#include <linux/file.h>
#include <linux/smp_lock.h>
#include <linux/quotaops.h>
-#include <linux/dnotify.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/capability.h>
#include <linux/security.h>
#include <linux/mount.h>
#include <linux/vfs.h>
+#include <linux/fcntl.h>
#include <asm/uaccess.h>
#include <linux/fs.h>
+#include <linux/personality.h>
#include <linux/pagemap.h>
+#include <linux/syscalls.h>
+#include <linux/rcupdate.h>
+#include <linux/audit.h>
+#include <linux/vs_limit.h>
+#include <linux/vs_dlimit.h>
#include <linux/vserver/xid.h>
+#include <asm/unistd.h>
+
int vfs_statfs(struct super_block *sb, struct kstatfs *buf)
{
int retval = -ENODEV;
if (retval == 0 && buf->f_frsize == 0)
buf->f_frsize = buf->f_bsize;
}
+ if (!vx_check(0, VX_ADMIN|VX_WATCH))
+ vx_vsi_statfs(sb, buf);
}
return retval;
}
return error;
}
-int do_truncate(struct dentry *dentry, loff_t length)
+int do_truncate(struct dentry *dentry, loff_t length, unsigned int time_attrs,
+ struct file *filp)
{
int err;
struct iattr newattrs;
return -EINVAL;
newattrs.ia_size = length;
- newattrs.ia_valid = ATTR_SIZE | ATTR_CTIME;
- down(&dentry->d_inode->i_sem);
- down_write(&dentry->d_inode->i_alloc_sem);
+ newattrs.ia_valid = ATTR_SIZE | time_attrs;
+ if (filp) {
+ newattrs.ia_file = filp;
+ newattrs.ia_valid |= ATTR_FILE;
+ }
+
+ mutex_lock(&dentry->d_inode->i_mutex);
err = notify_change(dentry, &newattrs);
- up_write(&dentry->d_inode->i_alloc_sem);
- up(&dentry->d_inode->i_sem);
+ mutex_unlock(&dentry->d_inode->i_mutex);
return err;
}
-static inline long do_sys_truncate(const char __user * path, loff_t length)
+static long do_sys_truncate(const char __user * path, loff_t length)
{
struct nameidata nd;
struct inode * inode;
if (!S_ISREG(inode->i_mode))
goto dput_and_out;
- error = permission(inode,MAY_WRITE,&nd);
+ error = vfs_permission(&nd, MAY_WRITE);
if (error)
goto dput_and_out;
error = -EROFS;
- if (IS_RDONLY(inode))
+ if (IS_RDONLY(inode) || MNT_IS_RDONLY(nd.mnt))
goto dput_and_out;
error = -EPERM;
error = locks_verify_truncate(inode, NULL, length);
if (!error) {
DQUOT_INIT(inode);
- error = do_truncate(nd.dentry, length);
+ error = do_truncate(nd.dentry, length, 0, NULL);
}
put_write_access(inode);
return do_sys_truncate(path, (long)length);
}
-static inline long do_sys_ftruncate(unsigned int fd, loff_t length, int small)
+static long do_sys_ftruncate(unsigned int fd, loff_t length, int small)
{
struct inode * inode;
struct dentry *dentry;
error = locks_verify_truncate(inode, file, length);
if (!error)
- error = do_truncate(dentry, length);
+ error = do_truncate(dentry, length, 0, file);
out_putf:
fput(file);
out:
asmlinkage long sys_ftruncate(unsigned int fd, unsigned long length)
{
- return do_sys_ftruncate(fd, length, 1);
+ long ret = do_sys_ftruncate(fd, length, 1);
+ /* avoid REGPARM breakage on x86: */
+ prevent_tail_call(ret);
+ return ret;
}
/* LFS versions of truncate are only needed on 32 bit machines */
asmlinkage long sys_ftruncate64(unsigned int fd, loff_t length)
{
- return do_sys_ftruncate(fd, length, 0);
+ long ret = do_sys_ftruncate(fd, length, 0);
+ /* avoid REGPARM breakage on x86: */
+ prevent_tail_call(ret);
+ return ret;
}
#endif
-#if !(defined(__alpha__) || defined(__ia64__))
+#ifdef __ARCH_WANT_SYS_UTIME
/*
* sys_utime() can be implemented in user-level using sys_utimes().
inode = nd.dentry->d_inode;
error = -EROFS;
- if (IS_RDONLY(inode))
+ if (IS_RDONLY(inode) || MNT_IS_RDONLY(nd.mnt))
goto dput_and_out;
/* Don't worry, the checks are done in inode_change_ok() */
error = get_user(newattrs.ia_atime.tv_sec, ×->actime);
newattrs.ia_atime.tv_nsec = 0;
- if (!error)
+ if (!error)
error = get_user(newattrs.ia_mtime.tv_sec, ×->modtime);
newattrs.ia_mtime.tv_nsec = 0;
if (error)
goto dput_and_out;
if (current->fsuid != inode->i_uid &&
- (error = permission(inode,MAY_WRITE,&nd)) != 0)
+ (error = vfs_permission(&nd, MAY_WRITE)) != 0)
goto dput_and_out;
}
- down(&inode->i_sem);
+ mutex_lock(&inode->i_mutex);
error = notify_change(nd.dentry, &newattrs);
- up(&inode->i_sem);
+ mutex_unlock(&inode->i_mutex);
dput_and_out:
path_release(&nd);
out:
* must be owner or have write permission.
* Else, update from *times, must be owner or super user.
*/
-long do_utimes(char __user * filename, struct timeval * times)
+long do_utimes(int dfd, char __user *filename, struct timeval *times)
{
int error;
struct nameidata nd;
struct inode * inode;
struct iattr newattrs;
- error = user_path_walk(filename, &nd);
+ error = __user_walk_fd(dfd, filename, LOOKUP_FOLLOW, &nd);
if (error)
goto out;
inode = nd.dentry->d_inode;
error = -EROFS;
- if (IS_RDONLY(inode))
+ if (IS_RDONLY(inode) || MNT_IS_RDONLY(nd.mnt))
goto dput_and_out;
/* Don't worry, the checks are done in inode_change_ok() */
goto dput_and_out;
if (current->fsuid != inode->i_uid &&
- (error = permission(inode,MAY_WRITE,&nd)) != 0)
+ (error = vfs_permission(&nd, MAY_WRITE)) != 0)
goto dput_and_out;
}
- down(&inode->i_sem);
+ mutex_lock(&inode->i_mutex);
error = notify_change(nd.dentry, &newattrs);
- up(&inode->i_sem);
+ mutex_unlock(&inode->i_mutex);
dput_and_out:
path_release(&nd);
out:
return error;
}
-asmlinkage long sys_utimes(char __user * filename, struct timeval __user * utimes)
+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(filename, utimes ? times : NULL);
+ 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);
}
* We do this by temporarily clearing all FS-related capabilities and
* switching the fsuid/fsgid around to the real ones.
*/
-asmlinkage long sys_access(const char __user * filename, int mode)
+asmlinkage long sys_faccessat(int dfd, const char __user *filename, int mode)
{
struct nameidata nd;
int old_fsuid, old_fsgid;
else
current->cap_effective = current->cap_permitted;
- res = __user_walk(filename, LOOKUP_FOLLOW|LOOKUP_ACCESS, &nd);
+ res = __user_walk_fd(dfd, filename, LOOKUP_FOLLOW|LOOKUP_ACCESS, &nd);
if (!res) {
- res = permission(nd.dentry->d_inode, mode, &nd);
+ 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)
+ 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);
return res;
}
+asmlinkage long sys_access(const char __user *filename, int mode)
+{
+ return sys_faccessat(AT_FDCWD, filename, mode);
+}
+
asmlinkage long sys_chdir(const char __user * filename)
{
struct nameidata nd;
if (error)
goto out;
- error = permission(nd.dentry->d_inode,MAY_EXEC,&nd);
+ error = vfs_permission(&nd, MAY_EXEC);
if (error)
goto dput_and_out;
return error;
}
+EXPORT_SYMBOL_GPL(sys_chdir);
+
asmlinkage long sys_fchdir(unsigned int fd)
{
struct file *file;
if (!S_ISDIR(inode->i_mode))
goto out_putf;
- error = permission(inode, MAY_EXEC, NULL);
+ error = file_permission(file, MAY_EXEC);
if (!error)
set_fs_pwd(current->fs, mnt, dentry);
out_putf:
if (error)
goto out;
- error = permission(nd.dentry->d_inode,MAY_EXEC,&nd);
+ error = vfs_permission(&nd, MAY_EXEC);
if (error)
goto dput_and_out;
return error;
}
+EXPORT_SYMBOL_GPL(sys_chroot);
+
asmlinkage long sys_fchmod(unsigned int fd, mode_t mode)
{
struct inode * inode;
dentry = file->f_dentry;
inode = dentry->d_inode;
- err = -EPERM;
- if (IS_BARRIER(inode) && !vx_check(0, VX_ADMIN))
- goto out_putf;
+ audit_inode(NULL, inode, 0);
+
err = -EROFS;
- if (IS_RDONLY(inode))
+ if (IS_RDONLY(inode) || MNT_IS_RDONLY(file->f_vfsmnt))
goto out_putf;
err = -EPERM;
if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
goto out_putf;
- down(&inode->i_sem);
+ 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;
err = notify_change(dentry, &newattrs);
- up(&inode->i_sem);
+ mutex_unlock(&inode->i_mutex);
out_putf:
fput(file);
return err;
}
-asmlinkage long sys_chmod(const char __user * filename, mode_t mode)
+asmlinkage long sys_fchmodat(int dfd, const char __user *filename,
+ mode_t mode)
{
struct nameidata nd;
struct inode * inode;
int error;
struct iattr newattrs;
- error = user_path_walk(filename, &nd);
+ error = __user_walk_fd(dfd, filename, LOOKUP_FOLLOW, &nd);
if (error)
goto out;
inode = nd.dentry->d_inode;
- error = -EPERM;
- if (IS_BARRIER(inode) && !vx_check(0, VX_ADMIN))
- goto dput_and_out;
-
error = -EROFS;
- if (IS_RDONLY(inode))
+ if (IS_RDONLY(inode) || MNT_IS_RDONLY(nd.mnt))
goto dput_and_out;
error = -EPERM;
if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
goto dput_and_out;
- down(&inode->i_sem);
+ 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);
- up(&inode->i_sem);
+ mutex_unlock(&inode->i_mutex);
dput_and_out:
path_release(&nd);
return error;
}
-static int chown_common(struct dentry * dentry, uid_t user, gid_t group)
+asmlinkage long sys_chmod(const char __user *filename, mode_t mode)
+{
+ return sys_fchmodat(AT_FDCWD, filename, mode);
+}
+
+static int chown_common(struct dentry *dentry, struct vfsmount *mnt,
+ uid_t user, gid_t group)
{
struct inode * inode;
int error;
goto out;
}
error = -EROFS;
- if (IS_RDONLY(inode))
+ if (IS_RDONLY(inode) || MNT_IS_RDONLY(mnt))
goto out;
error = -EPERM;
if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
goto out;
-
newattrs.ia_valid = ATTR_CTIME;
if (user != (uid_t) -1) {
newattrs.ia_valid |= ATTR_UID;
}
if (!S_ISDIR(inode->i_mode))
newattrs.ia_valid |= ATTR_KILL_SUID|ATTR_KILL_SGID;
- down(&inode->i_sem);
+ mutex_lock(&inode->i_mutex);
error = notify_change(dentry, &newattrs);
- up(&inode->i_sem);
+ mutex_unlock(&inode->i_mutex);
out:
return error;
}
error = user_path_walk(filename, &nd);
if (!error) {
- error = chown_common(nd.dentry, user, group);
+ error = chown_common(nd.dentry, nd.mnt, user, group);
+ path_release(&nd);
+ }
+ return error;
+}
+
+asmlinkage long sys_fchownat(int dfd, const char __user *filename, uid_t user,
+ gid_t group, int flag)
+{
+ struct nameidata nd;
+ int error = -EINVAL;
+ int follow;
+
+ if ((flag & ~AT_SYMLINK_NOFOLLOW) != 0)
+ goto out;
+
+ follow = (flag & AT_SYMLINK_NOFOLLOW) ? 0 : LOOKUP_FOLLOW;
+ error = __user_walk_fd(dfd, filename, follow, &nd);
+ if (!error) {
+ error = chown_common(nd.dentry, nd.mnt, user, group);
path_release(&nd);
}
+out:
return error;
}
error = user_path_walk_link(filename, &nd);
if (!error) {
- error = chown_common(nd.dentry, user, group);
+ error = chown_common(nd.dentry, nd.mnt, user, group);
path_release(&nd);
}
return error;
file = fget(fd);
if (file) {
- error = chown_common(file->f_dentry, user, group);
+ struct dentry * dentry;
+ dentry = file->f_dentry;
+ audit_inode(NULL, dentry->d_inode, 0);
+ error = chown_common(dentry, file->f_vfsmnt, user, group);
fput(file);
}
return 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.
- */
-struct file *filp_open(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++;
- if (namei_flags & O_TRUNC)
- namei_flags |= 2;
-
- error = open_namei(filename, namei_flags, mode, &nd);
- if (!error)
- return dentry_open(nd.dentry, nd.mnt, flags);
-
- return ERR_PTR(error);
-}
-
-EXPORT_SYMBOL(filp_open);
-
-struct file *dentry_open(struct dentry *dentry, struct vfsmount *mnt, int flags)
+static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt,
+ int flags, struct file *f,
+ int (*open)(struct inode *, struct file *))
{
- struct file * f;
struct inode *inode;
int error;
- error = -ENFILE;
- f = get_empty_filp();
- if (!f)
- goto cleanup_dentry;
f->f_flags = flags;
- f->f_mode = (flags+1) & O_ACCMODE;
+ f->f_mode = ((flags+1) & O_ACCMODE) | FMODE_LSEEK |
+ FMODE_PREAD | FMODE_PWRITE;
inode = dentry->d_inode;
if (f->f_mode & FMODE_WRITE) {
error = get_write_access(inode);
}
f->f_mapping = inode->i_mapping;
- file_ra_state_init(&f->f_ra, f->f_mapping);
f->f_dentry = dentry;
f->f_vfsmnt = mnt;
f->f_pos = 0;
f->f_op = fops_get(inode->i_fop);
file_move(f, &inode->i_sb->s_files);
- if (f->f_op && f->f_op->open) {
- error = f->f_op->open(inode,f);
+ if (!open && f->f_op)
+ open = f->f_op->open;
+ if (open) {
+ error = open(inode, f);
if (error)
goto cleanup_all;
}
+
f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC);
+ file_ra_state_init(&f->f_ra, f->f_mapping->host->i_mapping);
+
/* NB: we're sure to have correct a_ops only after f_op->open */
if (f->f_flags & O_DIRECT) {
- if (!f->f_mapping || !f->f_mapping->a_ops ||
- !f->f_mapping->a_ops->direct_IO) {
- fput(f);
- f = ERR_PTR(-EINVAL);
+ if (!f->f_mapping->a_ops ||
+ ((!f->f_mapping->a_ops->direct_IO) &&
+ (!f->f_mapping->a_ops->get_xip_page))) {
+ fput(f);
+ f = ERR_PTR(-EINVAL);
}
}
f->f_vfsmnt = NULL;
cleanup_file:
put_filp(f);
-cleanup_dentry:
dput(dentry);
mntput(mnt);
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
+ * @dentry: pointer to dentry
+ * @open: open callback
+ *
+ * Helper for filesystems that want to use lookup open intents and pass back
+ * 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()
+ * filesystem callback is substituted.
+ */
+struct file *lookup_instantiate_filp(struct nameidata *nd, struct dentry *dentry,
+ int (*open)(struct inode *, struct file *))
+{
+ if (IS_ERR(nd->intent.open.file))
+ goto out;
+ if (IS_ERR(dentry))
+ goto out_err;
+ nd->intent.open.file = __dentry_open(dget(dentry), mntget(nd->mnt),
+ nd->intent.open.flags - 1,
+ nd->intent.open.file,
+ open);
+out:
+ return nd->intent.open.file;
+out_err:
+ release_open_intent(nd);
+ nd->intent.open.file = (struct file *)dentry;
+ goto out;
+}
+EXPORT_SYMBOL_GPL(lookup_instantiate_filp);
+
+/**
+ * nameidata_to_filp - convert a nameidata to an open filp.
+ * @nd: pointer to nameidata
+ * @flags: open flags
+ *
+ * Note that this function destroys the original nameidata
+ */
+struct file *nameidata_to_filp(struct nameidata *nd, int flags)
+{
+ struct file *filp;
+
+ /* 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)
+ filp = __dentry_open(nd->dentry, nd->mnt, flags, filp, NULL);
+ else
+ path_release(nd);
+ return filp;
+}
+
+/*
+ * dentry_open() will have done dput(dentry) and mntput(mnt) if it returns an
+ * error.
+ */
+struct file *dentry_open(struct dentry *dentry, struct vfsmount *mnt, int flags)
+{
+ int error;
+ struct file *f;
+
+ error = -ENFILE;
+ f = get_empty_filp();
+ if (f == NULL) {
+ dput(dentry);
+ mntput(mnt);
+ return ERR_PTR(error);
+ }
+
+ return __dentry_open(dentry, mnt, flags, f, NULL);
+}
EXPORT_SYMBOL(dentry_open);
/*
{
struct files_struct * files = current->files;
int fd, error;
+ struct fdtable *fdt;
error = -EMFILE;
spin_lock(&files->file_lock);
repeat:
- fd = find_next_zero_bit(files->open_fds->fds_bits,
- files->max_fdset,
+ fdt = files_fdtable(files);
+ fd = find_next_zero_bit(fdt->open_fds->fds_bits,
+ fdt->max_fdset,
files->next_fd);
/*
* N.B. For clone tasks sharing a files structure, this test
* will limit the total number of files that can be opened.
*/
- if (fd >= current->rlim[RLIMIT_NOFILE].rlim_cur)
+ if (fd >= current->signal->rlim[RLIMIT_NOFILE].rlim_cur)
goto out;
- /* Do we need to expand the fdset array? */
- if (fd >= files->max_fdset) {
- error = expand_fdset(files, fd);
- if (!error) {
- error = -EMFILE;
- goto repeat;
- }
- goto out;
- }
-
- /*
- * Check whether we need to expand the fd array.
- */
- if (fd >= files->max_fds) {
- error = expand_fd_array(files, fd);
- if (!error) {
- error = -EMFILE;
- goto repeat;
- }
+ /* Do we need to expand the fd array or fd set? */
+ error = expand_files(files, fd);
+ if (error < 0)
goto out;
+
+ if (error) {
+ /*
+ * If we needed to expand the fs array we
+ * might have blocked - try again.
+ */
+ error = -EMFILE;
+ goto repeat;
}
- FD_SET(fd, files->open_fds);
- FD_CLR(fd, files->close_on_exec);
+ FD_SET(fd, fdt->open_fds);
+ FD_CLR(fd, fdt->close_on_exec);
files->next_fd = fd + 1;
vx_openfd_inc(fd);
#if 1
/* Sanity check */
- if (files->fd[fd] != NULL) {
+ if (fdt->fd[fd] != NULL) {
printk(KERN_WARNING "get_unused_fd: slot %d not NULL!\n", fd);
- files->fd[fd] = NULL;
+ fdt->fd[fd] = NULL;
}
#endif
error = fd;
EXPORT_SYMBOL(get_unused_fd);
-static inline void __put_unused_fd(struct files_struct *files, unsigned int fd)
+static void __put_unused_fd(struct files_struct *files, unsigned int fd)
{
- __FD_CLR(fd, files->open_fds);
+ struct fdtable *fdt = files_fdtable(files);
+ __FD_CLR(fd, fdt->open_fds);
if (fd < files->next_fd)
files->next_fd = fd;
+ vx_openfd_dec(fd);
}
void fastcall put_unused_fd(unsigned int fd)
EXPORT_SYMBOL(put_unused_fd);
/*
- * Install a file pointer in the fd array.
+ * Install a file pointer in the fd array.
*
* The VFS is full of places where we drop the files lock between
* setting the open_fds bitmap and installing the file in the file
void fastcall fd_install(unsigned int fd, struct file * file)
{
struct files_struct *files = current->files;
+ struct fdtable *fdt;
spin_lock(&files->file_lock);
- if (unlikely(files->fd[fd] != NULL))
- BUG();
- files->fd[fd] = file;
+ fdt = files_fdtable(files);
+ BUG_ON(fdt->fd[fd] != NULL);
+ rcu_assign_pointer(fdt->fd[fd], file);
spin_unlock(&files->file_lock);
}
EXPORT_SYMBOL(fd_install);
-asmlinkage long sys_open(const char __user * filename, int flags, int mode)
+long do_sys_open(int dfd, const char __user *filename, int flags, int mode)
{
- char * tmp;
- int fd, error;
+ char *tmp = getname(filename);
+ int fd = PTR_ERR(tmp);
-#if BITS_PER_LONG != 32
- flags |= O_LARGEFILE;
-#endif
- tmp = getname(filename);
- fd = PTR_ERR(tmp);
if (!IS_ERR(tmp)) {
fd = get_unused_fd();
if (fd >= 0) {
- struct file *f = filp_open(tmp, flags, mode);
- error = PTR_ERR(f);
- if (IS_ERR(f))
- goto out_error;
- fd_install(fd, f);
+ struct file *f = do_filp_open(dfd, tmp, flags, mode);
+ if (IS_ERR(f)) {
+ put_unused_fd(fd);
+ fd = PTR_ERR(f);
+ } else {
+ fsnotify_open(f->f_dentry);
+ fd_install(fd, f);
+ }
}
-out:
putname(tmp);
}
return fd;
+}
-out_error:
- put_unused_fd(fd);
- fd = error;
- goto out;
+asmlinkage long sys_open(const char __user *filename, int flags, int mode)
+{
+ long ret;
+
+ if (force_o_largefile())
+ flags |= O_LARGEFILE;
+
+ ret = do_sys_open(AT_FDCWD, filename, flags, mode);
+ /* avoid REGPARM breakage on x86: */
+ prevent_tail_call(ret);
+ return ret;
+}
+
+asmlinkage long sys_openat(int dfd, const char __user *filename, int flags,
+ int mode)
+{
+ long ret;
+
+ if (force_o_largefile())
+ flags |= O_LARGEFILE;
+
+ ret = do_sys_open(dfd, filename, flags, mode);
+ /* avoid REGPARM breakage on x86: */
+ prevent_tail_call(ret);
+ return ret;
}
-EXPORT_SYMBOL_GPL(sys_open);
#ifndef __alpha__
*/
int filp_close(struct file *filp, fl_owner_t id)
{
- int retval;
-
- /* Report and clear outstanding errors */
- retval = filp->f_error;
- if (retval)
- filp->f_error = 0;
+ int retval = 0;
if (!file_count(filp)) {
printk(KERN_ERR "VFS: Close: file count is 0\n");
- return retval;
+ return 0;
}
- if (filp->f_op && filp->f_op->flush) {
- int err = filp->f_op->flush(filp);
- if (!retval)
- retval = err;
- }
+ if (filp->f_op && filp->f_op->flush)
+ retval = filp->f_op->flush(filp);
dnotify_flush(filp, id);
locks_remove_posix(filp, id);
{
struct file * filp;
struct files_struct *files = current->files;
+ struct fdtable *fdt;
spin_lock(&files->file_lock);
- if (fd >= files->max_fds)
+ fdt = files_fdtable(files);
+ if (fd >= fdt->max_fds)
goto out_unlock;
- filp = files->fd[fd];
+ filp = fdt->fd[fd];
if (!filp)
goto out_unlock;
- files->fd[fd] = NULL;
- FD_CLR(fd, files->close_on_exec);
+ rcu_assign_pointer(fdt->fd[fd], NULL);
+ FD_CLR(fd, fdt->close_on_exec);
__put_unused_fd(files, fd);
spin_unlock(&files->file_lock);
- vx_openfd_dec(fd);
return filp_close(filp, files);
out_unlock:
}
EXPORT_SYMBOL(generic_file_open);
+
+/*
+ * This is used by subsystems that don't want seekable
+ * file descriptors
+ */
+int nonseekable_open(struct inode *inode, struct file *filp)
+{
+ filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE);
+ return 0;
+}
+
+EXPORT_SYMBOL(nonseekable_open);