From 244b2c5ca8b14627e4a17755e5922221e121c771 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Wed, 09 Oct 2024 06:15:07 +0000
Subject: [PATCH] change system file
---
kernel/net/ipv4/tcp_fastopen.c | 245 ++++++++++++++++++++++++++++++------------------
1 files changed, 154 insertions(+), 91 deletions(-)
diff --git a/kernel/net/ipv4/tcp_fastopen.c b/kernel/net/ipv4/tcp_fastopen.c
index 119d2c2..92d63cf 100644
--- a/kernel/net/ipv4/tcp_fastopen.c
+++ b/kernel/net/ipv4/tcp_fastopen.c
@@ -30,15 +30,15 @@
* for a valid cookie, so this is an acceptable risk.
*/
get_random_bytes(key, sizeof(key));
- tcp_fastopen_reset_cipher(net, NULL, key, sizeof(key));
+ tcp_fastopen_reset_cipher(net, NULL, key, NULL);
}
static void tcp_fastopen_ctx_free(struct rcu_head *head)
{
struct tcp_fastopen_context *ctx =
container_of(head, struct tcp_fastopen_context, rcu);
- crypto_free_cipher(ctx->tfm);
- kfree(ctx);
+
+ kfree_sensitive(ctx);
}
void tcp_fastopen_destroy_cipher(struct sock *sk)
@@ -67,31 +67,27 @@
}
int tcp_fastopen_reset_cipher(struct net *net, struct sock *sk,
- void *key, unsigned int len)
+ void *primary_key, void *backup_key)
{
struct tcp_fastopen_context *ctx, *octx;
struct fastopen_queue *q;
- int err;
+ int err = 0;
ctx = kmalloc(sizeof(*ctx), GFP_KERNEL);
- if (!ctx)
- return -ENOMEM;
- ctx->tfm = crypto_alloc_cipher("aes", 0, 0);
-
- if (IS_ERR(ctx->tfm)) {
- err = PTR_ERR(ctx->tfm);
-error: kfree(ctx);
- pr_err("TCP: TFO aes cipher alloc error: %d\n", err);
- return err;
+ if (!ctx) {
+ err = -ENOMEM;
+ goto out;
}
- err = crypto_cipher_setkey(ctx->tfm, key, len);
- if (err) {
- pr_err("TCP: TFO cipher key error: %d\n", err);
- crypto_free_cipher(ctx->tfm);
- goto error;
- }
- memcpy(ctx->key, key, len);
+ ctx->key[0].key[0] = get_unaligned_le64(primary_key);
+ ctx->key[0].key[1] = get_unaligned_le64(primary_key + 8);
+ if (backup_key) {
+ ctx->key[1].key[0] = get_unaligned_le64(backup_key);
+ ctx->key[1].key[1] = get_unaligned_le64(backup_key + 8);
+ ctx->num = 2;
+ } else {
+ ctx->num = 1;
+ }
spin_lock(&net->ipv4.tcp_fastopen_ctx_lock);
if (sk) {
@@ -108,66 +104,81 @@
if (octx)
call_rcu(&octx->rcu, tcp_fastopen_ctx_free);
+out:
return err;
}
-static bool __tcp_fastopen_cookie_gen(struct sock *sk, const void *path,
- struct tcp_fastopen_cookie *foc)
+int tcp_fastopen_get_cipher(struct net *net, struct inet_connection_sock *icsk,
+ u64 *key)
{
struct tcp_fastopen_context *ctx;
- bool ok = false;
+ int n_keys = 0, i;
rcu_read_lock();
-
- ctx = rcu_dereference(inet_csk(sk)->icsk_accept_queue.fastopenq.ctx);
- if (!ctx)
- ctx = rcu_dereference(sock_net(sk)->ipv4.tcp_fastopen_ctx);
-
+ if (icsk)
+ ctx = rcu_dereference(icsk->icsk_accept_queue.fastopenq.ctx);
+ else
+ ctx = rcu_dereference(net->ipv4.tcp_fastopen_ctx);
if (ctx) {
- crypto_cipher_encrypt_one(ctx->tfm, foc->val, path);
- foc->len = TCP_FASTOPEN_COOKIE_SIZE;
- ok = true;
+ n_keys = tcp_fastopen_context_len(ctx);
+ for (i = 0; i < n_keys; i++) {
+ put_unaligned_le64(ctx->key[i].key[0], key + (i * 2));
+ put_unaligned_le64(ctx->key[i].key[1], key + (i * 2) + 1);
+ }
}
rcu_read_unlock();
- return ok;
+
+ return n_keys;
}
-/* Generate the fastopen cookie by doing aes128 encryption on both
- * the source and destination addresses. Pad 0s for IPv4 or IPv4-mapped-IPv6
- * addresses. For the longer IPv6 addresses use CBC-MAC.
- *
- * XXX (TFO) - refactor when TCP_FASTOPEN_COOKIE_SIZE != AES_BLOCK_SIZE.
- */
-static bool tcp_fastopen_cookie_gen(struct sock *sk,
- struct request_sock *req,
- struct sk_buff *syn,
- struct tcp_fastopen_cookie *foc)
+static bool __tcp_fastopen_cookie_gen_cipher(struct request_sock *req,
+ struct sk_buff *syn,
+ const siphash_key_t *key,
+ struct tcp_fastopen_cookie *foc)
{
+ BUILD_BUG_ON(TCP_FASTOPEN_COOKIE_SIZE != sizeof(u64));
+
if (req->rsk_ops->family == AF_INET) {
const struct iphdr *iph = ip_hdr(syn);
- __be32 path[4] = { iph->saddr, iph->daddr, 0, 0 };
- return __tcp_fastopen_cookie_gen(sk, path, foc);
+ foc->val[0] = cpu_to_le64(siphash(&iph->saddr,
+ sizeof(iph->saddr) +
+ sizeof(iph->daddr),
+ key));
+ foc->len = TCP_FASTOPEN_COOKIE_SIZE;
+ return true;
}
-
#if IS_ENABLED(CONFIG_IPV6)
if (req->rsk_ops->family == AF_INET6) {
const struct ipv6hdr *ip6h = ipv6_hdr(syn);
- struct tcp_fastopen_cookie tmp;
- if (__tcp_fastopen_cookie_gen(sk, &ip6h->saddr, &tmp)) {
- struct in6_addr *buf = &tmp.addr;
- int i;
-
- for (i = 0; i < 4; i++)
- buf->s6_addr32[i] ^= ip6h->daddr.s6_addr32[i];
- return __tcp_fastopen_cookie_gen(sk, buf, foc);
- }
+ foc->val[0] = cpu_to_le64(siphash(&ip6h->saddr,
+ sizeof(ip6h->saddr) +
+ sizeof(ip6h->daddr),
+ key));
+ foc->len = TCP_FASTOPEN_COOKIE_SIZE;
+ return true;
}
#endif
return false;
}
+/* Generate the fastopen cookie by applying SipHash to both the source and
+ * destination addresses.
+ */
+static void tcp_fastopen_cookie_gen(struct sock *sk,
+ struct request_sock *req,
+ struct sk_buff *syn,
+ struct tcp_fastopen_cookie *foc)
+{
+ struct tcp_fastopen_context *ctx;
+
+ rcu_read_lock();
+ ctx = tcp_fastopen_get_ctx(sk);
+ if (ctx)
+ __tcp_fastopen_cookie_gen_cipher(req, syn, &ctx->key[0], foc);
+ rcu_read_unlock();
+}
/* If an incoming SYN or SYNACK frame contains a payload and/or FIN,
* queue this additional data / FIN.
@@ -212,6 +223,35 @@
tcp_fin(sk);
}
+/* returns 0 - no key match, 1 for primary, 2 for backup */
+static int tcp_fastopen_cookie_gen_check(struct sock *sk,
+ struct request_sock *req,
+ struct sk_buff *syn,
+ struct tcp_fastopen_cookie *orig,
+ struct tcp_fastopen_cookie *valid_foc)
+{
+ struct tcp_fastopen_cookie search_foc = { .len = -1 };
+ struct tcp_fastopen_cookie *foc = valid_foc;
+ struct tcp_fastopen_context *ctx;
+ int i, ret = 0;
+
+ rcu_read_lock();
+ ctx = tcp_fastopen_get_ctx(sk);
+ if (!ctx)
+ goto out;
+ for (i = 0; i < tcp_fastopen_context_len(ctx); i++) {
+ __tcp_fastopen_cookie_gen_cipher(req, syn, &ctx->key[i], foc);
+ if (tcp_fastopen_cookie_match(foc, orig)) {
+ ret = i + 1;
+ goto out;
+ }
+ foc = &search_foc;
+ }
+out:
+ rcu_read_unlock();
+ return ret;
+}
+
static struct sock *tcp_fastopen_create_child(struct sock *sk,
struct sk_buff *skb,
struct request_sock *req)
@@ -220,10 +260,6 @@
struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
struct sock *child;
bool own_req;
-
- req->num_retrans = 0;
- req->num_timeout = 0;
- req->sk = NULL;
child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL,
NULL, &own_req);
@@ -240,7 +276,7 @@
*/
tp = tcp_sk(child);
- tp->fastopen_rsk = req;
+ rcu_assign_pointer(tp->fastopen_rsk, req);
tcp_rsk(req)->tfo_listener = true;
/* RFC1323: The window in SYN & SYN/ACK segments is never
@@ -259,7 +295,7 @@
refcount_set(&req->rsk_refcnt, 2);
/* Now finish processing the fastopen child socket. */
- tcp_init_transfer(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB);
+ tcp_init_transfer(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB, skb);
tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
@@ -276,6 +312,7 @@
static bool tcp_fastopen_queue_check(struct sock *sk)
{
struct fastopen_queue *fastopenq;
+ int max_qlen;
/* Make sure the listener has enabled fastopen, and we don't
* exceed the max # of pending TFO requests allowed before trying
@@ -288,10 +325,11 @@
* temporarily vs a server not supporting Fast Open at all.
*/
fastopenq = &inet_csk(sk)->icsk_accept_queue.fastopenq;
- if (fastopenq->max_qlen == 0)
+ max_qlen = READ_ONCE(fastopenq->max_qlen);
+ if (max_qlen == 0)
return false;
- if (fastopenq->qlen >= fastopenq->max_qlen) {
+ if (fastopenq->qlen >= max_qlen) {
struct request_sock *req1;
spin_lock(&fastopenq->lock);
req1 = fastopenq->rskq_rst_head;
@@ -313,7 +351,7 @@
const struct dst_entry *dst,
int flag)
{
- return (sock_net(sk)->ipv4.sysctl_tcp_fastopen & flag) ||
+ return (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen) & flag) ||
tcp_sk(sk)->fastopen_no_cookie ||
(dst && dst_metric(dst, RTAX_FASTOPEN_NO_COOKIE));
}
@@ -328,9 +366,10 @@
const struct dst_entry *dst)
{
bool syn_data = TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1;
- int tcp_fastopen = sock_net(sk)->ipv4.sysctl_tcp_fastopen;
+ int tcp_fastopen = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen);
struct tcp_fastopen_cookie valid_foc = { .len = -1 };
struct sock *child;
+ int ret = 0;
if (foc->len == 0) /* Client requests a cookie */
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENCOOKIEREQD);
@@ -345,31 +384,44 @@
if (tcp_fastopen_no_cookie(sk, dst, TFO_SERVER_COOKIE_NOT_REQD))
goto fastopen;
- if (foc->len >= 0 && /* Client presents or requests a cookie */
- tcp_fastopen_cookie_gen(sk, req, skb, &valid_foc) &&
- foc->len == TCP_FASTOPEN_COOKIE_SIZE &&
- foc->len == valid_foc.len &&
- !memcmp(foc->val, valid_foc.val, foc->len)) {
- /* Cookie is valid. Create a (full) child socket to accept
- * the data in SYN before returning a SYN-ACK to ack the
- * data. If we fail to create the socket, fall back and
- * ack the ISN only but includes the same cookie.
- *
- * Note: Data-less SYN with valid cookie is allowed to send
- * data in SYN_RECV state.
- */
-fastopen:
- child = tcp_fastopen_create_child(sk, skb, req);
- if (child) {
- foc->len = -1;
+ if (foc->len == 0) {
+ /* Client requests a cookie. */
+ tcp_fastopen_cookie_gen(sk, req, skb, &valid_foc);
+ } else if (foc->len > 0) {
+ ret = tcp_fastopen_cookie_gen_check(sk, req, skb, foc,
+ &valid_foc);
+ if (!ret) {
NET_INC_STATS(sock_net(sk),
- LINUX_MIB_TCPFASTOPENPASSIVE);
- return child;
+ LINUX_MIB_TCPFASTOPENPASSIVEFAIL);
+ } else {
+ /* Cookie is valid. Create a (full) child socket to
+ * accept the data in SYN before returning a SYN-ACK to
+ * ack the data. If we fail to create the socket, fall
+ * back and ack the ISN only but includes the same
+ * cookie.
+ *
+ * Note: Data-less SYN with valid cookie is allowed to
+ * send data in SYN_RECV state.
+ */
+fastopen:
+ child = tcp_fastopen_create_child(sk, skb, req);
+ if (child) {
+ if (ret == 2) {
+ valid_foc.exp = foc->exp;
+ *foc = valid_foc;
+ NET_INC_STATS(sock_net(sk),
+ LINUX_MIB_TCPFASTOPENPASSIVEALTKEY);
+ } else {
+ foc->len = -1;
+ }
+ NET_INC_STATS(sock_net(sk),
+ LINUX_MIB_TCPFASTOPENPASSIVE);
+ return child;
+ }
+ NET_INC_STATS(sock_net(sk),
+ LINUX_MIB_TCPFASTOPENPASSIVEFAIL);
}
- NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENPASSIVEFAIL);
- } else if (foc->len > 0) /* Client presents an invalid cookie */
- NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENPASSIVEFAIL);
-
+ }
valid_foc.exp = foc->exp;
*foc = valid_foc;
return NULL;
@@ -394,7 +446,10 @@
cookie->len = -1;
return true;
}
- return cookie->len > 0;
+ if (cookie->len > 0)
+ return true;
+ tcp_sk(sk)->fastopen_client_fail = TFO_COOKIE_UNAVAILABLE;
+ return false;
}
/* This function checks if we want to defer sending SYN until the first
@@ -453,6 +508,9 @@
{
struct net *net = sock_net(sk);
+ if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout))
+ return;
+
/* Paired with READ_ONCE() in tcp_fastopen_active_should_disable() */
WRITE_ONCE(net->ipv4.tfo_active_disable_stamp, jiffies);
@@ -471,11 +529,16 @@
*/
bool tcp_fastopen_active_should_disable(struct sock *sk)
{
- unsigned int tfo_bh_timeout = sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout;
- int tfo_da_times = atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times);
+ unsigned int tfo_bh_timeout =
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout);
unsigned long timeout;
+ int tfo_da_times;
int multiplier;
+ if (!tfo_bh_timeout)
+ return false;
+
+ tfo_da_times = atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times);
if (!tfo_da_times)
return false;
--
Gitblit v1.6.2