[PATCH] swap: swap_lock replace list+device

The idea of a swap_device_lock per device, and a swap_list_lock over them all,
is appealing; but in practice almost every holder of swap_device_lock must
already hold swap_list_lock, which defeats the purpose of the split.

The only exceptions have been swap_duplicate, valid_swaphandles and an
untrodden path in try_to_unuse (plus a few places added in this series).
valid_swaphandles doesn't show up high in profiles, but swap_duplicate does
demand attention.  However, with the hold time in get_swap_pages so much
reduced, I've not yet found a load and set of swap device priorities to show
even swap_duplicate benefitting from the split.  Certainly the split is mere
overhead in the common case of a single swap device.

So, replace swap_list_lock and swap_device_lock by spinlock_t swap_lock
(generally we seem to prefer an _ in the name, and not hide in a macro).

If someone can show a regression in swap_duplicate, then probably we should
add a hashlock for the swap_map entries alone (shorts being anatomic), so as
to help the case of the single swap device too.
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

Documentation/vm/locking

@@ -83,19 +83,18 @@ single address space optimization, so that the zap_page_range (from
 vmtruncate) does not lose sending ipi's to cloned threads that might 
 be spawned underneath it and go to user mode to drag in pte's into tlbs.
 
-swap_list_lock/swap_device_lock
--------------------------------
+swap_lock
+--------------
 The swap devices are chained in priority order from the "swap_list" header. 
 The "swap_list" is used for the round-robin swaphandle allocation strategy.
 The #free swaphandles is maintained in "nr_swap_pages". These two together
-are protected by the swap_list_lock. 
+are protected by the swap_lock.
 
-The swap_device_lock, which is per swap device, protects the reference 
-counts on the corresponding swaphandles, maintained in the "swap_map"
-array, and the "highest_bit" and "lowest_bit" fields.
+The swap_lock also protects all the device reference counts on the
+corresponding swaphandles, maintained in the "swap_map" array, and the
+"highest_bit" and "lowest_bit" fields.
 
-Both of these are spinlocks, and are never acquired from intr level. The
-locking hierarchy is swap_list_lock -> swap_device_lock.
+The swap_lock is a spinlock, and is never acquired from intr level.
 
 To prevent races between swap space deletion or async readahead swapins
 deciding whether a swap handle is being used, ie worthy of being read in

include/linux/swap.h

@@ -121,7 +121,7 @@ enum {
  */
 struct swap_info_struct {
 	unsigned int flags;
-	spinlock_t sdev_lock;
+	int prio;			/* swap priority */
 	struct file *swap_file;
 	struct block_device *bdev;
 	struct list_head extent_list;
@@ -135,7 +135,6 @@ struct swap_info_struct {
 	unsigned int pages;
 	unsigned int max;
 	unsigned int inuse_pages;
-	int prio;			/* swap priority */
 	int next;			/* next entry on swap list */
 };
 
@@ -221,13 +220,7 @@ extern int can_share_swap_page(struct page *);
 extern int remove_exclusive_swap_page(struct page *);
 struct backing_dev_info;
 
-extern struct swap_list_t swap_list;
-extern spinlock_t swaplock;
-
-#define swap_list_lock()	spin_lock(&swaplock)
-#define swap_list_unlock()	spin_unlock(&swaplock)
-#define swap_device_lock(p)	spin_lock(&p->sdev_lock)
-#define swap_device_unlock(p)	spin_unlock(&p->sdev_lock)
+extern spinlock_t swap_lock;
 
 /* linux/mm/thrash.c */
 extern struct mm_struct * swap_token_mm;

mm/filemap.c

@@ -54,9 +54,8 @@
  *
  *  ->i_mmap_lock		(vmtruncate)
  *    ->private_lock		(__free_pte->__set_page_dirty_buffers)
- *      ->swap_list_lock
- *        ->swap_device_lock	(exclusive_swap_page, others)
- *          ->mapping->tree_lock
+ *      ->swap_lock		(exclusive_swap_page, others)
+ *        ->mapping->tree_lock
  *
  *  ->i_sem
  *    ->i_mmap_lock		(truncate->unmap_mapping_range)
@@ -86,7 +85,7 @@
  *    ->page_table_lock		(anon_vma_prepare and various)
  *
  *  ->page_table_lock
- *    ->swap_device_lock	(try_to_unmap_one)
+ *    ->swap_lock		(try_to_unmap_one)
  *    ->private_lock		(try_to_unmap_one)
  *    ->tree_lock		(try_to_unmap_one)
  *    ->zone.lru_lock		(follow_page->mark_page_accessed)

mm/rmap.c

@@ -34,9 +34,8 @@
  *       anon_vma->lock
  *         mm->page_table_lock
  *           zone->lru_lock (in mark_page_accessed)
- *           swap_list_lock (in swap_free etc's swap_info_get)
+ *           swap_lock (in swap_duplicate, swap_info_get)
  *             mmlist_lock (in mmput, drain_mmlist and others)
- *             swap_device_lock (in swap_duplicate, swap_info_get)
  *             mapping->private_lock (in __set_page_dirty_buffers)
  *             inode_lock (in set_page_dirty's __mark_inode_dirty)
  *               sb_lock (within inode_lock in fs/fs-writeback.c)