Commit 10cc04f5 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

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.
  ...
parents 520c8534 9047beab
......@@ -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.
......@@ -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.
......
......@@ -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/
......
This diff is collapsed.
......@@ -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;
......
......@@ -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;
......
......@@ -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);
......
......@@ -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;
}
/*
......
......@@ -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.
......
......@@ -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
......
/* -*- 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