public inbox for passt-dev@passt.top
 help / color / mirror / code / Atom feed
From: David Gibson <david@gibson.dropbear.id.au>
To: Stefano Brivio <sbrivio@redhat.com>, passt-dev@passt.top
Cc: jmaloy@redhat.com, David Gibson <david@gibson.dropbear.id.au>
Subject: [PATCH v8 10/27] tcp: Re-use flow hash for initial sequence number generation
Date: Thu, 18 Jul 2024 15:26:36 +1000	[thread overview]
Message-ID: <20240718052653.3241585-11-david@gibson.dropbear.id.au> (raw)
In-Reply-To: <20240718052653.3241585-1-david@gibson.dropbear.id.au>

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 <david@gibson.dropbear.id.au>
---
 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;
 
-- 
@@ -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


  parent reply	other threads:[~2024-07-18  5:27 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-07-18  5:26 [PATCH v8 00/27] Unified flow table David Gibson
2024-07-18  5:26 ` [PATCH v8 01/27] flow: Common address information for initiating side David Gibson
2024-07-18  5:26 ` [PATCH v8 02/27] flow: Common address information for target side David Gibson
2024-07-18  5:26 ` [PATCH v8 03/27] tcp, flow: Remove redundant information, repack connection structures David Gibson
2024-07-18  5:26 ` [PATCH v8 04/27] tcp: Obtain guest address from flowside David Gibson
2024-07-18  5:26 ` [PATCH v8 05/27] tcp: Manage outbound address via flow table David Gibson
2024-07-18  5:26 ` [PATCH v8 06/27] tcp: Simplify endpoint validation using flowside information David Gibson
2024-07-18  5:26 ` [PATCH v8 07/27] tcp_splice: Eliminate SPLICE_V6 flag David Gibson
2024-07-18  5:26 ` [PATCH v8 08/27] tcp, flow: Replace TCP specific hash function with general flow hash David Gibson
2024-07-18  5:26 ` [PATCH v8 09/27] flow, tcp: Generalise TCP hash table to general flow hash table David Gibson
2024-07-18  5:26 ` David Gibson [this message]
2024-07-18  5:26 ` [PATCH v8 11/27] icmp: Remove redundant id field from flow table entry David Gibson
2024-07-18  5:26 ` [PATCH v8 12/27] icmp: Obtain destination addresses from the flowsides David Gibson
2024-07-18  5:26 ` [PATCH v8 13/27] icmp: Look up ping flows using flow hash David Gibson
2024-07-18  5:26 ` [PATCH v8 14/27] icmp: Eliminate icmp_id_map David Gibson
2024-07-18  5:26 ` [PATCH v8 15/27] flow: Helper to create sockets based on flowside David Gibson
2024-07-18  5:26 ` [PATCH v8 16/27] icmp: Manage outbound socket address via flow table David Gibson
2024-07-18  5:26 ` [PATCH v8 17/27] flow, tcp: Flow based NAT and port forwarding for TCP David Gibson
2024-07-18  5:26 ` [PATCH v8 18/27] flow, icmp: Use general flow forwarding rules for ICMP David Gibson
2024-07-18  5:26 ` [PATCH v8 19/27] fwd: Update flow forwarding logic for UDP David Gibson
2024-07-18  5:26 ` [PATCH v8 20/27] udp: Create flows for datagrams from originating sockets David Gibson
2024-07-18  5:26 ` [PATCH v8 21/27] udp: Handle "spliced" datagrams with per-flow sockets David Gibson
2024-07-18  5:26 ` [PATCH v8 22/27] udp: Remove obsolete splice tracking David Gibson
2024-07-18  5:26 ` [PATCH v8 23/27] udp: Find or create flows for datagrams from tap interface David Gibson
2024-07-18  5:26 ` [PATCH v8 24/27] udp: Direct datagrams from host to guest via flow table David Gibson
2024-07-18  5:26 ` [PATCH v8 25/27] udp: Remove obsolete socket tracking David Gibson
2024-07-18  5:26 ` [PATCH v8 26/27] udp: Remove rdelta port forwarding maps David Gibson
2024-07-18  5:26 ` [PATCH v8 27/27] udp: Rename UDP listening sockets David Gibson
2024-07-19 19:20 ` [PATCH v8 00/27] Unified flow table Stefano Brivio
2024-07-20  3:37   ` David Gibson

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20240718052653.3241585-11-david@gibson.dropbear.id.au \
    --to=david@gibson.dropbear.id.au \
    --cc=jmaloy@redhat.com \
    --cc=passt-dev@passt.top \
    --cc=sbrivio@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
Code repositories for project(s) associated with this public inbox

	https://passt.top/passt

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for IMAP folder(s).