[PATCH v2 2/3] mm/memory-failure: add panic_on_unrecoverable_memory_failure sysctl

[Breno Leitao]

Add a sysctl that allows the system to panic when an unrecoverable
memory failure is detected. This covers kernel pages, high-order
kernel pages, and unknown page types that cannot be recovered.

Signed-off-by: Breno Leitao <leitao@xxxxxxxxxx>
---
 mm/memory-failure.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 6ff80e01b91a..d0d911c54ff1 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -74,6 +74,8 @@ static int sysctl_memory_failure_recovery __read_mostly = 1;
 
 static int sysctl_enable_soft_offline __read_mostly = 1;
 
+static int sysctl_panic_on_unrecoverable_mf __read_mostly;
+
 atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0);
 
 static bool hw_memory_failure __read_mostly = false;
@@ -155,6 +157,15 @@ static const struct ctl_table memory_failure_table[] = {
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= SYSCTL_ZERO,
 		.extra2		= SYSCTL_ONE,
+	},
+	{
+		.procname	= "panic_on_unrecoverable_memory_failure",
+		.data		= &sysctl_panic_on_unrecoverable_mf,
+		.maxlen		= sizeof(sysctl_panic_on_unrecoverable_mf),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
 	}
 };
 
@@ -1298,6 +1309,11 @@ static int action_result(unsigned long pfn, enum mf_action_page_type type,
 	pr_err("%#lx: recovery action for %s: %s\n",
 		pfn, action_page_types[type], action_name[result]);
 
+	if (sysctl_panic_on_unrecoverable_mf && result == MF_IGNORED &&
+	    (type == MF_MSG_KERNEL || type == MF_MSG_KERNEL_HIGH_ORDER ||
+	     type == MF_MSG_UNKNOWN))
+		panic("Memory failure: %#lx: unrecoverable page", pfn);
+
 	return (result == MF_RECOVERED || result == MF_DELAYED) ? 0 : -EBUSY;
 }
 

-- 
2.52.0