[PATCH v3 2/3] mm/memory-failure: add CONFIG_BOOTPARAM_MEMORY_FAILURE_PANIC option

[Breno Leitao]

Add a kernel configuration option to enable panic on unrecoverable
memory failures at boot time, similar to CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC
and CONFIG_BOOTPARAM_HARDLOCKUP_PANIC.

This allows systems that prioritize availability over recovery to
automatically panic when encountering unrecoverable kernel memory
failures. The behavior can still be controlled at runtime via the
panic_on_unrecoverable_memory_failure sysctl.

When enabled, the kernel will panic if:
 * A memory failure affects kernel pages that cannot be recovered
 * A memory failure affects high-order kernel pages
 * A memory failure affects unknown page types that cannot be recovered

Examples of BOOTPARAM configuration usage:

1. Building with the panic option enabled by default:
   CONFIG_BOOTPARAM_MEMORY_FAILURE_PANIC=y

2. Disabling at runtime even when compiled in:
   echo 0 > /proc/sys/vm/panic_on_unrecoverable_memory_failure

3. Enabling at runtime when not compiled in by default:
   echo 1 > /proc/sys/vm/panic_on_unrecoverable_memory_failure

Similar to other BOOTPARAM options, this provides a balance between:
 - Safe defaults (disabled by default without CONFIG option)
 - Production flexibility (can be enabled at build time)
 - Runtime control (can be toggled via sysctl)

This is consistent with the kernel's approach to other panic-on-error
options that allow systems to choose between attempting recovery or
failing fast when critical errors are detected.

Signed-off-by: Breno Leitao <leitao@xxxxxxxxxx>
---
 mm/Kconfig          | 9 +++++++++
 mm/memory-failure.c | 3 ++-
 2 files changed, 11 insertions(+), 1 deletion(-)

diff --git a/mm/Kconfig b/mm/Kconfig
index ebd8ea353687e..596f24a872ff6 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -733,6 +733,15 @@ config MEMORY_FAILURE
 	  even when some of its memory has uncorrected errors. This requires
 	  special hardware support and typically ECC memory.
 
+config BOOTPARAM_MEMORY_FAILURE_PANIC
+	bool "Panic on unrecoverable memory failure"
+	depends on MEMORY_FAILURE
+	help
+	  Say Y here 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. Can be disabled
+	  at runtime via the panic_on_unrecoverable_memory_failure sysctl.
+
 config HWPOISON_INJECT
 	tristate "HWPoison pages injector"
 	depends on MEMORY_FAILURE && DEBUG_KERNEL && PROC_FS
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 852c595aff108..cf06960b4d069 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -74,7 +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;
+static int sysctl_panic_on_unrecoverable_mf __read_mostly =
+			IS_ENABLED(CONFIG_BOOTPARAM_MEMORY_FAILURE_PANIC);
 
 atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0);
 

-- 
2.52.0