HWPOISON: Add soft page offline support

[safe/jmp/linux-2.6] / Documentation / ABI / testing / sysfs-memory-page-offline

diff --git a/Documentation/ABI/testing/sysfs-memory-page-offline b/Documentation/ABI/testing/sysfs-memory-page-offline
new file mode 100644 (file)
index 0000000..e14703f
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-memory-page-offline
@@ -0,0 +1,44 @@
+What:          /sys/devices/system/memory/soft_offline_page
+Date:          Sep 2009
+KernelVersion: 2.6.33
+Contact:       andi@firstfloor.org
+Description:
+               Soft-offline the memory page containing the physical address
+               written into this file. Input is a hex number specifying the
+               physical address of the page. The kernel will then attempt
+               to soft-offline it, by moving the contents elsewhere or
+               dropping it if possible. The kernel will then be placed
+               on the bad page list and never be reused.
+
+               The offlining is done in kernel specific granuality.
+               Normally it's the base page size of the kernel, but
+               this might change.
+
+               The page must be still accessible, not poisoned. The
+               kernel will never kill anything for this, but rather
+               fail the offline.  Return value is the size of the
+               number, or a error when the offlining failed.  Reading
+               the file is not allowed.
+
+What:          /sys/devices/system/memory/hard_offline_page
+Date:          Sep 2009
+KernelVersion: 2.6.33
+Contact:       andi@firstfloor.org
+Description:
+               Hard-offline the memory page containing the physical
+               address written into this file. Input is a hex number
+               specifying the physical address of the page. The
+               kernel will then attempt to hard-offline the page, by
+               trying to drop the page or killing any owner or
+               triggering IO errors if needed.  Note this may kill
+               any processes owning the page. The kernel will avoid
+               to access this page assuming it's poisoned by the
+               hardware.
+
+               The offlining is done in kernel specific granuality.
+               Normally it's the base page size of the kernel, but
+               this might change.
+
+               Return value is the size of the number, or a error when
+               the offlining failed.
+               Reading the file is not allowed.