/* License: GPL */ #include #include #include #include #include #include #include #include #include #include #include #include static const struct sock_diag_handler *sock_diag_handlers[AF_MAX]; static int (*inet_rcv_compat)(struct sk_buff *skb, struct nlmsghdr *nlh); static DEFINE_MUTEX(sock_diag_table_mutex); static struct workqueue_struct *broadcast_wq; static u64 sock_gen_cookie(struct sock *sk) { while (1) { u64 res = atomic64_read(&sk->sk_cookie); if (res) return res; res = atomic64_inc_return(&sock_net(sk)->cookie_gen); atomic64_cmpxchg(&sk->sk_cookie, 0, res); } } int sock_diag_check_cookie(struct sock *sk, const __u32 *cookie) { u64 res; if (cookie[0] == INET_DIAG_NOCOOKIE && cookie[1] == INET_DIAG_NOCOOKIE) return 0; res = sock_gen_cookie(sk); if ((u32)res != cookie[0] || (u32)(res >> 32) != cookie[1]) return -ESTALE; return 0; } EXPORT_SYMBOL_GPL(sock_diag_check_cookie); void sock_diag_save_cookie(struct sock *sk, __u32 *cookie) { u64 res = sock_gen_cookie(sk); cookie[0] = (u32)res; cookie[1] = (u32)(res >> 32); } EXPORT_SYMBOL_GPL(sock_diag_save_cookie); int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attrtype) { u32 mem[SK_MEMINFO_VARS]; mem[SK_MEMINFO_RMEM_ALLOC] = sk_rmem_alloc_get(sk); mem[SK_MEMINFO_RCVBUF] = sk->sk_rcvbuf; mem[SK_MEMINFO_WMEM_ALLOC] = sk_wmem_alloc_get(sk); mem[SK_MEMINFO_SNDBUF] = sk->sk_sndbuf; mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc; mem[SK_MEMINFO_WMEM_QUEUED] = sk->sk_wmem_queued; mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc); mem[SK_MEMINFO_BACKLOG] = sk->sk_backlog.len; mem[SK_MEMINFO_DROPS] = atomic_read(&sk->sk_drops); return nla_put(skb, attrtype, sizeof(mem), &mem); } EXPORT_SYMBOL_GPL(sock_diag_put_meminfo); int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk, struct sk_buff *skb, int attrtype) { struct sock_fprog_kern *fprog; struct sk_filter *filter; struct nlattr *attr; unsigned int flen; int err = 0; if (!may_report_filterinfo) { nla_reserve(skb, attrtype, 0); return 0; } rcu_read_lock(); filter = rcu_dereference(sk->sk_filter); if (!filter) goto out; fprog = filter->prog->orig_prog; if (!fprog) goto out; flen = bpf_classic_proglen(fprog); attr = nla_reserve(skb, attrtype, flen); if (attr == NULL) { err = -EMSGSIZE; goto out; } memcpy(nla_data(attr), fprog->filter, flen); out: rcu_read_unlock(); return err; } EXPORT_SYMBOL(sock_diag_put_filterinfo); struct broadcast_sk { struct sock *sk; struct work_struct work; }; static size_t sock_diag_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct inet_diag_msg) + nla_total_size(sizeof(u8)) /* INET_DIAG_PROTOCOL */ + nla_total_size_64bit(sizeof(struct tcp_info))); /* INET_DIAG_INFO */ } static void sock_diag_broadcast_destroy_work(struct work_struct *work) { struct broadcast_sk *bsk = container_of(work, struct broadcast_sk, work); struct sock *sk = bsk->sk; const struct sock_diag_handler *hndl; struct sk_buff *skb; const enum sknetlink_groups group = sock_diag_destroy_group(sk); int err = -1; WARN_ON(group == SKNLGRP_NONE); skb = nlmsg_new(sock_diag_nlmsg_size(), GFP_KERNEL); if (!skb) goto out; mutex_lock(&sock_diag_table_mutex); hndl = sock_diag_handlers[sk->sk_family]; if (hndl && hndl->get_info) err = hndl->get_info(skb, sk); mutex_unlock(&sock_diag_table_mutex); if (!err) nlmsg_multicast(sock_net(sk)->diag_nlsk, skb, 0, group, GFP_KERNEL); else kfree_skb(skb); out: sk_destruct(sk); kfree(bsk); } void sock_diag_broadcast_destroy(struct sock *sk) { /* Note, this function is often called from an interrupt context. */ struct broadcast_sk *bsk = kmalloc(sizeof(struct broadcast_sk), GFP_ATOMIC); if (!bsk) return sk_destruct(sk); bsk->sk = sk; INIT_WORK(&bsk->work, sock_diag_broadcast_destroy_work); queue_work(broadcast_wq, &bsk->work); } void sock_diag_register_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh)) { mutex_lock(&sock_diag_table_mutex); inet_rcv_compat = fn; mutex_unlock(&sock_diag_table_mutex); } EXPORT_SYMBOL_GPL(sock_diag_register_inet_compat); void sock_diag_unregister_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh)) { mutex_lock(&sock_diag_table_mutex); inet_rcv_compat = NULL; mutex_unlock(&sock_diag_table_mutex); } EXPORT_SYMBOL_GPL(sock_diag_unregister_inet_compat); int sock_diag_register(const struct sock_diag_handler *hndl) { int err = 0; if (hndl->family >= AF_MAX) return -EINVAL; mutex_lock(&sock_diag_table_mutex); if (sock_diag_handlers[hndl->family]) err = -EBUSY; else sock_diag_handlers[hndl->family] = hndl; mutex_unlock(&sock_diag_table_mutex); return err; } EXPORT_SYMBOL_GPL(sock_diag_register); void sock_diag_unregister(const struct sock_diag_handler *hnld) { int family = hnld->family; if (family >= AF_MAX) return; mutex_lock(&sock_diag_table_mutex); BUG_ON(sock_diag_handlers[family] != hnld); sock_diag_handlers[family] = NULL; mutex_unlock(&sock_diag_table_mutex); } EXPORT_SYMBOL_GPL(sock_diag_unregister); static int __sock_diag_cmd(struct sk_buff *skb, struct nlmsghdr *nlh) { int err; struct sock_diag_req *req = nlmsg_data(nlh); const struct sock_diag_handler *hndl; if (nlmsg_len(nlh) < sizeof(*req)) return -EINVAL; if (req->sdiag_family >= AF_MAX) return -EINVAL; if (sock_diag_handlers[req->sdiag_family] == NULL) request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, NETLINK_SOCK_DIAG, req->sdiag_family); mutex_lock(&sock_diag_table_mutex); hndl = sock_diag_handlers[req->sdiag_family]; if (hndl == NULL) err = -ENOENT; else if (nlh->nlmsg_type == SOCK_DIAG_BY_FAMILY) err = hndl->dump(skb, nlh); else if (nlh->nlmsg_type == SOCK_DESTROY && hndl->destroy) err = hndl->destroy(skb, nlh); else err = -EOPNOTSUPP; mutex_unlock(&sock_diag_table_mutex); return err; } static int sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) { int ret; switch (nlh->nlmsg_type) { case TCPDIAG_GETSOCK: case DCCPDIAG_GETSOCK: if (inet_rcv_compat == NULL) request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, NETLINK_SOCK_DIAG, AF_INET); mutex_lock(&sock_diag_table_mutex); if (inet_rcv_compat != NULL) ret = inet_rcv_compat(skb, nlh); else ret = -EOPNOTSUPP; mutex_unlock(&sock_diag_table_mutex); return ret; case SOCK_DIAG_BY_FAMILY: case SOCK_DESTROY: return __sock_diag_cmd(skb, nlh); default: return -EINVAL; } } static DEFINE_MUTEX(sock_diag_mutex); static void sock_diag_rcv(struct sk_buff *skb) { mutex_lock(&sock_diag_mutex); netlink_rcv_skb(skb, &sock_diag_rcv_msg); mutex_unlock(&sock_diag_mutex); } static int sock_diag_bind(struct net *net, int group) { switch (group) { case SKNLGRP_INET_TCP_DESTROY: case SKNLGRP_INET_UDP_DESTROY: if (!sock_diag_handlers[AF_INET]) request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, NETLINK_SOCK_DIAG, AF_INET); break; case SKNLGRP_INET6_TCP_DESTROY: case SKNLGRP_INET6_UDP_DESTROY: if (!sock_diag_handlers[AF_INET6]) request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, NETLINK_SOCK_DIAG, AF_INET); break; } return 0; } int sock_diag_destroy(struct sock *sk, int err) { if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) return -EPERM; if (!sk->sk_prot->diag_destroy) return -EOPNOTSUPP; return sk->sk_prot->diag_destroy(sk, err); } EXPORT_SYMBOL_GPL(sock_diag_destroy); static int __net_init diag_net_init(struct net *net) { struct netlink_kernel_cfg cfg = { .groups = SKNLGRP_MAX, .input = sock_diag_rcv, .bind = sock_diag_bind, .flags = NL_CFG_F_NONROOT_RECV, }; net->diag_nlsk = netlink_kernel_create(net, NETLINK_SOCK_DIAG, &cfg); return net->diag_nlsk == NULL ? -ENOMEM : 0; } static void __net_exit diag_net_exit(struct net *net) { netlink_kernel_release(net->diag_nlsk); net->diag_nlsk = NULL; } static struct pernet_operations diag_net_ops = { .init = diag_net_init, .exit = diag_net_exit, }; static int __init sock_diag_init(void) { broadcast_wq = alloc_workqueue("sock_diag_events", 0, 0); BUG_ON(!broadcast_wq); return register_pernet_subsys(&diag_net_ops); } device_initcall(sock_diag_init); 2017-02-10sched: move err set right before goto errout in tc_ctl_tfilterJiri Pirko1-10/+19 This makes the reader to know right away what is the error value. Signed-off-by: Jiri Pirko <jiri@mellanox.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-10sched: push TC filter protocol creation into a separate functionJiri Pirko1-51/+59 Make the long function tc_ctl_tfilter a little bit shorter and easier to read. Also make the creation of filter proto symmetric to destruction. Signed-off-by: Jiri Pirko <jiri@mellanox.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-10sched: move tcf_proto_destroy and tcf_destroy_chain helpers into cls_apiJiri Pirko13-24/+32 Creation is done in this file, move destruction to be at the same place. Signed-off-by: Jiri Pirko <jiri@mellanox.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-10sched: rename tcf_destroy to tcf_destroy_protoJiri Pirko2-6/+6 This function destroys TC filter protocol, not TC filter. So name it accordingly. Signed-off-by: Jiri Pirko <jiri@mellanox.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-07net/sched: act_mirred: remove duplicated include from act_mirred.cWei Yongjun1-2/+0 Remove duplicated include. Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com> Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-03Merge git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf-nextDavid S. Miller1-1/+1 Pablo Neira Ayuso says: ==================== Netfilter updates for net-next The following patchset contains Netfilter updates for your net-next tree, they are: 1) Stash ctinfo 3-bit field into pointer to nf_conntrack object from sk_buff so we only access one single cacheline in the conntrack hotpath. Patchset from Florian Westphal. 2) Don't leak pointer to internal structures when exporting x_tables ruleset back to userspace, from Willem DeBruijn. This includes new helper functions to copy data to userspace such as xt_data_to_user() as well as conversions of our ip_tables, ip6_tables and arp_tables clients to use it. Not surprinsingly, ebtables requires an ad-hoc update. There is also a new field in x_tables extensions to indicate the amount of bytes that we copy to userspace. 3) Add nf_log_all_netns sysctl: This new knob allows you to enable logging via nf_log infrastructure for all existing netnamespaces. Given the effort to provide pernet syslog has been discontinued, let's provide a way to restore logging using netfilter kernel logging facilities in trusted environments. Patch from Michal Kubecek. 4) Validate SCTP checksum from conntrack helper, from Davide Caratti. 5) Merge UDPlite conntrack and NAT helpers into UDP, this was mostly a copy&paste from the original helper, from Florian Westphal. 6) Reset netfilter state when duplicating packets, also from Florian. 7) Remove unnecessary check for broadcast in IPv6 in pkttype match and nft_meta, from Liping Zhang. 8) Add missing code to deal with loopback packets from nft_meta when used by the netdev family, also from Liping. 9) Several cleanups on nf_tables, one to remove unnecessary check from the netlink control plane path to add table, set and stateful objects and code consolidation when unregister chain hooks, from Gao Feng. 10) Fix harmless reference counter underflow in IPVS that, however, results in problems with the introduction of the new refcount_t type, from David Windsor. 11) Enable LIBCRC32C from nf_ct_sctp instead of nf_nat_sctp, from Davide Caratti. 12) Missing documentation on nf_tables uapi header, from Liping Zhang. 13) Use rb_entry() helper in xt_connlimit, from Geliang Tang. ==================== Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-03sched: cls_flower: expose priority to offloading netdeviceJiri Pirko1-0/+3 The driver that offloads flower rules needs to know with which priority user inserted the rules. So add this information into offload struct. Signed-off-by: Jiri Pirko <jiri@mellanox.com> Acked-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-03net/sched: act_ife: Change to use ife moduleYotam Gigi2-78/+33 Use the encode/decode functionality from the ife module instead of using implementation inside the act_ife. Reviewed-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: Yotam Gigi <yotamg@mellanox.com> Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Roman Mashak <mrv@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-03net/sched: act_ife: Unexport ife_tlv_meta_encodeYotam Gigi1-2/+2 As the function ife_tlv_meta_encode is not used by any other module, unexport it and make it static for the act_ife module. Signed-off-by: Yotam Gigi <yotamg@mellanox.com> Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Roman Mashak <mrv@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-02Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/netDavid S. Miller2-85/+48 All merge conflicts were simple overlapping changes. Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-02skbuff: add and use skb_nfct helperFlorian Westphal1-1/+1 Followup patch renames skb->nfct and changes its type so add a helper to avoid intrusive rename change later. Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>