btrfs: tree-checker: Check level for leaves and nodes

[sagit-ice-cold/kernel_xiaomi_msm8998.git] / fs / btrfs / file.c

diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 72e7346..0529736 100644 (file)
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1291,7 +1291,8 @@ out:
  * on error we return an unlocked page and the error value
  * on success we return a locked page and 0
  */
-static int prepare_uptodate_page(struct page *page, u64 pos,
+static int prepare_uptodate_page(struct inode *inode,
+                                struct page *page, u64 pos,
                                 bool force_uptodate)
 {
        int ret = 0;
@@ -1306,6 +1307,10 @@ static int prepare_uptodate_page(struct page *page, u64 pos,
                        unlock_page(page);
                        return -EIO;
                }
+               if (page->mapping != inode->i_mapping) {
+                       unlock_page(page);
+                       return -EAGAIN;
+               }
        }
        return 0;
 }
@@ -1324,6 +1329,7 @@ static noinline int prepare_pages(struct inode *inode, struct page **pages,
        int faili;
 
        for (i = 0; i < num_pages; i++) {
+again:
                pages[i] = find_or_create_page(inode->i_mapping, index + i,
                                               mask | __GFP_WRITE);
                if (!pages[i]) {
@@ -1333,13 +1339,17 @@ static noinline int prepare_pages(struct inode *inode, struct page **pages,
                }
 
                if (i == 0)
-                       err = prepare_uptodate_page(pages[i], pos,
+                       err = prepare_uptodate_page(inode, pages[i], pos,
                                                    force_uptodate);
-               if (i == num_pages - 1)
-                       err = prepare_uptodate_page(pages[i],
+               if (!err && i == num_pages - 1)
+                       err = prepare_uptodate_page(inode, pages[i],
                                                    pos + write_bytes, false);
                if (err) {
                        page_cache_release(pages[i]);
+                       if (err == -EAGAIN) {
+                               err = 0;
+                               goto again;
+                       }
                        faili = i - 1;
                        goto fail;
                }
@@ -1516,27 +1526,24 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 
                reserve_bytes = num_pages << PAGE_CACHE_SHIFT;
 
-               if (BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
-                                            BTRFS_INODE_PREALLOC)) {
-                       ret = check_can_nocow(inode, pos, &write_bytes);
-                       if (ret < 0)
-                               break;
-                       if (ret > 0) {
-                               /*
-                                * For nodata cow case, no need to reserve
-                                * data space.
-                                */
-                               only_release_metadata = true;
-                               /*
-                                * our prealloc extent may be smaller than
-                                * write_bytes, so scale down.
-                                */
-                               num_pages = DIV_ROUND_UP(write_bytes + offset,
-                                                        PAGE_CACHE_SIZE);
-                               reserve_bytes = num_pages << PAGE_CACHE_SHIFT;
-                               goto reserve_metadata;
-                       }
+               if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
+                                             BTRFS_INODE_PREALLOC)) &&
+                   check_can_nocow(inode, pos, &write_bytes) > 0) {
+                       /*
+                        * For nodata cow case, no need to reserve
+                        * data space.
+                        */
+                       only_release_metadata = true;
+                       /*
+                        * our prealloc extent may be smaller than
+                        * write_bytes, so scale down.
+                        */
+                       num_pages = DIV_ROUND_UP(write_bytes + offset,
+                                                PAGE_CACHE_SIZE);
+                       reserve_bytes = num_pages << PAGE_CACHE_SHIFT;
+                       goto reserve_metadata;
                }
+
                ret = btrfs_check_data_free_space(inode, pos, write_bytes);
                if (ret < 0)
                        break;
@@ -1854,10 +1861,19 @@ int btrfs_release_file(struct inode *inode, struct file *filp)
 static int start_ordered_ops(struct inode *inode, loff_t start, loff_t end)
 {
        int ret;
+       struct blk_plug plug;
 
+       /*
+        * This is only called in fsync, which would do synchronous writes, so
+        * a plug can merge adjacent IOs as much as possible.  Esp. in case of
+        * multiple disks using raid profile, a large IO can be split to
+        * several segments of stripe length (currently 64K).
+        */
+       blk_start_plug(&plug);
        atomic_inc(&BTRFS_I(inode)->sync_writers);
        ret = btrfs_fdatawrite_range(inode, start, end);
        atomic_dec(&BTRFS_I(inode)->sync_writers);
+       blk_finish_plug(&plug);
 
        return ret;
 }
@@ -1875,7 +1891,7 @@ static int start_ordered_ops(struct inode *inode, loff_t start, loff_t end)
  */
 int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 {
-       struct dentry *dentry = file->f_path.dentry;
+       struct dentry *dentry = file_dentry(file);
        struct inode *inode = d_inode(dentry);
        struct btrfs_root *root = BTRFS_I(inode)->root;
        struct btrfs_trans_handle *trans;
@@ -2764,7 +2780,7 @@ static long btrfs_fallocate(struct file *file, int mode,
                if (!ret)
                        ret = btrfs_prealloc_file_range(inode, mode,
                                        range->start,
-                                       range->len, 1 << inode->i_blkbits,
+                                       range->len, i_blocksize(inode),
                                        offset + len, &alloc_hint);
                list_del(&range->list);
                kfree(range);