[PATCH] swap: swap extent list is ordered

[linux-2.6] / mm / swapfile.c

diff --git a/mm/swapfile.c b/mm/swapfile.c
index 60cd24a55204efc5c84956443d02f9806bd66a9d..73521d39e9850f93fc1248651cd9ca66fae827b0 100644 (file)
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -832,9 +832,9 @@ sector_t map_swap_page(struct swap_info_struct *sis, pgoff_t offset)
                                offset < (se->start_page + se->nr_pages)) {
                        return se->start_block + (offset - se->start_page);
                }
-               lh = se->list.prev;
+               lh = se->list.next;
                if (lh == &sis->extent_list)
-                       lh = lh->prev;
+                       lh = lh->next;
                se = list_entry(lh, struct swap_extent, list);
                sis->curr_swap_extent = se;
                BUG_ON(se == start_se);         /* It *must* be present */
@@ -859,10 +859,9 @@ static void destroy_swap_extents(struct swap_info_struct *sis)
 
 /*
  * Add a block range (and the corresponding page range) into this swapdev's
- * extent list.  The extent list is kept sorted in block order.
+ * extent list.  The extent list is kept sorted in page order.
  *
- * This function rather assumes that it is called in ascending sector_t order.
- * It doesn't look for extent coalescing opportunities.
+ * This function rather assumes that it is called in ascending page order.
  */
 static int
 add_swap_extent(struct swap_info_struct *sis, unsigned long start_page,
@@ -872,16 +871,15 @@ add_swap_extent(struct swap_info_struct *sis, unsigned long start_page,
        struct swap_extent *new_se;
        struct list_head *lh;
 
-       lh = sis->extent_list.next;     /* The highest-addressed block */
-       while (lh != &sis->extent_list) {
+       lh = sis->extent_list.prev;     /* The highest page extent */
+       if (lh != &sis->extent_list) {
                se = list_entry(lh, struct swap_extent, list);
-               if (se->start_block + se->nr_pages == start_block &&
-                   se->start_page  + se->nr_pages == start_page) {
+               BUG_ON(se->start_page + se->nr_pages != start_page);
+               if (se->start_block + se->nr_pages == start_block) {
                        /* Merge it */
                        se->nr_pages += nr_pages;
                        return 0;
                }
-               lh = lh->next;
        }
 
        /*
@@ -894,14 +892,7 @@ add_swap_extent(struct swap_info_struct *sis, unsigned long start_page,
        new_se->nr_pages = nr_pages;
        new_se->start_block = start_block;
 
-       lh = sis->extent_list.prev;     /* The lowest block */
-       while (lh != &sis->extent_list) {
-               se = list_entry(lh, struct swap_extent, list);
-               if (se->start_block > start_block)
-                       break;
-               lh = lh->prev;
-       }
-       list_add_tail(&new_se->list, lh);
+       list_add_tail(&new_se->list, &sis->extent_list);
        sis->nr_extents++;
        return 0;
 }
@@ -926,7 +917,7 @@ add_swap_extent(struct swap_info_struct *sis, unsigned long start_page,
  * requirements, they are simply tossed out - we will never use those blocks
  * for swapping.
  *
- * For S_ISREG swapfiles we hold i_sem across the life of the swapon.  This
+ * For S_ISREG swapfiles we set S_SWAPFILE across the life of the swapon.  This
  * prevents root from shooting her foot off by ftruncating an in-use swapfile,
  * which will scribble on the fs.
  *
@@ -1008,8 +999,9 @@ reprobe:
        }
        ret = 0;
        if (page_no == 0)
-               ret = -EINVAL;
+               page_no = 1;    /* force Empty message */
        sis->max = page_no;
+       sis->pages = page_no - 1;
        sis->highest_bit = page_no - 1;
 done:
        sis->curr_swap_extent = list_entry(sis->extent_list.prev,
@@ -1128,6 +1120,7 @@ asmlinkage long sys_swapoff(const char __user * specialfile)
                swap_list_unlock();
                goto out_dput;
        }
+       destroy_swap_extents(p);
        down(&swapon_sem);
        swap_list_lock();
        drain_mmlist();
@@ -1138,7 +1131,6 @@ asmlinkage long sys_swapoff(const char __user * specialfile)
        swap_map = p->swap_map;
        p->swap_map = NULL;
        p->flags = 0;
-       destroy_swap_extents(p);
        swap_device_unlock(p);
        swap_list_unlock();
        up(&swapon_sem);
@@ -1446,6 +1438,10 @@ asmlinkage long sys_swapon(const char __user * specialfile, int swap_flags)
                p->highest_bit = maxpages - 1;
 
                error = -EINVAL;
+               if (!maxpages)
+                       goto bad_swap;
+               if (swap_header->info.nr_badpages && S_ISREG(inode->i_mode))
+                       goto bad_swap;
                if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES)
                        goto bad_swap;
                
@@ -1470,25 +1466,27 @@ asmlinkage long sys_swapon(const char __user * specialfile, int swap_flags)
                if (error) 
                        goto bad_swap;
        }
-       
+
        if (swapfilesize && maxpages > swapfilesize) {
                printk(KERN_WARNING
                       "Swap area shorter than signature indicates\n");
                error = -EINVAL;
                goto bad_swap;
        }
+       if (nr_good_pages) {
+               p->swap_map[0] = SWAP_MAP_BAD;
+               p->max = maxpages;
+               p->pages = nr_good_pages;
+               error = setup_swap_extents(p);
+               if (error)
+                       goto bad_swap;
+               nr_good_pages = p->pages;
+       }
        if (!nr_good_pages) {
                printk(KERN_WARNING "Empty swap-file\n");
                error = -EINVAL;
                goto bad_swap;
        }
-       p->swap_map[0] = SWAP_MAP_BAD;
-       p->max = maxpages;
-       p->pages = nr_good_pages;
-
-       error = setup_swap_extents(p);
-       if (error)
-               goto bad_swap;
 
        down(&swapon_sem);
        swap_list_lock();
@@ -1524,6 +1522,7 @@ bad_swap:
                set_blocksize(bdev, p->old_block_size);
                bd_release(bdev);
        }
+       destroy_swap_extents(p);
 bad_swap_2:
        swap_list_lock();
        swap_map = p->swap_map;
@@ -1533,7 +1532,6 @@ bad_swap_2:
        if (!(swap_flags & SWAP_FLAG_PREFER))
                ++least_priority;
        swap_list_unlock();
-       destroy_swap_extents(p);
        vfree(swap_map);
        if (swap_file)
                filp_close(swap_file, NULL);