[PATCH] mm: pte_offset_map_lock loops

[linux-2.6] / mm / swapfile.c

diff --git a/mm/swapfile.c b/mm/swapfile.c
index 0184f510aacefd5cdce18b18a2d2f91008e255db..510f0039b00030a7867d38be885f87afcdd76c4f 100644 (file)
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -398,17 +398,14 @@ void free_swap_and_cache(swp_entry_t entry)
 }
 
 /*
- * Always set the resulting pte to be nowrite (the same as COW pages
- * after one process has exited).  We don't know just how many PTEs will
- * share this swap entry, so be cautious and let do_wp_page work out
- * what to do if a write is requested later.
- *
- * vma->vm_mm->page_table_lock is held.
+ * No need to decide whether this PTE shares the swap entry with others,
+ * just let do_wp_page work it out if a write is requested later - to
+ * force COW, vm_page_prot omits write permission from any private vma.
  */
 static void unuse_pte(struct vm_area_struct *vma, pte_t *pte,
                unsigned long addr, swp_entry_t entry, struct page *page)
 {
-       inc_mm_counter(vma->vm_mm, rss);
+       inc_mm_counter(vma->vm_mm, anon_rss);
        get_page(page);
        set_pte_at(vma->vm_mm, addr, pte,
                   pte_mkold(mk_pte(page, vma->vm_page_prot)));
@@ -425,23 +422,25 @@ static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
                                unsigned long addr, unsigned long end,
                                swp_entry_t entry, struct page *page)
 {
-       pte_t *pte;
        pte_t swp_pte = swp_entry_to_pte(entry);
+       pte_t *pte;
+       spinlock_t *ptl;
+       int found = 0;
 
-       pte = pte_offset_map(pmd, addr);
+       pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
        do {
                /*
                 * swapoff spends a _lot_ of time in this loop!
                 * Test inline before going to call unuse_pte.
                 */
                if (unlikely(pte_same(*pte, swp_pte))) {
-                       unuse_pte(vma, pte, addr, entry, page);
-                       pte_unmap(pte);
-                       return 1;
+                       unuse_pte(vma, pte++, addr, entry, page);
+                       found = 1;
+                       break;
                }
        } while (pte++, addr += PAGE_SIZE, addr != end);
-       pte_unmap(pte - 1);
-       return 0;
+       pte_unmap_unlock(pte - 1, ptl);
+       return found;
 }
 
 static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud,
@@ -523,12 +522,10 @@ static int unuse_mm(struct mm_struct *mm,
                down_read(&mm->mmap_sem);
                lock_page(page);
        }
-       spin_lock(&mm->page_table_lock);
        for (vma = mm->mmap; vma; vma = vma->vm_next) {
                if (vma->anon_vma && unuse_vma(vma, entry, page))
                        break;
        }
-       spin_unlock(&mm->page_table_lock);
        up_read(&mm->mmap_sem);
        /*
         * Currently unuse_mm cannot fail, but leave error handling
@@ -1381,6 +1378,7 @@ asmlinkage long sys_swapon(const char __user * specialfile, int swap_flags)
                error = bd_claim(bdev, sys_swapon);
                if (error < 0) {
                        bdev = NULL;
+                       error = -EINVAL;
                        goto bad_swap;
                }
                p->old_block_size = block_size(bdev);