Btrfs: fix unexpected return value of fiemap

[cascardo/linux.git] / fs / btrfs / extent_io.c

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index d247fc0..f661688 100644 (file)
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -3200,14 +3200,10 @@ int extent_read_full_page(struct extent_io_tree *tree, struct page *page,
        return ret;
 }
 
-static noinline void update_nr_written(struct page *page,
-                                     struct writeback_control *wbc,
-                                     unsigned long nr_written)
+static void update_nr_written(struct page *page, struct writeback_control *wbc,
+                             unsigned long nr_written)
 {
        wbc->nr_to_write -= nr_written;
-       if (wbc->range_cyclic || (wbc->nr_to_write > 0 &&
-           wbc->range_start == 0 && wbc->range_end == LLONG_MAX))
-               page->mapping->writeback_index = page->index + nr_written;
 }
 
 /*
@@ -3368,6 +3364,8 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 
        while (cur <= end) {
                u64 em_end;
+               unsigned long max_nr;
+
                if (cur >= i_size) {
                        if (tree->ops && tree->ops->writepage_end_io_hook)
                                tree->ops->writepage_end_io_hook(page, cur,
@@ -3423,32 +3421,23 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
                        continue;
                }
 
-               if (tree->ops && tree->ops->writepage_io_hook) {
-                       ret = tree->ops->writepage_io_hook(page, cur,
-                                               cur + iosize - 1);
-               } else {
-                       ret = 0;
+               max_nr = (i_size >> PAGE_SHIFT) + 1;
+
+               set_range_writeback(tree, cur, cur + iosize - 1);
+               if (!PageWriteback(page)) {
+                       btrfs_err(BTRFS_I(inode)->root->fs_info,
+                                  "page %lu not writeback, cur %llu end %llu",
+                              page->index, cur, end);
                }
-               if (ret) {
-                       SetPageError(page);
-               } else {
-                       unsigned long max_nr = (i_size >> PAGE_SHIFT) + 1;
 
-                       set_range_writeback(tree, cur, cur + iosize - 1);
-                       if (!PageWriteback(page)) {
-                               btrfs_err(BTRFS_I(inode)->root->fs_info,
-                                          "page %lu not writeback, cur %llu end %llu",
-                                      page->index, cur, end);
-                       }
+               ret = submit_extent_page(write_flags, tree, wbc, page,
+                                        sector, iosize, pg_offset,
+                                        bdev, &epd->bio, max_nr,
+                                        end_bio_extent_writepage,
+                                        0, 0, 0, false);
+               if (ret)
+                       SetPageError(page);
 
-                       ret = submit_extent_page(write_flags, tree, wbc, page,
-                                                sector, iosize, pg_offset,
-                                                bdev, &epd->bio, max_nr,
-                                                end_bio_extent_writepage,
-                                                0, 0, 0, false);
-                       if (ret)
-                               SetPageError(page);
-               }
                cur = cur + iosize;
                pg_offset += iosize;
                nr++;
@@ -3920,12 +3909,13 @@ static int extent_write_cache_pages(struct extent_io_tree *tree,
        struct inode *inode = mapping->host;
        int ret = 0;
        int done = 0;
-       int err = 0;
        int nr_to_write_done = 0;
        struct pagevec pvec;
        int nr_pages;
        pgoff_t index;
        pgoff_t end;            /* Inclusive */
+       pgoff_t done_index;
+       int range_whole = 0;
        int scanned = 0;
        int tag;
 
@@ -3948,6 +3938,8 @@ static int extent_write_cache_pages(struct extent_io_tree *tree,
        } else {
                index = wbc->range_start >> PAGE_SHIFT;
                end = wbc->range_end >> PAGE_SHIFT;
+               if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
+                       range_whole = 1;
                scanned = 1;
        }
        if (wbc->sync_mode == WB_SYNC_ALL)
@@ -3957,6 +3949,7 @@ static int extent_write_cache_pages(struct extent_io_tree *tree,
 retry:
        if (wbc->sync_mode == WB_SYNC_ALL)
                tag_pages_for_writeback(mapping, index, end);
+       done_index = index;
        while (!done && !nr_to_write_done && (index <= end) &&
               (nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
                        min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1))) {
@@ -3966,6 +3959,7 @@ retry:
                for (i = 0; i < nr_pages; i++) {
                        struct page *page = pvec.pages[i];
 
+                       done_index = page->index;
                        /*
                         * At this point we hold neither mapping->tree_lock nor
                         * lock on the page itself: the page may be truncated or
@@ -4007,8 +4001,20 @@ retry:
                                unlock_page(page);
                                ret = 0;
                        }
-                       if (!err && ret < 0)
-                               err = ret;
+                       if (ret < 0) {
+                               /*
+                                * done_index is set past this page,
+                                * so media errors will not choke
+                                * background writeout for the entire
+                                * file. This has consequences for
+                                * range_cyclic semantics (ie. it may
+                                * not be suitable for data integrity
+                                * writeout).
+                                */
+                               done_index = page->index + 1;
+                               done = 1;
+                               break;
+                       }
 
                        /*
                         * the filesystem may choose to bump up nr_to_write.
@@ -4020,7 +4026,7 @@ retry:
                pagevec_release(&pvec);
                cond_resched();
        }
-       if (!scanned && !done && !err) {
+       if (!scanned && !done) {
                /*
                 * We hit the last page and there is more work to be done: wrap
                 * back to the start of the file
@@ -4029,8 +4035,12 @@ retry:
                index = 0;
                goto retry;
        }
+
+       if (wbc->range_cyclic || (wbc->nr_to_write > 0 && range_whole))
+               mapping->writeback_index = done_index;
+
        btrfs_add_delayed_iput(inode);
-       return err;
+       return ret;
 }
 
 static void flush_epd_write_bio(struct extent_page_data *epd)
@@ -4379,8 +4389,12 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
        if (ret < 0) {
                btrfs_free_path(path);
                return ret;
+       } else {
+               WARN_ON(!ret);
+               if (ret == 1)
+                       ret = 0;
        }
-       WARN_ON(!ret);
+
        path->slots[0]--;
        btrfs_item_key_to_cpu(path->nodes[0], &found_key, path->slots[0]);
        found_type = found_key.type;
@@ -4822,7 +4836,7 @@ struct extent_buffer *alloc_test_extent_buffer(struct btrfs_fs_info *fs_info,
                return NULL;
        eb->fs_info = fs_info;
 again:
-       ret = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM);
+       ret = radix_tree_preload(GFP_NOFS);
        if (ret)
                goto free_eb;
        spin_lock(&fs_info->buffer_lock);
@@ -4923,7 +4937,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
        if (uptodate)
                set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
 again:
-       ret = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM);
+       ret = radix_tree_preload(GFP_NOFS);
        if (ret)
                goto free_eb;