#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>
#include <net/ip.h>
#include <net/tcp_states.h>
#include <net/inet_ecn.h>
+#include <net/dst.h>
#include <linux/seq_file.h>
/* 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
#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
#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
#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 */
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;
atomic_read(&tcp_memory_allocated) > sysctl_tcp_mem[2]);
}
+/* syncookies: remember time of last synqueue overflow */
+static inline void tcp_synq_overflow(struct sock *sk)
+{
+ tcp_sk(sk)->rx_opt.ts_recent_stamp = jiffies;
+}
+
+/* syncookies: no recent synqueue overflow on this listening socket? */
+static inline int tcp_synq_no_recent_overflow(const struct sock *sk)
+{
+ unsigned long last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp;
+ return time_after(jiffies, last_overflow + TCP_TIMEOUT_INIT);
+}
+
extern struct proto tcp_prot;
#define TCP_INC_STATS(net, field) SNMP_INC_STATS((net)->mib.tcp_statistics, field)
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
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,
int __user *optlen);
extern int tcp_setsockopt(struct sock *sk, int level,
int optname, char __user *optval,
- int optlen);
+ unsigned int optlen);
extern int compat_tcp_getsockopt(struct sock *sk,
int level, int optname,
char __user *optval, int __user *optlen);
extern int compat_tcp_setsockopt(struct sock *sk,
int level, int optname,
- char __user *optval, int optlen);
+ 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,
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);
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);
int nonagle);
extern int tcp_may_send_now(struct sock *sk);
extern int tcp_retransmit_skb(struct sock *, struct sk_buff *);
+extern void tcp_retransmit_timer(struct sock *sk);
extern void tcp_xmit_retransmit_queue(struct sock *);
extern void tcp_simple_retransmit(struct sock *);
extern int tcp_trim_head(struct sock *, struct sk_buff *, u32);
}
extern unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu);
-extern unsigned int tcp_current_mss(struct sock *sk, int large);
+extern unsigned int tcp_current_mss(struct sock *sk);
+
+/* Bound MSS / TSO packet size with the half of the window */
+static inline int tcp_bound_to_half_wnd(struct tcp_sock *tp, int pktsize)
+{
+ if (tp->max_window && pktsize > (tp->max_window >> 1))
+ return max(tp->max_window >> 1, 68U - tp->tcp_header_len);
+ else
+ return pktsize;
+}
/* tcp.c */
extern void tcp_get_info(struct sock *, struct tcp_info *);
extern int tcp_mss_to_mtu(struct sock *sk, int mss);
extern void tcp_mtup_init(struct sock *sk);
+static inline void tcp_bound_rto(const struct sock *sk)
+{
+ if (inet_csk(sk)->icsk_rto > TCP_RTO_MAX)
+ inet_csk(sk)->icsk_rto = TCP_RTO_MAX;
+}
+
+static inline u32 __tcp_set_rto(const struct tcp_sock *tp)
+{
+ return (tp->srtt >> 3) + tp->rttvar;
+}
+
static inline void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd)
{
tp->pred_flags = htonl((tp->tcp_header_len << 26) |
tcp_fast_path_on(tp);
}
+/* Compute the actual rto_min value */
+static inline u32 tcp_rto_min(struct sock *sk)
+{
+ struct dst_entry *dst = __sk_dst_get(sk);
+ u32 rto_min = TCP_RTO_MIN;
+
+ if (dst && dst_metric_locked(dst, RTAX_RTO_MIN))
+ rto_min = dst_metric_rtt(dst, RTAX_RTO_MIN);
+ return rto_min;
+}
+
/* Compute the actual receive window we are currently advertising.
* Rcv_nxt can be after the window if our peer push more data
* than the offered window.
return skb_shinfo(skb)->gso_size;
}
-static inline void tcp_dec_pcount_approx_int(__u32 *count, const int decr)
-{
- if (*count) {
- *count -= decr;
- if ((int)*count < 0)
- *count = 0;
- }
-}
-
-static inline void tcp_dec_pcount_approx(__u32 *count,
- const struct sk_buff *skb)
-{
- tcp_dec_pcount_approx_int(count, tcp_skb_pcount(skb));
-}
-
/* Events passed to congestion control interface */
enum tcp_ca_event {
CA_EVENT_TX_START, /* first transmit when no packets in flight */
return tp->packets_out - tcp_left_out(tp) + tp->retrans_out;
}
+#define TCP_INFINITE_SSTHRESH 0x7fffffff
+
+static inline bool tcp_in_initial_slowstart(const struct tcp_sock *tp)
+{
+ return tp->snd_ssthresh >= TCP_INFINITE_SSTHRESH;
+}
+
/* If cwnd > ssthresh, we may raise ssthresh to be half-way to cwnd.
* The exception is rate halving phase, when cwnd is decreasing towards
* ssthresh.
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, 1), tp->nonagle);
-}
-
static inline void tcp_init_wl(struct tcp_sock *tp, u32 seq)
{
tp->snd_wl1 = seq;
{
struct tcp_sock *tp = tcp_sk(sk);
- if (!sysctl_tcp_low_latency && tp->ucopy.task) {
- __skb_queue_tail(&tp->ucopy.prequeue, skb);
- tp->ucopy.memory += skb->truesize;
- if (tp->ucopy.memory > sk->sk_rcvbuf) {
- struct sk_buff *skb1;
-
- BUG_ON(sock_owned_by_user(sk));
-
- while ((skb1 = __skb_dequeue(&tp->ucopy.prequeue)) != NULL) {
- sk_backlog_rcv(sk, skb1);
- NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPPREQUEUEDROPPED);
- }
-
- tp->ucopy.memory = 0;
- } else if (skb_queue_len(&tp->ucopy.prequeue) == 1) {
- wake_up_interruptible(sk->sk_sleep);
- if (!inet_csk_ack_scheduled(sk))
- inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
- (3 * TCP_RTO_MIN) / 4,
- TCP_RTO_MAX);
+ if (sysctl_tcp_low_latency || !tp->ucopy.task)
+ return 0;
+
+ __skb_queue_tail(&tp->ucopy.prequeue, skb);
+ tp->ucopy.memory += skb->truesize;
+ if (tp->ucopy.memory > sk->sk_rcvbuf) {
+ struct sk_buff *skb1;
+
+ BUG_ON(sock_owned_by_user(sk));
+
+ while ((skb1 = __skb_dequeue(&tp->ucopy.prequeue)) != NULL) {
+ sk_backlog_rcv(sk, skb1);
+ NET_INC_STATS_BH(sock_net(sk),
+ LINUX_MIB_TCPPREQUEUEDROPPED);
}
- return 1;
+
+ tp->ucopy.memory = 0;
+ } else if (skb_queue_len(&tp->ucopy.prequeue) == 1) {
+ 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,
+ (3 * tcp_rto_min(sk)) / 4,
+ TCP_RTO_MAX);
}
- return 0;
+ return 1;
}
/* 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)
{
return tp->keepalive_time ? : sysctl_tcp_keepalive_time;
}
+static inline int keepalive_probes(const struct tcp_sock *tp)
+{
+ return tp->keepalive_probes ? : sysctl_tcp_keepalive_probes;
+}
+
static inline int tcp_fin_time(const struct sock *sk)
{
int fin_timeout = tcp_sk(sk)->linger2 ? : sysctl_tcp_fin_timeout;
return fin_timeout;
}
-static inline int tcp_paws_check(const struct tcp_options_received *rx_opt, int rst)
+static inline int tcp_paws_check(const struct tcp_options_received *rx_opt,
+ int paws_win)
{
- if ((s32)(rx_opt->rcv_tsval - rx_opt->ts_recent) >= 0)
- return 0;
- if (get_seconds() >= rx_opt->ts_recent_stamp + TCP_PAWS_24DAYS)
+ if ((s32)(rx_opt->ts_recent - rx_opt->rcv_tsval) <= paws_win)
+ return 1;
+ if (unlikely(get_seconds() >= rx_opt->ts_recent_stamp + TCP_PAWS_24DAYS))
+ return 1;
+
+ return 0;
+}
+
+static inline int tcp_paws_reject(const struct tcp_options_received *rx_opt,
+ int rst)
+{
+ if (tcp_paws_check(rx_opt, 0))
return 0;
/* RST segments are not recommended to carry timestamp,
#define tcp_twsk_md5_key(twsk) NULL
#endif
-extern struct tcp_md5sig_pool **tcp_alloc_md5sig_pool(void);
+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)
{
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)
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.
*/
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,
#ifdef CONFIG_TCP_MD5SIG
struct tcp_md5sig_key *(*md5_lookup) (struct sock *sk,
struct request_sock *req);
+ int (*calc_md5_hash) (char *location,
+ struct tcp_md5sig_key *md5,
+ struct sock *sk,
+ struct request_sock *req,
+ struct sk_buff *skb);
#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);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff