diff options
Diffstat (limited to 'net/dccp')
30 files changed, 2183 insertions, 1964 deletions
diff --git a/net/dccp/Kconfig b/net/dccp/Kconfig index e2a095d0fd8..b8a68dd4100 100644 --- a/net/dccp/Kconfig +++ b/net/dccp/Kconfig @@ -4,15 +4,15 @@ menu "DCCP Configuration (EXPERIMENTAL)" config IP_DCCP tristate "The DCCP Protocol (EXPERIMENTAL)" ---help--- - Datagram Congestion Control Protocol + Datagram Congestion Control Protocol (RFC 4340) - From draft-ietf-dccp-spec-11 <http://www.icir.org/kohler/dcp/draft-ietf-dccp-spec-11.txt>. + From http://www.ietf.org/rfc/rfc4340.txt: The Datagram Congestion Control Protocol (DCCP) is a transport protocol that implements bidirectional, unicast connections of congestion-controlled, unreliable datagrams. It should be suitable for use by applications such as streaming media, Internet telephony, - and on-line games + and on-line games. To compile this protocol support as a module, choose M here: the module will be called dccp. @@ -38,6 +38,9 @@ config IP_DCCP_DEBUG ---help--- Only use this if you're hacking DCCP. + When compiling DCCP as a module, this debugging output can be toggled + by setting the parameter dccp_debug of the `dccp' module to 0 or 1. + Just say N. config NET_DCCPPROBE @@ -49,7 +52,7 @@ config NET_DCCPPROBE DCCP congestion avoidance modules. If you don't understand what was just said, you don't need it: say N. - Documentation on how to use the packet generator can be found + Documentation on how to use DCCP connection probing can be found at http://linux-net.osdl.org/index.php/DccpProbe To compile this code as a module, choose M here: the diff --git a/net/dccp/Makefile b/net/dccp/Makefile index 17ed99c4661..f4f8793aaff 100644 --- a/net/dccp/Makefile +++ b/net/dccp/Makefile @@ -1,13 +1,13 @@ -obj-$(CONFIG_IPV6) += dccp_ipv6.o - -dccp_ipv6-y := ipv6.o - obj-$(CONFIG_IP_DCCP) += dccp.o dccp_ipv4.o dccp-y := ccid.o feat.o input.o minisocks.o options.o output.o proto.o timer.o dccp_ipv4-y := ipv4.o +# build dccp_ipv6 as module whenever either IPv6 or DCCP is a module +obj-$(subst y,$(CONFIG_IP_DCCP),$(CONFIG_IPV6)) += dccp_ipv6.o +dccp_ipv6-y := ipv6.o + dccp-$(CONFIG_IP_DCCP_ACKVEC) += ackvec.o obj-$(CONFIG_INET_DCCP_DIAG) += dccp_diag.o diff --git a/net/dccp/ackvec.c b/net/dccp/ackvec.c index 4d176d33983..a086c6312d3 100644 --- a/net/dccp/ackvec.c +++ b/net/dccp/ackvec.c @@ -21,8 +21,8 @@ #include <net/sock.h> -static kmem_cache_t *dccp_ackvec_slab; -static kmem_cache_t *dccp_ackvec_record_slab; +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) { @@ -67,15 +67,16 @@ static void dccp_ackvec_insert_avr(struct dccp_ackvec *av, int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb) { struct dccp_sock *dp = dccp_sk(sk); -#ifdef CONFIG_IP_DCCP_DEBUG - const char *debug_prefix = dp->dccps_role == DCCP_ROLE_CLIENT ? - "CLIENT tx: " : "server tx: "; -#endif struct dccp_ackvec *av = dp->dccps_hc_rx_ackvec; - int len = av->dccpav_vec_len + 2; + /* Figure out how many options do we need to represent the ackvec */ + const u16 nr_opts = (av->dccpav_vec_len + + DCCP_MAX_ACKVEC_OPT_LEN - 1) / + DCCP_MAX_ACKVEC_OPT_LEN; + u16 len = av->dccpav_vec_len + 2 * nr_opts, i; struct timeval now; u32 elapsed_time; - unsigned char *to, *from; + const unsigned char *tail, *from; + unsigned char *to; struct dccp_ackvec_record *avr; if (DCCP_SKB_CB(skb)->dccpd_opt_len + len > DCCP_MAX_OPT_LEN) @@ -94,26 +95,39 @@ int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb) DCCP_SKB_CB(skb)->dccpd_opt_len += len; - to = skb_push(skb, len); - *to++ = DCCPO_ACK_VECTOR_0; - *to++ = len; - + to = skb_push(skb, len); len = av->dccpav_vec_len; from = av->dccpav_buf + av->dccpav_buf_head; + tail = av->dccpav_buf + DCCP_MAX_ACKVEC_LEN; + + for (i = 0; i < nr_opts; ++i) { + int copylen = len; + + if (len > DCCP_MAX_ACKVEC_OPT_LEN) + copylen = DCCP_MAX_ACKVEC_OPT_LEN; - /* Check if buf_head wraps */ - if ((int)av->dccpav_buf_head + len > DCCP_MAX_ACKVEC_LEN) { - const u32 tailsize = DCCP_MAX_ACKVEC_LEN - av->dccpav_buf_head; + *to++ = DCCPO_ACK_VECTOR_0; + *to++ = copylen + 2; - memcpy(to, from, tailsize); - to += tailsize; - len -= tailsize; - from = av->dccpav_buf; + /* Check if buf_head wraps */ + if (from + copylen > tail) { + const u16 tailsize = tail - from; + + memcpy(to, from, tailsize); + to += tailsize; + len -= tailsize; + copylen -= tailsize; + from = av->dccpav_buf; + } + + memcpy(to, from, copylen); + from += copylen; + to += copylen; + len -= copylen; } - memcpy(to, from, len); /* - * From draft-ietf-dccp-spec-11.txt: + * 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 @@ -129,9 +143,9 @@ int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb) dccp_ackvec_insert_avr(av, avr); - dccp_pr_debug("%sACK Vector 0, len=%d, ack_seqno=%llu, " + dccp_pr_debug("%s ACK Vector 0, len=%d, ack_seqno=%llu, " "ack_ackno=%llu\n", - debug_prefix, avr->dccpavr_sent_len, + dccp_role(sk), avr->dccpavr_sent_len, (unsigned long long)avr->dccpavr_ack_seqno, (unsigned long long)avr->dccpavr_ack_ackno); return 0; @@ -145,7 +159,6 @@ struct dccp_ackvec *dccp_ackvec_alloc(const gfp_t priority) 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_vec_len = 0; @@ -174,13 +187,13 @@ void dccp_ackvec_free(struct dccp_ackvec *av) } static inline u8 dccp_ackvec_state(const struct dccp_ackvec *av, - const u8 index) + const u32 index) { return av->dccpav_buf[index] & DCCP_ACKVEC_STATE_MASK; } static inline u8 dccp_ackvec_len(const struct dccp_ackvec *av, - const u8 index) + const u32 index) { return av->dccpav_buf[index] & DCCP_ACKVEC_LEN_MASK; } @@ -210,7 +223,7 @@ static inline int dccp_ackvec_set_buf_head_state(struct dccp_ackvec *av, gap = -new_head; } new_head += DCCP_MAX_ACKVEC_LEN; - } + } av->dccpav_buf_head = new_head; @@ -224,7 +237,7 @@ static inline int dccp_ackvec_set_buf_head_state(struct dccp_ackvec *av, } /* - * Implements the draft-ietf-dccp-spec-11.txt Appendix A + * Implements the RFC 4340, Appendix A */ int dccp_ackvec_add(struct dccp_ackvec *av, const struct sock *sk, const u64 ackno, const u8 state) @@ -237,7 +250,7 @@ int dccp_ackvec_add(struct dccp_ackvec *av, const struct sock *sk, * We may well decide to do buffer compression, etc, but for now lets * just drop. * - * From Appendix A: + * From Appendix A.1.1 (`New Packets'): * * Of course, the circular buffer may overflow, either when the * HC-Sender is sending data at a very high rate, when the @@ -274,13 +287,13 @@ int dccp_ackvec_add(struct dccp_ackvec *av, const struct sock *sk, /* * A.1.2. Old Packets * - * When a packet with Sequence Number S arrives, and - * S <= buf_ackno, the HC-Receiver will scan the table - * for the byte corresponding to S. (Indexing structures + * When a packet with Sequence Number S <= buf_ackno + * arrives, the HC-Receiver will scan the table for + * the byte corresponding to S. (Indexing structures * could reduce the complexity of this scan.) */ u64 delta = dccp_delta_seqno(ackno, av->dccpav_buf_ackno); - u8 index = av->dccpav_buf_head; + u32 index = av->dccpav_buf_head; while (1) { const u8 len = dccp_ackvec_len(av, index); @@ -322,21 +335,18 @@ out_duplicate: #ifdef CONFIG_IP_DCCP_DEBUG void dccp_ackvector_print(const u64 ackno, const unsigned char *vector, int len) { - if (!dccp_debug) - return; - - printk("ACK vector len=%d, ackno=%llu |", len, - (unsigned long long)ackno); + dccp_pr_debug_cat("ACK vector len=%d, ackno=%llu |", len, + (unsigned long long)ackno); while (len--) { const u8 state = (*vector & DCCP_ACKVEC_STATE_MASK) >> 6; const u8 rl = *vector & DCCP_ACKVEC_LEN_MASK; - printk("%d,%d|", state, rl); + dccp_pr_debug_cat("%d,%d|", state, rl); ++vector; } - printk("\n"); + dccp_pr_debug_cat("\n"); } void dccp_ackvec_print(const struct dccp_ackvec *av) @@ -380,24 +390,20 @@ void dccp_ackvec_check_rcv_ackno(struct dccp_ackvec *av, struct sock *sk, */ list_for_each_entry_reverse(avr, &av->dccpav_records, dccpavr_node) { if (ackno == avr->dccpavr_ack_seqno) { -#ifdef CONFIG_IP_DCCP_DEBUG - struct dccp_sock *dp = dccp_sk(sk); - const char *debug_prefix = dp->dccps_role == DCCP_ROLE_CLIENT ? - "CLIENT rx ack: " : "server rx ack: "; -#endif - dccp_pr_debug("%sACK packet 0, len=%d, ack_seqno=%llu, " + dccp_pr_debug("%s ACK packet 0, len=%d, ack_seqno=%llu, " "ack_ackno=%llu, ACKED!\n", - debug_prefix, 1, + dccp_role(sk), 1, (unsigned long long)avr->dccpavr_ack_seqno, (unsigned long long)avr->dccpavr_ack_ackno); dccp_ackvec_throw_record(av, avr); break; - } + } else if (avr->dccpavr_ack_seqno > ackno) + break; /* old news */ } } static void dccp_ackvec_check_rcv_ackvector(struct dccp_ackvec *av, - struct sock *sk, u64 ackno, + struct sock *sk, u64 *ackno, const unsigned char len, const unsigned char *vector) { @@ -420,7 +426,7 @@ static void dccp_ackvec_check_rcv_ackvector(struct dccp_ackvec *av, const u8 rl = *vector & DCCP_ACKVEC_LEN_MASK; u64 ackno_end_rl; - dccp_set_seqno(&ackno_end_rl, ackno - rl); + dccp_set_seqno(&ackno_end_rl, *ackno - rl); /* * If our AVR sequence number is greater than the ack, go @@ -428,25 +434,19 @@ static void dccp_ackvec_check_rcv_ackvector(struct dccp_ackvec *av, */ list_for_each_entry_from(avr, &av->dccpav_records, dccpavr_node) { - if (!after48(avr->dccpavr_ack_seqno, ackno)) + if (!after48(avr->dccpavr_ack_seqno, *ackno)) goto found; } /* End of the dccpav_records list, not found, exit */ break; found: - if (between48(avr->dccpavr_ack_seqno, ackno_end_rl, ackno)) { + if (between48(avr->dccpavr_ack_seqno, ackno_end_rl, *ackno)) { 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); - const char *debug_prefix = - dp->dccps_role == DCCP_ROLE_CLIENT ? - "CLIENT rx ack: " : "server rx ack: "; -#endif - dccp_pr_debug("%sACK vector 0, len=%d, " + dccp_pr_debug("%s ACK vector 0, len=%d, " "ack_seqno=%llu, ack_ackno=%llu, " "ACKED!\n", - debug_prefix, len, + dccp_role(sk), len, (unsigned long long) avr->dccpavr_ack_seqno, (unsigned long long) @@ -460,27 +460,23 @@ found: */ } - dccp_set_seqno(&ackno, ackno_end_rl - 1); + dccp_set_seqno(ackno, ackno_end_rl - 1); ++vector; } } int dccp_ackvec_parse(struct sock *sk, const struct sk_buff *skb, - const u8 opt, const u8 *value, const u8 len) + u64 *ackno, const u8 opt, const u8 *value, const u8 len) { - if (len > DCCP_MAX_ACKVEC_LEN) + if (len > DCCP_MAX_ACKVEC_OPT_LEN) return -1; /* dccp_ackvector_print(DCCP_SKB_CB(skb)->dccpd_ack_seq, value, len); */ dccp_ackvec_check_rcv_ackvector(dccp_sk(sk)->dccps_hc_rx_ackvec, sk, - DCCP_SKB_CB(skb)->dccpd_ack_seq, - len, value); + ackno, len, value); return 0; } -static char dccp_ackvec_slab_msg[] __initdata = - KERN_CRIT "DCCP: Unable to create ack vectors slab caches\n"; - int __init dccp_ackvec_init(void) { dccp_ackvec_slab = kmem_cache_create("dccp_ackvec", @@ -502,7 +498,7 @@ out_destroy_slab: kmem_cache_destroy(dccp_ackvec_slab); dccp_ackvec_slab = NULL; out_err: - printk(dccp_ackvec_slab_msg); + DCCP_CRIT("Unable to create Ack Vector slab cache"); return -ENOBUFS; } diff --git a/net/dccp/ackvec.h b/net/dccp/ackvec.h index 2424effac7f..96504a3b16e 100644 --- a/net/dccp/ackvec.h +++ b/net/dccp/ackvec.h @@ -17,7 +17,9 @@ #include <linux/types.h> /* Read about the ECN nonce to see why it is 253 */ -#define DCCP_MAX_ACKVEC_LEN 253 +#define DCCP_MAX_ACKVEC_OPT_LEN 253 +/* We can spread an ack vector across multiple options */ +#define DCCP_MAX_ACKVEC_LEN (DCCP_MAX_ACKVEC_OPT_LEN * 2) #define DCCP_ACKVEC_STATE_RECEIVED 0 #define DCCP_ACKVEC_STATE_ECN_MARKED (1 << 6) @@ -28,8 +30,7 @@ /** struct dccp_ackvec - ack vector * - * This data structure is the one defined in the DCCP draft - * Appendix A. + * This data structure is the one defined in RFC 4340, Appendix A. * * @dccpav_buf_head - circular buffer head * @dccpav_buf_tail - circular buffer tail @@ -42,7 +43,6 @@ * Ack Vectors it has recently sent. For each packet sent carrying an * Ack Vector, it remembers four variables: * - * @dccpav_ack_ptr - the value of buf_head at the time of acknowledgement. * @dccpav_records - list of dccp_ackvec_record * @dccpav_ack_nonce - the one-bit sum of the ECN Nonces for all State 0. * @@ -53,9 +53,8 @@ struct dccp_ackvec { u64 dccpav_buf_ackno; struct list_head dccpav_records; struct timeval dccpav_time; - u8 dccpav_buf_head; - u8 dccpav_ack_ptr; - u8 dccpav_vec_len; + u16 dccpav_buf_head; + u16 dccpav_vec_len; u8 dccpav_buf_nonce; u8 dccpav_ack_nonce; u8 dccpav_buf[DCCP_MAX_ACKVEC_LEN]; @@ -78,9 +77,9 @@ struct dccp_ackvec_record { struct list_head dccpavr_node; u64 dccpavr_ack_seqno; u64 dccpavr_ack_ackno; - u8 dccpavr_ack_ptr; + u16 dccpavr_ack_ptr; + u16 dccpavr_sent_len; u8 dccpavr_ack_nonce; - u8 dccpavr_sent_len; }; struct sock; @@ -99,7 +98,8 @@ extern int dccp_ackvec_add(struct dccp_ackvec *av, const struct sock *sk, extern void dccp_ackvec_check_rcv_ackno(struct dccp_ackvec *av, struct sock *sk, const u64 ackno); extern int dccp_ackvec_parse(struct sock *sk, const struct sk_buff *skb, - const u8 opt, const u8 *value, const u8 len); + u64 *ackno, const u8 opt, + const u8 *value, const u8 len); extern int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb); @@ -138,7 +138,8 @@ static inline void dccp_ackvec_check_rcv_ackno(struct dccp_ackvec *av, } static inline int dccp_ackvec_parse(struct sock *sk, const struct sk_buff *skb, - const u8 opt, const u8 *value, const u8 len) + const u64 *ackno, const u8 opt, + const u8 *value, const u8 len) { return -1; } diff --git a/net/dccp/ccid.c b/net/dccp/ccid.c index ff05e59043c..d8cf92f09e6 100644 --- a/net/dccp/ccid.c +++ b/net/dccp/ccid.c @@ -55,9 +55,9 @@ static inline void ccids_read_unlock(void) #define ccids_read_unlock() do { } while(0) #endif -static kmem_cache_t *ccid_kmem_cache_create(int obj_size, const char *fmt,...) +static struct kmem_cache *ccid_kmem_cache_create(int obj_size, const char *fmt,...) { - kmem_cache_t *slab; + struct kmem_cache *slab; char slab_name_fmt[32], *slab_name; va_list args; @@ -75,7 +75,7 @@ static kmem_cache_t *ccid_kmem_cache_create(int obj_size, const char *fmt,...) return slab; } -static void ccid_kmem_cache_destroy(kmem_cache_t *slab) +static void ccid_kmem_cache_destroy(struct kmem_cache *slab) { if (slab != NULL) { const char *name = kmem_cache_name(slab); diff --git a/net/dccp/ccid.h b/net/dccp/ccid.h index f7eb6c61341..c65cb2453e4 100644 --- a/net/dccp/ccid.h +++ b/net/dccp/ccid.h @@ -27,9 +27,9 @@ struct ccid_operations { unsigned char ccid_id; const char *ccid_name; struct module *ccid_owner; - kmem_cache_t *ccid_hc_rx_slab; + struct kmem_cache *ccid_hc_rx_slab; __u32 ccid_hc_rx_obj_size; - kmem_cache_t *ccid_hc_tx_slab; + struct kmem_cache *ccid_hc_tx_slab; __u32 ccid_hc_tx_obj_size; int (*ccid_hc_rx_init)(struct ccid *ccid, struct sock *sk); int (*ccid_hc_tx_init)(struct ccid *ccid, struct sock *sk); @@ -43,8 +43,6 @@ struct ccid_operations { unsigned char* value); int (*ccid_hc_rx_insert_options)(struct sock *sk, struct sk_buff *skb); - int (*ccid_hc_tx_insert_options)(struct sock *sk, - struct sk_buff *skb); void (*ccid_hc_tx_packet_recv)(struct sock *sk, struct sk_buff *skb); int (*ccid_hc_tx_parse_options)(struct sock *sk, @@ -52,9 +50,9 @@ struct ccid_operations { unsigned char len, u16 idx, unsigned char* value); int (*ccid_hc_tx_send_packet)(struct sock *sk, - struct sk_buff *skb, int len); - void (*ccid_hc_tx_packet_sent)(struct sock *sk, int more, - int len); + struct sk_buff *skb); + void (*ccid_hc_tx_packet_sent)(struct sock *sk, + int more, unsigned int len); void (*ccid_hc_rx_get_info)(struct sock *sk, struct tcp_info *info); void (*ccid_hc_tx_get_info)(struct sock *sk, @@ -94,16 +92,16 @@ extern void ccid_hc_rx_delete(struct ccid *ccid, struct sock *sk); extern void ccid_hc_tx_delete(struct ccid *ccid, struct sock *sk); static inline int ccid_hc_tx_send_packet(struct ccid *ccid, struct sock *sk, - struct sk_buff *skb, int len) + struct sk_buff *skb) { int rc = 0; if (ccid->ccid_ops->ccid_hc_tx_send_packet != NULL) - rc = ccid->ccid_ops->ccid_hc_tx_send_packet(sk, skb, len); + rc = ccid->ccid_ops->ccid_hc_tx_send_packet(sk, skb); return rc; } static inline void ccid_hc_tx_packet_sent(struct ccid *ccid, struct sock *sk, - int more, int len) + int more, unsigned int len) { if (ccid->ccid_ops->ccid_hc_tx_packet_sent != NULL) ccid->ccid_ops->ccid_hc_tx_packet_sent(sk, more, len); @@ -146,14 +144,6 @@ static inline int ccid_hc_rx_parse_options(struct ccid *ccid, struct sock *sk, return rc; } -static inline int ccid_hc_tx_insert_options(struct ccid *ccid, struct sock *sk, - struct sk_buff *skb) -{ - if (ccid->ccid_ops->ccid_hc_tx_insert_options != NULL) - return ccid->ccid_ops->ccid_hc_tx_insert_options(sk, skb); - return 0; -} - static inline int ccid_hc_rx_insert_options(struct ccid *ccid, struct sock *sk, struct sk_buff *skb) { diff --git a/net/dccp/ccids/Kconfig b/net/dccp/ccids/Kconfig index 32752f75044..80f46988769 100644 --- a/net/dccp/ccids/Kconfig +++ b/net/dccp/ccids/Kconfig @@ -22,19 +22,26 @@ config IP_DCCP_CCID2 for lost packets, would prefer CCID 2 to CCID 3. On-line games may also prefer CCID 2. - CCID 2 is further described in: - http://www.icir.org/kohler/dccp/draft-ietf-dccp-ccid2-10.txt + CCID 2 is further described in RFC 4341, + http://www.ietf.org/rfc/rfc4341.txt - This text was extracted from: - http://www.icir.org/kohler/dccp/draft-ietf-dccp-spec-13.txt + This text was extracted from RFC 4340 (sec. 10.1), + http://www.ietf.org/rfc/rfc4340.txt + + To compile this CCID as a module, choose M here: the module will be + called dccp_ccid2. If in doubt, say M. config IP_DCCP_CCID2_DEBUG - bool "CCID2 debug" + bool "CCID2 debugging messages" depends on IP_DCCP_CCID2 ---help--- - Enable CCID2 debug messages. + Enable CCID2-specific debugging messages. + + When compiling CCID2 as a module, this debugging output can + additionally be toggled by setting the ccid2_debug module + parameter to 0 or 1. If in doubt, say N. @@ -53,20 +60,66 @@ config IP_DCCP_CCID3 suitable than CCID 2 for applications such streaming media where a relatively smooth sending rate is of importance. - CCID 3 is further described in: - - http://www.icir.org/kohler/dccp/draft-ietf-dccp-ccid3-11.txt. + CCID 3 is further described in RFC 4342, + http://www.ietf.org/rfc/rfc4342.txt The TFRC congestion control algorithms were initially described in RFC 3448. - This text was extracted from: - http://www.icir.org/kohler/dccp/draft-ietf-dccp-spec-13.txt + This text was extracted from RFC 4340 (sec. 10.2), + http://www.ietf.org/rfc/rfc4340.txt + To compile this CCID as a module, choose M here: the module will be + called dccp_ccid3. + If in doubt, say M. config IP_DCCP_TFRC_LIB depends on IP_DCCP_CCID3 def_tristate IP_DCCP_CCID3 +config IP_DCCP_CCID3_DEBUG + bool "CCID3 debugging messages" + depends on IP_DCCP_CCID3 + ---help--- + Enable CCID3-specific debugging messages. + + When compiling CCID3 as a module, this debugging output can + additionally be toggled by setting the ccid3_debug module + parameter to 0 or 1. + + If in doubt, say N. + +config IP_DCCP_CCID3_RTO + int "Use higher bound for nofeedback timer" + default 100 + depends on IP_DCCP_CCID3 && EXPERIMENTAL + ---help--- + Use higher lower bound for nofeedback timer expiration. + + The TFRC nofeedback timer normally expires after the maximum of 4 + RTTs and twice the current send interval (RFC 3448, 4.3). On LANs + with a small RTT this can mean a high processing load and reduced + performance, since then the nofeedback timer is triggered very + frequently. + + This option enables to set a higher lower bound for the nofeedback + value. Values in units of milliseconds can be set here. + + A value of 0 disables this feature by enforcing the value specified + in RFC 3448. The following values have been suggested as bounds for + experimental use: + * 16-20ms to match the typical multimedia inter-frame interval + * 100ms as a reasonable compromise [default] + * 1000ms corresponds to the lower TCP RTO bound (RFC 2988, 2.4) + + The default of 100ms is a compromise between a large value for + efficient DCCP implementations, and a small value to avoid disrupting + the network in times of congestion. + + The purpose of the nofeedback timer is to slow DCCP down when there + is serious network congestion: experimenting with larger values should + therefore not be performed on WANs. + + endmenu diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c index 2efb505aeb3..fd38b05d6f7 100644 --- a/net/dccp/ccids/ccid2.c +++ b/net/dccp/ccids/ccid2.c @@ -23,7 +23,7 @@ */ /* - * This implementation should follow: draft-ietf-dccp-ccid2-10.txt + * This implementation should follow RFC 4341 * * BUGS: * - sequence number wrapping @@ -33,18 +33,11 @@ #include "../dccp.h" #include "ccid2.h" -static int 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); \ - } while (0) -#else -#define ccid2_pr_debug(format, a...) -#endif +static int ccid2_debug; +#define ccid2_pr_debug(format, a...) DCCP_PR_DEBUG(ccid2_debug, format, ##a) -#ifdef CONFIG_IP_DCCP_CCID2_DEBUG static void ccid2_hc_tx_check_sanity(const struct ccid2_hc_tx_sock *hctx) { int len = 0; @@ -86,7 +79,8 @@ static void ccid2_hc_tx_check_sanity(const struct ccid2_hc_tx_sock *hctx) BUG_ON(len != hctx->ccid2hctx_seqbufc * CCID2_SEQBUF_LEN); } #else -#define ccid2_hc_tx_check_sanity(hctx) do {} while (0) +#define ccid2_pr_debug(format, a...) +#define ccid2_hc_tx_check_sanity(hctx) #endif static int ccid2_hc_tx_alloc_seq(struct ccid2_hc_tx_sock *hctx, int num, @@ -131,8 +125,7 @@ static int ccid2_hc_tx_alloc_seq(struct ccid2_hc_tx_sock *hctx, int num, return 0; } -static int ccid2_hc_tx_send_packet(struct sock *sk, - struct sk_buff *skb, int len) +static int ccid2_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb) { struct ccid2_hc_tx_sock *hctx; @@ -274,7 +267,7 @@ static void ccid2_start_rto_timer(struct sock *sk) jiffies + hctx->ccid2hctx_rto); } -static void ccid2_hc_tx_packet_sent(struct sock *sk, int more, int len) +static void ccid2_hc_tx_packet_sent(struct sock *sk, int more, unsigned int len) { struct dccp_sock *dp = dccp_sk(sk); struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); @@ -352,14 +345,14 @@ static void ccid2_hc_tx_packet_sent(struct sock *sk, int more, int len) #ifdef CONFIG_IP_DCCP_CCID2_DEBUG ccid2_pr_debug("pipe=%d\n", hctx->ccid2hctx_pipe); - ccid2_pr_debug("Sent: seq=%llu\n", seq); + ccid2_pr_debug("Sent: seq=%llu\n", (unsigned long long)seq); do { struct ccid2_seq *seqp = hctx->ccid2hctx_seqt; while (seqp != hctx->ccid2hctx_seqh) { ccid2_pr_debug("out seq=%llu acked=%d time=%lu\n", - seqp->ccid2s_seq, seqp->ccid2s_acked, - seqp->ccid2s_sent); + (unsigned long long)seqp->ccid2s_seq, + seqp->ccid2s_acked, seqp->ccid2s_sent); seqp = seqp->ccid2s_next; } } while (0); @@ -426,7 +419,7 @@ static int ccid2_ackvector(struct sock *sk, struct sk_buff *skb, int offset, return -1; out_invalid_option: - BUG_ON(1); /* should never happen... options were previously parsed ! */ + DCCP_BUG("Invalid option - this should not happen (previous parsing)!"); return -1; } @@ -480,7 +473,8 @@ static inline void ccid2_new_ack(struct sock *sk, /* first measurement */ if (hctx->ccid2hctx_srtt == -1) { ccid2_pr_debug("R: %lu Time=%lu seq=%llu\n", - r, jiffies, seqp->ccid2s_seq); + r, jiffies, + (unsigned long long)seqp->ccid2s_seq); ccid2_change_srtt(hctx, r); hctx->ccid2hctx_rttvar = r >> 1; } else { @@ -524,8 +518,8 @@ static inline void ccid2_new_ack(struct sock *sk, hctx->ccid2hctx_lastrtt = jiffies; ccid2_pr_debug("srtt: %ld rttvar: %ld rto: %ld (HZ=%d) R=%lu\n", - hctx->ccid2hctx_srtt, hctx->ccid2hctx_rttvar, - hctx->ccid2hctx_rto, HZ, r); + hctx->ccid2hctx_srtt, hctx->ccid2hctx_rttvar, + hctx->ccid2hctx_rto, HZ, r); hctx->ccid2hctx_sent = 0; } @@ -618,7 +612,17 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) } ackno = DCCP_SKB_CB(skb)->dccpd_ack_seq; - seqp = hctx->ccid2hctx_seqh->ccid2s_prev; + if (after48(ackno, hctx->ccid2hctx_high_ack)) + hctx->ccid2hctx_high_ack = ackno; + + seqp = hctx->ccid2hctx_seqt; + while (before48(seqp->ccid2s_seq, ackno)) { + seqp = seqp->ccid2s_next; + if (seqp == hctx->ccid2hctx_seqh) { + seqp = hctx->ccid2hctx_seqh->ccid2s_prev; + break; + } + } /* If in slow-start, cwnd can increase at most Ack Ratio / 2 packets for * this single ack. I round up. @@ -636,8 +640,9 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) u64 ackno_end_rl; dccp_set_seqno(&ackno_end_rl, ackno - rl); - ccid2_pr_debug("ackvec start:%llu end:%llu\n", ackno, - ackno_end_rl); + ccid2_pr_debug("ackvec start:%llu end:%llu\n", + (unsigned long long)ackno, + (unsigned long long)ackno_end_rl); /* if the seqno we are analyzing is larger than the * current ackno, then move towards the tail of our * seqnos. @@ -662,9 +667,9 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) /* new packet received or marked */ if (state != DCCP_ACKVEC_STATE_NOT_RECEIVED && !seqp->ccid2s_acked) { - if (state == + if (state == DCCP_ACKVEC_STATE_ECN_MARKED) { - ccid2_congestion_event(hctx, + ccid2_congestion_event(hctx, seqp); } else ccid2_new_ack(sk, seqp, @@ -672,7 +677,7 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) seqp->ccid2s_acked = 1; ccid2_pr_debug("Got ack for %llu\n", - seqp->ccid2s_seq); + (unsigned long long)seqp->ccid2s_seq); ccid2_hc_tx_dec_pipe(sk); } if (seqp == hctx->ccid2hctx_seqt) { @@ -695,7 +700,14 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) /* The state about what is acked should be correct now * Check for NUMDUPACK */ - seqp = hctx->ccid2hctx_seqh->ccid2s_prev; + seqp = hctx->ccid2hctx_seqt; + while (before48(seqp->ccid2s_seq, hctx->ccid2hctx_high_ack)) { + seqp = seqp->ccid2s_next; + if (seqp == hctx->ccid2hctx_seqh) { + seqp = hctx->ccid2hctx_seqh->ccid2s_prev; + break; + } + } done = 0; while (1) { if (seqp->ccid2s_acked) { @@ -718,7 +730,7 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) while (1) { |