X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=fs%2Fopen.c;h=eb5563ff8d44fbd9c5236a946da878634da94ff3;hb=refs%2Fheads%2Fvserver;hp=d92305b3cd6cff7e9bd9879de98dafcff692926a;hpb=76828883507a47dae78837ab5dec5a5b4513c667;p=linux-2.6.git diff --git a/fs/open.c b/fs/open.c index d92305b3c..eb5563ff8 100644 --- a/fs/open.c +++ b/fs/open.c @@ -6,7 +6,6 @@ #include #include -#include #include #include #include @@ -27,28 +26,31 @@ #include #include #include +#include +#include #include #include -#include +#include +#include -#include - -int vfs_statfs(struct super_block *sb, struct kstatfs *buf) +int vfs_statfs(struct dentry *dentry, struct kstatfs *buf) { int retval = -ENODEV; - if (sb) { + if (dentry) { + struct super_block *sb = dentry->d_sb; + retval = -ENOSYS; if (sb->s_op->statfs) { memset(buf, 0, sizeof(*buf)); - retval = security_sb_statfs(sb); + retval = security_sb_statfs(dentry); if (retval) return retval; - retval = sb->s_op->statfs(sb, buf); + retval = sb->s_op->statfs(dentry, buf); if (retval == 0 && buf->f_frsize == 0) buf->f_frsize = buf->f_bsize; } - if (!vx_check(0, VX_ADMIN|VX_WATCH)) + if (!vx_check(0, VS_ADMIN|VS_WATCH)) vx_vsi_statfs(sb, buf); } return retval; @@ -56,12 +58,12 @@ int vfs_statfs(struct super_block *sb, struct kstatfs *buf) EXPORT_SYMBOL(vfs_statfs); -static int vfs_statfs_native(struct super_block *sb, struct statfs *buf) +static int vfs_statfs_native(struct dentry *dentry, struct statfs *buf) { struct kstatfs st; int retval; - retval = vfs_statfs(sb, &st); + retval = vfs_statfs(dentry, &st); if (retval) return retval; @@ -99,12 +101,12 @@ static int vfs_statfs_native(struct super_block *sb, struct statfs *buf) return 0; } -static int vfs_statfs64(struct super_block *sb, struct statfs64 *buf) +static int vfs_statfs64(struct dentry *dentry, struct statfs64 *buf) { struct kstatfs st; int retval; - retval = vfs_statfs(sb, &st); + retval = vfs_statfs(dentry, &st); if (retval) return retval; @@ -134,7 +136,7 @@ asmlinkage long sys_statfs(const char __user * path, struct statfs __user * buf) error = user_path_walk(path, &nd); if (!error) { struct statfs tmp; - error = vfs_statfs_native(nd.dentry->d_inode->i_sb, &tmp); + error = vfs_statfs_native(nd.dentry, &tmp); if (!error && copy_to_user(buf, &tmp, sizeof(tmp))) error = -EFAULT; path_release(&nd); @@ -153,7 +155,7 @@ asmlinkage long sys_statfs64(const char __user *path, size_t sz, struct statfs64 error = user_path_walk(path, &nd); if (!error) { struct statfs64 tmp; - error = vfs_statfs64(nd.dentry->d_inode->i_sb, &tmp); + error = vfs_statfs64(nd.dentry, &tmp); if (!error && copy_to_user(buf, &tmp, sizeof(tmp))) error = -EFAULT; path_release(&nd); @@ -172,7 +174,7 @@ asmlinkage long sys_fstatfs(unsigned int fd, struct statfs __user * buf) file = fget(fd); if (!file) goto out; - error = vfs_statfs_native(file->f_dentry->d_inode->i_sb, &tmp); + error = vfs_statfs_native(file->f_path.dentry, &tmp); if (!error && copy_to_user(buf, &tmp, sizeof(tmp))) error = -EFAULT; fput(file); @@ -193,7 +195,7 @@ asmlinkage long sys_fstatfs64(unsigned int fd, size_t sz, struct statfs64 __user file = fget(fd); if (!file) goto out; - error = vfs_statfs64(file->f_dentry->d_inode->i_sb, &tmp); + error = vfs_statfs64(file->f_path.dentry, &tmp); if (!error && copy_to_user(buf, &tmp, sizeof(tmp))) error = -EFAULT; fput(file); @@ -309,7 +311,7 @@ static long do_sys_ftruncate(unsigned int fd, loff_t length, int small) if (file->f_flags & O_LARGEFILE) small = 0; - dentry = file->f_dentry; + dentry = file->f_path.dentry; inode = dentry->d_inode; error = -EINVAL; if (!S_ISREG(inode->i_mode) || !(file->f_mode & FMODE_WRITE)) @@ -326,7 +328,7 @@ static long do_sys_ftruncate(unsigned int fd, loff_t length, int small) error = locks_verify_truncate(inode, file, length); if (!error) - error = do_truncate(dentry, length, 0, file); + error = do_truncate(dentry, length, ATTR_MTIME|ATTR_CTIME, file); out_putf: fput(file); out: @@ -357,137 +359,6 @@ asmlinkage long sys_ftruncate64(unsigned int fd, loff_t length) } #endif -#ifdef __ARCH_WANT_SYS_UTIME - -/* - * sys_utime() can be implemented in user-level using sys_utimes(). - * Is this for backwards compatibility? If so, why not move it - * into the appropriate arch directory (for those architectures that - * need it). - */ - -/* If times==NULL, set access and modification to current time, - * must be owner or have write permission. - * Else, update from *times, must be owner or super user. - */ -asmlinkage long sys_utime(char __user * filename, struct utimbuf __user * times) -{ - int error; - struct nameidata nd; - struct inode * inode; - struct iattr newattrs; - - error = user_path_walk(filename, &nd); - if (error) - goto out; - inode = nd.dentry->d_inode; - - error = -EROFS; - if (IS_RDONLY(inode) || MNT_IS_RDONLY(nd.mnt)) - goto dput_and_out; - - /* Don't worry, the checks are done in inode_change_ok() */ - newattrs.ia_valid = ATTR_CTIME | ATTR_MTIME | ATTR_ATIME; - if (times) { - error = -EPERM; - if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) - goto dput_and_out; - - error = get_user(newattrs.ia_atime.tv_sec, ×->actime); - newattrs.ia_atime.tv_nsec = 0; - if (!error) - error = get_user(newattrs.ia_mtime.tv_sec, ×->modtime); - newattrs.ia_mtime.tv_nsec = 0; - if (error) - goto dput_and_out; - - newattrs.ia_valid |= ATTR_ATIME_SET | ATTR_MTIME_SET; - } else { - error = -EACCES; - if (IS_IMMUTABLE(inode)) - goto dput_and_out; - - if (current->fsuid != inode->i_uid && - (error = vfs_permission(&nd, MAY_WRITE)) != 0) - goto dput_and_out; - } - mutex_lock(&inode->i_mutex); - error = notify_change(nd.dentry, &newattrs); - mutex_unlock(&inode->i_mutex); -dput_and_out: - path_release(&nd); -out: - return error; -} - -#endif - -/* If times==NULL, set access and modification to current time, - * must be owner or have write permission. - * Else, update from *times, must be owner or super user. - */ -long do_utimes(int dfd, char __user *filename, struct timeval *times) -{ - int error; - struct nameidata nd; - struct inode * inode; - struct iattr newattrs; - - error = __user_walk_fd(dfd, filename, LOOKUP_FOLLOW, &nd); - - if (error) - goto out; - inode = nd.dentry->d_inode; - - error = -EROFS; - if (IS_RDONLY(inode) || MNT_IS_RDONLY(nd.mnt)) - goto dput_and_out; - - /* Don't worry, the checks are done in inode_change_ok() */ - newattrs.ia_valid = ATTR_CTIME | ATTR_MTIME | ATTR_ATIME; - if (times) { - error = -EPERM; - if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) - goto dput_and_out; - - newattrs.ia_atime.tv_sec = times[0].tv_sec; - newattrs.ia_atime.tv_nsec = times[0].tv_usec * 1000; - newattrs.ia_mtime.tv_sec = times[1].tv_sec; - newattrs.ia_mtime.tv_nsec = times[1].tv_usec * 1000; - newattrs.ia_valid |= ATTR_ATIME_SET | ATTR_MTIME_SET; - } else { - error = -EACCES; - if (IS_IMMUTABLE(inode)) - goto dput_and_out; - - if (current->fsuid != inode->i_uid && - (error = vfs_permission(&nd, MAY_WRITE)) != 0) - goto dput_and_out; - } - mutex_lock(&inode->i_mutex); - error = notify_change(nd.dentry, &newattrs); - mutex_unlock(&inode->i_mutex); -dput_and_out: - path_release(&nd); -out: - return error; -} - -asmlinkage long sys_futimesat(int dfd, char __user *filename, struct timeval __user *utimes) -{ - struct timeval times[2]; - - if (utimes && copy_from_user(×, utimes, sizeof(times))) - return -EFAULT; - return do_utimes(dfd, filename, utimes ? times : NULL); -} - -asmlinkage long sys_utimes(char __user *filename, struct timeval __user *utimes) -{ - return sys_futimesat(AT_FDCWD, filename, utimes); -} - - /* * access() needs to use the real uid/gid, not the effective uid/gid. * We do this by temporarily clearing all FS-related capabilities and @@ -524,16 +395,21 @@ asmlinkage long sys_faccessat(int dfd, const char __user *filename, int mode) current->cap_effective = current->cap_permitted; res = __user_walk_fd(dfd, filename, LOOKUP_FOLLOW|LOOKUP_ACCESS, &nd); - if (!res) { - res = vfs_permission(&nd, mode); - /* SuS v2 requires we report a read only fs too */ - if(!res && (mode & S_IWOTH) - && (IS_RDONLY(nd.dentry->d_inode) || MNT_IS_RDONLY(nd.mnt)) - && !special_file(nd.dentry->d_inode->i_mode)) - res = -EROFS; - path_release(&nd); - } + if (res) + goto out; + + 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)) + goto out_path_release; + + if(IS_RDONLY(nd.dentry->d_inode) || MNT_IS_RDONLY(nd.mnt)) + res = -EROFS; +out_path_release: + path_release(&nd); +out: current->fsuid = old_fsuid; current->fsgid = old_fsgid; current->cap_effective = old_cap; @@ -551,7 +427,8 @@ asmlinkage long sys_chdir(const char __user * filename) struct nameidata nd; int error; - error = __user_walk(filename, LOOKUP_FOLLOW|LOOKUP_DIRECTORY, &nd); + error = __user_walk(filename, + LOOKUP_FOLLOW|LOOKUP_DIRECTORY|LOOKUP_CHDIR, &nd); if (error) goto out; @@ -580,8 +457,8 @@ asmlinkage long sys_fchdir(unsigned int fd) if (!file) goto out; - dentry = file->f_dentry; - mnt = file->f_vfsmnt; + dentry = file->f_path.dentry; + mnt = file->f_path.mnt; inode = dentry->d_inode; error = -ENOTDIR; @@ -635,9 +512,11 @@ asmlinkage long sys_fchmod(unsigned int fd, mode_t mode) if (!file) goto out; - dentry = file->f_dentry; + dentry = file->f_path.dentry; inode = dentry->d_inode; + audit_inode(NULL, inode); + err = -EROFS; if (IS_RDONLY(inode) || MNT_IS_RDONLY(file->f_vfsmnt)) goto out_putf; @@ -669,11 +548,11 @@ asmlinkage long sys_fchmodat(int dfd, const char __user *filename, error = __user_walk_fd(dfd, filename, LOOKUP_FOLLOW, &nd); if (error) goto out; - inode = nd.dentry->d_inode; - error = -EROFS; - if (IS_RDONLY(inode) || MNT_IS_RDONLY(nd.mnt)) + error = cow_check_and_break(&nd); + if (error) goto dput_and_out; + inode = nd.dentry->d_inode; error = -EPERM; if (IS_IMMUTABLE(inode) || IS_APPEND(inode)) @@ -719,11 +598,11 @@ static int chown_common(struct dentry *dentry, struct vfsmount *mnt, newattrs.ia_valid = ATTR_CTIME; if (user != (uid_t) -1) { newattrs.ia_valid |= ATTR_UID; - newattrs.ia_uid = vx_map_uid(user); + newattrs.ia_uid = dx_map_uid(user); } if (group != (gid_t) -1) { newattrs.ia_valid |= ATTR_GID; - newattrs.ia_gid = vx_map_gid(group); + newattrs.ia_gid = dx_map_gid(group); } if (!S_ISDIR(inode->i_mode)) newattrs.ia_valid |= ATTR_KILL_SUID|ATTR_KILL_SGID; @@ -740,10 +619,15 @@ asmlinkage long sys_chown(const char __user * filename, uid_t user, gid_t group) int error; error = user_path_walk(filename, &nd); - if (!error) { + if (error) + goto out; +#ifdef CONFIG_VSERVER_COWBL + error = cow_check_and_break(&nd); + if (!error) +#endif error = chown_common(nd.dentry, nd.mnt, user, group); - path_release(&nd); - } + path_release(&nd); +out: return error; } @@ -759,10 +643,14 @@ asmlinkage long sys_fchownat(int dfd, const char __user *filename, uid_t user, follow = (flag & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW; error = __user_walk_fd(dfd, filename, follow, &nd); - if (!error) { + if (error) + goto out; +#ifdef CONFIG_VSERVER_COWBL + error = cow_check_and_break(&nd); + if (!error) +#endif error = chown_common(nd.dentry, nd.mnt, user, group); - path_release(&nd); - } + path_release(&nd); out: return error; } @@ -773,10 +661,15 @@ asmlinkage long sys_lchown(const char __user * filename, uid_t user, gid_t group int error; error = user_path_walk_link(filename, &nd); - if (!error) { + if (error) + goto out; +#ifdef CONFIG_VSERVER_COWBL + error = cow_check_and_break(&nd); + if (!error) +#endif error = chown_common(nd.dentry, nd.mnt, user, group); - path_release(&nd); - } + path_release(&nd); +out: return error; } @@ -785,12 +678,17 @@ asmlinkage long sys_fchown(unsigned int fd, uid_t user, gid_t group) { struct file * file; int error = -EBADF; + struct dentry * dentry; file = fget(fd); - if (file) { - error = chown_common(file->f_dentry, file->f_vfsmnt, user, group); - fput(file); - } + if (!file) + goto out; + + dentry = file->f_path.dentry; + audit_inode(NULL, dentry->d_inode); + error = chown_common(dentry, file->f_vfsmnt, user, group); + fput(file); +out: return error; } @@ -812,8 +710,8 @@ static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt, } f->f_mapping = inode->i_mapping; - f->f_dentry = dentry; - f->f_vfsmnt = mnt; + f->f_path.dentry = dentry; + 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); @@ -847,8 +745,8 @@ cleanup_all: if (f->f_mode & FMODE_WRITE) put_write_access(inode); file_kill(f); - f->f_dentry = NULL; - f->f_vfsmnt = NULL; + f->f_path.dentry = NULL; + f->f_path.mnt = NULL; cleanup_file: put_filp(f); dput(dentry); @@ -903,6 +801,10 @@ EXPORT_SYMBOL(filp_open); * a fully instantiated struct file to the caller. * This function is meant to be called from within a filesystem's * lookup method. + * Beware of calling it for non-regular files! Those ->open methods might block + * (e.g. in fifo_open), leaving you with parent locked (and in case of fifo, + * leading to a deadlock, as nobody can open that fifo anymore, because + * another process to open fifo will block on locked parent when doing lookup). * Note that in case of error, nd->intent.open.file is destroyed, but the * path information remains valid. * If the open callback is set to NULL, then the standard f_op->open() @@ -942,7 +844,7 @@ struct file *nameidata_to_filp(struct nameidata *nd, int flags) /* Pick up the filp from the open intent */ filp = nd->intent.open.file; /* Has the filesystem initialised the file for us? */ - if (filp->f_dentry == NULL) + if (filp->f_path.dentry == NULL) filp = __dentry_open(nd->dentry, nd->mnt, flags, filp, NULL); else path_release(nd); @@ -984,9 +886,8 @@ int get_unused_fd(void) repeat: fdt = files_fdtable(files); - fd = find_next_zero_bit(fdt->open_fds->fds_bits, - fdt->max_fdset, - fdt->next_fd); + fd = find_next_zero_bit(fdt->open_fds->fds_bits, fdt->max_fds, + files->next_fd); /* * N.B. For clone tasks sharing a files structure, this test @@ -1011,7 +912,7 @@ repeat: FD_SET(fd, fdt->open_fds); FD_CLR(fd, fdt->close_on_exec); - fdt->next_fd = fd + 1; + files->next_fd = fd + 1; vx_openfd_inc(fd); #if 1 /* Sanity check */ @@ -1033,8 +934,8 @@ static void __put_unused_fd(struct files_struct *files, unsigned int fd) { struct fdtable *fdt = files_fdtable(files); __FD_CLR(fd, fdt->open_fds); - if (fd < fdt->next_fd) - fdt->next_fd = fd; + if (fd < files->next_fd) + files->next_fd = fd; vx_openfd_dec(fd); } @@ -1087,7 +988,7 @@ long do_sys_open(int dfd, const char __user *filename, int flags, int mode) put_unused_fd(fd); fd = PTR_ERR(f); } else { - fsnotify_open(f->f_dentry); + fsnotify_open(f->f_path.dentry); fd_install(fd, f); } } @@ -1108,7 +1009,6 @@ asmlinkage long sys_open(const char __user *filename, int flags, int mode) prevent_tail_call(ret); return ret; } -EXPORT_SYMBOL_GPL(sys_open); asmlinkage long sys_openat(int dfd, const char __user *filename, int flags, int mode) @@ -1123,7 +1023,6 @@ asmlinkage long sys_openat(int dfd, const char __user *filename, int flags, prevent_tail_call(ret); return ret; } -EXPORT_SYMBOL_GPL(sys_openat); #ifndef __alpha__ @@ -1152,7 +1051,7 @@ int filp_close(struct file *filp, fl_owner_t id) } if (filp->f_op && filp->f_op->flush) - retval = filp->f_op->flush(filp); + retval = filp->f_op->flush(filp, id); dnotify_flush(filp, id); locks_remove_posix(filp, id); @@ -1172,6 +1071,7 @@ asmlinkage long sys_close(unsigned int fd) struct file * filp; struct files_struct *files = current->files; struct fdtable *fdt; + int retval; spin_lock(&files->file_lock); fdt = files_fdtable(files); @@ -1184,7 +1084,16 @@ asmlinkage long sys_close(unsigned int fd) FD_CLR(fd, fdt->close_on_exec); __put_unused_fd(files, fd); spin_unlock(&files->file_lock); - return filp_close(filp, files); + retval = filp_close(filp, files); + + /* can't restart close syscall because file table entry was cleared */ + if (unlikely(retval == -ERESTARTSYS || + retval == -ERESTARTNOINTR || + retval == -ERESTARTNOHAND || + retval == -ERESTART_RESTARTBLOCK)) + retval = -EINTR; + + return retval; out_unlock: spin_unlock(&files->file_lock); @@ -1200,6 +1109,7 @@ EXPORT_SYMBOL(sys_close); asmlinkage long sys_vhangup(void) { if (capable(CAP_SYS_TTY_CONFIG)) { + /* XXX: this needs locking */ tty_vhangup(current->signal->tty); return 0; }