radix-tree: use iterators in find_get_pages* functions

Replace radix_tree_gang_lookup_slot() and
radix_tree_gang_lookup_tag_slot() in page-cache lookup functions with
brand-new radix-tree direct iterating.  This avoids the double-scanning
and pointer copying.

Iterator don't stop after nr_pages page-get fails in a row, it continue
lookup till the radix-tree end.  Thus we can safely remove these restart
conditions.

Unfortunately, old implementation didn't forbid nr_pages == 0, this corner
case does not fit into new code, so the patch adds an extra check at the
beginning.

Signed-off-by: Konstantin Khlebnikov <khlebnikov@openvz.org>
Tested-by: Hugh Dickins <hughd@google.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/filemap.c b/mm/filemap.c
index c3811bc..79c4b2b 100644 (file)
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -813,20 +813,19 @@ EXPORT_SYMBOL(find_or_create_page);
 unsigned find_get_pages(struct address_space *mapping, pgoff_t start,
                            unsigned int nr_pages, struct page **pages)
 {
-       unsigned int i;
-       unsigned int ret;
-       unsigned int nr_found, nr_skip;
+       struct radix_tree_iter iter;
+       void **slot;
+       unsigned ret = 0;
+
+       if (unlikely(!nr_pages))
+               return 0;
 
        rcu_read_lock();
 restart:
-       nr_found = radix_tree_gang_lookup_slot(&mapping->page_tree,
-                               (void ***)pages, NULL, start, nr_pages);
-       ret = 0;
-       nr_skip = 0;
-       for (i = 0; i < nr_found; i++) {
+       radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) {
                struct page *page;
 repeat:
-               page = radix_tree_deref_slot((void **)pages[i]);
+               page = radix_tree_deref_slot(slot);
                if (unlikely(!page))
                        continue;
 
@@ -837,7 +836,7 @@ repeat:
                                 * when entry at index 0 moves out of or back
                                 * to root: none yet gotten, safe to restart.
                                 */
-                               WARN_ON(start | i);
+                               WARN_ON(iter.index);
                                goto restart;
                        }
                        /*
@@ -845,7 +844,6 @@ repeat:
                         * here as an exceptional entry: so skip over it -
                         * we only reach this from invalidate_mapping_pages().
                         */
-                       nr_skip++;
                        continue;
                }
 
@@ -853,21 +851,16 @@ repeat:
                        goto repeat;
 
                /* Has the page moved? */
-               if (unlikely(page != *((void **)pages[i]))) {
+               if (unlikely(page != *slot)) {
                        page_cache_release(page);
                        goto repeat;
                }
 
                pages[ret] = page;
-               ret++;
+               if (++ret == nr_pages)
+                       break;
        }
 
-       /*
-        * If all entries were removed before we could secure them,
-        * try again, because callers stop trying once 0 is returned.
-        */
-       if (unlikely(!ret && nr_found > nr_skip))
-               goto restart;
        rcu_read_unlock();
        return ret;
 }
@@ -887,21 +880,22 @@ repeat:
 unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index,
                               unsigned int nr_pages, struct page **pages)
 {
-       unsigned int i;
-       unsigned int ret;
-       unsigned int nr_found;
+       struct radix_tree_iter iter;
+       void **slot;
+       unsigned int ret = 0;
+
+       if (unlikely(!nr_pages))
+               return 0;
 
        rcu_read_lock();
 restart:
-       nr_found = radix_tree_gang_lookup_slot(&mapping->page_tree,
-                               (void ***)pages, NULL, index, nr_pages);
-       ret = 0;
-       for (i = 0; i < nr_found; i++) {
+       radix_tree_for_each_contig(slot, &mapping->page_tree, &iter, index) {
                struct page *page;
 repeat:
-               page = radix_tree_deref_slot((void **)pages[i]);
+               page = radix_tree_deref_slot(slot);
+               /* The hole, there no reason to continue */
                if (unlikely(!page))
-                       continue;
+                       break;
 
                if (radix_tree_exception(page)) {
                        if (radix_tree_deref_retry(page)) {
@@ -924,7 +918,7 @@ repeat:
                        goto repeat;
 
                /* Has the page moved? */
-               if (unlikely(page != *((void **)pages[i]))) {
+               if (unlikely(page != *slot)) {
                        page_cache_release(page);
                        goto repeat;
                }
@@ -934,14 +928,14 @@ repeat:
                 * otherwise we can get both false positives and false
                 * negatives, which is just confusing to the caller.
                 */
-               if (page->mapping == NULL || page->index != index) {
+               if (page->mapping == NULL || page->index != iter.index) {
                        page_cache_release(page);
                        break;
                }
 
                pages[ret] = page;
-               ret++;
-               index++;
+               if (++ret == nr_pages)
+                       break;
        }
        rcu_read_unlock();
        return ret;
@@ -962,19 +956,20 @@ EXPORT_SYMBOL(find_get_pages_contig);
 unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index,
                        int tag, unsigned int nr_pages, struct page **pages)
 {
-       unsigned int i;
-       unsigned int ret;
-       unsigned int nr_found;
+       struct radix_tree_iter iter;
+       void **slot;
+       unsigned ret = 0;
+
+       if (unlikely(!nr_pages))
+               return 0;
 
        rcu_read_lock();
 restart:
-       nr_found = radix_tree_gang_lookup_tag_slot(&mapping->page_tree,
-                               (void ***)pages, *index, nr_pages, tag);
-       ret = 0;
-       for (i = 0; i < nr_found; i++) {
+       radix_tree_for_each_tagged(slot, &mapping->page_tree,
+                                  &iter, *index, tag) {
                struct page *page;
 repeat:
-               page = radix_tree_deref_slot((void **)pages[i]);
+               page = radix_tree_deref_slot(slot);
                if (unlikely(!page))
                        continue;
 
@@ -998,21 +993,16 @@ repeat:
                        goto repeat;
 
                /* Has the page moved? */
-               if (unlikely(page != *((void **)pages[i]))) {
+               if (unlikely(page != *slot)) {
                        page_cache_release(page);
                        goto repeat;
                }
 
                pages[ret] = page;
-               ret++;
+               if (++ret == nr_pages)
+                       break;
        }
 
-       /*
-        * If all entries were removed before we could secure them,
-        * try again, because callers stop trying once 0 is returned.
-        */
-       if (unlikely(!ret && nr_found))
-               goto restart;
        rcu_read_unlock();
 
        if (ret)