Merge branch 'get-rid-of-the-address_space-override-in-setsockopt-v2'

Christoph Hellwig says:

====================
get rid of the address_space override in setsockopt v2

setsockopt is the last place in architecture-independ code that still
uses set_fs to force the uaccess routines to operate on kernel pointers.

This series adds a new sockptr_t type that can contained either a kernel
or user pointer, and which has accessors that do the right thing, and
then uses it for setsockopt, starting by refactoring some low-level
helpers and moving them over to it before finally doing the main
setsockopt method.

Note that apparently the eBPF selftests do not even cover this path, so
the series has been tested with a testing patch that always copies the
data first and passes a kernel pointer.  This is something that works for
most common sockopts (and is something that the ePBF support relies on),
but unfortunately in various corner cases we either don't use the passed
in length, or in one case actually copy data back from setsockopt, or in
case of bpfilter straight out do not work with kernel pointers at all.

Against net-next/master.

Changes since v1:
 - check that users don't pass in kernel addresses
 - more bpfilter cleanups
 - cosmetic mptcp tweak
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 10 insertions, 14 deletions

diff --git a/net/socket.c b/net/socket.c
index 93846568c2fb..94ca4547cd7c 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2094,10 +2094,10 @@ static bool sock_use_custom_sol_socket(const struct socket *sock)
  *	Set a socket option. Because we don't know the option lengths we have
  *	to pass the user mode parameter for the protocols to sort out.
  */
-int __sys_setsockopt(int fd, int level, int optname, char __user *optval,
+int __sys_setsockopt(int fd, int level, int optname, char __user *user_optval,
 		int optlen)
 {
-	mm_segment_t oldfs = get_fs();
+	sockptr_t optval;
 	char *kernel_optval = NULL;
 	int err, fput_needed;
 	struct socket *sock;
@@ -2105,6 +2105,10 @@ int __sys_setsockopt(int fd, int level, int optname, char __user *optval,
 	if (optlen < 0)
 		return -EINVAL;
 
+	err = init_user_sockptr(&optval, user_optval);
+	if (err)
+		return err;
+
 	sock = sockfd_lookup_light(fd, &err, &fput_needed);
 	if (!sock)
 		return err;
@@ -2115,7 +2119,7 @@ int __sys_setsockopt(int fd, int level, int optname, char __user *optval,
 
 	if (!in_compat_syscall())
 		err = BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock->sk, &level, &optname,
-						     optval, &optlen,
+						     user_optval, &optlen,
 						     &kernel_optval);
 	if (err < 0)
 		goto out_put;
@@ -2124,11 +2128,8 @@ int __sys_setsockopt(int fd, int level, int optname, char __user *optval,
 		goto out_put;
 	}
 
-	if (kernel_optval) {
-		set_fs(KERNEL_DS);
-		optval = (char __user __force *)kernel_optval;
-	}
-
+	if (kernel_optval)
+		optval = KERNEL_SOCKPTR(kernel_optval);
 	if (level == SOL_SOCKET && !sock_use_custom_sol_socket(sock))
 		err = sock_setsockopt(sock, level, optname, optval, optlen);
 	else if (unlikely(!sock->ops->setsockopt))
@@ -2136,12 +2137,7 @@ int __sys_setsockopt(int fd, int level, int optname, char __user *optval,
 	else
 		err = sock->ops->setsockopt(sock, level, optname, optval,
 					    optlen);
-
-	if (kernel_optval) {
-		set_fs(oldfs);
-		kfree(kernel_optval);
-	}
-
+	kfree(kernel_optval);
 out_put:
 	fput_light(sock->file, fput_needed);
 	return err;