diff mbox

[v4,3/4] btrfs: extended inode refs

Message ID 1345494561-28758-4-git-send-email-mfasheh@suse.de (mailing list archive)
State New, archived
Headers show

Commit Message

Mark Fasheh Aug. 20, 2012, 8:29 p.m. UTC
Teach tree-log.c about extended inode refs. In particular, we have to adjust
the behavior of inode ref replay as well as log tree recovery to account for
the existence of extended refs.

Signed-off-by: Mark Fasheh <mfasheh@suse.de>
---
 fs/btrfs/backref.c  |   68 +++++++++++
 fs/btrfs/backref.h  |    5 +
 fs/btrfs/tree-log.c |  316 ++++++++++++++++++++++++++++++++++++++++++---------
 3 files changed, 337 insertions(+), 52 deletions(-)

Comments

Jan Schmidt Oct. 9, 2012, 12:52 p.m. UTC | #1
Hi Chris, Hi Mark,

I'm currently working on extended inode refs for btrfs send, reading the version
of fs/btrfs/backref.c in Chris' next branch. Concerning commit
f8728be56e48e4a64ed49a71c66b3e6436869838 ...

On Mon, August 20, 2012 at 22:29 (+0200), Mark Fasheh wrote:
> Teach tree-log.c about extended inode refs. In particular, we have to adjust
> the behavior of inode ref replay as well as log tree recovery to account for
> the existence of extended refs.
> 
> Signed-off-by: Mark Fasheh <mfasheh@suse.de>
> ---
>  fs/btrfs/backref.c  |   68 +++++++++++
>  fs/btrfs/backref.h  |    5 +
>  fs/btrfs/tree-log.c |  316 ++++++++++++++++++++++++++++++++++++++++++---------
>  3 files changed, 337 insertions(+), 52 deletions(-)

I had made comments on v3 of this one, which were obviously ignored for v4. I
did not reply to v4, which is the version in "next". Despite that, this commit
has got a

    Reviewed-by: Jan Schmidt <list.btrfs@jan-o-sch.net

Chris, can you please remove that tag from the commit mentioned?

Thanks,
-Jan
--
To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Mark Fasheh Oct. 9, 2012, 6:25 p.m. UTC | #2
On Tue, Oct 09, 2012 at 02:52:29PM +0200, Jan Schmidt wrote:
> Hi Chris, Hi Mark,
> 
> I'm currently working on extended inode refs for btrfs send, reading the version
> of fs/btrfs/backref.c in Chris' next branch. Concerning commit
> f8728be56e48e4a64ed49a71c66b3e6436869838 ...
> 
> On Mon, August 20, 2012 at 22:29 (+0200), Mark Fasheh wrote:
> > Teach tree-log.c about extended inode refs. In particular, we have to adjust
> > the behavior of inode ref replay as well as log tree recovery to account for
> > the existence of extended refs.
> > 
> > Signed-off-by: Mark Fasheh <mfasheh@suse.de>
> > ---
> >  fs/btrfs/backref.c  |   68 +++++++++++
> >  fs/btrfs/backref.h  |    5 +
> >  fs/btrfs/tree-log.c |  316 ++++++++++++++++++++++++++++++++++++++++++---------
> >  3 files changed, 337 insertions(+), 52 deletions(-)
> 
> I had made comments on v3 of this one, which were obviously ignored for v4. I
> did not reply to v4, which is the version in "next". Despite that, this commit
> has got a
> 
>     Reviewed-by: Jan Schmidt <list.btrfs@jan-o-sch.net
> 
> Chris, can you please remove that tag from the commit mentioned?

Yes, this was clearly a mistake - pretty much neither of us could completely
figure out that code ;)

I think what happened is the Reviewed-by: from what *used* to be patch 3 got
accidentally applied to this one:

http://marc.info/?l=linux-btrfs&m=134502070513822&w=4

They are very obviously different patches though.
	--Mark

--
Mark Fasheh
--
To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
diff mbox

Patch

diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index a383c18..658e09c 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -1111,6 +1111,74 @@  static int inode_ref_info(u64 inum, u64 ioff, struct btrfs_root *fs_root,
 				found_key);
 }
 
+int btrfs_find_one_extref(struct btrfs_root *root, u64 inode_objectid,
+			  u64 start_off, struct btrfs_path *path,
+			  struct btrfs_inode_extref **ret_extref,
+			  u64 *found_off)
+{
+	int ret, slot;
+	struct btrfs_key key;
+	struct btrfs_key found_key;
+	struct btrfs_inode_extref *extref;
+	struct extent_buffer *leaf;
+	unsigned long ptr;
+
+	key.objectid = inode_objectid;
+	btrfs_set_key_type(&key, BTRFS_INODE_EXTREF_KEY);
+	key.offset = start_off;
+
+	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+	if (ret < 0)
+		return ret;
+
+	while (1) {
+		leaf = path->nodes[0];
+		slot = path->slots[0];
+		if (slot >= btrfs_header_nritems(leaf)) {
+			/*
+			 * If the item at offset is not found,
+			 * btrfs_search_slot will point us to the slot
+			 * where it should be inserted. In our case
+			 * that will be the slot directly before the
+			 * next INODE_REF_KEY_V2 item. In the case
+			 * that we're pointing to the last slot in a
+			 * leaf, we must move one leaf over.
+			 */
+			ret = btrfs_next_leaf(root, path);
+			if (ret) {
+				if (ret >= 1)
+					ret = -ENOENT;
+				break;
+			}
+			continue;
+		}
+
+		btrfs_item_key_to_cpu(leaf, &found_key, slot);
+
+		/*
+		 * Check that we're still looking at an extended ref key for
+		 * this particular objectid. If we have different
+		 * objectid or type then there are no more to be found
+		 * in the tree and we can exit.
+		 */
+		ret = -ENOENT;
+		if (found_key.objectid != inode_objectid)
+			break;
+		if (btrfs_key_type(&found_key) != BTRFS_INODE_EXTREF_KEY)
+			break;
+
+		ret = 0;
+		ptr = btrfs_item_ptr_offset(leaf, path->slots[0]);
+		extref = (struct btrfs_inode_extref *)ptr;
+		*ret_extref = extref;
+		if (found_off)
+			*found_off = found_key.offset;
+		break;
+	}
+
+	return ret;
+}
+
 /*
  * this iterates to turn a btrfs_inode_ref into a full filesystem path. elements
  * of the path are separated by '/' and the path is guaranteed to be
diff --git a/fs/btrfs/backref.h b/fs/btrfs/backref.h
index c18d8ac..9f3e251 100644
--- a/fs/btrfs/backref.h
+++ b/fs/btrfs/backref.h
@@ -66,4 +66,9 @@  struct inode_fs_paths *init_ipath(s32 total_bytes, struct btrfs_root *fs_root,
 					struct btrfs_path *path);
 void free_ipath(struct inode_fs_paths *ipath);
 
+int btrfs_find_one_extref(struct btrfs_root *root, u64 inode_objectid,
+			  u64 start_off, struct btrfs_path *path,
+			  struct btrfs_inode_extref **ret_extref,
+			  u64 *found_off);
+
 #endif
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index da265dd..7b97112 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -23,8 +23,10 @@ 
 #include "disk-io.h"
 #include "locking.h"
 #include "print-tree.h"
+#include "backref.h"
 #include "compat.h"
 #include "tree-log.h"
+#include "hash.h"
 
 /* magic values for the inode_only field in btrfs_log_inode:
  *
@@ -764,8 +766,16 @@  static noinline int backref_in_log(struct btrfs_root *log,
 	if (ret != 0)
 		goto out;
 
-	item_size = btrfs_item_size_nr(path->nodes[0], path->slots[0]);
 	ptr = btrfs_item_ptr_offset(path->nodes[0], path->slots[0]);
+
+	if (key->type == BTRFS_INODE_EXTREF_KEY) {
+		if (btrfs_find_name_in_ext_backref(path, name, namelen, NULL))
+			match = 1;
+
+		goto out;
+	}
+
+	item_size = btrfs_item_size_nr(path->nodes[0], path->slots[0]);
 	ptr_end = ptr + item_size;
 	while (ptr < ptr_end) {
 		ref = (struct btrfs_inode_ref *)ptr;
@@ -791,27 +801,35 @@  static inline int __add_inode_ref(struct btrfs_trans_handle *trans,
 				  struct btrfs_path *path,
 				  struct btrfs_root *log_root,
 				  struct inode *dir, struct inode *inode,
-				  struct btrfs_key *key,
 				  struct extent_buffer *eb,
-				  struct btrfs_inode_ref *ref,
-				  char *name, int namelen, int *search_done)
+				  u64 inode_objectid, u64 parent_objectid,
+				  u64 ref_index, char *name, int namelen,
+				  int *search_done)
 {
 	int ret;
+	char *victim_name;
+	int victim_name_len;
+	struct extent_buffer *leaf;
 	struct btrfs_dir_item *di;
+	struct btrfs_key search_key;
+	struct btrfs_inode_extref *extref;
 
-	ret = btrfs_search_slot(NULL, root, key, path, 0, 0);
+	/* Search old style refs */
+	search_key.objectid = inode_objectid;
+	search_key.type = BTRFS_INODE_REF_KEY;
+	search_key.offset = parent_objectid;
+	ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0);
 	if (ret == 0) {
-		char *victim_name;
-		int victim_name_len;
 		struct btrfs_inode_ref *victim_ref;
 		unsigned long ptr;
 		unsigned long ptr_end;
-		struct extent_buffer *leaf = path->nodes[0];
+
+		leaf = path->nodes[0];
 
 		/* are we trying to overwrite a back ref for the root directory
 		 * if so, just jump out, we're done
 		 */
-		if (key->objectid == key->offset)
+		if (search_key.objectid == search_key.offset)
 			return 1;
 
 		/* check all the names in this back reference to see
@@ -831,7 +849,7 @@  static inline int __add_inode_ref(struct btrfs_trans_handle *trans,
 					   (unsigned long)(victim_ref + 1),
 					   victim_name_len);
 
-			if (!backref_in_log(log_root, key, victim_name,
+			if (!backref_in_log(log_root, &search_key, victim_name,
 					    victim_name_len)) {
 				btrfs_inc_nlink(inode);
 				btrfs_release_path(path);
@@ -854,10 +872,61 @@  static inline int __add_inode_ref(struct btrfs_trans_handle *trans,
 	}
 	btrfs_release_path(path);
 
+	/* Same search but for extended refs */
+	extref = btrfs_lookup_inode_extref(NULL, root, path, name, namelen,
+					   inode_objectid, parent_objectid, 0,
+					   0);
+	if (!IS_ERR_OR_NULL(extref)) {
+		u32 item_size;
+		u32 cur_offset = 0;
+		unsigned long base;
+		struct inode *victim_parent;
+
+		leaf = path->nodes[0];
+
+		item_size = btrfs_item_size_nr(leaf, path->slots[0]);
+		base = btrfs_item_ptr_offset(leaf, path->slots[0]);
+
+		while (cur_offset < item_size) {
+			extref = (struct btrfs_inode_extref *)base + cur_offset;
+
+			victim_name_len = btrfs_inode_extref_name_len(eb, extref);
+			victim_name = kmalloc(namelen, GFP_NOFS);
+			leaf = path->nodes[0];
+			read_extent_buffer(eb, name, (unsigned long)&extref->name, namelen);
+
+			search_key.objectid = inode_objectid;
+			search_key.type = BTRFS_INODE_EXTREF_KEY;
+			search_key.offset = btrfs_extref_hash(parent_objectid,
+							      name, namelen);
+			if (!backref_in_log(log_root, &search_key, victim_name,
+					    victim_name_len)) {
+				ret = -ENOENT;
+				victim_parent = read_one_inode(root,
+							       parent_objectid);
+				if (victim_parent) {
+					btrfs_inc_nlink(inode);
+					btrfs_release_path(path);
+
+					ret = btrfs_unlink_inode(trans, root,
+								 victim_parent,
+								 inode,
+								 victim_name,
+								 victim_name_len);
+				}
+				iput(victim_parent);
+			}
+			kfree(victim_name);
+			BUG_ON(ret);
+
+			cur_offset += victim_name_len + sizeof(*extref);
+		}
+		*search_done = 1;
+	}
+
 	/* look for a conflicting sequence number */
 	di = btrfs_lookup_dir_index_item(trans, root, path, btrfs_ino(dir),
-					 btrfs_inode_ref_index(eb, ref),
-					 name, namelen, 0);
+					 ref_index, name, namelen, 0);
 	if (di && !IS_ERR(di)) {
 		ret = drop_one_dir_item(trans, root, path, dir, di);
 		BUG_ON(ret);
@@ -876,6 +945,48 @@  static inline int __add_inode_ref(struct btrfs_trans_handle *trans,
 	return 0;
 }
 
+static int extref_get_fields(struct extent_buffer *eb, unsigned long ref_ptr,
+			     u32 *namelen, char **name, u64 *index,
+			     u64 *parent_objectid)
+{
+	struct btrfs_inode_extref *extref;
+
+	extref = (struct btrfs_inode_extref *)ref_ptr;
+
+	*namelen = btrfs_inode_extref_name_len(eb, extref);
+	*name = kmalloc(*namelen, GFP_NOFS);
+	if (*name == NULL)
+		return -ENOMEM;
+
+	read_extent_buffer(eb, *name, (unsigned long)&extref->name,
+			   *namelen);
+
+	*index = btrfs_inode_extref_index(eb, extref);
+	if (parent_objectid)
+		*parent_objectid = btrfs_inode_extref_parent(eb, extref);
+
+	return 0;
+}
+
+static int ref_get_fields(struct extent_buffer *eb, unsigned long ref_ptr,
+			  u32 *namelen, char **name, u64 *index)
+{
+	struct btrfs_inode_ref *ref;
+
+	ref = (struct btrfs_inode_ref *)ref_ptr;
+
+	*namelen = btrfs_inode_ref_name_len(eb, ref);
+	*name = kmalloc(*namelen, GFP_NOFS);
+	if (*name == NULL)
+		return -ENOMEM;
+
+	read_extent_buffer(eb, *name, (unsigned long)(ref + 1), *namelen);
+
+	*index = btrfs_inode_ref_index(eb, ref);
+
+	return 0;
+}
+
 /*
  * replay one inode back reference item found in the log tree.
  * eb, slot and key refer to the buffer and key found in the log tree.
@@ -889,7 +1000,6 @@  static noinline int add_inode_ref(struct btrfs_trans_handle *trans,
 				  struct extent_buffer *eb, int slot,
 				  struct btrfs_key *key)
 {
-	struct btrfs_inode_ref *ref;
 	struct inode *dir;
 	struct inode *inode;
 	unsigned long ref_ptr;
@@ -898,6 +1008,27 @@  static noinline int add_inode_ref(struct btrfs_trans_handle *trans,
 	int namelen;
 	int ret;
 	int search_done = 0;
+	int log_ref_ver = 0;
+	u64 parent_objectid;
+	u64 inode_objectid;
+	u64 ref_index;
+	int ref_struct_size;
+
+	ref_ptr = btrfs_item_ptr_offset(eb, slot);
+	ref_end = ref_ptr + btrfs_item_size_nr(eb, slot);
+
+	if (key->type == BTRFS_INODE_EXTREF_KEY) {
+		struct btrfs_inode_extref *r;
+
+		ref_struct_size = sizeof(struct btrfs_inode_extref);
+		log_ref_ver = 1;
+		r = (struct btrfs_inode_extref *)ref_ptr;
+		parent_objectid = btrfs_inode_extref_parent(eb, r);
+	} else {
+		ref_struct_size = sizeof(struct btrfs_inode_ref);
+		parent_objectid = key->offset;
+	}
+	inode_objectid = key->objectid;
 
 	/*
 	 * it is possible that we didn't log all the parent directories
@@ -905,32 +1036,38 @@  static noinline int add_inode_ref(struct btrfs_trans_handle *trans,
 	 * copy the back ref in.  The link count fixup code will take
 	 * care of the rest
 	 */
-	dir = read_one_inode(root, key->offset);
+	dir = read_one_inode(root, parent_objectid);
 	if (!dir)
 		return -ENOENT;
 
-	inode = read_one_inode(root, key->objectid);
+	inode = read_one_inode(root, inode_objectid);
 	if (!inode) {
 		iput(dir);
 		return -EIO;
 	}
 
-	ref_ptr = btrfs_item_ptr_offset(eb, slot);
-	ref_end = ref_ptr + btrfs_item_size_nr(eb, slot);
-
 	while (ref_ptr < ref_end) {
-		ref = (struct btrfs_inode_ref *)ref_ptr;
-
-		namelen = btrfs_inode_ref_name_len(eb, ref);
-		name = kmalloc(namelen, GFP_NOFS);
-		BUG_ON(!name);
-
-		read_extent_buffer(eb, name, (unsigned long)(ref + 1), namelen);
+		if (log_ref_ver) {
+			ret = extref_get_fields(eb, ref_ptr, &namelen, &name,
+						&ref_index, &parent_objectid);
+			/*
+			 * parent object can change from one array
+			 * item to another.
+			 */
+			if (!dir)
+				dir = read_one_inode(root, parent_objectid);
+			if (!dir)
+				return -ENOENT;
+		} else {
+			ret = ref_get_fields(eb, ref_ptr, &namelen, &name,
+					     &ref_index);
+		}
+		if (ret)
+			return ret;
 
 		/* if we already have a perfect match, we're done */
 		if (!inode_in_dir(root, path, btrfs_ino(dir), btrfs_ino(inode),
-				  btrfs_inode_ref_index(eb, ref),
-				  name, namelen)) {
+				  ref_index, name, namelen)) {
 			/*
 			 * look for a conflicting back reference in the
 			 * metadata. if we find one we have to unlink that name
@@ -941,8 +1078,10 @@  static noinline int add_inode_ref(struct btrfs_trans_handle *trans,
 
 			if (!search_done) {
 				ret = __add_inode_ref(trans, root, path, log,
-						      dir, inode, key, eb, ref,
-						      name, namelen,
+						      dir, inode, eb,
+						      inode_objectid,
+						      parent_objectid,
+						      ref_index, name, namelen,
 						      &search_done);
 				if (ret == 1)
 					goto out;
@@ -951,14 +1090,18 @@  static noinline int add_inode_ref(struct btrfs_trans_handle *trans,
 
 			/* insert our name */
 			ret = btrfs_add_link(trans, dir, inode, name, namelen,
-					     0, btrfs_inode_ref_index(eb, ref));
+					     0, ref_index);
 			BUG_ON(ret);
 
 			btrfs_update_inode(trans, root, inode);
 		}
 
-		ref_ptr = (unsigned long)(ref + 1) + namelen;
+		ref_ptr = (unsigned long)(ref_ptr + ref_struct_size) + namelen;
 		kfree(name);
+		if (log_ref_ver) {
+			iput(dir);
+			dir = NULL;
+		}
 	}
 
 	/* finally write the back reference in the inode */
@@ -982,25 +1125,54 @@  static int insert_orphan_item(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
+static int count_inode_extrefs(struct btrfs_root *root,
+			       struct inode *inode, struct btrfs_path *path)
+{
+	int ret = 0;
+	int name_len;
+	unsigned int nlink = 0;
+	u32 item_size;
+	u32 cur_offset = 0;
+	u64 inode_objectid = btrfs_ino(inode);
+	u64 offset = 0;
+	unsigned long ptr;
+	struct btrfs_inode_extref *extref;
+	struct extent_buffer *leaf;
 
-/*
- * There are a few corners where the link count of the file can't
- * be properly maintained during replay.  So, instead of adding
- * lots of complexity to the log code, we just scan the backrefs
- * for any file that has been through replay.
- *
- * The scan will update the link count on the inode to reflect the
- * number of back refs found.  If it goes down to zero, the iput
- * will free the inode.
- */
-static noinline int fixup_inode_link_count(struct btrfs_trans_handle *trans,
-					   struct btrfs_root *root,
-					   struct inode *inode)
+	while (1) {
+		ret = btrfs_find_one_extref(root, inode_objectid, offset, path,
+					    &extref, &offset);
+		if (ret)
+			break;
+
+		leaf = path->nodes[0];
+		item_size = btrfs_item_size_nr(leaf, path->slots[0]);
+		ptr = btrfs_item_ptr_offset(leaf, path->slots[0]);
+
+		while (cur_offset < item_size) {
+			extref = (struct btrfs_inode_extref *) (ptr + cur_offset);
+			name_len = btrfs_inode_extref_name_len(leaf, extref);
+
+			nlink++;
+
+			cur_offset += name_len + sizeof(*extref);
+		}
+
+		offset++;
+	}
+	btrfs_release_path(path);
+
+	if (ret < 0)
+		return ret;
+	return nlink;
+}
+
+static int count_inode_refs(struct btrfs_root *root,
+			       struct inode *inode, struct btrfs_path *path)
 {
-	struct btrfs_path *path;
 	int ret;
 	struct btrfs_key key;
-	u64 nlink = 0;
+	unsigned int nlink = 0;
 	unsigned long ptr;
 	unsigned long ptr_end;
 	int name_len;
@@ -1010,10 +1182,6 @@  static noinline int fixup_inode_link_count(struct btrfs_trans_handle *trans,
 	key.type = BTRFS_INODE_REF_KEY;
 	key.offset = (u64)-1;
 
-	path = btrfs_alloc_path();
-	if (!path)
-		return -ENOMEM;
-
 	while (1) {
 		ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
 		if (ret < 0)
@@ -1047,6 +1215,45 @@  static noinline int fixup_inode_link_count(struct btrfs_trans_handle *trans,
 		btrfs_release_path(path);
 	}
 	btrfs_release_path(path);
+
+	return nlink;
+}
+
+/*
+ * There are a few corners where the link count of the file can't
+ * be properly maintained during replay.  So, instead of adding
+ * lots of complexity to the log code, we just scan the backrefs
+ * for any file that has been through replay.
+ *
+ * The scan will update the link count on the inode to reflect the
+ * number of back refs found.  If it goes down to zero, the iput
+ * will free the inode.
+ */
+static noinline int fixup_inode_link_count(struct btrfs_trans_handle *trans,
+					   struct btrfs_root *root,
+					   struct inode *inode)
+{
+	struct btrfs_path *path;
+	int ret;
+	u64 nlink = 0;
+	u64 ino = btrfs_ino(inode);
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	ret = count_inode_refs(root, inode, path);
+	if (ret < 0)
+		goto out;
+
+	nlink = ret;
+
+	ret = count_inode_extrefs(root, inode, path);
+	if (ret < 0)
+		goto out;
+
+	nlink += ret;
+
 	if (nlink != inode->i_nlink) {
 		set_nlink(inode, nlink);
 		btrfs_update_inode(trans, root, inode);
@@ -1062,9 +1269,10 @@  static noinline int fixup_inode_link_count(struct btrfs_trans_handle *trans,
 		ret = insert_orphan_item(trans, root, ino);
 		BUG_ON(ret);
 	}
-	btrfs_free_path(path);
 
-	return 0;
+out:
+	btrfs_free_path(path);
+	return ret;
 }
 
 static noinline int fixup_inode_link_counts(struct btrfs_trans_handle *trans,
@@ -1711,6 +1919,10 @@  static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb,
 			ret = add_inode_ref(wc->trans, root, log, path,
 					    eb, i, &key);
 			BUG_ON(ret && ret != -ENOENT);
+		} else if (key.type == BTRFS_INODE_EXTREF_KEY) {
+			ret = add_inode_ref(wc->trans, root, log, path,
+					    eb, i, &key);
+			BUG_ON(ret && ret != -ENOENT);
 		} else if (key.type == BTRFS_EXTENT_DATA_KEY) {
 			ret = replay_one_extent(wc->trans, root, path,
 						eb, i, &key);