From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mail.ozlabs.org (mail.ozlabs.org [IPv6:2404:9400:2221:ea00::3]) by passt.top (Postfix) with ESMTPS id 15A775A031A for ; Thu, 18 Jul 2024 07:27:03 +0200 (CEST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gibson.dropbear.id.au; s=202312; t=1721280418; bh=101Hkmj/FOidjOvkVRRLQJT6/uzsxx2ee3Bvf94IyD8=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=piFxNEsnWoRFyjyDX83jn7YwDdYcb47eICGjCahY5rRe7FPcPQanmTzjM7+cROfoa qkzbz8pd+0W+qnsZ/hHqygEbzPz4DVDJA0lYyguQfOpqcNtSf/tkbyE/MkjfaslgXq sdG/qGk7bRSZKby1OcVrVeg7v/H2gRVFFRhVmzmyFdPeaEf7UDMhxmeJLUHhAdd/J3 iwAs2lrzFlW4uNPaUrpzfyzAoJZiARsF9Wyl04btPH/zE4T4m4A6YB3kcbDinSM6+V A6nQii+ZnLg1CdZGQOluvsGY8oDmgUXdK1qoRmnQ4o3ffVwtriwhIT1R3wZdT5svXq ui3W1iCpslQFA== Received: by gandalf.ozlabs.org (Postfix, from userid 1007) id 4WPhBV5lkqz4x0n; Thu, 18 Jul 2024 15:26:58 +1000 (AEST) From: David Gibson To: Stefano Brivio , passt-dev@passt.top Subject: [PATCH v8 04/27] tcp: Obtain guest address from flowside Date: Thu, 18 Jul 2024 15:26:30 +1000 Message-ID: <20240718052653.3241585-5-david@gibson.dropbear.id.au> X-Mailer: git-send-email 2.45.2 In-Reply-To: <20240718052653.3241585-1-david@gibson.dropbear.id.au> References: <20240718052653.3241585-1-david@gibson.dropbear.id.au> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Message-ID-Hash: CATL56IQMDSJJDIRXPALXKMCXVGLNEVZ X-Message-ID-Hash: CATL56IQMDSJJDIRXPALXKMCXVGLNEVZ 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: jmaloy@redhat.com, David Gibson X-Mailman-Version: 3.3.8 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: 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 3d3df4c9..bac72c02 100644 --- a/tcp.c +++ b/tcp.c @@ -1059,7 +1059,6 @@ 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 @@ -1070,27 +1069,26 @@ 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); @@ -1103,7 +1101,6 @@ 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 @@ -1114,8 +1111,7 @@ 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) @@ -1125,10 +1121,7 @@ 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; @@ -1149,7 +1142,6 @@ 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 @@ -1158,8 +1150,7 @@ 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) { @@ -1167,13 +1158,13 @@ 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); @@ -1476,17 +1467,11 @@ 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 11dce021..9b198984 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