1 files changed, 128 insertions, 62 deletions

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 03a49c703377..aa04b9a5093b 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>
@@ -62,9 +63,6 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo);
 /* Minimal accepted MSS. It is (60+60+8) - (20+20). */
 #define TCP_MIN_MSS             88U
 
-/* Minimal RCV_MSS. */
-#define TCP_MIN_RCVMSS          536U
-
 /* The least MTU to use for probing */
 #define TCP_BASE_MSS            512
 
@@ -167,6 +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
@@ -177,6 +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
@@ -193,6 +196,9 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo);
 #define TCP_NAGLE_CORK          2       /* Socket is corked         */
 #define TCP_NAGLE_PUSH          4       /* Cork is overridden for already queued data */
 
+/* TCP thin-stream limits */
+#define TCP_THIN_LINEAR_RETRIES 6       /* After 6 linear retries, do exp. backoff */
+
 extern struct inet_timewait_death_row tcp_death_row;
 
 /* sysctl variables for tcp */
@@ -237,6 +243,9 @@ extern int sysctl_tcp_base_mss;
 extern int sysctl_tcp_workaround_signed_windows;
 extern int sysctl_tcp_slow_start_after_idle;
 extern int sysctl_tcp_max_ssthresh;
+extern int sysctl_tcp_cookie_size;
+extern int sysctl_tcp_thin_linear_timeouts;
+extern int sysctl_tcp_thin_dupack;
 
 extern atomic_t tcp_memory_allocated;
 extern struct percpu_counter tcp_sockets_allocated;
@@ -343,11 +352,6 @@ static inline void tcp_dec_quickack_mode(struct sock *sk,
 
 extern void tcp_enter_quickack_mode(struct sock *sk);
 
-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;
-}
-
 #define TCP_ECN_OK              1
 #define TCP_ECN_QUEUE_CWR       2
 #define TCP_ECN_DEMAND_CWR      4
@@ -359,8 +363,7 @@ TCP_ECN_create_request(struct request_sock *req, struct tcphdr *th)
                 inet_rsk(req)->ecn_ok = 1;
 }
 
-enum tcp_tw_status
-{
+enum tcp_tw_status {
         TCP_TW_SUCCESS = 0,
         TCP_TW_RST = 1,
         TCP_TW_ACK = 2,
@@ -402,6 +405,8 @@ extern int			compat_tcp_setsockopt(struct sock *sk,
                                         int level, int optname,
                                         char __user *optval, unsigned int optlen);
 extern void                     tcp_set_keepalive(struct sock *sk, int val);
+extern void                     tcp_syn_ack_timeout(struct sock *sk,
+                                                    struct request_sock *req);
 extern int                      tcp_recvmsg(struct kiocb *iocb, struct sock *sk,
                                             struct msghdr *msg,
                                             size_t len, int nonblock, 
@@ -409,6 +414,7 @@ extern int			tcp_recvmsg(struct kiocb *iocb, struct sock *sk,
 
 extern void                     tcp_parse_options(struct sk_buff *skb,
                                                   struct tcp_options_received *opt_rx,
+                                                  u8 **hvpp,
                                                   int estab);
 
 extern u8                       *tcp_parse_md5sig_option(struct tcphdr *th);
@@ -443,7 +449,8 @@ extern int			tcp_connect(struct sock *sk);
 
 extern struct sk_buff *         tcp_make_synack(struct sock *sk,
                                                 struct dst_entry *dst,
-                                                struct request_sock *req);
+                                                struct request_sock *req,
+                                                struct request_values *rvp);
 
 extern int                      tcp_disconnect(struct sock *sk, int flags);
 
@@ -856,13 +863,6 @@ static inline void tcp_check_probe_timer(struct sock *sk)
                                           icsk->icsk_rto, TCP_RTO_MAX);
 }
 
-static inline void tcp_push_pending_frames(struct sock *sk)
-{
-        struct tcp_sock *tp = tcp_sk(sk);
-
-        __tcp_push_pending_frames(sk, tcp_current_mss(sk), tp->nonagle);
-}
-
 static inline void tcp_init_wl(struct tcp_sock *tp, u32 seq)
 {
         tp->snd_wl1 = seq;
@@ -939,7 +939,7 @@ static inline int tcp_prequeue(struct sock *sk, struct sk_buff *skb)
 
                 tp->ucopy.memory = 0;
         } else if (skb_queue_len(&tp->ucopy.prequeue) == 1) {
-                wake_up_interruptible_poll(sk->sk_sleep,
+                wake_up_interruptible_sync_poll(sk->sk_sleep,
                                            POLLIN | POLLRDNORM | POLLRDBAND);
                 if (!inet_csk_ack_scheduled(sk))
                         inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
@@ -972,7 +972,8 @@ static inline void tcp_sack_reset(struct tcp_options_received *rx_opt)
 /* Determine a window scaling and initial window to offer. */
 extern void tcp_select_initial_window(int __space, __u32 mss,
                                       __u32 *rcv_wnd, __u32 *window_clamp,
-                                      int wscale_ok, __u8 *rcv_wscale);
+                                      int wscale_ok, __u8 *rcv_wscale,
+                                      __u32 init_rcv_wnd);
 
 static inline int tcp_win_from_space(int space)
 {
@@ -1193,33 +1194,18 @@ extern int			tcp_v4_md5_do_del(struct sock *sk,
 #define tcp_twsk_md5_key(twsk)  NULL
 #endif
 
-extern struct tcp_md5sig_pool   **tcp_alloc_md5sig_pool(struct sock *);
+extern struct tcp_md5sig_pool * __percpu *tcp_alloc_md5sig_pool(struct sock *);
 extern void                     tcp_free_md5sig_pool(void);
 
-extern struct tcp_md5sig_pool   *__tcp_get_md5sig_pool(int cpu);
-extern void                     __tcp_put_md5sig_pool(void);
+extern struct tcp_md5sig_pool   *tcp_get_md5sig_pool(void);
+extern void                     tcp_put_md5sig_pool(void);
+
 extern int tcp_md5_hash_header(struct tcp_md5sig_pool *, struct tcphdr *);
 extern int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *, struct sk_buff *,
                                  unsigned header_len);
 extern int tcp_md5_hash_key(struct tcp_md5sig_pool *hp,
                             struct tcp_md5sig_key *key);
 
-static inline
-struct tcp_md5sig_pool          *tcp_get_md5sig_pool(void)
-{
-        int cpu = get_cpu();
-        struct tcp_md5sig_pool *ret = __tcp_get_md5sig_pool(cpu);
-        if (!ret)
-                put_cpu();
-        return ret;
-}
-
-static inline void              tcp_put_md5sig_pool(void)
-{
-        __tcp_put_md5sig_pool();
-        put_cpu();
-}
-
 /* write queue abstraction */
 static inline void tcp_write_queue_purge(struct sock *sk)
 {
@@ -1228,6 +1214,7 @@ static inline void tcp_write_queue_purge(struct sock *sk)
         while ((skb = __skb_dequeue(&sk->sk_write_queue)) != NULL)
                 sk_wmem_free_skb(sk, skb);
         sk_mem_reclaim(sk);
+        tcp_clear_all_retrans_hints(tcp_sk(sk));
 }
 
 static inline struct sk_buff *tcp_write_queue_head(struct sock *sk)
@@ -1259,29 +1246,6 @@ static inline struct sk_buff *tcp_write_queue_prev(struct sock *sk, struct sk_bu
 #define tcp_for_write_queue_from_safe(skb, tmp, sk)                     \
         skb_queue_walk_from_safe(&(sk)->sk_write_queue, skb, tmp)
 
-/* This function calculates a "timeout" which is equivalent to the timeout of a
- * TCP connection after "boundary" unsucessful, exponentially backed-off
- * retransmissions with an initial RTO of TCP_RTO_MIN.
- */
-static inline bool retransmits_timed_out(const struct sock *sk,
-                                         unsigned int boundary)
-{
-        unsigned int timeout, linear_backoff_thresh;
-
-        if (!inet_csk(sk)->icsk_retransmits)
-                return false;
-
-        linear_backoff_thresh = ilog2(TCP_RTO_MAX/TCP_RTO_MIN);
-
-        if (boundary <= linear_backoff_thresh)
-                timeout = ((2 << boundary) - 1) * TCP_RTO_MIN;
-        else
-                timeout = ((2 << linear_backoff_thresh) - 1) * TCP_RTO_MIN +
-                          (boundary - linear_backoff_thresh) * TCP_RTO_MAX;
-
-        return (tcp_time_stamp - tcp_sk(sk)->retrans_stamp) >= timeout;
-}
-
 static inline struct sk_buff *tcp_send_head(struct sock *sk)
 {
         return sk->sk_send_head;
@@ -1364,6 +1328,15 @@ static inline int tcp_write_queue_empty(struct sock *sk)
         return skb_queue_empty(&sk->sk_write_queue);
 }
 
+static inline void tcp_push_pending_frames(struct sock *sk)
+{
+        if (tcp_send_head(sk)) {
+                struct tcp_sock *tp = tcp_sk(sk);
+
+                __tcp_push_pending_frames(sk, tcp_current_mss(sk), tp->nonagle);
+        }
+}
+
 /* Start sequence of the highest skb with SACKed bit, valid only if
  * sacked > 0 or when the caller has ensured validity by itself.
  */
@@ -1403,6 +1376,14 @@ static inline void tcp_highest_sack_combine(struct sock *sk,
                 tcp_sk(sk)->highest_sack = new;
 }
 
+/* Determines whether this is a thin stream (which may suffer from
+ * increased latency). Used to trigger latency-reducing mechanisms.
+ */
+static inline unsigned int tcp_stream_is_thin(struct tcp_sock *tp)
+{
+        return tp->packets_out < 4 && !tcp_in_initial_slowstart(tp);
+}
+
 /* /proc */
 enum tcp_seq_states {
         TCP_SEQ_STATE_LISTENING,
@@ -1480,6 +1461,91 @@ struct tcp_request_sock_ops {
 #endif
 };
 
+/* Using SHA1 for now, define some constants.
+ */
+#define COOKIE_DIGEST_WORDS (SHA_DIGEST_WORDS)
+#define COOKIE_MESSAGE_WORDS (SHA_MESSAGE_BYTES / 4)
+#define COOKIE_WORKSPACE_WORDS (COOKIE_DIGEST_WORDS + COOKIE_MESSAGE_WORDS)
+
+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);