From 78541c1dc60b65ecfce5a6a096fc260219d6784e Mon Sep 17 00:00:00 2001 From: Andrew Lutomirski Date: Wed, 16 Apr 2014 21:41:34 -0700 Subject: net: Fix ns_capable check in sock_diag_put_filterinfo The caller needs capabilities on the namespace being queried, not on their own namespace. This is a security bug, although it likely has only a minor impact. Cc: stable@vger.kernel.org Signed-off-by: Andy Lutomirski Acked-by: Nicolas Dichtel Signed-off-by: David S. Miller --- net/core/sock_diag.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/core') diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index d7af18859322..9deb6abd6cf6 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -49,7 +49,7 @@ int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attrtype) } EXPORT_SYMBOL_GPL(sock_diag_put_meminfo); -int sock_diag_put_filterinfo(struct user_namespace *user_ns, struct sock *sk, +int sock_diag_put_filterinfo(struct sock *sk, struct sk_buff *skb, int attrtype) { struct sock_fprog_kern *fprog; @@ -58,7 +58,7 @@ int sock_diag_put_filterinfo(struct user_namespace *user_ns, struct sock *sk, unsigned int flen; int err = 0; - if (!ns_capable(user_ns, CAP_NET_ADMIN)) { + if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) { nla_reserve(skb, attrtype, 0); return 0; } -- cgit v1.2.3 From 83d5b7ef99c9f05e87333b334a638de1264ab8e4 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 22 Apr 2014 20:18:57 -0700 Subject: net: filter: initialize A and X registers exisiting BPF verifier allows uninitialized access to registers, 'ret A' is considered to be a valid filter. So initialize A and X to zero to prevent leaking kernel memory In the future BPF verifier will be rejecting such filters Signed-off-by: Alexei Starovoitov Cc: Daniel Borkmann Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- net/core/filter.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) (limited to 'net/core') diff --git a/net/core/filter.c b/net/core/filter.c index cd58614660cf..9d79ca0a6e8e 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -122,6 +122,13 @@ noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) return 0; } +/* Register mappings for user programs. */ +#define A_REG 0 +#define X_REG 7 +#define TMP_REG 8 +#define ARG2_REG 2 +#define ARG3_REG 3 + /** * __sk_run_filter - run a filter on a given context * @ctx: buffer to run the filter on @@ -242,6 +249,8 @@ unsigned int __sk_run_filter(void *ctx, const struct sock_filter_int *insn) regs[FP_REG] = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; regs[ARG1_REG] = (u64) (unsigned long) ctx; + regs[A_REG] = 0; + regs[X_REG] = 0; select_insn: goto *jumptable[insn->code]; @@ -643,13 +652,6 @@ static u64 __get_raw_cpu_id(u64 ctx, u64 A, u64 X, u64 r4, u64 r5) return raw_smp_processor_id(); } -/* Register mappings for user programs. */ -#define A_REG 0 -#define X_REG 7 -#define TMP_REG 8 -#define ARG2_REG 2 -#define ARG3_REG 3 - static bool convert_bpf_extensions(struct sock_filter *fp, struct sock_filter_int **insnp) { -- cgit v1.2.3 From a53b72c83a4216f2eb883ed45a0cbce014b8e62d Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 23 Apr 2014 14:26:25 -0700 Subject: net: Move the permission check in sock_diag_put_filterinfo to packet_diag_dump The permission check in sock_diag_put_filterinfo is wrong, and it is so removed from it's sources it is not clear why it is wrong. Move the computation into packet_diag_dump and pass a bool of the result into sock_diag_filterinfo. This does not yet correct the capability check but instead simply moves it to make it clear what is going on. Reported-by: Andy Lutomirski Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- net/core/sock_diag.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/core') diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index 9deb6abd6cf6..a4216a4c9572 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -49,7 +49,7 @@ int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attrtype) } EXPORT_SYMBOL_GPL(sock_diag_put_meminfo); -int sock_diag_put_filterinfo(struct sock *sk, +int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk, struct sk_buff *skb, int attrtype) { struct sock_fprog_kern *fprog; @@ -58,7 +58,7 @@ int sock_diag_put_filterinfo(struct sock *sk, unsigned int flen; int err = 0; - if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) { + if (!may_report_filterinfo) { nla_reserve(skb, attrtype, 0); return 0; } -- cgit v1.2.3 From a3b299da869d6e78cf42ae0b1b41797bcb8c5e4b Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 23 Apr 2014 14:26:56 -0700 Subject: net: Add variants of capable for use on on sockets sk_net_capable - The common case, operations that are safe in a network namespace. sk_capable - Operations that are not known to be safe in a network namespace sk_ns_capable - The general case for special cases. Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- net/core/sock.c | 49 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 49 insertions(+) (limited to 'net/core') diff --git a/net/core/sock.c b/net/core/sock.c index b4fff008136f..664ee4295b6f 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -145,6 +145,55 @@ static DEFINE_MUTEX(proto_list_mutex); static LIST_HEAD(proto_list); +/** + * sk_ns_capable - General socket capability test + * @sk: Socket to use a capability on or through + * @user_ns: The user namespace of the capability to use + * @cap: The capability to use + * + * Test to see if the opener of the socket had when the socket was + * created and the current process has the capability @cap in the user + * namespace @user_ns. + */ +bool sk_ns_capable(const struct sock *sk, + struct user_namespace *user_ns, int cap) +{ + return file_ns_capable(sk->sk_socket->file, user_ns, cap) && + ns_capable(user_ns, cap); +} +EXPORT_SYMBOL(sk_ns_capable); + +/** + * sk_capable - Socket global capability test + * @sk: Socket to use a capability on or through + * @cap: The global capbility to use + * + * Test to see if the opener of the socket had when the socket was + * created and the current process has the capability @cap in all user + * namespaces. + */ +bool sk_capable(const struct sock *sk, int cap) +{ + return sk_ns_capable(sk, &init_user_ns, cap); +} +EXPORT_SYMBOL(sk_capable); + +/** + * sk_net_capable - Network namespace socket capability test + * @sk: Socket to use a capability on or through + * @cap: The capability to use + * + * Test to see if the opener of the socket had when the socke was created + * and the current process has the capability @cap over the network namespace + * the socket is a member of. + */ +bool sk_net_capable(const struct sock *sk, int cap) +{ + return sk_ns_capable(sk, sock_net(sk)->user_ns, cap); +} +EXPORT_SYMBOL(sk_net_capable); + + #ifdef CONFIG_MEMCG_KMEM int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss) { -- cgit v1.2.3 From 90f62cf30a78721641e08737bda787552428061e Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 23 Apr 2014 14:29:27 -0700 Subject: net: Use netlink_ns_capable to verify the permisions of netlink messages It is possible by passing a netlink socket to a more privileged executable and then to fool that executable into writing to the socket data that happens to be valid netlink message to do something that privileged executable did not intend to do. To keep this from happening replace bare capable and ns_capable calls with netlink_capable, netlink_net_calls and netlink_ns_capable calls. Which act the same as the previous calls except they verify that the opener of the socket had the desired permissions as well. Reported-by: Andy Lutomirski Signed-off-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) (limited to 'net/core') diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index d4ff41739b0f..64ad17d077ed 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1395,7 +1395,8 @@ static int do_set_master(struct net_device *dev, int ifindex) return 0; } -static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, +static int do_setlink(const struct sk_buff *skb, + struct net_device *dev, struct ifinfomsg *ifm, struct nlattr **tb, char *ifname, int modified) { const struct net_device_ops *ops = dev->netdev_ops; @@ -1407,7 +1408,7 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, err = PTR_ERR(net); goto errout; } - if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) { + if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) { err = -EPERM; goto errout; } @@ -1661,7 +1662,7 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh) if (err < 0) goto errout; - err = do_setlink(dev, ifm, tb, ifname, 0); + err = do_setlink(skb, dev, ifm, tb, ifname, 0); errout: return err; } @@ -1778,7 +1779,8 @@ err: } EXPORT_SYMBOL(rtnl_create_link); -static int rtnl_group_changelink(struct net *net, int group, +static int rtnl_group_changelink(const struct sk_buff *skb, + struct net *net, int group, struct ifinfomsg *ifm, struct nlattr **tb) { @@ -1787,7 +1789,7 @@ static int rtnl_group_changelink(struct net *net, int group, for_each_netdev(net, dev) { if (dev->group == group) { - err = do_setlink(dev, ifm, tb, NULL, 0); + err = do_setlink(skb, dev, ifm, tb, NULL, 0); if (err < 0) return err; } @@ -1929,12 +1931,12 @@ replay: modified = 1; } - return do_setlink(dev, ifm, tb, ifname, modified); + return do_setlink(skb, dev, ifm, tb, ifname, modified); } if (!(nlh->nlmsg_flags & NLM_F_CREATE)) { if (ifm->ifi_index == 0 && tb[IFLA_GROUP]) - return rtnl_group_changelink(net, + return rtnl_group_changelink(skb, net, nla_get_u32(tb[IFLA_GROUP]), ifm, tb); return -ENODEV; @@ -2321,7 +2323,7 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh) int err = -EINVAL; __u8 *addr; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL); @@ -2773,7 +2775,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) sz_idx = type>>2; kind = type&3; - if (kind != 2 && !ns_capable(net->user_ns, CAP_NET_ADMIN)) + if (kind != 2 && !netlink_net_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (kind == 2 && nlh->nlmsg_flags&NLM_F_DUMP) { -- cgit v1.2.3 From 973462bbde79bb827824c73b59027a0aed5c9ca6 Mon Sep 17 00:00:00 2001 From: David Gibson Date: Thu, 24 Apr 2014 10:22:35 +1000 Subject: rtnetlink: Warn when interface's information won't fit in our packet Without IFLA_EXT_MASK specified, the information reported for a single interface in response to RTM_GETLINK is expected to fit within a netlink packet of NLMSG_GOODSIZE. If it doesn't, however, things will go badly wrong, When listing all interfaces, netlink_dump() will incorrectly treat -EMSGSIZE on the first message in a packet as the end of the listing and omit information for that interface and all subsequent ones. This can cause getifaddrs(3) to enter an infinite loop. This patch won't fix the problem, but it will WARN_ON() making it easier to track down what's going wrong. Signed-off-by: David Gibson Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) (limited to 'net/core') diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 64ad17d077ed..8db72ac88feb 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1198,6 +1198,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) struct hlist_head *head; struct nlattr *tb[IFLA_MAX+1]; u32 ext_filter_mask = 0; + int err; s_h = cb->args[0]; s_idx = cb->args[1]; @@ -1218,11 +1219,17 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; - if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, 0, - NLM_F_MULTI, - ext_filter_mask) <= 0) + err = rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, 0, + NLM_F_MULTI, + ext_filter_mask); + /* If we ran out of room on the first message, + * we're in trouble + */ + WARN_ON((err == -EMSGSIZE) && (skb->len == 0)); + + if (err <= 0) goto out; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); -- cgit v1.2.3 From c53864fd60227de025cb79e05493b13f69843971 Mon Sep 17 00:00:00 2001 From: David Gibson Date: Thu, 24 Apr 2014 10:22:36 +1000 Subject: rtnetlink: Only supply IFLA_VF_PORTS information when RTEXT_FILTER_VF is set Since 115c9b81928360d769a76c632bae62d15206a94a (rtnetlink: Fix problem with buffer allocation), RTM_NEWLINK messages only contain the IFLA_VFINFO_LIST attribute if they were solicited by a GETLINK message containing an IFLA_EXT_MASK attribute with the RTEXT_FILTER_VF flag. That was done because some user programs broke when they received more data than expected - because IFLA_VFINFO_LIST contains information for each VF it can become large if there are many VFs. However, the IFLA_VF_PORTS attribute, supplied for devices which implement ndo_get_vf_port (currently the 'enic' driver only), has the same problem. It supplies per-VF information and can therefore become large, but it is not currently conditional on the IFLA_EXT_MASK value. Worse, it interacts badly with the existing EXT_MASK handling. When IFLA_EXT_MASK is not supplied, the buffer for netlink replies is fixed at NLMSG_GOODSIZE. If the information for IFLA_VF_PORTS exceeds this, then rtnl_fill_ifinfo() returns -EMSGSIZE on the first message in a packet. netlink_dump() will misinterpret this as having finished the listing and omit data for this interface and all subsequent ones. That can cause getifaddrs(3) to enter an infinite loop. This patch addresses the problem by only supplying IFLA_VF_PORTS when IFLA_EXT_MASK is supplied with the RTEXT_FILTER_VF flag set. Signed-off-by: David Gibson Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) (limited to 'net/core') diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 8db72ac88feb..9837bebf93ce 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -774,7 +774,8 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev, return 0; } -static size_t rtnl_port_size(const struct net_device *dev) +static size_t rtnl_port_size(const struct net_device *dev, + u32 ext_filter_mask) { size_t port_size = nla_total_size(4) /* PORT_VF */ + nla_total_size(PORT_PROFILE_MAX) /* PORT_PROFILE */ @@ -790,7 +791,8 @@ static size_t rtnl_port_size(const struct net_device *dev) size_t port_self_size = nla_total_size(sizeof(struct nlattr)) + port_size; - if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent) + if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent || + !(ext_filter_mask & RTEXT_FILTER_VF)) return 0; if (dev_num_vf(dev->dev.parent)) return port_self_size + vf_ports_size + @@ -826,7 +828,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(ext_filter_mask & RTEXT_FILTER_VF ? 4 : 0) /* IFLA_NUM_VF */ + rtnl_vfinfo_size(dev, ext_filter_mask) /* IFLA_VFINFO_LIST */ - + rtnl_port_size(dev) /* IFLA_VF_PORTS + IFLA_PORT_SELF */ + + rtnl_port_size(dev, ext_filter_mask) /* IFLA_VF_PORTS + IFLA_PORT_SELF */ + rtnl_link_get_size(dev) /* IFLA_LINKINFO */ + rtnl_link_get_af_size(dev) /* IFLA_AF_SPEC */ + nla_total_size(MAX_PHYS_PORT_ID_LEN); /* IFLA_PHYS_PORT_ID */ @@ -888,11 +890,13 @@ static int rtnl_port_self_fill(struct sk_buff *skb, struct net_device *dev) return 0; } -static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev) +static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev, + u32 ext_filter_mask) { int err; - if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent) + if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent || + !(ext_filter_mask & RTEXT_FILTER_VF)) return 0; err = rtnl_port_self_fill(skb, dev); @@ -1079,7 +1083,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, nla_nest_end(skb, vfinfo); } - if (rtnl_port_fill(skb, dev)) + if (rtnl_port_fill(skb, dev, ext_filter_mask)) goto nla_put_failure; if (dev->rtnl_link_ops || rtnl_have_link_slave_info(dev)) { -- cgit v1.2.3