tmpfs radix_tree: locate_item to speed up swapoff

We have already acknowledged that swapoff of a tmpfs file is slower than
it was before conversion to the generic radix_tree: a little slower
there will be acceptable, if the hotter paths are faster.

But it was a shock to find swapoff of a 500MB file 20 times slower on my
laptop, taking 10 minutes; and at that rate it significantly slows down
my testing.

Now, most of that turned out to be overhead from PROVE_LOCKING and
PROVE_RCU: without those it was only 4 times slower than before; and
more realistic tests on other machines don't fare as badly.

I've tried a number of things to improve it, including tagging the swap
entries, then doing lookup by tag: I'd expected that to halve the time,
but in practice it's erratic, and often counter-productive.

The only change I've so far found to make a consistent improvement, is
to short-circuit the way we go back and forth, gang lookup packing
entries into the array supplied, then shmem scanning that array for the
target entry.  Scanning in place doubles the speed, so it's now only
twice as slow as before (or three times slower when the PROVEs are on).

So, add radix_tree_locate_item() as an expedient, once-off,
single-caller hack to do the lookup directly in place.  #ifdef it on
CONFIG_SHMEM and CONFIG_SWAP, as much to document its limited
applicability as save space in other configurations.  And, sadly,
#include sched.h for cond_resched().

Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index b7edf8251455153de9bdeb19be3fa9bd50753765..9d4539c52e53e5f3635345260049999ba90d735e 100644 (file)
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -252,6 +252,7 @@ unsigned long radix_tree_range_tag_if_tagged(struct radix_tree_root *root,
                unsigned long nr_to_tag,
                unsigned int fromtag, unsigned int totag);
 int radix_tree_tagged(struct radix_tree_root *root, unsigned int tag);
+unsigned long radix_tree_locate_item(struct radix_tree_root *root, void *item);
 
 static inline void radix_tree_preload_end(void)
 {

diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 348eaefbed74c38b7cc2554f4a7a111280f65f2e..a2f9da59c1970cfab2a55c94f43da8843551ef05 100644 (file)
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -1203,6 +1203,98 @@ radix_tree_gang_lookup_tag_slot(struct radix_tree_root *root, void ***results,
 }
 EXPORT_SYMBOL(radix_tree_gang_lookup_tag_slot);
 
+#if defined(CONFIG_SHMEM) && defined(CONFIG_SWAP)
+#include <linux/sched.h> /* for cond_resched() */
+
+/*
+ * This linear search is at present only useful to shmem_unuse_inode().
+ */
+static unsigned long __locate(struct radix_tree_node *slot, void *item,
+                             unsigned long index, unsigned long *found_index)
+{
+       unsigned int shift, height;
+       unsigned long i;
+
+       height = slot->height;
+       shift = (height-1) * RADIX_TREE_MAP_SHIFT;
+
+       for ( ; height > 1; height--) {
+               i = (index >> shift) & RADIX_TREE_MAP_MASK;
+               for (;;) {
+                       if (slot->slots[i] != NULL)
+                               break;
+                       index &= ~((1UL << shift) - 1);
+                       index += 1UL << shift;
+                       if (index == 0)
+                               goto out;       /* 32-bit wraparound */
+                       i++;
+                       if (i == RADIX_TREE_MAP_SIZE)
+                               goto out;
+               }
+
+               shift -= RADIX_TREE_MAP_SHIFT;
+               slot = rcu_dereference_raw(slot->slots[i]);
+               if (slot == NULL)
+                       goto out;
+       }
+
+       /* Bottom level: check items */
+       for (i = 0; i < RADIX_TREE_MAP_SIZE; i++) {
+               if (slot->slots[i] == item) {
+                       *found_index = index + i;
+                       index = 0;
+                       goto out;
+               }
+       }
+       index += RADIX_TREE_MAP_SIZE;
+out:
+       return index;
+}
+
+/**
+ *     radix_tree_locate_item - search through radix tree for item
+ *     @root:          radix tree root
+ *     @item:          item to be found
+ *
+ *     Returns index where item was found, or -1 if not found.
+ *     Caller must hold no lock (since this time-consuming function needs
+ *     to be preemptible), and must check afterwards if item is still there.
+ */
+unsigned long radix_tree_locate_item(struct radix_tree_root *root, void *item)
+{
+       struct radix_tree_node *node;
+       unsigned long max_index;
+       unsigned long cur_index = 0;
+       unsigned long found_index = -1;
+
+       do {
+               rcu_read_lock();
+               node = rcu_dereference_raw(root->rnode);
+               if (!radix_tree_is_indirect_ptr(node)) {
+                       rcu_read_unlock();
+                       if (node == item)
+                               found_index = 0;
+                       break;
+               }
+
+               node = indirect_to_ptr(node);
+               max_index = radix_tree_maxindex(node->height);
+               if (cur_index > max_index)
+                       break;
+
+               cur_index = __locate(node, item, cur_index, &found_index);
+               rcu_read_unlock();
+               cond_resched();
+       } while (cur_index != 0 && cur_index <= max_index);
+
+       return found_index;
+}
+#else
+unsigned long radix_tree_locate_item(struct radix_tree_root *root, void *item)
+{
+       return -1;
+}
+#endif /* CONFIG_SHMEM && CONFIG_SWAP */
 
 /**
  *     radix_tree_shrink    -    shrink height of a radix tree to minimal

diff --git a/mm/shmem.c b/mm/shmem.c
index 3a5be0feb6af69170884512b8d6d58a361d79a98..1c702f6f1241fadb04e83ac4e1c0aecab4d7de4b 100644 (file)
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -356,42 +356,6 @@ export:
        return ret;
 }
 
-/*
- * Lockless lookup of swap entry in radix tree, avoiding refcount on pages.
- */
-static pgoff_t shmem_find_swap(struct address_space *mapping, void *radswap)
-{
-       void  **slots[PAGEVEC_SIZE];
-       pgoff_t indices[PAGEVEC_SIZE];
-       unsigned int nr_found;
-
-restart:
-       nr_found = 1;
-       indices[0] = -1;
-       while (nr_found) {
-               pgoff_t index = indices[nr_found - 1] + 1;
-               unsigned int i;
-
-               rcu_read_lock();
-               nr_found = radix_tree_gang_lookup_slot(&mapping->page_tree,
-                                       slots, indices, index, PAGEVEC_SIZE);
-               for (i = 0; i < nr_found; i++) {
-                       void *item = radix_tree_deref_slot(slots[i]);
-                       if (radix_tree_deref_retry(item)) {
-                               rcu_read_unlock();
-                               goto restart;
-                       }
-                       if (item == radswap) {
-                               rcu_read_unlock();
-                               return indices[i];
-                       }
-               }
-               rcu_read_unlock();
-               cond_resched();
-       }
-       return -1;
-}
-
 /*
  * Remove swap entry from radix tree, free the swap and its page cache.
  */
@@ -612,7 +576,7 @@ static int shmem_unuse_inode(struct shmem_inode_info *info,
        int error;
 
        radswap = swp_to_radix_entry(swap);
-       index = shmem_find_swap(mapping, radswap);
+       index = radix_tree_locate_item(&mapping->page_tree, radswap);
        if (index == -1)
                return 0;