Blob Blame History Raw
From 5375d121198e13f80731574f697d2d15ad1888ec Mon Sep 17 00:00:00 2001
From: Laurent Dufour <ldufour@linux.ibm.com>
Date: Wed, 13 Jul 2022 17:47:28 +0200
Subject: [PATCH] powerpc/watchdog: introduce a NMI watchdog's factor

References: bsc#1201846 ltc#198761
Patch-mainline: v5.20-rc1
Git-commit: f5e74e836097d1004077390717d4bd95d4a2c27a

Introduce a factor which would apply to the NMI watchdog timeout.

This factor is a percentage added to the watchdog_tresh value. The value is
set under the watchdog_mutex protection and lockup_detector_reconfigure()
is called to recompute wd_panic_timeout_tb.

Once the factor is set, it remains until it is set back to 0, which means
no impact.

Signed-off-by: Laurent Dufour <ldufour@linux.ibm.com>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220713154729.80789-4-ldufour@linux.ibm.com
Acked-by: Michal Suchanek <msuchanek@suse.de>
---
 arch/powerpc/include/asm/nmi.h |  2 ++
 arch/powerpc/kernel/watchdog.c | 21 ++++++++++++++++++++-
 2 files changed, 22 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/include/asm/nmi.h b/arch/powerpc/include/asm/nmi.h
--- a/arch/powerpc/include/asm/nmi.h
+++ b/arch/powerpc/include/asm/nmi.h
@@ -5,8 +5,10 @@
 
 #ifdef CONFIG_PPC_WATCHDOG
 extern void arch_touch_nmi_watchdog(void);
+void watchdog_nmi_set_timeout_pct(u64 pct);
 #else
 static inline void arch_touch_nmi_watchdog(void) {}
+static inline void watchdog_nmi_set_timeout_pct(u64 pct) {}
 #endif
 
 #if defined(CONFIG_NMI_IPI) && defined(CONFIG_STACKTRACE)
diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c
index dd882d00845d..dbcc4a793f0b 100644
--- a/arch/powerpc/kernel/watchdog.c
+++ b/arch/powerpc/kernel/watchdog.c
@@ -91,6 +91,10 @@ static cpumask_t wd_smp_cpus_pending;
 static cpumask_t wd_smp_cpus_stuck;
 static u64 wd_smp_last_reset_tb;
 
+#ifdef CONFIG_PPC_PSERIES
+static u64 wd_timeout_pct;
+#endif
+
 /*
  * Try to take the exclusive watchdog action / NMI IPI / printing lock.
  * wd_smp_lock must be held. If this fails, we should return and wait
@@ -527,7 +531,13 @@ static int stop_watchdog_on_cpu(unsigned int cpu)
 
 static void watchdog_calc_timeouts(void)
 {
-	wd_panic_timeout_tb = watchdog_thresh * ppc_tb_freq;
+	u64 threshold = watchdog_thresh;
+
+#ifdef CONFIG_PPC_PSERIES
+	threshold += (READ_ONCE(wd_timeout_pct) * threshold) / 100;
+#endif
+
+	wd_panic_timeout_tb = threshold * ppc_tb_freq;
 
 	/* Have the SMP detector trigger a bit later */
 	wd_smp_panic_timeout_tb = wd_panic_timeout_tb * 3 / 2;
@@ -570,3 +580,12 @@ int __init watchdog_nmi_probe(void)
 	}
 	return 0;
 }
+
+#ifdef CONFIG_PPC_PSERIES
+void watchdog_nmi_set_timeout_pct(u64 pct)
+{
+	pr_info("Set the NMI watchdog timeout factor to %llu%%\n", pct);
+	WRITE_ONCE(wd_timeout_pct, pct);
+	lockup_detector_reconfigure();
+}
+#endif
-- 
2.35.3