HWPOISON: Add madvise() based injector for hardware poisoned pages v4

Impact: optional, useful for debugging

Add a new madvice sub command to inject poison for some
pages in a process' address space.  This is useful for
testing the poison page handling.

This patch can allow root to tie up large amounts of memory.
I got feedback from container developers and they didn't see any
problem.

v2: Use write flag for get_user_pages to make sure to always get
a fresh page
v3: Don't request write mapping (Fengguang Wu)
v4: Move MADV_* number to avoid conflict with KSM (Hugh Dickins)

Signed-off-by: Andi Kleen <ak@linux.intel.com>

2 files changed, 31 insertions, 0 deletions

diff --git a/include/asm-generic/mman-common.h b/include/asm-generic/mman-common.h
index 3b69ad3..c325d1e 100644
--- a/include/asm-generic/mman-common.h
+++ b/include/asm-generic/mman-common.h
@@ -34,6 +34,7 @@
 #define MADV_REMOVE	9		/* remove these pages & resources */
 #define MADV_DONTFORK	10		/* don't inherit across fork */
 #define MADV_DOFORK	11		/* do inherit across fork */
+#define MADV_HWPOISON	100		/* poison a page for testing */
 
 /* compatibility flags */
 #define MAP_FILE	0
diff --git a/mm/madvise.c b/mm/madvise.c
index 76eb419..8dbd38b 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -207,6 +207,32 @@ static long madvise_remove(struct vm_area_struct *vma,
 	return error;
 }
 
+#ifdef CONFIG_MEMORY_FAILURE
+/*
+ * Error injection support for memory error handling.
+ */
+static int madvise_hwpoison(unsigned long start, unsigned long end)
+{
+	int ret = 0;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+	for (; start < end; start += PAGE_SIZE) {
+		struct page *p;
+		int ret = get_user_pages(current, current->mm, start, 1,
+						0, 0, &p, NULL);
+		if (ret != 1)
+			return ret;
+		printk(KERN_INFO "Injecting memory failure for page %lx at %lx\n",
+		       page_to_pfn(p), start);
+		/* Ignore return value for now */
+		__memory_failure(page_to_pfn(p), 0, 1);
+		put_page(p);
+	}
+	return ret;
+}
+#endif
+
 static long
 madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev,
 		unsigned long start, unsigned long end, int behavior)
@@ -307,6 +333,10 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
 	int write;
 	size_t len;
 
+#ifdef CONFIG_MEMORY_FAILURE
+	if (behavior == MADV_HWPOISON)
+		return madvise_hwpoison(start, start+len_in);
+#endif
 	if (!madvise_behavior_valid(behavior))
 		return error;