Btrfs: fix fiemap bugs with delalloc

The Btrfs fiemap code wasn't properly returning delalloc extents,
so applications that trust fiemap to decide if there are holes in the
file see holes instead of delalloc.

This reworks the btrfs fiemap code, adding a get_extent helper that
searches for delalloc ranges and also adding a helper for extent_fiemap
that skips past holes in the file.

Signed-off-by: Chris Mason <chris.mason@oracle.com>

1 files changed, 124 insertions, 2 deletions

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 8d392ed73d57..44b926646e33 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1913,7 +1913,7 @@ static int btrfs_clean_io_failures(struct inode *inode, u64 start)
 
         private = 0;
         if (count_range_bits(&BTRFS_I(inode)->io_failure_tree, &private,
-                             (u64)-1, 1, EXTENT_DIRTY)) {
+                             (u64)-1, 1, EXTENT_DIRTY, 0)) {
                 ret = get_state_private(&BTRFS_I(inode)->io_failure_tree,
                                         start, &private_failure);
                 if (ret == 0) {
@@ -5282,6 +5282,128 @@ out:
         return em;
 }
 
+struct extent_map *btrfs_get_extent_fiemap(struct inode *inode, struct page *page,
+                                           size_t pg_offset, u64 start, u64 len,
+                                           int create)
+{
+        struct extent_map *em;
+        struct extent_map *hole_em = NULL;
+        u64 range_start = start;
+        u64 end;
+        u64 found;
+        u64 found_end;
+        int err = 0;
+
+        em = btrfs_get_extent(inode, page, pg_offset, start, len, create);
+        if (IS_ERR(em))
+                return em;
+        if (em) {
+                /*
+                 * if our em maps to a hole, there might
+                 * actually be delalloc bytes behind it
+                 */
+                if (em->block_start != EXTENT_MAP_HOLE)
+                        return em;
+                else
+                        hole_em = em;
+        }
+
+        /* check to see if we've wrapped (len == -1 or similar) */
+        end = start + len;
+        if (end < start)
+                end = (u64)-1;
+        else
+                end -= 1;
+
+        em = NULL;
+
+        /* ok, we didn't find anything, lets look for delalloc */
+        found = count_range_bits(&BTRFS_I(inode)->io_tree, &range_start,
+                                 end, len, EXTENT_DELALLOC, 1);
+        found_end = range_start + found;
+        if (found_end < range_start)
+                found_end = (u64)-1;
+
+        /*
+         * we didn't find anything useful, return
+         * the original results from get_extent()
+         */
+        if (range_start > end || found_end <= start) {
+                em = hole_em;
+                hole_em = NULL;
+                goto out;
+        }
+
+        /* adjust the range_start to make sure it doesn't
+         * go backwards from the start they passed in
+         */
+        range_start = max(start,range_start);
+        found = found_end - range_start;
+
+        if (found > 0) {
+                u64 hole_start = start;
+                u64 hole_len = len;
+
+                em = alloc_extent_map(GFP_NOFS);
+                if (!em) {
+                        err = -ENOMEM;
+                        goto out;
+                }
+                /*
+                 * when btrfs_get_extent can't find anything it
+                 * returns one huge hole
+                 *
+                 * make sure what it found really fits our range, and
+                 * adjust to make sure it is based on the start from
+                 * the caller
+                 */
+                if (hole_em) {
+                        u64 calc_end = extent_map_end(hole_em);
+
+                        if (calc_end <= start || (hole_em->start > end)) {
+                                free_extent_map(hole_em);
+                                hole_em = NULL;
+                        } else {
+                                hole_start = max(hole_em->start, start);
+                                hole_len = calc_end - hole_start;
+                        }
+                }
+                em->bdev = NULL;
+                if (hole_em && range_start > hole_start) {
+                        /* our hole starts before our delalloc, so we
+                         * have to return just the parts of the hole
+                         * that go until  the delalloc starts
+                         */
+                        em->len = min(hole_len,
+                                      range_start - hole_start);
+                        em->start = hole_start;
+                        em->orig_start = hole_start;
+                        /*
+                         * don't adjust block start at all,
+                         * it is fixed at EXTENT_MAP_HOLE
+                         */
+                        em->block_start = hole_em->block_start;
+                        em->block_len = hole_len;
+                } else {
+                        em->start = range_start;
+                        em->len = found;
+                        em->orig_start = range_start;
+                        em->block_start = EXTENT_MAP_DELALLOC;
+                        em->block_len = found;
+                }
+        } else if (hole_em) {
+                return hole_em;
+        }
+out:
+
+        free_extent_map(hole_em);
+        if (err) {
+                free_extent_map(em);
+                return ERR_PTR(err);
+        }
+        return em;
+}
+
 static struct extent_map *btrfs_new_extent_direct(struct inode *inode,
                                                   u64 start, u64 len)
 {
@@ -6104,7 +6226,7 @@ out:
 static int btrfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
                 __u64 start, __u64 len)
 {
-        return extent_fiemap(inode, fieinfo, start, len, btrfs_get_extent);
+        return extent_fiemap(inode, fieinfo, start, len, btrfs_get_extent_fiemap);
 }
 
 int btrfs_readpage(struct file *file, struct page *page)