rcu/cpu_stall_cputime: fix the hardirq count for x86 architecture

When counting the number of hardirqs in the x86 architecture,
it is essential to add arch_irq_stat_cpu to ensure accuracy.

For example, a CPU loop within the rcu_read_lock function.

Before:
[   70.910184] rcu: INFO: rcu_preempt self-detected stall on CPU
[   70.910436] rcu:     3-....: (4999 ticks this GP) idle=***
[   70.910711] rcu:              hardirqs   softirqs   csw/system
[   70.910870] rcu:      number:        0        657            0
[   70.911024] rcu:     cputime:        0          0         2498   ==> 2498(ms)
[   70.911278] rcu:     (t=5001 jiffies g=3677 q=29 ncpus=8)

After:
[   68.046132] rcu: INFO: rcu_preempt self-detected stall on CPU
[   68.046354] rcu:     2-....: (4999 ticks this GP) idle=***
[   68.046628] rcu:              hardirqs   softirqs   csw/system
[   68.046793] rcu:      number:     2498        663            0
[   68.046951] rcu:     cputime:        0          0         2496   ==> 2496(ms)
[   68.047244] rcu:     (t=5000 jiffies g=3825 q=4 ncpus=8)

Fixes: be42f00 ("rcu: Add RCU stall diagnosis information")
Reported-by: kernel test robot <[email protected]>
Closes: https://lore.kernel.org/oe-kbuild-all/[email protected]/
Signed-off-by: Yongliang Gao <[email protected]>
Reviewed-by: Neeraj Upadhyay <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Boqun Feng <[email protected]>
Signed-off-by: Joel Fernandes <[email protected]>

Author: Yongliang Gao

kernel/rcu/tree.c

@@ -801,6 +801,10 @@ static int rcu_watching_snap_save(struct rcu_data *rdp)
 	return 0;
 }
 
+#ifndef arch_irq_stat_cpu
+#define arch_irq_stat_cpu(cpu) 0
+#endif
+
 /*
  * Returns positive if the specified CPU has passed through a quiescent state
  * by virtue of being in or having passed through an dynticks idle state since
@@ -936,9 +940,9 @@ static int rcu_watching_snap_recheck(struct rcu_data *rdp)
 			rsrp->cputime_irq     = kcpustat_field(kcsp, CPUTIME_IRQ, cpu);
 			rsrp->cputime_softirq = kcpustat_field(kcsp, CPUTIME_SOFTIRQ, cpu);
 			rsrp->cputime_system  = kcpustat_field(kcsp, CPUTIME_SYSTEM, cpu);
-			rsrp->nr_hardirqs = kstat_cpu_irqs_sum(rdp->cpu);
-			rsrp->nr_softirqs = kstat_cpu_softirqs_sum(rdp->cpu);
-			rsrp->nr_csw = nr_context_switches_cpu(rdp->cpu);
+			rsrp->nr_hardirqs = kstat_cpu_irqs_sum(cpu) + arch_irq_stat_cpu(cpu);
+			rsrp->nr_softirqs = kstat_cpu_softirqs_sum(cpu);
+			rsrp->nr_csw = nr_context_switches_cpu(cpu);
 			rsrp->jiffies = jiffies;
 			rsrp->gp_seq = rdp->gp_seq;
 		}

kernel/rcu/tree.h

@@ -168,7 +168,7 @@ struct rcu_snap_record {
 	u64		cputime_irq;	/* Accumulated cputime of hard irqs */
 	u64		cputime_softirq;/* Accumulated cputime of soft irqs */
 	u64		cputime_system; /* Accumulated cputime of kernel tasks */
-	unsigned long	nr_hardirqs;	/* Accumulated number of hard irqs */
+	u64		nr_hardirqs;	/* Accumulated number of hard irqs */
 	unsigned int	nr_softirqs;	/* Accumulated number of soft irqs */
 	unsigned long long nr_csw;	/* Accumulated number of task switches */
 	unsigned long   jiffies;	/* Track jiffies value */

kernel/rcu/tree_stall.h

@@ -435,8 +435,8 @@ static void print_cpu_stat_info(int cpu)
 	rsr.cputime_system  = kcpustat_field(kcsp, CPUTIME_SYSTEM, cpu);
 
 	pr_err("\t         hardirqs   softirqs   csw/system\n");
-	pr_err("\t number: %8ld %10d %12lld\n",
-		kstat_cpu_irqs_sum(cpu) - rsrp->nr_hardirqs,
+	pr_err("\t number: %8lld %10d %12lld\n",
+		kstat_cpu_irqs_sum(cpu) + arch_irq_stat_cpu(cpu) - rsrp->nr_hardirqs,
 		kstat_cpu_softirqs_sum(cpu) - rsrp->nr_softirqs,
 		nr_context_switches_cpu(cpu) - rsrp->nr_csw);
 	pr_err("\tcputime: %8lld %10lld %12lld   ==> %d(ms)\n",