Re: [net-next-2.6 PATCH v6 4/7 RFC] TCPCT part 1d: define TCP cookie option, extend existing struct's

[William Allen Simpson <william.allen.simpson@gmail.com>]

[-- Attachment #1: Type: text/plain, Size: 1918 bytes --]

Eric Dumazet wrote:
> William Allen Simpson a écrit :
>> There is nothing yet in this patch series to send data with a SYN.  Back in
>> early October, David required that the various s_data and cookie structures
>> be compressed and consolidated.  So, for the client side, the cookie_*
>> fields are filled and the s_data_* fields are zero (ignored), while the
>> server side can have both filled.
>>
>> Moreover, *this* patch does nothing other than allocate and deallocate the
>> structure, zero filled by kzalloc().
>>
>> SYN data will be implemented (much) later.
> 
> okay
> 
Still no technical corrections.  Seeking Acks.

Trying to get review back on track.  The patch is still the same.

This patch allocates and deallocates the structures.  One main
difference (off the top of my head) from Alan's original patch is
that it uses sk->sk_allocation instead of GFP_ATOMIC in a couple of
places.  David Miller wanted to reduce the number of atomic
allocations, and sk->sk_allocation can be GFP_KERNEL or GFP_ATOMIC.

AFAICT, it's usually GFP_KERNEL in both tcp_v4_init_sock() and
tcp_v6_init_sock(), as they're called by inet_create() via
sk->sk_prot->init() shortly after calling sock_init_data() that set
sk->sk_allocation to GFP_KERNEL.

I used the existing variable just in case there are other code paths
that I've missed, and just in case there are future changes adding
code paths.

Limited multiple (=) assignments to only 2 per line for readability
(that in existing code have 4 per line and run well beyond 80
characters, triggering a warning in scripts/checkpatch.pl).

Data structures are carefully composed to require minimal additions.
For example, the struct tcp_options_received cookie_plus variable fits
between existing 16-bit and 8-bit variables, requiring no additional
space (taking alignment into consideration).  There are no additions to
tcp_request_sock, and only 1 pointer in tcp_sock.


[-- Attachment #2: TCPCT+1d6++.patch --]
[-- Type: text/plain, Size: 10948 bytes --]

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index eaa3113..7fee8a4 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -247,31 +247,38 @@ struct tcp_options_received {
 		sack_ok : 4,	/* SACK seen on SYN packet		*/
 		snd_wscale : 4,	/* Window scaling received from sender	*/
 		rcv_wscale : 4;	/* Window scaling to send to receiver	*/
-/*	SACKs data	*/
+	u8	cookie_plus:6,	/* bytes in authenticator/cookie option	*/
+		cookie_out_never:1,
+		cookie_in_always:1;
 	u8	num_sacks;	/* Number of SACK blocks		*/
-	u16	user_mss;  	/* mss requested by user in ioctl */
+	u16	user_mss;	/* mss requested by user in ioctl	*/
 	u16	mss_clamp;	/* Maximal mss, negotiated at connection setup */
 };
 
 static inline void tcp_clear_options(struct tcp_options_received *rx_opt)
 {
-	rx_opt->tstamp_ok = rx_opt->sack_ok = rx_opt->wscale_ok = rx_opt->snd_wscale = 0;
+	rx_opt->tstamp_ok = rx_opt->sack_ok = 0;
+	rx_opt->wscale_ok = rx_opt->snd_wscale = 0;
+	rx_opt->cookie_plus = 0;
 }
 
 /* This is the max number of SACKS that we'll generate and process. It's safe
- * to increse this, although since:
+ * to increase this, although since:
  *   size = TCPOLEN_SACK_BASE_ALIGNED (4) + n * TCPOLEN_SACK_PERBLOCK (8)
  * only four options will fit in a standard TCP header */
 #define TCP_NUM_SACKS 4
 
+struct tcp_cookie_values;
+struct tcp_request_sock_ops;
+
 struct tcp_request_sock {
 	struct inet_request_sock 	req;
 #ifdef CONFIG_TCP_MD5SIG
 	/* Only used by TCP MD5 Signature so far. */
 	const struct tcp_request_sock_ops *af_specific;
 #endif
-	u32			 	rcv_isn;
-	u32			 	snt_isn;
+	u32				rcv_isn;
+	u32				snt_isn;
 };
 
 static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req)
@@ -441,6 +448,12 @@ struct tcp_sock {
 /* TCP MD5 Signature Option information */
 	struct tcp_md5sig_info	*md5sig_info;
 #endif
+
+	/* When the cookie options are generated and exchanged, then this
+	 * object holds a reference to them (cookie_values->kref).  Also
+	 * contains related tcp_cookie_transactions fields.
+	 */
+	struct tcp_cookie_values  *cookie_values;
 };
 
 static inline struct tcp_sock *tcp_sk(const struct sock *sk)
@@ -459,6 +472,10 @@ struct tcp_timewait_sock {
 	u16			  tw_md5_keylen;
 	u8			  tw_md5_key[TCP_MD5SIG_MAXKEYLEN];
 #endif
+	/* Few sockets in timewait have cookies; in that case, then this
+	 * object holds a reference to them (tw_cookie_values->kref).
+	 */
+	struct tcp_cookie_values  *tw_cookie_values;
 };
 
 static inline struct tcp_timewait_sock *tcp_twsk(const struct sock *sk)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 738b65f..f9abd9b 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -30,6 +30,7 @@
 #include <linux/dmaengine.h>
 #include <linux/crypto.h>
 #include <linux/cryptohash.h>
+#include <linux/kref.h>
 
 #include <net/inet_connection_sock.h>
 #include <net/inet_timewait_sock.h>
@@ -164,6 +165,7 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo);
 #define TCPOPT_SACK             5       /* SACK Block */
 #define TCPOPT_TIMESTAMP	8	/* Better RTT estimations/PAWS */
 #define TCPOPT_MD5SIG		19	/* MD5 Signature (RFC2385) */
+#define TCPOPT_COOKIE		253	/* Cookie extension (experimental) */
 
 /*
  *     TCP option lengths
@@ -174,6 +176,10 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo);
 #define TCPOLEN_SACK_PERM      2
 #define TCPOLEN_TIMESTAMP      10
 #define TCPOLEN_MD5SIG         18
+#define TCPOLEN_COOKIE_BASE    2	/* Cookie-less header extension */
+#define TCPOLEN_COOKIE_PAIR    3	/* Cookie pair header extension */
+#define TCPOLEN_COOKIE_MIN     (TCPOLEN_COOKIE_BASE+TCP_COOKIE_MIN)
+#define TCPOLEN_COOKIE_MAX     (TCPOLEN_COOKIE_BASE+TCP_COOKIE_MAX)
 
 /* But this is what stacks really send out. */
 #define TCPOLEN_TSTAMP_ALIGNED		12
@@ -1482,6 +1488,83 @@ struct tcp_request_sock_ops {
 
 extern int tcp_cookie_generator(u32 *bakery);
 
+/**
+ *	struct tcp_cookie_values - each socket needs extra space for the
+ *	cookies, together with (optional) space for any SYN data.
+ *
+ *	A tcp_sock contains a pointer to the current value, and this is
+ *	cloned to the tcp_timewait_sock.
+ *
+ * @cookie_pair:	variable data from the option exchange.
+ *
+ * @cookie_desired:	user specified tcpct_cookie_desired.  Zero
+ *			indicates default (sysctl_tcp_cookie_size).
+ *			After cookie sent, remembers size of cookie.
+ *			Range 0, TCP_COOKIE_MIN to TCP_COOKIE_MAX.
+ *
+ * @s_data_desired:	user specified tcpct_s_data_desired.  When the
+ *			constant payload is specified (@s_data_constant),
+ *			holds its length instead.
+ *			Range 0 to TCP_MSS_DESIRED.
+ *
+ * @s_data_payload:	constant data that is to be included in the
+ *			payload of SYN or SYNACK segments when the
+ *			cookie option is present.
+ */
+struct tcp_cookie_values {
+	struct kref	kref;
+	u8		cookie_pair[TCP_COOKIE_PAIR_SIZE];
+	u8		cookie_pair_size;
+	u8		cookie_desired;
+	u16		s_data_desired:11,
+			s_data_constant:1,
+			s_data_in:1,
+			s_data_out:1,
+			s_data_unused:2;
+	u8		s_data_payload[0];
+};
+
+static inline void tcp_cookie_values_release(struct kref *kref)
+{
+	kfree(container_of(kref, struct tcp_cookie_values, kref));
+}
+
+/* The length of constant payload data.  Note that s_data_desired is
+ * overloaded, depending on s_data_constant: either the length of constant
+ * data (returned here) or the limit on variable data.
+ */
+static inline int tcp_s_data_size(const struct tcp_sock *tp)
+{
+	return (tp->cookie_values != NULL && tp->cookie_values->s_data_constant)
+		? tp->cookie_values->s_data_desired
+		: 0;
+}
+
+/**
+ *	struct tcp_extend_values - tcp_ipv?.c to tcp_output.c workspace.
+ *
+ *	As tcp_request_sock has already been extended in other places, the
+ *	only remaining method is to pass stack values along as function
+ *	parameters.  These parameters are not needed after sending SYNACK.
+ *
+ * @cookie_bakery:	cryptographic secret and message workspace.
+ *
+ * @cookie_plus:	bytes in authenticator/cookie option, copied from
+ *			struct tcp_options_received (above).
+ */
+struct tcp_extend_values {
+	struct request_values		rv;
+	u32				cookie_bakery[COOKIE_WORKSPACE_WORDS];
+	u8				cookie_plus:6,
+					cookie_out_never:1,
+					cookie_in_always:1;
+};
+
+static inline struct tcp_extend_values *tcp_xv(struct request_values *rvp)
+{
+	return (struct tcp_extend_values *)rvp;
+}
+
 extern void tcp_v4_init(void);
 extern void tcp_init(void);
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 397ab8f..2bb7864 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1834,6 +1834,19 @@ static int tcp_v4_init_sock(struct sock *sk)
 	tp->af_specific = &tcp_sock_ipv4_specific;
 #endif
 
+	/* TCP Cookie Transactions */
+	if (sysctl_tcp_cookie_size > 0) {
+		/* Default, cookies without s_data_payload. */
+		tp->cookie_values =
+			kzalloc(sizeof(*tp->cookie_values),
+				sk->sk_allocation);
+		if (tp->cookie_values != NULL)
+			kref_init(&tp->cookie_values->kref);
+	}
+	/* Presumed zeroed, in order of appearance:
+	 *	cookie_in_always, cookie_out_never,
+	 *	s_data_constant, s_data_in, s_data_out
+	 */
 	sk->sk_sndbuf = sysctl_tcp_wmem[1];
 	sk->sk_rcvbuf = sysctl_tcp_rmem[1];
 
@@ -1887,6 +1900,13 @@ void tcp_v4_destroy_sock(struct sock *sk)
 		sk->sk_sndmsg_page = NULL;
 	}
 
+	/* TCP Cookie Transactions */
+	if (tp->cookie_values != NULL) {
+		kref_put(&tp->cookie_values->kref,
+			 tcp_cookie_values_release);
+		tp->cookie_values = NULL;
+	}
+
 	percpu_counter_dec(&tcp_sockets_allocated);
 }
 
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 7a42990..53ef6d8 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -389,14 +389,43 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
 		const struct inet_request_sock *ireq = inet_rsk(req);
 		struct tcp_request_sock *treq = tcp_rsk(req);
 		struct inet_connection_sock *newicsk = inet_csk(newsk);
-		struct tcp_sock *newtp;
+		struct tcp_sock *newtp = tcp_sk(newsk);
+		struct tcp_sock *oldtp = tcp_sk(sk);
+		struct tcp_cookie_values *oldcvp = oldtp->cookie_values;
+
+		/* TCP Cookie Transactions require space for the cookie pair,
+		 * as it differs for each connection.  There is no need to
+		 * copy any s_data_payload stored at the original socket.
+		 * Failure will prevent resuming the connection.
+		 *
+		 * Presumed copied, in order of appearance:
+		 *	cookie_in_always, cookie_out_never
+		 */
+		if (oldcvp != NULL) {
+			struct tcp_cookie_values *newcvp =
+				kzalloc(sizeof(*newtp->cookie_values),
+					GFP_ATOMIC);
+
+			if (newcvp != NULL) {
+				kref_init(&newcvp->kref);
+				newcvp->cookie_desired =
+						oldcvp->cookie_desired;
+				newtp->cookie_values = newcvp;
+			} else {
+				/* Not Yet Implemented */
+				newtp->cookie_values = NULL;
+			}
+		}
 
 		/* Now setup tcp_sock */
-		newtp = tcp_sk(newsk);
 		newtp->pred_flags = 0;
-		newtp->rcv_wup = newtp->copied_seq = newtp->rcv_nxt = treq->rcv_isn + 1;
-		newtp->snd_sml = newtp->snd_una = newtp->snd_nxt = treq->snt_isn + 1;
-		newtp->snd_up = treq->snt_isn + 1;
+
+		newtp->rcv_wup = newtp->copied_seq =
+		newtp->rcv_nxt = treq->rcv_isn + 1;
+
+		newtp->snd_sml = newtp->snd_una =
+		newtp->snd_nxt = newtp->snd_up =
+			treq->snt_isn + 1 + tcp_s_data_size(oldtp);
 
 		tcp_prequeue_init(newtp);
 
@@ -429,8 +458,8 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
 		tcp_set_ca_state(newsk, TCP_CA_Open);
 		tcp_init_xmit_timers(newsk);
 		skb_queue_head_init(&newtp->out_of_order_queue);
-		newtp->write_seq = treq->snt_isn + 1;
-		newtp->pushed_seq = newtp->write_seq;
+		newtp->write_seq = newtp->pushed_seq =
+			treq->snt_isn + 1 + tcp_s_data_size(oldtp);
 
 		newtp->rx_opt.saw_tstamp = 0;
 
@@ -596,7 +625,8 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 	 * Invalid ACK: reset will be sent by listening socket
 	 */
 	if ((flg & TCP_FLAG_ACK) &&
-	    (TCP_SKB_CB(skb)->ack_seq != tcp_rsk(req)->snt_isn + 1))
+	    (TCP_SKB_CB(skb)->ack_seq !=
+	     tcp_rsk(req)->snt_isn + 1 + tcp_s_data_size(tcp_sk(sk))))
 		return sk;
 
 	/* Also, it would be not so bad idea to check rcv_tsecr, which
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 3e327bc..973096a 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1865,6 +1865,19 @@ static int tcp_v6_init_sock(struct sock *sk)
 	tp->af_specific = &tcp_sock_ipv6_specific;
 #endif
 
+	/* TCP Cookie Transactions */
+	if (sysctl_tcp_cookie_size > 0) {
+		/* Default, cookies without s_data_payload. */
+		tp->cookie_values =
+			kzalloc(sizeof(*tp->cookie_values),
+				sk->sk_allocation);
+		if (tp->cookie_values != NULL)
+			kref_init(&tp->cookie_values->kref);
+	}
+	/* Presumed zeroed, in order of appearance:
+	 *	cookie_in_always, cookie_out_never,
+	 *	s_data_constant, s_data_in, s_data_out
+	 */
 	sk->sk_sndbuf = sysctl_tcp_wmem[1];
 	sk->sk_rcvbuf = sysctl_tcp_rmem[1];