tcp: TCP Fast Open Server - header & support functions
This patch adds all the necessary data structure and support
functions to implement TFO server side. It also documents a number
of flags for the sysctl_tcp_fastopen knob, and adds a few Linux
extension MIBs.
In addition, it includes the following:
1. a new TCP_FASTOPEN socket option an application must call to
supply a max backlog allowed in order to enable TFO on its listener.
2. A number of key data structures:
"fastopen_rsk" in tcp_sock - for a big socket to access its
request_sock for retransmission and ack processing purpose. It is
non-NULL iff 3WHS not completed.
"fastopenq" in request_sock_queue - points to a per Fast Open
listener data structure "fastopen_queue" to keep track of qlen (# of
outstanding Fast Open requests) and max_qlen, among other things.
"listener" in tcp_request_sock - to point to the original listener
for book-keeping purpose, i.e., to maintain qlen against max_qlen
as part of defense against IP spoofing attack.
3. various data structure and functions, many in tcp_fastopen.c, to
support server side Fast Open cookie operations, including
/proc/sys/net/ipv4/tcp_fastopen_key to allow manual rekeying.
Signed-off-by: H.K. Jerry Chu <hkchu@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Tom Herbert <therbert@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 957acd1..8de53e1 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -263,6 +263,10 @@
SNMP_MIB_ITEM("TCPChallengeACK", LINUX_MIB_TCPCHALLENGEACK),
SNMP_MIB_ITEM("TCPSYNChallenge", LINUX_MIB_TCPSYNCHALLENGE),
SNMP_MIB_ITEM("TCPFastOpenActive", LINUX_MIB_TCPFASTOPENACTIVE),
+ SNMP_MIB_ITEM("TCPFastOpenPassive", LINUX_MIB_TCPFASTOPENPASSIVE),
+ SNMP_MIB_ITEM("TCPFastOpenPassiveFail", LINUX_MIB_TCPFASTOPENPASSIVEFAIL),
+ SNMP_MIB_ITEM("TCPFastOpenListenOverflow", LINUX_MIB_TCPFASTOPENLISTENOVERFLOW),
+ SNMP_MIB_ITEM("TCPFastOpenCookieReqd", LINUX_MIB_TCPFASTOPENCOOKIEREQD),
SNMP_MIB_SENTINEL
};
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 3e78c79b..9205e49 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -232,6 +232,45 @@
return 0;
}
+int proc_tcp_fastopen_key(ctl_table *ctl, int write, void __user *buffer,
+ size_t *lenp, loff_t *ppos)
+{
+ ctl_table tbl = { .maxlen = (TCP_FASTOPEN_KEY_LENGTH * 2 + 10) };
+ struct tcp_fastopen_context *ctxt;
+ int ret;
+ u32 user_key[4]; /* 16 bytes, matching TCP_FASTOPEN_KEY_LENGTH */
+
+ tbl.data = kmalloc(tbl.maxlen, GFP_KERNEL);
+ if (!tbl.data)
+ return -ENOMEM;
+
+ rcu_read_lock();
+ ctxt = rcu_dereference(tcp_fastopen_ctx);
+ if (ctxt)
+ memcpy(user_key, ctxt->key, TCP_FASTOPEN_KEY_LENGTH);
+ rcu_read_unlock();
+
+ snprintf(tbl.data, tbl.maxlen, "%08x-%08x-%08x-%08x",
+ user_key[0], user_key[1], user_key[2], user_key[3]);
+ ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
+
+ if (write && ret == 0) {
+ if (sscanf(tbl.data, "%x-%x-%x-%x", user_key, user_key + 1,
+ user_key + 2, user_key + 3) != 4) {
+ ret = -EINVAL;
+ goto bad_key;
+ }
+ tcp_fastopen_reset_cipher(user_key, TCP_FASTOPEN_KEY_LENGTH);
+ }
+
+bad_key:
+ pr_debug("proc FO key set 0x%x-%x-%x-%x <- 0x%s: %u\n",
+ user_key[0], user_key[1], user_key[2], user_key[3],
+ (char *)tbl.data, ret);
+ kfree(tbl.data);
+ return ret;
+}
+
static struct ctl_table ipv4_table[] = {
{
.procname = "tcp_timestamps",
@@ -386,6 +425,12 @@
.proc_handler = proc_dointvec,
},
{
+ .procname = "tcp_fastopen_key",
+ .mode = 0600,
+ .maxlen = ((TCP_FASTOPEN_KEY_LENGTH * 2) + 10),
+ .proc_handler = proc_tcp_fastopen_key,
+ },
+ {
.procname = "tcp_tw_recycle",
.data = &tcp_death_row.sysctl_tw_recycle,
.maxlen = sizeof(int),
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index a7f729c..8f7ef0a 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -1,10 +1,91 @@
+#include <linux/err.h>
#include <linux/init.h>
#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/tcp.h>
+#include <linux/rcupdate.h>
+#include <linux/rculist.h>
+#include <net/inetpeer.h>
+#include <net/tcp.h>
-int sysctl_tcp_fastopen;
+int sysctl_tcp_fastopen __read_mostly;
+
+struct tcp_fastopen_context __rcu *tcp_fastopen_ctx;
+
+static DEFINE_SPINLOCK(tcp_fastopen_ctx_lock);
+
+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);
+}
+
+int tcp_fastopen_reset_cipher(void *key, unsigned int len)
+{
+ int err;
+ struct tcp_fastopen_context *ctx, *octx;
+
+ 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;
+ }
+ 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);
+
+ spin_lock(&tcp_fastopen_ctx_lock);
+
+ octx = rcu_dereference_protected(tcp_fastopen_ctx,
+ lockdep_is_held(&tcp_fastopen_ctx_lock));
+ rcu_assign_pointer(tcp_fastopen_ctx, ctx);
+ spin_unlock(&tcp_fastopen_ctx_lock);
+
+ if (octx)
+ call_rcu(&octx->rcu, tcp_fastopen_ctx_free);
+ return err;
+}
+
+/* Computes the fastopen cookie for the peer.
+ * The peer address is a 128 bits long (pad with zeros for IPv4).
+ *
+ * The caller must check foc->len to determine if a valid cookie
+ * has been generated successfully.
+*/
+void tcp_fastopen_cookie_gen(__be32 addr, struct tcp_fastopen_cookie *foc)
+{
+ __be32 peer_addr[4] = { addr, 0, 0, 0 };
+ struct tcp_fastopen_context *ctx;
+
+ rcu_read_lock();
+ ctx = rcu_dereference(tcp_fastopen_ctx);
+ if (ctx) {
+ crypto_cipher_encrypt_one(ctx->tfm,
+ foc->val,
+ (__u8 *)peer_addr);
+ foc->len = TCP_FASTOPEN_COOKIE_SIZE;
+ }
+ rcu_read_unlock();
+}
static int __init tcp_fastopen_init(void)
{
+ __u8 key[TCP_FASTOPEN_KEY_LENGTH];
+
+ get_random_bytes(key, sizeof(key));
+ tcp_fastopen_reset_cipher(key, sizeof(key));
return 0;
}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index ce4ffe9..d47d5fe 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -378,7 +378,7 @@
/* 4. Try to fixup all. It is made immediately after connection enters
* established state.
*/
-static void tcp_init_buffer_space(struct sock *sk)
+void tcp_init_buffer_space(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
int maxwin;
@@ -4038,7 +4038,7 @@
}
/* When we get a reset we do this. */
-static void tcp_reset(struct sock *sk)
+void tcp_reset(struct sock *sk)
{
/* We want the right error as BSD sees it (and indeed as we do). */
switch (sk->sk_state) {