#include <linux/string.h>
#include <linux/mm.h>
#include <linux/file.h>
-#include <linux/smp_lock.h>
#include <linux/quotaops.h>
#include <linux/fsnotify.h>
#include <linux/module.h>
#include <linux/syscalls.h>
#include <linux/rcupdate.h>
#include <linux/audit.h>
+#include <linux/falloc.h>
int vfs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
error = user_path_walk(path, &nd);
if (!error) {
struct statfs tmp;
- error = vfs_statfs_native(nd.dentry, &tmp);
+ error = vfs_statfs_native(nd.path.dentry, &tmp);
if (!error && copy_to_user(buf, &tmp, sizeof(tmp)))
error = -EFAULT;
- path_release(&nd);
+ path_put(&nd.path);
}
return error;
}
error = user_path_walk(path, &nd);
if (!error) {
struct statfs64 tmp;
- error = vfs_statfs64(nd.dentry, &tmp);
+ error = vfs_statfs64(nd.path.dentry, &tmp);
if (!error && copy_to_user(buf, &tmp, sizeof(tmp)))
error = -EFAULT;
- path_release(&nd);
+ path_put(&nd.path);
}
return error;
}
newattrs.ia_valid |= ATTR_FILE;
}
+ /* Remove suid/sgid on truncate too */
+ newattrs.ia_valid |= should_remove_suid(dentry);
+
mutex_lock(&dentry->d_inode->i_mutex);
err = notify_change(dentry, &newattrs);
mutex_unlock(&dentry->d_inode->i_mutex);
error = user_path_walk(path, &nd);
if (error)
goto out;
- inode = nd.dentry->d_inode;
+ inode = nd.path.dentry->d_inode;
/* For directories it's -EISDIR, for other non-regulars - -EINVAL */
error = -EISDIR;
if (!S_ISREG(inode->i_mode))
goto dput_and_out;
- error = vfs_permission(&nd, MAY_WRITE);
+ error = mnt_want_write(nd.path.mnt);
if (error)
goto dput_and_out;
- error = -EROFS;
- if (IS_RDONLY(inode))
- goto dput_and_out;
+ error = vfs_permission(&nd, MAY_WRITE);
+ if (error)
+ goto mnt_drop_write_and_out;
error = -EPERM;
if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
- goto dput_and_out;
+ goto mnt_drop_write_and_out;
+
+ error = get_write_access(inode);
+ if (error)
+ goto mnt_drop_write_and_out;
/*
- * Make sure that there are no leases.
+ * 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);
if (error)
- goto dput_and_out;
-
- error = get_write_access(inode);
- if (error)
- goto dput_and_out;
+ goto put_write_and_out;
error = locks_verify_truncate(inode, NULL, length);
if (!error) {
DQUOT_INIT(inode);
- error = do_truncate(nd.dentry, length, 0, NULL);
+ error = do_truncate(nd.path.dentry, length, 0, NULL);
}
- put_write_access(inode);
+put_write_and_out:
+ put_write_access(inode);
+mnt_drop_write_and_out:
+ mnt_drop_write(nd.path.mnt);
dput_and_out:
- path_release(&nd);
+ path_put(&nd.path);
out:
return error;
}
{
long ret = do_sys_ftruncate(fd, length, 1);
/* avoid REGPARM breakage on x86: */
- prevent_tail_call(ret);
+ asmlinkage_protect(2, ret, fd, length);
return ret;
}
{
long ret = do_sys_ftruncate(fd, length, 0);
/* avoid REGPARM breakage on x86: */
- prevent_tail_call(ret);
+ asmlinkage_protect(2, ret, fd, length);
return ret;
}
#endif
+asmlinkage long sys_fallocate(int fd, int mode, loff_t offset, loff_t len)
+{
+ struct file *file;
+ struct inode *inode;
+ long ret = -EINVAL;
+
+ if (offset < 0 || len <= 0)
+ goto out;
+
+ /* Return error if mode is not supported */
+ ret = -EOPNOTSUPP;
+ if (mode && !(mode & FALLOC_FL_KEEP_SIZE))
+ goto out;
+
+ ret = -EBADF;
+ file = fget(fd);
+ if (!file)
+ goto out;
+ if (!(file->f_mode & FMODE_WRITE))
+ goto out_fput;
+ /*
+ * 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;
+
+ ret = -ESPIPE;
+ if (S_ISFIFO(inode->i_mode))
+ goto out_fput;
+
+ 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;
+
+ ret = -EFBIG;
+ /* Check for wrap through zero too */
+ if (((offset + len) > inode->i_sb->s_maxbytes) || ((offset + len) < 0))
+ goto out_fput;
+
+ if (inode->i_op && inode->i_op->fallocate)
+ ret = inode->i_op->fallocate(inode, mode, offset, len);
+ else
+ ret = -EOPNOTSUPP;
+
+out_fput:
+ fput(file);
+out:
+ return ret;
+}
+
/*
* access() needs to use the real uid/gid, not the effective uid/gid.
* We do this by temporarily clearing all FS-related capabilities and
res = vfs_permission(&nd, mode);
/* SuS v2 requires we report a read only fs too */
if(res || !(mode & S_IWOTH) ||
- special_file(nd.dentry->d_inode->i_mode))
+ special_file(nd.path.dentry->d_inode->i_mode))
goto out_path_release;
-
- if(IS_RDONLY(nd.dentry->d_inode))
+ /*
+ * This is a rare case where using __mnt_is_readonly()
+ * is OK without a mnt_want/drop_write() pair. Since
+ * no actual write to the fs is performed here, we do
+ * not need to telegraph to that to anyone.
+ *
+ * By doing this, we accept that this access is
+ * inherently racy and know that the fs may change
+ * state before we even see this result.
+ */
+ if (__mnt_is_readonly(nd.path.mnt))
res = -EROFS;
out_path_release:
- path_release(&nd);
+ path_put(&nd.path);
out:
current->fsuid = old_fsuid;
current->fsgid = old_fsgid;
if (error)
goto dput_and_out;
- set_fs_pwd(current->fs, nd.mnt, nd.dentry);
+ set_fs_pwd(current->fs, &nd.path);
dput_and_out:
- path_release(&nd);
+ path_put(&nd.path);
out:
return error;
}
asmlinkage long sys_fchdir(unsigned int fd)
{
struct file *file;
- struct dentry *dentry;
struct inode *inode;
- struct vfsmount *mnt;
int error;
error = -EBADF;
if (!file)
goto out;
- dentry = file->f_path.dentry;
- mnt = file->f_path.mnt;
- inode = dentry->d_inode;
+ inode = file->f_path.dentry->d_inode;
error = -ENOTDIR;
if (!S_ISDIR(inode->i_mode))
error = file_permission(file, MAY_EXEC);
if (!error)
- set_fs_pwd(current->fs, mnt, dentry);
+ set_fs_pwd(current->fs, &file->f_path);
out_putf:
fput(file);
out:
if (!capable(CAP_SYS_CHROOT))
goto dput_and_out;
- set_fs_root(current->fs, nd.mnt, nd.dentry);
+ set_fs_root(current->fs, &nd.path);
set_fs_altroot();
error = 0;
dput_and_out:
- path_release(&nd);
+ path_put(&nd.path);
out:
return error;
}
dentry = file->f_path.dentry;
inode = dentry->d_inode;
- audit_inode(NULL, inode);
+ audit_inode(NULL, dentry);
- err = -EROFS;
- if (IS_RDONLY(inode))
+ err = mnt_want_write(file->f_path.mnt);
+ if (err)
goto out_putf;
err = -EPERM;
if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
- goto out_putf;
+ goto out_drop_write;
mutex_lock(&inode->i_mutex);
if (mode == (mode_t) -1)
mode = inode->i_mode;
err = notify_change(dentry, &newattrs);
mutex_unlock(&inode->i_mutex);
+out_drop_write:
+ mnt_drop_write(file->f_path.mnt);
out_putf:
fput(file);
out:
error = __user_walk_fd(dfd, filename, LOOKUP_FOLLOW, &nd);
if (error)
goto out;
- inode = nd.dentry->d_inode;
+ inode = nd.path.dentry->d_inode;
- error = -EROFS;
- if (IS_RDONLY(inode))
+ error = mnt_want_write(nd.path.mnt);
+ if (error)
goto dput_and_out;
error = -EPERM;
if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
- goto dput_and_out;
+ goto out_drop_write;
mutex_lock(&inode->i_mutex);
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(nd.dentry, &newattrs);
+ error = notify_change(nd.path.dentry, &newattrs);
mutex_unlock(&inode->i_mutex);
+out_drop_write:
+ mnt_drop_write(nd.path.mnt);
dput_and_out:
- path_release(&nd);
+ path_put(&nd.path);
out:
return error;
}
printk(KERN_ERR "chown_common: NULL inode\n");
goto out;
}
- error = -EROFS;
- if (IS_RDONLY(inode))
- goto out;
error = -EPERM;
if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
goto out;
newattrs.ia_gid = group;
}
if (!S_ISDIR(inode->i_mode))
- newattrs.ia_valid |= ATTR_KILL_SUID|ATTR_KILL_SGID;
+ newattrs.ia_valid |=
+ ATTR_KILL_SUID | ATTR_KILL_SGID | ATTR_KILL_PRIV;
mutex_lock(&inode->i_mutex);
error = notify_change(dentry, &newattrs);
mutex_unlock(&inode->i_mutex);
error = user_path_walk(filename, &nd);
if (error)
goto out;
- error = chown_common(nd.dentry, user, group);
- path_release(&nd);
+ error = mnt_want_write(nd.path.mnt);
+ if (error)
+ goto out_release;
+ error = chown_common(nd.path.dentry, user, group);
+ mnt_drop_write(nd.path.mnt);
+out_release:
+ path_put(&nd.path);
out:
return error;
}
error = __user_walk_fd(dfd, filename, follow, &nd);
if (error)
goto out;
- error = chown_common(nd.dentry, user, group);
- path_release(&nd);
+ error = mnt_want_write(nd.path.mnt);
+ if (error)
+ goto out_release;
+ error = chown_common(nd.path.dentry, user, group);
+ mnt_drop_write(nd.path.mnt);
+out_release:
+ path_put(&nd.path);
out:
return error;
}
error = user_path_walk_link(filename, &nd);
if (error)
goto out;
- error = chown_common(nd.dentry, user, group);
- path_release(&nd);
+ error = mnt_want_write(nd.path.mnt);
+ if (error)
+ goto out_release;
+ error = chown_common(nd.path.dentry, user, group);
+ mnt_drop_write(nd.path.mnt);
+out_release:
+ path_put(&nd.path);
out:
return error;
}
if (!file)
goto out;
+ error = mnt_want_write(file->f_path.mnt);
+ if (error)
+ goto out_fput;
dentry = file->f_path.dentry;
- audit_inode(NULL, dentry->d_inode);
+ audit_inode(NULL, dentry);
error = chown_common(dentry, user, group);
+ mnt_drop_write(file->f_path.mnt);
+out_fput:
fput(file);
out:
return error;
}
+/*
+ * You have to be very careful that these write
+ * counts get cleaned up in error cases and
+ * upon __fput(). This should probably never
+ * be called outside of __dentry_open().
+ */
+static inline int __get_file_write_access(struct inode *inode,
+ struct vfsmount *mnt)
+{
+ int error;
+ error = get_write_access(inode);
+ if (error)
+ return error;
+ /*
+ * Do not take mount writer counts on
+ * special files since no writes to
+ * the mount itself will occur.
+ */
+ if (!special_file(inode->i_mode)) {
+ /*
+ * Balanced in __fput()
+ */
+ error = mnt_want_write(mnt);
+ if (error)
+ put_write_access(inode);
+ }
+ return error;
+}
+
static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt,
int flags, struct file *f,
int (*open)(struct inode *, struct file *))
FMODE_PREAD | FMODE_PWRITE;
inode = dentry->d_inode;
if (f->f_mode & FMODE_WRITE) {
- error = get_write_access(inode);
+ error = __get_file_write_access(inode, mnt);
if (error)
goto cleanup_file;
+ if (!special_file(inode->i_mode))
+ file_take_write(f);
}
f->f_mapping = inode->i_mapping;
f->f_op = fops_get(inode->i_fop);
file_move(f, &inode->i_sb->s_files);
+ error = security_dentry_open(f);
+ if (error)
+ goto cleanup_all;
+
if (!open && f->f_op)
open = f->f_op->open;
if (open) {
cleanup_all:
fops_put(f->f_op);
- if (f->f_mode & FMODE_WRITE)
+ if (f->f_mode & FMODE_WRITE) {
put_write_access(inode);
+ if (!special_file(inode->i_mode)) {
+ /*
+ * We don't consider this a real
+ * mnt_want/drop_write() pair
+ * because it all happenend right
+ * here, so just reset the state.
+ */
+ file_reset_write(f);
+ mnt_drop_write(mnt);
+ }
+ }
file_kill(f);
f->f_path.dentry = NULL;
f->f_path.mnt = NULL;
return ERR_PTR(error);
}
-/*
- * Note that while the flag value (low two bits) for sys_open means:
- * 00 - read-only
- * 01 - write-only
- * 10 - read-write
- * 11 - special
- * it is changed into
- * 00 - no permissions needed
- * 01 - read-permission
- * 10 - write-permission
- * 11 - read-write
- * for the internal routines (ie open_namei()/follow_link() etc). 00 is
- * used by symlinks.
- */
-static struct file *do_filp_open(int dfd, const char *filename, int flags,
- int mode)
-{
- int namei_flags, error;
- struct nameidata nd;
-
- namei_flags = flags;
- if ((namei_flags+1) & O_ACCMODE)
- namei_flags++;
-
- error = open_namei(dfd, filename, namei_flags, mode, &nd);
- if (!error)
- return nameidata_to_filp(&nd, flags);
-
- return ERR_PTR(error);
-}
-
-struct file *filp_open(const char *filename, int flags, int mode)
-{
- return do_filp_open(AT_FDCWD, filename, flags, mode);
-}
-EXPORT_SYMBOL(filp_open);
-
/**
* lookup_instantiate_filp - instantiates the open intent filp
* @nd: pointer to nameidata
goto out;
if (IS_ERR(dentry))
goto out_err;
- nd->intent.open.file = __dentry_open(dget(dentry), mntget(nd->mnt),
+ nd->intent.open.file = __dentry_open(dget(dentry), mntget(nd->path.mnt),
nd->intent.open.flags - 1,
nd->intent.open.file,
open);
filp = nd->intent.open.file;
/* Has the filesystem initialised the file for us? */
if (filp->f_path.dentry == NULL)
- filp = __dentry_open(nd->dentry, nd->mnt, flags, filp, NULL);
+ filp = __dentry_open(nd->path.dentry, nd->path.mnt, flags, filp,
+ NULL);
else
- path_release(nd);
+ path_put(&nd->path);
return filp;
}
int error;
struct file *f;
+ /*
+ * We must always pass in a valid mount pointer. Historically
+ * callers got away with not passing it, but we must enforce this at
+ * the earliest possible point now to avoid strange problems deep in the
+ * filesystem stack.
+ */
+ if (!mnt) {
+ printk(KERN_WARNING "%s called with NULL vfsmount\n", __func__);
+ dump_stack();
+ return ERR_PTR(-EINVAL);
+ }
+
error = -ENFILE;
f = get_empty_filp();
if (f == NULL) {
/*
* Find an empty file descriptor entry, and mark it busy.
*/
-int get_unused_fd(void)
+int get_unused_fd_flags(int flags)
{
struct files_struct * files = current->files;
int fd, error;
repeat:
fdt = files_fdtable(files);
- fd = find_next_zero_bit(fdt->open_fds->fds_bits,
- fdt->max_fdset,
+ fd = find_next_zero_bit(fdt->open_fds->fds_bits, fdt->max_fds,
files->next_fd);
/*
}
FD_SET(fd, fdt->open_fds);
- FD_CLR(fd, fdt->close_on_exec);
+ if (flags & O_CLOEXEC)
+ FD_SET(fd, fdt->close_on_exec);
+ else
+ FD_CLR(fd, fdt->close_on_exec);
files->next_fd = fd + 1;
#if 1
/* Sanity check */
return error;
}
+int get_unused_fd(void)
+{
+ return get_unused_fd_flags(0);
+}
+
EXPORT_SYMBOL(get_unused_fd);
static void __put_unused_fd(struct files_struct *files, unsigned int fd)
files->next_fd = fd;
}
-void fastcall put_unused_fd(unsigned int fd)
+void put_unused_fd(unsigned int fd)
{
struct files_struct *files = current->files;
spin_lock(&files->file_lock);
* will follow.
*/
-void fastcall fd_install(unsigned int fd, struct file * file)
+void fd_install(unsigned int fd, struct file *file)
{
struct files_struct *files = current->files;
struct fdtable *fdt;
int fd = PTR_ERR(tmp);
if (!IS_ERR(tmp)) {
- fd = get_unused_fd();
+ fd = get_unused_fd_flags(flags);
if (fd >= 0) {
struct file *f = do_filp_open(dfd, tmp, flags, mode);
if (IS_ERR(f)) {
ret = do_sys_open(AT_FDCWD, filename, flags, mode);
/* avoid REGPARM breakage on x86: */
- prevent_tail_call(ret);
+ asmlinkage_protect(3, ret, filename, flags, mode);
return ret;
}
-EXPORT_SYMBOL_GPL(sys_open);
asmlinkage long sys_openat(int dfd, const char __user *filename, int flags,
int mode)
ret = do_sys_open(dfd, filename, flags, mode);
/* avoid REGPARM breakage on x86: */
- prevent_tail_call(ret);
+ asmlinkage_protect(4, ret, dfd, filename, flags, mode);
return ret;
}
int generic_file_open(struct inode * inode, struct file * filp)
{
if (!(filp->f_flags & O_LARGEFILE) && i_size_read(inode) > MAX_NON_LFS)
- return -EFBIG;
+ return -EOVERFLOW;
return 0;
}
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff