radix_tree: exceptional entries and indices

A patchset to extend tmpfs to MAX_LFS_FILESIZE by abandoning its
peculiar swap vector, instead keeping a file's swap entries in the same
radix tree as its struct page pointers: thus saving memory, and
simplifying its code and locking.

This patch:

The radix_tree is used by several subsystems for different purposes.  A
major use is to store the struct page pointers of a file's pagecache for
memory management.  But what if mm wanted to store something other than
page pointers there too?

The low bit of a radix_tree entry is already used to denote an indirect
pointer, for internal use, and the unlikely radix_tree_deref_retry()
case.

Define the next bit as denoting an exceptional entry, and supply inline
functions radix_tree_exception() to return non-0 in either unlikely
case, and radix_tree_exceptional_entry() to return non-0 in the second
case.

If a subsystem already uses radix_tree with that bit set, no problem: it
does not affect internal workings at all, but is defined for the
convenience of those storing well-aligned pointers in the radix_tree.

The radix_tree_gang_lookups have an implicit assumption that the caller
can deduce the offset of each entry returned e.g.  by the page->index of
a struct page.  But that may not be feasible for some kinds of item to
be stored there.

radix_tree_gang_lookup_slot() allow for an optional indices argument,
output array in which to return those offsets.  The same could be added
to other radix_tree_gang_lookups, but for now keep it to the only one
for which we need it.

Signed-off-by: Hugh Dickins <hughd@google.com>
Acked-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 19 insertions, 10 deletions

diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 7ea2e033d715..348eaefbed74 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -823,8 +823,8 @@ unsigned long radix_tree_prev_hole(struct radix_tree_root *root,
 EXPORT_SYMBOL(radix_tree_prev_hole);
 
 static unsigned int
-__lookup(struct radix_tree_node *slot, void ***results, unsigned long index,
-        unsigned int max_items, unsigned long *next_index)
+__lookup(struct radix_tree_node *slot, void ***results, unsigned long *indices,
+        unsigned long index, unsigned int max_items, unsigned long *next_index)
 {
         unsigned int nr_found = 0;
         unsigned int shift, height;
@@ -857,12 +857,16 @@ __lookup(struct radix_tree_node *slot, void ***results, unsigned long index,
 
         /* Bottom level: grab some items */
         for (i = index & RADIX_TREE_MAP_MASK; i < RADIX_TREE_MAP_SIZE; i++) {
-                index++;
                 if (slot->slots[i]) {
-                        results[nr_found++] = &(slot->slots[i]);
-                        if (nr_found == max_items)
+                        results[nr_found] = &(slot->slots[i]);
+                        if (indices)
+                                indices[nr_found] = index;
+                        if (++nr_found == max_items) {
+                                index++;
                                 goto out;
+                        }
                 }
+                index++;
         }
 out:
         *next_index = index;
@@ -918,8 +922,8 @@ radix_tree_gang_lookup(struct radix_tree_root *root, void **results,
 
                 if (cur_index > max_index)
                         break;
-                slots_found = __lookup(node, (void ***)results + ret, cur_index,
-                                        max_items - ret, &next_index);
+                slots_found = __lookup(node, (void ***)results + ret, NULL,
+                                cur_index, max_items - ret, &next_index);
                 nr_found = 0;
                 for (i = 0; i < slots_found; i++) {
                         struct radix_tree_node *slot;
@@ -944,6 +948,7 @@ EXPORT_SYMBOL(radix_tree_gang_lookup);
  *      radix_tree_gang_lookup_slot - perform multiple slot lookup on radix tree
  *      @root:          radix tree root
  *      @results:       where the results of the lookup are placed
+ *      @indices:       where their indices should be placed (but usually NULL)
  *      @first_index:   start the lookup from this key
  *      @max_items:     place up to this many items at *results
  *
@@ -958,7 +963,8 @@ EXPORT_SYMBOL(radix_tree_gang_lookup);
  *      protection, radix_tree_deref_slot may fail requiring a retry.
  */
 unsigned int
-radix_tree_gang_lookup_slot(struct radix_tree_root *root, void ***results,
+radix_tree_gang_lookup_slot(struct radix_tree_root *root,
+                        void ***results, unsigned long *indices,
                         unsigned long first_index, unsigned int max_items)
 {
         unsigned long max_index;
@@ -974,6 +980,8 @@ radix_tree_gang_lookup_slot(struct radix_tree_root *root, void ***results,
                 if (first_index > 0)
                         return 0;
                 results[0] = (void **)&root->rnode;
+                if (indices)
+                        indices[0] = 0;
                 return 1;
         }
         node = indirect_to_ptr(node);
@@ -987,8 +995,9 @@ radix_tree_gang_lookup_slot(struct radix_tree_root *root, void ***results,
 
                 if (cur_index > max_index)
                         break;
-                slots_found = __lookup(node, results + ret, cur_index,
-                                        max_items - ret, &next_index);
+                slots_found = __lookup(node, results + ret,
+                                indices ? indices + ret : NULL,
+                                cur_index, max_items - ret, &next_index);
                 ret += slots_found;
                 if (next_index == 0)
                         break;