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: David Gibson <david@gibson.dropbear.id.au>
Subject: [PATCH v3 09/15] tcp: Re-use flow hash for initial sequence number generation
Date: Thu, 21 Dec 2023 18:02:31 +1100	[thread overview]
Message-ID: <20231221070237.1422557-10-david@gibson.dropbear.id.au> (raw)
In-Reply-To: <20231221070237.1422557-1-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 a few
extras to slot the connection into the flow 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  | 35 +++++++++++++----------------------
 3 files changed, 38 insertions(+), 29 deletions(-)

diff --git a/flow.c b/flow.c
index 3d016c3..e4ea931 100644
--- a/flow.c
+++ b/flow.c
@@ -281,16 +281,16 @@ 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_eq(flow_hashtab[b], FLOW_SIDX_NONE) &&
@@ -300,17 +300,35 @@ 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), "hash table insert: bucket: %u", b);
+
+	return hash;
 }
 
 /**
diff --git a/flow.h b/flow.h
index adb5d44..e1aeeed 100644
--- a/flow.h
+++ b/flow.h
@@ -158,7 +158,7 @@ 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_hash_lookup(const struct ctx *c, uint8_t proto, uint8_t pif,
 			     int af, const void *eaddr, const void *faddr,
diff --git a/tcp.c b/tcp.c
index b6d046f..008eb0d 100644
--- a/tcp.c
+++ b/tcp.c
@@ -1578,28 +1578,16 @@ 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, eaddr, 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);
-	uint64_t hash;
-	uint32_t ns;
-
-	inany_siphash_feed(&state, &TAPFSIDE(conn)->faddr);
-	inany_siphash_feed(&state, &TAPFSIDE(conn)->eaddr);
-	hash = siphash_final(&state, 36,
-			     (uint64_t)TAPFSIDE(conn)->fport << 16 |
-			     TAPFSIDE(conn)->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;
 }
 
 /**
@@ -1758,6 +1746,7 @@ static void tcp_conn_from_tap(struct ctx *c,
 	const struct sockaddr *sa;
 	struct tcp_tap_conn *conn;
 	union flow *flow;
+	uint64_t hash;
 	socklen_t sl;
 	int s, mss;
 
@@ -1824,10 +1813,10 @@ static void tcp_conn_from_tap(struct ctx *c,
 	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);
-	conn->seq_ack_from_tap = conn->seq_to_tap;
+	hash = flow_hash_insert(c, FLOW_SIDX(conn, TAPSIDE));
 
-	flow_hash_insert(c, FLOW_SIDX(conn, TAPSIDE));
+	conn->seq_to_tap = tcp_init_seq(hash, now);
+	conn->seq_ack_from_tap = conn->seq_to_tap;
 
 	if (!bind(s, sa, sl)) {
 		tcp_rst(c, conn);	/* Nobody is listening then */
@@ -2518,6 +2507,8 @@ static void tcp_tap_conn_from_sock(struct ctx *c,
 				   struct tcp_tap_conn *conn, int s,
 				   const struct timespec *now)
 {
+	uint64_t hash;
+
 	ASSERT(flowside_complete(SOCKFSIDE(conn)));
 
 	conn->f.type = FLOW_TCP;
@@ -2544,8 +2535,8 @@ static void tcp_tap_conn_from_sock(struct ctx *c,
 	FLOW_FWD_DBG(conn, TAPSIDE);
 	ASSERT(flow_complete(&conn->f));
 
-	tcp_seq_init(c, conn, now);
-	flow_hash_insert(c, FLOW_SIDX(conn, TAPSIDE));
+	hash = flow_hash_insert(c, FLOW_SIDX(conn, TAPSIDE));
+	conn->seq_to_tap = tcp_init_seq(hash, now);
 
 	conn->seq_ack_from_tap = conn->seq_to_tap;
 
-- 
@@ -1578,28 +1578,16 @@ 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, eaddr, 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);
-	uint64_t hash;
-	uint32_t ns;
-
-	inany_siphash_feed(&state, &TAPFSIDE(conn)->faddr);
-	inany_siphash_feed(&state, &TAPFSIDE(conn)->eaddr);
-	hash = siphash_final(&state, 36,
-			     (uint64_t)TAPFSIDE(conn)->fport << 16 |
-			     TAPFSIDE(conn)->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;
 }
 
 /**
@@ -1758,6 +1746,7 @@ static void tcp_conn_from_tap(struct ctx *c,
 	const struct sockaddr *sa;
 	struct tcp_tap_conn *conn;
 	union flow *flow;
+	uint64_t hash;
 	socklen_t sl;
 	int s, mss;
 
@@ -1824,10 +1813,10 @@ static void tcp_conn_from_tap(struct ctx *c,
 	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);
-	conn->seq_ack_from_tap = conn->seq_to_tap;
+	hash = flow_hash_insert(c, FLOW_SIDX(conn, TAPSIDE));
 
-	flow_hash_insert(c, FLOW_SIDX(conn, TAPSIDE));
+	conn->seq_to_tap = tcp_init_seq(hash, now);
+	conn->seq_ack_from_tap = conn->seq_to_tap;
 
 	if (!bind(s, sa, sl)) {
 		tcp_rst(c, conn);	/* Nobody is listening then */
@@ -2518,6 +2507,8 @@ static void tcp_tap_conn_from_sock(struct ctx *c,
 				   struct tcp_tap_conn *conn, int s,
 				   const struct timespec *now)
 {
+	uint64_t hash;
+
 	ASSERT(flowside_complete(SOCKFSIDE(conn)));
 
 	conn->f.type = FLOW_TCP;
@@ -2544,8 +2535,8 @@ static void tcp_tap_conn_from_sock(struct ctx *c,
 	FLOW_FWD_DBG(conn, TAPSIDE);
 	ASSERT(flow_complete(&conn->f));
 
-	tcp_seq_init(c, conn, now);
-	flow_hash_insert(c, FLOW_SIDX(conn, TAPSIDE));
+	hash = flow_hash_insert(c, FLOW_SIDX(conn, TAPSIDE));
+	conn->seq_to_tap = tcp_init_seq(hash, now);
 
 	conn->seq_ack_from_tap = conn->seq_to_tap;
 
-- 
2.43.0


  parent reply	other threads:[~2023-12-21  7:02 UTC|newest]

Thread overview: 33+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-12-21  7:02 [PATCH v3 00/15] RFC: Unified flow table David Gibson
2023-12-21  7:02 ` [PATCH v3 01/15] flow: Common data structures for tracking flow addresses David Gibson
2024-01-13 22:50   ` Stefano Brivio
2024-01-16  6:14     ` David Gibson
2023-12-21  7:02 ` [PATCH v3 02/15] tcp, flow: Maintain guest side flow information David Gibson
2024-01-13 22:51   ` Stefano Brivio
2024-01-16  6:23     ` David Gibson
2023-12-21  7:02 ` [PATCH v3 03/15] tcp, flow: Maintain host " David Gibson
2023-12-21  7:02 ` [PATCH v3 04/15] tcp_splice,flow: Maintain flow information for spliced connections David Gibson
2024-01-17 19:59   ` Stefano Brivio
2024-01-18  1:01     ` David Gibson
2023-12-21  7:02 ` [PATCH v3 05/15] flow, tcp, tcp_splice: Uniform debug helpers for new flows David Gibson
2024-01-17 19:59   ` Stefano Brivio
2024-01-18  1:04     ` David Gibson
2024-01-18 15:40       ` Stefano Brivio
2023-12-21  7:02 ` [PATCH v3 06/15] tcp, flow: Replace TCP specific hash function with general flow hash David Gibson
2024-01-17 19:59   ` Stefano Brivio
2024-01-18  1:15     ` David Gibson
2024-01-18 15:42       ` Stefano Brivio
2024-01-18 23:55         ` David Gibson
2023-12-21  7:02 ` [PATCH v3 07/15] flow: Add helper to determine a flow's protocol David Gibson
2023-12-21  7:02 ` [PATCH v3 08/15] flow, tcp: Generalise TCP hash table to general flow hash table David Gibson
2023-12-21  7:02 ` David Gibson [this message]
2023-12-21  7:02 ` [PATCH v3 10/15] icmp: Store ping socket information in the flow table David Gibson
2023-12-21  7:02 ` [PATCH v3 11/15] icmp: Populate guest side information for ping flows David Gibson
2023-12-21  7:02 ` [PATCH v3 12/15] icmp: Populate and use host side flow information David Gibson
2024-01-17 19:59   ` Stefano Brivio
2024-01-18  1:22     ` David Gibson
2024-01-18 15:43       ` Stefano Brivio
2024-01-18 23:58         ` David Gibson
2023-12-21  7:02 ` [PATCH v3 13/15] icmp: Use 'flowside' epoll references for ping sockets David Gibson
2023-12-21  7:02 ` [PATCH v3 14/15] icmp: Merge EPOLL_TYPE_ICMP and EPOLL_TYPE_ICMPV6 David Gibson
2023-12-21  7:02 ` [PATCH v3 15/15] icmp: Eliminate icmp_id_map 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=20231221070237.1422557-10-david@gibson.dropbear.id.au \
    --to=david@gibson.dropbear.id.au \
    --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).