vmscan: kswapd: don't retry balance_pgdat() if all zones are unreclaimable

[safe/jmp/linux-2.6] / mm / madvise.c

diff --git a/mm/madvise.c b/mm/madvise.c
index 66c3126..319528b 100644 (file)
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -9,8 +9,10 @@
 #include <linux/pagemap.h>
 #include <linux/syscalls.h>
 #include <linux/mempolicy.h>
+#include <linux/page-isolation.h>
 #include <linux/hugetlb.h>
 #include <linux/sched.h>
+#include <linux/ksm.h>
 
 /*
  * Any behaviour which results in changes to the vma->vm_flags needs to
@@ -63,6 +65,12 @@ static long madvise_behavior(struct vm_area_struct * vma,
                }
                new_flags &= ~VM_DONTCOPY;
                break;
+       case MADV_MERGEABLE:
+       case MADV_UNMERGEABLE:
+               error = ksm_madvise(vma, start, end, behavior, &new_flags);
+               if (error)
+                       goto out;
+               break;
        }
 
        if (new_flags == vma->vm_flags) {
@@ -211,6 +219,38 @@ 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(int bhv, 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_fast(start, 1, 0, &p);
+               if (ret != 1)
+                       return ret;
+               if (bhv == MADV_SOFT_OFFLINE) {
+                       printk(KERN_INFO "Soft offlining page %lx at %lx\n",
+                               page_to_pfn(p), start);
+                       ret = soft_offline_page(p, MF_COUNT_INCREASED);
+                       if (ret)
+                               break;
+                       continue;
+               }
+               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, MF_COUNT_INCREASED);
+       }
+       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)
@@ -239,6 +279,10 @@ madvise_behavior_valid(int behavior)
        case MADV_REMOVE:
        case MADV_WILLNEED:
        case MADV_DONTNEED:
+#ifdef CONFIG_KSM
+       case MADV_MERGEABLE:
+       case MADV_UNMERGEABLE:
+#endif
                return 1;
 
        default:
@@ -273,6 +317,9 @@ madvise_behavior_valid(int behavior)
  *  MADV_DONTFORK - omit this area from child's address space when forking:
  *             typically, to avoid COWing pages pinned by get_user_pages().
  *  MADV_DOFORK - cancel MADV_DONTFORK: no longer omit this area when forking.
+ *  MADV_MERGEABLE - the application recommends that KSM try to merge pages in
+ *             this area with pages of identical content from other such areas.
+ *  MADV_UNMERGEABLE- cancel MADV_MERGEABLE: no longer merge pages with others.
  *
  * return values:
  *  zero    - success
@@ -294,6 +341,10 @@ 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 || behavior == MADV_SOFT_OFFLINE)
+               return madvise_hwpoison(behavior, start, start+len_in);
+#endif
        if (!madvise_behavior_valid(behavior))
                return error;