#define _TCP_H
#define TCP_DEBUG 1
-#define INET_CSK_DEBUG 1
#define FASTRETRANS_DEBUG 1
-/* Cancel timers, when they are not required. */
-#undef INET_CSK_CLEAR_TIMERS
-
-#include <linux/config.h>
#include <linux/list.h>
#include <linux/tcp.h>
#include <linux/slab.h>
#include <linux/cache.h>
#include <linux/percpu.h>
+#include <linux/skbuff.h>
+#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/inet_hashtables.h>
#include <net/checksum.h>
#include <net/request_sock.h>
#include <net/snmp.h>
#include <net/ip.h>
#include <net/tcp_states.h>
+#include <net/inet_ecn.h>
+#include <net/dst.h>
#include <linux/seq_file.h>
extern struct inet_hashinfo tcp_hashinfo;
-extern atomic_t tcp_orphan_count;
-extern int tcp_tw_count;
+extern struct percpu_counter tcp_orphan_count;
extern void tcp_time_wait(struct sock *sk, int state, int timeo);
-extern void tcp_tw_deschedule(struct inet_timewait_sock *tw);
#define MAX_TCP_HEADER (128 + MAX_HEADER)
+#define MAX_TCP_OPTION_SPACE 40
/*
* Never offer a window over 32767 without using window scaling. Some
/* 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
/* After receiving this amount of duplicate ACKs fast retransmit starts. */
#define TCP_FASTRETRANS_THRESH 3
*/
#define TCP_SYN_RETRIES 5 /* number of times to retry active opening a
- * connection: ~180sec is RFC minumum */
+ * connection: ~180sec is RFC minimum */
#define TCP_SYNACK_RETRIES 5 /* number of times to retry passive opening a
- * connection: ~180sec is RFC minumum */
+ * connection: ~180sec is RFC minimum */
#define TCP_ORPHAN_RETRIES 7 /* number of times to retry on an orphaned
#define MAX_TCP_SYNCNT 127
#define TCP_SYNQ_INTERVAL (HZ/5) /* Period of SYNACK timer */
-#define TCP_SYNQ_HSIZE 512 /* Size of SYNACK hash table */
#define TCP_PAWS_24DAYS (60 * 60 * 24 * 24)
#define TCP_PAWS_MSL 60 /* Per-host timestamps are invalidated
* timestamps. It must be less than
* minimal timewait lifetime.
*/
-
-#define TCP_TW_RECYCLE_SLOTS_LOG 5
-#define TCP_TW_RECYCLE_SLOTS (1<<TCP_TW_RECYCLE_SLOTS_LOG)
-
-/* If time > 4sec, it is "slow" path, no recycling is required,
- so that we select tick to get range about 4 seconds.
- */
-
-#if HZ <= 16 || HZ > 4096
-# error Unsupported: HZ <= 16 or HZ > 4096
-#elif HZ <= 32
-# define TCP_TW_RECYCLE_TICK (5+2-TCP_TW_RECYCLE_SLOTS_LOG)
-#elif HZ <= 64
-# define TCP_TW_RECYCLE_TICK (6+2-TCP_TW_RECYCLE_SLOTS_LOG)
-#elif HZ <= 128
-# define TCP_TW_RECYCLE_TICK (7+2-TCP_TW_RECYCLE_SLOTS_LOG)
-#elif HZ <= 256
-# define TCP_TW_RECYCLE_TICK (8+2-TCP_TW_RECYCLE_SLOTS_LOG)
-#elif HZ <= 512
-# define TCP_TW_RECYCLE_TICK (9+2-TCP_TW_RECYCLE_SLOTS_LOG)
-#elif HZ <= 1024
-# define TCP_TW_RECYCLE_TICK (10+2-TCP_TW_RECYCLE_SLOTS_LOG)
-#elif HZ <= 2048
-# define TCP_TW_RECYCLE_TICK (11+2-TCP_TW_RECYCLE_SLOTS_LOG)
-#else
-# define TCP_TW_RECYCLE_TICK (12+2-TCP_TW_RECYCLE_SLOTS_LOG)
-#endif
/*
* TCP option
*/
#define TCPOPT_SACK_PERM 4 /* SACK Permitted */
#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_WINDOW 3
#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 TCPOLEN_SACK_BASE 2
#define TCPOLEN_SACK_BASE_ALIGNED 4
#define TCPOLEN_SACK_PERBLOCK 8
-
-#define ICSK_TIME_RETRANS 1 /* Retransmit timer */
-#define ICSK_TIME_DACK 2 /* Delayed ack timer */
-#define ICSK_TIME_PROBE0 3 /* Zero window probe timer */
-#define ICSK_TIME_KEEPOPEN 4 /* Keepalive timer */
+#define TCPOLEN_MD5SIG_ALIGNED 20
+#define TCPOLEN_MSS_ALIGNED 4
/* Flags in tp->nonagle */
#define TCP_NAGLE_OFF 1 /* Nagle's algo is disabled */
#define TCP_NAGLE_CORK 2 /* Socket is corked */
-#define TCP_NAGLE_PUSH 4 /* Cork is overriden for already queued data */
+#define TCP_NAGLE_PUSH 4 /* Cork is overridden for already queued data */
+
+extern struct inet_timewait_death_row tcp_death_row;
/* sysctl variables for tcp */
extern int sysctl_tcp_timestamps;
extern int sysctl_tcp_window_scaling;
extern int sysctl_tcp_sack;
extern int sysctl_tcp_fin_timeout;
-extern int sysctl_tcp_tw_recycle;
extern int sysctl_tcp_keepalive_time;
extern int sysctl_tcp_keepalive_probes;
extern int sysctl_tcp_keepalive_intvl;
extern int sysctl_tcp_rfc1337;
extern int sysctl_tcp_abort_on_overflow;
extern int sysctl_tcp_max_orphans;
-extern int sysctl_tcp_max_tw_buckets;
extern int sysctl_tcp_fack;
extern int sysctl_tcp_reordering;
extern int sysctl_tcp_ecn;
extern int sysctl_tcp_adv_win_scale;
extern int sysctl_tcp_tw_reuse;
extern int sysctl_tcp_frto;
+extern int sysctl_tcp_frto_response;
extern int sysctl_tcp_low_latency;
+extern int sysctl_tcp_dma_copybreak;
extern int sysctl_tcp_nometrics_save;
extern int sysctl_tcp_moderate_rcvbuf;
extern int sysctl_tcp_tso_win_divisor;
+extern int sysctl_tcp_abc;
+extern int sysctl_tcp_mtu_probing;
+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 atomic_t tcp_memory_allocated;
-extern atomic_t tcp_sockets_allocated;
+extern struct percpu_counter tcp_sockets_allocated;
extern int tcp_memory_pressure;
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
-#define AF_INET_FAMILY(fam) ((fam) == AF_INET)
-#else
-#define AF_INET_FAMILY(fam) 1
-#endif
-
-/*
- * Pointers to address related TCP functions
- * (i.e. things that depend on the address family)
- */
-
-struct tcp_func {
- int (*queue_xmit) (struct sk_buff *skb,
- int ipfragok);
-
- void (*send_check) (struct sock *sk,
- struct tcphdr *th,
- int len,
- struct sk_buff *skb);
-
- int (*rebuild_header) (struct sock *sk);
-
- int (*conn_request) (struct sock *sk,
- struct sk_buff *skb);
-
- struct sock * (*syn_recv_sock) (struct sock *sk,
- struct sk_buff *skb,
- struct request_sock *req,
- struct dst_entry *dst);
-
- int (*remember_stamp) (struct sock *sk);
-
- __u16 net_header_len;
-
- int (*setsockopt) (struct sock *sk,
- int level,
- int optname,
- char __user *optval,
- int optlen);
-
- int (*getsockopt) (struct sock *sk,
- int level,
- int optname,
- char __user *optval,
- int __user *optlen);
-
-
- void (*addr2sockaddr) (struct sock *sk,
- struct sockaddr *);
-
- int sockaddr_len;
-};
-
/*
* The next routines deal with comparing 32 bit unsigned ints
* and worry about wraparound (automatic with unsigned arithmetic).
{
return (__s32)(seq1-seq2) < 0;
}
+#define after(seq2, seq1) before(seq1, seq2)
-static inline int after(__u32 seq1, __u32 seq2)
+/* is s2<=s1<=s3 ? */
+static inline int between(__u32 seq1, __u32 seq2, __u32 seq3)
{
- return (__s32)(seq2-seq1) < 0;
+ return seq3 - seq2 >= seq1 - seq2;
}
+static inline int tcp_too_many_orphans(struct sock *sk, int num)
+{
+ return (num > sysctl_tcp_max_orphans) ||
+ (sk->sk_wmem_queued > SOCK_MIN_SNDBUF &&
+ atomic_read(&tcp_memory_allocated) > sysctl_tcp_mem[2]);
+}
-/* is s2<=s1<=s3 ? */
-static inline int between(__u32 seq1, __u32 seq2, __u32 seq3)
+/* syncookies: remember time of last synqueue overflow */
+static inline void tcp_synq_overflow(struct sock *sk)
{
- return seq3 - seq2 >= seq1 - seq2;
+ 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;
-DECLARE_SNMP_STAT(struct tcp_mib, tcp_statistics);
-#define TCP_INC_STATS(field) SNMP_INC_STATS(tcp_statistics, field)
-#define TCP_INC_STATS_BH(field) SNMP_INC_STATS_BH(tcp_statistics, field)
-#define TCP_INC_STATS_USER(field) SNMP_INC_STATS_USER(tcp_statistics, field)
-#define TCP_DEC_STATS(field) SNMP_DEC_STATS(tcp_statistics, field)
-#define TCP_ADD_STATS_BH(field, val) SNMP_ADD_STATS_BH(tcp_statistics, field, val)
-#define TCP_ADD_STATS_USER(field, val) SNMP_ADD_STATS_USER(tcp_statistics, field, val)
+#define TCP_INC_STATS(net, field) SNMP_INC_STATS((net)->mib.tcp_statistics, field)
+#define TCP_INC_STATS_BH(net, field) SNMP_INC_STATS_BH((net)->mib.tcp_statistics, field)
+#define TCP_DEC_STATS(net, field) SNMP_DEC_STATS((net)->mib.tcp_statistics, field)
+#define TCP_ADD_STATS_USER(net, field, val) SNMP_ADD_STATS_USER((net)->mib.tcp_statistics, field, val)
extern void tcp_v4_err(struct sk_buff *skb, u32);
extern int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw);
-extern int tcp_sendmsg(struct kiocb *iocb, struct sock *sk,
+extern int tcp_sendmsg(struct kiocb *iocb, struct socket *sock,
struct msghdr *msg, size_t size);
extern ssize_t tcp_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags);
extern void tcp_rcv_space_adjust(struct sock *sk);
-enum inet_csk_ack_state_t {
- ICSK_ACK_SCHED = 1,
- ICSK_ACK_TIMER = 2,
- ICSK_ACK_PUSHED = 4
-};
+extern void tcp_cleanup_rbuf(struct sock *sk, int copied);
-static inline void inet_csk_schedule_ack(struct sock *sk)
-{
- inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_SCHED;
-}
+extern int tcp_twsk_unique(struct sock *sk,
+ struct sock *sktw, void *twp);
-static inline int inet_csk_ack_scheduled(const struct sock *sk)
-{
- return inet_csk(sk)->icsk_ack.pending & ICSK_ACK_SCHED;
-}
+extern void tcp_twsk_destructor(struct sock *sk);
+
+extern ssize_t tcp_splice_read(struct socket *sk, loff_t *ppos,
+ struct pipe_inode_info *pipe, size_t len, unsigned int flags);
static inline void tcp_dec_quickack_mode(struct sock *sk,
const unsigned int pkts)
extern void tcp_enter_quickack_mode(struct sock *sk);
-static inline void inet_csk_delack_init(struct sock *sk)
-{
- memset(&inet_csk(sk)->icsk_ack, 0, sizeof(inet_csk(sk)->icsk_ack));
-}
+#define TCP_ECN_OK 1
+#define TCP_ECN_QUEUE_CWR 2
+#define TCP_ECN_DEMAND_CWR 4
-static inline void tcp_clear_options(struct tcp_options_received *rx_opt)
+static __inline__ void
+TCP_ECN_create_request(struct request_sock *req, struct tcphdr *th)
{
- rx_opt->tstamp_ok = rx_opt->sack_ok = rx_opt->wscale_ok = rx_opt->snd_wscale = 0;
+ if (sysctl_tcp_ecn && th->ece && th->cwr)
+ 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,
extern int tcp_child_process(struct sock *parent,
struct sock *child,
struct sk_buff *skb);
+extern int tcp_use_frto(struct sock *sk);
extern void tcp_enter_frto(struct sock *sk);
extern void tcp_enter_loss(struct sock *sk, int how);
extern void tcp_clear_retrans(struct tcp_sock *tp);
extern void tcp_close(struct sock *sk,
long timeout);
-extern struct sock * inet_csk_accept(struct sock *sk, int flags, int *err);
extern unsigned int tcp_poll(struct file * file, struct socket *sock, struct poll_table_struct *wait);
extern int tcp_getsockopt(struct sock *sk, int level,
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, unsigned int optlen);
extern void tcp_set_keepalive(struct sock *sk, int val);
extern int tcp_recvmsg(struct kiocb *iocb, struct sock *sk,
struct msghdr *msg,
size_t len, int nonblock,
int flags, int *addr_len);
-extern int tcp_listen_start(struct sock *sk);
-
extern void tcp_parse_options(struct sk_buff *skb,
struct tcp_options_received *opt_rx,
- int estab);
+ u8 **hvpp,
+ int estab,
+ struct dst_entry *dst);
+
+extern u8 *tcp_parse_md5sig_option(struct tcphdr *th);
/*
* TCP v4 functions exported for the inet6 API
*/
-extern void tcp_v4_send_check(struct sock *sk,
- struct tcphdr *th, int len,
+extern void tcp_v4_send_check(struct sock *sk, int len,
struct sk_buff *skb);
extern int tcp_v4_conn_request(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);
-extern void tcp_unhash(struct sock *sk);
-
-extern int tcp_v4_hash_connecting(struct sock *sk);
-
/* From syncookies.c */
+extern __u32 syncookie_secret[2][16-4+SHA_DIGEST_WORDS];
extern struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
struct ip_options *opt);
extern __u32 cookie_v4_init_sequence(struct sock *sk, struct sk_buff *skb,
__u16 *mss);
+extern __u32 cookie_init_timestamp(struct request_sock *req);
+extern void cookie_check_timestamp(struct tcp_options_received *tcp_opt);
+
+/* From net/ipv6/syncookies.c */
+extern struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb);
+extern __u32 cookie_v6_init_sequence(struct sock *sk, struct sk_buff *skb,
+ __u16 *mss);
+
/* tcp_output.c */
-extern void __tcp_push_pending_frames(struct sock *sk, struct tcp_sock *tp,
- unsigned int cur_mss, int nonagle);
-extern int tcp_may_send_now(struct sock *sk, struct tcp_sock *tp);
+extern void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss,
+ 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 int tcp_fragment(struct sock *, struct sk_buff *, u32, unsigned int);
extern void tcp_send_probe0(struct sock *);
extern void tcp_send_partial(struct sock *);
extern int tcp_write_wakeup(struct sock *);
extern void tcp_send_fin(struct sock *sk);
-extern void tcp_send_active_reset(struct sock *sk,
- unsigned int __nocast priority);
+extern void tcp_send_active_reset(struct sock *sk, gfp_t priority);
extern int tcp_send_synack(struct sock *);
extern void tcp_push_one(struct sock *, unsigned int mss_now);
extern void tcp_send_ack(struct sock *sk);
inet_csk_clear_xmit_timers(sk);
}
-extern void inet_csk_delete_keepalive_timer(struct sock *sk);
-extern void inet_csk_reset_keepalive_timer(struct sock *sk, unsigned long timeout);
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);
-#ifdef INET_CSK_DEBUG
-extern const char inet_csk_timer_bug_msg[];
-#endif
+/* 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_diag.c */
+/* tcp.c */
extern void tcp_get_info(struct sock *, struct tcp_info *);
/* Read 'sendfile()'-style from a TCP socket */
extern int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
sk_read_actor_t recv_actor);
-static inline void inet_csk_clear_xmit_timer(struct sock *sk, const int what)
-{
- struct inet_connection_sock *icsk = inet_csk(sk);
-
- if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0) {
- icsk->icsk_pending = 0;
-#ifdef INET_CSK_CLEAR_TIMERS
- sk_stop_timer(sk, &icsk->icsk_retransmit_timer);
-#endif
- } else if (what == ICSK_TIME_DACK) {
- icsk->icsk_ack.blocked = icsk->icsk_ack.pending = 0;
-#ifdef INET_CSK_CLEAR_TIMERS
- sk_stop_timer(sk, &icsk->icsk_delack_timer);
-#endif
- }
-#ifdef INET_CSK_DEBUG
- else {
- pr_debug(inet_csk_timer_bug_msg);
- }
-#endif
-}
+extern void tcp_initialize_rcv_mss(struct sock *sk);
-/*
- * Reset the retransmission timer
- */
-static inline void inet_csk_reset_xmit_timer(struct sock *sk, const int what,
- unsigned long when)
-{
- struct inet_connection_sock *icsk = inet_csk(sk);
+extern int tcp_mtu_to_mss(struct sock *sk, int pmtu);
+extern int tcp_mss_to_mtu(struct sock *sk, int mss);
+extern void tcp_mtup_init(struct sock *sk);
- if (when > TCP_RTO_MAX) {
-#ifdef INET_CSK_DEBUG
- pr_debug("reset_xmit_timer: sk=%p %d when=0x%lx, caller=%p\n",
- sk, what, when, current_text_addr());
-#endif
- when = TCP_RTO_MAX;
- }
-
- if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0) {
- icsk->icsk_pending = what;
- icsk->icsk_timeout = jiffies + when;
- sk_reset_timer(sk, &icsk->icsk_retransmit_timer, icsk->icsk_timeout);
- } else if (what == ICSK_TIME_DACK) {
- icsk->icsk_ack.pending |= ICSK_ACK_TIMER;
- icsk->icsk_ack.timeout = jiffies + when;
- sk_reset_timer(sk, &icsk->icsk_delack_timer, icsk->icsk_ack.timeout);
- }
-#ifdef INET_CSK_DEBUG
- else {
- pr_debug(inet_csk_timer_bug_msg);
- }
-#endif
+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;
}
-/* Initialize RCV_MSS value.
- * RCV_MSS is an our guess about MSS used by the peer.
- * We haven't any direct information about the MSS.
- * It's better to underestimate the RCV_MSS rather than overestimate.
- * Overestimations make us ACKing less frequently than needed.
- * Underestimations are more easy to detect and fix by tcp_measure_rcv_mss().
- */
-
-static inline void tcp_initialize_rcv_mss(struct sock *sk)
+static inline u32 __tcp_set_rto(const struct tcp_sock *tp)
{
- struct tcp_sock *tp = tcp_sk(sk);
- unsigned int hint = min_t(unsigned int, tp->advmss, tp->mss_cache);
-
- hint = min(hint, tp->rcv_wnd/2);
- hint = min(hint, TCP_MIN_RCVMSS);
- hint = max(hint, TCP_MIN_MSS);
-
- inet_csk(sk)->icsk_ack.rcv_mss = hint;
+ return (tp->srtt >> 3) + tp->rttvar;
}
-static __inline__ void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd)
+static inline void __tcp_fast_path_on(struct tcp_sock *tp, u32 snd_wnd)
{
tp->pred_flags = htonl((tp->tcp_header_len << 26) |
ntohl(TCP_FLAG_ACK) |
snd_wnd);
}
-static __inline__ void tcp_fast_path_on(struct tcp_sock *tp)
+static inline void tcp_fast_path_on(struct tcp_sock *tp)
{
__tcp_fast_path_on(tp, tp->snd_wnd >> tp->rx_opt.snd_wscale);
}
-static inline void tcp_fast_path_check(struct sock *sk, struct tcp_sock *tp)
+static inline void tcp_fast_path_check(struct sock *sk)
{
+ struct tcp_sock *tp = tcp_sk(sk);
+
if (skb_queue_empty(&tp->out_of_order_queue) &&
tp->rcv_wnd &&
atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf &&
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.
*/
-static __inline__ u32 tcp_receive_window(const struct tcp_sock *tp)
+static inline u32 tcp_receive_window(const struct tcp_sock *tp)
{
s32 win = tp->rcv_wup + tp->rcv_wnd - tp->rcv_nxt;
/* TCP timestamps are only 32-bits, this causes a slight
* complication on 64-bit systems since we store a snapshot
- * of jiffies in the buffer control blocks below. We decidely
- * only use of the low 32-bits of jiffies and hide the ugly
+ * of jiffies in the buffer control blocks below. We decided
+ * to use only the low 32-bits of jiffies and hide the ugly
* casts with the following macro.
*/
#define tcp_time_stamp ((__u32)(jiffies))
-/* This is what the send packet queueing engine uses to pass
+/* This is what the send packet queuing engine uses to pass
* TCP per-packet control information to the transmission
* code. We also store the host-order sequence numbers in
* here too. This is 36 bytes on 32-bit architectures,
#define TCPCB_EVER_RETRANS 0x80 /* Ever retransmitted frame */
#define TCPCB_RETRANS (TCPCB_SACKED_RETRANS|TCPCB_EVER_RETRANS)
-#define TCPCB_URG 0x20 /* Urgent pointer advenced here */
-
-#define TCPCB_AT_TAIL (TCPCB_URG)
-
- __u16 urg_ptr; /* Valid w/URG flags is set. */
__u32 ack_seq; /* Sequence number ACK'd */
};
#define TCP_SKB_CB(__skb) ((struct tcp_skb_cb *)&((__skb)->cb[0]))
-#include <net/tcp_ecn.h>
-
/* Due to TSO, an SKB can be composed of multiple actual
* packets. To keep these tracked properly, we use this.
*/
static inline int tcp_skb_pcount(const struct sk_buff *skb)
{
- return skb_shinfo(skb)->tso_segs;
+ return skb_shinfo(skb)->gso_segs;
}
/* This is valid iff tcp_skb_pcount() > 1. */
static inline int tcp_skb_mss(const struct sk_buff *skb)
{
- return skb_shinfo(skb)->tso_size;
-}
-
-static inline void tcp_dec_pcount_approx(__u32 *count,
- const struct sk_buff *skb)
-{
- if (*count) {
- *count -= tcp_skb_pcount(skb);
- if ((int)*count < 0)
- *count = 0;
- }
-}
-
-static inline void tcp_packets_out_inc(struct sock *sk,
- struct tcp_sock *tp,
- const struct sk_buff *skb)
-{
- int orig = tp->packets_out;
-
- tp->packets_out += tcp_skb_pcount(skb);
- if (!orig)
- inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, inet_csk(sk)->icsk_rto);
-}
-
-static inline void tcp_packets_out_dec(struct tcp_sock *tp,
- const struct sk_buff *skb)
-{
- tp->packets_out -= tcp_skb_pcount(skb);
+ return skb_shinfo(skb)->gso_size;
}
/* Events passed to congestion control interface */
* Interface for adding new TCP congestion control handlers
*/
#define TCP_CA_NAME_MAX 16
+#define TCP_CA_MAX 128
+#define TCP_CA_BUF_MAX (TCP_CA_NAME_MAX*TCP_CA_MAX)
+
+#define TCP_CONG_NON_RESTRICTED 0x1
+#define TCP_CONG_RTT_STAMP 0x2
+
struct tcp_congestion_ops {
struct list_head list;
+ unsigned long flags;
/* initialize private data (optional) */
- void (*init)(struct tcp_sock *tp);
+ void (*init)(struct sock *sk);
/* cleanup private data (optional) */
- void (*release)(struct tcp_sock *tp);
+ void (*release)(struct sock *sk);
/* return slow start threshold (required) */
- u32 (*ssthresh)(struct tcp_sock *tp);
+ u32 (*ssthresh)(struct sock *sk);
/* lower bound for congestion window (optional) */
- u32 (*min_cwnd)(struct tcp_sock *tp);
+ u32 (*min_cwnd)(const struct sock *sk);
/* do new cwnd calculation (required) */
- void (*cong_avoid)(struct tcp_sock *tp, u32 ack,
- u32 rtt, u32 in_flight, int good_ack);
- /* round trip time sample per acked packet (optional) */
- void (*rtt_sample)(struct tcp_sock *tp, u32 usrtt);
+ void (*cong_avoid)(struct sock *sk, u32 ack, u32 in_flight);
/* call before changing ca_state (optional) */
- void (*set_state)(struct tcp_sock *tp, u8 new_state);
+ void (*set_state)(struct sock *sk, u8 new_state);
/* call when cwnd event occurs (optional) */
- void (*cwnd_event)(struct tcp_sock *tp, enum tcp_ca_event ev);
+ void (*cwnd_event)(struct sock *sk, enum tcp_ca_event ev);
/* new value of cwnd after loss (optional) */
- u32 (*undo_cwnd)(struct tcp_sock *tp);
+ u32 (*undo_cwnd)(struct sock *sk);
/* hook for packet ack accounting (optional) */
- void (*pkts_acked)(struct tcp_sock *tp, u32 num_acked);
- /* get info for tcp_diag (optional) */
- void (*get_info)(struct tcp_sock *tp, u32 ext, struct sk_buff *skb);
+ void (*pkts_acked)(struct sock *sk, u32 num_acked, s32 rtt_us);
+ /* get info for inet_diag (optional) */
+ void (*get_info)(struct sock *sk, u32 ext, struct sk_buff *skb);
char name[TCP_CA_NAME_MAX];
struct module *owner;
extern int tcp_register_congestion_control(struct tcp_congestion_ops *type);
extern void tcp_unregister_congestion_control(struct tcp_congestion_ops *type);
-extern void tcp_init_congestion_control(struct tcp_sock *tp);
-extern void tcp_cleanup_congestion_control(struct tcp_sock *tp);
+extern void tcp_init_congestion_control(struct sock *sk);
+extern void tcp_cleanup_congestion_control(struct sock *sk);
extern int tcp_set_default_congestion_control(const char *name);
extern void tcp_get_default_congestion_control(char *name);
-extern int tcp_set_congestion_control(struct tcp_sock *tp, const char *name);
+extern void tcp_get_available_congestion_control(char *buf, size_t len);
+extern void tcp_get_allowed_congestion_control(char *buf, size_t len);
+extern int tcp_set_allowed_congestion_control(char *allowed);
+extern int tcp_set_congestion_control(struct sock *sk, const char *name);
+extern void tcp_slow_start(struct tcp_sock *tp);
+extern void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w);
extern struct tcp_congestion_ops tcp_init_congestion_ops;
-extern u32 tcp_reno_ssthresh(struct tcp_sock *tp);
-extern void tcp_reno_cong_avoid(struct tcp_sock *tp, u32 ack,
- u32 rtt, u32 in_flight, int flag);
-extern u32 tcp_reno_min_cwnd(struct tcp_sock *tp);
+extern u32 tcp_reno_ssthresh(struct sock *sk);
+extern void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 in_flight);
+extern u32 tcp_reno_min_cwnd(const struct sock *sk);
extern struct tcp_congestion_ops tcp_reno;
-static inline void tcp_set_ca_state(struct tcp_sock *tp, u8 ca_state)
+static inline void tcp_set_ca_state(struct sock *sk, const u8 ca_state)
+{
+ struct inet_connection_sock *icsk = inet_csk(sk);
+
+ if (icsk->icsk_ca_ops->set_state)
+ icsk->icsk_ca_ops->set_state(sk, ca_state);
+ icsk->icsk_ca_state = ca_state;
+}
+
+static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event)
+{
+ const struct inet_connection_sock *icsk = inet_csk(sk);
+
+ if (icsk->icsk_ca_ops->cwnd_event)
+ icsk->icsk_ca_ops->cwnd_event(sk, event);
+}
+
+/* These functions determine how the current flow behaves in respect of SACK
+ * handling. SACK is negotiated with the peer, and therefore it can vary
+ * between different flows.
+ *
+ * tcp_is_sack - SACK enabled
+ * tcp_is_reno - No SACK
+ * tcp_is_fack - FACK enabled, implies SACK enabled
+ */
+static inline int tcp_is_sack(const struct tcp_sock *tp)
+{
+ return tp->rx_opt.sack_ok;
+}
+
+static inline int tcp_is_reno(const struct tcp_sock *tp)
+{
+ return !tcp_is_sack(tp);
+}
+
+static inline int tcp_is_fack(const struct tcp_sock *tp)
+{
+ return tp->rx_opt.sack_ok & 2;
+}
+
+static inline void tcp_enable_fack(struct tcp_sock *tp)
{
- if (tp->ca_ops->set_state)
- tp->ca_ops->set_state(tp, ca_state);
- tp->ca_state = ca_state;
+ tp->rx_opt.sack_ok |= 2;
}
-static inline void tcp_ca_event(struct tcp_sock *tp, enum tcp_ca_event event)
+static inline unsigned int tcp_left_out(const struct tcp_sock *tp)
{
- if (tp->ca_ops->cwnd_event)
- tp->ca_ops->cwnd_event(tp, event);
+ return tp->sacked_out + tp->lost_out;
}
/* This determines how many packets are "in the network" to the best
* "Packets left network, but not honestly ACKed yet" PLUS
* "Packets fast retransmitted"
*/
-static __inline__ unsigned int tcp_packets_in_flight(const struct tcp_sock *tp)
+static inline unsigned int tcp_packets_in_flight(const struct tcp_sock *tp)
{
- return (tp->packets_out - tp->left_out + tp->retrans_out);
+ 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.
*/
-static inline __u32 tcp_current_ssthresh(struct tcp_sock *tp)
+static inline __u32 tcp_current_ssthresh(const struct sock *sk)
{
- if ((1<<tp->ca_state)&(TCPF_CA_CWR|TCPF_CA_Recovery))
+ const struct tcp_sock *tp = tcp_sk(sk);
+ if ((1 << inet_csk(sk)->icsk_ca_state) & (TCPF_CA_CWR | TCPF_CA_Recovery))
return tp->snd_ssthresh;
else
return max(tp->snd_ssthresh,
(tp->snd_cwnd >> 2)));
}
-static inline void tcp_sync_left_out(struct tcp_sock *tp)
-{
- if (tp->rx_opt.sack_ok &&
- (tp->sacked_out >= tp->packets_out - tp->lost_out))
- tp->sacked_out = tp->packets_out - tp->lost_out;
- tp->left_out = tp->sacked_out + tp->lost_out;
-}
-
-/* Set slow start threshold and cwnd not falling to slow start */
-static inline void __tcp_enter_cwr(struct tcp_sock *tp)
-{
- tp->undo_marker = 0;
- tp->snd_ssthresh = tp->ca_ops->ssthresh(tp);
- tp->snd_cwnd = min(tp->snd_cwnd,
- tcp_packets_in_flight(tp) + 1U);
- tp->snd_cwnd_cnt = 0;
- tp->high_seq = tp->snd_nxt;
- tp->snd_cwnd_stamp = tcp_time_stamp;
- TCP_ECN_queue_cwr(tp);
-}
-
-static inline void tcp_enter_cwr(struct tcp_sock *tp)
-{
- tp->prior_ssthresh = 0;
- if (tp->ca_state < TCP_CA_CWR) {
- __tcp_enter_cwr(tp);
- tcp_set_ca_state(tp, TCP_CA_CWR);
- }
-}
+/* Use define here intentionally to get WARN_ON location shown at the caller */
+#define tcp_verify_left_out(tp) WARN_ON(tcp_left_out(tp) > tp->packets_out)
+extern void tcp_enter_cwr(struct sock *sk, const int set_ssthresh);
extern __u32 tcp_init_cwnd(struct tcp_sock *tp, struct dst_entry *dst);
/* Slow start with delack produces 3 packets of burst, so that
- * it is safe "de facto".
+ * it is safe "de facto". This will be the default - same as
+ * the default reordering threshold - but if reordering increases,
+ * we must be able to allow cwnd to burst at least this much in order
+ * to not pull it back when holes are filled.
*/
static __inline__ __u32 tcp_max_burst(const struct tcp_sock *tp)
{
- return 3;
+ return tp->reordering;
+}
+
+/* Returns end sequence number of the receiver's advertised window */
+static inline u32 tcp_wnd_end(const struct tcp_sock *tp)
+{
+ return tp->snd_una + tp->snd_wnd;
}
+extern int tcp_is_cwnd_limited(const struct sock *sk, u32 in_flight);
-static __inline__ void tcp_minshall_update(struct tcp_sock *tp, int mss,
- const struct sk_buff *skb)
+static inline void tcp_minshall_update(struct tcp_sock *tp, unsigned int mss,
+ const struct sk_buff *skb)
{
if (skb->len < mss)
tp->snd_sml = TCP_SKB_CB(skb)->end_seq;
}
-static __inline__ void tcp_check_probe_timer(struct sock *sk, struct tcp_sock *tp)
+static inline void tcp_check_probe_timer(struct sock *sk)
{
+ struct tcp_sock *tp = tcp_sk(sk);
const struct inet_connection_sock *icsk = inet_csk(sk);
+
if (!tp->packets_out && !icsk->icsk_pending)
- inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0, icsk->icsk_rto);
+ inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
+ icsk->icsk_rto, TCP_RTO_MAX);
}
-static __inline__ void tcp_push_pending_frames(struct sock *sk,
- struct tcp_sock *tp)
+static inline void tcp_push_pending_frames(struct sock *sk)
{
- __tcp_push_pending_frames(sk, tp, tcp_current_mss(sk, 1), tp->nonagle);
+ 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 ack, u32 seq)
+static inline void tcp_init_wl(struct tcp_sock *tp, u32 seq)
{
tp->snd_wl1 = seq;
}
-static __inline__ void tcp_update_wl(struct tcp_sock *tp, u32 ack, u32 seq)
+static inline void tcp_update_wl(struct tcp_sock *tp, u32 seq)
{
tp->snd_wl1 = seq;
}
-extern void tcp_destroy_sock(struct sock *sk);
-
-
/*
* Calculate(/check) TCP checksum
*/
-static __inline__ u16 tcp_v4_check(struct tcphdr *th, int len,
- unsigned long saddr, unsigned long daddr,
- unsigned long base)
+static inline __sum16 tcp_v4_check(int len, __be32 saddr,
+ __be32 daddr, __wsum base)
{
return csum_tcpudp_magic(saddr,daddr,len,IPPROTO_TCP,base);
}
-static __inline__ int __tcp_checksum_complete(struct sk_buff *skb)
+static inline __sum16 __tcp_checksum_complete(struct sk_buff *skb)
{
- return (unsigned short)csum_fold(skb_checksum(skb, 0, skb->len, skb->csum));
+ return __skb_checksum_complete(skb);
}
-static __inline__ int tcp_checksum_complete(struct sk_buff *skb)
+static inline int tcp_checksum_complete(struct sk_buff *skb)
{
- return skb->ip_summed != CHECKSUM_UNNECESSARY &&
+ return !skb_csum_unnecessary(skb) &&
__tcp_checksum_complete(skb);
}
/* Prequeue for VJ style copy to user, combined with checksumming. */
-static __inline__ void tcp_prequeue_init(struct tcp_sock *tp)
+static inline void tcp_prequeue_init(struct tcp_sock *tp)
{
tp->ucopy.task = NULL;
tp->ucopy.len = 0;
tp->ucopy.memory = 0;
skb_queue_head_init(&tp->ucopy.prequeue);
+#ifdef CONFIG_NET_DMA
+ tp->ucopy.dma_chan = NULL;
+ tp->ucopy.wakeup = 0;
+ tp->ucopy.pinned_list = NULL;
+ tp->ucopy.dma_cookie = 0;
+#endif
}
/* Packet is added to VJ-style prequeue for processing in process
*
* NOTE: is this not too big to inline?
*/
-static __inline__ int tcp_prequeue(struct sock *sk, struct sk_buff *skb)
+static inline int tcp_prequeue(struct sock *sk, struct sk_buff *skb)
{
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->sk_backlog_rcv(sk, skb1);
- NET_INC_STATS_BH(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);
+ 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_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;
}
"Close Wait","Last ACK","Listen","Closing"
};
#endif
+extern void tcp_set_state(struct sock *sk, int state);
-static __inline__ void tcp_set_state(struct sock *sk, int state)
-{
- int oldstate = sk->sk_state;
-
- switch (state) {
- case TCP_ESTABLISHED:
- if (oldstate != TCP_ESTABLISHED)
- TCP_INC_STATS(TCP_MIB_CURRESTAB);
- break;
-
- case TCP_CLOSE:
- if (oldstate == TCP_CLOSE_WAIT || oldstate == TCP_ESTABLISHED)
- TCP_INC_STATS(TCP_MIB_ESTABRESETS);
-
- sk->sk_prot->unhash(sk);
- if (inet_csk(sk)->icsk_bind_hash &&
- !(sk->sk_userlocks & SOCK_BINDPORT_LOCK))
- inet_put_port(&tcp_hashinfo, sk);
- /* fall through */
- default:
- if (oldstate==TCP_ESTABLISHED)
- TCP_DEC_STATS(TCP_MIB_CURRESTAB);
- }
-
- /* Change state AFTER socket is unhashed to avoid closed
- * socket sitting in hash tables.
- */
- sk->sk_state = state;
-
-#ifdef STATE_TRACE
- SOCK_DEBUG(sk, "TCP sk=%p, State %s -> %s\n",sk, statename[oldstate],statename[state]);
-#endif
-}
+extern void tcp_done(struct sock *sk);
-static __inline__ void tcp_done(struct sock *sk)
-{
- tcp_set_state(sk, TCP_CLOSE);
- tcp_clear_xmit_timers(sk);
-
- sk->sk_shutdown = SHUTDOWN_MASK;
-
- if (!sock_flag(sk, SOCK_DEAD))
- sk->sk_state_change(sk);
- else
- tcp_destroy_sock(sk);
-}
-
-static __inline__ void tcp_sack_reset(struct tcp_options_received *rx_opt)
+static inline void tcp_sack_reset(struct tcp_options_received *rx_opt)
{
rx_opt->dsack = 0;
- rx_opt->eff_sacks = 0;
rx_opt->num_sacks = 0;
}
-static __inline__ void tcp_build_and_update_options(__u32 *ptr, struct tcp_sock *tp, __u32 tstamp)
-{
- if (tp->rx_opt.tstamp_ok) {
- *ptr++ = __constant_htonl((TCPOPT_NOP << 24) |
- (TCPOPT_NOP << 16) |
- (TCPOPT_TIMESTAMP << 8) |
- TCPOLEN_TIMESTAMP);
- *ptr++ = htonl(tstamp);
- *ptr++ = htonl(tp->rx_opt.ts_recent);
- }
- if (tp->rx_opt.eff_sacks) {
- struct tcp_sack_block *sp = tp->rx_opt.dsack ? tp->duplicate_sack : tp->selective_acks;
- int this_sack;
-
- *ptr++ = __constant_htonl((TCPOPT_NOP << 24) |
- (TCPOPT_NOP << 16) |
- (TCPOPT_SACK << 8) |
- (TCPOLEN_SACK_BASE +
- (tp->rx_opt.eff_sacks * TCPOLEN_SACK_PERBLOCK)));
- for(this_sack = 0; this_sack < tp->rx_opt.eff_sacks; this_sack++) {
- *ptr++ = htonl(sp[this_sack].start_seq);
- *ptr++ = htonl(sp[this_sack].end_seq);
- }
- if (tp->rx_opt.dsack) {
- tp->rx_opt.dsack = 0;
- tp->rx_opt.eff_sacks--;
- }
- }
-}
-
-/* Construct a tcp options header for a SYN or SYN_ACK packet.
- * If this is every changed make sure to change the definition of
- * MAX_SYN_SIZE to match the new maximum number of options that you
- * can generate.
- */
-static inline void tcp_syn_build_options(__u32 *ptr, int mss, int ts, int sack,
- int offer_wscale, int wscale, __u32 tstamp, __u32 ts_recent)
-{
- /* We always get an MSS option.
- * The option bytes which will be seen in normal data
- * packets should timestamps be used, must be in the MSS
- * advertised. But we subtract them from tp->mss_cache so
- * that calculations in tcp_sendmsg are simpler etc.
- * So account for this fact here if necessary. If we
- * don't do this correctly, as a receiver we won't
- * recognize data packets as being full sized when we
- * should, and thus we won't abide by the delayed ACK
- * rules correctly.
- * SACKs don't matter, we never delay an ACK when we
- * have any of those going out.
- */
- *ptr++ = htonl((TCPOPT_MSS << 24) | (TCPOLEN_MSS << 16) | mss);
- if (ts) {
- if(sack)
- *ptr++ = __constant_htonl((TCPOPT_SACK_PERM << 24) | (TCPOLEN_SACK_PERM << 16) |
- (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP);
- else
- *ptr++ = __constant_htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
- (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP);
- *ptr++ = htonl(tstamp); /* TSVAL */
- *ptr++ = htonl(ts_recent); /* TSECR */
- } else if(sack)
- *ptr++ = __constant_htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
- (TCPOPT_SACK_PERM << 8) | TCPOLEN_SACK_PERM);
- if (offer_wscale)
- *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_WINDOW << 16) | (TCPOLEN_WINDOW << 8) | (wscale));
-}
-
/* 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,
return tcp_win_from_space(sk->sk_rcvbuf);
}
-static inline void inet_csk_reqsk_queue_add(struct sock *sk,
- struct request_sock *req,
- struct sock *child)
-{
- reqsk_queue_add(&inet_csk(sk)->icsk_accept_queue, req, sk, child);
-}
-
-static inline void inet_csk_reqsk_queue_removed(struct sock *sk,
- struct request_sock *req)
-{
- if (reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req) == 0)
- inet_csk_delete_keepalive_timer(sk);
-}
-
-static inline void inet_csk_reqsk_queue_added(struct sock *sk,
- const unsigned long timeout)
-{
- if (reqsk_queue_added(&inet_csk(sk)->icsk_accept_queue) == 0)
- inet_csk_reset_keepalive_timer(sk, timeout);
-}
-
-static inline int inet_csk_reqsk_queue_len(const struct sock *sk)
-{
- return reqsk_queue_len(&inet_csk(sk)->icsk_accept_queue);
-}
-
-static inline int inet_csk_reqsk_queue_young(const struct sock *sk)
-{
- return reqsk_queue_len_young(&inet_csk(sk)->icsk_accept_queue);
-}
-
-static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk)
-{
- return reqsk_queue_is_full(&inet_csk(sk)->icsk_accept_queue);
-}
-
-static inline void inet_csk_reqsk_queue_unlink(struct sock *sk,
- struct request_sock *req,
- struct request_sock **prev)
-{
- reqsk_queue_unlink(&inet_csk(sk)->icsk_accept_queue, req, prev);
-}
-
-static inline void inet_csk_reqsk_queue_drop(struct sock *sk,
- struct request_sock *req,
- struct request_sock **prev)
-{
- inet_csk_reqsk_queue_unlink(sk, req, prev);
- inet_csk_reqsk_queue_removed(sk, req);
- reqsk_free(req);
-}
-
-static __inline__ void tcp_openreq_init(struct request_sock *req,
- struct tcp_options_received *rx_opt,
- struct sk_buff *skb)
+static inline void tcp_openreq_init(struct request_sock *req,
+ struct tcp_options_received *rx_opt,
+ struct sk_buff *skb)
{
struct inet_request_sock *ireq = inet_rsk(req);
req->rcv_wnd = 0; /* So that tcp_send_synack() knows! */
+ req->cookie_ts = 0;
tcp_rsk(req)->rcv_isn = TCP_SKB_CB(skb)->seq;
req->mss = rx_opt->mss_clamp;
req->ts_recent = rx_opt->saw_tstamp ? rx_opt->rcv_tsval : 0;
ireq->wscale_ok = rx_opt->wscale_ok;
ireq->acked = 0;
ireq->ecn_ok = 0;
- ireq->rmt_port = skb->h.th->source;
+ ireq->rmt_port = tcp_hdr(skb)->source;
+ ireq->loc_port = tcp_hdr(skb)->dest;
}
-extern void tcp_enter_memory_pressure(void);
+extern void tcp_enter_memory_pressure(struct sock *sk);
static inline int keepalive_intvl_when(const struct tcp_sock *tp)
{
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 (xtime.tv_sec >= 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,
However, we can relax time bounds for RST segments to MSL.
*/
- if (rst && xtime.tv_sec >= rx_opt->ts_recent_stamp + TCP_PAWS_MSL)
+ if (rst && get_seconds() >= rx_opt->ts_recent_stamp + TCP_PAWS_MSL)
return 0;
return 1;
}
#define TCP_CHECK_TIMER(sk) do { } while (0)
-static inline int tcp_use_frto(const struct sock *sk)
+static inline void tcp_mib_init(struct net *net)
{
- const struct tcp_sock *tp = tcp_sk(sk);
-
- /* F-RTO must be activated in sysctl and there must be some
- * unsent new data, and the advertised window should allow
- * sending it.
- */
- return (sysctl_tcp_frto && sk->sk_send_head &&
- !after(TCP_SKB_CB(sk->sk_send_head)->end_seq,
- tp->snd_una + tp->snd_wnd));
+ /* See RFC 2012 */
+ TCP_ADD_STATS_USER(net, TCP_MIB_RTOALGORITHM, 1);
+ TCP_ADD_STATS_USER(net, TCP_MIB_RTOMIN, TCP_RTO_MIN*1000/HZ);
+ TCP_ADD_STATS_USER(net, TCP_MIB_RTOMAX, TCP_RTO_MAX*1000/HZ);
+ TCP_ADD_STATS_USER(net, TCP_MIB_MAXCONN, -1);
}
-static inline void tcp_mib_init(void)
+/* from STCP */
+static inline void tcp_clear_retrans_hints_partial(struct tcp_sock *tp)
{
- /* See RFC 2012 */
- TCP_ADD_STATS_USER(TCP_MIB_RTOALGORITHM, 1);
- TCP_ADD_STATS_USER(TCP_MIB_RTOMIN, TCP_RTO_MIN*1000/HZ);
- TCP_ADD_STATS_USER(TCP_MIB_RTOMAX, TCP_RTO_MAX*1000/HZ);
- TCP_ADD_STATS_USER(TCP_MIB_MAXCONN, -1);
+ tp->lost_skb_hint = NULL;
+ tp->scoreboard_skb_hint = NULL;
+}
+
+static inline void tcp_clear_all_retrans_hints(struct tcp_sock *tp)
+{
+ tcp_clear_retrans_hints_partial(tp);
+ tp->retransmit_skb_hint = NULL;
+}
+
+/* MD5 Signature */
+struct crypto_hash;
+
+/* - key database */
+struct tcp_md5sig_key {
+ u8 *key;
+ u8 keylen;
+};
+
+struct tcp4_md5sig_key {
+ struct tcp_md5sig_key base;
+ __be32 addr;
+};
+
+struct tcp6_md5sig_key {
+ struct tcp_md5sig_key base;
+#if 0
+ u32 scope_id; /* XXX */
+#endif
+ struct in6_addr addr;
+};
+
+/* - sock block */
+struct tcp_md5sig_info {
+ struct tcp4_md5sig_key *keys4;
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+ struct tcp6_md5sig_key *keys6;
+ u32 entries6;
+ u32 alloced6;
+#endif
+ u32 entries4;
+ u32 alloced4;
+};
+
+/* - pseudo header */
+struct tcp4_pseudohdr {
+ __be32 saddr;
+ __be32 daddr;
+ __u8 pad;
+ __u8 protocol;
+ __be16 len;
+};
+
+struct tcp6_pseudohdr {
+ struct in6_addr saddr;
+ struct in6_addr daddr;
+ __be32 len;
+ __be32 protocol; /* including padding */
+};
+
+union tcp_md5sum_block {
+ struct tcp4_pseudohdr ip4;
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+ struct tcp6_pseudohdr ip6;
+#endif
+};
+
+/* - pool: digest algorithm, hash description and scratch buffer */
+struct tcp_md5sig_pool {
+ struct hash_desc md5_desc;
+ union tcp_md5sum_block md5_blk;
+};
+
+#define TCP_MD5SIG_MAXKEYS (~(u32)0) /* really?! */
+
+/* - functions */
+extern int tcp_v4_md5_hash_skb(char *md5_hash,
+ struct tcp_md5sig_key *key,
+ struct sock *sk,
+ struct request_sock *req,
+ struct sk_buff *skb);
+
+extern struct tcp_md5sig_key *tcp_v4_md5_lookup(struct sock *sk,
+ struct sock *addr_sk);
+
+extern int tcp_v4_md5_do_add(struct sock *sk,
+ __be32 addr,
+ u8 *newkey,
+ u8 newkeylen);
+
+extern int tcp_v4_md5_do_del(struct sock *sk,
+ __be32 addr);
+
+#ifdef CONFIG_TCP_MD5SIG
+#define tcp_twsk_md5_key(twsk) ((twsk)->tw_md5_keylen ? \
+ &(struct tcp_md5sig_key) { \
+ .key = (twsk)->tw_md5_key, \
+ .keylen = (twsk)->tw_md5_keylen, \
+ } : NULL)
+#else
+#define tcp_twsk_md5_key(twsk) NULL
+#endif
+
+extern struct tcp_md5sig_pool **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 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)
+{
+ struct sk_buff *skb;
+
+ 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_peek(&sk->sk_write_queue);
+}
+
+static inline struct sk_buff *tcp_write_queue_tail(struct sock *sk)
+{
+ return skb_peek_tail(&sk->sk_write_queue);
+}
+
+static inline struct sk_buff *tcp_write_queue_next(struct sock *sk, struct sk_buff *skb)
+{
+ return skb_queue_next(&sk->sk_write_queue, skb);
+}
+
+static inline struct sk_buff *tcp_write_queue_prev(struct sock *sk, struct sk_buff *skb)
+{
+ return skb_queue_prev(&sk->sk_write_queue, skb);
+}
+
+#define tcp_for_write_queue(skb, sk) \
+ skb_queue_walk(&(sk)->sk_write_queue, skb)
+
+#define tcp_for_write_queue_from(skb, sk) \
+ skb_queue_walk_from(&(sk)->sk_write_queue, skb)
+
+#define tcp_for_write_queue_from_safe(skb, tmp, sk) \
+ skb_queue_walk_from_safe(&(sk)->sk_write_queue, skb, tmp)
+
+
+static inline struct sk_buff *tcp_send_head(struct sock *sk)
+{
+ return sk->sk_send_head;
+}
+
+static inline bool tcp_skb_is_last(const struct sock *sk,
+ const struct sk_buff *skb)
+{
+ return skb_queue_is_last(&sk->sk_write_queue, skb);
+}
+
+static inline void tcp_advance_send_head(struct sock *sk, struct sk_buff *skb)
+{
+ if (tcp_skb_is_last(sk, skb))
+ sk->sk_send_head = NULL;
+ else
+ sk->sk_send_head = tcp_write_queue_next(sk, skb);
+}
+
+static inline void tcp_check_send_head(struct sock *sk, struct sk_buff *skb_unlinked)
+{
+ if (sk->sk_send_head == skb_unlinked)
+ sk->sk_send_head = NULL;
+}
+
+static inline void tcp_init_send_head(struct sock *sk)
+{
+ sk->sk_send_head = NULL;
+}
+
+static inline void __tcp_add_write_queue_tail(struct sock *sk, struct sk_buff *skb)
+{
+ __skb_queue_tail(&sk->sk_write_queue, skb);
+}
+
+static inline void tcp_add_write_queue_tail(struct sock *sk, struct sk_buff *skb)
+{
+ __tcp_add_write_queue_tail(sk, skb);
+
+ /* Queue it, remembering where we must start sending. */
+ if (sk->sk_send_head == NULL) {
+ sk->sk_send_head = skb;
+
+ if (tcp_sk(sk)->highest_sack == NULL)
+ tcp_sk(sk)->highest_sack = skb;
+ }
+}
+
+static inline void __tcp_add_write_queue_head(struct sock *sk, struct sk_buff *skb)
+{
+ __skb_queue_head(&sk->sk_write_queue, skb);
+}
+
+/* Insert buff after skb on the write queue of sk. */
+static inline void tcp_insert_write_queue_after(struct sk_buff *skb,
+ struct sk_buff *buff,
+ struct sock *sk)
+{
+ __skb_queue_after(&sk->sk_write_queue, skb, buff);
+}
+
+/* Insert new before skb on the write queue of sk. */
+static inline void tcp_insert_write_queue_before(struct sk_buff *new,
+ struct sk_buff *skb,
+ struct sock *sk)
+{
+ __skb_queue_before(&sk->sk_write_queue, skb, new);
+
+ if (sk->sk_send_head == skb)
+ sk->sk_send_head = new;
+}
+
+static inline void tcp_unlink_write_queue(struct sk_buff *skb, struct sock *sk)
+{
+ __skb_unlink(skb, &sk->sk_write_queue);
+}
+
+static inline int tcp_write_queue_empty(struct sock *sk)
+{
+ return skb_queue_empty(&sk->sk_write_queue);
+}
+
+/* Start sequence of the highest skb with SACKed bit, valid only if
+ * sacked > 0 or when the caller has ensured validity by itself.
+ */
+static inline u32 tcp_highest_sack_seq(struct tcp_sock *tp)
+{
+ if (!tp->sacked_out)
+ return tp->snd_una;
+
+ if (tp->highest_sack == NULL)
+ return tp->snd_nxt;
+
+ return TCP_SKB_CB(tp->highest_sack)->seq;
+}
+
+static inline void tcp_advance_highest_sack(struct sock *sk, struct sk_buff *skb)
+{
+ tcp_sk(sk)->highest_sack = tcp_skb_is_last(sk, skb) ? NULL :
+ tcp_write_queue_next(sk, skb);
+}
+
+static inline struct sk_buff *tcp_highest_sack(struct sock *sk)
+{
+ return tcp_sk(sk)->highest_sack;
+}
+
+static inline void tcp_highest_sack_reset(struct sock *sk)
+{
+ tcp_sk(sk)->highest_sack = tcp_write_queue_head(sk);
+}
+
+/* Called when old skb is about to be deleted (to be combined with new skb) */
+static inline void tcp_highest_sack_combine(struct sock *sk,
+ struct sk_buff *old,
+ struct sk_buff *new)
+{
+ if (tcp_sk(sk)->sacked_out && (old == tcp_sk(sk)->highest_sack))
+ tcp_sk(sk)->highest_sack = new;
}
/* /proc */
};
struct tcp_seq_afinfo {
- struct module *owner;
char *name;
sa_family_t family;
- int (*seq_show) (struct seq_file *m, void *v);
- struct file_operations *seq_fops;
+ struct file_operations seq_fops;
+ struct seq_operations seq_ops;
};
struct tcp_iter_state {
+ struct seq_net_private p;
sa_family_t family;
enum tcp_seq_states state;
struct sock *syn_wait_sk;
int bucket, sbucket, num, uid;
- struct seq_operations seq_ops;
};
-extern int tcp_proc_register(struct tcp_seq_afinfo *afinfo);
-extern void tcp_proc_unregister(struct tcp_seq_afinfo *afinfo);
+extern int tcp_proc_register(struct net *net, struct tcp_seq_afinfo *afinfo);
+extern void tcp_proc_unregister(struct net *net, struct tcp_seq_afinfo *afinfo);
+
+extern struct request_sock_ops tcp_request_sock_ops;
+extern struct request_sock_ops tcp6_request_sock_ops;
+
+extern void tcp_v4_destroy_sock(struct sock *sk);
+
+extern int tcp_v4_gso_send_check(struct sk_buff *skb);
+extern struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int features);
+extern struct sk_buff **tcp_gro_receive(struct sk_buff **head,
+ struct sk_buff *skb);
+extern struct sk_buff **tcp4_gro_receive(struct sk_buff **head,
+ struct sk_buff *skb);
+extern int tcp_gro_complete(struct sk_buff *skb);
+extern int tcp4_gro_complete(struct sk_buff *skb);
+
+#ifdef CONFIG_PROC_FS
+extern int tcp4_proc_init(void);
+extern void tcp4_proc_exit(void);
+#endif
+
+/* TCP af-specific functions */
+struct tcp_sock_af_ops {
+#ifdef CONFIG_TCP_MD5SIG
+ struct tcp_md5sig_key *(*md5_lookup) (struct sock *sk,
+ struct sock *addr_sk);
+ int (*calc_md5_hash) (char *location,
+ struct tcp_md5sig_key *md5,
+ struct sock *sk,
+ struct request_sock *req,
+ struct sk_buff *skb);
+ int (*md5_add) (struct sock *sk,
+ struct sock *addr_sk,
+ u8 *newkey,
+ u8 len);
+ int (*md5_parse) (struct sock *sk,
+ char __user *optval,
+ int optlen);
+#endif
+};
+
+struct tcp_request_sock_ops {
+#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);
#endif /* _TCP_H */
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff