ext3-ea-in-inode-2.6-suse.patch

非常经典的一个分布式系统

+		    !memcmp(name, last->e_name, name_len)) {
+			memcpy(rentry, last, sizeof(struct ext3_xattr_entry));
+			ret = 0;
+		} else {
+			*free -= EXT3_XATTR_LEN(last->e_name_len);
+			*free -= le32_to_cpu(last->e_value_size);
+		}
+		last = next;
+	}
+	
+	brelse(iloc.bh);
+	return ret;
+}
+
+/*
+ * ext3_xattr_block_find()
+ *
+ * search attribute and calculate free space in EA block (if it allocated)
+ * NOTE: free space includes space our attribute hold
+ */
+int
+ext3_xattr_block_find(struct inode *inode, int name_index, const char *name,
+	       struct ext3_xattr_entry *rentry, int *free)
+{
+	struct buffer_head *bh = NULL;
+	struct ext3_xattr_entry *entry;
+	char *end;
+	int name_len, error = -ENOENT;
+
+	if (!EXT3_I(inode)->i_file_acl) {
+		*free = inode->i_sb->s_blocksize -
+			sizeof(struct ext3_xattr_header) -
+			sizeof(__u32);
+		return -ENOENT;
+	}
+	ea_idebug(inode, "reading block %d", EXT3_I(inode)->i_file_acl);
+	bh = sb_bread(inode->i_sb, EXT3_I(inode)->i_file_acl);
+	if (!bh)
+		return -EIO;
+	ea_bdebug(bh, "b_count=%d, refcount=%d",
+		atomic_read(&(bh->b_count)), le32_to_cpu(HDR(bh)->h_refcount));
+	end = bh->b_data + bh->b_size;
+	if (HDR(bh)->h_magic != cpu_to_le32(EXT3_XATTR_MAGIC) ||
+	    HDR(bh)->h_blocks != cpu_to_le32(1)) {
+bad_block:	ext3_error(inode->i_sb, "ext3_xattr_get",
+			"inode %ld: bad block %d", inode->i_ino,
+			EXT3_I(inode)->i_file_acl);
+		brelse(bh);
+		return -EIO;
+	}
+	/* find named attribute */
+	name_len = strlen(name);
+	*free = bh->b_size - sizeof(__u32);
+
+	entry = FIRST_ENTRY(bh);
+	while (!IS_LAST_ENTRY(entry)) {
+		struct ext3_xattr_entry *next =
+			EXT3_XATTR_NEXT(entry);
+		if ((char *)next >= end)
+			goto bad_block;
+		if (name_index == entry->e_name_index &&
+		    name_len == entry->e_name_len &&
+		    memcmp(name, entry->e_name, name_len) == 0) {
+			memcpy(rentry, entry, sizeof(struct ext3_xattr_entry));
+			error = 0;
+		} else {
+			*free -= EXT3_XATTR_LEN(entry->e_name_len);
+			*free -= le32_to_cpu(entry->e_value_size);
+		}
+		entry = next;
+	}
+	brelse(bh);
+
+	return error;
+}
+
+/*
+ * ext3_xattr_inode_set()
+ *
+ * this routine add/remove/replace attribute in inode body
+ */
+int
+ext3_xattr_ibody_set(handle_t *handle, struct inode *inode, int name_index,
+		      const char *name, const void *value, size_t value_len,
+		      int flags)
+{
+	struct ext3_xattr_entry *last, *next, *here = NULL;
+	struct ext3_inode *raw_inode;
+	int name_len = strlen(name);
+	int esize = EXT3_XATTR_LEN(name_len);
+	struct buffer_head *bh;
+	int err, storage_size;
+	struct ext3_iloc iloc;
+	int free, min_offs;
+	char *start, *end;
+	
+	if (EXT3_SB(inode->i_sb)->s_inode_size <= EXT3_GOOD_OLD_INODE_SIZE)
+		return -ENOSPC;
+
+	err = ext3_get_inode_loc(inode, &iloc, 0);
+	if (err)
+		return err;
+	raw_inode = ext3_raw_inode(&iloc);
+	bh = iloc.bh;
+
+	storage_size = EXT3_SB(inode->i_sb)->s_inode_size -
+				EXT3_GOOD_OLD_INODE_SIZE -
+				EXT3_I(inode)->i_extra_isize -
+				sizeof(__u32);
+	start = (char *) raw_inode + EXT3_GOOD_OLD_INODE_SIZE +
+			EXT3_I(inode)->i_extra_isize;
+	if ((*(__u32*) start) != EXT3_XATTR_MAGIC) {
+		/* inode had no attributes before */
+		*((__u32*) start) = cpu_to_le32(EXT3_XATTR_MAGIC);
+	}
+	start += sizeof(__u32);
+	end = (char *) raw_inode + EXT3_SB(inode->i_sb)->s_inode_size;
+	min_offs = storage_size;
+	free = storage_size - sizeof(__u32);
+
+	last = (struct ext3_xattr_entry *) start;	
+	while (!IS_LAST_ENTRY(last)) {
+		next = EXT3_XATTR_NEXT(last);
+		if (le32_to_cpu(last->e_value_size) > storage_size ||
+				(char *) next >= end) {
+			ext3_error(inode->i_sb, "ext3_xattr_ibody_set",
+				"inode %ld", inode->i_ino);
+			brelse(bh);
+			return -EIO;
+		}
+		
+		if (last->e_value_size) {
+			int offs = le16_to_cpu(last->e_value_offs);
+			if (offs < min_offs)
+				min_offs = offs;
+		}
+		if (name_index == last->e_name_index &&
+			name_len == last->e_name_len &&
+			!memcmp(name, last->e_name, name_len))
+			here = last;
+		else {
+			/* we calculate all but our attribute
+			 * because it will be removed before changing */
+			free -= EXT3_XATTR_LEN(last->e_name_len);
+			free -= le32_to_cpu(last->e_value_size);
+		}
+		last = next;
+	}
+
+	if (value && (esize + value_len > free)) {
+		brelse(bh);
+		return -ENOSPC;
+	}
+	
+	err = ext3_reserve_inode_write(handle, inode, &iloc);
+	if (err) {
+		brelse(bh);	
+		return err;
+	}
+
+	if (here) {
+		/* time to remove old value */
+		struct ext3_xattr_entry *e;
+		int size = le32_to_cpu(here->e_value_size);
+		int border = le16_to_cpu(here->e_value_offs);
+		char *src;
+
+		/* move tail */
+		memmove(start + min_offs + size, start + min_offs,
+				border - min_offs);
+
+		/* recalculate offsets */
+		e = (struct ext3_xattr_entry *) start;
+		while (!IS_LAST_ENTRY(e)) {
+			struct ext3_xattr_entry *next = EXT3_XATTR_NEXT(e);
+			int offs = le16_to_cpu(e->e_value_offs);
+			if (offs < border)
+				e->e_value_offs =
+					cpu_to_le16(offs + size);
+			e = next;
+		}
+		min_offs += size;
+
+		/* remove entry */
+		border = EXT3_XATTR_LEN(here->e_name_len);
+		src = (char *) here + EXT3_XATTR_LEN(here->e_name_len);
+		size = (char *) last - src;
+		if ((char *) here + size > end)
+			printk("ALERT at %s:%d: 0x%p + %d > 0x%p\n",
+					__FILE__, __LINE__, here, size, end);
+		memmove(here, src, size);
+		last = (struct ext3_xattr_entry *) ((char *) last - border);
+		*((__u32 *) last) = 0;
+	}
+	
+	if (value) {
+		int offs = min_offs - value_len;
+		/* use last to create new entry */
+		last->e_name_len = strlen(name);
+		last->e_name_index = name_index;
+		last->e_value_offs = cpu_to_le16(offs);
+		last->e_value_size = cpu_to_le32(value_len);
+		last->e_hash = last->e_value_block = 0;
+		memset(last->e_name, 0, esize);
+		memcpy(last->e_name, name, last->e_name_len);
+		if (start + offs + value_len > end)
+			printk("ALERT at %s:%d: 0x%p + %d + %zd > 0x%p\n",
+			       __FILE__, __LINE__, start, offs,
+			       value_len, end);
+		memcpy(start + offs, value, value_len);
+		last = EXT3_XATTR_NEXT(last);
+		*((__u32 *) last) = 0;
+	}
+	
+	ext3_mark_iloc_dirty(handle, inode, &iloc);
+	brelse(bh);
+
+	return 0;
+}
+
+/*
  * ext3_xattr_set_handle()
  *
  * Create, replace or remove an extended attribute for this inode. Buffer
@@ -470,6 +959,104 @@
  */
 int
 ext3_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
+		const char *name, const void *value, size_t value_len,
+		int flags)
+{
+	struct ext3_xattr_entry entry;
+	int err, where = 0, found = 0, total;
+	int free1 = -1, free2 = -1;
+	int name_len;
+	
+	ea_idebug(inode, "name=%d.%s, value=%p, value_len=%ld",
+		  name_index, name, value, (long)value_len);
+
+	if (IS_RDONLY(inode))
+		return -EROFS;
+	if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
+		return -EPERM;
+	if (value == NULL)
+		value_len = 0;
+	if (name == NULL)
+		return -EINVAL;
+	name_len = strlen(name);
+	if (name_len > 255 || value_len > inode->i_sb->s_blocksize)
+		return -ERANGE;
+	down_write(&EXT3_I(inode)->xattr_sem);
+
+	/* try to find attribute in inode body */
+	err = ext3_xattr_ibody_find(inode, name_index, name, &entry, &free1);
+	if (err == 0) {
+		/* found EA in inode */
+		found = 1;
+		where = 0;
+	} else if (err == -ENOENT) {
+		/* there is no such attribute in inode body */
+		/* try to find attribute in dedicated block */
+		err = ext3_xattr_block_find(inode, name_index, name,
+						&entry, &free2);
+		if (err != 0 && err != -ENOENT) {
+			/* not found EA in block */
+			goto finish;	
+		} else if (err == 0) {
+			/* found EA in block */
+			where = 1;
+			found = 1;
+		}
+	} else
+		goto finish;
+
+	/* check flags: may replace? may create ? */
+	if (found && (flags & XATTR_CREATE)) {
+		err = -EEXIST;
+		goto finish;
+	} else if (!found && (flags & XATTR_REPLACE)) {
+		err = -ENODATA;
+		goto finish;
+	}
+
+	/* check if we have enough space to store attribute */
+	total = EXT3_XATTR_LEN(strlen(name)) + value_len;
+	if (free1 >= 0 && total > free1 && free2 >= 0 && total > free2) {
+		/* have no enough space */
+		err = -ENOSPC;
+		goto finish;
+	}
+	
+	/* time to remove attribute */
+	if (found) {
+		if (where == 0) {
+			/* EA is stored in inode body */
+			ext3_xattr_ibody_set(handle, inode, name_index, name,
+					NULL, 0, flags);
+		} else {
+			/* EA is stored in separated block */
+			ext3_xattr_block_set(handle, inode, name_index, name,
+					NULL, 0, flags);
+		}
+	}
+
+	/* try to store EA in inode body */
+	err = ext3_xattr_ibody_set(handle, inode, name_index, name,
+				value, value_len, flags);
+	if (err) {
+		/* can't store EA in inode body */
+		/* try to store in block */
+		err = ext3_xattr_block_set(handle, inode, name_index,
+					name, value, value_len, flags);	
+	}
+
+finish:	
+	up_write(&EXT3_I(inode)->xattr_sem);
+	return err;
+}
+
+/*
+ * ext3_xattr_block_set()
+ *
+ * this routine add/remove/replace attribute in EA block
+ */
+int
+ext3_xattr_block_set(handle_t *handle, struct inode *inode, int name_index,
 		      const char *name, const void *value, size_t value_len,
 		      int flags)
 {
@@ -492,22 +1078,7 @@
 	 *             towards the end of the block).
 	 * end -- Points right after the block pointed to by header.
 	 */
-
-	ea_idebug(inode, "name=%d.%s, value=%p, value_len=%ld",
-		  name_index, name, value, (long)value_len);
-
-	if (IS_RDONLY(inode))
-		return -EROFS;
-	if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
-		return -EPERM;
-	if (value == NULL)
-		value_len = 0;
-	if (name == NULL)
-		return -EINVAL;
 	name_len = strlen(name);
-	if (name_len > 255 || value_len > sb->s_blocksize)
-		return -ERANGE;
-	down_write(&EXT3_I(inode)->xattr_sem);
 	if (EXT3_I(inode)->i_file_acl) {
 		/* The inode already has an extended attribute block. */
 		bh = sb_bread(sb, EXT3_I(inode)->i_file_acl);
@@ -733,7 +1304,6 @@
 	brelse(bh);
 	if (!(bh && header == HDR(bh)))
 		kfree(header);
-	up_write(&EXT3_I(inode)->xattr_sem);
 
 	return error;
 }
Index: linux-2.6.0/fs/ext3/xattr.h
===================================================================
--- linux-2.6.0.orig/fs/ext3/xattr.h	2003-06-24 18:04:43.000000000 +0400
+++ linux-2.6.0/fs/ext3/xattr.h	2004-01-14 18:54:12.000000000 +0300
@@ -77,7 +77,8 @@
 extern int ext3_xattr_get(struct inode *, int, const char *, void *, size_t);
 extern int ext3_xattr_list(struct inode *, char *, size_t);
 extern int ext3_xattr_set(struct inode *, int, const char *, const void *, size_t, int);
-extern int ext3_xattr_set_handle(handle_t *, struct inode *, int, const char *, const void *, size_t, int);
+extern int ext3_xattr_set_handle(handle_t *, struct inode *, int, const char *,const void *,size_t,int);
+extern int ext3_xattr_block_set(handle_t *, struct inode *, int, const char *,const void *,size_t,int);
 
 extern void ext3_xattr_delete_inode(handle_t *, struct inode *);
 extern void ext3_xattr_put_super(struct super_block *);
Index: linux-2.6.0/include/linux/ext3_fs.h
===================================================================
--- linux-2.6.0.orig/include/linux/ext3_fs.h	2004-01-14 18:54:11.000000000 +0300
+++ linux-2.6.0/include/linux/ext3_fs.h	2004-01-14 18:54:12.000000000 +0300
@@ -265,6 +265,8 @@
 			__u32	m_i_reserved2[2];
 		} masix2;
 	} osd2;				/* OS dependent 2 */
+	__u16	i_extra_isize;
+	__u16	i_pad1;
 };
 
 #define i_size_high	i_dir_acl
@@ -721,6 +723,7 @@
 extern int ext3_forget(handle_t *, int, struct inode *, struct buffer_head *, int);
 extern struct buffer_head * ext3_getblk (handle_t *, struct inode *, long, int, int *);
 extern struct buffer_head * ext3_bread (handle_t *, struct inode *, int, int, int *);
+int ext3_get_inode_loc(struct inode *inode, struct ext3_iloc *iloc, int in_mem);
 
 extern void ext3_read_inode (struct inode *);
 extern void ext3_write_inode (struct inode *, int);
Index: linux-2.6.0/include/linux/ext3_fs_i.h
===================================================================
--- linux-2.6.0.orig/include/linux/ext3_fs_i.h	2003-12-30 08:32:44.000000000 +0300
+++ linux-2.6.0/include/linux/ext3_fs_i.h	2004-01-14 18:54:12.000000000 +0300
@@ -96,6 +96,9 @@
 	 */
 	loff_t	i_disksize;
 
+	/* on-disk additional length */
+	__u16 i_extra_isize;
+
 	/*
 	 * truncate_sem is for serialising ext3_truncate() against
 	 * ext3_getblock().  In the 2.4 ext2 design, great chunks of inode's

%diffstat
 fs/ext3/ialloc.c          |    5 
 fs/ext3/inode.c           |   10 
 fs/ext3/xattr.c           |  634 +++++++++++++++++++++++++++++++++++++++++++---
 fs/ext3/xattr.h           |    3 
 include/linux/ext3_fs.h   |    2 
 include/linux/ext3_fs_i.h |    3 
 6 files changed, 623 insertions(+), 34 deletions(-)