Merge tag 'irq-core-2024-05-12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull interrupt subsystem updates from Thomas Gleixner:
 "Core code:

   - Interrupt storm detection for the lockup watchdog:

     Lockups which are caused by interrupt storms are not easy to debug
     because there is no information about the events which make the
     lockup detector trigger.

     To make this more user friendly, provide an extenstion to interrupt
     statistics which allows to take snapshots and an interface to
     retrieve the delta to the snapshot. Use this new mechanism in the
     watchdog code to do a two stage lockup analysis by taking the
     snapshot and printing the deltas for the topmost active interrupts
     on the second trigger.

     Note: This contains both the interrupt and the watchdog changes as
     the latter depend on the former obviously.

   - Avoid summation loops in the /proc/interrupts output and use the
     global counter when possible

   - Skip suspended interrupts on CPU hotplug operations to ensure that
     they are not delivered before the system resumes the device drivers
     when coming out of suspend.

   - On CPU hot-unplug interrupts which are affine to the outgoing CPU
     are migrated to a different CPU in the affinity mask. This can fail
     when the CPUs have no vectors left. Instead of giving up try to
     migrate it to any online CPU and thereby breaking the affinity
     setting in order to prevent a stale device interrupt which targets
     an offline CPU

   - The usual small cleanups

  Driver code:

   - Support for the RISCV AIA MSI controller

   - Make the interrupt allocation for the Loongson PCH controller more
     flexible to prevent vector exhaustion

   - The usual set of cleanups and fixes all over the place"

* tag 'irq-core-2024-05-12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (51 commits)
  irqchip/gic-v3-its: Remove BUG_ON in its_vpe_irq_domain_alloc
  cpuidle: Avoid explicit cpumask allocation on stack
  irqchip/sifive-plic: Avoid explicit cpumask allocation on stack
  irqchip/riscv-aplic-direct: Avoid explicit cpumask allocation on stack
  irqchip/loongson-eiointc: Avoid explicit cpumask allocation on stack
  irqchip/gic-v3-its: Avoid explicit cpumask allocation on stack
  irqchip/irq-bcm6345-l1: Avoid explicit cpumask allocation on stack
  cpumask: Introduce cpumask_first_and_and()
  irqchip/irq-brcmstb-l2: Avoid saving mask on shutdown
  genirq: Reuse irq_is_nmi()
  genirq/cpuhotplug: Retry with cpu_online_mask when migration fails
  genirq/cpuhotplug: Skip suspended interrupts when restoring affinity
  arm64: dts: st: Add interrupt parent to pinctrl on stm32mp251
  arm64: dts: st: Add exti1 and exti2 nodes on stm32mp251
  ARM: dts: stm32: List exti parent interrupts on stm32mp131
  ARM: dts: stm32: List exti parent interrupts on stm32mp151
  arm64: Kconfig.platforms: Enable STM32_EXTI for ARCH_STM32
  irqchip/stm32-exti: Mark events reserved with RIF configuration check
  irqchip/stm32-exti: Skip secure events
  irqchip/stm32-exti: Convert driver to standard PM
  ...

9 files changed, 311 insertions, 53 deletions

diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
index 2531f3496ab6..529adb1f5859 100644
--- a/kernel/irq/Kconfig
+++ b/kernel/irq/Kconfig
@@ -108,6 +108,10 @@ config GENERIC_IRQ_MATRIX_ALLOCATOR
 config GENERIC_IRQ_RESERVATION_MODE
 	bool
 
+# Snapshot for interrupt statistics
+config GENERIC_IRQ_STAT_SNAPSHOT
+	bool
+
 # Support forced irq threading
 config IRQ_FORCED_THREADING
        bool
diff --git a/kernel/irq/cpuhotplug.c b/kernel/irq/cpuhotplug.c
index 1ed2b1739363..75cadbc3c232 100644
--- a/kernel/irq/cpuhotplug.c
+++ b/kernel/irq/cpuhotplug.c
@@ -130,6 +130,22 @@ static bool migrate_one_irq(struct irq_desc *desc)
 	 * CPU.
 	 */
 	err = irq_do_set_affinity(d, affinity, false);
+
+	/*
+	 * If there are online CPUs in the affinity mask, but they have no
+	 * vectors left to make the migration work, try to break the
+	 * affinity by migrating to any online CPU.
+	 */
+	if (err == -ENOSPC && !irqd_affinity_is_managed(d) && affinity != cpu_online_mask) {
+		pr_debug("IRQ%u: set affinity failed for %*pbl, re-try with online CPUs\n",
+			 d->irq, cpumask_pr_args(affinity));
+
+		affinity = cpu_online_mask;
+		brokeaff = true;
+
+		err = irq_do_set_affinity(d, affinity, false);
+	}
+
 	if (err) {
 		pr_warn_ratelimited("IRQ%u: set affinity failed(%d).\n",
 				    d->irq, err);
@@ -195,10 +211,15 @@ static void irq_restore_affinity_of_irq(struct irq_desc *desc, unsigned int cpu)
 	    !irq_data_get_irq_chip(data) || !cpumask_test_cpu(cpu, affinity))
 		return;
 
-	if (irqd_is_managed_and_shutdown(data)) {
-		irq_startup(desc, IRQ_RESEND, IRQ_START_COND);
+	/*
+	 * Don't restore suspended interrupts here when a system comes back
+	 * from S3. They are reenabled via resume_device_irqs().
+	 */
+	if (desc->istate & IRQS_SUSPENDED)
 		return;
-	}
+
+	if (irqd_is_managed_and_shutdown(data))
+		irq_startup(desc, IRQ_RESEND, IRQ_START_COND);
 
 	/*
 	 * If the interrupt can only be directed to a single target
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index bcc7f21db9ee..ed28059e9849 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -98,6 +98,8 @@ extern void mask_irq(struct irq_desc *desc);
 extern void unmask_irq(struct irq_desc *desc);
 extern void unmask_threaded_irq(struct irq_desc *desc);
 
+extern unsigned int kstat_irqs_desc(struct irq_desc *desc, const struct cpumask *cpumask);
+
 #ifdef CONFIG_SPARSE_IRQ
 static inline void irq_mark_irq(unsigned int irq) { }
 #else
@@ -258,7 +260,7 @@ static inline void irq_state_set_masked(struct irq_desc *desc)
 
 static inline void __kstat_incr_irqs_this_cpu(struct irq_desc *desc)
 {
-	__this_cpu_inc(*desc->kstat_irqs);
+	__this_cpu_inc(desc->kstat_irqs->cnt);
 	__this_cpu_inc(kstat.irqs_sum);
 }
 
@@ -278,6 +280,11 @@ static inline int irq_desc_is_chained(struct irq_desc *desc)
 	return (desc->action && desc->action == &chained_action);
 }
 
+static inline bool irq_is_nmi(struct irq_desc *desc)
+{
+	return desc->istate & IRQS_NMI;
+}
+
 #ifdef CONFIG_PM_SLEEP
 bool irq_pm_check_wakeup(struct irq_desc *desc);
 void irq_pm_install_action(struct irq_desc *desc, struct irqaction *action);
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 4c6b32318ce3..88ac3652fcf2 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -134,7 +134,7 @@ static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node,
 	desc->name = NULL;
 	desc->owner = owner;
 	for_each_possible_cpu(cpu)
-		*per_cpu_ptr(desc->kstat_irqs, cpu) = 0;
+		*per_cpu_ptr(desc->kstat_irqs, cpu) = (struct irqstat) { };
 	desc_smp_init(desc, node, affinity);
 }
 
@@ -186,7 +186,7 @@ static int init_desc(struct irq_desc *desc, int irq, int node,
 		     const struct cpumask *affinity,
 		     struct module *owner)
 {
-	desc->kstat_irqs = alloc_percpu(unsigned int);
+	desc->kstat_irqs = alloc_percpu(struct irqstat);
 	if (!desc->kstat_irqs)
 		return -ENOMEM;
 
@@ -911,10 +911,7 @@ int irq_set_percpu_devid_partition(unsigned int irq,
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 
-	if (!desc)
-		return -EINVAL;
-
-	if (desc->percpu_enabled)
+	if (!desc || desc->percpu_enabled)
 		return -EINVAL;
 
 	desc->percpu_enabled = kzalloc(sizeof(*desc->percpu_enabled), GFP_KERNEL);
@@ -922,10 +919,7 @@ int irq_set_percpu_devid_partition(unsigned int irq,
 	if (!desc->percpu_enabled)
 		return -ENOMEM;
 
-	if (affinity)
-		desc->percpu_affinity = affinity;
-	else
-		desc->percpu_affinity = cpu_possible_mask;
+	desc->percpu_affinity = affinity ? : cpu_possible_mask;
 
 	irq_set_percpu_devid_flags(irq);
 	return 0;
@@ -968,33 +962,58 @@ unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 
-	return desc && desc->kstat_irqs ?
-			*per_cpu_ptr(desc->kstat_irqs, cpu) : 0;
+	return desc && desc->kstat_irqs ? per_cpu(desc->kstat_irqs->cnt, cpu) : 0;
 }
 
-static bool irq_is_nmi(struct irq_desc *desc)
+unsigned int kstat_irqs_desc(struct irq_desc *desc, const struct cpumask *cpumask)
 {
-	return desc->istate & IRQS_NMI;
-}
-
-static unsigned int kstat_irqs(unsigned int irq)
-{
-	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned int sum = 0;
 	int cpu;
 
-	if (!desc || !desc->kstat_irqs)
-		return 0;
 	if (!irq_settings_is_per_cpu_devid(desc) &&
 	    !irq_settings_is_per_cpu(desc) &&
 	    !irq_is_nmi(desc))
 		return data_race(desc->tot_count);
 
-	for_each_possible_cpu(cpu)
-		sum += data_race(*per_cpu_ptr(desc->kstat_irqs, cpu));
+	for_each_cpu(cpu, cpumask)
+		sum += data_race(per_cpu(desc->kstat_irqs->cnt, cpu));
 	return sum;
 }
 
+static unsigned int kstat_irqs(unsigned int irq)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+
+	if (!desc || !desc->kstat_irqs)
+		return 0;
+	return kstat_irqs_desc(desc, cpu_possible_mask);
+}
+
+#ifdef CONFIG_GENERIC_IRQ_STAT_SNAPSHOT
+
+void kstat_snapshot_irqs(void)
+{
+	struct irq_desc *desc;
+	unsigned int irq;
+
+	for_each_irq_desc(irq, desc) {
+		if (!desc->kstat_irqs)
+			continue;
+		this_cpu_write(desc->kstat_irqs->ref, this_cpu_read(desc->kstat_irqs->cnt));
+	}
+}
+
+unsigned int kstat_get_irq_since_snapshot(unsigned int irq)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+
+	if (!desc || !desc->kstat_irqs)
+		return 0;
+	return this_cpu_read(desc->kstat_irqs->cnt) - this_cpu_read(desc->kstat_irqs->ref);
+}
+
+#endif
+
 /**
  * kstat_irqs_usr - Get the statistics for an interrupt from thread context
  * @irq:	The interrupt number
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 3dd1c871e091..aadc8891cc16 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -909,10 +909,11 @@ EXPORT_SYMBOL_GPL(irq_create_of_mapping);
  */
 void irq_dispose_mapping(unsigned int virq)
 {
-	struct irq_data *irq_data = irq_get_irq_data(virq);
+	struct irq_data *irq_data;
 	struct irq_domain *domain;
 
-	if (!virq || !irq_data)
+	irq_data = virq ? irq_get_irq_data(virq) : NULL;
+	if (!irq_data)
 		return;
 
 	domain = irq_data->domain;
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index bf9ae8a8686f..71b0fc2d0aea 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -564,7 +564,7 @@ irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify)
 	/* The release function is promised process context */
 	might_sleep();
 
-	if (!desc || desc->istate & IRQS_NMI)
+	if (!desc || irq_is_nmi(desc))
 		return -EINVAL;
 
 	/* Complete initialisation of *notify */
@@ -800,10 +800,14 @@ void __enable_irq(struct irq_desc *desc)
 		irq_settings_set_noprobe(desc);
 		/*
 		 * Call irq_startup() not irq_enable() here because the
-		 * interrupt might be marked NOAUTOEN. So irq_startup()
-		 * needs to be invoked when it gets enabled the first
-		 * time. If it was already started up, then irq_startup()
-		 * will invoke irq_enable() under the hood.
+		 * interrupt might be marked NOAUTOEN so irq_startup()
+		 * needs to be invoked when it gets enabled the first time.
+		 * This is also required when __enable_irq() is invoked for
+		 * a managed and shutdown interrupt from the S3 resume
+		 * path.
+		 *
+		 * If it was already started up, then irq_startup() will
+		 * invoke irq_enable() under the hood.
 		 */
 		irq_startup(desc, IRQ_RESEND, IRQ_START_FORCE);
 		break;
@@ -898,7 +902,7 @@ int irq_set_irq_wake(unsigned int irq, unsigned int on)
 		return -EINVAL;
 
 	/* Don't use NMIs as wake up interrupts please */
-	if (desc->istate & IRQS_NMI) {
+	if (irq_is_nmi(desc)) {
 		ret = -EINVAL;
 		goto out_unlock;
 	}
@@ -1624,7 +1628,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 		 */
 		unsigned int oldtype;
 
-		if (desc->istate & IRQS_NMI) {
+		if (irq_is_nmi(desc)) {
 			pr_err("Invalid attempt to share NMI for %s (irq %d) on irqchip %s.\n",
 				new->name, irq, desc->irq_data.chip->name);
 			ret = -EINVAL;
@@ -2082,7 +2086,7 @@ const void *free_nmi(unsigned int irq, void *dev_id)
 	unsigned long flags;
 	const void *devname;
 
-	if (!desc || WARN_ON(!(desc->istate & IRQS_NMI)))
+	if (!desc || WARN_ON(!irq_is_nmi(desc)))
 		return NULL;
 
 	if (WARN_ON(irq_settings_is_per_cpu_devid(desc)))
@@ -2548,7 +2552,7 @@ void free_percpu_nmi(unsigned int irq, void __percpu *dev_id)
 	if (!desc || !irq_settings_is_per_cpu_devid(desc))
 		return;
 
-	if (WARN_ON(!(desc->istate & IRQS_NMI)))
+	if (WARN_ON(!irq_is_nmi(desc)))
 		return;
 
 	kfree(__free_percpu_irq(irq, dev_id));
@@ -2684,7 +2688,7 @@ int request_percpu_nmi(unsigned int irq, irq_handler_t handler,
 		return -EINVAL;
 
 	/* The line cannot already be NMI */
-	if (desc->istate & IRQS_NMI)
+	if (irq_is_nmi(desc))
 		return -EINVAL;
 
 	action = kzalloc(sizeof(struct irqaction), GFP_KERNEL);
@@ -2745,7 +2749,7 @@ int prepare_percpu_nmi(unsigned int irq)
 	if (!desc)
 		return -EINVAL;
 
-	if (WARN(!(desc->istate & IRQS_NMI),
+	if (WARN(!irq_is_nmi(desc),
 		 KERN_ERR "prepare_percpu_nmi called for a non-NMI interrupt: irq %u\n",
 		 irq)) {
 		ret = -EINVAL;
@@ -2787,7 +2791,7 @@ void teardown_percpu_nmi(unsigned int irq)
 	if (!desc)
 		return;
 
-	if (WARN_ON(!(desc->istate & IRQS_NMI)))
+	if (WARN_ON(!irq_is_nmi(desc)))
 		goto out;
 
 	irq_nmi_teardown(desc);
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 623b8136e9af..5c320c3f10a7 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -488,18 +488,15 @@ int show_interrupts(struct seq_file *p, void *v)
 	if (!desc || irq_settings_is_hidden(desc))
 		goto outsparse;
 
-	if (desc->kstat_irqs) {
-		for_each_online_cpu(j)
-			any_count |= data_race(*per_cpu_ptr(desc->kstat_irqs, j));
-	}
+	if (desc->kstat_irqs)
+		any_count = kstat_irqs_desc(desc, cpu_online_mask);
 
 	if ((!desc->action || irq_desc_is_chained(desc)) && !any_count)
 		goto outsparse;
 
 	seq_printf(p, "%*d: ", prec, i);
 	for_each_online_cpu(j)
-		seq_printf(p, "%10u ", desc->kstat_irqs ?
-					*per_cpu_ptr(desc->kstat_irqs, j) : 0);
+		seq_printf(p, "%10u ", desc->kstat_irqs ? per_cpu(desc->kstat_irqs->cnt, j) : 0);
 
 	raw_spin_lock_irqsave(&desc->lock, flags);
 	if (desc->irq_data.chip) {
diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c
index 5f2c66860ac6..b07a2d732ffb 100644
--- a/kernel/irq/resend.c
+++ b/kernel/irq/resend.c
@@ -190,7 +190,7 @@ int irq_inject_interrupt(unsigned int irq)
 	 *  - not NMI type
 	 *  - activated
 	 */
-	if ((desc->istate & IRQS_NMI) || !irqd_is_activated(&desc->irq_data))
+	if (irq_is_nmi(desc) || !irqd_is_activated(&desc->irq_data))
 		err = -EINVAL;
 	else
 		err = check_irq_resend(desc, true);
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index d7b2125503af..d12ff74889ed 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -12,20 +12,25 @@
 
 #define pr_fmt(fmt) "watchdog: " fmt
 
-#include <linux/mm.h>
 #include <linux/cpu.h>
-#include <linux/nmi.h>
 #include <linux/init.h>
+#include <linux/irq.h>
+#include <linux/irqdesc.h>
+#include <linux/kernel_stat.h>
+#include <linux/kvm_para.h>
+#include <linux/math64.h>
+#include <linux/mm.h>
 #include <linux/module.h>
+#include <linux/nmi.h>
+#include <linux/stop_machine.h>
 #include <linux/sysctl.h>
 #include <linux/tick.h>
+
 #include <linux/sched/clock.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/isolation.h>
-#include <linux/stop_machine.h>
 
 #include <asm/irq_regs.h>
-#include <linux/kvm_para.h>
 
 static DEFINE_MUTEX(watchdog_mutex);
 
@@ -35,6 +40,8 @@ static DEFINE_MUTEX(watchdog_mutex);
 # define WATCHDOG_HARDLOCKUP_DEFAULT	0
 #endif
 
+#define NUM_SAMPLE_PERIODS	5
+
 unsigned long __read_mostly watchdog_enabled;
 int __read_mostly watchdog_user_enabled = 1;
 static int __read_mostly watchdog_hardlockup_user_enabled = WATCHDOG_HARDLOCKUP_DEFAULT;
@@ -333,6 +340,188 @@ __setup("watchdog_thresh=", watchdog_thresh_setup);
 
 static void __lockup_detector_cleanup(void);
 
+#ifdef CONFIG_SOFTLOCKUP_DETECTOR_INTR_STORM
+enum stats_per_group {
+	STATS_SYSTEM,
+	STATS_SOFTIRQ,
+	STATS_HARDIRQ,
+	STATS_IDLE,
+	NUM_STATS_PER_GROUP,
+};
+
+static const enum cpu_usage_stat tracked_stats[NUM_STATS_PER_GROUP] = {
+	CPUTIME_SYSTEM,
+	CPUTIME_SOFTIRQ,
+	CPUTIME_IRQ,
+	CPUTIME_IDLE,
+};
+
+static DEFINE_PER_CPU(u16, cpustat_old[NUM_STATS_PER_GROUP]);
+static DEFINE_PER_CPU(u8, cpustat_util[NUM_SAMPLE_PERIODS][NUM_STATS_PER_GROUP]);
+static DEFINE_PER_CPU(u8, cpustat_tail);
+
+/*
+ * We don't need nanosecond resolution. A granularity of 16ms is
+ * sufficient for our precision, allowing us to use u16 to store
+ * cpustats, which will roll over roughly every ~1000 seconds.
+ * 2^24 ~= 16 * 10^6
+ */
+static u16 get_16bit_precision(u64 data_ns)
+{
+	return data_ns >> 24LL; /* 2^24ns ~= 16.8ms */
+}
+
+static void update_cpustat(void)
+{
+	int i;
+	u8 util;
+	u16 old_stat, new_stat;
+	struct kernel_cpustat kcpustat;
+	u64 *cpustat = kcpustat.cpustat;
+	u8 tail = __this_cpu_read(cpustat_tail);
+	u16 sample_period_16 = get_16bit_precision(sample_period);
+
+	kcpustat_cpu_fetch(&kcpustat, smp_processor_id());
+
+	for (i = 0; i < NUM_STATS_PER_GROUP; i++) {
+		old_stat = __this_cpu_read(cpustat_old[i]);
+		new_stat = get_16bit_precision(cpustat[tracked_stats[i]]);
+		util = DIV_ROUND_UP(100 * (new_stat - old_stat), sample_period_16);
+		__this_cpu_write(cpustat_util[tail][i], util);
+		__this_cpu_write(cpustat_old[i], new_stat);
+	}
+
+	__this_cpu_write(cpustat_tail, (tail + 1) % NUM_SAMPLE_PERIODS);
+}
+
+static void print_cpustat(void)
+{
+	int i, group;
+	u8 tail = __this_cpu_read(cpustat_tail);
+	u64 sample_period_second = sample_period;
+
+	do_div(sample_period_second, NSEC_PER_SEC);
+
+	/*
+	 * Outputting the "watchdog" prefix on every line is redundant and not
+	 * concise, and the original alarm information is sufficient for
+	 * positioning in logs, hence here printk() is used instead of pr_crit().
+	 */
+	printk(KERN_CRIT "CPU#%d Utilization every %llus during lockup:\n",
+	       smp_processor_id(), sample_period_second);
+
+	for (i = 0; i < NUM_SAMPLE_PERIODS; i++) {
+		group = (tail + i) % NUM_SAMPLE_PERIODS;
+		printk(KERN_CRIT "\t#%d: %3u%% system,\t%3u%% softirq,\t"
+			"%3u%% hardirq,\t%3u%% idle\n", i + 1,
+			__this_cpu_read(cpustat_util[group][STATS_SYSTEM]),
+			__this_cpu_read(cpustat_util[group][STATS_SOFTIRQ]),
+			__this_cpu_read(cpustat_util[group][STATS_HARDIRQ]),
+			__this_cpu_read(cpustat_util[group][STATS_IDLE]));
+	}
+}
+
+#define HARDIRQ_PERCENT_THRESH          50
+#define NUM_HARDIRQ_REPORT              5
+struct irq_counts {
+	int irq;
+	u32 counts;
+};
+
+static DEFINE_PER_CPU(bool, snapshot_taken);
+
+/* Tabulate the most frequent interrupts. */
+static void tabulate_irq_count(struct irq_counts *irq_counts, int irq, u32 counts, int rank)
+{
+	int i;
+	struct irq_counts new_count = {irq, counts};
+
+	for (i = 0; i < rank; i++) {
+		if (counts > irq_counts[i].counts)
+			swap(new_count, irq_counts[i]);
+	}
+}
+
+/*
+ * If the hardirq time exceeds HARDIRQ_PERCENT_THRESH% of the sample_period,
+ * then the cause of softlockup might be interrupt storm. In this case, it
+ * would be useful to start interrupt counting.
+ */
+static bool need_counting_irqs(void)
+{
+	u8 util;
+	int tail = __this_cpu_read(cpustat_tail);
+
+	tail = (tail + NUM_HARDIRQ_REPORT - 1) % NUM_HARDIRQ_REPORT;
+	util = __this_cpu_read(cpustat_util[tail][STATS_HARDIRQ]);
+	return util > HARDIRQ_PERCENT_THRESH;
+}
+
+static void start_counting_irqs(void)
+{
+	if (!__this_cpu_read(snapshot_taken)) {
+		kstat_snapshot_irqs();
+		__this_cpu_write(snapshot_taken, true);
+	}
+}
+
+static void stop_counting_irqs(void)
+{
+	__this_cpu_write(snapshot_taken, false);
+}
+
+static void print_irq_counts(void)
+{
+	unsigned int i, count;
+	struct irq_counts irq_counts_sorted[NUM_HARDIRQ_REPORT] = {
+		{-1, 0}, {-1, 0}, {-1, 0}, {-1, 0}, {-1, 0}
+	};
+
+	if (__this_cpu_read(snapshot_taken)) {
+		for_each_active_irq(i) {
+			count = kstat_get_irq_since_snapshot(i);
+			tabulate_irq_count(irq_counts_sorted, i, count, NUM_HARDIRQ_REPORT);
+		}
+
+		/*
+		 * Outputting the "watchdog" prefix on every line is redundant and not
+		 * concise, and the original alarm information is sufficient for
+		 * positioning in logs, hence here printk() is used instead of pr_crit().
+		 */
+		printk(KERN_CRIT "CPU#%d Detect HardIRQ Time exceeds %d%%. Most frequent HardIRQs:\n",
+		       smp_processor_id(), HARDIRQ_PERCENT_THRESH);
+
+		for (i = 0; i < NUM_HARDIRQ_REPORT; i++) {
+			if (irq_counts_sorted[i].irq == -1)
+				break;
+
+			printk(KERN_CRIT "\t#%u: %-10u\tirq#%d\n",
+			       i + 1, irq_counts_sorted[i].counts,
+			       irq_counts_sorted[i].irq);
+		}
+
+		/*
+		 * If the hardirq time is less than HARDIRQ_PERCENT_THRESH% in the last
+		 * sample_period, then we suspect the interrupt storm might be subsiding.
+		 */
+		if (!need_counting_irqs())
+			stop_counting_irqs();
+	}
+}
+
+static void report_cpu_status(void)
+{
+	print_cpustat();
+	print_irq_counts();
+}
+#else
+static inline void update_cpustat(void) { }
+static inline void report_cpu_status(void) { }
+static inline bool need_counting_irqs(void) { return false; }
+static inline void start_counting_irqs(void) { }
+static inline void stop_counting_irqs(void) { }
+#endif
+
 /*
  * Hard-lockup warnings should be triggered after just a few seconds. Soft-
  * lockups can have false positives under extreme conditions. So we generally
@@ -364,7 +553,7 @@ static void set_sample_period(void)
 	 * and hard thresholds) to increment before the
 	 * hardlockup detector generates a warning
 	 */
-	sample_period = get_softlockup_thresh() * ((u64)NSEC_PER_SEC / 5);
+	sample_period = get_softlockup_thresh() * ((u64)NSEC_PER_SEC / NUM_SAMPLE_PERIODS);
 	watchdog_update_hrtimer_threshold(sample_period);
 }
 
@@ -434,6 +623,18 @@ static int is_softlockup(unsigned long touch_ts,
 			 unsigned long now)
 {
 	if ((watchdog_enabled & WATCHDOG_SOFTOCKUP_ENABLED) && watchdog_thresh) {
+		/*
+		 * If period_ts has not been updated during a sample_period, then
+		 * in the subsequent few sample_periods, period_ts might also not
+		 * be updated, which could indicate a potential softlockup. In
+		 * this case, if we suspect the cause of the potential softlockup
+		 * might be interrupt storm, then we need to count the interrupts
+		 * to find which interrupt is storming.
+		 */
+		if (time_after_eq(now, period_ts + get_softlockup_thresh() / NUM_SAMPLE_PERIODS) &&
+		    need_counting_irqs())
+			start_counting_irqs();
+
 		/* Warn about unreasonable delays. */
 		if (time_after(now, period_ts + get_softlockup_thresh()))
 			return now - touch_ts;
@@ -456,6 +657,7 @@ static DEFINE_PER_CPU(struct cpu_stop_work, softlockup_stop_work);
 static int softlockup_fn(void *data)
 {
 	update_touch_ts();
+	stop_counting_irqs();
 	complete(this_cpu_ptr(&softlockup_completion));
 
 	return 0;
@@ -504,6 +706,8 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 	 */
 	period_ts = READ_ONCE(*this_cpu_ptr(&watchdog_report_ts));
 
+	update_cpustat();
+
 	/* Reset the interval when touched by known problematic code. */
 	if (period_ts == SOFTLOCKUP_DELAY_REPORT) {
 		if (unlikely(__this_cpu_read(softlockup_touch_sync))) {
@@ -539,6 +743,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 		pr_emerg("BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n",
 			smp_processor_id(), duration,
 			current->comm, task_pid_nr(current));
+		report_cpu_status();
 		print_modules();
 		print_irqtrace_events(current);
 		if (regs)