1 files changed, 71 insertions, 0 deletions
diff --git a/drivers/ras/Kconfig b/drivers/ras/Kconfig
new file mode 100644
index 000000000..070e17639
--- /dev/null
+++ b/drivers/ras/Kconfig
@@ -0,0 +1,71 @@
+# SPDX-License-Identifier: GPL-2.0-only
+menuconfig RAS
+	bool "Reliability, Availability and Serviceability (RAS) features"
+	help
+	  Reliability, availability and serviceability (RAS) is a computer
+	  hardware engineering term. Computers designed with higher levels
+	  of RAS have a multitude of features that protect data integrity
+	  and help them stay available for long periods of time without
+	  failure.
+
+	  Reliability can be defined as the probability that the system will
+	  produce correct outputs up to some given time. Reliability is
+	  enhanced by features that help to avoid, detect and repair hardware
+	  faults.
+
+	  Availability is the probability a system is operational at a given
+	  time, i.e. the amount of time a device is actually operating as the
+	  percentage of total time it should be operating.
+
+	  Serviceability or maintainability is the simplicity and speed with
+	  which a system can be repaired or maintained; if the time to repair
+	  a failed system increases, then availability will decrease.
+
+	  Note that Reliability and Availability are distinct concepts:
+	  Reliability is a measure of the ability of a system to function
+	  correctly, including avoiding data corruption, whereas Availability
+	  measures how often it is available for use, even though it may not
+	  be functioning correctly. For example, a server may run forever and
+	  so have ideal availability, but may be unreliable, with frequent
+	  data corruption.
+
+if RAS
+
+config RAS_CEC
+	bool "Correctable Errors Collector"
+	depends on X86_MCE && MEMORY_FAILURE && DEBUG_FS
+	help
+	  This is a small cache which collects correctable memory errors per 4K
+	  page PFN and counts their repeated occurrence. Once the counter for a
+	  PFN overflows, we try to soft-offline that page as we take it to mean
+	  that it has reached a relatively high error count and would probably
+	  be best if we don't use it anymore.
+
+	  Bear in mind that this is absolutely useless if your platform doesn't
+	  have ECC DIMMs and doesn't have DRAM ECC checking enabled in the BIOS.
+
+config RAS_CEC_DEBUG
+	bool "CEC debugging machinery"
+	default n
+	depends on RAS_CEC
+	help
+	  Add extra files to (debugfs)/ras/cec to test the correctable error
+	  collector feature. "pfn" is a writable file that allows user to
+	  simulate an error in a particular page frame. "array" is a read-only
+	  file that dumps out the current state of all pages logged so far.
+
+source "drivers/ras/amd/atl/Kconfig"
+
+config RAS_FMPM
+	tristate "FRU Memory Poison Manager"
+	default m
+	depends on AMD_ATL && ACPI_APEI
+	help
+	  Support saving and restoring memory error information across reboot
+	  using ACPI ERST as persistent storage. Error information is saved with
+	  the UEFI CPER "FRU Memory Poison" section format.
+
+	  Memory will be retired during boot time and run time depending on
+	  platform-specific policies.
+
+endif