During an LPM, while the memory transfer is in progress on the arrival
side, some latencies are 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 an 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 an LPM.
Introduce a new sysctl variable nmi_watchdog_factor. It allows to apply a
factor to the NMI watchdog timeout during an LPM. Just before the CPUs are
stopped for the switchover sequence, the NMI watchdog timer is set to
watchdog_thresh + 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_thresh 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 an LPM.
Reviewed-by: Nicholas Piggin <npig...@gmail.com>
Signed-off-by: Laurent Dufour <lduf...@linux.ibm.com>
---
Documentation/admin-guide/sysctl/kernel.rst | 12 ++++++
arch/powerpc/platforms/pseries/mobility.c | 43 +++++++++++++++++++++
2 files changed, 55 insertions(+)
diff --git a/Documentation/admin-guide/sysctl/kernel.rst
b/Documentation/admin-guide/sysctl/kernel.rst
index ddccd1077462..d73faa619c15 100644
--- a/Documentation/admin-guide/sysctl/kernel.rst
+++ b/Documentation/admin-guide/sysctl/kernel.rst
@@ -592,6 +592,18 @@ to the guest kernel command line (see
Documentation/admin-guide/kernel-parameters.rst).
+nmi_wd_lpm_factor (PPC only)
+============================
+
+Factor apply 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 an
+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).
+
+
numa_balancing
==============
diff --git a/arch/powerpc/platforms/pseries/mobility.c
b/arch/powerpc/platforms/pseries/mobility.c
index 6297467072e6..3d36a8955eaf 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 nmi_wd_lpm_factor = 200;
+
+#ifdef CONFIG_SYSCTL
+static struct ctl_table nmi_wd_lpm_factor_ctl_table[] = {
+ {
+ .procname = "nmi_wd_lpm_factor",
+ .data = &nmi_wd_lpm_factor,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_douintvec_minmax,
+ },
+ {}
+};
+static struct ctl_table nmi_wd_lpm_factor_sysctl_root[] = {
+ {
+ .procname = "kernel",
+ .mode = 0555,
+ .child = nmi_wd_lpm_factor_ctl_table,
+ },
+ {}
+};
+
+static int __init register_nmi_wd_lpm_factor_sysctl(void)
+{
+ register_sysctl_table(nmi_wd_lpm_factor_sysctl_root);
+
+ return 0;
+}
+device_initcall(register_nmi_wd_lpm_factor_sysctl);
+#endif /* CONFIG_SYSCTL */
+#endif /* CONFIG_PPC_WATCHDOG */
+
static int mobility_rtas_call(int token, char *buf, s32 scope)
{
int rc;
@@ -702,13 +735,20 @@ static int pseries_suspend(u64 handle)
static int pseries_migrate_partition(u64 handle)
{
int ret;
+ unsigned int factor = 0;
+#ifdef CONFIG_PPC_WATCHDOG
+ factor = nmi_wd_lpm_factor;
+#endif
ret = wait_for_vasi_session_suspending(handle);
if (ret)
return ret;
vas_migration_handler(VAS_SUSPEND);
+ if (factor)
+ watchdog_nmi_set_timeout_pct(factor);
+
ret = pseries_suspend(handle);
if (ret == 0) {
post_mobility_fixup();
@@ -722,6 +762,9 @@ static int pseries_migrate_partition(u64 handle)
} else
pseries_cancel_migration(handle, ret);
+ if (factor)
+ watchdog_nmi_set_timeout_pct(0);
+
vas_migration_handler(VAS_RESUME);
return ret;
--
2.37.0
