@@ -756,7 +756,7 @@ void __init arch_init_irq(void)
NULL))
pr_err("Failed to register fpu interrupt\n");
desc_fpu = irq_to_desc(irq_fpu);
- fpu_kstat_irq = this_cpu_ptr(desc_fpu->kstat_irqs);
+ fpu_kstat_irq = this_cpu_ptr(&desc_fpu->kstat_irqs->cnt);
}
if (dec_interrupt[DEC_IRQ_CASCADE] >= 0) {
if (request_irq(dec_interrupt[DEC_IRQ_CASCADE], no_action,
@@ -344,7 +344,7 @@ static int smp_boot_one_cpu(int cpuid, struct task_struct *idle)
struct irq_desc *desc = irq_to_desc(i);
if (desc && desc->kstat_irqs)
- *per_cpu_ptr(desc->kstat_irqs, cpuid) = 0;
+ *per_cpu_ptr(desc->kstat_irqs, cpuid) = (struct irqstat) { };
}
#endif
@@ -837,7 +837,7 @@ static inline void this_cpu_inc_rm(unsigned int __percpu *addr)
*/
static void kvmppc_rm_handle_irq_desc(struct irq_desc *desc)
{
- this_cpu_inc_rm(desc->kstat_irqs);
+ this_cpu_inc_rm(&desc->kstat_irqs->cnt);
__this_cpu_inc(kstat.irqs_sum);
}
@@ -17,6 +17,11 @@ struct irq_desc;
struct irq_domain;
struct pt_regs;
+struct irqstat {
+ unsigned int cnt;
+ unsigned int ref;
+};
+
/**
* struct irq_desc - interrupt descriptor
* @irq_common_data: per irq and chip data passed down to chip functions
@@ -55,7 +60,7 @@ struct pt_regs;
struct irq_desc {
struct irq_common_data irq_common_data;
struct irq_data irq_data;
- unsigned int __percpu *kstat_irqs;
+ struct irqstat __percpu *kstat_irqs;
irq_flow_handler_t handle_irq;
struct irqaction *action; /* IRQ action list */
unsigned int status_use_accessors;
@@ -119,7 +124,7 @@ extern struct irq_desc irq_desc[NR_IRQS];
static inline unsigned int irq_desc_kstat_cpu(struct irq_desc *desc,
unsigned int cpu)
{
- return desc->kstat_irqs ? *per_cpu_ptr(desc->kstat_irqs, cpu) : 0;
+ return desc->kstat_irqs ? per_cpu(desc->kstat_irqs->cnt, cpu) : 0;
}
static inline struct irq_desc *irq_data_to_desc(struct irq_data *data)
@@ -79,6 +79,10 @@ static inline unsigned int kstat_cpu_softirqs_sum(int cpu)
return sum;
}
+extern void kstat_snapshot_irqs(void);
+
+extern unsigned int kstat_get_irq_since_snapshot(unsigned int irq);
+
/*
* Number of interrupts per specific IRQ source, since bootup
*/
@@ -258,7 +258,7 @@ 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);
}
@@ -122,7 +122,7 @@ 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);
}
@@ -418,8 +418,8 @@ static struct irq_desc *alloc_desc(int irq, int node, unsigned int flags,
desc = kzalloc_node(sizeof(*desc), GFP_KERNEL, node);
if (!desc)
return NULL;
- /* allocate based on nr_cpu_ids */
- desc->kstat_irqs = alloc_percpu(unsigned int);
+
+ desc->kstat_irqs = alloc_percpu(struct irqstat);
if (!desc->kstat_irqs)
goto err_desc;
@@ -593,7 +593,7 @@ int __init early_irq_init(void)
count = ARRAY_SIZE(irq_desc);
for (i = 0; i < count; i++) {
- desc[i].kstat_irqs = alloc_percpu(unsigned int);
+ desc[i].kstat_irqs = alloc_percpu(struct irqstat);
alloc_masks(&desc[i], node);
raw_spin_lock_init(&desc[i].lock);
lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
@@ -952,8 +952,7 @@ 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)
@@ -975,10 +974,31 @@ static unsigned int kstat_irqs(unsigned int irq)
return data_race(desc->tot_count);
for_each_possible_cpu(cpu)
- sum += data_race(*per_cpu_ptr(desc->kstat_irqs, cpu));
+ sum += data_race(per_cpu(desc->kstat_irqs->cnt, cpu));
return sum;
}
+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);
+}
+
/**
* kstat_irqs_usr - Get the statistics for an interrupt from thread context
* @irq: The interrupt number
@@ -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 = data_race(desc->tot_count);
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) {
@@ -12,22 +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);
@@ -417,13 +420,104 @@ static void print_cpustat(void)
}
}
+#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);
+ }
+
+ /*
+ * We do not want the "watchdog: " prefix on every line,
+ * hence we use "printk" 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
/*
@@ -527,6 +621,18 @@ 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() / 5) &&
+ need_counting_irqs())
+ start_counting_irqs();
+
/* Warn about unreasonable delays. */
if (time_after(now, period_ts + get_softlockup_thresh()))
return now - touch_ts;
@@ -549,6 +655,7 @@ 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;
@@ -37,7 +37,7 @@ def show_irq_desc(prec, irq):
any_count = 0
if desc['kstat_irqs']:
for cpu in cpus.each_online_cpu():
- any_count += cpus.per_cpu(desc['kstat_irqs'], cpu)
+ any_count += cpus.per_cpu(desc['kstat_irqs'], cpu)['cnt']
if (desc['action'] == 0 or irq_desc_is_chained(desc)) and any_count == 0:
return text;
@@ -45,7 +45,7 @@ def show_irq_desc(prec, irq):
text += "%*d: " % (prec, irq)
for cpu in cpus.each_online_cpu():
if desc['kstat_irqs']:
- count = cpus.per_cpu(desc['kstat_irqs'], cpu)
+ count = cpus.per_cpu(desc['kstat_irqs'], cpu)['cnt']
else:
count = 0
text += "%10u" % (count)
@@ -177,7 +177,7 @@ def arm_common_show_interrupts(prec):
if desc == 0:
continue
for cpu in cpus.each_online_cpu():
- text += "%10u" % (cpus.per_cpu(desc['kstat_irqs'], cpu))
+ text += "%10u" % (cpus.per_cpu(desc['kstat_irqs'], cpu)['cnt'])
text += " %s" % (ipi_types[ipi].string())
text += "\n"
return text
When the watchdog determines that the current soft lockup is due to an interrupt storm based on CPU utilization, reporting the most frequent interrupts could be good enough for further troubleshooting. Below is an example of interrupt storm. The call tree does not provide useful information, but we can analyze which interrupt caused the soft lockup by comparing the counts of interrupts. [ 2987.488075] watchdog: BUG: soft lockup - CPU#9 stuck for 23s! [kworker/9:1:214] [ 2987.488607] CPU#9 Utilization every 4s during lockup: [ 2987.488941] #1: 0% system, 0% softirq, 100% hardirq, 0% idle [ 2987.489357] #2: 0% system, 0% softirq, 100% hardirq, 0% idle [ 2987.489771] #3: 0% system, 0% softirq, 100% hardirq, 0% idle [ 2987.490186] #4: 0% system, 0% softirq, 100% hardirq, 0% idle [ 2987.490601] #5: 0% system, 0% softirq, 100% hardirq, 0% idle [ 2987.491034] CPU#9 Detect HardIRQ Time exceeds 50%. Most frequent HardIRQs: [ 2987.491493] #1: 330985 irq#7 [ 2987.491743] #2: 5000 irq#10 [ 2987.492039] #3: 9 irq#91 [ 2987.492318] #4: 3 irq#118 ... [ 2987.492728] Call trace: [ 2987.492729] __do_softirq+0xa8/0x364 Signed-off-by: Bitao Hu <yaoma@linux.alibaba.com> --- arch/mips/dec/setup.c | 2 +- arch/parisc/kernel/smp.c | 2 +- arch/powerpc/kvm/book3s_hv_rm_xics.c | 2 +- include/linux/irqdesc.h | 9 ++- include/linux/kernel_stat.h | 4 + kernel/irq/internals.h | 2 +- kernel/irq/irqdesc.c | 34 ++++++-- kernel/irq/proc.c | 9 +-- kernel/watchdog.c | 115 ++++++++++++++++++++++++++- scripts/gdb/linux/interrupts.py | 6 +- 10 files changed, 159 insertions(+), 26 deletions(-)