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 v6 01/26] flow: Common address information for initiating side
Date: Fri, 14 Jun 2024 16:13:23 +1000	[thread overview]
Message-ID: <20240614061348.3814736-2-david@gibson.dropbear.id.au> (raw)
In-Reply-To: <20240614061348.3814736-1-david@gibson.dropbear.id.au>

Handling of each protocol needs some degree of tracking of the
addresses and ports at the end of each connection or flow.  Sometimes
that's explicit (as in the guest visible addresses for TCP
connections), sometimes implicit (the bound and connected addresses of
sockets).

To allow more consistent handling across protocols we want to
uniformly track the address and port at each end of the connection.
Furthermore, because we allow port remapping, and we sometimes need to
apply NAT, the addresses and ports can be different as seen by the
guest/namespace and as by the host.

Introduce 'struct flowside' to keep track of address and port
information related to one side of a flow. Store two of these in the
common fields of a flow to track that information for both sides.

For now we only populate the initiating side, requiring that
information be completed when a flows enter INI.  Later patches will
populate the target side.

For now this leaves some information redundantly recorded in both generic
and type specific fields.  We'll fix that in later patches.

Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
---
 flow.c       | 96 +++++++++++++++++++++++++++++++++++++++++++++++++---
 flow.h       | 16 +++++++++
 flow_table.h |  8 ++++-
 icmp.c       |  9 +++--
 passt.h      |  3 ++
 tcp.c        |  6 ++--
 6 files changed, 127 insertions(+), 11 deletions(-)

diff --git a/flow.c b/flow.c
index d05aa495..1819111d 100644
--- a/flow.c
+++ b/flow.c
@@ -108,6 +108,31 @@ static const union flow *flow_new_entry; /* = NULL */
 /* Last time the flow timers ran */
 static struct timespec flow_timer_run;
 
+/** flowside_from_af() - Initialise flowside from addresses
+ * @fside:	flowside to initialise
+ * @af:		Address family (AF_INET or AF_INET6)
+ * @eaddr:	Endpoint address (pointer to in_addr or in6_addr)
+ * @eport:	Endpoint port
+ * @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)
+{
+	if (faddr)
+		inany_from_af(&fside->faddr, af, faddr);
+	else
+		fside->faddr = inany_any6;
+	fside->fport = fport;
+
+	if (eaddr)
+		inany_from_af(&fside->eaddr, af, eaddr);
+	else
+		fside->eaddr = inany_any6;
+	fside->eport = eport;
+}
+
 /** flow_log_ - Log flow-related message
  * @f:		flow the message is related to
  * @pri:	Log priority
@@ -140,6 +165,8 @@ void flow_log_(const struct flow_common *f, int pri, const char *fmt, ...)
  */
 static void flow_set_state(struct flow_common *f, enum flow_state state)
 {
+	char estr[INANY_ADDRSTRLEN], fstr[INANY_ADDRSTRLEN];
+	const struct flowside *ini = &f->side[INISIDE];
 	uint8_t oldstate = f->state;
 
 	ASSERT(state < FLOW_NUM_STATES);
@@ -150,18 +177,28 @@ static void flow_set_state(struct flow_common *f, enum flow_state state)
 		  FLOW_STATE(f));
 
 	if (MAX(state, oldstate) >= FLOW_STATE_TGT)
-		flow_log_(f, LOG_DEBUG, "%s => %s", pif_name(f->pif[INISIDE]),
-			                            pif_name(f->pif[TGTSIDE]));
+		flow_log_(f, LOG_DEBUG, "%s [%s]:%hu -> [%s]:%hu => %s",
+			  pif_name(f->pif[INISIDE]),
+			  inany_ntop(&ini->eaddr, estr, sizeof(estr)),
+			  ini->eport,
+			  inany_ntop(&ini->faddr, fstr, sizeof(fstr)),
+			  ini->fport,
+			  pif_name(f->pif[TGTSIDE]));
 	else if (MAX(state, oldstate) >= FLOW_STATE_INI)
-		flow_log_(f, LOG_DEBUG, "%s => ?", pif_name(f->pif[INISIDE]));
+		flow_log_(f, LOG_DEBUG, "%s [%s]:%hu -> [%s]:%hu => ?",
+			  pif_name(f->pif[INISIDE]),
+			  inany_ntop(&ini->eaddr, estr, sizeof(estr)),
+			  ini->eport,
+			  inany_ntop(&ini->faddr, fstr, sizeof(fstr)),
+			  ini->fport);
 }
 
 /**
- * flow_initiate() - Move flow to INI, setting INISIDE details
+ * flow_initiate_() - Move flow to INI, setting setting pif[INISIDE]
  * @flow:	Flow to change state
  * @pif:	pif of the initiating side
  */
-void flow_initiate(union flow *flow, uint8_t pif)
+static void flow_initiate_(union flow *flow, uint8_t pif)
 {
 	struct flow_common *f = &flow->f;
 
@@ -174,6 +211,55 @@ void flow_initiate(union flow *flow, uint8_t pif)
 	flow_set_state(f, FLOW_STATE_INI);
 }
 
+/**
+ * flow_initiate_af() - Move flow to INI, setting INISIDE details
+ * @flow:	Flow to change state
+ * @pif:	pif of the initiating side
+ * @af:		Address family of @eaddr and @faddr
+ * @saddr:	Source address (pointer to in_addr or in6_addr)
+ * @sport:	Endpoint port
+ * @daddr:	Destination address (pointer to in_addr or in6_addr)
+ * @dport:	Destination port
+ *
+ * Return: pointer to the initiating flowside information
+ */
+const struct flowside *flow_initiate_af(union flow *flow, uint8_t pif,
+					sa_family_t af,
+					const void *saddr, in_port_t sport,
+					const void *daddr, in_port_t dport)
+{
+	struct flowside *ini = &flow->f.side[INISIDE];
+
+	flowside_from_af(ini, af, saddr, sport, daddr, dport);
+	flow_initiate_(flow, pif);
+	return ini;
+}
+
+/**
+ * flow_initiate_sa() - Move flow to INI, setting INISIDE details
+ * @flow:	Flow to change state
+ * @pif:	pif of the initiating side
+ * @ssa:	Source socket address
+ * @dport:	Destination port
+ *
+ * Return: pointer to the initiating flowside information
+ */
+const struct flowside *flow_initiate_sa(union flow *flow, uint8_t pif,
+					const union sockaddr_inany *ssa,
+					in_port_t dport)
+{
+	struct flowside *ini = &flow->f.side[INISIDE];
+
+	inany_from_sockaddr(&ini->eaddr, &ini->eport, ssa);
+	if (inany_v4(&ini->eaddr))
+		ini->faddr = inany_any4;
+	else
+		ini->faddr = inany_any6;
+	ini->fport = dport;
+	flow_initiate_(flow, pif);
+	return ini;
+}
+
 /**
  * flow_target() - Move flow to TGT, setting TGTSIDE details
  * @flow:	Flow to change state
diff --git a/flow.h b/flow.h
index 29ef9f12..b873ea7f 100644
--- a/flow.h
+++ b/flow.h
@@ -135,11 +135,26 @@ extern const uint8_t flow_proto[];
 #define INISIDE			0	/* Initiating side */
 #define TGTSIDE			1	/* Target side */
 
+/**
+ * struct flowside - Address information for one side of a flow
+ * @eaddr:	Endpoint address (remote address from passt's PoV)
+ * @faddr:	Forwarding address (local address from passt's PoV)
+ * @eport:	Endpoint port
+ * @fport:	Forwarding port
+ */
+struct flowside {
+	union inany_addr	faddr;
+	union inany_addr	eaddr;
+	in_port_t		fport;
+	in_port_t		eport;
+};
+
 /**
  * struct flow_common - Common fields for packet flows
  * @state:	State of the flow table entry
  * @type:	Type of packet flow
  * @pif[]:	Interface for each side of the flow
+ * @side[]:	Information for each side of the flow
  */
 struct flow_common {
 #ifdef __GNUC__
@@ -154,6 +169,7 @@ struct flow_common {
 		      "Not enough bits for type field");
 #endif
 	uint8_t		pif[SIDES];
+	struct flowside	side[SIDES];
 };
 
 #define FLOW_INDEX_BITS		17	/* 128k - 1 */
diff --git a/flow_table.h b/flow_table.h
index 1b163491..2e912532 100644
--- a/flow_table.h
+++ b/flow_table.h
@@ -107,7 +107,13 @@ static inline flow_sidx_t flow_sidx(const struct flow_common *f,
 union flow *flow_alloc(void);
 void flow_alloc_cancel(union flow *flow);
 
-void flow_initiate(union flow *flow, uint8_t pif);
+const struct flowside *flow_initiate_af(union flow *flow, uint8_t pif,
+					sa_family_t af,
+					const void *saddr, in_port_t sport,
+					const void *daddr, in_port_t dport);
+const struct flowside *flow_initiate_sa(union flow *flow, uint8_t pif,
+					const union sockaddr_inany *ssa,
+					in_port_t dport);
 void flow_target(union flow *flow, uint8_t pif);
 
 union flow *flow_set_type(union flow *flow, enum flow_type type);
diff --git a/icmp.c b/icmp.c
index 80330f6f..38d1deeb 100644
--- a/icmp.c
+++ b/icmp.c
@@ -146,12 +146,15 @@ static void icmp_ping_close(const struct ctx *c,
  * @id_sock:	Pointer to ping flow entry slot in icmp_id_map[] to update
  * @af:		Address family, AF_INET or AF_INET6
  * @id:		ICMP id for the new socket
+ * @saddr:	Source address
+ * @daddr:	Destination address
  *
  * Return: Newly opened ping flow, or NULL on failure
  */
 static struct icmp_ping_flow *icmp_ping_new(const struct ctx *c,
 					    struct icmp_ping_flow **id_sock,
-					    sa_family_t af, uint16_t id)
+					    sa_family_t af, uint16_t id,
+					    const void *saddr, const void *daddr)
 {
 	uint8_t flowtype = af == AF_INET ? FLOW_PING4 : FLOW_PING6;
 	union epoll_ref ref = { .type = EPOLL_TYPE_PING };
@@ -163,7 +166,7 @@ static struct icmp_ping_flow *icmp_ping_new(const struct ctx *c,
 	if (!flow)
 		return NULL;
 
-	flow_initiate(flow, PIF_TAP);
+	flow_initiate_af(flow, PIF_TAP, af, saddr, id, daddr, id);
 	flow_target(flow, PIF_HOST);
 	pingf = FLOW_SET_TYPE(flow, flowtype, ping);
 
@@ -269,7 +272,7 @@ int icmp_tap_handler(const struct ctx *c, uint8_t pif, sa_family_t af,
 	}
 
 	if (!(pingf = *id_sock))
-		if (!(pingf = icmp_ping_new(c, id_sock, af, id)))
+		if (!(pingf = icmp_ping_new(c, id_sock, af, id, saddr, daddr)))
 			return 1;
 
 	pingf->ts = now->tv_sec;
diff --git a/passt.h b/passt.h
index 46d073a2..76810867 100644
--- a/passt.h
+++ b/passt.h
@@ -17,6 +17,9 @@ union epoll_ref;
 
 #include "pif.h"
 #include "packet.h"
+#include "siphash.h"
+#include "ip.h"
+#include "inany.h"
 #include "flow.h"
 #include "icmp.h"
 #include "fwd.h"
diff --git a/tcp.c b/tcp.c
index 68524235..07a2eb1c 100644
--- a/tcp.c
+++ b/tcp.c
@@ -1629,7 +1629,7 @@ static void tcp_conn_from_tap(struct ctx *c, sa_family_t af,
 	if (!(flow = flow_alloc()))
 		return;
 
-	flow_initiate(flow, PIF_TAP);
+	flow_initiate_af(flow, PIF_TAP, af, saddr, srcport, daddr, dstport);
 
 	if (af == AF_INET) {
 		if (IN4_IS_ADDR_UNSPECIFIED(saddr) ||
@@ -2288,7 +2288,9 @@ void tcp_listen_handler(struct ctx *c, union epoll_ref ref,
 	if (s < 0)
 		goto cancel;
 
-	flow_initiate(flow, ref.tcp_listen.pif);
+	/* FIXME: When listening port has a specific bound address, record that
+	 * as the forwarding address */
+	flow_initiate_sa(flow, ref.tcp_listen.pif, &sa, ref.tcp_listen.port);
 
 	if (sa.sa_family == AF_INET) {
 		const struct in_addr *addr = &sa.sa4.sin_addr;
-- 
@@ -1629,7 +1629,7 @@ static void tcp_conn_from_tap(struct ctx *c, sa_family_t af,
 	if (!(flow = flow_alloc()))
 		return;
 
-	flow_initiate(flow, PIF_TAP);
+	flow_initiate_af(flow, PIF_TAP, af, saddr, srcport, daddr, dstport);
 
 	if (af == AF_INET) {
 		if (IN4_IS_ADDR_UNSPECIFIED(saddr) ||
@@ -2288,7 +2288,9 @@ void tcp_listen_handler(struct ctx *c, union epoll_ref ref,
 	if (s < 0)
 		goto cancel;
 
-	flow_initiate(flow, ref.tcp_listen.pif);
+	/* FIXME: When listening port has a specific bound address, record that
+	 * as the forwarding address */
+	flow_initiate_sa(flow, ref.tcp_listen.pif, &sa, ref.tcp_listen.port);
 
 	if (sa.sa_family == AF_INET) {
 		const struct in_addr *addr = &sa.sa4.sin_addr;
-- 
2.45.2


  reply	other threads:[~2024-06-14  6:13 UTC|newest]

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-06-14  6:13 [PATCH v6 00/26] RFC: Unified flow table David Gibson
2024-06-14  6:13 ` David Gibson [this message]
2024-06-25 22:23   ` [PATCH v6 01/26] flow: Common address information for initiating side Stefano Brivio
2024-06-26  0:19     ` David Gibson
2024-06-14  6:13 ` [PATCH v6 02/26] flow: Common address information for target side David Gibson
2024-06-25 22:23   ` Stefano Brivio
2024-06-26  0:25     ` David Gibson
2024-06-14  6:13 ` [PATCH v6 03/26] tcp, flow: Remove redundant information, repack connection structures David Gibson
2024-06-25 22:25   ` Stefano Brivio
2024-06-26  0:23     ` David Gibson
2024-06-14  6:13 ` [PATCH v6 04/26] tcp: Obtain guest address from flowside David Gibson
2024-06-14  6:13 ` [PATCH v6 05/26] tcp: Manage outbound address via flow table David Gibson
2024-06-14  6:13 ` [PATCH v6 06/26] tcp: Simplify endpoint validation using flowside information David Gibson
2024-06-14  6:13 ` [PATCH v6 07/26] tcp_splice: Eliminate SPLICE_V6 flag David Gibson
2024-06-14  6:13 ` [PATCH v6 08/26] tcp, flow: Replace TCP specific hash function with general flow hash David Gibson
2024-06-14  6:13 ` [PATCH v6 09/26] flow, tcp: Generalise TCP hash table to general flow hash table David Gibson
2024-06-14  6:13 ` [PATCH v6 10/26] tcp: Re-use flow hash for initial sequence number generation David Gibson
2024-06-14  6:13 ` [PATCH v6 11/26] icmp: Remove redundant id field from flow table entry David Gibson
2024-06-14  6:13 ` [PATCH v6 12/26] icmp: Obtain destination addresses from the flowsides David Gibson
2024-06-14  6:13 ` [PATCH v6 13/26] icmp: Look up ping flows using flow hash David Gibson
2024-06-14  6:13 ` [PATCH v6 14/26] icmp: Eliminate icmp_id_map David Gibson
2024-06-14  6:13 ` [PATCH v6 15/26] icmp: Manage outbound socket address via flow table David Gibson
2024-06-14  6:13 ` [PATCH v6 16/26] flow, tcp: Flow based NAT and port forwarding for TCP David Gibson
2024-06-26 22:49   ` Stefano Brivio
2024-06-27  5:55     ` David Gibson
2024-06-14  6:13 ` [PATCH v6 17/26] flow, icmp: Use general flow forwarding rules for ICMP David Gibson
2024-06-14  6:13 ` [PATCH v6 18/26] fwd: Update flow forwarding logic for UDP David Gibson
2024-06-14  6:13 ` [PATCH v6 19/26] udp: Create flow table entries " David Gibson
2024-06-14  6:13 ` [PATCH v6 20/26] udp: Direct traffic from tap according to flow table David Gibson
2024-06-14  6:13 ` [PATCH v6 21/26] udp: Direct traffic from host to guest " David Gibson
2024-06-14  6:13 ` [PATCH v6 22/26] udp: Direct spliced traffic " David Gibson
2024-06-14  6:13 ` [PATCH v6 23/26] udp: Remove 'splicesrc' tracking David Gibson
2024-06-14  6:13 ` [PATCH v6 24/26] udp: Remove tap port flags field David Gibson
2024-06-14  6:13 ` [PATCH v6 25/26] udp: Remove rdelta port forwarding maps David Gibson
2024-06-14  6:13 ` [PATCH v6 26/26] udp: Eliminate 'splice' flag from epoll reference 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=20240614061348.3814736-2-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).