linux-kernel - [PATCH] rcu/cpu_stall_cputime: fix the hardirq count for x86 architecture

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Message-Id: <20250108065716.2888148-1-leonylgao@gmail.com>
Date: Wed,  8 Jan 2025 14:57:16 +0800
From: Yongliang Gao <leonylgao@...il.com>
To: paulmck@...nel.org,
	frederic@...nel.org,
	thunder.leizhen@...wei.com
Cc: frankjpliu@...cent.com,
	rcu@...r.kernel.org,
	linux-kernel@...r.kernel.org,
	Yongliang Gao <leonylgao@...cent.com>
Subject: [PATCH] rcu/cpu_stall_cputime: fix the hardirq count for x86 architecture

From: Yongliang Gao <leonylgao@...cent.com>

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: be42f00b73a0 ("rcu: Add RCU stall diagnosis information")
Signed-off-by: Yongliang Gao <leonylgao@...cent.com>
---
 kernel/rcu/tree.c       | 6 +++---
 kernel/rcu/tree.h       | 2 +-
 kernel/rcu/tree_stall.h | 4 ++--
 3 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index ff98233d4aa5..69205b9fbe4d 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -937,9 +937,9 @@ 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;
 		}
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index a9a811d9d7a3..1bba2225e744 100644
--- a/kernel/rcu/tree.h
+++ b/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 */
diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
index 925fcdad5dea..56b21219442b 100644
--- a/kernel/rcu/tree_stall.h
+++ b/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",
-- 
2.39.3