exofs: Define on-disk per-inode optional layout attribute

* Layouts describe the way a file is spread on multiple devices.
  The layout information is stored in the objects attribute introduced
  in this patch.

* There can be multiple generating function for the layout.
  Currently defined:
    - No attribute present - use below moving-window on global
      device table, all devices.
      (This is the only one currently used in exofs)
    - an obj_id generated moving window - the obj_id is a randomizing
      factor in the otherwise global map layout.
    - An explicit layout stored, including a data_map and a device
      index list.
    - More might be defined in future ...

* There are two attributes defined of the same structure:
  A-data-files-layout - This layout is used by data-files. If present
                        at a directory, all files of that directory will
                        be created with this layout.
  A-meta-data-layout - This layout is used by a directory and other
                       meta-data information. Also inherited at creation
                       of subdirectories.

* At creation time inodes are created with the layout specified above.
  A usermode utility may change the creation layout on a give directory
  or file. Which in the case of directories, will also apply to newly
  created files/subdirectories, children of that directory.
  In the simple unaltered case of a newly created exofs, no layout
  attributes are present, and all layouts adhere to the layout specified
  at the device-table.

* In case of a future file system loaded in an old exofs-driver.
  At iget(), the generating_function is inspected and if not supported
  will return an IO error to the application and the inode will not
  be loaded. So not to damage any data.
  Note: After this patch we do not yet support any type of layout
        only the RAID0 patch that enables striping at the super-block
        level will add support for RAID0 layouts above. This way we
        are past and future compatible and fully bisectable.

* Access to the device table is done by an accessor since
  it will change according to above information.

Signed-off-by: Boaz Harrosh <bharrosh@panasas.com>

1 files changed, 51 insertions, 5 deletions

diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
index 03189a958b33..0163546ba05a 100644
--- a/fs/exofs/inode.c
+++ b/fs/exofs/inode.c
@@ -859,6 +859,15 @@ int exofs_setattr(struct dentry *dentry, struct iattr *iattr)
         return error;
 }
 
+static const struct osd_attr g_attr_inode_file_layout = ATTR_DEF(
+        EXOFS_APAGE_FS_DATA,
+        EXOFS_ATTR_INODE_FILE_LAYOUT,
+        0);
+static const struct osd_attr g_attr_inode_dir_layout = ATTR_DEF(
+        EXOFS_APAGE_FS_DATA,
+        EXOFS_ATTR_INODE_DIR_LAYOUT,
+        0);
+
 /*
  * Read an inode from the OSD, and return it as is.  We also return the size
  * attribute in the 'obj_size' argument.
@@ -867,11 +876,16 @@ static int exofs_get_inode(struct super_block *sb, struct exofs_i_info *oi,
                     struct exofs_fcb *inode, uint64_t *obj_size)
 {
         struct exofs_sb_info *sbi = sb->s_fs_info;
-        struct osd_attr attrs[2];
+        struct osd_attr attrs[] = {
+                [0] = g_attr_inode_data,
+                [1] = g_attr_inode_file_layout,
+                [2] = g_attr_inode_dir_layout,
+                [3] = g_attr_logical_length,
+        };
         struct exofs_io_state *ios;
+        struct exofs_on_disk_inode_layout *layout;
         int ret;
 
-        *obj_size = ~0;
         ret = exofs_get_io_state(&sbi->layout, &ios);
         if (unlikely(ret)) {
                 EXOFS_ERR("%s: exofs_get_io_state failed.\n", __func__);
@@ -882,8 +896,9 @@ static int exofs_get_inode(struct super_block *sb, struct exofs_i_info *oi,
         exofs_make_credential(oi->i_cred, &ios->obj);
         ios->cred = oi->i_cred;
 
-        attrs[0] = g_attr_inode_data;
-        attrs[1] = g_attr_logical_length;
+        attrs[1].len = exofs_on_disk_inode_layout_size(sbi->layout.s_numdevs);
+        attrs[2].len = exofs_on_disk_inode_layout_size(sbi->layout.s_numdevs);
+
         ios->in_attr = attrs;
         ios->in_attr_len = ARRAY_SIZE(attrs);
 
@@ -901,11 +916,42 @@ static int exofs_get_inode(struct super_block *sb, struct exofs_i_info *oi,
 
         ret = extract_attr_from_ios(ios, &attrs[1]);
         if (ret) {
+                EXOFS_ERR("%s: extract_attr of inode_data failed\n", __func__);
+                goto out;
+        }
+        if (attrs[1].len) {
+                layout = attrs[1].val_ptr;
+                if (layout->gen_func != cpu_to_le16(LAYOUT_MOVING_WINDOW)) {
+                        EXOFS_ERR("%s: unsupported files layout %d\n",
+                                __func__, layout->gen_func);
+                        ret = -ENOTSUPP;
+                        goto out;
+                }
+        }
+
+        ret = extract_attr_from_ios(ios, &attrs[2]);
+        if (ret) {
+                EXOFS_ERR("%s: extract_attr of inode_data failed\n", __func__);
+                goto out;
+        }
+        if (attrs[2].len) {
+                layout = attrs[2].val_ptr;
+                if (layout->gen_func != cpu_to_le16(LAYOUT_MOVING_WINDOW)) {
+                        EXOFS_ERR("%s: unsupported meta-data layout %d\n",
+                                __func__, layout->gen_func);
+                        ret = -ENOTSUPP;
+                        goto out;
+                }
+        }
+
+        *obj_size = ~0;
+        ret = extract_attr_from_ios(ios, &attrs[3]);
+        if (ret) {
                 EXOFS_ERR("%s: extract_attr of logical_length failed\n",
                           __func__);
                 goto out;
         }
-        *obj_size = get_unaligned_be64(attrs[1].val_ptr);
+        *obj_size = get_unaligned_be64(attrs[3].val_ptr);
 
 out:
         exofs_put_io_state(ios);