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 09/19] tcp: Obtain guest address from flowside
Date: Tue, 14 May 2024 11:03:27 +1000 [thread overview]
Message-ID: <20240514010337.1104606-10-david@gibson.dropbear.id.au> (raw)
In-Reply-To: <20240514010337.1104606-1-david@gibson.dropbear.id.au>
Currently we always deliver inbound TCP packets to the guest's most
recent observed IP address. This has the odd side effect that if the
guest changes its IP address with active TCP connections we might
deliver packets from old connections to the new address. That won't
work; it will probably result in an RST from the guest. Worse, if the
guest added a new address but also retains the old one, then we could
break those old connections by redirecting them to the new address.
Now that we maintain flowside information, we have a record of the correct
guest side address and can just use it.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
---
tcp.c | 47 ++++++++++++++++-------------------------------
1 file changed, 16 insertions(+), 31 deletions(-)
diff --git a/tcp.c b/tcp.c
index d4cd78c..078ec69 100644
--- a/tcp.c
+++ b/tcp.c
@@ -1327,7 +1327,6 @@ static void tcp_fill_header(struct tcphdr *th,
/**
* tcp_fill_headers4() - Fill 802.3, IPv4, TCP headers in pre-cooked buffers
- * @c: Execution context
* @conn: Connection pointer
* @taph: tap backend specific header
* @iph: Pointer to IPv4 header
@@ -1338,27 +1337,26 @@ static void tcp_fill_header(struct tcphdr *th,
*
* Return: The IPv4 payload length, host order
*/
-static size_t tcp_fill_headers4(const struct ctx *c,
- const struct tcp_tap_conn *conn,
+static size_t tcp_fill_headers4(const struct tcp_tap_conn *conn,
struct tap_hdr *taph,
struct iphdr *iph, struct tcphdr *th,
size_t dlen, const uint16_t *check,
uint32_t seq)
{
const struct flowside *tapside = TAPFLOW(conn);
- const struct in_addr *a4 = inany_v4(&tapside->faddr);
+ const struct in_addr *src4 = inany_v4(&tapside->faddr);
+ const struct in_addr *dst4 = inany_v4(&tapside->eaddr);
size_t l4len = dlen + sizeof(*th);
size_t l3len = l4len + sizeof(*iph);
- ASSERT(a4);
+ ASSERT(src4 && dst4);
iph->tot_len = htons(l3len);
- iph->saddr = a4->s_addr;
- iph->daddr = c->ip4.addr_seen.s_addr;
+ iph->saddr = src4->s_addr;
+ iph->daddr = dst4->s_addr;
iph->check = check ? *check :
- csum_ip4_header(l3len, IPPROTO_TCP,
- *a4, c->ip4.addr_seen);
+ csum_ip4_header(l3len, IPPROTO_TCP, *src4, *dst4);
tcp_fill_header(th, conn, seq);
@@ -1371,7 +1369,6 @@ static size_t tcp_fill_headers4(const struct ctx *c,
/**
* tcp_fill_headers6() - Fill 802.3, IPv6, TCP headers in pre-cooked buffers
- * @c: Execution context
* @conn: Connection pointer
* @taph: tap backend specific header
* @ip6h: Pointer to IPv6 header
@@ -1382,8 +1379,7 @@ static size_t tcp_fill_headers4(const struct ctx *c,
*
* Return: The IPv6 payload length, host order
*/
-static size_t tcp_fill_headers6(const struct ctx *c,
- const struct tcp_tap_conn *conn,
+static size_t tcp_fill_headers6(const struct tcp_tap_conn *conn,
struct tap_hdr *taph,
struct ipv6hdr *ip6h, struct tcphdr *th,
size_t dlen, uint32_t seq)
@@ -1393,10 +1389,7 @@ static size_t tcp_fill_headers6(const struct ctx *c,
ip6h->payload_len = htons(l4len);
ip6h->saddr = tapside->faddr.a6;
- if (IN6_IS_ADDR_LINKLOCAL(&ip6h->saddr))
- ip6h->daddr = c->ip6.addr_ll_seen;
- else
- ip6h->daddr = c->ip6.addr_seen;
+ ip6h->daddr = tapside->eaddr.a6;
ip6h->hop_limit = 255;
ip6h->version = 6;
@@ -1417,7 +1410,6 @@ static size_t tcp_fill_headers6(const struct ctx *c,
/**
* tcp_l2_buf_fill_headers() - Fill 802.3, IP, TCP headers in pre-cooked buffers
- * @c: Execution context
* @conn: Connection pointer
* @iov: Pointer to an array of iovec of TCP pre-cooked buffers
* @dlen: TCP payload length
@@ -1426,8 +1418,7 @@ static size_t tcp_fill_headers6(const struct ctx *c,
*
* Return: IP payload length, host order
*/
-static size_t tcp_l2_buf_fill_headers(const struct ctx *c,
- const struct tcp_tap_conn *conn,
+static size_t tcp_l2_buf_fill_headers(const struct tcp_tap_conn *conn,
struct iovec *iov, size_t dlen,
const uint16_t *check, uint32_t seq)
{
@@ -1435,13 +1426,13 @@ static size_t tcp_l2_buf_fill_headers(const struct ctx *c,
const struct in_addr *a4 = inany_v4(&tapside->faddr);
if (a4) {
- return tcp_fill_headers4(c, conn, iov[TCP_IOV_TAP].iov_base,
+ return tcp_fill_headers4(conn, iov[TCP_IOV_TAP].iov_base,
iov[TCP_IOV_IP].iov_base,
iov[TCP_IOV_PAYLOAD].iov_base, dlen,
check, seq);
}
- return tcp_fill_headers6(c, conn, iov[TCP_IOV_TAP].iov_base,
+ return tcp_fill_headers6(conn, iov[TCP_IOV_TAP].iov_base,
iov[TCP_IOV_IP].iov_base,
iov[TCP_IOV_PAYLOAD].iov_base, dlen,
seq);
@@ -1657,7 +1648,7 @@ static int tcp_send_flag(struct ctx *c, struct tcp_tap_conn *conn, int flags)
th->syn = !!(flags & SYN);
th->fin = !!(flags & FIN);
- l4len = tcp_l2_buf_fill_headers(c, conn, iov, optlen, NULL,
+ l4len = tcp_l2_buf_fill_headers(conn, iov, optlen, NULL,
conn->seq_to_tap);
iov[TCP_IOV_PAYLOAD].iov_len = l4len;
@@ -1757,17 +1748,11 @@ static void tcp_seq_init(const struct ctx *c, struct tcp_tap_conn *conn,
{
struct siphash_state state = SIPHASH_INIT(c->hash_secret);
const struct flowside *tapside = TAPFLOW(conn);
- union inany_addr aany;
uint64_t hash;
uint32_t ns;
- if (CONN_V4(conn))
- inany_from_af(&aany, AF_INET, &c->ip4.addr);
- else
- inany_from_af(&aany, AF_INET6, &c->ip6.addr);
-
inany_siphash_feed(&state, &tapside->faddr);
- inany_siphash_feed(&state, &aany);
+ inany_siphash_feed(&state, &tapside->eaddr);
hash = siphash_final(&state, 36,
(uint64_t)tapside->fport << 16 | tapside->eport);
@@ -2149,7 +2134,7 @@ static void tcp_data_to_tap(const struct ctx *c, struct tcp_tap_conn *conn,
tcp4_seq_update[tcp4_payload_used].len = dlen;
iov = tcp4_l2_iov[tcp4_payload_used++];
- l4len = tcp_l2_buf_fill_headers(c, conn, iov, dlen, check, seq);
+ l4len = tcp_l2_buf_fill_headers(conn, iov, dlen, check, seq);
iov[TCP_IOV_PAYLOAD].iov_len = l4len;
if (tcp4_payload_used > TCP_FRAMES_MEM - 1)
tcp_payload_flush(c);
@@ -2158,7 +2143,7 @@ static void tcp_data_to_tap(const struct ctx *c, struct tcp_tap_conn *conn,
tcp6_seq_update[tcp6_payload_used].len = dlen;
iov = tcp6_l2_iov[tcp6_payload_used++];
- l4len = tcp_l2_buf_fill_headers(c, conn, iov, dlen, NULL, seq);
+ l4len = tcp_l2_buf_fill_headers(conn, iov, dlen, NULL, seq);
iov[TCP_IOV_PAYLOAD].iov_len = l4len;
if (tcp6_payload_used > TCP_FRAMES_MEM - 1)
tcp_payload_flush(c);
--
@@ -1327,7 +1327,6 @@ static void tcp_fill_header(struct tcphdr *th,
/**
* tcp_fill_headers4() - Fill 802.3, IPv4, TCP headers in pre-cooked buffers
- * @c: Execution context
* @conn: Connection pointer
* @taph: tap backend specific header
* @iph: Pointer to IPv4 header
@@ -1338,27 +1337,26 @@ static void tcp_fill_header(struct tcphdr *th,
*
* Return: The IPv4 payload length, host order
*/
-static size_t tcp_fill_headers4(const struct ctx *c,
- const struct tcp_tap_conn *conn,
+static size_t tcp_fill_headers4(const struct tcp_tap_conn *conn,
struct tap_hdr *taph,
struct iphdr *iph, struct tcphdr *th,
size_t dlen, const uint16_t *check,
uint32_t seq)
{
const struct flowside *tapside = TAPFLOW(conn);
- const struct in_addr *a4 = inany_v4(&tapside->faddr);
+ const struct in_addr *src4 = inany_v4(&tapside->faddr);
+ const struct in_addr *dst4 = inany_v4(&tapside->eaddr);
size_t l4len = dlen + sizeof(*th);
size_t l3len = l4len + sizeof(*iph);
- ASSERT(a4);
+ ASSERT(src4 && dst4);
iph->tot_len = htons(l3len);
- iph->saddr = a4->s_addr;
- iph->daddr = c->ip4.addr_seen.s_addr;
+ iph->saddr = src4->s_addr;
+ iph->daddr = dst4->s_addr;
iph->check = check ? *check :
- csum_ip4_header(l3len, IPPROTO_TCP,
- *a4, c->ip4.addr_seen);
+ csum_ip4_header(l3len, IPPROTO_TCP, *src4, *dst4);
tcp_fill_header(th, conn, seq);
@@ -1371,7 +1369,6 @@ static size_t tcp_fill_headers4(const struct ctx *c,
/**
* tcp_fill_headers6() - Fill 802.3, IPv6, TCP headers in pre-cooked buffers
- * @c: Execution context
* @conn: Connection pointer
* @taph: tap backend specific header
* @ip6h: Pointer to IPv6 header
@@ -1382,8 +1379,7 @@ static size_t tcp_fill_headers4(const struct ctx *c,
*
* Return: The IPv6 payload length, host order
*/
-static size_t tcp_fill_headers6(const struct ctx *c,
- const struct tcp_tap_conn *conn,
+static size_t tcp_fill_headers6(const struct tcp_tap_conn *conn,
struct tap_hdr *taph,
struct ipv6hdr *ip6h, struct tcphdr *th,
size_t dlen, uint32_t seq)
@@ -1393,10 +1389,7 @@ static size_t tcp_fill_headers6(const struct ctx *c,
ip6h->payload_len = htons(l4len);
ip6h->saddr = tapside->faddr.a6;
- if (IN6_IS_ADDR_LINKLOCAL(&ip6h->saddr))
- ip6h->daddr = c->ip6.addr_ll_seen;
- else
- ip6h->daddr = c->ip6.addr_seen;
+ ip6h->daddr = tapside->eaddr.a6;
ip6h->hop_limit = 255;
ip6h->version = 6;
@@ -1417,7 +1410,6 @@ static size_t tcp_fill_headers6(const struct ctx *c,
/**
* tcp_l2_buf_fill_headers() - Fill 802.3, IP, TCP headers in pre-cooked buffers
- * @c: Execution context
* @conn: Connection pointer
* @iov: Pointer to an array of iovec of TCP pre-cooked buffers
* @dlen: TCP payload length
@@ -1426,8 +1418,7 @@ static size_t tcp_fill_headers6(const struct ctx *c,
*
* Return: IP payload length, host order
*/
-static size_t tcp_l2_buf_fill_headers(const struct ctx *c,
- const struct tcp_tap_conn *conn,
+static size_t tcp_l2_buf_fill_headers(const struct tcp_tap_conn *conn,
struct iovec *iov, size_t dlen,
const uint16_t *check, uint32_t seq)
{
@@ -1435,13 +1426,13 @@ static size_t tcp_l2_buf_fill_headers(const struct ctx *c,
const struct in_addr *a4 = inany_v4(&tapside->faddr);
if (a4) {
- return tcp_fill_headers4(c, conn, iov[TCP_IOV_TAP].iov_base,
+ return tcp_fill_headers4(conn, iov[TCP_IOV_TAP].iov_base,
iov[TCP_IOV_IP].iov_base,
iov[TCP_IOV_PAYLOAD].iov_base, dlen,
check, seq);
}
- return tcp_fill_headers6(c, conn, iov[TCP_IOV_TAP].iov_base,
+ return tcp_fill_headers6(conn, iov[TCP_IOV_TAP].iov_base,
iov[TCP_IOV_IP].iov_base,
iov[TCP_IOV_PAYLOAD].iov_base, dlen,
seq);
@@ -1657,7 +1648,7 @@ static int tcp_send_flag(struct ctx *c, struct tcp_tap_conn *conn, int flags)
th->syn = !!(flags & SYN);
th->fin = !!(flags & FIN);
- l4len = tcp_l2_buf_fill_headers(c, conn, iov, optlen, NULL,
+ l4len = tcp_l2_buf_fill_headers(conn, iov, optlen, NULL,
conn->seq_to_tap);
iov[TCP_IOV_PAYLOAD].iov_len = l4len;
@@ -1757,17 +1748,11 @@ static void tcp_seq_init(const struct ctx *c, struct tcp_tap_conn *conn,
{
struct siphash_state state = SIPHASH_INIT(c->hash_secret);
const struct flowside *tapside = TAPFLOW(conn);
- union inany_addr aany;
uint64_t hash;
uint32_t ns;
- if (CONN_V4(conn))
- inany_from_af(&aany, AF_INET, &c->ip4.addr);
- else
- inany_from_af(&aany, AF_INET6, &c->ip6.addr);
-
inany_siphash_feed(&state, &tapside->faddr);
- inany_siphash_feed(&state, &aany);
+ inany_siphash_feed(&state, &tapside->eaddr);
hash = siphash_final(&state, 36,
(uint64_t)tapside->fport << 16 | tapside->eport);
@@ -2149,7 +2134,7 @@ static void tcp_data_to_tap(const struct ctx *c, struct tcp_tap_conn *conn,
tcp4_seq_update[tcp4_payload_used].len = dlen;
iov = tcp4_l2_iov[tcp4_payload_used++];
- l4len = tcp_l2_buf_fill_headers(c, conn, iov, dlen, check, seq);
+ l4len = tcp_l2_buf_fill_headers(conn, iov, dlen, check, seq);
iov[TCP_IOV_PAYLOAD].iov_len = l4len;
if (tcp4_payload_used > TCP_FRAMES_MEM - 1)
tcp_payload_flush(c);
@@ -2158,7 +2143,7 @@ static void tcp_data_to_tap(const struct ctx *c, struct tcp_tap_conn *conn,
tcp6_seq_update[tcp6_payload_used].len = dlen;
iov = tcp6_l2_iov[tcp6_payload_used++];
- l4len = tcp_l2_buf_fill_headers(c, conn, iov, dlen, NULL, seq);
+ l4len = tcp_l2_buf_fill_headers(conn, iov, dlen, NULL, seq);
iov[TCP_IOV_PAYLOAD].iov_len = l4len;
if (tcp6_payload_used > TCP_FRAMES_MEM - 1)
tcp_payload_flush(c);
--
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 ` David Gibson [this message]
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 ` [PATCH v5 12/19] tcp, flow: Replace TCP specific hash function with general flow hash David Gibson
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=20240514010337.1104606-10-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).