mm: fix swapops.h:131 bug if remap_file_pages raced migration

[~andy/linux] / mm / migrate.c

diff --git a/mm/migrate.c b/mm/migrate.c
index b494fdb9a6363e058f802069ba5de8e677005b45..bed48809e5d01c14513a1395a12a3c4098341755 100644 (file)
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -177,6 +177,37 @@ out:
        return SWAP_AGAIN;
 }
 
+/*
+ * Congratulations to trinity for discovering this bug.
+ * mm/fremap.c's remap_file_pages() accepts any range within a single vma to
+ * convert that vma to VM_NONLINEAR; and generic_file_remap_pages() will then
+ * replace the specified range by file ptes throughout (maybe populated after).
+ * If page migration finds a page within that range, while it's still located
+ * by vma_interval_tree rather than lost to i_mmap_nonlinear list, no problem:
+ * zap_pte() clears the temporary migration entry before mmap_sem is dropped.
+ * But if the migrating page is in a part of the vma outside the range to be
+ * remapped, then it will not be cleared, and remove_migration_ptes() needs to
+ * deal with it.  Fortunately, this part of the vma is of course still linear,
+ * so we just need to use linear location on the nonlinear list.
+ */
+static int remove_linear_migration_ptes_from_nonlinear(struct page *page,
+               struct address_space *mapping, void *arg)
+{
+       struct vm_area_struct *vma;
+       /* hugetlbfs does not support remap_pages, so no huge pgoff worries */
+       pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
+       unsigned long addr;
+
+       list_for_each_entry(vma,
+               &mapping->i_mmap_nonlinear, shared.nonlinear) {
+
+               addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
+               if (addr >= vma->vm_start && addr < vma->vm_end)
+                       remove_migration_pte(page, vma, addr, arg);
+       }
+       return SWAP_AGAIN;
+}
+
 /*
  * Get rid of all migration entries and replace them by
  * references to the indicated page.
@@ -186,6 +217,7 @@ static void remove_migration_ptes(struct page *old, struct page *new)
        struct rmap_walk_control rwc = {
                .rmap_one = remove_migration_pte,
                .arg = old,
+               .file_nonlinear = remove_linear_migration_ptes_from_nonlinear,
        };
 
        rmap_walk(new, &rwc);