reintroduce accept4

Introduce a new accept4() system call.  The addition of this system call
matches analogous changes in 2.6.27 (dup3(), evenfd2(), signalfd4(),
inotify_init1(), epoll_create1(), pipe2()) which added new system calls
that differed from analogous traditional system calls in adding a flags
argument that can be used to access additional functionality.

The accept4() system call is exactly the same as accept(), except that
it adds a flags bit-mask argument.  Two flags are initially implemented.
(Most of the new system calls in 2.6.27 also had both of these flags.)

SOCK_CLOEXEC causes the close-on-exec (FD_CLOEXEC) flag to be enabled
for the new file descriptor returned by accept4().  This is a useful
security feature to avoid leaking information in a multithreaded
program where one thread is doing an accept() at the same time as
another thread is doing a fork() plus exec().  More details here:
http://udrepper.livejournal.com/20407.html "Secure File Descriptor Handling",
Ulrich Drepper).

The other flag is SOCK_NONBLOCK, which causes the O_NONBLOCK flag
to be enabled on the new open file description created by accept4().
(This flag is merely a convenience, saving the use of additional calls
fcntl(F_GETFL) and fcntl (F_SETFL) to achieve the same result.

Here's a test program.  Works on x86-32.  Should work on x86-64, but
I (mtk) don't have a system to hand to test with.

It tests accept4() with each of the four possible combinations of
SOCK_CLOEXEC and SOCK_NONBLOCK set/clear in 'flags', and verifies
that the appropriate flags are set on the file descriptor/open file
description returned by accept4().

I tested Ulrich's patch in this thread by applying against 2.6.28-rc2,
and it passes according to my test program.

/* test_accept4.c

  Copyright (C) 2008, Linux Foundation, written by Michael Kerrisk
       <mtk.manpages@gmail.com>

  Licensed under the GNU GPLv2 or later.
*/
#define _GNU_SOURCE
#include <unistd.h>
#include <sys/syscall.h>
#include <sys/socket.h>
#include <netinet/in.h>
#include <stdlib.h>
#include <fcntl.h>
#include <stdio.h>
#include <string.h>

#define PORT_NUM 33333

#define die(msg) do { perror(msg); exit(EXIT_FAILURE); } while (0)

/**********************************************************************/

/* The following is what we need until glibc gets a wrapper for
  accept4() */

/* Flags for socket(), socketpair(), accept4() */
#ifndef SOCK_CLOEXEC
#define SOCK_CLOEXEC    O_CLOEXEC
#endif
#ifndef SOCK_NONBLOCK
#define SOCK_NONBLOCK   O_NONBLOCK
#endif

#ifdef __x86_64__
#define SYS_accept4 288
#elif __i386__
#define USE_SOCKETCALL 1
#define SYS_ACCEPT4 18
#else
#error "Sorry -- don't know the syscall # on this architecture"
#endif

static int
accept4(int fd, struct sockaddr *sockaddr, socklen_t *addrlen, int flags)
{
   printf("Calling accept4(): flags = %x", flags);
   if (flags != 0) {
       printf(" (");
       if (flags & SOCK_CLOEXEC)
           printf("SOCK_CLOEXEC");
       if ((flags & SOCK_CLOEXEC) && (flags & SOCK_NONBLOCK))
           printf(" ");
       if (flags & SOCK_NONBLOCK)
           printf("SOCK_NONBLOCK");
       printf(")");
   }
   printf("\n");

#if USE_SOCKETCALL
   long args[6];

   args[0] = fd;
   args[1] = (long) sockaddr;
   args[2] = (long) addrlen;
   args[3] = flags;

   return syscall(SYS_socketcall, SYS_ACCEPT4, args);
#else
   return syscall(SYS_accept4, fd, sockaddr, addrlen, flags);
#endif
}

/**********************************************************************/

static int
do_test(int lfd, struct sockaddr_in *conn_addr,
       int closeonexec_flag, int nonblock_flag)
{
   int connfd, acceptfd;
   int fdf, flf, fdf_pass, flf_pass;
   struct sockaddr_in claddr;
   socklen_t addrlen;

   printf("=======================================\n");

   connfd = socket(AF_INET, SOCK_STREAM, 0);
   if (connfd == -1)
       die("socket");
   if (connect(connfd, (struct sockaddr *) conn_addr,
               sizeof(struct sockaddr_in)) == -1)
       die("connect");

   addrlen = sizeof(struct sockaddr_in);
   acceptfd = accept4(lfd, (struct sockaddr *) &claddr, &addrlen,
                      closeonexec_flag | nonblock_flag);
   if (acceptfd == -1) {
       perror("accept4()");
       close(connfd);
       return 0;
   }

   fdf = fcntl(acceptfd, F_GETFD);
   if (fdf == -1)
       die("fcntl:F_GETFD");
   fdf_pass = ((fdf & FD_CLOEXEC) != 0) ==
              ((closeonexec_flag & SOCK_CLOEXEC) != 0);
   printf("Close-on-exec flag is %sset (%s); ",
           (fdf & FD_CLOEXEC) ? "" : "not ",
           fdf_pass ? "OK" : "failed");

   flf = fcntl(acceptfd, F_GETFL);
   if (flf == -1)
       die("fcntl:F_GETFD");
   flf_pass = ((flf & O_NONBLOCK) != 0) ==
              ((nonblock_flag & SOCK_NONBLOCK) !=0);
   printf("nonblock flag is %sset (%s)\n",
           (flf & O_NONBLOCK) ? "" : "not ",
           flf_pass ? "OK" : "failed");

   close(acceptfd);
   close(connfd);

   printf("Test result: %s\n", (fdf_pass && flf_pass) ? "PASS" : "FAIL");
   return fdf_pass && flf_pass;
}

static int
create_listening_socket(int port_num)
{
   struct sockaddr_in svaddr;
   int lfd;
   int optval;

   memset(&svaddr, 0, sizeof(struct sockaddr_in));
   svaddr.sin_family = AF_INET;
   svaddr.sin_addr.s_addr = htonl(INADDR_ANY);
   svaddr.sin_port = htons(port_num);

   lfd = socket(AF_INET, SOCK_STREAM, 0);
   if (lfd == -1)
       die("socket");

   optval = 1;
   if (setsockopt(lfd, SOL_SOCKET, SO_REUSEADDR, &optval,
                  sizeof(optval)) == -1)
       die("setsockopt");

   if (bind(lfd, (struct sockaddr *) &svaddr,
            sizeof(struct sockaddr_in)) == -1)
       die("bind");

   if (listen(lfd, 5) == -1)
       die("listen");

   return lfd;
}

int
main(int argc, char *argv[])
{
   struct sockaddr_in conn_addr;
   int lfd;
   int port_num;
   int passed;

   passed = 1;

   port_num = (argc > 1) ? atoi(argv[1]) : PORT_NUM;

   memset(&conn_addr, 0, sizeof(struct sockaddr_in));
   conn_addr.sin_family = AF_INET;
   conn_addr.sin_addr.s_addr = htonl(INADDR_LOOPBACK);
   conn_addr.sin_port = htons(port_num);

   lfd = create_listening_socket(port_num);

   if (!do_test(lfd, &conn_addr, 0, 0))
       passed = 0;
   if (!do_test(lfd, &conn_addr, SOCK_CLOEXEC, 0))
       passed = 0;
   if (!do_test(lfd, &conn_addr, 0, SOCK_NONBLOCK))
       passed = 0;
   if (!do_test(lfd, &conn_addr, SOCK_CLOEXEC, SOCK_NONBLOCK))
       passed = 0;

   close(lfd);

   exit(passed ? EXIT_SUCCESS : EXIT_FAILURE);
}

[mtk.manpages@gmail.com: rewrote changelog, updated test program]
Signed-off-by: Ulrich Drepper <drepper@redhat.com>
Tested-by: Michael Kerrisk <mtk.manpages@gmail.com>
Acked-by: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: <linux-api@vger.kernel.org>
Cc: <linux-arch@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/net/socket.c b/net/socket.c
index 57550c3..92764d8 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1426,8 +1426,8 @@
  *	clean when we restucture accept also.
  */
 
-long do_accept(int fd, struct sockaddr __user *upeer_sockaddr,
-	       int __user *upeer_addrlen, int flags)
+asmlinkage long sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr,
+			    int __user *upeer_addrlen, int flags)
 {
 	struct socket *sock, *newsock;
 	struct file *newfile;
@@ -1510,66 +1510,10 @@
 	goto out_put;
 }
 
-#if 0
-#ifdef HAVE_SET_RESTORE_SIGMASK
-asmlinkage long sys_paccept(int fd, struct sockaddr __user *upeer_sockaddr,
-			    int __user *upeer_addrlen,
-			    const sigset_t __user *sigmask,
-			    size_t sigsetsize, int flags)
-{
-	sigset_t ksigmask, sigsaved;
-	int ret;
-
-	if (sigmask) {
-		/* XXX: Don't preclude handling different sized sigset_t's.  */
-		if (sigsetsize != sizeof(sigset_t))
-			return -EINVAL;
-		if (copy_from_user(&ksigmask, sigmask, sizeof(ksigmask)))
-			return -EFAULT;
-
-		sigdelsetmask(&ksigmask, sigmask(SIGKILL)|sigmask(SIGSTOP));
-		sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
-        }
-
-	ret = do_accept(fd, upeer_sockaddr, upeer_addrlen, flags);
-
-	if (ret < 0 && signal_pending(current)) {
-		/*
-		 * Don't restore the signal mask yet. Let do_signal() deliver
-		 * the signal on the way back to userspace, before the signal
-		 * mask is restored.
-		 */
-		if (sigmask) {
-			memcpy(&current->saved_sigmask, &sigsaved,
-			       sizeof(sigsaved));
-			set_restore_sigmask();
-		}
-	} else if (sigmask)
-		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
-
-	return ret;
-}
-#else
-asmlinkage long sys_paccept(int fd, struct sockaddr __user *upeer_sockaddr,
-			    int __user *upeer_addrlen,
-			    const sigset_t __user *sigmask,
-			    size_t sigsetsize, int flags)
-{
-	/* The platform does not support restoring the signal mask in the
-	 * return path.  So we do not allow using paccept() with a signal
-	 * mask.  */
-	if (sigmask)
-		return -EINVAL;
-
-	return do_accept(fd, upeer_sockaddr, upeer_addrlen, flags);
-}
-#endif
-#endif
-
 asmlinkage long sys_accept(int fd, struct sockaddr __user *upeer_sockaddr,
 			   int __user *upeer_addrlen)
 {
-	return do_accept(fd, upeer_sockaddr, upeer_addrlen, 0);
+	return sys_accept4(fd, upeer_sockaddr, upeer_addrlen, 0);
 }
 
 /*
@@ -2096,7 +2040,7 @@
 	AL(0),AL(3),AL(3),AL(3),AL(2),AL(3),
 	AL(3),AL(3),AL(4),AL(4),AL(4),AL(6),
 	AL(6),AL(2),AL(5),AL(5),AL(3),AL(3),
-	AL(6)
+	AL(4)
 };
 
 #undef AL
@@ -2115,7 +2059,7 @@
 	unsigned long a0, a1;
 	int err;
 
-	if (call < 1 || call > SYS_PACCEPT)
+	if (call < 1 || call > SYS_ACCEPT4)
 		return -EINVAL;
 
 	/* copy_from_user should be SMP safe. */
@@ -2143,9 +2087,8 @@
 		err = sys_listen(a0, a1);
 		break;
 	case SYS_ACCEPT:
-		err =
-		    do_accept(a0, (struct sockaddr __user *)a1,
-			      (int __user *)a[2], 0);
+		err = sys_accept4(a0, (struct sockaddr __user *)a1,
+				  (int __user *)a[2], 0);
 		break;
 	case SYS_GETSOCKNAME:
 		err =
@@ -2192,12 +2135,9 @@
 	case SYS_RECVMSG:
 		err = sys_recvmsg(a0, (struct msghdr __user *)a1, a[2]);
 		break;
-	case SYS_PACCEPT:
-		err =
-		    sys_paccept(a0, (struct sockaddr __user *)a1,
-			        (int __user *)a[2],
-				(const sigset_t __user *) a[3],
-				a[4], a[5]);
+	case SYS_ACCEPT4:
+		err = sys_accept4(a0, (struct sockaddr __user *)a1,
+				  (int __user *)a[2], a[3]);
 		break;
 	default:
 		err = -EINVAL;