From patchwork Mon Oct 6 19:21:16 2008 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Paul Moore X-Patchwork-Id: 2962 Return-Path: X-Original-To: patchwork-incoming@ozlabs.org Delivered-To: patchwork-incoming@ozlabs.org Received: from vger.kernel.org (vger.kernel.org [209.132.176.167]) by ozlabs.org (Postfix) with ESMTP id 8F545DDF01 for ; Tue, 7 Oct 2008 06:22:19 +1100 (EST) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753174AbYJFTVd (ORCPT ); Mon, 6 Oct 2008 15:21:33 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752970AbYJFTVc (ORCPT ); Mon, 6 Oct 2008 15:21:32 -0400 Received: from g1t0028.austin.hp.com ([15.216.28.35]:33879 "EHLO g1t0028.austin.hp.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752939AbYJFTVV (ORCPT ); Mon, 6 Oct 2008 15:21:21 -0400 Received: from g5t0029.atlanta.hp.com (g5t0029.atlanta.hp.com [16.228.8.141]) by g1t0028.austin.hp.com (Postfix) with ESMTP id 94FBB1C6BA; Mon, 6 Oct 2008 19:21:20 +0000 (UTC) Received: from ldl.fc.hp.com (ldl.fc.hp.com [15.11.146.30]) by g5t0029.atlanta.hp.com (Postfix) with ESMTP id 5F493101F1; Mon, 6 Oct 2008 19:21:20 +0000 (UTC) Received: from localhost (ldl.fc.hp.com [127.0.0.1]) by ldl.fc.hp.com (Postfix) with ESMTP id 1FC7139C009; Mon, 6 Oct 2008 13:21:20 -0600 (MDT) X-Virus-Scanned: Debian amavisd-new at ldl.fc.hp.com Received: from ldl.fc.hp.com ([127.0.0.1]) by localhost (ldl.fc.hp.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id AR3kulN-eg3R; Mon, 6 Oct 2008 13:21:18 -0600 (MDT) Received: from flek.lan (squirrel.fc.hp.com [15.11.146.57]) by ldl.fc.hp.com (Postfix) with ESMTP id D3E3413401D; Mon, 6 Oct 2008 13:21:16 -0600 (MDT) From: Paul Moore Subject: [PATCH v7 13/17] selinux: Set socket NetLabel based on connection endpoint To: selinux@tycho.nsa.gov, netdev@vger.kernel.org, linux-security-module@vger.kernel.org Date: Mon, 06 Oct 2008 15:21:16 -0400 Message-ID: <20081006192116.15686.30860.stgit@flek.lan> In-Reply-To: <20081006191516.15686.80823.stgit@flek.lan> References: <20081006191516.15686.80823.stgit@flek.lan> User-Agent: StGIT/0.13 MIME-Version: 1.0 Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org Previous work enabled the use of address based NetLabel selectors, which while highly useful, brought the potential for additional per-packet overhead when used. This patch attempts to solve that by applying NetLabel socket labels when sockets are connect()'d. This should alleviate the per-packet NetLabel labeling for all connected sockets (yes, it even works for connected DGRAM sockets). Signed-off-by: Paul Moore Reviewed-by: James Morris --- include/net/cipso_ipv4.h | 5 + include/net/netlabel.h | 13 +++ net/ipv4/cipso_ipv4.c | 74 ++++++++++++++++++ net/netlabel/netlabel_kapi.c | 78 ++++++++++++++++++- security/selinux/hooks.c | 11 +-- security/selinux/include/netlabel.h | 19 ++++- security/selinux/include/objsec.h | 1 security/selinux/netlabel.c | 147 ++++++++++++++++++++++++++++------- 8 files changed, 311 insertions(+), 37 deletions(-) -- To unsubscribe from this list: send the line "unsubscribe netdev" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html diff --git a/include/net/cipso_ipv4.h b/include/net/cipso_ipv4.h index 2ce093b..811febf 100644 --- a/include/net/cipso_ipv4.h +++ b/include/net/cipso_ipv4.h @@ -207,6 +207,7 @@ void cipso_v4_error(struct sk_buff *skb, int error, u32 gateway); int cipso_v4_sock_setattr(struct sock *sk, const struct cipso_v4_doi *doi_def, const struct netlbl_lsm_secattr *secattr); +void cipso_v4_sock_delattr(struct sock *sk); int cipso_v4_sock_getattr(struct sock *sk, struct netlbl_lsm_secattr *secattr); int cipso_v4_skbuff_setattr(struct sk_buff *skb, const struct cipso_v4_doi *doi_def, @@ -230,6 +231,10 @@ static inline int cipso_v4_sock_setattr(struct sock *sk, return -ENOSYS; } +static inline void cipso_v4_sock_delattr(struct sock *sk) +{ +} + static inline int cipso_v4_sock_getattr(struct sock *sk, struct netlbl_lsm_secattr *secattr) { diff --git a/include/net/netlabel.h b/include/net/netlabel.h index 3f67e6d..074cad4 100644 --- a/include/net/netlabel.h +++ b/include/net/netlabel.h @@ -380,8 +380,12 @@ int netlbl_secattr_catmap_setrng(struct netlbl_lsm_secattr_catmap *catmap, int netlbl_enabled(void); int netlbl_sock_setattr(struct sock *sk, const struct netlbl_lsm_secattr *secattr); +void netlbl_sock_delattr(struct sock *sk); int netlbl_sock_getattr(struct sock *sk, struct netlbl_lsm_secattr *secattr); +int netlbl_conn_setattr(struct sock *sk, + struct sockaddr *addr, + const struct netlbl_lsm_secattr *secattr); int netlbl_skbuff_setattr(struct sk_buff *skb, u16 family, const struct netlbl_lsm_secattr *secattr); @@ -449,11 +453,20 @@ static inline int netlbl_sock_setattr(struct sock *sk, { return -ENOSYS; } +static inline void netlbl_sock_delattr(struct sock *sk) +{ +} static inline int netlbl_sock_getattr(struct sock *sk, struct netlbl_lsm_secattr *secattr) { return -ENOSYS; } +static inline int netlbl_conn_setattr(struct sock *sk, + struct sockaddr *addr, + const struct netlbl_lsm_secattr *secattr) +{ + return -ENOSYS; +} static inline int netlbl_skbuff_setattr(struct sk_buff *skb, u16 family, const struct netlbl_lsm_secattr *secattr) diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index e13d6db..23768b9 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -1810,6 +1810,80 @@ socket_setattr_failure: } /** + * cipso_v4_sock_delattr - Delete the CIPSO option from a socket + * @sk: the socket + * + * Description: + * Removes the CIPSO option from a socket, if present. + * + */ +void cipso_v4_sock_delattr(struct sock *sk) +{ + u8 hdr_delta; + struct ip_options *opt; + struct inet_sock *sk_inet; + + sk_inet = inet_sk(sk); + opt = sk_inet->opt; + if (opt == NULL || opt->cipso == 0) + return; + + if (opt->srr || opt->rr || opt->ts || opt->router_alert) { + u8 cipso_len; + u8 cipso_off; + unsigned char *cipso_ptr; + int iter; + int optlen_new; + + cipso_off = opt->cipso - sizeof(struct iphdr); + cipso_ptr = &opt->__data[cipso_off]; + cipso_len = cipso_ptr[1]; + + if (opt->srr > opt->cipso) + opt->srr -= cipso_len; + if (opt->rr > opt->cipso) + opt->rr -= cipso_len; + if (opt->ts > opt->cipso) + opt->ts -= cipso_len; + if (opt->router_alert > opt->cipso) + opt->router_alert -= cipso_len; + opt->cipso = 0; + + memmove(cipso_ptr, cipso_ptr + cipso_len, + opt->optlen - cipso_off - cipso_len); + + /* determining the new total option length is tricky because of + * the padding necessary, the only thing i can think to do at + * this point is walk the options one-by-one, skipping the + * padding at the end to determine the actual option size and + * from there we can determine the new total option length */ + iter = 0; + optlen_new = 0; + while (iter < opt->optlen) + if (opt->__data[iter] != IPOPT_NOP) { + iter += opt->__data[iter + 1]; + optlen_new = iter; + } else + iter++; + hdr_delta = opt->optlen; + opt->optlen = (optlen_new + 3) & ~3; + hdr_delta -= opt->optlen; + } else { + /* only the cipso option was present on the socket so we can + * remove the entire option struct */ + sk_inet->opt = NULL; + hdr_delta = opt->optlen; + kfree(opt); + } + + if (sk_inet->is_icsk && hdr_delta > 0) { + struct inet_connection_sock *sk_conn = inet_csk(sk); + sk_conn->icsk_ext_hdr_len -= hdr_delta; + sk_conn->icsk_sync_mss(sk, sk_conn->icsk_pmtu_cookie); + } +} + +/** * cipso_v4_getattr - Helper function for the cipso_v4_*_getattr functions * @cipso: the CIPSO v4 option * @secattr: the security attributes diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c index cc8047d..78fc557 100644 --- a/net/netlabel/netlabel_kapi.c +++ b/net/netlabel/netlabel_kapi.c @@ -10,7 +10,7 @@ */ /* - * (c) Copyright Hewlett-Packard Development Company, L.P., 2006 + * (c) Copyright Hewlett-Packard Development Company, L.P., 2006, 2008 * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -456,6 +456,20 @@ socket_setattr_return: } /** + * netlbl_sock_delattr - Delete all the NetLabel labels on a socket + * @sk: the socket + * + * Description: + * Remove all the NetLabel labeling from @sk. The caller is responsible for + * ensuring that @sk is locked. + * + */ +void netlbl_sock_delattr(struct sock *sk) +{ + cipso_v4_sock_delattr(sk); +} + +/** * netlbl_sock_getattr - Determine the security attributes of a sock * @sk: the sock * @secattr: the security attributes @@ -473,6 +487,68 @@ int netlbl_sock_getattr(struct sock *sk, struct netlbl_lsm_secattr *secattr) } /** + * netlbl_conn_setattr - Label a connected socket using the correct protocol + * @sk: the socket to label + * @addr: the destination address + * @secattr: the security attributes + * + * Description: + * Attach the correct label to the given connected socket using the security + * attributes specified in @secattr. The caller is responsible for ensuring + * that @sk is locked. Returns zero on success, negative values on failure. + * + */ +int netlbl_conn_setattr(struct sock *sk, + struct sockaddr *addr, + const struct netlbl_lsm_secattr *secattr) +{ + int ret_val; + struct sockaddr_in *addr4; + struct netlbl_domaddr4_map *af4_entry; + + rcu_read_lock(); + switch (addr->sa_family) { + case AF_INET: + addr4 = (struct sockaddr_in *)addr; + af4_entry = netlbl_domhsh_getentry_af4(secattr->domain, + addr4->sin_addr.s_addr); + if (af4_entry == NULL) { + ret_val = -ENOENT; + goto conn_setattr_return; + } + switch (af4_entry->type) { + case NETLBL_NLTYPE_CIPSOV4: + ret_val = cipso_v4_sock_setattr(sk, + af4_entry->type_def.cipsov4, + secattr); + break; + case NETLBL_NLTYPE_UNLABELED: + /* just delete the protocols we support for right now + * but we could remove other protocols if needed */ + cipso_v4_sock_delattr(sk); + ret_val = 0; + break; + default: + ret_val = -ENOENT; + } + break; +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) + case AF_INET6: + /* since we don't support any IPv6 labeling protocols right + * now we can optimize everything away until we do */ + ret_val = 0; + break; +#endif /* IPv6 */ + default: + ret_val = 0; + } + +conn_setattr_return: + rcu_read_unlock(); + return ret_val; +} + +/** * netlbl_skbuff_setattr - Label a packet using the correct protocol * @skb: the packet * @family: protocol family diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 7432bdd..632ac3e 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -3794,6 +3794,7 @@ out: static int selinux_socket_connect(struct socket *sock, struct sockaddr *address, int addrlen) { + struct sock *sk = sock->sk; struct inode_security_struct *isec; int err; @@ -3807,7 +3808,6 @@ static int selinux_socket_connect(struct socket *sock, struct sockaddr *address, isec = SOCK_INODE(sock)->i_security; if (isec->sclass == SECCLASS_TCP_SOCKET || isec->sclass == SECCLASS_DCCP_SOCKET) { - struct sock *sk = sock->sk; struct avc_audit_data ad; struct sockaddr_in *addr4 = NULL; struct sockaddr_in6 *addr6 = NULL; @@ -3841,6 +3841,8 @@ static int selinux_socket_connect(struct socket *sock, struct sockaddr *address, goto out; } + err = selinux_netlbl_socket_connect(sk, address); + out: return err; } @@ -4290,8 +4292,6 @@ static void selinux_sock_graft(struct sock *sk, struct socket *parent) sk->sk_family == PF_UNIX) isec->sid = sksec->sid; sksec->sclass = isec->sclass; - - selinux_netlbl_sock_graft(sk, parent); } static int selinux_inet_conn_request(struct sock *sk, struct sk_buff *skb, @@ -4342,8 +4342,7 @@ static void selinux_inet_csk_clone(struct sock *newsk, selinux_netlbl_sk_security_reset(newsksec, req->rsk_ops->family); } -static void selinux_inet_conn_established(struct sock *sk, - struct sk_buff *skb) +static void selinux_inet_conn_established(struct sock *sk, struct sk_buff *skb) { u16 family = sk->sk_family; struct sk_security_struct *sksec = sk->sk_security; @@ -4353,6 +4352,8 @@ static void selinux_inet_conn_established(struct sock *sk, family = PF_INET; selinux_skb_peerlbl_sid(skb, family, &sksec->peer_sid); + + selinux_netlbl_inet_conn_established(sk, family); } static void selinux_req_classify_flow(const struct request_sock *req, diff --git a/security/selinux/include/netlabel.h b/security/selinux/include/netlabel.h index b3e6ae0..982bac0 100644 --- a/security/selinux/include/netlabel.h +++ b/security/selinux/include/netlabel.h @@ -52,7 +52,7 @@ int selinux_netlbl_skbuff_setsid(struct sk_buff *skb, u16 family, u32 sid); -void selinux_netlbl_sock_graft(struct sock *sk, struct socket *sock); +void selinux_netlbl_inet_conn_established(struct sock *sk, u16 family); int selinux_netlbl_socket_post_create(struct socket *sock); int selinux_netlbl_inode_permission(struct inode *inode, int mask); int selinux_netlbl_sock_rcv_skb(struct sk_security_struct *sksec, @@ -62,6 +62,8 @@ int selinux_netlbl_sock_rcv_skb(struct sk_security_struct *sksec, int selinux_netlbl_socket_setsockopt(struct socket *sock, int level, int optname); +int selinux_netlbl_socket_connect(struct sock *sk, struct sockaddr *addr); + #else static inline void selinux_netlbl_cache_invalidate(void) { @@ -98,8 +100,14 @@ static inline int selinux_netlbl_skbuff_setsid(struct sk_buff *skb, return 0; } -static inline void selinux_netlbl_sock_graft(struct sock *sk, - struct socket *sock) +static inline int selinux_netlbl_conn_setsid(struct sock *sk, + struct sockaddr *addr) +{ + return 0; +} + +static inline void selinux_netlbl_inet_conn_established(struct sock *sk, + u16 family) { return; } @@ -125,6 +133,11 @@ static inline int selinux_netlbl_socket_setsockopt(struct socket *sock, { return 0; } +static inline int selinux_netlbl_socket_connect(struct sock *sk, + struct sockaddr *addr) +{ + return 0; +} #endif /* CONFIG_NETLABEL */ #endif diff --git a/security/selinux/include/objsec.h b/security/selinux/include/objsec.h index f46dd1c..ad34787 100644 --- a/security/selinux/include/objsec.h +++ b/security/selinux/include/objsec.h @@ -118,6 +118,7 @@ struct sk_security_struct { NLBL_REQUIRE, NLBL_LABELED, NLBL_REQSKB, + NLBL_CONNLABELED, } nlbl_state; #endif }; diff --git a/security/selinux/netlabel.c b/security/selinux/netlabel.c index 090404d..b22b7da 100644 --- a/security/selinux/netlabel.c +++ b/security/selinux/netlabel.c @@ -29,10 +29,12 @@ #include #include +#include +#include #include #include -#include -#include +#include +#include #include "objsec.h" #include "security.h" @@ -79,8 +81,6 @@ static int selinux_netlbl_sock_setsid(struct sock *sk) int rc; struct sk_security_struct *sksec = sk->sk_security; struct netlbl_lsm_secattr secattr; - struct inet_sock *sk_inet; - struct inet_connection_sock *sk_conn; if (sksec->nlbl_state != NLBL_REQUIRE) return 0; @@ -96,20 +96,6 @@ static int selinux_netlbl_sock_setsid(struct sock *sk) sksec->nlbl_state = NLBL_LABELED; break; case -EDESTADDRREQ: - /* we are going to possibly end up labeling the individual - * packets later which is problematic for stream sockets - * because of the additional IP header size, our solution is to - * allow for the maximum IP header length (40 bytes for IPv4, - * we don't have to worry about IPv6 yet) just in case */ - sk_inet = inet_sk(sk); - if (sk_inet->is_icsk) { - sk_conn = inet_csk(sk); - if (sk_inet->opt) - sk_conn->icsk_ext_hdr_len -= - sk_inet->opt->optlen; - sk_conn->icsk_ext_hdr_len += 40; - sk_conn->icsk_sync_mss(sk, sk_conn->icsk_pmtu_cookie); - } sksec->nlbl_state = NLBL_REQSKB; rc = 0; break; @@ -247,21 +233,77 @@ skbuff_setsid_return: } /** - * selinux_netlbl_sock_graft - Netlabel the new socket + * selinux_netlbl_inet_conn_established - Netlabel the newly accepted connection * @sk: the new connection - * @sock: the new socket * * Description: - * The connection represented by @sk is being grafted onto @sock so set the - * socket's NetLabel to match the SID of @sk. + * A new connection has been established on @sk so make sure it is labeled + * correctly with the NetLabel susbsystem. * */ -void selinux_netlbl_sock_graft(struct sock *sk, struct socket *sock) +void selinux_netlbl_inet_conn_established(struct sock *sk, u16 family) { - /* Try to set the NetLabel on the socket to save time later, if we fail - * here we will pick up the pieces in later calls to - * selinux_netlbl_inode_permission(). */ - selinux_netlbl_sock_setsid(sk); + int rc; + struct sk_security_struct *sksec = sk->sk_security; + struct netlbl_lsm_secattr secattr; + struct inet_sock *sk_inet = inet_sk(sk); + struct sockaddr_in addr; + + if (sksec->nlbl_state != NLBL_REQUIRE) + return; + + netlbl_secattr_init(&secattr); + if (security_netlbl_sid_to_secattr(sksec->sid, &secattr) != 0) + goto inet_conn_established_return; + + rc = netlbl_sock_setattr(sk, &secattr); + switch (rc) { + case 0: + sksec->nlbl_state = NLBL_LABELED; + break; + case -EDESTADDRREQ: + /* no PF_INET6 support yet because we don't support any IPv6 + * labeling protocols */ + if (family != PF_INET) { + sksec->nlbl_state = NLBL_UNSET; + goto inet_conn_established_return; + } + + addr.sin_family = family; + addr.sin_addr.s_addr = sk_inet->daddr; + if (netlbl_conn_setattr(sk, (struct sockaddr *)&addr, + &secattr) != 0) { + /* we failed to label the connected socket (could be + * for a variety of reasons, the actual "why" isn't + * important here) so we have to go to our backup plan, + * labeling the packets individually in the netfilter + * local output hook. this is okay but we need to + * adjust the MSS of the connection to take into + * account any labeling overhead, since we don't know + * the exact overhead at this point we'll use the worst + * case value which is 40 bytes for IPv4 */ + struct inet_connection_sock *sk_conn = inet_csk(sk); + sk_conn->icsk_ext_hdr_len += 40 - + (sk_inet->opt ? sk_inet->opt->optlen : 0); + sk_conn->icsk_sync_mss(sk, sk_conn->icsk_pmtu_cookie); + + sksec->nlbl_state = NLBL_REQSKB; + } else + sksec->nlbl_state = NLBL_CONNLABELED; + break; + default: + /* note that we are failing to label the socket which could be + * a bad thing since it means traffic could leave the system + * without the desired labeling, however, all is not lost as + * we have a check in selinux_netlbl_inode_permission() to + * pick up the pieces that we might drop here because we can't + * return an error code */ + break; + } + +inet_conn_established_return: + netlbl_secattr_destroy(&secattr); + return; } /** @@ -398,7 +440,8 @@ int selinux_netlbl_socket_setsockopt(struct socket *sock, struct netlbl_lsm_secattr secattr; if (level == IPPROTO_IP && optname == IP_OPTIONS && - sksec->nlbl_state == NLBL_LABELED) { + (sksec->nlbl_state == NLBL_LABELED || + sksec->nlbl_state == NLBL_CONNLABELED)) { netlbl_secattr_init(&secattr); lock_sock(sk); rc = netlbl_sock_getattr(sk, &secattr); @@ -410,3 +453,51 @@ int selinux_netlbl_socket_setsockopt(struct socket *sock, return rc; } + +/** + * selinux_netlbl_socket_connect - Label a client-side socket on connect + * @sk: the socket to label + * @addr: the destination address + * + * Description: + * Attempt to label a connected socket with NetLabel using the given address. + * Returns zero values on success, negative values on failure. + * + */ +int selinux_netlbl_socket_connect(struct sock *sk, struct sockaddr *addr) +{ + int rc; + struct sk_security_struct *sksec = sk->sk_security; + struct netlbl_lsm_secattr secattr; + + if (sksec->nlbl_state != NLBL_REQSKB && + sksec->nlbl_state != NLBL_CONNLABELED) + return 0; + + netlbl_secattr_init(&secattr); + local_bh_disable(); + bh_lock_sock_nested(sk); + + /* connected sockets are allowed to disconnect when the address family + * is set to AF_UNSPEC, if that is what is happening we want to reset + * the socket */ + if (addr->sa_family == AF_UNSPEC) { + netlbl_sock_delattr(sk); + sksec->nlbl_state = NLBL_REQSKB; + rc = 0; + goto socket_connect_return; + } + rc = security_netlbl_sid_to_secattr(sksec->sid, &secattr); + if (rc != 0) + goto socket_connect_return; + rc = netlbl_conn_setattr(sk, addr, &secattr); + if (rc != 0) + goto socket_connect_return; + sksec->nlbl_state = NLBL_CONNLABELED; + +socket_connect_return: + bh_unlock_sock(sk); + local_bh_enable(); + netlbl_secattr_destroy(&secattr); + return rc; +}