exofs: Write sbi->s_nextid as part of the Create command

Before when creating a new inode, we'd set the sb->s_dirt flag,
and sometime later the system would write out s_nextid as part
of the sb_info. Also on inode sync we would force the sb sync
as well.

Define the s_nextid as a new partition attribute and set it
every time we create a new object.
At mount we read it from it's new place.

We now never set sb->s_dirt anywhere in exofs. write_super
is actually never called. The call to exofs_write_super from
exofs_put_super is also removed because the VFS always calls
->sync_fs before calling ->put_super twice.

To stay backward-and-forward compatible we also write the old
s_nextid in the super_block object at unmount, and support zero
length attribute on mount.

This also fixes a BUG where in layouts when group_width was not
a divisor of EXOFS_SUPER_ID (0x10000) the s_nextid was not read
from the device it was written to. Because of the sliding window
layout trick, and because the read was always done from the 0
device but the write was done via the raid engine that might slide
the device view. Now we read and write through the raid engine.

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

1 files changed, 16 insertions, 2 deletions

diff --git a/fs/exofs/common.h b/fs/exofs/common.h
index f0d520312d8b..5e74ad3d4009 100644
--- a/fs/exofs/common.h
+++ b/fs/exofs/common.h
@@ -53,10 +53,14 @@
 #define EXOFS_ROOT_ID   0x10002 /* object ID for root directory */
 
 /* exofs Application specific page/attribute */
+/* Inode attrs */
 # define EXOFS_APAGE_FS_DATA    (OSD_APAGE_APP_DEFINED_FIRST + 3)
 # define EXOFS_ATTR_INODE_DATA  1
 # define EXOFS_ATTR_INODE_FILE_LAYOUT   2
 # define EXOFS_ATTR_INODE_DIR_LAYOUT    3
+/* Partition attrs */
+# define EXOFS_APAGE_SB_DATA    (0xF0000000U + 3)
+# define EXOFS_ATTR_SB_STATS    1
 
 /*
  * The maximum number of files we can have is limited by the size of the
@@ -86,8 +90,8 @@ enum {
  */
 enum {EXOFS_FSCB_VER = 1, EXOFS_DT_VER = 1};
 struct exofs_fscb {
-        __le64  s_nextid;       /* Highest object ID used */
-        __le64  s_numfiles;     /* Number of files on fs */
+        __le64  s_nextid;       /* Only used after mkfs */
+        __le64  s_numfiles;     /* Only used after mkfs */
         __le32  s_version;      /* == EXOFS_FSCB_VER */
         __le16  s_magic;        /* Magic signature */
         __le16  s_newfs;        /* Non-zero if this is a new fs */
@@ -98,6 +102,16 @@ struct exofs_fscb {
 } __packed;
 
 /*
+ * This struct is set on the FS partition's attributes.
+ * [EXOFS_APAGE_SB_DATA, EXOFS_ATTR_SB_STATS] and is written together
+ * with the create command, to atomically persist the sb writeable information.
+ */
+struct exofs_sb_stats {
+        __le64  s_nextid;       /* Highest object ID used */
+        __le64  s_numfiles;     /* Number of files on fs */
+} __packed;
+
+/*
  * Describes the raid used in the FS. It is part of the device table.
  * This here is taken from the pNFS-objects definition. In exofs we
  * use one raid policy through-out the filesystem. (NOTE: the funny