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 4AA745A031E for ; Thu, 18 Jul 2024 07:27:07 +0200 (CEST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gibson.dropbear.id.au; s=202312; t=1721280418; bh=WtAjakQdZkdnsexFK3W2J5MSjv0TZUBdo8TppXCa3+A=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=ecPmnOue+uNQ0GcOHSH29t/R+O9vjtqkpC3pI7SdaUlQqqcWaf29r4gHGcgKCDHmp 0d2w3x+UZwOsoCy12LPMsQchpoiYD0XH2EUZTXSLTadB8yMcWvX/Kfw/YDOrf4vWAX 4i6YPwjsdJ1fS18/tjYyUTAxK+o0GPCYuVhy2jjTgpigE2qVqlRVfhZffUsJc9WzaI QYptsbSvfSRebRjNjqgqdRapFZDVY2wR/IoQkrE269GRuqfEWciPnzbnYt050UiOqf E6t1zXINf+SuywlcB8mk2IeLB8m+qCei0z0hEpZNMEuFndO8FnkiMDRnz7DX2sj7nq c8J9zoXmToXuQ== Received: by gandalf.ozlabs.org (Postfix, from userid 1007) id 4WPhBV6LRgz4x3n; Thu, 18 Jul 2024 15:26:58 +1000 (AEST) From: David Gibson To: Stefano Brivio , passt-dev@passt.top Subject: [PATCH v8 10/27] tcp: Re-use flow hash for initial sequence number generation Date: Thu, 18 Jul 2024 15:26:36 +1000 Message-ID: <20240718052653.3241585-11-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: JHJTTMZT7TTGSKGPNRFKRA5GVLENQ3NA X-Message-ID-Hash: JHJTTMZT7TTGSKGPNRFKRA5GVLENQ3NA 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: 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 b291f254..8eea8615 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.sidei, b); + + return hash; } /** diff --git a/flow.h b/flow.h index fcb4121d..e3a778a7 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.flowi == b.flowi) && (a.sidei == b.sidei); } -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 09648551..b6eca5d8 100644 --- a/tcp.c +++ b/tcp.c @@ -1294,28 +1294,16 @@ 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; } /** @@ -1488,6 +1476,7 @@ 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())) @@ -1584,11 +1573,10 @@ 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)) { @@ -2110,6 +2098,7 @@ 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); @@ -2133,8 +2122,8 @@ 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