The previous version didn't take the mmap_sem before calling gup(),
which is racy.
Use get_user_pages_fast() instead which doesn't need any locks.
This is also faster of course, but then it doesn't really matter
because this is just a testing path.
Based on report from Nick Piggin.
Cc: npiggin@suse.de
Signed-off-by: Andi Kleen <ak@linux.intel.com>
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);
+ int ret = get_user_pages_fast(start, 1, 0, &p);
if (ret != 1)
return ret;
printk(KERN_INFO "Injecting memory failure for page %lx at %lx\n",