[PATCH v3 3/3] Documentation: document panic_on_unrecoverable_memory_failure sysctl

[Breno Leitao]

Document the vm.panic_on_unrecoverable_memory_failure sysctl in the
admin guide, including the CONFIG_BOOTPARAM_MEMORY_FAILURE_PANIC kernel
configuration option that allows enabling this behavior at build time.

This follows the same format as panic_on_unrecovered_nmi and other
panic-on-error documentation, providing clear examples of:
 - Enabling panic at build time via CONFIG option
 - Disabling at runtime via sysctl
 - Enabling at runtime via sysctl

Signed-off-by: Breno Leitao <leitao@xxxxxxxxxx>
---
 Documentation/admin-guide/sysctl/vm.rst | 46 +++++++++++++++++++++++++++++++++
 1 file changed, 46 insertions(+)

diff --git a/Documentation/admin-guide/sysctl/vm.rst b/Documentation/admin-guide/sysctl/vm.rst
index 97e12359775c9..af545869bc1b4 100644
--- a/Documentation/admin-guide/sysctl/vm.rst
+++ b/Documentation/admin-guide/sysctl/vm.rst
@@ -67,6 +67,7 @@ Currently, these files are in /proc/sys/vm:
 - page-cluster
 - page_lock_unfairness
 - panic_on_oom
+- panic_on_unrecoverable_memory_failure
 - percpu_pagelist_high_fraction
 - stat_interval
 - stat_refresh
@@ -925,6 +926,51 @@ panic_on_oom=2+kdump gives you very strong tool to investigate
 why oom happens. You can get snapshot.
 
 
+panic_on_unrecoverable_memory_failure
+======================================
+
+When a hardware memory error (e.g. multi-bit ECC) hits an in-use kernel
+page that cannot be recovered by the memory failure handler, the default
+behaviour is to ignore the error and continue operation.  This is
+dangerous because the corrupted data remains accessible to the kernel,
+risking silent data corruption or a delayed crash when the poisoned
+memory is next accessed.
+
+Pages that reach this path include slab objects (dentry cache, inode
+cache, etc.), page tables, kernel stacks, and other kernel allocations
+that lack the reverse mapping needed to isolate all references.
+
+For many environments it is preferable to panic immediately with a clean
+crash dump that captures the original error context, rather than to
+continue and face a random crash later whose cause is difficult to
+diagnose.
+
+= =====================================================================
+0 Try to continue operation (default).
+1 Panic immediately.  If the ``panic`` sysctl is also non-zero then the
+  machine will be rebooted.
+= =====================================================================
+
+This sysctl can be set to 1 at boot time by enabling the
+``CONFIG_BOOTPARAM_MEMORY_FAILURE_PANIC`` kernel configuration option.
+This provides systems with the ability to enforce panic-on-error behavior
+from the kernel build, without requiring runtime sysctl configuration.
+
+Examples:
+
+1. Enable panic on unrecoverable memory failure at kernel build time::
+
+     CONFIG_BOOTPARAM_MEMORY_FAILURE_PANIC=y
+
+2. Disable at runtime even when compiled in::
+
+     echo 0 > /proc/sys/vm/panic_on_unrecoverable_memory_failure
+
+3. Enable at runtime when not enabled at build time::
+
+     echo 1 > /proc/sys/vm/panic_on_unrecoverable_memory_failure
+
+
 percpu_pagelist_high_fraction
 =============================
 

-- 
2.52.0