From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from gandalf.ozlabs.org (mail.ozlabs.org [IPv6:2404:9400:2221:ea00::3]) by passt.top (Postfix) with ESMTPS id AA4B75A027D for ; Wed, 16 Nov 2022 05:42:23 +0100 (CET) Received: by gandalf.ozlabs.org (Postfix, from userid 1007) id 4NBr4R2bdxz4xwp; Wed, 16 Nov 2022 15:42:15 +1100 (AEDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gibson.dropbear.id.au; s=201602; t=1668573735; bh=ZLOcQevka0M2TOFywD3Ag5WscqiKX09F8Cc6XrK4pnI=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=lWA2DIpoeSPk+V//RclQLjTvOWevFqDAiVmgvesf1m5Oi12Q2LDns1hGsy/vMLcIY WMJ9YxcrevdrmMRTGQ5dayz+lDaWgnKILKEXd45iWECfOdejkgLC0hr4Li+sDtINWS CbwqVcx3hJMbznD3C35rLlLxcFxGAqrkRP38epmI= From: David Gibson To: passt-dev@passt.top, Stefano Brivio Subject: [PATCH 19/32] inany: Helper functions for handling addresses which could be IPv4 or IPv6 Date: Wed, 16 Nov 2022 15:41:59 +1100 Message-Id: <20221116044212.3876516-20-david@gibson.dropbear.id.au> X-Mailer: git-send-email 2.38.1 In-Reply-To: <20221116044212.3876516-1-david@gibson.dropbear.id.au> References: <20221116044212.3876516-1-david@gibson.dropbear.id.au> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Message-ID-Hash: YJT4GS33PGV4U6H2A2KZGP63O7ME4AL2 X-Message-ID-Hash: YJT4GS33PGV4U6H2A2KZGP63O7ME4AL2 X-MailFrom: dgibson@gandalf.ozlabs.org X-Mailman-Rule-Misses: dmarc-mitigation; no-senders; approved; emergency; loop; banned-address; member-moderation; nonmember-moderation; administrivia; implicit-dest; max-recipients; max-size; news-moderation; no-subject; digests; suspicious-header CC: David Gibson X-Mailman-Version: 3.3.3 Precedence: list List-Id: Development discussion and patches for passt Archived-At: Archived-At: List-Archive: List-Archive: List-Help: List-Owner: List-Post: List-Subscribe: List-Unsubscribe: struct tcp_conn stores an address which could be IPv6 or IPv4 using a union. We can do this without an additional tag by encoding IPv4 addresses as IPv4-mapped IPv6 addresses. This approach is useful wider than the specific place in tcp_conn, so expose a new 'union inany_addr' like this from a new inany.h. Along with that create a number of helper functions to make working with these "inany" addresses easier. Signed-off-by: David Gibson --- Makefile | 6 ++-- inany.h | 68 ++++++++++++++++++++++++++++++++++++++++ tcp.c | 88 +++++++++++++++++++++++++--------------------------- tcp_conn.h | 15 ++------- tcp_splice.c | 1 + 5 files changed, 117 insertions(+), 61 deletions(-) create mode 100644 inany.h diff --git a/Makefile b/Makefile index 9046b0b..ca453aa 100644 --- a/Makefile +++ b/Makefile @@ -44,9 +44,9 @@ SRCS = $(PASST_SRCS) $(QRAP_SRCS) MANPAGES = passt.1 pasta.1 qrap.1 PASST_HEADERS = arch.h arp.h checksum.h conf.h dhcp.h dhcpv6.h icmp.h \ - isolation.h lineread.h log.h ndp.h netlink.h packet.h passt.h pasta.h \ - pcap.h port_fwd.h siphash.h tap.h tcp.h tcp_conn.h tcp_splice.h udp.h \ - util.h + inany.h isolation.h lineread.h log.h ndp.h netlink.h packet.h passt.h \ + pasta.h pcap.h port_fwd.h siphash.h tap.h tcp.h tcp_conn.h \ + tcp_splice.h udp.h util.h HEADERS = $(PASST_HEADERS) seccomp.h # On gcc 11 and 12, with -O2 and -flto, tcp_hash() and siphash_20b(), if diff --git a/inany.h b/inany.h new file mode 100644 index 0000000..4e53da9 --- /dev/null +++ b/inany.h @@ -0,0 +1,68 @@ +/* SPDX-License-Identifier: AGPL-3.0-or-later + * Copyright Red Hat + * Author: David Gibson + * + * inany.h - Types and helpers for handling addresses which could be + * IPv6 or IPv4 (encoded as IPv4-mapped IPv6 addresses) + */ + +#include + +/** union inany_addr - Represents either an IPv4 or IPv6 address + * @a6: Address as an IPv6 address, may be IPv4-mapped + * @_v4._zero: All zero-bits for an IPv4 address + * @_v4._one: All one-bits for an IPv4 address + * @_v4.a4: If @a6 is an IPv4 mapped address, this is the raw IPv4 address + * + * Fields starting with _ shouldn't be accessed except via helpers. + */ +union inany_addr { + struct in6_addr a6; + struct { + uint8_t _zero[10]; + uint8_t _one[2]; + struct in_addr a4; + } _v4mapped; +}; + +/** inany_v4 - Extract IPv4 address, if present, from IPv[46] address + * @addr: IPv4 or IPv6 address + * + * Return: IPv4 address if @addr is IPv4, NULL otherwise + */ +static inline const struct in_addr *inany_v4(const union inany_addr *addr) +{ + if (!IN6_IS_ADDR_V4MAPPED(&addr->a6)) + return NULL; + return &addr->_v4mapped.a4; +} + +/** inany_equals - Compare two IPv[46] addresses + * @a, @b: IPv[46] addresses + * + * Return: true if @a and @b are the same address + */ +static inline bool inany_equals(const union inany_addr *a, + const union inany_addr *b) +{ + return IN6_ARE_ADDR_EQUAL(&a->a6, &b->a6); +} + +/** inany_from_af - Set IPv[46] address from IPv4 or IPv6 address + * @aa: Pointer to store IPv[46] address + * @af: Address family of @addr + * @addr: struct in_addr (IPv4) or struct in6_addr (IPv6) + */ +static inline void inany_from_af(union inany_addr *aa, int af, const void *addr) +{ + if (af == AF_INET6) { + aa->a6 = *((struct in6_addr *)addr); + } else if (af == AF_INET) { + memset(&aa->_v4mapped._zero, 0, sizeof(aa->_v4mapped._zero)); + memset(&aa->_v4mapped._one, 0xff, sizeof(aa->_v4mapped._one)); + aa->_v4mapped.a4 = *((struct in_addr *)addr); + } else { + /* Not valid to call with other address families */ + assert(0); + } +} diff --git a/tcp.c b/tcp.c index 7686766..4040198 100644 --- a/tcp.c +++ b/tcp.c @@ -301,6 +301,7 @@ #include "conf.h" #include "tcp_splice.h" #include "log.h" +#include "inany.h" #include "tcp_conn.h" @@ -404,7 +405,7 @@ struct tcp6_l2_head { /* For MSS6 macro: keep in sync with tcp6_l2_buf_t */ #define OPT_SACK 5 #define OPT_TS 8 -#define CONN_V4(conn) IN6_IS_ADDR_V4MAPPED(&conn->a.a6) +#define CONN_V4(conn) (!!inany_v4(&(conn)->addr)) #define CONN_V6(conn) (!CONN_V4(conn)) #define CONN_IS_CLOSING(conn) \ ((conn->events & ESTABLISHED) && \ @@ -438,7 +439,7 @@ static int tcp_sock_init_ext [NUM_PORTS][IP_VERSIONS]; static int tcp_sock_ns [NUM_PORTS][IP_VERSIONS]; /* Table of destinations with very low RTT (assumed to be local), LRU */ -static struct in6_addr low_rtt_dst[LOW_RTT_TABLE_SIZE]; +static union inany_addr low_rtt_dst[LOW_RTT_TABLE_SIZE]; /* Static buffers */ @@ -861,7 +862,7 @@ static int tcp_rtt_dst_low(const struct tcp_tap_conn *conn) int i; for (i = 0; i < LOW_RTT_TABLE_SIZE; i++) - if (IN6_ARE_ADDR_EQUAL(&conn->a.a6, low_rtt_dst + i)) + if (inany_equals(&conn->addr, low_rtt_dst + i)) return 1; return 0; @@ -883,7 +884,7 @@ static void tcp_rtt_dst_check(const struct tcp_tap_conn *conn, return; for (i = 0; i < LOW_RTT_TABLE_SIZE; i++) { - if (IN6_ARE_ADDR_EQUAL(&conn->a.a6, low_rtt_dst + i)) + if (inany_equals(&conn->addr, low_rtt_dst + i)) return; if (hole == -1 && IN6_IS_ADDR_UNSPECIFIED(low_rtt_dst + i)) hole = i; @@ -895,10 +896,10 @@ static void tcp_rtt_dst_check(const struct tcp_tap_conn *conn, if (hole == -1) return; - memcpy(low_rtt_dst + hole++, &conn->a.a6, sizeof(conn->a.a6)); + low_rtt_dst[hole++] = conn->addr; if (hole == LOW_RTT_TABLE_SIZE) hole = 0; - memcpy(low_rtt_dst + hole, &in6addr_any, sizeof(conn->a.a6)); + inany_from_af(low_rtt_dst + hole, AF_INET6, &in6addr_any); #else (void)conn; (void)tinfo; @@ -1187,13 +1188,14 @@ static int tcp_hash_match(const struct tcp_tap_conn *conn, int af, const void *addr, in_port_t tap_port, in_port_t sock_port) { - if (af == AF_INET && CONN_V4(conn) && - !memcmp(&conn->a.a4.a, addr, sizeof(conn->a.a4.a)) && + const struct in_addr *a4 = inany_v4(&conn->addr); + + if (af == AF_INET && a4 && !memcmp(a4, addr, sizeof(*a4)) && conn->tap_port == tap_port && conn->sock_port == sock_port) return 1; if (af == AF_INET6 && - IN6_ARE_ADDR_EQUAL(&conn->a.a6, addr) && + IN6_ARE_ADDR_EQUAL(&conn->addr.a6, addr) && conn->tap_port == tap_port && conn->sock_port == sock_port) return 1; @@ -1253,11 +1255,13 @@ static unsigned int tcp_hash(const struct ctx *c, int af, const void *addr, static unsigned int tcp_conn_hash(const struct ctx *c, const struct tcp_tap_conn *conn) { - if (CONN_V6(conn)) - return tcp_hash(c, AF_INET6, &conn->a.a6, + const struct in_addr *a4 = inany_v4(&conn->addr); + + if (a4) + return tcp_hash(c, AF_INET, a4, conn->tap_port, conn->sock_port); else - return tcp_hash(c, AF_INET, &conn->a.a4.a, + return tcp_hash(c, AF_INET6, &conn->addr.a6, conn->tap_port, conn->sock_port); } @@ -1582,6 +1586,7 @@ static size_t tcp_l2_buf_fill_headers(const struct ctx *c, void *p, size_t plen, const uint16_t *check, uint32_t seq) { + const struct in_addr *a4 = inany_v4(&conn->addr); size_t ip_len, eth_len; #define SET_TCP_HEADER_COMMON_V4_V6(b, conn, seq) \ @@ -1599,13 +1604,33 @@ do { \ } \ } while (0) - if (CONN_V6(conn)) { + if (a4) { + struct tcp4_l2_buf_t *b = (struct tcp4_l2_buf_t *)p; + + ip_len = plen + sizeof(struct iphdr) + sizeof(struct tcphdr); + b->iph.tot_len = htons(ip_len); + b->iph.saddr = a4->s_addr; + b->iph.daddr = c->ip4.addr_seen.s_addr; + + if (check) + b->iph.check = *check; + else + tcp_update_check_ip4(b); + + SET_TCP_HEADER_COMMON_V4_V6(b, conn, seq); + + tcp_update_check_tcp4(b); + + eth_len = ip_len + sizeof(struct ethhdr); + if (c->mode == MODE_PASST) + b->vnet_len = htonl(eth_len); + } else { struct tcp6_l2_buf_t *b = (struct tcp6_l2_buf_t *)p; ip_len = plen + sizeof(struct ipv6hdr) + sizeof(struct tcphdr); b->ip6h.payload_len = htons(plen + sizeof(struct tcphdr)); - b->ip6h.saddr = conn->a.a6; + b->ip6h.saddr = conn->addr.a6; if (IN6_IS_ADDR_LINKLOCAL(&b->ip6h.saddr)) b->ip6h.daddr = c->ip6.addr_ll_seen; else @@ -1621,26 +1646,6 @@ do { \ b->ip6h.flow_lbl[1] = (conn->sock >> 8) & 0xff; b->ip6h.flow_lbl[2] = (conn->sock >> 0) & 0xff; - eth_len = ip_len + sizeof(struct ethhdr); - if (c->mode == MODE_PASST) - b->vnet_len = htonl(eth_len); - } else { - struct tcp4_l2_buf_t *b = (struct tcp4_l2_buf_t *)p; - - ip_len = plen + sizeof(struct iphdr) + sizeof(struct tcphdr); - b->iph.tot_len = htons(ip_len); - b->iph.saddr = conn->a.a4.a.s_addr; - b->iph.daddr = c->ip4.addr_seen.s_addr; - - if (check) - b->iph.check = *check; - else - tcp_update_check_ip4(b); - - SET_TCP_HEADER_COMMON_V4_V6(b, conn, seq); - - tcp_update_check_tcp4(b); - eth_len = ip_len + sizeof(struct ethhdr); if (c->mode == MODE_PASST) b->vnet_len = htonl(eth_len); @@ -2144,18 +2149,14 @@ static void tcp_conn_from_tap(struct ctx *c, int af, const void *addr, if (!(conn->wnd_from_tap = (htons(th->window) >> conn->ws_from_tap))) conn->wnd_from_tap = 1; + inany_from_af(&conn->addr, af, addr); + if (af == AF_INET) { sa = (struct sockaddr *)&addr4; sl = sizeof(addr4); - - memset(&conn->a.a4.zero, 0, sizeof(conn->a.a4.zero)); - memset(&conn->a.a4.one, 0xff, sizeof(conn->a.a4.one)); - memcpy(&conn->a.a4.a, addr, sizeof(conn->a.a4.a)); } else { sa = (struct sockaddr *)&addr6; sl = sizeof(addr6); - - memcpy(&conn->a.a6, addr, sizeof(conn->a.a6)); } conn->sock_port = ntohs(th->dest); @@ -2808,7 +2809,7 @@ static void tcp_tap_conn_from_sock(struct ctx *c, union epoll_ref ref, memcpy(&sa6.sin6_addr, src, sizeof(*src)); } - memcpy(&conn->a.a6, &sa6.sin6_addr, sizeof(conn->a.a6)); + inany_from_af(&conn->addr, AF_INET6, &sa6.sin6_addr); conn->sock_port = ntohs(sa6.sin6_port); conn->tap_port = ref.r.p.tcp.tcp.index; @@ -2824,15 +2825,12 @@ static void tcp_tap_conn_from_sock(struct ctx *c, union epoll_ref ref, memcpy(&sa4, sa, sizeof(sa4)); - memset(&conn->a.a4.zero, 0, sizeof(conn->a.a4.zero)); - memset(&conn->a.a4.one, 0xff, sizeof(conn->a.a4.one)); - if (IN4_IS_ADDR_LOOPBACK(&sa4.sin_addr) || IN4_IS_ADDR_UNSPECIFIED(&sa4.sin_addr) || IN4_ARE_ADDR_EQUAL(&sa4.sin_addr, &c->ip4.addr_seen)) sa4.sin_addr = c->ip4.gw; - conn->a.a4.a = sa4.sin_addr; + inany_from_af(&conn->addr, AF_INET, &sa4.sin_addr); conn->sock_port = ntohs(sa4.sin_port); conn->tap_port = ref.r.p.tcp.tcp.index; diff --git a/tcp_conn.h b/tcp_conn.h index 4bffe9a..bf50e1c 100644 --- a/tcp_conn.h +++ b/tcp_conn.h @@ -35,10 +35,7 @@ extern const char *tcp_common_flag_str[]; * @ws_to_tap: Window scaling factor advertised to tap/guest * @sndbuf: Sending buffer in kernel, rounded to 2 ^ SNDBUF_BITS * @seq_dup_ack_approx: Last duplicate ACK number sent to tap - * @a.a6: IPv6 remote address, can be IPv4-mapped - * @a.a4.zero: Zero prefix for IPv4-mapped, see RFC 6890, Table 20 - * @a.a4.one: Ones prefix for IPv4-mapped - * @a.a4.a: IPv4 address + * @addr: Remote address (IPv4 or IPv6) * @tap_port: Guest-facing tap port * @sock_port: Remote, socket-facing port * @wnd_from_tap: Last window size from tap, unscaled (as received) @@ -108,15 +105,7 @@ struct tcp_tap_conn { uint8_t seq_dup_ack_approx; - union { - struct in6_addr a6; - struct { - uint8_t zero[10]; - uint8_t one[2]; - struct in_addr a; - } a4; - } a; - + union inany_addr addr; in_port_t tap_port; in_port_t sock_port; diff --git a/tcp_splice.c b/tcp_splice.c index 2852e76..30ab0eb 100644 --- a/tcp_splice.c +++ b/tcp_splice.c @@ -52,6 +52,7 @@ #include "passt.h" #include "log.h" #include "tcp_splice.h" +#include "inany.h" #include "tcp_conn.h" -- 2.38.1