fs: add ksys_dup{,3}() helper; remove in-kernel calls to sys_dup{,3}()

Using ksys_dup() and ksys_dup3() as helper functions allows us to
avoid the in-kernel calls to the sys_dup() and sys_dup3() syscalls.
The ksys_ prefix denotes that these functions are meant as a drop-in
replacement for the syscalls. In particular, they use the same
calling convention as sys_dup{,3}().

In the near future, the fs-external callers of ksys_dup{,3}() should be
converted to call do_dup2() directly. Then, ksys_dup{,3}() can be moved
within sys_dup{,3}() again.

This patch is part of a series which removes in-kernel calls to syscalls.
On this basis, the syscall entry path can be streamlined. For details, see
http://lkml.kernel.org/r/20180325162527.GA17492@light.dominikbrodowski.net

Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Dominik Brodowski <linux@dominikbrodowski.net>

diff --git a/fs/file.c b/fs/file.c
index 42f0db4bd0fb54402171de9609ab961cc3f6aa6e..d304004f0b652772928cf931158c7953b3346542 100644 (file)
--- a/fs/file.c
+++ b/fs/file.c
@@ -870,7 +870,7 @@ int replace_fd(unsigned fd, struct file *file, unsigned flags)
        return err;
 }
 
-SYSCALL_DEFINE3(dup3, unsigned int, oldfd, unsigned int, newfd, int, flags)
+static int ksys_dup3(unsigned int oldfd, unsigned int newfd, int flags)
 {
        int err = -EBADF;
        struct file *file;
@@ -904,6 +904,11 @@ SYSCALL_DEFINE3(dup3, unsigned int, oldfd, unsigned int, newfd, int, flags)
        return err;
 }
 
+SYSCALL_DEFINE3(dup3, unsigned int, oldfd, unsigned int, newfd, int, flags)
+{
+       return ksys_dup3(oldfd, newfd, flags);
+}
+
 SYSCALL_DEFINE2(dup2, unsigned int, oldfd, unsigned int, newfd)
 {
        if (unlikely(newfd == oldfd)) { /* corner case */
@@ -916,10 +921,10 @@ SYSCALL_DEFINE2(dup2, unsigned int, oldfd, unsigned int, newfd)
                rcu_read_unlock();
                return retval;
        }
-       return sys_dup3(oldfd, newfd, 0);
+       return ksys_dup3(oldfd, newfd, 0);
 }
 
-SYSCALL_DEFINE1(dup, unsigned int, fildes)
+int ksys_dup(unsigned int fildes)
 {
        int ret = -EBADF;
        struct file *file = fget_raw(fildes);
@@ -934,6 +939,11 @@ SYSCALL_DEFINE1(dup, unsigned int, fildes)
        return ret;
 }
 
+SYSCALL_DEFINE1(dup, unsigned int, fildes)
+{
+       return ksys_dup(fildes);
+}
+
 int f_dupfd(unsigned int from, struct file *file, unsigned flags)
 {
        int err;

diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 48964c408c7bca578c71ce6512cf3f246b1850e3..50876ae1d17ba70353dee11f613b1c99c9fd8b44 100644 (file)
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -949,5 +949,6 @@ asmlinkage long sys_statx(int dfd, const char __user *path, unsigned flags,
 int ksys_mount(char __user *dev_name, char __user *dir_name, char __user *type,
               unsigned long flags, void __user *data);
 int ksys_umount(char __user *name, int flags);
+int ksys_dup(unsigned int fildes);
 
 #endif

diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c
index 1c4da835333232a04c033a0056311860d151b5ba..e8573e1776f6cd0476fdd83fcffa99753107508c 100644 (file)
--- a/init/do_mounts_initrd.c
+++ b/init/do_mounts_initrd.c
@@ -39,8 +39,8 @@ static int init_linuxrc(struct subprocess_info *info, struct cred *new)
        sys_unshare(CLONE_FS | CLONE_FILES);
        /* stdin/stdout/stderr for /linuxrc */
        sys_open("/dev/console", O_RDWR, 0);
-       sys_dup(0);
-       sys_dup(0);
+       ksys_dup(0);
+       ksys_dup(0);
        /* move initrd over / and chdir/chroot in initrd root */
        sys_chdir("/root");
        ksys_mount(".", "/", NULL, MS_MOVE, NULL);

diff --git a/init/main.c b/init/main.c
index 969eaf140ef0a5d356e2c9a085b5d2a86c215eba..b8649d1466e1896aed249098da61d5b50e5d90ac 100644 (file)
--- a/init/main.c
+++ b/init/main.c
@@ -1077,8 +1077,8 @@ static noinline void __init kernel_init_freeable(void)
        if (sys_open((const char __user *) "/dev/console", O_RDWR, 0) < 0)
                pr_err("Warning: unable to open an initial console.\n");
 
-       (void) sys_dup(0);
-       (void) sys_dup(0);
+       (void) ksys_dup(0);
+       (void) ksys_dup(0);
        /*
         * check if there is an early userspace init.  If yes, let it do all
         * the work