Merge git://git.kernel.org/pub/scm/linux/kernel/git/hch/xfs-icache-races

* git://git.kernel.org/pub/scm/linux/kernel/git/hch/xfs-icache-races:
  xfs: fix freeing of inodes not yet added to the inode cache
  vfs: add __destroy_inode
  vfs: fix inode_init_always calling convention
This commit is contained in:
Linus Torvalds 2009-08-07 18:53:44 -07:00
commit fb385003c4
4 changed files with 99 additions and 103 deletions

View File

@ -120,12 +120,11 @@ static void wake_up_inode(struct inode *inode)
* These are initializations that need to be done on every inode
* allocation as the fields are not initialised by slab allocation.
*/
struct inode *inode_init_always(struct super_block *sb, struct inode *inode)
int inode_init_always(struct super_block *sb, struct inode *inode)
{
static const struct address_space_operations empty_aops;
static struct inode_operations empty_iops;
static const struct file_operations empty_fops;
struct address_space *const mapping = &inode->i_data;
inode->i_sb = sb;
@ -152,7 +151,7 @@ struct inode *inode_init_always(struct super_block *sb, struct inode *inode)
inode->dirtied_when = 0;
if (security_inode_alloc(inode))
goto out_free_inode;
goto out;
/* allocate and initialize an i_integrity */
if (ima_inode_alloc(inode))
@ -198,16 +197,12 @@ struct inode *inode_init_always(struct super_block *sb, struct inode *inode)
inode->i_fsnotify_mask = 0;
#endif
return inode;
return 0;
out_free_security:
security_inode_free(inode);
out_free_inode:
if (inode->i_sb->s_op->destroy_inode)
inode->i_sb->s_op->destroy_inode(inode);
else
kmem_cache_free(inode_cachep, (inode));
return NULL;
out:
return -ENOMEM;
}
EXPORT_SYMBOL(inode_init_always);
@ -220,12 +215,21 @@ static struct inode *alloc_inode(struct super_block *sb)
else
inode = kmem_cache_alloc(inode_cachep, GFP_KERNEL);
if (inode)
return inode_init_always(sb, inode);
return NULL;
if (!inode)
return NULL;
if (unlikely(inode_init_always(sb, inode))) {
if (inode->i_sb->s_op->destroy_inode)
inode->i_sb->s_op->destroy_inode(inode);
else
kmem_cache_free(inode_cachep, inode);
return NULL;
}
return inode;
}
void destroy_inode(struct inode *inode)
void __destroy_inode(struct inode *inode)
{
BUG_ON(inode_has_buffers(inode));
ima_inode_free(inode);
@ -237,13 +241,17 @@ void destroy_inode(struct inode *inode)
if (inode->i_default_acl && inode->i_default_acl != ACL_NOT_CACHED)
posix_acl_release(inode->i_default_acl);
#endif
}
EXPORT_SYMBOL(__destroy_inode);
void destroy_inode(struct inode *inode)
{
__destroy_inode(inode);
if (inode->i_sb->s_op->destroy_inode)
inode->i_sb->s_op->destroy_inode(inode);
else
kmem_cache_free(inode_cachep, (inode));
}
EXPORT_SYMBOL(destroy_inode);
/*
* These are initializations that only need to be done

View File

@ -64,6 +64,10 @@ xfs_inode_alloc(
ip = kmem_zone_alloc(xfs_inode_zone, KM_SLEEP);
if (!ip)
return NULL;
if (inode_init_always(mp->m_super, VFS_I(ip))) {
kmem_zone_free(xfs_inode_zone, ip);
return NULL;
}
ASSERT(atomic_read(&ip->i_iocount) == 0);
ASSERT(atomic_read(&ip->i_pincount) == 0);
@ -105,17 +109,6 @@ xfs_inode_alloc(
#ifdef XFS_DIR2_TRACE
ip->i_dir_trace = ktrace_alloc(XFS_DIR2_KTRACE_SIZE, KM_NOFS);
#endif
/*
* Now initialise the VFS inode. We do this after the xfs_inode
* initialisation as internal failures will result in ->destroy_inode
* being called and that will pass down through the reclaim path and
* free the XFS inode. This path requires the XFS inode to already be
* initialised. Hence if this call fails, the xfs_inode has already
* been freed and we should not reference it at all in the error
* handling.
*/
if (!inode_init_always(mp->m_super, VFS_I(ip)))
return NULL;
/* prevent anyone from using this yet */
VFS_I(ip)->i_state = I_NEW|I_LOCK;
@ -123,6 +116,71 @@ xfs_inode_alloc(
return ip;
}
STATIC void
xfs_inode_free(
struct xfs_inode *ip)
{
switch (ip->i_d.di_mode & S_IFMT) {
case S_IFREG:
case S_IFDIR:
case S_IFLNK:
xfs_idestroy_fork(ip, XFS_DATA_FORK);
break;
}
if (ip->i_afp)
xfs_idestroy_fork(ip, XFS_ATTR_FORK);
#ifdef XFS_INODE_TRACE
ktrace_free(ip->i_trace);
#endif
#ifdef XFS_BMAP_TRACE
ktrace_free(ip->i_xtrace);
#endif
#ifdef XFS_BTREE_TRACE
ktrace_free(ip->i_btrace);
#endif
#ifdef XFS_RW_TRACE
ktrace_free(ip->i_rwtrace);
#endif
#ifdef XFS_ILOCK_TRACE
ktrace_free(ip->i_lock_trace);
#endif
#ifdef XFS_DIR2_TRACE
ktrace_free(ip->i_dir_trace);
#endif
if (ip->i_itemp) {
/*
* Only if we are shutting down the fs will we see an
* inode still in the AIL. If it is there, we should remove
* it to prevent a use-after-free from occurring.
*/
xfs_log_item_t *lip = &ip->i_itemp->ili_item;
struct xfs_ail *ailp = lip->li_ailp;
ASSERT(((lip->li_flags & XFS_LI_IN_AIL) == 0) ||
XFS_FORCED_SHUTDOWN(ip->i_mount));
if (lip->li_flags & XFS_LI_IN_AIL) {
spin_lock(&ailp->xa_lock);
if (lip->li_flags & XFS_LI_IN_AIL)
xfs_trans_ail_delete(ailp, lip);
else
spin_unlock(&ailp->xa_lock);
}
xfs_inode_item_destroy(ip);
ip->i_itemp = NULL;
}
/* asserts to verify all state is correct here */
ASSERT(atomic_read(&ip->i_iocount) == 0);
ASSERT(atomic_read(&ip->i_pincount) == 0);
ASSERT(!spin_is_locked(&ip->i_flags_lock));
ASSERT(completion_done(&ip->i_flush));
kmem_zone_free(xfs_inode_zone, ip);
}
/*
* Check the validity of the inode we just found it the cache
*/
@ -167,7 +225,7 @@ xfs_iget_cache_hit(
* errors cleanly, then tag it so it can be set up correctly
* later.
*/
if (!inode_init_always(mp->m_super, VFS_I(ip))) {
if (inode_init_always(mp->m_super, VFS_I(ip))) {
error = ENOMEM;
goto out_error;
}
@ -299,7 +357,8 @@ out_preload_end:
if (lock_flags)
xfs_iunlock(ip, lock_flags);
out_destroy:
xfs_destroy_inode(ip);
__destroy_inode(VFS_I(ip));
xfs_inode_free(ip);
return error;
}
@ -504,62 +563,7 @@ xfs_ireclaim(
xfs_qm_dqdetach(ip);
xfs_iunlock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
switch (ip->i_d.di_mode & S_IFMT) {
case S_IFREG:
case S_IFDIR:
case S_IFLNK:
xfs_idestroy_fork(ip, XFS_DATA_FORK);
break;
}
if (ip->i_afp)
xfs_idestroy_fork(ip, XFS_ATTR_FORK);
#ifdef XFS_INODE_TRACE
ktrace_free(ip->i_trace);
#endif
#ifdef XFS_BMAP_TRACE
ktrace_free(ip->i_xtrace);
#endif
#ifdef XFS_BTREE_TRACE
ktrace_free(ip->i_btrace);
#endif
#ifdef XFS_RW_TRACE
ktrace_free(ip->i_rwtrace);
#endif
#ifdef XFS_ILOCK_TRACE
ktrace_free(ip->i_lock_trace);
#endif
#ifdef XFS_DIR2_TRACE
ktrace_free(ip->i_dir_trace);
#endif
if (ip->i_itemp) {
/*
* Only if we are shutting down the fs will we see an
* inode still in the AIL. If it is there, we should remove
* it to prevent a use-after-free from occurring.
*/
xfs_log_item_t *lip = &ip->i_itemp->ili_item;
struct xfs_ail *ailp = lip->li_ailp;
ASSERT(((lip->li_flags & XFS_LI_IN_AIL) == 0) ||
XFS_FORCED_SHUTDOWN(ip->i_mount));
if (lip->li_flags & XFS_LI_IN_AIL) {
spin_lock(&ailp->xa_lock);
if (lip->li_flags & XFS_LI_IN_AIL)
xfs_trans_ail_delete(ailp, lip);
else
spin_unlock(&ailp->xa_lock);
}
xfs_inode_item_destroy(ip);
ip->i_itemp = NULL;
}
/* asserts to verify all state is correct here */
ASSERT(atomic_read(&ip->i_iocount) == 0);
ASSERT(atomic_read(&ip->i_pincount) == 0);
ASSERT(!spin_is_locked(&ip->i_flags_lock));
ASSERT(completion_done(&ip->i_flush));
kmem_zone_free(xfs_inode_zone, ip);
xfs_inode_free(ip);
}
/*

View File

@ -309,23 +309,6 @@ static inline struct inode *VFS_I(struct xfs_inode *ip)
return &ip->i_vnode;
}
/*
* Get rid of a partially initialized inode.
*
* We have to go through destroy_inode to make sure allocations
* from init_inode_always like the security data are undone.
*
* We mark the inode bad so that it takes the short cut in
* the reclaim path instead of going through the flush path
* which doesn't make sense for an inode that has never seen the
* light of day.
*/
static inline void xfs_destroy_inode(struct xfs_inode *ip)
{
make_bad_inode(VFS_I(ip));
return destroy_inode(VFS_I(ip));
}
/*
* i_flags helper functions
*/

View File

@ -2137,7 +2137,7 @@ extern loff_t default_llseek(struct file *file, loff_t offset, int origin);
extern loff_t vfs_llseek(struct file *file, loff_t offset, int origin);
extern struct inode * inode_init_always(struct super_block *, struct inode *);
extern int inode_init_always(struct super_block *, struct inode *);
extern void inode_init_once(struct inode *);
extern void inode_add_to_lists(struct super_block *, struct inode *);
extern void iput(struct inode *);
@ -2164,6 +2164,7 @@ extern void __iget(struct inode * inode);
extern void iget_failed(struct inode *);
extern void clear_inode(struct inode *);
extern void destroy_inode(struct inode *);
extern void __destroy_inode(struct inode *);
extern struct inode *new_inode(struct super_block *);
extern int should_remove_suid(struct dentry *);
extern int file_remove_suid(struct file *);