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 v5 12/19] tcp, flow: Replace TCP specific hash function with general flow hash
Date: Tue, 14 May 2024 11:03:30 +1000 [thread overview]
Message-ID: <20240514010337.1104606-13-david@gibson.dropbear.id.au> (raw)
In-Reply-To: <20240514010337.1104606-1-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 | 35 +++++++++++++++++++++++++++---
flow.h | 19 ++++++++++++++++
flow_table.h | 2 ++
tcp.c | 61 ++++++++++------------------------------------------
4 files changed, 64 insertions(+), 53 deletions(-)
diff --git a/flow.c b/flow.c
index aff077b..fdd22b7 100644
--- a/flow.c
+++ b/flow.c
@@ -116,9 +116,9 @@ static struct timespec flow_timer_run;
* @faddr: Forwarding address (pointer to in_addr or in6_addr)
* @fport: Forwarding port
*/
-static void flowside_from_af(struct flowside *fside, sa_family_t af,
- const void *eaddr, in_port_t eport,
- const void *faddr, in_port_t fport)
+void flowside_from_af(struct flowside *fside, sa_family_t af,
+ const void *eaddr, in_port_t eport,
+ const void *faddr, in_port_t fport)
{
if (faddr)
inany_from_af(&fside->faddr, af, faddr);
@@ -397,6 +397,35 @@ void flow_alloc_cancel(union flow *flow)
flow_new_entry = NULL;
}
+/**
+ * flow_hash() - Calculate hash value for one side of a flow
+ * @c: Execution context
+ * @proto: Protocol of this flow (IP L4 protocol number)
+ * @pif: pif of the side to hash
+ * @fside: Flowside (must not have unspecified parts)
+ *
+ * Return: hash value
+ */
+uint64_t flow_hash(const struct ctx *c, uint8_t proto, uint8_t pif,
+ 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(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)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 437579b..6d68e09 100644
--- a/flow.h
+++ b/flow.h
@@ -147,6 +147,25 @@ struct flowside {
in_port_t eport;
};
+/**
+ * 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 inany_equals(&left->eaddr, &right->eaddr) &&
+ left->eport == right->eport &&
+ inany_equals(&left->faddr, &right->faddr) &&
+ left->fport == right->fport;
+}
+
+void flowside_from_af(struct flowside *fside, sa_family_t af,
+ const void *eaddr, in_port_t eport,
+ const void *faddr, in_port_t fport);
+
/**
* struct flow_common - Common fields for packet flows
* @side[]: Information for each side of the flow
diff --git a/flow_table.h b/flow_table.h
index 91ade0a..0083c87 100644
--- a/flow_table.h
+++ b/flow_table.h
@@ -126,5 +126,7 @@ void flow_activate(struct flow_common *f);
#define FLOW_ACTIVATE(flow_) \
(flow_activate(&(flow_)->f))
+uint64_t flow_hash(const struct ctx *c, uint8_t proto, uint8_t pif,
+ const struct flowside *fside);
#endif /* FLOW_TABLE_H */
diff --git a/tcp.c b/tcp.c
index 9895c19..983a537 100644
--- a/tcp.c
+++ b/tcp.c
@@ -523,7 +523,7 @@ 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,
@@ -1073,46 +1073,6 @@ 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 = TAPFLOW(conn);
-
- 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
@@ -1125,8 +1085,7 @@ static uint64_t tcp_conn_hash(const struct ctx *c,
{
const struct flowside *tapside = TAPFLOW(conn);
- return tcp_hash(c, &tapside->faddr, tapside->eport,
- tapside->fport);
+ return flow_hash(c, IPPROTO_TCP, conn->f.pif[TAPSIDE(conn)], tapside);
}
/**
@@ -1201,25 +1160,26 @@ 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, af, eaddr, eport, faddr, fport);
- b = tcp_hash(c, &aany, eport, fport) % TCP_HASH_TABLE_SIZE;
+ b = flow_hash(c, IPPROTO_TCP, PIF_TAP, &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(flow)], &fside))
b = mod_sub(b, 1, TCP_HASH_TABLE_SIZE);
return &flow->tcp;
@@ -2523,7 +2483,8 @@ 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) {
--
@@ -523,7 +523,7 @@ 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,
@@ -1073,46 +1073,6 @@ 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 = TAPFLOW(conn);
-
- 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
@@ -1125,8 +1085,7 @@ static uint64_t tcp_conn_hash(const struct ctx *c,
{
const struct flowside *tapside = TAPFLOW(conn);
- return tcp_hash(c, &tapside->faddr, tapside->eport,
- tapside->fport);
+ return flow_hash(c, IPPROTO_TCP, conn->f.pif[TAPSIDE(conn)], tapside);
}
/**
@@ -1201,25 +1160,26 @@ 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, af, eaddr, eport, faddr, fport);
- b = tcp_hash(c, &aany, eport, fport) % TCP_HASH_TABLE_SIZE;
+ b = flow_hash(c, IPPROTO_TCP, PIF_TAP, &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(flow)], &fside))
b = mod_sub(b, 1, TCP_HASH_TABLE_SIZE);
return &flow->tcp;
@@ -2523,7 +2483,8 @@ 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) {
--
2.45.0
next prev parent reply other threads:[~2024-05-14 1:03 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-05-14 1:03 [PATCH v5 00/19] RFC: Unified flow table David Gibson
2024-05-14 1:03 ` [PATCH v5 01/19] flow: Clarify and enforce flow state transitions David Gibson
2024-05-16 9:30 ` Stefano Brivio
[not found] ` <ZkbVxtvmP7f0aL1S@zatzit>
2024-05-17 11:00 ` Stefano Brivio
2024-05-18 6:47 ` David Gibson
2024-05-14 1:03 ` [PATCH v5 02/19] flow: Make side 0 always be the initiating side David Gibson
2024-05-16 12:06 ` Stefano Brivio
2024-05-14 1:03 ` [PATCH v5 03/19] flow: Record the pifs for each side of each flow David Gibson
2024-05-14 1:03 ` [PATCH v5 04/19] tcp: Remove interim 'tapside' field from connection David Gibson
2024-05-14 1:03 ` [PATCH v5 05/19] flow: Common data structures for tracking flow addresses David Gibson
2024-05-14 1:03 ` [PATCH v5 06/19] flow: Populate address information for initiating side David Gibson
[not found] ` <20240516202337.1b90e5f2@elisabeth>
[not found] ` <ZkbcwkdEwjGv6uwG@zatzit>
[not found] ` <20240517215845.4d09eaae@elisabeth>
2024-05-18 7:00 ` David Gibson
2024-05-14 1:03 ` [PATCH v5 07/19] flow: Populate address information for non-initiating side David Gibson
2024-05-14 1:03 ` [PATCH v5 08/19] tcp, flow: Remove redundant information, repack connection structures David Gibson
2024-05-14 1:03 ` [PATCH v5 09/19] tcp: Obtain guest address from flowside David Gibson
2024-05-14 1:03 ` [PATCH v5 10/19] tcp: Simplify endpoint validation using flowside information David Gibson
2024-05-14 1:03 ` [PATCH v5 11/19] tcp_splice: Eliminate SPLICE_V6 flag David Gibson
2024-05-14 1:03 ` David Gibson [this message]
2024-05-14 1:03 ` [PATCH v5 13/19] flow, tcp: Generalise TCP hash table to general flow hash table David Gibson
2024-05-14 1:03 ` [PATCH v5 14/19] tcp: Re-use flow hash for initial sequence number generation David Gibson
2024-05-14 1:03 ` [PATCH v5 15/19] icmp: Use flowsides as the source of truth wherever possible David Gibson
[not found] ` <20240516225350.06aebcd7@elisabeth>
[not found] ` <ZkcAHhCpx3F0SW2K@zatzit>
[not found] ` <20240517221123.1c7197a3@elisabeth>
2024-05-18 7:08 ` David Gibson
2024-05-14 1:03 ` [PATCH v5 16/19] icmp: Look up ping flows using flow hash David Gibson
2024-05-14 1:03 ` [PATCH v5 17/19] icmp: Eliminate icmp_id_map David Gibson
2024-05-14 1:03 ` [PATCH v5 18/19] flow, tcp: Flow based NAT and port forwarding for TCP David Gibson
[not found] ` <20240518001345.2d127b09@elisabeth>
2024-05-20 5:44 ` David Gibson
2024-05-14 1:03 ` [PATCH v5 19/19] flow, icmp: Use general flow forwarding rules for ICMP David Gibson
[not found] ` <20240518001408.004011b2@elisabeth>
2024-05-20 5:56 ` 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=20240514010337.1104606-13-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).