summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/debugfs/inode.c69
-rw-r--r--fs/dlm/user.c1
-rw-r--r--fs/ext4/extents.c2
-rw-r--r--fs/ext4/ialloc.c10
-rw-r--r--fs/ext4/inode.c39
-rw-r--r--fs/ext4/super.c1
-rw-r--r--fs/fcntl.c4
-rw-r--r--fs/fuse/dir.c51
-rw-r--r--fs/namei.c10
-rw-r--r--fs/nfs/nfs4xdr.c2
-rw-r--r--fs/ocfs2/refcounttree.c5
-rw-r--r--fs/open.c2
-rw-r--r--fs/reiserfs/procfs.c99
-rw-r--r--fs/reiserfs/super.c3
-rw-r--r--fs/xfs/xfs_dinode.h3
-rw-r--r--fs/xfs/xfs_inode.c31
-rw-r--r--fs/xfs/xfs_log_recover.c13
17 files changed, 151 insertions, 194 deletions
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 4888cb3fdef7..c7c83ff0f752 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -533,8 +533,7 @@ EXPORT_SYMBOL_GPL(debugfs_remove);
*/
void debugfs_remove_recursive(struct dentry *dentry)
{
- struct dentry *child;
- struct dentry *parent;
+ struct dentry *child, *next, *parent;
if (IS_ERR_OR_NULL(dentry))
return;
@@ -544,61 +543,37 @@ void debugfs_remove_recursive(struct dentry *dentry)
return;
parent = dentry;
+ down:
mutex_lock(&parent->d_inode->i_mutex);
+ list_for_each_entry_safe(child, next, &parent->d_subdirs, d_u.d_child) {
+ if (!debugfs_positive(child))
+ continue;
- while (1) {
- /*
- * When all dentries under "parent" has been removed,
- * walk up the tree until we reach our starting point.
- */
- if (list_empty(&parent->d_subdirs)) {
- mutex_unlock(&parent->d_inode->i_mutex);
- if (parent == dentry)
- break;
- parent = parent->d_parent;
- mutex_lock(&parent->d_inode->i_mutex);
- }
- child = list_entry(parent->d_subdirs.next, struct dentry,
- d_u.d_child);
- next_sibling:
-
- /*
- * If "child" isn't empty, walk down the tree and
- * remove all its descendants first.
- */
+ /* perhaps simple_empty(child) makes more sense */
if (!list_empty(&child->d_subdirs)) {
mutex_unlock(&parent->d_inode->i_mutex);
parent = child;
- mutex_lock(&parent->d_inode->i_mutex);
- continue;
+ goto down;
}
- __debugfs_remove(child, parent);
- if (parent->d_subdirs.next == &child->d_u.d_child) {
- /*
- * Try the next sibling.
- */
- if (child->d_u.d_child.next != &parent->d_subdirs) {
- child = list_entry(child->d_u.d_child.next,
- struct dentry,
- d_u.d_child);
- goto next_sibling;
- }
-
- /*
- * Avoid infinite loop if we fail to remove
- * one dentry.
- */
- mutex_unlock(&parent->d_inode->i_mutex);
- break;
- }
- simple_release_fs(&debugfs_mount, &debugfs_mount_count);
+ up:
+ if (!__debugfs_remove(child, parent))
+ simple_release_fs(&debugfs_mount, &debugfs_mount_count);
}
- parent = dentry->d_parent;
+ mutex_unlock(&parent->d_inode->i_mutex);
+ child = parent;
+ parent = parent->d_parent;
mutex_lock(&parent->d_inode->i_mutex);
- __debugfs_remove(dentry, parent);
+
+ if (child != dentry) {
+ next = list_entry(child->d_u.d_child.next, struct dentry,
+ d_u.d_child);
+ goto up;
+ }
+
+ if (!__debugfs_remove(child, parent))
+ simple_release_fs(&debugfs_mount, &debugfs_mount_count);
mutex_unlock(&parent->d_inode->i_mutex);
- simple_release_fs(&debugfs_mount, &debugfs_mount_count);
}
EXPORT_SYMBOL_GPL(debugfs_remove_recursive);
diff --git a/fs/dlm/user.c b/fs/dlm/user.c
index 911649a47dd5..812149119fa3 100644
--- a/fs/dlm/user.c
+++ b/fs/dlm/user.c
@@ -686,7 +686,6 @@ static int device_close(struct inode *inode, struct file *file)
device_remove_lockspace() */
sigprocmask(SIG_SETMASK, &tmpsig, NULL);
- recalc_sigpending();
return 0;
}
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index a61873808f76..72ba4705d4fa 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -4412,7 +4412,7 @@ void ext4_ext_truncate(handle_t *handle, struct inode *inode)
retry:
err = ext4_es_remove_extent(inode, last_block,
EXT_MAX_BLOCKS - last_block);
- if (err == ENOMEM) {
+ if (err == -ENOMEM) {
cond_resched();
congestion_wait(BLK_RW_ASYNC, HZ/50);
goto retry;
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index f03598c6ffd3..8bf5999875ee 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -734,11 +734,8 @@ repeat_in_this_group:
ino = ext4_find_next_zero_bit((unsigned long *)
inode_bitmap_bh->b_data,
EXT4_INODES_PER_GROUP(sb), ino);
- if (ino >= EXT4_INODES_PER_GROUP(sb)) {
- if (++group == ngroups)
- group = 0;
- continue;
- }
+ if (ino >= EXT4_INODES_PER_GROUP(sb))
+ goto next_group;
if (group == 0 && (ino+1) < EXT4_FIRST_INO(sb)) {
ext4_error(sb, "reserved inode found cleared - "
"inode=%lu", ino + 1);
@@ -769,6 +766,9 @@ repeat_in_this_group:
goto got; /* we grabbed the inode! */
if (ino < EXT4_INODES_PER_GROUP(sb))
goto repeat_in_this_group;
+next_group:
+ if (++group == ngroups)
+ group = 0;
}
err = -ENOSPC;
goto out;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index ba33c67d6e48..dd32a2eacd0d 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -555,14 +555,13 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
int ret;
unsigned long long status;
-#ifdef ES_AGGRESSIVE_TEST
- if (retval != map->m_len) {
- printk("ES len assertion failed for inode: %lu "
- "retval %d != map->m_len %d "
- "in %s (lookup)\n", inode->i_ino, retval,
- map->m_len, __func__);
+ if (unlikely(retval != map->m_len)) {
+ ext4_warning(inode->i_sb,
+ "ES len assertion failed for inode "
+ "%lu: retval %d != map->m_len %d",
+ inode->i_ino, retval, map->m_len);
+ WARN_ON(1);
}
-#endif
status = map->m_flags & EXT4_MAP_UNWRITTEN ?
EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
@@ -656,14 +655,13 @@ found:
int ret;
unsigned long long status;
-#ifdef ES_AGGRESSIVE_TEST
- if (retval != map->m_len) {
- printk("ES len assertion failed for inode: %lu "
- "retval %d != map->m_len %d "
- "in %s (allocation)\n", inode->i_ino, retval,
- map->m_len, __func__);
+ if (unlikely(retval != map->m_len)) {
+ ext4_warning(inode->i_sb,
+ "ES len assertion failed for inode "
+ "%lu: retval %d != map->m_len %d",
+ inode->i_ino, retval, map->m_len);
+ WARN_ON(1);
}
-#endif
/*
* If the extent has been zeroed out, we don't need to update
@@ -1637,14 +1635,13 @@ add_delayed:
int ret;
unsigned long long status;
-#ifdef ES_AGGRESSIVE_TEST
- if (retval != map->m_len) {
- printk("ES len assertion failed for inode: %lu "
- "retval %d != map->m_len %d "
- "in %s (lookup)\n", inode->i_ino, retval,
- map->m_len, __func__);
+ if (unlikely(retval != map->m_len)) {
+ ext4_warning(inode->i_sb,
+ "ES len assertion failed for inode "
+ "%lu: retval %d != map->m_len %d",
+ inode->i_ino, retval, map->m_len);
+ WARN_ON(1);
}
-#endif
status = map->m_flags & EXT4_MAP_UNWRITTEN ?
EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index bca26f34edf4..36b141e420b7 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -5481,6 +5481,7 @@ static void __exit ext4_exit_fs(void)
kset_unregister(ext4_kset);
ext4_exit_system_zone();
ext4_exit_pageio();
+ ext4_exit_es();
}
MODULE_AUTHOR("Remy Card, Stephen Tweedie, Andrew Morton, Andreas Dilger, Theodore Ts'o and others");
diff --git a/fs/fcntl.c b/fs/fcntl.c
index 6599222536eb..65343c3741ff 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -730,14 +730,14 @@ static int __init fcntl_init(void)
* Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY
* is defined as O_NONBLOCK on some platforms and not on others.
*/
- BUILD_BUG_ON(19 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32(
+ BUILD_BUG_ON(20 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32(
O_RDONLY | O_WRONLY | O_RDWR |
O_CREAT | O_EXCL | O_NOCTTY |
O_TRUNC | O_APPEND | /* O_NONBLOCK | */
__O_SYNC | O_DSYNC | FASYNC |
O_DIRECT | O_LARGEFILE | O_DIRECTORY |
O_NOFOLLOW | O_NOATIME | O_CLOEXEC |
- __FMODE_EXEC | O_PATH
+ __FMODE_EXEC | O_PATH | __O_TMPFILE
));
fasync_cache = kmem_cache_create("fasync_cache",
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 0eda52738ec4..72a5d5b04494 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -1223,30 +1223,46 @@ static int fuse_direntplus_link(struct file *file,
if (name.name[1] == '.' && name.len == 2)
return 0;
}
+
+ if (invalid_nodeid(o->nodeid))
+ return -EIO;
+ if (!fuse_valid_type(o->attr.mode))
+ return -EIO;
+
fc = get_fuse_conn(dir);
name.hash = full_name_hash(name.name, name.len);
dentry = d_lookup(parent, &name);
- if (dentry && dentry->d_inode) {
+ if (dentry) {
inode = dentry->d_inode;
- if (get_node_id(inode) == o->nodeid) {
+ if (!inode) {
+ d_drop(dentry);
+ } else if (get_node_id(inode) != o->nodeid ||
+ ((o->attr.mode ^ inode->i_mode) & S_IFMT)) {
+ err = d_invalidate(dentry);
+ if (err)
+ goto out;
+ } else if (is_bad_inode(inode)) {
+ err = -EIO;
+ goto out;
+ } else {
struct fuse_inode *fi;
fi = get_fuse_inode(inode);
spin_lock(&fc->lock);
fi->nlookup++;
spin_unlock(&fc->lock);
+ fuse_change_attributes(inode, &o->attr,
+ entry_attr_timeout(o),
+ attr_version);
+
/*
* The other branch to 'found' comes via fuse_iget()
* which bumps nlookup inside
*/
goto found;
}
- err = d_invalidate(dentry);
- if (err)
- goto out;
dput(dentry);
- dentry = NULL;
}
dentry = d_alloc(parent, &name);
@@ -1259,25 +1275,30 @@ static int fuse_direntplus_link(struct file *file,
if (!inode)
goto out;
- alias = d_materialise_unique(dentry, inode);
- err = PTR_ERR(alias);
- if (IS_ERR(alias))
- goto out;
+ if (S_ISDIR(inode->i_mode)) {
+ mutex_lock(&fc->inst_mutex);
+ alias = fuse_d_add_directory(dentry, inode);
+ mutex_unlock(&fc->inst_mutex);
+ err = PTR_ERR(alias);
+ if (IS_ERR(alias)) {
+ iput(inode);
+ goto out;
+ }
+ } else {
+ alias = d_splice_alias(inode, dentry);
+ }
+
if (alias) {
dput(dentry);
dentry = alias;
}
found:
- fuse_change_attributes(inode, &o->attr, entry_attr_timeout(o),
- attr_version);
-
fuse_change_entry_timeout(dentry, o);
err = 0;
out:
- if (dentry)
- dput(dentry);
+ dput(dentry);
return err;
}
diff --git a/fs/namei.c b/fs/namei.c
index 8b61d103a8a7..89a612e392eb 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3671,15 +3671,11 @@ SYSCALL_DEFINE5(linkat, int, olddfd, const char __user *, oldname,
if ((flags & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH)) != 0)
return -EINVAL;
/*
- * To use null names we require CAP_DAC_READ_SEARCH
- * This ensures that not everyone will be able to create
- * handlink using the passed filedescriptor.
+ * Using empty names is equivalent to using AT_SYMLINK_FOLLOW
+ * on /proc/self/fd/<fd>.
*/
- if (flags & AT_EMPTY_PATH) {
- if (!capable(CAP_DAC_READ_SEARCH))
- return -ENOENT;
+ if (flags & AT_EMPTY_PATH)
how = LOOKUP_EMPTY;
- }
if (flags & AT_SYMLINK_FOLLOW)
how |= LOOKUP_FOLLOW;
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index c74d6168db99..3850b018815f 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -1118,11 +1118,11 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap,
len, ((char *)p - (char *)q) + 4);
BUG();
}
- len = (char *)p - (char *)q - (bmval_len << 2);
*q++ = htonl(bmval0);
*q++ = htonl(bmval1);
if (bmval_len == 3)
*q++ = htonl(bmval2);
+ len = (char *)p - (char *)(q + 1);
*q = htonl(len);
/* out: */
diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c
index 998b17eda09d..9f6b96a09615 100644
--- a/fs/ocfs2/refcounttree.c
+++ b/fs/ocfs2/refcounttree.c
@@ -2965,6 +2965,11 @@ int ocfs2_duplicate_clusters_by_page(handle_t *handle,
to = map_end & (PAGE_CACHE_SIZE - 1);
page = find_or_create_page(mapping, page_index, GFP_NOFS);
+ if (!page) {
+ ret = -ENOMEM;
+ mlog_errno(ret);
+ break;
+ }
/*
* In case PAGE_CACHE_SIZE <= CLUSTER_SIZE, This page
diff --git a/fs/open.c b/fs/open.c
index d53e29895082..7931f76acc2b 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -823,7 +823,7 @@ static inline int build_open_flags(int flags, umode_t mode, struct open_flags *o
int lookup_flags = 0;
int acc_mode;
- if (flags & O_CREAT)
+ if (flags & (O_CREAT | __O_TMPFILE))
op->mode = (mode & S_IALLUGO) | S_IFREG;
else
op->mode = 0;
diff --git a/fs/reiserfs/procfs.c b/fs/reiserfs/procfs.c
index 33532f79b4f7..a958444a75fc 100644
--- a/fs/reiserfs/procfs.c
+++ b/fs/reiserfs/procfs.c
@@ -19,12 +19,13 @@
/*
* LOCKING:
*
- * We rely on new Alexander Viro's super-block locking.
+ * These guys are evicted from procfs as the very first step in ->kill_sb().
*
*/
-static int show_version(struct seq_file *m, struct super_block *sb)
+static int show_version(struct seq_file *m, void *unused)
{
+ struct super_block *sb = m->private;
char *format;
if (REISERFS_SB(sb)->s_properties & (1 << REISERFS_3_6)) {
@@ -66,8 +67,9 @@ static int show_version(struct seq_file *m, struct super_block *sb)
#define DJP( x ) le32_to_cpu( jp -> x )
#define JF( x ) ( r -> s_journal -> x )
-static int show_super(struct seq_file *m, struct super_block *sb)
+static int show_super(struct seq_file *m, void *unused)
{
+ struct super_block *sb = m->private;
struct reiserfs_sb_info *r = REISERFS_SB(sb);
seq_printf(m, "state: \t%s\n"
@@ -128,8 +130,9 @@ static int show_super(struct seq_file *m, struct super_block *sb)
return 0;
}
-static int show_per_level(struct seq_file *m, struct super_block *sb)
+static int show_per_level(struct seq_file *m, void *unused)
{
+ struct super_block *sb = m->private;
struct reiserfs_sb_info *r = REISERFS_SB(sb);
int level;
@@ -186,8 +189,9 @@ static int show_per_level(struct seq_file *m, struct super_block *sb)
return 0;
}
-static int show_bitmap(struct seq_file *m, struct super_block *sb)
+static int show_bitmap(struct seq_file *m, void *unused)
{
+ struct super_block *sb = m->private;
struct reiserfs_sb_info *r = REISERFS_SB(sb);
seq_printf(m, "free_block: %lu\n"
@@ -218,8 +222,9 @@ static int show_bitmap(struct seq_file *m, struct super_block *sb)
return 0;
}
-static int show_on_disk_super(struct seq_file *m, struct super_block *sb)
+static int show_on_disk_super(struct seq_file *m, void *unused)
{
+ struct super_block *sb = m->private;
struct reiserfs_sb_info *sb_info = REISERFS_SB(sb);
struct reiserfs_super_block *rs = sb_info->s_rs;
int hash_code = DFL(s_hash_function_code);
@@ -261,8 +266,9 @@ static int show_on_disk_super(struct seq_file *m, struct super_block *sb)
return 0;
}
-static int show_oidmap(struct seq_file *m, struct super_block *sb)
+static int show_oidmap(struct seq_file *m, void *unused)
{
+ struct super_block *sb = m->private;
struct reiserfs_sb_info *sb_info = REISERFS_SB(sb);
struct reiserfs_super_block *rs = sb_info->s_rs;
unsigned int mapsize = le16_to_cpu(rs->s_v1.s_oid_cursize);
@@ -291,8 +297,9 @@ static int show_oidmap(struct seq_file *m, struct super_block *sb)
return 0;
}
-static int show_journal(struct seq_file *m, struct super_block *sb)
+static int show_journal(struct seq_file *m, void *unused)
{
+ struct super_block *sb = m->private;
struct reiserfs_sb_info *r = REISERFS_SB(sb);
struct reiserfs_super_block *rs = r->s_rs;
struct journal_params *jp = &rs->s_v1.s_journal;
@@ -383,92 +390,24 @@ static int show_journal(struct seq_file *m, struct super_block *sb)
return 0;
}
-/* iterator */
-static int test_sb(struct super_block *sb, void *data)
-{
- return data == sb;
-}
-
-static int set_sb(struct super_block *sb, void *data)
-{
- return -ENOENT;
-}
-
-struct reiserfs_seq_private {
- struct super_block *sb;
- int (*show) (struct seq_file *, struct super_block *);
-};
-
-static void *r_start(struct seq_file *m, loff_t * pos)
-{
- struct reiserfs_seq_private *priv = m->private;
- loff_t l = *pos;
-
- if (l)
- return NULL;
-
- if (IS_ERR(sget(&reiserfs_fs_type, test_sb, set_sb, 0, priv->sb)))
- return NULL;
-
- up_write(&priv->sb->s_umount);
- return priv->sb;
-}
-
-static void *r_next(struct seq_file *m, void *v, loff_t * pos)
-{
- ++*pos;
- if (v)
- deactivate_super(v);
- return NULL;
-}
-
-static void r_stop(struct seq_file *m, void *v)
-{
- if (v)
- deactivate_super(v);
-}
-
-static int r_show(struct seq_file *m, void *v)
-{
- struct reiserfs_seq_private *priv = m->private;
- return priv->show(m, v);
-}
-
-static const struct seq_operations r_ops = {
- .start = r_start,
- .next = r_next,
- .stop = r_stop,
- .show = r_show,
-};
-
static int r_open(struct inode *inode, struct file *file)
{
- struct reiserfs_seq_private *priv;
- int ret = seq_open_private(file, &r_ops,
- sizeof(struct reiserfs_seq_private));
-
- if (!ret) {
- struct seq_file *m = file->private_data;
- priv = m->private;
- priv->sb = proc_get_parent_data(inode);
- priv->show = PDE_DATA(inode);
- }
- return ret;
+ return single_open(file, PDE_DATA(inode),
+ proc_get_parent_data(inode));
}
static const struct file_operations r_file_operations = {
.open = r_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = seq_release_private,
- .owner = THIS_MODULE,
+ .release = single_release,
};
static struct proc_dir_entry *proc_info_root = NULL;
static const char proc_info_root_name[] = "fs/reiserfs";
static void add_file(struct super_block *sb, char *name,
- int (*func) (struct seq_file *, struct super_block *))
+ int (*func) (struct seq_file *, void *))
{
proc_create_data(name, 0, REISERFS_SB(sb)->procdir,
&r_file_operations, func);
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index f8a23c3078f8..e2e202a07b31 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -499,6 +499,7 @@ int remove_save_link(struct inode *inode, int truncate)
static void reiserfs_kill_sb(struct super_block *s)
{
if (REISERFS_SB(s)) {
+ reiserfs_proc_info_done(s);
/*
* Force any pending inode evictions to occur now. Any
* inodes to be removed that have extended attributes
@@ -554,8 +555,6 @@ static void reiserfs_put_super(struct super_block *s)
REISERFS_SB(s)->reserved_blocks);
}
- reiserfs_proc_info_done(s);
-
reiserfs_write_unlock(s);
mutex_destroy(&REISERFS_SB(s)->lock);
kfree(s->s_fs_info);
diff --git a/fs/xfs/xfs_dinode.h b/fs/xfs/xfs_dinode.h
index 07d735a80a0f..e5869b50dc41 100644
--- a/fs/xfs/xfs_dinode.h
+++ b/fs/xfs/xfs_dinode.h
@@ -39,6 +39,9 @@ typedef struct xfs_timestamp {
* There is a very similar struct icdinode in xfs_inode which matches the
* layout of the first 96 bytes of this structure, but is kept in native
* format instead of big endian.
+ *
+ * Note: di_flushiter is only used by v1/2 inodes - it's effectively a zeroed
+ * padding field for v3 inodes.
*/
typedef struct xfs_dinode {
__be16 di_magic; /* inode magic # = XFS_DINODE_MAGIC */
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index b78481f99d9d..bb262c25c8de 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -896,7 +896,6 @@ xfs_dinode_to_disk(
to->di_projid_lo = cpu_to_be16(from->di_projid_lo);
to->di_projid_hi = cpu_to_be16(from->di_projid_hi);
memcpy(to->di_pad, from->di_pad, sizeof(to->di_pad));
- to->di_flushiter = cpu_to_be16(from->di_flushiter);
to->di_atime.t_sec = cpu_to_be32(from->di_atime.t_sec);
to->di_atime.t_nsec = cpu_to_be32(from->di_atime.t_nsec);
to->di_mtime.t_sec = cpu_to_be32(from->di_mtime.t_sec);
@@ -924,6 +923,9 @@ xfs_dinode_to_disk(
to->di_lsn = cpu_to_be64(from->di_lsn);
memcpy(to->di_pad2, from->di_pad2, sizeof(to->di_pad2));
uuid_copy(&to->di_uuid, &from->di_uuid);
+ to->di_flushiter = 0;
+ } else {
+ to->di_flushiter = cpu_to_be16(from->di_flushiter);
}
}
@@ -1029,10 +1031,14 @@ xfs_dinode_calc_crc(
/*
* Read the disk inode attributes into the in-core inode structure.
*
- * If we are initialising a new inode and we are not utilising the
- * XFS_MOUNT_IKEEP inode cluster mode, we can simple build the new inode core
- * with a random generation number. If we are keeping inodes around, we need to
- * read the inode cluster to get the existing generation number off disk.
+ * For version 5 superblocks, if we are initialising a new inode and we are not
+ * utilising the XFS_MOUNT_IKEEP inode cluster mode, we can simple build the new
+ * inode core with a random generation number. If we are keeping inodes around,
+ * we need to read the inode cluster to get the existing generation number off
+ * disk. Further, if we are using version 4 superblocks (i.e. v1/v2 inode
+ * format) then log recovery is dependent on the di_flushiter field being
+ * initialised from the current on-disk value and hence we must also read the
+ * inode off disk.
*/
int
xfs_iread(
@@ -1054,6 +1060,7 @@ xfs_iread(
/* shortcut IO on inode allocation if possible */
if ((iget_flags & XFS_IGET_CREATE) &&
+ xfs_sb_version_hascrc(&mp->m_sb) &&
!(mp->m_flags & XFS_MOUNT_IKEEP)) {
/* initialise the on-disk inode core */
memset(&ip->i_d, 0, sizeof(ip->i_d));
@@ -2882,12 +2889,18 @@ xfs_iflush_int(
__func__, ip->i_ino, ip->i_d.di_forkoff, ip);
goto corrupt_out;
}
+
/*
- * bump the flush iteration count, used to detect flushes which
- * postdate a log record during recovery. This is redundant as we now
- * log every change and hence this can't happen. Still, it doesn't hurt.
+ * Inode item log recovery for v1/v2 inodes are dependent on the
+ * di_flushiter count for correct sequencing. We bump the flush
+ * iteration count so we can detect flushes which postdate a log record
+ * during recovery. This is redundant as we now log every change and
+ * hence this can't happen but we need to still do it to ensure
+ * backwards compatibility with old kernels that predate logging all
+ * inode changes.
*/
- ip->i_d.di_flushiter++;
+ if (ip->i_d.di_version < 3)
+ ip->i_d.di_flushiter++;
/*
* Copy the dirty parts of the inode into the on-disk
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 6fcc910a50b9..7681b19aa5dc 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -2592,8 +2592,16 @@ xlog_recover_inode_pass2(
goto error;
}
- /* Skip replay when the on disk inode is newer than the log one */
- if (dicp->di_flushiter < be16_to_cpu(dip->di_flushiter)) {
+ /*
+ * di_flushiter is only valid for v1/2 inodes. All changes for v3 inodes
+ * are transactional and if ordering is necessary we can determine that
+ * more accurately by the LSN field in the V3 inode core. Don't trust
+ * the inode versions we might be changing them here - use the
+ * superblock flag to determine whether we need to look at di_flushiter
+ * to skip replay when the on disk inode is newer than the log one
+ */
+ if (!xfs_sb_version_hascrc(&mp->m_sb) &&
+ dicp->di_flushiter < be16_to_cpu(dip->di_flushiter)) {
/*
* Deal with the wrap case, DI_MAX_FLUSH is less
* than smaller numbers
@@ -2608,6 +2616,7 @@ xlog_recover_inode_pass2(
goto error;
}
}
+
/* Take the opportunity to reset the flush iteration count */
dicp->di_flushiter = 0;
generated by cgit v1.2.3 (git 2.0.4) at 2024-11-10 17:10:15 +0000