diff options
Diffstat (limited to 'net/dccp')
-rw-r--r-- | net/dccp/ackvec.c | 20 | ||||
-rw-r--r-- | net/dccp/ackvec.h | 4 | ||||
-rw-r--r-- | net/dccp/ccids/Kconfig | 8 | ||||
-rw-r--r-- | net/dccp/ccids/ccid2.c | 204 | ||||
-rw-r--r-- | net/dccp/ccids/ccid2.h | 9 | ||||
-rw-r--r-- | net/dccp/ccids/ccid3.c | 12 | ||||
-rw-r--r-- | net/dccp/dccp.h | 2 | ||||
-rw-r--r-- | net/dccp/feat.h | 5 | ||||
-rw-r--r-- | net/dccp/ipv4.c | 14 | ||||
-rw-r--r-- | net/dccp/ipv6.c | 15 | ||||
-rw-r--r-- | net/dccp/output.c | 90 | ||||
-rw-r--r-- | net/dccp/proto.c | 16 | ||||
-rw-r--r-- | net/dccp/sysctl.c | 8 |
13 files changed, 264 insertions, 143 deletions
diff --git a/net/dccp/ackvec.c b/net/dccp/ackvec.c index 8c211c5..4d176d3 100644 --- a/net/dccp/ackvec.c +++ b/net/dccp/ackvec.c @@ -142,14 +142,13 @@ struct dccp_ackvec *dccp_ackvec_alloc(const gfp_t priority) struct dccp_ackvec *av = kmem_cache_alloc(dccp_ackvec_slab, priority); if (av != NULL) { - av->dccpav_buf_head = - av->dccpav_buf_tail = DCCP_MAX_ACKVEC_LEN - 1; + av->dccpav_buf_head = DCCP_MAX_ACKVEC_LEN - 1; av->dccpav_buf_ackno = DCCP_MAX_SEQNO + 1; av->dccpav_buf_nonce = av->dccpav_buf_nonce = 0; av->dccpav_ack_ptr = 0; av->dccpav_time.tv_sec = 0; av->dccpav_time.tv_usec = 0; - av->dccpav_sent_len = av->dccpav_vec_len = 0; + av->dccpav_vec_len = 0; INIT_LIST_HEAD(&av->dccpav_records); } @@ -353,11 +352,13 @@ static void dccp_ackvec_throw_record(struct dccp_ackvec *av, { struct dccp_ackvec_record *next; - av->dccpav_buf_tail = avr->dccpavr_ack_ptr - 1; - if (av->dccpav_buf_tail == 0) - av->dccpav_buf_tail = DCCP_MAX_ACKVEC_LEN - 1; - - av->dccpav_vec_len -= avr->dccpavr_sent_len; + /* sort out vector length */ + if (av->dccpav_buf_head <= avr->dccpavr_ack_ptr) + av->dccpav_vec_len = avr->dccpavr_ack_ptr - av->dccpav_buf_head; + else + av->dccpav_vec_len = DCCP_MAX_ACKVEC_LEN - 1 + - av->dccpav_buf_head + + avr->dccpavr_ack_ptr; /* free records */ list_for_each_entry_safe_from(avr, next, &av->dccpav_records, @@ -434,8 +435,7 @@ static void dccp_ackvec_check_rcv_ackvector(struct dccp_ackvec *av, break; found: if (between48(avr->dccpavr_ack_seqno, ackno_end_rl, ackno)) { - const u8 state = (*vector & - DCCP_ACKVEC_STATE_MASK) >> 6; + const u8 state = *vector & DCCP_ACKVEC_STATE_MASK; if (state != DCCP_ACKVEC_STATE_NOT_RECEIVED) { #ifdef CONFIG_IP_DCCP_DEBUG struct dccp_sock *dp = dccp_sk(sk); diff --git a/net/dccp/ackvec.h b/net/dccp/ackvec.h index 0adf4b5..2424eff 100644 --- a/net/dccp/ackvec.h +++ b/net/dccp/ackvec.h @@ -54,9 +54,7 @@ struct dccp_ackvec { struct list_head dccpav_records; struct timeval dccpav_time; u8 dccpav_buf_head; - u8 dccpav_buf_tail; u8 dccpav_ack_ptr; - u8 dccpav_sent_len; u8 dccpav_vec_len; u8 dccpav_buf_nonce; u8 dccpav_ack_nonce; @@ -107,7 +105,7 @@ extern int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb); static inline int dccp_ackvec_pending(const struct dccp_ackvec *av) { - return av->dccpav_sent_len != av->dccpav_vec_len; + return av->dccpav_vec_len; } #else /* CONFIG_IP_DCCP_ACKVEC */ static inline int dccp_ackvec_init(void) diff --git a/net/dccp/ccids/Kconfig b/net/dccp/ccids/Kconfig index ca00191..32752f7 100644 --- a/net/dccp/ccids/Kconfig +++ b/net/dccp/ccids/Kconfig @@ -30,6 +30,14 @@ config IP_DCCP_CCID2 If in doubt, say M. +config IP_DCCP_CCID2_DEBUG + bool "CCID2 debug" + depends on IP_DCCP_CCID2 + ---help--- + Enable CCID2 debug messages. + + If in doubt, say N. + config IP_DCCP_CCID3 tristate "CCID3 (TCP-Friendly) (EXPERIMENTAL)" depends on IP_DCCP diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c index e961562..457dd3d 100644 --- a/net/dccp/ccids/ccid2.c +++ b/net/dccp/ccids/ccid2.c @@ -27,7 +27,6 @@ * * BUGS: * - sequence number wrapping - * - jiffies wrapping */ #include "../ccid.h" @@ -36,8 +35,7 @@ static int ccid2_debug; -#undef CCID2_DEBUG -#ifdef CCID2_DEBUG +#ifdef CONFIG_IP_DCCP_CCID2_DEBUG #define ccid2_pr_debug(format, a...) \ do { if (ccid2_debug) \ printk(KERN_DEBUG "%s: " format, __FUNCTION__, ##a); \ @@ -46,9 +44,7 @@ static int ccid2_debug; #define ccid2_pr_debug(format, a...) #endif -static const int ccid2_seq_len = 128; - -#ifdef CCID2_DEBUG +#ifdef CONFIG_IP_DCCP_CCID2_DEBUG static void ccid2_hc_tx_check_sanity(const struct ccid2_hc_tx_sock *hctx) { int len = 0; @@ -71,8 +67,8 @@ static void ccid2_hc_tx_check_sanity(const struct ccid2_hc_tx_sock *hctx) /* packets are sent sequentially */ BUG_ON(seqp->ccid2s_seq <= prev->ccid2s_seq); - BUG_ON(seqp->ccid2s_sent < prev->ccid2s_sent); - BUG_ON(len > ccid2_seq_len); + BUG_ON(time_before(seqp->ccid2s_sent, + prev->ccid2s_sent)); seqp = prev; } @@ -84,16 +80,57 @@ static void ccid2_hc_tx_check_sanity(const struct ccid2_hc_tx_sock *hctx) do { seqp = seqp->ccid2s_prev; len++; - BUG_ON(len > ccid2_seq_len); } while (seqp != hctx->ccid2hctx_seqh); - BUG_ON(len != ccid2_seq_len); ccid2_pr_debug("total len=%d\n", len); + BUG_ON(len != hctx->ccid2hctx_seqbufc * CCID2_SEQBUF_LEN); } #else #define ccid2_hc_tx_check_sanity(hctx) do {} while (0) #endif +static int ccid2_hc_tx_alloc_seq(struct ccid2_hc_tx_sock *hctx, int num, + gfp_t gfp) +{ + struct ccid2_seq *seqp; + int i; + + /* check if we have space to preserve the pointer to the buffer */ + if (hctx->ccid2hctx_seqbufc >= (sizeof(hctx->ccid2hctx_seqbuf) / + sizeof(struct ccid2_seq*))) + return -ENOMEM; + + /* allocate buffer and initialize linked list */ + seqp = kmalloc(sizeof(*seqp) * num, gfp); + if (seqp == NULL) + return -ENOMEM; + + for (i = 0; i < (num - 1); i++) { + seqp[i].ccid2s_next = &seqp[i + 1]; + seqp[i + 1].ccid2s_prev = &seqp[i]; + } + seqp[num - 1].ccid2s_next = seqp; + seqp->ccid2s_prev = &seqp[num - 1]; + + /* This is the first allocation. Initiate the head and tail. */ + if (hctx->ccid2hctx_seqbufc == 0) + hctx->ccid2hctx_seqh = hctx->ccid2hctx_seqt = seqp; + else { + /* link the existing list with the one we just created */ + hctx->ccid2hctx_seqh->ccid2s_next = seqp; + seqp->ccid2s_prev = hctx->ccid2hctx_seqh; + + hctx->ccid2hctx_seqt->ccid2s_prev = &seqp[num - 1]; + seqp[num - 1].ccid2s_next = hctx->ccid2hctx_seqt; + } + + /* store the original pointer to the buffer so we can free it */ + hctx->ccid2hctx_seqbuf[hctx->ccid2hctx_seqbufc] = seqp; + hctx->ccid2hctx_seqbufc++; + + return 0; +} + static int ccid2_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb, int len) { @@ -122,7 +159,7 @@ static int ccid2_hc_tx_send_packet(struct sock *sk, } } - return 100; /* XXX */ + return 1; /* XXX CCID should dequeue when ready instead of polling */ } static void ccid2_change_l_ack_ratio(struct sock *sk, int val) @@ -150,10 +187,8 @@ static void ccid2_change_l_ack_ratio(struct sock *sk, int val) dp->dccps_l_ack_ratio = val; } -static void ccid2_change_cwnd(struct sock *sk, int val) +static void ccid2_change_cwnd(struct ccid2_hc_tx_sock *hctx, int val) { - struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); - if (val == 0) val = 1; @@ -164,6 +199,17 @@ static void ccid2_change_cwnd(struct sock *sk, int val) hctx->ccid2hctx_cwnd = val; } +static void ccid2_change_srtt(struct ccid2_hc_tx_sock *hctx, long val) +{ + ccid2_pr_debug("change SRTT to %ld\n", val); + hctx->ccid2hctx_srtt = val; +} + +static void ccid2_change_pipe(struct ccid2_hc_tx_sock *hctx, long val) +{ + hctx->ccid2hctx_pipe = val; +} + static void ccid2_start_rto_timer(struct sock *sk); static void ccid2_hc_tx_rto_expire(unsigned long data) @@ -193,11 +239,11 @@ static void ccid2_hc_tx_rto_expire(unsigned long data) ccid2_start_rto_timer(sk); /* adjust pipe, cwnd etc */ - hctx->ccid2hctx_pipe = 0; + ccid2_change_pipe(hctx, 0); hctx->ccid2hctx_ssthresh = hctx->ccid2hctx_cwnd >> 1; if (hctx->ccid2hctx_ssthresh < 2) hctx->ccid2hctx_ssthresh = 2; - ccid2_change_cwnd(sk, 1); + ccid2_change_cwnd(hctx, 1); /* clear state about stuff we sent */ hctx->ccid2hctx_seqt = hctx->ccid2hctx_seqh; @@ -232,13 +278,14 @@ static void ccid2_hc_tx_packet_sent(struct sock *sk, int more, int len) { struct dccp_sock *dp = dccp_sk(sk); struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); + struct ccid2_seq *next; u64 seq; ccid2_hc_tx_check_sanity(hctx); BUG_ON(!hctx->ccid2hctx_sendwait); hctx->ccid2hctx_sendwait = 0; - hctx->ccid2hctx_pipe++; + ccid2_change_pipe(hctx, hctx->ccid2hctx_pipe + 1); BUG_ON(hctx->ccid2hctx_pipe < 0); /* There is an issue. What if another packet is sent between @@ -251,15 +298,23 @@ static void ccid2_hc_tx_packet_sent(struct sock *sk, int more, int len) hctx->ccid2hctx_seqh->ccid2s_seq = seq; hctx->ccid2hctx_seqh->ccid2s_acked = 0; hctx->ccid2hctx_seqh->ccid2s_sent = jiffies; - hctx->ccid2hctx_seqh = hctx->ccid2hctx_seqh->ccid2s_next; - ccid2_pr_debug("cwnd=%d pipe=%d\n", hctx->ccid2hctx_cwnd, - hctx->ccid2hctx_pipe); + next = hctx->ccid2hctx_seqh->ccid2s_next; + /* check if we need to alloc more space */ + if (next == hctx->ccid2hctx_seqt) { + int rc; + + ccid2_pr_debug("allocating more space in history\n"); + rc = ccid2_hc_tx_alloc_seq(hctx, CCID2_SEQBUF_LEN, GFP_KERNEL); + BUG_ON(rc); /* XXX what do we do? */ - if (hctx->ccid2hctx_seqh == hctx->ccid2hctx_seqt) { - /* XXX allocate more space */ - WARN_ON(1); + next = hctx->ccid2hctx_seqh->ccid2s_next; + BUG_ON(next == hctx->ccid2hctx_seqt); } + hctx->ccid2hctx_seqh = next; + + ccid2_pr_debug("cwnd=%d pipe=%d\n", hctx->ccid2hctx_cwnd, + hctx->ccid2hctx_pipe); hctx->ccid2hctx_sent++; @@ -295,7 +350,7 @@ static void ccid2_hc_tx_packet_sent(struct sock *sk, int more, int len) if (!timer_pending(&hctx->ccid2hctx_rtotimer)) ccid2_start_rto_timer(sk); -#ifdef CCID2_DEBUG +#ifdef CONFIG_IP_DCCP_CCID2_DEBUG ccid2_pr_debug("pipe=%d\n", hctx->ccid2hctx_pipe); ccid2_pr_debug("Sent: seq=%llu\n", seq); do { @@ -398,7 +453,7 @@ static inline void ccid2_new_ack(struct sock *sk, /* increase every 2 acks */ hctx->ccid2hctx_ssacks++; if (hctx->ccid2hctx_ssacks == 2) { - ccid2_change_cwnd(sk, hctx->ccid2hctx_cwnd + 1); + ccid2_change_cwnd(hctx, hctx->ccid2hctx_cwnd+1); hctx->ccid2hctx_ssacks = 0; *maxincr = *maxincr - 1; } @@ -411,26 +466,28 @@ static inline void ccid2_new_ack(struct sock *sk, hctx->ccid2hctx_acks++; if (hctx->ccid2hctx_acks >= hctx->ccid2hctx_cwnd) { - ccid2_change_cwnd(sk, hctx->ccid2hctx_cwnd + 1); + ccid2_change_cwnd(hctx, hctx->ccid2hctx_cwnd + 1); hctx->ccid2hctx_acks = 0; } } /* update RTO */ if (hctx->ccid2hctx_srtt == -1 || - (jiffies - hctx->ccid2hctx_lastrtt) >= hctx->ccid2hctx_srtt) { - unsigned long r = jiffies - seqp->ccid2s_sent; + time_after(jiffies, hctx->ccid2hctx_lastrtt + hctx->ccid2hctx_srtt)) { + unsigned long r = (long)jiffies - (long)seqp->ccid2s_sent; int s; /* first measurement */ if (hctx->ccid2hctx_srtt == -1) { ccid2_pr_debug("R: %lu Time=%lu seq=%llu\n", r, jiffies, seqp->ccid2s_seq); - hctx->ccid2hctx_srtt = r; + ccid2_change_srtt(hctx, r); hctx->ccid2hctx_rttvar = r >> 1; } else { /* RTTVAR */ long tmp = hctx->ccid2hctx_srtt - r; + long srtt; + if (tmp < 0) tmp *= -1; @@ -440,10 +497,12 @@ static inline void ccid2_new_ack(struct sock *sk, hctx->ccid2hctx_rttvar += tmp; /* SRTT */ - hctx->ccid2hctx_srtt *= 7; - hctx->ccid2hctx_srtt >>= 3; + srtt = hctx->ccid2hctx_srtt; + srtt *= 7; + srtt >>= 3; tmp = r >> 3; - hctx->ccid2hctx_srtt += tmp; + srtt += tmp; + ccid2_change_srtt(hctx, srtt); } s = hctx->ccid2hctx_rttvar << 2; /* clock granularity is 1 when based on jiffies */ @@ -479,13 +538,29 @@ static void ccid2_hc_tx_dec_pipe(struct sock *sk) { struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); - hctx->ccid2hctx_pipe--; + ccid2_change_pipe(hctx, hctx->ccid2hctx_pipe-1); BUG_ON(hctx->ccid2hctx_pipe < 0); if (hctx->ccid2hctx_pipe == 0) ccid2_hc_tx_kill_rto_timer(sk); } +static void ccid2_congestion_event(struct ccid2_hc_tx_sock *hctx, + struct ccid2_seq *seqp) +{ + if (time_before(seqp->ccid2s_sent, hctx->ccid2hctx_last_cong)) { + ccid2_pr_debug("Multiple losses in an RTT---treating as one\n"); + return; + } + + hctx->ccid2hctx_last_cong = jiffies; + + ccid2_change_cwnd(hctx, hctx->ccid2hctx_cwnd >> 1); + hctx->ccid2hctx_ssthresh = hctx->ccid2hctx_cwnd; + if (hctx->ccid2hctx_ssthresh < 2) + hctx->ccid2hctx_ssthresh = 2; +} + static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) { struct dccp_sock *dp = dccp_sk(sk); @@ -496,7 +571,6 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) unsigned char veclen; int offset = 0; int done = 0; - int loss = 0; unsigned int maxincr = 0; ccid2_hc_tx_check_sanity(hctx); @@ -582,15 +656,16 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) * run length */ while (between48(seqp->ccid2s_seq,ackno_end_rl,ackno)) { - const u8 state = (*vector & - DCCP_ACKVEC_STATE_MASK) >> 6; + const u8 state = *vector & + DCCP_ACKVEC_STATE_MASK; /* new packet received or marked */ if (state != DCCP_ACKVEC_STATE_NOT_RECEIVED && !seqp->ccid2s_acked) { if (state == DCCP_ACKVEC_STATE_ECN_MARKED) { - loss = 1; + ccid2_congestion_event(hctx, + seqp); } else ccid2_new_ack(sk, seqp, &maxincr); @@ -642,7 +717,13 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) /* check for lost packets */ while (1) { if (!seqp->ccid2s_acked) { - loss = 1; + ccid2_pr_debug("Packet lost: %llu\n", + seqp->ccid2s_seq); + /* XXX need to traverse from tail -> head in + * order to detect multiple congestion events in + * one ack vector. + */ + ccid2_congestion_event(hctx, seqp); ccid2_hc_tx_dec_pipe(sk); } if (seqp == hctx->ccid2hctx_seqt) @@ -661,53 +742,33 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) hctx->ccid2hctx_seqt = hctx->ccid2hctx_seqt->ccid2s_next; } - if (loss) { - /* XXX do bit shifts guarantee a 0 as the new bit? */ - ccid2_change_cwnd(sk, hctx->ccid2hctx_cwnd >> 1); - hctx->ccid2hctx_ssthresh = hctx->ccid2hctx_cwnd; - if (hctx->ccid2hctx_ssthresh < 2) - hctx->ccid2hctx_ssthresh = 2; - } - ccid2_hc_tx_check_sanity(hctx); } static int ccid2_hc_tx_init(struct ccid *ccid, struct sock *sk) { struct ccid2_hc_tx_sock *hctx = ccid_priv(ccid); - int seqcount = ccid2_seq_len; - int i; - /* XXX init variables with proper values */ - hctx->ccid2hctx_cwnd = 1; - hctx->ccid2hctx_ssthresh = 10; + ccid2_change_cwnd(hctx, 1); + /* Initialize ssthresh to infinity. This means that we will exit the + * initial slow-start after the first packet loss. This is what we + * want. + */ + hctx->ccid2hctx_ssthresh = ~0; hctx->ccid2hctx_numdupack = 3; + hctx->ccid2hctx_seqbufc = 0; /* XXX init ~ to window size... */ - hctx->ccid2hctx_seqbuf = kmalloc(sizeof(*hctx->ccid2hctx_seqbuf) * - seqcount, gfp_any()); - if (hctx->ccid2hctx_seqbuf == NULL) + if (ccid2_hc_tx_alloc_seq(hctx, CCID2_SEQBUF_LEN, GFP_ATOMIC) != 0) return -ENOMEM; - for (i = 0; i < (seqcount - 1); i++) { - hctx->ccid2hctx_seqbuf[i].ccid2s_next = - &hctx->ccid2hctx_seqbuf[i + 1]; - hctx->ccid2hctx_seqbuf[i + 1].ccid2s_prev = - &hctx->ccid2hctx_seqbuf[i]; - } - hctx->ccid2hctx_seqbuf[seqcount - 1].ccid2s_next = - hctx->ccid2hctx_seqbuf; - hctx->ccid2hctx_seqbuf->ccid2s_prev = - &hctx->ccid2hctx_seqbuf[seqcount - 1]; - - hctx->ccid2hctx_seqh = hctx->ccid2hctx_seqbuf; - hctx->ccid2hctx_seqt = hctx->ccid2hctx_seqh; hctx->ccid2hctx_sent = 0; hctx->ccid2hctx_rto = 3 * HZ; - hctx->ccid2hctx_srtt = -1; + ccid2_change_srtt(hctx, -1); hctx->ccid2hctx_rttvar = -1; hctx->ccid2hctx_lastrtt = 0; hctx->ccid2hctx_rpdupack = -1; + hctx->ccid2hctx_last_cong = jiffies; hctx->ccid2hctx_rtotimer.function = &ccid2_hc_tx_rto_expire; hctx->ccid2hctx_rtotimer.data = (unsigned long)sk; @@ -720,10 +781,13 @@ static int ccid2_hc_tx_init(struct ccid *ccid, struct sock *sk) static void ccid2_hc_tx_exit(struct sock *sk) { struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); + int i; ccid2_hc_tx_kill_rto_timer(sk); - kfree(hctx->ccid2hctx_seqbuf); - hctx->ccid2hctx_seqbuf = NULL; + + for (i = 0; i < hctx->ccid2hctx_seqbufc; i++) + kfree(hctx->ccid2hctx_seqbuf[i]); + hctx->ccid2hctx_seqbufc = 0; } static void ccid2_hc_rx_packet_recv(struct sock *sk, struct sk_buff *skb) diff --git a/net/dccp/ccids/ccid2.h b/net/dccp/ccids/ccid2.h index 451a874..5b2ef4a 100644 --- a/net/dccp/ccids/ccid2.h +++ b/net/dccp/ccids/ccid2.h @@ -35,6 +35,9 @@ struct ccid2_seq { struct ccid2_seq *ccid2s_next; }; +#define CCID2_SEQBUF_LEN 256 +#define CCID2_SEQBUF_MAX 128 + /** struct ccid2_hc_tx_sock - CCID2 TX half connection * * @ccid2hctx_ssacks - ACKs recv in slow start @@ -50,10 +53,11 @@ struct ccid2_hc_tx_sock { int ccid2hctx_cwnd; int ccid2hctx_ssacks; int ccid2hctx_acks; - int ccid2hctx_ssthresh; + unsigned int ccid2hctx_ssthresh; int ccid2hctx_pipe; int ccid2hctx_numdupack; - struct ccid2_seq *ccid2hctx_seqbuf; + struct ccid2_seq *ccid2hctx_seqbuf[CCID2_SEQBUF_MAX]; + int ccid2hctx_seqbufc; struct ccid2_seq *ccid2hctx_seqh; struct ccid2_seq *ccid2hctx_seqt; long ccid2hctx_rto; @@ -67,6 +71,7 @@ struct ccid2_hc_tx_sock { u64 ccid2hctx_rpseq; int ccid2hctx_rpdupack; int ccid2hctx_sendwait; + unsigned long ccid2hctx_last_cong; }; struct ccid2_hc_rx_sock { diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c index 090bc39..195aa95 100644 --- a/net/dccp/ccids/ccid3.c +++ b/net/dccp/ccids/ccid3.c @@ -900,7 +900,7 @@ found: static void ccid3_hc_rx_update_li(struct sock *sk, u64 seq_loss, u8 win_loss) { struct ccid3_hc_rx_sock *hcrx = ccid3_hc_rx_sk(sk); - struct dccp_li_hist_entry *next, *head; + struct dccp_li_hist_entry *head; u64 seq_temp; if (list_empty(&hcrx->ccid3hcrx_li_hist)) { @@ -908,15 +908,15 @@ static void ccid3_hc_rx_update_li(struct sock *sk, u64 seq_loss, u8 win_loss) &hcrx->ccid3hcrx_li_hist, seq_loss, win_loss)) return; - next = (struct dccp_li_hist_entry *) - hcrx->ccid3hcrx_li_hist.next; - next->dccplih_interval = ccid3_hc_rx_calc_first_li(sk); + head = list_entry(hcrx->ccid3hcrx_li_hist.next, + struct dccp_li_hist_entry, dccplih_node); + head->dccplih_interval = ccid3_hc_rx_calc_first_li(sk); } else { struct dccp_li_hist_entry *entry; struct list_head *tail; - head = (struct dccp_li_hist_entry *) - hcrx->ccid3hcrx_li_hist.next; + head = list_entry(hcrx->ccid3hcrx_li_hist.next, + struct dccp_li_hist_entry, dccplih_node); /* FIXME win count check removed as was wrong */ /* should make this check with receive history */ /* and compare there as per section 10.2 of RFC4342 */ diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index a5c5475..0a21be4 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -130,7 +130,7 @@ extern void dccp_send_delayed_ack(struct sock *sk); extern void dccp_send_sync(struct sock *sk, const u64 seq, const enum dccp_pkt_type pkt_type); -extern int dccp_write_xmit(struct sock *sk, struct sk_buff *skb, long *timeo); +extern void dccp_write_xmit(struct sock *sk, int block); extern void dccp_write_space(struct sock *sk); extern void dccp_init_xmit_timers(struct sock *sk); diff --git a/net/dccp/feat.h b/net/dccp/feat.h index b44c4550..cee553d 100644 --- a/net/dccp/feat.h +++ b/net/dccp/feat.h @@ -27,5 +27,10 @@ extern int dccp_feat_clone(struct sock *oldsk, struct sock *newsk); extern int dccp_feat_init(struct dccp_minisock *dmsk); extern int dccp_feat_default_sequence_window; +extern int dccp_feat_default_rx_ccid; +extern int dccp_feat_default_tx_ccid; +extern int dccp_feat_default_ack_ratio; +extern int dccp_feat_default_send_ack_vector; +extern int dccp_feat_default_send_ndp_count; #endif /* _DCCP_FEAT_H */ diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 7f56f7e..9a1a76a 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -501,6 +501,9 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) dccp_openreq_init(req, &dp, skb); + if (security_inet_conn_request(sk, skb, req)) + goto drop_and_free; + ireq = inet_rsk(req); ireq->loc_addr = daddr; ireq->rmt_addr = saddr; @@ -605,10 +608,10 @@ static struct sock *dccp_v4_hnd_req(struct sock *sk, struct sk_buff *skb) if (req != NULL) return dccp_check_req(sk, skb, req, prev); - nsk = __inet_lookup_established(&dccp_hashinfo, - iph->saddr, dh->dccph_sport, - iph->daddr, ntohs(dh->dccph_dport), - inet_iif(skb)); + nsk = inet_lookup_established(&dccp_hashinfo, + iph->saddr, dh->dccph_sport, + iph->daddr, dh->dccph_dport, + inet_iif(skb)); if (nsk != NULL) { if (nsk->sk_state != DCCP_TIME_WAIT) { bh_lock_sock(nsk); @@ -678,6 +681,7 @@ static struct dst_entry* dccp_v4_route_skb(struct sock *sk, } }; + security_skb_classify_flow(skb, &fl); if (ip_route_output_flow(&rt, &fl, sk, 0)) { IP_INC_STATS_BH(IPSTATS_MIB_OUTNOROUTES); return NULL; @@ -921,7 +925,7 @@ static int dccp_v4_rcv(struct sk_buff *skb) * Look up flow ID in table and get corresponding socket */ sk = __inet_lookup(&dccp_hashinfo, skb->nh.iph->saddr, dh->dccph_sport, - skb->nh.iph->daddr, ntohs(dh->dccph_dport), + skb->nh.iph->daddr, dh->dccph_dport, inet_iif(skb)); /* diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 610c722..7a47399 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -201,6 +201,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, fl.oif = sk->sk_bound_dev_if; fl.fl_ip_dport = usin->sin6_port; fl.fl_ip_sport = inet->sport; + security_sk_classify_flow(sk, &fl); if (np->opt != NULL && np->opt->srcrt != NULL) { const struct rt0_hdr *rt0 = (struct rt0_hdr *)np->opt->srcrt; @@ -230,7 +231,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, ipv6_addr_copy(&np->saddr, saddr); inet->rcv_saddr = LOOPBACK4_IPV6; - __ip6_dst_store(sk, dst, NULL); + __ip6_dst_store(sk, dst, NULL, NULL); icsk->icsk_ext_hdr_len = 0; if (np->opt != NULL) @@ -322,6 +323,7 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, fl.oif = sk->sk_bound_dev_if; fl.fl_ip_dport = inet->dport; fl.fl_ip_sport = inet->sport; + security_sk_classify_flow(sk, &fl); err = ip6_dst_lookup(sk, &dst, &fl); if (err) { @@ -422,6 +424,7 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req, fl.oif = ireq6->iif; fl.fl_ip_dport = inet_rsk(req)->rmt_port; fl.fl_ip_sport = inet_sk(sk)->sport; + security_req_classify_flow(req, &fl); if (dst == NULL) { opt = np->opt; @@ -566,6 +569,7 @@ static void dccp_v6_ctl_send_reset(struct sk_buff *rxskb) fl.oif = inet6_iif(rxskb); fl.fl_ip_dport = dh->dccph_dport; fl.fl_ip_sport = dh->dccph_sport; + security_skb_classify_flow(rxskb, &fl); /* sk = NULL, but it is safe for now. RST socket required. */ if (!ip6_dst_lookup(NULL, &skb->dst, &fl)) { @@ -622,6 +626,7 @@ static void dccp_v6_reqsk_send_ack(struct sk_buff *rxskb, fl.oif = inet6_iif(rxskb); fl.fl_ip_dport = dh->dccph_dport; fl.fl_ip_sport = dh->dccph_sport; + security_req_classify_flow(req, &fl); if (!ip6_dst_lookup(NULL, &skb->dst, &fl)) { if (xfrm_lookup(&skb->dst, &fl, NULL, 0) >= 0) { @@ -704,6 +709,9 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) dccp_openreq_init(req, &dp, skb); + if (security_inet_conn_request(sk, skb, req)) + goto drop_and_free; + ireq6 = inet6_rsk(req); ireq = inet_rsk(req); ipv6_addr_copy(&ireq6->rmt_addr, &skb->nh.ipv6h->saddr); @@ -842,6 +850,7 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, fl.oif = sk->sk_bound_dev_if; fl.fl_ip_dport = inet_rsk(req)->rmt_port; fl.fl_ip_sport = inet_sk(sk)->sport; + security_sk_classify_flow(sk, &fl); if (ip6_dst_lookup(sk, &dst, &fl)) goto out; @@ -863,7 +872,7 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, * comment in that function for the gory details. -acme */ - __ip6_dst_store(newsk, dst, NULL); + __ip6_dst_store(newsk, dst, NULL, NULL); newsk->sk_route_caps = dst->dev->features & ~(NETIF_F_IP_CSUM | NETIF_F_TSO); newdp6 = (struct dccp6_sock *)newsk; @@ -961,7 +970,7 @@ static int dccp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) if (skb->protocol == htons(ETH_P_IP)) return dccp_v4_do_rcv(sk, skb); - if (sk_filter(sk, skb, 0)) + if (sk_filter(sk, skb)) goto discard; /* diff --git a/net/dccp/output.c b/net/dccp/output.c index 58669be..7102e3a 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -198,7 +198,7 @@ static int dccp_wait_for_ccid(struct sock *sk, struct sk_buff *skb, while (1) { prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); - if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) + if (sk->sk_err) goto do_error; if (!*timeo) goto do_nonblock; @@ -234,37 +234,72 @@ do_interrupted: goto out; } -int dccp_write_xmit(struct sock *sk, struct sk_buff *skb, long *timeo) +static void dccp_write_xmit_timer(unsigned long data) { + struct sock *sk = (struct sock *)data; + struct dccp_sock *dp = dccp_sk(sk); + + bh_lock_sock(sk); + if (sock_owned_by_user(sk)) + sk_reset_timer(sk, &dp->dccps_xmit_timer, jiffies+1); + else + dccp_write_xmit(sk, 0); + bh_unlock_sock(sk); + sock_put(sk); +} + +void dccp_write_xmit(struct sock *sk, int block) { - const struct dccp_sock *dp = dccp_sk(sk); - int err = ccid_hc_tx_send_packet(dp->dccps_hc_tx_ccid, sk, skb, + struct dccp_sock *dp = dccp_sk(sk); + struct sk_buff *skb; + long timeo = 30000; /* If a packet is taking longer than 2 secs + we have other issues */ + + while ((skb = skb_peek(&sk->sk_write_queue))) { + int err = ccid_hc_tx_send_packet(dp->dccps_hc_tx_ccid, sk, skb, skb->len); - if (err > 0) - err = dccp_wait_for_ccid(sk, skb, timeo); + if (err > 0) { + if (!block) { + sk_reset_timer(sk, &dp->dccps_xmit_timer, + msecs_to_jiffies(err)+jiffies); + break; + } else + err = dccp_wait_for_ccid(sk, skb, &timeo); + if (err) { + printk(KERN_CRIT "%s:err at dccp_wait_for_ccid" + " %d\n", __FUNCTION__, err); + dump_stack(); + } + } - if (err == 0) { - struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb); - const int len = skb->len; + skb_dequeue(&sk->sk_write_queue); + if (err == 0) { + struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb); + const int len = skb->len; - if (sk->sk_state == DCCP_PARTOPEN) { - /* See 8.1.5. Handshake Completion */ - inet_csk_schedule_ack(sk); - inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK, + if (sk->sk_state == DCCP_PARTOPEN) { + /* See 8.1.5. Handshake Completion */ + inet_csk_schedule_ack(sk); + inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK, inet_csk(sk)->icsk_rto, DCCP_RTO_MAX); - dcb->dccpd_type = DCCP_PKT_DATAACK; - } else if (dccp_ack_pending(sk)) - dcb->dccpd_type = DCCP_PKT_DATAACK; - else - dcb->dccpd_type = DCCP_PKT_DATA; - - err = dccp_transmit_skb(sk, skb); - ccid_hc_tx_packet_sent(dp->dccps_hc_tx_ccid, sk, 0, len); - } else - kfree_skb(skb); - - return err; + dcb->dccpd_type = DCCP_PKT_DATAACK; + } else if (dccp_ack_pending(sk)) + dcb->dccpd_type = DCCP_PKT_DATAACK; + else + dcb->dccpd_type = DCCP_PKT_DATA; + + err = dccp_transmit_skb(sk, skb); + ccid_hc_tx_packet_sent(dp->dccps_hc_tx_ccid, sk, 0, len); + if (err) { + printk(KERN_CRIT "%s:err from " + "ccid_hc_tx_packet_sent %d\n", + __FUNCTION__, err); + dump_stack(); + } + } else + kfree(skb); + } } int dccp_retransmit_skb(struct sock *sk, struct sk_buff *skb) @@ -426,6 +461,9 @@ static inline void dccp_connect_init(struct sock *sk) dccp_set_seqno(&dp->dccps_awl, max48(dp->dccps_awl, dp->dccps_iss)); icsk->icsk_retransmits = 0; + init_timer(&dp->dccps_xmit_timer); + dp->dccps_xmit_timer.data = (unsigned long)sk; + dp->dccps_xmit_timer.function = dccp_write_xmit_timer; } int dccp_connect(struct sock *sk) @@ -560,8 +598,10 @@ void dccp_send_close(struct sock *sk, const int active) DCCP_PKT_CLOSE : DCCP_PKT_CLOSEREQ; if (active) { + dccp_write_xmit(sk, 1); dccp_skb_entail(sk, skb); dccp_transmit_skb(sk, skb_clone(skb, prio)); + /* FIXME do we need a retransmit timer here? */ } else dccp_transmit_skb(sk, skb); } diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 6f14bb5..962df0e 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -662,17 +662,8 @@ int dccp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if (rc != 0) goto out_discard; - rc = dccp_write_xmit(sk, skb, &timeo); - /* - * XXX we don't use sk_write_queue, so just discard the packet. - * Current plan however is to _use_ sk_write_queue with - * an algorith similar to tcp_sendmsg, where the main difference - * is that in DCCP we have to respect packet boundaries, so - * no coalescing of skbs. - * - * This bug was _quickly_ found & fixed by just looking at an OSTRA - * generated callgraph 8) -acme - */ + skb_queue_tail(&sk->sk_write_queue, skb); + dccp_write_xmit(sk,0); out_release: release_sock(sk); return rc ? : len; @@ -846,6 +837,7 @@ static int dccp_close_state(struct sock *sk) void dccp_close(struct sock *sk, long timeout) { + struct dccp_sock *dp = dccp_sk(sk); struct sk_buff *skb; int state; @@ -862,6 +854,8 @@ void dccp_close(struct sock *sk, long timeout) goto adjudge_to_death; } + sk_stop_timer(sk, &dp->dccps_xmit_timer); + /* * We need to flush the recv. buffs. We do this only on the * descriptor close, not protocol-sourced closes, because the diff --git a/net/dccp/sysctl.c b/net/dccp/sysctl.c index c1ba945..38bc157 100644 --- a/net/dccp/sysctl.c +++ b/net/dccp/sysctl.c @@ -11,18 +11,12 @@ #include <linux/mm.h> #include <linux/sysctl.h> +#include "feat.h" #ifndef CONFIG_SYSCTL #error This file should not be compiled without CONFIG_SYSCTL defined #endif -extern int dccp_feat_default_sequence_window; -extern int dccp_feat_default_rx_ccid; -extern int dccp_feat_default_tx_ccid; -extern int dccp_feat_default_ack_ratio; -extern int dccp_feat_default_send_ack_vector; -extern int dccp_feat_default_send_ndp_count; - static struct ctl_table dccp_default_table[] = { { .ctl_name = NET_DCCP_DEFAULT_SEQ_WINDOW, |