Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Laurent Dufour <ldufour@linux.ibm.com>
To:     mpe@ellerman.id.au, benh@kernel.crashing.org, paulus@samba.org,
        nathanl@linux.ibm.com, haren@linux.vnet.ibm.com, npiggin@gmail.com
Cc:     linuxppc-dev@lists.ozlabs.org, linux-kernel@vger.kernel.org
Subject: [PATCH v2 4/4] pseries/mobility: Set NMI watchdog factor during LPM
Date:   Tue, 14 Jun 2022 15:54:14 +0200
Message-Id: <20220614135414.37746-5-ldufour@linux.ibm.com>
In-Reply-To: <20220614135414.37746-1-ldufour@linux.ibm.com>
References: <20220614135414.37746-1-ldufour@linux.ibm.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

During a LPM, while the memory transfer is in progress on the arrival side,
some latencies is generated when accessing not yet transferred pages on the
arrival side. Thus, the NMI watchdog may be triggered too frequently, which
increases the risk to hit a NMI interrupt in a bad place in the kernel,
leading to a kernel panic.

Disabling the Hard Lockup Watchdog until the memory transfer could be a too
strong work around, some users would want this timeout to be eventually
triggered if the system is hanging even during LPM.

Introduce a new sysctl variable lpm_nmi_watchdog_factor. It allows to apply
a factor to the NMI watchdog timeout during a LPM. Just before the CPU are
stopped for the switchover sequence, the NMI watchdog timer is set to
 watchdog_tresh + factor%

A value of 0 has no effect. The default value is 200, meaning that the NMI
watchdog is set to 30s during LPM (based on a 10s watchdog_tresh value).
Once the memory transfer is achieved, the factor is reset to 0.

Setting this value to a high number is like disabling the NMI watchdog
during a LPM.

Signed-off-by: Laurent Dufour <ldufour@linux.ibm.com>
---
 Documentation/admin-guide/sysctl/kernel.rst | 12 ++++++
 arch/powerpc/platforms/pseries/mobility.c   | 48 +++++++++++++++++++++
 2 files changed, 60 insertions(+)

diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst
index ddccd1077462..53701ed671de 100644
--- a/Documentation/admin-guide/sysctl/kernel.rst
+++ b/Documentation/admin-guide/sysctl/kernel.rst
@@ -485,6 +485,18 @@ When ``kptr_restrict`` is set to 2, kernel pointers printed using
 %pK will be replaced with 0s regardless of privileges.
 
 
+lpm_nmi_watchdog_factor (PPC only)
+==================================
+
+Factor apply to to the NMI watchdog timeout (only when ``nmi_watchdog`` is
+set to 1). This factor represents the percentage added to
+``watchdog_thresh`` when calculating the NMI watchdog timeout during a
+LPM. The soft lockup timeout is not impacted.
+
+A value of 0 means no change. The default value is 200 meaning the NMI
+watchdog is set to 30s (based on ``watchdog_thresh`` equal to 10).
+
+
 modprobe
 ========
 
diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c
index 179bbd4ae881..4284ceaf9060 100644
--- a/arch/powerpc/platforms/pseries/mobility.c
+++ b/arch/powerpc/platforms/pseries/mobility.c
@@ -48,6 +48,39 @@ struct update_props_workarea {
 #define MIGRATION_SCOPE	(1)
 #define PRRN_SCOPE -2
 
+#ifdef CONFIG_PPC_WATCHDOG
+static unsigned int lpm_nmi_wd_factor = 200;
+
+#ifdef CONFIG_SYSCTL
+static struct ctl_table lpm_nmi_wd_factor_ctl_table[] = {
+	{
+		.procname	= "lpm_nmi_watchdog_factor",
+		.data		= &lpm_nmi_wd_factor,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_douintvec_minmax,
+	},
+	{}
+};
+static struct ctl_table lpm_nmi_wd_factor_sysctl_root[] = {
+	{
+		.procname       = "kernel",
+		.mode           = 0555,
+		.child          = lpm_nmi_wd_factor_ctl_table,
+	},
+	{}
+};
+
+static int __init register_lpm_nmi_wd_factor_sysctl(void)
+{
+	register_sysctl_table(lpm_nmi_wd_factor_sysctl_root);
+
+	return 0;
+}
+device_initcall(register_lpm_nmi_wd_factor_sysctl);
+#endif /* CONFIG_SYSCTL */
+#endif /* CONFIG_PPC_WATCHDOG */
+
 static int mobility_rtas_call(int token, char *buf, s32 scope)
 {
 	int rc;
@@ -702,6 +735,7 @@ static int pseries_suspend(u64 handle)
 static int pseries_migrate_partition(u64 handle)
 {
 	int ret;
+	unsigned int factor = lpm_nmi_wd_factor;
 
 	ret = wait_for_vasi_session_suspending(handle);
 	if (ret)
@@ -709,6 +743,13 @@ static int pseries_migrate_partition(u64 handle)
 
 	vas_migration_handler(VAS_SUSPEND);
 
+#ifdef CONFIG_PPC_WATCHDOG
+	if (factor) {
+		pr_info("Set the NMI watchdog factor to %u%%\n", factor);
+		watchdog_nmi_set_lpm_factor(factor);
+	}
+#endif /* CONFIG_PPC_WATCHDOG */
+
 	ret = pseries_suspend(handle);
 	if (ret == 0) {
 		post_mobility_fixup();
@@ -716,6 +757,13 @@ static int pseries_migrate_partition(u64 handle)
 	} else
 		pseries_cancel_migration(handle, ret);
 
+#ifdef CONFIG_PPC_WATCHDOG
+	if (factor) {
+		pr_info("Restoring NMI watchdog timer\n");
+		watchdog_nmi_set_lpm_factor(0);
+	}
+#endif /* CONFIG_PPC_WATCHDOG */
+
 	vas_migration_handler(VAS_RESUME);
 
 	return ret;
-- 
2.36.1