public inbox for passt-dev@passt.top
 help / color / mirror / code / Atom feed
From: David Gibson <david@gibson.dropbear.id.au>
To: passt-dev@passt.top, Stefano Brivio <sbrivio@redhat.com>
Cc: David Gibson <david@gibson.dropbear.id.au>
Subject: [PATCH v4 10/16] tcp: Re-use flow hash for initial sequence number generation
Date: Fri,  3 May 2024 11:11:29 +1000	[thread overview]
Message-ID: <20240503011135.2924437-11-david@gibson.dropbear.id.au> (raw)
In-Reply-To: <20240503011135.2924437-1-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  | 34 ++++++++++++----------------------
 3 files changed, 37 insertions(+), 29 deletions(-)

diff --git a/flow.c b/flow.c
index 8cefbed..c30910e 100644
--- a/flow.c
+++ b/flow.c
@@ -320,16 +320,16 @@ 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) &&
@@ -339,17 +339,35 @@ 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 c1181cc..c186f24 100644
--- a/flow.h
+++ b/flow.h
@@ -169,7 +169,7 @@ 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, sa_family_t af,
diff --git a/tcp.c b/tcp.c
index 7f83014..8b4d792 100644
--- a/tcp.c
+++ b/tcp.c
@@ -1572,28 +1572,16 @@ 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 tap flowside faddr, fport and eport
+ * 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 = &conn->f.side[TAPSIDE];
-	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;
 }
 
 /**
@@ -1771,6 +1759,7 @@ 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()))
@@ -1845,10 +1834,10 @@ 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);
-	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;
 
 	sockaddr_from_inany(&sa, &sl, &sockside->eaddr, sockside->eport,
 			    c->ifi6);
@@ -2533,6 +2522,7 @@ static void tcp_tap_conn_from_sock(struct ctx *c, in_port_t dstport,
 	const struct flowside *sockside = &flow->f.side[SOCKSIDE];
 	struct flowside *tapside = &flow->f.side[TAPSIDE];
 	struct tcp_tap_conn *conn;
+	uint64_t hash;
 
 	tapside->pif = PIF_TAP;
 	tapside->faddr = sockside->eaddr;
@@ -2555,8 +2545,8 @@ 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, 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;
 
-- 
@@ -1572,28 +1572,16 @@ 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 tap flowside faddr, fport and eport
+ * 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 = &conn->f.side[TAPSIDE];
-	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;
 }
 
 /**
@@ -1771,6 +1759,7 @@ 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()))
@@ -1845,10 +1834,10 @@ 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);
-	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;
 
 	sockaddr_from_inany(&sa, &sl, &sockside->eaddr, sockside->eport,
 			    c->ifi6);
@@ -2533,6 +2522,7 @@ static void tcp_tap_conn_from_sock(struct ctx *c, in_port_t dstport,
 	const struct flowside *sockside = &flow->f.side[SOCKSIDE];
 	struct flowside *tapside = &flow->f.side[TAPSIDE];
 	struct tcp_tap_conn *conn;
+	uint64_t hash;
 
 	tapside->pif = PIF_TAP;
 	tapside->faddr = sockside->eaddr;
@@ -2555,8 +2545,8 @@ 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, 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;
 
-- 
2.44.0


  parent reply	other threads:[~2024-05-03  1:11 UTC|newest]

Thread overview: 23+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-05-03  1:11 [PATCH v4 00/16] RFC: Unified flow table David Gibson
2024-05-03  1:11 ` [PATCH v4 01/16] flow: Common data structures for tracking flow addresses David Gibson
2024-05-13 18:07   ` Stefano Brivio
2024-05-14  0:11     ` David Gibson
2024-05-03  1:11 ` [PATCH v4 02/16] tcp: Maintain flowside information for "tap" connections David Gibson
2024-05-13 18:07   ` Stefano Brivio
2024-05-14  0:15     ` David Gibson
2024-05-03  1:11 ` [PATCH v4 03/16] tcp_splice: Maintain flowside information for spliced connections David Gibson
2024-05-03  1:11 ` [PATCH v4 04/16] tcp: Obtain guest address from flowside David Gibson
2024-05-13 18:07   ` Stefano Brivio
2024-05-14  0:18     ` David Gibson
2024-05-03  1:11 ` [PATCH v4 05/16] tcp: Simplify endpoint validation using flowside information David Gibson
2024-05-03  1:11 ` [PATCH v4 06/16] tcp, tcp_splice: Construct sockaddrs for connect() from flowside David Gibson
2024-05-03  1:11 ` [PATCH v4 07/16] tcp_splice: Eliminate SPLICE_V6 flag David Gibson
2024-05-03  1:11 ` [PATCH v4 08/16] tcp, flow: Replace TCP specific hash function with general flow hash David Gibson
2024-05-03  1:11 ` [PATCH v4 09/16] flow, tcp: Generalise TCP hash table to general flow hash table David Gibson
2024-05-03  1:11 ` David Gibson [this message]
2024-05-03  1:11 ` [PATCH v4 11/16] icmp: Populate flowside information David Gibson
2024-05-03  1:11 ` [PATCH v4 12/16] icmp: Use flowsides as the source of truth wherever possible David Gibson
2024-05-03  1:11 ` [PATCH v4 13/16] icmp: Look up ping flows using flow hash David Gibson
2024-05-03  1:11 ` [PATCH v4 14/16] icmp: Eliminate icmp_id_map David Gibson
2024-05-03  1:11 ` [PATCH v4 15/16] flow, tcp: flow based NAT and port forwarding for TCP David Gibson
2024-05-03  1:11 ` [PATCH v4 16/16] flow, icmp: Use general flow forwarding rules for ICMP 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=20240503011135.2924437-11-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).