ocfs2: Add xattr bucket iteration for large numbers of EAs

Ocfs2 breaks up xattr index tree leaves into 4k regions, called buckets.
Attributes are stored within a given bucket, depending on hash value.

After a discussion with Mark, we decided that the per-bucket index
(xe_entry[]) would only exist in the 1st block of a bucket. Likewise,
name/value pairs will not straddle more than one block. This allows the
majority of operations to work directly on the buffer heads in a leaf block.

This patch adds code to iterate the buckets in an EA. A new abstration of
ocfs2_xattr_bucket is added. It records the bhs in this bucket and
ocfs2_xattr_header. This keeps the code neat, improving readibility.

Signed-off-by: Tao Ma <tao.ma@oracle.com>
Signed-off-by: Mark Fasheh <mfasheh@suse.com>

1 files changed, 33 insertions, 2 deletions

diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h
index 98e1f8bba0e1..8d5e72f2c5cf 100644
--- a/fs/ocfs2/ocfs2_fs.h
+++ b/fs/ocfs2/ocfs2_fs.h
@@ -755,8 +755,13 @@ struct ocfs2_xattr_header {
 	__le16	xh_count;                       /* contains the count of how
 						   many records are in the
 						   local xattr storage. */
-	__le16	xh_reserved1;
-	__le32	xh_reserved2;
+	__le16	xh_free_start;                  /* current offset for storing
+						   xattr. */
+	__le16	xh_name_value_len;              /* total length of name/value
+						   length in this bucket. */
+	__le16	xh_num_buckets;                 /* bucket nums in one extent
+						   record, only valid in the
+						   first bucket. */
 	__le64  xh_csum;
 	struct ocfs2_xattr_entry xh_entries[0]; /* xattr entry list. */
 };
@@ -793,6 +798,10 @@ struct ocfs2_xattr_tree_root {
 #define OCFS2_XATTR_SIZE(size)	(((size) + OCFS2_XATTR_ROUND) & \
 				~(OCFS2_XATTR_ROUND))
 
+#define OCFS2_XATTR_BUCKET_SIZE			4096
+#define OCFS2_XATTR_MAX_BLOCKS_PER_BUCKET 	(OCFS2_XATTR_BUCKET_SIZE \
+						 / OCFS2_MIN_BLOCKSIZE)
+
 /*
  * On disk structure for xattr block.
  */
@@ -963,6 +972,17 @@ static inline u64 ocfs2_backup_super_blkno(struct super_block *sb, int index)
 	return 0;
 
 }
+
+static inline u16 ocfs2_xattr_recs_per_xb(struct super_block *sb)
+{
+	int size;
+
+	size = sb->s_blocksize -
+		offsetof(struct ocfs2_xattr_block,
+			 xb_attrs.xb_root.xt_list.l_recs);
+
+	return size / sizeof(struct ocfs2_extent_rec);
+}
 #else
 static inline int ocfs2_fast_symlink_chars(int blocksize)
 {
@@ -1046,6 +1066,17 @@ static inline uint64_t ocfs2_backup_super_blkno(int blocksize, int index)
 
 	return 0;
 }
+
+static inline int ocfs2_xattr_recs_per_xb(int blocksize)
+{
+	int size;
+
+	size = blocksize -
+		offsetof(struct ocfs2_xattr_block,
+			 xb_attrs.xb_root.xt_list.l_recs);
+
+	return size / sizeof(struct ocfs2_extent_rec);
+}
 #endif  /* __KERNEL__ */