Require the address and port information for the target (non initiating) side to be populated when a flow enters TGT state. Implement that for TCP and ICMP. For now this leaves some information redundantly recorded in both generic and type specific fields. We'll fix that in later patches. For TCP we now use the information from the flow to construct the destination socket address in both tcp_conn_from_tap() and tcp_splice_connect(). Signed-off-by: David Gibson --- flow.c | 38 ++++++++++++++++++------ flow_table.h | 5 +++- icmp.c | 3 +- inany.h | 1 - pif.c | 45 ++++++++++++++++++++++++++++ pif.h | 17 +++++++++++ tcp.c | 82 ++++++++++++++++++++++++++++------------------------ tcp_splice.c | 45 +++++++++++----------------- 8 files changed, 158 insertions(+), 78 deletions(-) diff --git a/flow.c b/flow.c index 44e7b3b8..f064fad1 100644 --- a/flow.c +++ b/flow.c @@ -165,8 +165,10 @@ void flow_log_(const struct flow_common *f, int pri, const char *fmt, ...) */ static void flow_set_state(struct flow_common *f, enum flow_state state) { - char estr[INANY_ADDRSTRLEN], fstr[INANY_ADDRSTRLEN]; + char estr0[INANY_ADDRSTRLEN], fstr0[INANY_ADDRSTRLEN]; + char estr1[INANY_ADDRSTRLEN], fstr1[INANY_ADDRSTRLEN]; const struct flowside *ini = &f->side[INISIDE]; + const struct flowside *tgt = &f->side[TGTSIDE]; uint8_t oldstate = f->state; ASSERT(state < FLOW_NUM_STATES); @@ -177,19 +179,24 @@ static void flow_set_state(struct flow_common *f, enum flow_state state) FLOW_STATE(f)); if (MAX(state, oldstate) >= FLOW_STATE_TGT) - flow_log_(f, LOG_DEBUG, "%s [%s]:%hu -> [%s]:%hu => %s", + flow_log_(f, LOG_DEBUG, + "%s [%s]:%hu -> [%s]:%hu => %s [%s]:%hu -> [%s]:%hu", pif_name(f->pif[INISIDE]), - inany_ntop(&ini->eaddr, estr, sizeof(estr)), + inany_ntop(&ini->eaddr, estr0, sizeof(estr0)), ini->eport, - inany_ntop(&ini->faddr, fstr, sizeof(fstr)), + inany_ntop(&ini->faddr, fstr0, sizeof(fstr0)), ini->fport, - pif_name(f->pif[TGTSIDE])); + pif_name(f->pif[TGTSIDE]), + inany_ntop(&tgt->faddr, fstr1, sizeof(fstr1)), + tgt->fport, + inany_ntop(&tgt->eaddr, estr1, sizeof(estr1)), + tgt->eport); else if (MAX(state, oldstate) >= FLOW_STATE_INI) flow_log_(f, LOG_DEBUG, "%s [%s]:%hu -> [%s]:%hu => ?", pif_name(f->pif[INISIDE]), - inany_ntop(&ini->eaddr, estr, sizeof(estr)), + inany_ntop(&ini->eaddr, estr0, sizeof(estr0)), ini->eport, - inany_ntop(&ini->faddr, fstr, sizeof(fstr)), + inany_ntop(&ini->faddr, fstr0, sizeof(fstr0)), ini->fport); } @@ -261,21 +268,34 @@ const struct flowside *flow_initiate_sa(union flow *flow, uint8_t pif, } /** - * flow_target() - Move flow to TGT, setting TGTSIDE details + * flow_target_af() - Move flow to TGT, setting TGTSIDE details * @flow: Flow to change state * @pif: pif of the target side + * @af: Address family for @eaddr and @faddr + * @saddr: Source address (pointer to in_addr or in6_addr) + * @sport: Endpoint port + * @daddr: Destination address (pointer to in_addr or in6_addr) + * @dport: Destination port + * + * Return: pointer to the target flowside information */ -void flow_target(union flow *flow, uint8_t pif) +const struct flowside *flow_target_af(union flow *flow, uint8_t pif, + sa_family_t af, + const void *saddr, in_port_t sport, + const void *daddr, in_port_t dport) { struct flow_common *f = &flow->f; + struct flowside *tgt = &f->side[TGTSIDE]; ASSERT(pif != PIF_NONE); ASSERT(flow_new_entry == flow && f->state == FLOW_STATE_INI); ASSERT(f->type == FLOW_TYPE_NONE); ASSERT(f->pif[INISIDE] != PIF_NONE && f->pif[TGTSIDE] == PIF_NONE); + flowside_from_af(tgt, af, daddr, dport, saddr, sport); f->pif[TGTSIDE] = pif; flow_set_state(f, FLOW_STATE_TGT); + return tgt; } /** diff --git a/flow_table.h b/flow_table.h index ad1bc787..00dca4b2 100644 --- a/flow_table.h +++ b/flow_table.h @@ -114,7 +114,10 @@ const struct flowside *flow_initiate_af(union flow *flow, uint8_t pif, const struct flowside *flow_initiate_sa(union flow *flow, uint8_t pif, const union sockaddr_inany *ssa, in_port_t dport); -void flow_target(union flow *flow, uint8_t pif); +const struct flowside *flow_target_af(union flow *flow, uint8_t pif, + sa_family_t af, + const void *saddr, in_port_t sport, + const void *daddr, in_port_t dport); union flow *flow_set_type(union flow *flow, enum flow_type type); #define FLOW_SET_TYPE(flow_, t_, var_) (&flow_set_type((flow_), (t_))->var_) diff --git a/icmp.c b/icmp.c index cf88ac1f..fd92c7da 100644 --- a/icmp.c +++ b/icmp.c @@ -167,7 +167,8 @@ static struct icmp_ping_flow *icmp_ping_new(const struct ctx *c, return NULL; flow_initiate_af(flow, PIF_TAP, af, saddr, id, daddr, id); - flow_target(flow, PIF_HOST); + /* FIXME: Record outbound source address when known */ + flow_target_af(flow, PIF_HOST, af, NULL, 0, daddr, 0); pingf = FLOW_SET_TYPE(flow, flowtype, ping); pingf->seq = -1; diff --git a/inany.h b/inany.h index 47b66fa9..8eaf5335 100644 --- a/inany.h +++ b/inany.h @@ -187,7 +187,6 @@ static inline bool inany_is_unspecified(const union inany_addr *a) * * Return: true if @a is in fe80::/10 (IPv6 link local unicast) */ -/* cppcheck-suppress unusedFunction */ static inline bool inany_is_linklocal6(const union inany_addr *a) { return IN6_IS_ADDR_LINKLOCAL(&a->a6); diff --git a/pif.c b/pif.c index ebf01cc8..9f2d39cc 100644 --- a/pif.c +++ b/pif.c @@ -7,9 +7,14 @@ #include #include +#include #include "util.h" #include "pif.h" +#include "siphash.h" +#include "ip.h" +#include "inany.h" +#include "passt.h" const char *pif_type_str[] = { [PIF_NONE] = "<none>", @@ -19,3 +24,43 @@ const char *pif_type_str[] = { }; static_assert(ARRAY_SIZE(pif_type_str) == PIF_NUM_TYPES, "pif_type_str[] doesn't match enum pif_type"); + + +/** pif_sockaddr() - Construct a socket address suitable for an interface + * @c: Execution context + * @sa: Pointer to sockaddr to fill in + * @sl: Updated to relevant of length of initialised @sa + * @pif: Interface to create the socket address + * @addr: IPv[46] address + * @port: Port (host byte order) + * + * Return: true if resulting socket address is non-trivial (specified address or + * non-zero port), false otherwise + */ +bool pif_sockaddr(const struct ctx *c, union sockaddr_inany *sa, socklen_t *sl, + uint8_t pif, const union inany_addr *addr, in_port_t port) +{ + const struct in_addr *v4 = inany_v4(addr); + + ASSERT(pif_is_socket(pif)); + + if (v4) { + sa->sa_family = AF_INET; + sa->sa4.sin_addr = *v4; + sa->sa4.sin_port = htons(port); + memset(&sa->sa4.sin_zero, 0, sizeof(sa->sa4.sin_zero)); + *sl = sizeof(sa->sa4); + return !IN4_IS_ADDR_UNSPECIFIED(v4) || port; + } + + sa->sa_family = AF_INET6; + sa->sa6.sin6_addr = addr->a6; + sa->sa6.sin6_port = htons(port); + if (pif == PIF_HOST && IN6_IS_ADDR_LINKLOCAL(&addr->a6)) + sa->sa6.sin6_scope_id = c->ifi6; + else + sa->sa6.sin6_scope_id = 0; + sa->sa6.sin6_flowinfo = 0; + *sl = sizeof(sa->sa6); + return !IN6_IS_ADDR_UNSPECIFIED(&addr->a6) || port; +} diff --git a/pif.h b/pif.h index ca85b349..0e97afa1 100644 --- a/pif.h +++ b/pif.h @@ -7,6 +7,9 @@ #ifndef PIF_H #define PIF_H +union inany_addr; +union sockaddr_inany; + /** * enum pif_type - Type of passt/pasta interface ("pif") * @@ -43,4 +46,18 @@ static inline const char *pif_name(uint8_t pif) return pif_type(pif); } +/** + * pif_is_socket() - Is interface implemented via L4 sockets? + * @pif: pif to check + * + * Return: true of @pif is an L4 socket based interface, otherwise false + */ +static inline bool pif_is_socket(uint8_t pif) +{ + return pif == PIF_HOST || pif == PIF_SPLICE; +} + +bool pif_sockaddr(const struct ctx *c, union sockaddr_inany *sa, socklen_t *sl, + uint8_t pif, const union inany_addr *addr, in_port_t port); + #endif /* PIF_H */ diff --git a/tcp.c b/tcp.c index f4c910f3..46f6c145 100644 --- a/tcp.c +++ b/tcp.c @@ -1601,18 +1601,10 @@ static void tcp_conn_from_tap(struct ctx *c, sa_family_t af, { in_port_t srcport = ntohs(th->source); in_port_t dstport = ntohs(th->dest); - struct sockaddr_in addr4 = { - .sin_family = AF_INET, - .sin_port = htons(dstport), - .sin_addr = *(struct in_addr *)daddr, - }; - struct sockaddr_in6 addr6 = { - .sin6_family = AF_INET6, - .sin6_port = htons(dstport), - .sin6_addr = *(struct in6_addr *)daddr, - }; - const struct sockaddr *sa; + const struct flowside *ini, *tgt; struct tcp_tap_conn *conn; + union inany_addr dstaddr; /* FIXME: Avoid bulky temporary */ + union sockaddr_inany sa; union flow *flow; int s = -1, mss; socklen_t sl; @@ -1620,9 +1612,22 @@ static void tcp_conn_from_tap(struct ctx *c, sa_family_t af, if (!(flow = flow_alloc())) return; - flow_initiate_af(flow, PIF_TAP, af, saddr, srcport, daddr, dstport); + ini = flow_initiate_af(flow, PIF_TAP, + af, saddr, srcport, daddr, dstport); + + dstaddr = ini->faddr; + if (!c->no_map_gw) { + if (inany_equals4(&dstaddr, &c->ip4.gw)) + dstaddr = inany_loopback4; + else if (inany_equals6(&dstaddr, &c->ip6.gw)) + dstaddr = inany_loopback6; + + } - flow_target(flow, PIF_HOST); + /* FIXME: Record outbound source address when known */ + tgt = flow_target_af(flow, PIF_HOST, AF_INET6, + NULL, 0, /* Kernel decides source address */ + &dstaddr, dstport); conn = FLOW_SET_TYPE(flow, FLOW_TCP, tcp); if (af == AF_INET) { @@ -1641,9 +1646,6 @@ static void tcp_conn_from_tap(struct ctx *c, sa_family_t af, dstport); goto cancel; } - - sa = (struct sockaddr *)&addr4; - sl = sizeof(addr4); } else if (af == AF_INET6) { if (IN6_IS_ADDR_UNSPECIFIED(saddr) || IN6_IS_ADDR_MULTICAST(saddr) || srcport == 0 || @@ -1658,9 +1660,6 @@ static void tcp_conn_from_tap(struct ctx *c, sa_family_t af, dstport); goto cancel; } - - sa = (struct sockaddr *)&addr6; - sl = sizeof(addr6); } else { ASSERT(0); } @@ -1668,12 +1667,7 @@ static void tcp_conn_from_tap(struct ctx *c, sa_family_t af, if ((s = tcp_conn_sock(c, af)) < 0) goto cancel; - if (!c->no_map_gw) { - if (af == AF_INET && IN4_ARE_ADDR_EQUAL(daddr, &c->ip4.gw)) - addr4.sin_addr.s_addr = htonl(INADDR_LOOPBACK); - if (af == AF_INET6 && IN6_ARE_ADDR_EQUAL(daddr, &c->ip6.gw)) - addr6.sin6_addr = in6addr_loopback; - } + pif_sockaddr(c, &sa, &sl, PIF_HOST, &tgt->eaddr, tgt->eport); /* Use bind() to check if the target address is local (EADDRINUSE or * similar) and already bound, and set the LOCAL flag in that case. @@ -1685,7 +1679,7 @@ static void tcp_conn_from_tap(struct ctx *c, sa_family_t af, * * So, if bind() succeeds, close the socket, get a new one, and proceed. */ - if (bind(s, sa, sl)) { + if (bind(s, &sa.sa, sl)) { if (errno != EADDRNOTAVAIL && errno != EACCES) conn_flag(c, conn, LOCAL); } else { @@ -1695,7 +1689,7 @@ static void tcp_conn_from_tap(struct ctx *c, sa_family_t af, goto cancel; } - if (af == AF_INET6 && IN6_IS_ADDR_LINKLOCAL(&addr6.sin6_addr)) { + if (inany_is_linklocal6(&tgt->eaddr)) { struct sockaddr_in6 addr6_ll = { .sin6_family = AF_INET6, .sin6_addr = c->ip6.addr_ll, @@ -1703,6 +1697,8 @@ static void tcp_conn_from_tap(struct ctx *c, sa_family_t af, }; if (bind(s, (struct sockaddr *)&addr6_ll, sizeof(addr6_ll))) goto cancel; + } else if (!inany_is_loopback(&tgt->eaddr)) { + tcp_bind_outbound(c, s, af); } conn->sock = s; @@ -1738,12 +1734,7 @@ static void tcp_conn_from_tap(struct ctx *c, sa_family_t af, tcp_hash_insert(c, conn); - if ((af == AF_INET && !IN4_IS_ADDR_LOOPBACK(&addr4.sin_addr)) || - (af == AF_INET6 && !IN6_IS_ADDR_LOOPBACK(&addr6.sin6_addr) && - !IN6_IS_ADDR_LINKLOCAL(&addr6.sin6_addr))) - tcp_bind_outbound(c, s, af); - - if (connect(s, sa, sl)) { + if (connect(s, &sa.sa, sl)) { if (errno != EINPROGRESS) { tcp_rst(c, conn); goto cancel; @@ -2241,9 +2232,25 @@ static void tcp_tap_conn_from_sock(struct ctx *c, in_port_t dstport, const union sockaddr_inany *sa, const struct timespec *now) { + union inany_addr saddr, daddr; /* FIXME: avoid bulky temporaries */ struct tcp_tap_conn *conn; + in_port_t srcport; + + inany_from_sockaddr(&saddr, &srcport, sa); + tcp_snat_inbound(c, &saddr); - flow_target(flow, PIF_TAP); + if (inany_v4(&saddr)) { + daddr = inany_from_v4(c->ip4.addr_seen); + } else { + if (inany_is_linklocal6(&saddr)) + daddr.a6 = c->ip6.addr_ll_seen; + else + daddr.a6 = c->ip6.addr_seen; + } + dstport += c->tcp.fwd_in.delta[dstport]; + + flow_target_af(flow, PIF_TAP, AF_INET6, + &saddr, srcport, &daddr, dstport); conn = FLOW_SET_TYPE(flow, FLOW_TCP, tcp); conn->sock = s; @@ -2251,10 +2258,9 @@ static void tcp_tap_conn_from_sock(struct ctx *c, in_port_t dstport, conn->ws_to_tap = conn->ws_from_tap = 0; conn_event(c, conn, SOCK_ACCEPTED); - inany_from_sockaddr(&conn->faddr, &conn->fport, sa); - conn->eport = dstport + c->tcp.fwd_in.delta[dstport]; - - tcp_snat_inbound(c, &conn->faddr); + conn->faddr = saddr; + conn->fport = srcport; + conn->eport = dstport; tcp_seq_init(c, conn, now); tcp_hash_insert(c, conn); diff --git a/tcp_splice.c b/tcp_splice.c index f2d4fc60..83fc7ba4 100644 --- a/tcp_splice.c +++ b/tcp_splice.c @@ -320,31 +320,20 @@ static int tcp_splice_connect_finish(const struct ctx *c, * tcp_splice_connect() - Create and connect socket for new spliced connection * @c: Execution context * @conn: Connection pointer - * @af: Address family - * @pif: pif on which to create socket - * @port: Destination port, host order * * Return: 0 for connect() succeeded or in progress, negative value on error */ -static int tcp_splice_connect(const struct ctx *c, struct tcp_splice_conn *conn, - sa_family_t af, uint8_t pif, in_port_t port) +static int tcp_splice_connect(const struct ctx *c, struct tcp_splice_conn *conn) { - struct sockaddr_in6 addr6 = { - .sin6_family = AF_INET6, - .sin6_port = htons(port), - .sin6_addr = IN6ADDR_LOOPBACK_INIT, - }; - struct sockaddr_in addr4 = { - .sin_family = AF_INET, - .sin_port = htons(port), - .sin_addr = IN4ADDR_LOOPBACK_INIT, - }; - const struct sockaddr *sa; + const struct flowside *tgt = &conn->f.side[TGTSIDE]; + sa_family_t af = inany_v4(&tgt->eaddr) ? AF_INET : AF_INET6; + uint8_t tgtpif = conn->f.pif[TGTSIDE]; + union sockaddr_inany sa; socklen_t sl; - if (pif == PIF_HOST) + if (tgtpif == PIF_HOST) conn->s[1] = tcp_conn_sock(c, af); - else if (pif == PIF_SPLICE) + else if (tgtpif == PIF_SPLICE) conn->s[1] = tcp_conn_sock_ns(c, af); else ASSERT(0); @@ -358,15 +347,9 @@ static int tcp_splice_connect(const struct ctx *c, struct tcp_splice_conn *conn, conn->s[1]); } - if (CONN_V6(conn)) { - sa = (struct sockaddr *)&addr6; - sl = sizeof(addr6); - } else { - sa = (struct sockaddr *)&addr4; - sl = sizeof(addr4); - } + pif_sockaddr(c, &sa, &sl, tgtpif, &tgt->eaddr, tgt->eport); - if (connect(conn->s[1], sa, sl)) { + if (connect(conn->s[1], &sa.sa, sl)) { if (errno != EINPROGRESS) { flow_trace(conn, "Couldn't connect socket for splice: %s", strerror(errno)); @@ -471,7 +454,13 @@ bool tcp_splice_conn_from_sock(const struct ctx *c, return false; } - flow_target(flow, tgtpif); + /* FIXME: Record outbound source address when known */ + if (af == AF_INET) + flow_target_af(flow, tgtpif, AF_INET, + NULL, 0, &in4addr_loopback, dstport); + else + flow_target_af(flow, tgtpif, AF_INET6, + NULL, 0, &in6addr_loopback, dstport); conn = FLOW_SET_TYPE(flow, FLOW_TCP_SPLICE, tcp_splice); conn->flags = af == AF_INET ? 0 : SPLICE_V6; @@ -483,7 +472,7 @@ bool tcp_splice_conn_from_sock(const struct ctx *c, if (setsockopt(s0, SOL_TCP, TCP_QUICKACK, &((int){ 1 }), sizeof(int))) flow_trace(conn, "failed to set TCP_QUICKACK on %i", s0); - if (tcp_splice_connect(c, conn, af, tgtpif, dstport)) + if (tcp_splice_connect(c, conn)) conn_flag(c, conn, CLOSING); FLOW_ACTIVATE(conn); -- 2.45.2

Currently we always deliver inbound TCP packets to the guest's most recent observed IP address. This has the odd side effect that if the guest changes its IP address with active TCP connections we might deliver packets from old connections to the new address. That won't work; it will probably result in an RST from the guest. Worse, if the guest added a new address but also retains the old one, then we could break those old connections by redirecting them to the new address. Now that we maintain flowside information, we have a record of the correct guest side address and can just use it. Signed-off-by: David Gibson --- tcp.c | 41 +++++++++++++---------------------------- tcp_buf.c | 6 +++--- tcp_internal.h | 3 +-- 3 files changed, 17 insertions(+), 33 deletions(-) diff --git a/tcp.c b/tcp.c index 727bbd93..b03028ad 100644 --- a/tcp.c +++ b/tcp.c @@ -1021,7 +1021,6 @@ static void tcp_fill_header(struct tcphdr *th, /** * tcp_fill_headers4() - Fill 802.3, IPv4, TCP headers in pre-cooked buffers - * @c: Execution context * @conn: Connection pointer * @taph: tap backend specific header * @iph: Pointer to IPv4 header @@ -1032,27 +1031,26 @@ static void tcp_fill_header(struct tcphdr *th, * * Return: The IPv4 payload length, host order */ -static size_t tcp_fill_headers4(const struct ctx *c, - const struct tcp_tap_conn *conn, +static size_t tcp_fill_headers4(const struct tcp_tap_conn *conn, struct tap_hdr *taph, struct iphdr *iph, struct tcphdr *th, size_t dlen, const uint16_t *check, uint32_t seq) { const struct flowside *tapside = TAPFLOW(conn); - const struct in_addr *a4 = inany_v4(&tapside->faddr); + const struct in_addr *src4 = inany_v4(&tapside->faddr); + const struct in_addr *dst4 = inany_v4(&tapside->eaddr); size_t l4len = dlen + sizeof(*th); size_t l3len = l4len + sizeof(*iph); - ASSERT(a4); + ASSERT(src4 && dst4); iph->tot_len = htons(l3len); - iph->saddr = a4->s_addr; - iph->daddr = c->ip4.addr_seen.s_addr; + iph->saddr = src4->s_addr; + iph->daddr = dst4->s_addr; iph->check = check ? *check : - csum_ip4_header(l3len, IPPROTO_TCP, - *a4, c->ip4.addr_seen); + csum_ip4_header(l3len, IPPROTO_TCP, *src4, *dst4); tcp_fill_header(th, conn, seq); @@ -1065,7 +1063,6 @@ static size_t tcp_fill_headers4(const struct ctx *c, /** * tcp_fill_headers6() - Fill 802.3, IPv6, TCP headers in pre-cooked buffers - * @c: Execution context * @conn: Connection pointer * @taph: tap backend specific header * @ip6h: Pointer to IPv6 header @@ -1076,8 +1073,7 @@ static size_t tcp_fill_headers4(const struct ctx *c, * * Return: The IPv6 payload length, host order */ -static size_t tcp_fill_headers6(const struct ctx *c, - const struct tcp_tap_conn *conn, +static size_t tcp_fill_headers6(const struct tcp_tap_conn *conn, struct tap_hdr *taph, struct ipv6hdr *ip6h, struct tcphdr *th, size_t dlen, uint32_t seq) @@ -1087,10 +1083,7 @@ static size_t tcp_fill_headers6(const struct ctx *c, ip6h->payload_len = htons(l4len); ip6h->saddr = tapside->faddr.a6; - if (IN6_IS_ADDR_LINKLOCAL(&ip6h->saddr)) - ip6h->daddr = c->ip6.addr_ll_seen; - else - ip6h->daddr = c->ip6.addr_seen; + ip6h->daddr = tapside->eaddr.a6; ip6h->hop_limit = 255; ip6h->version = 6; @@ -1111,7 +1104,6 @@ static size_t tcp_fill_headers6(const struct ctx *c, /** * tcp_l2_buf_fill_headers() - Fill 802.3, IP, TCP headers in pre-cooked buffers - * @c: Execution context * @conn: Connection pointer * @iov: Pointer to an array of iovec of TCP pre-cooked buffers * @dlen: TCP payload length @@ -1120,8 +1112,7 @@ static size_t tcp_fill_headers6(const struct ctx *c, * * Return: IP payload length, host order */ -size_t tcp_l2_buf_fill_headers(const struct ctx *c, - const struct tcp_tap_conn *conn, +size_t tcp_l2_buf_fill_headers(const struct tcp_tap_conn *conn, struct iovec *iov, size_t dlen, const uint16_t *check, uint32_t seq) { @@ -1129,13 +1120,13 @@ size_t tcp_l2_buf_fill_headers(const struct ctx *c, const struct in_addr *a4 = inany_v4(&tapside->faddr); if (a4) { - return tcp_fill_headers4(c, conn, iov[TCP_IOV_TAP].iov_base, + return tcp_fill_headers4(conn, iov[TCP_IOV_TAP].iov_base, iov[TCP_IOV_IP].iov_base, iov[TCP_IOV_PAYLOAD].iov_base, dlen, check, seq); } - return tcp_fill_headers6(c, conn, iov[TCP_IOV_TAP].iov_base, + return tcp_fill_headers6(conn, iov[TCP_IOV_TAP].iov_base, iov[TCP_IOV_IP].iov_base, iov[TCP_IOV_PAYLOAD].iov_base, dlen, seq); @@ -1430,17 +1421,11 @@ static void tcp_seq_init(const struct ctx *c, struct tcp_tap_conn *conn, { struct siphash_state state = SIPHASH_INIT(c->hash_secret); const struct flowside *tapside = TAPFLOW(conn); - union inany_addr aany; uint64_t hash; uint32_t ns; - if (CONN_V4(conn)) - inany_from_af(&aany, AF_INET, &c->ip4.addr); - else - inany_from_af(&aany, AF_INET6, &c->ip6.addr); - inany_siphash_feed(&state, &tapside->faddr); - inany_siphash_feed(&state, &aany); + inany_siphash_feed(&state, &tapside->eaddr); hash = siphash_final(&state, 36, (uint64_t)tapside->fport << 16 | tapside->eport); diff --git a/tcp_buf.c b/tcp_buf.c index ff9f7970..9878e4b1 100644 --- a/tcp_buf.c +++ b/tcp_buf.c @@ -316,7 +316,7 @@ int tcp_buf_send_flag(struct ctx *c, struct tcp_tap_conn *conn, int flags) return ret; } - l4len = tcp_l2_buf_fill_headers(c, conn, iov, optlen, NULL, seq); + l4len = tcp_l2_buf_fill_headers(conn, iov, optlen, NULL, seq); iov[TCP_IOV_PAYLOAD].iov_len = l4len; if (flags & DUP_ACK) { @@ -373,7 +373,7 @@ static void tcp_data_to_tap(const struct ctx *c, struct tcp_tap_conn *conn, tcp4_frame_conns[tcp4_payload_used] = conn; iov = tcp4_l2_iov[tcp4_payload_used++]; - l4len = tcp_l2_buf_fill_headers(c, conn, iov, dlen, check, seq); + l4len = tcp_l2_buf_fill_headers(conn, iov, dlen, check, seq); iov[TCP_IOV_PAYLOAD].iov_len = l4len; if (tcp4_payload_used > TCP_FRAMES_MEM - 1) tcp_payload_flush(c); @@ -381,7 +381,7 @@ static void tcp_data_to_tap(const struct ctx *c, struct tcp_tap_conn *conn, tcp6_frame_conns[tcp6_payload_used] = conn; iov = tcp6_l2_iov[tcp6_payload_used++]; - l4len = tcp_l2_buf_fill_headers(c, conn, iov, dlen, NULL, seq); + l4len = tcp_l2_buf_fill_headers(conn, iov, dlen, NULL, seq); iov[TCP_IOV_PAYLOAD].iov_len = l4len; if (tcp6_payload_used > TCP_FRAMES_MEM - 1) tcp_payload_flush(c); diff --git a/tcp_internal.h b/tcp_internal.h index 4f61e5c3..ac6d4b21 100644 --- a/tcp_internal.h +++ b/tcp_internal.h @@ -88,8 +88,7 @@ void tcp_rst_do(struct ctx *c, struct tcp_tap_conn *conn); tcp_rst_do(c, conn); \ } while (0) -size_t tcp_l2_buf_fill_headers(const struct ctx *c, - const struct tcp_tap_conn *conn, +size_t tcp_l2_buf_fill_headers(const struct tcp_tap_conn *conn, struct iovec *iov, size_t dlen, const uint16_t *check, uint32_t seq); int tcp_update_seqack_wnd(const struct ctx *c, struct tcp_tap_conn *conn, -- 2.45.2

Now that we store all our endpoints in the flowside structure, use some inany helpers to make validation of those endpoints simpler. Signed-off-by: David Gibson --- inany.h | 1 - tcp.c | 72 +++++++++++++++------------------------------------------ 2 files changed, 18 insertions(+), 55 deletions(-) diff --git a/inany.h b/inany.h index 8eaf5335..d2893cec 100644 --- a/inany.h +++ b/inany.h @@ -211,7 +211,6 @@ static inline bool inany_is_multicast(const union inany_addr *a) * * Return: true if @a is specified and a unicast address */ -/* cppcheck-suppress unusedFunction */ static inline bool inany_is_unicast(const union inany_addr *a) { return !inany_is_unspecified(a) && !inany_is_multicast(a); diff --git a/tcp.c b/tcp.c index f92414fb..45ea9a71 100644 --- a/tcp.c +++ b/tcp.c @@ -1642,38 +1642,14 @@ static void tcp_conn_from_tap(struct ctx *c, sa_family_t af, &dstaddr, dstport); conn = FLOW_SET_TYPE(flow, FLOW_TCP, tcp); - if (af == AF_INET) { - if (IN4_IS_ADDR_UNSPECIFIED(saddr) || - IN4_IS_ADDR_BROADCAST(saddr) || - IN4_IS_ADDR_MULTICAST(saddr) || srcport == 0 || - IN4_IS_ADDR_UNSPECIFIED(daddr) || - IN4_IS_ADDR_BROADCAST(daddr) || - IN4_IS_ADDR_MULTICAST(daddr) || dstport == 0) { - char sstr[INET_ADDRSTRLEN], dstr[INET_ADDRSTRLEN]; - - debug("Invalid endpoint in TCP SYN: %s:%hu -> %s:%hu", - inet_ntop(AF_INET, saddr, sstr, sizeof(sstr)), - srcport, - inet_ntop(AF_INET, daddr, dstr, sizeof(dstr)), - dstport); - goto cancel; - } - } else if (af == AF_INET6) { - if (IN6_IS_ADDR_UNSPECIFIED(saddr) || - IN6_IS_ADDR_MULTICAST(saddr) || srcport == 0 || - IN6_IS_ADDR_UNSPECIFIED(daddr) || - IN6_IS_ADDR_MULTICAST(daddr) || dstport == 0) { - char sstr[INET6_ADDRSTRLEN], dstr[INET6_ADDRSTRLEN]; - - debug("Invalid endpoint in TCP SYN: %s:%hu -> %s:%hu", - inet_ntop(AF_INET6, saddr, sstr, sizeof(sstr)), - srcport, - inet_ntop(AF_INET6, daddr, dstr, sizeof(dstr)), - dstport); - goto cancel; - } - } else { - ASSERT(0); + if (!inany_is_unicast(&ini->eaddr) || ini->eport == 0 || + !inany_is_unicast(&ini->faddr) || ini->fport == 0) { + char sstr[INANY_ADDRSTRLEN], dstr[INANY_ADDRSTRLEN]; + + debug("Invalid endpoint in TCP SYN: %s:%hu -> %s:%hu", + inany_ntop(&ini->eaddr, sstr, sizeof(sstr)), ini->eport, + inany_ntop(&ini->faddr, dstr, sizeof(dstr)), ini->fport); + goto cancel; } if ((s = tcp_conn_sock(c, af)) < 0) @@ -2279,7 +2255,7 @@ static void tcp_tap_conn_from_sock(struct ctx *c, in_port_t dstport, void tcp_listen_handler(struct ctx *c, union epoll_ref ref, const struct timespec *now) { - char sastr[SOCKADDR_STRLEN]; + const struct flowside *ini; union sockaddr_inany sa; socklen_t sl = sizeof(sa); union flow *flow; @@ -2294,23 +2270,15 @@ void tcp_listen_handler(struct ctx *c, union epoll_ref ref, /* FIXME: When listening port has a specific bound address, record that * as the forwarding address */ - flow_initiate_sa(flow, ref.tcp_listen.pif, &sa, ref.tcp_listen.port); - - if (sa.sa_family == AF_INET) { - const struct in_addr *addr = &sa.sa4.sin_addr; - in_port_t port = sa.sa4.sin_port; - - if (IN4_IS_ADDR_UNSPECIFIED(addr) || - IN4_IS_ADDR_BROADCAST(addr) || - IN4_IS_ADDR_MULTICAST(addr) || port == 0) - goto bad_endpoint; - } else if (sa.sa_family == AF_INET6) { - const struct in6_addr *addr = &sa.sa6.sin6_addr; - in_port_t port = sa.sa6.sin6_port; - - if (IN6_IS_ADDR_UNSPECIFIED(addr) || - IN6_IS_ADDR_MULTICAST(addr) || port == 0) - goto bad_endpoint; + ini = flow_initiate_sa(flow, ref.tcp_listen.pif, &sa, + ref.tcp_listen.port); + + if (!inany_is_unicast(&ini->eaddr) || ini->eport == 0) { + char sastr[SOCKADDR_STRLEN]; + + err("Invalid endpoint from TCP accept(): %s", + sockaddr_ntop(&sa, sastr, sizeof(sastr))); + goto cancel; } if (tcp_splice_conn_from_sock(c, ref.tcp_listen.pif, @@ -2320,10 +2288,6 @@ void tcp_listen_handler(struct ctx *c, union epoll_ref ref, tcp_tap_conn_from_sock(c, ref.tcp_listen.port, flow, s, &sa, now); return; -bad_endpoint: - err("Invalid endpoint from TCP accept(): %s", - sockaddr_ntop(&sa, sastr, sizeof(sastr))); - cancel: flow_alloc_cancel(flow); } -- 2.45.2

Currently we match TCP packets received on the tap connection to a TCP connection via a hash table based on the forwarding address and both ports. We hope in future to allow for multiple guest side addresses, or for multiple interfaces which means we may need to distinguish based on the endpoint address and pif as well. We also want a unified hash table to cover multiple protocols, not just TCP. Replace the TCP specific hash function with one suitable for general flows, or rather for one side of a general flow. This includes all the information from struct flowside, plus the pif and the L4 protocol number. Signed-off-by: David Gibson --- flow.c | 35 +++++++++++++++++++++++++++--- flow.h | 19 ++++++++++++++++ flow_table.h | 3 +++ tcp.c | 61 ++++++++++------------------------------------------ 4 files changed, 65 insertions(+), 53 deletions(-) diff --git a/flow.c b/flow.c index f064fad1..30d10e9d 100644 --- a/flow.c +++ b/flow.c @@ -116,9 +116,9 @@ static struct timespec flow_timer_run; * @faddr: Forwarding address (pointer to in_addr or in6_addr) * @fport: Forwarding port */ -static void flowside_from_af(struct flowside *fside, sa_family_t af, - const void *eaddr, in_port_t eport, - const void *faddr, in_port_t fport) +void flowside_from_af(struct flowside *fside, sa_family_t af, + const void *eaddr, in_port_t eport, + const void *faddr, in_port_t fport) { if (faddr) inany_from_af(&fside->faddr, af, faddr); @@ -401,6 +401,35 @@ void flow_alloc_cancel(union flow *flow) flow_new_entry = NULL; } +/** + * flow_hash() - Calculate hash value for one side of a flow + * @c: Execution context + * @proto: Protocol of this flow (IP L4 protocol number) + * @pif: pif of the side to hash + * @fside: Flowside (must not have unspecified parts) + * + * Return: hash value + */ +uint64_t flow_hash(const struct ctx *c, uint8_t proto, uint8_t pif, + const struct flowside *fside) +{ + struct siphash_state state = SIPHASH_INIT(c->hash_secret); + + /* For the hash table to work, we need complete endpoint information, + * and at least a forwarding port. + */ + ASSERT(pif != PIF_NONE && !inany_is_unspecified(&fside->eaddr) && + fside->eport != 0 && fside->fport != 0); + + inany_siphash_feed(&state, &fside->faddr); + inany_siphash_feed(&state, &fside->eaddr); + + return siphash_final(&state, 38, (uint64_t)proto << 40 | + (uint64_t)pif << 32 | + (uint64_t)fside->fport << 16 | + (uint64_t)fside->eport); +} + /** * flow_defer_handler() - Handler for per-flow deferred and timed tasks * @c: Execution context diff --git a/flow.h b/flow.h index 4c3762b9..0b1e5de2 100644 --- a/flow.h +++ b/flow.h @@ -149,6 +149,25 @@ struct flowside { in_port_t eport; }; +/** + * flowside_eq() - Check if two flowsides are equal + * @left, @right: Flowsides to compare + * + * Return: true if equal, false otherwise + */ +static inline bool flowside_eq(const struct flowside *left, + const struct flowside *right) +{ + return inany_equals(&left->eaddr, &right->eaddr) && + left->eport == right->eport && + inany_equals(&left->faddr, &right->faddr) && + left->fport == right->fport; +} + +void flowside_from_af(struct flowside *fside, sa_family_t af, + const void *eaddr, in_port_t eport, + const void *faddr, in_port_t fport); + /** * struct flow_common - Common fields for packet flows * @state: State of the flow table entry diff --git a/flow_table.h b/flow_table.h index 00dca4b2..9bfa1174 100644 --- a/flow_table.h +++ b/flow_table.h @@ -126,4 +126,7 @@ void flow_activate(struct flow_common *f); #define FLOW_ACTIVATE(flow_) \ (flow_activate(&(flow_)->f)) +uint64_t flow_hash(const struct ctx *c, uint8_t proto, uint8_t pif, + const struct flowside *fside); + #endif /* FLOW_TABLE_H */ diff --git a/tcp.c b/tcp.c index 45ea9a71..b1ad1014 100644 --- a/tcp.c +++ b/tcp.c @@ -376,7 +376,7 @@ static struct iovec tcp_iov [UIO_MAXIOV]; #define CONN(idx) (&(FLOW(idx)->tcp)) -/* Table for lookup from remote address, local port, remote port */ +/* Table for lookup from flowside information */ static flow_sidx_t tc_hash[TCP_HASH_TABLE_SIZE]; static_assert(ARRAY_SIZE(tc_hash) >= FLOW_MAX, @@ -814,46 +814,6 @@ static int tcp_opt_get(const char *opts, size_t len, uint8_t type_find, return -1; } -/** - * tcp_hash_match() - Check if a connection entry matches address and ports - * @conn: Connection entry to match against - * @faddr: Guest side forwarding address - * @eport: Guest side endpoint port - * @fport: Guest side forwarding port - * - * Return: 1 on match, 0 otherwise - */ -static int tcp_hash_match(const struct tcp_tap_conn *conn, - const union inany_addr *faddr, - in_port_t eport, in_port_t fport) -{ - const struct flowside *tapside = TAPFLOW(conn); - - if (inany_equals(&tapside->faddr, faddr) && - tapside->eport == eport && tapside->fport == fport) - return 1; - - return 0; -} - -/** - * tcp_hash() - Calculate hash value for connection given address and ports - * @c: Execution context - * @faddr: Guest side forwarding address - * @eport: Guest side endpoint port - * @fport: Guest side forwarding port - * - * Return: hash value, needs to be adjusted for table size - */ -static uint64_t tcp_hash(const struct ctx *c, const union inany_addr *faddr, - in_port_t eport, in_port_t fport) -{ - struct siphash_state state = SIPHASH_INIT(c->hash_secret); - - inany_siphash_feed(&state, faddr); - return siphash_final(&state, 20, (uint64_t)eport << 16 | fport); -} - /** * tcp_conn_hash() - Calculate hash bucket of an existing connection * @c: Execution context @@ -866,8 +826,7 @@ static uint64_t tcp_conn_hash(const struct ctx *c, { const struct flowside *tapside = TAPFLOW(conn); - return tcp_hash(c, &tapside->faddr, tapside->eport, - tapside->fport); + return flow_hash(c, IPPROTO_TCP, conn->f.pif[TAPSIDE(conn)], tapside); } /** @@ -941,25 +900,26 @@ static void tcp_hash_remove(const struct ctx *c, * tcp_hash_lookup() - Look up connection given remote address and ports * @c: Execution context * @af: Address family, AF_INET or AF_INET6 + * @eaddr: Guest side endpoint address (guest local address) * @faddr: Guest side forwarding address (guest remote address) * @eport: Guest side endpoint port (guest local port) * @fport: Guest side forwarding port (guest remote port) * * Return: connection pointer, if found, -ENOENT otherwise */ -static struct tcp_tap_conn *tcp_hash_lookup(const struct ctx *c, - sa_family_t af, const void *faddr, +static struct tcp_tap_conn *tcp_hash_lookup(const struct ctx *c, sa_family_t af, + const void *eaddr, const void *faddr, in_port_t eport, in_port_t fport) { - union inany_addr aany; + struct flowside fside; union flow *flow; unsigned b; - inany_from_af(&aany, af, faddr); + flowside_from_af(&fside, af, eaddr, eport, faddr, fport); - b = tcp_hash(c, &aany, eport, fport) % TCP_HASH_TABLE_SIZE; + b = flow_hash(c, IPPROTO_TCP, PIF_TAP, &fside) % TCP_HASH_TABLE_SIZE; while ((flow = flow_at_sidx(tc_hash[b])) && - !tcp_hash_match(&flow->tcp, &aany, eport, fport)) + !flowside_eq(&flow->f.side[TAPSIDE(flow)], &fside)) b = mod_sub(b, 1, TCP_HASH_TABLE_SIZE); return &flow->tcp; @@ -2047,7 +2007,8 @@ int tcp_tap_handler(struct ctx *c, uint8_t pif, sa_family_t af, optlen = MIN(optlen, ((1UL << 4) /* from doff width */ - 6) * 4UL); opts = packet_get(p, idx, sizeof(*th), optlen, NULL); - conn = tcp_hash_lookup(c, af, daddr, ntohs(th->source), ntohs(th->dest)); + conn = tcp_hash_lookup(c, af, saddr, daddr, + ntohs(th->source), ntohs(th->dest)); /* New connection from tap */ if (!conn) { -- 2.45.2

We generate TCP initial sequence numbers, when we need them, from a hash of the source and destination addresses and ports, plus a timestamp. Moments later, we generate another hash of the same information plus some more to insert the connection into the flow hash table. With some tweaks to the flow_hash_insert() interface and changing the order we can re-use that hash table hash for the initial sequence number, rather than calculating another one. It won't generate identical results, but that doesn't matter as long as the sequence numbers are well scattered. Signed-off-by: David Gibson --- flow.c | 30 ++++++++++++++++++++++++------ flow.h | 2 +- tcp.c | 33 +++++++++++---------------------- 3 files changed, 36 insertions(+), 29 deletions(-) diff --git a/flow.c b/flow.c index 21310531..6f09781a 100644 --- a/flow.c +++ b/flow.c @@ -455,16 +455,16 @@ static uint64_t flow_sidx_hash(const struct ctx *c, flow_sidx_t sidx) } /** - * flow_hash_probe() - Find hash bucket for a flow - * @c: Execution context + * flow_hash_probe_() - Find hash bucket for a flow, given hash + * @hash: Raw hash value for flow & side * @sidx: Flow and side to find bucket for * * Return: If @sidx is in the hash table, its current bucket, otherwise a * suitable free bucket for it. */ -static inline unsigned flow_hash_probe(const struct ctx *c, flow_sidx_t sidx) +static inline unsigned flow_hash_probe_(uint64_t hash, flow_sidx_t sidx) { - unsigned b = flow_sidx_hash(c, sidx) % FLOW_HASH_SIZE; + unsigned b = hash % FLOW_HASH_SIZE; /* Linear probing */ while (flow_sidx_valid(flow_hashtab[b]) && @@ -474,18 +474,36 @@ static inline unsigned flow_hash_probe(const struct ctx *c, flow_sidx_t sidx) return b; } +/** + * flow_hash_probe() - Find hash bucket for a flow + * @c: Execution context + * @sidx: Flow and side to find bucket for + * + * Return: If @sidx is in the hash table, its current bucket, otherwise a + * suitable free bucket for it. + */ +static inline unsigned flow_hash_probe(const struct ctx *c, flow_sidx_t sidx) +{ + return flow_hash_probe_(flow_sidx_hash(c, sidx), sidx); +} + /** * flow_hash_insert() - Insert side of a flow into into hash table * @c: Execution context * @sidx: Flow & side index + * + * Return: raw (un-modded) hash value of side of flow */ -void flow_hash_insert(const struct ctx *c, flow_sidx_t sidx) +uint64_t flow_hash_insert(const struct ctx *c, flow_sidx_t sidx) { - unsigned b = flow_hash_probe(c, sidx); + uint64_t hash = flow_sidx_hash(c, sidx); + unsigned b = flow_hash_probe_(hash, sidx); flow_hashtab[b] = sidx; flow_dbg(flow_at_sidx(sidx), "Side %u hash table insert: bucket: %u", sidx.side, b); + + return hash; } /** diff --git a/flow.h b/flow.h index c0bf0010..c3a15ca6 100644 --- a/flow.h +++ b/flow.h @@ -229,7 +229,7 @@ static inline bool flow_sidx_eq(flow_sidx_t a, flow_sidx_t b) return (a.flow == b.flow) && (a.side == b.side); } -void flow_hash_insert(const struct ctx *c, flow_sidx_t sidx); +uint64_t flow_hash_insert(const struct ctx *c, flow_sidx_t sidx); void flow_hash_remove(const struct ctx *c, flow_sidx_t sidx); flow_sidx_t flow_lookup_af(const struct ctx *c, uint8_t proto, uint8_t pif, sa_family_t af, diff --git a/tcp.c b/tcp.c index 8cc91add..4d3ffe57 100644 --- a/tcp.c +++ b/tcp.c @@ -1248,28 +1248,16 @@ static void tcp_tap_window_update(struct tcp_tap_conn *conn, unsigned wnd) } /** - * tcp_seq_init() - Calculate initial sequence number according to RFC 6528 - * @c: Execution context - * @conn: TCP connection, with faddr, fport and eport populated + * tcp_init_seq() - Calculate initial sequence number according to RFC 6528 + * @hash: Hash of connection details * @now: Current timestamp */ -static void tcp_seq_init(const struct ctx *c, struct tcp_tap_conn *conn, - const struct timespec *now) +static uint32_t tcp_init_seq(uint64_t hash, const struct timespec *now) { - struct siphash_state state = SIPHASH_INIT(c->hash_secret); - const struct flowside *tapside = TAPFLOW(conn); - uint64_t hash; - uint32_t ns; - - inany_siphash_feed(&state, &tapside->faddr); - inany_siphash_feed(&state, &tapside->eaddr); - hash = siphash_final(&state, 36, - (uint64_t)tapside->fport << 16 | tapside->eport); - /* 32ns ticks, overflows 32 bits every 137s */ - ns = (now->tv_sec * 1000000000 + now->tv_nsec) >> 5; + uint32_t ns = (now->tv_sec * 1000000000 + now->tv_nsec) >> 5; - conn->seq_to_tap = ((uint32_t)(hash >> 32) ^ (uint32_t)hash) + ns; + return ((uint32_t)(hash >> 32) ^ (uint32_t)hash) + ns; } /** @@ -1441,6 +1429,7 @@ static void tcp_conn_from_tap(struct ctx *c, sa_family_t af, union sockaddr_inany sa; union flow *flow; int s = -1, mss; + uint64_t hash; socklen_t sl; if (!(flow = flow_alloc())) @@ -1537,11 +1526,10 @@ static void tcp_conn_from_tap(struct ctx *c, sa_family_t af, conn->seq_from_tap = conn->seq_init_from_tap + 1; conn->seq_ack_to_tap = conn->seq_from_tap; - tcp_seq_init(c, conn, now); + hash = flow_hash_insert(c, TAP_SIDX(conn)); + conn->seq_to_tap = tcp_init_seq(hash, now); conn->seq_ack_from_tap = conn->seq_to_tap; - flow_hash_insert(c, TAP_SIDX(conn)); - tcp_bind_outbound(c, conn, s); if (connect(s, &sa.sa, sl)) { @@ -2053,6 +2041,7 @@ static void tcp_tap_conn_from_sock(struct ctx *c, in_port_t dstport, union inany_addr saddr, daddr; /* FIXME: avoid bulky temporaries */ struct tcp_tap_conn *conn; in_port_t srcport; + uint64_t hash; inany_from_sockaddr(&saddr, &srcport, sa); tcp_snat_inbound(c, &saddr); @@ -2076,8 +2065,8 @@ static void tcp_tap_conn_from_sock(struct ctx *c, in_port_t dstport, conn->ws_to_tap = conn->ws_from_tap = 0; conn_event(c, conn, SOCK_ACCEPTED); - tcp_seq_init(c, conn, now); - flow_hash_insert(c, TAP_SIDX(conn)); + hash = flow_hash_insert(c, TAP_SIDX(conn)); + conn->seq_to_tap = tcp_init_seq(hash, now); conn->seq_ack_from_tap = conn->seq_to_tap; -- 2.45.2

icmp_sock_handler() obtains the guest address from it's most recently observed IP. However, this can now be obtained from the common flowside information. icmp_tap_handler() builds its socket address for sendto() directly from the destination address supplied by the incoming tap packet. This can instead be generated from the flow. Using the flowsides as the common source of truth here prepares us for allowing more flexible NAT and forwarding by properly initialising that flowside information. Signed-off-by: David Gibson --- icmp.c | 27 +++++++++++++++++---------- tap.c | 11 ----------- tap.h | 1 - 3 files changed, 17 insertions(+), 22 deletions(-) diff --git a/icmp.c b/icmp.c index 00142422..56203708 100644 --- a/icmp.c +++ b/icmp.c @@ -111,11 +111,18 @@ void icmp_sock_handler(const struct ctx *c, union epoll_ref ref) flow_dbg(pingf, "echo reply to tap, ID: %"PRIu16", seq: %"PRIu16, ini->eport, seq); - if (pingf->f.type == FLOW_PING4) - tap_icmp4_send(c, sr.sa4.sin_addr, tap_ip4_daddr(c), buf, n); - else if (pingf->f.type == FLOW_PING6) - tap_icmp6_send(c, &sr.sa6.sin6_addr, - tap_ip6_daddr(c, &sr.sa6.sin6_addr), buf, n); + if (pingf->f.type == FLOW_PING4) { + const struct in_addr *saddr = inany_v4(&ini->faddr); + const struct in_addr *daddr = inany_v4(&ini->eaddr); + + ASSERT(saddr && daddr); /* Must have IPv4 addresses */ + tap_icmp4_send(c, *saddr, *daddr, buf, n); + } else if (pingf->f.type == FLOW_PING6) { + const struct in6_addr *saddr = &ini->faddr.a6; + const struct in6_addr *daddr = &ini->eaddr.a6; + + tap_icmp6_send(c, saddr, daddr, buf, n); + } return; unexpected: @@ -225,11 +232,12 @@ int icmp_tap_handler(const struct ctx *c, uint8_t pif, sa_family_t af, const void *saddr, const void *daddr, const struct pool *p, const struct timespec *now) { - union sockaddr_inany sa = { .sa_family = af }; - const socklen_t sl = af == AF_INET ? sizeof(sa.sa4) : sizeof(sa.sa6); struct icmp_ping_flow *pingf, **id_sock; + const struct flowside *tgt; + union sockaddr_inany sa; size_t dlen, l4len; uint16_t id, seq; + socklen_t sl; void *pkt; (void)saddr; @@ -250,7 +258,6 @@ int icmp_tap_handler(const struct ctx *c, uint8_t pif, sa_family_t af, id = ntohs(ih->un.echo.id); id_sock = &icmp_id_map[V4][id]; seq = ntohs(ih->un.echo.sequence); - sa.sa4.sin_addr = *(struct in_addr *)daddr; } else if (af == AF_INET6) { const struct icmp6hdr *ih; @@ -266,8 +273,6 @@ int icmp_tap_handler(const struct ctx *c, uint8_t pif, sa_family_t af, id = ntohs(ih->icmp6_identifier); id_sock = &icmp_id_map[V6][id]; seq = ntohs(ih->icmp6_sequence); - sa.sa6.sin6_addr = *(struct in6_addr *)daddr; - sa.sa6.sin6_scope_id = c->ifi6; } else { ASSERT(0); } @@ -276,8 +281,10 @@ int icmp_tap_handler(const struct ctx *c, uint8_t pif, sa_family_t af, if (!(pingf = icmp_ping_new(c, id_sock, af, id, saddr, daddr))) return 1; + tgt = &pingf->f.side[TGTSIDE]; pingf->ts = now->tv_sec; + pif_sockaddr(c, &sa, &sl, PIF_HOST, &tgt->eaddr, 0); if (sendto(pingf->sock, pkt, l4len, MSG_NOSIGNAL, &sa.sa, sl) < 0) { flow_dbg(pingf, "failed to relay request to socket: %s", strerror(errno)); diff --git a/tap.c b/tap.c index ec994a2e..32a7b09c 100644 --- a/tap.c +++ b/tap.c @@ -90,17 +90,6 @@ void tap_send_single(const struct ctx *c, const void *data, size_t l2len) tap_send_frames(c, iov, iovcnt, 1); } -/** - * tap_ip4_daddr() - Normal IPv4 destination address for inbound packets - * @c: Execution context - * - * Return: IPv4 address - */ -struct in_addr tap_ip4_daddr(const struct ctx *c) -{ - return c->ip4.addr_seen; -} - /** * tap_ip6_daddr() - Normal IPv6 destination address for inbound packets * @c: Execution context diff --git a/tap.h b/tap.h index d496bd0e..ec9e2ace 100644 --- a/tap.h +++ b/tap.h @@ -43,7 +43,6 @@ static inline void tap_hdr_update(struct tap_hdr *thdr, size_t l2len) thdr->vnet_len = htonl(l2len); } -struct in_addr tap_ip4_daddr(const struct ctx *c); void tap_udp4_send(const struct ctx *c, struct in_addr src, in_port_t sport, struct in_addr dst, in_port_t dport, const void *in, size_t dlen); -- 2.45.2

With previous reworks the icmp_id_map data structure is now maintained, but never used for anything. Eliminate it. Signed-off-by: David Gibson --- icmp.c | 19 ++----------------- 1 file changed, 2 insertions(+), 17 deletions(-) diff --git a/icmp.c b/icmp.c index b78712a1..e2e697e7 100644 --- a/icmp.c +++ b/icmp.c @@ -47,9 +47,6 @@ #define PINGF(idx) (&(FLOW(idx)->ping)) -/* Indexed by ICMP echo identifier */ -static struct icmp_ping_flow *icmp_id_map[IP_VERSIONS][ICMP_NUM_IDS]; - /** * icmp_sock_handler() - Handle new data from ICMP or ICMPv6 socket * @c: Execution context @@ -137,22 +134,14 @@ unexpected: static void icmp_ping_close(const struct ctx *c, const struct icmp_ping_flow *pingf) { - uint16_t id = pingf->f.side[INISIDE].eport; - epoll_ctl(c->epollfd, EPOLL_CTL_DEL, pingf->sock, NULL); close(pingf->sock); flow_hash_remove(c, FLOW_SIDX(pingf, INISIDE)); - - if (pingf->f.type == FLOW_PING4) - icmp_id_map[V4][id] = NULL; - else - icmp_id_map[V6][id] = NULL; } /** * icmp_ping_new() - Prepare a new ping socket for a new id * @c: Execution context - * @id_sock: Pointer to ping flow entry slot in icmp_id_map[] to update * @af: Address family, AF_INET or AF_INET6 * @id: ICMP id for the new socket * @saddr: Source address @@ -161,7 +150,6 @@ static void icmp_ping_close(const struct ctx *c, * Return: Newly opened ping flow, or NULL on failure */ static struct icmp_ping_flow *icmp_ping_new(const struct ctx *c, - struct icmp_ping_flow **id_sock, sa_family_t af, uint16_t id, const void *saddr, const void *daddr) { @@ -207,7 +195,6 @@ static struct icmp_ping_flow *icmp_ping_new(const struct ctx *c, flow_dbg(pingf, "new socket %i for echo ID %"PRIu16, pingf->sock, id); flow_hash_insert(c, FLOW_SIDX(pingf, INISIDE)); - *id_sock = pingf; FLOW_ACTIVATE(pingf); @@ -234,7 +221,7 @@ int icmp_tap_handler(const struct ctx *c, uint8_t pif, sa_family_t af, const void *saddr, const void *daddr, const struct pool *p, const struct timespec *now) { - struct icmp_ping_flow *pingf, **id_sock; + struct icmp_ping_flow *pingf; const struct flowside *tgt; union sockaddr_inany sa; size_t dlen, l4len; @@ -261,7 +248,6 @@ int icmp_tap_handler(const struct ctx *c, uint8_t pif, sa_family_t af, proto = IPPROTO_ICMP; id = ntohs(ih->un.echo.id); - id_sock = &icmp_id_map[V4][id]; seq = ntohs(ih->un.echo.sequence); } else if (af == AF_INET6) { const struct icmp6hdr *ih; @@ -277,7 +263,6 @@ int icmp_tap_handler(const struct ctx *c, uint8_t pif, sa_family_t af, proto = IPPROTO_ICMPV6; id = ntohs(ih->icmp6_identifier); - id_sock = &icmp_id_map[V6][id]; seq = ntohs(ih->icmp6_sequence); } else { ASSERT(0); @@ -288,7 +273,7 @@ int icmp_tap_handler(const struct ctx *c, uint8_t pif, sa_family_t af, if (flow) pingf = &flow->ping; - else if (!(pingf = icmp_ping_new(c, id_sock, af, id, saddr, daddr))) + else if (!(pingf = icmp_ping_new(c, af, id, saddr, daddr))) return 1; tgt = &pingf->f.side[TGTSIDE]; -- 2.45.2

Currently the code to translate host side addresses and ports to guest side addresses and ports, and vice versa, is scattered across the TCP code. This includes both port redirection as controlled by the -t and -T options, and our special case NAT controlled by the --no-map-gw option. Gather this logic into fwd_nat_from_*() functions for each input interface in fwd.c which take protocol and address information for the initiating side and generates the pif and address information for the forwarded side. This performs any NAT or port forwarding needed. We create a flow_target() helper which applies those forwarding functions as needed to automatically move a flow from INI to TGT state. Signed-off-by: David Gibson --- flow.c | 53 +++++++++++++++++++ flow_table.h | 2 + fwd.c | 146 +++++++++++++++++++++++++++++++++++++++++++++++++++ fwd.h | 9 ++++ tcp.c | 103 ++++++++++-------------------------- tcp_splice.c | 64 ++-------------------- tcp_splice.h | 5 +- 7 files changed, 243 insertions(+), 139 deletions(-) diff --git a/flow.c b/flow.c index cf952a32..c638fc18 100644 --- a/flow.c +++ b/flow.c @@ -399,6 +399,59 @@ const struct flowside *flow_target_af(union flow *flow, uint8_t pif, return tgt; } + +/** + * flow_target() - Determine where flow should forward to, and move to TGT + * @c: Execution context + * @flow: Flow to forward + * @proto: Protocol + * + * Return: pointer to the target flowside information + */ +const struct flowside *flow_target(const struct ctx *c, union flow *flow, + uint8_t proto) +{ + char estr[INANY_ADDRSTRLEN], fstr[INANY_ADDRSTRLEN]; + struct flow_common *f = &flow->f; + const struct flowside *ini = &f->side[INISIDE]; + struct flowside *tgt = &f->side[TGTSIDE]; + uint8_t tgtpif = PIF_NONE; + + ASSERT(flow_new_entry == flow && f->state == FLOW_STATE_INI); + ASSERT(f->type == FLOW_TYPE_NONE); + ASSERT(f->pif[INISIDE] != PIF_NONE && f->pif[TGTSIDE] == PIF_NONE); + ASSERT(flow->f.state == FLOW_STATE_INI); + + switch (f->pif[INISIDE]) { + case PIF_TAP: + tgtpif = fwd_nat_from_tap(c, proto, ini, tgt); + break; + + case PIF_SPLICE: + tgtpif = fwd_nat_from_splice(c, proto, ini, tgt); + break; + + case PIF_HOST: + tgtpif = fwd_nat_from_host(c, proto, ini, tgt); + break; + + default: + flow_err(flow, "No rules to forward %s [%s]:%hu -> [%s]:%hu", + pif_name(f->pif[INISIDE]), + inany_ntop(&ini->eaddr, estr, sizeof(estr)), + ini->eport, + inany_ntop(&ini->faddr, fstr, sizeof(fstr)), + ini->fport); + } + + if (tgtpif == PIF_NONE) + return NULL; + + f->pif[TGTSIDE] = tgtpif; + flow_set_state(f, FLOW_STATE_TGT); + return tgt; +} + /** * flow_set_type() - Set type and move to TYPED * @flow: Flow to change state diff --git a/flow_table.h b/flow_table.h index 00dca4b2..457f27b1 100644 --- a/flow_table.h +++ b/flow_table.h @@ -118,6 +118,8 @@ const struct flowside *flow_target_af(union flow *flow, uint8_t pif, sa_family_t af, const void *saddr, in_port_t sport, const void *daddr, in_port_t dport); +const struct flowside *flow_target(const struct ctx *c, union flow *flow, + uint8_t proto); union flow *flow_set_type(union flow *flow, enum flow_type type); #define FLOW_SET_TYPE(flow_, t_, var_) (&flow_set_type((flow_), (t_))->var_) diff --git a/fwd.c b/fwd.c index d3f17988..5731a536 100644 --- a/fwd.c +++ b/fwd.c @@ -25,6 +25,7 @@ #include "fwd.h" #include "passt.h" #include "lineread.h" +#include "flow_table.h" /* See enum in kernel's include/net/tcp_states.h */ #define UDP_LISTEN 0x07 @@ -154,3 +155,148 @@ void fwd_scan_ports_init(struct ctx *c) &c->tcp.fwd_out, &c->tcp.fwd_in); } } + +/** + * fwd_nat_from_tap() - Determine to forward a flow from the tap interface + * @c: Execution context + * @proto: Protocol (IP L4 protocol number) + * @ini: Flow address information of the initiating side + * @tgt: Flow address information on the target side (updated) + * + * Return: pif of the target interface to forward the flow to, PIF_NONE if the + * flow cannot or should not be forwarded at all. + */ +uint8_t fwd_nat_from_tap(const struct ctx *c, uint8_t proto, + const struct flowside *ini, struct flowside *tgt) +{ + (void)proto; + + tgt->eaddr = ini->faddr; + tgt->eport = ini->fport; + + if (!c->no_map_gw) { + if (inany_equals4(&tgt->eaddr, &c->ip4.gw)) + tgt->eaddr = inany_loopback4; + else if (inany_equals6(&tgt->eaddr, &c->ip6.gw)) + tgt->eaddr = inany_loopback6; + } + + /* The relevant addr_out controls the host side source address. This + * may be unspecified, which allows the kernel to pick an address. + */ + if (inany_v4(&tgt->eaddr)) + tgt->faddr = inany_from_v4(c->ip4.addr_out); + else + tgt->faddr.a6 = c->ip6.addr_out; + + /* Let the kernel pick a host side source port */ + tgt->fport = 0; + + return PIF_HOST; +} + +/** + * fwd_nat_from_splice() - Determine to forward a flow from the splice interface + * @c: Execution context + * @proto: Protocol (IP L4 protocol number) + * @ini: Flow address information of the initiating side + * @tgt: Flow address information on the target side (updated) + * + * Return: pif of the target interface to forward the flow to, PIF_NONE if the + * flow cannot or should not be forwarded at all. + */ +uint8_t fwd_nat_from_splice(const struct ctx *c, uint8_t proto, + const struct flowside *ini, struct flowside *tgt) +{ + if (!inany_is_loopback(&ini->eaddr) || + (!inany_is_loopback(&ini->faddr) && !inany_is_unspecified(&ini->faddr))) { + char estr[INANY_ADDRSTRLEN], fstr[INANY_ADDRSTRLEN]; + + debug("Non loopback address on %s: [%s]:%hu -> [%s]:%hu", + pif_name(PIF_SPLICE), + inany_ntop(&ini->eaddr, estr, sizeof(estr)), ini->eport, + inany_ntop(&ini->faddr, fstr, sizeof(fstr)), ini->fport); + return PIF_NONE; + } + + if (inany_v4(&ini->eaddr)) + tgt->eaddr = inany_loopback4; + else + tgt->eaddr = inany_loopback6; + + /* Preserve the specific loopback adddress used, but let the kernel pick + * a source port on the target side */ + tgt->faddr = ini->eaddr; + tgt->fport = 0; + + tgt->eport = ini->fport; + if (proto == IPPROTO_TCP) + tgt->eport += c->tcp.fwd_out.delta[tgt->eport]; + + /* Let the kernel pick a host side source port */ + tgt->fport = 0; + + return PIF_HOST; +} + +/** + * fwd_nat_from_host() - Determine to forward a flow from the host interface + * @c: Execution context + * @proto: Protocol (IP L4 protocol number) + * @ini: Flow address information of the initiating side + * @tgt: Flow address information on the target side (updated) + * + * Return: pif of the target interface to forward the flow to, PIF_NONE if the + * flow cannot or should not be forwarded at all. + */ +uint8_t fwd_nat_from_host(const struct ctx *c, uint8_t proto, + const struct flowside *ini, struct flowside *tgt) +{ + /* Common for spliced and non-spliced cases */ + tgt->eport = ini->fport; + if (proto == IPPROTO_TCP) + tgt->eport += c->tcp.fwd_in.delta[tgt->eport]; + + if (c->mode == MODE_PASTA && inany_is_loopback(&ini->eaddr) && + proto == IPPROTO_TCP) { + /* spliceable */ + + /* Preserve the specific loopback adddress used, but let the + * kernel pick a source port on the target side */ + tgt->faddr = ini->eaddr; + tgt->fport = 0; + + if (inany_v4(&ini->eaddr)) + tgt->eaddr = inany_loopback4; + else + tgt->eaddr = inany_loopback6; + return PIF_SPLICE; + } + + tgt->faddr = ini->eaddr; + tgt->fport = ini->eport; + + if (inany_is_loopback4(&tgt->faddr) || + inany_is_unspecified4(&tgt->faddr) || + inany_equals4(&tgt->faddr, &c->ip4.addr_seen)) { + tgt->faddr = inany_from_v4(c->ip4.gw); + } else if (inany_is_loopback6(&tgt->faddr) || + inany_equals6(&tgt->faddr, &c->ip6.addr_seen) || + inany_equals6(&tgt->faddr, &c->ip6.addr)) { + if (IN6_IS_ADDR_LINKLOCAL(&c->ip6.gw)) + tgt->faddr.a6 = c->ip6.gw; + else + tgt->faddr.a6 = c->ip6.addr_ll; + } + + if (inany_v4(&tgt->faddr)) { + tgt->eaddr = inany_from_v4(c->ip4.addr_seen); + } else { + if (inany_is_linklocal6(&tgt->faddr)) + tgt->eaddr.a6 = c->ip6.addr_ll_seen; + else + tgt->eaddr.a6 = c->ip6.addr_seen; + } + + return PIF_TAP; +} diff --git a/fwd.h b/fwd.h index 41645d7f..b4aa8d57 100644 --- a/fwd.h +++ b/fwd.h @@ -7,6 +7,8 @@ #ifndef FWD_H #define FWD_H +struct flowside; + /* Number of ports for both TCP and UDP */ #define NUM_PORTS (1U << 16) @@ -42,4 +44,11 @@ void fwd_scan_ports_udp(struct fwd_ports *fwd, const struct fwd_ports *rev, const struct fwd_ports *tcp_rev); void fwd_scan_ports_init(struct ctx *c); +uint8_t fwd_nat_from_tap(const struct ctx *c, uint8_t proto, + const struct flowside *ini, struct flowside *tgt); +uint8_t fwd_nat_from_splice(const struct ctx *c, uint8_t proto, + const struct flowside *ini, struct flowside *tgt); +uint8_t fwd_nat_from_host(const struct ctx *c, uint8_t proto, + const struct flowside *ini, struct flowside *tgt); + #endif /* FWD_H */ diff --git a/tcp.c b/tcp.c index 4d3ffe57..e89b12b3 100644 --- a/tcp.c +++ b/tcp.c @@ -1423,7 +1423,6 @@ static void tcp_conn_from_tap(struct ctx *c, sa_family_t af, { in_port_t srcport = ntohs(th->source); in_port_t dstport = ntohs(th->dest); - union inany_addr srcaddr, dstaddr; /* FIXME: Avoid bulky temporaries */ const struct flowside *ini, *tgt; struct tcp_tap_conn *conn; union sockaddr_inany sa; @@ -1438,34 +1437,16 @@ static void tcp_conn_from_tap(struct ctx *c, sa_family_t af, ini = flow_initiate_af(flow, PIF_TAP, af, saddr, srcport, daddr, dstport); - dstaddr = ini->faddr; - if (!c->no_map_gw) { - if (inany_equals4(&dstaddr, &c->ip4.gw)) - dstaddr = inany_loopback4; - else if (inany_equals6(&dstaddr, &c->ip6.gw)) - dstaddr = inany_loopback6; - - } + if (!(tgt = flow_target(c, flow, IPPROTO_TCP))) + goto cancel; - if (inany_is_linklocal6(&dstaddr)) { - srcaddr.a6 = c->ip6.addr_ll; - } else if (inany_is_loopback(&dstaddr)) { - srcaddr = dstaddr; - } else if (inany_v4(&dstaddr)) { - if (!IN4_IS_ADDR_UNSPECIFIED(&c->ip4.addr_out)) - srcaddr = inany_from_v4(c->ip4.addr_out); - else - srcaddr = inany_any4; - } else { - if (!IN6_IS_ADDR_UNSPECIFIED(&c->ip6.addr_out)) - srcaddr.a6 = c->ip6.addr_out; - else - srcaddr = inany_any6; + if (flow->f.pif[TGTSIDE] != PIF_HOST) { + flow_err(flow, "No support for forwarding TCP from %s to %s", + pif_name(flow->f.pif[INISIDE]), + pif_name(flow->f.pif[TGTSIDE])); + goto cancel; } - tgt = flow_target_af(flow, PIF_HOST, AF_INET6, - &srcaddr, 0, /* Kernel decides source port */ - &dstaddr, dstport); conn = FLOW_SET_TYPE(flow, FLOW_TCP, tcp); if (!inany_is_unicast(&ini->eaddr) || ini->eport == 0 || @@ -2003,63 +1984,20 @@ static void tcp_connect_finish(struct ctx *c, struct tcp_tap_conn *conn) conn_flag(c, conn, ACK_FROM_TAP_DUE); } -/** - * tcp_snat_inbound() - Translate source address for inbound data if needed - * @c: Execution context - * @addr: Source address of inbound packet/connection - */ -static void tcp_snat_inbound(const struct ctx *c, union inany_addr *addr) -{ - if (inany_is_loopback4(addr) || - inany_is_unspecified4(addr) || - inany_equals4(addr, &c->ip4.addr_seen)) { - *addr = inany_from_v4(c->ip4.gw); - } else if (inany_is_loopback6(addr) || - inany_equals6(addr, &c->ip6.addr_seen) || - inany_equals6(addr, &c->ip6.addr)) { - if (IN6_IS_ADDR_LINKLOCAL(&c->ip6.gw)) - addr->a6 = c->ip6.gw; - else - addr->a6 = c->ip6.addr_ll; - } -} - /** * tcp_tap_conn_from_sock() - Initialize state for non-spliced connection * @c: Execution context - * @dstport: Destination port for connection (host side) * @flow: flow to initialise * @s: Accepted socket * @sa: Peer socket address (from accept()) * @now: Current timestamp */ -static void tcp_tap_conn_from_sock(struct ctx *c, in_port_t dstport, - union flow *flow, int s, - const union sockaddr_inany *sa, +static void tcp_tap_conn_from_sock(struct ctx *c, union flow *flow, int s, const struct timespec *now) { - union inany_addr saddr, daddr; /* FIXME: avoid bulky temporaries */ - struct tcp_tap_conn *conn; - in_port_t srcport; + struct tcp_tap_conn *conn = FLOW_SET_TYPE(flow, FLOW_TCP, tcp); uint64_t hash; - inany_from_sockaddr(&saddr, &srcport, sa); - tcp_snat_inbound(c, &saddr); - - if (inany_v4(&saddr)) { - daddr = inany_from_v4(c->ip4.addr_seen); - } else { - if (inany_is_linklocal6(&saddr)) - daddr.a6 = c->ip6.addr_ll_seen; - else - daddr.a6 = c->ip6.addr_seen; - } - dstport += c->tcp.fwd_in.delta[dstport]; - - flow_target_af(flow, PIF_TAP, AF_INET6, - &saddr, srcport, &daddr, dstport); - conn = FLOW_SET_TYPE(flow, FLOW_TCP, tcp); - conn->sock = s; conn->timer = -1; conn->ws_to_tap = conn->ws_from_tap = 0; @@ -2115,11 +2053,26 @@ void tcp_listen_handler(struct ctx *c, union epoll_ref ref, goto cancel; } - if (tcp_splice_conn_from_sock(c, ref.tcp_listen.pif, - ref.tcp_listen.port, flow, s, &sa)) - return; + if (!flow_target(c, flow, IPPROTO_TCP)) + goto cancel; + + switch (flow->f.pif[TGTSIDE]) { + case PIF_SPLICE: + case PIF_HOST: + tcp_splice_conn_from_sock(c, flow, s); + break; + + case PIF_TAP: + tcp_tap_conn_from_sock(c, flow, s, now); + break; + + default: + flow_err(flow, "No support for forwarding TCP from %s to %s", + pif_name(flow->f.pif[INISIDE]), + pif_name(flow->f.pif[TGTSIDE])); + goto cancel; + } - tcp_tap_conn_from_sock(c, ref.tcp_listen.port, flow, s, &sa, now); return; cancel: diff --git a/tcp_splice.c b/tcp_splice.c index c45fd55a..28f01b59 100644 --- a/tcp_splice.c +++ b/tcp_splice.c @@ -394,72 +394,18 @@ static int tcp_conn_sock_ns(const struct ctx *c, sa_family_t af) /** * tcp_splice_conn_from_sock() - Attempt to init state for a spliced connection * @c: Execution context - * @pif0: pif id of side 0 - * @dstport: Side 0 destination port of connection * @flow: flow to initialise * @s0: Accepted (side 0) socket * @sa: Peer address of connection * - * Return: true if able to create a spliced connection, false otherwise * #syscalls:pasta setsockopt */ -bool tcp_splice_conn_from_sock(const struct ctx *c, - uint8_t pif0, in_port_t dstport, - union flow *flow, int s0, - const union sockaddr_inany *sa) +void tcp_splice_conn_from_sock(const struct ctx *c, union flow *flow, int s0) { - struct tcp_splice_conn *conn; - union inany_addr src; - in_port_t srcport; - sa_family_t af; - uint8_t tgtpif; + struct tcp_splice_conn *conn = FLOW_SET_TYPE(flow, FLOW_TCP_SPLICE, + tcp_splice); - if (c->mode != MODE_PASTA) - return false; - - inany_from_sockaddr(&src, &srcport, sa); - af = inany_v4(&src) ? AF_INET : AF_INET6; - - switch (pif0) { - case PIF_SPLICE: - if (!inany_is_loopback(&src)) { - char str[INANY_ADDRSTRLEN]; - - /* We can't use flow_err() etc. because we haven't set - * the flow type yet - */ - warn("Bad source address %s for splice, closing", - inany_ntop(&src, str, sizeof(str))); - - /* We *don't* want to fall back to tap */ - flow_alloc_cancel(flow); - return true; - } - - tgtpif = PIF_HOST; - dstport += c->tcp.fwd_out.delta[dstport]; - break; - - case PIF_HOST: - if (!inany_is_loopback(&src)) - return false; - - tgtpif = PIF_SPLICE; - dstport += c->tcp.fwd_in.delta[dstport]; - break; - - default: - return false; - } - - /* FIXME: Record outbound source address when known */ - if (af == AF_INET) - flow_target_af(flow, tgtpif, AF_INET, - NULL, 0, &in4addr_loopback, dstport); - else - flow_target_af(flow, tgtpif, AF_INET6, - NULL, 0, &in6addr_loopback, dstport); - conn = FLOW_SET_TYPE(flow, FLOW_TCP_SPLICE, tcp_splice); + ASSERT(c->mode == MODE_PASTA); conn->s[0] = s0; conn->s[1] = -1; @@ -473,8 +419,6 @@ bool tcp_splice_conn_from_sock(const struct ctx *c, conn_flag(c, conn, CLOSING); FLOW_ACTIVATE(conn); - - return true; } /** diff --git a/tcp_splice.h b/tcp_splice.h index ed8f0c58..a20f3e21 100644 --- a/tcp_splice.h +++ b/tcp_splice.h @@ -11,10 +11,7 @@ union sockaddr_inany; void tcp_splice_sock_handler(struct ctx *c, union epoll_ref ref, uint32_t events); -bool tcp_splice_conn_from_sock(const struct ctx *c, - uint8_t pif0, in_port_t dstport, - union flow *flow, int s0, - const union sockaddr_inany *sa); +void tcp_splice_conn_from_sock(const struct ctx *c, union flow *flow, int s0); void tcp_splice_init(struct ctx *c); #endif /* TCP_SPLICE_H */ -- 2.45.2

Add logic to the fwd_nat_from_*() functions to forwarding UDP packets. The logic here doesn't exactly match our current forwarding, since our current forwarding has some very strange and buggy edge cases. Instead it's attempting to replicate what appears to be the intended logic behind the current forwarding. Signed-off-by: David Gibson --- fwd.c | 26 ++++++++++++++++++++++---- 1 file changed, 22 insertions(+), 4 deletions(-) diff --git a/fwd.c b/fwd.c index 5731a536..4377de44 100644 --- a/fwd.c +++ b/fwd.c @@ -169,12 +169,15 @@ void fwd_scan_ports_init(struct ctx *c) uint8_t fwd_nat_from_tap(const struct ctx *c, uint8_t proto, const struct flowside *ini, struct flowside *tgt) { - (void)proto; - tgt->eaddr = ini->faddr; tgt->eport = ini->fport; - if (!c->no_map_gw) { + if (proto == IPPROTO_UDP && tgt->eport == 53) { + if (inany_equals4(&tgt->eaddr, &c->ip4.dns_match)) + tgt->eaddr = inany_from_v4(c->ip4.dns_host); + else if (inany_equals6(&tgt->eaddr, &c->ip6.dns_match)) + tgt->eaddr.a6 = c->ip6.dns_host; + } else if (!c->no_map_gw) { if (inany_equals4(&tgt->eaddr, &c->ip4.gw)) tgt->eaddr = inany_loopback4; else if (inany_equals6(&tgt->eaddr, &c->ip6.gw)) @@ -191,6 +194,10 @@ uint8_t fwd_nat_from_tap(const struct ctx *c, uint8_t proto, /* Let the kernel pick a host side source port */ tgt->fport = 0; + if (proto == IPPROTO_UDP) { + /* But for UDP we preserve the source port */ + tgt->fport = ini->eport; + } return PIF_HOST; } @@ -232,9 +239,14 @@ uint8_t fwd_nat_from_splice(const struct ctx *c, uint8_t proto, tgt->eport = ini->fport; if (proto == IPPROTO_TCP) tgt->eport += c->tcp.fwd_out.delta[tgt->eport]; + else if (proto == IPPROTO_UDP) + tgt->eport += c->udp.fwd_out.f.delta[tgt->eport]; /* Let the kernel pick a host side source port */ tgt->fport = 0; + if (proto == IPPROTO_UDP) + /* But for UDP preserve the source port */ + tgt->fport = ini->eport; return PIF_HOST; } @@ -256,20 +268,26 @@ uint8_t fwd_nat_from_host(const struct ctx *c, uint8_t proto, tgt->eport = ini->fport; if (proto == IPPROTO_TCP) tgt->eport += c->tcp.fwd_in.delta[tgt->eport]; + else if (proto == IPPROTO_UDP) + tgt->eport += c->udp.fwd_in.f.delta[tgt->eport]; if (c->mode == MODE_PASTA && inany_is_loopback(&ini->eaddr) && - proto == IPPROTO_TCP) { + (proto == IPPROTO_TCP || proto == IPPROTO_UDP)) { /* spliceable */ /* Preserve the specific loopback adddress used, but let the * kernel pick a source port on the target side */ tgt->faddr = ini->eaddr; tgt->fport = 0; + if (proto == IPPROTO_UDP) + /* But for UDP preserve the source port */ + tgt->fport = ini->eport; if (inany_v4(&ini->eaddr)) tgt->eaddr = inany_loopback4; else tgt->eaddr = inany_loopback6; + return PIF_SPLICE; } -- 2.45.2

When forwarding a datagram to a socket, we need to find a socket with a suitable local address to send it. Currently we keep track of such sockets in an array indexed by local port, but this can't properly handle cases where we have multiple local addresses in active use. For "spliced" (socket to socket) cases, improve this by instead opening a socket specifically for the target side of the flow. We connect() as well as bind()ing that socket, so that it will only receive the flow's reply packets, not anything else. We direct datagrams sent via that socket using the addresses from the flow table, effectively replacing bespoke addressing logic with the unified logic in fwd.c When we create the flow, we also take a duplicate of the originating socket, and use that to deliver reply datagrams back to the origin, again using addresses from the flow table entry. Signed-off-by: David Gibson --- epoll_type.h | 2 + flow.c | 20 +++ flow.h | 2 + flow_table.h | 14 ++ passt.c | 4 + udp.c | 403 ++++++++++++++++++--------------------------------- udp.h | 6 +- udp_flow.h | 2 + util.c | 1 + 9 files changed, 194 insertions(+), 260 deletions(-) diff --git a/epoll_type.h b/epoll_type.h index b6c04199..7a752ed1 100644 --- a/epoll_type.h +++ b/epoll_type.h @@ -22,6 +22,8 @@ enum epoll_type { EPOLL_TYPE_TCP_TIMER, /* UDP sockets */ EPOLL_TYPE_UDP, + /* UDP socket for replies on a specific flow */ + EPOLL_TYPE_UDP_REPLY, /* ICMP/ICMPv6 ping sockets */ EPOLL_TYPE_PING, /* inotify fd watching for end of netns (pasta) */ diff --git a/flow.c b/flow.c index 0cb9495b..2e100ddb 100644 --- a/flow.c +++ b/flow.c @@ -236,6 +236,26 @@ int flowside_sock_l4(const struct ctx *c, enum epoll_type type, uint8_t pif, } } +/** flowside_connect() - Connect a socket based on flowside + * @c: Execution context + * @s: Socket to connect + * @pif: Target pif + * @tgt: Target flowside + * + * Connect @s to the endpoint address and port from @tgt. + * + * Return: 0 on success, negative on error + */ +int flowside_connect(const struct ctx *c, int s, + uint8_t pif, const struct flowside *tgt) +{ + union sockaddr_inany sa; + socklen_t sl; + + pif_sockaddr(c, &sa, &sl, pif, &tgt->eaddr, tgt->eport); + return connect(s, &sa.sa, sl); +} + /** flow_log_ - Log flow-related message * @f: flow the message is related to * @pri: Log priority diff --git a/flow.h b/flow.h index 3752e5ee..3f65ceb9 100644 --- a/flow.h +++ b/flow.h @@ -168,6 +168,8 @@ static inline bool flowside_eq(const struct flowside *left, int flowside_sock_l4(const struct ctx *c, enum epoll_type type, uint8_t pif, const struct flowside *tgt, uint32_t data); +int flowside_connect(const struct ctx *c, int s, + uint8_t pif, const struct flowside *tgt); /** * struct flow_common - Common fields for packet flows diff --git a/flow_table.h b/flow_table.h index 3fbc7c8d..1faac4a7 100644 --- a/flow_table.h +++ b/flow_table.h @@ -92,6 +92,20 @@ static inline flow_sidx_t flow_sidx_opposite(flow_sidx_t sidx) return (flow_sidx_t){.flow = sidx.flow, .side = !sidx.side}; } +/** pif_at_sidx - Interface for a given flow and side + * @sidx: Flow & side index + * + * Return: pif for the flow & side given by @sidx + */ +static inline uint8_t pif_at_sidx(flow_sidx_t sidx) +{ + const union flow *flow = flow_at_sidx(sidx); + + if (!flow) + return PIF_NONE; + return flow->f.pif[sidx.side]; +} + /** flow_sidx_t - Index of one side of a flow from common structure * @f: Common flow fields pointer * @side: Which side to refer to (0 or 1) diff --git a/passt.c b/passt.c index e4d45daa..f9405bee 100644 --- a/passt.c +++ b/passt.c @@ -67,6 +67,7 @@ char *epoll_type_str[] = { [EPOLL_TYPE_TCP_LISTEN] = "listening TCP socket", [EPOLL_TYPE_TCP_TIMER] = "TCP timer", [EPOLL_TYPE_UDP] = "UDP socket", + [EPOLL_TYPE_UDP_REPLY] = "UDP reply socket", [EPOLL_TYPE_PING] = "ICMP/ICMPv6 ping socket", [EPOLL_TYPE_NSQUIT_INOTIFY] = "namespace inotify watch", [EPOLL_TYPE_NSQUIT_TIMER] = "namespace timer watch", @@ -349,6 +350,9 @@ loop: case EPOLL_TYPE_UDP: udp_buf_sock_handler(&c, ref, eventmask, &now); break; + case EPOLL_TYPE_UDP_REPLY: + udp_reply_sock_handler(&c, ref, eventmask, &now); + break; case EPOLL_TYPE_PING: icmp_sock_handler(&c, ref); break; diff --git a/udp.c b/udp.c index daf4fe26..f4c696db 100644 --- a/udp.c +++ b/udp.c @@ -35,7 +35,31 @@ * =================== * * UDP doesn't use listen(), but we consider long term sockets which are allowed - * to create new flows "listening" by analogy with TCP. + * to create new flows "listening" by analogy with TCP. This listening socket + * could receive packets from multiple flows, so we use a hash table match to + * find the specific flow for a datagram. + * + * When a UDP flow is initiated from a listening socket we take a duplicate of + * the socket and store it in uflow->s[INISIDE]. This will last for the + * lifetime of the flow, even if the original listening socket is closed due to + * port auto-probing. The duplicate is used to deliver replies back to the + * originating side. + * + * Reply sockets + * ============= + * + * When a UDP flow targets a socket, we create a "reply" socket in + * uflow->s[TGTSIDE] both to deliver datagrams to the target side and receive + * replies on the target side. This socket is both bound and connected and has + * EPOLL_TYPE_UDP_REPLY. The connect() means it will only receive datagrams + * associated with this flow, so the epoll reference directly points to the flow + * and we don't need a hash lookup. + * + * NOTE: it's possible that the reply socket could have a bound address + * overlapping with an unrelated listening socket. We assume datagrams for the + * flow will come to the reply socket in preference to a listening socket. The + * sample program contrib/udp-reuseaddr/reuseaddr-priority.c documents and tests + * that assumption. * * Port tracking * ============= @@ -56,62 +80,6 @@ * * Packets are forwarded back and forth, by prepending and stripping UDP headers * in the obvious way, with no port translation. - * - * In PASTA mode, the L2-L4 translation is skipped for connections to ports - * bound between namespaces using the loopback interface, messages are directly - * transferred between L4 sockets instead. These are called spliced connections - * for consistency with the TCP implementation, but the splice() syscall isn't - * actually used as it wouldn't make sense for datagram-based connections: a - * pair of recvmmsg() and sendmmsg() deals with this case. - * - * The connection tracking for PASTA mode is slightly complicated by the absence - * of actual connections, see struct udp_splice_port, and these examples: - * - * - from init to namespace: - * - * - forward direction: 127.0.0.1:5000 -> 127.0.0.1:80 in init from socket s, - * with epoll reference: index = 80, splice = 1, orig = 1, ns = 0 - * - if udp_splice_ns[V4][5000].sock: - * - send packet to udp_splice_ns[V4][5000].sock, with destination port - * 80 - * - otherwise: - * - create new socket udp_splice_ns[V4][5000].sock - * - bind in namespace to 127.0.0.1:5000 - * - add to epoll with reference: index = 5000, splice = 1, orig = 0, - * ns = 1 - * - update udp_splice_init[V4][80].ts and udp_splice_ns[V4][5000].ts with - * current time - * - * - reverse direction: 127.0.0.1:80 -> 127.0.0.1:5000 in namespace socket s, - * having epoll reference: index = 5000, splice = 1, orig = 0, ns = 1 - * - if udp_splice_init[V4][80].sock: - * - send to udp_splice_init[V4][80].sock, with destination port 5000 - * - update udp_splice_init[V4][80].ts and udp_splice_ns[V4][5000].ts with - * current time - * - otherwise, discard - * - * - from namespace to init: - * - * - forward direction: 127.0.0.1:2000 -> 127.0.0.1:22 in namespace from - * socket s, with epoll reference: index = 22, splice = 1, orig = 1, ns = 1 - * - if udp4_splice_init[V4][2000].sock: - * - send packet to udp_splice_init[V4][2000].sock, with destination - * port 22 - * - otherwise: - * - create new socket udp_splice_init[V4][2000].sock - * - bind in init to 127.0.0.1:2000 - * - add to epoll with reference: index = 2000, splice = 1, orig = 0, - * ns = 0 - * - update udp_splice_ns[V4][22].ts and udp_splice_init[V4][2000].ts with - * current time - * - * - reverse direction: 127.0.0.1:22 -> 127.0.0.1:2000 in init from socket s, - * having epoll reference: index = 2000, splice = 1, orig = 0, ns = 0 - * - if udp_splice_ns[V4][22].sock: - * - send to udp_splice_ns[V4][22].sock, with destination port 2000 - * - update udp_splice_ns[V4][22].ts and udp_splice_init[V4][2000].ts with - * current time - * - otherwise, discard */ #include @@ -134,6 +102,7 @@ #include #include #include +#include #include "checksum.h" #include "util.h" @@ -223,7 +192,6 @@ static struct ethhdr udp6_eth_hdr; * @ip4h: Pre-filled IPv4 header (except for tot_len and saddr) * @taph: Tap backend specific header * @s_in: Source socket address, filled in by recvmmsg() - * @splicesrc: Source port for splicing, or -1 if not spliceable * @tosidx: sidx for the destination side of this datagram's flow */ static struct udp_meta_t { @@ -232,7 +200,6 @@ static struct udp_meta_t { struct tap_hdr taph; union sockaddr_inany s_in; - int splicesrc; flow_sidx_t tosidx; } #ifdef __AVX2__ @@ -270,7 +237,6 @@ static struct mmsghdr udp_mh_splice [UDP_MAX_FRAMES]; /* IOVs for L2 frames */ static struct iovec udp_l2_iov [UDP_MAX_FRAMES][UDP_NUM_IOVS]; - /** * udp_portmap_clear() - Clear UDP port map before configuration */ @@ -383,140 +349,6 @@ static void udp_iov_init(const struct ctx *c) udp_iov_init_one(c, i); } -/** - * udp_splice_new() - Create and prepare socket for "spliced" binding - * @c: Execution context - * @v6: Set for IPv6 sockets - * @src: Source port of original connection, host order - * @ns: Does the splice originate in the ns or not - * - * Return: prepared socket, negative error code on failure - * - * #syscalls:pasta getsockname - */ -int udp_splice_new(const struct ctx *c, int v6, in_port_t src, bool ns) -{ - struct epoll_event ev = { .events = EPOLLIN | EPOLLRDHUP | EPOLLHUP }; - union epoll_ref ref = { .type = EPOLL_TYPE_UDP, - .udp = { .splice = true, .v6 = v6, .port = src } - }; - struct udp_splice_port *sp; - int act, s; - - if (ns) { - ref.udp.pif = PIF_SPLICE; - sp = &udp_splice_ns[v6 ? V6 : V4][src]; - act = UDP_ACT_SPLICE_NS; - } else { - ref.udp.pif = PIF_HOST; - sp = &udp_splice_init[v6 ? V6 : V4][src]; - act = UDP_ACT_SPLICE_INIT; - } - - s = socket(v6 ? AF_INET6 : AF_INET, SOCK_DGRAM | SOCK_NONBLOCK, - IPPROTO_UDP); - - if (s > FD_REF_MAX) { - close(s); - return -EIO; - } - - if (s < 0) - return s; - - ref.fd = s; - - if (v6) { - struct sockaddr_in6 addr6 = { - .sin6_family = AF_INET6, - .sin6_port = htons(src), - .sin6_addr = IN6ADDR_LOOPBACK_INIT, - }; - if (bind(s, (struct sockaddr *)&addr6, sizeof(addr6))) - goto fail; - } else { - struct sockaddr_in addr4 = { - .sin_family = AF_INET, - .sin_port = htons(src), - .sin_addr = IN4ADDR_LOOPBACK_INIT, - }; - if (bind(s, (struct sockaddr *)&addr4, sizeof(addr4))) - goto fail; - } - - sp->sock = s; - bitmap_set(udp_act[v6 ? V6 : V4][act], src); - - ev.data.u64 = ref.u64; - epoll_ctl(c->epollfd, EPOLL_CTL_ADD, s, &ev); - return s; - -fail: - close(s); - return -1; -} - -/** - * struct udp_splice_new_ns_arg - Arguments for udp_splice_new_ns() - * @c: Execution context - * @v6: Set for IPv6 - * @src: Source port of originating datagram, host order - * @dst: Destination port of originating datagram, host order - * @s: Newly created socket or negative error code - */ -struct udp_splice_new_ns_arg { - const struct ctx *c; - int v6; - in_port_t src; - int s; -}; - -/** - * udp_splice_new_ns() - Enter namespace and call udp_splice_new() - * @arg: See struct udp_splice_new_ns_arg - * - * Return: 0 - */ -static int udp_splice_new_ns(void *arg) -{ - struct udp_splice_new_ns_arg *a; - - a = (struct udp_splice_new_ns_arg *)arg; - - ns_enter(a->c); - - a->s = udp_splice_new(a->c, a->v6, a->src, true); - - return 0; -} - -/** - * udp_mmh_splice_port() - Is source address of message suitable for splicing? - * @ref: epoll reference for incoming message's origin socket - * @mmh: mmsghdr of incoming message - * - * Return: if source address of message in @mmh refers to localhost (127.0.0.1 - * or ::1) its source port (host order), otherwise -1. - */ -static int udp_mmh_splice_port(union epoll_ref ref, const struct mmsghdr *mmh) -{ - const struct sockaddr_in6 *sa6 = mmh->msg_hdr.msg_name; - const struct sockaddr_in *sa4 = mmh->msg_hdr.msg_name; - - ASSERT(ref.type == EPOLL_TYPE_UDP); - - if (!ref.udp.splice) - return -1; - - if (ref.udp.v6 && IN6_IS_ADDR_LOOPBACK(&sa6->sin6_addr)) - return ntohs(sa6->sin6_port); - - if (!ref.udp.v6 && IN4_IS_ADDR_LOOPBACK(&sa4->sin_addr)) - return ntohs(sa4->sin_port); - - return -1; -} - /** * udp_at_sidx() - Get UDP specific flow at given sidx * @sidx: Flow and side to retrieve @@ -542,6 +374,16 @@ struct udp_flow *udp_at_sidx(flow_sidx_t sidx) */ static void udp_flow_close(const struct ctx *c, const struct udp_flow *uflow) { + if (uflow->s[INISIDE] >= 0) { + /* The listening socket needs to stay in epoll */ + close(uflow->s[INISIDE]); + } + + if (uflow->s[TGTSIDE] >= 0) { + /* But the flow specific one needs to be removed */ + epoll_ctl(c->epollfd, EPOLL_CTL_DEL, uflow->s[TGTSIDE], NULL); + close(uflow->s[TGTSIDE]); + } flow_hash_remove(c, FLOW_SIDX(uflow, INISIDE)); } @@ -549,26 +391,80 @@ static void udp_flow_close(const struct ctx *c, const struct udp_flow *uflow) * udp_flow_new() - Common setup for a new UDP flow * @c: Execution context * @flow: Initiated flow + * @s_ini: Initiating socket (or -1) * @now: Timestamp * * Return: UDP specific flow, if successful, NULL on failure */ static flow_sidx_t udp_flow_new(const struct ctx *c, union flow *flow, - const struct timespec *now) + int s_ini, const struct timespec *now) { const struct flowside *ini = &flow->f.side[INISIDE]; struct udp_flow *uflow = NULL; + const struct flowside *tgt; + uint8_t tgtpif; if (!inany_is_unicast(&ini->eaddr) || ini->eport == 0) { flow_dbg(flow, "Invalid endpoint to initiate UDP flow"); goto cancel; } - if (!flow_target(c, flow, IPPROTO_UDP)) + if (!(tgt = flow_target(c, flow, IPPROTO_UDP))) goto cancel; + tgtpif = flow->f.pif[TGTSIDE]; uflow = FLOW_SET_TYPE(flow, FLOW_UDP, udp); uflow->ts = now->tv_sec; + uflow->s[INISIDE] = uflow->s[TGTSIDE] = -1; + + if (s_ini >= 0) { + /* When using auto port-scanning the listening port could go + * away, so we need to duplicate it */ + uflow->s[INISIDE] = fcntl(s_ini, F_DUPFD_CLOEXEC, 0); + if (uflow->s[INISIDE] < 0) { + flow_err(uflow, + "Couldn't duplicate listening socket: %s", + strerror(errno)); + goto cancel; + } + } + + if (pif_is_socket(tgtpif)) { + union { + flow_sidx_t sidx; + uint32_t data; + } fref = { + .sidx = FLOW_SIDX(flow, TGTSIDE), + }; + + uflow->s[TGTSIDE] = flowside_sock_l4(c, EPOLL_TYPE_UDP_REPLY, + tgtpif, tgt, fref.data); + if (uflow->s[TGTSIDE] < 0) { + flow_dbg(uflow, + "Couldn't open socket for spliced flow: %s", + strerror(errno)); + goto cancel; + } + + if (flowside_connect(c, uflow->s[TGTSIDE], tgtpif, tgt) < 0) { + flow_dbg(uflow, + "Couldn't connect flow socket: %s", + strerror(errno)); + goto cancel; + } + + /* It's possible, if unlikely, that we could receive some + * unrelated packets in between the bind() and connect() of this + * socket. For now we just discard these. We could consider + * trying to re-direct these to an appropriate handler, if we + * need to. + */ + /* cppcheck-suppress nullPointer */ + while (recv(uflow->s[TGTSIDE], NULL, 0, MSG_DONTWAIT) >= 0) + ; + if (errno != EAGAIN) + warn_perror("Unexpected error discarding datagrams"); + } flow_hash_insert(c, FLOW_SIDX(uflow, INISIDE)); FLOW_ACTIVATE(uflow); @@ -580,7 +476,6 @@ cancel: udp_flow_close(c, uflow); flow_alloc_cancel(flow); return FLOW_SIDX_NONE; - } /** @@ -590,6 +485,8 @@ cancel: * @meta: Metadata buffer for the datagram * @now: Timestamp * + * #syscalls fcntl + * * Return: sidx for the destination side of the flow for this packet, or * FLOW_SIDX_NONE if we couldn't find or create a flow. */ @@ -623,7 +520,7 @@ static flow_sidx_t udp_flow_from_sock(const struct ctx *c, union epoll_ref ref, } flow_initiate_sa(flow, ref.udp.pif, &meta->s_in, ref.udp.port); - return udp_flow_new(c, flow, now); + return udp_flow_new(c, flow, ref.fd, now); } /** @@ -647,55 +544,16 @@ static void udp_splice_prepare(struct mmsghdr *mmh, unsigned idx) * @now: Timestamp */ static void udp_splice_send(const struct ctx *c, size_t start, size_t n, - in_port_t src, in_port_t dst, - union epoll_ref ref, - const struct timespec *now) + flow_sidx_t tosidx) { - int s; - - if (ref.udp.v6) { - udp_splice_to.sa6 = (struct sockaddr_in6) { - .sin6_family = AF_INET6, - .sin6_addr = in6addr_loopback, - .sin6_port = htons(dst), - }; - } else { - udp_splice_to.sa4 = (struct sockaddr_in) { - .sin_family = AF_INET, - .sin_addr = in4addr_loopback, - .sin_port = htons(dst), - }; - } - - if (ref.udp.pif == PIF_SPLICE) { - src += c->udp.fwd_in.rdelta[src]; - s = udp_splice_init[ref.udp.v6][src].sock; - if (s < 0 && ref.udp.orig) - s = udp_splice_new(c, ref.udp.v6, src, false); - - if (s < 0) - return; - - udp_splice_ns[ref.udp.v6][dst].ts = now->tv_sec; - udp_splice_init[ref.udp.v6][src].ts = now->tv_sec; - } else { - ASSERT(ref.udp.pif == PIF_HOST); - src += c->udp.fwd_out.rdelta[src]; - s = udp_splice_ns[ref.udp.v6][src].sock; - if (s < 0 && ref.udp.orig) { - struct udp_splice_new_ns_arg arg = { - c, ref.udp.v6, src, -1, - }; - - NS_CALL(udp_splice_new_ns, &arg); - s = arg.s; - } - if (s < 0) - return; + const struct udp_flow *uflow = udp_at_sidx(tosidx); + const struct flowside *toside = &uflow->f.side[tosidx.side]; + uint8_t topif = uflow->f.pif[tosidx.side]; + int s = uflow->s[tosidx.side]; + socklen_t sl; - udp_splice_init[ref.udp.v6][dst].ts = now->tv_sec; - udp_splice_ns[ref.udp.v6][src].ts = now->tv_sec; - } + pif_sockaddr(c, &udp_splice_to, &sl, topif, + &toside->eaddr, toside->eport); sendmmsg(s, udp_mh_splice + start, n, MSG_NOSIGNAL); } @@ -922,20 +780,18 @@ void udp_buf_sock_handler(const struct ctx *c, union epoll_ref ref, uint32_t eve dstport += c->udp.fwd_in.f.delta[dstport]; /* We divide datagrams into batches based on how we need to send them, - * determined by udp_meta[i].splicesrc and udp_meta[i].tosidx. To avoid - * either two passes through the array, or recalculating splicesrc and - * tosidxfor a single entry, we have to populate it one entry *ahead* of - * the loop counter. + * determined by udp_meta[i].tosidx. To avoid either two passes through + * the array, or recalculating tosidx for a single entry, we have to + * populate it one entry *ahead* of the loop counter. */ - udp_meta[0].splicesrc = udp_mmh_splice_port(ref, mmh_recv); udp_meta[0].tosidx = udp_flow_from_sock(c, ref, &udp_meta[0], now); for (i = 0; i < n; ) { flow_sidx_t batchsidx = udp_meta[i].tosidx; - int batchsrc = udp_meta[i].splicesrc; + uint8_t batchpif = pif_at_sidx(batchsidx); int batchstart = i; do { - if (batchsrc >= 0) + if (pif_is_socket(batchpif)) udp_splice_prepare(mmh_recv, i); else udp_tap_prepare(c, mmh_recv, i, dstport, @@ -944,23 +800,54 @@ void udp_buf_sock_handler(const struct ctx *c, union epoll_ref ref, uint32_t eve if (++i >= n) break; - udp_meta[i].splicesrc = udp_mmh_splice_port(ref, - &mmh_recv[i]); udp_meta[i].tosidx = udp_flow_from_sock(c, ref, &udp_meta[i], now); - } while (flow_sidx_eq(udp_meta[i].tosidx, batchsidx) && - udp_meta[i].splicesrc == batchsrc); + } while (flow_sidx_eq(udp_meta[i].tosidx, batchsidx)); - if (batchsrc >= 0) + if (pif_is_socket(batchpif)) udp_splice_send(c, batchstart, i - batchstart, - batchsrc, dstport, ref, now); + batchsidx); else tap_send_frames(c, &udp_l2_iov[batchstart][0], UDP_NUM_IOVS, i - batchstart); } } +/** + * udp_reply_sock_handler() - Handle new data from flow specific socket + * @c: Execution context + * @ref: epoll reference + * @events: epoll events bitmap + * @now: Current timestamp + * + * #syscalls recvmmsg + */ +void udp_reply_sock_handler(const struct ctx *c, union epoll_ref ref, + uint32_t events, const struct timespec *now) +{ + flow_sidx_t tosidx = flow_sidx_opposite(ref.flowside); + struct udp_flow *uflow = udp_at_sidx(ref.flowside); + const struct flowside *fromside = &uflow->f.side[ref.flowside.side]; + bool v6 = !inany_v4(&fromside->eaddr); + struct mmsghdr *mmh_recv = v6 ? udp6_mh_recv : udp4_mh_recv; + int from_s = uflow->s[ref.flowside.side]; + int n, i; + + ASSERT(!c->no_udp && uflow); + + if ((n = udp_sock_recv(c, from_s, events, mmh_recv)) <= 0) + return; + + flow_trace(uflow, "Received %d datagrams on reply socket", n); + uflow->ts = now->tv_sec; + + for (i = 0; i < n; i++) + udp_splice_prepare(mmh_recv, i); + + udp_splice_send(c, 0, n, tosidx); +} + /** * udp_tap_handler() - Handle packets from tap * @c: Execution context diff --git a/udp.h b/udp.h index 5865def2..db5e546e 100644 --- a/udp.h +++ b/udp.h @@ -9,8 +9,10 @@ #define UDP_TIMER_INTERVAL 1000 /* ms */ void udp_portmap_clear(void); -void udp_buf_sock_handler(const struct ctx *c, union epoll_ref ref, uint32_t events, - const struct timespec *now); +void udp_buf_sock_handler(const struct ctx *c, union epoll_ref ref, + uint32_t events, const struct timespec *now); +void udp_reply_sock_handler(const struct ctx *c, union epoll_ref ref, + uint32_t events, const struct timespec *now); int udp_tap_handler(struct ctx *c, uint8_t pif, sa_family_t af, const void *saddr, const void *daddr, const struct pool *p, int idx, const struct timespec *now); diff --git a/udp_flow.h b/udp_flow.h index 18af9ac4..d5b8784f 100644 --- a/udp_flow.h +++ b/udp_flow.h @@ -11,12 +11,14 @@ * struct udp - Descriptor for a flow of UDP packets * @f: Generic flow information * @ts: Activity timestamp + * @s: Socket fd (or -1) for each side of the flow */ struct udp_flow { /* Must be first element */ struct flow_common f; time_t ts; + int s[SIDES]; }; bool udp_flow_timer(const struct ctx *c, const struct udp_flow *uflow, diff --git a/util.c b/util.c index f2994a79..7c57ab15 100644 --- a/util.c +++ b/util.c @@ -61,6 +61,7 @@ int sock_l4_sa(const struct ctx *c, enum epoll_type type, socktype = SOCK_STREAM | SOCK_NONBLOCK; break; case EPOLL_TYPE_UDP: + case EPOLL_TYPE_UDP_REPLY: proto = IPPROTO_UDP; socktype = SOCK_DGRAM | SOCK_NONBLOCK; break; -- 2.45.2

Currently we create flows for datagrams from socket interfaces, and use them to direct "spliced" (socket to socket) datagrams. We don't yet match datagrams from the tap interface to existing flows, nor create new flows for them. Add that functionality, matching datagrams from tap to existing flows when they exist, or creating new ones. As with spliced flows, when creating a new flow from tap to socket, we create a new connected socket to receive reply datagrams attached to that flow specifically. We extend udp_flow_sock_handler() to handle reply packets bound for tap rather than another socket. For non-obvious reasons, this caused a failure for me when running under valgrind, because valgrind invoked rt_sigreturn which is not in our seccomp filter. Since we already allow rt_signaction and others in the valgrind, it seems reasonable to add rt_sigreturn as well. Signed-off-by: David Gibson --- Makefile | 2 +- udp.c | 211 +++++++++++++++++++++++++------------------------------ udp.h | 4 +- 3 files changed, 99 insertions(+), 118 deletions(-) diff --git a/Makefile b/Makefile index 92cbd5a6..bd504d23 100644 --- a/Makefile +++ b/Makefile @@ -128,7 +128,7 @@ qrap: $(QRAP_SRCS) passt.h $(CC) $(FLAGS) $(CFLAGS) $(CPPFLAGS) $(QRAP_SRCS) -o qrap $(LDFLAGS) valgrind: EXTRA_SYSCALLS += rt_sigprocmask rt_sigtimedwait rt_sigaction \ - getpid gettid kill clock_gettime mmap \ + rt_sigreturn getpid gettid kill clock_gettime mmap \ munmap open unlink gettimeofday futex valgrind: FLAGS += -g -DVALGRIND valgrind: all diff --git a/udp.c b/udp.c index a4eb6d0f..a26ffe0c 100644 --- a/udp.c +++ b/udp.c @@ -103,6 +103,7 @@ #include #include #include +#include #include "checksum.h" #include "util.h" @@ -373,6 +374,8 @@ static void udp_flow_close(const struct ctx *c, const struct udp_flow *uflow) close(uflow->s[TGTSIDE]); } flow_hash_remove(c, FLOW_SIDX(uflow, INISIDE)); + if (!pif_is_socket(uflow->f.pif[TGTSIDE])) + flow_hash_remove(c, FLOW_SIDX(uflow, TGTSIDE)); } /** @@ -455,6 +458,13 @@ static flow_sidx_t udp_flow_new(const struct ctx *c, union flow *flow, } flow_hash_insert(c, FLOW_SIDX(uflow, INISIDE)); + + /* If the target side is a socket, it will be a reply socket that knows + * its own flowside. But if it's tap, then we need to look it up by + * hash. + */ + if (!pif_is_socket(tgtpif)) + flow_hash_insert(c, FLOW_SIDX(uflow, TGTSIDE)); FLOW_ACTIVATE(uflow); return FLOW_SIDX(uflow, TGTSIDE); @@ -817,6 +827,8 @@ void udp_reply_sock_handler(const struct ctx *c, union epoll_ref ref, flow_sidx_t tosidx = flow_sidx_opposite(ref.flowside); struct udp_flow *uflow = udp_at_sidx(ref.flowside); const struct flowside *fromside = &uflow->f.side[ref.flowside.side]; + const struct flowside *toside = &uflow->f.side[tosidx.side]; + uint8_t topif = uflow->f.pif[tosidx.side]; bool v6 = !inany_v4(&fromside->eaddr); struct mmsghdr *mmh_recv = v6 ? udp6_mh_recv : udp4_mh_recv; int from_s = uflow->s[ref.flowside.side]; @@ -830,10 +842,64 @@ void udp_reply_sock_handler(const struct ctx *c, union epoll_ref ref, flow_trace(uflow, "Received %d datagrams on reply socket", n); uflow->ts = now->tv_sec; - for (i = 0; i < n; i++) - udp_splice_prepare(mmh_recv, i); + for (i = 0; i < n; i++) { + if (pif_is_socket(topif)) + udp_splice_prepare(mmh_recv, i); + else + udp_tap_prepare(c, mmh_recv, i, toside->eport, v6, now); + } - udp_splice_send(c, 0, n, tosidx); + if (pif_is_socket(topif)) + udp_splice_send(c, 0, n, tosidx); + else + tap_send_frames(c, &udp_l2_iov[0][0], UDP_NUM_IOVS, n); +} + +/** + * udp_flow_from_tap() - Find or create UDP flow for tap packets + * @c: Execution context + * @pif: pif on which the packet is arriving + * @af: Address family, AF_INET or AF_INET6 + * @saddr: Source address on guest side + * @daddr: Destination address guest side + * @srcport: Source port on guest side + * @dstport: Destination port on guest side + * + * Return: sidx for the destination side of the flow for this packet, or + * FLOW_SIDX_NONE if we couldn't find or create a flow. + */ +static flow_sidx_t udp_flow_from_tap(const struct ctx *c, + uint8_t pif, sa_family_t af, + const void *saddr, const void *daddr, + in_port_t srcport, in_port_t dstport, + const struct timespec *now) +{ + struct udp_flow *uflow; + union flow *flow; + flow_sidx_t sidx; + + ASSERT(pif == PIF_TAP); + + sidx = flow_lookup_af(c, IPPROTO_UDP, pif, af, saddr, daddr, + srcport, dstport); + if ((uflow = udp_at_sidx(sidx))) { + uflow->ts = now->tv_sec; + return flow_sidx_opposite(sidx); + } + + if (!(flow = flow_alloc())) { + char sstr[INET6_ADDRSTRLEN], dstr[INET6_ADDRSTRLEN]; + + debug("Couldn't allocate flow for UDP datagram from %s %s:%hu -> %s:%hu", + pif_name(pif), + inet_ntop(af, saddr, sstr, sizeof(sstr)), srcport, + inet_ntop(af, daddr, dstr, sizeof(dstr)), dstport); + return FLOW_SIDX_NONE; + } + + flow_initiate_af(flow, PIF_TAP, af, saddr, srcport, daddr, dstport); + + return udp_flow_new(c, flow, -1, now); } /** @@ -851,24 +917,22 @@ void udp_reply_sock_handler(const struct ctx *c, union epoll_ref ref, * * #syscalls sendmmsg */ -int udp_tap_handler(struct ctx *c, uint8_t pif, +int udp_tap_handler(const struct ctx *c, uint8_t pif, sa_family_t af, const void *saddr, const void *daddr, const struct pool *p, int idx, const struct timespec *now) { + const struct flowside *toside; struct mmsghdr mm[UIO_MAXIOV]; + union sockaddr_inany to_sa; struct iovec m[UIO_MAXIOV]; - struct sockaddr_in6 s_in6; - struct sockaddr_in s_in; const struct udphdr *uh; - struct sockaddr *sa; + struct udp_flow *uflow; int i, s, count = 0; + flow_sidx_t tosidx; in_port_t src, dst; + uint8_t topif; socklen_t sl; - (void)c; - (void)saddr; - (void)pif; - uh = packet_get(p, idx, 0, sizeof(*uh), NULL); if (!uh) return 1; @@ -877,116 +941,33 @@ int udp_tap_handler(struct ctx *c, uint8_t pif, * and destination, so we can just take those from the first message. */ src = ntohs(uh->source); - src += c->udp.fwd_in.rdelta[src]; dst = ntohs(uh->dest); - if (af == AF_INET) { - s_in = (struct sockaddr_in) { - .sin_family = AF_INET, - .sin_port = uh->dest, - .sin_addr = *(struct in_addr *)daddr, - }; + tosidx = udp_flow_from_tap(c, pif, af, saddr, daddr, src, dst, now); + if (!(uflow = udp_at_sidx(tosidx))) { + char sstr[INET6_ADDRSTRLEN], dstr[INET6_ADDRSTRLEN]; - sa = (struct sockaddr *)&s_in; - sl = sizeof(s_in); - - if (IN4_ARE_ADDR_EQUAL(&s_in.sin_addr, &c->ip4.dns_match) && - ntohs(s_in.sin_port) == 53) { - s_in.sin_addr = c->ip4.dns_host; - udp_tap_map[V4][src].ts = now->tv_sec; - udp_tap_map[V4][src].flags |= PORT_DNS_FWD; - bitmap_set(udp_act[V4][UDP_ACT_TAP], src); - } else if (IN4_ARE_ADDR_EQUAL(&s_in.sin_addr, &c->ip4.gw) && - !c->no_map_gw) { - if (!(udp_tap_map[V4][dst].flags & PORT_LOCAL) || - (udp_tap_map[V4][dst].flags & PORT_LOOPBACK)) - s_in.sin_addr.s_addr = htonl(INADDR_LOOPBACK); - else - s_in.sin_addr = c->ip4.addr_seen; - } - - debug("UDP from tap src=%hu dst=%hu, s=%d", - src, dst, udp_tap_map[V4][src].sock); - if ((s = udp_tap_map[V4][src].sock) < 0) { - struct in_addr bind_addr = IN4ADDR_ANY_INIT; - union udp_epoll_ref uref = { - .port = src, - .pif = PIF_HOST, - }; - const char *bind_if = NULL; - - if (!IN4_IS_ADDR_LOOPBACK(&s_in.sin_addr)) - bind_if = c->ip4.ifname_out; - - if (!IN4_IS_ADDR_LOOPBACK(&s_in.sin_addr)) - bind_addr = c->ip4.addr_out; - - s = sock_l4(c, AF_INET, EPOLL_TYPE_UDP, &bind_addr, - bind_if, src, uref.u32); - if (s < 0) - return p->count - idx; - - udp_tap_map[V4][src].sock = s; - bitmap_set(udp_act[V4][UDP_ACT_TAP], src); - } - - udp_tap_map[V4][src].ts = now->tv_sec; - } else { - s_in6 = (struct sockaddr_in6) { - .sin6_family = AF_INET6, - .sin6_port = uh->dest, - .sin6_addr = *(struct in6_addr *)daddr, - }; - const struct in6_addr *bind_addr = &in6addr_any; - - sa = (struct sockaddr *)&s_in6; - sl = sizeof(s_in6); - - if (IN6_ARE_ADDR_EQUAL(daddr, &c->ip6.dns_match) && - ntohs(s_in6.sin6_port) == 53) { - s_in6.sin6_addr = c->ip6.dns_host; - udp_tap_map[V6][src].ts = now->tv_sec; - udp_tap_map[V6][src].flags |= PORT_DNS_FWD; - bitmap_set(udp_act[V6][UDP_ACT_TAP], src); - } else if (IN6_ARE_ADDR_EQUAL(daddr, &c->ip6.gw) && - !c->no_map_gw) { - if (!(udp_tap_map[V6][dst].flags & PORT_LOCAL) || - (udp_tap_map[V6][dst].flags & PORT_LOOPBACK)) - s_in6.sin6_addr = in6addr_loopback; - else if (udp_tap_map[V6][dst].flags & PORT_GUA) - s_in6.sin6_addr = c->ip6.addr; - else - s_in6.sin6_addr = c->ip6.addr_seen; - } else if (IN6_IS_ADDR_LINKLOCAL(&s_in6.sin6_addr)) { - bind_addr = &c->ip6.addr_ll; - } - - if ((s = udp_tap_map[V6][src].sock) < 0) { - union udp_epoll_ref uref = { - .v6 = 1, - .port = src, - .pif = PIF_HOST, - }; - const char *bind_if = NULL; - - if (!IN6_IS_ADDR_LOOPBACK(&s_in6.sin6_addr)) - bind_if = c->ip6.ifname_out; + debug("Dropping datagram with no flow %s %s:%hu -> %s:%hu", + pif_name(pif), + inet_ntop(af, saddr, sstr, sizeof(sstr)), src, + inet_ntop(af, daddr, dstr, sizeof(dstr)), dst); + return 1; + } - if (!IN6_IS_ADDR_LOOPBACK(&s_in6.sin6_addr) && - !IN6_IS_ADDR_LINKLOCAL(&s_in6.sin6_addr)) - bind_addr = &c->ip6.addr_out; + topif = uflow->f.pif[tosidx.side]; + if (topif != PIF_HOST) { + uint8_t frompif = uflow->f.pif[!tosidx.side]; - s = sock_l4(c, AF_INET6, EPOLL_TYPE_UDP, bind_addr, - bind_if, src, uref.u32); - if (s < 0) - return p->count - idx; + flow_err(uflow, "No support for forwarding UDP from %s to %s", + pif_name(frompif), pif_name(topif)); + return 1; + } + toside = &uflow->f.side[tosidx.side]; - udp_tap_map[V6][src].sock = s; - bitmap_set(udp_act[V6][UDP_ACT_TAP], src); - } + s = udp_at_sidx(tosidx)->s[tosidx.side]; + ASSERT(s >= 0); - udp_tap_map[V6][src].ts = now->tv_sec; - } + pif_sockaddr(c, &to_sa, &sl, topif, &toside->eaddr, toside->eport); for (i = 0; i < (int)p->count - idx; i++) { struct udphdr *uh_send; @@ -996,7 +977,7 @@ int udp_tap_handler(struct ctx *c, uint8_t pif, if (!uh_send) return p->count - idx; - mm[i].msg_hdr.msg_name = sa; + mm[i].msg_hdr.msg_name = &to_sa; mm[i].msg_hdr.msg_namelen = sl; if (len) { diff --git a/udp.h b/udp.h index 310f42fd..88417fb0 100644 --- a/udp.h +++ b/udp.h @@ -13,8 +13,8 @@ void udp_buf_sock_handler(const struct ctx *c, union epoll_ref ref, uint32_t events, const struct timespec *now); void udp_reply_sock_handler(const struct ctx *c, union epoll_ref ref, uint32_t events, const struct timespec *now); -int udp_tap_handler(struct ctx *c, uint8_t pif, sa_family_t af, - const void *saddr, const void *daddr, +int udp_tap_handler(const struct ctx *c, uint8_t pif, + sa_family_t af, const void *saddr, const void *daddr, const struct pool *p, int idx, const struct timespec *now); int udp_sock_init(const struct ctx *c, int ns, sa_family_t af, const void *addr, const char *ifname, in_port_t port); -- 2.45.2

Now that UDP datagrams are all directed via the flow table, we no longer use the udp_tap_map[ or udp_act[] arrays. Remove them and connected code. Signed-off-by: David Gibson --- udp.c | 92 +---------------------------------------------------------- 1 file changed, 1 insertion(+), 91 deletions(-) diff --git a/udp.c b/udp.c index 7d63faf6..e1cd9921 100644 --- a/udp.c +++ b/udp.c @@ -100,38 +100,10 @@ #define UDP_CONN_TIMEOUT 180 /* s, timeout for ephemeral or local bind */ #define UDP_MAX_FRAMES 32 /* max # of frames to receive at once */ -/** - * struct udp_tap_port - Port tracking based on tap-facing source port - * @sock: Socket bound to source port used as index - * @flags: Flags for recent activity type seen from/to port - * @ts: Activity timestamp from tap, used for socket aging - */ -struct udp_tap_port { - int sock; - uint8_t flags; -#define PORT_LOCAL BIT(0) /* Port was contacted from local address */ -#define PORT_LOOPBACK BIT(1) /* Port was contacted from loopback address */ -#define PORT_GUA BIT(2) /* Port was contacted from global unicast */ -#define PORT_DNS_FWD BIT(3) /* Port used as source for DNS remapped query */ - - time_t ts; -}; - -/* Port tracking, arrays indexed by packet source port (host order) */ -static struct udp_tap_port udp_tap_map [IP_VERSIONS][NUM_PORTS]; - /* "Spliced" sockets indexed by bound port (host order) */ static int udp_splice_ns [IP_VERSIONS][NUM_PORTS]; static int udp_splice_init[IP_VERSIONS][NUM_PORTS]; -enum udp_act_type { - UDP_ACT_TAP, - UDP_ACT_TYPE_MAX, -}; - -/* Activity-based aging for bindings */ -static uint8_t udp_act[IP_VERSIONS][UDP_ACT_TYPE_MAX][DIV_ROUND_UP(NUM_PORTS, 8)]; - /* Static buffers */ /** @@ -214,7 +186,6 @@ void udp_portmap_clear(void) unsigned i; for (i = 0; i < NUM_PORTS; i++) { - udp_tap_map[V4][i].sock = udp_tap_map[V6][i].sock = -1; udp_splice_ns[V4][i] = udp_splice_ns[V6][i] = -1; udp_splice_init[V4][i] = udp_splice_init[V6][i] = -1; } @@ -952,7 +923,6 @@ int udp_sock_init(const struct ctx *c, int ns, sa_family_t af, r4 = s = sock_l4(c, AF_INET, EPOLL_TYPE_UDP, addr, ifname, port, uref.u32); - udp_tap_map[V4][port].sock = s < 0 ? -1 : s; udp_splice_init[V4][port] = s < 0 ? -1 : s; } else { r4 = s = sock_l4(c, AF_INET, EPOLL_TYPE_UDP, @@ -969,7 +939,6 @@ int udp_sock_init(const struct ctx *c, int ns, sa_family_t af, r6 = s = sock_l4(c, AF_INET6, EPOLL_TYPE_UDP, addr, ifname, port, uref.u32); - udp_tap_map[V6][port].sock = s < 0 ? -1 : s; udp_splice_init[V6][port] = s < 0 ? -1 : s; } else { r6 = s = sock_l4(c, AF_INET6, EPOLL_TYPE_UDP, @@ -1005,43 +974,6 @@ static void udp_splice_iov_init(void) } } -/** - * udp_timer_one() - Handler for timed events on one port - * @c: Execution context - * @v6: Set for IPv6 connections - * @type: Socket type - * @port: Port number, host order - * @now: Current timestamp - */ -static void udp_timer_one(struct ctx *c, int v6, enum udp_act_type type, - in_port_t port, const struct timespec *now) -{ - struct udp_tap_port *tp; - int *sockp = NULL; - - switch (type) { - case UDP_ACT_TAP: - tp = &udp_tap_map[v6 ? V6 : V4][port]; - - if (now->tv_sec - tp->ts > UDP_CONN_TIMEOUT) { - sockp = &tp->sock; - tp->flags = 0; - } - - break; - default: - return; - } - - if (sockp && *sockp >= 0) { - int s = *sockp; - *sockp = -1; - epoll_ctl(c->epollfd, EPOLL_CTL_DEL, s, NULL); - close(s); - bitmap_clear(udp_act[v6 ? V6 : V4][type], port); - } -} - /** * udp_port_rebind() - Rebind ports to match forward maps * @c: Execution context @@ -1126,9 +1058,7 @@ bool udp_flow_timer(const struct ctx *c, const struct udp_flow *uflow, */ void udp_timer(struct ctx *c, const struct timespec *now) { - int n, t, v6 = 0; - unsigned int i; - long *word, tmp; + (void)now; if (c->mode == MODE_PASTA) { if (c->udp.fwd_out.f.mode == FWD_AUTO) { @@ -1143,26 +1073,6 @@ void udp_timer(struct ctx *c, const struct timespec *now) udp_port_rebind(c, false); } } - - if (!c->ifi4) - v6 = 1; -v6: - for (t = 0; t < UDP_ACT_TYPE_MAX; t++) { - word = (long *)udp_act[v6 ? V6 : V4][t]; - for (i = 0; i < ARRAY_SIZE(udp_act[0][0]); - i += sizeof(long), word++) { - tmp = *word; - while ((n = ffsl(tmp))) { - tmp &= ~(1UL << (n - 1)); - udp_timer_one(c, v6, t, i * 8 + n - 1, now); - } - } - } - - if (!v6 && c->ifi6) { - v6 = 1; - goto v6; - } } /** -- 2.45.2

EPOLL_TYPE_UDP is now only used for "listening" sockets; long lived sockets which can initiate new flows. Rename to EPOLL_TYPE_UDP_LISTEN and associated functions to match. Along with that, remove the .orig field from union udp_listen_epoll_ref, since it is now always true. Signed-off-by: David Gibson --- epoll_type.h | 4 ++-- passt.c | 6 +++--- passt.h | 2 +- udp.c | 25 +++++++++++-------------- udp.h | 12 +++++------- util.c | 2 +- 6 files changed, 23 insertions(+), 28 deletions(-) diff --git a/epoll_type.h b/epoll_type.h index 7a752ed1..0ad1efa0 100644 --- a/epoll_type.h +++ b/epoll_type.h @@ -20,8 +20,8 @@ enum epoll_type { EPOLL_TYPE_TCP_LISTEN, /* timerfds used for TCP timers */ EPOLL_TYPE_TCP_TIMER, - /* UDP sockets */ - EPOLL_TYPE_UDP, + /* UDP "listening" sockets */ + EPOLL_TYPE_UDP_LISTEN, /* UDP socket for replies on a specific flow */ EPOLL_TYPE_UDP_REPLY, /* ICMP/ICMPv6 ping sockets */ diff --git a/passt.c b/passt.c index f9405bee..eed74ec9 100644 --- a/passt.c +++ b/passt.c @@ -66,7 +66,7 @@ char *epoll_type_str[] = { [EPOLL_TYPE_TCP_SPLICE] = "connected spliced TCP socket", [EPOLL_TYPE_TCP_LISTEN] = "listening TCP socket", [EPOLL_TYPE_TCP_TIMER] = "TCP timer", - [EPOLL_TYPE_UDP] = "UDP socket", + [EPOLL_TYPE_UDP_LISTEN] = "listening UDP socket", [EPOLL_TYPE_UDP_REPLY] = "UDP reply socket", [EPOLL_TYPE_PING] = "ICMP/ICMPv6 ping socket", [EPOLL_TYPE_NSQUIT_INOTIFY] = "namespace inotify watch", @@ -347,8 +347,8 @@ loop: case EPOLL_TYPE_TCP_TIMER: tcp_timer_handler(&c, ref); break; - case EPOLL_TYPE_UDP: - udp_buf_sock_handler(&c, ref, eventmask, &now); + case EPOLL_TYPE_UDP_LISTEN: + udp_listen_sock_handler(&c, ref, eventmask, &now); break; case EPOLL_TYPE_UDP_REPLY: udp_reply_sock_handler(&c, ref, eventmask, &now); diff --git a/passt.h b/passt.h index 0d76b498..4cc2b6f0 100644 --- a/passt.h +++ b/passt.h @@ -48,7 +48,7 @@ union epoll_ref { uint32_t flow; flow_sidx_t flowside; union tcp_listen_epoll_ref tcp_listen; - union udp_epoll_ref udp; + union udp_listen_epoll_ref udp; uint32_t data; int nsdir_fd; }; diff --git a/udp.c b/udp.c index 8affcf12..58cf6b93 100644 --- a/udp.c +++ b/udp.c @@ -420,10 +420,7 @@ static flow_sidx_t udp_flow_from_sock(const struct ctx *c, union epoll_ref ref, union flow *flow; flow_sidx_t sidx; - ASSERT(ref.type == EPOLL_TYPE_UDP); - - if (!ref.udp.orig) - return FLOW_SIDX_NONE; + ASSERT(ref.type == EPOLL_TYPE_UDP_LISTEN); sidx = flow_lookup_sa(c, IPPROTO_UDP, ref.udp.pif, &meta->s_in, ref.udp.port); if ((uflow = udp_at_sidx(sidx))) { @@ -604,7 +601,7 @@ int udp_sock_recv(const struct ctx *c, int s, uint32_t events, } /** - * udp_buf_sock_handler() - Handle new data from socket + * udp_listen_sock_handler() - Handle new data from socket * @c: Execution context * @ref: epoll reference * @events: epoll events bitmap @@ -612,8 +609,8 @@ int udp_sock_recv(const struct ctx *c, int s, uint32_t events, * * #syscalls recvmmsg */ -void udp_buf_sock_handler(const struct ctx *c, union epoll_ref ref, uint32_t events, - const struct timespec *now) +void udp_listen_sock_handler(const struct ctx *c, union epoll_ref ref, + uint32_t events, const struct timespec *now) { struct mmsghdr *mmh_recv = ref.udp.v6 ? udp6_mh_recv : udp4_mh_recv; int n, i; @@ -881,7 +878,7 @@ int udp_tap_handler(const struct ctx *c, uint8_t pif, int udp_sock_init(const struct ctx *c, int ns, sa_family_t af, const void *addr, const char *ifname, in_port_t port) { - union udp_epoll_ref uref = { .orig = true, .port = port }; + union udp_listen_epoll_ref uref = { .port = port }; int s, r4 = FD_REF_MAX + 1, r6 = FD_REF_MAX + 1; if (ns) @@ -893,12 +890,12 @@ int udp_sock_init(const struct ctx *c, int ns, sa_family_t af, uref.v6 = 0; if (!ns) { - r4 = s = sock_l4(c, AF_INET, EPOLL_TYPE_UDP, addr, - ifname, port, uref.u32); + r4 = s = sock_l4(c, AF_INET, EPOLL_TYPE_UDP_LISTEN, + addr, ifname, port, uref.u32); udp_splice_init[V4][port] = s < 0 ? -1 : s; } else { - r4 = s = sock_l4(c, AF_INET, EPOLL_TYPE_UDP, + r4 = s = sock_l4(c, AF_INET, EPOLL_TYPE_UDP_LISTEN, &in4addr_loopback, ifname, port, uref.u32); udp_splice_ns[V4][port] = s < 0 ? -1 : s; @@ -909,12 +906,12 @@ int udp_sock_init(const struct ctx *c, int ns, sa_family_t af, uref.v6 = 1; if (!ns) { - r6 = s = sock_l4(c, AF_INET6, EPOLL_TYPE_UDP, addr, - ifname, port, uref.u32); + r6 = s = sock_l4(c, AF_INET6, EPOLL_TYPE_UDP_LISTEN, + addr, ifname, port, uref.u32); udp_splice_init[V6][port] = s < 0 ? -1 : s; } else { - r6 = s = sock_l4(c, AF_INET6, EPOLL_TYPE_UDP, + r6 = s = sock_l4(c, AF_INET6, EPOLL_TYPE_UDP_LISTEN, &in6addr_loopback, ifname, port, uref.u32); udp_splice_ns[V6][port] = s < 0 ? -1 : s; diff --git a/udp.h b/udp.h index ba803d51..18a86892 100644 --- a/udp.h +++ b/udp.h @@ -9,8 +9,8 @@ #define UDP_TIMER_INTERVAL 1000 /* ms */ void udp_portmap_clear(void); -void udp_buf_sock_handler(const struct ctx *c, union epoll_ref ref, - uint32_t events, const struct timespec *now); +void udp_listen_sock_handler(const struct ctx *c, union epoll_ref ref, + uint32_t events, const struct timespec *now); void udp_reply_sock_handler(const struct ctx *c, union epoll_ref ref, uint32_t events, const struct timespec *now); int udp_tap_handler(const struct ctx *c, uint8_t pif, @@ -23,21 +23,19 @@ void udp_timer(struct ctx *c, const struct timespec *now); void udp_update_l2_buf(const unsigned char *eth_d, const unsigned char *eth_s); /** - * union udp_epoll_ref - epoll reference portion for TCP connections + * union udp_listen_epoll_ref - epoll reference for "listening" UDP sockets * @port: Source port for connected sockets, bound port otherwise * @pif: pif for this socket * @bound: Set if this file descriptor is a bound socket * @splice: Set if descriptor packets to be "spliced" - * @orig: Set if a spliced socket which can originate "connections" * @v6: Set for IPv6 sockets or connections * @u32: Opaque u32 value of reference */ -union udp_epoll_ref { +union udp_listen_epoll_ref { struct { in_port_t port; uint8_t pif; - bool orig:1, - v6:1; + bool v6:1; }; uint32_t u32; }; diff --git a/util.c b/util.c index 7c57ab15..82b0028b 100644 --- a/util.c +++ b/util.c @@ -60,7 +60,7 @@ int sock_l4_sa(const struct ctx *c, enum epoll_type type, proto = IPPROTO_TCP; socktype = SOCK_STREAM | SOCK_NONBLOCK; break; - case EPOLL_TYPE_UDP: + case EPOLL_TYPE_UDP_LISTEN: case EPOLL_TYPE_UDP_REPLY: proto = IPPROTO_UDP; socktype = SOCK_DGRAM | SOCK_NONBLOCK; -- 2.45.2