diff options
Diffstat (limited to 'net/ipv4')
62 files changed, 2207 insertions, 1027 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 57737b8..7d12c6a 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -174,12 +174,12 @@ static int inet_autobind(struct sock *sk) /* We may need to bind the socket. */ lock_sock(sk); inet = inet_sk(sk); - if (!inet->num) { + if (!inet->inet_num) { if (sk->sk_prot->get_port(sk, 0)) { release_sock(sk); return -EAGAIN; } - inet->sport = htons(inet->num); + inet->inet_sport = htons(inet->inet_num); } release_sock(sk); return 0; @@ -262,7 +262,8 @@ static inline int inet_netns_ok(struct net *net, int protocol) * Create an inet socket. */ -static int inet_create(struct net *net, struct socket *sock, int protocol) +static int inet_create(struct net *net, struct socket *sock, int protocol, + int kern) { struct sock *sk; struct inet_protosw *answer; @@ -325,7 +326,7 @@ lookup_protocol: } err = -EPERM; - if (answer->capability > 0 && !capable(answer->capability)) + if (sock->type == SOCK_RAW && !kern && !capable(CAP_NET_RAW)) goto out_rcu_unlock; err = -EAFNOSUPPORT; @@ -354,7 +355,7 @@ lookup_protocol: inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) != 0; if (SOCK_RAW == sock->type) { - inet->num = protocol; + inet->inet_num = protocol; if (IPPROTO_RAW == protocol) inet->hdrincl = 1; } @@ -364,7 +365,7 @@ lookup_protocol: else inet->pmtudisc = IP_PMTUDISC_WANT; - inet->id = 0; + inet->inet_id = 0; sock_init_data(sock, sk); @@ -381,13 +382,13 @@ lookup_protocol: sk_refcnt_debug_inc(sk); - if (inet->num) { + if (inet->inet_num) { /* It assumes that any protocol which allows * the user to assign a number at socket * creation time automatically * shares. */ - inet->sport = htons(inet->num); + inet->inet_sport = htons(inet->inet_num); /* Add to protocol hash chains. */ sk->sk_prot->hash(sk); } @@ -494,27 +495,27 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) /* Check these errors (active socket, double bind). */ err = -EINVAL; - if (sk->sk_state != TCP_CLOSE || inet->num) + if (sk->sk_state != TCP_CLOSE || inet->inet_num) goto out_release_sock; - inet->rcv_saddr = inet->saddr = addr->sin_addr.s_addr; + inet->inet_rcv_saddr = inet->inet_saddr = addr->sin_addr.s_addr; if (chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST) - inet->saddr = 0; /* Use device */ + inet->inet_saddr = 0; /* Use device */ /* Make sure we are allowed to bind here. */ if (sk->sk_prot->get_port(sk, snum)) { - inet->saddr = inet->rcv_saddr = 0; + inet->inet_saddr = inet->inet_rcv_saddr = 0; err = -EADDRINUSE; goto out_release_sock; } - if (inet->rcv_saddr) + if (inet->inet_rcv_saddr) sk->sk_userlocks |= SOCK_BINDADDR_LOCK; if (snum) sk->sk_userlocks |= SOCK_BINDPORT_LOCK; - inet->sport = htons(inet->num); - inet->daddr = 0; - inet->dport = 0; + inet->inet_sport = htons(inet->inet_num); + inet->inet_daddr = 0; + inet->inet_dport = 0; sk_dst_reset(sk); err = 0; out_release_sock: @@ -532,7 +533,7 @@ int inet_dgram_connect(struct socket *sock, struct sockaddr * uaddr, if (uaddr->sa_family == AF_UNSPEC) return sk->sk_prot->disconnect(sk, flags); - if (!inet_sk(sk)->num && inet_autobind(sk)) + if (!inet_sk(sk)->inet_num && inet_autobind(sk)) return -EAGAIN; return sk->sk_prot->connect(sk, (struct sockaddr *)uaddr, addr_len); } @@ -685,21 +686,21 @@ int inet_getname(struct socket *sock, struct sockaddr *uaddr, { struct sock *sk = sock->sk; struct inet_sock *inet = inet_sk(sk); - struct sockaddr_in *sin = (struct sockaddr_in *)uaddr; + DECLARE_SOCKADDR(struct sockaddr_in *, sin, uaddr); sin->sin_family = AF_INET; if (peer) { - if (!inet->dport || + if (!inet->inet_dport || (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_SYN_SENT)) && peer == 1)) return -ENOTCONN; - sin->sin_port = inet->dport; - sin->sin_addr.s_addr = inet->daddr; + sin->sin_port = inet->inet_dport; + sin->sin_addr.s_addr = inet->inet_daddr; } else { - __be32 addr = inet->rcv_saddr; + __be32 addr = inet->inet_rcv_saddr; if (!addr) - addr = inet->saddr; - sin->sin_port = inet->sport; + addr = inet->inet_saddr; + sin->sin_port = inet->inet_sport; sin->sin_addr.s_addr = addr; } memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); @@ -714,7 +715,7 @@ int inet_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, struct sock *sk = sock->sk; /* We may need to bind the socket. */ - if (!inet_sk(sk)->num && inet_autobind(sk)) + if (!inet_sk(sk)->inet_num && inet_autobind(sk)) return -EAGAIN; return sk->sk_prot->sendmsg(iocb, sk, msg, size); @@ -728,7 +729,7 @@ static ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset, struct sock *sk = sock->sk; /* We may need to bind the socket. */ - if (!inet_sk(sk)->num && inet_autobind(sk)) + if (!inet_sk(sk)->inet_num && inet_autobind(sk)) return -EAGAIN; if (sk->sk_prot->sendpage) @@ -931,7 +932,7 @@ static const struct proto_ops inet_sockraw_ops = { #endif }; -static struct net_proto_family inet_family_ops = { +static const struct net_proto_family inet_family_ops = { .family = PF_INET, .create = inet_create, .owner = THIS_MODULE, @@ -947,7 +948,6 @@ static struct inet_protosw inetsw_array[] = .protocol = IPPROTO_TCP, .prot = &tcp_prot, .ops = &inet_stream_ops, - .capability = -1, .no_check = 0, .flags = INET_PROTOSW_PERMANENT | INET_PROTOSW_ICSK, @@ -958,7 +958,6 @@ static struct inet_protosw inetsw_array[] = .protocol = IPPROTO_UDP, .prot = &udp_prot, .ops = &inet_dgram_ops, - .capability = -1, .no_check = UDP_CSUM_DEFAULT, .flags = INET_PROTOSW_PERMANENT, }, @@ -969,7 +968,6 @@ static struct inet_protosw inetsw_array[] = .protocol = IPPROTO_IP, /* wild card */ .prot = &raw_prot, .ops = &inet_sockraw_ops, - .capability = CAP_NET_RAW, .no_check = UDP_CSUM_DEFAULT, .flags = INET_PROTOSW_REUSE, } @@ -1059,9 +1057,9 @@ static int inet_sk_reselect_saddr(struct sock *sk) struct inet_sock *inet = inet_sk(sk); int err; struct rtable *rt; - __be32 old_saddr = inet->saddr; + __be32 old_saddr = inet->inet_saddr; __be32 new_saddr; - __be32 daddr = inet->daddr; + __be32 daddr = inet->inet_daddr; if (inet->opt && inet->opt->srr) daddr = inet->opt->faddr; @@ -1071,7 +1069,7 @@ static int inet_sk_reselect_saddr(struct sock *sk) RT_CONN_FLAGS(sk), sk->sk_bound_dev_if, sk->sk_protocol, - inet->sport, inet->dport, sk, 0); + inet->inet_sport, inet->inet_dport, sk, 0); if (err) return err; @@ -1087,7 +1085,7 @@ static int inet_sk_reselect_saddr(struct sock *sk) __func__, &old_saddr, &new_saddr); } - inet->saddr = inet->rcv_saddr = new_saddr; + inet->inet_saddr = inet->inet_rcv_saddr = new_saddr; /* * XXX The only one ugly spot where we need to @@ -1113,7 +1111,7 @@ int inet_sk_rebuild_header(struct sock *sk) return 0; /* Reroute. */ - daddr = inet->daddr; + daddr = inet->inet_daddr; if (inet->opt && inet->opt->srr) daddr = inet->opt->faddr; { @@ -1123,7 +1121,7 @@ int inet_sk_rebuild_header(struct sock *sk) .nl_u = { .ip4_u = { .daddr = daddr, - .saddr = inet->saddr, + .saddr = inet->inet_saddr, .tos = RT_CONN_FLAGS(sk), }, }, @@ -1131,8 +1129,8 @@ int inet_sk_rebuild_header(struct sock *sk) .flags = inet_sk_flowi_flags(sk), .uli_u = { .ports = { - .sport = inet->sport, - .dport = inet->dport, + .sport = inet->inet_sport, + .dport = inet->inet_dport, }, }, }; diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index 5c66270..7ed3e4a 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -1,3 +1,4 @@ +#include <crypto/hash.h> #include <linux/err.h> #include <linux/module.h> #include <net/ip.h> @@ -5,10 +6,67 @@ #include <net/ah.h> #include <linux/crypto.h> #include <linux/pfkeyv2.h> -#include <linux/spinlock.h> +#include <linux/scatterlist.h> #include <net/icmp.h> #include <net/protocol.h> +struct ah_skb_cb { + struct xfrm_skb_cb xfrm; + void *tmp; +}; + +#define AH_SKB_CB(__skb) ((struct ah_skb_cb *)&((__skb)->cb[0])) + +static void *ah_alloc_tmp(struct crypto_ahash *ahash, int nfrags, + unsigned int size) +{ + unsigned int len; + + len = size + crypto_ahash_digestsize(ahash) + + (crypto_ahash_alignmask(ahash) & + ~(crypto_tfm_ctx_alignment() - 1)); + + len = ALIGN(len, crypto_tfm_ctx_alignment()); + + len += sizeof(struct ahash_request) + crypto_ahash_reqsize(ahash); + len = ALIGN(len, __alignof__(struct scatterlist)); + + len += sizeof(struct scatterlist) * nfrags; + + return kmalloc(len, GFP_ATOMIC); +} + +static inline u8 *ah_tmp_auth(void *tmp, unsigned int offset) +{ + return tmp + offset; +} + +static inline u8 *ah_tmp_icv(struct crypto_ahash *ahash, void *tmp, + unsigned int offset) +{ + return PTR_ALIGN((u8 *)tmp + offset, crypto_ahash_alignmask(ahash) + 1); +} + +static inline struct ahash_request *ah_tmp_req(struct crypto_ahash *ahash, + u8 *icv) +{ + struct ahash_request *req; + + req = (void *)PTR_ALIGN(icv + crypto_ahash_digestsize(ahash), + crypto_tfm_ctx_alignment()); + + ahash_request_set_tfm(req, ahash); + + return req; +} + +static inline struct scatterlist *ah_req_sg(struct crypto_ahash *ahash, + struct ahash_request *req) +{ + return (void *)ALIGN((unsigned long)(req + 1) + + crypto_ahash_reqsize(ahash), + __alignof__(struct scatterlist)); +} /* Clear mutable options and find final destination to substitute * into IP header for icv calculation. Options are already checked @@ -54,20 +112,72 @@ static int ip_clear_mutable_options(struct iphdr *iph, __be32 *daddr) return 0; } +static void ah_output_done(struct crypto_async_request *base, int err) +{ + u8 *icv; + struct iphdr *iph; + struct sk_buff *skb = base->data; + struct xfrm_state *x = skb_dst(skb)->xfrm; + struct ah_data *ahp = x->data; + struct iphdr *top_iph = ip_hdr(skb); + struct ip_auth_hdr *ah = ip_auth_hdr(skb); + int ihl = ip_hdrlen(skb); + + iph = AH_SKB_CB(skb)->tmp; + icv = ah_tmp_icv(ahp->ahash, iph, ihl); + memcpy(ah->auth_data, icv, ahp->icv_trunc_len); + + top_iph->tos = iph->tos; + top_iph->ttl = iph->ttl; + top_iph->frag_off = iph->frag_off; + if (top_iph->ihl != 5) { + top_iph->daddr = iph->daddr; + memcpy(top_iph+1, iph+1, top_iph->ihl*4 - sizeof(struct iphdr)); + } + + err = ah->nexthdr; + + kfree(AH_SKB_CB(skb)->tmp); + xfrm_output_resume(skb, err); +} + static int ah_output(struct xfrm_state *x, struct sk_buff *skb) { int err; + int nfrags; + int ihl; + u8 *icv; + struct sk_buff *trailer; + struct crypto_ahash *ahash; + struct ahash_request *req; + struct scatterlist *sg; struct iphdr *iph, *top_iph; struct ip_auth_hdr *ah; struct ah_data *ahp; - union { - struct iphdr iph; - char buf[60]; - } tmp_iph; + + ahp = x->data; + ahash = ahp->ahash; + + if ((err = skb_cow_data(skb, 0, &trailer)) < 0) + goto out; + nfrags = err; skb_push(skb, -skb_network_offset(skb)); + ah = ip_auth_hdr(skb); + ihl = ip_hdrlen(skb); + + err = -ENOMEM; + iph = ah_alloc_tmp(ahash, nfrags, ihl); + if (!iph) + goto out; + + icv = ah_tmp_icv(ahash, iph, ihl); + req = ah_tmp_req(ahash, icv); + sg = ah_req_sg(ahash, req); + + memset(ah->auth_data, 0, ahp->icv_trunc_len); + top_iph = ip_hdr(skb); - iph = &tmp_iph.iph; iph->tos = top_iph->tos; iph->ttl = top_iph->ttl; @@ -78,10 +188,9 @@ static int ah_output(struct xfrm_state *x, struct sk_buff *skb) memcpy(iph+1, top_iph+1, top_iph->ihl*4 - sizeof(struct iphdr)); err = ip_clear_mutable_options(top_iph, &top_iph->daddr); if (err) - goto error; + goto out_free; } - ah = ip_auth_hdr(skb); ah->nexthdr = *skb_mac_header(skb); *skb_mac_header(skb) = IPPROTO_AH; @@ -91,20 +200,31 @@ static int ah_output(struct xfrm_state *x, struct sk_buff *skb) top_iph->ttl = 0; top_iph->check = 0; - ahp = x->data; ah->hdrlen = (XFRM_ALIGN8(sizeof(*ah) + ahp->icv_trunc_len) >> 2) - 2; ah->reserved = 0; ah->spi = x->id.spi; ah->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output); - spin_lock_bh(&x->lock); - err = ah_mac_digest(ahp, skb, ah->auth_data); - memcpy(ah->auth_data, ahp->work_icv, ahp->icv_trunc_len); - spin_unlock_bh(&x->lock); + sg_init_table(sg, nfrags); + skb_to_sgvec(skb, sg, 0, skb->len); - if (err) - goto error; + ahash_request_set_crypt(req, sg, icv, skb->len); + ahash_request_set_callback(req, 0, ah_output_done, skb); + + AH_SKB_CB(skb)->tmp = iph; + + err = crypto_ahash_digest(req); + if (err) { + if (err == -EINPROGRESS) + goto out; + + if (err == -EBUSY) + err = NET_XMIT_DROP; + goto out_free; + } + + memcpy(ah->auth_data, icv, ahp->icv_trunc_len); top_iph->tos = iph->tos; top_iph->ttl = iph->ttl; @@ -114,28 +234,67 @@ static int ah_output(struct xfrm_state *x, struct sk_buff *skb) memcpy(top_iph+1, iph+1, top_iph->ihl*4 - sizeof(struct iphdr)); } - err = 0; - -error: +out_free: + kfree(iph); +out: return err; } +static void ah_input_done(struct crypto_async_request *base, int err) +{ + u8 *auth_data; + u8 *icv; + struct iphdr *work_iph; + struct sk_buff *skb = base->data; + struct xfrm_state *x = xfrm_input_state(skb); + struct ah_data *ahp = x->data; + struct ip_auth_hdr *ah = ip_auth_hdr(skb); + int ihl = ip_hdrlen(skb); + int ah_hlen = (ah->hdrlen + 2) << 2; + + work_iph = AH_SKB_CB(skb)->tmp; + auth_data = ah_tmp_auth(work_iph, ihl); + icv = ah_tmp_icv(ahp->ahash, auth_data, ahp->icv_trunc_len); + + err = memcmp(icv, auth_data, ahp->icv_trunc_len) ? -EBADMSG: 0; + if (err) + goto out; + + skb->network_header += ah_hlen; + memcpy(skb_network_header(skb), work_iph, ihl); + __skb_pull(skb, ah_hlen + ihl); + skb_set_transport_header(skb, -ihl); + + err = ah->nexthdr; +out: + kfree(AH_SKB_CB(skb)->tmp); + xfrm_input_resume(skb, err); +} + static int ah_input(struct xfrm_state *x, struct sk_buff *skb) { int ah_hlen; int ihl; int nexthdr; - int err = -EINVAL; - struct iphdr *iph; + int nfrags; + u8 *auth_data; + u8 *icv; + struct sk_buff *trailer; + struct crypto_ahash *ahash; + struct ahash_request *req; + struct scatterlist *sg; + struct iphdr *iph, *work_iph; struct ip_auth_hdr *ah; struct ah_data *ahp; - char work_buf[60]; + int err = -ENOMEM; if (!pskb_may_pull(skb, sizeof(*ah))) goto out; ah = (struct ip_auth_hdr *)skb->data; ahp = x->data; + ahash = ahp->ahash; + nexthdr = ah->nexthdr; ah_hlen = (ah->hdrlen + 2) << 2; @@ -156,9 +315,24 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb) ah = (struct ip_auth_hdr *)skb->data; iph = ip_hdr(skb); + ihl = ip_hdrlen(skb); + + if ((err = skb_cow_data(skb, 0, &trailer)) < 0) + goto out; + nfrags = err; + + work_iph = ah_alloc_tmp(ahash, nfrags, ihl + ahp->icv_trunc_len); + if (!work_iph) + goto out; + + auth_data = ah_tmp_auth(work_iph, ihl); + icv = ah_tmp_icv(ahash, auth_data, ahp->icv_trunc_len); + req = ah_tmp_req(ahash, icv); + sg = ah_req_sg(ahash, req); - ihl = skb->data - skb_network_header(skb); - memcpy(work_buf, iph, ihl); + memcpy(work_iph, iph, ihl); + memcpy(auth_data, ah->auth_data, ahp->icv_trunc_len); + memset(ah->auth_data, 0, ahp->icv_trunc_len); iph->ttl = 0; iph->tos = 0; @@ -166,35 +340,44 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb) iph->check = 0; if (ihl > sizeof(*iph)) { __be32 dummy; - if (ip_clear_mutable_options(iph, &dummy)) - goto out; + err = ip_clear_mutable_options(iph, &dummy); + if (err) + goto out_free; } - spin_lock(&x->lock); - { - u8 auth_data[MAX_AH_AUTH_LEN]; + skb_push(skb, ihl); - memcpy(auth_data, ah->auth_data, ahp->icv_trunc_len); - skb_push(skb, ihl); - err = ah_mac_digest(ahp, skb, ah->auth_data); - if (err) - goto unlock; - if (memcmp(ahp->work_icv, auth_data, ahp->icv_trunc_len)) - err = -EBADMSG; + sg_init_table(sg, nfrags); + skb_to_sgvec(skb, sg, 0, skb->len); + + ahash_request_set_crypt(req, sg, icv, skb->len); + ahash_request_set_callback(req, 0, ah_input_done, skb); + + AH_SKB_CB(skb)->tmp = work_iph; + + err = crypto_ahash_digest(req); + if (err) { + if (err == -EINPROGRESS) + goto out; + + if (err == -EBUSY) + err = NET_XMIT_DROP; + goto out_free; } -unlock: - spin_unlock(&x->lock); + err = memcmp(icv, auth_data, ahp->icv_trunc_len) ? -EBADMSG: 0; if (err) - goto out; + goto out_free; skb->network_header += ah_hlen; - memcpy(skb_network_header(skb), work_buf, ihl); - skb->transport_header = skb->network_header; + memcpy(skb_network_header(skb), work_iph, ihl); __skb_pull(skb, ah_hlen + ihl); + skb_set_transport_header(skb, -ihl); - return nexthdr; + err = nexthdr; +out_free: + kfree (work_iph); out: return err; } @@ -222,7 +405,7 @@ static int ah_init_state(struct xfrm_state *x) { struct ah_data *ahp = NULL; struct xfrm_algo_desc *aalg_desc; - struct crypto_hash *tfm; + struct crypto_ahash *ahash; if (!x->aalg) goto error; @@ -231,44 +414,40 @@ static int ah_init_state(struct xfrm_state *x) goto error; ahp = kzalloc(sizeof(*ahp), GFP_KERNEL); - if (ahp == NULL) + if (!ahp) return -ENOMEM; - tfm = crypto_alloc_hash(x->aalg->alg_name, 0, CRYPTO_ALG_ASYNC); - if (IS_ERR(tfm)) + ahash = crypto_alloc_ahash(x->aalg->alg_name, 0, 0); + if (IS_ERR(ahash)) goto error; - ahp->tfm = tfm; - if (crypto_hash_setkey(tfm, x->aalg->alg_key, - (x->aalg->alg_key_len + 7) / 8)) + ahp->ahash = ahash; + if (crypto_ahash_setkey(ahash, x->aalg->alg_key, + (x->aalg->alg_key_len + 7) / 8)) goto error; /* * Lookup the algorithm description maintained by xfrm_algo, * verify crypto transform properties, and store information * we need for AH processing. This lookup cannot fail here - * after a successful crypto_alloc_hash(). + * after a successful crypto_alloc_ahash(). */ aalg_desc = xfrm_aalg_get_byname(x->aalg->alg_name, 0); BUG_ON(!aalg_desc); if (aalg_desc->uinfo.auth.icv_fullbits/8 != - crypto_hash_digestsize(tfm)) { + crypto_ahash_digestsize(ahash)) { printk(KERN_INFO "AH: %s digestsize %u != %hu\n", - x->aalg->alg_name, crypto_hash_digestsize(tfm), + x->aalg->alg_name, crypto_ahash_digestsize(ahash), aalg_desc->uinfo.auth.icv_fullbits/8); goto error; } ahp->icv_full_len = aalg_desc->uinfo.auth.icv_fullbits/8; - ahp->icv_trunc_len = aalg_desc->uinfo.auth.icv_truncbits/8; + ahp->icv_trunc_len = x->aalg->alg_trunc_len/8; BUG_ON(ahp->icv_trunc_len > MAX_AH_AUTH_LEN); - ahp->work_icv = kmalloc(ahp->icv_full_len, GFP_KERNEL); - if (!ahp->work_icv) - goto error; - x->props.header_len = XFRM_ALIGN8(sizeof(struct ip_auth_hdr) + ahp->icv_trunc_len); if (x->props.mode == XFRM_MODE_TUNNEL) @@ -279,8 +458,7 @@ static int ah_init_state(struct xfrm_state *x) error: if (ahp) { - kfree(ahp->work_icv); - crypto_free_hash(ahp->tfm); + crypto_free_ahash(ahp->ahash); kfree(ahp); } return -EINVAL; @@ -293,8 +471,7 @@ static void ah_destroy(struct xfrm_state *x) if (!ahp) return; - kfree(ahp->work_icv); - crypto_free_hash(ahp->tfm); + crypto_free_ahash(ahp->ahash); kfree(ahp); } diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 039cc1f..1e029dc 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -2017,7 +2017,7 @@ req_setattr_failure: * values on failure. * */ -int cipso_v4_delopt(struct ip_options **opt_ptr) +static int cipso_v4_delopt(struct ip_options **opt_ptr) { int hdr_delta = 0; struct ip_options *opt = *opt_ptr; diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index 5e6c5a0..fb24658 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -39,7 +39,7 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) sk_dst_reset(sk); oif = sk->sk_bound_dev_if; - saddr = inet->saddr; + saddr = inet->inet_saddr; if (ipv4_is_multicast(usin->sin_addr.s_addr)) { if (!oif) oif = inet->mc_index; @@ -49,7 +49,7 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) err = ip_route_connect(&rt, usin->sin_addr.s_addr, saddr, RT_CONN_FLAGS(sk), oif, sk->sk_protocol, - inet->sport, usin->sin_port, sk, 1); + inet->inet_sport, usin->sin_port, sk, 1); if (err) { if (err == -ENETUNREACH) IP_INC_STATS_BH(sock_net(sk), IPSTATS_MIB_OUTNOROUTES); @@ -60,14 +60,14 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) ip_rt_put(rt); return -EACCES; } - if (!inet->saddr) - inet->saddr = rt->rt_src; /* Update source address */ - if (!inet->rcv_saddr) - inet->rcv_saddr = rt->rt_src; - inet->daddr = rt->rt_dst; - inet->dport = usin->sin_port; + if (!inet->inet_saddr) + inet->inet_saddr = rt->rt_src; /* Update source address */ + if (!inet->inet_rcv_saddr) + inet->inet_rcv_saddr = rt->rt_src; + inet->inet_daddr = rt->rt_dst; + inet->inet_dport = usin->sin_port; sk->sk_state = TCP_ESTABLISHED; - inet->id = jiffies; + inet->inet_id = jiffies; sk_dst_set(sk, &rt->u.dst); return(0); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index e049da8..5cdbc10 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -140,11 +140,11 @@ void in_dev_finish_destroy(struct in_device *idev) #endif dev_put(dev); if (!idev->dead) - printk("Freeing alive in_device %p\n", idev); - else { + pr_err("Freeing alive in_device %p\n", idev); + else kfree(idev); - } } +EXPORT_SYMBOL(in_dev_finish_destroy); static struct in_device *inetdev_init(struct net_device *dev) { @@ -159,7 +159,8 @@ static struct in_device *inetdev_init(struct net_device *dev) sizeof(in_dev->cnf)); in_dev->cnf.sysctl = NULL; in_dev->dev = dev; - if ((in_dev->arp_parms = neigh_parms_alloc(dev, &arp_tbl)) == NULL) + in_dev->arp_parms = neigh_parms_alloc(dev, &arp_tbl); + if (!in_dev->arp_parms) goto out_kfree; if (IPV4_DEVCONF(in_dev->cnf, FORWARDING)) dev_disable_lro(dev); @@ -405,13 +406,15 @@ struct in_device *inetdev_by_index(struct net *net, int ifindex) { struct net_device *dev; struct in_device *in_dev = NULL; - read_lock(&dev_base_lock); - dev = __dev_get_by_index(net, ifindex); + + rcu_read_lock(); + dev = dev_get_by_index_rcu(net, ifindex); if (dev) in_dev = in_dev_get(dev); - read_unlock(&dev_base_lock); + rcu_read_unlock(); return in_dev; } +EXPORT_SYMBOL(inetdev_by_index); /* Called only from RTNL semaphored context. No locks. */ @@ -557,7 +560,7 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg * Determine a default network mask, based on the IP address. */ -static __inline__ int inet_abc_len(__be32 addr) +static inline int inet_abc_len(__be32 addr) { int rc = -1; /* Something else, probably a multicast. */ @@ -646,13 +649,15 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg) rtnl_lock(); ret = -ENODEV; - if ((dev = __dev_get_by_name(net, ifr.ifr_name)) == NULL) + dev = __dev_get_by_name(net, ifr.ifr_name); + if (!dev) goto done; if (colon) *colon = ':'; - if ((in_dev = __in_dev_get_rtnl(dev)) != NULL) { + in_dev = __in_dev_get_rtnl(dev); + if (in_dev) { if (tryaddrmatch) { /* Matthias Andree */ /* compare label and address (4.4BSD style) */ @@ -720,7 +725,8 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg) if (!ifa) { ret = -ENOBUFS; - if ((ifa = inet_alloc_ifa()) == NULL) + ifa = inet_alloc_ifa(); + if (!ifa) break; if (colon) memcpy(ifa->ifa_label, ifr.ifr_name, IFNAMSIZ); @@ -822,10 +828,10 @@ static int inet_gifconf(struct net_device *dev, char __user *buf, int len) struct ifreq ifr; int done = 0; - if (!in_dev || (ifa = in_dev->ifa_list) == NULL) + if (!in_dev) goto out; - for (; ifa; ifa = ifa->ifa_next) { + for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) { if (!buf) { done += sizeof(ifr); continue; @@ -875,36 +881,33 @@ __be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope) if (!addr) addr = ifa->ifa_local; } endfor_ifa(in_dev); -no_in_dev: - rcu_read_unlock(); if (addr) - goto out; + goto out_unlock; +no_in_dev: /* Not loopback addresses on loopback should be preferred in this case. It is importnat that lo is the first interface in dev_base list. */ - read_lock(&dev_base_lock); - rcu_read_lock(); - for_each_netdev(net, dev) { - if ((in_dev = __in_dev_get_rcu(dev)) == NULL) + for_each_netdev_rcu(net, dev) { + in_dev = __in_dev_get_rcu(dev); + if (!in_dev) continue; for_primary_ifa(in_dev) { if (ifa->ifa_scope != RT_SCOPE_LINK && ifa->ifa_scope <= scope) { addr = ifa->ifa_local; - goto out_unlock_both; + goto out_unlock; } } endfor_ifa(in_dev); } -out_unlock_both: - read_unlock(&dev_base_lock); +out_unlock: rcu_read_unlock(); -out: return addr; } +EXPORT_SYMBOL(inet_select_addr); static __be32 confirm_addr_indev(struct in_device *in_dev, __be32 dst, __be32 local, int scope) @@ -940,7 +943,7 @@ static __be32 confirm_addr_indev(struct in_device *in_dev, __be32 dst, } } endfor_ifa(in_dev); - return same? addr : 0; + return same ? addr : 0; } /* @@ -961,17 +964,16 @@ __be32 inet_confirm_addr(struct in_device *in_dev, return confirm_addr_indev(in_dev, dst, local, scope); net = dev_net(in_dev->dev); - read_lock(&dev_base_lock); rcu_read_lock(); - for_each_netdev(net, dev) { - if ((in_dev = __in_dev_get_rcu(dev))) { + for_each_netdev_rcu(net, dev) { + in_dev = __in_dev_get_rcu(dev); + if (in_dev) { addr = confirm_addr_indev(in_dev, dst, local, scope); if (addr) break; } } rcu_read_unlock(); - read_unlock(&dev_base_lock); return addr; } @@ -984,14 +986,16 @@ int register_inetaddr_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&inetaddr_chain, nb); } +EXPORT_SYMBOL(register_inetaddr_notifier); int unregister_inetaddr_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&inetaddr_chain, nb); } +EXPORT_SYMBOL(unregister_inetaddr_notifier); -/* Rename ifa_labels for a device name change. Make some effort to preserve existing - * alias numbering and to create unique labels if possible. +/* Rename ifa_labels for a device name change. Make some effort to preserve + * existing alias numbering and to create unique labels if possible. */ static void inetdev_changename(struct net_device *dev, struct in_device *in_dev) { @@ -1010,11 +1014,10 @@ static void inetdev_changename(struct net_device *dev, struct in_device *in_dev) sprintf(old, ":%d", named); dot = old; } - if (strlen(dot) + strlen(dev->name) < IFNAMSIZ) { + if (strlen(dot) + strlen(dev->name) < IFNAMSIZ) strcat(ifa->ifa_label, dot); - } else { + else strcpy(ifa->ifa_label + (IFNAMSIZ - strlen(dot) - 1), dot); - } skip: rtmsg_ifa(RTM_NEWADDR, ifa, NULL, 0); } @@ -1061,8 +1064,9 @@ static int inetdev_event(struct notifier_block *this, unsigned long event, if (!inetdev_valid_mtu(dev->mtu)) break; if (dev->flags & IFF_LOOPBACK) { - struct in_ifaddr *ifa; - if ((ifa = inet_alloc_ifa()) != NULL) { + struct in_ifaddr *ifa = inet_alloc_ifa(); + + if (ifa) { ifa->ifa_local = ifa->ifa_address = htonl(INADDR_LOOPBACK); ifa->ifa_prefixlen = 8; @@ -1170,38 +1174,54 @@ nla_put_failure: static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); - int idx, ip_idx; + int h, s_h; + int idx, s_idx; + int ip_idx, s_ip_idx; struct net_device *dev; struct in_device *in_dev; struct in_ifaddr *ifa; - int s_ip_idx, s_idx = cb->args[0]; + struct hlist_head *head; + struct hlist_node *node; - s_ip_idx = ip_idx = cb->args[1]; - idx = 0; - for_each_netdev(net, dev) { - if (idx < s_idx) - goto cont; - if (idx > s_idx) - s_ip_idx = 0; - if ((in_dev = __in_dev_get_rtnl(dev)) == NULL) - goto cont; - - for (ifa = in_dev->ifa_list, ip_idx = 0; ifa; - ifa = ifa->ifa_next, ip_idx++) { - if (ip_idx < s_ip_idx) - continue; - if (inet_fill_ifaddr(skb, ifa, NETLINK_CB(cb->skb).pid, + s_h = cb->args[0]; + s_idx = idx = cb->args[1]; + s_ip_idx = ip_idx = cb->args[2]; + + for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { + idx = 0; + head = &net->dev_index_head[h]; + rcu_read_lock(); + hlist_for_each_entry_rcu(dev, node, head, index_hlist) { + if (idx < s_idx) + goto cont; + if (idx > s_idx) + s_ip_idx = 0; + in_dev = __in_dev_get_rcu(dev); + if (!in_dev) + goto cont; + + for (ifa = in_dev->ifa_list, ip_idx = 0; ifa; + ifa = ifa->ifa_next, ip_idx++) { + if (ip_idx < s_ip_idx) + continue; + if (inet_fill_ifaddr(skb, ifa, + NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, - RTM_NEWADDR, NLM_F_MULTI) <= 0) - goto done; - } + RTM_NEWADDR, NLM_F_MULTI) <= 0) { + rcu_read_unlock(); + goto done; + } + } cont: - idx++; + idx++; + } + rcu_read_unlock(); } done: - cb->args[0] = idx; - cb->args[1] = ip_idx; + cb->args[0] = h; + cb->args[1] = idx; + cb->args[2] = ip_idx; return skb->len; } @@ -1239,18 +1259,18 @@ static void devinet_copy_dflt_conf(struct net *net, int i) { struct net_device *dev; - read_lock(&dev_base_lock); - for_each_netdev(net, dev) { + rcu_read_lock(); + for_each_netdev_rcu(net, dev) { struct in_device *in_dev; - rcu_read_lock(); + in_dev = __in_dev_get_rcu(dev); if (in_dev && !test_bit(i, in_dev->cnf.state)) in_dev->cnf.data[i] = net->ipv4.devconf_dflt->data[i]; - rcu_read_unlock(); } - read_unlock(&dev_base_lock); + rcu_read_unlock(); } +/* called with RTNL locked */ static void inet_forward_change(struct net *net) { struct net_device *dev; @@ -1259,7 +1279,6 @@ static void inet_forward_change(struct net *net) IPV4_DEVCONF_ALL(net, ACCEPT_REDIRECTS) = !on; IPV4_DEVCONF_DFLT(net, FORWARDING) = on; - read_lock(&dev_base_lock); for_each_netdev(net, dev) { struct in_device *in_dev; if (on) @@ -1270,7 +1289,6 @@ static void inet_forward_change(struct net *net) IN_DEV_CONF_SET(in_dev, FORWARDING, on); rcu_read_unlock(); } - read_unlock(&dev_base_lock); } static int devinet_conf_proc(ctl_table *ctl, int write, @@ -1378,6 +1396,7 @@ static struct devinet_sysctl_table { DEVINET_SYSCTL_RW_ENTRY(SEND_REDIRECTS, "send_redirects"), DEVINET_SYSCTL_RW_ENTRY(ACCEPT_SOURCE_ROUTE, "accept_source_route"), + DEVINET_SYSCTL_RW_ENTRY(ACCEPT_LOCAL, "accept_local"), DEVINET_SYSCTL_RW_ENTRY(PROXY_ARP, "proxy_arp"), DEVINET_SYSCTL_RW_ENTRY(MEDIUM_ID, "medium_id"), DEVINET_SYSCTL_RW_ENTRY(BOOTP_RELAY, "bootp_relay"), @@ -1512,7 +1531,7 @@ static __net_init int devinet_init_net(struct net *net) all = &ipv4_devconf; dflt = &ipv4_devconf_dflt; - if (net != &init_net) { + if (!net_eq(net, &init_net)) { all = kmemdup(all, sizeof(ipv4_devconf), GFP_KERNEL); if (all == NULL) goto err_alloc_all; @@ -1603,8 +1622,3 @@ void __init devinet_init(void) rtnl_register(PF_INET, RTM_GETADDR, NULL, inet_dump_ifaddr); } -EXPORT_SYMBOL(in_dev_finish_destroy); -EXPORT_SYMBOL(inet_select_addr); -EXPORT_SYMBOL(inetdev_by_index); -EXPORT_SYMBOL(register_inetaddr_notifier); -EXPORT_SYMBOL(unregister_inetaddr_notifier); diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 12f7287..1948895 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -530,7 +530,7 @@ static int esp_init_authenc(struct xfrm_state *x) } err = crypto_aead_setauthsize( - aead, aalg_desc->uinfo.auth.icv_truncbits / 8); + aead, x->aalg->alg_trunc_len / 8); if (err) goto free_key; } diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index aa00398..3323168 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -125,7 +125,7 @@ void fib_select_default(struct net *net, #endif tb = fib_get_table(net, table); if (FIB_RES_GW(*res) && FIB_RES_NH(*res).nh_scope == RT_SCOPE_LINK) - tb->tb_select_default(tb, flp, res); + fib_table_select_default(tb, flp, res); } static void fib_flush(struct net *net) @@ -139,7 +139,7 @@ static void fib_flush(struct net *net) for (h = 0; h < FIB_TABLE_HASHSZ; h++) { head = &net->ipv4.fib_table_hash[h]; hlist_for_each_entry(tb, node, head, tb_hlist) - flushed += tb->tb_flush(tb); + flushed += fib_table_flush(tb); } if (flushed) @@ -162,7 +162,7 @@ struct net_device * ip_dev_find(struct net *net, __be32 addr) #endif local_table = fib_get_table(net, RT_TABLE_LOCAL); - if (!local_table || local_table->tb_lookup(local_table, &fl, &res)) + if (!local_table || fib_table_lookup(local_table, &fl, &res)) return NULL; if (res.type != RTN_LOCAL) goto out; @@ -200,7 +200,7 @@ static inline unsigned __inet_dev_addr_type(struct net *net, local_table = fib_get_table(net, RT_TABLE_LOCAL); if (local_table) { ret = RTN_UNICAST; - if (!local_table->tb_lookup(local_table, &fl, &res)) { + if (!fib_table_lookup(local_table, &fl, &res)) { if (!dev || dev == res.fi->fib_dev) ret = res.type; fib_res_put(&res); @@ -241,16 +241,17 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, .iif = oif }; struct fib_result res; - int no_addr, rpf; + int no_addr, rpf, accept_local; int ret; struct net *net; - no_addr = rpf = 0; + no_addr = rpf = accept_local = 0; rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); if (in_dev) { no_addr = in_dev->ifa_list == NULL; rpf = IN_DEV_RPFILTER(in_dev); + accept_local = IN_DEV_ACCEPT_LOCAL(in_dev); } rcu_read_unlock(); @@ -260,8 +261,10 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, net = dev_net(dev); if (fib_lookup(net, &fl, &res)) goto last_resort; - if (res.type != RTN_UNICAST) - goto e_inval_res; + if (res.type != RTN_UNICAST) { + if (res.type != RTN_LOCAL || !accept_local) + goto e_inval_res; + } *spec_dst = FIB_RES_PREFSRC(res); fib_combine_itag(itag, &res); #ifdef CONFIG_IP_ROUTE_MULTIPATH @@ -476,13 +479,13 @@ int ip_rt_ioctl(struct net *net, unsigned int cmd, void __user *arg) if (cmd == SIOCDELRT) { tb = fib_get_table(net, cfg.fc_table); if (tb) - err = tb->tb_delete(tb, &cfg); + err = fib_table_delete(tb, &cfg); else err = -ESRCH; } else { tb = fib_new_table(net, cfg.fc_table); if (tb) - err = tb->tb_insert(tb, &cfg); + err = fib_table_insert(tb, &cfg); else err = -ENOBUFS; } @@ -597,7 +600,7 @@ static int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, void *ar goto errout; } - err = tb->tb_delete(tb, &cfg); + err = fib_table_delete(tb, &cfg); errout: return err; } @@ -619,7 +622,7 @@ static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, void *ar goto errout; } - err = tb->tb_insert(tb, &cfg); + err = fib_table_insert(tb, &cfg); errout: return err; } @@ -650,7 +653,7 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) if (dumped) memset(&cb->args[2], 0, sizeof(cb->args) - 2 * sizeof(cb->args[0])); - if (tb->tb_dump(tb, skb, cb) < 0) + if (fib_table_dump(tb, skb, cb) < 0) goto out; dumped = 1; next: @@ -704,9 +707,9 @@ static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifad cfg.fc_scope = RT_SCOPE_HOST; if (cmd == RTM_NEWROUTE) - tb->tb_insert(tb, &cfg); + fib_table_insert(tb, &cfg); else - tb->tb_delete(tb, &cfg); + fib_table_delete(tb, &cfg); } void fib_add_ifaddr(struct in_ifaddr *ifa) @@ -835,7 +838,7 @@ static void nl_fib_lookup(struct fib_result_nl *frn, struct fib_table *tb ) local_bh_disable(); frn->tb_id = tb->tb_id; - frn->err = tb->tb_lookup(tb, &fl, &res); + frn->err = fib_table_lookup(tb, &fl, &res); if (!frn->err) { frn->prefixlen = res.prefixlen; @@ -895,11 +898,11 @@ static void nl_fib_lookup_exit(struct net *net) net->ipv4.fibnl = NULL; } -static void fib_disable_ip(struct net_device *dev, int force) +static void fib_disable_ip(struct net_device *dev, int force, int delay) { if (fib_sync_down_dev(dev, force)) fib_flush(dev_net(dev)); - rt_cache_flush(dev_net(dev), 0); + rt_cache_flush(dev_net(dev), delay); arp_ifdown(dev); } @@ -922,7 +925,7 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event, /* Last address was deleted from this interface. Disable IP. */ - fib_disable_ip(dev, 1); + fib_disable_ip(dev, 1, 0); } else { rt_cache_flush(dev_net(dev), -1); } @@ -937,7 +940,7 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo struct in_device *in_dev = __in_dev_get_rtnl(dev); if (event == NETDEV_UNREGISTER) { - fib_disable_ip(dev, 2); + fib_disable_ip(dev, 2, -1); return NOTIFY_DONE; } @@ -955,12 +958,15 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo rt_cache_flush(dev_net(dev), -1); break; case NETDEV_DOWN: - fib_disable_ip(dev, 0); + fib_disable_ip(dev, 0, 0); break; case NETDEV_CHANGEMTU: case NETDEV_CHANGE: rt_cache_flush(dev_net(dev), 0); break; + case NETDEV_UNREGISTER_BATCH: + rt_cache_flush_batch(); + break; } return NOTIFY_DONE; } @@ -1012,7 +1018,7 @@ static void __net_exit ip_fib_net_exit(struct net *net) head = &net->ipv4.fib_table_hash[i]; hlist_for_each_entry_safe(tb, node, tmp, head, tb_hlist) { hlist_del(node); - tb->tb_flush(tb); + fib_table_flush(tb); kfree(tb); } } diff --git a/net/ipv4/fib_hash.c b/net/ipv4/fib_hash.c index ecd3945..14972017b 100644 --- a/net/ipv4/fib_hash.c +++ b/net/ipv4/fib_hash.c @@ -242,8 +242,8 @@ fn_new_zone(struct fn_hash *table, int z) return fz; } -static int -fn_hash_lookup(struct fib_table *tb, const struct flowi *flp, struct fib_result *res) +int fib_table_lookup(struct fib_table *tb, + const struct flowi *flp, struct fib_result *res) { int err; struct fn_zone *fz; @@ -274,8 +274,8 @@ out: return err; } -static void -fn_hash_select_default(struct fib_table *tb, const struct flowi *flp, struct fib_result *res) +void fib_table_select_default(struct fib_table *tb, + const struct flowi *flp, struct fib_result *res) { int order, last_idx; struct hlist_node *node; @@ -366,7 +366,7 @@ static struct fib_node *fib_find_node(struct fn_zone *fz, __be32 key) return NULL; } -static int fn_hash_insert(struct fib_table *tb, struct fib_config *cfg) +int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) { struct fn_hash *table = (struct fn_hash *) tb->tb_data; struct fib_node *new_f = NULL; @@ -544,8 +544,7 @@ out: return err; } - -static int fn_hash_delete(struct fib_table *tb, struct fib_config *cfg) +int fib_table_delete(struct fib_table *tb, struct fib_config *cfg) { struct fn_hash *table = (struct fn_hash *)tb->tb_data; struct fib_node *f; @@ -662,7 +661,7 @@ static int fn_flush_list(struct fn_zone *fz, int idx) return found; } -static int fn_hash_flush(struct fib_table *tb) +int fib_table_flush(struct fib_table *tb) { struct fn_hash *table = (struct fn_hash *) tb->tb_data; struct fn_zone *fz; @@ -743,7 +742,8 @@ fn_hash_dump_zone(struct sk_buff *skb, struct netlink_callback *cb, return skb->len; } -static int fn_hash_dump(struct fib_table *tb, struct sk_buff *skb, struct netlink_callback *cb) +int fib_table_dump(struct fib_table *tb, struct sk_buff *skb, + struct netlink_callback *cb) { int m, s_m; struct fn_zone *fz; @@ -787,12 +787,7 @@ struct fib_table *fib_hash_table(u32 id) tb->tb_id = id; tb->tb_default = -1; - tb->tb_lookup = fn_hash_lookup; - tb->tb_insert = fn_hash_insert; - tb->tb_delete = fn_hash_delete; - tb->tb_flush = fn_hash_flush; - tb->tb_select_default = fn_hash_select_default; - tb->tb_dump = fn_hash_dump; + memset(tb->tb_data, 0, sizeof(struct fn_hash)); return tb; } diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 92d9d97..ca2d07b 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -94,7 +94,7 @@ static int fib4_rule_action(struct fib_rule *rule, struct flowi *flp, if ((tbl = fib_get_table(rule->fr_net, rule->table)) == NULL) goto errout; - err = tbl->tb_lookup(tbl, flp, (struct fib_result *) arg->result); + err = fib_table_lookup(tbl, flp, (struct fib_result *) arg->result); if (err > 0) err = -EAGAIN; errout: @@ -284,7 +284,7 @@ static int fib_default_rules_init(struct fib_rules_ops *ops) { int err; - err = fib_default_rule_add(ops, 0, RT_TABLE_LOCAL, FIB_RULE_PERMANENT); + err = fib_default_rule_add(ops, 0, RT_TABLE_LOCAL, 0); if (err < 0) return err; err = fib_default_rule_add(ops, 0x7FFE, RT_TABLE_MAIN, 0); @@ -301,13 +301,9 @@ int __net_init fib4_rules_init(struct net *net) int err; struct fib_rules_ops *ops; - ops = kmemdup(&fib4_rules_ops_template, sizeof(*ops), GFP_KERNEL); - if (ops == NULL) - return -ENOMEM; - INIT_LIST_HEAD(&ops->rules_list); - ops->fro_net = net; - - fib_rules_register(ops); + ops = fib_rules_register(&fib4_rules_ops_template, net); + if (IS_ERR(ops)) + return PTR_ERR(ops); err = fib_default_rules_init(ops); if (err < 0) @@ -318,12 +314,10 @@ int __net_init fib4_rules_init(struct net *net) fail: /* also cleans all rules already added */ fib_rules_unregister(ops); - kfree(ops); return err; } void __net_exit fib4_rules_exit(struct net *net) { fib_rules_unregister(net->ipv4.rules_ops); - kfree(net->ipv4.rules_ops); } diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 9b096d6..ed19aa6 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -228,7 +228,7 @@ static struct fib_info *fib_find_info(const struct fib_info *nfi) head = &fib_info_hash[hash]; hlist_for_each_entry(fi, node, head, fib_hash) { - if (fi->fib_net != nfi->fib_net) + if (!net_eq(fi->fib_net, nfi->fib_net)) continue; if (fi->fib_nhs != nfi->fib_nhs) continue; @@ -1047,7 +1047,7 @@ int fib_sync_down_addr(struct net *net, __be32 local) return 0; hlist_for_each_entry(fi, node, head, fib_lhash) { - if (fi->fib_net != net) + if (!net_eq(fi->fib_net, net)) continue; if (fi->fib_prefsrc == local) { fi->fib_flags |= RTNH_F_DEAD; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 291bdf5..af5d897 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1174,7 +1174,7 @@ done: /* * Caller must hold RTNL. */ -static int fn_trie_insert(struct fib_table *tb, struct fib_config *cfg) +int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) { struct trie *t = (struct trie *) tb->tb_data; struct fib_alias *fa, *new_fa; @@ -1373,8 +1373,8 @@ static int check_leaf(struct trie *t, struct leaf *l, return 1; } -static int fn_trie_lookup(struct fib_table *tb, const struct flowi *flp, - struct fib_result *res) +int fib_table_lookup(struct fib_table *tb, const struct flowi *flp, + struct fib_result *res) { struct trie *t = (struct trie *) tb->tb_data; int ret; @@ -1595,7 +1595,7 @@ static void trie_leaf_remove(struct trie *t, struct leaf *l) /* * Caller must hold RTNL. */ -static int fn_trie_delete(struct fib_table *tb, struct fib_config *cfg) +int fib_table_delete(struct fib_table *tb, struct fib_config *cfg) { struct trie *t = (struct trie *) tb->tb_data; u32 key, mask; @@ -1786,7 +1786,7 @@ static struct leaf *trie_leafindex(struct trie *t, int index) /* * Caller must hold RTNL. */ -static int fn_trie_flush(struct fib_table *tb) +int fib_table_flush(struct fib_table *tb) { struct trie *t = (struct trie *) tb->tb_data; struct leaf *l, *ll = NULL; @@ -1807,9 +1807,9 @@ static int fn_trie_flush(struct fib_table *tb) return found; } -static void fn_trie_select_default(struct fib_table *tb, - const struct flowi *flp, - struct fib_result *res) +void fib_table_select_default(struct fib_table *tb, + const struct flowi *flp, + struct fib_result *res) { struct trie *t = (struct trie *) tb->tb_data; int order, last_idx; @@ -1952,8 +1952,8 @@ static int fn_trie_dump_leaf(struct leaf *l, struct fib_table *tb, return skb->len; } -static int fn_trie_dump(struct fib_table *tb, struct sk_buff *skb, - struct netlink_callback *cb) +int fib_table_dump(struct fib_table *tb, struct sk_buff *skb, + struct netlink_callback *cb) { struct leaf *l; struct trie *t = (struct trie *) tb->tb_data; @@ -2020,12 +2020,6 @@ struct fib_table *fib_hash_table(u32 id) tb->tb_id = id; tb->tb_default = -1; - tb->tb_lookup = fn_trie_lookup; - tb->tb_insert = fn_trie_insert; - tb->tb_delete = fn_trie_delete; - tb->tb_flush = fn_trie_flush; - tb->tb_select_default = fn_trie_select_default; - tb->tb_dump = fn_trie_dump; t = (struct trie *) tb->tb_data; memset(t, 0, sizeof(*t)); diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 5bc13fe..fe11f60 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -501,15 +501,16 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) if (!(rt->rt_flags & RTCF_LOCAL)) { struct net_device *dev = NULL; + rcu_read_lock(); if (rt->fl.iif && net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr) - dev = dev_get_by_index(net, rt->fl.iif); + dev = dev_get_by_index_rcu(net, rt->fl.iif); - if (dev) { + if (dev) saddr = inet_select_addr(dev, 0, RT_SCOPE_LINK); - dev_put(dev); - } else + else saddr = 0; + rcu_read_unlock(); } tos = icmp_pointers[type].error ? ((iph->tos & IPTOS_TOS_MASK) | @@ -1165,6 +1166,10 @@ static int __net_init icmp_sk_init(struct net *net) sk->sk_sndbuf = (2 * ((64 * 1024) + sizeof(struct sk_buff))); + /* + * Speedup sock_wfree() + */ + sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); inet_sk(sk)->pmtudisc = IP_PMTUDISC_DONT; } diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index d41e5de..76c0840 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -1899,8 +1899,9 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct err = -EADDRNOTAVAIL; for (pmc=inet->mc_list; pmc; pmc=pmc->next) { - if (pmc->multi.imr_multiaddr.s_addr == imr.imr_multiaddr.s_addr - && pmc->multi.imr_ifindex == imr.imr_ifindex) + if ((pmc->multi.imr_multiaddr.s_addr == + imr.imr_multiaddr.s_addr) && + (pmc->multi.imr_ifindex == imr.imr_ifindex)) break; } if (!pmc) { /* must have a prior join */ @@ -2311,9 +2312,10 @@ static inline struct ip_mc_list *igmp_mc_get_first(struct seq_file *seq) struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); state->in_dev = NULL; - for_each_netdev(net, state->dev) { + for_each_netdev_rcu(net, state->dev) { struct in_device *in_dev; - in_dev = in_dev_get(state->dev); + + in_dev = __in_dev_get_rcu(state->dev); if (!in_dev) continue; read_lock(&in_dev->mc_list_lock); @@ -2323,7 +2325,6 @@ static inline struct ip_mc_list *igmp_mc_get_first(struct seq_file *seq) break; } read_unlock(&in_dev->mc_list_lock); - in_dev_put(in_dev); } return im; } @@ -2333,16 +2334,15 @@ static struct ip_mc_list *igmp_mc_get_next(struct seq_file *seq, struct ip_mc_li struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); im = im->next; while (!im) { - if (likely(state->in_dev != NULL)) { + if (likely(state->in_dev != NULL)) read_unlock(&state->in_dev->mc_list_lock); - in_dev_put(state->in_dev); - } - state->dev = next_net_device(state->dev); + + state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->in_dev = NULL; break; } - state->in_dev = in_dev_get(state->dev); + state->in_dev = __in_dev_get_rcu(state->dev); if (!state->in_dev) continue; read_lock(&state->in_dev->mc_list_lock); @@ -2361,9 +2361,9 @@ static struct ip_mc_list *igmp_mc_get_idx(struct seq_file *seq, loff_t pos) } static void *igmp_mc_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(dev_base_lock) + __acquires(rcu) { - read_lock(&dev_base_lock); + rcu_read_lock(); return *pos ? igmp_mc_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } @@ -2379,16 +2379,15 @@ static void *igmp_mc_seq_next(struct seq_file *seq, void *v, loff_t *pos) } static void igmp_mc_seq_stop(struct seq_file *seq, void *v) - __releases(dev_base_lock) + __releases(rcu) { struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); if (likely(state->in_dev != NULL)) { read_unlock(&state->in_dev->mc_list_lock); - in_dev_put(state->in_dev); state->in_dev = NULL; } state->dev = NULL; - read_unlock(&dev_base_lock); + rcu_read_unlock(); } static int igmp_mc_seq_show(struct seq_file *seq, void *v) @@ -2462,9 +2461,9 @@ static inline struct ip_sf_list *igmp_mcf_get_first(struct seq_file *seq) state->idev = NULL; state->im = NULL; - for_each_netdev(net, state->dev) { + for_each_netdev_rcu(net, state->dev) { struct in_device *idev; - idev = in_dev_get(state->dev); + idev = __in_dev_get_rcu(state->dev); if (unlikely(idev == NULL)) continue; read_lock(&idev->mc_list_lock); @@ -2480,7 +2479,6 @@ static inline struct ip_sf_list *igmp_mcf_get_first(struct seq_file *seq) spin_unlock_bh(&im->lock); } read_unlock(&idev->mc_list_lock); - in_dev_put(idev); } return psf; } @@ -2494,16 +2492,15 @@ static struct ip_sf_list *igmp_mcf_get_next(struct seq_file *seq, struct ip_sf_l spin_unlock_bh(&state->im->lock); state->im = state->im->next; while (!state->im) { - if (likely(state->idev != NULL)) { + if (likely(state->idev != NULL)) read_unlock(&state->idev->mc_list_lock); - in_dev_put(state->idev); - } - state->dev = next_net_device(state->dev); + + state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->idev = NULL; goto out; } - state->idev = in_dev_get(state->dev); + state->idev = __in_dev_get_rcu(state->dev); if (!state->idev) continue; read_lock(&state->idev->mc_list_lock); @@ -2528,8 +2525,9 @@ static struct ip_sf_list *igmp_mcf_get_idx(struct seq_file *seq, loff_t pos) } static void *igmp_mcf_seq_start(struct seq_file *seq, loff_t *pos) + __acquires(rcu) { - read_lock(&dev_base_lock); + rcu_read_lock(); return *pos ? igmp_mcf_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } @@ -2545,6 +2543,7 @@ static void *igmp_mcf_seq_next(struct seq_file *seq, void *v, loff_t *pos) } static void igmp_mcf_seq_stop(struct seq_file *seq, void *v) + __releases(rcu) { struct igmp_mcf_iter_state *state = igmp_mcf_seq_private(seq); if (likely(state->im != NULL)) { @@ -2553,11 +2552,10 @@ static void igmp_mcf_seq_stop(struct seq_file *seq, void *v) } if (likely(state->idev != NULL)) { read_unlock(&state->idev->mc_list_lock); - in_dev_put(state->idev); state->idev = NULL; } state->dev = NULL; - read_unlock(&dev_base_lock); + rcu_read_unlock(); } static int igmp_mcf_seq_show(struct seq_file *seq, void *v) diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 537731b..ee16475 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -112,7 +112,7 @@ again: hashinfo->bhash_size)]; spin_lock(&head->lock); inet_bind_bucket_for_each(tb, node, &head->chain) - if (ib_net(tb) == net && tb->port == rover) { + if (net_eq(ib_net(tb), net) && tb->port == rover) { if (tb->fastreuse > 0 && sk->sk_reuse && sk->sk_state != TCP_LISTEN && @@ -158,7 +158,7 @@ have_snum: hashinfo->bhash_size)]; spin_lock(&head->lock); inet_bind_bucket_for_each(tb, node, &head->chain) - if (ib_net(tb) == net && tb->port == snum) + if (net_eq(ib_net(tb), net) && tb->port == snum) goto tb_found; } tb = NULL; @@ -358,6 +358,7 @@ struct dst_entry *inet_csk_route_req(struct sock *sk, const struct inet_request_sock *ireq = inet_rsk(req); struct ip_options *opt = inet_rsk(req)->opt; struct flowi fl = { .oif = sk->sk_bound_dev_if, + .mark = sk->sk_mark, .nl_u = { .ip4_u = { .daddr = ((opt && opt->srr) ? opt->faddr : @@ -367,7 +368,7 @@ struct dst_entry *inet_csk_route_req(struct sock *sk, .proto = sk->sk_protocol, .flags = inet_sk_flowi_flags(sk), .uli_u = { .ports = - { .sport = inet_sk(sk)->sport, + { .sport = inet_sk(sk)->inet_sport, .dport = ireq->rmt_port } } }; struct net *net = sock_net(sk); @@ -530,7 +531,7 @@ void inet_csk_reqsk_queue_prune(struct sock *parent, &expire, &resend); if (!expire && (!resend || - !req->rsk_ops->rtx_syn_ack(parent, req) || + !req->rsk_ops->rtx_syn_ack(parent, req, NULL) || inet_rsk(req)->acked)) { unsigned long timeo; @@ -574,9 +575,9 @@ struct sock *inet_csk_clone(struct sock *sk, const struct request_sock *req, newsk->sk_state = TCP_SYN_RECV; newicsk->icsk_bind_hash = NULL; - inet_sk(newsk)->dport = inet_rsk(req)->rmt_port; - inet_sk(newsk)->num = ntohs(inet_rsk(req)->loc_port); - inet_sk(newsk)->sport = inet_rsk(req)->loc_port; + inet_sk(newsk)->inet_dport = inet_rsk(req)->rmt_port; + inet_sk(newsk)->inet_num = ntohs(inet_rsk(req)->loc_port); + inet_sk(newsk)->inet_sport = inet_rsk(req)->loc_port; newsk->sk_write_space = sk_stream_write_space; newicsk->icsk_retransmits = 0; @@ -607,8 +608,8 @@ void inet_csk_destroy_sock(struct sock *sk) /* It cannot be in hash table! */ WARN_ON(!sk_unhashed(sk)); - /* If it has not 0 inet_sk(sk)->num, it must be bound */ - WARN_ON(inet_sk(sk)->num && !inet_csk(sk)->icsk_bind_hash); + /* If it has not 0 inet_sk(sk)->inet_num, it must be bound */ + WARN_ON(inet_sk(sk)->inet_num && !inet_csk(sk)->icsk_bind_hash); sk->sk_prot->destroy(sk); @@ -643,8 +644,8 @@ int inet_csk_listen_start(struct sock *sk, const int nr_table_entries) * after validation is complete. */ sk->sk_state = TCP_LISTEN; - if (!sk->sk_prot->get_port(sk, inet->num)) { - inet->sport = htons(inet->num); + if (!sk->sk_prot->get_port(sk, inet->inet_num)) { + inet->inet_sport = htons(inet->inet_num); sk_dst_reset(sk); sk->sk_prot->hash(sk); @@ -720,8 +721,8 @@ void inet_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr) const struct inet_sock *inet = inet_sk(sk); sin->sin_family = AF_INET; - sin->sin_addr.s_addr = inet->daddr; - sin->sin_port = inet->dport; + sin->sin_addr.s_addr = inet->inet_daddr; + sin->sin_port = inet->inet_dport; } EXPORT_SYMBOL_GPL(inet_csk_addr2sockaddr); diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index a706a47..bdb78dd 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -116,10 +116,10 @@ static int inet_csk_diag_fill(struct sock *sk, r->id.idiag_cookie[0] = (u32)(unsigned long)sk; r->id.idiag_cookie[1] = (u32)(((unsigned long)sk >> 31) >> 1); - r->id.idiag_sport = inet->sport; - r->id.idiag_dport = inet->dport; - r->id.idiag_src[0] = inet->rcv_saddr; - r->id.idiag_dst[0] = inet->daddr; + r->id.idiag_sport = inet->inet_sport; + r->id.idiag_dport = inet->inet_dport; + r->id.idiag_src[0] = inet->inet_rcv_saddr; + r->id.idiag_dst[0] = inet->inet_daddr; #if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) if (r->idiag_family == AF_INET6) { @@ -504,11 +504,11 @@ static int inet_csk_diag_dump(struct sock *sk, } else #endif { - entry.saddr = &inet->rcv_saddr; - entry.daddr = &inet->daddr; + entry.saddr = &inet->inet_rcv_saddr; + entry.daddr = &inet->inet_daddr; } - entry.sport = inet->num; - entry.dport = ntohs(inet->dport); + entry.sport = inet->inet_num; + entry.dport = ntohs(inet->inet_dport); entry.userlocks = sk->sk_userlocks; if (!inet_diag_bc_run(RTA_DATA(bc), RTA_PAYLOAD(bc), &entry)) @@ -584,7 +584,7 @@ static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk, if (tmo < 0) tmo = 0; - r->id.idiag_sport = inet->sport; + r->id.idiag_sport = inet->inet_sport; r->id.idiag_dport = ireq->rmt_port; r->id.idiag_src[0] = ireq->loc_addr; r->id.idiag_dst[0] = ireq->rmt_addr; @@ -639,7 +639,7 @@ static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk, if (cb->nlh->nlmsg_len > 4 + NLMSG_SPACE(sizeof(*r))) { bc = (struct rtattr *)(r + 1); - entry.sport = inet->num; + entry.sport = inet->inet_num; entry.userlocks = sk->sk_userlocks; } @@ -732,7 +732,7 @@ static int inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) continue; } - if (r->id.idiag_sport != inet->sport && + if (r->id.idiag_sport != inet->inet_sport && r->id.idiag_sport) goto next_listen; @@ -774,7 +774,7 @@ skip_listen_ht: if (!(r->idiag_states & ~(TCPF_LISTEN | TCPF_SYN_RECV))) goto unlock; - for (i = s_i; i < hashinfo->ehash_size; i++) { + for (i = s_i; i <= hashinfo->ehash_mask; i++) { struct inet_ehash_bucket *head = &hashinfo->ehash[i]; spinlock_t *lock = inet_ehash_lockp(hashinfo, i); struct sock *sk; @@ -797,10 +797,10 @@ skip_listen_ht: goto next_normal; if (!(r->idiag_states & (1 << sk->sk_state))) goto next_normal; - if (r->id.idiag_sport != inet->sport && + if (r->id.idiag_sport != inet->inet_sport && r->id.idiag_sport) goto next_normal; - if (r->id.idiag_dport != inet->dport && + if (r->id.idiag_dport != inet->inet_dport && r->id.idiag_dport) goto next_normal; if (inet_csk_diag_dump(sk, skb, cb) < 0) { diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 625cc5f..21e5e32 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -64,7 +64,7 @@ void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb, atomic_inc(&hashinfo->bsockets); - inet_sk(sk)->num = snum; + inet_sk(sk)->inet_num = snum; sk_add_bind_node(sk, &tb->owners); tb->num_owners++; inet_csk(sk)->icsk_bind_hash = tb; @@ -76,7 +76,7 @@ void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb, static void __inet_put_port(struct sock *sk) { struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; - const int bhash = inet_bhashfn(sock_net(sk), inet_sk(sk)->num, + const int bhash = inet_bhashfn(sock_net(sk), inet_sk(sk)->inet_num, hashinfo->bhash_size); struct inet_bind_hashbucket *head = &hashinfo->bhash[bhash]; struct inet_bind_bucket *tb; @@ -88,7 +88,7 @@ static void __inet_put_port(struct sock *sk) __sk_del_bind_node(sk); tb->num_owners--; inet_csk(sk)->icsk_bind_hash = NULL; - inet_sk(sk)->num = 0; + inet_sk(sk)->inet_num = 0; inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb); spin_unlock(&head->lock); } @@ -105,7 +105,7 @@ EXPORT_SYMBOL(inet_put_port); void __inet_inherit_port(struct sock *sk, struct sock *child) { struct inet_hashinfo *table = sk->sk_prot->h.hashinfo; - const int bhash = inet_bhashfn(sock_net(sk), inet_sk(child)->num, + const int bhash = inet_bhashfn(sock_net(sk), inet_sk(child)->inet_num, table->bhash_size); struct inet_bind_hashbucket *head = &table->bhash[bhash]; struct inet_bind_bucket *tb; @@ -126,9 +126,9 @@ static inline int compute_score(struct sock *sk, struct net *net, int score = -1; struct inet_sock *inet = inet_sk(sk); - if (net_eq(sock_net(sk), net) && inet->num == hnum && + if (net_eq(sock_net(sk), net) && inet->inet_num == hnum && !ipv6_only_sock(sk)) { - __be32 rcv_saddr = inet->rcv_saddr; + __be32 rcv_saddr = inet->inet_rcv_saddr; score = sk->sk_family == PF_INET ? 1 : 0; if (rcv_saddr) { if (rcv_saddr != daddr) @@ -209,7 +209,7 @@ struct sock * __inet_lookup_established(struct net *net, * have wildcards anyways. */ unsigned int hash = inet_ehashfn(net, daddr, hnum, saddr, sport); - unsigned int slot = hash & (hashinfo->ehash_size - 1); + unsigned int slot = hash & hashinfo->ehash_mask; struct inet_ehash_bucket *head = &hashinfo->ehash[slot]; rcu_read_lock(); @@ -273,18 +273,20 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row, { struct inet_hashinfo *hinfo = death_row->hashinfo; struct inet_sock *inet = inet_sk(sk); - __be32 daddr = inet->rcv_saddr; - __be32 saddr = inet->daddr; + __be32 daddr = inet->inet_rcv_saddr; + __be32 saddr = inet->inet_daddr; int dif = sk->sk_bound_dev_if; INET_ADDR_COOKIE(acookie, saddr, daddr) - const __portpair ports = INET_COMBINED_PORTS(inet->dport, lport); + const __portpair ports = INET_COMBINED_PORTS(inet->inet_dport, lport); struct net *net = sock_net(sk); - unsigned int hash = inet_ehashfn(net, daddr, lport, saddr, inet->dport); + unsigned int hash = inet_ehashfn(net, daddr, lport, + saddr, inet->inet_dport); struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash); spinlock_t *lock = inet_ehash_lockp(hinfo, hash); struct sock *sk2; const struct hlist_nulls_node *node; struct inet_timewait_sock *tw; + int twrefcnt = 0; spin_lock(lock); @@ -312,25 +314,28 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row, unique: /* Must record num and sport now. Otherwise we will see * in hash table socket with a funny identity. */ - inet->num = lport; - inet->sport = htons(lport); + inet->inet_num = lport; + inet->inet_sport = htons(lport); sk->sk_hash = hash; WARN_ON(!sk_unhashed(sk)); __sk_nulls_add_node_rcu(sk, &head->chain); + if (tw) { + twrefcnt = inet_twsk_unhash(tw); + NET_INC_STATS_BH(net, LINUX_MIB_TIMEWAITRECYCLED); + } spin_unlock(lock); + if (twrefcnt) + inet_twsk_put(tw); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); if (twp) { *twp = tw; - NET_INC_STATS_BH(net, LINUX_MIB_TIMEWAITRECYCLED); } else if (tw) { /* Silly. Should hash-dance instead... */ inet_twsk_deschedule(tw, death_row); - NET_INC_STATS_BH(net, LINUX_MIB_TIMEWAITRECYCLED); inet_twsk_put(tw); } - return 0; not_unique: @@ -341,8 +346,9 @@ not_unique: static inline u32 inet_sk_port_offset(const struct sock *sk) { const struct inet_sock *inet = inet_sk(sk); - return secure_ipv4_port_ephemeral(inet->rcv_saddr, inet->daddr, - inet->dport); + return secure_ipv4_port_ephemeral(inet->inet_rcv_saddr, + inet->inet_daddr, + inet->inet_dport); } void __inet_hash_nolisten(struct sock *sk) @@ -424,7 +430,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, void (*hash)(struct sock *sk)) { struct inet_hashinfo *hinfo = death_row->hashinfo; - const unsigned short snum = inet_sk(sk)->num; + const unsigned short snum = inet_sk(sk)->inet_num; struct inet_bind_hashbucket *head; struct inet_bind_bucket *tb; int ret; @@ -452,7 +458,8 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, * unique enough. */ inet_bind_bucket_for_each(tb, node, &head->chain) { - if (ib_net(tb) == net && tb->port == port) { + if (net_eq(ib_net(tb), net) && + tb->port == port) { if (tb->fastreuse >= 0) goto next_port; WARN_ON(hlist_empty(&tb->owners)); @@ -485,7 +492,7 @@ ok: /* Head lock still held and bh's disabled */ inet_bind_hash(sk, tb, port); if (sk_unhashed(sk)) { - inet_sk(sk)->sport = htons(port); + inet_sk(sk)->inet_sport = htons(port); hash(sk); } spin_unlock(&head->lock); diff --git a/net/ipv4/inet_lro.c b/net/ipv4/inet_lro.c index 6a667da..47038cb 100644 --- a/net/ipv4/inet_lro.c +++ b/net/ipv4/inet_lro.c @@ -64,15 +64,15 @@ static int lro_tcp_ip_check(struct iphdr *iph, struct tcphdr *tcph, if (iph->ihl != IPH_LEN_WO_OPTIONS) return -1; - if (tcph->cwr || tcph->ece || tcph->urg || !tcph->ack - || tcph->rst || tcph->syn || tcph->fin) + if (tcph->cwr || tcph->ece || tcph->urg || !tcph->ack || + tcph->rst || tcph->syn || tcph->fin) return -1; if (INET_ECN_is_ce(ipv4_get_dsfield(iph))) return -1; - if (tcph->doff != TCPH_LEN_WO_OPTIONS - && tcph->doff != TCPH_LEN_W_TIMESTAMP) + if (tcph->doff != TCPH_LEN_WO_OPTIONS && + tcph->doff != TCPH_LEN_W_TIMESTAMP) return -1; /* check tcp options (only timestamp allowed) */ @@ -262,10 +262,10 @@ static int lro_check_tcp_conn(struct net_lro_desc *lro_desc, struct iphdr *iph, struct tcphdr *tcph) { - if ((lro_desc->iph->saddr != iph->saddr) - || (lro_desc->iph->daddr != iph->daddr) - || (lro_desc->tcph->source != tcph->source) - || (lro_desc->tcph->dest != tcph->dest)) + if ((lro_desc->iph->saddr != iph->saddr) || + (lro_desc->iph->daddr != iph->daddr) || + (lro_desc->tcph->source != tcph->source) || + (lro_desc->tcph->dest != tcph->dest)) return -1; return 0; } @@ -339,9 +339,9 @@ static int __lro_proc_skb(struct net_lro_mgr *lro_mgr, struct sk_buff *skb, u64 flags; int vlan_hdr_len = 0; - if (!lro_mgr->get_skb_header - || lro_mgr->get_skb_header(skb, (void *)&iph, (void *)&tcph, - &flags, priv)) + if (!lro_mgr->get_skb_header || + lro_mgr->get_skb_header(skb, (void *)&iph, (void *)&tcph, + &flags, priv)) goto out; if (!(flags & LRO_IPV4) || !(flags & LRO_TCP)) @@ -351,8 +351,8 @@ static int __lro_proc_skb(struct net_lro_mgr *lro_mgr, struct sk_buff *skb, if (!lro_desc) goto out; - if ((skb->protocol == htons(ETH_P_8021Q)) - && !(lro_mgr->features & LRO_F_EXTRACT_VLAN_ID)) + if ((skb->protocol == htons(ETH_P_8021Q)) && + !(lro_mgr->features & LRO_F_EXTRACT_VLAN_ID)) vlan_hdr_len = VLAN_HLEN; if (!lro_desc->active) { /* start new lro session */ @@ -446,9 +446,9 @@ static struct sk_buff *__lro_proc_segment(struct net_lro_mgr *lro_mgr, int hdr_len = LRO_MAX_PG_HLEN; int vlan_hdr_len = 0; - if (!lro_mgr->get_frag_header - || lro_mgr->get_frag_header(frags, (void *)&mac_hdr, (void *)&iph, - (void *)&tcph, &flags, priv)) { + if (!lro_mgr->get_frag_header || + lro_mgr->get_frag_header(frags, (void *)&mac_hdr, (void *)&iph, + (void *)&tcph, &flags, priv)) { mac_hdr = page_address(frags->page) + frags->page_offset; goto out1; } @@ -472,8 +472,8 @@ static struct sk_buff *__lro_proc_segment(struct net_lro_mgr *lro_mgr, if (!skb) goto out; - if ((skb->protocol == htons(ETH_P_8021Q)) - && !(lro_mgr->features & LRO_F_EXTRACT_VLAN_ID)) + if ((skb->protocol == htons(ETH_P_8021Q)) && + !(lro_mgr->features & LRO_F_EXTRACT_VLAN_ID)) vlan_hdr_len = VLAN_HLEN; iph = (void *)(skb->data + vlan_hdr_len); diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 13f0781..0fdf45e 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -14,22 +14,33 @@ #include <net/inet_timewait_sock.h> #include <net/ip.h> + +/* + * unhash a timewait socket from established hash + * lock must be hold by caller + */ +int inet_twsk_unhash(struct inet_timewait_sock *tw) +{ + if (hlist_nulls_unhashed(&tw->tw_node)) + return 0; + + hlist_nulls_del_rcu(&tw->tw_node); + sk_nulls_node_init(&tw->tw_node); + return 1; +} + /* Must be called with locally disabled BHs. */ static void __inet_twsk_kill(struct inet_timewait_sock *tw, struct inet_hashinfo *hashinfo) { struct inet_bind_hashbucket *bhead; struct inet_bind_bucket *tb; + int refcnt; /* Unlink from established hashes. */ spinlock_t *lock = inet_ehash_lockp(hashinfo, tw->tw_hash); spin_lock(lock); - if (hlist_nulls_unhashed(&tw->tw_node)) { - spin_unlock(lock); - return; - } - hlist_nulls_del_rcu(&tw->tw_node); - sk_nulls_node_init(&tw->tw_node); + refcnt = inet_twsk_unhash(tw); spin_unlock(lock); /* Disassociate with bind bucket. */ @@ -37,9 +48,12 @@ static void __inet_twsk_kill(struct inet_timewait_sock *tw, hashinfo->bhash_size)]; spin_lock(&bhead->lock); tb = tw->tw_tb; - __hlist_del(&tw->tw_bind_node); - tw->tw_tb = NULL; - inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb); + if (tb) { + __hlist_del(&tw->tw_bind_node); + tw->tw_tb = NULL; + inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb); + refcnt++; + } spin_unlock(&bhead->lock); #ifdef SOCK_REFCNT_DEBUG if (atomic_read(&tw->tw_refcnt) != 1) { @@ -47,7 +61,10 @@ static void __inet_twsk_kill(struct inet_timewait_sock *tw, tw->tw_prot->name, tw, atomic_read(&tw->tw_refcnt)); } #endif - inet_twsk_put(tw); + while (refcnt) { + inet_twsk_put(tw); + refcnt--; + } } static noinline void inet_twsk_free(struct inet_timewait_sock *tw) @@ -86,7 +103,7 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, Note, that any socket with inet->num != 0 MUST be bound in binding cache, even if it is closed. */ - bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), inet->num, + bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), inet->inet_num, hashinfo->bhash_size)]; spin_lock(&bhead->lock); tw->tw_tb = icsk->icsk_bind_hash; @@ -101,13 +118,22 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, * Should be done before removing sk from established chain * because readers are lockless and search established first. */ - atomic_inc(&tw->tw_refcnt); inet_twsk_add_node_rcu(tw, &ehead->twchain); /* Step 3: Remove SK from established hash. */ if (__sk_nulls_del_node_init_rcu(sk)) sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); + /* + * Notes : + * - We initially set tw_refcnt to 0 in inet_twsk_alloc() + * - We add one reference for the bhash link + * - We add one reference for the ehash link + * - We want this refcnt update done before allowing other + * threads to find this tw in ehash chain. + */ + atomic_add(1 + 1 + 1, &tw->tw_refcnt); + spin_unlock(lock); } @@ -124,14 +150,14 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, const int stat kmemcheck_annotate_bitfield(tw, flags); /* Give us an identity. */ - tw->tw_daddr = inet->daddr; - tw->tw_rcv_saddr = inet->rcv_saddr; + tw->tw_daddr = inet->inet_daddr; + tw->tw_rcv_saddr = inet->inet_rcv_saddr; tw->tw_bound_dev_if = sk->sk_bound_dev_if; - tw->tw_num = inet->num; + tw->tw_num = inet->inet_num; tw->tw_state = TCP_TIME_WAIT; tw->tw_substate = state; - tw->tw_sport = inet->sport; - tw->tw_dport = inet->dport; + tw->tw_sport = inet->inet_sport; + tw->tw_dport = inet->inet_dport; tw->tw_family = sk->sk_family; tw->tw_reuse = sk->sk_reuse; tw->tw_hash = sk->sk_hash; @@ -139,7 +165,12 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, const int stat tw->tw_transparent = inet->transparent; tw->tw_prot = sk->sk_prot_creator; twsk_net_set(tw, hold_net(sock_net(sk))); - atomic_set(&tw->tw_refcnt, 1); + /* + * Because we use RCU lookups, we should not set tw_refcnt + * to a non null value before everything is setup for this + * timewait socket. + */ + atomic_set(&tw->tw_refcnt, 0); inet_twsk_dead_node_init(tw); __module_get(tw->tw_prot->owner); } @@ -421,37 +452,46 @@ out: EXPORT_SYMBOL_GPL(inet_twdr_twcal_tick); -void inet_twsk_purge(struct net *net, struct inet_hashinfo *hashinfo, +void inet_twsk_purge(struct inet_hashinfo *hashinfo, struct inet_timewait_death_row *twdr, int family) { struct inet_timewait_sock *tw; struct sock *sk; struct hlist_nulls_node *node; - int h; + unsigned int slot; - local_bh_disable(); - for (h = 0; h < (hashinfo->ehash_size); h++) { - struct inet_ehash_bucket *head = - inet_ehash_bucket(hashinfo, h); - spinlock_t *lock = inet_ehash_lockp(hashinfo, h); + for (slot = 0; slot <= hashinfo->ehash_mask; slot++) { + struct inet_ehash_bucket *head = &hashinfo->ehash[slot]; +restart_rcu: + rcu_read_lock(); restart: - spin_lock(lock); - sk_nulls_for_each(sk, node, &head->twchain) { - + sk_nulls_for_each_rcu(sk, node, &head->twchain) { tw = inet_twsk(sk); - if (!net_eq(twsk_net(tw), net) || - tw->tw_family != family) + if ((tw->tw_family != family) || + atomic_read(&twsk_net(tw)->count)) + continue; + + if (unlikely(!atomic_inc_not_zero(&tw->tw_refcnt))) continue; - atomic_inc(&tw->tw_refcnt); - spin_unlock(lock); + if (unlikely((tw->tw_family != family) || + atomic_read(&twsk_net(tw)->count))) { + inet_twsk_put(tw); + goto restart; + } + + rcu_read_unlock(); inet_twsk_deschedule(tw, twdr); inet_twsk_put(tw); - - goto restart; + goto restart_rcu; } - spin_unlock(lock); + /* If the nulls value we got at the end of this lookup is + * not the expected one, we must restart lookup. + * We probably met an item that was moved to another chain. + */ + if (get_nulls_value(node) != slot) + goto restart; + rcu_read_unlock(); } - local_bh_enable(); } EXPORT_SYMBOL_GPL(inet_twsk_purge); diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index b1fbe18..6bcfe52 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -67,9 +67,6 @@ * ip_id_count: idlock */ -/* Exported for inet_getid inline function. */ -DEFINE_SPINLOCK(inet_peer_idlock); - static struct kmem_cache *peer_cachep __read_mostly; #define node_height(x) x->avl_height @@ -390,7 +387,7 @@ struct inet_peer *inet_getpeer(__be32 daddr, int create) n->v4daddr = daddr; atomic_set(&n->refcnt, 1); atomic_set(&n->rid, 0); - n->ip_id_count = secure_ip_id(daddr); + atomic_set(&n->ip_id_count, secure_ip_id(daddr)); n->tcp_ts_stamp = 0; write_lock_bh(&peer_pool_lock); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 301a389..86964b3 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -206,10 +206,11 @@ static void ip_expire(unsigned long arg) struct sk_buff *head = qp->q.fragments; /* Send an ICMP "Fragment Reassembly Timeout" message. */ - if ((head->dev = dev_get_by_index(net, qp->iif)) != NULL) { + rcu_read_lock(); + head->dev = dev_get_by_index_rcu(net, qp->iif); + if (head->dev) icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0); - dev_put(head->dev); - } + rcu_read_unlock(); } out: spin_unlock(&qp->q.lock); @@ -651,7 +652,7 @@ static int ip4_frags_ns_ctl_register(struct net *net) struct ctl_table_header *hdr; table = ip4_frags_ns_ctl_table; - if (net != &init_net) { + if (!net_eq(net, &init_net)) { table = kmemdup(table, sizeof(ip4_frags_ns_ctl_table), GFP_KERNEL); if (table == NULL) goto err_alloc; @@ -669,7 +670,7 @@ static int ip4_frags_ns_ctl_register(struct net *net) return 0; err_reg: - if (net != &init_net) + if (!net_eq(net, &init_net)) kfree(table); err_alloc: return -ENOMEM; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 1433338..f36ce15 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -125,7 +125,7 @@ static int ipgre_tunnel_bind_dev(struct net_device *dev); #define HASH_SIZE 16 -static int ipgre_net_id; +static int ipgre_net_id __read_mostly; struct ipgre_net { struct ip_tunnel *tunnels[4][HASH_SIZE]; @@ -156,8 +156,13 @@ struct ipgre_net { #define tunnels_r tunnels[2] #define tunnels_l tunnels[1] #define tunnels_wc tunnels[0] +/* + * Locking : hash tables are protected by RCU and a spinlock + */ +static DEFINE_SPINLOCK(ipgre_lock); -static DEFINE_RWLOCK(ipgre_lock); +#define for_each_ip_tunnel_rcu(start) \ + for (t = rcu_dereference(start); t; t = rcu_dereference(t->next)) /* Given src, dst and key, find appropriate for input tunnel. */ @@ -175,7 +180,7 @@ static struct ip_tunnel * ipgre_tunnel_lookup(struct net_device *dev, ARPHRD_ETHER : ARPHRD_IPGRE; int score, cand_score = 4; - for (t = ign->tunnels_r_l[h0^h1]; t; t = t->next) { + for_each_ip_tunnel_rcu(ign->tunnels_r_l[h0 ^ h1]) { if (local != t->parms.iph.saddr || remote != t->parms.iph.daddr || key != t->parms.i_key || @@ -200,7 +205,7 @@ static struct ip_tunnel * ipgre_tunnel_lookup(struct net_device *dev, } } - for (t = ign->tunnels_r[h0^h1]; t; t = t->next) { + for_each_ip_tunnel_rcu(ign->tunnels_r[h0 ^ h1]) { if (remote != t->parms.iph.daddr || key != t->parms.i_key || !(t->dev->flags & IFF_UP)) @@ -224,7 +229,7 @@ static struct ip_tunnel * ipgre_tunnel_lookup(struct net_device *dev, } } - for (t = ign->tunnels_l[h1]; t; t = t->next) { + for_each_ip_tunnel_rcu(ign->tunnels_l[h1]) { if ((local != t->parms.iph.saddr && (local != t->parms.iph.daddr || !ipv4_is_multicast(local))) || @@ -250,7 +255,7 @@ static struct ip_tunnel * ipgre_tunnel_lookup(struct net_device *dev, } } - for (t = ign->tunnels_wc[h1]; t; t = t->next) { + for_each_ip_tunnel_rcu(ign->tunnels_wc[h1]) { if (t->parms.i_key != key || !(t->dev->flags & IFF_UP)) continue; @@ -276,8 +281,9 @@ static struct ip_tunnel * ipgre_tunnel_lookup(struct net_device *dev, if (cand != NULL) return cand; - if (ign->fb_tunnel_dev->flags & IFF_UP) - return netdev_priv(ign->fb_tunnel_dev); + dev = ign->fb_tunnel_dev; + if (dev->flags & IFF_UP) + return netdev_priv(dev); return NULL; } @@ -311,10 +317,10 @@ static void ipgre_tunnel_link(struct ipgre_net *ign, struct ip_tunnel *t) { struct ip_tunnel **tp = ipgre_bucket(ign, t); + spin_lock_bh(&ipgre_lock); t->next = *tp; - write_lock_bh(&ipgre_lock); - *tp = t; - write_unlock_bh(&ipgre_lock); + rcu_assign_pointer(*tp, t); + spin_unlock_bh(&ipgre_lock); } static void ipgre_tunnel_unlink(struct ipgre_net *ign, struct ip_tunnel *t) @@ -323,9 +329,9 @@ static void ipgre_tunnel_unlink(struct ipgre_net *ign, struct ip_tunnel *t) for (tp = ipgre_bucket(ign, t); *tp; tp = &(*tp)->next) { if (t == *tp) { - write_lock_bh(&ipgre_lock); + spin_lock_bh(&ipgre_lock); *tp = t->next; - write_unlock_bh(&ipgre_lock); + spin_unlock_bh(&ipgre_lock); break; } } @@ -476,7 +482,7 @@ static void ipgre_err(struct sk_buff *skb, u32 info) break; } - read_lock(&ipgre_lock); + rcu_read_lock(); t = ipgre_tunnel_lookup(skb->dev, iph->daddr, iph->saddr, flags & GRE_KEY ? *(((__be32 *)p) + (grehlen / 4) - 1) : 0, @@ -494,7 +500,7 @@ static void ipgre_err(struct sk_buff *skb, u32 info) t->err_count = 1; t->err_time = jiffies; out: - read_unlock(&ipgre_lock); + rcu_read_unlock(); return; } @@ -573,7 +579,7 @@ static int ipgre_rcv(struct sk_buff *skb) gre_proto = *(__be16 *)(h + 2); - read_lock(&ipgre_lock); + rcu_read_lock(); if ((tunnel = ipgre_tunnel_lookup(skb->dev, iph->saddr, iph->daddr, key, gre_proto))) { @@ -647,13 +653,13 @@ static int ipgre_rcv(struct sk_buff *skb) ipgre_ecn_decapsulate(iph, skb); netif_rx(skb); - read_unlock(&ipgre_lock); + rcu_read_unlock(); return(0); } icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); drop: - read_unlock(&ipgre_lock); + rcu_read_unlock(); drop_nolock: kfree_skb(skb); return(0); @@ -662,7 +668,8 @@ drop_nolock: static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); - struct net_device_stats *stats = &tunnel->dev->stats; + struct net_device_stats *stats = &dev->stats; + struct netdev_queue *txq = netdev_get_tx_queue(dev, 0); struct iphdr *old_iph = ip_hdr(skb); struct iphdr *tiph; u8 tos; @@ -810,7 +817,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom); if (!new_skb) { ip_rt_put(rt); - stats->tx_dropped++; + txq->tx_dropped++; dev_kfree_skb(skb); return NETDEV_TX_OK; } @@ -1283,33 +1290,27 @@ static const struct net_protocol ipgre_protocol = { .netns_ok = 1, }; -static void ipgre_destroy_tunnels(struct ipgre_net *ign) +static void ipgre_destroy_tunnels(struct ipgre_net *ign, struct list_head *head) { int prio; for (prio = 0; prio < 4; prio++) { int h; for (h = 0; h < HASH_SIZE; h++) { - struct ip_tunnel *t; - while ((t = ign->tunnels[prio][h]) != NULL) - unregister_netdevice(t->dev); + struct ip_tunnel *t = ign->tunnels[prio][h]; + + while (t != NULL) { + unregister_netdevice_queue(t->dev, head); + t = t->next; + } } } } static int ipgre_init_net(struct net *net) { + struct ipgre_net *ign = net_generic(net, ipgre_net_id); int err; - struct ipgre_net *ign; - - err = -ENOMEM; - ign = kzalloc(sizeof(struct ipgre_net), GFP_KERNEL); - if (ign == NULL) - goto err_alloc; - - err = net_assign_generic(net, ipgre_net_id, ign); - if (err < 0) - goto err_assign; ign->fb_tunnel_dev = alloc_netdev(sizeof(struct ip_tunnel), "gre0", ipgre_tunnel_setup); @@ -1330,27 +1331,26 @@ static int ipgre_init_net(struct net *net) err_reg_dev: free_netdev(ign->fb_tunnel_dev); err_alloc_dev: - /* nothing */ -err_assign: - kfree(ign); -err_alloc: return err; } static void ipgre_exit_net(struct net *net) { struct ipgre_net *ign; + LIST_HEAD(list); ign = net_generic(net, ipgre_net_id); rtnl_lock(); - ipgre_destroy_tunnels(ign); + ipgre_destroy_tunnels(ign, &list); + unregister_netdevice_many(&list); rtnl_unlock(); - kfree(ign); } static struct pernet_operations ipgre_net_ops = { .init = ipgre_init_net, .exit = ipgre_exit_net, + .id = &ipgre_net_id, + .size = sizeof(struct ipgre_net), }; static int ipgre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[]) @@ -1471,7 +1471,7 @@ static void ipgre_tap_setup(struct net_device *dev) dev->features |= NETIF_F_NETNS_LOCAL; } -static int ipgre_newlink(struct net_device *dev, struct nlattr *tb[], +static int ipgre_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]) { struct ip_tunnel *nt; @@ -1670,7 +1670,7 @@ static int __init ipgre_init(void) return -EAGAIN; } - err = register_pernet_gen_device(&ipgre_net_id, &ipgre_net_ops); + err = register_pernet_device(&ipgre_net_ops); if (err < 0) goto gen_device_failed; @@ -1688,7 +1688,7 @@ out: tap_ops_failed: rtnl_link_unregister(&ipgre_link_ops); rtnl_link_failed: - unregister_pernet_gen_device(ipgre_net_id, &ipgre_net_ops); + unregister_pernet_device(&ipgre_net_ops); gen_device_failed: inet_del_protocol(&ipgre_protocol, IPPROTO_GRE); goto out; @@ -1698,7 +1698,7 @@ static void __exit ipgre_fini(void) { rtnl_link_unregister(&ipgre_tap_ops); rtnl_link_unregister(&ipgre_link_ops); - unregister_pernet_gen_device(ipgre_net_id, &ipgre_net_ops); + unregister_pernet_device(&ipgre_net_ops); if (inet_del_protocol(&ipgre_protocol, IPPROTO_GRE) < 0) printk(KERN_INFO "ipgre close: can't remove protocol\n"); } diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 6c98b43..c29de98 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -161,10 +161,10 @@ int ip_call_ra_chain(struct sk_buff *skb) /* If socket is bound to an interface, only report * the packet if it came from that interface. */ - if (sk && inet_sk(sk)->num == protocol && + if (sk && inet_sk(sk)->inet_num == protocol && (!sk->sk_bound_dev_if || sk->sk_bound_dev_if == dev->ifindex) && - sock_net(sk) == dev_net(dev)) { + net_eq(sock_net(sk), dev_net(dev))) { if (ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)) { if (ip_defrag(skb, IP_DEFRAG_CALL_RA_CHAIN)) { read_unlock(&ip_ra_lock); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index f989518..e34013a 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -264,9 +264,11 @@ int ip_mc_output(struct sk_buff *skb) This check is duplicated in ip_mr_input at the moment. */ - && ((rt->rt_flags&RTCF_LOCAL) || !(IPCB(skb)->flags&IPSKB_FORWARDED)) + && + ((rt->rt_flags & RTCF_LOCAL) || + !(IPCB(skb)->flags & IPSKB_FORWARDED)) #endif - ) { + ) { struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC); if (newskb) NF_HOOK(PF_INET, NF_INET_POST_ROUTING, newskb, @@ -329,7 +331,7 @@ int ip_queue_xmit(struct sk_buff *skb, int ipfragok) __be32 daddr; /* Use correct destination address if we have options. */ - daddr = inet->daddr; + daddr = inet->inet_daddr; if(opt && opt->srr) daddr = opt->faddr; @@ -338,13 +340,13 @@ int ip_queue_xmit(struct sk_buff *skb, int ipfragok) .mark = sk->sk_mark, .nl_u = { .ip4_u = { .daddr = daddr, - .saddr = inet->saddr, + .saddr = inet->inet_saddr, .tos = RT_CONN_FLAGS(sk) } }, .proto = sk->sk_protocol, .flags = inet_sk_flowi_flags(sk), .uli_u = { .ports = - { .sport = inet->sport, - .dport = inet->dport } } }; + { .sport = inet->inet_sport, + .dport = inet->inet_dport } } }; /* If this fails, retransmit mechanism of transport layer will * keep trying until route appears or the connection times @@ -379,7 +381,7 @@ packet_routed: if (opt && opt->optlen) { iph->ihl += opt->optlen >> 2; - ip_options_build(skb, opt, inet->daddr, rt, 0); + ip_options_build(skb, opt, inet->inet_daddr, rt, 0); } ip_select_ident_more(iph, &rt->u.dst, sk, @@ -501,8 +503,8 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) if (skb->sk) { frag->sk = skb->sk; frag->destructor = sock_wfree; - truesizes += frag->truesize; } + truesizes += frag->truesize; } /* Everything is OK. Generate! */ @@ -846,7 +848,8 @@ int ip_append_data(struct sock *sk, maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen; if (inet->cork.length + length > 0xFFFF - fragheaderlen) { - ip_local_error(sk, EMSGSIZE, rt->rt_dst, inet->dport, mtu-exthdrlen); + ip_local_error(sk, EMSGSIZE, rt->rt_dst, inet->inet_dport, + mtu-exthdrlen); return -EMSGSIZE; } @@ -1100,7 +1103,7 @@ ssize_t ip_append_page(struct sock *sk, struct page *page, maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen; if (inet->cork.length + size > 0xFFFF - fragheaderlen) { - ip_local_error(sk, EMSGSIZE, rt->rt_dst, inet->dport, mtu); + ip_local_error(sk, EMSGSIZE, rt->rt_dst, inet->inet_dport, mtu); return -EMSGSIZE; } diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index e982b5c..cafad9b 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -245,7 +245,7 @@ int ip_ra_control(struct sock *sk, unsigned char on, { struct ip_ra_chain *ra, *new_ra, **rap; - if (sk->sk_type != SOCK_RAW || inet_sk(sk)->num == IPPROTO_RAW) + if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num == IPPROTO_RAW) return -EINVAL; new_ra = on ? kmalloc(sizeof(*new_ra), GFP_KERNEL) : NULL; @@ -480,7 +480,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, case IP_OPTIONS: { struct ip_options *opt = NULL; - if (optlen > 40 || optlen < 0) + if (optlen > 40) goto e_inval; err = ip_options_get_from_user(sock_net(sk), &opt, optval, optlen); @@ -492,7 +492,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, if (sk->sk_family == PF_INET || (!((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) && - inet->daddr != LOOPBACK4_IPV6)) { + inet->inet_daddr != LOOPBACK4_IPV6)) { #endif if (inet->opt) icsk->icsk_ext_hdr_len -= inet->opt->optlen; @@ -575,7 +575,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, inet->hdrincl = val ? 1 : 0; break; case IP_MTU_DISCOVER: - if (val < 0 || val > 3) + if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_PROBE) goto e_inval; inet->pmtudisc = val; break; @@ -1180,8 +1180,8 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, if (inet->cmsg_flags & IP_CMSG_PKTINFO) { struct in_pktinfo info; - info.ipi_addr.s_addr = inet->rcv_saddr; - info.ipi_spec_dst.s_addr = inet->rcv_saddr; + info.ipi_addr.s_addr = inet->inet_rcv_saddr; + info.ipi_spec_dst.s_addr = inet->inet_rcv_saddr; info.ipi_ifindex = inet->mc_index; put_cmsg(&msg, SOL_IP, IP_PKTINFO, sizeof(info), &info); } diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index f8d04c2..4e08b7f 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -1172,10 +1172,9 @@ static int __init ic_dynamic(void) schedule_timeout_uninterruptible(1); #ifdef IPCONFIG_DHCP /* DHCP isn't done until we get a DHCPACK. */ - if ((ic_got_reply & IC_BOOTP) - && (ic_proto_enabled & IC_USE_DHCP) - && ic_dhcp_msgtype != DHCPACK) - { + if ((ic_got_reply & IC_BOOTP) && + (ic_proto_enabled & IC_USE_DHCP) && + ic_dhcp_msgtype != DHCPACK) { ic_got_reply = 0; printk(","); continue; @@ -1344,9 +1343,9 @@ static int __init ip_auto_config(void) */ if (ic_myaddr == NONE || #ifdef CONFIG_ROOT_NFS - (root_server_addr == NONE - && ic_servaddr == NONE - && ROOT_DEV == Root_NFS) || + (root_server_addr == NONE && + ic_servaddr == NONE && + ROOT_DEV == Root_NFS) || #endif ic_first_dev->next) { #ifdef IPCONFIG_DYNAMIC diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index ae40ed1..eda04fe 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -119,7 +119,7 @@ #define HASH_SIZE 16 #define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&0xF) -static int ipip_net_id; +static int ipip_net_id __read_mostly; struct ipip_net { struct ip_tunnel *tunnels_r_l[HASH_SIZE]; struct ip_tunnel *tunnels_r[HASH_SIZE]; @@ -134,7 +134,13 @@ static void ipip_fb_tunnel_init(struct net_device *dev); static void ipip_tunnel_init(struct net_device *dev); static void ipip_tunnel_setup(struct net_device *dev); -static DEFINE_RWLOCK(ipip_lock); +/* + * Locking : hash tables are protected by RCU and a spinlock + */ +static DEFINE_SPINLOCK(ipip_lock); + +#define for_each_ip_tunnel_rcu(start) \ + for (t = rcu_dereference(start); t; t = rcu_dereference(t->next)) static struct ip_tunnel * ipip_tunnel_lookup(struct net *net, __be32 remote, __be32 local) @@ -144,20 +150,21 @@ static struct ip_tunnel * ipip_tunnel_lookup(struct net *net, struct ip_tunnel *t; struct ipip_net *ipn = net_generic(net, ipip_net_id); - for (t = ipn->tunnels_r_l[h0^h1]; t; t = t->next) { + for_each_ip_tunnel_rcu(ipn->tunnels_r_l[h0 ^ h1]) if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP)) return t; - } - for (t = ipn->tunnels_r[h0]; t; t = t->next) { + + for_each_ip_tunnel_rcu(ipn->tunnels_r[h0]) if (remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP)) return t; - } - for (t = ipn->tunnels_l[h1]; t; t = t->next) { + + for_each_ip_tunnel_rcu(ipn->tunnels_l[h1]) if (local == t->parms.iph.saddr && (t->dev->flags&IFF_UP)) return t; - } - if ((t = ipn->tunnels_wc[0]) != NULL && (t->dev->flags&IFF_UP)) + + t = rcu_dereference(ipn->tunnels_wc[0]); + if (t && (t->dev->flags&IFF_UP)) return t; return NULL; } @@ -193,9 +200,9 @@ static void ipip_tunnel_unlink(struct ipip_net *ipn, struct ip_tunnel *t) for (tp = ipip_bucket(ipn, t); *tp; tp = &(*tp)->next) { if (t == *tp) { - write_lock_bh(&ipip_lock); + spin_lock_bh(&ipip_lock); *tp = t->next; - write_unlock_bh(&ipip_lock); + spin_unlock_bh(&ipip_lock); break; } } @@ -205,10 +212,10 @@ static void ipip_tunnel_link(struct ipip_net *ipn, struct ip_tunnel *t) { struct ip_tunnel **tp = ipip_bucket(ipn, t); + spin_lock_bh(&ipip_lock); t->next = *tp; - write_lock_bh(&ipip_lock); - *tp = t; - write_unlock_bh(&ipip_lock); + rcu_assign_pointer(*tp, t); + spin_unlock_bh(&ipip_lock); } static struct ip_tunnel * ipip_tunnel_locate(struct net *net, @@ -267,9 +274,9 @@ static void ipip_tunnel_uninit(struct net_device *dev) struct ipip_net *ipn = net_generic(net, ipip_net_id); if (dev == ipn->fb_tunnel_dev) { - write_lock_bh(&ipip_lock); + spin_lock_bh(&ipip_lock); ipn->tunnels_wc[0] = NULL; - write_unlock_bh(&ipip_lock); + spin_unlock_bh(&ipip_lock); } else ipip_tunnel_unlink(ipn, netdev_priv(dev)); dev_put(dev); @@ -318,7 +325,7 @@ static int ipip_err(struct sk_buff *skb, u32 info) err = -ENOENT; - read_lock(&ipip_lock); + rcu_read_lock(); t = ipip_tunnel_lookup(dev_net(skb->dev), iph->daddr, iph->saddr); if (t == NULL || t->parms.iph.daddr == 0) goto out; @@ -333,7 +340,7 @@ static int ipip_err(struct sk_buff *skb, u32 info) t->err_count = 1; t->err_time = jiffies; out: - read_unlock(&ipip_lock); + rcu_read_unlock(); return err; } @@ -351,11 +358,11 @@ static int ipip_rcv(struct sk_buff *skb) struct ip_tunnel *tunnel; const struct iphdr *iph = ip_hdr(skb); - read_lock(&ipip_lock); + rcu_read_lock(); if ((tunnel = ipip_tunnel_lookup(dev_net(skb->dev), iph->saddr, iph->daddr)) != NULL) { if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) { - read_unlock(&ipip_lock); + rcu_read_unlock(); kfree_skb(skb); return 0; } @@ -374,10 +381,10 @@ static int ipip_rcv(struct sk_buff *skb) nf_reset(skb); ipip_ecn_decapsulate(iph, skb); netif_rx(skb); - read_unlock(&ipip_lock); + rcu_read_unlock(); return 0; } - read_unlock(&ipip_lock); + rcu_read_unlock(); return -1; } @@ -390,7 +397,8 @@ static int ipip_rcv(struct sk_buff *skb) static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); - struct net_device_stats *stats = &tunnel->dev->stats; + struct net_device_stats *stats = &dev->stats; + struct netdev_queue *txq = netdev_get_tx_queue(dev, 0); struct iphdr *tiph = &tunnel->parms.iph; u8 tos = tunnel->parms.iph.tos; __be16 df = tiph->frag_off; @@ -480,7 +488,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom); if (!new_skb) { ip_rt_put(rt); - stats->tx_dropped++; + txq->tx_dropped++; dev_kfree_skb(skb); return NETDEV_TX_OK; } @@ -748,33 +756,27 @@ static struct xfrm_tunnel ipip_handler = { static const char banner[] __initconst = KERN_INFO "IPv4 over IPv4 tunneling driver\n"; -static void ipip_destroy_tunnels(struct ipip_net *ipn) +static void ipip_destroy_tunnels(struct ipip_net *ipn, struct list_head *head) { int prio; for (prio = 1; prio < 4; prio++) { int h; for (h = 0; h < HASH_SIZE; h++) { - struct ip_tunnel *t; - while ((t = ipn->tunnels[prio][h]) != NULL) - unregister_netdevice(t->dev); + struct ip_tunnel *t = ipn->tunnels[prio][h]; + + while (t != NULL) { + unregister_netdevice_queue(t->dev, head); + t = t->next; + } } } } static int ipip_init_net(struct net *net) { + struct ipip_net *ipn = net_generic(net, ipip_net_id); int err; - struct ipip_net *ipn; - - err = -ENOMEM; - ipn = kzalloc(sizeof(struct ipip_net), GFP_KERNEL); - if (ipn == NULL) - goto err_alloc; - - err = net_assign_generic(net, ipip_net_id, ipn); - if (err < 0) - goto err_assign; ipn->tunnels[0] = ipn->tunnels_wc; ipn->tunnels[1] = ipn->tunnels_l; @@ -801,27 +803,26 @@ err_reg_dev: free_netdev(ipn->fb_tunnel_dev); err_alloc_dev: /* nothing */ -err_assign: - kfree(ipn); -err_alloc: return err; } static void ipip_exit_net(struct net *net) { - struct ipip_net *ipn; + struct ipip_net *ipn = net_generic(net, ipip_net_id); + LIST_HEAD(list); - ipn = net_generic(net, ipip_net_id); rtnl_lock(); - ipip_destroy_tunnels(ipn); - unregister_netdevice(ipn->fb_tunnel_dev); + ipip_destroy_tunnels(ipn, &list); + unregister_netdevice_queue(ipn->fb_tunnel_dev, &list); + unregister_netdevice_many(&list); rtnl_unlock(); - kfree(ipn); } static struct pernet_operations ipip_net_ops = { .init = ipip_init_net, .exit = ipip_exit_net, + .id = &ipip_net_id, + .size = sizeof(struct ipip_net), }; static int __init ipip_init(void) @@ -835,7 +836,7 @@ static int __init ipip_init(void) return -EAGAIN; } - err = register_pernet_gen_device(&ipip_net_id, &ipip_net_ops); + err = register_pernet_device(&ipip_net_ops); if (err) xfrm4_tunnel_deregister(&ipip_handler, AF_INET); @@ -847,7 +848,7 @@ static void __exit ipip_fini(void) if (xfrm4_tunnel_deregister(&ipip_handler, AF_INET)) printk(KERN_INFO "ipip close: can't deregister tunnel\n"); - unregister_pernet_gen_device(ipip_net_id, &ipip_net_ops); + unregister_pernet_device(&ipip_net_ops); } module_init(ipip_init); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 99508d6..54596f7 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -275,7 +275,8 @@ failure: * @notify: Set to 1, if the caller is a notifier_call */ -static int vif_delete(struct net *net, int vifi, int notify) +static int vif_delete(struct net *net, int vifi, int notify, + struct list_head *head) { struct vif_device *v; struct net_device *dev; @@ -319,7 +320,7 @@ static int vif_delete(struct net *net, int vifi, int notify) } if (v->flags&(VIFF_TUNNEL|VIFF_REGISTER) && !notify) - unregister_netdevice(dev); + unregister_netdevice_queue(dev, head); dev_put(dev); return 0; @@ -469,8 +470,18 @@ static int vif_add(struct net *net, struct vifctl *vifc, int mrtsock) return err; } break; + + case VIFF_USE_IFINDEX: case 0: - dev = ip_dev_find(net, vifc->vifc_lcl_addr.s_addr); + if (vifc->vifc_flags == VIFF_USE_IFINDEX) { + dev = dev_get_by_index(net, vifc->vifc_lcl_ifindex); + if (dev && dev->ip_ptr == NULL) { + dev_put(dev); + return -EADDRNOTAVAIL; + } + } else + dev = ip_dev_find(net, vifc->vifc_lcl_addr.s_addr); + if (!dev) return -EADDRNOTAVAIL; err = dev_set_allmulti(dev, 1); @@ -862,14 +873,16 @@ static int ipmr_mfc_add(struct net *net, struct mfcctl *mfc, int mrtsock) static void mroute_clean_tables(struct net *net) { int i; + LIST_HEAD(list); /* * Shut down all active vif entries */ for (i = 0; i < net->ipv4.maxvif; i++) { if (!(net->ipv4.vif_table[i].flags&VIFF_STATIC)) - vif_delete(net, i, 0); + vif_delete(net, i, 0, &list); } + unregister_netdevice_many(&list); /* * Wipe the cache @@ -948,7 +961,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi switch (optname) { case MRT_INIT: if (sk->sk_type != SOCK_RAW || - inet_sk(sk)->num != IPPROTO_IGMP) + inet_sk(sk)->inet_num != IPPROTO_IGMP) return -EOPNOTSUPP; if (optlen != sizeof(int)) return -ENOPROTOOPT; @@ -985,7 +998,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi if (optname == MRT_ADD_VIF) { ret = vif_add(net, &vif, sk == net->ipv4.mroute_sk); } else { - ret = vif_delete(net, vif.vifc_vifi, 0); + ret = vif_delete(net, vif.vifc_vifi, 0, NULL); } rtnl_unlock(); return ret; @@ -1148,6 +1161,7 @@ static int ipmr_device_event(struct notifier_block *this, unsigned long event, v struct net *net = dev_net(dev); struct vif_device *v; int ct; + LIST_HEAD(list); if (!net_eq(dev_net(dev), net)) return NOTIFY_DONE; @@ -1157,8 +1171,9 @@ static int ipmr_device_event(struct notifier_block *this, unsigned long event, v v = &net->ipv4.vif_table[0]; for (ct = 0; ct < net->ipv4.maxvif; ct++, v++) { if (v->dev == dev) - vif_delete(net, ct, 1); + vif_delete(net, ct, 1, &list); } + unregister_netdevice_many(&list); return NOTIFY_DONE; } diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index db52c0c..c14623f 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -155,10 +155,10 @@ static int nf_ip_reroute(struct sk_buff *skb, if (entry->hook == NF_INET_LOCAL_OUT) { const struct iphdr *iph = ip_hdr(skb); - if (!(iph->tos == rt_info->tos - && skb->mark == rt_info->mark - && iph->daddr == rt_info->daddr - && iph->saddr == rt_info->saddr)) + if (!(iph->tos == rt_info->tos && + skb->mark == rt_info->mark && + iph->daddr == rt_info->daddr && + iph->saddr == rt_info->saddr)) return ip_route_me_harder(skb, RTN_UNSPEC); } return 0; diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 27774c9..0663276 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -384,11 +384,11 @@ static int mark_source_chains(struct xt_table_info *newinfo, |= ((1 << hook) | (1 << NF_ARP_NUMHOOKS)); /* Unconditional return/END. */ - if ((e->target_offset == sizeof(struct arpt_entry) - && (strcmp(t->target.u.user.name, - ARPT_STANDARD_TARGET) == 0) - && t->verdict < 0 - && unconditional(&e->arp)) || visited) { + if ((e->target_offset == sizeof(struct arpt_entry) && + (strcmp(t->target.u.user.name, + ARPT_STANDARD_TARGET) == 0) && + t->verdict < 0 && unconditional(&e->arp)) || + visited) { unsigned int oldpos, size; if ((strcmp(t->target.u.user.name, @@ -427,8 +427,8 @@ static int mark_source_chains(struct xt_table_info *newinfo, int newpos = t->verdict; if (strcmp(t->target.u.user.name, - ARPT_STANDARD_TARGET) == 0 - && newpos >= 0) { + ARPT_STANDARD_TARGET) == 0 && + newpos >= 0) { if (newpos > newinfo->size - sizeof(struct arpt_entry)) { duprintf("mark_source_chains: " @@ -559,8 +559,8 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e, { unsigned int h; - if ((unsigned long)e % __alignof__(struct arpt_entry) != 0 - || (unsigned char *)e + sizeof(struct arpt_entry) >= limit) { + if ((unsigned long)e % __alignof__(struct arpt_entry) != 0 || + (unsigned char *)e + sizeof(struct arpt_entry) >= limit) { duprintf("Bad offset %p\n", e); return -EINVAL; } @@ -1251,8 +1251,8 @@ check_compat_entry_size_and_hooks(struct compat_arpt_entry *e, int ret, off, h; duprintf("check_compat_entry_size_and_hooks %p\n", e); - if ((unsigned long)e % __alignof__(struct compat_arpt_entry) != 0 - || (unsigned char *)e + sizeof(struct compat_arpt_entry) >= limit) { + if ((unsigned long)e % __alignof__(struct compat_arpt_entry) != 0 || + (unsigned char *)e + sizeof(struct compat_arpt_entry) >= limit) { duprintf("Bad offset %p, limit = %p\n", e, limit); return -EINVAL; } diff --git a/net/ipv4/netfilter/ip_queue.c b/net/ipv4/netfilter/ip_queue.c index c9f90e8..2855f1f 100644 --- a/net/ipv4/netfilter/ip_queue.c +++ b/net/ipv4/netfilter/ip_queue.c @@ -497,10 +497,9 @@ ipq_rcv_nl_event(struct notifier_block *this, { struct netlink_notify *n = ptr; - if (event == NETLINK_URELEASE && - n->protocol == NETLINK_FIREWALL && n->pid) { + if (event == NETLINK_URELEASE && n->protocol == NETLINK_FIREWALL) { write_lock_bh(&queue_lock); - if ((n->net == &init_net) && (n->pid == peer_pid)) + if ((net_eq(n->net, &init_net)) && (n->pid == peer_pid)) __ipq_reset(); write_unlock_bh(&queue_lock); } @@ -621,7 +620,7 @@ cleanup_netlink_notifier: static void __exit ip_queue_fini(void) { nf_unregister_queue_handlers(&nfqh); - synchronize_net(); + ipq_flush(NULL, 0); #ifdef CONFIG_SYSCTL diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index cde755d..572330a 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -89,9 +89,9 @@ ip_packet_match(const struct iphdr *ip, #define FWINV(bool, invflg) ((bool) ^ !!(ipinfo->invflags & (invflg))) if (FWINV((ip->saddr&ipinfo->smsk.s_addr) != ipinfo->src.s_addr, - IPT_INV_SRCIP) - || FWINV((ip->daddr&ipinfo->dmsk.s_addr) != ipinfo->dst.s_addr, - IPT_INV_DSTIP)) { + IPT_INV_SRCIP) || + FWINV((ip->daddr&ipinfo->dmsk.s_addr) != ipinfo->dst.s_addr, + IPT_INV_DSTIP)) { dprintf("Source or dest mismatch.\n"); dprintf("SRC: %pI4. Mask: %pI4. Target: %pI4.%s\n", @@ -122,8 +122,8 @@ ip_packet_match(const struct iphdr *ip, } /* Check specific protocol */ - if (ipinfo->proto - && FWINV(ip->protocol != ipinfo->proto, IPT_INV_PROTO)) { + if (ipinfo->proto && + FWINV(ip->protocol != ipinfo->proto, IPT_INV_PROTO)) { dprintf("Packet protocol %hi does not match %hi.%s\n", ip->protocol, ipinfo->proto, ipinfo->invflags&IPT_INV_PROTO ? " (INV)":""); @@ -246,11 +246,11 @@ get_chainname_rulenum(struct ipt_entry *s, struct ipt_entry *e, } else if (s == e) { (*rulenum)++; - if (s->target_offset == sizeof(struct ipt_entry) - && strcmp(t->target.u.kernel.target->name, - IPT_STANDARD_TARGET) == 0 - && t->verdict < 0 - && unconditional(&s->ip)) { + if (s->target_offset == sizeof(struct ipt_entry) && + strcmp(t->target.u.kernel.target->name, + IPT_STANDARD_TARGET) == 0 && + t->verdict < 0 && + unconditional(&s->ip)) { /* Tail of chains: STANDARD target (return/policy) */ *comment = *chainname == hookname ? comments[NF_IP_TRACE_COMMENT_POLICY] @@ -388,8 +388,8 @@ ipt_do_table(struct sk_buff *skb, back = get_entry(table_base, back->comefrom); continue; } - if (table_base + v != ipt_next_entry(e) - && !(e->ip.flags & IPT_F_GOTO)) { + if (table_base + v != ipt_next_entry(e) && + !(e->ip.flags & IPT_F_GOTO)) { /* Save old back ptr in next entry */ struct ipt_entry *next = ipt_next_entry(e); next->comefrom = (void *)back - table_base; @@ -473,11 +473,11 @@ mark_source_chains(struct xt_table_info *newinfo, e->comefrom |= ((1 << hook) | (1 << NF_INET_NUMHOOKS)); /* Unconditional return/END. */ - if ((e->target_offset == sizeof(struct ipt_entry) - && (strcmp(t->target.u.user.name, - IPT_STANDARD_TARGET) == 0) - && t->verdict < 0 - && unconditional(&e->ip)) || visited) { + if ((e->target_offset == sizeof(struct ipt_entry) && + (strcmp(t->target.u.user.name, + IPT_STANDARD_TARGET) == 0) && + t->verdict < 0 && unconditional(&e->ip)) || + visited) { unsigned int oldpos, size; if ((strcmp(t->target.u.user.name, @@ -524,8 +524,8 @@ mark_source_chains(struct xt_table_info *newinfo, int newpos = t->verdict; if (strcmp(t->target.u.user.name, - IPT_STANDARD_TARGET) == 0 - && newpos >= 0) { + IPT_STANDARD_TARGET) == 0 && + newpos >= 0) { if (newpos > newinfo->size - sizeof(struct ipt_entry)) { duprintf("mark_source_chains: " @@ -735,8 +735,8 @@ check_entry_size_and_hooks(struct ipt_entry *e, { unsigned int h; - if ((unsigned long)e % __alignof__(struct ipt_entry) != 0 - || (unsigned char *)e + sizeof(struct ipt_entry) >= limit) { + if ((unsigned long)e % __alignof__(struct ipt_entry) != 0 || + (unsigned char *)e + sizeof(struct ipt_entry) >= limit) { duprintf("Bad offset %p\n", e); return -EINVAL; } @@ -1548,8 +1548,8 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e, int ret, off, h; duprintf("check_compat_entry_size_and_hooks %p\n", e); - if ((unsigned long)e % __alignof__(struct compat_ipt_entry) != 0 - || (unsigned char *)e + sizeof(struct compat_ipt_entry) >= limit) { + if ((unsigned long)e % __alignof__(struct compat_ipt_entry) != 0 || + (unsigned char *)e + sizeof(struct compat_ipt_entry) >= limit) { duprintf("Bad offset %p, limit = %p\n", e, limit); return -EINVAL; } diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 2e4f98b..40ca2d2 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -303,9 +303,9 @@ clusterip_tg(struct sk_buff *skb, const struct xt_target_param *par) /* special case: ICMP error handling. conntrack distinguishes between * error messages (RELATED) and information requests (see below) */ - if (ip_hdr(skb)->protocol == IPPROTO_ICMP - && (ctinfo == IP_CT_RELATED - || ctinfo == IP_CT_RELATED+IP_CT_IS_REPLY)) + if (ip_hdr(skb)->protocol == IPPROTO_ICMP && + (ctinfo == IP_CT_RELATED || + ctinfo == IP_CT_RELATED + IP_CT_IS_REPLY)) return XT_CONTINUE; /* ip_conntrack_icmp guarantees us that we only have ICMP_ECHO, @@ -362,8 +362,8 @@ static bool clusterip_tg_check(const struct xt_tgchk_param *par) return false; } - if (e->ip.dmsk.s_addr != htonl(0xffffffff) - || e->ip.dst.s_addr == 0) { + if (e->ip.dmsk.s_addr != htonl(0xffffffff) || + e->ip.dst.s_addr == 0) { printk(KERN_ERR "CLUSTERIP: Please specify destination IP\n"); return false; } @@ -495,14 +495,14 @@ arp_mangle(unsigned int hook, struct clusterip_config *c; /* we don't care about non-ethernet and non-ipv4 ARP */ - if (arp->ar_hrd != htons(ARPHRD_ETHER) - || arp->ar_pro != htons(ETH_P_IP) - || arp->ar_pln != 4 || arp->ar_hln != ETH_ALEN) + if (arp->ar_hrd != htons(ARPHRD_ETHER) || + arp->ar_pro != htons(ETH_P_IP) || + arp->ar_pln != 4 || arp->ar_hln != ETH_ALEN) return NF_ACCEPT; /* we only want to mangle arp requests and replies */ - if (arp->ar_op != htons(ARPOP_REPLY) - && arp->ar_op != htons(ARPOP_REQUEST)) + if (arp->ar_op != htons(ARPOP_REPLY) && + arp->ar_op != htons(ARPOP_REQUEST)) return NF_ACCEPT; payload = (void *)(arp+1); diff --git a/net/ipv4/netfilter/ipt_ECN.c b/net/ipv4/netfilter/ipt_ECN.c index f7e2fa0..549e206 100644 --- a/net/ipv4/netfilter/ipt_ECN.c +++ b/net/ipv4/netfilter/ipt_ECN.c @@ -85,8 +85,8 @@ ecn_tg(struct sk_buff *skb, const struct xt_target_param *par) if (!set_ect_ip(skb, einfo)) return NF_DROP; - if (einfo->operation & (IPT_ECN_OP_SET_ECE | IPT_ECN_OP_SET_CWR) - && ip_hdr(skb)->protocol == IPPROTO_TCP) + if (einfo->operation & (IPT_ECN_OP_SET_ECE | IPT_ECN_OP_SET_CWR) && + ip_hdr(skb)->protocol == IPPROTO_TCP) if (!set_ect_tcp(skb, einfo)) return NF_DROP; @@ -108,8 +108,8 @@ static bool ecn_tg_check(const struct xt_tgchk_param *par) einfo->ip_ect); return false; } - if ((einfo->operation & (IPT_ECN_OP_SET_ECE|IPT_ECN_OP_SET_CWR)) - && (e->ip.proto != IPPROTO_TCP || (e->ip.invflags & XT_INV_PROTO))) { + if ((einfo->operation & (IPT_ECN_OP_SET_ECE|IPT_ECN_OP_SET_CWR)) && + (e->ip.proto != IPPROTO_TCP || (e->ip.invflags & XT_INV_PROTO))) { printk(KERN_WARNING "ECN: cannot use TCP operations on a " "non-tcp rule\n"); return false; diff --git a/net/ipv4/netfilter/ipt_LOG.c b/net/ipv4/netfilter/ipt_LOG.c index acc44c6..ee128ef 100644 --- a/net/ipv4/netfilter/ipt_LOG.c +++ b/net/ipv4/netfilter/ipt_LOG.c @@ -74,8 +74,8 @@ static void dump_packet(const struct nf_loginfo *info, if (ntohs(ih->frag_off) & IP_OFFSET) printk("FRAG:%u ", ntohs(ih->frag_off) & IP_OFFSET); - if ((logflags & IPT_LOG_IPOPT) - && ih->ihl * 4 > sizeof(struct iphdr)) { + if ((logflags & IPT_LOG_IPOPT) && + ih->ihl * 4 > sizeof(struct iphdr)) { const unsigned char *op; unsigned char _opt[4 * 15 - sizeof(struct iphdr)]; unsigned int i, optsize; @@ -146,8 +146,8 @@ static void dump_packet(const struct nf_loginfo *info, /* Max length: 11 "URGP=65535 " */ printk("URGP=%u ", ntohs(th->urg_ptr)); - if ((logflags & IPT_LOG_TCPOPT) - && th->doff * 4 > sizeof(struct tcphdr)) { + if ((logflags & IPT_LOG_TCPOPT) && + th->doff * 4 > sizeof(struct tcphdr)) { unsigned char _opt[4 * 15 - sizeof(struct tcphdr)]; const unsigned char *op; unsigned int i, optsize; @@ -238,9 +238,9 @@ static void dump_packet(const struct nf_loginfo *info, printk("TYPE=%u CODE=%u ", ich->type, ich->code); /* Max length: 25 "INCOMPLETE [65535 bytes] " */ - if (ich->type <= NR_ICMP_TYPES - && required_len[ich->type] - && skb->len-iphoff-ih->ihl*4 < required_len[ich->type]) { + if (ich->type <= NR_ICMP_TYPES && + required_len[ich->type] && + skb->len-iphoff-ih->ihl*4 < required_len[ich->type]) { printk("INCOMPLETE [%u bytes] ", skb->len - iphoff - ih->ihl*4); break; @@ -276,8 +276,8 @@ static void dump_packet(const struct nf_loginfo *info, } /* Max length: 10 "MTU=65535 " */ - if (ich->type == ICMP_DEST_UNREACH - && ich->code == ICMP_FRAG_NEEDED) + if (ich->type == ICMP_DEST_UNREACH && + ich->code == ICMP_FRAG_NEEDED) printk("MTU=%u ", ntohs(ich->un.frag.mtu)); } break; @@ -407,8 +407,8 @@ ipt_log_packet(u_int8_t pf, if (in && !out) { /* MAC logging for input chain only. */ printk("MAC="); - if (skb->dev && skb->dev->hard_header_len - && skb->mac_header != skb->network_header) { + if (skb->dev && skb->dev->hard_header_len && + skb->mac_header != skb->network_header) { int i; const unsigned char *p = skb_mac_header(skb); for (i = 0; i < skb->dev->hard_header_len; i++,p++) diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c index dada086..650b540 100644 --- a/net/ipv4/netfilter/ipt_MASQUERADE.c +++ b/net/ipv4/netfilter/ipt_MASQUERADE.c @@ -59,8 +59,8 @@ masquerade_tg(struct sk_buff *skb, const struct xt_target_param *par) ct = nf_ct_get(skb, &ctinfo); nat = nfct_nat(ct); - NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED - || ctinfo == IP_CT_RELATED + IP_CT_IS_REPLY)); + NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || + ctinfo == IP_CT_RELATED + IP_CT_IS_REPLY)); /* Source address is 0.0.0.0 - locally generated packet that is * probably not supposed to be masqueraded. diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c index c93ae44..5113b8f 100644 --- a/net/ipv4/netfilter/ipt_REJECT.c +++ b/net/ipv4/netfilter/ipt_REJECT.c @@ -184,8 +184,8 @@ static bool reject_tg_check(const struct xt_tgchk_param *par) return false; } else if (rejinfo->with == IPT_TCP_RESET) { /* Must specify that it's a TCP packet */ - if (e->ip.proto != IPPROTO_TCP - || (e->ip.invflags & XT_INV_PROTO)) { + if (e->ip.proto != IPPROTO_TCP || + (e->ip.invflags & XT_INV_PROTO)) { printk("ipt_REJECT: TCP_RESET invalid for non-tcp\n"); return false; } diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c index d32cc4b..399061c 100644 --- a/net/ipv4/netfilter/ipt_ULOG.c +++ b/net/ipv4/netfilter/ipt_ULOG.c @@ -226,9 +226,9 @@ static void ipt_ulog_packet(unsigned int hooknum, else *(pm->prefix) = '\0'; - if (in && in->hard_header_len > 0 - && skb->mac_header != skb->network_header - && in->hard_header_len <= ULOG_MAC_LEN) { + if (in && in->hard_header_len > 0 && + skb->mac_header != skb->network_header && + in->hard_header_len <= ULOG_MAC_LEN) { memcpy(pm->mac, skb_mac_header(skb), in->hard_header_len); pm->mac_len = in->hard_header_len; } else diff --git a/net/ipv4/netfilter/ipt_ecn.c b/net/ipv4/netfilter/ipt_ecn.c index 6289b64..2a1e56b 100644 --- a/net/ipv4/netfilter/ipt_ecn.c +++ b/net/ipv4/netfilter/ipt_ecn.c @@ -96,8 +96,8 @@ static bool ecn_mt_check(const struct xt_mtchk_param *par) if (info->invert & IPT_ECN_OP_MATCH_MASK) return false; - if (info->operation & (IPT_ECN_OP_MATCH_ECE|IPT_ECN_OP_MATCH_CWR) - && ip->proto != IPPROTO_TCP) { + if (info->operation & (IPT_ECN_OP_MATCH_ECE|IPT_ECN_OP_MATCH_CWR) && + ip->proto != IPPROTO_TCP) { printk(KERN_WARNING "ipt_ecn: can't match TCP bits in rule for" " non-tcp packets\n"); return false; diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index 036047f..fae78c3 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -130,8 +130,8 @@ ipt_local_hook(unsigned int hook, u_int32_t mark; /* root is playing with raw sockets. */ - if (skb->len < sizeof(struct iphdr) - || ip_hdrlen(skb) < sizeof(struct iphdr)) + if (skb->len < sizeof(struct iphdr) || + ip_hdrlen(skb) < sizeof(struct iphdr)) return NF_ACCEPT; /* Save things which could affect route */ diff --git a/net/ipv4/netfilter/iptable_security.c b/net/ipv4/netfilter/iptable_security.c index 99eb76c6..3bd3d63 100644 --- a/net/ipv4/netfilter/iptable_security.c +++ b/net/ipv4/netfilter/iptable_security.c @@ -94,8 +94,8 @@ ipt_local_out_hook(unsigned int hook, int (*okfn)(struct sk_buff *)) { /* Somebody is playing with raw sockets. */ - if (skb->len < sizeof(struct iphdr) - || ip_hdrlen(skb) < sizeof(struct iphdr)) + if (skb->len < sizeof(struct iphdr) || + ip_hdrlen(skb) < sizeof(struct iphdr)) return NF_ACCEPT; return ipt_do_table(skb, hook, in, out, dev_net(out)->ipv4.iptable_security); diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index 092d68f..d171b12 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -247,10 +247,10 @@ getorigdst(struct sock *sk, int optval, void __user *user, int *len) struct nf_conntrack_tuple tuple; memset(&tuple, 0, sizeof(tuple)); - tuple.src.u3.ip = inet->rcv_saddr; - tuple.src.u.tcp.port = inet->sport; - tuple.dst.u3.ip = inet->daddr; - tuple.dst.u.tcp.port = inet->dport; + tuple.src.u3.ip = inet->inet_rcv_saddr; + tuple.src.u.tcp.port = inet->inet_sport; + tuple.dst.u3.ip = inet->inet_daddr; + tuple.dst.u.tcp.port = inet->inet_dport; tuple.src.l3num = PF_INET; tuple.dst.protonum = sk->sk_protocol; diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c index 9072058..7afd39b 100644 --- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c +++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c @@ -54,8 +54,8 @@ static const u_int8_t invmap[] = { static bool icmp_invert_tuple(struct nf_conntrack_tuple *tuple, const struct nf_conntrack_tuple *orig) { - if (orig->dst.u.icmp.type >= sizeof(invmap) - || !invmap[orig->dst.u.icmp.type]) + if (orig->dst.u.icmp.type >= sizeof(invmap) || + !invmap[orig->dst.u.icmp.type]) return false; tuple->src.u.icmp.id = orig->src.u.icmp.id; @@ -101,8 +101,8 @@ static bool icmp_new(struct nf_conn *ct, const struct sk_buff *skb, [ICMP_ADDRESS] = 1 }; - if (ct->tuplehash[0].tuple.dst.u.icmp.type >= sizeof(valid_new) - || !valid_new[ct->tuplehash[0].tuple.dst.u.icmp.type]) { + if (ct->tuplehash[0].tuple.dst.u.icmp.type >= sizeof(valid_new) || + !valid_new[ct->tuplehash[0].tuple.dst.u.icmp.type]) { /* Can't create a new ICMP `conn' with this. */ pr_debug("icmp: can't create new conn with type %u\n", ct->tuplehash[0].tuple.dst.u.icmp.type); @@ -201,11 +201,11 @@ icmp_error(struct net *net, struct sk_buff *skb, unsigned int dataoff, } /* Need to track icmp error message? */ - if (icmph->type != ICMP_DEST_UNREACH - && icmph->type != ICMP_SOURCE_QUENCH - && icmph->type != ICMP_TIME_EXCEEDED - && icmph->type != ICMP_PARAMETERPROB - && icmph->type != ICMP_REDIRECT) + if (icmph->type != ICMP_DEST_UNREACH && + icmph->type != ICMP_SOURCE_QUENCH && + icmph->type != ICMP_TIME_EXCEEDED && + icmph->type != ICMP_PARAMETERPROB && + icmph->type != ICMP_REDIRECT) return NF_ACCEPT; return icmp_error_message(net, skb, ctinfo, hooknum); @@ -238,17 +238,17 @@ static const struct nla_policy icmp_nla_policy[CTA_PROTO_MAX+1] = { static int icmp_nlattr_to_tuple(struct nlattr *tb[], struct nf_conntrack_tuple *tuple) { - if (!tb[CTA_PROTO_ICMP_TYPE] - || !tb[CTA_PROTO_ICMP_CODE] - || !tb[CTA_PROTO_ICMP_ID]) + if (!tb[CTA_PROTO_ICMP_TYPE] || + !tb[CTA_PROTO_ICMP_CODE] || + !tb[CTA_PROTO_ICMP_ID]) return -EINVAL; tuple->dst.u.icmp.type = nla_get_u8(tb[CTA_PROTO_ICMP_TYPE]); tuple->dst.u.icmp.code = nla_get_u8(tb[CTA_PROTO_ICMP_CODE]); tuple->src.u.icmp.id = nla_get_be16(tb[CTA_PROTO_ICMP_ID]); - if (tuple->dst.u.icmp.type >= sizeof(invmap) - || !invmap[tuple->dst.u.icmp.type]) + if (tuple->dst.u.icmp.type >= sizeof(invmap) || + !invmap[tuple->dst.u.icmp.type]) return -EINVAL; return 0; diff --git a/net/ipv4/netfilter/nf_nat_helper.c b/net/ipv4/netfilter/nf_nat_helper.c index f9520fa..7f10a6b 100644 --- a/net/ipv4/netfilter/nf_nat_helper.c +++ b/net/ipv4/netfilter/nf_nat_helper.c @@ -41,18 +41,14 @@ adjust_tcp_sequence(u32 seq, struct nf_conn *ct, enum ip_conntrack_info ctinfo) { - int dir; - struct nf_nat_seq *this_way, *other_way; + enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); struct nf_conn_nat *nat = nfct_nat(ct); + struct nf_nat_seq *this_way = &nat->seq[dir]; - pr_debug("adjust_tcp_sequence: seq = %u, sizediff = %d\n", seq, seq); - - dir = CTINFO2DIR(ctinfo); - - this_way = &nat->seq[dir]; - other_way = &nat->seq[!dir]; + pr_debug("adjust_tcp_sequence: seq = %u, sizediff = %d\n", + seq, sizediff); - pr_debug("nf_nat_resize_packet: Seq_offset before: "); + pr_debug("adjust_tcp_sequence: Seq_offset before: "); DUMP_OFFSET(this_way); spin_lock_bh(&nf_nat_seqofs_lock); @@ -63,13 +59,13 @@ adjust_tcp_sequence(u32 seq, * retransmit */ if (this_way->offset_before == this_way->offset_after || before(this_way->correction_pos, seq)) { - this_way->correction_pos = seq; - this_way->offset_before = this_way->offset_after; - this_way->offset_after += sizediff; + this_way->correction_pos = seq; + this_way->offset_before = this_way->offset_after; + this_way->offset_after += sizediff; } spin_unlock_bh(&nf_nat_seqofs_lock); - pr_debug("nf_nat_resize_packet: Seq_offset after: "); + pr_debug("adjust_tcp_sequence: Seq_offset after: "); DUMP_OFFSET(this_way); } diff --git a/net/ipv4/netfilter/nf_nat_standalone.c b/net/ipv4/netfilter/nf_nat_standalone.c index 5f41d01..5678e95 100644 --- a/net/ipv4/netfilter/nf_nat_standalone.c +++ b/net/ipv4/netfilter/nf_nat_standalone.c @@ -197,11 +197,11 @@ nf_nat_out(unsigned int hooknum, (ct = nf_ct_get(skb, &ctinfo)) != NULL) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); - if (ct->tuplehash[dir].tuple.src.u3.ip != - ct->tuplehash[!dir].tuple.dst.u3.ip - || ct->tuplehash[dir].tuple.src.u.all != - ct->tuplehash[!dir].tuple.dst.u.all - ) + if ((ct->tuplehash[dir].tuple.src.u3.ip != + ct->tuplehash[!dir].tuple.dst.u3.ip) || + (ct->tuplehash[dir].tuple.src.u.all != + ct->tuplehash[!dir].tuple.dst.u.all) + ) return ip_xfrm_me_harder(skb) == 0 ? ret : NF_DROP; } #endif diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index ab996f9..ce154b4 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -87,7 +87,7 @@ void raw_hash_sk(struct sock *sk) struct raw_hashinfo *h = sk->sk_prot->h.raw_hash; struct hlist_head *head; - head = &h->ht[inet_sk(sk)->num & (RAW_HTABLE_SIZE - 1)]; + head = &h->ht[inet_sk(sk)->inet_num & (RAW_HTABLE_SIZE - 1)]; write_lock_bh(&h->lock); sk_add_node(sk, head); @@ -115,9 +115,9 @@ static struct sock *__raw_v4_lookup(struct net *net, struct sock *sk, sk_for_each_from(sk, node) { struct inet_sock *inet = inet_sk(sk); - if (net_eq(sock_net(sk), net) && inet->num == num && - !(inet->daddr && inet->daddr != raddr) && - !(inet->rcv_saddr && inet->rcv_saddr != laddr) && + if (net_eq(sock_net(sk), net) && inet->inet_num == num && + !(inet->inet_daddr && inet->inet_daddr != raddr) && + !(inet->inet_rcv_saddr && inet->inet_rcv_saddr != laddr) && !(sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif)) goto found; /* gotcha */ } @@ -292,7 +292,6 @@ static int raw_rcv_skb(struct sock * sk, struct sk_buff * skb) /* Charge it to the socket. */ if (sock_queue_rcv_skb(sk, skb) < 0) { - atomic_inc(&sk->sk_drops); kfree_skb(skb); return NET_RX_DROP; } @@ -327,7 +326,7 @@ static int raw_send_hdrinc(struct sock *sk, void *from, size_t length, int err; if (length > rt->u.dst.dev->mtu) { - ip_local_error(sk, EMSGSIZE, rt->rt_dst, inet->dport, + ip_local_error(sk, EMSGSIZE, rt->rt_dst, inet->inet_dport, rt->u.dst.dev->mtu); return -EMSGSIZE; } @@ -500,10 +499,10 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, err = -EDESTADDRREQ; if (sk->sk_state != TCP_ESTABLISHED) goto out; - daddr = inet->daddr; + daddr = inet->inet_daddr; } - ipc.addr = inet->saddr; + ipc.addr = inet->inet_saddr; ipc.opt = NULL; ipc.shtx.flags = 0; ipc.oif = sk->sk_bound_dev_if; @@ -645,9 +644,9 @@ static int raw_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (addr->sin_addr.s_addr && chk_addr_ret != RTN_LOCAL && chk_addr_ret != RTN_MULTICAST && chk_addr_ret != RTN_BROADCAST) goto out; - inet->rcv_saddr = inet->saddr = addr->sin_addr.s_addr; + inet->inet_rcv_saddr = inet->inet_saddr = addr->sin_addr.s_addr; if (chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST) - inet->saddr = 0; /* Use device */ + inet->inet_saddr = 0; /* Use device */ sk_dst_reset(sk); ret = 0; out: return ret; @@ -692,7 +691,7 @@ static int raw_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if (err) goto done; - sock_recv_timestamp(msg, sk, skb); + sock_recv_ts_and_drops(msg, sk, skb); /* Copy the address. */ if (sin) { @@ -717,7 +716,7 @@ static int raw_init(struct sock *sk) { struct raw_sock *rp = raw_sk(sk); - if (inet_sk(sk)->num == IPPROTO_ICMP) + if (inet_sk(sk)->inet_num == IPPROTO_ICMP) memset(&rp->filter, 0, sizeof(rp->filter)); return 0; } @@ -754,7 +753,7 @@ static int do_raw_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen) { if (optname == ICMP_FILTER) { - if (inet_sk(sk)->num != IPPROTO_ICMP) + if (inet_sk(sk)->inet_num != IPPROTO_ICMP) return -EOPNOTSUPP; else return raw_seticmpfilter(sk, optval, optlen); @@ -784,7 +783,7 @@ static int do_raw_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { if (optname == ICMP_FILTER) { - if (inet_sk(sk)->num != IPPROTO_ICMP) + if (inet_sk(sk)->inet_num != IPPROTO_ICMP) return -EOPNOTSUPP; else return raw_geticmpfilter(sk, optval, optlen); @@ -943,10 +942,10 @@ EXPORT_SYMBOL_GPL(raw_seq_stop); static void raw_sock_seq_show(struct seq_file *seq, struct sock *sp, int i) { struct inet_sock *inet = inet_sk(sp); - __be32 dest = inet->daddr, - src = inet->rcv_saddr; + __be32 dest = inet->inet_daddr, + src = inet->inet_rcv_saddr; __u16 destp = 0, - srcp = inet->num; + srcp = inet->inet_num; seq_printf(seq, "%4d: %08X:%04X %08X:%04X" " %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %d\n", diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 0d9f584..e446496 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -513,43 +513,42 @@ static const struct file_operations rt_cpu_seq_fops = { }; #ifdef CONFIG_NET_CLS_ROUTE -static int ip_rt_acct_read(char *buffer, char **start, off_t offset, - int length, int *eof, void *data) -{ - unsigned int i; - - if ((offset & 3) || (length & 3)) - return -EIO; - - if (offset >= sizeof(struct ip_rt_acct) * 256) { - *eof = 1; - return 0; - } - - if (offset + length >= sizeof(struct ip_rt_acct) * 256) { - length = sizeof(struct ip_rt_acct) * 256 - offset; - *eof = 1; +static int rt_acct_proc_show(struct seq_file *m, void *v) +{ + struct ip_rt_acct *dst, *src; + unsigned int i, j; + + dst = kcalloc(256, sizeof(struct ip_rt_acct), GFP_KERNEL); + if (!dst) + return -ENOMEM; + + for_each_possible_cpu(i) { + src = (struct ip_rt_acct *)per_cpu_ptr(ip_rt_acct, i); + for (j = 0; j < 256; j++) { + dst[j].o_bytes += src[j].o_bytes; + dst[j].o_packets += src[j].o_packets; + dst[j].i_bytes += src[j].i_bytes; + dst[j].i_packets += src[j].i_packets; + } } - offset /= sizeof(u32); - - if (length > 0) { - u32 *dst = (u32 *) buffer; - - *start = buffer; - memset(dst, 0, length); - - for_each_possible_cpu(i) { - unsigned int j; - u32 *src; + seq_write(m, dst, 256 * sizeof(struct ip_rt_acct)); + kfree(dst); + return 0; +} - src = ((u32 *) per_cpu_ptr(ip_rt_acct, i)) + offset; - for (j = 0; j < length/4; j++) - dst[j] += src[j]; - } - } - return length; +static int rt_acct_proc_open(struct inode *inode, struct file *file) +{ + return single_open(file, rt_acct_proc_show, NULL); } + +static const struct file_operations rt_acct_proc_fops = { + .owner = THIS_MODULE, + .open = rt_acct_proc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; #endif static int __net_init ip_rt_do_proc_init(struct net *net) @@ -567,8 +566,7 @@ static int __net_init ip_rt_do_proc_init(struct net *net) goto err2; #ifdef CONFIG_NET_CLS_ROUTE - pde = create_proc_read_entry("rt_acct", 0, net->proc_net, - ip_rt_acct_read, NULL); + pde = proc_create("rt_acct", 0, net->proc_net, &rt_acct_proc_fops); if (!pde) goto err3; #endif @@ -703,7 +701,7 @@ static inline int compare_keys(struct flowi *fl1, struct flowi *fl2) static inline int compare_netns(struct rtable *rt1, struct rtable *rt2) { - return dev_net(rt1->u.dst.dev) == dev_net(rt2->u.dst.dev); + return net_eq(dev_net(rt1->u.dst.dev), dev_net(rt2->u.dst.dev)); } static inline int rt_is_expired(struct rtable *rth) @@ -902,6 +900,12 @@ void rt_cache_flush(struct net *net, int delay) rt_do_flush(!in_softirq()); } +/* Flush previous cache invalidated entries from the cache */ +void rt_cache_flush_batch(void) +{ + rt_do_flush(!in_softirq()); +} + /* * We change rt_genid and let gc do the cleanup */ @@ -1346,9 +1350,9 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, return; net = dev_net(dev); - if (new_gw == old_gw || !IN_DEV_RX_REDIRECTS(in_dev) - || ipv4_is_multicast(new_gw) || ipv4_is_lbcast(new_gw) - || ipv4_is_zeronet(new_gw)) + if (new_gw == old_gw || !IN_DEV_RX_REDIRECTS(in_dev) || + ipv4_is_multicast(new_gw) || ipv4_is_lbcast(new_gw) || + ipv4_is_zeronet(new_gw)) goto reject_redirect; if (!rt_caching(net)) @@ -1628,9 +1632,6 @@ unsigned short ip_rt_frag_needed(struct net *net, struct iphdr *iph, __be32 daddr = iph->daddr; unsigned short est_mtu = 0; - if (ipv4_config.no_pmtu_disc) - return 0; - for (k = 0; k < 2; k++) { for (i = 0; i < 2; i++) { unsigned hash = rt_hash(daddr, skeys[i], ikeys[k], @@ -2314,10 +2315,11 @@ skip_cache: ip_hdr(skb)->protocol); if (our #ifdef CONFIG_IP_MROUTE - || (!ipv4_is_local_multicast(daddr) && - IN_DEV_MFORWARD(in_dev)) + || + (!ipv4_is_local_multicast(daddr) && + IN_DEV_MFORWARD(in_dev)) #endif - ) { + ) { rcu_read_unlock(); return ip_route_input_mc(skb, daddr, saddr, tos, dev, our); @@ -2514,9 +2516,9 @@ static int ip_route_output_slow(struct net *net, struct rtable **rp, of another iface. --ANK */ - if (oldflp->oif == 0 - && (ipv4_is_multicast(oldflp->fl4_dst) || - oldflp->fl4_dst == htonl(0xFFFFFFFF))) { + if (oldflp->oif == 0 && + (ipv4_is_multicast(oldflp->fl4_dst) || + oldflp->fl4_dst == htonl(0xFFFFFFFF))) { /* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */ dev_out = ip_dev_find(net, oldflp->fl4_src); if (dev_out == NULL) @@ -2855,7 +2857,7 @@ static int rt_fill_info(struct net *net, error = rt->u.dst.error; expires = rt->u.dst.expires ? rt->u.dst.expires - jiffies : 0; if (rt->peer) { - id = rt->peer->ip_id_count; + id = atomic_read(&rt->peer->ip_id_count) & 0xffff; if (rt->peer->tcp_ts_stamp) { ts = rt->peer->tcp_ts; tsage = get_seconds() - rt->peer->tcp_ts_stamp; @@ -3257,7 +3259,7 @@ static __net_init int sysctl_route_net_init(struct net *net) struct ctl_table *tbl; tbl = ipv4_route_flush_table; - if (net != &init_net) { + if (!net_eq(net, &init_net)) { tbl = kmemdup(tbl, sizeof(ipv4_route_flush_table), GFP_KERNEL); if (tbl == NULL) goto err_dup; diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index a6e0e07..26399ad 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -253,6 +253,8 @@ EXPORT_SYMBOL(cookie_check_timestamp); struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, struct ip_options *opt) { + struct tcp_options_received tcp_opt; + u8 *hash_location; struct inet_request_sock *ireq; struct tcp_request_sock *treq; struct tcp_sock *tp = tcp_sk(sk); @@ -263,7 +265,6 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, int mss; struct rtable *rt; __u8 rcv_wscale; - struct tcp_options_received tcp_opt; if (!sysctl_tcp_syncookies || !th->ack) goto out; @@ -276,13 +277,6 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SYNCOOKIESRECV); - /* check for timestamp cookie support */ - memset(&tcp_opt, 0, sizeof(tcp_opt)); - tcp_parse_options(skb, &tcp_opt, 0); - - if (tcp_opt.saw_tstamp) - cookie_check_timestamp(&tcp_opt); - ret = NULL; req = inet_reqsk_alloc(&tcp_request_sock_ops); /* for safety */ if (!req) @@ -298,12 +292,6 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, ireq->loc_addr = ip_hdr(skb)->daddr; ireq->rmt_addr = ip_hdr(skb)->saddr; ireq->ecn_ok = 0; - ireq->snd_wscale = tcp_opt.snd_wscale; - ireq->rcv_wscale = tcp_opt.rcv_wscale; - ireq->sack_ok = tcp_opt.sack_ok; - ireq->wscale_ok = tcp_opt.wscale_ok; - ireq->tstamp_ok = tcp_opt.saw_tstamp; - req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0; /* We throwed the options of the initial SYN away, so we hope * the ACK carries the same options again (see RFC1122 4.2.3.8) @@ -333,7 +321,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, * no easy way to do this. */ { - struct flowi fl = { .nl_u = { .ip4_u = + struct flowi fl = { .mark = sk->sk_mark, + .nl_u = { .ip4_u = { .daddr = ((opt && opt->srr) ? opt->faddr : ireq->rmt_addr), @@ -351,6 +340,20 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, } } + /* check for timestamp cookie support */ + memset(&tcp_opt, 0, sizeof(tcp_opt)); + tcp_parse_options(skb, &tcp_opt, &hash_location, 0, &rt->u.dst); + + if (tcp_opt.saw_tstamp) + cookie_check_timestamp(&tcp_opt); + + ireq->snd_wscale = tcp_opt.snd_wscale; + ireq->rcv_wscale = tcp_opt.rcv_wscale; + ireq->sack_ok = tcp_opt.sack_ok; + ireq->wscale_ok = tcp_opt.wscale_ok; + ireq->tstamp_ok = tcp_opt.saw_tstamp; + req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0; + /* Try to redo what tcp_v4_send_synack did. */ req->window_clamp = tp->window_clamp ? :dst_metric(&rt->u.dst, RTAX_WINDOW); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 3000567..7e3712c 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -569,6 +569,13 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec, }, { + .procname = "tcp_cookie_size", + .data = &sysctl_tcp_cookie_size, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { .procname = "udp_mem", .data = &sysctl_udp_mem, .maxlen = sizeof(sysctl_udp_mem), @@ -660,7 +667,7 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) struct ctl_table *table; table = ipv4_net_table; - if (net != &init_net) { + if (!net_eq(net, &init_net)) { table = kmemdup(table, sizeof(ipv4_net_table), GFP_KERNEL); if (table == NULL) goto err_alloc; @@ -691,7 +698,7 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) return 0; err_reg: - if (net != &init_net) + if (!net_eq(net, &init_net)) kfree(table); err_alloc: return -ENOMEM; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index f1813bc..c8666b7 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -264,6 +264,7 @@ #include <linux/cache.h> #include <linux/err.h> #include <linux/crypto.h> +#include <linux/time.h> #include <net/icmp.h> #include <net/tcp.h> @@ -2042,7 +2043,7 @@ int tcp_disconnect(struct sock *sk, int flags) __skb_queue_purge(&sk->sk_async_wait_queue); #endif - inet->dport = 0; + inet->inet_dport = 0; if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) inet_reset_saddr(sk); @@ -2059,6 +2060,7 @@ int tcp_disconnect(struct sock *sk, int flags) tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tp->snd_cwnd_cnt = 0; tp->bytes_acked = 0; + tp->window_clamp = 0; tcp_set_ca_state(sk, TCP_CA_Open); tcp_clear_retrans(tp); inet_csk_delack_init(sk); @@ -2066,7 +2068,7 @@ int tcp_disconnect(struct sock *sk, int flags) memset(&tp->rx_opt, 0, sizeof(tp->rx_opt)); __sk_dst_reset(sk); - WARN_ON(inet->num && !icsk->icsk_bind_hash); + WARN_ON(inet->inet_num && !icsk->icsk_bind_hash); sk->sk_error_report(sk); return err; @@ -2083,8 +2085,9 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int val; int err = 0; - /* This is a string value all the others are int's */ - if (optname == TCP_CONGESTION) { + /* These are data/string values, all the others are ints */ + switch (optname) { + case TCP_CONGESTION: { char name[TCP_CA_NAME_MAX]; if (optlen < 1) @@ -2101,6 +2104,93 @@ static int do_tcp_setsockopt(struct sock *sk, int level, release_sock(sk); return err; } + case TCP_COOKIE_TRANSACTIONS: { + struct tcp_cookie_transactions ctd; + struct tcp_cookie_values *cvp = NULL; + + if (sizeof(ctd) > optlen) + return -EINVAL; + if (copy_from_user(&ctd, optval, sizeof(ctd))) + return -EFAULT; + + if (ctd.tcpct_used > sizeof(ctd.tcpct_value) || + ctd.tcpct_s_data_desired > TCP_MSS_DESIRED) + return -EINVAL; + + if (ctd.tcpct_cookie_desired == 0) { + /* default to global value */ + } else if ((0x1 & ctd.tcpct_cookie_desired) || + ctd.tcpct_cookie_desired > TCP_COOKIE_MAX || + ctd.tcpct_cookie_desired < TCP_COOKIE_MIN) { + return -EINVAL; + } + + if (TCP_COOKIE_OUT_NEVER & ctd.tcpct_flags) { + /* Supercedes all other values */ + lock_sock(sk); + if (tp->cookie_values != NULL) { + kref_put(&tp->cookie_values->kref, + tcp_cookie_values_release); + tp->cookie_values = NULL; + } + tp->rx_opt.cookie_in_always = 0; /* false */ + tp->rx_opt.cookie_out_never = 1; /* true */ + release_sock(sk); + return err; + } + + /* Allocate ancillary memory before locking. + */ + if (ctd.tcpct_used > 0 || + (tp->cookie_values == NULL && + (sysctl_tcp_cookie_size > 0 || + ctd.tcpct_cookie_desired > 0 || + ctd.tcpct_s_data_desired > 0))) { + cvp = kzalloc(sizeof(*cvp) + ctd.tcpct_used, + GFP_KERNEL); + if (cvp == NULL) + return -ENOMEM; + } + lock_sock(sk); + tp->rx_opt.cookie_in_always = + (TCP_COOKIE_IN_ALWAYS & ctd.tcpct_flags); + tp->rx_opt.cookie_out_never = 0; /* false */ + + if (tp->cookie_values != NULL) { + if (cvp != NULL) { + /* Changed values are recorded by a changed + * pointer, ensuring the cookie will differ, + * without separately hashing each value later. + */ + kref_put(&tp->cookie_values->kref, + tcp_cookie_values_release); + kref_init(&cvp->kref); + tp->cookie_values = cvp; + } else { + cvp = tp->cookie_values; + } + } + if (cvp != NULL) { + cvp->cookie_desired = ctd.tcpct_cookie_desired; + + if (ctd.tcpct_used > 0) { + memcpy(cvp->s_data_payload, ctd.tcpct_value, + ctd.tcpct_used); + cvp->s_data_desired = ctd.tcpct_used; + cvp->s_data_constant = 1; /* true */ + } else { + /* No constant payload data. */ + cvp->s_data_desired = ctd.tcpct_s_data_desired; + cvp->s_data_constant = 0; /* false */ + } + } + release_sock(sk); + return err; + } + default: + /* fallthru */ + break; + }; if (optlen < sizeof(int)) return -EINVAL; @@ -2425,6 +2515,47 @@ static int do_tcp_getsockopt(struct sock *sk, int level, if (copy_to_user(optval, icsk->icsk_ca_ops->name, len)) return -EFAULT; return 0; + + case TCP_COOKIE_TRANSACTIONS: { + struct tcp_cookie_transactions ctd; + struct tcp_cookie_values *cvp = tp->cookie_values; + + if (get_user(len, optlen)) + return -EFAULT; + if (len < sizeof(ctd)) + return -EINVAL; + + memset(&ctd, 0, sizeof(ctd)); + ctd.tcpct_flags = (tp->rx_opt.cookie_in_always ? + TCP_COOKIE_IN_ALWAYS : 0) + | (tp->rx_opt.cookie_out_never ? + TCP_COOKIE_OUT_NEVER : 0); + + if (cvp != NULL) { + ctd.tcpct_flags |= (cvp->s_data_in ? + TCP_S_DATA_IN : 0) + | (cvp->s_data_out ? + TCP_S_DATA_OUT : 0); + + ctd.tcpct_cookie_desired = cvp->cookie_desired; + ctd.tcpct_s_data_desired = cvp->s_data_desired; + + /* Cookie(s) saved, return as nonce */ + if (sizeof(ctd.tcpct_value) < cvp->cookie_pair_size) { + /* impossible? */ + return -EINVAL; + } + memcpy(&ctd.tcpct_value[0], &cvp->cookie_pair[0], + cvp->cookie_pair_size); + ctd.tcpct_used = cvp->cookie_pair_size; + } + + if (put_user(sizeof(ctd), optlen)) + return -EFAULT; + if (copy_to_user(optval, &ctd, sizeof(ctd))) + return -EFAULT; + return 0; + } default: return -ENOPROTOOPT; } @@ -2847,6 +2978,135 @@ EXPORT_SYMBOL(tcp_md5_hash_key); #endif +/** + * Each Responder maintains up to two secret values concurrently for + * efficient secret rollover. Each secret value has 4 states: + * + * Generating. (tcp_secret_generating != tcp_secret_primary) + * Generates new Responder-Cookies, but not yet used for primary + * verification. This is a short-term state, typically lasting only + * one round trip time (RTT). + * + * Primary. (tcp_secret_generating == tcp_secret_primary) + * Used both for generation and primary verification. + * + * Retiring. (tcp_secret_retiring != tcp_secret_secondary) + * Used for verification, until the first failure that can be + * verified by the newer Generating secret. At that time, this + * cookie's state is changed to Secondary, and the Generating + * cookie's state is changed to Primary. This is a short-term state, + * typically lasting only one round trip time (RTT). + * + * Secondary. (tcp_secret_retiring == tcp_secret_secondary) + * Used for secondary verification, after primary verification + * failures. This state lasts no more than twice the Maximum Segment + * Lifetime (2MSL). Then, the secret is discarded. + */ +struct tcp_cookie_secret { + /* The secret is divided into two parts. The digest part is the + * equivalent of previously hashing a secret and saving the state, + * and serves as an initialization vector (IV). The message part + * serves as the trailing secret. + */ + u32 secrets[COOKIE_WORKSPACE_WORDS]; + unsigned long expires; +}; + +#define TCP_SECRET_1MSL (HZ * TCP_PAWS_MSL) +#define TCP_SECRET_2MSL (HZ * TCP_PAWS_MSL * 2) +#define TCP_SECRET_LIFE (HZ * 600) + +static struct tcp_cookie_secret tcp_secret_one; +static struct tcp_cookie_secret tcp_secret_two; + +/* Essentially a circular list, without dynamic allocation. */ +static struct tcp_cookie_secret *tcp_secret_generating; +static struct tcp_cookie_secret *tcp_secret_primary; +static struct tcp_cookie_secret *tcp_secret_retiring; +static struct tcp_cookie_secret *tcp_secret_secondary; + +static DEFINE_SPINLOCK(tcp_secret_locker); + +/* Select a pseudo-random word in the cookie workspace. + */ +static inline u32 tcp_cookie_work(const u32 *ws, const int n) +{ + return ws[COOKIE_DIGEST_WORDS + ((COOKIE_MESSAGE_WORDS-1) & ws[n])]; +} + +/* Fill bakery[COOKIE_WORKSPACE_WORDS] with generator, updating as needed. + * Called in softirq context. + * Returns: 0 for success. + */ +int tcp_cookie_generator(u32 *bakery) +{ + unsigned long jiffy = jiffies; + + if (unlikely(time_after_eq(jiffy, tcp_secret_generating->expires))) { + spin_lock_bh(&tcp_secret_locker); + if (!time_after_eq(jiffy, tcp_secret_generating->expires)) { + /* refreshed by another */ + memcpy(bakery, + &tcp_secret_generating->secrets[0], + COOKIE_WORKSPACE_WORDS); + } else { + /* still needs refreshing */ + get_random_bytes(bakery, COOKIE_WORKSPACE_WORDS); + + /* The first time, paranoia assumes that the + * randomization function isn't as strong. But, + * this secret initialization is delayed until + * the last possible moment (packet arrival). + * Although that time is observable, it is + * unpredictably variable. Mash in the most + * volatile clock bits available, and expire the + * secret extra quickly. + */ + if (unlikely(tcp_secret_primary->expires == + tcp_secret_secondary->expires)) { + struct timespec tv; + + getnstimeofday(&tv); + bakery[COOKIE_DIGEST_WORDS+0] ^= + (u32)tv.tv_nsec; + + tcp_secret_secondary->expires = jiffy + + TCP_SECRET_1MSL + + (0x0f & tcp_cookie_work(bakery, 0)); + } else { + tcp_secret_secondary->expires = jiffy + + TCP_SECRET_LIFE + + (0xff & tcp_cookie_work(bakery, 1)); + tcp_secret_primary->expires = jiffy + + TCP_SECRET_2MSL + + (0x1f & tcp_cookie_work(bakery, 2)); + } + memcpy(&tcp_secret_secondary->secrets[0], + bakery, COOKIE_WORKSPACE_WORDS); + + rcu_assign_pointer(tcp_secret_generating, + tcp_secret_secondary); + rcu_assign_pointer(tcp_secret_retiring, + tcp_secret_primary); + /* + * Neither call_rcu() nor synchronize_rcu() needed. + * Retiring data is not freed. It is replaced after + * further (locked) pointer updates, and a quiet time + * (minimum 1MSL, maximum LIFE - 2MSL). + */ + } + spin_unlock_bh(&tcp_secret_locker); + } else { + rcu_read_lock_bh(); + memcpy(bakery, + &rcu_dereference(tcp_secret_generating)->secrets[0], + COOKIE_WORKSPACE_WORDS); + rcu_read_unlock_bh(); + } + return 0; +} +EXPORT_SYMBOL(tcp_cookie_generator); + void tcp_done(struct sock *sk) { if (sk->sk_state == TCP_SYN_SENT || sk->sk_state == TCP_SYN_RECV) @@ -2881,6 +3141,7 @@ void __init tcp_init(void) struct sk_buff *skb = NULL; unsigned long nr_pages, limit; int order, i, max_share; + unsigned long jiffy = jiffies; BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb)); @@ -2903,11 +3164,10 @@ void __init tcp_init(void) (totalram_pages >= 128 * 1024) ? 13 : 15, 0, - &tcp_hashinfo.ehash_size, NULL, + &tcp_hashinfo.ehash_mask, thash_entries ? 0 : 512 * 1024); - tcp_hashinfo.ehash_size = 1 << tcp_hashinfo.ehash_size; - for (i = 0; i < tcp_hashinfo.ehash_size; i++) { + for (i = 0; i <= tcp_hashinfo.ehash_mask; i++) { INIT_HLIST_NULLS_HEAD(&tcp_hashinfo.ehash[i].chain, i); INIT_HLIST_NULLS_HEAD(&tcp_hashinfo.ehash[i].twchain, i); } @@ -2916,7 +3176,7 @@ void __init tcp_init(void) tcp_hashinfo.bhash = alloc_large_system_hash("TCP bind", sizeof(struct inet_bind_hashbucket), - tcp_hashinfo.ehash_size, + tcp_hashinfo.ehash_mask + 1, (totalram_pages >= 128 * 1024) ? 13 : 15, 0, @@ -2971,10 +3231,19 @@ void __init tcp_init(void) sysctl_tcp_rmem[2] = max(87380, max_share); printk(KERN_INFO "TCP: Hash tables configured " - "(established %d bind %d)\n", - tcp_hashinfo.ehash_size, tcp_hashinfo.bhash_size); + "(established %u bind %u)\n", + tcp_hashinfo.ehash_mask + 1, tcp_hashinfo.bhash_size); tcp_register_congestion_control(&tcp_reno); + + memset(&tcp_secret_one.secrets[0], 0, sizeof(tcp_secret_one.secrets)); + memset(&tcp_secret_two.secrets[0], 0, sizeof(tcp_secret_two.secrets)); + tcp_secret_one.expires = jiffy; /* past due */ + tcp_secret_two.expires = jiffy; /* past due */ + tcp_secret_generating = &tcp_secret_one; + tcp_secret_primary = &tcp_secret_one; + tcp_secret_retiring = &tcp_secret_two; + tcp_secret_secondary = &tcp_secret_two; } EXPORT_SYMBOL(tcp_close); diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c index fcbcd4f..939edb3 100644 --- a/net/ipv4/tcp_diag.c +++ b/net/ipv4/tcp_diag.c @@ -27,7 +27,7 @@ static void tcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, r->idiag_rqueue = sk->sk_ack_backlog; r->idiag_wqueue = sk->sk_max_ack_backlog; } else { - r->idiag_rqueue = tp->rcv_nxt - tp->copied_seq; + r->idiag_rqueue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0); r->idiag_wqueue = tp->write_seq - tp->snd_una; } if (info != NULL) diff --git a/net/ipv4/tcp_htcp.c b/net/ipv4/tcp_htcp.c index 26d5c7f..7c94a49 100644 --- a/net/ipv4/tcp_htcp.c +++ b/net/ipv4/tcp_htcp.c @@ -92,8 +92,8 @@ static inline void measure_rtt(struct sock *sk, u32 srtt) if (icsk->icsk_ca_state == TCP_CA_Open) { if (ca->maxRTT < ca->minRTT) ca->maxRTT = ca->minRTT; - if (ca->maxRTT < srtt - && srtt <= ca->maxRTT + msecs_to_jiffies(20)) + if (ca->maxRTT < srtt && + srtt <= ca->maxRTT + msecs_to_jiffies(20)) ca->maxRTT = srtt; } } @@ -123,9 +123,9 @@ static void measure_achieved_throughput(struct sock *sk, u32 pkts_acked, s32 rtt ca->packetcount += pkts_acked; - if (ca->packetcount >= tp->snd_cwnd - (ca->alpha >> 7 ? : 1) - && now - ca->lasttime >= ca->minRTT - && ca->minRTT > 0) { + if (ca->packetcount >= tp->snd_cwnd - (ca->alpha >> 7 ? : 1) && + now - ca->lasttime >= ca->minRTT && + ca->minRTT > 0) { __u32 cur_Bi = ca->packetcount * HZ / (now - ca->lasttime); if (htcp_ccount(ca) <= 3) { diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index d86784b..57ae96a 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -140,7 +140,7 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb) * "len" is invariant segment length, including TCP header. */ len += skb->data - skb_transport_header(skb); - if (len >= TCP_MIN_RCVMSS + sizeof(struct tcphdr) || + if (len >= TCP_MSS_DEFAULT + sizeof(struct tcphdr) || /* If PSH is not set, packet should be * full sized, provided peer TCP is not badly broken. * This observation (if it is correct 8)) allows @@ -411,7 +411,7 @@ void tcp_initialize_rcv_mss(struct sock *sk) unsigned int hint = min_t(unsigned int, tp->advmss, tp->mss_cache); hint = min(hint, tp->rcv_wnd / 2); - hint = min(hint, TCP_MIN_RCVMSS); + hint = min(hint, TCP_MSS_DEFAULT); hint = max(hint, TCP_MIN_MSS); inet_csk(sk)->icsk_ack.rcv_mss = hint; @@ -2300,7 +2300,7 @@ static inline int tcp_fackets_out(struct tcp_sock *tp) * they differ. Since neither occurs due to loss, TCP should really * ignore them. */ -static inline int tcp_dupack_heurestics(struct tcp_sock *tp) +static inline int tcp_dupack_heuristics(struct tcp_sock *tp) { return tcp_is_fack(tp) ? tp->fackets_out : tp->sacked_out + 1; } @@ -2425,7 +2425,7 @@ static int tcp_time_to_recover(struct sock *sk) return 1; /* Not-A-Trick#2 : Classic rule... */ - if (tcp_dupack_heurestics(tp) > tp->reordering) + if (tcp_dupack_heuristics(tp) > tp->reordering) return 1; /* Trick#3 : when we use RFC2988 timer restart, fast @@ -3698,7 +3698,7 @@ old_ack: * the fast version below fails. */ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx, - int estab) + u8 **hvpp, int estab, struct dst_entry *dst) { unsigned char *ptr; struct tcphdr *th = tcp_hdr(skb); @@ -3737,7 +3737,8 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx, break; case TCPOPT_WINDOW: if (opsize == TCPOLEN_WINDOW && th->syn && - !estab && sysctl_tcp_window_scaling) { + !estab && sysctl_tcp_window_scaling && + !dst_feature(dst, RTAX_FEATURE_NO_WSCALE)) { __u8 snd_wscale = *(__u8 *)ptr; opt_rx->wscale_ok = 1; if (snd_wscale > 14) { @@ -3753,7 +3754,8 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx, case TCPOPT_TIMESTAMP: if ((opsize == TCPOLEN_TIMESTAMP) && ((estab && opt_rx->tstamp_ok) || - (!estab && sysctl_tcp_timestamps))) { + (!estab && sysctl_tcp_timestamps && + !dst_feature(dst, RTAX_FEATURE_NO_TSTAMP)))) { opt_rx->saw_tstamp = 1; opt_rx->rcv_tsval = get_unaligned_be32(ptr); opt_rx->rcv_tsecr = get_unaligned_be32(ptr + 4); @@ -3761,7 +3763,8 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx, break; case TCPOPT_SACK_PERM: if (opsize == TCPOLEN_SACK_PERM && th->syn && - !estab && sysctl_tcp_sack) { + !estab && sysctl_tcp_sack && + !dst_feature(dst, RTAX_FEATURE_NO_SACK)) { opt_rx->sack_ok = 1; tcp_sack_reset(opt_rx); } @@ -3782,7 +3785,30 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx, */ break; #endif - } + case TCPOPT_COOKIE: + /* This option is variable length. + */ + switch (opsize) { + case TCPOLEN_COOKIE_BASE: + /* not yet implemented */ + break; + case TCPOLEN_COOKIE_PAIR: + /* not yet implemented */ + break; + case TCPOLEN_COOKIE_MIN+0: + case TCPOLEN_COOKIE_MIN+2: + case TCPOLEN_COOKIE_MIN+4: + case TCPOLEN_COOKIE_MIN+6: + case TCPOLEN_COOKIE_MAX: + /* 16-bit multiple */ + opt_rx->cookie_plus = opsize; + *hvpp = ptr; + default: + /* ignore option */ + break; + }; + break; + }; ptr += opsize-2; length -= opsize; @@ -3810,17 +3836,20 @@ static int tcp_parse_aligned_timestamp(struct tcp_sock *tp, struct tcphdr *th) * If it is wrong it falls back on tcp_parse_options(). */ static int tcp_fast_parse_options(struct sk_buff *skb, struct tcphdr *th, - struct tcp_sock *tp) + struct tcp_sock *tp, u8 **hvpp) { - if (th->doff == sizeof(struct tcphdr) >> 2) { + /* In the spirit of fast parsing, compare doff directly to constant + * values. Because equality is used, short doff can be ignored here. + */ + if (th->doff == (sizeof(*th) / 4)) { tp->rx_opt.saw_tstamp = 0; return 0; } else if (tp->rx_opt.tstamp_ok && - th->doff == (sizeof(struct tcphdr)>>2)+(TCPOLEN_TSTAMP_ALIGNED>>2)) { + th->doff == ((sizeof(*th) + TCPOLEN_TSTAMP_ALIGNED) / 4)) { if (tcp_parse_aligned_timestamp(tp, th)) return 1; } - tcp_parse_options(skb, &tp->rx_opt, 1); + tcp_parse_options(skb, &tp->rx_opt, hvpp, 1, NULL); return 1; } @@ -4075,8 +4104,10 @@ static inline int tcp_sack_extend(struct tcp_sack_block *sp, u32 seq, static void tcp_dsack_set(struct sock *sk, u32 seq, u32 end_seq) { struct tcp_sock *tp = tcp_sk(sk); + struct dst_entry *dst = __sk_dst_get(sk); - if (tcp_is_sack(tp) && sysctl_tcp_dsack) { + if (tcp_is_sack(tp) && sysctl_tcp_dsack && + !dst_feature(dst, RTAX_FEATURE_NO_DSACK)) { int mib_idx; if (before(seq, tp->rcv_nxt)) @@ -4105,13 +4136,15 @@ static void tcp_dsack_extend(struct sock *sk, u32 seq, u32 end_seq) static void tcp_send_dupack(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); + struct dst_entry *dst = __sk_dst_get(sk); if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq && before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) { NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_DELAYEDACKLOST); tcp_enter_quickack_mode(sk); - if (tcp_is_sack(tp) && sysctl_tcp_dsack) { + if (tcp_is_sack(tp) && sysctl_tcp_dsack && + !dst_feature(dst, RTAX_FEATURE_NO_DSACK)) { u32 end_seq = TCP_SKB_CB(skb)->end_seq; if (after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt)) @@ -4845,11 +4878,11 @@ static void __tcp_ack_snd_check(struct sock *sk, int ofo_possible) struct tcp_sock *tp = tcp_sk(sk); /* More than one full frame received... */ - if (((tp->rcv_nxt - tp->rcv_wup) > inet_csk(sk)->icsk_ack.rcv_mss + if (((tp->rcv_nxt - tp->rcv_wup) > inet_csk(sk)->icsk_ack.rcv_mss && /* ... and right edge of window advances far enough. * (tcp_recvmsg() will send ACK otherwise). Or... */ - && __tcp_select_window(sk) >= tp->rcv_wnd) || + __tcp_select_window(sk) >= tp->rcv_wnd) || /* We ACK each frame or... */ tcp_in_quickack_mode(sk) || /* We have out of order data. */ @@ -5070,10 +5103,12 @@ out: static int tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, struct tcphdr *th, int syn_inerr) { + u8 *hash_location; struct tcp_sock *tp = tcp_sk(sk); /* RFC1323: H1. Apply PAWS check first. */ - if (tcp_fast_parse_options(skb, th, tp) && tp->rx_opt.saw_tstamp && + if (tcp_fast_parse_options(skb, th, tp, &hash_location) && + tp->rx_opt.saw_tstamp && tcp_paws_discard(sk, skb)) { if (!th->rst) { NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED); @@ -5361,11 +5396,14 @@ discard: static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, struct tcphdr *th, unsigned len) { - struct tcp_sock *tp = tcp_sk(sk); + u8 *hash_location; struct inet_connection_sock *icsk = inet_csk(sk); + struct tcp_sock *tp = tcp_sk(sk); + struct dst_entry *dst = __sk_dst_get(sk); + struct tcp_cookie_values *cvp = tp->cookie_values; int saved_clamp = tp->rx_opt.mss_clamp; - tcp_parse_options(skb, &tp->rx_opt, 0); + tcp_parse_options(skb, &tp->rx_opt, &hash_location, 0, dst); if (th->ack) { /* rfc793: @@ -5462,6 +5500,31 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, * Change state from SYN-SENT only after copied_seq * is initialized. */ tp->copied_seq = tp->rcv_nxt; + + if (cvp != NULL && + cvp->cookie_pair_size > 0 && + tp->rx_opt.cookie_plus > 0) { + int cookie_size = tp->rx_opt.cookie_plus + - TCPOLEN_COOKIE_BASE; + int cookie_pair_size = cookie_size + + cvp->cookie_desired; + + /* A cookie extension option was sent and returned. + * Note that each incoming SYNACK replaces the + * Responder cookie. The initial exchange is most + * fragile, as protection against spoofing relies + * entirely upon the sequence and timestamp (above). + * This replacement strategy allows the correct pair to + * pass through, while any others will be filtered via + * Responder verification later. + */ + if (sizeof(cvp->cookie_pair) >= cookie_pair_size) { + memcpy(&cvp->cookie_pair[cvp->cookie_desired], + hash_location, cookie_size); + cvp->cookie_pair_size = cookie_pair_size; + } + } + smp_mb(); tcp_set_state(sk, TCP_ESTABLISHED); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 7cda24b..29002ab 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -165,10 +165,10 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) nexthop = inet->opt->faddr; } - tmp = ip_route_connect(&rt, nexthop, inet->saddr, + tmp = ip_route_connect(&rt, nexthop, inet->inet_saddr, RT_CONN_FLAGS(sk), sk->sk_bound_dev_if, IPPROTO_TCP, - inet->sport, usin->sin_port, sk, 1); + inet->inet_sport, usin->sin_port, sk, 1); if (tmp < 0) { if (tmp == -ENETUNREACH) IP_INC_STATS_BH(sock_net(sk), IPSTATS_MIB_OUTNOROUTES); @@ -183,11 +183,11 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (!inet->opt || !inet->opt->srr) daddr = rt->rt_dst; - if (!inet->saddr) - inet->saddr = rt->rt_src; - inet->rcv_saddr = inet->saddr; + if (!inet->inet_saddr) + inet->inet_saddr = rt->rt_src; + inet->inet_rcv_saddr = inet->inet_saddr; - if (tp->rx_opt.ts_recent_stamp && inet->daddr != daddr) { + if (tp->rx_opt.ts_recent_stamp && inet->inet_daddr != daddr) { /* Reset inherited state */ tp->rx_opt.ts_recent = 0; tp->rx_opt.ts_recent_stamp = 0; @@ -204,20 +204,20 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) * when trying new connection. */ if (peer != NULL && - peer->tcp_ts_stamp + TCP_PAWS_MSL >= get_seconds()) { + (u32)get_seconds() - peer->tcp_ts_stamp <= TCP_PAWS_MSL) { tp->rx_opt.ts_recent_stamp = peer->tcp_ts_stamp; tp->rx_opt.ts_recent = peer->tcp_ts; } } - inet->dport = usin->sin_port; - inet->daddr = daddr; + inet->inet_dport = usin->sin_port; + inet->inet_daddr = daddr; inet_csk(sk)->icsk_ext_hdr_len = 0; if (inet->opt) inet_csk(sk)->icsk_ext_hdr_len = inet->opt->optlen; - tp->rx_opt.mss_clamp = 536; + tp->rx_opt.mss_clamp = TCP_MSS_DEFAULT; /* Socket identity is still unknown (sport may be zero). * However we set state to SYN-SENT and not releasing socket @@ -230,7 +230,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) goto failure; err = ip_route_newports(&rt, IPPROTO_TCP, - inet->sport, inet->dport, sk); + inet->inet_sport, inet->inet_dport, sk); if (err) goto failure; @@ -239,12 +239,12 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) sk_setup_caps(sk, &rt->u.dst); if (!tp->write_seq) - tp->write_seq = secure_tcp_sequence_number(inet->saddr, - inet->daddr, - inet->sport, + tp->write_seq = secure_tcp_sequence_number(inet->inet_saddr, + inet->inet_daddr, + inet->inet_sport, usin->sin_port); - inet->id = tp->write_seq ^ jiffies; + inet->inet_id = tp->write_seq ^ jiffies; err = tcp_connect(sk); rt = NULL; @@ -261,7 +261,7 @@ failure: tcp_set_state(sk, TCP_CLOSE); ip_rt_put(rt); sk->sk_route_caps = 0; - inet->dport = 0; + inet->inet_dport = 0; return err; } @@ -520,12 +520,13 @@ void tcp_v4_send_check(struct sock *sk, int len, struct sk_buff *skb) struct tcphdr *th = tcp_hdr(skb); if (skb->ip_summed == CHECKSUM_PARTIAL) { - th->check = ~tcp_v4_check(len, inet->saddr, - inet->daddr, 0); + th->check = ~tcp_v4_check(len, inet->inet_saddr, + inet->inet_daddr, 0); skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = offsetof(struct tcphdr, check); } else { - th->check = tcp_v4_check(len, inet->saddr, inet->daddr, + th->check = tcp_v4_check(len, inet->inet_saddr, + inet->inet_daddr, csum_partial(th, th->doff << 2, skb->csum)); @@ -741,8 +742,9 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, * This still operates on a request_sock only, not on a big * socket. */ -static int __tcp_v4_send_synack(struct sock *sk, struct request_sock *req, - struct dst_entry *dst) +static int __tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst, + struct request_sock *req, + struct request_values *rvp) { const struct inet_request_sock *ireq = inet_rsk(req); int err = -1; @@ -752,7 +754,7 @@ static int __tcp_v4_send_synack(struct sock *sk, struct request_sock *req, if (!dst && (dst = inet_csk_route_req(sk, req)) == NULL) return -1; - skb = tcp_make_synack(sk, dst, req); + skb = tcp_make_synack(sk, dst, req, rvp); if (skb) { struct tcphdr *th = tcp_hdr(skb); @@ -773,9 +775,10 @@ static int __tcp_v4_send_synack(struct sock *sk, struct request_sock *req, return err; } -static int tcp_v4_send_synack(struct sock *sk, struct request_sock *req) +static int tcp_v4_send_synack(struct sock *sk, struct request_sock *req, + struct request_values *rvp) { - return __tcp_v4_send_synack(sk, req, NULL); + return __tcp_v4_send_synack(sk, NULL, req, rvp); } /* @@ -848,7 +851,7 @@ static struct tcp_md5sig_key * struct tcp_md5sig_key *tcp_v4_md5_lookup(struct sock *sk, struct sock *addr_sk) { - return tcp_v4_md5_do_lookup(sk, inet_sk(addr_sk)->daddr); + return tcp_v4_md5_do_lookup(sk, inet_sk(addr_sk)->inet_daddr); } EXPORT_SYMBOL(tcp_v4_md5_lookup); @@ -923,7 +926,7 @@ EXPORT_SYMBOL(tcp_v4_md5_do_add); static int tcp_v4_md5_add_func(struct sock *sk, struct sock *addr_sk, u8 *newkey, u8 newkeylen) { - return tcp_v4_md5_do_add(sk, inet_sk(addr_sk)->daddr, + return tcp_v4_md5_do_add(sk, inet_sk(addr_sk)->inet_daddr, newkey, newkeylen); } @@ -1089,8 +1092,8 @@ int tcp_v4_md5_hash_skb(char *md5_hash, struct tcp_md5sig_key *key, __be32 saddr, daddr; if (sk) { - saddr = inet_sk(sk)->saddr; - daddr = inet_sk(sk)->daddr; + saddr = inet_sk(sk)->inet_saddr; + daddr = inet_sk(sk)->inet_daddr; } else if (req) { saddr = inet_rsk(req)->loc_addr; daddr = inet_rsk(req)->rmt_addr; @@ -1210,13 +1213,16 @@ static struct timewait_sock_ops tcp_timewait_sock_ops = { int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) { - struct inet_request_sock *ireq; + struct tcp_extend_values tmp_ext; struct tcp_options_received tmp_opt; + u8 *hash_location; struct request_sock *req; + struct inet_request_sock *ireq; + struct tcp_sock *tp = tcp_sk(sk); + struct dst_entry *dst = NULL; __be32 saddr = ip_hdr(skb)->saddr; __be32 daddr = ip_hdr(skb)->daddr; __u32 isn = TCP_SKB_CB(skb)->when; - struct dst_entry *dst = NULL; #ifdef CONFIG_SYN_COOKIES int want_cookie = 0; #else @@ -1256,27 +1262,65 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) tcp_rsk(req)->af_specific = &tcp_request_sock_ipv4_ops; #endif + ireq = inet_rsk(req); + ireq->loc_addr = daddr; + ireq->rmt_addr = saddr; + ireq->no_srccheck = inet_sk(sk)->transparent; + ireq->opt = tcp_v4_save_options(sk, skb); + + dst = inet_csk_route_req(sk, req); + if(!dst) + goto drop_and_free; + tcp_clear_options(&tmp_opt); - tmp_opt.mss_clamp = 536; - tmp_opt.user_mss = tcp_sk(sk)->rx_opt.user_mss; + tmp_opt.mss_clamp = TCP_MSS_DEFAULT; + tmp_opt.user_mss = tp->rx_opt.user_mss; + tcp_parse_options(skb, &tmp_opt, &hash_location, 0, dst); + + if (tmp_opt.cookie_plus > 0 && + tmp_opt.saw_tstamp && + !tp->rx_opt.cookie_out_never && + (sysctl_tcp_cookie_size > 0 || + (tp->cookie_values != NULL && + tp->cookie_values->cookie_desired > 0))) { + u8 *c; + u32 *mess = &tmp_ext.cookie_bakery[COOKIE_DIGEST_WORDS]; + int l = tmp_opt.cookie_plus - TCPOLEN_COOKIE_BASE; + + if (tcp_cookie_generator(&tmp_ext.cookie_bakery[0]) != 0) + goto drop_and_release; + + /* Secret recipe starts with IP addresses */ + *mess++ ^= daddr; + *mess++ ^= saddr; - tcp_parse_options(skb, &tmp_opt, 0); + /* plus variable length Initiator Cookie */ + c = (u8 *)mess; + while (l-- > 0) + *c++ ^= *hash_location++; + +#ifdef CONFIG_SYN_COOKIES + want_cookie = 0; /* not our kind of cookie */ +#endif + tmp_ext.cookie_out_never = 0; /* false */ + tmp_ext.cookie_plus = tmp_opt.cookie_plus; + } else if (!tp->rx_opt.cookie_in_always) { + /* redundant indications, but ensure initialization. */ + tmp_ext.cookie_out_never = 1; /* true */ + tmp_ext.cookie_plus = 0; + } else { + goto drop_and_release; + } + tmp_ext.cookie_in_always = tp->rx_opt.cookie_in_always; if (want_cookie && !tmp_opt.saw_tstamp) tcp_clear_options(&tmp_opt); tmp_opt.tstamp_ok = tmp_opt.saw_tstamp; - tcp_openreq_init(req, &tmp_opt, skb); - ireq = inet_rsk(req); - ireq->loc_addr = daddr; - ireq->rmt_addr = saddr; - ireq->no_srccheck = inet_sk(sk)->transparent; - ireq->opt = tcp_v4_save_options(sk, skb); - if (security_inet_conn_request(sk, skb, req)) - goto drop_and_free; + goto drop_and_release; if (!want_cookie) TCP_ECN_create_request(req, tcp_hdr(skb)); @@ -1301,10 +1345,9 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) */ if (tmp_opt.saw_tstamp && tcp_death_row.sysctl_tw_recycle && - (dst = inet_csk_route_req(sk, req)) != NULL && (peer = rt_get_peer((struct rtable *)dst)) != NULL && peer->v4daddr == saddr) { - if (get_seconds() < peer->tcp_ts_stamp + TCP_PAWS_MSL && + if ((u32)get_seconds() - peer->tcp_ts_stamp < TCP_PAWS_MSL && (s32)(peer->tcp_ts - req->ts_recent) > TCP_PAWS_WINDOW) { NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSPASSIVEREJECTED); @@ -1333,7 +1376,9 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) } tcp_rsk(req)->snt_isn = isn; - if (__tcp_v4_send_synack(sk, req, dst) || want_cookie) + if (__tcp_v4_send_synack(sk, dst, req, + (struct request_values *)&tmp_ext) || + want_cookie) goto drop_and_free; inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT); @@ -1380,9 +1425,9 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newtp = tcp_sk(newsk); newinet = inet_sk(newsk); ireq = inet_rsk(req); - newinet->daddr = ireq->rmt_addr; - newinet->rcv_saddr = ireq->loc_addr; - newinet->saddr = ireq->loc_addr; + newinet->inet_daddr = ireq->rmt_addr; + newinet->inet_rcv_saddr = ireq->loc_addr; + newinet->inet_saddr = ireq->loc_addr; newinet->opt = ireq->opt; ireq->opt = NULL; newinet->mc_index = inet_iif(skb); @@ -1390,7 +1435,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, inet_csk(newsk)->icsk_ext_hdr_len = 0; if (newinet->opt) inet_csk(newsk)->icsk_ext_hdr_len = newinet->opt->optlen; - newinet->id = newtp->write_seq ^ jiffies; + newinet->inet_id = newtp->write_seq ^ jiffies; tcp_mtup_init(newsk); tcp_sync_mss(newsk, dst_mtu(dst)); @@ -1403,7 +1448,8 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, #ifdef CONFIG_TCP_MD5SIG /* Copy over the MD5 key from the original socket */ - if ((key = tcp_v4_md5_do_lookup(sk, newinet->daddr)) != NULL) { + key = tcp_v4_md5_do_lookup(sk, newinet->inet_daddr); + if (key != NULL) { /* * We're using one, so create a matching key * on the newsk structure. If we fail to get @@ -1412,7 +1458,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, */ char *newkey = kmemdup(key->key, key->keylen, GFP_ATOMIC); if (newkey != NULL) - tcp_v4_md5_do_add(newsk, newinet->daddr, + tcp_v4_md5_do_add(newsk, newinet->inet_daddr, newkey, key->keylen); newsk->sk_route_caps &= ~NETIF_F_GSO_MASK; } @@ -1711,8 +1757,8 @@ int tcp_v4_remember_stamp(struct sock *sk) struct inet_peer *peer = NULL; int release_it = 0; - if (!rt || rt->rt_dst != inet->daddr) { - peer = inet_getpeer(inet->daddr, 1); + if (!rt || rt->rt_dst != inet->inet_daddr) { + peer = inet_getpeer(inet->inet_daddr, 1); release_it = 1; } else { if (!rt->peer) @@ -1722,9 +1768,9 @@ int tcp_v4_remember_stamp(struct sock *sk) if (peer) { if ((s32)(peer->tcp_ts - tp->rx_opt.ts_recent) <= 0 || - (peer->tcp_ts_stamp + TCP_PAWS_MSL < get_seconds() && - peer->tcp_ts_stamp <= tp->rx_opt.ts_recent_stamp)) { - peer->tcp_ts_stamp = tp->rx_opt.ts_recent_stamp; + ((u32)get_seconds() - peer->tcp_ts_stamp > TCP_PAWS_MSL && + peer->tcp_ts_stamp <= (u32)tp->rx_opt.ts_recent_stamp)) { + peer->tcp_ts_stamp = (u32)tp->rx_opt.ts_recent_stamp; peer->tcp_ts = tp->rx_opt.ts_recent; } if (release_it) @@ -1743,9 +1789,9 @@ int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw) const struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw); if ((s32)(peer->tcp_ts - tcptw->tw_ts_recent) <= 0 || - (peer->tcp_ts_stamp + TCP_PAWS_MSL < get_seconds() && - peer->tcp_ts_stamp <= tcptw->tw_ts_recent_stamp)) { - peer->tcp_ts_stamp = tcptw->tw_ts_recent_stamp; + ((u32)get_seconds() - peer->tcp_ts_stamp > TCP_PAWS_MSL && + peer->tcp_ts_stamp <= (u32)tcptw->tw_ts_recent_stamp)) { + peer->tcp_ts_stamp = (u32)tcptw->tw_ts_recent_stamp; peer->tcp_ts = tcptw->tw_ts_recent; } inet_putpeer(peer); @@ -1810,7 +1856,7 @@ static int tcp_v4_init_sock(struct sock *sk) */ tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tp->snd_cwnd_clamp = ~0; - tp->mss_cache = 536; + tp->mss_cache = TCP_MSS_DEFAULT; tp->reordering = sysctl_tcp_reordering; icsk->icsk_ca_ops = &tcp_init_congestion_ops; @@ -1826,6 +1872,19 @@ static int tcp_v4_init_sock(struct sock *sk) tp->af_specific = &tcp_sock_ipv4_specific; #endif + /* TCP Cookie Transactions */ + if (sysctl_tcp_cookie_size > 0) { + /* Default, cookies without s_data_payload. */ + tp->cookie_values = + kzalloc(sizeof(*tp->cookie_values), + sk->sk_allocation); + if (tp->cookie_values != NULL) + kref_init(&tp->cookie_values->kref); + } + /* Presumed zeroed, in order of appearance: + * cookie_in_always, cookie_out_never, + * s_data_constant, s_data_in, s_data_out + */ sk->sk_sndbuf = sysctl_tcp_wmem[1]; sk->sk_rcvbuf = sysctl_tcp_rmem[1]; @@ -1879,6 +1938,13 @@ void tcp_v4_destroy_sock(struct sock *sk) sk->sk_sndmsg_page = NULL; } + /* TCP Cookie Transactions */ + if (tp->cookie_values != NULL) { + kref_put(&tp->cookie_values->kref, + tcp_cookie_values_release); + tp->cookie_values = NULL; + } + percpu_counter_dec(&tcp_sockets_allocated); } @@ -2000,7 +2066,7 @@ static void *established_get_first(struct seq_file *seq) struct net *net = seq_file_net(seq); void *rc = NULL; - for (st->bucket = 0; st->bucket < tcp_hashinfo.ehash_size; ++st->bucket) { + for (st->bucket = 0; st->bucket <= tcp_hashinfo.ehash_mask; ++st->bucket) { struct sock *sk; struct hlist_nulls_node *node; struct inet_timewait_sock *tw; @@ -2061,10 +2127,10 @@ get_tw: st->state = TCP_SEQ_STATE_ESTABLISHED; /* Look for next non empty bucket */ - while (++st->bucket < tcp_hashinfo.ehash_size && + while (++st->bucket <= tcp_hashinfo.ehash_mask && empty_bucket(st)) ; - if (st->bucket >= tcp_hashinfo.ehash_size) + if (st->bucket > tcp_hashinfo.ehash_mask) return NULL; spin_lock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket)); @@ -2225,7 +2291,7 @@ static void get_openreq4(struct sock *sk, struct request_sock *req, " %02X %08X:%08X %02X:%08lX %08X %5d %8d %u %d %p%n", i, ireq->loc_addr, - ntohs(inet_sk(sk)->sport), + ntohs(inet_sk(sk)->inet_sport), ireq->rmt_addr, ntohs(ireq->rmt_port), TCP_SYN_RECV, @@ -2248,10 +2314,11 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i, int *len) struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); struct inet_sock *inet = inet_sk(sk); - __be32 dest = inet->daddr; - __be32 src = inet->rcv_saddr; - __u16 destp = ntohs(inet->dport); - __u16 srcp = ntohs(inet->sport); + __be32 dest = inet->inet_daddr; + __be32 src = inet->inet_rcv_saddr; + __u16 destp = ntohs(inet->inet_dport); + __u16 srcp = ntohs(inet->inet_sport); + int rx_queue; if (icsk->icsk_pending == ICSK_TIME_RETRANS) { timer_active = 1; @@ -2267,12 +2334,19 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i, int *len) timer_expires = jiffies; } + if (sk->sk_state == TCP_LISTEN) + rx_queue = sk->sk_ack_backlog; + else + /* + * because we dont lock socket, we might find a transient negative value + */ + rx_queue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0); + seq_printf(f, "%4d: %08X:%04X %08X:%04X %02X %08X:%08X %02X:%08lX " "%08X %5d %8d %lu %d %p %lu %lu %u %u %d%n", i, src, srcp, dest, destp, sk->sk_state, tp->write_seq - tp->snd_una, - sk->sk_state == TCP_LISTEN ? sk->sk_ack_backlog : - (tp->rcv_nxt - tp->copied_seq), + rx_queue, timer_active, jiffies_to_clock_t(timer_expires - jiffies), icsk->icsk_retransmits, @@ -2463,12 +2537,17 @@ static int __net_init tcp_sk_init(struct net *net) static void __net_exit tcp_sk_exit(struct net *net) { inet_ctl_sock_destroy(net->ipv4.tcp_sock); - inet_twsk_purge(net, &tcp_hashinfo, &tcp_death_row, AF_INET); +} + +static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list) +{ + inet_twsk_purge(&tcp_hashinfo, &tcp_death_row, AF_INET); } static struct pernet_operations __net_initdata tcp_sk_ops = { - .init = tcp_sk_init, - .exit = tcp_sk_exit, + .init = tcp_sk_init, + .exit = tcp_sk_exit, + .exit_batch = tcp_sk_exit_batch, }; void __init tcp_v4_init(void) diff --git a/net/ipv4/tcp_lp.c b/net/ipv4/tcp_lp.c index ce3c41f..de87037 100644 --- a/net/ipv4/tcp_lp.c +++ b/net/ipv4/tcp_lp.c @@ -143,8 +143,8 @@ static u32 tcp_lp_remote_hz_estimator(struct sock *sk) goto out; /* we can't calc remote HZ with no different!! */ - if (tp->rx_opt.rcv_tsval == lp->remote_ref_time - || tp->rx_opt.rcv_tsecr == lp->local_ref_time) + if (tp->rx_opt.rcv_tsval == lp->remote_ref_time || + tp->rx_opt.rcv_tsecr == lp->local_ref_time) goto out; m = HZ * (tp->rx_opt.rcv_tsval - diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 4c03598..87accec 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -26,13 +26,7 @@ #include <net/inet_common.h> #include <net/xfrm.h> -#ifdef CONFIG_SYSCTL -#define SYNC_INIT 0 /* let the user enable it */ -#else -#define SYNC_INIT 1 -#endif - -int sysctl_tcp_syncookies __read_mostly = SYNC_INIT; +int sysctl_tcp_syncookies __read_mostly = 1; EXPORT_SYMBOL(sysctl_tcp_syncookies); int sysctl_tcp_abort_on_overflow __read_mostly; @@ -96,13 +90,14 @@ enum tcp_tw_status tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, const struct tcphdr *th) { - struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw); struct tcp_options_received tmp_opt; + u8 *hash_location; + struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw); int paws_reject = 0; - tmp_opt.saw_tstamp = 0; if (th->doff > (sizeof(*th) >> 2) && tcptw->tw_ts_recent_stamp) { - tcp_parse_options(skb, &tmp_opt, 0); + tmp_opt.tstamp_ok = 1; + tcp_parse_options(skb, &tmp_opt, &hash_location, 1, NULL); if (tmp_opt.saw_tstamp) { tmp_opt.ts_recent = tcptw->tw_ts_recent; @@ -389,14 +384,43 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, const struct inet_request_sock *ireq = inet_rsk(req); struct tcp_request_sock *treq = tcp_rsk(req); struct inet_connection_sock *newicsk = inet_csk(newsk); - struct tcp_sock *newtp; + struct tcp_sock *newtp = tcp_sk(newsk); + struct tcp_sock *oldtp = tcp_sk(sk); + struct tcp_cookie_values *oldcvp = oldtp->cookie_values; + + /* TCP Cookie Transactions require space for the cookie pair, + * as it differs for each connection. There is no need to + * copy any s_data_payload stored at the original socket. + * Failure will prevent resuming the connection. + * + * Presumed copied, in order of appearance: + * cookie_in_always, cookie_out_never + */ + if (oldcvp != NULL) { + struct tcp_cookie_values *newcvp = + kzalloc(sizeof(*newtp->cookie_values), + GFP_ATOMIC); + + if (newcvp != NULL) { + kref_init(&newcvp->kref); + newcvp->cookie_desired = + oldcvp->cookie_desired; + newtp->cookie_values = newcvp; + } else { + /* Not Yet Implemented */ + newtp->cookie_values = NULL; + } + } /* Now setup tcp_sock */ - newtp = tcp_sk(newsk); newtp->pred_flags = 0; - newtp->rcv_wup = newtp->copied_seq = newtp->rcv_nxt = treq->rcv_isn + 1; - newtp->snd_sml = newtp->snd_una = newtp->snd_nxt = treq->snt_isn + 1; - newtp->snd_up = treq->snt_isn + 1; + + newtp->rcv_wup = newtp->copied_seq = + newtp->rcv_nxt = treq->rcv_isn + 1; + + newtp->snd_sml = newtp->snd_una = + newtp->snd_nxt = newtp->snd_up = + treq->snt_isn + 1 + tcp_s_data_size(oldtp); tcp_prequeue_init(newtp); @@ -429,8 +453,8 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, tcp_set_ca_state(newsk, TCP_CA_Open); tcp_init_xmit_timers(newsk); skb_queue_head_init(&newtp->out_of_order_queue); - newtp->write_seq = treq->snt_isn + 1; - newtp->pushed_seq = newtp->write_seq; + newtp->write_seq = newtp->pushed_seq = + treq->snt_isn + 1 + tcp_s_data_size(oldtp); newtp->rx_opt.saw_tstamp = 0; @@ -476,7 +500,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, if (newtp->af_specific->md5_lookup(sk, newsk)) newtp->tcp_header_len += TCPOLEN_MD5SIG_ALIGNED; #endif - if (skb->len >= TCP_MIN_RCVMSS+newtp->tcp_header_len) + if (skb->len >= TCP_MSS_DEFAULT + newtp->tcp_header_len) newicsk->icsk_ack.last_seg_size = skb->len - newtp->tcp_header_len; newtp->rx_opt.mss_clamp = req->mss; TCP_ECN_openreq_child(newtp, req); @@ -495,15 +519,16 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct request_sock **prev) { + struct tcp_options_received tmp_opt; + u8 *hash_location; + struct sock *child; const struct tcphdr *th = tcp_hdr(skb); __be32 flg = tcp_flag_word(th) & (TCP_FLAG_RST|TCP_FLAG_SYN|TCP_FLAG_ACK); int paws_reject = 0; - struct tcp_options_received tmp_opt; - struct sock *child; - tmp_opt.saw_tstamp = 0; - if (th->doff > (sizeof(struct tcphdr)>>2)) { - tcp_parse_options(skb, &tmp_opt, 0); + if ((th->doff > (sizeof(*th) >> 2)) && (req->ts_recent)) { + tmp_opt.tstamp_ok = 1; + tcp_parse_options(skb, &tmp_opt, &hash_location, 1, NULL); if (tmp_opt.saw_tstamp) { tmp_opt.ts_recent = req->ts_recent; @@ -537,7 +562,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, * Enforce "SYN-ACK" according to figure 8, figure 6 * of RFC793, fixed by RFC1122. */ - req->rsk_ops->rtx_syn_ack(sk, req); + req->rsk_ops->rtx_syn_ack(sk, req, NULL); return NULL; } @@ -596,7 +621,8 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, * Invalid ACK: reset will be sent by listening socket */ if ((flg & TCP_FLAG_ACK) && - (TCP_SKB_CB(skb)->ack_seq != tcp_rsk(req)->snt_isn + 1)) + (TCP_SKB_CB(skb)->ack_seq != + tcp_rsk(req)->snt_isn + 1 + tcp_s_data_size(tcp_sk(sk)))) return sk; /* Also, it would be not so bad idea to check rcv_tsecr, which diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index fcd278a..93316a9 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -59,6 +59,10 @@ int sysctl_tcp_base_mss __read_mostly = 512; /* By default, RFC2861 behavior. */ int sysctl_tcp_slow_start_after_idle __read_mostly = 1; +int sysctl_tcp_cookie_size __read_mostly = 0; /* TCP_COOKIE_MAX */ +EXPORT_SYMBOL_GPL(sysctl_tcp_cookie_size); + + /* Account for new data that has been sent to the network. */ static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb) { @@ -362,15 +366,45 @@ static inline int tcp_urg_mode(const struct tcp_sock *tp) #define OPTION_TS (1 << 1) #define OPTION_MD5 (1 << 2) #define OPTION_WSCALE (1 << 3) +#define OPTION_COOKIE_EXTENSION (1 << 4) struct tcp_out_options { u8 options; /* bit field of OPTION_* */ u8 ws; /* window scale, 0 to disable */ u8 num_sack_blocks; /* number of SACK blocks to include */ + u8 hash_size; /* bytes in hash_location */ u16 mss; /* 0 to disable */ __u32 tsval, tsecr; /* need to include OPTION_TS */ + __u8 *hash_location; /* temporary pointer, overloaded */ }; +/* The sysctl int routines are generic, so check consistency here. + */ +static u8 tcp_cookie_size_check(u8 desired) +{ + if (desired > 0) { + /* previously specified */ + return desired; + } + if (sysctl_tcp_cookie_size <= 0) { + /* no default specified */ + return 0; + } + if (sysctl_tcp_cookie_size <= TCP_COOKIE_MIN) { + /* value too small, specify minimum */ + return TCP_COOKIE_MIN; + } + if (sysctl_tcp_cookie_size >= TCP_COOKIE_MAX) { + /* value too large, specify maximum */ + return TCP_COOKIE_MAX; + } + if (0x1 & sysctl_tcp_cookie_size) { + /* 8-bit multiple, illegal, fix it */ + return (u8)(sysctl_tcp_cookie_size + 0x1); + } + return (u8)sysctl_tcp_cookie_size; +} + /* Write previously computed TCP options to the packet. * * Beware: Something in the Internet is very sensitive to the ordering of @@ -385,17 +419,34 @@ struct tcp_out_options { * (but it may well be that other scenarios fail similarly). */ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp, - const struct tcp_out_options *opts, - __u8 **md5_hash) { - if (unlikely(OPTION_MD5 & opts->options)) { - *ptr++ = htonl((TCPOPT_NOP << 24) | - (TCPOPT_NOP << 16) | - (TCPOPT_MD5SIG << 8) | - TCPOLEN_MD5SIG); - *md5_hash = (__u8 *)ptr; + struct tcp_out_options *opts) +{ + u8 options = opts->options; /* mungable copy */ + + /* Having both authentication and cookies for security is redundant, + * and there's certainly not enough room. Instead, the cookie-less + * extension variant is proposed. + * + * Consider the pessimal case with authentication. The options + * could look like: + * COOKIE|MD5(20) + MSS(4) + SACK|TS(12) + WSCALE(4) == 40 + */ + if (unlikely(OPTION_MD5 & options)) { + if (unlikely(OPTION_COOKIE_EXTENSION & options)) { + *ptr++ = htonl((TCPOPT_COOKIE << 24) | + (TCPOLEN_COOKIE_BASE << 16) | + (TCPOPT_MD5SIG << 8) | + TCPOLEN_MD5SIG); + } else { + *ptr++ = htonl((TCPOPT_NOP << 24) | + (TCPOPT_NOP << 16) | + (TCPOPT_MD5SIG << 8) | + TCPOLEN_MD5SIG); + } + options &= ~OPTION_COOKIE_EXTENSION; + /* overload cookie hash location */ + opts->hash_location = (__u8 *)ptr; ptr += 4; - } else { - *md5_hash = NULL; } if (unlikely(opts->mss)) { @@ -404,12 +455,13 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp, opts->mss); } - if (likely(OPTION_TS & opts->options)) { - if (unlikely(OPTION_SACK_ADVERTISE & opts->options)) { + if (likely(OPTION_TS & options)) { + if (unlikely(OPTION_SACK_ADVERTISE & options)) { *ptr++ = htonl((TCPOPT_SACK_PERM << 24) | (TCPOLEN_SACK_PERM << 16) | (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP); + options &= ~OPTION_SACK_ADVERTISE; } else { *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | @@ -420,15 +472,52 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp, *ptr++ = htonl(opts->tsecr); } - if (unlikely(OPTION_SACK_ADVERTISE & opts->options && - !(OPTION_TS & opts->options))) { + /* Specification requires after timestamp, so do it now. + * + * Consider the pessimal case without authentication. The options + * could look like: + * MSS(4) + SACK|TS(12) + COOKIE(20) + WSCALE(4) == 40 + */ + if (unlikely(OPTION_COOKIE_EXTENSION & options)) { + __u8 *cookie_copy = opts->hash_location; + u8 cookie_size = opts->hash_size; + + /* 8-bit multiple handled in tcp_cookie_size_check() above, + * and elsewhere. + */ + if (0x2 & cookie_size) { + __u8 *p = (__u8 *)ptr; + + /* 16-bit multiple */ + *p++ = TCPOPT_COOKIE; + *p++ = TCPOLEN_COOKIE_BASE + cookie_size; + *p++ = *cookie_copy++; + *p++ = *cookie_copy++; + ptr++; + cookie_size -= 2; + } else { + /* 32-bit multiple */ + *ptr++ = htonl(((TCPOPT_NOP << 24) | + (TCPOPT_NOP << 16) | + (TCPOPT_COOKIE << 8) | + TCPOLEN_COOKIE_BASE) + + cookie_size); + } + + if (cookie_size > 0) { + memcpy(ptr, cookie_copy, cookie_size); + ptr += (cookie_size / 4); + } + } + + if (unlikely(OPTION_SACK_ADVERTISE & options)) { *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_SACK_PERM << 8) | TCPOLEN_SACK_PERM); } - if (unlikely(OPTION_WSCALE & opts->options)) { + if (unlikely(OPTION_WSCALE & options)) { *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_WINDOW << 16) | (TCPOLEN_WINDOW << 8) | @@ -463,13 +552,18 @@ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb, struct tcp_out_options *opts, struct tcp_md5sig_key **md5) { struct tcp_sock *tp = tcp_sk(sk); - unsigned size = 0; + struct tcp_cookie_values *cvp = tp->cookie_values; + struct dst_entry *dst = __sk_dst_get(sk); + unsigned remaining = MAX_TCP_OPTION_SPACE; + u8 cookie_size = (!tp->rx_opt.cookie_out_never && cvp != NULL) ? + tcp_cookie_size_check(cvp->cookie_desired) : + 0; #ifdef CONFIG_TCP_MD5SIG *md5 = tp->af_specific->md5_lookup(sk, sk); if (*md5) { opts->options |= OPTION_MD5; - size += TCPOLEN_MD5SIG_ALIGNED; + remaining -= TCPOLEN_MD5SIG_ALIGNED; } #else *md5 = NULL; @@ -485,26 +579,76 @@ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb, * SACKs don't matter, we never delay an ACK when we have any of those * going out. */ opts->mss = tcp_advertise_mss(sk); - size += TCPOLEN_MSS_ALIGNED; + remaining -= TCPOLEN_MSS_ALIGNED; - if (likely(sysctl_tcp_timestamps && *md5 == NULL)) { + if (likely(sysctl_tcp_timestamps && + !dst_feature(dst, RTAX_FEATURE_NO_TSTAMP) && + *md5 == NULL)) { opts->options |= OPTION_TS; opts->tsval = TCP_SKB_CB(skb)->when; opts->tsecr = tp->rx_opt.ts_recent; - size += TCPOLEN_TSTAMP_ALIGNED; + remaining -= TCPOLEN_TSTAMP_ALIGNED; } - if (likely(sysctl_tcp_window_scaling)) { + if (likely(sysctl_tcp_window_scaling && + !dst_feature(dst, RTAX_FEATURE_NO_WSCALE))) { opts->ws = tp->rx_opt.rcv_wscale; opts->options |= OPTION_WSCALE; - size += TCPOLEN_WSCALE_ALIGNED; + remaining -= TCPOLEN_WSCALE_ALIGNED; } - if (likely(sysctl_tcp_sack)) { + if (likely(sysctl_tcp_sack && + !dst_feature(dst, RTAX_FEATURE_NO_SACK))) { opts->options |= OPTION_SACK_ADVERTISE; if (unlikely(!(OPTION_TS & opts->options))) - size += TCPOLEN_SACKPERM_ALIGNED; + remaining -= TCPOLEN_SACKPERM_ALIGNED; } - return size; + /* Note that timestamps are required by the specification. + * + * Odd numbers of bytes are prohibited by the specification, ensuring + * that the cookie is 16-bit aligned, and the resulting cookie pair is + * 32-bit aligned. + */ + if (*md5 == NULL && + (OPTION_TS & opts->options) && + cookie_size > 0) { + int need = TCPOLEN_COOKIE_BASE + cookie_size; + + if (0x2 & need) { + /* 32-bit multiple */ + need += 2; /* NOPs */ + + if (need > remaining) { + /* try shrinking cookie to fit */ + cookie_size -= 2; + need -= 4; + } + } + while (need > remaining && TCP_COOKIE_MIN <= cookie_size) { + cookie_size -= 4; + need -= 4; + } + if (TCP_COOKIE_MIN <= cookie_size) { + opts->options |= OPTION_COOKIE_EXTENSION; + opts->hash_location = (__u8 *)&cvp->cookie_pair[0]; + opts->hash_size = cookie_size; + + /* Remember for future incarnations. */ + cvp->cookie_desired = cookie_size; + + if (cvp->cookie_desired != cvp->cookie_pair_size) { + /* Currently use random bytes as a nonce, + * assuming these are completely unpredictable + * by hostile users of the same system. + */ + get_random_bytes(&cvp->cookie_pair[0], + cookie_size); + cvp->cookie_pair_size = cookie_size; + } + + remaining -= need; + } + } + return MAX_TCP_OPTION_SPACE - remaining; } /* Set up TCP options for SYN-ACKs. */ @@ -512,48 +656,77 @@ static unsigned tcp_synack_options(struct sock *sk, struct request_sock *req, unsigned mss, struct sk_buff *skb, struct tcp_out_options *opts, - struct tcp_md5sig_key **md5) { - unsigned size = 0; + struct tcp_md5sig_key **md5, + struct tcp_extend_values *xvp) +{ struct inet_request_sock *ireq = inet_rsk(req); - char doing_ts; + unsigned remaining = MAX_TCP_OPTION_SPACE; + u8 cookie_plus = (xvp != NULL && !xvp->cookie_out_never) ? + xvp->cookie_plus : + 0; + bool doing_ts = ireq->tstamp_ok; #ifdef CONFIG_TCP_MD5SIG *md5 = tcp_rsk(req)->af_specific->md5_lookup(sk, req); if (*md5) { opts->options |= OPTION_MD5; - size += TCPOLEN_MD5SIG_ALIGNED; + remaining -= TCPOLEN_MD5SIG_ALIGNED; + + /* We can't fit any SACK blocks in a packet with MD5 + TS + * options. There was discussion about disabling SACK + * rather than TS in order to fit in better with old, + * buggy kernels, but that was deemed to be unnecessary. + */ + doing_ts &= !ireq->sack_ok; } #else *md5 = NULL; #endif - /* we can't fit any SACK blocks in a packet with MD5 + TS - options. There was discussion about disabling SACK rather than TS in - order to fit in better with old, buggy kernels, but that was deemed - to be unnecessary. */ - doing_ts = ireq->tstamp_ok && !(*md5 && ireq->sack_ok); - + /* We always send an MSS option. */ opts->mss = mss; - size += TCPOLEN_MSS_ALIGNED; + remaining -= TCPOLEN_MSS_ALIGNED; if (likely(ireq->wscale_ok)) { opts->ws = ireq->rcv_wscale; opts->options |= OPTION_WSCALE; - size += TCPOLEN_WSCALE_ALIGNED; + remaining -= TCPOLEN_WSCALE_ALIGNED; } if (likely(doing_ts)) { opts->options |= OPTION_TS; opts->tsval = TCP_SKB_CB(skb)->when; opts->tsecr = req->ts_recent; - size += TCPOLEN_TSTAMP_ALIGNED; + remaining -= TCPOLEN_TSTAMP_ALIGNED; } if (likely(ireq->sack_ok)) { opts->options |= OPTION_SACK_ADVERTISE; if (unlikely(!doing_ts)) - size += TCPOLEN_SACKPERM_ALIGNED; + remaining -= TCPOLEN_SACKPERM_ALIGNED; } - return size; + /* Similar rationale to tcp_syn_options() applies here, too. + * If the <SYN> options fit, the same options should fit now! + */ + if (*md5 == NULL && + doing_ts && + cookie_plus > TCPOLEN_COOKIE_BASE) { + int need = cookie_plus; /* has TCPOLEN_COOKIE_BASE */ + + if (0x2 & need) { + /* 32-bit multiple */ + need += 2; /* NOPs */ + } + if (need <= remaining) { + opts->options |= OPTION_COOKIE_EXTENSION; + opts->hash_size = cookie_plus - TCPOLEN_COOKIE_BASE; + remaining -= need; + } else { + /* There's no error return, so flag it. */ + xvp->cookie_out_never = 1; /* true */ + opts->hash_size = 0; + } + } + return MAX_TCP_OPTION_SPACE - remaining; } /* Compute TCP options for ESTABLISHED sockets. This is not the @@ -619,7 +792,6 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, struct tcp_out_options opts; unsigned tcp_options_size, tcp_header_size; struct tcp_md5sig_key *md5; - __u8 *md5_hash_location; struct tcphdr *th; int err; @@ -661,8 +833,8 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, /* Build TCP header and checksum it. */ th = tcp_hdr(skb); - th->source = inet->sport; - th->dest = inet->dport; + th->source = inet->inet_sport; + th->dest = inet->inet_dport; th->seq = htonl(tcb->seq); th->ack_seq = htonl(tp->rcv_nxt); *(((__be16 *)th) + 6) = htons(((tcp_header_size >> 2) << 12) | @@ -690,7 +862,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, } } - tcp_options_write((__be32 *)(th + 1), tp, &opts, &md5_hash_location); + tcp_options_write((__be32 *)(th + 1), tp, &opts); if (likely((tcb->flags & TCPCB_FLAG_SYN) == 0)) TCP_ECN_send(sk, skb, tcp_header_size); @@ -698,7 +870,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, /* Calculate the MD5 hash, as we have all we need now */ if (md5) { sk->sk_route_caps &= ~NETIF_F_GSO_MASK; - tp->af_specific->calc_md5_hash(md5_hash_location, + tp->af_specific->calc_md5_hash(opts.hash_location, md5, sk, NULL, skb); } #endif @@ -1918,8 +2090,8 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) * case, when window is shrunk to zero. In this case * our retransmit serves as a zero window probe. */ - if (!before(TCP_SKB_CB(skb)->seq, tcp_wnd_end(tp)) - && TCP_SKB_CB(skb)->seq != tp->snd_una) + if (!before(TCP_SKB_CB(skb)->seq, tcp_wnd_end(tp)) && + TCP_SKB_CB(skb)->seq != tp->snd_una) return -EAGAIN; if (skb->len > cur_mss) { @@ -2219,16 +2391,17 @@ int tcp_send_synack(struct sock *sk) /* Prepare a SYN-ACK. */ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, - struct request_sock *req) + struct request_sock *req, + struct request_values *rvp) { + struct tcp_out_options opts; + struct tcp_extend_values *xvp = tcp_xv(rvp); struct inet_request_sock *ireq = inet_rsk(req); struct tcp_sock *tp = tcp_sk(sk); struct tcphdr *th; - int tcp_header_size; - struct tcp_out_options opts; struct sk_buff *skb; struct tcp_md5sig_key *md5; - __u8 *md5_hash_location; + int tcp_header_size; int mss; skb = sock_wmalloc(sk, MAX_TCP_HEADER + 15, 1, GFP_ATOMIC); @@ -2266,8 +2439,8 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, #endif TCP_SKB_CB(skb)->when = tcp_time_stamp; tcp_header_size = tcp_synack_options(sk, req, mss, - skb, &opts, &md5) + - sizeof(struct tcphdr); + skb, &opts, &md5, xvp) + + sizeof(*th); skb_push(skb, tcp_header_size); skb_reset_transport_header(skb); @@ -2284,19 +2457,58 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, */ tcp_init_nondata_skb(skb, tcp_rsk(req)->snt_isn, TCPCB_FLAG_SYN | TCPCB_FLAG_ACK); + + if (OPTION_COOKIE_EXTENSION & opts.options) { + const struct tcp_cookie_values *cvp = tp->cookie_values; + + if (cvp != NULL && + cvp->s_data_constant && + cvp->s_data_desired > 0) { + u8 *buf = skb_put(skb, cvp->s_data_desired); + + /* copy data directly from the listening socket. */ + memcpy(buf, cvp->s_data_payload, cvp->s_data_desired); + TCP_SKB_CB(skb)->end_seq += cvp->s_data_desired; + } + + if (opts.hash_size > 0) { + __u32 workspace[SHA_WORKSPACE_WORDS]; + u32 *mess = &xvp->cookie_bakery[COOKIE_DIGEST_WORDS]; + u32 *tail = &mess[COOKIE_MESSAGE_WORDS-1]; + + /* Secret recipe depends on the Timestamp, (future) + * Sequence and Acknowledgment Numbers, Initiator + * Cookie, and others handled by IP variant caller. + */ + *tail-- ^= opts.tsval; + *tail-- ^= tcp_rsk(req)->rcv_isn + 1; + *tail-- ^= TCP_SKB_CB(skb)->seq + 1; + + /* recommended */ + *tail-- ^= ((th->dest << 16) | th->source); + *tail-- ^= (u32)(unsigned long)cvp; /* per sockopt */ + + sha_transform((__u32 *)&xvp->cookie_bakery[0], + (char *)mess, + &workspace[0]); + opts.hash_location = + (__u8 *)&xvp->cookie_bakery[0]; + } + } + th->seq = htonl(TCP_SKB_CB(skb)->seq); th->ack_seq = htonl(tcp_rsk(req)->rcv_isn + 1); /* RFC1323: The window in SYN & SYN/ACK segments is never scaled. */ th->window = htons(min(req->rcv_wnd, 65535U)); - tcp_options_write((__be32 *)(th + 1), tp, &opts, &md5_hash_location); + tcp_options_write((__be32 *)(th + 1), tp, &opts); th->doff = (tcp_header_size >> 2); TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS); #ifdef CONFIG_TCP_MD5SIG /* Okay, we have all we need - do the md5 hash if needed */ if (md5) { - tcp_rsk(req)->af_specific->calc_md5_hash(md5_hash_location, + tcp_rsk(req)->af_specific->calc_md5_hash(opts.hash_location, md5, NULL, req, skb); } #endif @@ -2315,7 +2527,9 @@ static void tcp_connect_init(struct sock *sk) * See tcp_input.c:tcp_rcv_state_process case TCP_SYN_SENT. */ tp->tcp_header_len = sizeof(struct tcphdr) + - (sysctl_tcp_timestamps ? TCPOLEN_TSTAMP_ALIGNED : 0); + (sysctl_tcp_timestamps && + (!dst_feature(dst, RTAX_FEATURE_NO_TSTAMP) ? + TCPOLEN_TSTAMP_ALIGNED : 0)); #ifdef CONFIG_TCP_MD5SIG if (tp->af_specific->md5_lookup(sk, sk) != NULL) @@ -2341,7 +2555,8 @@ static void tcp_connect_init(struct sock *sk) tp->advmss - (tp->rx_opt.ts_recent_stamp ? tp->tcp_header_len - sizeof(struct tcphdr) : 0), &tp->rcv_wnd, &tp->window_clamp, - sysctl_tcp_window_scaling, + (sysctl_tcp_window_scaling && + !dst_feature(dst, RTAX_FEATURE_NO_WSCALE)), &rcv_wscale); tp->rx_opt.rcv_wscale = rcv_wscale; diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c index 59f5b5e..bb110c5 100644 --- a/net/ipv4/tcp_probe.c +++ b/net/ipv4/tcp_probe.c @@ -94,8 +94,9 @@ static int jtcp_rcv_established(struct sock *sk, struct sk_buff *skb, const struct inet_sock *inet = inet_sk(sk); /* Only update if port matches */ - if ((port == 0 || ntohs(inet->dport) == port || ntohs(inet->sport) == port) - && (full || tp->snd_cwnd != tcp_probe.lastcwnd)) { + if ((port == 0 || ntohs(inet->inet_dport) == port || + ntohs(inet->inet_sport) == port) && + (full || tp->snd_cwnd != tcp_probe.lastcwnd)) { spin_lock(&tcp_probe.lock); /* If log fills, just silently drop */ @@ -103,10 +104,10 @@ static int jtcp_rcv_established(struct sock *sk, struct sk_buff *skb, struct tcp_log *p = tcp_probe.log + tcp_probe.head; p->tstamp = ktime_get(); - p->saddr = inet->saddr; - p->sport = inet->sport; - p->daddr = inet->daddr; - p->dport = inet->dport; + p->saddr = inet->inet_saddr; + p->sport = inet->inet_sport; + p->daddr = inet->inet_daddr; + p->dport = inet->inet_dport; p->length = skb->len; p->snd_nxt = tp->snd_nxt; p->snd_una = tp->snd_una; diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index cdb2ca7..8353a53 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -141,14 +141,14 @@ static int tcp_write_timeout(struct sock *sk) if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { if (icsk->icsk_retransmits) - dst_negative_advice(&sk->sk_dst_cache); + dst_negative_advice(&sk->sk_dst_cache, sk); retry_until = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries; } else { if (retransmits_timed_out(sk, sysctl_tcp_retries1)) { /* Black hole detection */ tcp_mtu_probing(icsk, sk); - dst_negative_advice(&sk->sk_dst_cache); + dst_negative_advice(&sk->sk_dst_cache, sk); } retry_until = sysctl_tcp_retries2; @@ -303,15 +303,15 @@ void tcp_retransmit_timer(struct sock *sk) struct inet_sock *inet = inet_sk(sk); if (sk->sk_family == AF_INET) { LIMIT_NETDEBUG(KERN_DEBUG "TCP: Peer %pI4:%u/%u unexpectedly shrunk window %u:%u (repaired)\n", - &inet->daddr, ntohs(inet->dport), - inet->num, tp->snd_una, tp->snd_nxt); + &inet->inet_daddr, ntohs(inet->inet_dport), + inet->inet_num, tp->snd_una, tp->snd_nxt); } #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) else if (sk->sk_family == AF_INET6) { struct ipv6_pinfo *np = inet6_sk(sk); LIMIT_NETDEBUG(KERN_DEBUG "TCP: Peer %pI6:%u/%u unexpectedly shrunk window %u:%u (repaired)\n", - &np->daddr, ntohs(inet->dport), - inet->num, tp->snd_una, tp->snd_nxt); + &np->daddr, ntohs(inet->inet_dport), + inet->inet_num, tp->snd_una, tp->snd_nxt); } #endif #endif diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c index e9bbff7..b612acf 100644 --- a/net/ipv4/tcp_veno.c +++ b/net/ipv4/tcp_veno.c @@ -165,9 +165,8 @@ static void tcp_veno_cong_avoid(struct sock *sk, u32 ack, u32 in_flight) * every other rtt. */ if (tp->snd_cwnd_cnt >= tp->snd_cwnd) { - if (veno->inc - && tp->snd_cwnd < - tp->snd_cwnd_clamp) { + if (veno->inc && + tp->snd_cwnd < tp->snd_cwnd_clamp) { tp->snd_cwnd++; veno->inc = 0; } else diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c index 66b6821..a0f2403 100644 --- a/net/ipv4/tcp_yeah.c +++ b/net/ipv4/tcp_yeah.c @@ -157,8 +157,8 @@ static void tcp_yeah_cong_avoid(struct sock *sk, u32 ack, u32 in_flight) if (queue > TCP_YEAH_ALPHA || rtt - yeah->vegas.baseRTT > (yeah->vegas.baseRTT / TCP_YEAH_PHY)) { - if (queue > TCP_YEAH_ALPHA - && tp->snd_cwnd > yeah->reno_count) { + if (queue > TCP_YEAH_ALPHA && + tp->snd_cwnd > yeah->reno_count) { u32 reduction = min(queue / TCP_YEAH_GAMMA , tp->snd_cwnd >> TCP_YEAH_EPSILON); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 0fa9f70..1f95348 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -106,7 +106,7 @@ #include <net/xfrm.h> #include "udp_impl.h" -struct udp_table udp_table; +struct udp_table udp_table __read_mostly; EXPORT_SYMBOL(udp_table); int sysctl_udp_mem[3] __read_mostly; @@ -121,28 +121,30 @@ EXPORT_SYMBOL(sysctl_udp_wmem_min); atomic_t udp_memory_allocated; EXPORT_SYMBOL(udp_memory_allocated); -#define PORTS_PER_CHAIN (65536 / UDP_HTABLE_SIZE) +#define MAX_UDP_PORTS 65536 +#define PORTS_PER_CHAIN (MAX_UDP_PORTS / UDP_HTABLE_SIZE_MIN) static int udp_lib_lport_inuse(struct net *net, __u16 num, const struct udp_hslot *hslot, unsigned long *bitmap, struct sock *sk, int (*saddr_comp)(const struct sock *sk1, - const struct sock *sk2)) + const struct sock *sk2), + unsigned int log) { struct sock *sk2; struct hlist_nulls_node *node; sk_nulls_for_each(sk2, node, &hslot->head) - if (net_eq(sock_net(sk2), net) && - sk2 != sk && - (bitmap || sk2->sk_hash == num) && - (!sk2->sk_reuse || !sk->sk_reuse) && - (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if - || sk2->sk_bound_dev_if == sk->sk_bound_dev_if) && + if (net_eq(sock_net(sk2), net) && + sk2 != sk && + (bitmap || udp_sk(sk2)->udp_port_hash == num) && + (!sk2->sk_reuse || !sk->sk_reuse) && + (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if || + sk2->sk_bound_dev_if == sk->sk_bound_dev_if) && (*saddr_comp)(sk, sk2)) { if (bitmap) - __set_bit(sk2->sk_hash / UDP_HTABLE_SIZE, + __set_bit(udp_sk(sk2)->udp_port_hash >> log, bitmap); else return 1; @@ -150,18 +152,51 @@ static int udp_lib_lport_inuse(struct net *net, __u16 num, return 0; } +/* + * Note: we still hold spinlock of primary hash chain, so no other writer + * can insert/delete a socket with local_port == num + */ +static int udp_lib_lport_inuse2(struct net *net, __u16 num, + struct udp_hslot *hslot2, + struct sock *sk, + int (*saddr_comp)(const struct sock *sk1, + const struct sock *sk2)) +{ + struct sock *sk2; + struct hlist_nulls_node *node; + int res = 0; + + spin_lock(&hslot2->lock); + udp_portaddr_for_each_entry(sk2, node, &hslot2->head) + if (net_eq(sock_net(sk2), net) && + sk2 != sk && + (udp_sk(sk2)->udp_port_hash == num) && + (!sk2->sk_reuse || !sk->sk_reuse) && + (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if || + sk2->sk_bound_dev_if == sk->sk_bound_dev_if) && + (*saddr_comp)(sk, sk2)) { + res = 1; + break; + } + spin_unlock(&hslot2->lock); + return res; +} + /** * udp_lib_get_port - UDP/-Lite port lookup for IPv4 and IPv6 * * @sk: socket struct in question * @snum: port number to look up * @saddr_comp: AF-dependent comparison of bound local IP addresses + * @hash2_nulladdr: AF-dependant hash value in secondary hash chains, + * with NULL address */ int udp_lib_get_port(struct sock *sk, unsigned short snum, int (*saddr_comp)(const struct sock *sk1, - const struct sock *sk2)) + const struct sock *sk2), + unsigned int hash2_nulladdr) { - struct udp_hslot *hslot; + struct udp_hslot *hslot, *hslot2; struct udp_table *udptable = sk->sk_prot->h.udp_table; int error = 1; struct net *net = sock_net(sk); @@ -180,13 +215,15 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum, /* * force rand to be an odd multiple of UDP_HTABLE_SIZE */ - rand = (rand | 1) * UDP_HTABLE_SIZE; - for (last = first + UDP_HTABLE_SIZE; first != last; first++) { - hslot = &udptable->hash[udp_hashfn(net, first)]; + rand = (rand | 1) * (udptable->mask + 1); + for (last = first + udptable->mask + 1; + first != last; + first++) { + hslot = udp_hashslot(udptable, net, first); bitmap_zero(bitmap, PORTS_PER_CHAIN); spin_lock_bh(&hslot->lock); udp_lib_lport_inuse(net, snum, hslot, bitmap, sk, - saddr_comp); + saddr_comp, udptable->log); snum = first; /* @@ -196,7 +233,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum, */ do { if (low <= snum && snum <= high && - !test_bit(snum / UDP_HTABLE_SIZE, bitmap)) + !test_bit(snum >> udptable->log, bitmap)) goto found; snum += rand; } while (snum != first); @@ -204,17 +241,51 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum, } goto fail; } else { - hslot = &udptable->hash[udp_hashfn(net, snum)]; + hslot = udp_hashslot(udptable, net, snum); spin_lock_bh(&hslot->lock); - if (udp_lib_lport_inuse(net, snum, hslot, NULL, sk, saddr_comp)) + if (hslot->count > 10) { + int exist; + unsigned int slot2 = udp_sk(sk)->udp_portaddr_hash ^ snum; + + slot2 &= udptable->mask; + hash2_nulladdr &= udptable->mask; + + hslot2 = udp_hashslot2(udptable, slot2); + if (hslot->count < hslot2->count) + goto scan_primary_hash; + + exist = udp_lib_lport_inuse2(net, snum, hslot2, + sk, saddr_comp); + if (!exist && (hash2_nulladdr != slot2)) { + hslot2 = udp_hashslot2(udptable, hash2_nulladdr); + exist = udp_lib_lport_inuse2(net, snum, hslot2, + sk, saddr_comp); + } + if (exist) + goto fail_unlock; + else + goto found; + } +scan_primary_hash: + if (udp_lib_lport_inuse(net, snum, hslot, NULL, sk, + saddr_comp, 0)) goto fail_unlock; } found: - inet_sk(sk)->num = snum; - sk->sk_hash = snum; + inet_sk(sk)->inet_num = snum; + udp_sk(sk)->udp_port_hash = snum; + udp_sk(sk)->udp_portaddr_hash ^= snum; if (sk_unhashed(sk)) { sk_nulls_add_node_rcu(sk, &hslot->head); + hslot->count++; sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); + + hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash); + spin_lock(&hslot2->lock); + hlist_nulls_add_head_rcu(&udp_sk(sk)->udp_portaddr_node, + &hslot2->head); + hslot2->count++; + spin_unlock(&hslot2->lock); } error = 0; fail_unlock: @@ -229,13 +300,26 @@ static int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2) struct inet_sock *inet1 = inet_sk(sk1), *inet2 = inet_sk(sk2); return (!ipv6_only_sock(sk2) && - (!inet1->rcv_saddr || !inet2->rcv_saddr || - inet1->rcv_saddr == inet2->rcv_saddr)); + (!inet1->inet_rcv_saddr || !inet2->inet_rcv_saddr || + inet1->inet_rcv_saddr == inet2->inet_rcv_saddr)); +} + +static unsigned int udp4_portaddr_hash(struct net *net, __be32 saddr, + unsigned int port) +{ + return jhash_1word(saddr, net_hash_mix(net)) ^ port; } int udp_v4_get_port(struct sock *sk, unsigned short snum) { - return udp_lib_get_port(sk, snum, ipv4_rcv_saddr_equal); + unsigned int hash2_nulladdr = + udp4_portaddr_hash(sock_net(sk), INADDR_ANY, snum); + unsigned int hash2_partial = + udp4_portaddr_hash(sock_net(sk), inet_sk(sk)->inet_rcv_saddr, 0); + + /* precompute partial secondary hash */ + udp_sk(sk)->udp_portaddr_hash = hash2_partial; + return udp_lib_get_port(sk, snum, ipv4_rcv_saddr_equal, hash2_nulladdr); } static inline int compute_score(struct sock *sk, struct net *net, __be32 saddr, @@ -244,23 +328,61 @@ static inline int compute_score(struct sock *sk, struct net *net, __be32 saddr, { int score = -1; - if (net_eq(sock_net(sk), net) && sk->sk_hash == hnum && + if (net_eq(sock_net(sk), net) && udp_sk(sk)->udp_port_hash == hnum && !ipv6_only_sock(sk)) { struct inet_sock *inet = inet_sk(sk); score = (sk->sk_family == PF_INET ? 1 : 0); - if (inet->rcv_saddr) { - if (inet->rcv_saddr != daddr) + if (inet->inet_rcv_saddr) { + if (inet->inet_rcv_saddr != daddr) + return -1; + score += 2; + } + if (inet->inet_daddr) { + if (inet->inet_daddr != saddr) + return -1; + score += 2; + } + if (inet->inet_dport) { + if (inet->inet_dport != sport) + return -1; + score += 2; + } + if (sk->sk_bound_dev_if) { + if (sk->sk_bound_dev_if != dif) return -1; score += 2; } - if (inet->daddr) { - if (inet->daddr != saddr) + } + return score; +} + +/* + * In this second variant, we check (daddr, dport) matches (inet_rcv_sadd, inet_num) + */ +#define SCORE2_MAX (1 + 2 + 2 + 2) +static inline int compute_score2(struct sock *sk, struct net *net, + __be32 saddr, __be16 sport, + __be32 daddr, unsigned int hnum, int dif) +{ + int score = -1; + + if (net_eq(sock_net(sk), net) && !ipv6_only_sock(sk)) { + struct inet_sock *inet = inet_sk(sk); + + if (inet->inet_rcv_saddr != daddr) + return -1; + if (inet->inet_num != hnum) + return -1; + + score = (sk->sk_family == PF_INET ? 1 : 0); + if (inet->inet_daddr) { + if (inet->inet_daddr != saddr) return -1; score += 2; } - if (inet->dport) { - if (inet->dport != sport) + if (inet->inet_dport) { + if (inet->inet_dport != sport) return -1; score += 2; } @@ -273,6 +395,51 @@ static inline int compute_score(struct sock *sk, struct net *net, __be32 saddr, return score; } + +/* called with read_rcu_lock() */ +static struct sock *udp4_lib_lookup2(struct net *net, + __be32 saddr, __be16 sport, + __be32 daddr, unsigned int hnum, int dif, + struct udp_hslot *hslot2, unsigned int slot2) +{ + struct sock *sk, *result; + struct hlist_nulls_node *node; + int score, badness; + +begin: + result = NULL; + badness = -1; + udp_portaddr_for_each_entry_rcu(sk, node, &hslot2->head) { + score = compute_score2(sk, net, saddr, sport, + daddr, hnum, dif); + if (score > badness) { + result = sk; + badness = score; + if (score == SCORE2_MAX) + goto exact_match; + } + } + /* + * if the nulls value we got at the end of this lookup is + * not the expected one, we must restart lookup. + * We probably met an item that was moved to another chain. + */ + if (get_nulls_value(node) != slot2) + goto begin; + + if (result) { +exact_match: + if (unlikely(!atomic_inc_not_zero(&result->sk_refcnt))) + result = NULL; + else if (unlikely(compute_score2(result, net, saddr, sport, + daddr, hnum, dif) < badness)) { + sock_put(result); + goto begin; + } + } + return result; +} + /* UDP is nearly always wildcards out the wazoo, it makes no sense to try * harder than this. -DaveM */ @@ -283,11 +450,35 @@ static struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, struct sock *sk, *result; struct hlist_nulls_node *node; unsigned short hnum = ntohs(dport); - unsigned int hash = udp_hashfn(net, hnum); - struct udp_hslot *hslot = &udptable->hash[hash]; + unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask); + struct udp_hslot *hslot2, *hslot = &udptable->hash[slot]; int score, badness; rcu_read_lock(); + if (hslot->count > 10) { + hash2 = udp4_portaddr_hash(net, daddr, hnum); + slot2 = hash2 & udptable->mask; + hslot2 = &udptable->hash2[slot2]; + if (hslot->count < hslot2->count) + goto begin; + + result = udp4_lib_lookup2(net, saddr, sport, + daddr, hnum, dif, + hslot2, slot2); + if (!result) { + hash2 = udp4_portaddr_hash(net, INADDR_ANY, hnum); + slot2 = hash2 & udptable->mask; + hslot2 = &udptable->hash2[slot2]; + if (hslot->count < hslot2->count) + goto begin; + + result = udp4_lib_lookup2(net, INADDR_ANY, sport, + daddr, hnum, dif, + hslot2, slot2); + } + rcu_read_unlock(); + return result; + } begin: result = NULL; badness = -1; @@ -304,7 +495,7 @@ begin: * not the expected one, we must restart lookup. * We probably met an item that was moved to another chain. */ - if (get_nulls_value(node) != hash) + if (get_nulls_value(node) != slot) goto begin; if (result) { @@ -354,12 +545,13 @@ static inline struct sock *udp_v4_mcast_next(struct net *net, struct sock *sk, sk_nulls_for_each_from(s, node) { struct inet_sock *inet = inet_sk(s); - if (!net_eq(sock_net(s), net) || - s->sk_hash != hnum || - (inet->daddr && inet->daddr != rmt_addr) || - (inet->dport != rmt_port && inet->dport) || - (inet->rcv_saddr && inet->rcv_saddr != loc_addr) || - ipv6_only_sock(s) || + if (!net_eq(sock_net(s), net) || + udp_sk(s)->udp_port_hash != hnum || + (inet->inet_daddr && inet->inet_daddr != rmt_addr) || + (inet->inet_dport != rmt_port && inet->inet_dport) || + (inet->inet_rcv_saddr && + inet->inet_rcv_saddr != loc_addr) || + ipv6_only_sock(s) || (s->sk_bound_dev_if && s->sk_bound_dev_if != dif)) continue; if (!ip_mc_sf_allow(s, loc_addr, rmt_addr, dif)) @@ -642,14 +834,14 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, } else { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; - daddr = inet->daddr; - dport = inet->dport; + daddr = inet->inet_daddr; + dport = inet->inet_dport; /* Open fast path for connected socket. Route will not be used, if at least one option is set. */ connected = 1; } - ipc.addr = inet->saddr; + ipc.addr = inet->inet_saddr; ipc.oif = sk->sk_bound_dev_if; err = sock_tx_timestamp(msg, sk, &ipc.shtx); @@ -704,7 +896,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, .proto = sk->sk_protocol, .flags = inet_sk_flowi_flags(sk), .uli_u = { .ports = - { .sport = inet->sport, + { .sport = inet->inet_sport, .dport = dport } } }; struct net *net = sock_net(sk); @@ -748,7 +940,7 @@ back_from_confirm: inet->cork.fl.fl4_dst = daddr; inet->cork.fl.fl_ip_dport = dport; inet->cork.fl.fl4_src = saddr; - inet->cork.fl.fl_ip_sport = inet->sport; + inet->cork.fl.fl_ip_sport = inet->inet_sport; up->pending = AF_INET; do_append_data: @@ -862,6 +1054,7 @@ static unsigned int first_packet_length(struct sock *sk) udp_lib_checksum_complete(skb)) { UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, IS_UDPLITE(sk)); + atomic_inc(&sk->sk_drops); __skb_unlink(skb, rcvq); __skb_queue_tail(&list_kill, skb); } @@ -982,7 +1175,7 @@ try_again: UDP_INC_STATS_USER(sock_net(sk), UDP_MIB_INDATAGRAMS, is_udplite); - sock_recv_timestamp(msg, sk, skb); + sock_recv_ts_and_drops(msg, sk, skb); /* Copy the address. */ if (sin) { @@ -1023,15 +1216,15 @@ int udp_disconnect(struct sock *sk, int flags) */ sk->sk_state = TCP_CLOSE; - inet->daddr = 0; - inet->dport = 0; + inet->inet_daddr = 0; + inet->inet_dport = 0; sk->sk_bound_dev_if = 0; if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) inet_reset_saddr(sk); if (!(sk->sk_userlocks & SOCK_BINDPORT_LOCK)) { sk->sk_prot->unhash(sk); - inet->sport = 0; + inet->inet_sport = 0; } sk_dst_reset(sk); return 0; @@ -1042,13 +1235,22 @@ void udp_lib_unhash(struct sock *sk) { if (sk_hashed(sk)) { struct udp_table *udptable = sk->sk_prot->h.udp_table; - unsigned int hash = udp_hashfn(sock_net(sk), sk->sk_hash); - struct udp_hslot *hslot = &udptable->hash[hash]; + struct udp_hslot *hslot, *hslot2; + + hslot = udp_hashslot(udptable, sock_net(sk), + udp_sk(sk)->udp_port_hash); + hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash); spin_lock_bh(&hslot->lock); if (sk_nulls_del_node_init_rcu(sk)) { - inet_sk(sk)->num = 0; + hslot->count--; + inet_sk(sk)->inet_num = 0; sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); + + spin_lock(&hslot2->lock); + hlist_nulls_del_init_rcu(&udp_sk(sk)->udp_portaddr_node); + hslot2->count--; + spin_unlock(&hslot2->lock); } spin_unlock_bh(&hslot->lock); } @@ -1057,25 +1259,22 @@ EXPORT_SYMBOL(udp_lib_unhash); static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { - int is_udplite = IS_UDPLITE(sk); - int rc; + int rc = sock_queue_rcv_skb(sk, skb); + + if (rc < 0) { + int is_udplite = IS_UDPLITE(sk); - if ((rc = sock_queue_rcv_skb(sk, skb)) < 0) { /* Note that an ENOMEM error is charged twice */ - if (rc == -ENOMEM) { + if (rc == -ENOMEM) UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_RCVBUFERRORS, is_udplite); - atomic_inc(&sk->sk_drops); - } - goto drop; + UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, is_udplite); + kfree_skb(skb); + return -1; } return 0; -drop: - UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, is_udplite); - kfree_skb(skb); - return -1; } /* returns: @@ -1182,53 +1381,88 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) drop: UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, is_udplite); + atomic_inc(&sk->sk_drops); kfree_skb(skb); return -1; } + +static void flush_stack(struct sock **stack, unsigned int count, + struct sk_buff *skb, unsigned int final) +{ + unsigned int i; + struct sk_buff *skb1 = NULL; + struct sock *sk; + + for (i = 0; i < count; i++) { + sk = stack[i]; + if (likely(skb1 == NULL)) + skb1 = (i == final) ? skb : skb_clone(skb, GFP_ATOMIC); + + if (!skb1) { + atomic_inc(&sk->sk_drops); + UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_RCVBUFERRORS, + IS_UDPLITE(sk)); + UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, + IS_UDPLITE(sk)); + } + + if (skb1 && udp_queue_rcv_skb(sk, skb1) <= 0) + skb1 = NULL; + } + if (unlikely(skb1)) + kfree_skb(skb1); +} + /* * Multicasts and broadcasts go to each listener. * - * Note: called only from the BH handler context, - * so we don't need to lock the hashes. + * Note: called only from the BH handler context. */ static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb, struct udphdr *uh, __be32 saddr, __be32 daddr, struct udp_table *udptable) { - struct sock *sk; - struct udp_hslot *hslot = &udptable->hash[udp_hashfn(net, ntohs(uh->dest))]; + struct sock *sk, *stack[256 / sizeof(struct sock *)]; + struct udp_hslot *hslot = udp_hashslot(udptable, net, ntohs(uh->dest)); int dif; + unsigned int i, count = 0; spin_lock(&hslot->lock); sk = sk_nulls_head(&hslot->head); dif = skb->dev->ifindex; sk = udp_v4_mcast_next(net, sk, uh->dest, daddr, uh->source, saddr, dif); - if (sk) { - struct sock *sknext = NULL; - - do { - struct sk_buff *skb1 = skb; - - sknext = udp_v4_mcast_next(net, sk_nulls_next(sk), uh->dest, - daddr, uh->source, saddr, - dif); - if (sknext) - skb1 = skb_clone(skb, GFP_ATOMIC); - - if (skb1) { - int ret = udp_queue_rcv_skb(sk, skb1); - if (ret > 0) - /* we should probably re-process instead - * of dropping packets here. */ - kfree_skb(skb1); - } - sk = sknext; - } while (sknext); - } else - consume_skb(skb); + while (sk) { + stack[count++] = sk; + sk = udp_v4_mcast_next(net, sk_nulls_next(sk), uh->dest, + daddr, uh->source, saddr, dif); + if (unlikely(count == ARRAY_SIZE(stack))) { + if (!sk) + break; + flush_stack(stack, count, skb, ~0); + count = 0; + } + } + /* + * before releasing chain lock, we must take a reference on sockets + */ + for (i = 0; i < count; i++) + sock_hold(stack[i]); + spin_unlock(&hslot->lock); + + /* + * do the slow work with no lock held + */ + if (count) { + flush_stack(stack, count, skb, count - 1); + + for (i = 0; i < count; i++) + sock_put(stack[i]); + } else { + kfree_skb(skb); + } return 0; } @@ -1620,9 +1854,14 @@ static struct sock *udp_get_first(struct seq_file *seq, int start) struct udp_iter_state *state = seq->private; struct net *net = seq_file_net(seq); - for (state->bucket = start; state->bucket < UDP_HTABLE_SIZE; ++state->bucket) { + for (state->bucket = start; state->bucket <= state->udp_table->mask; + ++state->bucket) { struct hlist_nulls_node *node; struct udp_hslot *hslot = &state->udp_table->hash[state->bucket]; + + if (hlist_nulls_empty(&hslot->head)) + continue; + spin_lock_bh(&hslot->lock); sk_nulls_for_each(sk, node, &hslot->head) { if (!net_eq(sock_net(sk), net)) @@ -1647,7 +1886,7 @@ static struct sock *udp_get_next(struct seq_file *seq, struct sock *sk) } while (sk && (!net_eq(sock_net(sk), net) || sk->sk_family != state->family)); if (!sk) { - if (state->bucket < UDP_HTABLE_SIZE) + if (state->bucket <= state->udp_table->mask) spin_unlock_bh(&state->udp_table->hash[state->bucket].lock); return udp_get_first(seq, state->bucket + 1); } @@ -1667,7 +1906,7 @@ static struct sock *udp_get_idx(struct seq_file *seq, loff_t pos) static void *udp_seq_start(struct seq_file *seq, loff_t *pos) { struct udp_iter_state *state = seq->private; - state->bucket = UDP_HTABLE_SIZE; + state->bucket = MAX_UDP_PORTS; return *pos ? udp_get_idx(seq, *pos-1) : SEQ_START_TOKEN; } @@ -1689,7 +1928,7 @@ static void udp_seq_stop(struct seq_file *seq, void *v) { struct udp_iter_state *state = seq->private; - if (state->bucket < UDP_HTABLE_SIZE) + if (state->bucket <= state->udp_table->mask) spin_unlock_bh(&state->udp_table->hash[state->bucket].lock); } @@ -1744,12 +1983,12 @@ static void udp4_format_sock(struct sock *sp, struct seq_file *f, int bucket, int *len) { struct inet_sock *inet = inet_sk(sp); - __be32 dest = inet->daddr; - __be32 src = inet->rcv_saddr; - __u16 destp = ntohs(inet->dport); - __u16 srcp = ntohs(inet->sport); + __be32 dest = inet->inet_daddr; + __be32 src = inet->inet_rcv_saddr; + __u16 destp = ntohs(inet->inet_dport); + __u16 srcp = ntohs(inet->inet_sport); - seq_printf(f, "%4d: %08X:%04X %08X:%04X" + seq_printf(f, "%5d: %08X:%04X %08X:%04X" " %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %d%n", bucket, src, srcp, dest, destp, sp->sk_state, sk_wmem_alloc_get(sp), @@ -1815,21 +2054,60 @@ void udp4_proc_exit(void) } #endif /* CONFIG_PROC_FS */ -void __init udp_table_init(struct udp_table *table) +static __initdata unsigned long uhash_entries; +static int __init set_uhash_entries(char *str) { - int i; + if (!str) + return 0; + uhash_entries = simple_strtoul(str, &str, 0); + if (uhash_entries && uhash_entries < UDP_HTABLE_SIZE_MIN) + uhash_entries = UDP_HTABLE_SIZE_MIN; + return 1; +} +__setup("uhash_entries=", set_uhash_entries); - for (i = 0; i < UDP_HTABLE_SIZE; i++) { +void __init udp_table_init(struct udp_table *table, const char *name) +{ + unsigned int i; + + if (!CONFIG_BASE_SMALL) + table->hash = alloc_large_system_hash(name, + 2 * sizeof(struct udp_hslot), + uhash_entries, + 21, /* one slot per 2 MB */ + 0, + &table->log, + &table->mask, + 64 * 1024); + /* + * Make sure hash table has the minimum size + */ + if (CONFIG_BASE_SMALL || table->mask < UDP_HTABLE_SIZE_MIN - 1) { + table->hash = kmalloc(UDP_HTABLE_SIZE_MIN * + 2 * sizeof(struct udp_hslot), GFP_KERNEL); + if (!table->hash) + panic(name); + table->log = ilog2(UDP_HTABLE_SIZE_MIN); + table->mask = UDP_HTABLE_SIZE_MIN - 1; + } + table->hash2 = table->hash + (table->mask + 1); + for (i = 0; i <= table->mask; i++) { INIT_HLIST_NULLS_HEAD(&table->hash[i].head, i); + table->hash[i].count = 0; spin_lock_init(&table->hash[i].lock); } + for (i = 0; i <= table->mask; i++) { + INIT_HLIST_NULLS_HEAD(&table->hash2[i].head, i); + table->hash2[i].count = 0; + spin_lock_init(&table->hash2[i].lock); + } } void __init udp_init(void) { unsigned long nr_pages, limit; - udp_table_init(&udp_table); + udp_table_init(&udp_table, "UDP"); /* Set the pressure threshold up by the same strategy of TCP. It is a * fraction of global memory that is up to 1/2 at 256 MB, decreasing * toward zero with the amount of memory, with a floor of 128 pages. diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c index 95248d7..66f7951 100644 --- a/net/ipv4/udplite.c +++ b/net/ipv4/udplite.c @@ -12,7 +12,7 @@ */ #include "udp_impl.h" -struct udp_table udplite_table; +struct udp_table udplite_table __read_mostly; EXPORT_SYMBOL(udplite_table); static int udplite_rcv(struct sk_buff *skb) @@ -64,7 +64,6 @@ static struct inet_protosw udplite4_protosw = { .protocol = IPPROTO_UDPLITE, .prot = &udplite_prot, .ops = &inet_dgram_ops, - .capability = -1, .no_check = 0, /* must checksum (RFC 3828) */ .flags = INET_PROTOSW_PERMANENT, }; @@ -110,7 +109,7 @@ static inline int udplite4_proc_init(void) void __init udplite4_register(void) { - udp_table_init(&udplite_table); + udp_table_init(&udplite_table, "UDP-Lite"); if (proto_register(&udplite_prot, 1)) goto out_register_err; |
