#include <linux/mm.h>
#include <linux/file.h>
#include <linux/fdtable.h>
-#include <linux/quotaops.h>
#include <linux/fsnotify.h>
#include <linux/module.h>
-#include <linux/slab.h>
#include <linux/tty.h>
#include <linux/namei.h>
#include <linux/backing-dev.h>
#include <linux/securebits.h>
#include <linux/security.h>
#include <linux/mount.h>
-#include <linux/vfs.h>
#include <linux/fcntl.h>
+#include <linux/slab.h>
#include <asm/uaccess.h>
#include <linux/fs.h>
#include <linux/personality.h>
#include <linux/rcupdate.h>
#include <linux/audit.h>
#include <linux/falloc.h>
+#include <linux/fs_struct.h>
+#include <linux/ima.h>
+#include <linux/dnotify.h>
-int vfs_statfs(struct dentry *dentry, struct kstatfs *buf)
-{
- int retval = -ENODEV;
-
- if (dentry) {
- retval = -ENOSYS;
- if (dentry->d_sb->s_op->statfs) {
- memset(buf, 0, sizeof(*buf));
- retval = security_sb_statfs(dentry);
- if (retval)
- return retval;
- retval = dentry->d_sb->s_op->statfs(dentry, buf);
- if (retval == 0 && buf->f_frsize == 0)
- buf->f_frsize = buf->f_bsize;
- }
- }
- return retval;
-}
+#include "internal.h"
-EXPORT_SYMBOL(vfs_statfs);
-
-static int vfs_statfs_native(struct dentry *dentry, struct statfs *buf)
-{
- struct kstatfs st;
- int retval;
-
- retval = vfs_statfs(dentry, &st);
- if (retval)
- return retval;
-
- if (sizeof(*buf) == sizeof(st))
- memcpy(buf, &st, sizeof(st));
- else {
- if (sizeof buf->f_blocks == 4) {
- if ((st.f_blocks | st.f_bfree | st.f_bavail |
- st.f_bsize | st.f_frsize) &
- 0xffffffff00000000ULL)
- return -EOVERFLOW;
- /*
- * f_files and f_ffree may be -1; it's okay to stuff
- * that into 32 bits
- */
- if (st.f_files != -1 &&
- (st.f_files & 0xffffffff00000000ULL))
- return -EOVERFLOW;
- if (st.f_ffree != -1 &&
- (st.f_ffree & 0xffffffff00000000ULL))
- return -EOVERFLOW;
- }
-
- buf->f_type = st.f_type;
- buf->f_bsize = st.f_bsize;
- buf->f_blocks = st.f_blocks;
- buf->f_bfree = st.f_bfree;
- buf->f_bavail = st.f_bavail;
- buf->f_files = st.f_files;
- buf->f_ffree = st.f_ffree;
- buf->f_fsid = st.f_fsid;
- buf->f_namelen = st.f_namelen;
- buf->f_frsize = st.f_frsize;
- memset(buf->f_spare, 0, sizeof(buf->f_spare));
- }
- return 0;
-}
-
-static int vfs_statfs64(struct dentry *dentry, struct statfs64 *buf)
-{
- struct kstatfs st;
- int retval;
-
- retval = vfs_statfs(dentry, &st);
- if (retval)
- return retval;
-
- if (sizeof(*buf) == sizeof(st))
- memcpy(buf, &st, sizeof(st));
- else {
- buf->f_type = st.f_type;
- buf->f_bsize = st.f_bsize;
- buf->f_blocks = st.f_blocks;
- buf->f_bfree = st.f_bfree;
- buf->f_bavail = st.f_bavail;
- buf->f_files = st.f_files;
- buf->f_ffree = st.f_ffree;
- buf->f_fsid = st.f_fsid;
- buf->f_namelen = st.f_namelen;
- buf->f_frsize = st.f_frsize;
- memset(buf->f_spare, 0, sizeof(buf->f_spare));
- }
- return 0;
-}
-
-SYSCALL_DEFINE2(statfs, const char __user *, pathname, struct statfs __user *, buf)
-{
- struct path path;
- int error;
-
- error = user_path(pathname, &path);
- if (!error) {
- struct statfs tmp;
- error = vfs_statfs_native(path.dentry, &tmp);
- if (!error && copy_to_user(buf, &tmp, sizeof(tmp)))
- error = -EFAULT;
- path_put(&path);
- }
- return error;
-}
-
-SYSCALL_DEFINE3(statfs64, const char __user *, pathname, size_t, sz, struct statfs64 __user *, buf)
-{
- struct path path;
- long error;
-
- if (sz != sizeof(*buf))
- return -EINVAL;
- error = user_path(pathname, &path);
- if (!error) {
- struct statfs64 tmp;
- error = vfs_statfs64(path.dentry, &tmp);
- if (!error && copy_to_user(buf, &tmp, sizeof(tmp)))
- error = -EFAULT;
- path_put(&path);
- }
- return error;
-}
-
-SYSCALL_DEFINE2(fstatfs, unsigned int, fd, struct statfs __user *, buf)
-{
- struct file * file;
- struct statfs tmp;
- int error;
-
- error = -EBADF;
- file = fget(fd);
- if (!file)
- goto out;
- error = vfs_statfs_native(file->f_path.dentry, &tmp);
- if (!error && copy_to_user(buf, &tmp, sizeof(tmp)))
- error = -EFAULT;
- fput(file);
-out:
- return error;
-}
-
-SYSCALL_DEFINE3(fstatfs64, unsigned int, fd, size_t, sz, struct statfs64 __user *, buf)
-{
- struct file * file;
- struct statfs64 tmp;
- int error;
-
- if (sz != sizeof(*buf))
- return -EINVAL;
-
- error = -EBADF;
- file = fget(fd);
- if (!file)
- goto out;
- error = vfs_statfs64(file->f_path.dentry, &tmp);
- if (!error && copy_to_user(buf, &tmp, sizeof(tmp)))
- error = -EFAULT;
- fput(file);
-out:
- return error;
-}
+#define CREATE_TRACE_POINTS
+#include <trace/events/fs.h>
int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs,
struct file *filp)
{
- int err;
+ int ret;
struct iattr newattrs;
/* Not pretty: "inode->i_size" shouldn't really be signed. But it is. */
}
/* Remove suid/sgid on truncate too */
- newattrs.ia_valid |= should_remove_suid(dentry);
+ ret = should_remove_suid(dentry);
+ if (ret)
+ newattrs.ia_valid |= ret | ATTR_FORCE;
mutex_lock(&dentry->d_inode->i_mutex);
- err = notify_change(dentry, &newattrs);
+ ret = notify_change(dentry, &newattrs);
mutex_unlock(&dentry->d_inode->i_mutex);
- return err;
+ return ret;
}
+EXPORT_SYMBOL(do_truncate);
static long do_sys_truncate(const char __user *pathname, loff_t length)
{
* Make sure that there are no leases. get_write_access() protects
* against the truncate racing with a lease-granting setlease().
*/
- error = break_lease(inode, FMODE_WRITE);
+ error = break_lease(inode, O_WRONLY);
if (error)
goto put_write_and_out;
error = locks_verify_truncate(inode, NULL, length);
if (!error)
- error = security_path_truncate(&path, length, 0);
- if (!error) {
- DQUOT_INIT(inode);
+ error = security_path_truncate(&path);
+ if (!error)
error = do_truncate(path.dentry, length, 0, NULL);
- }
put_write_and_out:
put_write_access(inode);
return error;
}
-SYSCALL_DEFINE2(truncate, const char __user *, path, unsigned long, length)
+SYSCALL_DEFINE2(truncate, const char __user *, path, long, length)
{
- /* on 32-bit boxen it will cut the range 2^31--2^32-1 off */
- return do_sys_truncate(path, (long)length);
+ return do_sys_truncate(path, length);
}
static long do_sys_ftruncate(unsigned int fd, loff_t length, int small)
error = locks_verify_truncate(inode, file, length);
if (!error)
- error = security_path_truncate(&file->f_path, length,
- ATTR_MTIME|ATTR_CTIME);
+ error = security_path_truncate(&file->f_path);
if (!error)
error = do_truncate(dentry, length, ATTR_MTIME|ATTR_CTIME, file);
out_putf:
#endif
#endif /* BITS_PER_LONG == 32 */
-SYSCALL_DEFINE(fallocate)(int fd, int mode, loff_t offset, loff_t len)
+
+int do_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
{
- struct file *file;
- struct inode *inode;
- long ret = -EINVAL;
+ struct inode *inode = file->f_path.dentry->d_inode;
+ long ret;
if (offset < 0 || len <= 0)
- goto out;
+ return -EINVAL;
/* Return error if mode is not supported */
- ret = -EOPNOTSUPP;
- if (mode && !(mode & FALLOC_FL_KEEP_SIZE))
- goto out;
+ if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
+ return -EOPNOTSUPP;
+
+ /* Punch hole must have keep size set */
+ if ((mode & FALLOC_FL_PUNCH_HOLE) &&
+ !(mode & FALLOC_FL_KEEP_SIZE))
+ return -EOPNOTSUPP;
- ret = -EBADF;
- file = fget(fd);
- if (!file)
- goto out;
if (!(file->f_mode & FMODE_WRITE))
- goto out_fput;
+ return -EBADF;
+
+ /* It's not possible punch hole on append only file */
+ if (mode & FALLOC_FL_PUNCH_HOLE && IS_APPEND(inode))
+ return -EPERM;
+
+ if (IS_IMMUTABLE(inode))
+ return -EPERM;
+
/*
* Revalidate the write permissions, in case security policy has
* changed since the files were opened.
*/
ret = security_file_permission(file, MAY_WRITE);
if (ret)
- goto out_fput;
-
- inode = file->f_path.dentry->d_inode;
+ return ret;
- ret = -ESPIPE;
if (S_ISFIFO(inode->i_mode))
- goto out_fput;
+ return -ESPIPE;
- ret = -ENODEV;
/*
* Let individual file system decide if it supports preallocation
* for directories or not.
*/
if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode))
- goto out_fput;
+ return -ENODEV;
- ret = -EFBIG;
/* Check for wrap through zero too */
if (((offset + len) > inode->i_sb->s_maxbytes) || ((offset + len) < 0))
- goto out_fput;
+ return -EFBIG;
- if (inode->i_op->fallocate)
- ret = inode->i_op->fallocate(inode, mode, offset, len);
- else
- ret = -EOPNOTSUPP;
+ if (!file->f_op->fallocate)
+ return -EOPNOTSUPP;
-out_fput:
- fput(file);
-out:
- return ret;
+ return file->f_op->fallocate(file, mode, offset, len);
+}
+
+SYSCALL_DEFINE(fallocate)(int fd, int mode, loff_t offset, loff_t len)
+{
+ struct file *file;
+ int error = -EBADF;
+
+ file = fget(fd);
+ if (file) {
+ error = do_fallocate(file, mode, offset, len);
+ fput(file);
+ }
+
+ return error;
}
+
#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS
asmlinkage long SyS_fallocate(long fd, long mode, loff_t offset, loff_t len)
{
* We do this by temporarily clearing all FS-related capabilities and
* switching the fsuid/fsgid around to the real ones.
*/
-asmlinkage long sys_faccessat(int dfd, const char __user *filename, int mode)
+SYSCALL_DEFINE3(faccessat, int, dfd, const char __user *, filename, int, mode)
{
const struct cred *old_cred;
struct cred *override_cred;
return sys_faccessat(AT_FDCWD, filename, mode);
}
-asmlinkage long sys_chdir(const char __user * filename)
+SYSCALL_DEFINE1(chdir, const char __user *, filename)
{
struct path path;
int error;
if (error)
goto out;
- error = inode_permission(path.dentry->d_inode, MAY_EXEC | MAY_ACCESS);
+ error = inode_permission(path.dentry->d_inode, MAY_EXEC | MAY_CHDIR);
if (error)
goto dput_and_out;
return error;
}
-asmlinkage long sys_fchdir(unsigned int fd)
+SYSCALL_DEFINE1(fchdir, unsigned int, fd)
{
struct file *file;
struct inode *inode;
if (!S_ISDIR(inode->i_mode))
goto out_putf;
- error = inode_permission(inode, MAY_EXEC | MAY_ACCESS);
+ error = inode_permission(inode, MAY_EXEC | MAY_CHDIR);
if (!error)
set_fs_pwd(current->fs, &file->f_path);
out_putf:
if (error)
goto out;
- error = inode_permission(path.dentry->d_inode, MAY_EXEC | MAY_ACCESS);
+ error = inode_permission(path.dentry->d_inode, MAY_EXEC | MAY_CHDIR);
if (error)
goto dput_and_out;
error = -EPERM;
if (!capable(CAP_SYS_CHROOT))
goto dput_and_out;
+ error = security_path_chroot(&path);
+ if (error)
+ goto dput_and_out;
set_fs_root(current->fs, &path);
error = 0;
audit_inode(NULL, dentry);
- err = mnt_want_write(file->f_path.mnt);
+ err = mnt_want_write_file(file);
if (err)
goto out_putf;
mutex_lock(&inode->i_mutex);
+ err = security_path_chmod(dentry, file->f_vfsmnt, mode);
+ if (err)
+ goto out_unlock;
if (mode == (mode_t) -1)
mode = inode->i_mode;
newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO);
newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
err = notify_change(dentry, &newattrs);
+out_unlock:
mutex_unlock(&inode->i_mutex);
mnt_drop_write(file->f_path.mnt);
out_putf:
return err;
}
-asmlinkage long sys_fchmodat(int dfd, const char __user *filename,
- mode_t mode)
+SYSCALL_DEFINE3(fchmodat, int, dfd, const char __user *, filename, mode_t, mode)
{
struct path path;
struct inode *inode;
if (error)
goto dput_and_out;
mutex_lock(&inode->i_mutex);
+ error = security_path_chmod(path.dentry, path.mnt, mode);
+ if (error)
+ goto out_unlock;
if (mode == (mode_t) -1)
mode = inode->i_mode;
newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO);
newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
error = notify_change(path.dentry, &newattrs);
+out_unlock:
mutex_unlock(&inode->i_mutex);
mnt_drop_write(path.mnt);
dput_and_out:
return sys_fchmodat(AT_FDCWD, filename, mode);
}
-static int chown_common(struct dentry * dentry, uid_t user, gid_t group)
+static int chown_common(struct path *path, uid_t user, gid_t group)
{
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = path->dentry->d_inode;
int error;
struct iattr newattrs;
newattrs.ia_valid |=
ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_KILL_PRIV;
mutex_lock(&inode->i_mutex);
- error = notify_change(dentry, &newattrs);
+ error = security_path_chown(path, user, group);
+ if (!error)
+ error = notify_change(path->dentry, &newattrs);
mutex_unlock(&inode->i_mutex);
return error;
error = mnt_want_write(path.mnt);
if (error)
goto out_release;
- error = chown_common(path.dentry, user, group);
+ error = chown_common(&path, user, group);
mnt_drop_write(path.mnt);
out_release:
path_put(&path);
return error;
}
-asmlinkage long sys_fchownat(int dfd, const char __user *filename, uid_t user,
- gid_t group, int flag)
+SYSCALL_DEFINE5(fchownat, int, dfd, const char __user *, filename, uid_t, user,
+ gid_t, group, int, flag)
{
struct path path;
int error = -EINVAL;
error = mnt_want_write(path.mnt);
if (error)
goto out_release;
- error = chown_common(path.dentry, user, group);
+ error = chown_common(&path, user, group);
mnt_drop_write(path.mnt);
out_release:
path_put(&path);
error = mnt_want_write(path.mnt);
if (error)
goto out_release;
- error = chown_common(path.dentry, user, group);
+ error = chown_common(&path, user, group);
mnt_drop_write(path.mnt);
out_release:
path_put(&path);
if (!file)
goto out;
- error = mnt_want_write(file->f_path.mnt);
+ error = mnt_want_write_file(file);
if (error)
goto out_fput;
dentry = file->f_path.dentry;
audit_inode(NULL, dentry);
- error = chown_common(dentry, user, group);
+ error = chown_common(&file->f_path, user, group);
mnt_drop_write(file->f_path.mnt);
out_fput:
fput(file);
}
static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt,
- int flags, struct file *f,
+ struct file *f,
int (*open)(struct inode *, struct file *),
const struct cred *cred)
{
struct inode *inode;
int error;
- f->f_flags = flags;
- f->f_mode = (__force fmode_t)((flags+1) & O_ACCMODE) | FMODE_LSEEK |
+ f->f_mode = OPEN_FMODE(f->f_flags) | FMODE_LSEEK |
FMODE_PREAD | FMODE_PWRITE;
inode = dentry->d_inode;
if (f->f_mode & FMODE_WRITE) {
f->f_path.mnt = mnt;
f->f_pos = 0;
f->f_op = fops_get(inode->i_fop);
- file_move(f, &inode->i_sb->s_files);
+ file_sb_list_add(f, inode->i_sb);
error = security_dentry_open(f, cred);
if (error)
if (error)
goto cleanup_all;
}
+ ima_counts_get(f);
f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC);
mnt_drop_write(mnt);
}
}
- file_kill(f);
+ file_sb_list_del(f);
f->f_path.dentry = NULL;
f->f_path.mnt = NULL;
cleanup_file:
if (IS_ERR(dentry))
goto out_err;
nd->intent.open.file = __dentry_open(dget(dentry), mntget(nd->path.mnt),
- nd->intent.open.flags - 1,
nd->intent.open.file,
open, cred);
out:
*
* Note that this function destroys the original nameidata
*/
-struct file *nameidata_to_filp(struct nameidata *nd, int flags)
+struct file *nameidata_to_filp(struct nameidata *nd)
{
const struct cred *cred = current_cred();
struct file *filp;
/* Pick up the filp from the open intent */
filp = nd->intent.open.file;
+ nd->intent.open.file = NULL;
+
/* Has the filesystem initialised the file for us? */
- if (filp->f_path.dentry == NULL)
- filp = __dentry_open(nd->path.dentry, nd->path.mnt, flags, filp,
+ if (filp->f_path.dentry == NULL) {
+ path_get(&nd->path);
+ filp = __dentry_open(nd->path.dentry, nd->path.mnt, filp,
NULL, cred);
- else
- path_put(&nd->path);
+ }
return filp;
}
int error;
struct file *f;
+ validate_creds(cred);
+
/*
* We must always pass in a valid mount pointer. Historically
* callers got away with not passing it, but we must enforce this at
return ERR_PTR(error);
}
- return __dentry_open(dentry, mnt, flags, f, NULL, cred);
+ f->f_flags = flags;
+ return __dentry_open(dentry, mnt, f, NULL, cred);
}
EXPORT_SYMBOL(dentry_open);
if (!IS_ERR(tmp)) {
fd = get_unused_fd_flags(flags);
if (fd >= 0) {
- struct file *f = do_filp_open(dfd, tmp, flags, mode);
+ struct file *f = do_filp_open(dfd, tmp, flags, mode, 0);
if (IS_ERR(f)) {
put_unused_fd(fd);
fd = PTR_ERR(f);
} else {
- fsnotify_open(f->f_path.dentry);
+ fsnotify_open(f);
fd_install(fd, f);
+ trace_do_sys_open(tmp, flags, mode);
}
}
putname(tmp);
return ret;
}
-asmlinkage long sys_openat(int dfd, const char __user *filename, int flags,
- int mode)
+SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags,
+ int, mode)
{
long ret;
/*
* This is used by subsystems that don't want seekable
- * file descriptors
+ * file descriptors. The function is not supposed to ever fail, the only
+ * reason it returns an 'int' and not 'void' is so that it can be plugged
+ * directly into file_operations structure.
*/
int nonseekable_open(struct inode *inode, struct file *filp)
{
projects / linux-flexiantxendom0-natty.git / blobdiff