From ba1a6c7bc0ff33e405f5156dc8f4145437255f1f Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Sat, 23 Aug 2008 13:28:27 +0200 Subject: dccp: Always generate a Reset in response to option errors RFC4340 states that if a packet is received with an option error (such as a Mandatory Option as the last byte of the option list), the endpoint should repond with a Reset. In the LISTEN and RESPOND states, the endpoint correctly reponds with Reset, while in the REQUEST/OPEN states, packets with option errors are just ignored. The packet sequence is as follows: Case 1: Endpoint A Endpoint B (CLOSED) (CLOSED) <---------------- REQUEST RESPONSE -----------------> (*1) (with invalid option) <---------------- RESET (with Reset Code 5, "Option Error") (*1) currently just ignored, no Reset is sent Case 2: Endpoint A Endpoint B (OPEN) (OPEN) DATA-ACK -----------------> (*2) (with invalid option) <---------------- RESET (with Reset Code 5, "Option Error") (*2) currently just ignored, no Reset is sent This patch fixes the problem, by generating a Reset instead of silently ignoring option errors. Signed-off-by: Wei Yongjun Acked-by: Arnaldo Carvalho de Melo Acked-by: Gerrit Renker --- net/dccp/input.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/dccp/input.c') diff --git a/net/dccp/input.c b/net/dccp/input.c index 803933ab396d..779d0ed9ae94 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -370,7 +370,7 @@ int dccp_rcv_established(struct sock *sk, struct sk_buff *skb, goto discard; if (dccp_parse_options(sk, NULL, skb)) - goto discard; + return 1; if (DCCP_SKB_CB(skb)->dccpd_ack_seq != DCCP_PKT_WITHOUT_ACK_SEQ) dccp_event_ack_recv(sk, skb); @@ -610,7 +610,7 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, * Step 8: Process options and mark acknowledgeable */ if (dccp_parse_options(sk, NULL, skb)) - goto discard; + return 1; if (dcb->dccpd_ack_seq != DCCP_PKT_WITHOUT_ACK_SEQ) dccp_event_ack_recv(sk, skb); -- cgit v1.2.3 From 828755cee087e4a34f45d6c9db661ccd0631cc6d Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Thu, 4 Sep 2008 07:30:19 +0200 Subject: dccp: Per-socket initialisation of feature negotiation This provides feature-negotiation initialisation for both DCCP sockets and DCCP request_sockets, to support feature negotiation during connection setup. It also resolves a FIXME regarding the congestion control initialisation. Thanks to Wei Yongjun for help with the IPv6 side of this patch. Signed-off-by: Gerrit Renker Acked-by: Ian McDonald --- include/linux/dccp.h | 4 ++++ net/dccp/dccp.h | 3 ++- net/dccp/feat.c | 19 +++++++++++++++++++ net/dccp/feat.h | 1 + net/dccp/input.c | 2 -- net/dccp/ipv4.c | 3 ++- net/dccp/ipv6.c | 3 ++- net/dccp/minisocks.c | 7 ++++++- net/dccp/proto.c | 1 + 9 files changed, 37 insertions(+), 6 deletions(-) (limited to 'net/dccp/input.c') diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 3978aff197d9..484b8a1fb023 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -412,6 +412,7 @@ extern void dccp_minisock_init(struct dccp_minisock *dmsk); * @dreq_iss: initial sequence number sent on the Response (RFC 4340, 7.1) * @dreq_isr: initial sequence number received on the Request * @dreq_service: service code present on the Request (there is just one) + * @dreq_featneg: feature negotiation options for this connection * The following two fields are analogous to the ones in dccp_sock: * @dreq_timestamp_echo: last received timestamp to echo (13.1) * @dreq_timestamp_echo: the time of receiving the last @dreq_timestamp_echo @@ -421,6 +422,7 @@ struct dccp_request_sock { __u64 dreq_iss; __u64 dreq_isr; __be32 dreq_service; + struct list_head dreq_featneg; __u32 dreq_timestamp_echo; __u32 dreq_timestamp_time; }; @@ -498,6 +500,7 @@ struct dccp_ackvec; * @dccps_mss_cache - current value of MSS (path MTU minus header sizes) * @dccps_rate_last - timestamp for rate-limiting DCCP-Sync (RFC 4340, 7.5.4) * @dccps_minisock - associated minisock (accessed via dccp_msk) + * @dccps_featneg - tracks feature-negotiation state (mostly during handshake) * @dccps_hc_rx_ackvec - rx half connection ack vector * @dccps_hc_rx_ccid - CCID used for the receiver (or receiving half-connection) * @dccps_hc_tx_ccid - CCID used for the sender (or sending half-connection) @@ -535,6 +538,7 @@ struct dccp_sock { __u64 dccps_ndp_count:48; unsigned long dccps_rate_last; struct dccp_minisock dccps_minisock; + struct list_head dccps_featneg; struct dccp_ackvec *dccps_hc_rx_ackvec; struct ccid *dccps_hc_rx_ccid; struct ccid *dccps_hc_tx_ccid; diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index b4bc6e095a0e..ab096c06bba0 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -252,7 +252,8 @@ extern const char *dccp_state_name(const int state); extern void dccp_set_state(struct sock *sk, const int state); extern void dccp_done(struct sock *sk); -extern void dccp_reqsk_init(struct request_sock *req, struct sk_buff *skb); +extern int dccp_reqsk_init(struct request_sock *rq, struct dccp_sock const *dp, + struct sk_buff const *skb); extern int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb); diff --git a/net/dccp/feat.c b/net/dccp/feat.c index 2ec2cd117699..faade82856fe 100644 --- a/net/dccp/feat.c +++ b/net/dccp/feat.c @@ -279,6 +279,25 @@ void dccp_feat_list_purge(struct list_head *fn_list) } EXPORT_SYMBOL_GPL(dccp_feat_list_purge); +/* generate @to as full clone of @from - @to must not contain any nodes */ +int dccp_feat_clone_list(struct list_head const *from, struct list_head *to) +{ + struct dccp_feat_entry *entry, *new; + + INIT_LIST_HEAD(to); + list_for_each_entry(entry, from, node) { + new = dccp_feat_clone_entry(entry); + if (new == NULL) + goto cloning_failed; + list_add_tail(&new->node, to); + } + return 0; + +cloning_failed: + dccp_feat_list_purge(to); + return -ENOMEM; +} + int dccp_feat_change(struct dccp_minisock *dmsk, u8 type, u8 feature, u8 *val, u8 len, gfp_t gfp) { diff --git a/net/dccp/feat.h b/net/dccp/feat.h index 94203c230c65..7e953fd0a79b 100644 --- a/net/dccp/feat.h +++ b/net/dccp/feat.h @@ -95,6 +95,7 @@ extern int dccp_feat_confirm_recv(struct sock *sk, u8 type, u8 feature, u8 *val, u8 len); extern void dccp_feat_clean(struct dccp_minisock *dmsk); extern int dccp_feat_clone(struct sock *oldsk, struct sock *newsk); +extern int dccp_feat_clone_list(struct list_head const *, struct list_head *); extern int dccp_feat_init(struct dccp_minisock *dmsk); #endif /* _DCCP_FEAT_H */ diff --git a/net/dccp/input.c b/net/dccp/input.c index 779d0ed9ae94..3070015edc75 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -590,8 +590,6 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, if (inet_csk(sk)->icsk_af_ops->conn_request(sk, skb) < 0) return 1; - - /* FIXME: do congestion control initialization */ goto discard; } if (dh->dccph_type == DCCP_PKT_RESET) diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 882c5c4de69e..0ce84ea89119 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -595,7 +595,8 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) if (req == NULL) goto drop; - dccp_reqsk_init(req, skb); + if (dccp_reqsk_init(req, dccp_sk(sk), skb)) + goto drop_and_free; dreq = dccp_rsk(req); if (dccp_parse_options(sk, dreq, skb)) diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 5e1ee0da2c40..33e8a1ea3041 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -424,7 +424,8 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) if (req == NULL) goto drop; - dccp_reqsk_init(req, skb); + if (dccp_reqsk_init(req, dccp_sk(sk), skb)) + goto drop_and_free; dreq = dccp_rsk(req); if (dccp_parse_options(sk, dreq, skb)) diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index b2804e2d1b8c..e487133ae079 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -125,6 +125,7 @@ struct sock *dccp_create_openreq_child(struct sock *sk, newdp->dccps_timestamp_time = dreq->dreq_timestamp_time; newicsk->icsk_rto = DCCP_TIMEOUT_INIT; + INIT_LIST_HEAD(&newdp->dccps_featneg); if (dccp_feat_clone(sk, newsk)) goto out_free; @@ -304,7 +305,8 @@ void dccp_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, EXPORT_SYMBOL_GPL(dccp_reqsk_send_ack); -void dccp_reqsk_init(struct request_sock *req, struct sk_buff *skb) +int dccp_reqsk_init(struct request_sock *req, + struct dccp_sock const *dp, struct sk_buff const *skb) { struct dccp_request_sock *dreq = dccp_rsk(req); @@ -312,6 +314,9 @@ void dccp_reqsk_init(struct request_sock *req, struct sk_buff *skb) inet_rsk(req)->acked = 0; req->rcv_wnd = sysctl_dccp_feat_sequence_window; dreq->dreq_timestamp_echo = 0; + + /* inherit feature negotiation options from listening socket */ + return dccp_feat_clone_list(&dp->dccps_featneg, &dreq->dreq_featneg); } EXPORT_SYMBOL_GPL(dccp_reqsk_init); diff --git a/net/dccp/proto.c b/net/dccp/proto.c index d0bd34819761..1cdf4ae99605 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -193,6 +193,7 @@ int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized) dccp_init_xmit_timers(sk); + INIT_LIST_HEAD(&dp->dccps_featneg); /* * FIXME: We're hardcoding the CCID, and doing this at this point makes * the listening (master) sock get CCID control blocks, which is not -- cgit v1.2.3 From c49b22729f3da7479c4e6c572d53fdd40201d0bd Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Thu, 4 Sep 2008 07:30:19 +0200 Subject: dccp: Integration of dynamic feature activation - part 3 (client side) This integrates feature-activation in the client, with these details: 1. When dccp_parse_options() fails, the reset code is already set, request_sent _state_process() currently overrides this with `Packet Error', which is not intended - so changed to use the reset code set in dccp_parse_options(); 2. There was a FIXME to change the error code when dccp_ackvec_add() fails. I have looked this up and found that: * the check whether ackno < ISN is already made earlier, * this Response is likely the 1st packet with an Ackno that the client gets, * so when dccp_ackvec_add() fails, the reason is likely not a packet error. 3. When feature negotiation fails, the socket should be marked as not usable, so that the application is notified that an error occurs. This is achieved by a new label, which uses an error code of `Aborted' and which sets the socket state to CLOSED, as well as sk_err. 4. Avoids parsing the Ack twice in Respond state by not doing option processing again in dccp_rcv_respond_partopen_state_process (as option processing has already been done on the request_sock in dccp_check_req). Since this addresses congestion-control initialisation, a corresponding FIXME has been removed. Signed-off-by: Gerrit Renker Acked-by: Ian McDonald --- net/dccp/input.c | 30 ++++++++++++++++++++++++++---- 1 file changed, 26 insertions(+), 4 deletions(-) (limited to 'net/dccp/input.c') diff --git a/net/dccp/input.c b/net/dccp/input.c index 3070015edc75..0672b7e1763e 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -421,8 +421,13 @@ static int dccp_rcv_request_sent_state_process(struct sock *sk, goto out_invalid_packet; } + /* + * If option processing (Step 8) failed, return 1 here so that + * dccp_v4_do_rcv() sends a Reset. The Reset code depends on + * the option type and is set in dccp_parse_options(). + */ if (dccp_parse_options(sk, NULL, skb)) - goto out_invalid_packet; + return 1; /* Obtain usec RTT sample from SYN exchange (used by CCID 3) */ if (likely(dp->dccps_options_received.dccpor_timestamp_echo)) @@ -475,6 +480,15 @@ static int dccp_rcv_request_sent_state_process(struct sock *sk, */ dccp_set_state(sk, DCCP_PARTOPEN); + /* + * If feature negotiation was successful, activate features now; + * an activation failure means that this host could not activate + * one ore more features (e.g. insufficient memory), which would + * leave at least one feature in an undefined state. + */ + if (dccp_feat_activate_values(sk, &dp->dccps_featneg)) + goto unable_to_proceed; + /* Make sure socket is routed, for correct metrics. */ icsk->icsk_af_ops->rebuild_header(sk); @@ -509,6 +523,16 @@ out_invalid_packet: /* dccp_v4_do_rcv will send a reset */ DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_PACKET_ERROR; return 1; + +unable_to_proceed: + DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_ABORTED; + /* + * We mark this socket as no longer usable, so that the loop in + * dccp_sendmsg() terminates and the application gets notified. + */ + dccp_set_state(sk, DCCP_CLOSED); + sk->sk_err = ECOMM; + return 1; } static int dccp_rcv_respond_partopen_state_process(struct sock *sk, @@ -600,7 +624,7 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, return 1; } - if (sk->sk_state != DCCP_REQUESTING) { + if (sk->sk_state != DCCP_REQUESTING && sk->sk_state != DCCP_RESPOND) { if (dccp_check_seqno(sk, skb)) goto discard; @@ -665,8 +689,6 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, return 1; case DCCP_REQUESTING: - /* FIXME: do congestion control initialization */ - queued = dccp_rcv_request_sent_state_process(sk, skb, dh, len); if (queued >= 0) return queued; -- cgit v1.2.3 From b235dc4abbc1356284bd0dc730efa711f394e0e2 Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Thu, 4 Sep 2008 07:30:19 +0200 Subject: dccp ccid-2: Phase out the use of boolean Ack Vector sysctl This removes the use of the sysctl and the minisock variable for the Send Ack Vector feature, which is now handled fully dynamically via feature negotiation; i.e. when CCID2 is enabled, Ack Vectors are automatically enabled (as per RFC 4341, 4.). Using a sysctl in parallel to this implementation would open the door to crashes, since much of the code relies on tests of the boolean minisock / sysctl variable. Thus, this patch replaces all tests of type if (dccp_msk(sk)->dccpms_send_ack_vector) /* ... */ with if (dp->dccps_hc_rx_ackvec != NULL) /* ... */ The dccps_hc_rx_ackvec is allocated by the dccp_hdlr_ackvec() when feature negotiation concluded that Ack Vectors are to be used on the half-connection. Otherwise, it is NULL (due to dccp_init_sock/dccp_create_openreq_child), so that the test is a valid one. The activation handler for Ack Vectors is called as soon as the feature negotiation has concluded at the * server when the Ack marking the transition RESPOND => OPEN arrives; * client after it has sent its ACK, marking the transition REQUEST => PARTOPEN. Adding the sequence number of the Response packet to the Ack Vector has been removed, since (a) connection establishment implies that the Response has been received; (b) the CCIDs only look at packets received in the (PART)OPEN state, i.e. this entry will always be ignored; (c) it can not be used for anything useful - to detect loss for instance, only packets received after the loss can serve as pseudo-dupacks. Signed-off-by: Gerrit Renker Acked-by: Ian McDonald --- Documentation/networking/dccp.txt | 3 --- include/linux/dccp.h | 3 --- net/dccp/dccp.h | 3 +-- net/dccp/diag.c | 2 +- net/dccp/input.c | 12 +++--------- net/dccp/minisocks.c | 1 - net/dccp/options.c | 7 ++----- net/dccp/proto.c | 3 +-- net/dccp/sysctl.c | 7 ------- 9 files changed, 8 insertions(+), 33 deletions(-) (limited to 'net/dccp/input.c') diff --git a/Documentation/networking/dccp.txt b/Documentation/networking/dccp.txt index 1403745ab406..7a3bb1abb830 100644 --- a/Documentation/networking/dccp.txt +++ b/Documentation/networking/dccp.txt @@ -133,9 +133,6 @@ retries2 importance for retransmitted acknowledgments and feature negotiation, data packets are never retransmitted. Analogue of tcp_retries2. -send_ackvec = 1 - Whether or not to send Ack Vector options (sec. 11.5). - tx_ccid = 2 Default CCID for the sender-receiver half-connection. Depending on the choice of CCID, the Send Ack Vector feature is enabled automatically. diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 60e94438eadd..61734e27abb7 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -360,7 +360,6 @@ static inline unsigned int dccp_hdr_len(const struct sk_buff *skb) #define DCCPF_INITIAL_SEQUENCE_WINDOW 100 #define DCCPF_INITIAL_ACK_RATIO 2 #define DCCPF_INITIAL_CCID DCCPC_CCID2 -#define DCCPF_INITIAL_SEND_ACK_VECTOR 1 /* FIXME: for now we're default to 1 but it should really be 0 */ #define DCCPF_INITIAL_SEND_NDP_COUNT 1 @@ -370,13 +369,11 @@ static inline unsigned int dccp_hdr_len(const struct sk_buff *skb) * Will be used to pass the state from dccp_request_sock to dccp_sock. * * @dccpms_sequence_window - Sequence Window Feature (section 7.5.2) - * @dccpms_send_ack_vector - Send Ack Vector Feature (section 11.5) * @dccpms_pending - List of features being negotiated * @dccpms_conf - */ struct dccp_minisock { __u64 dccpms_sequence_window; - __u8 dccpms_send_ack_vector; struct list_head dccpms_pending; struct list_head dccpms_conf; }; diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index 51436c825655..3fd16e82c003 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -98,7 +98,6 @@ extern int sysctl_dccp_retries2; extern int sysctl_dccp_feat_sequence_window; extern int sysctl_dccp_feat_rx_ccid; extern int sysctl_dccp_feat_tx_ccid; -extern int sysctl_dccp_feat_send_ack_vector; extern int sysctl_dccp_tx_qlen; extern int sysctl_dccp_sync_ratelimit; @@ -434,7 +433,7 @@ static inline int dccp_ack_pending(const struct sock *sk) const struct dccp_sock *dp = dccp_sk(sk); return dp->dccps_timestamp_echo != 0 || #ifdef CONFIG_IP_DCCP_ACKVEC - (dccp_msk(sk)->dccpms_send_ack_vector && + (dp->dccps_hc_rx_ackvec != NULL && dccp_ackvec_pending(dp->dccps_hc_rx_ackvec)) || #endif inet_csk_ack_scheduled(sk); diff --git a/net/dccp/diag.c b/net/dccp/diag.c index d8a3509b26f6..93aae7c95550 100644 --- a/net/dccp/diag.c +++ b/net/dccp/diag.c @@ -29,7 +29,7 @@ static void dccp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_backoff = icsk->icsk_backoff; info->tcpi_pmtu = icsk->icsk_pmtu_cookie; - if (dccp_msk(sk)->dccpms_send_ack_vector) + if (dp->dccps_hc_rx_ackvec != NULL) info->tcpi_options |= TCPI_OPT_SACK; ccid_hc_rx_get_info(dp->dccps_hc_rx_ccid, sk, info); diff --git a/net/dccp/input.c b/net/dccp/input.c index 0672b7e1763e..5eb443f656c1 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -163,7 +163,7 @@ static void dccp_event_ack_recv(struct sock *sk, struct sk_buff *skb) { struct dccp_sock *dp = dccp_sk(sk); - if (dccp_msk(sk)->dccpms_send_ack_vector) + if (dp->dccps_hc_rx_ackvec != NULL) dccp_ackvec_check_rcv_ackno(dp->dccps_hc_rx_ackvec, sk, DCCP_SKB_CB(skb)->dccpd_ack_seq); } @@ -375,7 +375,7 @@ int dccp_rcv_established(struct sock *sk, struct sk_buff *skb, if (DCCP_SKB_CB(skb)->dccpd_ack_seq != DCCP_PKT_WITHOUT_ACK_SEQ) dccp_event_ack_recv(sk, skb); - if (dccp_msk(sk)->dccpms_send_ack_vector && + if (dp->dccps_hc_rx_ackvec != NULL && dccp_ackvec_add(dp->dccps_hc_rx_ackvec, sk, DCCP_SKB_CB(skb)->dccpd_seq, DCCP_ACKVEC_STATE_RECEIVED)) @@ -434,12 +434,6 @@ static int dccp_rcv_request_sent_state_process(struct sock *sk, dp->dccps_syn_rtt = dccp_sample_rtt(sk, 10 * (tstamp - dp->dccps_options_received.dccpor_timestamp_echo)); - if (dccp_msk(sk)->dccpms_send_ack_vector && - dccp_ackvec_add(dp->dccps_hc_rx_ackvec, sk, - DCCP_SKB_CB(skb)->dccpd_seq, - DCCP_ACKVEC_STATE_RECEIVED)) - goto out_invalid_packet; /* FIXME: change error code */ - /* Stop the REQUEST timer */ inet_csk_clear_xmit_timer(sk, ICSK_TIME_RETRANS); WARN_ON(sk->sk_send_head == NULL); @@ -637,7 +631,7 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, if (dcb->dccpd_ack_seq != DCCP_PKT_WITHOUT_ACK_SEQ) dccp_event_ack_recv(sk, skb); - if (dccp_msk(sk)->dccpms_send_ack_vector && + if (dp->dccps_hc_rx_ackvec != NULL && dccp_ackvec_add(dp->dccps_hc_rx_ackvec, sk, DCCP_SKB_CB(skb)->dccpd_seq, DCCP_ACKVEC_STATE_RECEIVED)) diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index 9e2232572662..0ebf8ebcf3de 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -45,7 +45,6 @@ EXPORT_SYMBOL_GPL(dccp_death_row); void dccp_minisock_init(struct dccp_minisock *dmsk) { dmsk->dccpms_sequence_window = sysctl_dccp_feat_sequence_window; - dmsk->dccpms_send_ack_vector = sysctl_dccp_feat_send_ack_vector; } void dccp_time_wait(struct sock *sk, int state, int timeo) diff --git a/net/dccp/options.c b/net/dccp/options.c index 6b0704497e83..aca309e16632 100644 --- a/net/dccp/options.c +++ b/net/dccp/options.c @@ -26,7 +26,6 @@ int sysctl_dccp_feat_sequence_window = DCCPF_INITIAL_SEQUENCE_WINDOW; int sysctl_dccp_feat_rx_ccid = DCCPF_INITIAL_CCID; int sysctl_dccp_feat_tx_ccid = DCCPF_INITIAL_CCID; -int sysctl_dccp_feat_send_ack_vector = DCCPF_INITIAL_SEND_ACK_VECTOR; u64 dccp_decode_value_var(const u8 *bf, const u8 len) { @@ -145,8 +144,7 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq, case DCCPO_ACK_VECTOR_1: if (dccp_packet_without_ack(skb)) /* RFC 4340, 11.4 */ break; - - if (dccp_msk(sk)->dccpms_send_ack_vector && + if (dp->dccps_hc_rx_ackvec != NULL && dccp_ackvec_parse(sk, skb, &ackno, opt, value, len)) goto out_invalid_option; break; @@ -526,7 +524,6 @@ static void dccp_insert_option_padding(struct sk_buff *skb) int dccp_insert_options(struct sock *sk, struct sk_buff *skb) { struct dccp_sock *dp = dccp_sk(sk); - struct dccp_minisock *dmsk = dccp_msk(sk); DCCP_SKB_CB(skb)->dccpd_opt_len = 0; @@ -547,7 +544,7 @@ int dccp_insert_options(struct sock *sk, struct sk_buff *skb) if (dccp_insert_option_timestamp(sk, skb)) return -1; - } else if (dmsk->dccpms_send_ack_vector && + } else if (dp->dccps_hc_rx_ackvec != NULL && dccp_ackvec_pending(dp->dccps_hc_rx_ackvec) && dccp_insert_option_ackvec(sk, skb)) { return -1; diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 0d420790b795..775eaa3d0c49 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -207,7 +207,6 @@ EXPORT_SYMBOL_GPL(dccp_init_sock); void dccp_destroy_sock(struct sock *sk) { struct dccp_sock *dp = dccp_sk(sk); - struct dccp_minisock *dmsk = dccp_msk(sk); /* * DCCP doesn't use sk_write_queue, just sk_send_head @@ -225,7 +224,7 @@ void dccp_destroy_sock(struct sock *sk) kfree(dp->dccps_service_list); dp->dccps_service_list = NULL; - if (dmsk->dccpms_send_ack_vector) { + if (dp->dccps_hc_rx_ackvec != NULL) { dccp_ackvec_free(dp->dccps_hc_rx_ackvec); dp->dccps_hc_rx_ackvec = NULL; } diff --git a/net/dccp/sysctl.c b/net/dccp/sysctl.c index 587c12f915c1..018e210875e1 100644 --- a/net/dccp/sysctl.c +++ b/net/dccp/sysctl.c @@ -40,13 +40,6 @@ static struct ctl_table dccp_default_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, - { - .procname = "send_ackvec", - .data = &sysctl_dccp_feat_send_ack_vector, - .maxlen = sizeof(sysctl_dccp_feat_send_ack_vector), - .mode = 0644, - .proc_handler = proc_dointvec, - }, { .procname = "request_retries", .data = &sysctl_dccp_request_retries, -- cgit v1.2.3 From bfbddd085a5bced6efb9e1bc4d029438f9639784 Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Thu, 4 Sep 2008 07:30:19 +0200 Subject: dccp: Fix the adjustments to AWL and SWL This fixes a problem and a potential loophole with regard to seqno/ackno validity: the problem is that the initial adjustments to AWL/SWL were only performed at the begin of the connection, during the handshake. Since the Sequence Window feature is always greater than Wmin=32 (7.5.2), it is however necessary to perform these adjustments at least for the first W/W' (variables as per 7.5.1) packets in the lifetime of a connection. This requirement is complicated by the fact that W/W' can change at any time during the lifetime of a connection. Therefore the consequence is to perform this safety check each time SWL/AWL are updated. A second problem solved by this patch is that the remote/local Sequence Window feature values (which set the bounds for AWL/SWL/SWH) are undefined until the feature negotiation has completed. During the initial handshake we have more stringent sequence number protection, the changes added by this patch effect that {A,S}W{L,H} are within the correct bounds at the instant that feature negotiation completes (since the SeqWin feature activation handlers call dccp_update_gsr/gss()). A detailed rationale is below -- can be removed from the commit message. 1. Server sequence number checks during initial handshake --------------------------------------------------------- The server can not use the fields of the listening socket for seqno/ackno checks and thus needs to store all relevant information on a per-connection basis on the dccp_request socket. This is a size-constrained structure and has currently only ISS (dreq_iss) and ISR (dreq_isr) defined. Adding further fields (SW{L,H}, AW{L,H}) would increase the size of the struct and it is questionable whether this will have any practical gain. The currently implemented solution is as follows. * receiving first Request: dccp_v{4,6}_conn_request sets ISR := P.seqno, ISS := dccp_v{4,6}_init_sequence() * sending first Response: dccp_v{4,6}_send_response via dccp_make_response() sets P.seqno := ISS, sets P.ackno := ISR * receiving retransmitted Request: dccp_check_req() overrides ISR := P.seqno * answering retransmitted Request: dccp_make_response() sets ISS += 1, otherwise as per first Response * completing the handshake: succeeds in dccp_check_req() for the first Ack where P.ackno == ISS (P.seqno is not tested) * creating child socket: ISS, ISR are copied from the request_sock This solution will succeed whenever the server can receive the Request and the subsequent Ack in succession, without retransmissions. If there is packet loss, the client needs to retransmit until this condition succeeds; it will otherwise eventually give up. Adding further fields to the request_sock could increase the robustness a bit, in that it would make possible to let a reordered Ack (from a retransmitted Response) pass. The argument against such a solution is that if the packet loss is not persistent and an Ack gets through, why not wait for the one answering the original response: if the loss is persistent, it is probably better to not start the connection in the first place. Long story short: the present design (by Arnaldo) is simple and will likely work just as well as a more complicated solution. As a consequence, {A,S}W{L,H} are not needed until the moment the request_sock is cloned into the accept queue. At that stage feature negotiation has completed, so that the values for the local and remote Sequence Window feature (7.5.2) are known, i.e. we are now in a better position to compute {A,S}W{L,H}. 2. Client sequence number checks during initial handshake --------------------------------------------------------- Until entering PARTOPEN the client does not need the adjustments, since it constrains the Ack window to the packet it sent. * sending first Request: dccp_v{4,6}_connect() choose ISS, dccp_connect() then sets GAR := ISS (as per 8.5), dccp_transmit_skb() (with the previous bug fix) sets GSS := ISS, AWL := ISS, AWH := GSS * n-th retransmitted Request (with previous patch): dccp_retransmit_skb() via timer calls dccp_transmit_skb(), which sets GSS := ISS+n and then AWL := ISS, AWH := ISS+n * receiving any Response: dccp_rcv_request_sent_state_process() -- accepts packet if AWL <= P.ackno <= AWH; -- sets GSR = ISR = P.seqno * sending the Ack completing the handshake: dccp_send_ack() calls dccp_transmit_skb(), which sets GSS += 1 and AWL := ISS, AWH := GSS Signed-off-by: Gerrit Renker --- net/dccp/dccp.h | 20 ++++++++++++++++++++ net/dccp/input.c | 18 ++++++------------ net/dccp/minisocks.c | 30 +++++++++--------------------- 3 files changed, 35 insertions(+), 33 deletions(-) (limited to 'net/dccp/input.c') diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index f9ed0cbd1bf3..e4d6e76ced41 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -415,6 +415,23 @@ static inline void dccp_update_gsr(struct sock *sk, u64 seq) dp->dccps_gsr = seq; /* Sequence validity window depends on remote Sequence Window (7.5.1) */ dp->dccps_swl = SUB48(ADD48(dp->dccps_gsr, 1), dp->dccps_r_seq_win / 4); + /* + * Adjust SWL so that it is not below ISR. In contrast to RFC 4340, + * 7.5.1 we perform this check beyond the initial handshake: W/W' are + * always > 32, so for the first W/W' packets in the lifetime of a + * connection we always have to adjust SWL. + * A second reason why we are doing this is that the window depends on + * the feature-remote value of Sequence Window: nothing stops the peer + * from updating this value while we are busy adjusting SWL for the + * first W packets (we would have to count from scratch again then). + * Therefore it is safer to always make sure that the Sequence Window + * is not artificially extended by a peer who grows SWL downwards by + * continually updating the feature-remote Sequence-Window. + * If sequence numbers wrap it is bad luck. But that will take a while + * (48 bit), and this measure prevents Sequence-number attacks. + */ + if (before48(dp->dccps_swl, dp->dccps_isr)) + dp->dccps_swl = dp->dccps_isr; dp->dccps_swh = ADD48(dp->dccps_gsr, (3 * dp->dccps_r_seq_win) / 4); } @@ -425,6 +442,9 @@ static inline void dccp_update_gss(struct sock *sk, u64 seq) dp->dccps_gss = seq; /* Ack validity window depends on local Sequence Window value (7.5.1) */ dp->dccps_awl = SUB48(ADD48(dp->dccps_gss, 1), dp->dccps_l_seq_win); + /* Adjust AWL so that it is not below ISS - see comment above for SWL */ + if (before48(dp->dccps_awl, dp->dccps_iss)) + dp->dccps_awl = dp->dccps_iss; dp->dccps_awh = dp->dccps_gss; } diff --git a/net/dccp/input.c b/net/dccp/input.c index 5eb443f656c1..e3f43d55e3ce 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -440,20 +440,14 @@ static int dccp_rcv_request_sent_state_process(struct sock *sk, kfree_skb(sk->sk_send_head); sk->sk_send_head = NULL; - dp->dccps_isr = DCCP_SKB_CB(skb)->dccpd_seq; - dccp_update_gsr(sk, dp->dccps_isr); /* - * SWL and AWL are initially adjusted so that they are not less than - * the initial Sequence Numbers received and sent, respectively: - * SWL := max(GSR + 1 - floor(W/4), ISR), - * AWL := max(GSS - W' + 1, ISS). - * These adjustments MUST be applied only at the beginning of the - * connection. - * - * AWL was adjusted in dccp_v4_connect -acme + * Set ISR, GSR from packet. ISS was set in dccp_v{4,6}_connect + * and GSS in dccp_transmit_skb(). Setting AWL/AWH and SWL/SWH + * is done as part of activating the feature values below, since + * these settings depend on the local/remote Sequence Window + * features, which were undefined or not confirmed until now. */ - dccp_set_seqno(&dp->dccps_swl, - max48(dp->dccps_swl, dp->dccps_isr)); + dp->dccps_gsr = dp->dccps_isr = DCCP_SKB_CB(skb)->dccpd_seq; dccp_sync_mss(sk, icsk->icsk_pmtu_cookie); diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index 0ecb19c5e8ce..f4d9c8f60ede 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -120,30 +120,18 @@ struct sock *dccp_create_openreq_child(struct sock *sk, * * Choose S.ISS (initial seqno) or set from Init Cookies * Initialize S.GAR := S.ISS - * Set S.ISR, S.GSR, S.SWL, S.SWH from packet or Init Cookies - */ - newdp->dccps_gar = newdp->dccps_iss = dreq->dreq_iss; - dccp_update_gss(newsk, dreq->dreq_iss); - - newdp->dccps_isr = dreq->dreq_isr; - dccp_update_gsr(newsk, dreq->dreq_isr); - - /* - * SWL and AWL are initially adjusted so that they are not less than - * the initial Sequence Numbers received and sent, respectively: - * SWL := max(GSR + 1 - floor(W/4), ISR), - * AWL := max(GSS - W' + 1, ISS). - * These adjustments MUST be applied only at the beginning of the - * connection. + * Set S.ISR, S.GSR from packet (or Init Cookies) + * + * Setting AWL/AWH and SWL/SWH happens as part of the feature + * activation below, as these windows all depend on the local + * and remote Sequence Window feature values (7.5.2). */ - dccp_set_seqno(&newdp->dccps_swl, - max48(newdp->dccps_swl, newdp->dccps_isr)); - dccp_set_seqno(&newdp->dccps_awl, - max48(newdp->dccps_awl, newdp->dccps_iss)); + newdp->dccps_gss = newdp->dccps_iss = dreq->dreq_iss; + newdp->dccps_gar = newdp->dccps_iss; + newdp->dccps_gsr = newdp->dccps_isr = dreq->dreq_isr; /* - * Activate features after initialising the sequence numbers, - * since CCID initialisation may depend on GSS, ISR, ISS etc. + * Activate features: initialise CCIDs, sequence windows etc. */ if (dccp_feat_activate_values(newsk, &dreq->dreq_featneg)) { /* It is still raw copy of parent, so invalidate -- cgit v1.2.3 From ff49e27089ec363b7fc3849504e0435d447ab18a Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Thu, 4 Sep 2008 07:30:19 +0200 Subject: dccp ccid-2: Ack Vector interface clean-up This patch brings the Ack Vector interface up to date. Its main purpose is to lay the basis for the subsequent patches of this set, which will use the new data structure fields and routines. There are no real algorithmic changes, rather an adaptation: (1) Replaced the static Ack Vector size (2) with a #define so that it can be adapted (with low loss / Ack Ratio, a value of 1 works, so 2 seems to be sufficient for the moment) and added a solution so that computing the ECN nonce will continue to work - even with larger Ack Vectors. (2) Replaced the #defines for Ack Vector states with a complete enum. (3) Replaced #defines to compute Ack Vector length and state with general purpose routines (inlines), and updated code to use these. (4) Added a `tail' field (conversion to circular buffer in subsequent patch). (5) Updated the (outdated) documentation for Ack Vector struct. (6) All sequence number containers now trimmed to 48 bits. (7) Removal of unused bits: * removed dccpav_ack_nonce from struct dccp_ackvec, since this is already redundantly stored in the `dccpavr_ack_nonce' (of Ack Vector record); * removed Elapsed Time for Ack Vectors (it was nowhere used); * replaced semantics of dccpavr_sent_len with dccpavr_ack_runlen, since the code needs to be able to remember the old run length; * reduced the de-/allocation routines (redundant / duplicate tests). Justification for removing Elapsed Time information [can be removed]: --------------------------------------------------------------------- 1. The Elapsed Time information for Ack Vectors was nowhere used in the code. 2. DCCP does not implement rate-based pacing of acknowledgments. The only recommendation for always including Elapsed Time is in section 11.3 of RFC 4340: "Receivers that rate-pace acknowledgements SHOULD [...] include Elapsed Time options". But such is not the case here. 3. It does not really improve estimation accuracy. The Elapsed Time field only records the time between the arrival of the last acknowledgeable packet and the time the Ack Vector is sent out. Since Linux does not (yet) implement delayed Acks, the time difference will typically be small, since often the arrival of a data packet triggers sending feedback at the HC-receiver. Justification for changes in de-/allocation routines [can be removed]: ---------------------------------------------------------------------- * INIT_LIST_HEAD in dccp_ackvec_record_new was redundant, since the list pointers were later overwritten when the node was added via list_add(); * dccp_ackvec_record_new() was called in a single place only; * calls to list_del_init() before calling dccp_ackvec_record_delete() were redundant, since subsequently the entire element was k-freed; * since all calls to dccp_ackvec_record_delete() were preceded to a call to list_del_init(), the WARN_ON test would never evaluate to true; * since all calls to dccp_ackvec_record_delete() were made from within list_for_each_entry_safe(), the test for avr == NULL was redundant; * list_empty() in ackvec_free was redundant, since the same condition is embedded in the loop condition of the subsequent list_for_each_entry_safe(). Signed-off-by: Gerrit Renker --- net/dccp/ackvec.c | 178 ++++++++++++++++++------------------------------- net/dccp/ackvec.h | 103 +++++++++++++++------------- net/dccp/ccids/ccid2.c | 13 ++-- net/dccp/input.c | 6 +- 4 files changed, 127 insertions(+), 173 deletions(-) (limited to 'net/dccp/input.c') diff --git a/net/dccp/ackvec.c b/net/dccp/ackvec.c index 01e4d39fa232..85ad70cfba5b 100644 --- a/net/dccp/ackvec.c +++ b/net/dccp/ackvec.c @@ -1,7 +1,8 @@ /* * net/dccp/ackvec.c * - * An implementation of the DCCP protocol + * An implementation of Ack Vectors for the DCCP protocol + * Copyright (c) 2007 University of Aberdeen, Scotland, UK * Copyright (c) 2005 Arnaldo Carvalho de Melo * * This program is free software; you can redistribute it and/or modify it @@ -23,24 +24,32 @@ static struct kmem_cache *dccp_ackvec_slab; static struct kmem_cache *dccp_ackvec_record_slab; -static struct dccp_ackvec_record *dccp_ackvec_record_new(void) +struct dccp_ackvec *dccp_ackvec_alloc(const gfp_t priority) { - struct dccp_ackvec_record *avr = - kmem_cache_alloc(dccp_ackvec_record_slab, GFP_ATOMIC); + struct dccp_ackvec *av = kmem_cache_zalloc(dccp_ackvec_slab, priority); + + if (av != NULL) { + av->av_buf_head = DCCPAV_MAX_ACKVEC_LEN - 1; + INIT_LIST_HEAD(&av->av_records); + } + return av; +} - if (avr != NULL) - INIT_LIST_HEAD(&avr->avr_node); +static void dccp_ackvec_purge_records(struct dccp_ackvec *av) +{ + struct dccp_ackvec_record *cur, *next; - return avr; + list_for_each_entry_safe(cur, next, &av->av_records, avr_node) + kmem_cache_free(dccp_ackvec_record_slab, cur); + INIT_LIST_HEAD(&av->av_records); } -static void dccp_ackvec_record_delete(struct dccp_ackvec_record *avr) +void dccp_ackvec_free(struct dccp_ackvec *av) { - if (unlikely(avr == NULL)) - return; - /* Check if deleting a linked record */ - WARN_ON(!list_empty(&avr->avr_node)); - kmem_cache_free(dccp_ackvec_record_slab, avr); + if (likely(av != NULL)) { + dccp_ackvec_purge_records(av); + kmem_cache_free(dccp_ackvec_slab, av); + } } static void dccp_ackvec_insert_avr(struct dccp_ackvec *av, @@ -68,24 +77,16 @@ int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb) struct dccp_ackvec *av = dp->dccps_hc_rx_ackvec; /* Figure out how many options do we need to represent the ackvec */ const u8 nr_opts = DIV_ROUND_UP(av->av_vec_len, DCCP_SINGLE_OPT_MAXLEN); - u16 len = av->av_vec_len + 2 * nr_opts, i; - u32 elapsed_time; + u16 len = av->av_vec_len + 2 * nr_opts; + u8 i, nonce = 0; const unsigned char *tail, *from; unsigned char *to; struct dccp_ackvec_record *avr; - suseconds_t delta; if (DCCP_SKB_CB(skb)->dccpd_opt_len + len > DCCP_MAX_OPT_LEN) return -1; - delta = ktime_us_delta(ktime_get_real(), av->av_time); - elapsed_time = delta / 10; - - if (elapsed_time != 0 && - dccp_insert_option_elapsed_time(sk, skb, elapsed_time)) - return -1; - - avr = dccp_ackvec_record_new(); + avr = kmem_cache_alloc(dccp_ackvec_record_slab, GFP_ATOMIC); if (avr == NULL) return -1; @@ -94,7 +95,7 @@ int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb) to = skb_push(skb, len); len = av->av_vec_len; from = av->av_buf + av->av_buf_head; - tail = av->av_buf + DCCP_MAX_ACKVEC_LEN; + tail = av->av_buf + DCCPAV_MAX_ACKVEC_LEN; for (i = 0; i < nr_opts; ++i) { int copylen = len; @@ -102,7 +103,13 @@ int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb) if (len > DCCP_SINGLE_OPT_MAXLEN) copylen = DCCP_SINGLE_OPT_MAXLEN; - *to++ = DCCPO_ACK_VECTOR_0; + /* + * RFC 4340, 12.2: Encode the Nonce Echo for this Ack Vector via + * its type; ack_nonce is the sum of all individual buf_nonce's. + */ + nonce ^= av->av_buf_nonce[i]; + + *to++ = DCCPO_ACK_VECTOR_0 + av->av_buf_nonce[i]; *to++ = copylen + 2; /* Check if buf_head wraps */ @@ -123,75 +130,24 @@ int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb) } /* - * From RFC 4340, A.2: - * - * For each acknowledgement it sends, the HC-Receiver will add an - * acknowledgement record. ack_seqno will equal the HC-Receiver - * sequence number it used for the ack packet; ack_ptr will equal - * buf_head; ack_ackno will equal buf_ackno; and ack_nonce will - * equal buf_nonce. + * Each sent Ack Vector is recorded in the list, as per A.2 of RFC 4340. */ - avr->avr_ack_seqno = DCCP_SKB_CB(skb)->dccpd_seq; - avr->avr_ack_ptr = av->av_buf_head; - avr->avr_ack_ackno = av->av_buf_ackno; - avr->avr_ack_nonce = av->av_buf_nonce; - avr->avr_sent_len = av->av_vec_len; + avr->avr_ack_seqno = DCCP_SKB_CB(skb)->dccpd_seq; + avr->avr_ack_ptr = av->av_buf_head; + avr->avr_ack_ackno = av->av_buf_ackno; + avr->avr_ack_nonce = nonce; + avr->avr_ack_runlen = dccp_ackvec_runlen(av->av_buf + av->av_buf_head); dccp_ackvec_insert_avr(av, avr); dccp_pr_debug("%s ACK Vector 0, len=%d, ack_seqno=%llu, " "ack_ackno=%llu\n", - dccp_role(sk), avr->avr_sent_len, + dccp_role(sk), avr->avr_ack_runlen, (unsigned long long)avr->avr_ack_seqno, (unsigned long long)avr->avr_ack_ackno); return 0; } -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->av_buf_head = DCCP_MAX_ACKVEC_LEN - 1; - av->av_buf_ackno = UINT48_MAX + 1; - av->av_buf_nonce = 0; - av->av_time = ktime_set(0, 0); - av->av_vec_len = 0; - INIT_LIST_HEAD(&av->av_records); - } - - return av; -} - -void dccp_ackvec_free(struct dccp_ackvec *av) -{ - if (unlikely(av == NULL)) - return; - - if (!list_empty(&av->av_records)) { - struct dccp_ackvec_record *avr, *next; - - list_for_each_entry_safe(avr, next, &av->av_records, avr_node) { - list_del_init(&avr->avr_node); - dccp_ackvec_record_delete(avr); - } - } - - kmem_cache_free(dccp_ackvec_slab, av); -} - -static inline u8 dccp_ackvec_state(const struct dccp_ackvec *av, - const u32 index) -{ - return av->av_buf[index] & DCCP_ACKVEC_STATE_MASK; -} - -static inline u8 dccp_ackvec_len(const struct dccp_ackvec *av, - const u32 index) -{ - return av->av_buf[index] & DCCP_ACKVEC_LEN_MASK; -} - /* * If several packets are missing, the HC-Receiver may prefer to enter multiple * bytes with run length 0, rather than a single byte with a larger run length; @@ -204,7 +160,7 @@ static inline int dccp_ackvec_set_buf_head_state(struct dccp_ackvec *av, unsigned int gap; long new_head; - if (av->av_vec_len + packets > DCCP_MAX_ACKVEC_LEN) + if (av->av_vec_len + packets > DCCPAV_MAX_ACKVEC_LEN) return -ENOBUFS; gap = packets - 1; @@ -212,18 +168,18 @@ static inline int dccp_ackvec_set_buf_head_state(struct dccp_ackvec *av, if (new_head < 0) { if (gap > 0) { - memset(av->av_buf, DCCP_ACKVEC_STATE_NOT_RECEIVED, + memset(av->av_buf, DCCPAV_NOT_RECEIVED, gap + new_head + 1); gap = -new_head; } - new_head += DCCP_MAX_ACKVEC_LEN; + new_head += DCCPAV_MAX_ACKVEC_LEN; } av->av_buf_head = new_head; if (gap > 0) memset(av->av_buf + av->av_buf_head + 1, - DCCP_ACKVEC_STATE_NOT_RECEIVED, gap); + DCCPAV_NOT_RECEIVED, gap); av->av_buf[av->av_buf_head] = state; av->av_vec_len += packets; @@ -236,6 +192,8 @@ static inline int dccp_ackvec_set_buf_head_state(struct dccp_ackvec *av, int dccp_ackvec_add(struct dccp_ackvec *av, const struct sock *sk, const u64 ackno, const u8 state) { + u8 *cur_head = av->av_buf + av->av_buf_head, + *buf_end = av->av_buf + DCCPAV_MAX_ACKVEC_LEN; /* * Check at the right places if the buffer is full, if it is, tell the * caller to start dropping packets till the HC-Sender acks our ACK @@ -260,7 +218,7 @@ int dccp_ackvec_add(struct dccp_ackvec *av, const struct sock *sk, /* See if this is the first ackno being inserted */ if (av->av_vec_len == 0) { - av->av_buf[av->av_buf_head] = state; + *cur_head = state; av->av_vec_len = 1; } else if (after48(ackno, av->av_buf_ackno)) { const u64 delta = dccp_delta_seqno(av->av_buf_ackno, ackno); @@ -269,10 +227,9 @@ int dccp_ackvec_add(struct dccp_ackvec *av, const struct sock *sk, * Look if the state of this packet is the same as the * previous ackno and if so if we can bump the head len. */ - if (delta == 1 && - dccp_ackvec_state(av, av->av_buf_head) == state && - dccp_ackvec_len(av, av->av_buf_head) < DCCP_ACKVEC_LEN_MASK) - av->av_buf[av->av_buf_head]++; + if (delta == 1 && dccp_ackvec_state(cur_head) == state && + dccp_ackvec_runlen(cur_head) < DCCPAV_MAX_RUNLEN) + *cur_head += 1; else if (dccp_ackvec_set_buf_head_state(av, delta, state)) return -ENOBUFS; } else { @@ -285,21 +242,17 @@ int dccp_ackvec_add(struct dccp_ackvec *av, const struct sock *sk, * could reduce the complexity of this scan.) */ u64 delta = dccp_delta_seqno(ackno, av->av_buf_ackno); - u32 index = av->av_buf_head; while (1) { - const u8 len = dccp_ackvec_len(av, index); - const u8 av_state = dccp_ackvec_state(av, index); + const u8 len = dccp_ackvec_runlen(cur_head); /* * valid packets not yet in av_buf have a reserved * entry, with a len equal to 0. */ - if (av_state == DCCP_ACKVEC_STATE_NOT_RECEIVED && - len == 0 && delta == 0) { /* Found our - reserved seat! */ + if (*cur_head == DCCPAV_NOT_RECEIVED && delta == 0) { dccp_pr_debug("Found %llu reserved seat!\n", (unsigned long long)ackno); - av->av_buf[index] = state; + *cur_head = state; goto out; } /* len == 0 means one packet */ @@ -307,13 +260,12 @@ int dccp_ackvec_add(struct dccp_ackvec *av, const struct sock *sk, goto out_duplicate; delta -= len + 1; - if (++index == DCCP_MAX_ACKVEC_LEN) - index = 0; + if (++cur_head == buf_end) + cur_head = av->av_buf; } } av->av_buf_ackno = ackno; - av->av_time = ktime_get_real(); out: return 0; @@ -333,13 +285,13 @@ static void dccp_ackvec_throw_record(struct dccp_ackvec *av, if (av->av_buf_head <= avr->avr_ack_ptr) av->av_vec_len = avr->avr_ack_ptr - av->av_buf_head; else - av->av_vec_len = DCCP_MAX_ACKVEC_LEN - 1 - + av->av_vec_len = DCCPAV_MAX_ACKVEC_LEN - 1 - av->av_buf_head + avr->avr_ack_ptr; /* free records */ list_for_each_entry_safe_from(avr, next, &av->av_records, avr_node) { - list_del_init(&avr->avr_node); - dccp_ackvec_record_delete(avr); + list_del(&avr->avr_node); + kmem_cache_free(dccp_ackvec_record_slab, avr); } } @@ -357,7 +309,7 @@ void dccp_ackvec_check_rcv_ackno(struct dccp_ackvec *av, struct sock *sk, if (ackno == avr->avr_ack_seqno) { dccp_pr_debug("%s ACK packet 0, len=%d, ack_seqno=%llu, " "ack_ackno=%llu, ACKED!\n", - dccp_role(sk), 1, + dccp_role(sk), avr->avr_ack_runlen, (unsigned long long)avr->avr_ack_seqno, (unsigned long long)avr->avr_ack_ackno); dccp_ackvec_throw_record(av, avr); @@ -387,7 +339,7 @@ static void dccp_ackvec_check_rcv_ackvector(struct dccp_ackvec *av, */ avr = list_entry(av->av_records.next, struct dccp_ackvec_record, avr_node); while (i--) { - const u8 rl = *vector & DCCP_ACKVEC_LEN_MASK; + const u8 rl = dccp_ackvec_runlen(vector); u64 ackno_end_rl; dccp_set_seqno(&ackno_end_rl, *ackno - rl); @@ -404,8 +356,7 @@ static void dccp_ackvec_check_rcv_ackvector(struct dccp_ackvec *av, break; found: if (between48(avr->avr_ack_seqno, ackno_end_rl, *ackno)) { - const u8 state = *vector & DCCP_ACKVEC_STATE_MASK; - if (state != DCCP_ACKVEC_STATE_NOT_RECEIVED) { + if (dccp_ackvec_state(vector) != DCCPAV_NOT_RECEIVED) { dccp_pr_debug("%s ACK vector 0, len=%d, " "ack_seqno=%llu, ack_ackno=%llu, " "ACKED!\n", @@ -448,10 +399,9 @@ int __init dccp_ackvec_init(void) if (dccp_ackvec_slab == NULL) goto out_err; - dccp_ackvec_record_slab = - kmem_cache_create("dccp_ackvec_record", - sizeof(struct dccp_ackvec_record), - 0, SLAB_HWCACHE_ALIGN, NULL); + dccp_ackvec_record_slab = kmem_cache_create("dccp_ackvec_record", + sizeof(struct dccp_ackvec_record), + 0, SLAB_HWCACHE_ALIGN, NULL); if (dccp_ackvec_record_slab == NULL) goto out_destroy_slab; diff --git a/net/dccp/ackvec.h b/net/dccp/ackvec.h index 1c10814fdf72..df18f9030dbb 100644 --- a/net/dccp/ackvec.h +++ b/net/dccp/ackvec.h @@ -3,9 +3,9 @@ /* * net/dccp/ackvec.h * - * An implementation of the DCCP protocol + * An implementation of Ack Vectors for the DCCP protocol + * Copyright (c) 2007 University of Aberdeen, Scotland, UK * Copyright (c) 2005 Arnaldo Carvalho de Melo - * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. @@ -13,75 +13,84 @@ #include #include -#include #include #include -/* We can spread an ack vector across multiple options */ -#define DCCP_MAX_ACKVEC_LEN (DCCP_SINGLE_OPT_MAXLEN * 2) +/* + * Ack Vector buffer space is static, in multiples of %DCCP_SINGLE_OPT_MAXLEN, + * the maximum size of a single Ack Vector. Setting %DCCPAV_NUM_ACKVECS to 1 + * will be sufficient for most cases of low Ack Ratios, using a value of 2 gives + * more headroom if Ack Ratio is higher or when the sender acknowledges slowly. + */ +#define DCCPAV_NUM_ACKVECS 2 +#define DCCPAV_MAX_ACKVEC_LEN (DCCP_SINGLE_OPT_MAXLEN * DCCPAV_NUM_ACKVECS) /* Estimated minimum average Ack Vector length - used for updating MPS */ #define DCCPAV_MIN_OPTLEN 16 -#define DCCP_ACKVEC_STATE_RECEIVED 0 -#define DCCP_ACKVEC_STATE_ECN_MARKED (1 << 6) -#define DCCP_ACKVEC_STATE_NOT_RECEIVED (3 << 6) +enum dccp_ackvec_states { + DCCPAV_RECEIVED = 0x00, + DCCPAV_ECN_MARKED = 0x40, + DCCPAV_RESERVED = 0x80, + DCCPAV_NOT_RECEIVED = 0xC0 +}; +#define DCCPAV_MAX_RUNLEN 0x3F -#define DCCP_ACKVEC_STATE_MASK 0xC0 /* 11000000 */ -#define DCCP_ACKVEC_LEN_MASK 0x3F /* 00111111 */ +static inline u8 dccp_ackvec_runlen(const u8 *cell) +{ + return *cell & DCCPAV_MAX_RUNLEN; +} -/** struct dccp_ackvec - ack vector - * - * This data structure is the one defined in RFC 4340, Appendix A. - * - * @av_buf_head - circular buffer head - * @av_buf_tail - circular buffer tail - * @av_buf_ackno - ack # of the most recent packet acknowledgeable in the - * buffer (i.e. %av_buf_head) - * @av_buf_nonce - the one-bit sum of the ECN Nonces on all packets acked - * by the buffer with State 0 - * - * Additionally, the HC-Receiver must keep some information about the - * Ack Vectors it has recently sent. For each packet sent carrying an - * Ack Vector, it remembers four variables: +static inline u8 dccp_ackvec_state(const u8 *cell) +{ + return *cell & ~DCCPAV_MAX_RUNLEN; +} + +/** struct dccp_ackvec - Ack Vector main data structure * - * @av_records - list of dccp_ackvec_record - * @av_ack_nonce - the one-bit sum of the ECN Nonces for all State 0. + * This implements a fixed-size circular buffer within an array and is largely + * based on Appendix A of RFC 4340. * - * @av_time - the time in usecs - * @av_buf - circular buffer of acknowledgeable packets + * @av_buf: circular buffer storage area + * @av_buf_head: head index; begin of live portion in @av_buf + * @av_buf_tail: tail index; first index _after_ the live portion in @av_buf + * @av_buf_ackno: highest seqno of acknowledgeable packet recorded in @av_buf + * @av_buf_nonce: ECN nonce sums, each covering subsequent segments of up to + * %DCCP_SINGLE_OPT_MAXLEN cells in the live portion of @av_buf + * @av_records: list of %dccp_ackvec_record (Ack Vectors sent previously) + * @av_veclen: length of the live portion of @av_buf */ struct dccp_ackvec { - u64 av_buf_ackno; - struct list_head av_records; - ktime_t av_time; + u8 av_buf[DCCPAV_MAX_ACKVEC_LEN]; u16 av_buf_head; + u16 av_buf_tail; + u64 av_buf_ackno:48; + bool av_buf_nonce[DCCPAV_NUM_ACKVECS]; + struct list_head av_records; u16 av_vec_len; - u8 av_buf_nonce; - u8 av_ack_nonce; - u8 av_buf[DCCP_MAX_ACKVEC_LEN]; }; -/** struct dccp_ackvec_record - ack vector record +/** struct dccp_ackvec_record - Records information about sent Ack Vectors * - * ACK vector record as defined in Appendix A of spec. + * These list entries define the additional information which the HC-Receiver + * keeps about recently-sent Ack Vectors; again refer to RFC 4340, Appendix A. * - * The list is sorted by avr_ack_seqno + * @avr_node: the list node in @av_records + * @avr_ack_seqno: sequence number of the packet the Ack Vector was sent on + * @avr_ack_ackno: the Ack number that this record/Ack Vector refers to + * @avr_ack_ptr: pointer into @av_buf where this record starts + * @avr_ack_runlen: run length of @avr_ack_ptr at the time of sending + * @avr_ack_nonce: the sum of @av_buf_nonce's at the time this record was sent * - * @avr_node - node in av_records - * @avr_ack_seqno - sequence number of the packet this record was sent on - * @avr_ack_ackno - sequence number being acknowledged - * @avr_ack_ptr - pointer into av_buf where this record starts - * @avr_ack_nonce - av_ack_nonce at the time this record was sent - * @avr_sent_len - lenght of the record in av_buf + * The list as a whole is sorted in descending order by @avr_ack_seqno. */ struct dccp_ackvec_record { struct list_head avr_node; - u64 avr_ack_seqno; - u64 avr_ack_ackno; + u64 avr_ack_seqno:48; + u64 avr_ack_ackno:48; u16 avr_ack_ptr; - u16 avr_sent_len; - u8 avr_ack_nonce; + u8 avr_ack_runlen; + u8 avr_ack_nonce:1; }; struct sock; diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c index f56ab68a4b78..813d5cd40e8b 100644 --- a/net/dccp/ccids/ccid2.c +++ b/net/dccp/ccids/ccid2.c @@ -580,8 +580,7 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) &vector, &veclen)) != -1) { /* go through this ack vector */ while (veclen--) { - const u8 rl = *vector & DCCP_ACKVEC_LEN_MASK; - u64 ackno_end_rl = SUB48(ackno, rl); + u64 ackno_end_rl = SUB48(ackno, dccp_ackvec_runlen(vector)); ccid2_pr_debug("ackvec start:%llu end:%llu\n", (unsigned long long)ackno, @@ -604,17 +603,15 @@ 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; + const u8 state = dccp_ackvec_state(vector); /* new packet received or marked */ - if (state != DCCP_ACKVEC_STATE_NOT_RECEIVED && + if (state != DCCPAV_NOT_RECEIVED && !seqp->ccid2s_acked) { - if (state == - DCCP_ACKVEC_STATE_ECN_MARKED) { + if (state == DCCPAV_ECN_MARKED) ccid2_congestion_event(sk, seqp); - } else + else ccid2_new_ack(sk, seqp, &maxincr); diff --git a/net/dccp/input.c b/net/dccp/input.c index e3f43d55e3ce..70ad0ba72146 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -377,8 +377,7 @@ int dccp_rcv_established(struct sock *sk, struct sk_buff *skb, if (dp->dccps_hc_rx_ackvec != NULL && dccp_ackvec_add(dp->dccps_hc_rx_ackvec, sk, - DCCP_SKB_CB(skb)->dccpd_seq, - DCCP_ACKVEC_STATE_RECEIVED)) + DCCP_SKB_CB(skb)->dccpd_seq, DCCPAV_RECEIVED)) goto discard; dccp_deliver_input_to_ccids(sk, skb); @@ -627,8 +626,7 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, if (dp->dccps_hc_rx_ackvec != NULL && dccp_ackvec_add(dp->dccps_hc_rx_ackvec, sk, - DCCP_SKB_CB(skb)->dccpd_seq, - DCCP_ACKVEC_STATE_RECEIVED)) + DCCP_SKB_CB(skb)->dccpd_seq, DCCPAV_RECEIVED)) goto discard; dccp_deliver_input_to_ccids(sk, skb); -- cgit v1.2.3 From 68b1de15765f2b0e0925e692dab2b2fa2abd93fc Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Thu, 4 Sep 2008 07:30:19 +0200 Subject: dccp ccid-2: Algorithm to update buffer state This provides a routine to consistently update the buffer state when the peer acknowledges receipt of Ack Vectors; updating state in the list of Ack Vectors as well as in the circular buffer. While based on RFC 4340, several additional (and necessary) precautions were added to protect the consistency of the buffer state. These additions are essential, since analysis and experience showed that the basic algorithm was insufficient for this task (which lead to problems that were hard to debug). The algorithm now * deals with HC-sender acknowledging to HC-receiver and vice versa, * keeps track of the last unacknowledged but received seqno in tail_ackno, * has special cases to reset the overflow condition when appropriate, * is protected against receiving older information (would mess up buffer state). Note: The older code performed an unnecessary step, where the sender cleared Ack Vector state by parsing the Ack Vector received by the HC-receiver. Doing this was entirely redundant, since * the receiver always puts the full acknowledgment window (groups 2,3 in 11.4.2) into the Ack Vectors it sends; hence the HC-receiver is only interested in the highest state that the HC-sender received; * this means that the acknowledgment number on the (Data)Ack from the HC-sender is sufficient; and work done in parsing earlier state is not necessary, since the later state subsumes the earlier one (see also RFC 4340, A.4). This older interface (dccp_ackvec_parse()) is therefore removed. Signed-off-by: Gerrit Renker --- net/dccp/ackvec.c | 88 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ net/dccp/ackvec.h | 6 ++++ net/dccp/input.c | 4 +-- net/dccp/options.c | 6 ++-- 4 files changed, 98 insertions(+), 6 deletions(-) (limited to 'net/dccp/input.c') diff --git a/net/dccp/ackvec.c b/net/dccp/ackvec.c index 1184d5e5dc96..f1341a617f96 100644 --- a/net/dccp/ackvec.c +++ b/net/dccp/ackvec.c @@ -92,6 +92,24 @@ int dccp_ackvec_update_records(struct dccp_ackvec *av, u64 seqno, u8 nonce_sum) return 0; } +static struct dccp_ackvec_record *dccp_ackvec_lookup(struct list_head *av_list, + const u64 ackno) +{ + struct dccp_ackvec_record *avr; + /* + * Exploit that records are inserted in descending order of sequence + * number, start with the oldest record first. If @ackno is `before' + * the earliest ack_ackno, the packet is too old to be considered. + */ + list_for_each_entry_reverse(avr, av_list, avr_node) { + if (avr->avr_ack_seqno == ackno) + return avr; + if (before48(ackno, avr->avr_ack_seqno)) + break; + } + return NULL; +} + /* * Buffer index and length computation using modulo-buffersize arithmetic. * Note that, as pointers move from right to left, head is `before' tail. @@ -356,6 +374,76 @@ int dccp_ackvec_parse(struct sock *sk, const struct sk_buff *skb, return 0; } +/** + * dccp_ackvec_clear_state - Perform house-keeping / garbage-collection + * This routine is called when the peer acknowledges the receipt of Ack Vectors + * up to and including @ackno. While based on on section A.3 of RFC 4340, here + * are additional precautions to prevent corrupted buffer state. In particular, + * we use tail_ackno to identify outdated records; it always marks the earliest + * packet of group (2) in 11.4.2. + */ +void dccp_ackvec_clear_state(struct dccp_ackvec *av, const u64 ackno) + { + struct dccp_ackvec_record *avr, *next; + u8 runlen_now, eff_runlen; + s64 delta; + + avr = dccp_ackvec_lookup(&av->av_records, ackno); + if (avr == NULL) + return; + /* + * Deal with outdated acknowledgments: this arises when e.g. there are + * several old records and the acks from the peer come in slowly. In + * that case we may still have records that pre-date tail_ackno. + */ + delta = dccp_delta_seqno(av->av_tail_ackno, avr->avr_ack_ackno); + if (delta < 0) + goto free_records; + /* + * Deal with overlapping Ack Vectors: don't subtract more than the + * number of packets between tail_ackno and ack_ackno. + */ + eff_runlen = delta < avr->avr_ack_runlen ? delta : avr->avr_ack_runlen; + + runlen_now = dccp_ackvec_runlen(av->av_buf + avr->avr_ack_ptr); + /* + * The run length of Ack Vector cells does not decrease over time. If + * the run length is the same as at the time the Ack Vector was sent, we + * free the ack_ptr cell. That cell can however not be freed if the run + * length has increased: in this case we need to move the tail pointer + * backwards (towards higher indices), to its next-oldest neighbour. + */ + if (runlen_now > eff_runlen) { + + av->av_buf[avr->avr_ack_ptr] -= eff_runlen + 1; + av->av_buf_tail = __ackvec_idx_add(avr->avr_ack_ptr, 1); + + /* This move may not have cleared the overflow flag. */ + if (av->av_overflow) + av->av_overflow = (av->av_buf_head == av->av_buf_tail); + } else { + av->av_buf_tail = avr->avr_ack_ptr; + /* + * We have made sure that avr points to a valid cell within the + * buffer. This cell is either older than head, or equals head + * (empty buffer): in both cases we no longer have any overflow. + */ + av->av_overflow = 0; + } + + /* + * The peer has acknowledged up to and including ack_ackno. Hence the + * first packet in group (2) of 11.4.2 is the successor of ack_ackno. + */ + av->av_tail_ackno = ADD48(avr->avr_ack_ackno, 1); + +free_records: + list_for_each_entry_safe_from(avr, next, &av->av_records, avr_node) { + list_del(&avr->avr_node); + kmem_cache_free(dccp_ackvec_record_slab, avr); + } +} + int __init dccp_ackvec_init(void) { dccp_ackvec_slab = kmem_cache_create("dccp_ackvec", diff --git a/net/dccp/ackvec.h b/net/dccp/ackvec.h index 92f65b0fef5b..b757e9b4110f 100644 --- a/net/dccp/ackvec.h +++ b/net/dccp/ackvec.h @@ -118,6 +118,7 @@ extern int dccp_ackvec_parse(struct sock *sk, const struct sk_buff *skb, const u8 *value, const u8 len); extern int dccp_ackvec_update_records(struct dccp_ackvec *av, u64 seq, u8 sum); +extern void dccp_ackvec_clear_state(struct dccp_ackvec *av, const u64 ackno); extern u16 dccp_ackvec_buflen(const struct dccp_ackvec *av); static inline bool dccp_ackvec_is_empty(const struct dccp_ackvec *av) @@ -149,6 +150,11 @@ static inline int dccp_ackvec_add(struct dccp_ackvec *av, const struct sock *sk, return -1; } +static inline void dccp_ackvec_clear_state(struct dccp_ackvec *av, + const u64 ackno) +{ +} + static inline void dccp_ackvec_check_rcv_ackno(struct dccp_ackvec *av, struct sock *sk, const u64 ackno) { diff --git a/net/dccp/input.c b/net/dccp/input.c index 70ad0ba72146..77a5d57ab702 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -164,8 +164,8 @@ static void dccp_event_ack_recv(struct sock *sk, struct sk_buff *skb) struct dccp_sock *dp = dccp_sk(sk); if (dp->dccps_hc_rx_ackvec != NULL) - dccp_ackvec_check_rcv_ackno(dp->dccps_hc_rx_ackvec, sk, - DCCP_SKB_CB(skb)->dccpd_ack_seq); + dccp_ackvec_clear_state(dp->dccps_hc_rx_ackvec, + DCCP_SKB_CB(skb)->dccpd_ack_seq); } static void dccp_deliver_input_to_ccids(struct sock *sk, struct sk_buff *skb) diff --git a/net/dccp/options.c b/net/dccp/options.c index 3163ae980f16..b11d7b7167f0 100644 --- a/net/dccp/options.c +++ b/net/dccp/options.c @@ -54,7 +54,6 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq, struct dccp_sock *dp = dccp_sk(sk); const struct dccp_hdr *dh = dccp_hdr(skb); const u8 pkt_type = DCCP_SKB_CB(skb)->dccpd_type; - u64 ackno = DCCP_SKB_CB(skb)->dccpd_ack_seq; unsigned char *options = (unsigned char *)dh + dccp_hdr_len(skb); unsigned char *opt_ptr = options; const unsigned char *opt_end = (unsigned char *)dh + @@ -133,9 +132,8 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq, case DCCPO_ACK_VECTOR_1: if (dccp_packet_without_ack(skb)) /* RFC 4340, 11.4 */ break; - if (dp->dccps_hc_rx_ackvec != NULL && - dccp_ackvec_parse(sk, skb, &ackno, opt, value, len)) - goto out_invalid_option; + dccp_pr_debug("%s Ack Vector (len=%u)\n", dccp_role(sk), + len); break; case DCCPO_TIMESTAMP: if (len != 4) -- cgit v1.2.3 From 283fb4a5f39d1521d53e1044bff0ba2654acf145 Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Thu, 4 Sep 2008 07:30:19 +0200 Subject: dccp ccid-2: Consolidate Ack-Vector processing within main DCCP module This aggregates Ack Vector processing (handling input and clearing old state) into one function, for the following reasons and benefits: * all Ack Vector-specific processing is now in one place; * duplicated code is removed; * ensuring sanity: from an Ack Vector point of view, it is better to clear the old state first before entering new state; * Ack Event handling happens mostly within the CCIDs, not the main DCCP module. Signed-off-by: Gerrit Renker --- net/dccp/input.c | 31 +++++++++---------------------- 1 file changed, 9 insertions(+), 22 deletions(-) (limited to 'net/dccp/input.c') diff --git a/net/dccp/input.c b/net/dccp/input.c index 77a5d57ab702..9a108ce17fc7 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -159,13 +159,15 @@ static void dccp_rcv_reset(struct sock *sk, struct sk_buff *skb) dccp_time_wait(sk, DCCP_TIME_WAIT, 0); } -static void dccp_event_ack_recv(struct sock *sk, struct sk_buff *skb) +static void dccp_handle_ackvec_processing(struct sock *sk, struct sk_buff *skb) { - struct dccp_sock *dp = dccp_sk(sk); + struct dccp_ackvec *av = dccp_sk(sk)->dccps_hc_rx_ackvec; - if (dp->dccps_hc_rx_ackvec != NULL) - dccp_ackvec_clear_state(dp->dccps_hc_rx_ackvec, - DCCP_SKB_CB(skb)->dccpd_ack_seq); + if (av == NULL) + return; + if (DCCP_SKB_CB(skb)->dccpd_ack_seq != DCCP_PKT_WITHOUT_ACK_SEQ) + dccp_ackvec_clear_state(av, DCCP_SKB_CB(skb)->dccpd_ack_seq); + dccp_ackvec_input(av, skb); } static void dccp_deliver_input_to_ccids(struct sock *sk, struct sk_buff *skb) @@ -364,21 +366,13 @@ discard: int dccp_rcv_established(struct sock *sk, struct sk_buff *skb, const struct dccp_hdr *dh, const unsigned len) { - struct dccp_sock *dp = dccp_sk(sk); - if (dccp_check_seqno(sk, skb)) goto discard; if (dccp_parse_options(sk, NULL, skb)) return 1; - if (DCCP_SKB_CB(skb)->dccpd_ack_seq != DCCP_PKT_WITHOUT_ACK_SEQ) - dccp_event_ack_recv(sk, skb); - - if (dp->dccps_hc_rx_ackvec != NULL && - dccp_ackvec_add(dp->dccps_hc_rx_ackvec, sk, - DCCP_SKB_CB(skb)->dccpd_seq, DCCPAV_RECEIVED)) - goto discard; + dccp_handle_ackvec_processing(sk, skb); dccp_deliver_input_to_ccids(sk, skb); return __dccp_rcv_established(sk, skb, dh, len); @@ -621,14 +615,7 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, if (dccp_parse_options(sk, NULL, skb)) return 1; - if (dcb->dccpd_ack_seq != DCCP_PKT_WITHOUT_ACK_SEQ) - dccp_event_ack_recv(sk, skb); - - if (dp->dccps_hc_rx_ackvec != NULL && - dccp_ackvec_add(dp->dccps_hc_rx_ackvec, sk, - DCCP_SKB_CB(skb)->dccpd_seq, DCCPAV_RECEIVED)) - goto discard; - + dccp_handle_ackvec_processing(sk, skb); dccp_deliver_input_to_ccids(sk, skb); } -- cgit v1.2.3 From ddab05568eaa70fc92b2aae957136f188f724e9c Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Thu, 4 Sep 2008 07:30:19 +0200 Subject: dccp: Clean up slow-path input processing This patch rearranges the order of statements of the slow-path input processing (i.e. any other state than OPEN), to resolve the following issues. 1. Dependencies: the order of statements now better matches RFC 4340, 8.5, i.e. step 7 is before step 9 (previously 9 was before 7), and parsing options in step 8 (which can consume resources) now comes after step 7. 2. Bug-fix: in state CLOSED, there should not be any sequence number checking or option processing. This is why the test for CLOSED has been moved after the test for LISTEN. 3. As before sequence number checks are omitted if in state LISTEN/REQUEST, due to the note underneath the table in RFC 4340, 7.5.3. 4. Packets are now passed on to Ack Vector / CCID processing only after - step 7 (receive unexpected packets), - step 9 (receive Reset), - step 13 (receive CloseReq), - step 14 (receive Close) and only if the state is PARTOPEN. This simplifies CCID processing: - in LISTEN/CLOSED the CCIDs are non-existent; - in RESPOND/REQUEST the CCIDs have not yet been negotiated; - in CLOSEREQ and active-CLOSING the node has already closed this socket; - in passive-CLOSING the client is waiting for its Reset. In the last case, RFC 4340, 8.3 leaves it open to ignore further incoming data, which is the approach taken here. As a result of (3), CCID processing is now indeed confined to OPEN/PARTOPEN states, i.e. congestion control is performed only on the flow of data packets. This avoids pathological cases of doing congestion control on those messages which set up and terminate the connection. I have done a few checks to see if this creates a problem in other parts of the code. This seems not to be the case; even if there were one, it would be better to fix it than to perform congestion control on Close/Request/Response messages. Similarly for Ack Vectors (as they depend on the negotiated CCID). Signed-off-by: Gerrit Renker --- net/dccp/input.c | 68 +++++++++++++++++++++++++++----------------------------- 1 file changed, 33 insertions(+), 35 deletions(-) (limited to 'net/dccp/input.c') diff --git a/net/dccp/input.c b/net/dccp/input.c index 9a108ce17fc7..b1e38bf94456 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -603,22 +603,36 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, /* Caller (dccp_v4_do_rcv) will send Reset */ dcb->dccpd_reset_code = DCCP_RESET_CODE_NO_CONNECTION; return 1; + } else if (sk->sk_state == DCCP_CLOSED) { + dcb->dccpd_reset_code = DCCP_RESET_CODE_NO_CONNECTION; + return 1; } - if (sk->sk_state != DCCP_REQUESTING && sk->sk_state != DCCP_RESPOND) { - if (dccp_check_seqno(sk, skb)) - goto discard; - - /* - * Step 8: Process options and mark acknowledgeable - */ - if (dccp_parse_options(sk, NULL, skb)) - return 1; + /* Step 6: Check sequence numbers (omitted in LISTEN/REQUEST state) */ + if (sk->sk_state != DCCP_REQUESTING && dccp_check_seqno(sk, skb)) + goto discard; - dccp_handle_ackvec_processing(sk, skb); - dccp_deliver_input_to_ccids(sk, skb); + /* + * Step 7: Check for unexpected packet types + * If (S.is_server and P.type == Response) + * or (S.is_client and P.type == Request) + * or (S.state == RESPOND and P.type == Data), + * Send Sync packet acknowledging P.seqno + * Drop packet and return + */ + if ((dp->dccps_role != DCCP_ROLE_CLIENT && + dh->dccph_type == DCCP_PKT_RESPONSE) || + (dp->dccps_role == DCCP_ROLE_CLIENT && + dh->dccph_type == DCCP_PKT_REQUEST) || + (sk->sk_state == DCCP_RESPOND && dh->dccph_type == DCCP_PKT_DATA)) { + dccp_send_sync(sk, dcb->dccpd_seq, DCCP_PKT_SYNC); + goto discard; } + /* Step 8: Process options */ + if (dccp_parse_options(sk, NULL, skb)) + return 1; + /* * Step 9: Process Reset * If P.type == Reset, @@ -626,41 +640,21 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, * S.state := TIMEWAIT * Set TIMEWAIT timer * Drop packet and return - */ + */ if (dh->dccph_type == DCCP_PKT_RESET) { dccp_rcv_reset(sk, skb); return 0; - /* - * Step 7: Check for unexpected packet types - * If (S.is_server and P.type == Response) - * or (S.is_client and P.type == Request) - * or (S.state == RESPOND and P.type == Data), - * Send Sync packet acknowledging P.seqno - * Drop packet and return - */ - } else if ((dp->dccps_role != DCCP_ROLE_CLIENT && - dh->dccph_type == DCCP_PKT_RESPONSE) || - (dp->dccps_role == DCCP_ROLE_CLIENT && - dh->dccph_type == DCCP_PKT_REQUEST) || - (sk->sk_state == DCCP_RESPOND && - dh->dccph_type == DCCP_PKT_DATA)) { - dccp_send_sync(sk, dcb->dccpd_seq, DCCP_PKT_SYNC); - goto discard; - } else if (dh->dccph_type == DCCP_PKT_CLOSEREQ) { + } else if (dh->dccph_type == DCCP_PKT_CLOSEREQ) { /* Step 13 */ if (dccp_rcv_closereq(sk, skb)) return 0; goto discard; - } else if (dh->dccph_type == DCCP_PKT_CLOSE) { + } else if (dh->dccph_type == DCCP_PKT_CLOSE) { /* Step 14 */ if (dccp_rcv_close(sk, skb)) return 0; goto discard; } switch (sk->sk_state) { - case DCCP_CLOSED: - dcb->dccpd_reset_code = DCCP_RESET_CODE_NO_CONNECTION; - return 1; - case DCCP_REQUESTING: queued = dccp_rcv_request_sent_state_process(sk, skb, dh, len); if (queued >= 0) @@ -669,8 +663,12 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, __kfree_skb(skb); return 0; - case DCCP_RESPOND: case DCCP_PARTOPEN: + /* Step 8: if using Ack Vectors, mark packet acknowledgeable */ + dccp_handle_ackvec_processing(sk, skb); + dccp_deliver_input_to_ccids(sk, skb); + /* fall through */ + case DCCP_RESPOND: queued = dccp_rcv_respond_partopen_state_process(sk, skb, dh, len); break; -- cgit v1.2.3 From 49ffc29a0223adbe0ea7005eea3ab2a03abbeb06 Mon Sep 17 00:00:00 2001 From: Gerrit Renker Date: Thu, 4 Sep 2008 07:30:19 +0200 Subject: dccp: Clamping RTT values This extracts the clamping part of dccp_sample_rtt() and makes it available to other parts of the code (as e.g. used in the next patch). Note: The function dccp_sample_rtt() now reduces to subtracting the elapsed time. This could be eliminated but would require shorter prefixes and thus is not done by this patch - maybe an idea for later. Signed-off-by: Gerrit Renker --- net/dccp/dccp.h | 9 ++++++++- net/dccp/input.c | 11 +---------- 2 files changed, 9 insertions(+), 11 deletions(-) (limited to 'net/dccp/input.c') diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index b63a82ccb2b2..5281190aa19c 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -334,7 +334,14 @@ extern struct sk_buff *dccp_ctl_make_reset(struct sock *sk, extern int dccp_send_reset(struct sock *sk, enum dccp_reset_codes code); extern void dccp_send_close(struct sock *sk, const int active); extern int dccp_invalid_packet(struct sk_buff *skb); -extern u32 dccp_sample_rtt(struct sock *sk, long delta); + +static inline u32 dccp_sane_rtt(long usec_sample) +{ + if (unlikely(usec_sample <= 0 || usec_sample > DCCP_SANE_RTT_MAX)) + DCCP_WARN("RTT sample %ld out of bounds!\n", usec_sample); + return clamp_val(usec_sample, DCCP_SANE_RTT_MIN, DCCP_SANE_RTT_MAX); +} +extern u32 dccp_sample_rtt(struct sock *sk, long delta); static inline int dccp_bad_service_code(const struct sock *sk, const __be32 service) diff --git a/net/dccp/input.c b/net/dccp/input.c index b1e38bf94456..df0e6714aa11 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -707,16 +707,7 @@ u32 dccp_sample_rtt(struct sock *sk, long delta) /* dccpor_elapsed_time is either zeroed out or set and > 0 */ delta -= dccp_sk(sk)->dccps_options_received.dccpor_elapsed_time * 10; - if (unlikely(delta <= 0)) { - DCCP_WARN("unusable RTT sample %ld, using min\n", delta); - return DCCP_SANE_RTT_MIN; - } - if (unlikely(delta > DCCP_SANE_RTT_MAX)) { - DCCP_WARN("RTT sample %ld too large, using max\n", delta); - return DCCP_SANE_RTT_MAX; - } - - return delta; + return dccp_sane_rtt(delta); } EXPORT_SYMBOL_GPL(dccp_sample_rtt); -- cgit v1.2.3