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 08/16] tcp, flow: Replace TCP specific hash function with general flow hash
Date: Fri, 3 May 2024 11:11:27 +1000 [thread overview]
Message-ID: <20240503011135.2924437-9-david@gibson.dropbear.id.au> (raw)
In-Reply-To: <20240503011135.2924437-1-david@gibson.dropbear.id.au>
Currently we match TCP packets received on the tap connection to a TCP
connection via a hash table based on the forwarding address and both
ports. We hope in future to allow for multiple guest side addresses, or
for multiple interfaces which means we may need to distinguish based on
the endpoint address and pif as well. We also want a unified hash table
to cover multiple protocols, not just TCP.
Replace the TCP specific hash function with one suitable for general flows,
or rather for one side of a general flow. This includes all the
information from struct flowside, plus the L4 protocol number.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
---
flow.c | 28 ++++++++++++++++++++++++++
flow.h | 19 ++++++++++++++++++
tcp.c | 62 +++++++++++-----------------------------------------------
3 files changed, 58 insertions(+), 51 deletions(-)
diff --git a/flow.c b/flow.c
index 02d6008..370d422 100644
--- a/flow.c
+++ b/flow.c
@@ -268,6 +268,34 @@ void flow_alloc_cancel(union flow *flow)
flow_first_free = FLOW_IDX(flow);
}
+/**
+ * flow_hash() - Calculate hash value for one side of a flow
+ * @c: Execution context
+ * @proto: Protocol of this flow (IP L4 protocol number)
+ * @fside: Flowside (must not have unspecified parts)
+ *
+ * Return: hash value
+ */
+uint64_t flow_hash(const struct ctx *c, uint8_t proto,
+ const struct flowside *fside)
+{
+ struct siphash_state state = SIPHASH_INIT(c->hash_secret);
+
+ /* For the hash table to work, we need complete information in the
+ * flowside.
+ */
+ ASSERT(fside->pif != PIF_NONE &&
+ !inany_is_unspecified(&fside->faddr) && fside->fport != 0 &&
+ !inany_is_unspecified(&fside->eaddr) && fside->eport != 0);
+
+ inany_siphash_feed(&state, &fside->faddr);
+ inany_siphash_feed(&state, &fside->eaddr);
+
+ return siphash_final(&state, 38, (uint64_t)proto << 40 |
+ (uint64_t)fside->pif << 32 |
+ fside->fport << 16 | fside->eport);
+}
+
/**
* flow_defer_handler() - Handler for per-flow deferred and timed tasks
* @c: Execution context
diff --git a/flow.h b/flow.h
index 88caa76..218edc6 100644
--- a/flow.h
+++ b/flow.h
@@ -107,6 +107,22 @@ static inline void flowside_from_af(struct flowside *fside,
#define SIDES 2
+/**
+ * flowside_eq() - Check if two flowsides are equal
+ * @left, @right: Flowsides to compare
+ *
+ * Return: true if equal, false otherwise
+ */
+static inline bool flowside_eq(const struct flowside *left,
+ const struct flowside *right)
+{
+ return left->pif == right->pif &&
+ inany_equals(&left->eaddr, &right->eaddr) &&
+ left->eport == right->eport &&
+ inany_equals(&left->faddr, &right->faddr) &&
+ left->fport == right->fport;
+}
+
/**
* struct flow_common - Common fields for packet flows
* @side[]: Information for each side of the flow
@@ -128,6 +144,9 @@ union flow *flow_start(union flow *flow, enum flow_type type,
#define FLOW_START(flow_, t_, var_, i_) \
(&flow_start((flow_), (t_), (i_))->var_)
+uint64_t flow_hash(const struct ctx *c, uint8_t proto,
+ const struct flowside *fside);
+
/**
* struct flow_sidx - ID for one side of a specific flow
* @side: Side referenced (0 or 1)
diff --git a/tcp.c b/tcp.c
index 9ba2b07..2ad47c5 100644
--- a/tcp.c
+++ b/tcp.c
@@ -524,7 +524,7 @@ static struct iovec tcp_iov [UIO_MAXIOV];
#define CONN(idx) (&(FLOW(idx)->tcp))
-/* Table for lookup from remote address, local port, remote port */
+/* Table for lookup from flowside information */
static flow_sidx_t tc_hash[TCP_HASH_TABLE_SIZE];
static_assert(ARRAY_SIZE(tc_hash) >= FLOW_MAX,
@@ -1074,46 +1074,6 @@ static int tcp_opt_get(const char *opts, size_t len, uint8_t type_find,
return -1;
}
-/**
- * tcp_hash_match() - Check if a connection entry matches address and ports
- * @conn: Connection entry to match against
- * @faddr: Guest side forwarding address
- * @eport: Guest side endpoint port
- * @fport: Guest side forwarding port
- *
- * Return: 1 on match, 0 otherwise
- */
-static int tcp_hash_match(const struct tcp_tap_conn *conn,
- const union inany_addr *faddr,
- in_port_t eport, in_port_t fport)
-{
- const struct flowside *tapside = &conn->f.side[TAPSIDE];
-
- if (inany_equals(&tapside->faddr, faddr) &&
- tapside->eport == eport && tapside->fport == fport)
- return 1;
-
- return 0;
-}
-
-/**
- * tcp_hash() - Calculate hash value for connection given address and ports
- * @c: Execution context
- * @faddr: Guest side forwarding address
- * @eport: Guest side endpoint port
- * @fport: Guest side forwarding port
- *
- * Return: hash value, needs to be adjusted for table size
- */
-static uint64_t tcp_hash(const struct ctx *c, const union inany_addr *faddr,
- in_port_t eport, in_port_t fport)
-{
- struct siphash_state state = SIPHASH_INIT(c->hash_secret);
-
- inany_siphash_feed(&state, faddr);
- return siphash_final(&state, 20, (uint64_t)eport << 16 | fport);
-}
-
/**
* tcp_conn_hash() - Calculate hash bucket of an existing connection
* @c: Execution context
@@ -1124,9 +1084,7 @@ static uint64_t tcp_hash(const struct ctx *c, const union inany_addr *faddr,
static uint64_t tcp_conn_hash(const struct ctx *c,
const struct tcp_tap_conn *conn)
{
- const struct flowside *tapside = &conn->f.side[TAPSIDE];
-
- return tcp_hash(c, &tapside->faddr, tapside->eport, tapside->fport);
+ return flow_hash(c, IPPROTO_TCP, &conn->f.side[TAPSIDE]);
}
/**
@@ -1201,25 +1159,26 @@ static void tcp_hash_remove(const struct ctx *c,
* tcp_hash_lookup() - Look up connection given remote address and ports
* @c: Execution context
* @af: Address family, AF_INET or AF_INET6
+ * @eaddr: Guest side endpoint address (guest local address)
* @faddr: Guest side forwarding address (guest remote address)
* @eport: Guest side endpoint port (guest local port)
* @fport: Guest side forwarding port (guest remote port)
*
* Return: connection pointer, if found, -ENOENT otherwise
*/
-static struct tcp_tap_conn *tcp_hash_lookup(const struct ctx *c,
- sa_family_t af, const void *faddr,
+static struct tcp_tap_conn *tcp_hash_lookup(const struct ctx *c, sa_family_t af,
+ const void *eaddr, const void *faddr,
in_port_t eport, in_port_t fport)
{
- union inany_addr aany;
+ struct flowside fside;
union flow *flow;
unsigned b;
- inany_from_af(&aany, af, faddr);
+ flowside_from_af(&fside, PIF_TAP, af, faddr, fport, eaddr, eport);
- b = tcp_hash(c, &aany, eport, fport) % TCP_HASH_TABLE_SIZE;
+ b = flow_hash(c, IPPROTO_TCP, &fside) % TCP_HASH_TABLE_SIZE;
while ((flow = flow_at_sidx(tc_hash[b])) &&
- !tcp_hash_match(&flow->tcp, &aany, eport, fport))
+ !flowside_eq(&flow->f.side[TAPSIDE], &fside))
b = mod_sub(b, 1, TCP_HASH_TABLE_SIZE);
return &flow->tcp;
@@ -2522,7 +2481,8 @@ int tcp_tap_handler(struct ctx *c, uint8_t pif, sa_family_t af,
optlen = MIN(optlen, ((1UL << 4) /* from doff width */ - 6) * 4UL);
opts = packet_get(p, idx, sizeof(*th), optlen, NULL);
- conn = tcp_hash_lookup(c, af, daddr, ntohs(th->source), ntohs(th->dest));
+ conn = tcp_hash_lookup(c, af, saddr, daddr,
+ ntohs(th->source), ntohs(th->dest));
/* New connection from tap */
if (!conn) {
--
@@ -524,7 +524,7 @@ static struct iovec tcp_iov [UIO_MAXIOV];
#define CONN(idx) (&(FLOW(idx)->tcp))
-/* Table for lookup from remote address, local port, remote port */
+/* Table for lookup from flowside information */
static flow_sidx_t tc_hash[TCP_HASH_TABLE_SIZE];
static_assert(ARRAY_SIZE(tc_hash) >= FLOW_MAX,
@@ -1074,46 +1074,6 @@ static int tcp_opt_get(const char *opts, size_t len, uint8_t type_find,
return -1;
}
-/**
- * tcp_hash_match() - Check if a connection entry matches address and ports
- * @conn: Connection entry to match against
- * @faddr: Guest side forwarding address
- * @eport: Guest side endpoint port
- * @fport: Guest side forwarding port
- *
- * Return: 1 on match, 0 otherwise
- */
-static int tcp_hash_match(const struct tcp_tap_conn *conn,
- const union inany_addr *faddr,
- in_port_t eport, in_port_t fport)
-{
- const struct flowside *tapside = &conn->f.side[TAPSIDE];
-
- if (inany_equals(&tapside->faddr, faddr) &&
- tapside->eport == eport && tapside->fport == fport)
- return 1;
-
- return 0;
-}
-
-/**
- * tcp_hash() - Calculate hash value for connection given address and ports
- * @c: Execution context
- * @faddr: Guest side forwarding address
- * @eport: Guest side endpoint port
- * @fport: Guest side forwarding port
- *
- * Return: hash value, needs to be adjusted for table size
- */
-static uint64_t tcp_hash(const struct ctx *c, const union inany_addr *faddr,
- in_port_t eport, in_port_t fport)
-{
- struct siphash_state state = SIPHASH_INIT(c->hash_secret);
-
- inany_siphash_feed(&state, faddr);
- return siphash_final(&state, 20, (uint64_t)eport << 16 | fport);
-}
-
/**
* tcp_conn_hash() - Calculate hash bucket of an existing connection
* @c: Execution context
@@ -1124,9 +1084,7 @@ static uint64_t tcp_hash(const struct ctx *c, const union inany_addr *faddr,
static uint64_t tcp_conn_hash(const struct ctx *c,
const struct tcp_tap_conn *conn)
{
- const struct flowside *tapside = &conn->f.side[TAPSIDE];
-
- return tcp_hash(c, &tapside->faddr, tapside->eport, tapside->fport);
+ return flow_hash(c, IPPROTO_TCP, &conn->f.side[TAPSIDE]);
}
/**
@@ -1201,25 +1159,26 @@ static void tcp_hash_remove(const struct ctx *c,
* tcp_hash_lookup() - Look up connection given remote address and ports
* @c: Execution context
* @af: Address family, AF_INET or AF_INET6
+ * @eaddr: Guest side endpoint address (guest local address)
* @faddr: Guest side forwarding address (guest remote address)
* @eport: Guest side endpoint port (guest local port)
* @fport: Guest side forwarding port (guest remote port)
*
* Return: connection pointer, if found, -ENOENT otherwise
*/
-static struct tcp_tap_conn *tcp_hash_lookup(const struct ctx *c,
- sa_family_t af, const void *faddr,
+static struct tcp_tap_conn *tcp_hash_lookup(const struct ctx *c, sa_family_t af,
+ const void *eaddr, const void *faddr,
in_port_t eport, in_port_t fport)
{
- union inany_addr aany;
+ struct flowside fside;
union flow *flow;
unsigned b;
- inany_from_af(&aany, af, faddr);
+ flowside_from_af(&fside, PIF_TAP, af, faddr, fport, eaddr, eport);
- b = tcp_hash(c, &aany, eport, fport) % TCP_HASH_TABLE_SIZE;
+ b = flow_hash(c, IPPROTO_TCP, &fside) % TCP_HASH_TABLE_SIZE;
while ((flow = flow_at_sidx(tc_hash[b])) &&
- !tcp_hash_match(&flow->tcp, &aany, eport, fport))
+ !flowside_eq(&flow->f.side[TAPSIDE], &fside))
b = mod_sub(b, 1, TCP_HASH_TABLE_SIZE);
return &flow->tcp;
@@ -2522,7 +2481,8 @@ int tcp_tap_handler(struct ctx *c, uint8_t pif, sa_family_t af,
optlen = MIN(optlen, ((1UL << 4) /* from doff width */ - 6) * 4UL);
opts = packet_get(p, idx, sizeof(*th), optlen, NULL);
- conn = tcp_hash_lookup(c, af, daddr, ntohs(th->source), ntohs(th->dest));
+ conn = tcp_hash_lookup(c, af, saddr, daddr,
+ ntohs(th->source), ntohs(th->dest));
/* New connection from tap */
if (!conn) {
--
2.44.0
next prev 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 ` David Gibson [this message]
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 ` [PATCH v4 10/16] tcp: Re-use flow hash for initial sequence number generation David Gibson
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=20240503011135.2924437-9-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).