aboutsummaryrefslogtreecommitdiff
path: root/fs/namei.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/namei.c')
-rw-r--r--fs/namei.c345
1 files changed, 204 insertions, 141 deletions
diff --git a/fs/namei.c b/fs/namei.c
index ad74877e1442..ddb6a7c2b3d4 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -340,22 +340,14 @@ int generic_permission(struct inode *inode, int mask)
if (S_ISDIR(inode->i_mode)) {
/* DACs are overridable for directories */
- if (capable_wrt_inode_uidgid(inode, CAP_DAC_OVERRIDE))
- return 0;
if (!(mask & MAY_WRITE))
if (capable_wrt_inode_uidgid(inode,
CAP_DAC_READ_SEARCH))
return 0;
- return -EACCES;
- }
- /*
- * Read/write DACs are always overridable.
- * Executable DACs are overridable when there is
- * at least one exec bit set.
- */
- if (!(mask & MAY_EXEC) || (inode->i_mode & S_IXUGO))
if (capable_wrt_inode_uidgid(inode, CAP_DAC_OVERRIDE))
return 0;
+ return -EACCES;
+ }
/*
* Searching includes executable on directories, else just read.
@@ -364,6 +356,14 @@ int generic_permission(struct inode *inode, int mask)
if (mask == MAY_READ)
if (capable_wrt_inode_uidgid(inode, CAP_DAC_READ_SEARCH))
return 0;
+ /*
+ * Read/write DACs are always overridable.
+ * Executable DACs are overridable when there is
+ * at least one exec bit set.
+ */
+ if (!(mask & MAY_EXEC) || (inode->i_mode & S_IXUGO))
+ if (capable_wrt_inode_uidgid(inode, CAP_DAC_OVERRIDE))
+ return 0;
return -EACCES;
}
@@ -524,7 +524,7 @@ struct nameidata {
struct inode *link_inode;
unsigned root_seq;
int dfd;
-};
+} __randomize_layout;
static void set_nameidata(struct nameidata *p, int dfd, struct filename *name)
{
@@ -672,17 +672,15 @@ static bool legitimize_links(struct nameidata *nd)
/**
* unlazy_walk - try to switch to ref-walk mode.
* @nd: nameidata pathwalk data
- * @dentry: child of nd->path.dentry or NULL
- * @seq: seq number to check dentry against
* Returns: 0 on success, -ECHILD on failure
*
- * unlazy_walk attempts to legitimize the current nd->path, nd->root and dentry
- * for ref-walk mode. @dentry must be a path found by a do_lookup call on
- * @nd or NULL. Must be called from rcu-walk context.
+ * unlazy_walk attempts to legitimize the current nd->path and nd->root
+ * for ref-walk mode.
+ * Must be called from rcu-walk context.
* Nothing should touch nameidata between unlazy_walk() failure and
* terminate_walk().
*/
-static int unlazy_walk(struct nameidata *nd, struct dentry *dentry, unsigned seq)
+static int unlazy_walk(struct nameidata *nd)
{
struct dentry *parent = nd->path.dentry;
@@ -691,33 +689,66 @@ static int unlazy_walk(struct nameidata *nd, struct dentry *dentry, unsigned seq
nd->flags &= ~LOOKUP_RCU;
if (unlikely(!legitimize_links(nd)))
goto out2;
+ if (unlikely(!legitimize_path(nd, &nd->path, nd->seq)))
+ goto out1;
+ if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT)) {
+ if (unlikely(!legitimize_path(nd, &nd->root, nd->root_seq)))
+ goto out;
+ }
+ rcu_read_unlock();
+ BUG_ON(nd->inode != parent->d_inode);
+ return 0;
+
+out2:
+ nd->path.mnt = NULL;
+ nd->path.dentry = NULL;
+out1:
+ if (!(nd->flags & LOOKUP_ROOT))
+ nd->root.mnt = NULL;
+out:
+ rcu_read_unlock();
+ return -ECHILD;
+}
+
+/**
+ * unlazy_child - try to switch to ref-walk mode.
+ * @nd: nameidata pathwalk data
+ * @dentry: child of nd->path.dentry
+ * @seq: seq number to check dentry against
+ * Returns: 0 on success, -ECHILD on failure
+ *
+ * unlazy_child attempts to legitimize the current nd->path, nd->root and dentry
+ * for ref-walk mode. @dentry must be a path found by a do_lookup call on
+ * @nd. Must be called from rcu-walk context.
+ * Nothing should touch nameidata between unlazy_child() failure and
+ * terminate_walk().
+ */
+static int unlazy_child(struct nameidata *nd, struct dentry *dentry, unsigned seq)
+{
+ BUG_ON(!(nd->flags & LOOKUP_RCU));
+
+ nd->flags &= ~LOOKUP_RCU;
+ if (unlikely(!legitimize_links(nd)))
+ goto out2;
if (unlikely(!legitimize_mnt(nd->path.mnt, nd->m_seq)))
goto out2;
- if (unlikely(!lockref_get_not_dead(&parent->d_lockref)))
+ if (unlikely(!lockref_get_not_dead(&nd->path.dentry->d_lockref)))
goto out1;
/*
- * For a negative lookup, the lookup sequence point is the parents
- * sequence point, and it only needs to revalidate the parent dentry.
- *
- * For a positive lookup, we need to move both the parent and the
- * dentry from the RCU domain to be properly refcounted. And the
- * sequence number in the dentry validates *both* dentry counters,
- * since we checked the sequence number of the parent after we got
- * the child sequence number. So we know the parent must still
- * be valid if the child sequence number is still valid.
+ * We need to move both the parent and the dentry from the RCU domain
+ * to be properly refcounted. And the sequence number in the dentry
+ * validates *both* dentry counters, since we checked the sequence
+ * number of the parent after we got the child sequence number. So we
+ * know the parent must still be valid if the child sequence number is
*/
- if (!dentry) {
- if (read_seqcount_retry(&parent->d_seq, nd->seq))
- goto out;
- BUG_ON(nd->inode != parent->d_inode);
- } else {
- if (!lockref_get_not_dead(&dentry->d_lockref))
- goto out;
- if (read_seqcount_retry(&dentry->d_seq, seq))
- goto drop_dentry;
+ if (unlikely(!lockref_get_not_dead(&dentry->d_lockref)))
+ goto out;
+ if (unlikely(read_seqcount_retry(&dentry->d_seq, seq))) {
+ rcu_read_unlock();
+ dput(dentry);
+ goto drop_root_mnt;
}
-
/*
* Sequence counts matched. Now make sure that the root is
* still valid and get it if required.
@@ -733,10 +764,6 @@ static int unlazy_walk(struct nameidata *nd, struct dentry *dentry, unsigned seq
rcu_read_unlock();
return 0;
-drop_dentry:
- rcu_read_unlock();
- dput(dentry);
- goto drop_root_mnt;
out2:
nd->path.mnt = NULL;
out1:
@@ -749,27 +776,12 @@ drop_root_mnt:
return -ECHILD;
}
-static int unlazy_link(struct nameidata *nd, struct path *link, unsigned seq)
-{
- if (unlikely(!legitimize_path(nd, link, seq))) {
- drop_links(nd);
- nd->depth = 0;
- nd->flags &= ~LOOKUP_RCU;
- nd->path.mnt = NULL;
- nd->path.dentry = NULL;
- if (!(nd->flags & LOOKUP_ROOT))
- nd->root.mnt = NULL;
- rcu_read_unlock();
- } else if (likely(unlazy_walk(nd, NULL, 0)) == 0) {
- return 0;
- }
- path_put(link);
- return -ECHILD;
-}
-
static inline int d_revalidate(struct dentry *dentry, unsigned int flags)
{
- return dentry->d_op->d_revalidate(dentry, flags);
+ if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE))
+ return dentry->d_op->d_revalidate(dentry, flags);
+ else
+ return 1;
}
/**
@@ -790,7 +802,7 @@ static int complete_walk(struct nameidata *nd)
if (nd->flags & LOOKUP_RCU) {
if (!(nd->flags & LOOKUP_ROOT))
nd->root.mnt = NULL;
- if (unlikely(unlazy_walk(nd, NULL, 0)))
+ if (unlikely(unlazy_walk(nd)))
return -ECHILD;
}
@@ -996,7 +1008,7 @@ static int may_linkat(struct path *link)
/* Source inode owner (or CAP_FOWNER) can hardlink all they like,
* otherwise, it must be a safe source.
*/
- if (inode_owner_or_capable(inode) || safe_hardlink_source(inode))
+ if (safe_hardlink_source(inode) || inode_owner_or_capable(inode))
return 0;
audit_log_link_denied("linkat", link);
@@ -1016,7 +1028,7 @@ const char *get_link(struct nameidata *nd)
touch_atime(&last->link);
cond_resched();
} else if (atime_needs_update_rcu(&last->link, inode)) {
- if (unlikely(unlazy_walk(nd, NULL, 0)))
+ if (unlikely(unlazy_walk(nd)))
return ERR_PTR(-ECHILD);
touch_atime(&last->link);
}
@@ -1035,7 +1047,7 @@ const char *get_link(struct nameidata *nd)
if (nd->flags & LOOKUP_RCU) {
res = get(NULL, inode, &last->done);
if (res == ERR_PTR(-ECHILD)) {
- if (unlikely(unlazy_walk(nd, NULL, 0)))
+ if (unlikely(unlazy_walk(nd)))
return ERR_PTR(-ECHILD);
res = get(dentry, inode, &last->done);
}
@@ -1100,7 +1112,6 @@ static int follow_automount(struct path *path, struct nameidata *nd,
bool *need_mntput)
{
struct vfsmount *mnt;
- const struct cred *old_cred;
int err;
if (!path->dentry->d_op || !path->dentry->d_op->d_automount)
@@ -1129,9 +1140,7 @@ static int follow_automount(struct path *path, struct nameidata *nd,
if (nd->total_link_count >= 40)
return -ELOOP;
- old_cred = override_creds(&init_cred);
mnt = path->dentry->d_op->d_automount(path);
- revert_creds(old_cred);
if (IS_ERR(mnt)) {
/*
* The filesystem is allowed to return -EISDIR here to indicate
@@ -1472,19 +1481,14 @@ static struct dentry *lookup_dcache(const struct qstr *name,
struct dentry *dir,
unsigned int flags)
{
- struct dentry *dentry;
- int error;
-
- dentry = d_lookup(dir, name);
+ struct dentry *dentry = d_lookup(dir, name);
if (dentry) {
- if (dentry->d_flags & DCACHE_OP_REVALIDATE) {
- error = d_revalidate(dentry, flags);
- if (unlikely(error <= 0)) {
- if (!error)
- d_invalidate(dentry);
- dput(dentry);
- return ERR_PTR(error);
- }
+ int error = d_revalidate(dentry, flags);
+ if (unlikely(error <= 0)) {
+ if (!error)
+ d_invalidate(dentry);
+ dput(dentry);
+ return ERR_PTR(error);
}
}
return dentry;
@@ -1549,7 +1553,7 @@ static int lookup_fast(struct nameidata *nd,
bool negative;
dentry = __d_lookup_rcu(parent, &nd->last, &seq);
if (unlikely(!dentry)) {
- if (unlazy_walk(nd, NULL, 0))
+ if (unlazy_walk(nd))
return -ECHILD;
return 0;
}
@@ -1574,14 +1578,8 @@ static int lookup_fast(struct nameidata *nd,
return -ECHILD;
*seqp = seq;
- if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE))
- status = d_revalidate(dentry, nd->flags);
- if (unlikely(status <= 0)) {
- if (unlazy_walk(nd, dentry, seq))
- return -ECHILD;
- if (status == -ECHILD)
- status = d_revalidate(dentry, nd->flags);
- } else {
+ status = d_revalidate(dentry, nd->flags);
+ if (likely(status > 0)) {
/*
* Note: do negative dentry check after revalidation in
* case that drops it.
@@ -1592,15 +1590,17 @@ static int lookup_fast(struct nameidata *nd,
path->dentry = dentry;
if (likely(__follow_mount_rcu(nd, path, inode, seqp)))
return 1;
- if (unlazy_walk(nd, dentry, seq))
- return -ECHILD;
}
+ if (unlazy_child(nd, dentry, seq))
+ return -ECHILD;
+ if (unlikely(status == -ECHILD))
+ /* we'd been told to redo it in non-rcu mode */
+ status = d_revalidate(dentry, nd->flags);
} else {
dentry = __d_lookup(parent, &nd->last);
if (unlikely(!dentry))
return 0;
- if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE))
- status = d_revalidate(dentry, nd->flags);
+ status = d_revalidate(dentry, nd->flags);
}
if (unlikely(status <= 0)) {
if (!status)
@@ -1639,8 +1639,7 @@ again:
if (IS_ERR(dentry))
goto out;
if (unlikely(!d_in_lookup(dentry))) {
- if ((dentry->d_flags & DCACHE_OP_REVALIDATE) &&
- !(flags & LOOKUP_NO_REVAL)) {
+ if (!(flags & LOOKUP_NO_REVAL)) {
int error = d_revalidate(dentry, flags);
if (unlikely(error <= 0)) {
if (!error) {
@@ -1671,7 +1670,7 @@ static inline int may_lookup(struct nameidata *nd)
int err = inode_permission(nd->inode, MAY_EXEC|MAY_NOT_BLOCK);
if (err != -ECHILD)
return err;
- if (unlazy_walk(nd, NULL, 0))
+ if (unlazy_walk(nd))
return -ECHILD;
}
return inode_permission(nd->inode, MAY_EXEC);
@@ -1706,9 +1705,17 @@ static int pick_link(struct nameidata *nd, struct path *link,
error = nd_alloc_stack(nd);
if (unlikely(error)) {
if (error == -ECHILD) {
- if (unlikely(unlazy_link(nd, link, seq)))
- return -ECHILD;
- error = nd_alloc_stack(nd);
+ if (unlikely(!legitimize_path(nd, link, seq))) {
+ drop_links(nd);
+ nd->depth = 0;
+ nd->flags &= ~LOOKUP_RCU;
+ nd->path.mnt = NULL;
+ nd->path.dentry = NULL;
+ if (!(nd->flags & LOOKUP_ROOT))
+ nd->root.mnt = NULL;
+ rcu_read_unlock();
+ } else if (likely(unlazy_walk(nd)) == 0)
+ error = nd_alloc_stack(nd);
}
if (error) {
path_put(link);
@@ -2125,7 +2132,7 @@ OK:
}
if (unlikely(!d_can_lookup(nd->path.dentry))) {
if (nd->flags & LOOKUP_RCU) {
- if (unlazy_walk(nd, NULL, 0))
+ if (unlazy_walk(nd))
return -ECHILD;
}
return -ENOTDIR;
@@ -2135,22 +2142,19 @@ OK:
static const char *path_init(struct nameidata *nd, unsigned flags)
{
- int retval = 0;
const char *s = nd->name->name;
+ if (!*s)
+ flags &= ~LOOKUP_RCU;
+
nd->last_type = LAST_ROOT; /* if there are only slashes... */
nd->flags = flags | LOOKUP_JUMPED | LOOKUP_PARENT;
nd->depth = 0;
if (flags & LOOKUP_ROOT) {
struct dentry *root = nd->root.dentry;
struct inode *inode = root->d_inode;
- if (*s) {
- if (!d_can_lookup(root))
- return ERR_PTR(-ENOTDIR);
- retval = inode_permission(inode, MAY_EXEC);
- if (retval)
- return ERR_PTR(retval);
- }
+ if (*s && unlikely(!d_can_lookup(root)))
+ return ERR_PTR(-ENOTDIR);
nd->path = nd->root;
nd->inode = inode;
if (flags & LOOKUP_RCU) {
@@ -2248,6 +2252,35 @@ static inline int lookup_last(struct nameidata *nd)
return walk_component(nd, 0);
}
+static int handle_lookup_down(struct nameidata *nd)
+{
+ struct path path = nd->path;
+ struct inode *inode = nd->inode;
+ unsigned seq = nd->seq;
+ int err;
+
+ if (nd->flags & LOOKUP_RCU) {
+ /*
+ * don't bother with unlazy_walk on failure - we are
+ * at the very beginning of walk, so we lose nothing
+ * if we simply redo everything in non-RCU mode
+ */
+ if (unlikely(!__follow_mount_rcu(nd, &path, &inode, &seq)))
+ return -ECHILD;
+ } else {
+ dget(path.dentry);
+ err = follow_managed(&path, nd);
+ if (unlikely(err < 0))
+ return err;
+ inode = d_backing_inode(path.dentry);
+ seq = 0;
+ }
+ path_to_nameidata(&path, nd);
+ nd->inode = inode;
+ nd->seq = seq;
+ return 0;
+}
+
/* Returns 0 and nd will be valid on success; Retuns error, otherwise. */
static int path_lookupat(struct nameidata *nd, unsigned flags, struct path *path)
{
@@ -2256,6 +2289,15 @@ static int path_lookupat(struct nameidata *nd, unsigned flags, struct path *path
if (IS_ERR(s))
return PTR_ERR(s);
+
+ if (unlikely(flags & LOOKUP_DOWN)) {
+ err = handle_lookup_down(nd);
+ if (unlikely(err < 0)) {
+ terminate_walk(nd);
+ return err;
+ }
+ }
+
while (!(err = link_path_walk(s, nd))
&& ((err = lookup_last(nd)) > 0)) {
s = trailing_symlink(nd);
@@ -2582,7 +2624,7 @@ mountpoint_last(struct nameidata *nd)
/* If we're in rcuwalk, drop out of it to handle last component */
if (nd->flags & LOOKUP_RCU) {
- if (unlazy_walk(nd, NULL, 0))
+ if (unlazy_walk(nd))
return -ECHILD;
}
@@ -2941,10 +2983,16 @@ static inline int open_to_namei_flags(int flag)
static int may_o_create(const struct path *dir, struct dentry *dentry, umode_t mode)
{
+ struct user_namespace *s_user_ns;
int error = security_path_mknod(dir, dentry, mode, 0);
if (error)
return error;
+ s_user_ns = dir->dentry->d_sb->s_user_ns;
+ if (!kuid_has_mapping(s_user_ns, current_fsuid()) ||
+ !kgid_has_mapping(s_user_ns, current_fsgid()))
+ return -EOVERFLOW;
+
error = inode_permission(dir->dentry->d_inode, MAY_WRITE | MAY_EXEC);
if (error)
return error;
@@ -3069,9 +3117,6 @@ static int lookup_open(struct nameidata *nd, struct path *path,
if (d_in_lookup(dentry))
break;
- if (!(dentry->d_flags & DCACHE_OP_REVALIDATE))
- break;
-
error = d_revalidate(dentry, nd->flags);
if (likely(error > 0))
break;
@@ -3353,13 +3398,49 @@ out:
return error;
}
+struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode, int open_flag)
+{
+ struct dentry *child = NULL;
+ struct inode *dir = dentry->d_inode;
+ struct inode *inode;
+ int error;
+
+ /* we want directory to be writable */
+ error = inode_permission(dir, MAY_WRITE | MAY_EXEC);
+ if (error)
+ goto out_err;
+ error = -EOPNOTSUPP;
+ if (!dir->i_op->tmpfile)
+ goto out_err;
+ error = -ENOMEM;
+ child = d_alloc(dentry, &slash_name);
+ if (unlikely(!child))
+ goto out_err;
+ error = dir->i_op->tmpfile(dir, child, mode);
+ if (error)
+ goto out_err;
+ error = -ENOENT;
+ inode = child->d_inode;
+ if (unlikely(!inode))
+ goto out_err;
+ if (!(open_flag & O_EXCL)) {
+ spin_lock(&inode->i_lock);
+ inode->i_state |= I_LINKABLE;
+ spin_unlock(&inode->i_lock);
+ }
+ return child;
+
+out_err:
+ dput(child);
+ return ERR_PTR(error);
+}
+EXPORT_SYMBOL(vfs_tmpfile);
+
static int do_tmpfile(struct nameidata *nd, unsigned flags,
const struct open_flags *op,
struct file *file, int *opened)
{
- static const struct qstr name = QSTR_INIT("/", 1);
struct dentry *child;
- struct inode *dir;
struct path path;
int error = path_lookupat(nd, flags | LOOKUP_DIRECTORY, &path);
if (unlikely(error))
@@ -3367,25 +3448,12 @@ static int do_tmpfile(struct nameidata *nd, unsigned flags,
error = mnt_want_write(path.mnt);
if (unlikely(error))
goto out;
- dir = path.dentry->d_inode;
- /* we want directory to be writable */
- error = inode_permission(dir, MAY_WRITE | MAY_EXEC);
- if (error)
- goto out2;
- if (!dir->i_op->tmpfile) {
- error = -EOPNOTSUPP;
- goto out2;
- }
- child = d_alloc(path.dentry, &name);
- if (unlikely(!child)) {
- error = -ENOMEM;
+ child = vfs_tmpfile(path.dentry, op->mode, op->open_flag);
+ error = PTR_ERR(child);
+ if (unlikely(IS_ERR(child)))
goto out2;
- }
dput(path.dentry);
path.dentry = child;
- error = dir->i_op->tmpfile(dir, child, op->mode);
- if (error)
- goto out2;
audit_inode(nd->name, child, 0);
/* Don't check for other permissions, the inode was just created */
error = may_open(&path, 0, op->open_flag);
@@ -3396,14 +3464,8 @@ static int do_tmpfile(struct nameidata *nd, unsigned flags,
if (error)
goto out2;
error = open_check_o_direct(file);
- if (error) {
+ if (error)
fput(file);
- } else if (!(op->open_flag & O_EXCL)) {
- struct inode *inode = file_inode(file);
- spin_lock(&inode->i_lock);
- inode->i_state |= I_LINKABLE;
- spin_unlock(&inode->i_lock);
- }
out2:
mnt_drop_write(path.mnt);
out:
@@ -4269,6 +4331,7 @@ SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname
* The worst of all namespace operations - renaming directory. "Perverted"
* doesn't even start to describe it. Somebody in UCB had a heck of a trip...
* Problems:
+ *
* a) we can get into loop creation.
* b) race potential - two innocent renames can create a loop together.
* That's where 4.4 screws up. Current fix: serialization on
@@ -4299,11 +4362,11 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
{
int error;
bool is_dir = d_is_dir(old_dentry);
- const unsigned char *old_name;
struct inode *source = old_dentry->d_inode;
struct inode *target = new_dentry->d_inode;
bool new_is_dir = false;
unsigned max_links = new_dir->i_sb->s_max_links;
+ struct name_snapshot old_name;
if (source == target)
return 0;
@@ -4350,7 +4413,7 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
if (error)
return error;
- old_name = fsnotify_oldname_init(old_dentry->d_name.name);
+ take_dentry_name_snapshot(&old_name, old_dentry);
dget(new_dentry);
if (!is_dir || (flags & RENAME_EXCHANGE))
lock_two_nondirectories(source, target);
@@ -4405,14 +4468,14 @@ out:
inode_unlock(target);
dput(new_dentry);
if (!error) {
- fsnotify_move(old_dir, new_dir, old_name, is_dir,
+ fsnotify_move(old_dir, new_dir, old_name.name, is_dir,
!(flags & RENAME_EXCHANGE) ? target : NULL, old_dentry);
if (flags & RENAME_EXCHANGE) {
fsnotify_move(new_dir, old_dir, old_dentry->d_name.name,
new_is_dir, NULL, new_dentry);
}
}
- fsnotify_oldname_free(old_name);
+ release_dentry_name_snapshot(&old_name);
return error;
}
@@ -4735,7 +4798,7 @@ int __page_symlink(struct inode *inode, const char *symname, int len, int nofs)
struct page *page;
void *fsdata;
int err;
- unsigned int flags = AOP_FLAG_UNINTERRUPTIBLE;
+ unsigned int flags = 0;
if (nofs)
flags |= AOP_FLAG_NOFS;