flag parameters: socket and socketpair

This patch adds support for flag values which are ORed to the type passwd
to socket and socketpair.  The additional code is minimal.  The flag
values in this implementation can and must match the O_* flags.  This
avoids overhead in the conversion.

The internal functions sock_alloc_fd and sock_map_fd get a new parameters
and all callers are changed.

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
#include <fcntl.h>
#include <stdio.h>
#include <unistd.h>
#include <netinet/in.h>
#include <sys/socket.h>

#define PORT 57392

/* For Linux these must be the same.  */
#define SOCK_CLOEXEC O_CLOEXEC

int
main (void)
{
  int fd;
  fd = socket (PF_INET, SOCK_STREAM, 0);
  if (fd == -1)
    {
      puts ("socket(0) failed");
      return 1;
    }
  int coe = fcntl (fd, F_GETFD);
  if (coe == -1)
    {
      puts ("fcntl failed");
      return 1;
    }
  if (coe & FD_CLOEXEC)
    {
      puts ("socket(0) set close-on-exec flag");
      return 1;
    }
  close (fd);

  fd = socket (PF_INET, SOCK_STREAM|SOCK_CLOEXEC, 0);
  if (fd == -1)
    {
      puts ("socket(SOCK_CLOEXEC) failed");
      return 1;
    }
  coe = fcntl (fd, F_GETFD);
  if (coe == -1)
    {
      puts ("fcntl failed");
      return 1;
    }
  if ((coe & FD_CLOEXEC) == 0)
    {
      puts ("socket(SOCK_CLOEXEC) does not set close-on-exec flag");
      return 1;
    }
  close (fd);

  int fds[2];
  if (socketpair (PF_UNIX, SOCK_STREAM, 0, fds) == -1)
    {
      puts ("socketpair(0) failed");
      return 1;
    }
  for (int i = 0; i < 2; ++i)
    {
      coe = fcntl (fds[i], F_GETFD);
      if (coe == -1)
        {
          puts ("fcntl failed");
          return 1;
        }
      if (coe & FD_CLOEXEC)
        {
          printf ("socketpair(0) set close-on-exec flag for fds[%d]\n", i);
          return 1;
        }
      close (fds[i]);
    }

  if (socketpair (PF_UNIX, SOCK_STREAM|SOCK_CLOEXEC, 0, fds) == -1)
    {
      puts ("socketpair(SOCK_CLOEXEC) failed");
      return 1;
    }
  for (int i = 0; i < 2; ++i)
    {
      coe = fcntl (fds[i], F_GETFD);
      if (coe == -1)
        {
          puts ("fcntl failed");
          return 1;
        }
      if ((coe & FD_CLOEXEC) == 0)
        {
          printf ("socketpair(SOCK_CLOEXEC) does not set close-on-exec flag for fds[%d]\n", i);
          return 1;
        }
      close (fds[i]);
    }

  puts ("OK");

  return 0;
}
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Signed-off-by: Ulrich Drepper <drepper@redhat.com>
Acked-by: Davide Libenzi <davidel@xmailserver.org>
Cc: Michael Kerrisk <mtk.manpages@googlemail.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Ralf Baechle <ralf@linux-mips.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

5 files changed, 37 insertions, 11 deletions

diff --git a/include/asm-mips/socket.h b/include/asm-mips/socket.h
index 63f60254..facc2d7 100644
--- a/include/asm-mips/socket.h
+++ b/include/asm-mips/socket.h
@@ -102,6 +102,13 @@ enum sock_type {
 };
 
 #define SOCK_MAX (SOCK_PACKET + 1)
+/* Mask which covers at least up to SOCK_MASK-1.  The
+ *  * remaining bits are used as flags. */
+#define SOCK_TYPE_MASK 0xf
+
+/* Flags for socket, socketpair, paccept */
+#define SOCK_CLOEXEC	O_CLOEXEC
+#define SOCK_NONBLOCK	O_NONBLOCK
 
 #define ARCH_HAS_SOCKET_TYPES 1
 
diff --git a/include/linux/net.h b/include/linux/net.h
index 150a48c..8b5383c 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -20,6 +20,7 @@
 
 #include <linux/wait.h>
 #include <linux/socket.h>
+#include <linux/fcntl.h>	/* For O_CLOEXEC */
 #include <asm/socket.h>
 
 struct poll_table_struct;
@@ -94,6 +95,12 @@ enum sock_type {
 };
 
 #define SOCK_MAX (SOCK_PACKET + 1)
+/* Mask which covers at least up to SOCK_MASK-1.  The
+ * remaining bits are used as flags. */
+#define SOCK_TYPE_MASK 0xf
+
+/* Flags for socket, socketpair, paccept */
+#define SOCK_CLOEXEC	O_CLOEXEC
 
 #endif /* ARCH_HAS_SOCKET_TYPES */
 
@@ -208,7 +215,7 @@ extern int   	     sock_sendmsg(struct socket *sock, struct msghdr *msg,
 				  size_t len);
 extern int	     sock_recvmsg(struct socket *sock, struct msghdr *msg,
 				  size_t size, int flags);
-extern int 	     sock_map_fd(struct socket *sock);
+extern int 	     sock_map_fd(struct socket *sock, int flags);
 extern struct socket *sockfd_lookup(int fd, int *err);
 #define		     sockfd_put(sock) fput(sock->file)
 extern int	     net_ratelimit(void);
diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c
index 4507f74..cdf137a 100644
--- a/net/9p/trans_fd.c
+++ b/net/9p/trans_fd.c
@@ -1285,7 +1285,7 @@ static int p9_socket_open(struct p9_trans *trans, struct socket *csocket)
 	int fd, ret;
 
 	csocket->sk->sk_allocation = GFP_NOIO;
-	fd = sock_map_fd(csocket);
+	fd = sock_map_fd(csocket, 0);
 	if (fd < 0) {
 		P9_EPRINTK(KERN_ERR, "p9_socket_open: failed to map fd\n");
 		return fd;
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 79bece1..dbb79ad 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -3910,7 +3910,7 @@ static int sctp_getsockopt_peeloff(struct sock *sk, int len, char __user *optval
 		goto out;
 
 	/* Map the socket to an unused fd that can be returned to the user.  */
-	retval = sock_map_fd(newsock);
+	retval = sock_map_fd(newsock, 0);
 	if (retval < 0) {
 		sock_release(newsock);
 		goto out;
diff --git a/net/socket.c b/net/socket.c
index 1ba57d8..64601f9 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -349,11 +349,11 @@ static struct dentry_operations sockfs_dentry_operations = {
  *	but we take care of internal coherence yet.
  */
 
-static int sock_alloc_fd(struct file **filep)
+static int sock_alloc_fd(struct file **filep, int flags)
 {
 	int fd;
 
-	fd = get_unused_fd();
+	fd = get_unused_fd_flags(flags);
 	if (likely(fd >= 0)) {
 		struct file *file = get_empty_filp();
 
@@ -396,10 +396,10 @@ static int sock_attach_fd(struct socket *sock, struct file *file)
 	return 0;
 }
 
-int sock_map_fd(struct socket *sock)
+int sock_map_fd(struct socket *sock, int flags)
 {
 	struct file *newfile;
-	int fd = sock_alloc_fd(&newfile);
+	int fd = sock_alloc_fd(&newfile, flags);
 
 	if (likely(fd >= 0)) {
 		int err = sock_attach_fd(sock, newfile);
@@ -1218,12 +1218,18 @@ asmlinkage long sys_socket(int family, int type, int protocol)
 {
 	int retval;
 	struct socket *sock;
+	int flags;
+
+	flags = type & ~SOCK_TYPE_MASK;
+	if (flags & ~SOCK_CLOEXEC)
+		return -EINVAL;
+	type &= SOCK_TYPE_MASK;
 
 	retval = sock_create(family, type, protocol, &sock);
 	if (retval < 0)
 		goto out;
 
-	retval = sock_map_fd(sock);
+	retval = sock_map_fd(sock, flags & O_CLOEXEC);
 	if (retval < 0)
 		goto out_release;
 
@@ -1246,6 +1252,12 @@ asmlinkage long sys_socketpair(int family, int type, int protocol,
 	struct socket *sock1, *sock2;
 	int fd1, fd2, err;
 	struct file *newfile1, *newfile2;
+	int flags;
+
+	flags = type & ~SOCK_TYPE_MASK;
+	if (flags & ~SOCK_CLOEXEC)
+		return -EINVAL;
+	type &= SOCK_TYPE_MASK;
 
 	/*
 	 * Obtain the first socket and check if the underlying protocol
@@ -1264,13 +1276,13 @@ asmlinkage long sys_socketpair(int family, int type, int protocol,
 	if (err < 0)
 		goto out_release_both;
 
-	fd1 = sock_alloc_fd(&newfile1);
+	fd1 = sock_alloc_fd(&newfile1, flags & O_CLOEXEC);
 	if (unlikely(fd1 < 0)) {
 		err = fd1;
 		goto out_release_both;
 	}
 
-	fd2 = sock_alloc_fd(&newfile2);
+	fd2 = sock_alloc_fd(&newfile2, flags & O_CLOEXEC);
 	if (unlikely(fd2 < 0)) {
 		err = fd2;
 		put_filp(newfile1);
@@ -1426,7 +1438,7 @@ asmlinkage long sys_accept(int fd, struct sockaddr __user *upeer_sockaddr,
 	 */
 	__module_get(newsock->ops->owner);
 
-	newfd = sock_alloc_fd(&newfile);
+	newfd = sock_alloc_fd(&newfile, 0);
 	if (unlikely(newfd < 0)) {
 		err = newfd;
 		sock_release(newsock);