Commit 0e81cfd9 authored by Kuniyuki Iwashima's avatar Kuniyuki Iwashima Committed by David S. Miller
Browse files

af_unix: Move SOCK_PASS{CRED,PIDFD,SEC} to struct sock. 



As explained in the next patch, SO_PASSRIGHTS would have a problem
if we assigned a corresponding bit to socket->flags, so it must be
managed in struct sock.

Mixing socket->flags and sk->sk_flags for similar options will look
confusing, and sk->sk_flags does not have enough space on 32bit system.

Also, as mentioned in commit 16e57262 ("af_unix: dont send
SCM_CREDENTIALS by default"), SOCK_PASSCRED and SOCK_PASSPID handling
is known to be slow, and managing the flags in struct socket cannot
avoid that for embryo sockets.

Let's move SOCK_PASS{CRED,PIDFD,SEC} to struct sock.

While at it, other SOCK_XXX flags in net.h are grouped as enum.

Note that assign_bit() was atomic, so the writer side is moved down
after lock_sock() in setsockopt(), but the bit is only read once
in sendmsg() and recvmsg(), so lock_sock() is not needed there.

Signed-off-by: default avatarKuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: default avatarWillem de Bruijn <willemb@google.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent 7d8d93fd

include/linux/net.h

+7 −8
Original line number Diff line number Diff line
@@ -36,14 +36,13 @@ struct net; 
 * in sock->flags, but moved into sk->sk_wq->flags to be RCU protected.

 * Eventually all flags will be in sk->sk_wq->flags.

 */

#define SOCKWQ_ASYNC_NOSPACE	0

#define SOCKWQ_ASYNC_WAITDATA	1

#define SOCK_NOSPACE		2

#define SOCK_PASSCRED		3

#define SOCK_PASSSEC		4

#define SOCK_SUPPORT_ZC		5

#define SOCK_CUSTOM_SOCKOPT	6

#define SOCK_PASSPIDFD		7

enum socket_flags {

	SOCKWQ_ASYNC_NOSPACE,

	SOCKWQ_ASYNC_WAITDATA,

	SOCK_NOSPACE,

	SOCK_SUPPORT_ZC,

	SOCK_CUSTOM_SOCKOPT,

};



#ifndef ARCH_HAS_SOCKET_TYPES

/**

include/net/sock.h

+15 −1
Original line number Diff line number Diff line
@@ -337,6 +337,11 @@ struct sk_filter; 
  *	@sk_txtime_deadline_mode: set deadline mode for SO_TXTIME

  *	@sk_txtime_report_errors: set report errors mode for SO_TXTIME

  *	@sk_txtime_unused: unused txtime flags

  *	@sk_scm_recv_flags: all flags used by scm_recv()

  *	@sk_scm_credentials: flagged by SO_PASSCRED to recv SCM_CREDENTIALS

  *	@sk_scm_security: flagged by SO_PASSSEC to recv SCM_SECURITY

  *	@sk_scm_pidfd: flagged by SO_PASSPIDFD to recv SCM_PIDFD

  *	@sk_scm_unused: unused flags for scm_recv()

  *	@ns_tracker: tracker for netns reference

  *	@sk_user_frags: xarray of pages the user is holding a reference on.

  *	@sk_owner: reference to the real owner of the socket that calls
@@ -523,7 +528,16 @@ struct sock { 
#endif

	int			sk_disconnects;



	union {

		u8		sk_txrehash;

		u8		sk_scm_recv_flags;

		struct {

			u8	sk_scm_credentials : 1,

				sk_scm_security : 1,

				sk_scm_pidfd : 1,

				sk_scm_unused : 5;

		};

	};

	u8			sk_clockid;

	u8			sk_txtime_deadline_mode : 1,

				sk_txtime_report_errors : 1,

net/core/scm.c

+14 −15
Original line number Diff line number Diff line
@@ -406,12 +406,12 @@ struct scm_fp_list *scm_fp_dup(struct scm_fp_list *fpl) 
EXPORT_SYMBOL(scm_fp_dup);



#ifdef CONFIG_SECURITY_NETWORK

static void scm_passec(struct socket *sock, struct msghdr *msg, struct scm_cookie *scm)

static void scm_passec(struct sock *sk, struct msghdr *msg, struct scm_cookie *scm)

{

	struct lsm_context ctx;

	int err;



	if (test_bit(SOCK_PASSSEC, &sock->flags)) {

	if (sk->sk_scm_security) {

		err = security_secid_to_secctx(scm->secid, &ctx);



		if (err >= 0) {
@@ -423,16 +423,16 @@ static void scm_passec(struct socket *sock, struct msghdr *msg, struct scm_cooki 
	}

}



static bool scm_has_secdata(struct socket *sock)

static bool scm_has_secdata(struct sock *sk)

{

	return test_bit(SOCK_PASSSEC, &sock->flags);

	return sk->sk_scm_security;

}

#else

static void scm_passec(struct socket *sock, struct msghdr *msg, struct scm_cookie *scm)

static void scm_passec(struct sock *sk, struct msghdr *msg, struct scm_cookie *scm)

{

}



static bool scm_has_secdata(struct socket *sock)

static bool scm_has_secdata(struct sock *sk)

{

	return false;

}
@@ -474,20 +474,19 @@ static void scm_pidfd_recv(struct msghdr *msg, struct scm_cookie *scm) 
		fd_install(pidfd, pidfd_file);

}



static bool __scm_recv_common(struct socket *sock, struct msghdr *msg,

static bool __scm_recv_common(struct sock *sk, struct msghdr *msg,

			      struct scm_cookie *scm, int flags)

{

	if (!msg->msg_control) {

		if (test_bit(SOCK_PASSCRED, &sock->flags) ||

		    test_bit(SOCK_PASSPIDFD, &sock->flags) ||

		    scm->fp || scm_has_secdata(sock))

		if (sk->sk_scm_credentials || sk->sk_scm_pidfd ||

		    scm->fp || scm_has_secdata(sk))

			msg->msg_flags |= MSG_CTRUNC;



		scm_destroy(scm);

		return false;

	}



	if (test_bit(SOCK_PASSCRED, &sock->flags)) {

	if (sk->sk_scm_credentials) {

		struct user_namespace *current_ns = current_user_ns();

		struct ucred ucreds = {

			.pid = scm->creds.pid,
@@ -498,7 +497,7 @@ static bool __scm_recv_common(struct socket *sock, struct msghdr *msg, 
		put_cmsg(msg, SOL_SOCKET, SCM_CREDENTIALS, sizeof(ucreds), &ucreds);

	}



	scm_passec(sock, msg, scm);

	scm_passec(sk, msg, scm);



	if (scm->fp)

		scm_detach_fds(msg, scm);
@@ -509,7 +508,7 @@ static bool __scm_recv_common(struct socket *sock, struct msghdr *msg, 
void scm_recv(struct socket *sock, struct msghdr *msg,

	      struct scm_cookie *scm, int flags)

{

	if (!__scm_recv_common(sock, msg, scm, flags))

	if (!__scm_recv_common(sock->sk, msg, scm, flags))

		return;



	scm_destroy_cred(scm);
@@ -519,10 +518,10 @@ EXPORT_SYMBOL(scm_recv); 
void scm_recv_unix(struct socket *sock, struct msghdr *msg,

		   struct scm_cookie *scm, int flags)

{

	if (!__scm_recv_common(sock, msg, scm, flags))

	if (!__scm_recv_common(sock->sk, msg, scm, flags))

		return;



	if (test_bit(SOCK_PASSPIDFD, &sock->flags))

	if (sock->sk->sk_scm_pidfd)

		scm_pidfd_recv(msg, scm);



	scm_destroy_cred(scm);

net/core/sock.c

+23 −21
Original line number Diff line number Diff line
@@ -1220,24 +1220,6 @@ int sk_setsockopt(struct sock *sk, int level, int optname, 
			return 0;

		}

		return -EPERM;

	case SO_PASSSEC:

		if (!IS_ENABLED(CONFIG_SECURITY_NETWORK) || sk_may_scm_recv(sk))

			return -EOPNOTSUPP;



		assign_bit(SOCK_PASSSEC, &sock->flags, valbool);

		return 0;

	case SO_PASSCRED:

		if (!sk_may_scm_recv(sk))

			return -EOPNOTSUPP;



		assign_bit(SOCK_PASSCRED, &sock->flags, valbool);

		return 0;

	case SO_PASSPIDFD:

		if (!sk_is_unix(sk))

			return -EOPNOTSUPP;



		assign_bit(SOCK_PASSPIDFD, &sock->flags, valbool);

		return 0;

	case SO_TYPE:

	case SO_PROTOCOL:

	case SO_DOMAIN:
@@ -1568,6 +1550,26 @@ int sk_setsockopt(struct sock *sk, int level, int optname, 
		sock_valbool_flag(sk, SOCK_SELECT_ERR_QUEUE, valbool);

		break;



	case SO_PASSCRED:

		if (sk_may_scm_recv(sk))

			sk->sk_scm_credentials = valbool;

		else

			ret = -EOPNOTSUPP;

		break;



	case SO_PASSSEC:

		if (IS_ENABLED(CONFIG_SECURITY_NETWORK) && sk_may_scm_recv(sk))

			sk->sk_scm_security = valbool;

		else

			ret = -EOPNOTSUPP;

		break;



	case SO_PASSPIDFD:

		if (sk_is_unix(sk))

			sk->sk_scm_pidfd = valbool;

		else

			ret = -EOPNOTSUPP;

		break;



	case SO_INCOMING_CPU:

		reuseport_update_incoming_cpu(sk, val);
@@ -1867,14 +1869,14 @@ int sk_getsockopt(struct sock *sk, int level, int optname, 
		if (!sk_may_scm_recv(sk))

			return -EOPNOTSUPP;



		v.val = !!test_bit(SOCK_PASSCRED, &sock->flags);

		v.val = sk->sk_scm_credentials;

		break;



	case SO_PASSPIDFD:

		if (!sk_is_unix(sk))

			return -EOPNOTSUPP;



		v.val = !!test_bit(SOCK_PASSPIDFD, &sock->flags);

		v.val = sk->sk_scm_pidfd;

		break;



	case SO_PEERCRED:
@@ -1974,7 +1976,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname, 
		if (!IS_ENABLED(CONFIG_SECURITY_NETWORK) || !sk_may_scm_recv(sk))

			return -EOPNOTSUPP;



		v.val = !!test_bit(SOCK_PASSSEC, &sock->flags);

		v.val = sk->sk_scm_security;

		break;



	case SO_PEERSEC:

net/unix/af_unix.c

+2 −16
Original line number Diff line number Diff line
@@ -767,10 +767,7 @@ static void copy_peercred(struct sock *sk, struct sock *peersk) 


static bool unix_may_passcred(const struct sock *sk)

{

	struct socket *sock = sk->sk_socket;



	return test_bit(SOCK_PASSCRED, &sock->flags) ||

		test_bit(SOCK_PASSPIDFD, &sock->flags);

	return sk->sk_scm_credentials || sk->sk_scm_pidfd;

}



static int unix_listen(struct socket *sock, int backlog)
@@ -1713,17 +1710,6 @@ static int unix_socketpair(struct socket *socka, struct socket *sockb) 
	return 0;

}



static void unix_sock_inherit_flags(const struct socket *old,

				    struct socket *new)

{

	if (test_bit(SOCK_PASSCRED, &old->flags))

		set_bit(SOCK_PASSCRED, &new->flags);

	if (test_bit(SOCK_PASSPIDFD, &old->flags))

		set_bit(SOCK_PASSPIDFD, &new->flags);

	if (test_bit(SOCK_PASSSEC, &old->flags))

		set_bit(SOCK_PASSSEC, &new->flags);

}



static int unix_accept(struct socket *sock, struct socket *newsock,

		       struct proto_accept_arg *arg)

{
@@ -1760,7 +1746,7 @@ static int unix_accept(struct socket *sock, struct socket *newsock, 
	unix_state_lock(tsk);

	unix_update_edges(unix_sk(tsk));

	newsock->state = SS_CONNECTED;

	unix_sock_inherit_flags(sock, newsock);

	tsk->sk_scm_recv_flags = READ_ONCE(sk->sk_scm_recv_flags);

	sock_graft(tsk, newsock);

	unix_state_unlock(tsk);

	return 0;