#include <linux/init.h>
#include <linux/export.h>
+#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/namei.h>
* POSIX.1 2.4: an empty pathname is invalid (ENOENT).
* PATH_MAX includes the nul terminator --RR.
*/
-static int do_getname(const char __user *filename, char *page)
-{
- int retval;
- unsigned long len = PATH_MAX;
-
- if (!segment_eq(get_fs(), KERNEL_DS)) {
- if ((unsigned long) filename >= TASK_SIZE)
- return -EFAULT;
- if (TASK_SIZE - (unsigned long) filename < PATH_MAX)
- len = TASK_SIZE - (unsigned long) filename;
- }
-
- retval = strncpy_from_user(page, filename, len);
- if (retval > 0) {
- if (retval < len)
- return 0;
- return -ENAMETOOLONG;
- } else if (!retval)
- retval = -ENOENT;
- return retval;
-}
-
static char *getname_flags(const char __user *filename, int flags, int *empty)
{
- char *result = __getname();
- int retval;
+ char *result = __getname(), *err;
+ int len;
- if (!result)
+ if (unlikely(!result))
return ERR_PTR(-ENOMEM);
- retval = do_getname(filename, result);
- if (retval < 0) {
- if (retval == -ENOENT && empty)
+ len = strncpy_from_user(result, filename, PATH_MAX);
+ err = ERR_PTR(len);
+ if (unlikely(len < 0))
+ goto error;
+
+ /* The empty path is special. */
+ if (unlikely(!len)) {
+ if (empty)
*empty = 1;
- if (retval != -ENOENT || !(flags & LOOKUP_EMPTY)) {
- __putname(result);
- return ERR_PTR(retval);
- }
+ err = ERR_PTR(-ENOENT);
+ if (!(flags & LOOKUP_EMPTY))
+ goto error;
+ }
+
+ err = ERR_PTR(-ENAMETOOLONG);
+ if (likely(len < PATH_MAX)) {
+ audit_getname(result);
+ return result;
}
- audit_getname(result);
- return result;
+
+error:
+ __putname(result);
+ return err;
}
char *getname(const char __user * filename)
{
unsigned int mode = inode->i_mode;
- if (current_user_ns() != inode_userns(inode))
- goto other_perms;
-
- if (likely(current_fsuid() == inode->i_uid))
+ if (likely(uid_eq(current_fsuid(), inode->i_uid)))
mode >>= 6;
else {
if (IS_POSIXACL(inode) && (mode & S_IRWXG)) {
mode >>= 3;
}
-other_perms:
/*
* If the DACs are ok we don't need any capability check.
*/
if (S_ISDIR(inode->i_mode)) {
/* DACs are overridable for directories */
- if (ns_capable(inode_userns(inode), CAP_DAC_OVERRIDE))
+ if (inode_capable(inode, CAP_DAC_OVERRIDE))
return 0;
if (!(mask & MAY_WRITE))
- if (ns_capable(inode_userns(inode), CAP_DAC_READ_SEARCH))
+ if (inode_capable(inode, CAP_DAC_READ_SEARCH))
return 0;
return -EACCES;
}
* at least one exec bit set.
*/
if (!(mask & MAY_EXEC) || (inode->i_mode & S_IXUGO))
- if (ns_capable(inode_userns(inode), CAP_DAC_OVERRIDE))
+ if (inode_capable(inode, CAP_DAC_OVERRIDE))
return 0;
/*
*/
mask &= MAY_READ | MAY_WRITE | MAY_EXEC;
if (mask == MAY_READ)
- if (ns_capable(inode_userns(inode), CAP_DAC_READ_SEARCH))
+ if (inode_capable(inode, CAP_DAC_READ_SEARCH))
return 0;
return -EACCES;
mntget(nd->path.mnt);
rcu_read_unlock();
- br_read_unlock(vfsmount_lock);
+ br_read_unlock(&vfsmount_lock);
nd->flags &= ~LOOKUP_RCU;
return 0;
if (unlikely(!__d_rcu_to_refcount(dentry, nd->seq))) {
spin_unlock(&dentry->d_lock);
rcu_read_unlock();
- br_read_unlock(vfsmount_lock);
+ br_read_unlock(&vfsmount_lock);
return -ECHILD;
}
BUG_ON(nd->inode != dentry->d_inode);
spin_unlock(&dentry->d_lock);
mntget(nd->path.mnt);
rcu_read_unlock();
- br_read_unlock(vfsmount_lock);
+ br_read_unlock(&vfsmount_lock);
}
if (likely(!(nd->flags & LOOKUP_JUMPED)))
struct mount *parent;
struct dentry *mountpoint;
- br_read_lock(vfsmount_lock);
+ br_read_lock(&vfsmount_lock);
parent = mnt->mnt_parent;
if (&parent->mnt == path->mnt) {
- br_read_unlock(vfsmount_lock);
+ br_read_unlock(&vfsmount_lock);
return 0;
}
mntget(&parent->mnt);
mountpoint = dget(mnt->mnt_mountpoint);
- br_read_unlock(vfsmount_lock);
+ br_read_unlock(&vfsmount_lock);
dput(path->dentry);
path->dentry = mountpoint;
mntput(path->mnt);
if (!(nd->flags & LOOKUP_ROOT))
nd->root.mnt = NULL;
rcu_read_unlock();
- br_read_unlock(vfsmount_lock);
+ br_read_unlock(&vfsmount_lock);
return -ECHILD;
}
* small and for now I'd prefer to have fast path as straight as possible.
* It _is_ time-critical.
*/
-static int do_lookup(struct nameidata *nd, struct qstr *name,
- struct path *path, struct inode **inode)
+static int lookup_fast(struct nameidata *nd, struct qstr *name,
+ struct path *path, struct inode **inode)
{
struct vfsmount *mnt = nd->path.mnt;
struct dentry *dentry, *parent = nd->path.dentry;
*/
if (nd->flags & LOOKUP_RCU) {
unsigned seq;
- *inode = nd->inode;
- dentry = __d_lookup_rcu(parent, name, &seq, inode);
+ dentry = __d_lookup_rcu(parent, name, &seq, nd->inode);
if (!dentry)
goto unlazy;
- /* Memory barrier in read_seqcount_begin of child is enough */
+ /*
+ * This sequence count validates that the inode matches
+ * the dentry name information from lookup.
+ */
+ *inode = dentry->d_inode;
+ if (read_seqcount_retry(&dentry->d_seq, seq))
+ return -ECHILD;
+
+ /*
+ * This sequence count validates that the parent had no
+ * changes while we did the lookup of the dentry above.
+ *
+ * The memory barrier in read_seqcount_begin of child is
+ * enough, we can use __read_seqcount_retry here.
+ */
if (__read_seqcount_retry(&parent->d_seq, nd->seq))
return -ECHILD;
nd->seq = seq;
goto need_lookup;
}
}
-done:
+
path->mnt = mnt;
path->dentry = dentry;
err = follow_managed(path, nd->flags);
return 0;
need_lookup:
+ return 1;
+}
+
+/* Fast lookup failed, do it the slow way */
+static int lookup_slow(struct nameidata *nd, struct qstr *name,
+ struct path *path)
+{
+ struct dentry *dentry, *parent;
+ int err;
+
+ parent = nd->path.dentry;
BUG_ON(nd->inode != parent->d_inode);
mutex_lock(&parent->d_inode->i_mutex);
mutex_unlock(&parent->d_inode->i_mutex);
if (IS_ERR(dentry))
return PTR_ERR(dentry);
- goto done;
+ path->mnt = nd->path.mnt;
+ path->dentry = dentry;
+ err = follow_managed(path, nd->flags);
+ if (unlikely(err < 0)) {
+ path_put_conditional(path, nd);
+ return err;
+ }
+ if (err)
+ nd->flags |= LOOKUP_JUMPED;
+ return 0;
}
static inline int may_lookup(struct nameidata *nd)
if (!(nd->flags & LOOKUP_ROOT))
nd->root.mnt = NULL;
rcu_read_unlock();
- br_read_unlock(vfsmount_lock);
+ br_read_unlock(&vfsmount_lock);
}
}
*/
if (unlikely(type != LAST_NORM))
return handle_dots(nd, type);
- err = do_lookup(nd, name, path, &inode);
+ err = lookup_fast(nd, name, path, &inode);
if (unlikely(err)) {
- terminate_walk(nd);
- return err;
- }
- if (!inode) {
- path_to_nameidata(path, nd);
- terminate_walk(nd);
- return -ENOENT;
+ if (err < 0)
+ goto out_err;
+
+ err = lookup_slow(nd, name, path);
+ if (err < 0)
+ goto out_err;
+
+ inode = path->dentry->d_inode;
}
+ err = -ENOENT;
+ if (!inode)
+ goto out_path_put;
+
if (should_follow_link(inode, follow)) {
if (nd->flags & LOOKUP_RCU) {
if (unlikely(unlazy_walk(nd, path->dentry))) {
- terminate_walk(nd);
- return -ECHILD;
+ err = -ECHILD;
+ goto out_err;
}
}
BUG_ON(inode != path->dentry->d_inode);
path_to_nameidata(path, nd);
nd->inode = inode;
return 0;
+
+out_path_put:
+ path_to_nameidata(path, nd);
+out_err:
+ terminate_walk(nd);
+ return err;
}
/*
*/
static inline unsigned long hash_name(const char *name, unsigned int *hashp)
{
- unsigned long a, mask, hash, len;
+ unsigned long a, b, adata, bdata, mask, hash, len;
+ const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS;
hash = a = 0;
len = -sizeof(unsigned long);
hash = (hash + a) * 9;
len += sizeof(unsigned long);
a = load_unaligned_zeropad(name+len);
- /* Do we have any NUL or '/' bytes in this word? */
- mask = has_zero(a) | has_zero(a ^ REPEAT_BYTE('/'));
- } while (!mask);
-
- /* The mask *below* the first high bit set */
- mask = (mask - 1) & ~mask;
- mask >>= 7;
- hash += a & mask;
+ b = a ^ REPEAT_BYTE('/');
+ } while (!(has_zero(a, &adata, &constants) | has_zero(b, &bdata, &constants)));
+
+ adata = prep_zero_mask(a, adata, &constants);
+ bdata = prep_zero_mask(b, bdata, &constants);
+
+ mask = create_zero_mask(adata | bdata);
+
+ hash += a & zero_bytemask(mask);
*hashp = fold_hash(hash);
- return len + count_masked_bytes(mask);
+ return len + find_zero(mask);
}
#else
nd->path = nd->root;
nd->inode = inode;
if (flags & LOOKUP_RCU) {
- br_read_lock(vfsmount_lock);
+ br_read_lock(&vfsmount_lock);
rcu_read_lock();
nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
} else {
if (*name=='/') {
if (flags & LOOKUP_RCU) {
- br_read_lock(vfsmount_lock);
+ br_read_lock(&vfsmount_lock);
rcu_read_lock();
set_root_rcu(nd);
} else {
struct fs_struct *fs = current->fs;
unsigned seq;
- br_read_lock(vfsmount_lock);
+ br_read_lock(&vfsmount_lock);
rcu_read_lock();
do {
if (fput_needed)
*fp = file;
nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
- br_read_lock(vfsmount_lock);
+ br_read_lock(&vfsmount_lock);
rcu_read_lock();
} else {
path_get(&file->f_path);
*/
static inline int check_sticky(struct inode *dir, struct inode *inode)
{
- uid_t fsuid = current_fsuid();
+ kuid_t fsuid = current_fsuid();
if (!(dir->i_mode & S_ISVTX))
return 0;
- if (current_user_ns() != inode_userns(inode))
- goto other_userns;
- if (inode->i_uid == fsuid)
+ if (uid_eq(inode->i_uid, fsuid))
return 0;
- if (dir->i_uid == fsuid)
+ if (uid_eq(dir->i_uid, fsuid))
return 0;
-
-other_userns:
- return !ns_capable(inode_userns(inode), CAP_FOWNER);
+ return !inode_capable(inode, CAP_FOWNER);
}
/*
if (error)
return error;
- if ((S_ISCHR(mode) || S_ISBLK(mode)) &&
- !ns_capable(inode_userns(dir), CAP_MKNOD))
+ if ((S_ISCHR(mode) || S_ISBLK(mode)) && !capable(CAP_MKNOD))
return -EPERM;
if (!dir->i_op->mknod)