Commit 8dac6bee authored by Linus Torvalds's avatar Linus Torvalds

Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6:
  AFS: Use i_generation not i_version for the vnode uniquifier
  AFS: Set s_id in the superblock to the volume name
  vfs: Fix data corruption after failed write in __block_write_begin()
  afs: afs_fill_page reads too much, or wrong data
  VFS: Fix vfsmount overput on simultaneous automount
  fix wrong iput on d_inode introduced by e6bc45d6
  Delay struct net freeing while there's a sysfs instance refering to it
  afs: fix sget() races, close leak on umount
  ubifs: fix sget races
  ubifs: split allocation of ubifs_info into a separate function
  fix leak in proc_set_super()
parents f8f44f09 d6e43f75
......@@ -584,11 +584,11 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry,
success:
d_add(dentry, inode);
_leave(" = 0 { vn=%u u=%u } -> { ino=%lu v=%llu }",
_leave(" = 0 { vn=%u u=%u } -> { ino=%lu v=%u }",
fid.vnode,
fid.unique,
dentry->d_inode->i_ino,
(unsigned long long)dentry->d_inode->i_version);
dentry->d_inode->i_generation);
return NULL;
}
......@@ -671,10 +671,10 @@ static int afs_d_revalidate(struct dentry *dentry, struct nameidata *nd)
* been deleted and replaced, and the original vnode ID has
* been reused */
if (fid.unique != vnode->fid.unique) {
_debug("%s: file deleted (uq %u -> %u I:%llu)",
_debug("%s: file deleted (uq %u -> %u I:%u)",
dentry->d_name.name, fid.unique,
vnode->fid.unique,
(unsigned long long)dentry->d_inode->i_version);
dentry->d_inode->i_generation);
spin_lock(&vnode->lock);
set_bit(AFS_VNODE_DELETED, &vnode->flags);
spin_unlock(&vnode->lock);
......
......@@ -89,7 +89,7 @@ static void xdr_decode_AFSFetchStatus(const __be32 **_bp,
i_size_write(&vnode->vfs_inode, size);
vnode->vfs_inode.i_uid = status->owner;
vnode->vfs_inode.i_gid = status->group;
vnode->vfs_inode.i_version = vnode->fid.unique;
vnode->vfs_inode.i_generation = vnode->fid.unique;
vnode->vfs_inode.i_nlink = status->nlink;
mode = vnode->vfs_inode.i_mode;
......@@ -102,6 +102,7 @@ static void xdr_decode_AFSFetchStatus(const __be32 **_bp,
vnode->vfs_inode.i_ctime.tv_sec = status->mtime_server;
vnode->vfs_inode.i_mtime = vnode->vfs_inode.i_ctime;
vnode->vfs_inode.i_atime = vnode->vfs_inode.i_ctime;
vnode->vfs_inode.i_version = data_version;
}
expected_version = status->data_version;
......
......@@ -75,7 +75,8 @@ static int afs_inode_map_status(struct afs_vnode *vnode, struct key *key)
inode->i_ctime.tv_nsec = 0;
inode->i_atime = inode->i_mtime = inode->i_ctime;
inode->i_blocks = 0;
inode->i_version = vnode->fid.unique;
inode->i_generation = vnode->fid.unique;
inode->i_version = vnode->status.data_version;
inode->i_mapping->a_ops = &afs_fs_aops;
/* check to see whether a symbolic link is really a mountpoint */
......@@ -100,7 +101,7 @@ static int afs_iget5_test(struct inode *inode, void *opaque)
struct afs_iget_data *data = opaque;
return inode->i_ino == data->fid.vnode &&
inode->i_version == data->fid.unique;
inode->i_generation == data->fid.unique;
}
/*
......@@ -122,7 +123,7 @@ static int afs_iget5_set(struct inode *inode, void *opaque)
struct afs_vnode *vnode = AFS_FS_I(inode);
inode->i_ino = data->fid.vnode;
inode->i_version = data->fid.unique;
inode->i_generation = data->fid.unique;
vnode->fid = data->fid;
vnode->volume = data->volume;
......@@ -380,8 +381,7 @@ int afs_getattr(struct vfsmount *mnt, struct dentry *dentry,
inode = dentry->d_inode;
_enter("{ ino=%lu v=%llu }", inode->i_ino,
(unsigned long long)inode->i_version);
_enter("{ ino=%lu v=%u }", inode->i_ino, inode->i_generation);
generic_fillattr(inode, stat);
return 0;
......
......@@ -31,8 +31,8 @@
static void afs_i_init_once(void *foo);
static struct dentry *afs_mount(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data);
static void afs_kill_super(struct super_block *sb);
static struct inode *afs_alloc_inode(struct super_block *sb);
static void afs_put_super(struct super_block *sb);
static void afs_destroy_inode(struct inode *inode);
static int afs_statfs(struct dentry *dentry, struct kstatfs *buf);
......@@ -40,7 +40,7 @@ struct file_system_type afs_fs_type = {
.owner = THIS_MODULE,
.name = "afs",
.mount = afs_mount,
.kill_sb = kill_anon_super,
.kill_sb = afs_kill_super,
.fs_flags = 0,
};
......@@ -50,7 +50,6 @@ static const struct super_operations afs_super_ops = {
.drop_inode = afs_drop_inode,
.destroy_inode = afs_destroy_inode,
.evict_inode = afs_evict_inode,
.put_super = afs_put_super,
.show_options = generic_show_options,
};
......@@ -282,19 +281,25 @@ static int afs_parse_device_name(struct afs_mount_params *params,
*/
static int afs_test_super(struct super_block *sb, void *data)
{
struct afs_mount_params *params = data;
struct afs_super_info *as1 = data;
struct afs_super_info *as = sb->s_fs_info;
return as->volume == params->volume;
return as->volume == as1->volume;
}
static int afs_set_super(struct super_block *sb, void *data)
{
sb->s_fs_info = data;
return set_anon_super(sb, NULL);
}
/*
* fill in the superblock
*/
static int afs_fill_super(struct super_block *sb, void *data)
static int afs_fill_super(struct super_block *sb,
struct afs_mount_params *params)
{
struct afs_mount_params *params = data;
struct afs_super_info *as = NULL;
struct afs_super_info *as = sb->s_fs_info;
struct afs_fid fid;
struct dentry *root = NULL;
struct inode *inode = NULL;
......@@ -302,23 +307,13 @@ static int afs_fill_super(struct super_block *sb, void *data)
_enter("");
/* allocate a superblock info record */
as = kzalloc(sizeof(struct afs_super_info), GFP_KERNEL);
if (!as) {
_leave(" = -ENOMEM");
return -ENOMEM;
}
afs_get_volume(params->volume);
as->volume = params->volume;
/* fill in the superblock */
sb->s_blocksize = PAGE_CACHE_SIZE;
sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
sb->s_magic = AFS_FS_MAGIC;
sb->s_op = &afs_super_ops;
sb->s_fs_info = as;
sb->s_bdi = &as->volume->bdi;
strlcpy(sb->s_id, as->volume->vlocation->vldb.name, sizeof(sb->s_id));
/* allocate the root inode and dentry */
fid.vid = as->volume->vid;
......@@ -326,7 +321,7 @@ static int afs_fill_super(struct super_block *sb, void *data)
fid.unique = 1;
inode = afs_iget(sb, params->key, &fid, NULL, NULL);
if (IS_ERR(inode))
goto error_inode;
return PTR_ERR(inode);
if (params->autocell)
set_bit(AFS_VNODE_AUTOCELL, &AFS_FS_I(inode)->flags);
......@@ -342,16 +337,8 @@ static int afs_fill_super(struct super_block *sb, void *data)
_leave(" = 0");
return 0;
error_inode:
ret = PTR_ERR(inode);
inode = NULL;
error:
iput(inode);
afs_put_volume(as->volume);
kfree(as);
sb->s_fs_info = NULL;
_leave(" = %d", ret);
return ret;
}
......@@ -367,6 +354,7 @@ static struct dentry *afs_mount(struct file_system_type *fs_type,
struct afs_volume *vol;
struct key *key;
char *new_opts = kstrdup(options, GFP_KERNEL);
struct afs_super_info *as;
int ret;
_enter(",,%s,%p", dev_name, options);
......@@ -399,12 +387,22 @@ static struct dentry *afs_mount(struct file_system_type *fs_type,
ret = PTR_ERR(vol);
goto error;
}
params.volume = vol;
/* allocate a superblock info record */
as = kzalloc(sizeof(struct afs_super_info), GFP_KERNEL);
if (!as) {
ret = -ENOMEM;
afs_put_volume(vol);
goto error;
}
as->volume = vol;
/* allocate a deviceless superblock */
sb = sget(fs_type, afs_test_super, set_anon_super, &params);
sb = sget(fs_type, afs_test_super, afs_set_super, as);
if (IS_ERR(sb)) {
ret = PTR_ERR(sb);
afs_put_volume(vol);
kfree(as);
goto error;
}
......@@ -422,16 +420,16 @@ static struct dentry *afs_mount(struct file_system_type *fs_type,
} else {
_debug("reuse");
ASSERTCMP(sb->s_flags, &, MS_ACTIVE);
afs_put_volume(vol);
kfree(as);
}
afs_put_volume(params.volume);
afs_put_cell(params.cell);
kfree(new_opts);
_leave(" = 0 [%p]", sb);
return dget(sb->s_root);
error:
afs_put_volume(params.volume);
afs_put_cell(params.cell);
key_put(params.key);
kfree(new_opts);
......@@ -439,18 +437,12 @@ static struct dentry *afs_mount(struct file_system_type *fs_type,
return ERR_PTR(ret);
}
/*
* finish the unmounting process on the superblock
*/
static void afs_put_super(struct super_block *sb)
static void afs_kill_super(struct super_block *sb)
{
struct afs_super_info *as = sb->s_fs_info;
_enter("");
kill_anon_super(sb);
afs_put_volume(as->volume);
_leave("");
kfree(as);
}
/*
......
......@@ -84,23 +84,21 @@ void afs_put_writeback(struct afs_writeback *wb)
* partly or wholly fill a page that's under preparation for writing
*/
static int afs_fill_page(struct afs_vnode *vnode, struct key *key,
loff_t pos, unsigned len, struct page *page)
loff_t pos, struct page *page)
{
loff_t i_size;
unsigned eof;
int ret;
int len;
_enter(",,%llu,%u", (unsigned long long)pos, len);
ASSERTCMP(len, <=, PAGE_CACHE_SIZE);
_enter(",,%llu", (unsigned long long)pos);
i_size = i_size_read(&vnode->vfs_inode);
if (pos + len > i_size)
eof = i_size;
if (pos + PAGE_CACHE_SIZE > i_size)
len = i_size - pos;
else
eof = PAGE_CACHE_SIZE;
len = PAGE_CACHE_SIZE;
ret = afs_vnode_fetch_data(vnode, key, 0, eof, page);
ret = afs_vnode_fetch_data(vnode, key, pos, len, page);
if (ret < 0) {
if (ret == -ENOENT) {
_debug("got NOENT from server"
......@@ -153,9 +151,8 @@ int afs_write_begin(struct file *file, struct address_space *mapping,
*pagep = page;
/* page won't leak in error case: it eventually gets cleaned off LRU */
if (!PageUptodate(page)) {
_debug("not up to date");
ret = afs_fill_page(vnode, key, pos, len, page);
if (!PageUptodate(page) && len != PAGE_CACHE_SIZE) {
ret = afs_fill_page(vnode, key, index << PAGE_CACHE_SHIFT, page);
if (ret < 0) {
kfree(candidate);
_leave(" = %d [prep]", ret);
......
......@@ -1902,10 +1902,8 @@ int __block_write_begin(struct page *page, loff_t pos, unsigned len,
if (!buffer_uptodate(*wait_bh))
err = -EIO;
}
if (unlikely(err)) {
if (unlikely(err))
page_zero_new_buffers(page, from, to);
ClearPageUptodate(page);
}
return err;
}
EXPORT_SYMBOL(__block_write_begin);
......
......@@ -812,6 +812,11 @@ static int follow_automount(struct path *path, unsigned flags,
if (!mnt) /* mount collision */
return 0;
if (!*need_mntput) {
/* lock_mount() may release path->mnt on error */
mntget(path->mnt);
*need_mntput = true;
}
err = finish_automount(mnt, path);
switch (err) {
......@@ -819,12 +824,9 @@ static int follow_automount(struct path *path, unsigned flags,
/* Someone else made a mount here whilst we were busy */
return 0;
case 0:
dput(path->dentry);
if (*need_mntput)
mntput(path->mnt);
path_put(path);
path->mnt = mnt;
path->dentry = dget(mnt->mnt_root);
*need_mntput = true;
return 0;
default:
return err;
......@@ -844,9 +846,10 @@ static int follow_automount(struct path *path, unsigned flags,
*/
static int follow_managed(struct path *path, unsigned flags)
{
struct vfsmount *mnt = path->mnt; /* held by caller, must be left alone */
unsigned managed;
bool need_mntput = false;
int ret;
int ret = 0;
/* Given that we're not holding a lock here, we retain the value in a
* local variable for each dentry as we look at it so that we don't see
......@@ -861,7 +864,7 @@ static int follow_managed(struct path *path, unsigned flags)
BUG_ON(!path->dentry->d_op->d_manage);
ret = path->dentry->d_op->d_manage(path->dentry, false);
if (ret < 0)
return ret == -EISDIR ? 0 : ret;
break;
}
/* Transit to a mounted filesystem. */
......@@ -887,14 +890,19 @@ static int follow_managed(struct path *path, unsigned flags)
if (managed & DCACHE_NEED_AUTOMOUNT) {
ret = follow_automount(path, flags, &need_mntput);
if (ret < 0)
return ret == -EISDIR ? 0 : ret;
break;
continue;
}
/* We didn't change the current path point */
break;
}
return 0;
if (need_mntput && path->mnt == mnt)
mntput(path->mnt);
if (ret == -EISDIR)
ret = 0;
return ret;
}
int follow_down_one(struct path *path)
......@@ -2713,8 +2721,10 @@ static long do_unlinkat(int dfd, const char __user *pathname)
error = PTR_ERR(dentry);
if (!IS_ERR(dentry)) {
/* Why not before? Because we want correct error value */
if (nd.last.name[nd.last.len])
goto slashes;
inode = dentry->d_inode;
if (nd.last.name[nd.last.len] || !inode)
if (!inode)
goto slashes;
ihold(inode);
error = mnt_want_write(nd.path.mnt);
......
......@@ -28,11 +28,12 @@ static int proc_test_super(struct super_block *sb, void *data)
static int proc_set_super(struct super_block *sb, void *data)
{
struct pid_namespace *ns;
ns = (struct pid_namespace *)data;
int err = set_anon_super(sb, NULL);
if (!err) {
struct pid_namespace *ns = (struct pid_namespace *)data;
sb->s_fs_info = get_pid_ns(ns);
return set_anon_super(sb, NULL);
}
return err;
}
static struct dentry *proc_mount(struct file_system_type *fs_type,
......
......@@ -95,6 +95,14 @@ static int sysfs_set_super(struct super_block *sb, void *data)
return error;
}
static void free_sysfs_super_info(struct sysfs_super_info *info)
{
int type;
for (type = KOBJ_NS_TYPE_NONE; type < KOBJ_NS_TYPES; type++)
kobj_ns_drop(type, info->ns[type]);
kfree(info);
}
static struct dentry *sysfs_mount(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data)
{
......@@ -108,11 +116,11 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type,
return ERR_PTR(-ENOMEM);
for (type = KOBJ_NS_TYPE_NONE; type < KOBJ_NS_TYPES; type++)
info->ns[type] = kobj_ns_current(type);
info->ns[type] = kobj_ns_grab_current(type);
sb = sget(fs_type, sysfs_test_super, sysfs_set_super, info);
if (IS_ERR(sb) || sb->s_fs_info != info)
kfree(info);
free_sysfs_super_info(info);
if (IS_ERR(sb))
return ERR_CAST(sb);
if (!sb->s_root) {
......@@ -131,12 +139,11 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type,
static void sysfs_kill_sb(struct super_block *sb)
{
struct sysfs_super_info *info = sysfs_info(sb);
/* Remove the superblock from fs_supers/s_instances
* so we can't find it, before freeing sysfs_super_info.
*/
kill_anon_super(sb);
kfree(info);
free_sysfs_super_info(info);
}
static struct file_system_type sysfs_fs_type = {
......@@ -145,28 +152,6 @@ static struct file_system_type sysfs_fs_type = {
.kill_sb = sysfs_kill_sb,
};
void sysfs_exit_ns(enum kobj_ns_type type, const void *ns)
{
struct super_block *sb;
mutex_lock(&sysfs_mutex);
spin_lock(&sb_lock);
list_for_each_entry(sb, &sysfs_fs_type.fs_supers, s_instances) {
struct sysfs_super_info *info = sysfs_info(sb);
/*
* If we see a superblock on the fs_supers/s_instances
* list the unmount has not completed and sb->s_fs_info
* points to a valid struct sysfs_super_info.
*/
/* Ignore superblocks with the wrong ns */
if (info->ns[type] != ns)
continue;
info->ns[type] = NULL;
}
spin_unlock(&sb_lock);
mutex_unlock(&sysfs_mutex);
}
int __init sysfs_init(void)
{
int err = -ENOMEM;
......
......@@ -136,7 +136,7 @@ struct sysfs_addrm_cxt {
* instance).
*/
struct sysfs_super_info {
const void *ns[KOBJ_NS_TYPES];
void *ns[KOBJ_NS_TYPES];
};
#define sysfs_info(SB) ((struct sysfs_super_info *)(SB->s_fs_info))
extern struct sysfs_dirent sysfs_root;
......
......@@ -1848,7 +1848,6 @@ static void ubifs_put_super(struct super_block *sb)
bdi_destroy(&c->bdi);
ubi_close_volume(c->ubi);
mutex_unlock(&c->umount_mutex);
kfree(c);
}
static int ubifs_remount_fs(struct super_block *sb, int *flags, char *data)
......@@ -1971,17 +1970,12 @@ static struct ubi_volume_desc *open_ubi(const char *name, int mode)
return ERR_PTR(-EINVAL);
}
static int ubifs_fill_super(struct super_block *sb, void *data, int silent)
static struct ubifs_info *alloc_ubifs_info(struct ubi_volume_desc *ubi)
{
struct ubi_volume_desc *ubi = sb->s_fs_info;
struct ubifs_info *c;
struct inode *root;
int err;
c = kzalloc(sizeof(struct ubifs_info), GFP_KERNEL);
if (!c)
return -ENOMEM;
if (c) {
spin_lock_init(&c->cnt_lock);
spin_lock_init(&c->cs_lock);
spin_lock_init(&c->buds_lock);
......@@ -2014,18 +2008,27 @@ static int ubifs_fill_super(struct super_block *sb, void *data, int silent)
INIT_LIST_HEAD(&c->orph_new);
c->no_chk_data_crc = 1;
c->vfs_sb = sb;
c->highest_inum = UBIFS_FIRST_INO;
c->lhead_lnum = c->ltail_lnum = UBIFS_LOG_LNUM;
ubi_get_volume_info(ubi, &c->vi);
ubi_get_device_info(c->vi.ubi_num, &c->di);
}
return c;
}
static int ubifs_fill_super(struct super_block *sb, void *data, int silent)
{
struct ubifs_info *c = sb->s_fs_info;
struct inode *root;
int err;
c->vfs_sb = sb;
/* Re-open the UBI device in read-write mode */
c->ubi = ubi_open_volume(c->vi.ubi_num, c->vi.vol_id, UBI_READWRITE);
if (IS_ERR(c->ubi)) {
err = PTR_ERR(c->ubi);
goto out_free;
goto out;
}
/*
......@@ -2091,24 +2094,29 @@ static int ubifs_fill_super(struct super_block *sb, void *data, int silent)
bdi_destroy(&c->bdi);
out_close:
ubi_close_volume(c->ubi);
out_free:
kfree(c);
out:
return err;
}
static int sb_test(struct super_block *sb, void *data)
{
dev_t *dev = data;
struct ubifs_info *c1 = data;
struct ubifs_info *c = sb->s_fs_info;
return c->vi.cdev == *dev;
return c->vi.cdev == c1->vi.cdev;
}
static int sb_set(struct super_block *sb, void *data)
{
sb->s_fs_info = data;
return set_anon_super(sb, NULL);
}
static struct dentry *ubifs_mount(struct file_system_type *fs_type, int flags,
const char *name, void *data)
{
struct ubi_volume_desc *ubi;
struct ubi_volume_info vi;
struct ubifs_info *c;
struct super_block *sb;
int err;
......@@ -2125,19 +2133,24 @@ static struct dentry *ubifs_mount(struct file_system_type *fs_type, int flags,
name, (int)PTR_ERR(ubi));
return ERR_CAST(ubi);
}
ubi_get_volume_info(ubi, &vi);
dbg_gen("opened ubi%d_%d", vi.ubi_num, vi.vol_id);
c = alloc_ubifs_info(ubi);
if (!c) {
err = -ENOMEM;
goto out_close;
}
sb = sget(fs_type, &sb_test, &set_anon_super, &vi.cdev);
dbg_gen("opened ubi%d_%d", c->vi.ubi_num, c->vi.vol_id);
sb = sget(fs_type, sb_test, sb_set, c);
if (IS_ERR(sb)) {
err = PTR_ERR(sb);
goto out_close;
kfree(c);
}
if (sb->s_root) {
struct ubifs_info *c1 = sb->s_fs_info;
kfree(c);
/* A new mount point for already mounted UBIFS */
dbg_gen("this ubi volume is already mounted");
if (!!(flags & MS_RDONLY) != c1->ro_mount) {
......@@ -2146,11 +2159,6 @@ static struct dentry *ubifs_mount(struct file_system_type *fs_type, int flags,
}
} else {
sb->s_flags = flags;
/*
* Pass 'ubi' to 'fill_super()' in sb->s_fs_info where it is
* replaced by 'c'.
*/
sb->s_fs_info = ubi;
err = ubifs_fill_super(sb, data, flags & MS_SILENT ? 1 : 0);
if (err)
goto out_deact;
......@@ -2170,11 +2178,18 @@ static struct dentry *ubifs_mount(struct file_system_type *fs_type, int flags,
return ERR_PTR(err);
}
static void kill_ubifs_super(struct super_block *s)
{
struct ubifs_info *c = s->s_fs_info;
kill_anon_super(s);
kfree(c);
}
static struct file_system_type ubifs_fs_type = {
.name = "ubifs",
.owner = THIS_MODULE,
.mount = ubifs_mount,
.kill_sb = kill_anon_super,
.kill_sb = kill_ubifs_super,
};
/*
......
......@@ -32,15 +32,17 @@ enum kobj_ns_type {
/*
* Callbacks so sysfs can determine namespaces
* @current_ns: return calling task's namespace
* @grab_current_ns: return a new reference to calling task's namespace
* @netlink_ns: return namespace to which a sock belongs (right?)
* @initial_ns: return the initial namespace (i.e. init_net_ns)
* @drop_ns: drops a reference to namespace
*/
struct kobj_ns_type_operations {
enum kobj_ns_type type;
const void *(*current_ns)(void);
void *(*grab_current_ns)(void);
const void *(*netlink_ns)(struct sock *sk);
const void *(*initial_ns)(void);
void (*drop_ns)(void *);
};
int kobj_ns_type_register(const struct kobj_ns_type_operations *ops);
......@@ -48,9 +50,9 @@ int kobj_ns_type_registered(enum kobj_ns_type type);
const struct kobj_ns_type_operations *kobj_child_ns_ops(struct kobject *parent);
const struct kobj_ns_type_operations *kobj_ns_ops(struct kobject *kobj);
const void *kobj_ns_current(enum kobj_ns_type type);
void *kobj_ns_grab_current(enum kobj_ns_type type);
const void *kobj_ns_netlink(enum kobj_ns_type type, struct sock *sk);
const void *kobj_ns_initial(enum kobj_ns_type type);
void kobj_ns_exit(enum kobj_ns_type type, const void *ns);
void kobj_ns_drop(enum kobj_ns_type type, void *ns);
#endif /* _LINUX_KOBJECT_NS_H */
......@@ -177,9 +177,6 @@ struct sysfs_dirent *sysfs_get_dirent(struct sysfs_dirent *parent_sd,
struct sysfs_dirent *sysfs_get(struct sysfs_dirent *sd);
void sysfs_put(struct sysfs_dirent *sd);
/* Called to clear a ns tag when it is no longer valid */
void sysfs_exit_ns(enum kobj_ns_type type, const void *tag);
int __must_check sysfs_init(void);
#else /* CONFIG_SYSFS */
......@@ -338,10 +335,6 @@ static inline void sysfs_put(struct sysfs_dirent *sd)
{
}
static inline void sysfs_exit_ns(int type, const void *tag)
{
}
static inline int __must_check sysfs_init(void)
{
return 0;
......
......@@ -35,9 +35,12 @@ struct netns_ipvs;
#define NETDEV_HASHENTRIES (1 << NETDEV_HASHBITS)
struct net {
atomic_t count; /* To decided when the network
atomic_t passive; /* To decided when the network
* namespace should be freed.
*/
atomic_t count; /* To decided when the network
* namespace should be shut down.
*/
#ifdef NETNS_REFCNT_DEBUG
atomic_t use_count; /* To track references we
* destroy on demand
......@@ -154,6 +157,9 @@ int net_eq(const struct net *net1, const struct net *net2)
{
return net1 == net2;
}
extern void net_drop_ns(void *);
#else
static inline struct net *get_net(struct net *net)
......@@ -175,6 +181,8 @@ int net_eq(const struct net *net1, const struct net *net2)
{
return 1;
}
#define net_drop_ns NULL
#endif
......
......@@ -948,14 +948,14 @@ const struct kobj_ns_type_operations *kobj_ns_ops(struct kobject *kobj)
}
const void *kobj_ns_current(enum kobj_ns_type type)
void *kobj_ns_grab_current(enum kobj_ns_type type)
{
const void *ns = NULL;
void *ns = NULL;
spin_lock(&kobj_ns_type_lock);
if ((type > KOBJ_NS_TYPE_NONE) && (type < KOBJ_NS_TYPES) &&
kobj_ns_ops_tbl[type])
ns = kobj_ns_ops_tbl[type]->current_ns();
ns = kobj_ns_ops_tbl[type]->grab_current_ns();
spin_unlock(&kobj_ns_type_lock);
return ns;
......@@ -987,23 +987,15 @@ const void *kobj_ns_initial(enum kobj_ns_type type)
return ns;
}
/*
* kobj_ns_exit - invalidate a namespace tag
*
* @type: the namespace type (i.e. KOBJ_NS_TYPE_NET)
* @ns: the actual namespace being invalidated
*
* This is called when a tag is no longer valid. For instance,
* when a network namespace exits, it uses this helper to
* make sure no sb's sysfs_info points to the now-invalidated
* netns.
*/
void kobj_ns_exit(enum kobj_ns_type type, const void *ns)
void kobj_ns_drop(enum kobj_ns_type type, void *ns)
{
sysfs_exit_ns(type, ns);
spin_lock(&kobj_ns_type_lock);
if ((type > KOBJ_NS_TYPE_NONE) && (type < KOBJ_NS_TYPES) &&
kobj_ns_ops_tbl[type] && kobj_ns_ops_tbl[type]->drop_ns)
kobj_ns_ops_tbl[type]->drop_ns(ns);
spin_unlock(&kobj_ns_type_lock);
}
EXPORT_SYMBOL(kobject_get);
EXPORT_SYMBOL(kobject_put);
EXPORT_SYMBOL(kobject_del);
......
......@@ -1179,9 +1179,14 @@ static void remove_queue_kobjects(struct net_device *net)
#endif
}
static const void *net_current_ns(void)
static void *net_grab_current_ns(void)
{
return current->nsproxy->net_ns;
struct net *ns = current->nsproxy->net_ns;
#ifdef CONFIG_NET_NS
if (ns)
atomic_inc(&ns->passive);
#endif
return ns;
}
static const void *net_initial_ns(void)
......@@ -1196,22 +1201,13 @@ static const void *net_netlink_ns(struct sock *sk)
struct kobj_ns_type_operations net_ns_type_operations = {
.type = KOBJ_NS_TYPE_NET,
.current_ns = net_current_ns,
.grab_current_ns = net_grab_current_ns,
.netlink_ns = net_netlink_ns,
.initial_ns = net_initial_ns,
.drop_ns = net_drop_ns,
};
EXPORT_SYMBOL_GPL(net_ns_type_operations);
static void net_kobj_ns_exit(struct net *net)
{
kobj_ns_exit(KOBJ_NS_TYPE_NET, net);
}
static struct pernet_operations kobj_net_ops = {
.exit = net_kobj_ns_exit,
};
#ifdef CONFIG_HOTPLUG
static int netdev_uevent(struct device *d, struct kobj_uevent_env *env)
{
......@@ -1339,6 +1335,5 @@ EXPORT_SYMBOL(netdev_class_remove_file);
int netdev_kobject_init(void)
{
kobj_ns_type_register(&net_ns_type_operations);
register_pernet_subsys(&kobj_net_ops);
return class_register(&net_class);
}
......@@ -128,6 +128,7 @@ static __net_init int setup_net(struct net *net)
LIST_HEAD(net_exit_list);
atomic_set(&net->count, 1);
atomic_set(&net->passive, 1);
#ifdef NETNS_REFCNT_DEBUG
atomic_set(&net->use_count, 0);
......@@ -210,6 +211,13 @@ static void net_free(struct net *net)
kmem_cache_free(net_cachep, net);
}
void net_drop_ns(void *p)
{
struct net *ns = p;
if (ns && atomic_dec_and_test(&ns->passive))
net_free(ns);
}
struct net *copy_net_ns(unsigned long flags, struct net *old_net)
{
struct net *net;
......@@ -230,7 +238,7 @@ struct net *copy_net_ns(unsigned long flags, struct net *old_net)
}
mutex_unlock(&net_mutex);
if (rv < 0) {
net_free(net);
net_drop_ns(net);
return ERR_PTR(rv);
}
return net;
......@@ -286,7 +294,7 @@ static void cleanup_net(struct work_struct *work)
/* Finally it is safe to free my network namespace structure */
list_for_each_entry_safe(net, tmp, &net_exit_list, exit_list) {
list_del_init(&net->exit_list);
net_free(net);
net_drop_ns(net);
}
}
static DECLARE_WORK(net_cleanup_work, cleanup_net);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment