLOCKUP_ENABLED;
+	if (watchdog_softlockup_user_enabled)
+		watchdog_enabled |= WATCHDOG_SOFTOCKUP_ENABLED;
 }
 
 #ifdef CONFIG_SOFTLOCKUP_DETECTOR
@@ -179,8 +286,6 @@ static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts);
 static DEFINE_PER_CPU(unsigned long, watchdog_report_ts);
 static DEFINE_PER_CPU(struct hrtimer, watchdog_hrtimer);
 static DEFINE_PER_CPU(bool, softlockup_touch_sync);
-static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts);
-static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved);
 static unsigned long soft_lockup_nmi_warn;
 
 static int __init nowatchdog_setup(char *str)
@@ -192,7 +297,7 @@ __setup("nowatchdog", nowatchdog_setup);
 
 static int __init nosoftlockup_setup(char *str)
 {
-	soft_watchdog_user_enabled = 0;
+	watchdog_softlockup_user_enabled = 0;
 	return 1;
 }
 __setup("nosoftlockup", nosoftlockup_setup);
@@ -306,7 +411,7 @@ static int is_softlockup(unsigned long touch_ts,
 			 unsigned long period_ts,
 			 unsigned long now)
 {
-	if ((watchdog_enabled & SOFT_WATCHDOG_ENABLED) && watchdog_thresh){
+	if ((watchdog_enabled & WATCHDOG_SOFTOCKUP_ENABLED) && watchdog_thresh) {
 		/* Warn about unreasonable delays. */
 		if (time_after(now, period_ts + get_softlockup_thresh()))
 			return now - touch_ts;
@@ -315,22 +420,6 @@ static int is_softlockup(unsigned long touch_ts,
 }
 
 /* watchdog detector functions */
-bool is_hardlockup(void)
-{
-	unsigned long hrint = __this_cpu_read(hrtimer_interrupts);
-
-	if (__this_cpu_read(hrtimer_interrupts_saved) == hrint)
-		return true;
-
-	__this_cpu_write(hrtimer_interrupts_saved, hrint);
-	return false;
-}
-
-static void watchdog_interrupt_count(void)
-{
-	__this_cpu_inc(hrtimer_interrupts);
-}
-
 static DEFINE_PER_CPU(struct completion, softlockup_completion);
 static DEFINE_PER_CPU(struct cpu_stop_work, softlockup_stop_work);
 
@@ -361,8 +450,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 	if (!watchdog_enabled)
 		return HRTIMER_NORESTART;
 
-	/* kick the hardlockup detector */
-	watchdog_interrupt_count();
+	watchdog_hardlockup_kick();
 
 	/* kick the softlockup detector */
 	if (completion_done(this_cpu_ptr(&softlockup_completion))) {
@@ -458,7 +546,7 @@ static void watchdog_enable(unsigned int cpu)
 	complete(done);
 
 	/*
-	 * Start the timer first to prevent the NMI watchdog triggering
+	 * Start the timer first to prevent the hardlockup watchdog triggering
 	 * before the timer has a chance to fire.
 	 */
 	hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
@@ -468,9 +556,9 @@ static void watchdog_enable(unsigned int cpu)
 
 	/* Initialize timestamp */
 	update_touch_ts();
-	/* Enable the perf event */
-	if (watchdog_enabled & NMI_WATCHDOG_ENABLED)
-		watchdog_nmi_enable(cpu);
+	/* Enable the hardlockup detector */
+	if (watchdog_enabled & WATCHDOG_HARDLOCKUP_ENABLED)
+		watchdog_hardlockup_enable(cpu);
 }
 
 static void watchdog_disable(unsigned int cpu)
@@ -480,11 +568,11 @@ static void watchdog_disable(unsigned int cpu)
 	WARN_ON_ONCE(cpu != smp_processor_id());
 
 	/*
-	 * Disable the perf event first. That prevents that a large delay
-	 * between disabling the timer and disabling the perf event causes
-	 * the perf NMI to detect a false positive.
+	 * Disable the hardlockup detector first. That prevents that a large
+	 * delay between disabling the timer and disabling the hardlockup
+	 * detector causes a false positive.
 	 */
-	watchdog_nmi_disable(cpu);
+	watchdog_hardlockup_disable(cpu);
 	hrtimer_cancel(hrtimer);
 	wait_for_completion(this_cpu_ptr(&softlockup_completion));
 }
@@ -540,7 +628,7 @@ int lockup_detector_offline_cpu(unsigned int cpu)
 static void __lockup_detector_reconfigure(void)
 {
 	cpus_read_lock();
-	watchdog_nmi_stop();
+	watchdog_hardlockup_stop();
 
 	softlockup_stop_all();
 	set_sample_period();
@@ -548,7 +636,7 @@ static void __lockup_detector_reconfigure(void)
 	if (watchdog_enabled && watchdog_thresh)
 		softlockup_start_all();
 
-	watchdog_nmi_start();
+	watchdog_hardlockup_start();
 	cpus_read_unlock();
 	/*
 	 * Must be called outside the cpus locked section to prevent
@@ -589,9 +677,9 @@ static __init void lockup_detector_setup(void)
 static void __lockup_detector_reconfigure(void)
 {
 	cpus_read_lock();
-	watchdog_nmi_stop();
+	watchdog_hardlockup_stop();
 	lockup_detector_update_enable();
-	watchdog_nmi_start();
+	watchdog_hardlockup_start();
 	cpus_read_unlock();
 }
 void lockup_detector_reconfigure(void)
@@ -646,14 +734,14 @@ static void proc_watchdog_update(void)
 /*
  * common function for watchdog, nmi_watchdog and soft_watchdog parameter
  *
- * caller             | table->data points to      | 'which'
- * -------------------|----------------------------|--------------------------
- * proc_watchdog      | watchdog_user_enabled      | NMI_WATCHDOG_ENABLED |
- *                    |                            | SOFT_WATCHDOG_ENABLED
- * -------------------|----------------------------|--------------------------
- * proc_nmi_watchdog  | nmi_watchdog_user_enabled  | NMI_WATCHDOG_ENABLED
- * -------------------|----------------------------|--------------------------
- * proc_soft_watchdog | soft_watchdog_user_enabled | SOFT_WATCHDOG_ENABLED
+ * caller             | table->data points to            | 'which'
+ * -------------------|----------------------------------|-------------------------------
+ * proc_watchdog      | watchdog_user_enabled            | WATCHDOG_HARDLOCKUP_ENABLED |
+ *                    |                                  | WATCHDOG_SOFTOCKUP_ENABLED
+ * -------------------|----------------------------------|-------------------------------
+ * proc_nmi_watchdog  | watchdog_hardlockup_user_enabled | WATCHDOG_HARDLOCKUP_ENABLED
+ * -------------------|----------------------------------|-------------------------------
+ * proc_soft_watchdog | watchdog_softlockup_user_enabled | WATCHDOG_SOFTOCKUP_ENABLED
  */
 static int proc_watchdog_common(int which, struct ctl_table *table, int write,
 				void *buffer, size_t *lenp, loff_t *ppos)
@@ -685,7 +773,8 @@ static int proc_watchdog_common(int which, struct ctl_table *table, int write,
 int proc_watchdog(struct ctl_table *table, int write,
 		  void *buffer, size_t *lenp, loff_t *ppos)
 {
-	return proc_watchdog_common(NMI_WATCHDOG_ENABLED|SOFT_WATCHDOG_ENABLED,
+	return proc_watchdog_common(WATCHDOG_HARDLOCKUP_ENABLED |
+				    WATCHDOG_SOFTOCKUP_ENABLED,
 				    table, write, buffer, lenp, ppos);
 }
 
@@ -695,9 +784,9 @@ int proc_watchdog(struct ctl_table *table, int write,
 int proc_nmi_watchdog(struct ctl_table *table, int write,
 		      void *buffer, size_t *lenp, loff_t *ppos)
 {
-	if (!nmi_watchdog_available && write)
+	if (!watchdog_hardlockup_available && write)
 		return -ENOTSUPP;
-	return proc_watchdog_common(NMI_WATCHDOG_ENABLED,
+	return proc_watchdog_common(WATCHDOG_HARDLOCKUP_ENABLED,
 				    table, write, buffer, lenp, ppos);
 }
 
@@ -707,7 +796,7 @@ int proc_nmi_watchdog(struct ctl_table *table, int write,
 int proc_soft_watchdog(struct ctl_table *table, int write,
 			void *buffer, size_t *lenp, loff_t *ppos)
 {
-	return proc_watchdog_common(SOFT_WATCHDOG_ENABLED,
+	return proc_watchdog_common(WATCHDOG_SOFTOCKUP_ENABLED,
 				    table, write, buffer, lenp, ppos);
 }
 
@@ -773,15 +862,6 @@ static struct ctl_table watchdog_sysctls[] = {
 		.extra1		= SYSCTL_ZERO,
 		.extra2		= (void *)&sixty,
 	},
-	{
-		.procname       = "nmi_watchdog",
-		.data		= &nmi_watchdog_user_enabled,
-		.maxlen		= sizeof(int),
-		.mode		= NMI_WATCHDOG_SYSCTL_PERM,
-		.proc_handler   = proc_nmi_watchdog,
-		.extra1		= SYSCTL_ZERO,
-		.extra2		= SYSCTL_ONE,
-	},
 	{
 		.procname	= "watchdog_cpumask",
 		.data		= &watchdog_cpumask_bits,
@@ -792,7 +872,7 @@ static struct ctl_table watchdog_sysctls[] = {
 #ifdef CONFIG_SOFTLOCKUP_DETECTOR
 	{
 		.procname       = "soft_watchdog",
-		.data		= &soft_watchdog_user_enabled,
+		.data		= &watchdog_softlockup_user_enabled,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler   = proc_soft_watchdog,
@@ -845,14 +925,90 @@ static struct ctl_table watchdog_sysctls[] = {
 	{}
 };
 
+static struct ctl_table watchdog_hardlockup_sysctl[] = {
+	{
+		.procname       = "nmi_watchdog",
+		.data		= &watchdog_hardlockup_user_enabled,
+		.maxlen		= sizeof(int),
+		.mode		= 0444,
+		.proc_handler   = proc_nmi_watchdog,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
+	{}
+};
+
 static void __init watchdog_sysctl_init(void)
 {
 	register_sysctl_init("kernel", watchdog_sysctls);
+
+	if (watchdog_hardlockup_available)
+		watchdog_hardlockup_sysctl[0].mode = 0644;
+	register_sysctl_init("kernel", watchdog_hardlockup_sysctl);
 }
+
 #else
 #define watchdog_sysctl_init() do { } while (0)
 #endif /* CONFIG_SYSCTL */
 
+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_hardlockup_probe();
+	if (ret) {
+		pr_info("Delayed init of the lockup detector failed: %d\n", ret);
+		pr_info("Hard watchdog permanently disabled\n");
+		return;
+	}
+
+	allow_lockup_detector_init_retry = false;
+
+	watchdog_hardlockup_available = true;
+	lockup_detector_setup();
+}
+
+/*
+ * lockup_detector_retry_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 lockup_detector_retry_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);
+
+	watchdog_sysctl_init();
+
+	return 0;
+
+}
+late_initcall_sync(lockup_detector_check);
+
 void __init lockup_detector_init(void)
 {
 	if (tick_nohz_full_enabled())
@@ -861,8 +1017,10 @@ void __init lockup_detector_init(void)
 	cpumask_copy(&watchdog_cpumask,
 		     housekeeping_cpumask(HK_TYPE_TIMER));
 
-	if (!watchdog_nmi_probe())
-		nmi_watchdog_available = true;
+	if (!watchdog_hardlockup_probe())
+		watchdog_hardlockup_available = true;
+	else
+		allow_lockup_detector_init_retry = true;
+
 	lockup_detector_setup();
-	watchdog_sysctl_init();
 }

kernel/watchdog_buddy.c

@@ -0,0 +1,113 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/kernel.h>
+#include <linux/nmi.h>
+#include <linux/percpu-defs.h>
+
+static cpumask_t __read_mostly watchdog_cpus;
+
+static unsigned int watchdog_next_cpu(unsigned int cpu)
+{
+	unsigned int next_cpu;
+
+	next_cpu = cpumask_next(cpu, &watchdog_cpus);
+	if (next_cpu >= nr_cpu_ids)
+		next_cpu = cpumask_first(&watchdog_cpus);
+
+	if (next_cpu == cpu)
+		return nr_cpu_ids;
+
+	return next_cpu;
+}
+
+int __init watchdog_hardlockup_probe(void)
+{
+	return 0;
+}
+
+void watchdog_hardlockup_enable(unsigned int cpu)
+{
+	unsigned int next_cpu;
+
+	/*
+	 * The new CPU will be marked online before the hrtimer interrupt
+	 * gets a chance to run on it. If another CPU tests for a
+	 * hardlockup on the new CPU before it has run its the hrtimer
+	 * interrupt, it will get a false positive. Touch the watchdog on
+	 * the new CPU to delay the check for at least 3 sampling periods
+	 * to guarantee one hrtimer has run on the new CPU.
+	 */
+	watchdog_hardlockup_touch_cpu(cpu);
+
+	/*
+	 * We are going to check the next CPU. Our watchdog_hrtimer
+	 * need not be zero if the CPU has already been online earlier.
+	 * Touch the watchdog on the next CPU to avoid false positive
+	 * if we try to check it in less then 3 interrupts.
+	 */
+	next_cpu = watchdog_next_cpu(cpu);
+	if (next_cpu < nr_cpu_ids)
+		watchdog_hardlockup_touch_cpu(next_cpu);
+
+	/*
+	 * Makes sure that watchdog is touched on this CPU before
+	 * other CPUs could see it in watchdog_cpus. The counter
+	 * part is in watchdog_buddy_check_hardlockup().
+	 */
+	smp_wmb();
+
+	cpumask_set_cpu(cpu, &watchdog_cpus);
+}
+
+void watchdog_hardlockup_disable(unsigned int cpu)
+{
+	unsigned int next_cpu = watchdog_next_cpu(cpu);
+
+	/*
+	 * Offlining this CPU will cause the CPU before this one to start
+	 * checking the one after this one. If this CPU just finished checking
+	 * the next CPU and updating hrtimer_interrupts_saved, and then the
+	 * previous CPU checks it within one sample period, it will trigger a
+	 * false positive. Touch the watchdog on the next CPU to prevent it.
+	 */
+	if (next_cpu < nr_cpu_ids)
+		watchdog_hardlockup_touch_cpu(next_cpu);
+
+	/*
+	 * Makes sure that watchdog is touched on the next CPU before
+	 * this CPU disappear in watchdog_cpus. The counter part is in
+	 * watchdog_buddy_check_hardlockup().
+	 */
+	smp_wmb();
+
+	cpumask_clear_cpu(cpu, &watchdog_cpus);
+}
+
+void watchdog_buddy_check_hardlockup(int hrtimer_interrupts)
+{
+	unsigned int next_cpu;
+
+	/*
+	 * Test for hardlockups every 3 samples. The sample period is
+	 *  watchdog_thresh * 2 / 5, so 3 samples gets us back to slightly over
+	 *  watchdog_thresh (over by 20%).
+	 */
+	if (hrtimer_interrupts % 3 != 0)
+		return;
+
+	/* check for a hardlockup on the next CPU */
+	next_cpu = watchdog_next_cpu(smp_processor_id());
+	if (next_cpu >= nr_cpu_ids)
+		return;
+
+	/*
+	 * Make sure that the watchdog was touched on next CPU when
+	 * watchdog_next_cpu() returned another one because of
+	 * a change in watchdog_hardlockup_enable()/disable().
+	 */
+	smp_rmb();
+
+	watchdog_hardlockup_check(next_cpu, NULL);
+}

kernel/watchdog_perf.c

@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Detect hard lockups on a system
+ * Detect hard lockups on a system using perf
  *
  * started by Don Zickus, Copyright (C) 2010 Red Hat, Inc.
  *
@@ -20,28 +20,12 @@
 #include <asm/irq_regs.h>
 #include <linux/perf_event.h>
 
-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 atomic_t watchdog_cpus = ATOMIC_INIT(0);
 
-notrace void arch_touch_nmi_watchdog(void)
-{
-	/*
-	 * Using __raw here because some code paths have
-	 * preemption enabled.  If preemption is enabled
-	 * then interrupts should be enabled too, in which
-	 * case we shouldn't have to worry about the watchdog
-	 * going off.
-	 */
-	raw_cpu_write(watchdog_nmi_touch, true);
-}
-EXPORT_SYMBOL(arch_touch_nmi_watchdog);
-
 #ifdef CONFIG_HARDLOCKUP_CHECK_TIMESTAMP
 static DEFINE_PER_CPU(ktime_t, last_timestamp);
 static DEFINE_PER_CPU(unsigned int, nmi_rearmed);
@@ -114,61 +98,24 @@ static void watchdog_overflow_callback(struct perf_event *event,
 	/* Ensure the watchdog never gets throttled */
 	event->hw.interrupts = 0;
 
-	if (__this_cpu_read(watchdog_nmi_touch) == true) {
-		__this_cpu_write(watchdog_nmi_touch, false);
-		return;
-	}
-
 	if (!watchdog_check_timestamp())
 		return;
 
-	/* check for a hardlockup
-	 * This is done by making sure our timer interrupt
-	 * is incrementing.  The timer interrupt should have
-	 * fired multiple times before we overflow'd.  If it hasn't
-	 * then this is a good indication the cpu is stuck
-	 */
-	if (is_hardlockup()) {
-		int this_cpu = smp_processor_id();
-
-		/* only print hardlockups once */
-		if (__this_cpu_read(hard_watchdog_warn) == true)
-			return;
-
-		pr_emerg("Watchdog detected hard LOCKUP on cpu %d\n",
-			 this_cpu);
-		print_modules();
-		print_irqtrace_events(current);
-		if (regs)
-			show_regs(regs);
-		else
-			dump_stack();
-
-		/*
-		 * Perform all-CPU dump only once to avoid multiple hardlockups
-		 * generating interleaving traces
-		 */
-		if (sysctl_hardlockup_all_cpu_backtrace &&
-				!test_and_set_bit(0, &hardlockup_allcpu_dumped))
-			trigger_allbutself_cpu_backtrace();
-
-		if (hardlockup_panic)
-			nmi_panic(regs, "Hard LOCKUP");
-
-		__this_cpu_write(hard_watchdog_warn, true);
-		return;
-	}
-
-	__this_cpu_write(hard_watchdog_warn, false);
-	return;
+	watchdog_hardlockup_check(smp_processor_id(), regs);
 }
 
 static int hardlockup_detector_event_create(void)
 {
-	unsigned int cpu = smp_processor_id();
+	unsigned int cpu;
 	struct perf_event_attr *wd_attr;
 	struct perf_event *evt;
 
+	/*
+	 * Preemption is not disabled because memory will be allocated.
+	 * Ensure CPU-locality by calling this in per-CPU kthread.
+	 */
+	WARN_ON(!is_percpu_thread());
+	cpu = raw_smp_processor_id();
 	wd_attr = &wd_hw_attr;
 	wd_attr->sample_period = hw_nmi_get_sample_period(watchdog_thresh);
 
@@ -185,10 +132,14 @@ static int hardlockup_detector_event_create(void)
 }
 
 /**
- * hardlockup_detector_perf_enable - Enable the local event
+ * watchdog_hardlockup_enable - Enable the local event
+ *
+ * @cpu: The CPU to enable hard lockup on.
  */
-void hardlockup_detector_perf_enable(void)
+void watchdog_hardlockup_enable(unsigned int cpu)
 {
+	WARN_ON_ONCE(cpu != smp_processor_id());
+
 	if (hardlockup_detector_event_create())
 		return;
 
@@ -200,12 +151,16 @@ void hardlockup_detector_perf_enable(void)
 }
 
 /**
- * hardlockup_detector_perf_disable - Disable the local event
+ * watchdog_hardlockup_disable - Disable the local event
+ *
+ * @cpu: The CPU to enable hard lockup on.
  */
-void hardlockup_detector_perf_disable(void)
+void watchdog_hardlockup_disable(unsigned int cpu)
 {
 	struct perf_event *event = this_cpu_read(watchdog_ev);
 
+	WARN_ON_ONCE(cpu != smp_processor_id());
+
 	if (event) {
 		perf_event_disable(event);
 		this_cpu_write(watchdog_ev, NULL);
@@ -268,7 +223,7 @@ void __init hardlockup_detector_perf_restart(void)
 
 	lockdep_assert_cpus_held();
 
-	if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED))
+	if (!(watchdog_enabled & WATCHDOG_HARDLOCKUP_ENABLED))
 		return;
 
 	for_each_online_cpu(cpu) {
@@ -279,12 +234,22 @@ void __init hardlockup_detector_perf_restart(void)
 	}
 }
 
-/**
- * hardlockup_detector_perf_init - Probe whether NMI event is available at all
- */
-int __init hardlockup_detector_perf_init(void)
+bool __weak __init arch_perf_nmi_is_available(void)
 {
-	int ret = hardlockup_detector_event_create();
+	return true;
+}
+
+/**
+ * watchdog_hardlockup_probe - Probe whether NMI event is available at all
+ */
+int __init watchdog_hardlockup_probe(void)
+{
+	int ret;
+
+	if (!arch_perf_nmi_is_available())
+		return -ENODEV;
+
+	ret = hardlockup_detector_event_create();
 
 	if (ret) {
 		pr_info("Perf NMI watchdog permanently disabled\n");