btrfs: Drop EXTENT_UPTODATE check in hole punching and direct locking

In these instances, we are trying to determine if a page has been accessed
since we began the operation for the sake of retry.  This is easily
accomplished by doing a gang lookup in the page mapping radix tree, and it
saves us the dependency on the flag (so that we might eventually delete
it).

btrfs_page_exists_in_range borrows heavily from find_get_page, replacing
the radix tree look up with a gang lookup of 1, so that we can find the
next highest page >= index and see if it falls into our lock range.

Signed-off-by: Chris Mason <clm@fb.com>
Signed-off-by: Alex Gartrell <agartrell@fb.com>

diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index c9a24444ec9a317483c4486fb132b6893f57a19d..a0cf3e56fe20007c8cc1178a97dc734765ecdac7 100644 (file)
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -284,4 +284,6 @@ static inline void btrfs_inode_resume_unlocked_dio(struct inode *inode)
                  &BTRFS_I(inode)->runtime_flags);
 }
 
+bool btrfs_page_exists_in_range(struct inode *inode, loff_t start, loff_t end);
+
 #endif

diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 8accf94ef220515965e634d7ce759cae7a4f4eb9..e46bfaf6cde21d022f6376d2e45d0300d4e1e5a9 100644 (file)
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -2266,9 +2266,7 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
                if ((!ordered ||
                    (ordered->file_offset + ordered->len <= lockstart ||
                     ordered->file_offset > lockend)) &&
-                    !test_range_bit(&BTRFS_I(inode)->io_tree, lockstart,
-                                    lockend, EXTENT_UPTODATE, 0,
-                                    cached_state)) {
+                    !btrfs_page_exists_in_range(inode, lockstart, lockend)) {
                        if (ordered)
                                btrfs_put_ordered_extent(ordered);
                        break;

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 0b8ce3002cfe36c1190e224ab5731aec31d55fe9..a462da1a3e6a0bb0f33ab1ac0ef43279a3b278ea 100644 (file)
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -6735,6 +6735,71 @@ out:
        return ret;
 }
 
+bool btrfs_page_exists_in_range(struct inode *inode, loff_t start, loff_t end)
+{
+       struct radix_tree_root *root = &inode->i_mapping->page_tree;
+       int found = false;
+       void **pagep = NULL;
+       struct page *page = NULL;
+       int start_idx;
+       int end_idx;
+
+       start_idx = start >> PAGE_CACHE_SHIFT;
+
+       /*
+        * end is the last byte in the last page.  end == start is legal
+        */
+       end_idx = end >> PAGE_CACHE_SHIFT;
+
+       rcu_read_lock();
+
+       /* Most of the code in this while loop is lifted from
+        * find_get_page.  It's been modified to begin searching from a
+        * page and return just the first page found in that range.  If the
+        * found idx is less than or equal to the end idx then we know that
+        * a page exists.  If no pages are found or if those pages are
+        * outside of the range then we're fine (yay!) */
+       while (page == NULL &&
+              radix_tree_gang_lookup_slot(root, &pagep, NULL, start_idx, 1)) {
+               page = radix_tree_deref_slot(pagep);
+               if (unlikely(!page))
+                       break;
+
+               if (radix_tree_exception(page)) {
+                       if (radix_tree_deref_retry(page))
+                               continue;
+                       /*
+                        * Otherwise, shmem/tmpfs must be storing a swap entry
+                        * here as an exceptional entry: so return it without
+                        * attempting to raise page count.
+                        */
+                       break; /* TODO: Is this relevant for this use case? */
+               }
+
+               if (!page_cache_get_speculative(page))
+                       continue;
+
+               /*
+                * Has the page moved?
+                * This is part of the lockless pagecache protocol. See
+                * include/linux/pagemap.h for details.
+                */
+               if (unlikely(page != *pagep)) {
+                       page_cache_release(page);
+                       page = NULL;
+               }
+       }
+
+       if (page) {
+               if (page->index <= end_idx)
+                       found = true;
+               page_cache_release(page);
+       }
+
+       rcu_read_unlock();
+       return found;
+}
+
 static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend,
                              struct extent_state **cached_state, int writing)
 {
@@ -6759,10 +6824,9 @@ static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend,
                 * invalidate needs to happen so that reads after a write do not
                 * get stale data.
                 */
-               if (!ordered && (!writing ||
-                   !test_range_bit(&BTRFS_I(inode)->io_tree,
-                                   lockstart, lockend, EXTENT_UPTODATE, 0,
-                                   *cached_state)))
+               if (!ordered &&
+                   (!writing ||
+                    !btrfs_page_exists_in_range(inode, lockstart, lockend)))
                        break;
 
                unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend,