Merge branch 'upstream-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mfasheh/ocfs2

* 'upstream-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mfasheh/ocfs2: (138 commits)
  ocfs2: Access the right buffer_head in ocfs2_merge_rec_left.
  ocfs2: use min_t in ocfs2_quota_read()
  ocfs2: remove unneeded lvb casts
  ocfs2: Add xattr support checking in init_security
  ocfs2: alloc xattr bucket in ocfs2_xattr_set_handle
  ocfs2: calculate and reserve credits for xattr value in mknod
  ocfs2/xattr: fix credits calculation during index create
  ocfs2/xattr: Always updating ctime during xattr set.
  ocfs2/xattr: Remove extend_trans call and add its credits from the beginning
  ocfs2/dlm: Fix race during lockres mastery
  ocfs2/dlm: Fix race in adding/removing lockres' to/from the tracking list
  ocfs2/dlm: Hold off sending lockres drop ref message while lockres is migrating
  ocfs2/dlm: Clean up errors in dlm_proxy_ast_handler()
  ocfs2/dlm: Fix a race between migrate request and exit domain
  ocfs2: One more hamming code optimization.
  ocfs2: Another hamming code optimization.
  ocfs2: Don't hand-code xor in ocfs2_hamming_encode().
  ocfs2: Enable metadata checksums.
  ocfs2: Validate superblock with checksum and ecc.
  ocfs2: Checksum and ECC for directory blocks.
  ...

Documentation/filesystems/ocfs2.txt

@@ -31,7 +31,6 @@ Features which OCFS2 does not support yet:
 	- quotas
 	- Directory change notification (F_NOTIFY)
 	- Distributed Caching (F_SETLEASE/F_GETLEASE/break_lease)
-	- POSIX ACLs
 
 Mount options
 =============
@@ -79,3 +78,5 @@ inode64			Indicates that Ocfs2 is allowed to create inodes at
 			bits of significance.
 user_xattr	(*)	Enables Extended User Attributes.
 nouser_xattr		Disables Extended User Attributes.
+acl			Enables POSIX Access Control Lists support.
+noacl		(*)	Disables POSIX Access Control Lists support.

fs/Kconfig

@@ -189,6 +189,8 @@ config OCFS2_FS
 	select CONFIGFS_FS
 	select JBD2
 	select CRC32
+	select QUOTA
+	select QUOTA_TREE
 	help
 	  OCFS2 is a general purpose extent based shared disk cluster file
 	  system with many similarities to ext3. It supports 64 bit inode
@@ -258,15 +260,14 @@ config OCFS2_DEBUG_FS
 	  this option for debugging only as it is likely to decrease
 	  performance of the filesystem.
 
-config OCFS2_COMPAT_JBD
-	bool "Use JBD for compatibility"
+config OCFS2_FS_POSIX_ACL
+	bool "OCFS2 POSIX Access Control Lists"
 	depends on OCFS2_FS
+	select FS_POSIX_ACL
 	default n
-	select JBD
 	help
-	  The ocfs2 filesystem now uses JBD2 for its journalling.  JBD2
-	  is backwards compatible with JBD.  It is safe to say N here.
-	  However, if you really want to use the original JBD, say Y here.
+	  Posix Access Control Lists (ACLs) support permissions for users and
+	  groups beyond the owner/group/world scheme.
 
 endif # BLOCK
 
@@ -303,6 +304,10 @@ config PRINT_QUOTA_WARNING
 	  Note that this behavior is currently deprecated and may go away in
 	  future. Please use notification via netlink socket instead.
 
+# Generic support for tree structured quota files. Seleted when needed.
+config QUOTA_TREE
+	 tristate
+
 config QFMT_V1
 	tristate "Old quota format support"
 	depends on QUOTA
@@ -314,6 +319,7 @@ config QFMT_V1
 config QFMT_V2
 	tristate "Quota format v2 support"
 	depends on QUOTA
+	select QUOTA_TREE
 	help
 	  This quota format allows using quotas with 32-bit UIDs/GIDs. If you
 	  need this functionality say Y here.

fs/Makefile

@@ -54,6 +54,7 @@ obj-$(CONFIG_GENERIC_ACL)	+= generic_acl.o
 obj-$(CONFIG_QUOTA)		+= dquot.o
 obj-$(CONFIG_QFMT_V1)		+= quota_v1.o
 obj-$(CONFIG_QFMT_V2)		+= quota_v2.o
+obj-$(CONFIG_QUOTA_TREE)	+= quota_tree.o
 obj-$(CONFIG_QUOTACTL)		+= quota.o
 
 obj-$(CONFIG_PROC_FS)		+= proc/

fs/ext3/super.c

@@ -713,7 +713,9 @@ static struct dquot_operations ext3_quota_operations = {
 	.acquire_dquot	= ext3_acquire_dquot,
 	.release_dquot	= ext3_release_dquot,
 	.mark_dirty	= ext3_mark_dquot_dirty,
-	.write_info	= ext3_write_info
+	.write_info	= ext3_write_info,
+	.alloc_dquot	= dquot_alloc,
+	.destroy_dquot	= dquot_destroy,
 };
 
 static struct quotactl_ops ext3_qctl_operations = {
@@ -1035,8 +1037,7 @@ static int parse_options (char *options, struct super_block *sb,
 		case Opt_grpjquota:
 			qtype = GRPQUOTA;
 set_qf_name:
-			if ((sb_any_quota_enabled(sb) ||
-			     sb_any_quota_suspended(sb)) &&
+			if (sb_any_quota_loaded(sb) &&
 			    !sbi->s_qf_names[qtype]) {
 				printk(KERN_ERR
 					"EXT3-fs: Cannot change journaled "
@@ -1075,8 +1076,7 @@ static int parse_options (char *options, struct super_block *sb,
 		case Opt_offgrpjquota:
 			qtype = GRPQUOTA;
 clear_qf_name:
-			if ((sb_any_quota_enabled(sb) ||
-			     sb_any_quota_suspended(sb)) &&
+			if (sb_any_quota_loaded(sb) &&
 			    sbi->s_qf_names[qtype]) {
 				printk(KERN_ERR "EXT3-fs: Cannot change "
 					"journaled quota options when "
@@ -1095,8 +1095,7 @@ static int parse_options (char *options, struct super_block *sb,
 		case Opt_jqfmt_vfsv0:
 			qfmt = QFMT_VFS_V0;
 set_qf_format:
-			if ((sb_any_quota_enabled(sb) ||
-			     sb_any_quota_suspended(sb)) &&
+			if (sb_any_quota_loaded(sb) &&
 			    sbi->s_jquota_fmt != qfmt) {
 				printk(KERN_ERR "EXT3-fs: Cannot change "
 					"journaled quota options when "
@@ -1115,8 +1114,7 @@ static int parse_options (char *options, struct super_block *sb,
 			set_opt(sbi->s_mount_opt, GRPQUOTA);
 			break;
 		case Opt_noquota:
-			if (sb_any_quota_enabled(sb) ||
-			    sb_any_quota_suspended(sb)) {
+			if (sb_any_quota_loaded(sb)) {
 				printk(KERN_ERR "EXT3-fs: Cannot change quota "
 					"options when quota turned on.\n");
 				return 0;

fs/ext4/super.c

@@ -803,7 +803,9 @@ static struct dquot_operations ext4_quota_operations = {
 	.acquire_dquot	= ext4_acquire_dquot,
 	.release_dquot	= ext4_release_dquot,
 	.mark_dirty	= ext4_mark_dquot_dirty,
-	.write_info	= ext4_write_info
+	.write_info	= ext4_write_info,
+	.alloc_dquot	= dquot_alloc,
+	.destroy_dquot	= dquot_destroy,
 };
 
 static struct quotactl_ops ext4_qctl_operations = {
@@ -1142,8 +1144,7 @@ static int parse_options(char *options, struct super_block *sb,
 		case Opt_grpjquota:
 			qtype = GRPQUOTA;
 set_qf_name:
-			if ((sb_any_quota_enabled(sb) ||
-			     sb_any_quota_suspended(sb)) &&
+			if (sb_any_quota_loaded(sb) &&
 			    !sbi->s_qf_names[qtype]) {
 				printk(KERN_ERR
 				       "EXT4-fs: Cannot change journaled "
@@ -1182,8 +1183,7 @@ static int parse_options(char *options, struct super_block *sb,
 		case Opt_offgrpjquota:
 			qtype = GRPQUOTA;
 clear_qf_name:
-			if ((sb_any_quota_enabled(sb) ||
-			     sb_any_quota_suspended(sb)) &&
+			if (sb_any_quota_loaded(sb) &&
 			    sbi->s_qf_names[qtype]) {
 				printk(KERN_ERR "EXT4-fs: Cannot change "
 					"journaled quota options when "
@@ -1202,8 +1202,7 @@ static int parse_options(char *options, struct super_block *sb,
 		case Opt_jqfmt_vfsv0:
 			qfmt = QFMT_VFS_V0;
 set_qf_format:
-			if ((sb_any_quota_enabled(sb) ||
-			     sb_any_quota_suspended(sb)) &&
+			if (sb_any_quota_loaded(sb) &&
 			    sbi->s_jquota_fmt != qfmt) {
 				printk(KERN_ERR "EXT4-fs: Cannot change "
 					"journaled quota options when "
@@ -1222,7 +1221,7 @@ static int parse_options(char *options, struct super_block *sb,
 			set_opt(sbi->s_mount_opt, GRPQUOTA);
 			break;
 		case Opt_noquota:
-			if (sb_any_quota_enabled(sb)) {
+			if (sb_any_quota_loaded(sb)) {
 				printk(KERN_ERR "EXT4-fs: Cannot change quota "
 					"options when quota turned on.\n");
 				return 0;

fs/jbd2/commit.c

@@ -509,6 +509,10 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 		if (is_journal_aborted(journal)) {
 			clear_buffer_jbddirty(jh2bh(jh));
 			JBUFFER_TRACE(jh, "journal is aborting: refile");
+			jbd2_buffer_abort_trigger(jh,
+						  jh->b_frozen_data ?
+						  jh->b_frozen_triggers :
+						  jh->b_triggers);
 			jbd2_journal_refile_buffer(journal, jh);
 			/* If that was the last one, we need to clean up
 			 * any descriptor buffers which may have been
@@ -844,6 +848,9 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 		 * data.
 		 *
 		 * Otherwise, we can just throw away the frozen data now.
+		 *
+		 * We also know that the frozen data has already fired
+		 * its triggers if they exist, so we can clear that too.
 		 */
 		if (jh->b_committed_data) {
 			jbd2_free(jh->b_committed_data, bh->b_size);
@@ -851,10 +858,12 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 			if (jh->b_frozen_data) {
 				jh->b_committed_data = jh->b_frozen_data;
 				jh->b_frozen_data = NULL;
+				jh->b_frozen_triggers = NULL;
 			}
 		} else if (jh->b_frozen_data) {
 			jbd2_free(jh->b_frozen_data, bh->b_size);
 			jh->b_frozen_data = NULL;
+			jh->b_frozen_triggers = NULL;
 		}
 
 		spin_lock(&journal->j_list_lock);

fs/jbd2/journal.c

@@ -50,6 +50,7 @@ EXPORT_SYMBOL(jbd2_journal_unlock_updates);
 EXPORT_SYMBOL(jbd2_journal_get_write_access);
 EXPORT_SYMBOL(jbd2_journal_get_create_access);
 EXPORT_SYMBOL(jbd2_journal_get_undo_access);
+EXPORT_SYMBOL(jbd2_journal_set_triggers);
 EXPORT_SYMBOL(jbd2_journal_dirty_metadata);
 EXPORT_SYMBOL(jbd2_journal_release_buffer);
 EXPORT_SYMBOL(jbd2_journal_forget);
@@ -290,6 +291,7 @@ int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
 	struct page *new_page;
 	unsigned int new_offset;
 	struct buffer_head *bh_in = jh2bh(jh_in);
+	struct jbd2_buffer_trigger_type *triggers;
 
 	/*
 	 * The buffer really shouldn't be locked: only the current committing
@@ -314,12 +316,22 @@ int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
 		done_copy_out = 1;
 		new_page = virt_to_page(jh_in->b_frozen_data);
 		new_offset = offset_in_page(jh_in->b_frozen_data);
+		triggers = jh_in->b_frozen_triggers;
 	} else {
 		new_page = jh2bh(jh_in)->b_page;
 		new_offset = offset_in_page(jh2bh(jh_in)->b_data);
+		triggers = jh_in->b_triggers;
 	}
 
 	mapped_data = kmap_atomic(new_page, KM_USER0);
+	/*
+	 * Fire any commit trigger.  Do this before checking for escaping,
+	 * as the trigger may modify the magic offset.  If a copy-out
+	 * happens afterwards, it will have the correct data in the buffer.
+	 */
+	jbd2_buffer_commit_trigger(jh_in, mapped_data + new_offset,
+				   triggers);
+
 	/*
 	 * Check for escaping
 	 */
@@ -352,6 +364,13 @@ int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
 		new_page = virt_to_page(tmp);
 		new_offset = offset_in_page(tmp);
 		done_copy_out = 1;
+
+		/*
+		 * This isn't strictly necessary, as we're using frozen
+		 * data for the escaping, but it keeps consistency with
+		 * b_frozen_data usage.
+		 */
+		jh_in->b_frozen_triggers = jh_in->b_triggers;
 	}
 
 	/*

fs/jbd2/transaction.c

@@ -741,6 +741,12 @@ do_get_write_access(handle_t *handle, struct journal_head *jh,
 		source = kmap_atomic(page, KM_USER0);
 		memcpy(jh->b_frozen_data, source+offset, jh2bh(jh)->b_size);
 		kunmap_atomic(source, KM_USER0);
+
+		/*
+		 * Now that the frozen data is saved off, we need to store
+		 * any matching triggers.
+		 */
+		jh->b_frozen_triggers = jh->b_triggers;
 	}
 	jbd_unlock_bh_state(bh);
 
@@ -943,6 +949,47 @@ int jbd2_journal_get_undo_access(handle_t *handle, struct buffer_head *bh)
 	return err;
 }
 
+/**
+ * void jbd2_journal_set_triggers() - Add triggers for commit writeout
+ * @bh: buffer to trigger on
+ * @type: struct jbd2_buffer_trigger_type containing the trigger(s).
+ *
+ * Set any triggers on this journal_head.  This is always safe, because
+ * triggers for a committing buffer will be saved off, and triggers for
+ * a running transaction will match the buffer in that transaction.
+ *
+ * Call with NULL to clear the triggers.
+ */
+void jbd2_journal_set_triggers(struct buffer_head *bh,
+			       struct jbd2_buffer_trigger_type *type)
+{
+	struct journal_head *jh = bh2jh(bh);
+
+	jh->b_triggers = type;
+}
+
+void jbd2_buffer_commit_trigger(struct journal_head *jh, void *mapped_data,
+				struct jbd2_buffer_trigger_type *triggers)
+{
+	struct buffer_head *bh = jh2bh(jh);
+
+	if (!triggers || !triggers->t_commit)
+		return;
+
+	triggers->t_commit(triggers, bh, mapped_data, bh->b_size);
+}
+
+void jbd2_buffer_abort_trigger(struct journal_head *jh,
+			       struct jbd2_buffer_trigger_type *triggers)
+{
+	if (!triggers || !triggers->t_abort)
+		return;
+
+	triggers->t_abort(triggers, jh2bh(jh));
+}
+
+
+
 /**
  * int jbd2_journal_dirty_metadata() -  mark a buffer as containing dirty metadata
  * @handle: transaction to add buffer to.

fs/ocfs2/Makefile

@@ -12,6 +12,7 @@ obj-$(CONFIG_OCFS2_FS_USERSPACE_CLUSTER) += ocfs2_stack_user.o
 ocfs2-objs := \
 	alloc.o 		\
 	aops.o 			\
+	blockcheck.o		\
 	buffer_head_io.o	\
 	dcache.o 		\
 	dir.o 			\
@@ -35,8 +36,14 @@ ocfs2-objs := \
 	sysfile.o 		\
 	uptodate.o		\
 	ver.o			\
+	quota_local.o		\
+	quota_global.o		\
 	xattr.o
 
+ifeq ($(CONFIG_OCFS2_FS_POSIX_ACL),y)
+ocfs2-objs += acl.o
+endif
+
 ocfs2_stackglue-objs := stackglue.o
 ocfs2_stack_o2cb-objs := stack_o2cb.o
 ocfs2_stack_user-objs := stack_user.o

fs/ocfs2/acl.c

+/* -*- mode: c; c-basic-offset: 8; -*-
+ * vim: noexpandtab sw=8 ts=8 sts=0:
+ *
+ * acl.c
+ *
+ * Copyright (C) 2004, 2008 Oracle.  All rights reserved.
+ *
+ * CREDITS:
+ * Lots of code in this file is copy from linux/fs/ext3/acl.c.
+ * Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/string.h>
+
+#define MLOG_MASK_PREFIX ML_INODE
+#include <cluster/masklog.h>
+
+#include "ocfs2.h"
+#include "alloc.h"
+#include "dlmglue.h"
+#include "file.h"
+#include "ocfs2_fs.h"
+
+#include "xattr.h"
+#include "acl.h"
+
+/*
+ * Convert from xattr value to acl struct.
+ */
+static struct posix_acl *ocfs2_acl_from_xattr(const void *value, size_t size)
+{
+	int n, count;
+	struct posix_acl *acl;
+
+	if (!value)
+		return NULL;
+	if (size < sizeof(struct posix_acl_entry))
+		return ERR_PTR(-EINVAL);
+
+	count = size / sizeof(struct posix_acl_entry);
+	if (count < 0)
+		return ERR_PTR(-EINVAL);
+	if (count == 0)
+		return NULL;
+
+	acl = posix_acl_alloc(count, GFP_NOFS);
+	if (!acl)
+		return ERR_PTR(-ENOMEM);
+	for (n = 0; n < count; n++) {
+		struct ocfs2_acl_entry *entry =
+			(struct ocfs2_acl_entry *)value;
+
+		acl->a_entries[n].e_tag  = le16_to_cpu(entry->e_tag);
+		acl->a_entries[n].e_perm = le16_to_cpu(entry->e_perm);
+		acl->a_entries[n].e_id   = le32_to_cpu(entry->e_id);
+		value += sizeof(struct posix_acl_entry);
+
+	}
+	return acl;
+}
+
+/*
+ * Convert acl struct to xattr value.
+ */
+static void *ocfs2_acl_to_xattr(const struct posix_acl *acl, size_t *size)
+{
+	struct ocfs2_acl_entry *entry = NULL;
+	char *ocfs2_acl;
+	size_t n;
+
+	*size = acl->a_count * sizeof(struct posix_acl_entry);
+
+	ocfs2_acl = kmalloc(*size, GFP_NOFS);
+	if (!ocfs2_acl)
+		return ERR_PTR(-ENOMEM);
+
+	entry = (struct ocfs2_acl_entry *)ocfs2_acl;
+	for (n = 0; n < acl->a_count; n++, entry++) {
+		entry->e_tag  = cpu_to_le16(acl->a_entries[n].e_tag);
+		entry->e_perm = cpu_to_le16(acl->a_entries[n].e_perm);
+		entry->e_id   = cpu_to_le32(acl->a_entries[n].e_id);
+	}
+	return ocfs2_acl;
+}
+
+static struct posix_acl *ocfs2_get_acl_nolock(struct inode *inode,
+					      int type,
+					      struct buffer_head *di_bh)
+{
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	int name_index;
+	char *value = NULL;
+	struct posix_acl *acl;
+	int retval;
+
+	if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL))
+		return NULL;
+
+	switch (type) {
+	case ACL_TYPE_ACCESS:
+		name_index = OCFS2_XATTR_INDEX_POSIX_ACL_ACCESS;
+		break;
+	case ACL_TYPE_DEFAULT:
+		name_index = OCFS2_XATTR_INDEX_POSIX_ACL_DEFAULT;
+		break;
+	default:
+		return ERR_PTR(-EINVAL);
+	}
+
+	retval = ocfs2_xattr_get_nolock(inode, di_bh, name_index, "", NULL, 0);
+	if (retval > 0) {
+		value = kmalloc(retval, GFP_NOFS);
+		if (!value)
+			return ERR_PTR(-ENOMEM);
+		retval = ocfs2_xattr_get_nolock(inode, di_bh, name_index,
+						"", value, retval);
+	}
+
+	if (retval > 0)
+		acl = ocfs2_acl_from_xattr(value, retval);
+	else if (retval == -ENODATA || retval == 0)
+		acl = NULL;
+	else
+		acl = ERR_PTR(retval);
+
+	kfree(value);
+
+	return acl;
+}
+
+
+/*
+ * Get posix acl.
+ */
+static struct posix_acl *ocfs2_get_acl(struct inode *inode, int type)
+{
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	struct buffer_head *di_bh = NULL;
+	struct posix_acl *acl;
+	int ret;
+
+	if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL))
+		return NULL;
+
+	ret = ocfs2_inode_lock(inode, &di_bh, 0);
+	if (ret < 0) {
+		mlog_errno(ret);
+		acl = ERR_PTR(ret);
+		return acl;
+	}
+
+	acl = ocfs2_get_acl_nolock(inode, type, di_bh);
+
+	ocfs2_inode_unlock(inode, 0);
+
+	brelse(di_bh);
+
+	return acl;
+}
+
+/*
+ * Set the access or default ACL of an inode.
+ */
+static int ocfs2_set_acl(handle_t *handle,
+			 struct inode *inode,
+			 struct buffer_head *di_bh,
+			 int type,
+			 struct posix_acl *acl,
+			 struct ocfs2_alloc_context *meta_ac,
+			 struct ocfs2_alloc_context *data_ac)
+{
+	int name_index;
+	void *value = NULL;
+	size_t size = 0;
+	int ret;
+
+	if (S_ISLNK(inode->i_mode))
+		return -EOPNOTSUPP;
+
+	switch (type) {
+	case ACL_TYPE_ACCESS:
+		name_index = OCFS2_XATTR_INDEX_POSIX_ACL_ACCESS;
+		if (acl) {
+			mode_t mode = inode->i_mode;
+			ret = posix_acl_equiv_mode(acl, &mode);
+			if (ret < 0)
+				return ret;
+			else {
+				inode->i_mode = mode;
+				if (ret == 0)
+					acl = NULL;
+			}
+		}
+		break;
+	case ACL_TYPE_DEFAULT:
+		name_index = OCFS2_XATTR_INDEX_POSIX_ACL_DEFAULT;
+		if (!S_ISDIR(inode->i_mode))
+			return acl ? -EACCES : 0;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (acl) {
+		value = ocfs2_acl_to_xattr(acl, &size);
+		if (IS_ERR(value))
+			return (int)PTR_ERR(value);
+	}
+
+	if (handle)
+		ret = ocfs2_xattr_set_handle(handle, inode, di_bh, name_index,
+					     "", value, size, 0,
+					     meta_ac, data_ac);
+	else
+		ret = ocfs2_xattr_set(inode, name_index, "", value, size, 0);
+
+	kfree(value);
+
+	return ret;
+}
+
+int ocfs2_check_acl(struct inode *inode, int mask)
+{
+	struct posix_acl *acl = ocfs2_get_acl(inode, ACL_TYPE_ACCESS);
+
+	if (IS_ERR(acl))
+		return PTR_ERR(acl);
+	if (acl) {
+		int ret = posix_acl_permission(inode, acl, mask);
+		posix_acl_release(acl);
+		return ret;
+	}
+
+	return -EAGAIN;
+}
+
+int ocfs2_acl_chmod(struct inode *inode)
+{
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	struct posix_acl *acl, *clone;
+	int ret;
+
+	if (S_ISLNK(inode->i_mode))
+		return -EOPNOTSUPP;
+
+	if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL))
+		return 0;
+
+	acl = ocfs2_get_acl(inode, ACL_TYPE_ACCESS);
+	if (IS_ERR(acl) || !acl)
+		return PTR_ERR(acl);
+	clone = posix_acl_clone(acl, GFP_KERNEL);
+	posix_acl_release(acl);
+	if (!clone)
+		return -ENOMEM;
+	ret = posix_acl_chmod_masq(clone, inode->i_mode);
+	if (!ret)
+		ret = ocfs2_set_acl(NULL, inode, NULL, ACL_TYPE_ACCESS,
+				    clone, NULL, NULL);
+	posix_acl_release(clone);
+	return ret;
+}
+
+/*
+ * Initialize the ACLs of a new inode. If parent directory has default ACL,
+ * then clone to new inode. Called from ocfs2_mknod.
+ */
+int ocfs2_init_acl(handle_t *handle,
+		   struct inode *inode,
+		   struct inode *dir,
+		   struct buffer_head *di_bh,
+		   struct buffer_head *dir_bh,
+		   struct ocfs2_alloc_context *meta_ac,
+		   struct ocfs2_alloc_context *data_ac)
+{
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	struct posix_acl *acl = NULL;
+	int ret = 0;
+
+	if (!S_ISLNK(inode->i_mode)) {
+		if (osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) {
+			acl = ocfs2_get_acl_nolock(dir, ACL_TYPE_DEFAULT,
+						   dir_bh);
+			if (IS_ERR(acl))
+				return PTR_ERR(acl);
+		}
+		if (!acl)
+			inode->i_mode &= ~current->fs->umask;
+	}
+	if ((osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) && acl) {
+		struct posix_acl *clone;
+		mode_t mode;
+
+		if (S_ISDIR(inode->i_mode)) {
+			ret = ocfs2_set_acl(handle, inode, di_bh,
+					    ACL_TYPE_DEFAULT, acl,
+					    meta_ac, data_ac);
+			if (ret)
+				goto cleanup;
+		}
+		clone = posix_acl_clone(acl, GFP_NOFS);
+		ret = -ENOMEM;
+		if (!clone)
+			goto cleanup;
+
+		mode = inode->i_mode;
+		ret = posix_acl_create_masq(clone, &mode);
+		if (ret >= 0) {
+			inode->i_mode = mode;
+			if (ret > 0) {
+				ret = ocfs2_set_acl(handle, inode,
+						    di_bh, ACL_TYPE_ACCESS,
+						    clone, meta_ac, data_ac);
+			}
+		}
+		posix_acl_release(clone);
+	}
+cleanup:
+	posix_acl_release(acl);
+	return ret;
+}
+
+static size_t ocfs2_xattr_list_acl_access(struct inode *inode,
+					  char *list,
+					  size_t list_len,
+					  const char *name,
+					  size_t name_len)
+{
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	const size_t size = sizeof(POSIX_ACL_XATTR_ACCESS);
+
+	if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL))
+		return 0;
+
+	if (list && size <= list_len)
+		memcpy(list, POSIX_ACL_XATTR_ACCESS, size);
+	return size;
+}
+
+static size_t ocfs2_xattr_list_acl_default(struct inode *inode,
+					   char *list,
+					   size_t list_len,
+					   const char *name,
+					   size_t name_len)
+{
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	const size_t size = sizeof(POSIX_ACL_XATTR_DEFAULT);
+
+	if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL))
+		return 0;
+
+	if (list && size <= list_len)
+		memcpy(list, POSIX_ACL_XATTR_DEFAULT, size);
+	return size;
+}
+
+static int ocfs2_xattr_get_acl(struct inode *inode,
+			       int type,
+			       void *buffer,
+			       size_t size)
+{
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	struct posix_acl *acl;
+	int ret;
+
+	if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL))
+		return -EOPNOTSUPP;
+
+	acl = ocfs2_get_acl(inode, type);
+	if (IS_ERR(acl))
+		return PTR_ERR(acl);
+	if (acl == NULL)
+		return -ENODATA;
+	ret = posix_acl_to_xattr(acl, buffer, size);
+	posix_acl_release(acl);
+
+	return ret;
+}
+
+static int ocfs2_xattr_get_acl_access(struct inode *inode,
+				      const char *name,
+				      void *buffer,
+				      size_t size)
+{
+	if (strcmp(name, "") != 0)
+		return -EINVAL;
+	return ocfs2_xattr_get_acl(inode, ACL_TYPE_ACCESS, buffer, size);
+}
+
+static int ocfs2_xattr_get_acl_default(struct inode *inode,
+				       const char *name,
+				       void *buffer,
+				       size_t size)
+{
+	if (strcmp(name, "") != 0)
+		return -EINVAL;
+	return ocfs2_xattr_get_acl(inode, ACL_TYPE_DEFAULT, buffer, size);
+}
+
+static int ocfs2_xattr_set_acl(struct inode *inode,
+			       int type,
+			       const void *value,
+			       size_t size)
+{
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+	struct posix_acl *acl;
+	int ret = 0;
+
+	if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL))
+		return -EOPNOTSUPP;
+
+	if (!is_owner_or_cap(inode))
+		return -EPERM;
+
+	if (value) {
+		acl = posix_acl_from_xattr(value, size);
+		if (IS_ERR(acl))
+			return PTR_ERR(acl);
+		else if (acl) {
+			ret = posix_acl_valid(acl);
+			if (ret)
+				goto cleanup;
+		}
+	} else
+		acl = NULL;
+
+	ret = ocfs2_set_acl(NULL, inode, NULL, type, acl, NULL, NULL);
+
+cleanup:
+	posix_acl_release(acl);
+	return ret;
+}
+
+static int ocfs2_xattr_set_acl_access(struct inode *inode,
+				      const char *name,
+				      const void *value,
+				      size_t size,
+				      int flags)
+{
+	if (strcmp(name, "") != 0)
+		return -EINVAL;
+	return ocfs2_xattr_set_acl(inode, ACL_TYPE_ACCESS, value, size);
+}
+
+static int ocfs2_xattr_set_acl_default(struct inode *inode,
+				       const char *name,
+				       const void *value,
+				       size_t size,
+				       int flags)
+{
+	if (strcmp(name, "") != 0)
+		return -EINVAL;
+	return ocfs2_xattr_set_acl(inode, ACL_TYPE_DEFAULT, value, size);
+}
+
+struct xattr_handler ocfs2_xattr_acl_access_handler = {
+	.prefix	= POSIX_ACL_XATTR_ACCESS,
+	.list	= ocfs2_xattr_list_acl_access,
+	.get	= ocfs2_xattr_get_acl_access,
+	.set	= ocfs2_xattr_set_acl_access,
+};
+
+struct xattr_handler ocfs2_xattr_acl_default_handler = {
+	.prefix	= POSIX_ACL_XATTR_DEFAULT,
+	.list	= ocfs2_xattr_list_acl_default,
+	.get	= ocfs2_xattr_get_acl_default,
+	.set	= ocfs2_xattr_set_acl_default,
+};

fs/ocfs2/acl.h

+/* -*- mode: c; c-basic-offset: 8; -*-
+ * vim: noexpandtab sw=8 ts=8 sts=0:
+ *
+ * acl.h
+ *
+ * Copyright (C) 2004, 2008 Oracle.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+
+#ifndef OCFS2_ACL_H
+#define OCFS2_ACL_H
+
+#include <linux/posix_acl_xattr.h>
+
+struct ocfs2_acl_entry {
+	__le16 e_tag;
+	__le16 e_perm;
+	__le32 e_id;
+};
+
+#ifdef CONFIG_OCFS2_FS_POSIX_ACL
+
+extern int ocfs2_check_acl(struct inode *, int);
+extern int ocfs2_acl_chmod(struct inode *);
+extern int ocfs2_init_acl(handle_t *, struct inode *, struct inode *,
+			  struct buffer_head *, struct buffer_head *,
+			  struct ocfs2_alloc_context *,
+			  struct ocfs2_alloc_context *);
+
+#else /* CONFIG_OCFS2_FS_POSIX_ACL*/
+
+#define ocfs2_check_acl NULL
+static inline int ocfs2_acl_chmod(struct inode *inode)
+{
+	return 0;
+}
+static inline int ocfs2_init_acl(handle_t *handle,
+				 struct inode *inode,
+				 struct inode *dir,
+				 struct buffer_head *di_bh,
+				 struct buffer_head *dir_bh,
+				 struct ocfs2_alloc_context *meta_ac,
+				 struct ocfs2_alloc_context *data_ac)
+{
+	return 0;
+}
+
+#endif /* CONFIG_OCFS2_FS_POSIX_ACL*/
+
+#endif /* OCFS2_ACL_H */

fs/ocfs2/alloc.h

@@ -45,7 +45,9 @@
  *
  * ocfs2_extent_tree contains info for the root of the b-tree, it must have a
  * root ocfs2_extent_list and a root_bh so that they can be used in the b-tree
- * functions.
+ * functions.  With metadata ecc, we now call different journal_access
+ * functions for each type of metadata, so it must have the
+ * root_journal_access function.
  * ocfs2_extent_tree_operations abstract the normal operations we do for
  * the root of extent b-tree.
  */
@@ -54,6 +56,7 @@ struct ocfs2_extent_tree {
 	struct ocfs2_extent_tree_operations	*et_ops;
 	struct buffer_head			*et_root_bh;
 	struct ocfs2_extent_list		*et_root_el;
+	ocfs2_journal_access_func		et_root_journal_access;
 	void					*et_object;
 	unsigned int				et_max_leaf_clusters;
 };
@@ -68,10 +71,18 @@ void ocfs2_init_dinode_extent_tree(struct ocfs2_extent_tree *et,
 void ocfs2_init_xattr_tree_extent_tree(struct ocfs2_extent_tree *et,
 				       struct inode *inode,
 				       struct buffer_head *bh);
+struct ocfs2_xattr_value_buf;
 void ocfs2_init_xattr_value_extent_tree(struct ocfs2_extent_tree *et,
 					struct inode *inode,
-					struct buffer_head *bh,
-					struct ocfs2_xattr_value_root *xv);
+					struct ocfs2_xattr_value_buf *vb);
+
+/*
+ * Read an extent block into *bh.  If *bh is NULL, a bh will be
+ * allocated.  This is a cached read.  The extent block will be validated
+ * with ocfs2_validate_extent_block().
+ */
+int ocfs2_read_extent_block(struct inode *inode, u64 eb_blkno,
+			    struct buffer_head **bh);
 
 struct ocfs2_alloc_context;
 int ocfs2_insert_extent(struct ocfs2_super *osb,
@@ -110,6 +121,11 @@ int ocfs2_remove_extent(struct inode *inode,
 			u32 cpos, u32 len, handle_t *handle,
 			struct ocfs2_alloc_context *meta_ac,
 			struct ocfs2_cached_dealloc_ctxt *dealloc);
+int ocfs2_remove_btree_range(struct inode *inode,
+			     struct ocfs2_extent_tree *et,
+			     u32 cpos, u32 phys_cpos, u32 len,
+			     struct ocfs2_cached_dealloc_ctxt *dealloc);
+
 int ocfs2_num_free_extents(struct ocfs2_super *osb,
 			   struct inode *inode,
 			   struct ocfs2_extent_tree *et);
@@ -167,10 +183,18 @@ int __ocfs2_flush_truncate_log(struct ocfs2_super *osb);
  */
 struct ocfs2_cached_dealloc_ctxt {
 	struct ocfs2_per_slot_free_list		*c_first_suballocator;
+	struct ocfs2_cached_block_free 		*c_global_allocator;
 };
 static inline void ocfs2_init_dealloc_ctxt(struct ocfs2_cached_dealloc_ctxt *c)
 {
 	c->c_first_suballocator = NULL;
+	c->c_global_allocator = NULL;
+}
+int ocfs2_cache_cluster_dealloc(struct ocfs2_cached_dealloc_ctxt *ctxt,
+				u64 blkno, unsigned int bit);
+static inline int ocfs2_dealloc_has_cluster(struct ocfs2_cached_dealloc_ctxt *c)
+{
+	return c->c_global_allocator != NULL;
 }
 int ocfs2_run_deallocs(struct ocfs2_super *osb,
 		       struct ocfs2_cached_dealloc_ctxt *ctxt);

fs/ocfs2/aops.c

@@ -27,6 +27,7 @@
 #include <linux/swap.h>
 #include <linux/pipe_fs_i.h>
 #include <linux/mpage.h>
+#include <linux/quotaops.h>
 
 #define MLOG_MASK_PREFIX ML_FILE_IO
 #include <cluster/masklog.h>
@@ -68,20 +69,13 @@ static int ocfs2_symlink_get_block(struct inode *inode, sector_t iblock,
 		goto bail;
 	}
 
-	status = ocfs2_read_block(inode, OCFS2_I(inode)->ip_blkno, &bh);
+	status = ocfs2_read_inode_block(inode, &bh);
 	if (status < 0) {
 		mlog_errno(status);
 		goto bail;
 	}
 	fe = (struct ocfs2_dinode *) bh->b_data;
 
-	if (!OCFS2_IS_VALID_DINODE(fe)) {
-		mlog(ML_ERROR, "Invalid dinode #%llu: signature = %.*s\n",
-		     (unsigned long long)le64_to_cpu(fe->i_blkno), 7,
-		     fe->i_signature);
-		goto bail;
-	}
-
 	if ((u64)iblock >= ocfs2_clusters_to_blocks(inode->i_sb,
 						    le32_to_cpu(fe->i_clusters))) {
 		mlog(ML_ERROR, "block offset is outside the allocated size: "
@@ -262,7 +256,7 @@ static int ocfs2_readpage_inline(struct inode *inode, struct page *page)
 	BUG_ON(!PageLocked(page));
 	BUG_ON(!(OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL));
 
-	ret = ocfs2_read_block(inode, OCFS2_I(inode)->ip_blkno, &di_bh);
+	ret = ocfs2_read_inode_block(inode, &di_bh);
 	if (ret) {
 		mlog_errno(ret);
 		goto out;
@@ -481,12 +475,6 @@ handle_t *ocfs2_start_walk_page_trans(struct inode *inode,
 
 	if (ocfs2_should_order_data(inode)) {
 		ret = ocfs2_jbd2_file_inode(handle, inode);
-#ifdef CONFIG_OCFS2_COMPAT_JBD
-		ret = walk_page_buffers(handle,
-					page_buffers(page),
-					from, to, NULL,
-					ocfs2_journal_dirty_data);
-#endif
 		if (ret < 0)
 			mlog_errno(ret);
 	}
@@ -1072,15 +1060,8 @@ static void ocfs2_write_failure(struct inode *inode,
 		tmppage = wc->w_pages[i];
 
 		if (page_has_buffers(tmppage)) {
-			if (ocfs2_should_order_data(inode)) {
+			if (ocfs2_should_order_data(inode))
 				ocfs2_jbd2_file_inode(wc->w_handle, inode);
-#ifdef CONFIG_OCFS2_COMPAT_JBD
-				walk_page_buffers(wc->w_handle,
-						  page_buffers(tmppage),
-						  from, to, NULL,
-						  ocfs2_journal_dirty_data);
-#endif
-			}
 
 			block_commit_write(tmppage, from, to);
 		}
@@ -1531,7 +1512,7 @@ static int ocfs2_write_begin_inline(struct address_space *mapping,
 		goto out;
 	}
 
-	ret = ocfs2_journal_access(handle, inode, wc->w_di_bh,
+	ret = ocfs2_journal_access_di(handle, inode, wc->w_di_bh,
 				      OCFS2_JOURNAL_ACCESS_WRITE);
 	if (ret) {
 		ocfs2_commit_trans(osb, handle);
@@ -1750,15 +1731,20 @@ int ocfs2_write_begin_nolock(struct address_space *mapping,
 
 	wc->w_handle = handle;
 
+	if (clusters_to_alloc && vfs_dq_alloc_space_nodirty(inode,
+			ocfs2_clusters_to_bytes(osb->sb, clusters_to_alloc))) {
+		ret = -EDQUOT;
+		goto out_commit;
+	}
 	/*
 	 * We don't want this to fail in ocfs2_write_end(), so do it
 	 * here.
 	 */
-	ret = ocfs2_journal_access(handle, inode, wc->w_di_bh,
+	ret = ocfs2_journal_access_di(handle, inode, wc->w_di_bh,
 				      OCFS2_JOURNAL_ACCESS_WRITE);
 	if (ret) {
 		mlog_errno(ret);
-		goto out_commit;
+		goto out_quota;
 	}
 
 	/*
@@ -1771,14 +1757,14 @@ int ocfs2_write_begin_nolock(struct address_space *mapping,
 					 mmap_page);
 	if (ret) {
 		mlog_errno(ret);
-		goto out_commit;
+		goto out_quota;
 	}
 
 	ret = ocfs2_write_cluster_by_desc(mapping, data_ac, meta_ac, wc, pos,
 					  len);
 	if (ret) {
 		mlog_errno(ret);
-		goto out_commit;
+		goto out_quota;
 	}
 
 	if (data_ac)
@@ -1790,6 +1776,10 @@ int ocfs2_write_begin_nolock(struct address_space *mapping,
 	*pagep = wc->w_target_page;
 	*fsdata = wc;
 	return 0;
+out_quota:
+	if (clusters_to_alloc)
+		vfs_dq_free_space(inode,
+			  ocfs2_clusters_to_bytes(osb->sb, clusters_to_alloc));
 out_commit:
 	ocfs2_commit_trans(osb, handle);
 
@@ -1919,15 +1909,8 @@ int ocfs2_write_end_nolock(struct address_space *mapping,
 		}
 
 		if (page_has_buffers(tmppage)) {
-			if (ocfs2_should_order_data(inode)) {
+			if (ocfs2_should_order_data(inode))
 				ocfs2_jbd2_file_inode(wc->w_handle, inode);
-#ifdef CONFIG_OCFS2_COMPAT_JBD
-				walk_page_buffers(wc->w_handle,
-						  page_buffers(tmppage),
-						  from, to, NULL,
-						  ocfs2_journal_dirty_data);
-#endif
-			}
 			block_commit_write(tmppage, from, to);
 		}
 	}

fs/ocfs2/blockcheck.c

+/* -*- mode: c; c-basic-offset: 8; -*-
+ * vim: noexpandtab sw=8 ts=8 sts=0:
+ *
+ * blockcheck.c
+ *
+ * Checksum and ECC codes for the OCFS2 userspace library.
+ *
+ * Copyright (C) 2006, 2008 Oracle.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License, version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/crc32.h>
+#include <linux/buffer_head.h>
+#include <linux/bitops.h>
+#include <asm/byteorder.h>
+
+#include <cluster/masklog.h>
+
+#include "ocfs2.h"
+
+#include "blockcheck.h"
+
+
+/*
+ * We use the following conventions:
+ *
+ * d = # data bits
+ * p = # parity bits
+ * c = # total code bits (d + p)
+ */
+
+
+/*
+ * Calculate the bit offset in the hamming code buffer based on the bit's
+ * offset in the data buffer.  Since the hamming code reserves all
+ * power-of-two bits for parity, the data bit number and the code bit
+ * number are offest by all the parity bits beforehand.
+ *
+ * Recall that bit numbers in hamming code are 1-based.  This function
+ * takes the 0-based data bit from the caller.
+ *
+ * An example.  Take bit 1 of the data buffer.  1 is a power of two (2^0),
+ * so it's a parity bit.  2 is a power of two (2^1), so it's a parity bit.
+ * 3 is not a power of two.  So bit 1 of the data buffer ends up as bit 3
+ * in the code buffer.
+ *
+ * The caller can pass in *p if it wants to keep track of the most recent
+ * number of parity bits added.  This allows the function to start the
+ * calculation at the last place.
+ */
+static unsigned int calc_code_bit(unsigned int i, unsigned int *p_cache)
+{
+	unsigned int b, p = 0;
+
+	/*
+	 * Data bits are 0-based, but we're talking code bits, which
+	 * are 1-based.
+	 */
+	b = i + 1;
+
+	/* Use the cache if it is there */
+	if (p_cache)
+		p = *p_cache;
+        b += p;
+
+	/*
+	 * For every power of two below our bit number, bump our bit.
+	 *
+	 * We compare with (b + 1) because we have to compare with what b
+	 * would be _if_ it were bumped up by the parity bit.  Capice?
+	 *
+	 * p is set above.
+	 */
+	for (; (1 << p) < (b + 1); p++)
+		b++;
+
+	if (p_cache)
+		*p_cache = p;
+
+	return b;
+}
+
+/*
+ * This is the low level encoder function.  It can be called across
+ * multiple hunks just like the crc32 code.  'd' is the number of bits
+ * _in_this_hunk_.  nr is the bit offset of this hunk.  So, if you had
+ * two 512B buffers, you would do it like so:
+ *
+ * parity = ocfs2_hamming_encode(0, buf1, 512 * 8, 0);
+ * parity = ocfs2_hamming_encode(parity, buf2, 512 * 8, 512 * 8);
+ *
+ * If you just have one buffer, use ocfs2_hamming_encode_block().
+ */
+u32 ocfs2_hamming_encode(u32 parity, void *data, unsigned int d, unsigned int nr)
+{
+	unsigned int i, b, p = 0;
+
+	BUG_ON(!d);
+
+	/*
+	 * b is the hamming code bit number.  Hamming code specifies a
+	 * 1-based array, but C uses 0-based.  So 'i' is for C, and 'b' is
+	 * for the algorithm.
+	 *
+	 * The i++ in the for loop is so that the start offset passed
+	 * to ocfs2_find_next_bit_set() is one greater than the previously
+	 * found bit.
+	 */
+	for (i = 0; (i = ocfs2_find_next_bit(data, d, i)) < d; i++)
+	{
+		/*
+		 * i is the offset in this hunk, nr + i is the total bit
+		 * offset.
+		 */
+		b = calc_code_bit(nr + i, &p);
+
+		/*
+		 * Data bits in the resultant code are checked by
+		 * parity bits that are part of the bit number
+		 * representation.  Huh?
+		 *
+		 * <wikipedia href="http://en.wikipedia.org/wiki/Hamming_code">
+		 * In other words, the parity bit at position 2^k
+		 * checks bits in positions having bit k set in
+		 * their binary representation.  Conversely, for
+		 * instance, bit 13, i.e. 1101(2), is checked by
+		 * bits 1000(2) = 8, 0100(2)=4 and 0001(2) = 1.
+		 * </wikipedia>
+		 *
+		 * Note that 'k' is the _code_ bit number.  'b' in
+		 * our loop.
+		 */
+		parity ^= b;
+	}
+
+	/* While the data buffer was treated as little endian, the
+	 * return value is in host endian. */
+	return parity;
+}
+
+u32 ocfs2_hamming_encode_block(void *data, unsigned int blocksize)
+{
+	return ocfs2_hamming_encode(0, data, blocksize * 8, 0);
+}
+
+/*
+ * Like ocfs2_hamming_encode(), this can handle hunks.  nr is the bit
+ * offset of the current hunk.  If bit to be fixed is not part of the
+ * current hunk, this does nothing.
+ *
+ * If you only have one hunk, use ocfs2_hamming_fix_block().
+ */
+void ocfs2_hamming_fix(void *data, unsigned int d, unsigned int nr,
+		       unsigned int fix)
+{
+	unsigned int i, b;
+
+	BUG_ON(!d);
+
+	/*
+	 * If the bit to fix has an hweight of 1, it's a parity bit.  One
+	 * busted parity bit is its own error.  Nothing to do here.
+	 */
+	if (hweight32(fix) == 1)
+		return;
+
+	/*
+	 * nr + d is the bit right past the data hunk we're looking at.
+	 * If fix after that, nothing to do
+	 */
+	if (fix >= calc_code_bit(nr + d, NULL))
+		return;
+
+	/*
+	 * nr is the offset in the data hunk we're starting at.  Let's
+	 * start b at the offset in the code buffer.  See hamming_encode()
+	 * for a more detailed description of 'b'.
+	 */
+	b = calc_code_bit(nr, NULL);
+	/* If the fix is before this hunk, nothing to do */
+	if (fix < b)
+		return;
+
+	for (i = 0; i < d; i++, b++)
+	{
+		/* Skip past parity bits */
+		while (hweight32(b) == 1)
+			b++;
+
+		/*
+		 * i is the offset in this data hunk.
+		 * nr + i is the offset in the total data buffer.
+		 * b is the offset in the total code buffer.
+		 *
+		 * Thus, when b == fix, bit i in the current hunk needs
+		 * fixing.
+		 */
+		if (b == fix)
+		{
+			if (ocfs2_test_bit(i, data))
+				ocfs2_clear_bit(i, data);
+			else
+				ocfs2_set_bit(i, data);
+			break;
+		}
+	}
+}
+
+void ocfs2_hamming_fix_block(void *data, unsigned int blocksize,
+			     unsigned int fix)
+{
+	ocfs2_hamming_fix(data, blocksize * 8, 0, fix);
+}
+
+/*
+ * This function generates check information for a block.
+ * data is the block to be checked.  bc is a pointer to the
+ * ocfs2_block_check structure describing the crc32 and the ecc.
+ *
+ * bc should be a pointer inside data, as the function will
+ * take care of zeroing it before calculating the check information.  If
+ * bc does not point inside data, the caller must make sure any inline
+ * ocfs2_block_check structures are zeroed.
+ *
+ * The data buffer must be in on-disk endian (little endian for ocfs2).
+ * bc will be filled with little-endian values and will be ready to go to
+ * disk.
+ */
+void ocfs2_block_check_compute(void *data, size_t blocksize,
+			       struct ocfs2_block_check *bc)
+{
+	u32 crc;
+	u32 ecc;
+
+	memset(bc, 0, sizeof(struct ocfs2_block_check));
+
+	crc = crc32_le(~0, data, blocksize);
+	ecc = ocfs2_hamming_encode_block(data, blocksize);
+
+	/*
+	 * No ecc'd ocfs2 structure is larger than 4K, so ecc will be no
+	 * larger than 16 bits.
+	 */
+	BUG_ON(ecc > USHORT_MAX);
+
+	bc->bc_crc32e = cpu_to_le32(crc);
+	bc->bc_ecc = cpu_to_le16((u16)ecc);
+}
+
+/*
+ * This function validates existing check information.  Like _compute,
+ * the function will take care of zeroing bc before calculating check codes.
+ * If bc is not a pointer inside data, the caller must have zeroed any
+ * inline ocfs2_block_check structures.
+ *
+ * Again, the data passed in should be the on-disk endian.
+ */
+int ocfs2_block_check_validate(void *data, size_t blocksize,
+			       struct ocfs2_block_check *bc)
+{
+	int rc = 0;
+	struct ocfs2_block_check check;
+	u32 crc, ecc;
+
+	check.bc_crc32e = le32_to_cpu(bc->bc_crc32e);
+	check.bc_ecc = le16_to_cpu(bc->bc_ecc);
+
+	memset(bc, 0, sizeof(struct ocfs2_block_check));
+
+	/* Fast path - if the crc32 validates, we're good to go */
+	crc = crc32_le(~0, data, blocksize);
+	if (crc == check.bc_crc32e)
+		goto out;
+
+	mlog(ML_ERROR,
+	     "CRC32 failed: stored: %u, computed %u.  Applying ECC.\n",
+	     (unsigned int)check.bc_crc32e, (unsigned int)crc);
+
+	/* Ok, try ECC fixups */
+	ecc = ocfs2_hamming_encode_block(data, blocksize);
+	ocfs2_hamming_fix_block(data, blocksize, ecc ^ check.bc_ecc);
+
+	/* And check the crc32 again */
+	crc = crc32_le(~0, data, blocksize);
+	if (crc == check.bc_crc32e)
+		goto out;
+
+	mlog(ML_ERROR, "Fixed CRC32 failed: stored: %u, computed %u\n",
+	     (unsigned int)check.bc_crc32e, (unsigned int)crc);
+
+	rc = -EIO;
+
+out:
+	bc->bc_crc32e = cpu_to_le32(check.bc_crc32e);
+	bc->bc_ecc = cpu_to_le16(check.bc_ecc);
+
+	return rc;
+}
+
+/*
+ * This function generates check information for a list of buffer_heads.
+ * bhs is the blocks to be checked.  bc is a pointer to the
+ * ocfs2_block_check structure describing the crc32 and the ecc.
+ *
+ * bc should be a pointer inside data, as the function will
+ * take care of zeroing it before calculating the check information.  If
+ * bc does not point inside data, the caller must make sure any inline
+ * ocfs2_block_check structures are zeroed.
+ *
+ * The data buffer must be in on-disk endian (little endian for ocfs2).
+ * bc will be filled with little-endian values and will be ready to go to
+ * disk.
+ */
+void ocfs2_block_check_compute_bhs(struct buffer_head **bhs, int nr,
+				   struct ocfs2_block_check *bc)
+{
+	int i;
+	u32 crc, ecc;
+
+	BUG_ON(nr < 0);
+
+	if (!nr)
+		return;
+
+	memset(bc, 0, sizeof(struct ocfs2_block_check));
+
+	for (i = 0, crc = ~0, ecc = 0; i < nr; i++) {
+		crc = crc32_le(crc, bhs[i]->b_data, bhs[i]->b_size);
+		/*
+		 * The number of bits in a buffer is obviously b_size*8.
+		 * The offset of this buffer is b_size*i, so the bit offset
+		 * of this buffer is b_size*8*i.
+		 */
+		ecc = (u16)ocfs2_hamming_encode(ecc, bhs[i]->b_data,
+						bhs[i]->b_size * 8,
+						bhs[i]->b_size * 8 * i);
+	}
+
+	/*
+	 * No ecc'd ocfs2 structure is larger than 4K, so ecc will be no
+	 * larger than 16 bits.
+	 */
+	BUG_ON(ecc > USHORT_MAX);
+
+	bc->bc_crc32e = cpu_to_le32(crc);
+	bc->bc_ecc = cpu_to_le16((u16)ecc);
+}
+
+/*
+ * This function validates existing check information on a list of
+ * buffer_heads.  Like _compute_bhs, the function will take care of
+ * zeroing bc before calculating check codes.  If bc is not a pointer
+ * inside data, the caller must have zeroed any inline
+ * ocfs2_block_check structures.
+ *
+ * Again, the data passed in should be the on-disk endian.
+ */
+int ocfs2_block_check_validate_bhs(struct buffer_head **bhs, int nr,
+				   struct ocfs2_block_check *bc)
+{
+	int i, rc = 0;
+	struct ocfs2_block_check check;
+	u32 crc, ecc, fix;
+
+	BUG_ON(nr < 0);
+
+	if (!nr)
+		return 0;
+
+	check.bc_crc32e = le32_to_cpu(bc->bc_crc32e);
+	check.bc_ecc = le16_to_cpu(bc->bc_ecc);
+
+	memset(bc, 0, sizeof(struct ocfs2_block_check));
+
+	/* Fast path - if the crc32 validates, we're good to go */
+	for (i = 0, crc = ~0; i < nr; i++)
+		crc = crc32_le(crc, bhs[i]->b_data, bhs[i]->b_size);
+	if (crc == check.bc_crc32e)
+		goto out;
+
+	mlog(ML_ERROR,
+	     "CRC32 failed: stored: %u, computed %u.  Applying ECC.\n",
+	     (unsigned int)check.bc_crc32e, (unsigned int)crc);
+
+	/* Ok, try ECC fixups */
+	for (i = 0, ecc = 0; i < nr; i++) {
+		/*
+		 * The number of bits in a buffer is obviously b_size*8.
+		 * The offset of this buffer is b_size*i, so the bit offset
+		 * of this buffer is b_size*8*i.
+		 */
+		ecc = (u16)ocfs2_hamming_encode(ecc, bhs[i]->b_data,
+						bhs[i]->b_size * 8,
+						bhs[i]->b_size * 8 * i);
+	}
+	fix = ecc ^ check.bc_ecc;
+	for (i = 0; i < nr; i++) {
+		/*
+		 * Try the fix against each buffer.  It will only affect
+		 * one of them.
+		 */
+		ocfs2_hamming_fix(bhs[i]->b_data, bhs[i]->b_size * 8,
+				  bhs[i]->b_size * 8 * i, fix);
+	}
+
+	/* And check the crc32 again */
+	for (i = 0, crc = ~0; i < nr; i++)
+		crc = crc32_le(crc, bhs[i]->b_data, bhs[i]->b_size);
+	if (crc == check.bc_crc32e)
+		goto out;
+
+	mlog(ML_ERROR, "Fixed CRC32 failed: stored: %u, computed %u\n",
+	     (unsigned int)check.bc_crc32e, (unsigned int)crc);
+
+	rc = -EIO;
+
+out:
+	bc->bc_crc32e = cpu_to_le32(check.bc_crc32e);
+	bc->bc_ecc = cpu_to_le16(check.bc_ecc);
+
+	return rc;
+}
+
+/*
+ * These are the main API.  They check the superblock flag before
+ * calling the underlying operations.
+ *
+ * They expect the buffer(s) to be in disk format.
+ */
+void ocfs2_compute_meta_ecc(struct super_block *sb, void *data,
+			    struct ocfs2_block_check *bc)
+{
+	if (ocfs2_meta_ecc(OCFS2_SB(sb)))
+		ocfs2_block_check_compute(data, sb->s_blocksize, bc);
+}
+
+int ocfs2_validate_meta_ecc(struct super_block *sb, void *data,
+			    struct ocfs2_block_check *bc)
+{
+	int rc = 0;
+
+	if (ocfs2_meta_ecc(OCFS2_SB(sb)))
+		rc = ocfs2_block_check_validate(data, sb->s_blocksize, bc);
+
+	return rc;
+}
+
+void ocfs2_compute_meta_ecc_bhs(struct super_block *sb,
+				struct buffer_head **bhs, int nr,
+				struct ocfs2_block_check *bc)
+{
+	if (ocfs2_meta_ecc(OCFS2_SB(sb)))
+		ocfs2_block_check_compute_bhs(bhs, nr, bc);
+}
+
+int ocfs2_validate_meta_ecc_bhs(struct super_block *sb,
+				struct buffer_head **bhs, int nr,
+				struct ocfs2_block_check *bc)
+{
+	int rc = 0;
+
+	if (ocfs2_meta_ecc(OCFS2_SB(sb)))
+		rc = ocfs2_block_check_validate_bhs(bhs, nr, bc);
+
+	return rc;
+}
+

fs/ocfs2/blockcheck.h

+/* -*- mode: c; c-basic-offset: 8; -*-
+ * vim: noexpandtab sw=8 ts=8 sts=0:
+ *
+ * blockcheck.h
+ *
+ * Checksum and ECC codes for the OCFS2 userspace library.
+ *
+ * Copyright (C) 2004, 2008 Oracle.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License, version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+
+#ifndef OCFS2_BLOCKCHECK_H
+#define OCFS2_BLOCKCHECK_H
+
+
+/* High level block API */
+void ocfs2_compute_meta_ecc(struct super_block *sb, void *data,
+			    struct ocfs2_block_check *bc);
+int ocfs2_validate_meta_ecc(struct super_block *sb, void *data,
+			    struct ocfs2_block_check *bc);
+void ocfs2_compute_meta_ecc_bhs(struct super_block *sb,
+				struct buffer_head **bhs, int nr,
+				struct ocfs2_block_check *bc);
+int ocfs2_validate_meta_ecc_bhs(struct super_block *sb,
+				struct buffer_head **bhs, int nr,
+				struct ocfs2_block_check *bc);
+
+/* Lower level API */
+void ocfs2_block_check_compute(void *data, size_t blocksize,
+			       struct ocfs2_block_check *bc);
+int ocfs2_block_check_validate(void *data, size_t blocksize,
+			       struct ocfs2_block_check *bc);
+void ocfs2_block_check_compute_bhs(struct buffer_head **bhs, int nr,
+				   struct ocfs2_block_check *bc);
+int ocfs2_block_check_validate_bhs(struct buffer_head **bhs, int nr,
+				   struct ocfs2_block_check *bc);
+
+/*
+ * Hamming code functions
+ */
+
+/*
+ * Encoding hamming code parity bits for a buffer.
+ *
+ * This is the low level encoder function.  It can be called across
+ * multiple hunks just like the crc32 code.  'd' is the number of bits
+ * _in_this_hunk_.  nr is the bit offset of this hunk.  So, if you had
+ * two 512B buffers, you would do it like so:
+ *
+ * parity = ocfs2_hamming_encode(0, buf1, 512 * 8, 0);
+ * parity = ocfs2_hamming_encode(parity, buf2, 512 * 8, 512 * 8);
+ *
+ * If you just have one buffer, use ocfs2_hamming_encode_block().
+ */
+u32 ocfs2_hamming_encode(u32 parity, void *data, unsigned int d,
+			 unsigned int nr);
+/*
+ * Fix a buffer with a bit error.  The 'fix' is the original parity
+ * xor'd with the parity calculated now.
+ *
+ * Like ocfs2_hamming_encode(), this can handle hunks.  nr is the bit
+ * offset of the current hunk.  If bit to be fixed is not part of the
+ * current hunk, this does nothing.
+ *
+ * If you only have one buffer, use ocfs2_hamming_fix_block().
+ */
+void ocfs2_hamming_fix(void *data, unsigned int d, unsigned int nr,
+		       unsigned int fix);
+
+/* Convenience wrappers for a single buffer of data */
+extern u32 ocfs2_hamming_encode_block(void *data, unsigned int blocksize);
+extern void ocfs2_hamming_fix_block(void *data, unsigned int blocksize,
+				    unsigned int fix);
+#endif

fs/ocfs2/buffer_head_io.c

@@ -39,6 +39,18 @@
 
 #include "buffer_head_io.h"
 
+/*
+ * Bits on bh->b_state used by ocfs2.
+ *
+ * These MUST be after the JBD2 bits.  Hence, we use BH_JBDPrivateStart.
+ */
+enum ocfs2_state_bits {
+	BH_NeedsValidate = BH_JBDPrivateStart,
+};
+
+/* Expand the magic b_state functions */
+BUFFER_FNS(NeedsValidate, needs_validate);
+
 int ocfs2_write_block(struct ocfs2_super *osb, struct buffer_head *bh,
 		      struct inode *inode)
 {
@@ -166,7 +178,9 @@ int ocfs2_read_blocks_sync(struct ocfs2_super *osb, u64 block,
 }
 
 int ocfs2_read_blocks(struct inode *inode, u64 block, int nr,
-		      struct buffer_head *bhs[], int flags)
+		      struct buffer_head *bhs[], int flags,
+		      int (*validate)(struct super_block *sb,
+				      struct buffer_head *bh))
 {
 	int status = 0;
 	int i, ignore_cache = 0;
@@ -298,6 +312,8 @@ int ocfs2_read_blocks(struct inode *inode, u64 block, int nr,
 
 			clear_buffer_uptodate(bh);
 			get_bh(bh); /* for end_buffer_read_sync() */
+			if (validate)
+				set_buffer_needs_validate(bh);
 			bh->b_end_io = end_buffer_read_sync;
 			submit_bh(READ, bh);
 			continue;
@@ -328,6 +344,20 @@ int ocfs2_read_blocks(struct inode *inode, u64 block, int nr,
 				bhs[i] = NULL;
 				continue;
 			}
+
+			if (buffer_needs_validate(bh)) {
+				/* We never set NeedsValidate if the
+				 * buffer was held by the journal, so
+				 * that better not have changed */
+				BUG_ON(buffer_jbd(bh));
+				clear_buffer_needs_validate(bh);
+				status = validate(inode->i_sb, bh);
+				if (status) {
+					put_bh(bh);
+					bhs[i] = NULL;
+					continue;
+				}
+			}
 		}
 
 		/* Always set the buffer in the cache, even if it was

fs/ocfs2/buffer_head_io.h

@@ -31,21 +31,24 @@
 void ocfs2_end_buffer_io_sync(struct buffer_head *bh,
 			     int uptodate);
 
-static inline int ocfs2_read_block(struct inode	       *inode,
-				   u64                  off,
-				   struct buffer_head **bh);
-
 int ocfs2_write_block(struct ocfs2_super          *osb,
 		      struct buffer_head  *bh,
 		      struct inode        *inode);
-int ocfs2_read_blocks(struct inode	  *inode,
-		      u64                  block,
-		      int                  nr,
-		      struct buffer_head  *bhs[],
-		      int                  flags);
 int ocfs2_read_blocks_sync(struct ocfs2_super *osb, u64 block,
 			   unsigned int nr, struct buffer_head *bhs[]);
 
+/*
+ * If not NULL, validate() will be called on a buffer that is freshly
+ * read from disk.  It will not be called if the buffer was in cache.
+ * Note that if validate() is being used for this buffer, it needs to
+ * be set even for a READAHEAD call, as it marks the buffer for later
+ * validation.
+ */
+int ocfs2_read_blocks(struct inode *inode, u64 block, int nr,
+		      struct buffer_head *bhs[], int flags,
+		      int (*validate)(struct super_block *sb,
+				      struct buffer_head *bh));
+
 int ocfs2_write_super_or_backup(struct ocfs2_super *osb,
 				struct buffer_head *bh);
 
@@ -53,7 +56,9 @@ int ocfs2_write_super_or_backup(struct ocfs2_super *osb,
 #define OCFS2_BH_READAHEAD         8
 
 static inline int ocfs2_read_block(struct inode *inode, u64 off,
-				   struct buffer_head **bh)
+				   struct buffer_head **bh,
+				   int (*validate)(struct super_block *sb,
+						   struct buffer_head *bh))
 {
 	int status = 0;
 
@@ -63,7 +68,7 @@ static inline int ocfs2_read_block(struct inode *inode, u64 off,
 		goto bail;
 	}
 
-	status = ocfs2_read_blocks(inode, off, 1, bh, 0);
+	status = ocfs2_read_blocks(inode, off, 1, bh, 0, validate);
 
 bail:
 	return status;

fs/ocfs2/cluster/masklog.c

@@ -110,6 +110,7 @@ static struct mlog_attribute mlog_attrs[MLOG_MAX_BITS] = {
 	define_mask(QUORUM),
 	define_mask(EXPORT),
 	define_mask(XATTR),
+	define_mask(QUOTA),
 	define_mask(ERROR),
 	define_mask(NOTICE),
 	define_mask(KTHREAD),

fs/ocfs2/cluster/masklog.h

@@ -113,6 +113,7 @@
 #define ML_QUORUM	0x0000000008000000ULL /* net connection quorum */
 #define ML_EXPORT	0x0000000010000000ULL /* ocfs2 export operations */
 #define ML_XATTR	0x0000000020000000ULL /* ocfs2 extended attributes */
+#define ML_QUOTA	0x0000000040000000ULL /* ocfs2 quota operations */
 /* bits that are infrequently given and frequently matched in the high word */
 #define ML_ERROR	0x0000000100000000ULL /* sent to KERN_ERR */
 #define ML_NOTICE	0x0000000200000000ULL /* setn to KERN_NOTICE */

fs/ocfs2/dir.h

@@ -83,4 +83,6 @@ int ocfs2_fill_new_dir(struct ocfs2_super *osb,
 		       struct buffer_head *fe_bh,
 		       struct ocfs2_alloc_context *data_ac);
 
+struct ocfs2_dir_block_trailer *ocfs2_dir_trailer_from_size(int blocksize,
+							    void *data);
 #endif /* OCFS2_DIR_H */

fs/ocfs2/dlm/dlmast.c

@@ -275,6 +275,7 @@ int dlm_proxy_ast_handler(struct o2net_msg *msg, u32 len, void *data,
 	struct list_head *iter, *head=NULL;
 	u64 cookie;
 	u32 flags;
+	u8 node;
 
 	if (!dlm_grab(dlm)) {
 		dlm_error(DLM_REJECTED);
@@ -286,18 +287,21 @@ int dlm_proxy_ast_handler(struct o2net_msg *msg, u32 len, void *data,
 
 	name = past->name;
 	locklen = past->namelen;
-	cookie = be64_to_cpu(past->cookie);
+	cookie = past->cookie;
 	flags = be32_to_cpu(past->flags);
+	node = past->node_idx;
 
 	if (locklen > DLM_LOCKID_NAME_MAX) {
 		ret = DLM_IVBUFLEN;
-		mlog(ML_ERROR, "Invalid name length in proxy ast handler!\n");
+		mlog(ML_ERROR, "Invalid name length (%d) in proxy ast "
+		     "handler!\n", locklen);
 		goto leave;
 	}
 
 	if ((flags & (LKM_PUT_LVB|LKM_GET_LVB)) ==
 	     (LKM_PUT_LVB|LKM_GET_LVB)) {
-		mlog(ML_ERROR, "both PUT and GET lvb specified\n");
+		mlog(ML_ERROR, "Both PUT and GET lvb specified, (0x%x)\n",
+		     flags);
 		ret = DLM_BADARGS;
 		goto leave;
 	}
@@ -310,22 +314,21 @@ int dlm_proxy_ast_handler(struct o2net_msg *msg, u32 len, void *data,
 	if (past->type != DLM_AST &&
 	    past->type != DLM_BAST) {
 		mlog(ML_ERROR, "Unknown ast type! %d, cookie=%u:%llu"
-		     "name=%.*s\n", past->type, 
-		     dlm_get_lock_cookie_node(cookie),
-		     dlm_get_lock_cookie_seq(cookie),
-		     locklen, name);
+		     "name=%.*s, node=%u\n", past->type,
+		     dlm_get_lock_cookie_node(be64_to_cpu(cookie)),
+		     dlm_get_lock_cookie_seq(be64_to_cpu(cookie)),
+		     locklen, name, node);
 		ret = DLM_IVLOCKID;
 		goto leave;
 	}
 
 	res = dlm_lookup_lockres(dlm, name, locklen);
 	if (!res) {
-		mlog(0, "got %sast for unknown lockres! "
-		     "cookie=%u:%llu, name=%.*s, namelen=%u\n",
-		     past->type == DLM_AST ? "" : "b",
-		     dlm_get_lock_cookie_node(cookie),
-		     dlm_get_lock_cookie_seq(cookie),
-		     locklen, name, locklen);
+		mlog(0, "Got %sast for unknown lockres! cookie=%u:%llu, "
+		     "name=%.*s, node=%u\n", (past->type == DLM_AST ? "" : "b"),
+		     dlm_get_lock_cookie_node(be64_to_cpu(cookie)),
+		     dlm_get_lock_cookie_seq(be64_to_cpu(cookie)),
+		     locklen, name, node);
 		ret = DLM_IVLOCKID;
 		goto leave;
 	}
@@ -337,12 +340,12 @@ int dlm_proxy_ast_handler(struct o2net_msg *msg, u32 len, void *data,
 
 	spin_lock(&res->spinlock);
 	if (res->state & DLM_LOCK_RES_RECOVERING) {
-		mlog(0, "responding with DLM_RECOVERING!\n");
+		mlog(0, "Responding with DLM_RECOVERING!\n");
 		ret = DLM_RECOVERING;
 		goto unlock_out;
 	}
 	if (res->state & DLM_LOCK_RES_MIGRATING) {
-		mlog(0, "responding with DLM_MIGRATING!\n");
+		mlog(0, "Responding with DLM_MIGRATING!\n");
 		ret = DLM_MIGRATING;
 		goto unlock_out;
 	}
@@ -351,7 +354,7 @@ int dlm_proxy_ast_handler(struct o2net_msg *msg, u32 len, void *data,
 	lock = NULL;
 	list_for_each(iter, head) {
 		lock = list_entry (iter, struct dlm_lock, list);
-		if (be64_to_cpu(lock->ml.cookie) == cookie)
+		if (lock->ml.cookie == cookie)
 			goto do_ast;
 	}
 
@@ -363,15 +366,15 @@ int dlm_proxy_ast_handler(struct o2net_msg *msg, u32 len, void *data,
 
 	list_for_each(iter, head) {
 		lock = list_entry (iter, struct dlm_lock, list);
-		if (be64_to_cpu(lock->ml.cookie) == cookie)
+		if (lock->ml.cookie == cookie)
 			goto do_ast;
 	}
 
-	mlog(0, "got %sast for unknown lock!  cookie=%u:%llu, "
-	     "name=%.*s, namelen=%u\n", past->type == DLM_AST ? "" : "b", 
-	     dlm_get_lock_cookie_node(cookie),
-	     dlm_get_lock_cookie_seq(cookie),
-	     locklen, name, locklen);
+	mlog(0, "Got %sast for unknown lock! cookie=%u:%llu, name=%.*s, "
+	     "node=%u\n", past->type == DLM_AST ? "" : "b",
+	     dlm_get_lock_cookie_node(be64_to_cpu(cookie)),
+	     dlm_get_lock_cookie_seq(be64_to_cpu(cookie)),
+	     locklen, name, node);
 
 	ret = DLM_NORMAL;
 unlock_out:
@@ -383,7 +386,7 @@ int dlm_proxy_ast_handler(struct o2net_msg *msg, u32 len, void *data,
 	if (past->type == DLM_AST) {
 		/* do not alter lock refcount.  switching lists. */
 		list_move_tail(&lock->list, &res->granted);
-		mlog(0, "ast: adding to granted list... type=%d, "
+		mlog(0, "ast: Adding to granted list... type=%d, "
 		     "convert_type=%d\n", lock->ml.type, lock->ml.convert_type);
 		if (lock->ml.convert_type != LKM_IVMODE) {
 			lock->ml.type = lock->ml.convert_type;
@@ -408,7 +411,6 @@ int dlm_proxy_ast_handler(struct o2net_msg *msg, u32 len, void *data,
 		dlm_do_local_bast(dlm, res, lock, past->blocked_type);
 
 leave:
-
 	if (res)
 		dlm_lockres_put(res);
 

fs/ocfs2/dlm/dlmcommon.h

@@ -140,6 +140,7 @@ struct dlm_ctxt
 	unsigned int purge_count;
 	spinlock_t spinlock;
 	spinlock_t ast_lock;
+	spinlock_t track_lock;
 	char *name;
 	u8 node_num;
 	u32 key;
@@ -316,6 +317,8 @@ struct dlm_lock_resource
 	 * put on a list for the dlm thread to run. */
 	unsigned long    last_used;
 
+	struct dlm_ctxt *dlm;
+
 	unsigned migration_pending:1;
 	atomic_t asts_reserved;
 	spinlock_t spinlock;

fs/ocfs2/dlm/dlmdebug.c

@@ -630,43 +630,38 @@ static void *lockres_seq_start(struct seq_file *m, loff_t *pos)
 {
 	struct debug_lockres *dl = m->private;
 	struct dlm_ctxt *dlm = dl->dl_ctxt;
+	struct dlm_lock_resource *oldres = dl->dl_res;
 	struct dlm_lock_resource *res = NULL;
+	struct list_head *track_list;
 
-	spin_lock(&dlm->spinlock);
+	spin_lock(&dlm->track_lock);
+	if (oldres)
+		track_list = &oldres->tracking;
+	else
+		track_list = &dlm->tracking_list;
 
-	if (dl->dl_res) {
-		list_for_each_entry(res, &dl->dl_res->tracking, tracking) {
-			if (dl->dl_res) {
-				dlm_lockres_put(dl->dl_res);
-				dl->dl_res = NULL;
-			}
-			if (&res->tracking == &dlm->tracking_list) {
-				mlog(0, "End of list found, %p\n", res);
-				dl = NULL;
-				break;
-			}
+	list_for_each_entry(res, track_list, tracking) {
+		if (&res->tracking == &dlm->tracking_list)
+			res = NULL;
+		else
 			dlm_lockres_get(res);
-			dl->dl_res = res;
 		break;
 	}
-	} else {
-		if (!list_empty(&dlm->tracking_list)) {
-			list_for_each_entry(res, &dlm->tracking_list, tracking)
-				break;
-			dlm_lockres_get(res);
+	spin_unlock(&dlm->track_lock);
+
+	if (oldres)
+		dlm_lockres_put(oldres);
+
 	dl->dl_res = res;
+
+	if (res) {
+		spin_lock(&res->spinlock);
+		dump_lockres(res, dl->dl_buf, dl->dl_len - 1);
+		spin_unlock(&res->spinlock);
 	} else
 		dl = NULL;
-	}
-
-	if (dl) {
-		spin_lock(&dl->dl_res->spinlock);
-		dump_lockres(dl->dl_res, dl->dl_buf, dl->dl_len - 1);
-		spin_unlock(&dl->dl_res->spinlock);
-	}
-
-	spin_unlock(&dlm->spinlock);
 
+	/* passed to seq_show */
 	return dl;
 }
 

fs/ocfs2/dlm/dlmdomain.c

@@ -1550,6 +1550,7 @@ static struct dlm_ctxt *dlm_alloc_ctxt(const char *domain,
 	spin_lock_init(&dlm->spinlock);
 	spin_lock_init(&dlm->master_lock);
 	spin_lock_init(&dlm->ast_lock);
+	spin_lock_init(&dlm->track_lock);
 	INIT_LIST_HEAD(&dlm->list);
 	INIT_LIST_HEAD(&dlm->dirty_list);
 	INIT_LIST_HEAD(&dlm->reco.resources);

fs/ocfs2/dlm/dlmmaster.c

@@ -505,8 +505,10 @@ void dlm_change_lockres_owner(struct dlm_ctxt *dlm,
 static void dlm_lockres_release(struct kref *kref)
 {
 	struct dlm_lock_resource *res;
+	struct dlm_ctxt *dlm;
 
 	res = container_of(kref, struct dlm_lock_resource, refs);
+	dlm = res->dlm;
 
 	/* This should not happen -- all lockres' have a name
 	 * associated with them at init time. */
@@ -515,6 +517,7 @@ static void dlm_lockres_release(struct kref *kref)
 	mlog(0, "destroying lockres %.*s\n", res->lockname.len,
 	     res->lockname.name);
 
+	spin_lock(&dlm->track_lock);
 	if (!list_empty(&res->tracking))
 		list_del_init(&res->tracking);
 	else {
@@ -522,6 +525,9 @@ static void dlm_lockres_release(struct kref *kref)
 		     res->lockname.len, res->lockname.name);
 		dlm_print_one_lock_resource(res);
 	}
+	spin_unlock(&dlm->track_lock);
+
+	dlm_put(dlm);
 
 	if (!hlist_unhashed(&res->hash_node) ||
 	    !list_empty(&res->granted) ||
@@ -595,6 +601,10 @@ static void dlm_init_lockres(struct dlm_ctxt *dlm,
 	res->migration_pending = 0;
 	res->inflight_locks = 0;
 
+	/* put in dlm_lockres_release */
+	dlm_grab(dlm);
+	res->dlm = dlm;
+
 	kref_init(&res->refs);
 
 	/* just for consistency */
@@ -722,14 +732,21 @@ struct dlm_lock_resource * dlm_get_lock_resource(struct dlm_ctxt *dlm,
 	if (tmpres) {
 		int dropping_ref = 0;
 
+		spin_unlock(&dlm->spinlock);
+
 		spin_lock(&tmpres->spinlock);
+		/* We wait for the other thread that is mastering the resource */
+		if (tmpres->owner == DLM_LOCK_RES_OWNER_UNKNOWN) {
+			__dlm_wait_on_lockres(tmpres);
+			BUG_ON(tmpres->owner == DLM_LOCK_RES_OWNER_UNKNOWN);
+		}
+
 		if (tmpres->owner == dlm->node_num) {
 			BUG_ON(tmpres->state & DLM_LOCK_RES_DROPPING_REF);
 			dlm_lockres_grab_inflight_ref(dlm, tmpres);
 		} else if (tmpres->state & DLM_LOCK_RES_DROPPING_REF)
 			dropping_ref = 1;
 		spin_unlock(&tmpres->spinlock);
-		spin_unlock(&dlm->spinlock);
 
 		/* wait until done messaging the master, drop our ref to allow
 		 * the lockres to be purged, start over. */
@@ -2949,7 +2966,7 @@ static int dlm_do_migrate_request(struct dlm_ctxt *dlm,
 				  struct dlm_node_iter *iter)
 {
 	struct dlm_migrate_request migrate;
-	int ret, status = 0;
+	int ret, skip, status = 0;
 	int nodenum;
 
 	memset(&migrate, 0, sizeof(migrate));
@@ -2966,12 +2983,27 @@ static int dlm_do_migrate_request(struct dlm_ctxt *dlm,
 		    nodenum == new_master)
 			continue;
 
+		/* We could race exit domain. If exited, skip. */
+		spin_lock(&dlm->spinlock);
+		skip = (!test_bit(nodenum, dlm->domain_map));
+		spin_unlock(&dlm->spinlock);
+		if (skip) {
+			clear_bit(nodenum, iter->node_map);
+			continue;
+		}
+
 		ret = o2net_send_message(DLM_MIGRATE_REQUEST_MSG, dlm->key,
 					 &migrate, sizeof(migrate), nodenum,
 					 &status);
-		if (ret < 0)
-			mlog_errno(ret);
-		else if (status < 0) {
+		if (ret < 0) {
+			mlog(0, "migrate_request returned %d!\n", ret);
+			if (!dlm_is_host_down(ret)) {
+				mlog(ML_ERROR, "unhandled error=%d!\n", ret);
+				BUG();
+			}
+			clear_bit(nodenum, iter->node_map);
+			ret = 0;
+		} else if (status < 0) {
 			mlog(0, "migrate request (node %u) returned %d!\n",
 			     nodenum, status);
 			ret = status;

fs/ocfs2/dlm/dlmthread.c

@@ -181,7 +181,8 @@ static int dlm_purge_lockres(struct dlm_ctxt *dlm,
 
 		spin_lock(&res->spinlock);
 		/* This ensures that clear refmap is sent after the set */
-		__dlm_wait_on_lockres_flags(res, DLM_LOCK_RES_SETREF_INPROG);
+		__dlm_wait_on_lockres_flags(res, (DLM_LOCK_RES_SETREF_INPROG |
+						  DLM_LOCK_RES_MIGRATING));
 		spin_unlock(&res->spinlock);
 
 		/* clear our bit from the master's refmap, ignore errors */

fs/ocfs2/dlmglue.h

@@ -49,6 +49,19 @@ struct ocfs2_meta_lvb {
 	__be32       lvb_reserved2;
 };
 
+#define OCFS2_QINFO_LVB_VERSION 1
+
+struct ocfs2_qinfo_lvb {
+	__u8	lvb_version;
+	__u8	lvb_reserved[3];
+	__be32	lvb_bgrace;
+	__be32	lvb_igrace;
+	__be32	lvb_syncms;
+	__be32	lvb_blocks;
+	__be32	lvb_free_blk;
+	__be32	lvb_free_entry;
+};
+
 /* ocfs2_inode_lock_full() 'arg_flags' flags */
 /* don't wait on recovery. */
 #define OCFS2_META_LOCK_RECOVERY	(0x01)
@@ -69,6 +82,9 @@ void ocfs2_dentry_lock_res_init(struct ocfs2_dentry_lock *dl,
 struct ocfs2_file_private;
 void ocfs2_file_lock_res_init(struct ocfs2_lock_res *lockres,
 			      struct ocfs2_file_private *fp);
+struct ocfs2_mem_dqinfo;
+void ocfs2_qinfo_lock_res_init(struct ocfs2_lock_res *lockres,
+                               struct ocfs2_mem_dqinfo *info);
 void ocfs2_lock_res_free(struct ocfs2_lock_res *res);
 int ocfs2_create_new_inode_locks(struct inode *inode);
 int ocfs2_drop_inode_locks(struct inode *inode);
@@ -103,6 +119,9 @@ int ocfs2_dentry_lock(struct dentry *dentry, int ex);
 void ocfs2_dentry_unlock(struct dentry *dentry, int ex);
 int ocfs2_file_lock(struct file *file, int ex, int trylock);
 void ocfs2_file_unlock(struct file *file);
+int ocfs2_qinfo_lock(struct ocfs2_mem_dqinfo *oinfo, int ex);
+void ocfs2_qinfo_unlock(struct ocfs2_mem_dqinfo *oinfo, int ex);
+
 
 void ocfs2_mark_lockres_freeing(struct ocfs2_lock_res *lockres);
 void ocfs2_simple_drop_lockres(struct ocfs2_super *osb,

fs/ocfs2/extent_map.h

@@ -57,4 +57,28 @@ int ocfs2_xattr_get_clusters(struct inode *inode, u32 v_cluster,
 			     u32 *p_cluster, u32 *num_clusters,
 			     struct ocfs2_extent_list *el);
 
+int ocfs2_read_virt_blocks(struct inode *inode, u64 v_block, int nr,
+			   struct buffer_head *bhs[], int flags,
+			   int (*validate)(struct super_block *sb,
+					   struct buffer_head *bh));
+static inline int ocfs2_read_virt_block(struct inode *inode, u64 v_block,
+					struct buffer_head **bh,
+					int (*validate)(struct super_block *sb,
+							struct buffer_head *bh))
+{
+	int status = 0;
+
+	if (bh == NULL) {
+		printk("ocfs2: bh == NULL\n");
+		status = -EINVAL;
+		goto bail;
+	}
+
+	status = ocfs2_read_virt_blocks(inode, v_block, 1, bh, 0, validate);
+
+bail:
+	return status;
+}
+
+
 #endif  /* _EXTENT_MAP_H */

fs/ocfs2/file.h

@@ -51,6 +51,9 @@ int ocfs2_add_inode_data(struct ocfs2_super *osb,
 			 struct ocfs2_alloc_context *data_ac,
 			 struct ocfs2_alloc_context *meta_ac,
 			 enum ocfs2_alloc_restarted *reason_ret);
+int ocfs2_simple_size_update(struct inode *inode,
+			     struct buffer_head *di_bh,
+			     u64 new_i_size);
 int ocfs2_extend_no_holes(struct inode *inode, u64 new_i_size,
 			  u64 zero_to);
 int ocfs2_setattr(struct dentry *dentry, struct iattr *attr);

fs/ocfs2/inode.h

@@ -128,7 +128,7 @@ struct inode *ocfs2_iget(struct ocfs2_super *osb, u64 feoff, unsigned flags,
 			 int sysfile_type);
 int ocfs2_inode_init_private(struct inode *inode);
 int ocfs2_inode_revalidate(struct dentry *dentry);
-int ocfs2_populate_inode(struct inode *inode, struct ocfs2_dinode *fe,
+void ocfs2_populate_inode(struct inode *inode, struct ocfs2_dinode *fe,
 			  int create_ino);
 void ocfs2_read_inode(struct inode *inode);
 void ocfs2_read_inode2(struct inode *inode, void *opaque);
@@ -142,6 +142,8 @@ int ocfs2_mark_inode_dirty(handle_t *handle,
 			   struct buffer_head *bh);
 int ocfs2_aio_read(struct file *file, struct kiocb *req, struct iocb *iocb);
 int ocfs2_aio_write(struct file *file, struct kiocb *req, struct iocb *iocb);
+struct buffer_head *ocfs2_bread(struct inode *inode,
+				int block, int *err, int reada);
 
 void ocfs2_set_inode_flags(struct inode *inode);
 void ocfs2_get_inode_flags(struct ocfs2_inode_info *oi);
@@ -153,4 +155,16 @@ static inline blkcnt_t ocfs2_inode_sector_count(struct inode *inode)
 	return (blkcnt_t)(OCFS2_I(inode)->ip_clusters << c_to_s_bits);
 }
 
+/* Validate that a bh contains a valid inode */
+int ocfs2_validate_inode_block(struct super_block *sb,
+			       struct buffer_head *bh);
+/*
+ * Read an inode block into *bh.  If *bh is NULL, a bh will be allocated.
+ * This is a cached read.  The inode will be validated with
+ * ocfs2_validate_inode_block().
+ */
+int ocfs2_read_inode_block(struct inode *inode, struct buffer_head **bh);
+/* The same, but can be passed OCFS2_BH_* flags */
+int ocfs2_read_inode_block_full(struct inode *inode, struct buffer_head **bh,
+				int flags);
 #endif /* OCFS2_INODE_H */

fs/ocfs2/ocfs2_lockid.h

@@ -46,6 +46,7 @@ enum ocfs2_lock_type {
 	OCFS2_LOCK_TYPE_DENTRY,
 	OCFS2_LOCK_TYPE_OPEN,
 	OCFS2_LOCK_TYPE_FLOCK,
+	OCFS2_LOCK_TYPE_QINFO,
 	OCFS2_NUM_LOCK_TYPES
 };
 
@@ -77,6 +78,9 @@ static inline char ocfs2_lock_type_char(enum ocfs2_lock_type type)
 		case OCFS2_LOCK_TYPE_FLOCK:
 			c = 'F';
 			break;
+		case OCFS2_LOCK_TYPE_QINFO:
+			c = 'Q';
+			break;
 		default:
 			c = '\0';
 	}
@@ -95,6 +99,7 @@ static char *ocfs2_lock_type_strings[] = {
 	[OCFS2_LOCK_TYPE_DENTRY] = "Dentry",
 	[OCFS2_LOCK_TYPE_OPEN] = "Open",
 	[OCFS2_LOCK_TYPE_FLOCK] = "Flock",
+	[OCFS2_LOCK_TYPE_QINFO] = "Quota",
 };
 
 static inline const char *ocfs2_lock_type_string(enum ocfs2_lock_type type)

fs/ocfs2/slot_map.c

@@ -151,7 +151,7 @@ int ocfs2_refresh_slot_info(struct ocfs2_super *osb)
 	 * this is not true, the read of -1 (UINT64_MAX) will fail.
 	 */
 	ret = ocfs2_read_blocks(si->si_inode, -1, si->si_blocks, si->si_bh,
-				OCFS2_BH_IGNORE_CACHE);
+				OCFS2_BH_IGNORE_CACHE, NULL);
 	if (ret == 0) {
 		spin_lock(&osb->osb_lock);
 		ocfs2_update_slot_info(si);
@@ -405,7 +405,7 @@ static int ocfs2_map_slot_buffers(struct ocfs2_super *osb,
 
 		bh = NULL;  /* Acquire a fresh bh */
 		status = ocfs2_read_blocks(si->si_inode, blkno, 1, &bh,
-					   OCFS2_BH_IGNORE_CACHE);
+					   OCFS2_BH_IGNORE_CACHE, NULL);
 		if (status < 0) {
 			mlog_errno(status);
 			goto bail;

fs/ocfs2/symlink.c

@@ -84,7 +84,7 @@ static char *ocfs2_fast_symlink_getlink(struct inode *inode,
 
 	mlog_entry_void();
 
-	status = ocfs2_read_block(inode, OCFS2_I(inode)->ip_blkno, bh);
+	status = ocfs2_read_inode_block(inode, bh);
 	if (status < 0) {
 		mlog_errno(status);
 		link = ERR_PTR(status);