diff options
Diffstat (limited to 'net/dccp')
36 files changed, 4813 insertions, 3824 deletions
diff --git a/net/dccp/Kconfig b/net/dccp/Kconfig index 7aa2a7acc7e..8c0ef71bed2 100644 --- a/net/dccp/Kconfig +++ b/net/dccp/Kconfig @@ -1,7 +1,6 @@ menuconfig IP_DCCP - tristate "The DCCP Protocol (EXPERIMENTAL)" - depends on INET && EXPERIMENTAL - select IP_DCCP_CCID2 + tristate "The DCCP Protocol" + depends on INET ---help--- Datagram Congestion Control Protocol (RFC 4340) @@ -25,9 +24,6 @@ config INET_DCCP_DIAG def_tristate y if (IP_DCCP = y && INET_DIAG = y) def_tristate m -config IP_DCCP_ACKVEC - bool - source "net/dccp/ccids/Kconfig" menu "DCCP Kernel Hacking" @@ -53,7 +49,9 @@ config NET_DCCPPROBE what was just said, you don't need it: say N. Documentation on how to use DCCP connection probing can be found - at http://linux-net.osdl.org/index.php/DccpProbe + at: + + http://www.linuxfoundation.org/collaborate/workgroups/networking/dccpprobe To compile this code as a module, choose M here: the module will be called dccp_probe. diff --git a/net/dccp/Makefile b/net/dccp/Makefile index f4f8793aaff..5c8362b037e 100644 --- a/net/dccp/Makefile +++ b/net/dccp/Makefile @@ -1,6 +1,17 @@ obj-$(CONFIG_IP_DCCP) += dccp.o dccp_ipv4.o -dccp-y := ccid.o feat.o input.o minisocks.o options.o output.o proto.o timer.o +dccp-y := ccid.o feat.o input.o minisocks.o options.o output.o proto.o timer.o \ + qpolicy.o +# +# CCID algorithms to be used by dccp.ko +# +# CCID-2 is default (RFC 4340, p. 77) and has Ack Vectors as dependency +dccp-y += ccids/ccid2.o ackvec.o +dccp-$(CONFIG_IP_DCCP_CCID3) += ccids/ccid3.o +dccp-$(CONFIG_IP_DCCP_TFRC_LIB) += ccids/lib/tfrc.o \ + ccids/lib/tfrc_equation.o \ + ccids/lib/packet_history.o \ + ccids/lib/loss_interval.o dccp_ipv4-y := ipv4.o @@ -8,8 +19,6 @@ dccp_ipv4-y := ipv4.o obj-$(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 obj-$(CONFIG_NET_DCCPPROBE) += dccp_probe.o @@ -17,5 +26,3 @@ dccp-$(CONFIG_SYSCTL) += sysctl.o dccp_diag-y := diag.o dccp_probe-y := probe.o - -obj-y += ccids/ diff --git a/net/dccp/ackvec.c b/net/dccp/ackvec.c index 6de4bd195d2..ba07824af4c 100644 --- a/net/dccp/ackvec.c +++ b/net/dccp/ackvec.c @@ -1,470 +1,376 @@ /* * 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 <acme@ghostprotocols.net> * * This program is free software; you can redistribute it and/or modify it * under the terms of the GNU General Public License as published by the * Free Software Foundation; version 2 of the License; */ - -#include "ackvec.h" #include "dccp.h" - -#include <linux/dccp.h> -#include <linux/init.h> -#include <linux/errno.h> #include <linux/kernel.h> -#include <linux/skbuff.h> #include <linux/slab.h> - -#include <net/sock.h> +#include <linux/export.h> 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 (avr != NULL) - INIT_LIST_HEAD(&avr->avr_node); - - return avr; + if (av != NULL) { + av->av_buf_head = av->av_buf_tail = DCCPAV_MAX_ACKVEC_LEN - 1; + INIT_LIST_HEAD(&av->av_records); + } + return av; } -static void dccp_ackvec_record_delete(struct dccp_ackvec_record *avr) +static void dccp_ackvec_purge_records(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); + struct dccp_ackvec_record *cur, *next; + + 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_insert_avr(struct dccp_ackvec *av, - struct dccp_ackvec_record *avr) +void dccp_ackvec_free(struct dccp_ackvec *av) { - /* - * AVRs are sorted by seqno. Since we are sending them in order, we - * just add the AVR at the head of the list. - * -sorbo. - */ - if (!list_empty(&av->av_records)) { - const struct dccp_ackvec_record *head = - list_entry(av->av_records.next, - struct dccp_ackvec_record, - avr_node); - BUG_ON(before48(avr->avr_ack_seqno, head->avr_ack_seqno)); + if (likely(av != NULL)) { + dccp_ackvec_purge_records(av); + kmem_cache_free(dccp_ackvec_slab, av); } - - list_add(&avr->avr_node, &av->av_records); } -int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb) +/** + * dccp_ackvec_update_records - Record information about sent Ack Vectors + * @av: Ack Vector records to update + * @seqno: Sequence number of the packet carrying the Ack Vector just sent + * @nonce_sum: The sum of all buffer nonces contained in the Ack Vector + */ +int dccp_ackvec_update_records(struct dccp_ackvec *av, u64 seqno, u8 nonce_sum) { - struct dccp_sock *dp = dccp_sk(sk); - struct dccp_ackvec *av = dp->dccps_hc_rx_ackvec; - /* Figure out how many options do we need to represent the ackvec */ - const u16 nr_opts = DIV_ROUND_UP(av->av_vec_len, DCCP_MAX_ACKVEC_OPT_LEN); - u16 len = av->av_vec_len + 2 * nr_opts, i; - u32 elapsed_time; - 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; - - DCCP_SKB_CB(skb)->dccpd_opt_len += len; - - 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; - - for (i = 0; i < nr_opts; ++i) { - int copylen = len; - - if (len > DCCP_MAX_ACKVEC_OPT_LEN) - copylen = DCCP_MAX_ACKVEC_OPT_LEN; - - *to++ = DCCPO_ACK_VECTOR_0; - *to++ = copylen + 2; - - /* 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->av_buf; - } - - memcpy(to, from, copylen); - from += copylen; - to += copylen; - len -= copylen; - } + return -ENOBUFS; + avr->avr_ack_seqno = seqno; + avr->avr_ack_ptr = av->av_buf_head; + avr->avr_ack_ackno = av->av_buf_ackno; + avr->avr_ack_nonce = nonce_sum; + avr->avr_ack_runlen = dccp_ackvec_runlen(av->av_buf + av->av_buf_head); /* - * 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. + * When the buffer overflows, we keep no more than one record. This is + * the simplest way of disambiguating sender-Acks dating from before the + * overflow from sender-Acks which refer to after the overflow; a simple + * solution is preferable here since we are handling an exception. */ - 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; - - dccp_ackvec_insert_avr(av, avr); + if (av->av_overflow) + dccp_ackvec_purge_records(av); + /* + * Since GSS is incremented for each packet, the list is automatically + * arranged in descending order of @ack_seqno. + */ + list_add(&avr->avr_node, &av->av_records); - dccp_pr_debug("%s ACK Vector 0, len=%d, ack_seqno=%llu, " - "ack_ackno=%llu\n", - dccp_role(sk), avr->avr_sent_len, + dccp_pr_debug("Added Vector, ack_seqno=%llu, ack_ackno=%llu (rl=%u)\n", (unsigned long long)avr->avr_ack_seqno, - (unsigned long long)avr->avr_ack_ackno); + (unsigned long long)avr->avr_ack_ackno, + avr->avr_ack_runlen); return 0; } -struct dccp_ackvec *dccp_ackvec_alloc(const gfp_t priority) +static struct dccp_ackvec_record *dccp_ackvec_lookup(struct list_head *av_list, + const u64 ackno) { - 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); + 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 av; + return NULL; } -void dccp_ackvec_free(struct dccp_ackvec *av) +/* + * Buffer index and length computation using modulo-buffersize arithmetic. + * Note that, as pointers move from right to left, head is `before' tail. + */ +static inline u16 __ackvec_idx_add(const u16 a, const u16 b) { - 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); + return (a + b) % DCCPAV_MAX_ACKVEC_LEN; } -static inline u8 dccp_ackvec_state(const struct dccp_ackvec *av, - const u32 index) +static inline u16 __ackvec_idx_sub(const u16 a, const u16 b) { - return av->av_buf[index] & DCCP_ACKVEC_STATE_MASK; + return __ackvec_idx_add(a, DCCPAV_MAX_ACKVEC_LEN - b); } -static inline u8 dccp_ackvec_len(const struct dccp_ackvec *av, - const u32 index) +u16 dccp_ackvec_buflen(const struct dccp_ackvec *av) { - return av->av_buf[index] & DCCP_ACKVEC_LEN_MASK; + if (unlikely(av->av_overflow)) + return DCCPAV_MAX_ACKVEC_LEN; + return __ackvec_idx_sub(av->av_buf_tail, av->av_buf_head); } -/* - * 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; - * this simplifies table updates if one of the missing packets arrives. +/** + * dccp_ackvec_update_old - Update previous state as per RFC 4340, 11.4.1 + * @av: non-empty buffer to update + * @distance: negative or zero distance of @seqno from buf_ackno downward + * @seqno: the (old) sequence number whose record is to be updated + * @state: state in which packet carrying @seqno was received */ -static inline int dccp_ackvec_set_buf_head_state(struct dccp_ackvec *av, - const unsigned int packets, - const unsigned char state) +static void dccp_ackvec_update_old(struct dccp_ackvec *av, s64 distance, + u64 seqno, enum dccp_ackvec_states state) { - unsigned int gap; - long new_head; + u16 ptr = av->av_buf_head; - if (av->av_vec_len + packets > DCCP_MAX_ACKVEC_LEN) - return -ENOBUFS; + BUG_ON(distance > 0); + if (unlikely(dccp_ackvec_is_empty(av))) + return; - gap = packets - 1; - new_head = av->av_buf_head - packets; + do { + u8 runlen = dccp_ackvec_runlen(av->av_buf + ptr); - if (new_head < 0) { - if (gap > 0) { - memset(av->av_buf, DCCP_ACKVEC_STATE_NOT_RECEIVED, - gap + new_head + 1); - gap = -new_head; + if (distance + runlen >= 0) { + /* + * Only update the state if packet has not been received + * yet. This is OK as per the second table in RFC 4340, + * 11.4.1; i.e. here we are using the following table: + * RECEIVED + * 0 1 3 + * S +---+---+---+ + * T 0 | 0 | 0 | 0 | + * O +---+---+---+ + * R 1 | 1 | 1 | 1 | + * E +---+---+---+ + * D 3 | 0 | 1 | 3 | + * +---+---+---+ + * The "Not Received" state was set by reserve_seats(). + */ + if (av->av_buf[ptr] == DCCPAV_NOT_RECEIVED) + av->av_buf[ptr] = state; + else + dccp_pr_debug("Not changing %llu state to %u\n", + (unsigned long long)seqno, state); + break; } - new_head += DCCP_MAX_ACKVEC_LEN; - } - av->av_buf_head = new_head; + distance += runlen + 1; + ptr = __ackvec_idx_add(ptr, 1); - if (gap > 0) - memset(av->av_buf + av->av_buf_head + 1, - DCCP_ACKVEC_STATE_NOT_RECEIVED, gap); + } while (ptr != av->av_buf_tail); +} - av->av_buf[av->av_buf_head] = state; - av->av_vec_len += packets; - return 0; +/* Mark @num entries after buf_head as "Not yet received". */ +static void dccp_ackvec_reserve_seats(struct dccp_ackvec *av, u16 num) +{ + u16 start = __ackvec_idx_add(av->av_buf_head, 1), + len = DCCPAV_MAX_ACKVEC_LEN - start; + + /* check for buffer wrap-around */ + if (num > len) { + memset(av->av_buf + start, DCCPAV_NOT_RECEIVED, len); + start = 0; + num -= len; + } + if (num) + memset(av->av_buf + start, DCCPAV_NOT_RECEIVED, num); } -/* - * Implements the RFC 4340, Appendix A +/** + * dccp_ackvec_add_new - Record one or more new entries in Ack Vector buffer + * @av: container of buffer to update (can be empty or non-empty) + * @num_packets: number of packets to register (must be >= 1) + * @seqno: sequence number of the first packet in @num_packets + * @state: state in which packet carrying @seqno was received */ -int dccp_ackvec_add(struct dccp_ackvec *av, const struct sock *sk, - const u64 ackno, const u8 state) +static void dccp_ackvec_add_new(struct dccp_ackvec *av, u32 num_packets, + u64 seqno, enum dccp_ackvec_states state) { - /* - * 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 - * vectors, when we will free up space in av_buf. - * - * We may well decide to do buffer compression, etc, but for now lets - * just drop. - * - * 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 - * HC-Receiver's acknowledgements are not reaching the HC-Sender, - * or when the HC-Sender is forgetting to acknowledge those acks - * (so the HC-Receiver is unable to clean up old state). In this - * case, the HC-Receiver should either compress the buffer (by - * increasing run lengths when possible), transfer its state to - * a larger buffer, or, as a last resort, drop all received - * packets, without processing them whatsoever, until its buffer - * shrinks again. - */ + u32 num_cells = num_packets; - /* See if this is the first ackno being inserted */ - if (av->av_vec_len == 0) { - av->av_buf[av->av_buf_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); + if (num_packets > DCCPAV_BURST_THRESH) { + u32 lost_packets = num_packets - 1; + DCCP_WARN("Warning: large burst loss (%u)\n", lost_packets); /* - * Look if the state of this packet is the same as the - * previous ackno and if so if we can bump the head len. + * We received 1 packet and have a loss of size "num_packets-1" + * which we squeeze into num_cells-1 rather than reserving an + * entire byte for each lost packet. + * The reason is that the vector grows in O(burst_length); when + * it grows too large there will no room left for the payload. + * This is a trade-off: if a few packets out of the burst show + * up later, their state will not be changed; it is simply too + * costly to reshuffle/reallocate/copy the buffer each time. + * Should such problems persist, we will need to switch to a + * different underlying data structure. */ - 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]++; - else if (dccp_ackvec_set_buf_head_state(av, delta, state)) - return -ENOBUFS; - } else { - /* - * A.1.2. Old Packets - * - * 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->av_buf_ackno); - u32 index = av->av_buf_head; + for (num_packets = num_cells = 1; lost_packets; ++num_cells) { + u8 len = min(lost_packets, (u32)DCCPAV_MAX_RUNLEN); - while (1) { - const u8 len = dccp_ackvec_len(av, index); - const u8 state = dccp_ackvec_state(av, index); - /* - * valid packets not yet in av_buf have a reserved - * entry, with a len equal to 0. - */ - if (state == DCCP_ACKVEC_STATE_NOT_RECEIVED && - len == 0 && delta == 0) { /* Found our - reserved seat! */ - dccp_pr_debug("Found %llu reserved seat!\n", - (unsigned long long)ackno); - av->av_buf[index] = state; - goto out; - } - /* len == 0 means one packet */ - if (delta < len + 1) - goto out_duplicate; - - delta -= len + 1; - if (++index == DCCP_MAX_ACKVEC_LEN) - index = 0; + av->av_buf_head = __ackvec_idx_sub(av->av_buf_head, 1); + av->av_buf[av->av_buf_head] = DCCPAV_NOT_RECEIVED | len; + + lost_packets -= len; } } - av->av_buf_ackno = ackno; - av->av_time = ktime_get_real(); -out: - return 0; - -out_duplicate: - /* Duplicate packet */ - dccp_pr_debug("Received a dup or already considered lost " - "packet: %llu\n", (unsigned long long)ackno); - return -EILSEQ; -} - -#ifdef CONFIG_IP_DCCP_DEBUG -void dccp_ackvector_print(const u64 ackno, const unsigned char *vector, int len) -{ - dccp_pr_debug_cat("ACK vector len=%d, ackno=%llu |", len, - (unsigned long long)ackno); + if (num_cells + dccp_ackvec_buflen(av) >= DCCPAV_MAX_ACKVEC_LEN) { + DCCP_CRIT("Ack Vector buffer overflow: dropping old entries\n"); + av->av_overflow = true; + } - while (len--) { - const u8 state = (*vector & DCCP_ACKVEC_STATE_MASK) >> 6; - const u8 rl = *vector & DCCP_ACKVEC_LEN_MASK; + av->av_buf_head = __ackvec_idx_sub(av->av_buf_head, num_packets); + if (av->av_overflow) + av->av_buf_tail = av->av_buf_head; - dccp_pr_debug_cat("%d,%d|", state, rl); - ++vector; - } + av->av_buf[av->av_buf_head] = state; + av->av_buf_ackno = seqno; - dccp_pr_debug_cat("\n"); + if (num_packets > 1) + dccp_ackvec_reserve_seats(av, num_packets - 1); } -void dccp_ackvec_print(const struct dccp_ackvec *av) +/** + * dccp_ackvec_input - Register incoming packet in the buffer + */ +void dccp_ackvec_input(struct dccp_ackvec *av, struct sk_buff *skb) { - dccp_ackvector_print(av->av_buf_ackno, - av->av_buf + av->av_buf_head, - av->av_vec_len); -} -#endif + u64 seqno = DCCP_SKB_CB(skb)->dccpd_seq; + enum dccp_ackvec_states state = DCCPAV_RECEIVED; -static void dccp_ackvec_throw_record(struct dccp_ackvec *av, - struct dccp_ackvec_record *avr) -{ - struct dccp_ackvec_record *next; + if (dccp_ackvec_is_empty(av)) { + dccp_ackvec_add_new(av, 1, seqno, state); + av->av_tail_ackno = seqno; - /* sort out vector length */ - 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_buf_head + avr->avr_ack_ptr; + } else { + s64 num_packets = dccp_delta_seqno(av->av_buf_ackno, seqno); + u8 *current_head = av->av_buf + av->av_buf_head; - /* 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); - } -} + if (num_packets == 1 && + dccp_ackvec_state(current_head) == state && + dccp_ackvec_runlen(current_head) < DCCPAV_MAX_RUNLEN) { -void dccp_ackvec_check_rcv_ackno(struct dccp_ackvec *av, struct sock *sk, - const u64 ackno) -{ - struct dccp_ackvec_record *avr; + *current_head += 1; + av->av_buf_ackno = seqno; - /* - * If we traverse backwards, it should be faster when we have large - * windows. We will be receiving ACKs for stuff we sent a while back - * -sorbo. - */ - list_for_each_entry_reverse(avr, &av->av_records, avr_node) { - 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, - (unsigned long long)avr->avr_ack_seqno, - (unsigned long long)avr->avr_ack_ackno); - dccp_ackvec_throw_record(av, avr); - break; - } else if (avr->avr_ack_seqno > ackno) - break; /* old news */ + } else if (num_packets > 0) { + dccp_ackvec_add_new(av, num_packets, seqno, state); + } else { + dccp_ackvec_update_old(av, num_packets, seqno, state); + } } } -static void dccp_ackvec_check_rcv_ackvector(struct dccp_ackvec *av, - struct sock *sk, u64 *ackno, - const unsigned char len, - const unsigned char *vector) +/** + * 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) { - unsigned char i; - struct dccp_ackvec_record *avr; + struct dccp_ackvec_record *avr, *next; + u8 runlen_now, eff_runlen; + s64 delta; - /* Check if we actually sent an ACK vector */ - if (list_empty(&av->av_records)) + 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; - i = len; + runlen_now = dccp_ackvec_runlen(av->av_buf + avr->avr_ack_ptr); /* - * XXX - * I think it might be more efficient to work backwards. See comment on - * rcv_ackno. -sorbo. + * 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. */ - avr = list_entry(av->av_records.next, struct dccp_ackvec_record, avr_node); - while (i--) { - const u8 rl = *vector & DCCP_ACKVEC_LEN_MASK; - u64 ackno_end_rl; + if (runlen_now > eff_runlen) { - dccp_set_seqno(&ackno_end_rl, *ackno - rl); + 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; /* - * If our AVR sequence number is greater than the ack, go - * forward in the AVR list until it is not so. + * 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. */ - list_for_each_entry_from(avr, &av->av_records, avr_node) { - if (!after48(avr->avr_ack_seqno, *ackno)) - goto found; - } - /* End of the av_records list, not found, exit */ - 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) { - dccp_pr_debug("%s ACK vector 0, len=%d, " - "ack_seqno=%llu, ack_ackno=%llu, " - "ACKED!\n", - dccp_role(sk), len, - (unsigned long long) - avr->avr_ack_seqno, - (unsigned long long) - avr->avr_ack_ackno); - dccp_ackvec_throw_record(av, avr); - break; - } - /* - * If it wasn't received, continue scanning... we might - * find another one. - */ - } + 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); - dccp_set_seqno(ackno, ackno_end_rl - 1); - ++vector; +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 dccp_ackvec_parse(struct sock *sk, const struct sk_buff *skb, - u64 *ackno, const u8 opt, const u8 *value, const u8 len) +/* + * Routines to keep track of Ack Vectors received in an skb + */ +int dccp_ackvec_parsed_add(struct list_head *head, u8 *vec, u8 len, u8 nonce) { - if (len > DCCP_MAX_ACKVEC_OPT_LEN) - return -1; + struct dccp_ackvec_parsed *new = kmalloc(sizeof(*new), GFP_ATOMIC); + + if (new == NULL) + return -ENOBUFS; + new->vec = vec; + new->len = len; + new->nonce = nonce; - /* 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, - ackno, len, value); + list_add_tail(&new->node, head); return 0; } +EXPORT_SYMBOL_GPL(dccp_ackvec_parsed_add); + +void dccp_ackvec_parsed_cleanup(struct list_head *parsed_chunks) +{ + struct dccp_ackvec_parsed *cur, *next; + + list_for_each_entry_safe(cur, next, parsed_chunks, node) + kfree(cur); + INIT_LIST_HEAD(parsed_chunks); +} +EXPORT_SYMBOL_GPL(dccp_ackvec_parsed_cleanup); int __init dccp_ackvec_init(void) { @@ -474,10 +380,9 @@ 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 bcb64fb4ace..3284bfa988c 100644 --- a/net/dccp/ackvec.h +++ b/net/dccp/ackvec.h @@ -3,156 +3,136 @@ /* * 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 <acme@mandriva.com> - * * 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. */ +#include <linux/dccp.h> #include <linux/compiler.h> -#include <linux/ktime.h> #include <linux/list.h> #include <linux/types.h> -/* Read about the ECN nonce to see why it is 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) +/* + * 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. + * The maximum value is bounded by the u16 types for indices and functions. + */ +#define DCCPAV_NUM_ACKVECS 2 +#define DCCPAV_MAX_ACKVEC_LEN (DCCP_SINGLE_OPT_MAXLEN * DCCPAV_NUM_ACKVECS) -#define DCCP_ACKVEC_STATE_RECEIVED 0 -#define DCCP_ACKVEC_STATE_ECN_MARKED (1 << 6) -#define DCCP_ACKVEC_STATE_NOT_RECEIVED (3 << 6) +/* Estimated minimum average Ack Vector length - used for updating MPS */ +#define DCCPAV_MIN_OPTLEN 16 -#define DCCP_ACKVEC_STATE_MASK 0xC0 /* 11000000 */ -#define DCCP_ACKVEC_LEN_MASK 0x3F /* 00111111 */ +/* Threshold for coping with large bursts of losses */ +#define DCCPAV_BURST_THRESH (DCCPAV_MAX_ACKVEC_LEN / 8) -/** 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: +enum dccp_ackvec_states { + DCCPAV_RECEIVED = 0x00, + DCCPAV_ECN_MARKED = 0x40, + DCCPAV_RESERVED = 0x80, + DCCPAV_NOT_RECEIVED = 0xC0 +}; +#define DCCPAV_MAX_RUNLEN 0x3F + +static inline u8 dccp_ackvec_runlen(const u8 *cell) +{ + return *cell & DCCPAV_MAX_RUNLEN; +} + +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_tail_ackno: lowest 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_overflow: if 1 then buf_head == buf_tail indicates buffer wraparound + * @av_records: list of %dccp_ackvec_record (Ack Vectors sent previously) */ 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_vec_len; - u8 av_buf_nonce; - u8 av_ack_nonce; - u8 av_buf[DCCP_MAX_ACKVEC_LEN]; + u16 av_buf_tail; + u64 av_buf_ackno:48; + u64 av_tail_ackno:48; + bool av_buf_nonce[DCCPAV_NUM_ACKVECS]; + u8 av_overflow:1; + struct list_head av_records; }; -/** 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; -struct sk_buff; - -#ifdef CONFIG_IP_DCCP_ACKVEC -extern int dccp_ackvec_init(void); -extern void dccp_ackvec_exit(void); - -extern struct dccp_ackvec *dccp_ackvec_alloc(const gfp_t priority); -extern void dccp_ackvec_free(struct dccp_ackvec *av); - -extern int dccp_ackvec_add(struct dccp_ackvec *av, const struct sock *sk, - const u64 ackno, const u8 state); - -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, - u64 *ackno, const u8 opt, - const u8 *value, const u8 len); - -extern int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb); - -static inline int dccp_ackvec_pending(const struct dccp_ackvec *av) -{ - return av->av_vec_len; -} -#else /* CONFIG_IP_DCCP_ACKVEC */ -static inline int dccp_ackvec_init(void) -{ - return 0; -} - -static inline void dccp_ackvec_exit(void) -{ -} +int dccp_ackvec_init(void); +void dccp_ackvec_exit(void); -static inline struct dccp_ackvec *dccp_ackvec_alloc(const gfp_t priority) -{ - return NULL; -} +struct dccp_ackvec *dccp_ackvec_alloc(const gfp_t priority); +void dccp_ackvec_free(struct dccp_ackvec *av); -static inline void dccp_ackvec_free(struct dccp_ackvec *av) -{ -} +void dccp_ackvec_input(struct dccp_ackvec *av, struct sk_buff *skb); +int dccp_ackvec_update_records(struct dccp_ackvec *av, u64 seq, u8 sum); +void dccp_ackvec_clear_state(struct dccp_ackvec *av, const u64 ackno); +u16 dccp_ackvec_buflen(const struct dccp_ackvec *av); -static inline int dccp_ackvec_add(struct dccp_ackvec *av, const struct sock *sk, - const u64 ackno, const u8 state) +static inline bool dccp_ackvec_is_empty(const struct dccp_ackvec *av) { - return -1; + return av->av_overflow == 0 && av->av_buf_head == av->av_buf_tail; } -static inline void dccp_ackvec_check_rcv_ackno(struct dccp_ackvec *av, - struct sock *sk, const u64 ackno) -{ -} - -static inline int dccp_ackvec_parse(struct sock *sk, const struct sk_buff *skb, - const u64 *ackno, const u8 opt, - const u8 *value, const u8 len) -{ - return -1; -} - -static inline int dccp_insert_option_ackvec(const struct sock *sk, - const struct sk_buff *skb) -{ - return -1; -} +/** + * struct dccp_ackvec_parsed - Record offsets of Ack Vectors in skb + * @vec: start of vector (offset into skb) + * @len: length of @vec + * @nonce: whether @vec had an ECN nonce of 0 or 1 + * @node: FIFO - arranged in descending order of ack_ackno + * + * This structure is used by CCIDs to access Ack Vectors in a received skb. + */ +struct dccp_ackvec_parsed { + u8 *vec, + len, + nonce:1; + struct list_head node; +}; -static inline int dccp_ackvec_pending(const struct dccp_ackvec *av) -{ - return 0; -} -#endif /* CONFIG_IP_DCCP_ACKVEC */ +int dccp_ackvec_parsed_add(struct list_head *head, u8 *vec, u8 len, u8 nonce); +void dccp_ackvec_parsed_cleanup(struct list_head *parsed_chunks); #endif /* _ACKVEC_H */ diff --git a/net/dccp/ccid.c b/net/dccp/ccid.c index 4809753d12a..597557254dd 100644 --- a/net/dccp/ccid.c +++ b/net/dccp/ccid.c @@ -11,87 +11,101 @@ * published by the Free Software Foundation. */ +#include <linux/slab.h> + #include "ccid.h" +#include "ccids/lib/tfrc.h" -static struct ccid_operations *ccids[CCID_MAX]; -#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT) -static atomic_t ccids_lockct = ATOMIC_INIT(0); -static DEFINE_SPINLOCK(ccids_lock); +static struct ccid_operations *ccids[] = { + &ccid2_ops, +#ifdef CONFIG_IP_DCCP_CCID3 + &ccid3_ops, +#endif +}; -/* - * The strategy is: modifications ccids vector are short, do not sleep and - * veeery rare, but read access should be free of any exclusive locks. - */ -static void ccids_write_lock(void) +static struct ccid_operations *ccid_by_number(const u8 id) { - spin_lock(&ccids_lock); - while (atomic_read(&ccids_lockct) != 0) { - spin_unlock(&ccids_lock); - yield(); - spin_lock(&ccids_lock); - } + int i; + + for (i = 0; i < ARRAY_SIZE(ccids); i++) + if (ccids[i]->ccid_id == id) + return ccids[i]; + return NULL; } -static inline void ccids_write_unlock(void) +/* check that up to @array_len members in @ccid_array are supported */ +bool ccid_support_check(u8 const *ccid_array, u8 array_len) { - spin_unlock(&ccids_lock); + while (array_len > 0) + if (ccid_by_number(ccid_array[--array_len]) == NULL) + return false; + return true; } -static inline void ccids_read_lock(void) +/** + * ccid_get_builtin_ccids - Populate a list of built-in CCIDs + * @ccid_array: pointer to copy into + * @array_len: value to return length into + * + * This function allocates memory - caller must see that it is freed after use. + */ +int ccid_get_builtin_ccids(u8 **ccid_array, u8 *array_len) { - atomic_inc(&ccids_lockct); - smp_mb__after_atomic_inc(); - spin_unlock_wait(&ccids_lock); + *ccid_array = kmalloc(ARRAY_SIZE(ccids), gfp_any()); + if (*ccid_array == NULL) + return -ENOBUFS; + + for (*array_len = 0; *array_len < ARRAY_SIZE(ccids); *array_len += 1) + (*ccid_array)[*array_len] = ccids[*array_len]->ccid_id; + return 0; } -static inline void ccids_read_unlock(void) +int ccid_getsockopt_builtin_ccids(struct sock *sk, int len, + char __user *optval, int __user *optlen) { - atomic_dec(&ccids_lockct); -} + u8 *ccid_array, array_len; + int err = 0; -#else -#define ccids_write_lock() do { } while(0) -#define ccids_write_unlock() do { } while(0) -#define ccids_read_lock() do { } while(0) -#define ccids_read_unlock() do { } while(0) -#endif + if (ccid_get_builtin_ccids(&ccid_array, &array_len)) + return -ENOBUFS; + + if (put_user(array_len, optlen)) + err = -EFAULT; + else if (len > 0 && copy_to_user(optval, ccid_array, + len > array_len ? array_len : len)) + err = -EFAULT; -static struct kmem_cache *ccid_kmem_cache_create(int obj_size, const char *fmt,...) + kfree(ccid_array); + return err; +} + +static struct kmem_cache *ccid_kmem_cache_create(int obj_size, char *slab_name_fmt, const char *fmt,...) { struct kmem_cache *slab; - char slab_name_fmt[32], *slab_name; va_list args; va_start(args, fmt); - vsnprintf(slab_name_fmt, sizeof(slab_name_fmt), fmt, args); + vsnprintf(slab_name_fmt, CCID_SLAB_NAME_LENGTH, fmt, args); va_end(args); - slab_name = kstrdup(slab_name_fmt, GFP_KERNEL); - if (slab_name == NULL) - return NULL; - slab = kmem_cache_create(slab_name, sizeof(struct ccid) + obj_size, 0, + slab = kmem_cache_create(slab_name_fmt, sizeof(struct ccid) + obj_size, 0, SLAB_HWCACHE_ALIGN, NULL); - if (slab == NULL) - kfree(slab_name); return slab; } static void ccid_kmem_cache_destroy(struct kmem_cache *slab) { - if (slab != NULL) { - const char *name = kmem_cache_name(slab); - + if (slab != NULL) kmem_cache_destroy(slab); - kfree(name); - } } -int ccid_register(struct ccid_operations *ccid_ops) +static int ccid_activate(struct ccid_operations *ccid_ops) { int err = -ENOBUFS; ccid_ops->ccid_hc_rx_slab = ccid_kmem_cache_create(ccid_ops->ccid_hc_rx_obj_size, + ccid_ops->ccid_hc_rx_slab_name, "ccid%u_hc_rx_sock", ccid_ops->ccid_id); if (ccid_ops->ccid_hc_rx_slab == NULL) @@ -99,84 +113,46 @@ int ccid_register(struct ccid_operations *ccid_ops) ccid_ops->ccid_hc_tx_slab = ccid_kmem_cache_create(ccid_ops->ccid_hc_tx_obj_size, + ccid_ops->ccid_hc_tx_slab_name, "ccid%u_hc_tx_sock", ccid_ops->ccid_id); if (ccid_ops->ccid_hc_tx_slab == NULL) goto out_free_rx_slab; - ccids_write_lock(); - err = -EEXIST; - if (ccids[ccid_ops->ccid_id] == NULL) { - ccids[ccid_ops->ccid_id] = ccid_ops; - err = 0; - } - ccids_write_unlock(); - if (err != 0) - goto out_free_tx_slab; - - pr_info("CCID: Registered CCID %d (%s)\n", + pr_info("DCCP: Activated CCID %d (%s)\n", ccid_ops->ccid_id, ccid_ops->ccid_name); + err = 0; out: return err; -out_free_tx_slab: - ccid_kmem_cache_destroy(ccid_ops->ccid_hc_tx_slab); - ccid_ops->ccid_hc_tx_slab = NULL; - goto out; out_free_rx_slab: ccid_kmem_cache_destroy(ccid_ops->ccid_hc_rx_slab); ccid_ops->ccid_hc_rx_slab = NULL; goto out; } -EXPORT_SYMBOL_GPL(ccid_register); - -int ccid_unregister(struct ccid_operations *ccid_ops) +static void ccid_deactivate(struct ccid_operations *ccid_ops) { - ccids_write_lock(); - ccids[ccid_ops->ccid_id] = NULL; - ccids_write_unlock(); - ccid_kmem_cache_destroy(ccid_ops->ccid_hc_tx_slab); ccid_ops->ccid_hc_tx_slab = NULL; ccid_kmem_cache_destroy(ccid_ops->ccid_hc_rx_slab); ccid_ops->ccid_hc_rx_slab = NULL; - pr_info("CCID: Unregistered CCID %d (%s)\n", + pr_info("DCCP: Deactivated CCID %d (%s)\n", ccid_ops->ccid_id, ccid_ops->ccid_name); - return 0; } -EXPORT_SYMBOL_GPL(ccid_unregister); - -struct ccid *ccid_new(unsigned char id, struct sock *sk, int rx, gfp_t gfp) +struct ccid *ccid_new(const u8 id, struct sock *sk, bool rx) { - struct ccid_operations *ccid_ops; + struct ccid_operations *ccid_ops = ccid_by_number(id); struct ccid *ccid = NULL; - ccids_read_lock(); -#ifdef CONFIG_KMOD - if (ccids[id] == NULL) { - /* We only try to load if in process context */ - ccids_read_unlock(); - if (gfp & GFP_ATOMIC) - goto out; - request_module("net-dccp-ccid-%d", id); - ccids_read_lock(); - } -#endif - ccid_ops = ccids[id]; if (ccid_ops == NULL) - goto out_unlock; - - if (!try_module_get(ccid_ops->ccid_owner)) - goto out_unlock; - - ccids_read_unlock(); + goto out; ccid = kmem_cache_alloc(rx ? ccid_ops->ccid_hc_rx_slab : - ccid_ops->ccid_hc_tx_slab, gfp); + ccid_ops->ccid_hc_tx_slab, gfp_any()); if (ccid == NULL) - goto out_module_put; + goto out; ccid->ccid_ops = ccid_ops; if (rx) { memset(ccid + 1, 0, ccid_ops->ccid_hc_rx_obj_size); @@ -191,67 +167,57 @@ struct ccid *ccid_new(unsigned char id, struct sock *sk, int rx, gfp_t gfp) } out: return ccid; -out_unlock: - ccids_read_unlock(); - goto out; out_free_ccid: kmem_cache_free(rx ? ccid_ops->ccid_hc_rx_slab : ccid_ops->ccid_hc_tx_slab, ccid); ccid = NULL; -out_module_put: - module_put(ccid_ops->ccid_owner); goto out; } -EXPORT_SYMBOL_GPL(ccid_new); - -struct ccid *ccid_hc_rx_new(unsigned char id, struct sock *sk, gfp_t gfp) +void ccid_hc_rx_delete(struct ccid *ccid, struct sock *sk) { - return ccid_new(id, sk, 1, gfp); + if (ccid != NULL) { + if (ccid->ccid_ops->ccid_hc_rx_exit != NULL) + ccid->ccid_ops->ccid_hc_rx_exit(sk); + kmem_cache_free(ccid->ccid_ops->ccid_hc_rx_slab, ccid); + } } -EXPORT_SYMBOL_GPL(ccid_hc_rx_new); - -struct ccid *ccid_hc_tx_new(unsigned char id,struct sock *sk, gfp_t gfp) +void ccid_hc_tx_delete(struct ccid *ccid, struct sock *sk) { - return ccid_new(id, sk, 0, gfp); + if (ccid != NULL) { + if (ccid->ccid_ops->ccid_hc_tx_exit != NULL) + ccid->ccid_ops->ccid_hc_tx_exit(sk); + kmem_cache_free(ccid->ccid_ops->ccid_hc_tx_slab, ccid); + } } -EXPORT_SYMBOL_GPL(ccid_hc_tx_new); - -static void ccid_delete(struct ccid *ccid, struct sock *sk, int rx) +int __init ccid_initialize_builtins(void) { - struct ccid_operations *ccid_ops; + int i, err = tfrc_lib_init(); - if (ccid == NULL) - return; + if (err) + return err; - ccid_ops = ccid->ccid_ops; - if (rx) { - if (ccid_ops->ccid_hc_rx_exit != NULL) - ccid_ops->ccid_hc_rx_exit(sk); - kmem_cache_free(ccid_ops->ccid_hc_rx_slab, ccid); - } else { - if (ccid_ops->ccid_hc_tx_exit != NULL) - ccid_ops->ccid_hc_tx_exit(sk); - kmem_cache_free(ccid_ops->ccid_hc_tx_slab, ccid); + for (i = 0; i < ARRAY_SIZE(ccids); i++) { + err = ccid_activate(ccids[i]); + if (err) + goto unwind_registrations; } - ccids_read_lock(); - if (ccids[ccid_ops->ccid_id] != NULL) - module_put(ccid_ops->ccid_owner); - ccids_read_unlock(); -} + return 0; -void ccid_hc_rx_delete(struct ccid *ccid, struct sock *sk) -{ - ccid_delete(ccid, sk, 1); +unwind_registrations: + while(--i >= 0) + ccid_deactivate(ccids[i]); + tfrc_lib_exit(); + return err; } -EXPORT_SYMBOL_GPL(ccid_hc_rx_delete); - -void ccid_hc_tx_delete(struct ccid *ccid, struct sock *sk) +void ccid_cleanup_builtins(void) { - ccid_delete(ccid, sk, 0); -} + int i; -EXPORT_SYMBOL_GPL(ccid_hc_tx_delete); + for (i = 0; i < ARRAY_SIZE(ccids); i++) + ccid_deactivate(ccids[i]); + tfrc_lib_exit(); +} diff --git a/net/dccp/ccid.h b/net/dccp/ccid.h index fdeae7b5731..6eb837a47b5 100644 --- a/net/dccp/ccid.h +++ b/net/dccp/ccid.h @@ -19,7 +19,9 @@ #include <linux/list.h> #include <linux/module.h> -#define CCID_MAX 255 +/* maximum value for a CCID (RFC 4340, 19.5) */ +#define CCID_MAX 255 +#define CCID_SLAB_NAME_LENGTH 32 struct tcp_info; @@ -29,7 +31,6 @@ struct tcp_info; * @ccid_id: numerical CCID ID (up to %CCID_MAX, cf. table 5 in RFC 4340, 10.) * @ccid_ccmps: the CCMPS including network/transport headers (0 when disabled) * @ccid_name: alphabetical identifier string for @ccid_id - * @ccid_owner: module which implements/owns this CCID * @ccid_hc_{r,t}x_slab: memory pool for the receiver/sender half-connection * @ccid_hc_{r,t}x_obj_size: size of the receiver/sender half-connection socket * @@ -48,9 +49,10 @@ struct ccid_operations { unsigned char ccid_id; __u32 ccid_ccmps; const char *ccid_name; - struct module *ccid_owner; struct kmem_cache *ccid_hc_rx_slab, *ccid_hc_tx_slab; + char ccid_hc_rx_slab_name[CCID_SLAB_NAME_LENGTH]; + char ccid_hc_tx_slab_name[CCID_SLAB_NAME_LENGTH]; __u32 ccid_hc_rx_obj_size, ccid_hc_tx_obj_size; /* Interface Routines */ @@ -60,22 +62,18 @@ struct ccid_operations { void (*ccid_hc_tx_exit)(struct sock *sk); void (*ccid_hc_rx_packet_recv)(struct sock *sk, struct sk_buff *skb); - int (*ccid_hc_rx_parse_options)(struct sock *sk, - unsigned char option, - unsigned char len, u16 idx, - unsigned char* value); + int (*ccid_hc_rx_parse_options)(struct sock *sk, u8 pkt, + u8 opt, u8 *val, u8 len); int (*ccid_hc_rx_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, - unsigned char option, - unsigned char len, u16 idx, - unsigned char* value); + int (*ccid_hc_tx_parse_options)(struct sock *sk, u8 pkt, + u8 opt, u8 *val, u8 len); int (*ccid_hc_tx_send_packet)(struct sock *sk, struct sk_buff *skb); void (*ccid_hc_tx_packet_sent)(struct sock *sk, - int more, unsigned int len); + 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, @@ -90,8 +88,13 @@ struct ccid_operations { int __user *optlen); }; -extern int ccid_register(struct ccid_operations *ccid_ops); -extern int ccid_unregister(struct ccid_operations *ccid_ops); +extern struct ccid_operations ccid2_ops; +#ifdef CONFIG_IP_DCCP_CCID3 +extern struct ccid_operations ccid3_ops; +#endif + +int ccid_initialize_builtins(void); +void ccid_cleanup_builtins(void); struct ccid { struct ccid_operations *ccid_ops; @@ -103,31 +106,76 @@ static inline void *ccid_priv(const struct ccid *ccid) return (void *)ccid->ccid_priv; } -extern struct ccid *ccid_new(unsigned char id, struct sock *sk, int rx, - gfp_t gfp); +bool ccid_support_check(u8 const *ccid_array, u8 array_len); +int ccid_get_builtin_ccids(u8 **ccid_array, u8 *array_len); +int ccid_getsockopt_builtin_ccids(struct sock *sk, int len, + char __user *, int __user *); + +struct ccid *ccid_new(const u8 id, struct sock *sk, bool rx); + +static inline int ccid_get_current_rx_ccid(struct dccp_sock *dp) +{ + struct ccid *ccid = dp->dccps_hc_rx_ccid; -extern struct ccid *ccid_hc_rx_new(unsigned char id, struct sock *sk, - gfp_t gfp); -extern struct ccid *ccid_hc_tx_new(unsigned char id, struct sock *sk, - gfp_t gfp); + if (ccid == NULL || ccid->ccid_ops == NULL) + return -1; + return ccid->ccid_ops->ccid_id; +} + +static inline int ccid_get_current_tx_ccid(struct dccp_sock *dp) +{ + struct ccid *ccid = dp->dccps_hc_tx_ccid; -extern void ccid_hc_rx_delete(struct ccid *ccid, struct sock *sk); -extern void ccid_hc_tx_delete(struct ccid *ccid, struct sock *sk); + if (ccid == NULL || ccid->ccid_ops == NULL) + return -1; + return ccid->ccid_ops->ccid_id; +} + +void ccid_hc_rx_delete(struct ccid *ccid, struct sock *sk); +void ccid_hc_tx_delete(struct ccid *ccid, struct sock *sk); + +/* + * Congestion control of queued data packets via CCID decision. + * + * The TX CCID performs its congestion-control by indicating whether and when a + * queued packet may be sent, using the return code of ccid_hc_tx_send_packet(). + * The following modes are supported via the symbolic constants below: + * - timer-based pacing (CCID returns a delay value in milliseconds); + * - autonomous dequeueing (CCID internally schedules dccps_xmitlet). + */ + +enum ccid_dequeueing_decision { + CCID_PACKET_SEND_AT_ONCE = 0x00000, /* "green light": no delay */ + CCID_PACKET_DELAY_MAX = 0x0FFFF, /* maximum delay in msecs */ + CCID_PACKET_DELAY = 0x10000, /* CCID msec-delay mode */ + CCID_PACKET_WILL_DEQUEUE_LATER = 0x20000, /* CCID autonomous mode */ + CCID_PACKET_ERR = 0xF0000, /* error condition */ +}; + +static inline int ccid_packet_dequeue_eval(const int return_code) +{ + if (return_code < 0) + return CCID_PACKET_ERR; + if (return_code == 0) + return CCID_PACKET_SEND_AT_ONCE; + if (return_code <= CCID_PACKET_DELAY_MAX) + return CCID_PACKET_DELAY; + return return_code; +} static inline int ccid_hc_tx_send_packet(struct ccid *ccid, struct sock *sk, 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); - return rc; + return ccid->ccid_ops->ccid_hc_tx_send_packet(sk, skb); + return CCID_PACKET_SEND_AT_ONCE; } static inline void ccid_hc_tx_packet_sent(struct ccid *ccid, struct sock *sk, - int more, unsigned int len) + unsigned int len) { if (ccid->ccid_ops->ccid_hc_tx_packet_sent != NULL) - ccid->ccid_ops->ccid_hc_tx_packet_sent(sk, more, len); + ccid->ccid_ops->ccid_hc_tx_packet_sent(sk, len); } static inline void ccid_hc_rx_packet_recv(struct ccid *ccid, struct sock *sk, @@ -144,27 +192,31 @@ static inline void ccid_hc_tx_packet_recv(struct ccid *ccid, struct sock *sk, ccid->ccid_ops->ccid_hc_tx_packet_recv(sk, skb); } +/** + * ccid_hc_tx_parse_options - Parse CCID-specific options sent by the receiver + * @pkt: type of packet that @opt appears on (RFC 4340, 5.1) + * @opt: the CCID-specific option type (RFC 4340, 5.8 and 10.3) + * @val: value of @opt + * @len: length of @val in bytes + */ static inline int ccid_hc_tx_parse_options(struct ccid *ccid, struct sock *sk, - unsigned char option, - unsigned char len, u16 idx, - unsigned char* value) + u8 pkt, u8 opt, u8 *val, u8 len) { - int rc = 0; - if (ccid->ccid_ops->ccid_hc_tx_parse_options != NULL) - rc = ccid->ccid_ops->ccid_hc_tx_parse_options(sk, option, len, idx, - value); - return rc; + if (ccid->ccid_ops->ccid_hc_tx_parse_options == NULL) + return 0; + return ccid->ccid_ops->ccid_hc_tx_parse_options(sk, pkt, opt, val, len); } +/** + * ccid_hc_rx_parse_options - Parse CCID-specific options sent by the sender + * Arguments are analogous to ccid_hc_tx_parse_options() + */ static inline int ccid_hc_rx_parse_options(struct ccid *ccid, struct sock *sk, - unsigned char option, - unsigned char len, u16 idx, - unsigned char* value) + u8 pkt, u8 opt, u8 *val, u8 len) { - int rc = 0; - if (ccid->ccid_ops->ccid_hc_rx_parse_options != NULL) - rc = ccid->ccid_ops->ccid_hc_rx_parse_options(sk, option, len, idx, value); - return rc; + if (ccid->ccid_ops->ccid_hc_rx_parse_options == NULL) + return 0; + return ccid->ccid_ops->ccid_hc_rx_parse_options(sk, pkt, opt, val, len); } static inline int ccid_hc_rx_insert_options(struct ccid *ccid, struct sock *sk, @@ -194,7 +246,7 @@ static inline int ccid_hc_rx_getsockopt(struct ccid *ccid, struct sock *sk, u32 __user *optval, int __user *optlen) { int rc = -ENOPROTOOPT; - if (ccid->ccid_ops->ccid_hc_rx_getsockopt != NULL) + if (ccid != NULL && ccid->ccid_ops->ccid_hc_rx_getsockopt != NULL) rc = ccid->ccid_ops->ccid_hc_rx_getsockopt(sk, optname, len, optval, optlen); return rc; @@ -205,7 +257,7 @@ static inline int ccid_hc_tx_getsockopt(struct ccid *ccid, struct sock *sk, u32 __user *optval, int __user *optlen) { int rc = -ENOPROTOOPT; - if (ccid->ccid_ops->ccid_hc_tx_getsockopt != NULL) + if (ccid != NULL && ccid->ccid_ops->ccid_hc_tx_getsockopt != NULL) rc = ccid->ccid_ops->ccid_hc_tx_getsockopt(sk, optname, len, optval, optlen); return rc; diff --git a/net/dccp/ccids/Kconfig b/net/dccp/ccids/Kconfig index 12275943eab..8ba3fc9d6d1 100644 --- a/net/dccp/ccids/Kconfig +++ b/net/dccp/ccids/Kconfig @@ -1,119 +1,54 @@ -menu "DCCP CCIDs Configuration (EXPERIMENTAL)" - depends on EXPERIMENTAL - -config IP_DCCP_CCID2 - tristate "CCID2 (TCP-Like) (EXPERIMENTAL)" - def_tristate IP_DCCP - select IP_DCCP_ACKVEC - ---help--- - CCID 2, TCP-like Congestion Control, denotes Additive Increase, - Multiplicative Decrease (AIMD) congestion control with behavior - modelled directly on TCP, including congestion window, slow start, - timeouts, and so forth [RFC 2581]. CCID 2 achieves maximum - bandwidth over the long term, consistent with the use of end-to-end - congestion control, but halves its congestion window in response to - each congestion event. This leads to the abrupt rate changes - typical of TCP. Applications should use CCID 2 if they prefer - maximum bandwidth utilization to steadiness of rate. This is often - the case for applications that are not playing their data directly - to the user. For example, a hypothetical application that - transferred files over DCCP, using application-level retransmissions - for lost packets, would prefer CCID 2 to CCID 3. On-line games may - also prefer CCID 2. See RFC 4341 for further details. - - CCID2 is the default CCID used by DCCP. +menu "DCCP CCIDs Configuration" config IP_DCCP_CCID2_DEBUG - bool "CCID2 debugging messages" - depends on IP_DCCP_CCID2 - ---help--- - Enable CCID2-specific debugging messages. + bool "CCID-2 debugging messages" + ---help--- + Enable CCID-2 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. + The debugging output can additionally be toggled by setting the + ccid2_debug parameter to 0 or 1. - If in doubt, say N. + If in doubt, say N. config IP_DCCP_CCID3 - tristate "CCID3 (TCP-Friendly) (EXPERIMENTAL)" - def_tristate IP_DCCP - select IP_DCCP_TFRC_LIB + bool "CCID-3 (TCP-Friendly)" + def_bool y if (IP_DCCP = y || IP_DCCP = m) ---help--- - CCID 3 denotes TCP-Friendly Rate Control (TFRC), an equation-based + CCID-3 denotes TCP-Friendly Rate Control (TFRC), an equation-based rate-controlled congestion control mechanism. TFRC is designed to be reasonably fair when competing for bandwidth with TCP-like flows, where a flow is "reasonably fair" if its sending rate is generally within a factor of two of the sending rate of a TCP flow under the same conditions. However, TFRC has a much lower variation of - throughput over time compared with TCP, which makes CCID 3 more - suitable than CCID 2 for applications such streaming media where a + throughput over time compared with TCP, which makes CCID-3 more + suitable than CCID-2 for applications such streaming media where a relatively smooth sending rate is of importance. - CCID 3 is further described in RFC 4342, + 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. + RFC 5348. 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. + If in doubt, say N. 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) + bool "CCID-3 debugging messages" + depends on IP_DCCP_CCID3 + ---help--- + Enable CCID-3 specific debugging messages. - 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 debugging output can additionally be toggled by setting the + ccid3_debug parameter to 0 or 1. - 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. + If in doubt, say N. config IP_DCCP_TFRC_LIB - tristate - default n + def_bool y if IP_DCCP_CCID3 config IP_DCCP_TFRC_DEBUG - bool - depends on IP_DCCP_TFRC_LIB - default y if IP_DCCP_CCID3_DEBUG - + def_bool y if IP_DCCP_CCID3_DEBUG endmenu diff --git a/net/dccp/ccids/Makefile b/net/dccp/ccids/Makefile deleted file mode 100644 index 438f20bccff..00000000000 --- a/net/dccp/ccids/Makefile +++ /dev/null @@ -1,9 +0,0 @@ -obj-$(CONFIG_IP_DCCP_CCID3) += dccp_ccid3.o - -dccp_ccid3-y := ccid3.o - -obj-$(CONFIG_IP_DCCP_CCID2) += dccp_ccid2.o - -dccp_ccid2-y := ccid2.o - -obj-y += lib/ diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c index b5b52ebb269..f053198e730 100644 --- a/net/dccp/ccids/ccid2.c +++ b/net/dccp/ccids/ccid2.c @@ -1,6 +1,4 @@ /* - * net/dccp/ccids/ccid2.c - * * Copyright (c) 2005, 2006 Andrea Bittau <a.bittau@cs.ucl.ac.uk> * * Changes to meet Linux coding standards, and DCCP infrastructure fixes. @@ -25,70 +23,26 @@ /* * This implementation should follow RFC 4341 */ - -#include "../ccid.h" -#include "../dccp.h" +#include <linux/slab.h> +#include "../feat.h" #include "ccid2.h" #ifdef CONFIG_IP_DCCP_CCID2_DEBUG -static int ccid2_debug; +static bool ccid2_debug; #define ccid2_pr_debug(format, a...) DCCP_PR_DEBUG(ccid2_debug, format, ##a) - -static void ccid2_hc_tx_check_sanity(const struct ccid2_hc_tx_sock *hctx) -{ - int len = 0; - int pipe = 0; - struct ccid2_seq *seqp = hctx->ccid2hctx_seqh; - - /* there is data in the chain */ - if (seqp != hctx->ccid2hctx_seqt) { - seqp = seqp->ccid2s_prev; - len++; - if (!seqp->ccid2s_acked) - pipe++; - - while (seqp != hctx->ccid2hctx_seqt) { - struct ccid2_seq *prev = seqp->ccid2s_prev; - - len++; - if (!prev->ccid2s_acked) - pipe++; - - /* packets are sent sequentially */ - BUG_ON(dccp_delta_seqno(seqp->ccid2s_seq, - prev->ccid2s_seq ) >= 0); - BUG_ON(time_before(seqp->ccid2s_sent, - prev->ccid2s_sent)); - - seqp = prev; - } - } - - BUG_ON(pipe != hctx->ccid2hctx_pipe); - ccid2_pr_debug("len of chain=%d\n", len); - - do { - seqp = seqp->ccid2s_prev; - len++; - } while (seqp != hctx->ccid2hctx_seqh); - - ccid2_pr_debug("total len=%d\n", len); - BUG_ON(len != hctx->ccid2hctx_seqbufc * CCID2_SEQBUF_LEN); -} #else #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) +static int ccid2_hc_tx_alloc_seq(struct ccid2_hc_tx_sock *hc) { struct ccid2_seq *seqp; int i; /* check if we have space to preserve the pointer to the buffer */ - if (hctx->ccid2hctx_seqbufc >= (sizeof(hctx->ccid2hctx_seqbuf) / - sizeof(struct ccid2_seq*))) + if (hc->tx_seqbufc >= (sizeof(hc->tx_seqbuf) / + sizeof(struct ccid2_seq *))) return -ENOMEM; /* allocate buffer and initialize linked list */ @@ -104,38 +58,34 @@ static int ccid2_hc_tx_alloc_seq(struct ccid2_hc_tx_sock *hctx) seqp->ccid2s_prev = &seqp[CCID2_SEQBUF_LEN - 1]; /* This is the first allocation. Initiate the head and tail. */ - if (hctx->ccid2hctx_seqbufc == 0) - hctx->ccid2hctx_seqh = hctx->ccid2hctx_seqt = seqp; + if (hc->tx_seqbufc == 0) + hc->tx_seqh = hc->tx_seqt = seqp; else { /* link the existing list with the one we just created */ - hctx->ccid2hctx_seqh->ccid2s_next = seqp; - seqp->ccid2s_prev = hctx->ccid2hctx_seqh; + hc->tx_seqh->ccid2s_next = seqp; + seqp->ccid2s_prev = hc->tx_seqh; - hctx->ccid2hctx_seqt->ccid2s_prev = &seqp[CCID2_SEQBUF_LEN - 1]; - seqp[CCID2_SEQBUF_LEN - 1].ccid2s_next = hctx->ccid2hctx_seqt; + hc->tx_seqt->ccid2s_prev = &seqp[CCID2_SEQBUF_LEN - 1]; + seqp[CCID2_SEQBUF_LEN - 1].ccid2s_next = hc->tx_seqt; } /* store the original pointer to the buffer so we can free it */ - hctx->ccid2hctx_seqbuf[hctx->ccid2hctx_seqbufc] = seqp; - hctx->ccid2hctx_seqbufc++; + hc->tx_seqbuf[hc->tx_seqbufc] = seqp; + hc->tx_seqbufc++; return 0; } static int ccid2_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb) { - struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); - - if (hctx->ccid2hctx_pipe < hctx->ccid2hctx_cwnd) - return 0; - - return 1; /* XXX CCID should dequeue when ready instead of polling */ + if (ccid2_cwnd_network_limited(ccid2_hc_tx_sk(sk))) + return CCID_PACKET_WILL_DEQUEUE_LATER; + return CCID_PACKET_SEND_AT_ONCE; } static void ccid2_change_l_ack_ratio(struct sock *sk, u32 val) { - struct dccp_sock *dp = dccp_sk(sk); - u32 max_ratio = DIV_ROUND_UP(ccid2_hc_tx_sk(sk)->ccid2hctx_cwnd, 2); + u32 max_ratio = DIV_ROUND_UP(ccid2_hc_tx_sk(sk)->tx_cwnd, 2); /* * Ensure that Ack Ratio does not exceed ceil(cwnd/2), which is (2) from @@ -147,109 +97,186 @@ static void ccid2_change_l_ack_ratio(struct sock *sk, u32 val) DCCP_WARN("Limiting Ack Ratio (%u) to %u\n", val, max_ratio); val = max_ratio; } - if (val > 0xFFFF) /* RFC 4340, 11.3 */ - val = 0xFFFF; + dccp_feat_signal_nn_change(sk, DCCPF_ACK_RATIO, + min_t(u32, val, DCCPF_ACK_RATIO_MAX)); +} - if (val == dp->dccps_l_ack_ratio) - return; +static void ccid2_check_l_ack_ratio(struct sock *sk) +{ + struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); - ccid2_pr_debug("changing local ack ratio to %u\n", val); - dp->dccps_l_ack_ratio = val; + /* + * After a loss, idle period, application limited period, or RTO we + * need to check that the ack ratio is still less than the congestion + * window. Otherwise, we will send an entire congestion window of + * packets and got no response because we haven't sent ack ratio + * packets yet. + * If the ack ratio does need to be reduced, we reduce it to half of + * the congestion window (or 1 if that's zero) instead of to the + * congestion window. This prevents problems if one ack is lost. + */ + if (dccp_feat_nn_get(sk, DCCPF_ACK_RATIO) > hc->tx_cwnd) + ccid2_change_l_ack_ratio(sk, hc->tx_cwnd/2 ? : 1U); } -static void ccid2_change_srtt(struct ccid2_hc_tx_sock *hctx, long val) +static void ccid2_change_l_seq_window(struct sock *sk, u64 val) { - ccid2_pr_debug("change SRTT to %ld\n", val); - hctx->ccid2hctx_srtt = val; + dccp_feat_signal_nn_change(sk, DCCPF_SEQUENCE_WINDOW, + clamp_val(val, DCCPF_SEQ_WMIN, + DCCPF_SEQ_WMAX)); } -static void ccid2_start_rto_timer(struct sock *sk); - static void ccid2_hc_tx_rto_expire(unsigned long data) { struct sock *sk = (struct sock *)data; - struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); - long s; + struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); + const bool sender_was_blocked = ccid2_cwnd_network_limited(hc); bh_lock_sock(sk); if (sock_owned_by_user(sk)) { - sk_reset_timer(sk, &hctx->ccid2hctx_rtotimer, - jiffies + HZ / 5); + sk_reset_timer(sk, &hc->tx_rtotimer, jiffies + HZ / 5); goto out; } ccid2_pr_debug("RTO_EXPIRE\n"); - ccid2_hc_tx_check_sanity(hctx); - /* back-off timer */ - hctx->ccid2hctx_rto <<= 1; - - s = hctx->ccid2hctx_rto / HZ; - if (s > 60) - hctx->ccid2hctx_rto = 60 * HZ; - - ccid2_start_rto_timer(sk); + hc->tx_rto <<= 1; + if (hc->tx_rto > DCCP_RTO_MAX) + hc->tx_rto = DCCP_RTO_MAX; /* adjust pipe, cwnd etc */ - hctx->ccid2hctx_ssthresh = hctx->ccid2hctx_cwnd / 2; - if (hctx->ccid2hctx_ssthresh < 2) - hctx->ccid2hctx_ssthresh = 2; - hctx->ccid2hctx_cwnd = 1; - hctx->ccid2hctx_pipe = 0; + hc->tx_ssthresh = hc->tx_cwnd / 2; + if (hc->tx_ssthresh < 2) + hc->tx_ssthresh = 2; + hc->tx_cwnd = 1; + hc->tx_pipe = 0; /* clear state about stuff we sent */ - hctx->ccid2hctx_seqt = hctx->ccid2hctx_seqh; - hctx->ccid2hctx_packets_acked = 0; + hc->tx_seqt = hc->tx_seqh; + hc->tx_packets_acked = 0; /* clear ack ratio state. */ - hctx->ccid2hctx_rpseq = 0; - hctx->ccid2hctx_rpdupack = -1; + hc->tx_rpseq = 0; + hc->tx_rpdupack = -1; ccid2_change_l_ack_ratio(sk, 1); - ccid2_hc_tx_check_sanity(hctx); + + /* if we were blocked before, we may now send cwnd=1 packet */ + if (sender_was_blocked) + tasklet_schedule(&dccp_sk(sk)->dccps_xmitlet); + /* restart backed-off timer */ + sk_reset_timer(sk, &hc->tx_rtotimer, jiffies + hc->tx_rto); out: bh_unlock_sock(sk); sock_put(sk); } -static void ccid2_start_rto_timer(struct sock *sk) +/* + * Congestion window validation (RFC 2861). + */ +static bool ccid2_do_cwv = true; +module_param(ccid2_do_cwv, bool, 0644); +MODULE_PARM_DESC(ccid2_do_cwv, "Perform RFC2861 Congestion Window Validation"); + +/** + * ccid2_update_used_window - Track how much of cwnd is actually used + * This is done in addition to CWV. The sender needs to have an idea of how many + * packets may be in flight, to set the local Sequence Window value accordingly + * (RFC 4340, 7.5.2). The CWV mechanism is exploited to keep track of the + * maximum-used window. We use an EWMA low-pass filter to filter out noise. + */ +static void ccid2_update_used_window(struct ccid2_hc_tx_sock *hc, u32 new_wnd) { - struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); + hc->tx_expected_wnd = (3 * hc->tx_expected_wnd + new_wnd) / 4; +} - ccid2_pr_debug("setting RTO timeout=%ld\n", hctx->ccid2hctx_rto); +/* This borrows the code of tcp_cwnd_application_limited() */ +static void ccid2_cwnd_application_limited(struct sock *sk, const u32 now) +{ + struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); + /* don't reduce cwnd below the initial window (IW) */ + u32 init_win = rfc3390_bytes_to_packets(dccp_sk(sk)->dccps_mss_cache), + win_used = max(hc->tx_cwnd_used, init_win); + + if (win_used < hc->tx_cwnd) { + hc->tx_ssthresh = max(hc->tx_ssthresh, + (hc->tx_cwnd >> 1) + (hc->tx_cwnd >> 2)); + hc->tx_cwnd = (hc->tx_cwnd + win_used) >> 1; + } + hc->tx_cwnd_used = 0; + hc->tx_cwnd_stamp = now; - BUG_ON(timer_pending(&hctx->ccid2hctx_rtotimer)); - sk_reset_timer(sk, &hctx->ccid2hctx_rtotimer, - jiffies + hctx->ccid2hctx_rto); + ccid2_check_l_ack_ratio(sk); } -static void ccid2_hc_tx_packet_sent(struct sock *sk, int more, unsigned int len) +/* This borrows the code of tcp_cwnd_restart() */ +static void ccid2_cwnd_restart(struct sock *sk, const u32 now) +{ + struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); + u32 cwnd = hc->tx_cwnd, restart_cwnd, + iwnd = rfc3390_bytes_to_packets(dccp_sk(sk)->dccps_mss_cache); + + hc->tx_ssthresh = max(hc->tx_ssthresh, (cwnd >> 1) + (cwnd >> 2)); + + /* don't reduce cwnd below the initial window (IW) */ + restart_cwnd = min(cwnd, iwnd); + cwnd >>= (now - hc->tx_lsndtime) / hc->tx_rto; + hc->tx_cwnd = max(cwnd, restart_cwnd); + + hc->tx_cwnd_stamp = now; + hc->tx_cwnd_used = 0; + + ccid2_check_l_ack_ratio(sk); +} + +static void ccid2_hc_tx_packet_sent(struct sock *sk, unsigned int len) { struct dccp_sock *dp = dccp_sk(sk); - struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); + struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); + const u32 now = ccid2_time_stamp; struct ccid2_seq *next; - hctx->ccid2hctx_pipe++; + /* slow-start after idle periods (RFC 2581, RFC 2861) */ + if (ccid2_do_cwv && !hc->tx_pipe && + (s32)(now - hc->tx_lsndtime) >= hc->tx_rto) + ccid2_cwnd_restart(sk, now); - hctx->ccid2hctx_seqh->ccid2s_seq = dp->dccps_gss; - hctx->ccid2hctx_seqh->ccid2s_acked = 0; - hctx->ccid2hctx_seqh->ccid2s_sent = jiffies; + hc->tx_lsndtime = now; + hc->tx_pipe += 1; - next = hctx->ccid2hctx_seqh->ccid2s_next; + /* see whether cwnd was fully used (RFC 2861), update expected window */ + if (ccid2_cwnd_network_limited(hc)) { + ccid2_update_used_window(hc, hc->tx_cwnd); + hc->tx_cwnd_used = 0; + hc->tx_cwnd_stamp = now; + } else { + if (hc->tx_pipe > hc->tx_cwnd_used) + hc->tx_cwnd_used = hc->tx_pipe; + + ccid2_update_used_window(hc, hc->tx_cwnd_used); + + if (ccid2_do_cwv && (s32)(now - hc->tx_cwnd_stamp) >= hc->tx_rto) + ccid2_cwnd_application_limited(sk, now); + } + + hc->tx_seqh->ccid2s_seq = dp->dccps_gss; + hc->tx_seqh->ccid2s_acked = 0; + hc->tx_seqh->ccid2s_sent = now; + + next = hc->tx_seqh->ccid2s_next; /* check if we need to alloc more space */ - if (next == hctx->ccid2hctx_seqt) { - if (ccid2_hc_tx_alloc_seq(hctx)) { + if (next == hc->tx_seqt) { + if (ccid2_hc_tx_alloc_seq(hc)) { DCCP_CRIT("packet history - out of memory!"); /* FIXME: find a more graceful way to bail out */ return; } - next = hctx->ccid2hctx_seqh->ccid2s_next; - BUG_ON(next == hctx->ccid2hctx_seqt); + next = hc->tx_seqh->ccid2s_next; + BUG_ON(next == hc->tx_seqt); } - hctx->ccid2hctx_seqh = next; + hc->tx_seqh = next; - ccid2_pr_debug("cwnd=%d pipe=%d\n", hctx->ccid2hctx_cwnd, - hctx->ccid2hctx_pipe); + ccid2_pr_debug("cwnd=%d pipe=%d\n", hc->tx_cwnd, hc->tx_pipe); /* * FIXME: The code below is broken and the variables have been removed @@ -272,12 +299,12 @@ static void ccid2_hc_tx_packet_sent(struct sock *sk, int more, unsigned int len) */ #if 0 /* Ack Ratio. Need to maintain a concept of how many windows we sent */ - hctx->ccid2hctx_arsent++; + hc->tx_arsent++; /* We had an ack loss in this window... */ - if (hctx->ccid2hctx_ackloss) { - if (hctx->ccid2hctx_arsent >= hctx->ccid2hctx_cwnd) { - hctx->ccid2hctx_arsent = 0; - hctx->ccid2hctx_ackloss = 0; + if (hc->tx_ackloss) { + if (hc->tx_arsent >= hc->tx_cwnd) { + hc->tx_arsent = 0; + hc->tx_ackloss = 0; } } else { /* No acks lost up to now... */ @@ -287,234 +314,203 @@ static void ccid2_hc_tx_packet_sent(struct sock *sk, int more, unsigned int len) int denom = dp->dccps_l_ack_ratio * dp->dccps_l_ack_ratio - dp->dccps_l_ack_ratio; - denom = hctx->ccid2hctx_cwnd * hctx->ccid2hctx_cwnd / denom; + denom = hc->tx_cwnd * hc->tx_cwnd / denom; - if (hctx->ccid2hctx_arsent >= denom) { + if (hc->tx_arsent >= denom) { ccid2_change_l_ack_ratio(sk, dp->dccps_l_ack_ratio - 1); - hctx->ccid2hctx_arsent = 0; + hc->tx_arsent = 0; } } else { /* we can't increase ack ratio further [1] */ - hctx->ccid2hctx_arsent = 0; /* or maybe set it to cwnd*/ + hc->tx_arsent = 0; /* or maybe set it to cwnd*/ } } #endif - /* setup RTO timer */ - if (!timer_pending(&hctx->ccid2hctx_rtotimer)) - ccid2_start_rto_timer(sk); + sk_reset_timer(sk, &hc->tx_rtotimer, jiffies + hc->tx_rto); #ifdef CONFIG_IP_DCCP_CCID2_DEBUG do { - struct ccid2_seq *seqp = hctx->ccid2hctx_seqt; + struct ccid2_seq *seqp = hc->tx_seqt; - while (seqp != hctx->ccid2hctx_seqh) { - ccid2_pr_debug("out seq=%llu acked=%d time=%lu\n", + while (seqp != hc->tx_seqh) { + ccid2_pr_debug("out seq=%llu acked=%d time=%u\n", (unsigned long long)seqp->ccid2s_seq, seqp->ccid2s_acked, seqp->ccid2s_sent); seqp = seqp->ccid2s_next; } } while (0); ccid2_pr_debug("=========\n"); - ccid2_hc_tx_check_sanity(hctx); #endif } -/* XXX Lame code duplication! - * returns -1 if none was found. - * else returns the next offset to use in the function call. +/** + * ccid2_rtt_estimator - Sample RTT and compute RTO using RFC2988 algorithm + * This code is almost identical with TCP's tcp_rtt_estimator(), since + * - it has a higher sampling frequency (recommended by RFC 1323), + * - the RTO does not collapse into RTT due to RTTVAR going towards zero, + * - it is simple (cf. more complex proposals such as Eifel timer or research + * which suggests that the gain should be set according to window size), + * - in tests it was found to work well with CCID2 [gerrit]. */ -static int ccid2_ackvector(struct sock *sk, struct sk_buff *skb, int offset, - unsigned char **vec, unsigned char *veclen) +static void ccid2_rtt_estimator(struct sock *sk, const long mrtt) { - const struct dccp_hdr *dh = dccp_hdr(skb); - unsigned char *options = (unsigned char *)dh + dccp_hdr_len(skb); - unsigned char *opt_ptr; - const unsigned char *opt_end = (unsigned char *)dh + - (dh->dccph_doff * 4); - unsigned char opt, len; - unsigned char *value; - - BUG_ON(offset < 0); - options += offset; - opt_ptr = options; - if (opt_ptr >= opt_end) - return -1; - - while (opt_ptr != opt_end) { - opt = *opt_ptr++; - len = 0; - value = NULL; - - /* Check if this isn't a single byte option */ - if (opt > DCCPO_MAX_RESERVED) { - if (opt_ptr == opt_end) - goto out_invalid_option; - - len = *opt_ptr++; - if (len < 3) - goto out_invalid_option; + struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); + long m = mrtt ? : 1; + + if (hc->tx_srtt == 0) { + /* First measurement m */ + hc->tx_srtt = m << 3; + hc->tx_mdev = m << 1; + + hc->tx_mdev_max = max(hc->tx_mdev, tcp_rto_min(sk)); + hc->tx_rttvar = hc->tx_mdev_max; + + hc->tx_rtt_seq = dccp_sk(sk)->dccps_gss; + } else { + /* Update scaled SRTT as SRTT += 1/8 * (m - SRTT) */ + m -= (hc->tx_srtt >> 3); + hc->tx_srtt += m; + + /* Similarly, update scaled mdev with regard to |m| */ + if (m < 0) { + m = -m; + m -= (hc->tx_mdev >> 2); /* - * Remove the type and len fields, leaving - * just the value size + * This neutralises RTO increase when RTT < SRTT - mdev + * (see P. Sarolahti, A. Kuznetsov,"Congestion Control + * in Linux TCP", USENIX 2002, pp. 49-62). */ - len -= 2; - value = opt_ptr; - opt_ptr += len; + if (m > 0) + m >>= 3; + } else { + m -= (hc->tx_mdev >> 2); + } + hc->tx_mdev += m; - if (opt_ptr > opt_end) - goto out_invalid_option; + if (hc->tx_mdev > hc->tx_mdev_max) { + hc->tx_mdev_max = hc->tx_mdev; + if (hc->tx_mdev_max > hc->tx_rttvar) + hc->tx_rttvar = hc->tx_mdev_max; } - switch (opt) { - case DCCPO_ACK_VECTOR_0: - case DCCPO_ACK_VECTOR_1: - *vec = value; - *veclen = len; - return offset + (opt_ptr - options); + /* + * Decay RTTVAR at most once per flight, exploiting that + * 1) pipe <= cwnd <= Sequence_Window = W (RFC 4340, 7.5.2) + * 2) AWL = GSS-W+1 <= GAR <= GSS (RFC 4340, 7.5.1) + * GAR is a useful bound for FlightSize = pipe. + * AWL is probably too low here, as it over-estimates pipe. + */ + if (after48(dccp_sk(sk)->dccps_gar, hc->tx_rtt_seq)) { + if (hc->tx_mdev_max < hc->tx_rttvar) + hc->tx_rttvar -= (hc->tx_rttvar - + hc->tx_mdev_max) >> 2; + hc->tx_rtt_seq = dccp_sk(sk)->dccps_gss; + hc->tx_mdev_max = tcp_rto_min(sk); } } - return -1; - -out_invalid_option: - DCCP_BUG("Invalid option - this should not happen (previous parsing)!"); - return -1; -} - -static void ccid2_hc_tx_kill_rto_timer(struct sock *sk) -{ - struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); + /* + * Set RTO from SRTT and RTTVAR + * As in TCP, 4 * RTTVAR >= TCP_RTO_MIN, giving a minimum RTO of 200 ms. + * This agrees with RFC 4341, 5: + * "Because DCCP does not retransmit data, DCCP does not require + * TCP's recommended minimum timeout of one second". + */ + hc->tx_rto = (hc->tx_srtt >> 3) + hc->tx_rttvar; - sk_stop_timer(sk, &hctx->ccid2hctx_rtotimer); - ccid2_pr_debug("deleted RTO timer\n"); + if (hc->tx_rto > DCCP_RTO_MAX) + hc->tx_rto = DCCP_RTO_MAX; } -static inline void ccid2_new_ack(struct sock *sk, - struct ccid2_seq *seqp, - unsigned int *maxincr) +static void ccid2_new_ack(struct sock *sk, struct ccid2_seq *seqp, + unsigned int *maxincr) { - struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); - - if (hctx->ccid2hctx_cwnd < hctx->ccid2hctx_ssthresh) { - if (*maxincr > 0 && ++hctx->ccid2hctx_packets_acked == 2) { - hctx->ccid2hctx_cwnd += 1; - *maxincr -= 1; - hctx->ccid2hctx_packets_acked = 0; - } - } else if (++hctx->ccid2hctx_packets_acked >= hctx->ccid2hctx_cwnd) { - hctx->ccid2hctx_cwnd += 1; - hctx->ccid2hctx_packets_acked = 0; - } - - /* update RTO */ - if (hctx->ccid2hctx_srtt == -1 || - time_after(jiffies, hctx->ccid2hctx_lastrtt + hctx->ccid2hctx_srtt)) { - unsigned long r = (long)jiffies - (long)seqp->ccid2s_sent; - int s; - - /* first measurement */ - if (hctx->ccid2hctx_srtt == -1) { - ccid2_pr_debug("R: %lu Time=%lu seq=%llu\n", - r, jiffies, - (unsigned long long)seqp->ccid2s_seq); - ccid2_change_srtt(hctx, r); - hctx->ccid2hctx_rttvar = r >> 1; - } else { - /* RTTVAR */ - long tmp = hctx->ccid2hctx_srtt - r; - long srtt; - - if (tmp < 0) - tmp *= -1; - - tmp >>= 2; - hctx->ccid2hctx_rttvar *= 3; - hctx->ccid2hctx_rttvar >>= 2; - hctx->ccid2hctx_rttvar += tmp; - - /* SRTT */ - srtt = hctx->ccid2hctx_srtt; - srtt *= 7; - srtt >>= 3; - tmp = r >> 3; - srtt += tmp; - ccid2_change_srtt(hctx, srtt); + struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); + struct dccp_sock *dp = dccp_sk(sk); + int r_seq_used = hc->tx_cwnd / dp->dccps_l_ack_ratio; + + if (hc->tx_cwnd < dp->dccps_l_seq_win && + r_seq_used < dp->dccps_r_seq_win) { + if (hc->tx_cwnd < hc->tx_ssthresh) { + if (*maxincr > 0 && ++hc->tx_packets_acked >= 2) { + hc->tx_cwnd += 1; + *maxincr -= 1; + hc->tx_packets_acked = 0; + } + } else if (++hc->tx_packets_acked >= hc->tx_cwnd) { + hc->tx_cwnd += 1; + hc->tx_packets_acked = 0; } - s = hctx->ccid2hctx_rttvar << 2; - /* clock granularity is 1 when based on jiffies */ - if (!s) - s = 1; - hctx->ccid2hctx_rto = hctx->ccid2hctx_srtt + s; - - /* must be at least a second */ - s = hctx->ccid2hctx_rto / HZ; - /* DCCP doesn't require this [but I like it cuz my code sux] */ -#if 1 - if (s < 1) - hctx->ccid2hctx_rto = HZ; -#endif - /* max 60 seconds */ - if (s > 60) - hctx->ccid2hctx_rto = HZ * 60; - - 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); } - /* we got a new ack, so re-start RTO timer */ - ccid2_hc_tx_kill_rto_timer(sk); - ccid2_start_rto_timer(sk); -} - -static void ccid2_hc_tx_dec_pipe(struct sock *sk) -{ - struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); + /* + * Adjust the local sequence window and the ack ratio to allow about + * 5 times the number of packets in the network (RFC 4340 7.5.2) + */ + if (r_seq_used * CCID2_WIN_CHANGE_FACTOR >= dp->dccps_r_seq_win) + ccid2_change_l_ack_ratio(sk, dp->dccps_l_ack_ratio * 2); + else if (r_seq_used * CCID2_WIN_CHANGE_FACTOR < dp->dccps_r_seq_win/2) + ccid2_change_l_ack_ratio(sk, dp->dccps_l_ack_ratio / 2 ? : 1U); - if (hctx->ccid2hctx_pipe == 0) - DCCP_BUG("pipe == 0"); - else - hctx->ccid2hctx_pipe--; + if (hc->tx_cwnd * CCID2_WIN_CHANGE_FACTOR >= dp->dccps_l_seq_win) + ccid2_change_l_seq_window(sk, dp->dccps_l_seq_win * 2); + else if (hc->tx_cwnd * CCID2_WIN_CHANGE_FACTOR < dp->dccps_l_seq_win/2) + ccid2_change_l_seq_window(sk, dp->dccps_l_seq_win / 2); - if (hctx->ccid2hctx_pipe == 0) - ccid2_hc_tx_kill_rto_timer(sk); + /* + * FIXME: RTT is sampled several times per acknowledgment (for each + * entry in the Ack Vector), instead of once per Ack (as in TCP SACK). + * This causes the RTT to be over-estimated, since the older entries + * in the Ack Vector have earlier sending times. + * The cleanest solution is to not use the ccid2s_sent field at all + * and instead use DCCP timestamps: requires changes in other places. + */ + ccid2_rtt_estimator(sk, ccid2_time_stamp - seqp->ccid2s_sent); } static void ccid2_congestion_event(struct sock *sk, struct ccid2_seq *seqp) { - struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); + struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); - if (time_before(seqp->ccid2s_sent, hctx->ccid2hctx_last_cong)) { + if ((s32)(seqp->ccid2s_sent - hc->tx_last_cong) < 0) { ccid2_pr_debug("Multiple losses in an RTT---treating as one\n"); return; } - hctx->ccid2hctx_last_cong = jiffies; + hc->tx_last_cong = ccid2_time_stamp; + + hc->tx_cwnd = hc->tx_cwnd / 2 ? : 1U; + hc->tx_ssthresh = max(hc->tx_cwnd, 2U); - hctx->ccid2hctx_cwnd = hctx->ccid2hctx_cwnd / 2 ? : 1U; - hctx->ccid2hctx_ssthresh = max(hctx->ccid2hctx_cwnd, 2U); + ccid2_check_l_ack_ratio(sk); +} + +static int ccid2_hc_tx_parse_options(struct sock *sk, u8 packet_type, + u8 option, u8 *optval, u8 optlen) +{ + struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); - /* Avoid spurious timeouts resulting from Ack Ratio > cwnd */ - if (dccp_sk(sk)->dccps_l_ack_ratio > hctx->ccid2hctx_cwnd) - ccid2_change_l_ack_ratio(sk, hctx->ccid2hctx_cwnd); + switch (option) { + case DCCPO_ACK_VECTOR_0: + case DCCPO_ACK_VECTOR_1: + return dccp_ackvec_parsed_add(&hc->tx_av_chunks, optval, optlen, + option - DCCPO_ACK_VECTOR_0); + } + return 0; } static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) { struct dccp_sock *dp = dccp_sk(sk); - struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); + struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); + const bool sender_was_blocked = ccid2_cwnd_network_limited(hc); + struct dccp_ackvec_parsed *avp; u64 ackno, seqno; struct ccid2_seq *seqp; - unsigned char *vector; - unsigned char veclen; - int offset = 0; int done = 0; unsigned int maxincr = 0; - ccid2_hc_tx_check_sanity(hctx); /* check reverse path congestion */ seqno = DCCP_SKB_CB(skb)->dccpd_seq; @@ -523,49 +519,52 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) * -sorbo. */ /* need to bootstrap */ - if (hctx->ccid2hctx_rpdupack == -1) { - hctx->ccid2hctx_rpdupack = 0; - hctx->ccid2hctx_rpseq = seqno; + if (hc->tx_rpdupack == -1) { + hc->tx_rpdupack = 0; + hc->tx_rpseq = seqno; } else { /* check if packet is consecutive */ - if (dccp_delta_seqno(hctx->ccid2hctx_rpseq, seqno) == 1) - hctx->ccid2hctx_rpseq = seqno; + if (dccp_delta_seqno(hc->tx_rpseq, seqno) == 1) + hc->tx_rpseq = seqno; /* it's a later packet */ - else if (after48(seqno, hctx->ccid2hctx_rpseq)) { - hctx->ccid2hctx_rpdupack++; + else if (after48(seqno, hc->tx_rpseq)) { + hc->tx_rpdupack++; /* check if we got enough dupacks */ - if (hctx->ccid2hctx_rpdupack >= NUMDUPACK) { - hctx->ccid2hctx_rpdupack = -1; /* XXX lame */ - hctx->ccid2hctx_rpseq = 0; - + if (hc->tx_rpdupack >= NUMDUPACK) { + hc->tx_rpdupack = -1; /* XXX lame */ + hc->tx_rpseq = 0; +#ifdef __CCID2_COPES_GRACEFULLY_WITH_ACK_CONGESTION_CONTROL__ + /* + * FIXME: Ack Congestion Control is broken; in + * the current state instabilities occurred with + * Ack Ratios greater than 1; causing hang-ups + * and long RTO timeouts. This needs to be fixed + * before opening up dynamic changes. -- gerrit + */ ccid2_change_l_ack_ratio(sk, 2 * dp->dccps_l_ack_ratio); +#endif } } } /* check forward path congestion */ - /* still didn't send out new data packets */ - if (hctx->ccid2hctx_seqh == hctx->ccid2hctx_seqt) + if (dccp_packet_without_ack(skb)) return; - switch (DCCP_SKB_CB(skb)->dccpd_type) { - case DCCP_PKT_ACK: - case DCCP_PKT_DATAACK: - break; - default: - return; - } + /* still didn't send out new data packets */ + if (hc->tx_seqh == hc->tx_seqt) + goto done; ackno = DCCP_SKB_CB(skb)->dccpd_ack_seq; - if (after48(ackno, hctx->ccid2hctx_high_ack)) - hctx->ccid2hctx_high_ack = ackno; + if (after48(ackno, hc->tx_high_ack)) + hc->tx_high_ack = ackno; - seqp = hctx->ccid2hctx_seqt; + seqp = hc->tx_seqt; while (before48(seqp->ccid2s_seq, ackno)) { seqp = seqp->ccid2s_next; - if (seqp == hctx->ccid2hctx_seqh) { - seqp = hctx->ccid2hctx_seqh->ccid2s_prev; + if (seqp == hc->tx_seqh) { + seqp = hc->tx_seqh->ccid2s_prev; break; } } @@ -575,26 +574,26 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) * packets per acknowledgement. Rounding up avoids that cwnd is not * advanced when Ack Ratio is 1 and gives a slight edge otherwise. */ - if (hctx->ccid2hctx_cwnd < hctx->ccid2hctx_ssthresh) + if (hc->tx_cwnd < hc->tx_ssthresh) maxincr = DIV_ROUND_UP(dp->dccps_l_ack_ratio, 2); /* go through all ack vectors */ - while ((offset = ccid2_ackvector(sk, skb, offset, - &vector, &veclen)) != -1) { + list_for_each_entry(avp, &hc->tx_av_chunks, node) { /* go through this ack vector */ - while (veclen--) { - const u8 rl = *vector & DCCP_ACKVEC_LEN_MASK; - u64 ackno_end_rl = SUB48(ackno, rl); + for (; avp->len--; avp->vec++) { + u64 ackno_end_rl = SUB48(ackno, + dccp_ackvec_runlen(avp->vec)); - ccid2_pr_debug("ackvec start:%llu end:%llu\n", + ccid2_pr_debug("ackvec %llu |%u,%u|\n", (unsigned long long)ackno, - (unsigned long long)ackno_end_rl); + dccp_ackvec_state(avp->vec) >> 6, + dccp_ackvec_runlen(avp->vec)); /* if the seqno we are analyzing is larger than the * current ackno, then move towards the tail of our * seqnos. */ while (after48(seqp->ccid2s_seq, ackno)) { - if (seqp == hctx->ccid2hctx_seqt) { + if (seqp == hc->tx_seqt) { done = 1; break; } @@ -607,26 +606,24 @@ 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(avp->vec); /* 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); seqp->ccid2s_acked = 1; ccid2_pr_debug("Got ack for %llu\n", (unsigned long long)seqp->ccid2s_seq); - ccid2_hc_tx_dec_pipe(sk); + hc->tx_pipe--; } - if (seqp == hctx->ccid2hctx_seqt) { + if (seqp == hc->tx_seqt) { done = 1; break; } @@ -636,7 +633,6 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) break; ackno = SUB48(ackno_end_rl, 1); - vector++; } if (done) break; @@ -645,11 +641,11 @@ 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_seqt; - while (before48(seqp->ccid2s_seq, hctx->ccid2hctx_high_ack)) { + seqp = hc->tx_seqt; + while (before48(seqp->ccid2s_seq, hc->tx_high_ack)) { seqp = seqp->ccid2s_next; - if (seqp == hctx->ccid2hctx_seqh) { - seqp = hctx->ccid2hctx_seqh->ccid2s_prev; + if (seqp == hc->tx_seqh) { + seqp = hc->tx_seqh->ccid2s_prev; break; } } @@ -660,7 +656,7 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) if (done == NUMDUPACK) break; } - if (seqp == hctx->ccid2hctx_seqt) + if (seqp == hc->tx_seqt) break; seqp = seqp->ccid2s_prev; } @@ -681,125 +677,108 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) * one ack vector. */ ccid2_congestion_event(sk, seqp); - ccid2_hc_tx_dec_pipe(sk); + hc->tx_pipe--; } - if (seqp == hctx->ccid2hctx_seqt) + if (seqp == hc->tx_seqt) break; seqp = seqp->ccid2s_prev; } - hctx->ccid2hctx_seqt = last_acked; + hc->tx_seqt = last_acked; } /* trim acked packets in tail */ - while (hctx->ccid2hctx_seqt != hctx->ccid2hctx_seqh) { - if (!hctx->ccid2hctx_seqt->ccid2s_acked) + while (hc->tx_seqt != hc->tx_seqh) { + if (!hc->tx_seqt->ccid2s_acked) break; - hctx->ccid2hctx_seqt = hctx->ccid2hctx_seqt->ccid2s_next; + hc->tx_seqt = hc->tx_seqt->ccid2s_next; } - ccid2_hc_tx_check_sanity(hctx); + /* restart RTO timer if not all outstanding data has been acked */ + if (hc->tx_pipe == 0) + sk_stop_timer(sk, &hc->tx_rtotimer); + else + sk_reset_timer(sk, &hc->tx_rtotimer, jiffies + hc->tx_rto); +done: + /* check if incoming Acks allow pending packets to be sent */ + if (sender_was_blocked && !ccid2_cwnd_network_limited(hc)) + tasklet_schedule(&dccp_sk(sk)->dccps_xmitlet); + dccp_ackvec_parsed_cleanup(&hc->tx_av_chunks); } static int ccid2_hc_tx_init(struct ccid *ccid, struct sock *sk) { - struct ccid2_hc_tx_sock *hctx = ccid_priv(ccid); + struct ccid2_hc_tx_sock *hc = ccid_priv(ccid); struct dccp_sock *dp = dccp_sk(sk); u32 max_ratio; /* RFC 4341, 5: initialise ssthresh to arbitrarily high (max) value */ - hctx->ccid2hctx_ssthresh = ~0U; + hc->tx_ssthresh = ~0U; - /* - * RFC 4341, 5: "The cwnd parameter is initialized to at most four - * packets for new connections, following the rules from [RFC3390]". - * We need to convert the bytes of RFC3390 into the packets of RFC 4341. - */ - hctx->ccid2hctx_cwnd = min(4U, max(2U, 4380U / dp->dccps_mss_cache)); + /* Use larger initial windows (RFC 4341, section 5). */ + hc->tx_cwnd = rfc3390_bytes_to_packets(dp->dccps_mss_cache); + hc->tx_expected_wnd = hc->tx_cwnd; /* Make sure that Ack Ratio is enabled and within bounds. */ - max_ratio = DIV_ROUND_UP(hctx->ccid2hctx_cwnd, 2); + max_ratio = DIV_ROUND_UP(hc->tx_cwnd, 2); if (dp->dccps_l_ack_ratio == 0 || dp->dccps_l_ack_ratio > max_ratio) dp->dccps_l_ack_ratio = max_ratio; /* XXX init ~ to window size... */ - if (ccid2_hc_tx_alloc_seq(hctx)) + if (ccid2_hc_tx_alloc_seq(hc)) return -ENOMEM; - hctx->ccid2hctx_rto = 3 * HZ; - ccid2_change_srtt(hctx, -1); - hctx->ccid2hctx_rttvar = -1; - hctx->ccid2hctx_rpdupack = -1; - hctx->ccid2hctx_last_cong = jiffies; - setup_timer(&hctx->ccid2hctx_rtotimer, ccid2_hc_tx_rto_expire, + hc->tx_rto = DCCP_TIMEOUT_INIT; + hc->tx_rpdupack = -1; + hc->tx_last_cong = hc->tx_lsndtime = hc->tx_cwnd_stamp = ccid2_time_stamp; + hc->tx_cwnd_used = 0; + setup_timer(&hc->tx_rtotimer, ccid2_hc_tx_rto_expire, (unsigned long)sk); - - ccid2_hc_tx_check_sanity(hctx); + INIT_LIST_HEAD(&hc->tx_av_chunks); return 0; } static void ccid2_hc_tx_exit(struct sock *sk) { - struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk); + struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); int i; - ccid2_hc_tx_kill_rto_timer(sk); + sk_stop_timer(sk, &hc->tx_rtotimer); - for (i = 0; i < hctx->ccid2hctx_seqbufc; i++) - kfree(hctx->ccid2hctx_seqbuf[i]); - hctx->ccid2hctx_seqbufc = 0; + for (i = 0; i < hc->tx_seqbufc; i++) + kfree(hc->tx_seqbuf[i]); + hc->tx_seqbufc = 0; } static void ccid2_hc_rx_packet_recv(struct sock *sk, struct sk_buff *skb) { - const struct dccp_sock *dp = dccp_sk(sk); - struct ccid2_hc_rx_sock *hcrx = ccid2_hc_rx_sk(sk); - - switch (DCCP_SKB_CB(skb)->dccpd_type) { - case DCCP_PKT_DATA: - case DCCP_PKT_DATAACK: - hcrx->ccid2hcrx_data++; - if (hcrx->ccid2hcrx_data >= dp->dccps_r_ack_ratio) { - dccp_send_ack(sk); - hcrx->ccid2hcrx_data = 0; - } - break; + struct ccid2_hc_rx_sock *hc = ccid2_hc_rx_sk(sk); + + if (!dccp_data_packet(skb)) + return; + + if (++hc->rx_num_data_pkts >= dccp_sk(sk)->dccps_r_ack_ratio) { + dccp_send_ack(sk); + hc->rx_num_data_pkts = 0; } } -static struct ccid_operations ccid2 = { - .ccid_id = DCCPC_CCID2, - .ccid_name = "TCP-like", - .ccid_owner = THIS_MODULE, - .ccid_hc_tx_obj_size = sizeof(struct ccid2_hc_tx_sock), - .ccid_hc_tx_init = ccid2_hc_tx_init, - .ccid_hc_tx_exit = ccid2_hc_tx_exit, - .ccid_hc_tx_send_packet = ccid2_hc_tx_send_packet, - .ccid_hc_tx_packet_sent = ccid2_hc_tx_packet_sent, - .ccid_hc_tx_packet_recv = ccid2_hc_tx_packet_recv, - .ccid_hc_rx_obj_size = sizeof(struct ccid2_hc_rx_sock), - .ccid_hc_rx_packet_recv = ccid2_hc_rx_packet_recv, +struct ccid_operations ccid2_ops = { + .ccid_id = DCCPC_CCID2, + .ccid_name = "TCP-like", + .ccid_hc_tx_obj_size = sizeof(struct ccid2_hc_tx_sock), + .ccid_hc_tx_init = ccid2_hc_tx_init, + .ccid_hc_tx_exit = ccid2_hc_tx_exit, + .ccid_hc_tx_send_packet = ccid2_hc_tx_send_packet, + .ccid_hc_tx_packet_sent = ccid2_hc_tx_packet_sent, + .ccid_hc_tx_parse_options = ccid2_hc_tx_parse_options, + .ccid_hc_tx_packet_recv = ccid2_hc_tx_packet_recv, + .ccid_hc_rx_obj_size = sizeof(struct ccid2_hc_rx_sock), + .ccid_hc_rx_packet_recv = ccid2_hc_rx_packet_recv, }; #ifdef CONFIG_IP_DCCP_CCID2_DEBUG -module_param(ccid2_debug, bool, 0444); -MODULE_PARM_DESC(ccid2_debug, "Enable debug messages"); +module_param(ccid2_debug, bool, 0644); +MODULE_PARM_DESC(ccid2_debug, "Enable CCID-2 debug messages"); #endif - -static __init int ccid2_module_init(void) -{ - return ccid_register(&ccid2); -} -module_init(ccid2_module_init); - -static __exit void ccid2_module_exit(void) -{ - ccid_unregister(&ccid2); -} -module_exit(ccid2_module_exit); - -MODULE_AUTHOR("Andrea Bittau <a.bittau@cs.ucl.ac.uk>"); -MODULE_DESCRIPTION("DCCP TCP-Like (CCID2) CCID"); -MODULE_LICENSE("GPL"); -MODULE_ALIAS("net-dccp-ccid-2"); diff --git a/net/dccp/ccids/ccid2.h b/net/dccp/ccids/ccid2.h index 2c94ca02901..18c97543e52 100644 --- a/net/dccp/ccids/ccid2.h +++ b/net/dccp/ccids/ccid2.h @@ -1,6 +1,4 @@ /* - * net/dccp/ccids/ccid2.h - * * Copyright (c) 2005 Andrea Bittau <a.bittau@cs.ucl.ac.uk> * * This program is free software; you can redistribute it and/or modify @@ -20,18 +18,23 @@ #ifndef _DCCP_CCID2_H_ #define _DCCP_CCID2_H_ -#include <linux/dccp.h> #include <linux/timer.h> #include <linux/types.h> #include "../ccid.h" +#include "../dccp.h" + +/* + * CCID-2 timestamping faces the same issues as TCP timestamping. + * Hence we reuse/share as much of the code as possible. + */ +#define ccid2_time_stamp tcp_time_stamp + /* NUMDUPACK parameter from RFC 4341, p. 6 */ #define NUMDUPACK 3 -struct sock; - struct ccid2_seq { u64 ccid2s_seq; - unsigned long ccid2s_sent; + u32 ccid2s_sent; int ccid2s_acked; struct ccid2_seq *ccid2s_prev; struct ccid2_seq *ccid2s_next; @@ -40,36 +43,82 @@ struct ccid2_seq { #define CCID2_SEQBUF_LEN 1024 #define CCID2_SEQBUF_MAX 128 -/** struct ccid2_hc_tx_sock - CCID2 TX half connection - * - * @ccid2hctx_{cwnd,ssthresh,pipe}: as per RFC 4341, section 5 - * @ccid2hctx_packets_acked - Ack counter for deriving cwnd growth (RFC 3465) - * @ccid2hctx_lastrtt -time RTT was last measured - * @ccid2hctx_rpseq - last consecutive seqno - * @ccid2hctx_rpdupack - dupacks since rpseq -*/ +/* + * Multiple of congestion window to keep the sequence window at + * (RFC 4340 7.5.2) + */ +#define CCID2_WIN_CHANGE_FACTOR 5 + +/** + * struct ccid2_hc_tx_sock - CCID2 TX half connection + * @tx_{cwnd,ssthresh,pipe}: as per RFC 4341, section 5 + * @tx_packets_acked: Ack counter for deriving cwnd growth (RFC 3465) + * @tx_srtt: smoothed RTT estimate, scaled by 2^3 + * @tx_mdev: smoothed RTT variation, scaled by 2^2 + * @tx_mdev_max: maximum of @mdev during one flight + * @tx_rttvar: moving average/maximum of @mdev_max + * @tx_rto: RTO value deriving from SRTT and RTTVAR (RFC 2988) + * @tx_rtt_seq: to decay RTTVAR at most once per flight + * @tx_cwnd_used: actually used cwnd, W_used of RFC 2861 + * @tx_expected_wnd: moving average of @tx_cwnd_used + * @tx_cwnd_stamp: to track idle periods in CWV + * @tx_lsndtime: last time (in jiffies) a data packet was sent + * @tx_rpseq: last consecutive seqno + * @tx_rpdupack: dupacks since rpseq + * @tx_av_chunks: list of Ack Vectors received on current skb + */ struct ccid2_hc_tx_sock { - u32 ccid2hctx_cwnd; - u32 ccid2hctx_ssthresh; - u32 ccid2hctx_pipe; - u32 ccid2hctx_packets_acked; - struct ccid2_seq *ccid2hctx_seqbuf[CCID2_SEQBUF_MAX]; - int ccid2hctx_seqbufc; - struct ccid2_seq *ccid2hctx_seqh; - struct ccid2_seq *ccid2hctx_seqt; - long ccid2hctx_rto; - long ccid2hctx_srtt; - long ccid2hctx_rttvar; - unsigned long ccid2hctx_lastrtt; - struct timer_list ccid2hctx_rtotimer; - u64 ccid2hctx_rpseq; - int ccid2hctx_rpdupack; - unsigned long ccid2hctx_last_cong; - u64 ccid2hctx_high_ack; + u32 tx_cwnd; + u32 tx_ssthresh; + u32 tx_pipe; + u32 tx_packets_acked; + struct ccid2_seq *tx_seqbuf[CCID2_SEQBUF_MAX]; + int tx_seqbufc; + struct ccid2_seq *tx_seqh; + struct ccid2_seq *tx_seqt; + + /* RTT measurement: variables/principles are the same as in TCP */ + u32 tx_srtt, + tx_mdev, + tx_mdev_max, + tx_rttvar, + tx_rto; + u64 tx_rtt_seq:48; + struct timer_list tx_rtotimer; + + /* Congestion Window validation (optional, RFC 2861) */ + u32 tx_cwnd_used, + tx_expected_wnd, + tx_cwnd_stamp, + tx_lsndtime; + + u64 tx_rpseq; + int tx_rpdupack; + u32 tx_last_cong; + u64 tx_high_ack; + struct list_head tx_av_chunks; }; +static inline bool ccid2_cwnd_network_limited(struct ccid2_hc_tx_sock *hc) +{ + return hc->tx_pipe >= hc->tx_cwnd; +} + +/* + * Convert RFC 3390 larger initial window into an equivalent number of packets. + * This is based on the numbers specified in RFC 5681, 3.1. + */ +static inline u32 rfc3390_bytes_to_packets(const u32 smss) +{ + return smss <= 1095 ? 4 : (smss > 2190 ? 2 : 3); +} + +/** + * struct ccid2_hc_rx_sock - Receiving end of CCID-2 half-connection + * @rx_num_data_pkts: number of data packets received since last feedback + */ struct ccid2_hc_rx_sock { - int ccid2hcrx_data; + u32 rx_num_data_pkts; }; static inline struct ccid2_hc_tx_sock *ccid2_hc_tx_sk(const struct sock *sk) diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c index e76f460af0e..119c04317d4 100644 --- a/net/dccp/ccids/ccid3.c +++ b/net/dccp/ccids/ccid3.c @@ -1,6 +1,4 @@ /* - * net/dccp/ccids/ccid3.c - * * Copyright (c) 2007 The University of Aberdeen, Scotland, UK * Copyright (c) 2005-7 The University of Waikato, Hamilton, New Zealand. * Copyright (c) 2005-7 Ian McDonald <ian.mcdonald@jandi.co.nz> @@ -40,7 +38,7 @@ #include <asm/unaligned.h> #ifdef CONFIG_IP_DCCP_CCID3_DEBUG -static int ccid3_debug; +static bool ccid3_debug; #define ccid3_pr_debug(format, a...) DCCP_PR_DEBUG(ccid3_debug, format, ##a) #else #define ccid3_pr_debug(format, a...) @@ -52,11 +50,10 @@ static int ccid3_debug; #ifdef CONFIG_IP_DCCP_CCID3_DEBUG static const char *ccid3_tx_state_name(enum ccid3_hc_tx_states state) { - static char *ccid3_state_names[] = { + static const char *const ccid3_state_names[] = { [TFRC_SSTATE_NO_SENT] = "NO_SENT", [TFRC_SSTATE_NO_FBACK] = "NO_FBACK", [TFRC_SSTATE_FBACK] = "FBACK", - [TFRC_SSTATE_TERM] = "TERM", }; return ccid3_state_names[state]; @@ -66,14 +63,14 @@ static const char *ccid3_tx_state_name(enum ccid3_hc_tx_states state) static void ccid3_hc_tx_set_state(struct sock *sk, enum ccid3_hc_tx_states state) { - struct ccid3_hc_tx_sock *hctx = ccid3_hc_tx_sk(sk); - enum ccid3_hc_tx_states oldstate = hctx->ccid3hctx_state; + struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk); + enum ccid3_hc_tx_states oldstate = hc->tx_state; ccid3_pr_debug("%s(%p) %-8.8s -> %s\n", dccp_role(sk), sk, ccid3_tx_state_name(oldstate), ccid3_tx_state_name(state)); WARN_ON(state == oldstate); - hctx->ccid3hctx_state = state; + hc->tx_state = state; } /* @@ -87,42 +84,36 @@ static void ccid3_hc_tx_set_state(struct sock *sk, */ static inline u64 rfc3390_initial_rate(struct sock *sk) { - const struct ccid3_hc_tx_sock *hctx = ccid3_hc_tx_sk(sk); - const __u32 w_init = min_t(__u32, 4 * hctx->ccid3hctx_s, - max_t(__u32, 2 * hctx->ccid3hctx_s, 4380)); + const struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk); + const __u32 w_init = clamp_t(__u32, 4380U, 2 * hc->tx_s, 4 * hc->tx_s); - return scaled_div(w_init << 6, hctx->ccid3hctx_rtt); + return scaled_div(w_init << 6, hc->tx_rtt); } -/* - * Recalculate t_ipi and delta (should be called whenever X changes) +/** + * ccid3_update_send_interval - Calculate new t_ipi = s / X_inst + * This respects the granularity of X_inst (64 * bytes/second). */ -static void ccid3_update_send_interval(struct ccid3_hc_tx_sock *hctx) +static void ccid3_update_send_interval(struct ccid3_hc_tx_sock *hc) { - /* Calculate new t_ipi = s / X_inst (X_inst is in 64 * bytes/second) */ - hctx->ccid3hctx_t_ipi = scaled_div32(((u64)hctx->ccid3hctx_s) << 6, - hctx->ccid3hctx_x); - - /* Calculate new delta by delta = min(t_ipi / 2, t_gran / 2) */ - hctx->ccid3hctx_delta = min_t(u32, hctx->ccid3hctx_t_ipi / 2, - TFRC_OPSYS_HALF_TIME_GRAN); - - ccid3_pr_debug("t_ipi=%u, delta=%u, s=%u, X=%u\n", - hctx->ccid3hctx_t_ipi, hctx->ccid3hctx_delta, - hctx->ccid3hctx_s, (unsigned)(hctx->ccid3hctx_x >> 6)); + hc->tx_t_ipi = scaled_div32(((u64)hc->tx_s) << 6, hc->tx_x); + DCCP_BUG_ON(hc->tx_t_ipi == 0); + ccid3_pr_debug("t_ipi=%u, s=%u, X=%u\n", hc->tx_t_ipi, + hc->tx_s, (unsigned int)(hc->tx_x >> 6)); } -static u32 ccid3_hc_tx_idle_rtt(struct ccid3_hc_tx_sock *hctx, ktime_t now) +static u32 ccid3_hc_tx_idle_rtt(struct ccid3_hc_tx_sock *hc, ktime_t now) { - u32 delta = ktime_us_delta(now, hctx->ccid3hctx_t_last_win_count); + u32 delta = ktime_us_delta(now, hc->tx_t_last_win_count); - return delta / hctx->ccid3hctx_rtt; + return delta / hc->tx_rtt; } /** * ccid3_hc_tx_update_x - Update allowed sending rate X * @stamp: most recent time if available - can be left NULL. + * * This function tracks draft rfc3448bis, check there for latest details. * * Note: X and X_recv are both stored in units of 64 * bytes/second, to support @@ -132,9 +123,9 @@ static u32 ccid3_hc_tx_idle_rtt(struct ccid3_hc_tx_sock *hctx, ktime_t now) */ static void ccid3_hc_tx_update_x(struct sock *sk, ktime_t *stamp) { - struct ccid3_hc_tx_sock *hctx = ccid3_hc_tx_sk(sk); - __u64 min_rate = 2 * hctx->ccid3hctx_x_recv; - const __u64 old_x = hctx->ccid3hctx_x; + struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk); + __u64 min_rate = 2 * hc->tx_x_recv; + const __u64 old_x = hc->tx_x; ktime_t now = stamp ? *stamp : ktime_get_real(); /* @@ -143,80 +134,71 @@ static void ccid3_hc_tx_update_x(struct sock *sk, ktime_t *stamp) * a sender is idle if it has not sent anything over a 2-RTT-period. * For consistency with X and X_recv, min_rate is also scaled by 2^6. */ - if (ccid3_hc_tx_idle_rtt(hctx, now) >= 2) { + if (ccid3_hc_tx_idle_rtt(hc, now) >= 2) { min_rate = rfc3390_initial_rate(sk); - min_rate = max(min_rate, 2 * hctx->ccid3hctx_x_recv); + min_rate = max(min_rate, 2 * hc->tx_x_recv); } - if (hctx->ccid3hctx_p > 0) { + if (hc->tx_p > 0) { - hctx->ccid3hctx_x = min(((__u64)hctx->ccid3hctx_x_calc) << 6, - min_rate); - hctx->ccid3hctx_x = max(hctx->ccid3hctx_x, - (((__u64)hctx->ccid3hctx_s) << 6) / - TFRC_T_MBI); + hc->tx_x = min(((__u64)hc->tx_x_calc) << 6, min_rate); + hc->tx_x = max(hc->tx_x, (((__u64)hc->tx_s) << 6) / TFRC_T_MBI); - } else if (ktime_us_delta(now, hctx->ccid3hctx_t_ld) - - (s64)hctx->ccid3hctx_rtt >= 0) { + } else if (ktime_us_delta(now, hc->tx_t_ld) - (s64)hc->tx_rtt >= 0) { - hctx->ccid3hctx_x = - max(min(2 * hctx->ccid3hctx_x, min_rate), - scaled_div(((__u64)hctx->ccid3hctx_s) << 6, - hctx->ccid3hctx_rtt)); - hctx->ccid3hctx_t_ld = now; + hc->tx_x = min(2 * hc->tx_x, min_rate); + hc->tx_x = max(hc->tx_x, + scaled_div(((__u64)hc->tx_s) << 6, hc->tx_rtt)); + hc->tx_t_ld = now; } - if (hctx->ccid3hctx_x != old_x) { + if (hc->tx_x != old_x) { ccid3_pr_debug("X_prev=%u, X_now=%u, X_calc=%u, " - "X_recv=%u\n", (unsigned)(old_x >> 6), - (unsigned)(hctx->ccid3hctx_x >> 6), - hctx->ccid3hctx_x_calc, - (unsigned)(hctx->ccid3hctx_x_recv >> 6)); + "X_recv=%u\n", (unsigned int)(old_x >> 6), + (unsigned int)(hc->tx_x >> 6), hc->tx_x_calc, + (unsigned int)(hc->tx_x_recv >> 6)); - ccid3_update_send_interval(hctx); + ccid3_update_send_interval(hc); } } -/* - * Track the mean packet size `s' (cf. RFC 4342, 5.3 and RFC 3448, 4.1) +/** + * ccid3_hc_tx_update_s - Track the mean packet size `s' * @len: DCCP packet payload size in bytes + * + * cf. RFC 4342, 5.3 and RFC 3448, 4.1 */ -static inline void ccid3_hc_tx_update_s(struct ccid3_hc_tx_sock *hctx, int len) +static inline void ccid3_hc_tx_update_s(struct ccid3_hc_tx_sock *hc, int len) { - const u16 old_s = hctx->ccid3hctx_s; + const u16 old_s = hc->tx_s; - hctx->ccid3hctx_s = tfrc_ewma(hctx->ccid3hctx_s, len, 9); + hc->tx_s = tfrc_ewma(hc->tx_s, len, 9); - if (hctx->ccid3hctx_s != old_s) - ccid3_update_send_interval(hctx); + if (hc->tx_s != old_s) + ccid3_update_send_interval(hc); } /* * Update Window Counter using the algorithm from [RFC 4342, 8.1]. - * The algorithm is not applicable if RTT < 4 microseconds. + * As elsewhere, RTT > 0 is assumed by using dccp_sample_rtt(). */ -static inline void ccid3_hc_tx_update_win_count(struct ccid3_hc_tx_sock *hctx, +static inline void ccid3_hc_tx_update_win_count(struct ccid3_hc_tx_sock *hc, ktime_t now) { - u32 quarter_rtts; - - if (unlikely(hctx->ccid3hctx_rtt < 4)) /* avoid divide-by-zero */ - return; - - quarter_rtts = ktime_us_delta(now, hctx->ccid3hctx_t_last_win_count); - quarter_rtts /= hctx->ccid3hctx_rtt / 4; + u32 delta = ktime_us_delta(now, hc->tx_t_last_win_count), + quarter_rtts = (4 * delta) / hc->tx_rtt; if (quarter_rtts > 0) { - hctx->ccid3hctx_t_last_win_count = now; - hctx->ccid3hctx_last_win_count += min_t(u32, quarter_rtts, 5); - hctx->ccid3hctx_last_win_count &= 0xF; /* mod 16 */ + hc->tx_t_last_win_count = now; + hc->tx_last_win_count += min(quarter_rtts, 5U); + hc->tx_last_win_count &= 0xF; /* mod 16 */ } } static void ccid3_hc_tx_no_feedback_timer(unsigned long data) { struct sock *sk = (struct sock *)data; - struct ccid3_hc_tx_sock *hctx = ccid3_hc_tx_sk(sk); + struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk); unsigned long t_nfb = USEC_PER_SEC / 5; bh_lock_sock(sk); @@ -226,25 +208,27 @@ static void ccid3_hc_tx_no_feedback_timer(unsigned long data) goto restart_timer; } - ccid3_pr_debug("%s(%p, state=%s) - entry \n", dccp_role(sk), sk, - ccid3_tx_state_name(hctx->ccid3hctx_state)); + ccid3_pr_debug("%s(%p, state=%s) - entry\n", dccp_role(sk), sk, + ccid3_tx_state_name(hc->tx_state)); - if (hctx->ccid3hctx_state == TFRC_SSTATE_FBACK) - ccid3_hc_tx_set_state(sk, TFRC_SSTATE_NO_FBACK); - else if (hctx->ccid3hctx_state != TFRC_SSTATE_NO_FBACK) + /* Ignore and do not restart after leaving the established state */ + if ((1 << sk->sk_state) & ~(DCCPF_OPEN | DCCPF_PARTOPEN)) goto out; + /* Reset feedback state to "no feedback received" */ + if (hc->tx_state == TFRC_SSTATE_FBACK) + ccid3_hc_tx_set_state(sk, TFRC_SSTATE_NO_FBACK); + /* * Determine new allowed sending rate X as per draft rfc3448bis-00, 4.4 + * RTO is 0 if and only if no feedback has been received yet. */ - if (hctx->ccid3hctx_t_rto == 0 || /* no feedback received yet */ - hctx->ccid3hctx_p == 0) { + if (hc->tx_t_rto == 0 || hc->tx_p == 0) { /* halve send rate directly */ - hctx->ccid3hctx_x = max(hctx->ccid3hctx_x / 2, - (((__u64)hctx->ccid3hctx_s) << 6) / - TFRC_T_MBI); - ccid3_update_send_interval(hctx); + hc->tx_x = max(hc->tx_x / 2, + (((__u64)hc->tx_s) << 6) / TFRC_T_MBI); + ccid3_update_send_interval(hc); } else { /* * Modify the cached value of X_recv @@ -256,49 +240,47 @@ static void ccid3_hc_tx_no_feedback_timer(unsigned long data) * * Note that X_recv is scaled by 2^6 while X_calc is not */ - BUG_ON(hctx->ccid3hctx_p && !hctx->ccid3hctx_x_calc); - - if (hctx->ccid3hctx_x_calc > (hctx->ccid3hctx_x_recv >> 5)) - hctx->ccid3hctx_x_recv = - max(hctx->ccid3hctx_x_recv / 2, - (((__u64)hctx->ccid3hctx_s) << 6) / - (2 * TFRC_T_MBI)); + if (hc->tx_x_calc > (hc->tx_x_recv >> 5)) + hc->tx_x_recv = + max(hc->tx_x_recv / 2, + (((__u64)hc->tx_s) << 6) / (2*TFRC_T_MBI)); else { - hctx->ccid3hctx_x_recv = hctx->ccid3hctx_x_calc; - hctx->ccid3hctx_x_recv <<= 4; + hc->tx_x_recv = hc->tx_x_calc; + hc->tx_x_recv <<= 4; } ccid3_hc_tx_update_x(sk, NULL); } ccid3_pr_debug("Reduced X to %llu/64 bytes/sec\n", - (unsigned long long)hctx->ccid3hctx_x); + (unsigned long long)hc->tx_x); /* * Set new timeout for the nofeedback timer. * See comments in packet_recv() regarding the value of t_RTO. */ - if (unlikely(hctx->ccid3hctx_t_rto == 0)) /* no feedback yet */ + if (unlikely(hc->tx_t_rto == 0)) /* no feedback received yet */ t_nfb = TFRC_INITIAL_TIMEOUT; else - t_nfb = max(hctx->ccid3hctx_t_rto, 2 * hctx->ccid3hctx_t_ipi); + t_nfb = max(hc->tx_t_rto, 2 * hc->tx_t_ipi); restart_timer: - sk_reset_timer(sk, &hctx->ccid3hctx_no_feedback_timer, + sk_reset_timer(sk, &hc->tx_no_feedback_timer, jiffies + usecs_to_jiffies(t_nfb)); out: bh_unlock_sock(sk); sock_put(sk); } -/* - * returns - * > 0: delay (in msecs) that should pass before actually sending - * = 0: can send immediately - * < 0: error condition; do not send packet +/** + * ccid3_hc_tx_send_packet - Delay-based dequeueing of TX packets + * @skb: next packet candidate to send on @sk + * + * This function uses the convention of ccid_packet_dequeue_eval() and + * returns a millisecond-delay value between 0 and t_mbi = 64000 msec. */ static int ccid3_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb) { struct dccp_sock *dp = dccp_sk(sk); - struct ccid3_hc_tx_sock *hctx = ccid3_hc_tx_sk(sk); + struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk); ktime_t now = ktime_get_real(); s64 delay; @@ -310,18 +292,16 @@ static int ccid3_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb) if (unlikely(skb->len == 0)) return -EBADMSG; - switch (hctx->ccid3hctx_state) { - case TFRC_SSTATE_NO_SENT: - sk_reset_timer(sk, &hctx->ccid3hctx_no_feedback_timer, - (jiffies + - usecs_to_jiffies(TFRC_INITIAL_TIMEOUT))); - hctx->ccid3hctx_last_win_count = 0; - hctx->ccid3hctx_t_last_win_count = now; + if (hc->tx_state == TFRC_SSTATE_NO_SENT) { + sk_reset_timer(sk, &hc->tx_no_feedback_timer, (jiffies + + usecs_to_jiffies(TFRC_INITIAL_TIMEOUT))); + hc->tx_last_win_count = 0; + hc->tx_t_last_win_count = now; /* Set t_0 for initial packet */ - hctx->ccid3hctx_t_nom = now; + hc->tx_t_nom = now; - hctx->ccid3hctx_s = skb->len; + hc->tx_s = skb->len; /* * Use initial RTT sample when available: recommended by erratum @@ -330,123 +310,108 @@ static int ccid3_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb) */ if (dp->dccps_syn_rtt) { ccid3_pr_debug("SYN RTT = %uus\n", dp->dccps_syn_rtt); - hctx->ccid3hctx_rtt = dp->dccps_syn_rtt; - hctx->ccid3hctx_x = rfc3390_initial_rate(sk); - hctx->ccid3hctx_t_ld = now; + hc->tx_rtt = dp->dccps_syn_rtt; + hc->tx_x = rfc3390_initial_rate(sk); + hc->tx_t_ld = now; } else { - /* Sender does not have RTT sample: X_pps = 1 pkt/sec */ - hctx->ccid3hctx_x = hctx->ccid3hctx_s; - hctx->ccid3hctx_x <<= 6; + /* + * Sender does not have RTT sample: + * - set fallback RTT (RFC 4340, 3.4) since a RTT value + * is needed in several parts (e.g. window counter); + * - set sending rate X_pps = 1pps as per RFC 3448, 4.2. + */ + hc->tx_rtt = DCCP_FALLBACK_RTT; + hc->tx_x = hc->tx_s; + hc->tx_x <<= 6; } - ccid3_update_send_interval(hctx); + ccid3_update_send_interval(hc); ccid3_hc_tx_set_state(sk, TFRC_SSTATE_NO_FBACK); - break; - case TFRC_SSTATE_NO_FBACK: - case TFRC_SSTATE_FBACK: - delay = ktime_us_delta(hctx->ccid3hctx_t_nom, now); + + } else { + delay = ktime_us_delta(hc->tx_t_nom, now); ccid3_pr_debug("delay=%ld\n", (long)delay); /* - * Scheduling of packet transmissions [RFC 3448, 4.6] + * Scheduling of packet transmissions (RFC 5348, 8.3) * * if (t_now > t_nom - delta) * // send the packet now * else * // send the packet in (t_nom - t_now) milliseconds. */ - if (delay - (s64)hctx->ccid3hctx_delta >= 1000) - return (u32)delay / 1000L; + if (delay >= TFRC_T_DELTA) + return (u32)delay / USEC_PER_MSEC; - ccid3_hc_tx_update_win_count(hctx, now); - break; - case TFRC_SSTATE_TERM: - DCCP_BUG("%s(%p) - Illegal state TERM", dccp_role(sk), sk); - return -EINVAL; + ccid3_hc_tx_update_win_count(hc, now); } /* prepare to send now (add options etc.) */ dp->dccps_hc_tx_insert_options = 1; - DCCP_SKB_CB(skb)->dccpd_ccval = hctx->ccid3hctx_last_win_count; + DCCP_SKB_CB(skb)->dccpd_ccval = hc->tx_last_win_count; /* set the nominal send time for the next following packet */ - hctx->ccid3hctx_t_nom = ktime_add_us(hctx->ccid3hctx_t_nom, - hctx->ccid3hctx_t_ipi); - return 0; + hc->tx_t_nom = ktime_add_us(hc->tx_t_nom, hc->tx_t_ipi); + return CCID_PACKET_SEND_AT_ONCE; } -static void ccid3_hc_tx_packet_sent(struct sock *sk, int more, - unsigned int len) +static void ccid3_hc_tx_packet_sent(struct sock *sk, unsigned int len) { - struct ccid3_hc_tx_sock *hctx = ccid3_hc_tx_sk(sk); + struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk); - ccid3_hc_tx_update_s(hctx, len); + ccid3_hc_tx_update_s(hc, len); - if (tfrc_tx_hist_add(&hctx->ccid3hctx_hist, dccp_sk(sk)->dccps_gss)) + if (tfrc_tx_hist_add(&hc->tx_hist, dccp_sk(sk)->dccps_gss)) DCCP_CRIT("packet history - out of memory!"); } static void ccid3_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) { - struct ccid3_hc_tx_sock *hctx = ccid3_hc_tx_sk(sk); - struct ccid3_options_received *opt_recv; + struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk); + struct tfrc_tx_hist_entry *acked; ktime_t now; unsigned long t_nfb; - u32 pinv, r_sample; + u32 r_sample; /* we are only interested in ACKs */ if (!(DCCP_SKB_CB(skb)->dccpd_type == DCCP_PKT_ACK || DCCP_SKB_CB(skb)->dccpd_type == DCCP_PKT_DATAACK)) return; - /* ... and only in the established state */ - if (hctx->ccid3hctx_state != TFRC_SSTATE_FBACK && - hctx->ccid3hctx_state != TFRC_SSTATE_NO_FBACK) - return; - - opt_recv = &hctx->ccid3hctx_options_received; - now = ktime_get_real(); - - /* Estimate RTT from history if ACK number is valid */ - r_sample = tfrc_tx_hist_rtt(hctx->ccid3hctx_hist, - DCCP_SKB_CB(skb)->dccpd_ack_seq, now); - if (r_sample == 0) { - DCCP_WARN("%s(%p): %s with bogus ACK-%llu\n", dccp_role(sk), sk, - dccp_packet_name(DCCP_SKB_CB(skb)->dccpd_type), - (unsigned long long)DCCP_SKB_CB(skb)->dccpd_ack_seq); + /* + * Locate the acknowledged packet in the TX history. + * + * Returning "entry not found" here can for instance happen when + * - the host has not sent out anything (e.g. a passive server), + * - the Ack is outdated (packet with higher Ack number was received), + * - it is a bogus Ack (for a packet not sent on this connection). + */ + acked = tfrc_tx_hist_find_entry(hc->tx_hist, dccp_hdr_ack_seq(skb)); + if (acked == NULL) return; - } + /* For the sake of RTT sampling, ignore/remove all older entries */ + tfrc_tx_hist_purge(&acked->next); - /* Update receive rate in units of 64 * bytes/second */ - hctx->ccid3hctx_x_recv = opt_recv->ccid3or_receive_rate; - hctx->ccid3hctx_x_recv <<= 6; + /* Update the moving average for the RTT estimate (RFC 3448, 4.3) */ + now = ktime_get_real(); + r_sample = dccp_sample_rtt(sk, ktime_us_delta(now, acked->stamp)); + hc->tx_rtt = tfrc_ewma(hc->tx_rtt, r_sample, 9); - /* Update loss event rate (which is scaled by 1e6) */ - pinv = opt_recv->ccid3or_loss_event_rate; - if (pinv == ~0U || pinv == 0) /* see RFC 4342, 8.5 */ - hctx->ccid3hctx_p = 0; - else /* can not exceed 100% */ - hctx->ccid3hctx_p = scaled_div(1, pinv); - /* - * Validate new RTT sample and update moving average - */ - r_sample = dccp_sample_rtt(sk, r_sample); - hctx->ccid3hctx_rtt = tfrc_ewma(hctx->ccid3hctx_rtt, r_sample, 9); /* * Update allowed sending rate X as per draft rfc3448bis-00, 4.2/3 */ - if (hctx->ccid3hctx_state == TFRC_SSTATE_NO_FBACK) { + if (hc->tx_state == TFRC_SSTATE_NO_FBACK) { ccid3_hc_tx_set_state(sk, TFRC_SSTATE_FBACK); - if (hctx->ccid3hctx_t_rto == 0) { + if (hc->tx_t_rto == 0) { /* * Initial feedback packet: Larger Initial Windows (4.2) */ - hctx->ccid3hctx_x = rfc3390_initial_rate(sk); - hctx->ccid3hctx_t_ld = now; + hc->tx_x = rfc3390_initial_rate(sk); + hc->tx_t_ld = now; - ccid3_update_send_interval(hctx); + ccid3_update_send_interval(hc); goto done_computing_x; - } else if (hctx->ccid3hctx_p == 0) { + } else if (hc->tx_p == 0) { /* * First feedback after nofeedback timer expiry (4.3) */ @@ -455,25 +420,20 @@ static void ccid3_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) } /* Update sending rate (step 4 of [RFC 3448, 4.3]) */ - if (hctx->ccid3hctx_p > 0) - hctx->ccid3hctx_x_calc = - tfrc_calc_x(hctx->ccid3hctx_s, - hctx->ccid3hctx_rtt, - hctx->ccid3hctx_p); + if (hc->tx_p > 0) + hc->tx_x_calc = tfrc_calc_x(hc->tx_s, hc->tx_rtt, hc->tx_p); ccid3_hc_tx_update_x(sk, &now); done_computing_x: ccid3_pr_debug("%s(%p), RTT=%uus (sample=%uus), s=%u, " "p=%u, X_calc=%u, X_recv=%u, X=%u\n", - dccp_role(sk), - sk, hctx->ccid3hctx_rtt, r_sample, - hctx->ccid3hctx_s, hctx->ccid3hctx_p, - hctx->ccid3hctx_x_calc, - (unsigned)(hctx->ccid3hctx_x_recv >> 6), - (unsigned)(hctx->ccid3hctx_x >> 6)); + dccp_role(sk), sk, hc->tx_rtt, r_sample, + hc->tx_s, hc->tx_p, hc->tx_x_calc, + (unsigned int)(hc->tx_x_recv >> 6), + (unsigned int)(hc->tx_x >> 6)); /* unschedule no feedback timer */ - sk_stop_timer(sk, &hctx->ccid3hctx_no_feedback_timer); + sk_stop_timer(sk, &hc->tx_no_feedback_timer); /* * As we have calculated new ipi, delta, t_nom it is possible @@ -482,143 +442,109 @@ done_computing_x: sk->sk_write_space(sk); /* - * Update timeout interval for the nofeedback timer. - * We use a configuration option to increase the lower bound. - * This can help avoid triggering the nofeedback timer too - * often ('spinning') on LANs with small RTTs. + * Update timeout interval for the nofeedback timer. In order to control + * rate halving on networks with very low RTTs (<= 1 ms), use per-route + * tunable RTAX_RTO_MIN value as the lower bound. */ - hctx->ccid3hctx_t_rto = max_t(u32, 4 * hctx->ccid3hctx_rtt, - (CONFIG_IP_DCCP_CCID3_RTO * - (USEC_PER_SEC / 1000))); + hc->tx_t_rto = max_t(u32, 4 * hc->tx_rtt, + USEC_PER_SEC/HZ * tcp_rto_min(sk)); /* * Schedule no feedback timer to expire in * max(t_RTO, 2 * s/X) = max(t_RTO, 2 * t_ipi) */ - t_nfb = max(hctx->ccid3hctx_t_rto, 2 * hctx->ccid3hctx_t_ipi); + t_nfb = max(hc->tx_t_rto, 2 * hc->tx_t_ipi); ccid3_pr_debug("%s(%p), Scheduled no feedback timer to " "expire in %lu jiffies (%luus)\n", - dccp_role(sk), - sk, usecs_to_jiffies(t_nfb), t_nfb); + dccp_role(sk), sk, usecs_to_jiffies(t_nfb), t_nfb); - sk_reset_timer(sk, &hctx->ccid3hctx_no_feedback_timer, + sk_reset_timer(sk, &hc->tx_no_feedback_timer, jiffies + usecs_to_jiffies(t_nfb)); } -static int ccid3_hc_tx_parse_options(struct sock *sk, unsigned char option, - unsigned char len, u16 idx, - unsigned char *value) +static int ccid3_hc_tx_parse_options(struct sock *sk, u8 packet_type, + u8 option, u8 *optval, u8 optlen) { - int rc = 0; - const struct dccp_sock *dp = dccp_sk(sk); - struct ccid3_hc_tx_sock *hctx = ccid3_hc_tx_sk(sk); - struct ccid3_options_received *opt_recv; + struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk); __be32 opt_val; - opt_recv = &hctx->ccid3hctx_options_received; - - if (opt_recv->ccid3or_seqno != dp->dccps_gsr) { - opt_recv->ccid3or_seqno = dp->dccps_gsr; - opt_recv->ccid3or_loss_event_rate = ~0; - opt_recv->ccid3or_loss_intervals_idx = 0; - opt_recv->ccid3or_loss_intervals_len = 0; - opt_recv->ccid3or_receive_rate = 0; - } - switch (option) { + case TFRC_OPT_RECEIVE_RATE: case TFRC_OPT_LOSS_EVENT_RATE: - if (unlikely(len != 4)) { - DCCP_WARN("%s(%p), invalid len %d " - "for TFRC_OPT_LOSS_EVENT_RATE\n", - dccp_role(sk), sk, len); - rc = -EINVAL; - } else { - opt_val = get_unaligned((__be32 *)value); - opt_recv->ccid3or_loss_event_rate = ntohl(opt_val); - ccid3_pr_debug("%s(%p), LOSS_EVENT_RATE=%u\n", - dccp_role(sk), sk, - opt_recv->ccid3or_loss_event_rate); + /* Must be ignored on Data packets, cf. RFC 4342 8.3 and 8.5 */ + if (packet_type == DCCP_PKT_DATA) + break; + if (unlikely(optlen != 4)) { + DCCP_WARN("%s(%p), invalid len %d for %u\n", + dccp_role(sk), sk, optlen, option); + return -EINVAL; } - break; - case TFRC_OPT_LOSS_INTERVALS: - opt_recv->ccid3or_loss_intervals_idx = idx; - opt_recv->ccid3or_loss_intervals_len = len; - ccid3_pr_debug("%s(%p), LOSS_INTERVALS=(%u, %u)\n", - dccp_role(sk), sk, - opt_recv->ccid3or_loss_intervals_idx, - opt_recv->ccid3or_loss_intervals_len); - break; - case TFRC_OPT_RECEIVE_RATE: - if (unlikely(len != 4)) { - DCCP_WARN("%s(%p), invalid len %d " - "for TFRC_OPT_RECEIVE_RATE\n", - dccp_role(sk), sk, len); - rc = -EINVAL; - } else { - opt_val = get_unaligned((__be32 *)value); - opt_recv->ccid3or_receive_rate = ntohl(opt_val); + opt_val = ntohl(get_unaligned((__be32 *)optval)); + + if (option == TFRC_OPT_RECEIVE_RATE) { + /* Receive Rate is kept in units of 64 bytes/second */ + hc->tx_x_recv = opt_val; + hc->tx_x_recv <<= 6; + ccid3_pr_debug("%s(%p), RECEIVE_RATE=%u\n", - dccp_role(sk), sk, - opt_recv->ccid3or_receive_rate); + dccp_role(sk), sk, opt_val); + } else { + /* Update the fixpoint Loss Event Rate fraction */ + hc->tx_p = tfrc_invert_loss_event_rate(opt_val); + + ccid3_pr_debug("%s(%p), LOSS_EVENT_RATE=%u\n", + dccp_role(sk), sk, opt_val); } - break; } - - return rc; + return 0; } static int ccid3_hc_tx_init(struct ccid *ccid, struct sock *sk) { - struct ccid3_hc_tx_sock *hctx = ccid_priv(ccid); + struct ccid3_hc_tx_sock *hc = ccid_priv(ccid); - hctx->ccid3hctx_state = TFRC_SSTATE_NO_SENT; - hctx->ccid3hctx_hist = NULL; - setup_timer(&hctx->ccid3hctx_no_feedback_timer, + hc->tx_state = TFRC_SSTATE_NO_SENT; + hc->tx_hist = NULL; + setup_timer(&hc->tx_no_feedback_timer, ccid3_hc_tx_no_feedback_timer, (unsigned long)sk); - return 0; } static void ccid3_hc_tx_exit(struct sock *sk) { - struct ccid3_hc_tx_sock *hctx = ccid3_hc_tx_sk(sk); - - ccid3_hc_tx_set_state(sk, TFRC_SSTATE_TERM); - sk_stop_timer(sk, &hctx->ccid3hctx_no_feedback_timer); + struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk); - tfrc_tx_hist_purge(&hctx->ccid3hctx_hist); + sk_stop_timer(sk, &hc->tx_no_feedback_timer); + tfrc_tx_hist_purge(&hc->tx_hist); } static void ccid3_hc_tx_get_info(struct sock *sk, struct tcp_info *info) { - struct ccid3_hc_tx_sock *hctx; - - /* Listen socks doesn't have a private CCID block */ - if (sk->sk_state == DCCP_LISTEN) - return; - - hctx = ccid3_hc_tx_sk(sk); - info->tcpi_rto = hctx->ccid3hctx_t_rto; - info->tcpi_rtt = hctx->ccid3hctx_rtt; + info->tcpi_rto = ccid3_hc_tx_sk(sk)->tx_t_rto; + info->tcpi_rtt = ccid3_hc_tx_sk(sk)->tx_rtt; } static int ccid3_hc_tx_getsockopt(struct sock *sk, const int optname, int len, u32 __user *optval, int __user *optlen) { - const struct ccid3_hc_tx_sock *hctx; + const struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk); + struct tfrc_tx_info tfrc; const void *val; - /* Listen socks doesn't have a private CCID block */ - if (sk->sk_state == DCCP_LISTEN) - return -EINVAL; - - hctx = ccid3_hc_tx_sk(sk); switch (optname) { case DCCP_SOCKOPT_CCID_TX_INFO: - if (len < sizeof(hctx->ccid3hctx_tfrc)) + if (len < sizeof(tfrc)) return -EINVAL; - len = sizeof(hctx->ccid3hctx_tfrc); - val = &hctx->ccid3hctx_tfrc; + memset(&tfrc, 0, sizeof(tfrc)); + tfrc.tfrctx_x = hc->tx_x; + tfrc.tfrctx_x_recv = hc->tx_x_recv; + tfrc.tfrctx_x_calc = hc->tx_x_calc; + tfrc.tfrctx_rtt = hc->tx_rtt; + tfrc.tfrctx_p = hc->tx_p; + tfrc.tfrctx_rto = hc->tx_t_rto; + tfrc.tfrctx_ipi = hc->tx_t_ipi; + len = sizeof(tfrc); + val = &tfrc; break; default: return -ENOPROTOOPT; @@ -645,10 +571,9 @@ enum ccid3_fback_type { #ifdef CONFIG_IP_DCCP_CCID3_DEBUG static const char *ccid3_rx_state_name(enum ccid3_hc_rx_states state) { - static char *ccid3_rx_state_names[] = { + static const char *const ccid3_rx_state_names[] = { [TFRC_RSTATE_NO_DATA] = "NO_DATA", [TFRC_RSTATE_DATA] = "DATA", - [TFRC_RSTATE_TERM] = "TERM", }; return ccid3_rx_state_names[state]; @@ -658,34 +583,29 @@ static const char *ccid3_rx_state_name(enum ccid3_hc_rx_states state) static void ccid3_hc_rx_set_state(struct sock *sk, enum ccid3_hc_rx_states state) { - struct ccid3_hc_rx_sock *hcrx = ccid3_hc_rx_sk(sk); - enum ccid3_hc_rx_states oldstate = hcrx->ccid3hcrx_state; + struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk); + enum ccid3_hc_rx_states oldstate = hc->rx_state; ccid3_pr_debug("%s(%p) %-8.8s -> %s\n", dccp_role(sk), sk, ccid3_rx_state_name(oldstate), ccid3_rx_state_name(state)); WARN_ON(state == oldstate); - hcrx->ccid3hcrx_state = state; + hc->rx_state = state; } static void ccid3_hc_rx_send_feedback(struct sock *sk, const struct sk_buff *skb, enum ccid3_fback_type fbtype) { - struct ccid3_hc_rx_sock *hcrx = ccid3_hc_rx_sk(sk); + struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk); struct dccp_sock *dp = dccp_sk(sk); - ktime_t now; + ktime_t now = ktime_get_real(); s64 delta = 0; - if (unlikely(hcrx->ccid3hcrx_state == TFRC_RSTATE_TERM)) - return; - - now = ktime_get_real(); - switch (fbtype) { case CCID3_FBACK_INITIAL: - hcrx->ccid3hcrx_x_recv = 0; - hcrx->ccid3hcrx_pinv = ~0U; /* see RFC 4342, 8.5 */ + hc->rx_x_recv = 0; + hc->rx_pinv = ~0U; /* see RFC 4342, 8.5 */ break; case CCID3_FBACK_PARAM_CHANGE: /* @@ -698,27 +618,26 @@ static void ccid3_hc_rx_send_feedback(struct sock *sk, * the number of bytes since last feedback. * This is a safe fallback, since X is bounded above by X_calc. */ - if (hcrx->ccid3hcrx_x_recv > 0) + if (hc->rx_x_recv > 0) break; /* fall through */ case CCID3_FBACK_PERIODIC: - delta = ktime_us_delta(now, hcrx->ccid3hcrx_tstamp_last_feedback); + delta = ktime_us_delta(now, hc->rx_tstamp_last_feedback); if (delta <= 0) DCCP_BUG("delta (%ld) <= 0", (long)delta); else - hcrx->ccid3hcrx_x_recv = - scaled_div32(hcrx->ccid3hcrx_bytes_recv, delta); + hc->rx_x_recv = scaled_div32(hc->rx_bytes_recv, delta); break; default: return; } ccid3_pr_debug("Interval %ldusec, X_recv=%u, 1/p=%u\n", (long)delta, - hcrx->ccid3hcrx_x_recv, hcrx->ccid3hcrx_pinv); + hc->rx_x_recv, hc->rx_pinv); - hcrx->ccid3hcrx_tstamp_last_feedback = now; - hcrx->ccid3hcrx_last_counter = dccp_hdr(skb)->dccph_ccval; - hcrx->ccid3hcrx_bytes_recv = 0; + hc->rx_tstamp_last_feedback = now; + hc->rx_last_counter = dccp_hdr(skb)->dccph_ccval; + hc->rx_bytes_recv = 0; dp->dccps_hc_rx_insert_options = 1; dccp_send_ack(sk); @@ -726,30 +645,29 @@ static void ccid3_hc_rx_send_feedback(struct sock *sk, static int ccid3_hc_rx_insert_options(struct sock *sk, struct sk_buff *skb) { - const struct ccid3_hc_rx_sock *hcrx; + const struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk); __be32 x_recv, pinv; if (!(sk->sk_state == DCCP_OPEN || sk->sk_state == DCCP_PARTOPEN)) return 0; - hcrx = ccid3_hc_rx_sk(sk); - if (dccp_packet_without_ack(skb)) return 0; - x_recv = htonl(hcrx->ccid3hcrx_x_recv); - pinv = htonl(hcrx->ccid3hcrx_pinv); + x_recv = htonl(hc->rx_x_recv); + pinv = htonl(hc->rx_pinv); - if (dccp_insert_option(sk, skb, TFRC_OPT_LOSS_EVENT_RATE, + if (dccp_insert_option(skb, TFRC_OPT_LOSS_EVENT_RATE, &pinv, sizeof(pinv)) || - dccp_insert_option(sk, skb, TFRC_OPT_RECEIVE_RATE, + dccp_insert_option(skb, TFRC_OPT_RECEIVE_RATE, &x_recv, sizeof(x_recv))) return -1; return 0; } -/** ccid3_first_li - Implements [RFC 3448, 6.3.1] +/** + * ccid3_first_li - Implements [RFC 5348, 6.3.1] * * Determine the length of the first loss interval via inverse lookup. * Assume that X_recv can be computed by the throughput equation @@ -760,26 +678,27 @@ static int ccid3_hc_rx_insert_options(struct sock *sk, struct sk_buff *skb) */ static u32 ccid3_first_li(struct sock *sk) { - struct ccid3_hc_rx_sock *hcrx = ccid3_hc_rx_sk(sk); + struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk); u32 x_recv, p, delta; u64 fval; - if (hcrx->ccid3hcrx_rtt == 0) { + if (hc->rx_rtt == 0) { DCCP_WARN("No RTT estimate available, using fallback RTT\n"); - hcrx->ccid3hcrx_rtt = DCCP_FALLBACK_RTT; + hc->rx_rtt = DCCP_FALLBACK_RTT; } - delta = ktime_to_us(net_timedelta(hcrx->ccid3hcrx_tstamp_last_feedback)); - x_recv = scaled_div32(hcrx->ccid3hcrx_bytes_recv, delta); + delta = ktime_to_us(net_timedelta(hc->rx_tstamp_last_feedback)); + x_recv = scaled_div32(hc->rx_bytes_recv, delta); if (x_recv == 0) { /* would also trigger divide-by-zero */ DCCP_WARN("X_recv==0\n"); - if ((x_recv = hcrx->ccid3hcrx_x_recv) == 0) { + if (hc->rx_x_recv == 0) { DCCP_BUG("stored value of X_recv is zero"); return ~0U; } + x_recv = hc->rx_x_recv; } - fval = scaled_div(hcrx->ccid3hcrx_s, hcrx->ccid3hcrx_rtt); + fval = scaled_div(hc->rx_s, hc->rx_rtt); fval = scaled_div32(fval, x_recv); p = tfrc_calc_x_reverse_lookup(fval); @@ -791,19 +710,19 @@ static u32 ccid3_first_li(struct sock *sk) static void ccid3_hc_rx_packet_recv(struct sock *sk, struct sk_buff *skb) { - struct ccid3_hc_rx_sock *hcrx = ccid3_hc_rx_sk(sk); + struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk); enum ccid3_fback_type do_feedback = CCID3_FBACK_NONE; - const u32 ndp = dccp_sk(sk)->dccps_options_received.dccpor_ndp; + const u64 ndp = dccp_sk(sk)->dccps_options_received.dccpor_ndp; const bool is_data_packet = dccp_data_packet(skb); - if (unlikely(hcrx->ccid3hcrx_state == TFRC_RSTATE_NO_DATA)) { + if (unlikely(hc->rx_state == TFRC_RSTATE_NO_DATA)) { if (is_data_packet) { const u32 payload = skb->len - dccp_hdr(skb)->dccph_doff * 4; do_feedback = CCID3_FBACK_INITIAL; ccid3_hc_rx_set_state(sk, TFRC_RSTATE_DATA); - hcrx->ccid3hcrx_s = payload; + hc->rx_s = payload; /* - * Not necessary to update ccid3hcrx_bytes_recv here, + * Not necessary to update rx_bytes_recv here, * since X_recv = 0 for the first feedback packet (cf. * RFC 3448, 6.3) -- gerrit */ @@ -811,7 +730,7 @@ static void ccid3_hc_rx_packet_recv(struct sock *sk, struct sk_buff *skb) goto update_records; } - if (tfrc_rx_hist_duplicate(&hcrx->ccid3hcrx_hist, skb)) + if (tfrc_rx_hist_duplicate(&hc->rx_hist, skb)) return; /* done receiving */ if (is_data_packet) { @@ -819,23 +738,21 @@ static void ccid3_hc_rx_packet_recv(struct sock *sk, struct sk_buff *skb) /* * Update moving-average of s and the sum of received payload bytes */ - hcrx->ccid3hcrx_s = tfrc_ewma(hcrx->ccid3hcrx_s, payload, 9); - hcrx->ccid3hcrx_bytes_recv += payload; + hc->rx_s = tfrc_ewma(hc->rx_s, payload, 9); + hc->rx_bytes_recv += payload; } /* - * Handle pending losses and otherwise check for new loss + * Perform loss detection and handle pending losses */ - if (tfrc_rx_hist_loss_pending(&hcrx->ccid3hcrx_hist) && - tfrc_rx_handle_loss(&hcrx->ccid3hcrx_hist, - &hcrx->ccid3hcrx_li_hist, - skb, ndp, ccid3_first_li, sk) ) { + if (tfrc_rx_handle_loss(&hc->rx_hist, &hc->rx_li_hist, + skb, ndp, ccid3_first_li, sk)) { do_feedback = CCID3_FBACK_PARAM_CHANGE; goto done_receiving; } - if (tfrc_rx_hist_new_loss_indicated(&hcrx->ccid3hcrx_hist, skb, ndp)) - goto update_records; + if (tfrc_rx_hist_loss_pending(&hc->rx_hist)) + return; /* done receiving */ /* * Handle data packets: RTT sampling and monitoring p @@ -843,17 +760,17 @@ static void ccid3_hc_rx_packet_recv(struct sock *sk, struct sk_buff *skb) if (unlikely(!is_data_packet)) goto update_records; - if (!tfrc_lh_is_initialised(&hcrx->ccid3hcrx_li_hist)) { - const u32 sample = tfrc_rx_hist_sample_rtt(&hcrx->ccid3hcrx_hist, skb); + if (!tfrc_lh_is_initialised(&hc->rx_li_hist)) { + const u32 sample = tfrc_rx_hist_sample_rtt(&hc->rx_hist, skb); /* * Empty loss history: no loss so far, hence p stays 0. * Sample RTT values, since an RTT estimate is required for the * computation of p when the first loss occurs; RFC 3448, 6.3.1. */ if (sample != 0) - hcrx->ccid3hcrx_rtt = tfrc_ewma(hcrx->ccid3hcrx_rtt, sample, 9); + hc->rx_rtt = tfrc_ewma(hc->rx_rtt, sample, 9); - } else if (tfrc_lh_update_i_mean(&hcrx->ccid3hcrx_li_hist, skb)) { + } else if (tfrc_lh_update_i_mean(&hc->rx_li_hist, skb)) { /* * Step (3) of [RFC 3448, 6.1]: Recompute I_mean and, if I_mean * has decreased (resp. p has increased), send feedback now. @@ -864,11 +781,11 @@ static void ccid3_hc_rx_packet_recv(struct sock *sk, struct sk_buff *skb) /* * Check if the periodic once-per-RTT feedback is due; RFC 4342, 10.3 */ - if (SUB16(dccp_hdr(skb)->dccph_ccval, hcrx->ccid3hcrx_last_counter) > 3) + if (SUB16(dccp_hdr(skb)->dccph_ccval, hc->rx_last_counter) > 3) do_feedback = CCID3_FBACK_PERIODIC; update_records: - tfrc_rx_hist_add_packet(&hcrx->ccid3hcrx_hist, skb, ndp); + tfrc_rx_hist_add_packet(&hc->rx_hist, skb, ndp); done_receiving: if (do_feedback) @@ -877,57 +794,42 @@ done_receiving: static int ccid3_hc_rx_init(struct ccid *ccid, struct sock *sk) { - struct ccid3_hc_rx_sock *hcrx = ccid_priv(ccid); + struct ccid3_hc_rx_sock *hc = ccid_priv(ccid); - hcrx->ccid3hcrx_state = TFRC_RSTATE_NO_DATA; - tfrc_lh_init(&hcrx->ccid3hcrx_li_hist); - return tfrc_rx_hist_alloc(&hcrx->ccid3hcrx_hist); + hc->rx_state = TFRC_RSTATE_NO_DATA; + tfrc_lh_init(&hc->rx_li_hist); + return tfrc_rx_hist_alloc(&hc->rx_hist); } static void ccid3_hc_rx_exit(struct sock *sk) { - struct ccid3_hc_rx_sock *hcrx = ccid3_hc_rx_sk(sk); + struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk); - ccid3_hc_rx_set_state(sk, TFRC_RSTATE_TERM); - - tfrc_rx_hist_purge(&hcrx->ccid3hcrx_hist); - tfrc_lh_cleanup(&hcrx->ccid3hcrx_li_hist); + tfrc_rx_hist_purge(&hc->rx_hist); + tfrc_lh_cleanup(&hc->rx_li_hist); } static void ccid3_hc_rx_get_info(struct sock *sk, struct tcp_info *info) { - const struct ccid3_hc_rx_sock *hcrx; - - /* Listen socks doesn't have a private CCID block */ - if (sk->sk_state == DCCP_LISTEN) - return; - - hcrx = ccid3_hc_rx_sk(sk); - info->tcpi_ca_state = hcrx->ccid3hcrx_state; + info->tcpi_ca_state = ccid3_hc_rx_sk(sk)->rx_state; info->tcpi_options |= TCPI_OPT_TIMESTAMPS; - info->tcpi_rcv_rtt = hcrx->ccid3hcrx_rtt; + info->tcpi_rcv_rtt = ccid3_hc_rx_sk(sk)->rx_rtt; } static int ccid3_hc_rx_getsockopt(struct sock *sk, const int optname, int len, u32 __user *optval, int __user *optlen) { - const struct ccid3_hc_rx_sock *hcrx; + const struct ccid3_hc_rx_sock *hc = ccid3_hc_rx_sk(sk); struct tfrc_rx_info rx_info; const void *val; - /* Listen socks doesn't have a private CCID block */ - if (sk->sk_state == DCCP_LISTEN) - return -EINVAL; - - hcrx = ccid3_hc_rx_sk(sk); switch (optname) { case DCCP_SOCKOPT_CCID_RX_INFO: if (len < sizeof(rx_info)) return -EINVAL; - rx_info.tfrcrx_x_recv = hcrx->ccid3hcrx_x_recv; - rx_info.tfrcrx_rtt = hcrx->ccid3hcrx_rtt; - rx_info.tfrcrx_p = hcrx->ccid3hcrx_pinv == 0 ? ~0U : - scaled_div(1, hcrx->ccid3hcrx_pinv); + rx_info.tfrcrx_x_recv = hc->rx_x_recv; + rx_info.tfrcrx_rtt = hc->rx_rtt; + rx_info.tfrcrx_p = tfrc_invert_loss_event_rate(hc->rx_pinv); len = sizeof(rx_info); val = &rx_info; break; @@ -941,10 +843,9 @@ static int ccid3_hc_rx_getsockopt(struct sock *sk, const int optname, int len, return 0; } -static struct ccid_operations ccid3 = { +struct ccid_operations ccid3_ops = { .ccid_id = DCCPC_CCID3, .ccid_name = "TCP-Friendly Rate Control", - .ccid_owner = THIS_MODULE, .ccid_hc_tx_obj_size = sizeof(struct ccid3_hc_tx_sock), .ccid_hc_tx_init = ccid3_hc_tx_init, .ccid_hc_tx_exit = ccid3_hc_tx_exit, @@ -964,24 +865,6 @@ static struct ccid_operations ccid3 = { }; #ifdef CONFIG_IP_DCCP_CCID3_DEBUG -module_param(ccid3_debug, bool, 0444); -MODULE_PARM_DESC(ccid3_debug, "Enable debug messages"); +module_param(ccid3_debug, bool, 0644); +MODULE_PARM_DESC(ccid3_debug, "Enable CCID-3 debug messages"); #endif - -static __init int ccid3_module_init(void) -{ - return ccid_register(&ccid3); -} -module_init(ccid3_module_init); - -static __exit void ccid3_module_exit(void) -{ - ccid_unregister(&ccid3); -} -module_exit(ccid3_module_exit); - -MODULE_AUTHOR("Ian McDonald <ian.mcdonald@jandi.co.nz>, " - "Arnaldo Carvalho de Melo <acme@ghostprotocols.net>"); -MODULE_DESCRIPTION("DCCP TFRC CCID3 CCID"); -MODULE_LICENSE("GPL"); -MODULE_ALIAS("net-dccp-ccid-3"); diff --git a/net/dccp/ccids/ccid3.h b/net/dccp/ccids/ccid3.h index 49ca32bd7e7..1a9933c2967 100644 --- a/net/dccp/ccids/ccid3.h +++ b/net/dccp/ccids/ccid3.h @@ -1,6 +1,4 @@ /* - * net/dccp/ccids/ccid3.h - * * Copyright (c) 2005-7 The University of Waikato, Hamilton, New Zealand. * Copyright (c) 2007 The University of Aberdeen, Scotland, UK * @@ -44,128 +42,119 @@ #include "lib/tfrc.h" #include "../ccid.h" -/* Two seconds as per RFC 3448 4.2 */ +/* Two seconds as per RFC 5348, 4.2 */ #define TFRC_INITIAL_TIMEOUT (2 * USEC_PER_SEC) -/* In usecs - half the scheduling granularity as per RFC3448 4.6 */ -#define TFRC_OPSYS_HALF_TIME_GRAN (USEC_PER_SEC / (2 * HZ)) - /* Parameter t_mbi from [RFC 3448, 4.3]: backoff interval in seconds */ #define TFRC_T_MBI 64 +/* + * The t_delta parameter (RFC 5348, 8.3): delays of less than %USEC_PER_MSEC are + * rounded down to 0, since sk_reset_timer() here uses millisecond granularity. + * Hence we can use a constant t_delta = %USEC_PER_MSEC when HZ >= 500. A coarse + * resolution of HZ < 500 means that the error is below one timer tick (t_gran) + * when using the constant t_delta = t_gran / 2 = %USEC_PER_SEC / (2 * HZ). + */ +#if (HZ >= 500) +# define TFRC_T_DELTA USEC_PER_MSEC +#else +# define TFRC_T_DELTA (USEC_PER_SEC / (2 * HZ)) +#endif + enum ccid3_options { TFRC_OPT_LOSS_EVENT_RATE = 192, TFRC_OPT_LOSS_INTERVALS = 193, TFRC_OPT_RECEIVE_RATE = 194, }; -struct ccid3_options_received { - u64 ccid3or_seqno:48, - ccid3or_loss_intervals_idx:16; - u16 ccid3or_loss_intervals_len; - u32 ccid3or_loss_event_rate; - u32 ccid3or_receive_rate; -}; - /* TFRC sender states */ enum ccid3_hc_tx_states { TFRC_SSTATE_NO_SENT = 1, TFRC_SSTATE_NO_FBACK, TFRC_SSTATE_FBACK, - TFRC_SSTATE_TERM, }; -/** struct ccid3_hc_tx_sock - CCID3 sender half-connection socket - * - * @ccid3hctx_x - Current sending rate in 64 * bytes per second - * @ccid3hctx_x_recv - Receive rate in 64 * bytes per second - * @ccid3hctx_x_calc - Calculated rate in bytes per second - * @ccid3hctx_rtt - Estimate of current round trip time in usecs - * @ccid3hctx_p - Current loss event rate (0-1) scaled by 1000000 - * @ccid3hctx_s - Packet size in bytes - * @ccid3hctx_t_rto - Nofeedback Timer setting in usecs - * @ccid3hctx_t_ipi - Interpacket (send) interval (RFC 3448, 4.6) in usecs - * @ccid3hctx_state - Sender state, one of %ccid3_hc_tx_states - * @ccid3hctx_last_win_count - Last window counter sent - * @ccid3hctx_t_last_win_count - Timestamp of earliest packet - * with last_win_count value sent - * @ccid3hctx_no_feedback_timer - Handle to no feedback timer - * @ccid3hctx_t_ld - Time last doubled during slow start - * @ccid3hctx_t_nom - Nominal send time of next packet - * @ccid3hctx_delta - Send timer delta (RFC 3448, 4.6) in usecs - * @ccid3hctx_hist - Packet history - * @ccid3hctx_options_received - Parsed set of retrieved options +/** + * struct ccid3_hc_tx_sock - CCID3 sender half-connection socket + * @tx_x: Current sending rate in 64 * bytes per second + * @tx_x_recv: Receive rate in 64 * bytes per second + * @tx_x_calc: Calculated rate in bytes per second + * @tx_rtt: Estimate of current round trip time in usecs + * @tx_p: Current loss event rate (0-1) scaled by 1000000 + * @tx_s: Packet size in bytes + * @tx_t_rto: Nofeedback Timer setting in usecs + * @tx_t_ipi: Interpacket (send) interval (RFC 3448, 4.6) in usecs + * @tx_state: Sender state, one of %ccid3_hc_tx_states + * @tx_last_win_count: Last window counter sent + * @tx_t_last_win_count: Timestamp of earliest packet + * with last_win_count value sent + * @tx_no_feedback_timer: Handle to no feedback timer + * @tx_t_ld: Time last doubled during slow start + * @tx_t_nom: Nominal send time of next packet + * @tx_hist: Packet history */ struct ccid3_hc_tx_sock { - struct tfrc_tx_info ccid3hctx_tfrc; -#define ccid3hctx_x ccid3hctx_tfrc.tfrctx_x -#define ccid3hctx_x_recv ccid3hctx_tfrc.tfrctx_x_recv -#define ccid3hctx_x_calc ccid3hctx_tfrc.tfrctx_x_calc -#define ccid3hctx_rtt ccid3hctx_tfrc.tfrctx_rtt -#define ccid3hctx_p ccid3hctx_tfrc.tfrctx_p -#define ccid3hctx_t_rto ccid3hctx_tfrc.tfrctx_rto -#define ccid3hctx_t_ipi ccid3hctx_tfrc.tfrctx_ipi - u16 ccid3hctx_s; - enum ccid3_hc_tx_states ccid3hctx_state:8; - u8 ccid3hctx_last_win_count; - ktime_t ccid3hctx_t_last_win_count; - struct timer_list ccid3hctx_no_feedback_timer; - ktime_t ccid3hctx_t_ld; - ktime_t ccid3hctx_t_nom; - u32 ccid3hctx_delta; - struct tfrc_tx_hist_entry *ccid3hctx_hist; - struct ccid3_options_received ccid3hctx_options_received; + u64 tx_x; + u64 tx_x_recv; + u32 tx_x_calc; + u32 tx_rtt; + u32 tx_p; + u32 tx_t_rto; + u32 tx_t_ipi; + u16 tx_s; + enum ccid3_hc_tx_states tx_state:8; + u8 tx_last_win_count; + ktime_t tx_t_last_win_count; + struct timer_list tx_no_feedback_timer; + ktime_t tx_t_ld; + ktime_t tx_t_nom; + struct tfrc_tx_hist_entry *tx_hist; }; static inline struct ccid3_hc_tx_sock *ccid3_hc_tx_sk(const struct sock *sk) { - struct ccid3_hc_tx_sock *hctx = ccid_priv(dccp_sk(sk)->dccps_hc_tx_ccid); - BUG_ON(hctx == NULL); - return hctx; + struct ccid3_hc_tx_sock *hctx = ccid_priv(dccp_sk(sk)->dccps_hc_tx_ccid); + BUG_ON(hctx == NULL); + return hctx; } /* TFRC receiver states */ enum ccid3_hc_rx_states { TFRC_RSTATE_NO_DATA = 1, TFRC_RSTATE_DATA, - TFRC_RSTATE_TERM = 127, }; -/** struct ccid3_hc_rx_sock - CCID3 receiver half-connection socket - * - * @ccid3hcrx_x_recv - Receiver estimate of send rate (RFC 3448 4.3) - * @ccid3hcrx_rtt - Receiver estimate of rtt (non-standard) - * @ccid3hcrx_p - Current loss event rate (RFC 3448 5.4) - * @ccid3hcrx_last_counter - Tracks window counter (RFC 4342, 8.1) - * @ccid3hcrx_state - Receiver state, one of %ccid3_hc_rx_states - * @ccid3hcrx_bytes_recv - Total sum of DCCP payload bytes - * @ccid3hcrx_x_recv - Receiver estimate of send rate (RFC 3448, sec. 4.3) - * @ccid3hcrx_rtt - Receiver estimate of RTT - * @ccid3hcrx_tstamp_last_feedback - Time at which last feedback was sent - * @ccid3hcrx_tstamp_last_ack - Time at which last feedback was sent - * @ccid3hcrx_hist - Packet history (loss detection + RTT sampling) - * @ccid3hcrx_li_hist - Loss Interval database - * @ccid3hcrx_s - Received packet size in bytes - * @ccid3hcrx_pinv - Inverse of Loss Event Rate (RFC 4342, sec. 8.5) +/** + * struct ccid3_hc_rx_sock - CCID3 receiver half-connection socket + * @rx_last_counter: Tracks window counter (RFC 4342, 8.1) + * @rx_state: Receiver state, one of %ccid3_hc_rx_states + * @rx_bytes_recv: Total sum of DCCP payload bytes + * @rx_x_recv: Receiver estimate of send rate (RFC 3448, sec. 4.3) + * @rx_rtt: Receiver estimate of RTT + * @rx_tstamp_last_feedback: Time at which last feedback was sent + * @rx_hist: Packet history (loss detection + RTT sampling) + * @rx_li_hist: Loss Interval database + * @rx_s: Received packet size in bytes + * @rx_pinv: Inverse of Loss Event Rate (RFC 4342, sec. 8.5) */ struct ccid3_hc_rx_sock { - u8 ccid3hcrx_last_counter:4; - enum ccid3_hc_rx_states ccid3hcrx_state:8; - u32 ccid3hcrx_bytes_recv; - u32 ccid3hcrx_x_recv; - u32 ccid3hcrx_rtt; - ktime_t ccid3hcrx_tstamp_last_feedback; - struct tfrc_rx_hist ccid3hcrx_hist; - struct tfrc_loss_hist ccid3hcrx_li_hist; - u16 ccid3hcrx_s; -#define ccid3hcrx_pinv ccid3hcrx_li_hist.i_mean + u8 rx_last_counter:4; + enum ccid3_hc_rx_states rx_state:8; + u32 rx_bytes_recv; + u32 rx_x_recv; + u32 rx_rtt; + ktime_t rx_tstamp_last_feedback; + struct tfrc_rx_hist rx_hist; + struct tfrc_loss_hist rx_li_hist; + u16 rx_s; +#define rx_pinv rx_li_hist.i_mean }; static inline struct ccid3_hc_rx_sock *ccid3_hc_rx_sk(const struct sock *sk) { - struct ccid3_hc_rx_sock *hcrx = ccid_priv(dccp_sk(sk)->dccps_hc_rx_ccid); - BUG_ON(hcrx == NULL); - return hcrx; + struct ccid3_hc_rx_sock *hcrx = ccid_priv(dccp_sk(sk)->dccps_hc_rx_ccid); + BUG_ON(hcrx == NULL); + return hcrx; } #endif /* _DCCP_CCID3_H_ */ diff --git a/net/dccp/ccids/lib/Makefile b/net/dccp/ccids/lib/Makefile deleted file mode 100644 index 68c93e3d89d..00000000000 --- a/net/dccp/ccids/lib/Makefile +++ /dev/null @@ -1,3 +0,0 @@ -obj-$(CONFIG_IP_DCCP_TFRC_LIB) += dccp_tfrc_lib.o - -dccp_tfrc_lib-y := tfrc.o tfrc_equation.o packet_history.o loss_interval.o diff --git a/net/dccp/ccids/lib/loss_interval.c b/net/dccp/ccids/lib/loss_interval.c index 849e181e698..57f9fd78c4d 100644 --- a/net/dccp/ccids/lib/loss_interval.c +++ b/net/dccp/ccids/lib/loss_interval.c @@ -1,6 +1,4 @@ /* - * net/dccp/ccids/lib/loss_interval.c - * * Copyright (c) 2007 The University of Aberdeen, Scotland, UK * Copyright (c) 2005-7 The University of Waikato, Hamilton, New Zealand. * Copyright (c) 2005-7 Ian McDonald <ian.mcdonald@jandi.co.nz> @@ -21,7 +19,7 @@ static const int tfrc_lh_weights[NINTERVAL] = { 10, 10, 10, 10, 8, 6, 4, 2 }; /* implements LIFO semantics on the array */ static inline u8 LIH_INDEX(const u8 ctr) { - return (LIH_SIZE - 1 - (ctr % LIH_SIZE)); + return LIH_SIZE - 1 - (ctr % LIH_SIZE); } /* the `counter' index always points at the next entry to be populated */ @@ -60,14 +58,16 @@ void tfrc_lh_cleanup(struct tfrc_loss_hist *lh) lh->ring[LIH_INDEX(lh->counter)] = NULL; } } -EXPORT_SYMBOL_GPL(tfrc_lh_cleanup); static void tfrc_lh_calc_i_mean(struct tfrc_loss_hist *lh) { u32 i_i, i_tot0 = 0, i_tot1 = 0, w_tot = 0; int i, k = tfrc_lh_length(lh) - 1; /* k is as in rfc3448bis, 5.4 */ - for (i=0; i <= k; i++) { + if (k <= 0) + return; + + for (i = 0; i <= k; i++) { i_i = tfrc_lh_get_interval(lh, i); if (i < k) { @@ -78,7 +78,6 @@ static void tfrc_lh_calc_i_mean(struct tfrc_loss_hist *lh) i_tot1 += i_i * tfrc_lh_weights[i-1]; } - BUG_ON(w_tot == 0); lh->i_mean = max(i_tot0, i_tot1) / w_tot; } @@ -90,14 +89,14 @@ u8 tfrc_lh_update_i_mean(struct tfrc_loss_hist *lh, struct sk_buff *skb) { struct tfrc_loss_interval *cur = tfrc_lh_peek(lh); u32 old_i_mean = lh->i_mean; - s64 length; + s64 len; if (cur == NULL) /* not initialised */ return 0; - length = dccp_delta_seqno(cur->li_seqno, DCCP_SKB_CB(skb)->dccpd_seq); + len = dccp_delta_seqno(cur->li_seqno, DCCP_SKB_CB(skb)->dccpd_seq) + 1; - if (length - cur->li_length <= 0) /* duplicate or reordered */ + if (len - (s64)cur->li_length <= 0) /* duplicate or reordered */ return 0; if (SUB16(dccp_hdr(skb)->dccph_ccval, cur->li_ccval) > 4) @@ -114,12 +113,11 @@ u8 tfrc_lh_update_i_mean(struct tfrc_loss_hist *lh, struct sk_buff *skb) if (tfrc_lh_length(lh) == 1) /* due to RFC 3448, 6.3.1 */ return 0; - cur->li_length = length; + cur->li_length = len; tfrc_lh_calc_i_mean(lh); - return (lh->i_mean < old_i_mean); + return lh->i_mean < old_i_mean; } -EXPORT_SYMBOL_GPL(tfrc_lh_update_i_mean); /* Determine if `new_loss' does begin a new loss interval [RFC 4342, 10.2] */ static inline u8 tfrc_lh_is_new_loss(struct tfrc_loss_interval *cur, @@ -129,11 +127,13 @@ static inline u8 tfrc_lh_is_new_loss(struct tfrc_loss_interval *cur, (cur->li_is_closed || SUB16(new_loss->tfrchrx_ccval, cur->li_ccval) > 4); } -/** tfrc_lh_interval_add - Insert new record into the Loss Interval database +/** + * tfrc_lh_interval_add - Insert new record into the Loss Interval database * @lh: Loss Interval database * @rh: Receive history containing a fresh loss event * @calc_first_li: Caller-dependent routine to compute length of first interval * @sk: Used by @calc_first_li in caller-specific way (subtyping) + * * Updates I_mean and returns 1 if a new interval has in fact been added to @lh. */ int tfrc_lh_interval_add(struct tfrc_loss_hist *lh, struct tfrc_rx_hist *rh, @@ -159,7 +159,7 @@ int tfrc_lh_interval_add(struct tfrc_loss_hist *lh, struct tfrc_rx_hist *rh, else { cur->li_length = dccp_delta_seqno(cur->li_seqno, new->li_seqno); new->li_length = dccp_delta_seqno(new->li_seqno, - tfrc_rx_hist_last_rcv(rh)->tfrchrx_seqno); + tfrc_rx_hist_last_rcv(rh)->tfrchrx_seqno) + 1; if (lh->counter > (2*LIH_SIZE)) lh->counter -= LIH_SIZE; @@ -167,7 +167,6 @@ int tfrc_lh_interval_add(struct tfrc_loss_hist *lh, struct tfrc_rx_hist *rh, } return 1; } -EXPORT_SYMBOL_GPL(tfrc_lh_interval_add); int __init tfrc_li_init(void) { diff --git a/net/dccp/ccids/lib/loss_interval.h b/net/dccp/ccids/lib/loss_interval.h index 246018a3b26..57f631a86cc 100644 --- a/net/dccp/ccids/lib/loss_interval.h +++ b/net/dccp/ccids/lib/loss_interval.h @@ -1,8 +1,6 @@ #ifndef _DCCP_LI_HIST_ #define _DCCP_LI_HIST_ /* - * net/dccp/ccids/lib/loss_interval.h - * * Copyright (c) 2007 The University of Aberdeen, Scotland, UK * Copyright (c) 2005-7 The University of Waikato, Hamilton, New Zealand. * Copyright (c) 2005-7 Ian McDonald <ian.mcdonald@jandi.co.nz> @@ -67,9 +65,9 @@ static inline u8 tfrc_lh_length(struct tfrc_loss_hist *lh) struct tfrc_rx_hist; -extern int tfrc_lh_interval_add(struct tfrc_loss_hist *, struct tfrc_rx_hist *, - u32 (*first_li)(struct sock *), struct sock *); -extern u8 tfrc_lh_update_i_mean(struct tfrc_loss_hist *lh, struct sk_buff *); -extern void tfrc_lh_cleanup(struct tfrc_loss_hist *lh); +int tfrc_lh_interval_add(struct tfrc_loss_hist *, struct tfrc_rx_hist *, + u32 (*first_li)(struct sock *), struct sock *); +u8 tfrc_lh_update_i_mean(struct tfrc_loss_hist *lh, struct sk_buff *); +void tfrc_lh_cleanup(struct tfrc_loss_hist *lh); #endif /* _DCCP_LI_HIST_ */ diff --git a/net/dccp/ccids/lib/packet_history.c b/net/dccp/ccids/lib/packet_history.c index 20af1a69342..08df7a3acb3 100644 --- a/net/dccp/ccids/lib/packet_history.c +++ b/net/dccp/ccids/lib/packet_history.c @@ -1,6 +1,4 @@ /* - * net/dccp/packet_history.c - * * Copyright (c) 2007 The University of Aberdeen, Scotland, UK * Copyright (c) 2005-7 The University of Waikato, Hamilton, New Zealand. * @@ -40,18 +38,6 @@ #include "packet_history.h" #include "../../dccp.h" -/** - * tfrc_tx_hist_entry - Simple singly-linked TX history list - * @next: next oldest entry (LIFO order) - * @seqno: sequence number of this entry - * @stamp: send time of packet with sequence number @seqno - */ -struct tfrc_tx_hist_entry { - struct tfrc_tx_hist_entry *next; - u64 seqno; - ktime_t stamp; -}; - /* * Transmitter History Routines */ @@ -73,15 +59,6 @@ void tfrc_tx_packet_history_exit(void) } } -static struct tfrc_tx_hist_entry * - tfrc_tx_hist_find_entry(struct tfrc_tx_hist_entry *head, u64 seqno) -{ - while (head != NULL && head->seqno != seqno) - head = head->next; - - return head; -} - int tfrc_tx_hist_add(struct tfrc_tx_hist_entry **headp, u64 seqno) { struct tfrc_tx_hist_entry *entry = kmem_cache_alloc(tfrc_tx_hist_slab, gfp_any()); @@ -94,7 +71,6 @@ int tfrc_tx_hist_add(struct tfrc_tx_hist_entry **headp, u64 seqno) *headp = entry; return 0; } -EXPORT_SYMBOL_GPL(tfrc_tx_hist_add); void tfrc_tx_hist_purge(struct tfrc_tx_hist_entry **headp) { @@ -109,29 +85,9 @@ void tfrc_tx_hist_purge(struct tfrc_tx_hist_entry **headp) *headp = NULL; } -EXPORT_SYMBOL_GPL(tfrc_tx_hist_purge); - -u32 tfrc_tx_hist_rtt(struct tfrc_tx_hist_entry *head, const u64 seqno, - const ktime_t now) -{ - u32 rtt = 0; - struct tfrc_tx_hist_entry *packet = tfrc_tx_hist_find_entry(head, seqno); - - if (packet != NULL) { - rtt = ktime_us_delta(now, packet->stamp); - /* - * Garbage-collect older (irrelevant) entries: - */ - tfrc_tx_hist_purge(&packet->next); - } - - return rtt; -} -EXPORT_SYMBOL_GPL(tfrc_tx_hist_rtt); - /* - * Receiver History Routines + * Receiver History Routines */ static struct kmem_cache *tfrc_rx_hist_slab; @@ -153,7 +109,7 @@ void tfrc_rx_packet_history_exit(void) static inline void tfrc_rx_hist_entry_from_skb(struct tfrc_rx_hist_entry *entry, const struct sk_buff *skb, - const u32 ndp) + const u64 ndp) { const struct dccp_hdr *dh = dccp_hdr(skb); @@ -166,13 +122,12 @@ static inline void tfrc_rx_hist_entry_from_skb(struct tfrc_rx_hist_entry *entry, void tfrc_rx_hist_add_packet(struct tfrc_rx_hist *h, const struct sk_buff *skb, - const u32 ndp) + const u64 ndp) { struct tfrc_rx_hist_entry *entry = tfrc_rx_hist_last_rcv(h); tfrc_rx_hist_entry_from_skb(entry, skb, ndp); } -EXPORT_SYMBOL_GPL(tfrc_rx_hist_add_packet); /* has the packet contained in skb been seen before? */ int tfrc_rx_hist_duplicate(struct tfrc_rx_hist *h, struct sk_buff *skb) @@ -189,7 +144,6 @@ int tfrc_rx_hist_duplicate(struct tfrc_rx_hist *h, struct sk_buff *skb) return 0; } -EXPORT_SYMBOL_GPL(tfrc_rx_hist_duplicate); static void tfrc_rx_hist_swap(struct tfrc_rx_hist *h, const u8 a, const u8 b) { @@ -206,31 +160,39 @@ static void tfrc_rx_hist_swap(struct tfrc_rx_hist *h, const u8 a, const u8 b) * * In the descriptions, `Si' refers to the sequence number of entry number i, * whose NDP count is `Ni' (lower case is used for variables). - * Note: All __after_loss functions expect that a test against duplicates has - * been performed already: the seqno of the skb must not be less than the - * seqno of loss_prev; and it must not equal that of any valid hist_entry. + * Note: All __xxx_loss functions expect that a test against duplicates has been + * performed already: the seqno of the skb must not be less than the seqno + * of loss_prev; and it must not equal that of any valid history entry. */ +static void __do_track_loss(struct tfrc_rx_hist *h, struct sk_buff *skb, u64 n1) +{ + u64 s0 = tfrc_rx_hist_loss_prev(h)->tfrchrx_seqno, + s1 = DCCP_SKB_CB(skb)->dccpd_seq; + + if (!dccp_loss_free(s0, s1, n1)) { /* gap between S0 and S1 */ + h->loss_count = 1; + tfrc_rx_hist_entry_from_skb(tfrc_rx_hist_entry(h, 1), skb, n1); + } +} + static void __one_after_loss(struct tfrc_rx_hist *h, struct sk_buff *skb, u32 n2) { u64 s0 = tfrc_rx_hist_loss_prev(h)->tfrchrx_seqno, s1 = tfrc_rx_hist_entry(h, 1)->tfrchrx_seqno, s2 = DCCP_SKB_CB(skb)->dccpd_seq; - int n1 = tfrc_rx_hist_entry(h, 1)->tfrchrx_ndp, - d12 = dccp_delta_seqno(s1, s2), d2; - if (d12 > 0) { /* S1 < S2 */ + if (likely(dccp_delta_seqno(s1, s2) > 0)) { /* S1 < S2 */ h->loss_count = 2; tfrc_rx_hist_entry_from_skb(tfrc_rx_hist_entry(h, 2), skb, n2); return; } /* S0 < S2 < S1 */ - d2 = dccp_delta_seqno(s0, s2); - if (d2 == 1 || n2 >= d2) { /* S2 is direct successor of S0 */ - int d21 = -d12; + if (dccp_loss_free(s0, s2, n2)) { + u64 n1 = tfrc_rx_hist_entry(h, 1)->tfrchrx_ndp; - if (d21 == 1 || n1 >= d21) { + if (dccp_loss_free(s2, s1, n1)) { /* hole is filled: S0, S2, and S1 are consecutive */ h->loss_count = 0; h->loss_start = tfrc_rx_hist_index(h, 1); @@ -238,9 +200,9 @@ static void __one_after_loss(struct tfrc_rx_hist *h, struct sk_buff *skb, u32 n2 /* gap between S2 and S1: just update loss_prev */ tfrc_rx_hist_entry_from_skb(tfrc_rx_hist_loss_prev(h), skb, n2); - } else { /* hole between S0 and S2 */ + } else { /* gap between S0 and S2 */ /* - * Reorder history to insert S2 between S0 and s1 + * Reorder history to insert S2 between S0 and S1 */ tfrc_rx_hist_swap(h, 0, 3); h->loss_start = tfrc_rx_hist_index(h, 3); @@ -256,22 +218,18 @@ static int __two_after_loss(struct tfrc_rx_hist *h, struct sk_buff *skb, u32 n3) s1 = tfrc_rx_hist_entry(h, 1)->tfrchrx_seqno, s2 = tfrc_rx_hist_entry(h, 2)->tfrchrx_seqno, s3 = DCCP_SKB_CB(skb)->dccpd_seq; - int n1 = tfrc_rx_hist_entry(h, 1)->tfrchrx_ndp, - d23 = dccp_delta_seqno(s2, s3), d13, d3, d31; - if (d23 > 0) { /* S2 < S3 */ + if (likely(dccp_delta_seqno(s2, s3) > 0)) { /* S2 < S3 */ h->loss_count = 3; tfrc_rx_hist_entry_from_skb(tfrc_rx_hist_entry(h, 3), skb, n3); return 1; } /* S3 < S2 */ - d13 = dccp_delta_seqno(s1, s3); - if (d13 > 0) { + if (dccp_delta_seqno(s1, s3) > 0) { /* S1 < S3 < S2 */ /* - * The sequence number order is S1, S3, S2 - * Reorder history to insert entry between S1 and S2 + * Reorder history to insert S3 between S1 and S2 */ tfrc_rx_hist_swap(h, 2, 3); tfrc_rx_hist_entry_from_skb(tfrc_rx_hist_entry(h, 2), skb, n3); @@ -280,17 +238,15 @@ static int __two_after_loss(struct tfrc_rx_hist *h, struct sk_buff *skb, u32 n3) } /* S0 < S3 < S1 */ - d31 = -d13; - d3 = dccp_delta_seqno(s0, s3); - if (d3 == 1 || n3 >= d3) { /* S3 is a successor of S0 */ + if (dccp_loss_free(s0, s3, n3)) { + u64 n1 = tfrc_rx_hist_entry(h, 1)->tfrchrx_ndp; - if (d31 == 1 || n1 >= d31) { + if (dccp_loss_free(s3, s1, n1)) { /* hole between S0 and S1 filled by S3 */ - int d2 = dccp_delta_seqno(s1, s2), - n2 = tfrc_rx_hist_entry(h, 2)->tfrchrx_ndp; + u64 n2 = tfrc_rx_hist_entry(h, 2)->tfrchrx_ndp; - if (d2 == 1 || n2 >= d2) { + if (dccp_loss_free(s1, s2, n2)) { /* entire hole filled by S0, S3, S1, S2 */ h->loss_start = tfrc_rx_hist_index(h, 2); h->loss_count = 0; @@ -307,8 +263,8 @@ static int __two_after_loss(struct tfrc_rx_hist *h, struct sk_buff *skb, u32 n3) } /* - * The remaining case: S3 is not a successor of S0. - * Sequence order is S0, S3, S1, S2; reorder to insert between S0 and S1 + * The remaining case: S0 < S3 < S1 < S2; gap between S0 and S3 + * Reorder history to insert S3 between S0 and S1. */ tfrc_rx_hist_swap(h, 0, 3); h->loss_start = tfrc_rx_hist_index(h, 3); @@ -318,33 +274,25 @@ static int __two_after_loss(struct tfrc_rx_hist *h, struct sk_buff *skb, u32 n3) return 1; } -/* return the signed modulo-2^48 sequence number distance from entry e1 to e2 */ -static s64 tfrc_rx_hist_delta_seqno(struct tfrc_rx_hist *h, u8 e1, u8 e2) -{ - DCCP_BUG_ON(e1 > h->loss_count || e2 > h->loss_count); - - return dccp_delta_seqno(tfrc_rx_hist_entry(h, e1)->tfrchrx_seqno, - tfrc_rx_hist_entry(h, e2)->tfrchrx_seqno); -} - /* recycle RX history records to continue loss detection if necessary */ static void __three_after_loss(struct tfrc_rx_hist *h) { /* - * The distance between S0 and S1 is always greater than 1 and the NDP - * count of S1 is smaller than this distance. Otherwise there would - * have been no loss. Hence it is only necessary to see whether there - * are further missing data packets between S1/S2 and S2/S3. + * At this stage we know already that there is a gap between S0 and S1 + * (since S0 was the highest sequence number received before detecting + * the loss). To recycle the loss record, it is thus only necessary to + * check for other possible gaps between S1/S2 and between S2/S3. */ - int d2 = tfrc_rx_hist_delta_seqno(h, 1, 2), - d3 = tfrc_rx_hist_delta_seqno(h, 2, 3), - n2 = tfrc_rx_hist_entry(h, 2)->tfrchrx_ndp, + u64 s1 = tfrc_rx_hist_entry(h, 1)->tfrchrx_seqno, + s2 = tfrc_rx_hist_entry(h, 2)->tfrchrx_seqno, + s3 = tfrc_rx_hist_entry(h, 3)->tfrchrx_seqno; + u64 n2 = tfrc_rx_hist_entry(h, 2)->tfrchrx_ndp, n3 = tfrc_rx_hist_entry(h, 3)->tfrchrx_ndp; - if (d2 == 1 || n2 >= d2) { /* S2 is successor to S1 */ + if (dccp_loss_free(s1, s2, n2)) { - if (d3 == 1 || n3 >= d3) { - /* S3 is successor of S2: entire hole is filled */ + if (dccp_loss_free(s2, s3, n3)) { + /* no gap between S2 and S3: entire hole is filled */ h->loss_start = tfrc_rx_hist_index(h, 3); h->loss_count = 0; } else { @@ -353,7 +301,7 @@ static void __three_after_loss(struct tfrc_rx_hist *h) h->loss_count = 1; } - } else { /* gap between S1 and S2 */ + } else { /* gap between S1 and S2 */ h->loss_start = tfrc_rx_hist_index(h, 1); h->loss_count = 2; } @@ -367,18 +315,24 @@ static void __three_after_loss(struct tfrc_rx_hist *h) * @ndp: The NDP count belonging to @skb * @calc_first_li: Caller-dependent computation of first loss interval in @lh * @sk: Used by @calc_first_li (see tfrc_lh_interval_add) + * * Chooses action according to pending loss, updates LI database when a new * loss was detected, and does required post-processing. Returns 1 when caller * should send feedback, 0 otherwise. + * Since it also takes care of reordering during loss detection and updates the + * records accordingly, the caller should not perform any more RX history + * operations when loss_count is greater than 0 after calling this function. */ int tfrc_rx_handle_loss(struct tfrc_rx_hist *h, struct tfrc_loss_hist *lh, - struct sk_buff *skb, u32 ndp, + struct sk_buff *skb, const u64 ndp, u32 (*calc_first_li)(struct sock *), struct sock *sk) { int is_new_loss = 0; - if (h->loss_count == 1) { + if (h->loss_count == 0) { + __do_track_loss(h, skb, ndp); + } else if (h->loss_count == 1) { __one_after_loss(h, skb, ndp); } else if (h->loss_count != 2) { DCCP_BUG("invalid loss_count %d", h->loss_count); @@ -391,7 +345,6 @@ int tfrc_rx_handle_loss(struct tfrc_rx_hist *h, } return is_new_loss; } -EXPORT_SYMBOL_GPL(tfrc_rx_handle_loss); int tfrc_rx_hist_alloc(struct tfrc_rx_hist *h) { @@ -413,7 +366,6 @@ out_free: } return -ENOBUFS; } -EXPORT_SYMBOL_GPL(tfrc_rx_hist_alloc); void tfrc_rx_hist_purge(struct tfrc_rx_hist *h) { @@ -425,7 +377,6 @@ void tfrc_rx_hist_purge(struct tfrc_rx_hist *h) h->ring[i] = NULL; } } -EXPORT_SYMBOL_GPL(tfrc_rx_hist_purge); /** * tfrc_rx_hist_rtt_last_s - reference entry to compute RTT samples against @@ -437,7 +388,7 @@ static inline struct tfrc_rx_hist_entry * } /** - * tfrc_rx_hist_rtt_prev_s: previously suitable (wrt rtt_last_s) RTT-sampling entry + * tfrc_rx_hist_rtt_prev_s - previously suitable (wrt rtt_last_s) RTT-sampling entry */ static inline struct tfrc_rx_hist_entry * tfrc_rx_hist_rtt_prev_s(const struct tfrc_rx_hist *h) @@ -496,4 +447,3 @@ keep_ref_for_next_time: return sample; } -EXPORT_SYMBOL_GPL(tfrc_rx_hist_sample_rtt); diff --git a/net/dccp/ccids/lib/packet_history.h b/net/dccp/ccids/lib/packet_history.h index c7eeda49cb2..ee362b0b630 100644 --- a/net/dccp/ccids/lib/packet_history.h +++ b/net/dccp/ccids/lib/packet_history.h @@ -40,12 +40,28 @@ #include <linux/slab.h> #include "tfrc.h" -struct tfrc_tx_hist_entry; +/** + * tfrc_tx_hist_entry - Simple singly-linked TX history list + * @next: next oldest entry (LIFO order) + * @seqno: sequence number of this entry + * @stamp: send time of packet with sequence number @seqno + */ +struct tfrc_tx_hist_entry { + struct tfrc_tx_hist_entry *next; + u64 seqno; + ktime_t stamp; +}; + +static inline struct tfrc_tx_hist_entry * + tfrc_tx_hist_find_entry(struct tfrc_tx_hist_entry *head, u64 seqno) +{ + while (head != NULL && head->seqno != seqno) + head = head->next; + return head; +} -extern int tfrc_tx_hist_add(struct tfrc_tx_hist_entry **headp, u64 seqno); -extern void tfrc_tx_hist_purge(struct tfrc_tx_hist_entry **headp); -extern u32 tfrc_tx_hist_rtt(struct tfrc_tx_hist_entry *head, - const u64 seqno, const ktime_t now); +int tfrc_tx_hist_add(struct tfrc_tx_hist_entry **headp, u64 seqno); +void tfrc_tx_hist_purge(struct tfrc_tx_hist_entry **headp); /* Subtraction a-b modulo-16, respects circular wrap-around */ #define SUB16(a, b) (((a) + 16 - (b)) & 0xF) @@ -64,13 +80,12 @@ struct tfrc_rx_hist_entry { u64 tfrchrx_seqno:48, tfrchrx_ccval:4, tfrchrx_type:4; - u32 tfrchrx_ndp; /* In fact it is from 8 to 24 bits */ + u64 tfrchrx_ndp:48; ktime_t tfrchrx_tstamp; }; /** * tfrc_rx_hist - RX history structure for TFRC-based protocols - * * @ring: Packet history for RTT sampling and loss detection * @loss_count: Number of entries in circular history * @loss_start: Movable index (for loss detection) @@ -118,46 +133,23 @@ static inline struct tfrc_rx_hist_entry * return h->ring[h->loss_start]; } -/* initialise loss detection and disable RTT sampling */ -static inline void tfrc_rx_hist_loss_indicated(struct tfrc_rx_hist *h) -{ - h->loss_count = 1; -} - /* indicate whether previously a packet was detected missing */ -static inline int tfrc_rx_hist_loss_pending(const struct tfrc_rx_hist *h) +static inline bool tfrc_rx_hist_loss_pending(const struct tfrc_rx_hist *h) { - return h->loss_count; -} - -/* any data packets missing between last reception and skb ? */ -static inline int tfrc_rx_hist_new_loss_indicated(struct tfrc_rx_hist *h, - const struct sk_buff *skb, - u32 ndp) -{ - int delta = dccp_delta_seqno(tfrc_rx_hist_last_rcv(h)->tfrchrx_seqno, - DCCP_SKB_CB(skb)->dccpd_seq); - - if (delta > 1 && ndp < delta) - tfrc_rx_hist_loss_indicated(h); - - return tfrc_rx_hist_loss_pending(h); + return h->loss_count > 0; } -extern void tfrc_rx_hist_add_packet(struct tfrc_rx_hist *h, - const struct sk_buff *skb, const u32 ndp); +void tfrc_rx_hist_add_packet(struct tfrc_rx_hist *h, const struct sk_buff *skb, + const u64 ndp); -extern int tfrc_rx_hist_duplicate(struct tfrc_rx_hist *h, struct sk_buff *skb); +int tfrc_rx_hist_duplicate(struct tfrc_rx_hist *h, struct sk_buff *skb); struct tfrc_loss_hist; -extern int tfrc_rx_handle_loss(struct tfrc_rx_hist *h, - struct tfrc_loss_hist *lh, - struct sk_buff *skb, u32 ndp, - u32 (*first_li)(struct sock *sk), - struct sock *sk); -extern u32 tfrc_rx_hist_sample_rtt(struct tfrc_rx_hist *h, - const struct sk_buff *skb); -extern int tfrc_rx_hist_alloc(struct tfrc_rx_hist *h); -extern void tfrc_rx_hist_purge(struct tfrc_rx_hist *h); +int tfrc_rx_handle_loss(struct tfrc_rx_hist *h, struct tfrc_loss_hist *lh, + struct sk_buff *skb, const u64 ndp, + u32 (*first_li)(struct sock *sk), struct sock *sk); +u32 tfrc_rx_hist_sample_rtt(struct tfrc_rx_hist *h, const struct sk_buff *skb); +int tfrc_rx_hist_alloc(struct tfrc_rx_hist *h); +void tfrc_rx_hist_purge(struct tfrc_rx_hist *h); #endif /* _DCCP_PKT_HIST_ */ diff --git a/net/dccp/ccids/lib/tfrc.c b/net/dccp/ccids/lib/tfrc.c index d1dfbb8de64..62b5828acde 100644 --- a/net/dccp/ccids/lib/tfrc.c +++ b/net/dccp/ccids/lib/tfrc.c @@ -1,28 +1,19 @@ /* - * TFRC: main module holding the pieces of the TFRC library together + * TFRC library initialisation * * Copyright (c) 2007 The University of Aberdeen, Scotland, UK * Copyright (c) 2007 Arnaldo Carvalho de Melo <acme@redhat.com> */ -#include <linux/module.h> #include <linux/moduleparam.h> #include "tfrc.h" #ifdef CONFIG_IP_DCCP_TFRC_DEBUG -int tfrc_debug; -module_param(tfrc_debug, bool, 0444); -MODULE_PARM_DESC(tfrc_debug, "Enable debug messages"); +bool tfrc_debug; +module_param(tfrc_debug, bool, 0644); +MODULE_PARM_DESC(tfrc_debug, "Enable TFRC debug messages"); #endif -extern int tfrc_tx_packet_history_init(void); -extern void tfrc_tx_packet_history_exit(void); -extern int tfrc_rx_packet_history_init(void); -extern void tfrc_rx_packet_history_exit(void); - -extern int tfrc_li_init(void); -extern void tfrc_li_exit(void); - -static int __init tfrc_module_init(void) +int __init tfrc_lib_init(void) { int rc = tfrc_li_init(); @@ -46,18 +37,9 @@ out: return rc; } -static void __exit tfrc_module_exit(void) +void tfrc_lib_exit(void) { tfrc_rx_packet_history_exit(); tfrc_tx_packet_history_exit(); tfrc_li_exit(); } - -module_init(tfrc_module_init); -module_exit(tfrc_module_exit); - -MODULE_AUTHOR("Gerrit Renker <gerrit@erg.abdn.ac.uk>, " - "Ian McDonald <ian.mcdonald@jandi.co.nz>, " - "Arnaldo Carvalho de Melo <acme@redhat.com>"); -MODULE_DESCRIPTION("DCCP TFRC library"); -MODULE_LICENSE("GPL"); diff --git a/net/dccp/ccids/lib/tfrc.h b/net/dccp/ccids/lib/tfrc.h index 1fb1187bbf1..40ee7d62b65 100644 --- a/net/dccp/ccids/lib/tfrc.h +++ b/net/dccp/ccids/lib/tfrc.h @@ -1,8 +1,6 @@ #ifndef _TFRC_H_ #define _TFRC_H_ /* - * net/dccp/ccids/lib/tfrc.h - * * Copyright (c) 2007 The University of Aberdeen, Scotland, UK * Copyright (c) 2005-6 The University of Waikato, Hamilton, New Zealand. * Copyright (c) 2005-6 Ian McDonald <ian.mcdonald@jandi.co.nz> @@ -15,35 +13,34 @@ * (at your option) any later version. */ #include <linux/types.h> -#include <asm/div64.h> +#include <linux/math64.h> #include "../../dccp.h" -/* internal includes that this module exports: */ + +/* internal includes that this library exports: */ #include "loss_interval.h" #include "packet_history.h" #ifdef CONFIG_IP_DCCP_TFRC_DEBUG -extern int tfrc_debug; +extern bool tfrc_debug; #define tfrc_pr_debug(format, a...) DCCP_PR_DEBUG(tfrc_debug, format, ##a) #else #define tfrc_pr_debug(format, a...) #endif /* integer-arithmetic divisions of type (a * 1000000)/b */ -static inline u64 scaled_div(u64 a, u32 b) +static inline u64 scaled_div(u64 a, u64 b) { - BUG_ON(b==0); - a *= 1000000; - do_div(a, b); - return a; + BUG_ON(b == 0); + return div64_u64(a * 1000000, b); } -static inline u32 scaled_div32(u64 a, u32 b) +static inline u32 scaled_div32(u64 a, u64 b) { u64 result = scaled_div(a, b); if (result > UINT_MAX) { - DCCP_CRIT("Overflow: a(%llu)/b(%u) > ~0U", - (unsigned long long)a, b); + DCCP_CRIT("Overflow: %llu/%llu > UINT_MAX", + (unsigned long long)a, (unsigned long long)b); return UINT_MAX; } return result; @@ -58,7 +55,23 @@ static inline u32 tfrc_ewma(const u32 avg, const u32 newval, const u8 weight) return avg ? (weight * avg + (10 - weight) * newval) / 10 : newval; } -extern u32 tfrc_calc_x(u16 s, u32 R, u32 p); -extern u32 tfrc_calc_x_reverse_lookup(u32 fvalue); +u32 tfrc_calc_x(u16 s, u32 R, u32 p); +u32 tfrc_calc_x_reverse_lookup(u32 fvalue); +u32 tfrc_invert_loss_event_rate(u32 loss_event_rate); + +int tfrc_tx_packet_history_init(void); +void tfrc_tx_packet_history_exit(void); +int tfrc_rx_packet_history_init(void); +void tfrc_rx_packet_history_exit(void); +int tfrc_li_init(void); +void tfrc_li_exit(void); + +#ifdef CONFIG_IP_DCCP_TFRC_LIB +int tfrc_lib_init(void); +void tfrc_lib_exit(void); +#else +#define tfrc_lib_init() (0) +#define tfrc_lib_exit() +#endif #endif /* _TFRC_H_ */ diff --git a/net/dccp/ccids/lib/tfrc_equation.c b/net/dccp/ccids/lib/tfrc_equation.c index e4e64b76c10..88ef98285be 100644 --- a/net/dccp/ccids/lib/tfrc_equation.c +++ b/net/dccp/ccids/lib/tfrc_equation.c @@ -1,6 +1,4 @@ /* - * net/dccp/ccids/lib/tfrc_equation.c - * * Copyright (c) 2005 The University of Waikato, Hamilton, New Zealand. * Copyright (c) 2005 Ian McDonald <ian.mcdonald@jandi.co.nz> * Copyright (c) 2005 Arnaldo Carvalho de Melo <acme@conectiva.com.br> @@ -79,10 +77,10 @@ } With the given configuration, we have, with M = TFRC_CALC_X_ARRSIZE-1, - lookup[0][0] = g(1000000/(M+1)) = 1000000 * f(0.2%) - lookup[M][0] = g(1000000) = 1000000 * f(100%) - lookup[0][1] = g(TFRC_SMALLEST_P) = 1000000 * f(0.01%) - lookup[M][1] = g(TFRC_CALC_X_SPLIT) = 1000000 * f(5%) + lookup[0][0] = g(1000000/(M+1)) = 1000000 * f(0.2%) + lookup[M][0] = g(1000000) = 1000000 * f(100%) + lookup[0][1] = g(TFRC_SMALLEST_P) = 1000000 * f(0.01%) + lookup[M][1] = g(TFRC_CALC_X_SPLIT) = 1000000 * f(5%) In summary, the two columns represent f(p) for the following ranges: * The first column is for 0.002 <= p <= 1.0 @@ -610,11 +608,11 @@ static inline u32 tfrc_binsearch(u32 fval, u8 small) /** * tfrc_calc_x - Calculate the send rate as per section 3.1 of RFC3448 + * @s: packet size in bytes + * @R: RTT scaled by 1000000 (i.e., microseconds) + * @p: loss ratio estimate scaled by 1000000 * - * @s: packet size in bytes - * @R: RTT scaled by 1000000 (i.e., microseconds) - * @p: loss ratio estimate scaled by 1000000 - * Returns X_calc in bytes per second (not scaled). + * Returns X_calc in bytes per second (not scaled). */ u32 tfrc_calc_x(u16 s, u32 R, u32 p) { @@ -630,17 +628,17 @@ u32 tfrc_calc_x(u16 s, u32 R, u32 p) return ~0U; } - if (p <= TFRC_CALC_X_SPLIT) { /* 0.0000 < p <= 0.05 */ + if (p <= TFRC_CALC_X_SPLIT) { /* 0.0000 < p <= 0.05 */ if (p < TFRC_SMALLEST_P) { /* 0.0000 < p < 0.0001 */ DCCP_WARN("Value of p (%d) below resolution. " "Substituting %d\n", p, TFRC_SMALLEST_P); index = 0; - } else /* 0.0001 <= p <= 0.05 */ + } else /* 0.0001 <= p <= 0.05 */ index = p/TFRC_SMALLEST_P - 1; f = tfrc_calc_x_lookup[index][1]; - } else { /* 0.05 < p <= 1.00 */ + } else { /* 0.05 < p <= 1.00 */ index = p/(1000000/TFRC_CALC_X_ARRSIZE) - 1; f = tfrc_calc_x_lookup[index][0]; @@ -659,12 +657,10 @@ u32 tfrc_calc_x(u16 s, u32 R, u32 p) return scaled_div32(result, f); } -EXPORT_SYMBOL_GPL(tfrc_calc_x); - -/* +/** * tfrc_calc_x_reverse_lookup - try to find p given f(p) - * * @fvalue: function value to match, scaled by 1000000 + * * Returns closest match for p, also scaled by 1000000 */ u32 tfrc_calc_x_reverse_lookup(u32 fvalue) @@ -676,11 +672,11 @@ u32 tfrc_calc_x_reverse_lookup(u32 fvalue) /* Error cases. */ if (fvalue < tfrc_calc_x_lookup[0][1]) { - DCCP_WARN("fvalue %d smaller than resolution\n", fvalue); - return tfrc_calc_x_lookup[0][1]; + DCCP_WARN("fvalue %u smaller than resolution\n", fvalue); + return TFRC_SMALLEST_P; } if (fvalue > tfrc_calc_x_lookup[TFRC_CALC_X_ARRSIZE - 1][0]) { - DCCP_WARN("fvalue %d exceeds bounds!\n", fvalue); + DCCP_WARN("fvalue %u exceeds bounds!\n", fvalue); return 1000000; } @@ -694,4 +690,16 @@ u32 tfrc_calc_x_reverse_lookup(u32 fvalue) return (index + 1) * 1000000 / TFRC_CALC_X_ARRSIZE; } -EXPORT_SYMBOL_GPL(tfrc_calc_x_reverse_lookup); +/** + * tfrc_invert_loss_event_rate - Compute p so that 10^6 corresponds to 100% + * When @loss_event_rate is large, there is a chance that p is truncated to 0. + * To avoid re-entering slow-start in that case, we set p = TFRC_SMALLEST_P > 0. + */ +u32 tfrc_invert_loss_event_rate(u32 loss_event_rate) +{ + if (loss_event_rate == UINT_MAX) /* see RFC 4342, 8.5 */ + return 0; + if (unlikely(loss_event_rate == 0)) /* map 1/0 into 100% */ + return 1000000; + return max_t(u32, scaled_div(1, loss_event_rate), TFRC_SMALLEST_P); +} diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index 287a62bc2e0..c67816647cc 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -23,9 +23,9 @@ * DCCP - specific warning and debugging macros. */ #define DCCP_WARN(fmt, a...) LIMIT_NETDEBUG(KERN_WARNING "%s: " fmt, \ - __FUNCTION__, ##a) + __func__, ##a) #define DCCP_CRIT(fmt, a...) printk(KERN_CRIT fmt " at %s:%d/%s()\n", ##a, \ - __FILE__, __LINE__, __FUNCTION__) + __FILE__, __LINE__, __func__) #define DCCP_BUG(a...) do { DCCP_CRIT("BUG: " a); dump_stack(); } while(0) #define DCCP_BUG_ON(cond) do { if (unlikely((cond) != 0)) \ DCCP_BUG("\"%s\" holds (exception!)", \ @@ -36,22 +36,24 @@ printk(fmt, ##args); \ } while(0) #define DCCP_PR_DEBUG(enable, fmt, a...) DCCP_PRINTK(enable, KERN_DEBUG \ - "%s: " fmt, __FUNCTION__, ##a) + "%s: " fmt, __func__, ##a) #ifdef CONFIG_IP_DCCP_DEBUG -extern int dccp_debug; +extern bool dccp_debug; #define dccp_pr_debug(format, a...) DCCP_PR_DEBUG(dccp_debug, format, ##a) #define dccp_pr_debug_cat(format, a...) DCCP_PRINTK(dccp_debug, format, ##a) +#define dccp_debug(fmt, a...) dccp_pr_debug_cat(KERN_DEBUG fmt, ##a) #else #define dccp_pr_debug(format, a...) #define dccp_pr_debug_cat(format, a...) +#define dccp_debug(format, a...) #endif extern struct inet_hashinfo dccp_hashinfo; -extern atomic_t dccp_orphan_count; +extern struct percpu_counter dccp_orphan_count; -extern void dccp_time_wait(struct sock *sk, int state, int timeo); +void dccp_time_wait(struct sock *sk, int state, int timeo); /* * Set safe upper bounds for header and option length. Since Data Offset is 8 @@ -61,16 +63,19 @@ extern void dccp_time_wait(struct sock *sk, int state, int timeo); * - DCCP-Reset with ACK Subheader and 4 bytes of Reset Code fields * Hence a safe upper bound for the maximum option length is 1020-28 = 992 */ -#define MAX_DCCP_SPECIFIC_HEADER (255 * sizeof(int)) +#define MAX_DCCP_SPECIFIC_HEADER (255 * sizeof(uint32_t)) #define DCCP_MAX_PACKET_HDR 28 #define DCCP_MAX_OPT_LEN (MAX_DCCP_SPECIFIC_HEADER - DCCP_MAX_PACKET_HDR) #define MAX_DCCP_HEADER (MAX_DCCP_SPECIFIC_HEADER + MAX_HEADER) +/* Upper bound for initial feature-negotiation overhead (padded to 32 bits) */ +#define DCCP_FEATNEG_OVERHEAD (32 * sizeof(uint32_t)) + #define DCCP_TIMEWAIT_LEN (60 * HZ) /* how long to wait to destroy TIME-WAIT * state, about 60 seconds */ /* RFC 1122, 4.2.3.1 initial RTO value */ -#define DCCP_TIMEOUT_INIT ((unsigned)(3 * HZ)) +#define DCCP_TIMEOUT_INIT ((unsigned int)(3 * HZ)) /* * The maximum back-off value for retransmissions. This is needed for @@ -79,7 +84,7 @@ extern void dccp_time_wait(struct sock *sk, int state, int timeo); * - feature-negotiation retransmission (sec. 6.6.3), * - Acks in client-PARTOPEN state (sec. 8.1.5). */ -#define DCCP_RTO_MAX ((unsigned)(64 * HZ)) +#define DCCP_RTO_MAX ((unsigned int)(64 * HZ)) /* * RTT sampling: sanity bounds and fallback RTT value from RFC 4340, section 3.4 @@ -88,19 +93,10 @@ extern void dccp_time_wait(struct sock *sk, int state, int timeo); #define DCCP_FALLBACK_RTT (USEC_PER_SEC / 5) #define DCCP_SANE_RTT_MAX (3 * USEC_PER_SEC) -/* Maximal interval between probes for local resources. */ -#define DCCP_RESOURCE_PROBE_INTERVAL ((unsigned)(HZ / 2U)) - /* sysctl variables for DCCP */ extern int sysctl_dccp_request_retries; extern int sysctl_dccp_retries1; 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_ack_ratio; -extern int sysctl_dccp_feat_send_ack_vector; -extern int sysctl_dccp_feat_send_ndp_count; extern int sysctl_dccp_tx_qlen; extern int sysctl_dccp_sync_ratelimit; @@ -153,6 +149,30 @@ static inline u64 max48(const u64 seq1, const u64 seq2) return after48(seq1, seq2) ? seq1 : seq2; } +/** + * dccp_loss_count - Approximate the number of lost data packets in a burst loss + * @s1: last known sequence number before the loss ('hole') + * @s2: first sequence number seen after the 'hole' + * @ndp: NDP count on packet with sequence number @s2 + */ +static inline u64 dccp_loss_count(const u64 s1, const u64 s2, const u64 ndp) +{ + s64 delta = dccp_delta_seqno(s1, s2); + + WARN_ON(delta < 0); + delta -= ndp + 1; + + return delta > 0 ? delta : 0; +} + +/** + * dccp_loss_free - Evaluate condition for data loss from RFC 4340, 7.7.1 + */ +static inline bool dccp_loss_free(const u64 s1, const u64 s2, const u64 ndp) +{ + return dccp_loss_count(s1, s2, ndp) == 0; +} + enum { DCCP_MIB_NUM = 0, DCCP_MIB_ACTIVEOPENS, /* ActiveOpens */ @@ -175,17 +195,12 @@ enum { #define DCCP_MIB_MAX __DCCP_MIB_MAX struct dccp_mib { unsigned long mibs[DCCP_MIB_MAX]; -} __SNMP_MIB_ALIGN__; +}; DECLARE_SNMP_STAT(struct dccp_mib, dccp_statistics); #define DCCP_INC_STATS(field) SNMP_INC_STATS(dccp_statistics, field) #define DCCP_INC_STATS_BH(field) SNMP_INC_STATS_BH(dccp_statistics, field) -#define DCCP_INC_STATS_USER(field) SNMP_INC_STATS_USER(dccp_statistics, field) #define DCCP_DEC_STATS(field) SNMP_DEC_STATS(dccp_statistics, field) -#define DCCP_ADD_STATS_BH(field, val) \ - SNMP_ADD_STATS_BH(dccp_statistics, field, val) -#define DCCP_ADD_STATS_USER(field, val) \ - SNMP_ADD_STATS_USER(dccp_statistics, field, val) /* * Checksumming routines @@ -209,99 +224,108 @@ static inline void dccp_csum_outgoing(struct sk_buff *skb) skb->csum = skb_checksum(skb, 0, (cov > skb->len)? skb->len : cov, 0); } -extern void dccp_v4_send_check(struct sock *sk, int len, struct sk_buff *skb); +void dccp_v4_send_check(struct sock *sk, struct sk_buff *skb); -extern int dccp_retransmit_skb(struct sock *sk, struct sk_buff *skb); +int dccp_retransmit_skb(struct sock *sk); -extern void dccp_send_ack(struct sock *sk); -extern void dccp_reqsk_send_ack(struct sk_buff *sk, struct request_sock *rsk); +void dccp_send_ack(struct sock *sk); +void dccp_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, + struct request_sock *rsk); -extern void dccp_send_sync(struct sock *sk, const u64 seq, - const enum dccp_pkt_type pkt_type); +void dccp_send_sync(struct sock *sk, const u64 seq, + const enum dccp_pkt_type pkt_type); -extern void dccp_write_xmit(struct sock *sk, int block); -extern void dccp_write_space(struct sock *sk); +/* + * TX Packet Dequeueing Interface + */ +void dccp_qpolicy_push(struct sock *sk, struct sk_buff *skb); +bool dccp_qpolicy_full(struct sock *sk); +void dccp_qpolicy_drop(struct sock *sk, struct sk_buff *skb); +struct sk_buff *dccp_qpolicy_top(struct sock *sk); +struct sk_buff *dccp_qpolicy_pop(struct sock *sk); +bool dccp_qpolicy_param_ok(struct sock *sk, __be32 param); -extern void dccp_init_xmit_timers(struct sock *sk); +/* + * TX Packet Output and TX Timers + */ +void dccp_write_xmit(struct sock *sk); +void dccp_write_space(struct sock *sk); +void dccp_flush_write_queue(struct sock *sk, long *time_budget); + +void dccp_init_xmit_timers(struct sock *sk); static inline void dccp_clear_xmit_timers(struct sock *sk) { inet_csk_clear_xmit_timers(sk); } -extern unsigned int dccp_sync_mss(struct sock *sk, u32 pmtu); +unsigned int dccp_sync_mss(struct sock *sk, u32 pmtu); -extern const char *dccp_packet_name(const int type); -extern const char *dccp_state_name(const int state); +const char *dccp_packet_name(const int type); -extern void dccp_set_state(struct sock *sk, const int state); -extern void dccp_done(struct sock *sk); +void dccp_set_state(struct sock *sk, const int state); +void dccp_done(struct sock *sk); -extern void dccp_reqsk_init(struct request_sock *req, struct sk_buff *skb); +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); +int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb); -extern struct sock *dccp_create_openreq_child(struct sock *sk, - const struct request_sock *req, - const struct sk_buff *skb); +struct sock *dccp_create_openreq_child(struct sock *sk, + const struct request_sock *req, + const struct sk_buff *skb); -extern int dccp_v4_do_rcv(struct sock *sk, struct sk_buff *skb); +int dccp_v4_do_rcv(struct sock *sk, struct sk_buff *skb); -extern struct sock *dccp_v4_request_recv_sock(struct sock *sk, - struct sk_buff *skb, - struct request_sock *req, - struct dst_entry *dst); -extern struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb, - struct request_sock *req, - struct request_sock **prev); +struct sock *dccp_v4_request_recv_sock(struct sock *sk, struct sk_buff *skb, + struct request_sock *req, + struct dst_entry *dst); +struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb, + struct request_sock *req, + struct request_sock **prev); -extern int dccp_child_process(struct sock *parent, struct sock *child, - struct sk_buff *skb); -extern int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, - struct dccp_hdr *dh, unsigned len); -extern int dccp_rcv_established(struct sock *sk, struct sk_buff *skb, - const struct dccp_hdr *dh, const unsigned len); +int dccp_child_process(struct sock *parent, struct sock *child, + struct sk_buff *skb); +int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, + struct dccp_hdr *dh, unsigned int len); +int dccp_rcv_established(struct sock *sk, struct sk_buff *skb, + const struct dccp_hdr *dh, const unsigned int len); -extern int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized); -extern int dccp_destroy_sock(struct sock *sk); +int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized); +void dccp_destroy_sock(struct sock *sk); -extern void dccp_close(struct sock *sk, long timeout); -extern struct sk_buff *dccp_make_response(struct sock *sk, - struct dst_entry *dst, - struct request_sock *req); +void dccp_close(struct sock *sk, long timeout); +struct sk_buff *dccp_make_response(struct sock *sk, struct dst_entry *dst, + struct request_sock *req); -extern int dccp_connect(struct sock *sk); -extern int dccp_disconnect(struct sock *sk, int flags); -extern int dccp_getsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user *optlen); -extern int dccp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen); +int dccp_connect(struct sock *sk); +int dccp_disconnect(struct sock *sk, int flags); +int dccp_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen); +int dccp_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, unsigned int optlen); #ifdef CONFIG_COMPAT -extern int compat_dccp_getsockopt(struct sock *sk, - int level, int optname, - char __user *optval, int __user *optlen); -extern int compat_dccp_setsockopt(struct sock *sk, - int level, int optname, - char __user *optval, int optlen); +int compat_dccp_getsockopt(struct sock *sk, int level, int optname, + char __user *optval, int __user *optlen); +int compat_dccp_setsockopt(struct sock *sk, int level, int optname, + char __user *optval, unsigned int optlen); #endif -extern int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg); -extern int dccp_sendmsg(struct kiocb *iocb, struct sock *sk, - struct msghdr *msg, size_t size); -extern int dccp_recvmsg(struct kiocb *iocb, struct sock *sk, - struct msghdr *msg, size_t len, int nonblock, - int flags, int *addr_len); -extern void dccp_shutdown(struct sock *sk, int how); -extern int inet_dccp_listen(struct socket *sock, int backlog); -extern unsigned int dccp_poll(struct file *file, struct socket *sock, - poll_table *wait); -extern int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, - int addr_len); - -extern struct sk_buff *dccp_ctl_make_reset(struct socket *ctl, - struct sk_buff *skb); -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); +int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg); +int dccp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, + size_t size); +int dccp_recvmsg(struct kiocb *iocb, struct sock *sk, + struct msghdr *msg, size_t len, int nonblock, int flags, + int *addr_len); +void dccp_shutdown(struct sock *sk, int how); +int inet_dccp_listen(struct socket *sock, int backlog); +unsigned int dccp_poll(struct file *file, struct socket *sock, + poll_table *wait); +int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len); + +struct sk_buff *dccp_ctl_make_reset(struct sock *sk, struct sk_buff *skb); +int dccp_send_reset(struct sock *sk, enum dccp_reset_codes code); +void dccp_send_close(struct sock *sk, const int active); +int dccp_invalid_packet(struct sk_buff *skb); +u32 dccp_sample_rtt(struct sock *sk, long delta); static inline int dccp_bad_service_code(const struct sock *sk, const __be32 service) @@ -322,9 +346,16 @@ static inline int dccp_bad_service_code(const struct sock *sk, * @dccpd_opt_len: total length of all options (5.8) in the packet * @dccpd_seq: sequence number * @dccpd_ack_seq: acknowledgment number subheader field value + * * This is used for transmission as well as for reception. */ struct dccp_skb_cb { + union { + struct inet_skb_parm h4; +#if IS_ENABLED(CONFIG_IPV6) + struct inet6_skb_parm h6; +#endif + } header; __u8 dccpd_type:4; __u8 dccpd_ccval:4; __u8 dccpd_reset_code, @@ -389,52 +420,73 @@ static inline void dccp_hdr_set_ack(struct dccp_hdr_ack_bits *dhack, static inline void dccp_update_gsr(struct sock *sk, u64 seq) { struct dccp_sock *dp = dccp_sk(sk); - const struct dccp_minisock *dmsk = dccp_msk(sk); - dp->dccps_gsr = seq; - dccp_set_seqno(&dp->dccps_swl, - dp->dccps_gsr + 1 - (dmsk->dccpms_sequence_window / 4)); - dccp_set_seqno(&dp->dccps_swh, - dp->dccps_gsr + (3 * dmsk->dccpms_sequence_window) / 4); + if (after48(seq, dp->dccps_gsr)) + 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); } static inline void dccp_update_gss(struct sock *sk, u64 seq) { struct dccp_sock *dp = dccp_sk(sk); - dp->dccps_awh = dp->dccps_gss = seq; - dccp_set_seqno(&dp->dccps_awl, - (dp->dccps_gss - - dccp_msk(sk)->dccpms_sequence_window + 1)); + 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; +} + +static inline int dccp_ackvec_pending(const struct sock *sk) +{ + return dccp_sk(sk)->dccps_hc_rx_ackvec != NULL && + !dccp_ackvec_is_empty(dccp_sk(sk)->dccps_hc_rx_ackvec); } 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 && - dccp_ackvec_pending(dp->dccps_hc_rx_ackvec)) || -#endif - inet_csk_ack_scheduled(sk); + return dccp_ackvec_pending(sk) || inet_csk_ack_scheduled(sk); } -extern int dccp_insert_options(struct sock *sk, struct sk_buff *skb); -extern int dccp_insert_options_rsk(struct dccp_request_sock*, struct sk_buff*); -extern int dccp_insert_option_elapsed_time(struct sock *sk, - struct sk_buff *skb, - u32 elapsed_time); -extern u32 dccp_timestamp(void); -extern void dccp_timestamping_init(void); -extern int dccp_insert_option_timestamp(struct sock *sk, - struct sk_buff *skb); -extern int dccp_insert_option(struct sock *sk, struct sk_buff *skb, - unsigned char option, - const void *value, unsigned char len); +int dccp_feat_signal_nn_change(struct sock *sk, u8 feat, u64 nn_val); +int dccp_feat_finalise_settings(struct dccp_sock *dp); +int dccp_feat_server_ccid_dependencies(struct dccp_request_sock *dreq); +int dccp_feat_insert_opts(struct dccp_sock*, struct dccp_request_sock*, + struct sk_buff *skb); +int dccp_feat_activate_values(struct sock *sk, struct list_head *fn); +void dccp_feat_list_purge(struct list_head *fn_list); + +int dccp_insert_options(struct sock *sk, struct sk_buff *skb); +int dccp_insert_options_rsk(struct dccp_request_sock *, struct sk_buff *); +u32 dccp_timestamp(void); +void dccp_timestamping_init(void); +int dccp_insert_option(struct sk_buff *skb, unsigned char option, + const void *value, unsigned char len); #ifdef CONFIG_SYSCTL -extern int dccp_sysctl_init(void); -extern void dccp_sysctl_exit(void); +int dccp_sysctl_init(void); +void dccp_sysctl_exit(void); #else static inline int dccp_sysctl_init(void) { diff --git a/net/dccp/diag.c b/net/dccp/diag.c index d8a3509b26f..028fc43aacb 100644 --- a/net/dccp/diag.c +++ b/net/dccp/diag.c @@ -29,11 +29,14 @@ 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); - ccid_hc_tx_get_info(dp->dccps_hc_tx_ccid, sk, info); + if (dp->dccps_hc_rx_ccid != NULL) + ccid_hc_rx_get_info(dp->dccps_hc_rx_ccid, sk, info); + + if (dp->dccps_hc_tx_ccid != NULL) + ccid_hc_tx_get_info(dp->dccps_hc_tx_ccid, sk, info); } static void dccp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, @@ -45,11 +48,23 @@ static void dccp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, dccp_get_info(sk, _info); } -static struct inet_diag_handler dccp_diag_handler = { - .idiag_hashinfo = &dccp_hashinfo, +static void dccp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, + struct inet_diag_req_v2 *r, struct nlattr *bc) +{ + inet_diag_dump_icsk(&dccp_hashinfo, skb, cb, r, bc); +} + +static int dccp_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *nlh, + struct inet_diag_req_v2 *req) +{ + return inet_diag_dump_one_icsk(&dccp_hashinfo, in_skb, nlh, req); +} + +static const struct inet_diag_handler dccp_diag_handler = { + .dump = dccp_diag_dump, + .dump_one = dccp_diag_dump_one, .idiag_get_info = dccp_diag_get_info, - .idiag_type = DCCPDIAG_GETSOCK, - .idiag_info_size = sizeof(struct tcp_info), + .idiag_type = IPPROTO_DCCP, }; static int __init dccp_diag_init(void) @@ -68,4 +83,4 @@ module_exit(dccp_diag_fini); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Arnaldo Carvalho de Melo <acme@mandriva.com>"); MODULE_DESCRIPTION("DCCP inet_diag handler"); -MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_INET_DIAG, DCCPDIAG_GETSOCK); +MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-33 /* AF_INET - IPPROTO_DCCP */); diff --git a/net/dccp/feat.c b/net/dccp/feat.c index 4a4f6ce4498..9733ddbc96c 100644 --- a/net/dccp/feat.c +++ b/net/dccp/feat.c @@ -1,11 +1,18 @@ /* * net/dccp/feat.c * - * An implementation of the DCCP protocol - * Andrea Bittau <a.bittau@cs.ucl.ac.uk> + * Feature negotiation for the DCCP protocol (RFC 4340, section 6) + * + * Copyright (c) 2008 Gerrit Renker <gerrit@erg.abdn.ac.uk> + * Rewrote from scratch, some bits from earlier code by + * Copyright (c) 2005 Andrea Bittau <a.bittau@cs.ucl.ac.uk> + * * * ASSUMPTIONS * ----------- + * o Feature negotiation is coordinated with connection setup (as in TCP), wild + * changes of parameters of an established connection are not supported. + * o Changing non-negotiable (NN) values is supported in state OPEN/PARTOPEN. * o All currently known SP features have 1-byte quantities. If in the future * extensions of RFCs 4340..42 define features with item lengths larger than * one byte, a feature-specific extension of the code will be required. @@ -15,635 +22,1540 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. */ - #include <linux/module.h> - +#include <linux/slab.h> #include "ccid.h" #include "feat.h" -#define DCCP_FEAT_SP_NOAGREE (-123) - -int dccp_feat_change(struct dccp_minisock *dmsk, u8 type, u8 feature, - u8 *val, u8 len, gfp_t gfp) -{ - struct dccp_opt_pend *opt; - - dccp_feat_debug(type, feature, *val); - - if (len > 3) { - DCCP_WARN("invalid length %d\n", len); - return 1; - } - /* XXX add further sanity checks */ - - /* check if that feature is already being negotiated */ - list_for_each_entry(opt, &dmsk->dccpms_pending, dccpop_node) { - /* ok we found a negotiation for this option already */ - if (opt->dccpop_feat == feature && opt->dccpop_type == type) { - dccp_pr_debug("Replacing old\n"); - /* replace */ - BUG_ON(opt->dccpop_val == NULL); - kfree(opt->dccpop_val); - opt->dccpop_val = val; - opt->dccpop_len = len; - opt->dccpop_conf = 0; - return 0; - } - } - - /* negotiation for a new feature */ - opt = kmalloc(sizeof(*opt), gfp); - if (opt == NULL) - return -ENOMEM; - - opt->dccpop_type = type; - opt->dccpop_feat = feature; - opt->dccpop_len = len; - opt->dccpop_val = val; - opt->dccpop_conf = 0; - opt->dccpop_sc = NULL; - - BUG_ON(opt->dccpop_val == NULL); - - list_add_tail(&opt->dccpop_node, &dmsk->dccpms_pending); - return 0; -} +/* feature-specific sysctls - initialised to the defaults from RFC 4340, 6.4 */ +unsigned long sysctl_dccp_sequence_window __read_mostly = 100; +int sysctl_dccp_rx_ccid __read_mostly = 2, + sysctl_dccp_tx_ccid __read_mostly = 2; -EXPORT_SYMBOL_GPL(dccp_feat_change); - -static int dccp_feat_update_ccid(struct sock *sk, u8 type, u8 new_ccid_nr) +/* + * Feature activation handlers. + * + * These all use an u64 argument, to provide enough room for NN/SP features. At + * this stage the negotiated values have been checked to be within their range. + */ +static int dccp_hdlr_ccid(struct sock *sk, u64 ccid, bool rx) { struct dccp_sock *dp = dccp_sk(sk); - struct dccp_minisock *dmsk = dccp_msk(sk); - /* figure out if we are changing our CCID or the peer's */ - const int rx = type == DCCPO_CHANGE_R; - const u8 ccid_nr = rx ? dmsk->dccpms_rx_ccid : dmsk->dccpms_tx_ccid; - struct ccid *new_ccid; - - /* Check if nothing is being changed. */ - if (ccid_nr == new_ccid_nr) - return 0; + struct ccid *new_ccid = ccid_new(ccid, sk, rx); - new_ccid = ccid_new(new_ccid_nr, sk, rx, GFP_ATOMIC); if (new_ccid == NULL) return -ENOMEM; if (rx) { ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk); dp->dccps_hc_rx_ccid = new_ccid; - dmsk->dccpms_rx_ccid = new_ccid_nr; } else { ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk); dp->dccps_hc_tx_ccid = new_ccid; - dmsk->dccpms_tx_ccid = new_ccid_nr; } + return 0; +} + +static int dccp_hdlr_seq_win(struct sock *sk, u64 seq_win, bool rx) +{ + struct dccp_sock *dp = dccp_sk(sk); + + if (rx) { + dp->dccps_r_seq_win = seq_win; + /* propagate changes to update SWL/SWH */ + dccp_update_gsr(sk, dp->dccps_gsr); + } else { + dp->dccps_l_seq_win = seq_win; + /* propagate changes to update AWL */ + dccp_update_gss(sk, dp->dccps_gss); + } + return 0; +} +static int dccp_hdlr_ack_ratio(struct sock *sk, u64 ratio, bool rx) +{ + if (rx) + dccp_sk(sk)->dccps_r_ack_ratio = ratio; + else + dccp_sk(sk)->dccps_l_ack_ratio = ratio; return 0; } -static int dccp_feat_update(struct sock *sk, u8 type, u8 feat, u8 val) +static int dccp_hdlr_ackvec(struct sock *sk, u64 enable, bool rx) { - dccp_feat_debug(type, feat, val); + struct dccp_sock *dp = dccp_sk(sk); - switch (feat) { - case DCCPF_CCID: - return dccp_feat_update_ccid(sk, type, val); - default: - dccp_pr_debug("UNIMPLEMENTED: %s(%d, ...)\n", - dccp_feat_typename(type), feat); - break; + if (rx) { + if (enable && dp->dccps_hc_rx_ackvec == NULL) { + dp->dccps_hc_rx_ackvec = dccp_ackvec_alloc(gfp_any()); + if (dp->dccps_hc_rx_ackvec == NULL) + return -ENOMEM; + } else if (!enable) { + dccp_ackvec_free(dp->dccps_hc_rx_ackvec); + dp->dccps_hc_rx_ackvec = NULL; + } } return 0; } -static int dccp_feat_reconcile(struct sock *sk, struct dccp_opt_pend *opt, - u8 *rpref, u8 rlen) +static int dccp_hdlr_ndp(struct sock *sk, u64 enable, bool rx) +{ + if (!rx) + dccp_sk(sk)->dccps_send_ndp_count = (enable > 0); + return 0; +} + +/* + * Minimum Checksum Coverage is located at the RX side (9.2.1). This means that + * `rx' holds when the sending peer informs about his partial coverage via a + * ChangeR() option. In the other case, we are the sender and the receiver + * announces its coverage via ChangeL() options. The policy here is to honour + * such communication by enabling the corresponding partial coverage - but only + * if it has not been set manually before; the warning here means that all + * packets will be dropped. + */ +static int dccp_hdlr_min_cscov(struct sock *sk, u64 cscov, bool rx) { struct dccp_sock *dp = dccp_sk(sk); - u8 *spref, slen, *res = NULL; - int i, j, rc, agree = 1; - BUG_ON(rpref == NULL); + if (rx) + dp->dccps_pcrlen = cscov; + else { + if (dp->dccps_pcslen == 0) + dp->dccps_pcslen = cscov; + else if (cscov > dp->dccps_pcslen) + DCCP_WARN("CsCov %u too small, peer requires >= %u\n", + dp->dccps_pcslen, (u8)cscov); + } + return 0; +} + +static const struct { + u8 feat_num; /* DCCPF_xxx */ + enum dccp_feat_type rxtx; /* RX or TX */ + enum dccp_feat_type reconciliation; /* SP or NN */ + u8 default_value; /* as in 6.4 */ + int (*activation_hdlr)(struct sock *sk, u64 val, bool rx); +/* + * Lookup table for location and type of features (from RFC 4340/4342) + * +--------------------------+----+-----+----+----+---------+-----------+ + * | Feature | Location | Reconc. | Initial | Section | + * | | RX | TX | SP | NN | Value | Reference | + * +--------------------------+----+-----+----+----+---------+-----------+ + * | DCCPF_CCID | | X | X | | 2 | 10 | + * | DCCPF_SHORT_SEQNOS | | X | X | | 0 | 7.6.1 | + * | DCCPF_SEQUENCE_WINDOW | | X | | X | 100 | 7.5.2 | + * | DCCPF_ECN_INCAPABLE | X | | X | | 0 | 12.1 | + * | DCCPF_ACK_RATIO | | X | | X | 2 | 11.3 | + * | DCCPF_SEND_ACK_VECTOR | X | | X | | 0 | 11.5 | + * | DCCPF_SEND_NDP_COUNT | | X | X | | 0 | 7.7.2 | + * | DCCPF_MIN_CSUM_COVER | X | | X | | 0 | 9.2.1 | + * | DCCPF_DATA_CHECKSUM | X | | X | | 0 | 9.3.1 | + * | DCCPF_SEND_LEV_RATE | X | | X | | 0 | 4342/8.4 | + * +--------------------------+----+-----+----+----+---------+-----------+ + */ +} dccp_feat_table[] = { + { DCCPF_CCID, FEAT_AT_TX, FEAT_SP, 2, dccp_hdlr_ccid }, + { DCCPF_SHORT_SEQNOS, FEAT_AT_TX, FEAT_SP, 0, NULL }, + { DCCPF_SEQUENCE_WINDOW, FEAT_AT_TX, FEAT_NN, 100, dccp_hdlr_seq_win }, + { DCCPF_ECN_INCAPABLE, FEAT_AT_RX, FEAT_SP, 0, NULL }, + { DCCPF_ACK_RATIO, FEAT_AT_TX, FEAT_NN, 2, dccp_hdlr_ack_ratio}, + { DCCPF_SEND_ACK_VECTOR, FEAT_AT_RX, FEAT_SP, 0, dccp_hdlr_ackvec }, + { DCCPF_SEND_NDP_COUNT, FEAT_AT_TX, FEAT_SP, 0, dccp_hdlr_ndp }, + { DCCPF_MIN_CSUM_COVER, FEAT_AT_RX, FEAT_SP, 0, dccp_hdlr_min_cscov}, + { DCCPF_DATA_CHECKSUM, FEAT_AT_RX, FEAT_SP, 0, NULL }, + { DCCPF_SEND_LEV_RATE, FEAT_AT_RX, FEAT_SP, 0, NULL }, +}; +#define DCCP_FEAT_SUPPORTED_MAX ARRAY_SIZE(dccp_feat_table) + +/** + * dccp_feat_index - Hash function to map feature number into array position + * Returns consecutive array index or -1 if the feature is not understood. + */ +static int dccp_feat_index(u8 feat_num) +{ + /* The first 9 entries are occupied by the types from RFC 4340, 6.4 */ + if (feat_num > DCCPF_RESERVED && feat_num <= DCCPF_DATA_CHECKSUM) + return feat_num - 1; - /* check if we are the black sheep */ - if (dp->dccps_role == DCCP_ROLE_CLIENT) { - spref = rpref; - slen = rlen; - rpref = opt->dccpop_val; - rlen = opt->dccpop_len; - } else { - spref = opt->dccpop_val; - slen = opt->dccpop_len; + /* + * Other features: add cases for new feature types here after adding + * them to the above table. + */ + switch (feat_num) { + case DCCPF_SEND_LEV_RATE: + return DCCP_FEAT_SUPPORTED_MAX - 1; } + return -1; +} + +static u8 dccp_feat_type(u8 feat_num) +{ + int idx = dccp_feat_index(feat_num); + + if (idx < 0) + return FEAT_UNKNOWN; + return dccp_feat_table[idx].reconciliation; +} + +static int dccp_feat_default_value(u8 feat_num) +{ + int idx = dccp_feat_index(feat_num); /* - * Now we have server preference list in spref and client preference in - * rpref + * There are no default values for unknown features, so encountering a + * negative index here indicates a serious problem somewhere else. */ - BUG_ON(spref == NULL); - BUG_ON(rpref == NULL); + DCCP_BUG_ON(idx < 0); - /* FIXME sanity check vals */ + return idx < 0 ? 0 : dccp_feat_table[idx].default_value; +} - /* Are values in any order? XXX Lame "algorithm" here */ - for (i = 0; i < slen; i++) { - for (j = 0; j < rlen; j++) { - if (spref[i] == rpref[j]) { - res = &spref[i]; - break; - } - } - if (res) - break; - } +/* + * Debugging and verbose-printing section + */ +static const char *dccp_feat_fname(const u8 feat) +{ + static const char *const feature_names[] = { + [DCCPF_RESERVED] = "Reserved", + [DCCPF_CCID] = "CCID", + [DCCPF_SHORT_SEQNOS] = "Allow Short Seqnos", + [DCCPF_SEQUENCE_WINDOW] = "Sequence Window", + [DCCPF_ECN_INCAPABLE] = "ECN Incapable", + [DCCPF_ACK_RATIO] = "Ack Ratio", + [DCCPF_SEND_ACK_VECTOR] = "Send ACK Vector", + [DCCPF_SEND_NDP_COUNT] = "Send NDP Count", + [DCCPF_MIN_CSUM_COVER] = "Min. Csum Coverage", + [DCCPF_DATA_CHECKSUM] = "Send Data Checksum", + }; + if (feat > DCCPF_DATA_CHECKSUM && feat < DCCPF_MIN_CCID_SPECIFIC) + return feature_names[DCCPF_RESERVED]; - /* we didn't agree on anything */ - if (res == NULL) { - /* confirm previous value */ - switch (opt->dccpop_feat) { - case DCCPF_CCID: - /* XXX did i get this right? =P */ - if (opt->dccpop_type == DCCPO_CHANGE_L) - res = &dccp_msk(sk)->dccpms_tx_ccid; - else - res = &dccp_msk(sk)->dccpms_rx_ccid; - break; + if (feat == DCCPF_SEND_LEV_RATE) + return "Send Loss Event Rate"; + if (feat >= DCCPF_MIN_CCID_SPECIFIC) + return "CCID-specific"; - default: - DCCP_BUG("Fell through, feat=%d", opt->dccpop_feat); - /* XXX implement res */ - return -EFAULT; - } + return feature_names[feat]; +} - dccp_pr_debug("Don't agree... reconfirming %d\n", *res); - agree = 0; /* this is used for mandatory options... */ +static const char *const dccp_feat_sname[] = { + "DEFAULT", "INITIALISING", "CHANGING", "UNSTABLE", "STABLE", +}; + +#ifdef CONFIG_IP_DCCP_DEBUG +static const char *dccp_feat_oname(const u8 opt) +{ + switch (opt) { + case DCCPO_CHANGE_L: return "Change_L"; + case DCCPO_CONFIRM_L: return "Confirm_L"; + case DCCPO_CHANGE_R: return "Change_R"; + case DCCPO_CONFIRM_R: return "Confirm_R"; } + return NULL; +} - /* need to put result and our preference list */ - rlen = 1 + opt->dccpop_len; - rpref = kmalloc(rlen, GFP_ATOMIC); - if (rpref == NULL) - return -ENOMEM; +static void dccp_feat_printval(u8 feat_num, dccp_feat_val const *val) +{ + u8 i, type = dccp_feat_type(feat_num); + + if (val == NULL || (type == FEAT_SP && val->sp.vec == NULL)) + dccp_pr_debug_cat("(NULL)"); + else if (type == FEAT_SP) + for (i = 0; i < val->sp.len; i++) + dccp_pr_debug_cat("%s%u", i ? " " : "", val->sp.vec[i]); + else if (type == FEAT_NN) + dccp_pr_debug_cat("%llu", (unsigned long long)val->nn); + else + dccp_pr_debug_cat("unknown type %u", type); +} - *rpref = *res; - memcpy(&rpref[1], opt->dccpop_val, opt->dccpop_len); +static void dccp_feat_printvals(u8 feat_num, u8 *list, u8 len) +{ + u8 type = dccp_feat_type(feat_num); + dccp_feat_val fval = { .sp.vec = list, .sp.len = len }; + + if (type == FEAT_NN) + fval.nn = dccp_decode_value_var(list, len); + dccp_feat_printval(feat_num, &fval); +} - /* put it in the "confirm queue" */ - if (opt->dccpop_sc == NULL) { - opt->dccpop_sc = kmalloc(sizeof(*opt->dccpop_sc), GFP_ATOMIC); - if (opt->dccpop_sc == NULL) { - kfree(rpref); - return -ENOMEM; +static void dccp_feat_print_entry(struct dccp_feat_entry const *entry) +{ + dccp_debug(" * %s %s = ", entry->is_local ? "local" : "remote", + dccp_feat_fname(entry->feat_num)); + dccp_feat_printval(entry->feat_num, &entry->val); + dccp_pr_debug_cat(", state=%s %s\n", dccp_feat_sname[entry->state], + entry->needs_confirm ? "(Confirm pending)" : ""); +} + +#define dccp_feat_print_opt(opt, feat, val, len, mandatory) do { \ + dccp_pr_debug("%s(%s, ", dccp_feat_oname(opt), dccp_feat_fname(feat));\ + dccp_feat_printvals(feat, val, len); \ + dccp_pr_debug_cat(") %s\n", mandatory ? "!" : ""); } while (0) + +#define dccp_feat_print_fnlist(fn_list) { \ + const struct dccp_feat_entry *___entry; \ + \ + dccp_pr_debug("List Dump:\n"); \ + list_for_each_entry(___entry, fn_list, node) \ + dccp_feat_print_entry(___entry); \ +} +#else /* ! CONFIG_IP_DCCP_DEBUG */ +#define dccp_feat_print_opt(opt, feat, val, len, mandatory) +#define dccp_feat_print_fnlist(fn_list) +#endif + +static int __dccp_feat_activate(struct sock *sk, const int idx, + const bool is_local, dccp_feat_val const *fval) +{ + bool rx; + u64 val; + + if (idx < 0 || idx >= DCCP_FEAT_SUPPORTED_MAX) + return -1; + if (dccp_feat_table[idx].activation_hdlr == NULL) + return 0; + + if (fval == NULL) { + val = dccp_feat_table[idx].default_value; + } else if (dccp_feat_table[idx].reconciliation == FEAT_SP) { + if (fval->sp.vec == NULL) { + /* + * This can happen when an empty Confirm is sent + * for an SP (i.e. known) feature. In this case + * we would be using the default anyway. + */ + DCCP_CRIT("Feature #%d undefined: using default", idx); + val = dccp_feat_table[idx].default_value; + } else { + val = fval->sp.vec[0]; } } else { - /* recycle the confirm slot */ - BUG_ON(opt->dccpop_sc->dccpoc_val == NULL); - kfree(opt->dccpop_sc->dccpoc_val); - dccp_pr_debug("recycling confirm slot\n"); - } - memset(opt->dccpop_sc, 0, sizeof(*opt->dccpop_sc)); - - opt->dccpop_sc->dccpoc_val = rpref; - opt->dccpop_sc->dccpoc_len = rlen; - - /* update the option on our side [we are about to send the confirm] */ - rc = dccp_feat_update(sk, opt->dccpop_type, opt->dccpop_feat, *res); - if (rc) { - kfree(opt->dccpop_sc->dccpoc_val); - kfree(opt->dccpop_sc); - opt->dccpop_sc = NULL; - return rc; + val = fval->nn; } - dccp_pr_debug("Will confirm %d\n", *rpref); + /* Location is RX if this is a local-RX or remote-TX feature */ + rx = (is_local == (dccp_feat_table[idx].rxtx == FEAT_AT_RX)); - /* say we want to change to X but we just got a confirm X, suppress our - * change - */ - if (!opt->dccpop_conf) { - if (*opt->dccpop_val == *res) - opt->dccpop_conf = 1; - dccp_pr_debug("won't ask for change of same feature\n"); + dccp_debug(" -> activating %s %s, %sval=%llu\n", rx ? "RX" : "TX", + dccp_feat_fname(dccp_feat_table[idx].feat_num), + fval ? "" : "default ", (unsigned long long)val); + + return dccp_feat_table[idx].activation_hdlr(sk, val, rx); +} + +/** + * dccp_feat_activate - Activate feature value on socket + * @sk: fully connected DCCP socket (after handshake is complete) + * @feat_num: feature to activate, one of %dccp_feature_numbers + * @local: whether local (1) or remote (0) @feat_num is meant + * @fval: the value (SP or NN) to activate, or NULL to use the default value + * + * For general use this function is preferable over __dccp_feat_activate(). + */ +static int dccp_feat_activate(struct sock *sk, u8 feat_num, bool local, + dccp_feat_val const *fval) +{ + return __dccp_feat_activate(sk, dccp_feat_index(feat_num), local, fval); +} + +/* Test for "Req'd" feature (RFC 4340, 6.4) */ +static inline int dccp_feat_must_be_understood(u8 feat_num) +{ + return feat_num == DCCPF_CCID || feat_num == DCCPF_SHORT_SEQNOS || + feat_num == DCCPF_SEQUENCE_WINDOW; +} + +/* copy constructor, fval must not already contain allocated memory */ +static int dccp_feat_clone_sp_val(dccp_feat_val *fval, u8 const *val, u8 len) +{ + fval->sp.len = len; + if (fval->sp.len > 0) { + fval->sp.vec = kmemdup(val, len, gfp_any()); + if (fval->sp.vec == NULL) { + fval->sp.len = 0; + return -ENOBUFS; + } } + return 0; +} - return agree ? 0 : DCCP_FEAT_SP_NOAGREE; /* used for mandatory opts */ +static void dccp_feat_val_destructor(u8 feat_num, dccp_feat_val *val) +{ + if (unlikely(val == NULL)) + return; + if (dccp_feat_type(feat_num) == FEAT_SP) + kfree(val->sp.vec); + memset(val, 0, sizeof(*val)); } -static int dccp_feat_sp(struct sock *sk, u8 type, u8 feature, u8 *val, u8 len) +static struct dccp_feat_entry * + dccp_feat_clone_entry(struct dccp_feat_entry const *original) { - struct dccp_minisock *dmsk = dccp_msk(sk); - struct dccp_opt_pend *opt; - int rc = 1; - u8 t; + struct dccp_feat_entry *new; + u8 type = dccp_feat_type(original->feat_num); - /* - * We received a CHANGE. We gotta match it against our own preference - * list. If we got a CHANGE_R it means it's a change for us, so we need - * to compare our CHANGE_L list. - */ - if (type == DCCPO_CHANGE_L) - t = DCCPO_CHANGE_R; - else - t = DCCPO_CHANGE_L; + if (type == FEAT_UNKNOWN) + return NULL; - /* find our preference list for this feature */ - list_for_each_entry(opt, &dmsk->dccpms_pending, dccpop_node) { - if (opt->dccpop_type != t || opt->dccpop_feat != feature) - continue; + new = kmemdup(original, sizeof(struct dccp_feat_entry), gfp_any()); + if (new == NULL) + return NULL; - /* find the winner from the two preference lists */ - rc = dccp_feat_reconcile(sk, opt, val, len); - break; + if (type == FEAT_SP && dccp_feat_clone_sp_val(&new->val, + original->val.sp.vec, + original->val.sp.len)) { + kfree(new); + return NULL; } + return new; +} - /* We didn't deal with the change. This can happen if we have no - * preference list for the feature. In fact, it just shouldn't - * happen---if we understand a feature, we should have a preference list - * with at least the default value. - */ - BUG_ON(rc == 1); +static void dccp_feat_entry_destructor(struct dccp_feat_entry *entry) +{ + if (entry != NULL) { + dccp_feat_val_destructor(entry->feat_num, &entry->val); + kfree(entry); + } +} - return rc; +/* + * List management functions + * + * Feature negotiation lists rely on and maintain the following invariants: + * - each feat_num in the list is known, i.e. we know its type and default value + * - each feat_num/is_local combination is unique (old entries are overwritten) + * - SP values are always freshly allocated + * - list is sorted in increasing order of feature number (faster lookup) + */ +static struct dccp_feat_entry *dccp_feat_list_lookup(struct list_head *fn_list, + u8 feat_num, bool is_local) +{ + struct dccp_feat_entry *entry; + + list_for_each_entry(entry, fn_list, node) { + if (entry->feat_num == feat_num && entry->is_local == is_local) + return entry; + else if (entry->feat_num > feat_num) + break; + } + return NULL; } -static int dccp_feat_nn(struct sock *sk, u8 type, u8 feature, u8 *val, u8 len) +/** + * dccp_feat_entry_new - Central list update routine (called by all others) + * @head: list to add to + * @feat: feature number + * @local: whether the local (1) or remote feature with number @feat is meant + * + * This is the only constructor and serves to ensure the above invariants. + */ +static struct dccp_feat_entry * + dccp_feat_entry_new(struct list_head *head, u8 feat, bool local) { - struct dccp_opt_pend *opt; - struct dccp_minisock *dmsk = dccp_msk(sk); - u8 *copy; - int rc; + struct dccp_feat_entry *entry; + + list_for_each_entry(entry, head, node) + if (entry->feat_num == feat && entry->is_local == local) { + dccp_feat_val_destructor(entry->feat_num, &entry->val); + return entry; + } else if (entry->feat_num > feat) { + head = &entry->node; + break; + } - /* NN features must be Change L (sec. 6.3.2) */ - if (type != DCCPO_CHANGE_L) { - dccp_pr_debug("received %s for NN feature %d\n", - dccp_feat_typename(type), feature); - return -EFAULT; + entry = kmalloc(sizeof(*entry), gfp_any()); + if (entry != NULL) { + entry->feat_num = feat; + entry->is_local = local; + list_add_tail(&entry->node, head); } + return entry; +} - /* XXX sanity check opt val */ +/** + * dccp_feat_push_change - Add/overwrite a Change option in the list + * @fn_list: feature-negotiation list to update + * @feat: one of %dccp_feature_numbers + * @local: whether local (1) or remote (0) @feat_num is meant + * @needs_mandatory: whether to use Mandatory feature negotiation options + * @fval: pointer to NN/SP value to be inserted (will be copied) + */ +static int dccp_feat_push_change(struct list_head *fn_list, u8 feat, u8 local, + u8 mandatory, dccp_feat_val *fval) +{ + struct dccp_feat_entry *new = dccp_feat_entry_new(fn_list, feat, local); - /* copy option so we can confirm it */ - opt = kzalloc(sizeof(*opt), GFP_ATOMIC); - if (opt == NULL) + if (new == NULL) return -ENOMEM; - copy = kmemdup(val, len, GFP_ATOMIC); - if (copy == NULL) { - kfree(opt); - return -ENOMEM; - } + new->feat_num = feat; + new->is_local = local; + new->state = FEAT_INITIALISING; + new->needs_confirm = false; + new->empty_confirm = false; + new->val = *fval; + new->needs_mandatory = mandatory; - opt->dccpop_type = DCCPO_CONFIRM_R; /* NN can only confirm R */ - opt->dccpop_feat = feature; - opt->dccpop_val = copy; - opt->dccpop_len = len; + return 0; +} - /* change feature */ - rc = dccp_feat_update(sk, type, feature, *val); - if (rc) { - kfree(opt->dccpop_val); - kfree(opt); - return rc; - } +/** + * dccp_feat_push_confirm - Add a Confirm entry to the FN list + * @fn_list: feature-negotiation list to add to + * @feat: one of %dccp_feature_numbers + * @local: whether local (1) or remote (0) @feat_num is being confirmed + * @fval: pointer to NN/SP value to be inserted or NULL + * + * Returns 0 on success, a Reset code for further processing otherwise. + */ +static int dccp_feat_push_confirm(struct list_head *fn_list, u8 feat, u8 local, + dccp_feat_val *fval) +{ + struct dccp_feat_entry *new = dccp_feat_entry_new(fn_list, feat, local); - dccp_feat_debug(type, feature, *copy); + if (new == NULL) + return DCCP_RESET_CODE_TOO_BUSY; - list_add_tail(&opt->dccpop_node, &dmsk->dccpms_conf); + new->feat_num = feat; + new->is_local = local; + new->state = FEAT_STABLE; /* transition in 6.6.2 */ + new->needs_confirm = true; + new->empty_confirm = (fval == NULL); + new->val.nn = 0; /* zeroes the whole structure */ + if (!new->empty_confirm) + new->val = *fval; + new->needs_mandatory = false; return 0; } -static void dccp_feat_empty_confirm(struct dccp_minisock *dmsk, - u8 type, u8 feature) +static int dccp_push_empty_confirm(struct list_head *fn_list, u8 feat, u8 local) { - /* XXX check if other confirms for that are queued and recycle slot */ - struct dccp_opt_pend *opt = kzalloc(sizeof(*opt), GFP_ATOMIC); + return dccp_feat_push_confirm(fn_list, feat, local, NULL); +} - if (opt == NULL) { - /* XXX what do we do? Ignoring should be fine. It's a change - * after all =P - */ - return; - } +static inline void dccp_feat_list_pop(struct dccp_feat_entry *entry) +{ + list_del(&entry->node); + dccp_feat_entry_destructor(entry); +} - switch (type) { - case DCCPO_CHANGE_L: - opt->dccpop_type = DCCPO_CONFIRM_R; - break; - case DCCPO_CHANGE_R: - opt->dccpop_type = DCCPO_CONFIRM_L; - break; - default: - DCCP_WARN("invalid type %d\n", type); - kfree(opt); - return; +void dccp_feat_list_purge(struct list_head *fn_list) +{ + struct dccp_feat_entry *entry, *next; + + list_for_each_entry_safe(entry, next, fn_list, node) + dccp_feat_entry_destructor(entry); + INIT_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); } - opt->dccpop_feat = feature; - opt->dccpop_val = NULL; - opt->dccpop_len = 0; + return 0; - /* change feature */ - dccp_pr_debug("Empty %s(%d)\n", dccp_feat_typename(type), feature); +cloning_failed: + dccp_feat_list_purge(to); + return -ENOMEM; +} - list_add_tail(&opt->dccpop_node, &dmsk->dccpms_conf); +/** + * dccp_feat_valid_nn_length - Enforce length constraints on NN options + * Length is between 0 and %DCCP_OPTVAL_MAXLEN. Used for outgoing packets only, + * incoming options are accepted as long as their values are valid. + */ +static u8 dccp_feat_valid_nn_length(u8 feat_num) +{ + if (feat_num == DCCPF_ACK_RATIO) /* RFC 4340, 11.3 and 6.6.8 */ + return 2; + if (feat_num == DCCPF_SEQUENCE_WINDOW) /* RFC 4340, 7.5.2 and 6.5 */ + return 6; + return 0; +} + +static u8 dccp_feat_is_valid_nn_val(u8 feat_num, u64 val) +{ + switch (feat_num) { + case DCCPF_ACK_RATIO: + return val <= DCCPF_ACK_RATIO_MAX; + case DCCPF_SEQUENCE_WINDOW: + return val >= DCCPF_SEQ_WMIN && val <= DCCPF_SEQ_WMAX; + } + return 0; /* feature unknown - so we can't tell */ } -static void dccp_feat_flush_confirm(struct sock *sk) +/* check that SP values are within the ranges defined in RFC 4340 */ +static u8 dccp_feat_is_valid_sp_val(u8 feat_num, u8 val) { - struct dccp_minisock *dmsk = dccp_msk(sk); - /* Check if there is anything to confirm in the first place */ - int yes = !list_empty(&dmsk->dccpms_conf); + switch (feat_num) { + case DCCPF_CCID: + return val == DCCPC_CCID2 || val == DCCPC_CCID3; + /* Type-check Boolean feature values: */ + case DCCPF_SHORT_SEQNOS: + case DCCPF_ECN_INCAPABLE: + case DCCPF_SEND_ACK_VECTOR: + case DCCPF_SEND_NDP_COUNT: + case DCCPF_DATA_CHECKSUM: + case DCCPF_SEND_LEV_RATE: + return val < 2; + case DCCPF_MIN_CSUM_COVER: + return val < 16; + } + return 0; /* feature unknown */ +} - if (!yes) { - struct dccp_opt_pend *opt; +static u8 dccp_feat_sp_list_ok(u8 feat_num, u8 const *sp_list, u8 sp_len) +{ + if (sp_list == NULL || sp_len < 1) + return 0; + while (sp_len--) + if (!dccp_feat_is_valid_sp_val(feat_num, *sp_list++)) + return 0; + return 1; +} - list_for_each_entry(opt, &dmsk->dccpms_pending, dccpop_node) { - if (opt->dccpop_conf) { - yes = 1; - break; +/** + * dccp_feat_insert_opts - Generate FN options from current list state + * @skb: next sk_buff to be sent to the peer + * @dp: for client during handshake and general negotiation + * @dreq: used by the server only (all Changes/Confirms in LISTEN/RESPOND) + */ +int dccp_feat_insert_opts(struct dccp_sock *dp, struct dccp_request_sock *dreq, + struct sk_buff *skb) +{ + struct list_head *fn = dreq ? &dreq->dreq_featneg : &dp->dccps_featneg; + struct dccp_feat_entry *pos, *next; + u8 opt, type, len, *ptr, nn_in_nbo[DCCP_OPTVAL_MAXLEN]; + bool rpt; + + /* put entries into @skb in the order they appear in the list */ + list_for_each_entry_safe_reverse(pos, next, fn, node) { + opt = dccp_feat_genopt(pos); + type = dccp_feat_type(pos->feat_num); + rpt = false; + + if (pos->empty_confirm) { + len = 0; + ptr = NULL; + } else { + if (type == FEAT_SP) { + len = pos->val.sp.len; + ptr = pos->val.sp.vec; + rpt = pos->needs_confirm; + } else if (type == FEAT_NN) { + len = dccp_feat_valid_nn_length(pos->feat_num); + ptr = nn_in_nbo; + dccp_encode_value_var(pos->val.nn, ptr, len); + } else { + DCCP_BUG("unknown feature %u", pos->feat_num); + return -1; } } + dccp_feat_print_opt(opt, pos->feat_num, ptr, len, 0); + + if (dccp_insert_fn_opt(skb, opt, pos->feat_num, ptr, len, rpt)) + return -1; + if (pos->needs_mandatory && dccp_insert_option_mandatory(skb)) + return -1; + + if (skb->sk->sk_state == DCCP_OPEN && + (opt == DCCPO_CONFIRM_R || opt == DCCPO_CONFIRM_L)) { + /* + * Confirms don't get retransmitted (6.6.3) once the + * connection is in state OPEN + */ + dccp_feat_list_pop(pos); + } else { + /* + * Enter CHANGING after transmitting the Change + * option (6.6.2). + */ + if (pos->state == FEAT_INITIALISING) + pos->state = FEAT_CHANGING; + } } + return 0; +} - if (!yes) - return; +/** + * __feat_register_nn - Register new NN value on socket + * @fn: feature-negotiation list to register with + * @feat: an NN feature from %dccp_feature_numbers + * @mandatory: use Mandatory option if 1 + * @nn_val: value to register (restricted to 4 bytes) + * + * Note that NN features are local by definition (RFC 4340, 6.3.2). + */ +static int __feat_register_nn(struct list_head *fn, u8 feat, + u8 mandatory, u64 nn_val) +{ + dccp_feat_val fval = { .nn = nn_val }; + + if (dccp_feat_type(feat) != FEAT_NN || + !dccp_feat_is_valid_nn_val(feat, nn_val)) + return -EINVAL; + + /* Don't bother with default values, they will be activated anyway. */ + if (nn_val - (u64)dccp_feat_default_value(feat) == 0) + return 0; - /* OK there is something to confirm... */ - /* XXX check if packet is in flight? Send delayed ack?? */ - if (sk->sk_state == DCCP_OPEN) - dccp_send_ack(sk); + return dccp_feat_push_change(fn, feat, 1, mandatory, &fval); } -int dccp_feat_change_recv(struct sock *sk, u8 type, u8 feature, u8 *val, u8 len) +/** + * __feat_register_sp - Register new SP value/list on socket + * @fn: feature-negotiation list to register with + * @feat: an SP feature from %dccp_feature_numbers + * @is_local: whether the local (1) or the remote (0) @feat is meant + * @mandatory: use Mandatory option if 1 + * @sp_val: SP value followed by optional preference list + * @sp_len: length of @sp_val in bytes + */ +static int __feat_register_sp(struct list_head *fn, u8 feat, u8 is_local, + u8 mandatory, u8 const *sp_val, u8 sp_len) { - int rc; + dccp_feat_val fval; - dccp_feat_debug(type, feature, *val); + if (dccp_feat_type(feat) != FEAT_SP || + !dccp_feat_sp_list_ok(feat, sp_val, sp_len)) + return -EINVAL; - /* figure out if it's SP or NN feature */ - switch (feature) { - /* deal with SP features */ - case DCCPF_CCID: - rc = dccp_feat_sp(sk, type, feature, val, len); - break; + /* Avoid negotiating alien CCIDs by only advertising supported ones */ + if (feat == DCCPF_CCID && !ccid_support_check(sp_val, sp_len)) + return -EOPNOTSUPP; - /* deal with NN features */ - case DCCPF_ACK_RATIO: - rc = dccp_feat_nn(sk, type, feature, val, len); - break; + if (dccp_feat_clone_sp_val(&fval, sp_val, sp_len)) + return -ENOMEM; - /* XXX implement other features */ - default: - dccp_pr_debug("UNIMPLEMENTED: not handling %s(%d, ...)\n", - dccp_feat_typename(type), feature); - rc = -EFAULT; - break; + return dccp_feat_push_change(fn, feat, is_local, mandatory, &fval); +} + +/** + * dccp_feat_register_sp - Register requests to change SP feature values + * @sk: client or listening socket + * @feat: one of %dccp_feature_numbers + * @is_local: whether the local (1) or remote (0) @feat is meant + * @list: array of preferred values, in descending order of preference + * @len: length of @list in bytes + */ +int dccp_feat_register_sp(struct sock *sk, u8 feat, u8 is_local, + u8 const *list, u8 len) +{ /* any changes must be registered before establishing the connection */ + if (sk->sk_state != DCCP_CLOSED) + return -EISCONN; + if (dccp_feat_type(feat) != FEAT_SP) + return -EINVAL; + return __feat_register_sp(&dccp_sk(sk)->dccps_featneg, feat, is_local, + 0, list, len); +} + +/** + * dccp_feat_nn_get - Query current/pending value of NN feature + * @sk: DCCP socket of an established connection + * @feat: NN feature number from %dccp_feature_numbers + * + * For a known NN feature, returns value currently being negotiated, or + * current (confirmed) value if no negotiation is going on. + */ +u64 dccp_feat_nn_get(struct sock *sk, u8 feat) +{ + if (dccp_feat_type(feat) == FEAT_NN) { + struct dccp_sock *dp = dccp_sk(sk); + struct dccp_feat_entry *entry; + + entry = dccp_feat_list_lookup(&dp->dccps_featneg, feat, 1); + if (entry != NULL) + return entry->val.nn; + + switch (feat) { + case DCCPF_ACK_RATIO: + return dp->dccps_l_ack_ratio; + case DCCPF_SEQUENCE_WINDOW: + return dp->dccps_l_seq_win; + } + } + DCCP_BUG("attempt to look up unsupported feature %u", feat); + return 0; +} +EXPORT_SYMBOL_GPL(dccp_feat_nn_get); + +/** + * dccp_feat_signal_nn_change - Update NN values for an established connection + * @sk: DCCP socket of an established connection + * @feat: NN feature number from %dccp_feature_numbers + * @nn_val: the new value to use + * + * This function is used to communicate NN updates out-of-band. + */ +int dccp_feat_signal_nn_change(struct sock *sk, u8 feat, u64 nn_val) +{ + struct list_head *fn = &dccp_sk(sk)->dccps_featneg; + dccp_feat_val fval = { .nn = nn_val }; + struct dccp_feat_entry *entry; + + if (sk->sk_state != DCCP_OPEN && sk->sk_state != DCCP_PARTOPEN) + return 0; + + if (dccp_feat_type(feat) != FEAT_NN || + !dccp_feat_is_valid_nn_val(feat, nn_val)) + return -EINVAL; + + if (nn_val == dccp_feat_nn_get(sk, feat)) + return 0; /* already set or negotiation under way */ + + entry = dccp_feat_list_lookup(fn, feat, 1); + if (entry != NULL) { + dccp_pr_debug("Clobbering existing NN entry %llu -> %llu\n", + (unsigned long long)entry->val.nn, + (unsigned long long)nn_val); + dccp_feat_list_pop(entry); } - /* check if there were problems changing features */ - if (rc) { - /* If we don't agree on SP, we sent a confirm for old value. - * However we propagate rc to caller in case option was - * mandatory + inet_csk_schedule_ack(sk); + return dccp_feat_push_change(fn, feat, 1, 0, &fval); +} +EXPORT_SYMBOL_GPL(dccp_feat_signal_nn_change); + +/* + * Tracking features whose value depend on the choice of CCID + * + * This is designed with an extension in mind so that a list walk could be done + * before activating any features. However, the existing framework was found to + * work satisfactorily up until now, the automatic verification is left open. + * When adding new CCIDs, add a corresponding dependency table here. + */ +static const struct ccid_dependency *dccp_feat_ccid_deps(u8 ccid, bool is_local) +{ + static const struct ccid_dependency ccid2_dependencies[2][2] = { + /* + * CCID2 mandates Ack Vectors (RFC 4341, 4.): as CCID is a TX + * feature and Send Ack Vector is an RX feature, `is_local' + * needs to be reversed. */ - if (rc != DCCP_FEAT_SP_NOAGREE) - dccp_feat_empty_confirm(dccp_msk(sk), type, feature); + { /* Dependencies of the receiver-side (remote) CCID2 */ + { + .dependent_feat = DCCPF_SEND_ACK_VECTOR, + .is_local = true, + .is_mandatory = true, + .val = 1 + }, + { 0, 0, 0, 0 } + }, + { /* Dependencies of the sender-side (local) CCID2 */ + { + .dependent_feat = DCCPF_SEND_ACK_VECTOR, + .is_local = false, + .is_mandatory = true, + .val = 1 + }, + { 0, 0, 0, 0 } + } + }; + static const struct ccid_dependency ccid3_dependencies[2][5] = { + { /* + * Dependencies of the receiver-side CCID3 + */ + { /* locally disable Ack Vectors */ + .dependent_feat = DCCPF_SEND_ACK_VECTOR, + .is_local = true, + .is_mandatory = false, + .val = 0 + }, + { /* see below why Send Loss Event Rate is on */ + .dependent_feat = DCCPF_SEND_LEV_RATE, + .is_local = true, + .is_mandatory = true, + .val = 1 + }, + { /* NDP Count is needed as per RFC 4342, 6.1.1 */ + .dependent_feat = DCCPF_SEND_NDP_COUNT, + .is_local = false, + .is_mandatory = true, + .val = 1 + }, + { 0, 0, 0, 0 }, + }, + { /* + * CCID3 at the TX side: we request that the HC-receiver + * will not send Ack Vectors (they will be ignored, so + * Mandatory is not set); we enable Send Loss Event Rate + * (Mandatory since the implementation does not support + * the Loss Intervals option of RFC 4342, 8.6). + * The last two options are for peer's information only. + */ + { + .dependent_feat = DCCPF_SEND_ACK_VECTOR, + .is_local = false, + .is_mandatory = false, + .val = 0 + }, + { + .dependent_feat = DCCPF_SEND_LEV_RATE, + .is_local = false, + .is_mandatory = true, + .val = 1 + }, + { /* this CCID does not support Ack Ratio */ + .dependent_feat = DCCPF_ACK_RATIO, + .is_local = true, + .is_mandatory = false, + .val = 0 + }, + { /* tell receiver we are sending NDP counts */ + .dependent_feat = DCCPF_SEND_NDP_COUNT, + .is_local = true, + .is_mandatory = false, + .val = 1 + }, + { 0, 0, 0, 0 } + } + }; + switch (ccid) { + case DCCPC_CCID2: + return ccid2_dependencies[is_local]; + case DCCPC_CCID3: + return ccid3_dependencies[is_local]; + default: + return NULL; } +} - /* generate the confirm [if required] */ - dccp_feat_flush_confirm(sk); - +/** + * dccp_feat_propagate_ccid - Resolve dependencies of features on choice of CCID + * @fn: feature-negotiation list to update + * @id: CCID number to track + * @is_local: whether TX CCID (1) or RX CCID (0) is meant + * + * This function needs to be called after registering all other features. + */ +static int dccp_feat_propagate_ccid(struct list_head *fn, u8 id, bool is_local) +{ + const struct ccid_dependency *table = dccp_feat_ccid_deps(id, is_local); + int i, rc = (table == NULL); + + for (i = 0; rc == 0 && table[i].dependent_feat != DCCPF_RESERVED; i++) + if (dccp_feat_type(table[i].dependent_feat) == FEAT_SP) + rc = __feat_register_sp(fn, table[i].dependent_feat, + table[i].is_local, + table[i].is_mandatory, + &table[i].val, 1); + else + rc = __feat_register_nn(fn, table[i].dependent_feat, + table[i].is_mandatory, + table[i].val); return rc; } -EXPORT_SYMBOL_GPL(dccp_feat_change_recv); +/** + * dccp_feat_finalise_settings - Finalise settings before starting negotiation + * @dp: client or listening socket (settings will be inherited) + * + * This is called after all registrations (socket initialisation, sysctls, and + * sockopt calls), and before sending the first packet containing Change options + * (ie. client-Request or server-Response), to ensure internal consistency. + */ +int dccp_feat_finalise_settings(struct dccp_sock *dp) +{ + struct list_head *fn = &dp->dccps_featneg; + struct dccp_feat_entry *entry; + int i = 2, ccids[2] = { -1, -1 }; -int dccp_feat_confirm_recv(struct sock *sk, u8 type, u8 feature, - u8 *val, u8 len) + /* + * Propagating CCIDs: + * 1) not useful to propagate CCID settings if this host advertises more + * than one CCID: the choice of CCID may still change - if this is + * the client, or if this is the server and the client sends + * singleton CCID values. + * 2) since is that propagate_ccid changes the list, we defer changing + * the sorted list until after the traversal. + */ + list_for_each_entry(entry, fn, node) + if (entry->feat_num == DCCPF_CCID && entry->val.sp.len == 1) + ccids[entry->is_local] = entry->val.sp.vec[0]; + while (i--) + if (ccids[i] > 0 && dccp_feat_propagate_ccid(fn, ccids[i], i)) + return -1; + dccp_feat_print_fnlist(fn); + return 0; +} + +/** + * dccp_feat_server_ccid_dependencies - Resolve CCID-dependent features + * It is the server which resolves the dependencies once the CCID has been + * fully negotiated. If no CCID has been negotiated, it uses the default CCID. + */ +int dccp_feat_server_ccid_dependencies(struct dccp_request_sock *dreq) { - u8 t; - struct dccp_opt_pend *opt; - struct dccp_minisock *dmsk = dccp_msk(sk); - int found = 0; - int all_confirmed = 1; + struct list_head *fn = &dreq->dreq_featneg; + struct dccp_feat_entry *entry; + u8 is_local, ccid; - dccp_feat_debug(type, feature, *val); + for (is_local = 0; is_local <= 1; is_local++) { + entry = dccp_feat_list_lookup(fn, DCCPF_CCID, is_local); - /* locate our change request */ - switch (type) { - case DCCPO_CONFIRM_L: t = DCCPO_CHANGE_R; break; - case DCCPO_CONFIRM_R: t = DCCPO_CHANGE_L; break; - default: DCCP_WARN("invalid type %d\n", type); - return 1; + if (entry != NULL && !entry->empty_confirm) + ccid = entry->val.sp.vec[0]; + else + ccid = dccp_feat_default_value(DCCPF_CCID); + if (dccp_feat_propagate_ccid(fn, ccid, is_local)) + return -1; } - /* XXX sanity check feature value */ + return 0; +} + +/* Select the first entry in @servlist that also occurs in @clilist (6.3.1) */ +static int dccp_feat_preflist_match(u8 *servlist, u8 slen, u8 *clilist, u8 clen) +{ + u8 c, s; - list_for_each_entry(opt, &dmsk->dccpms_pending, dccpop_node) { - if (!opt->dccpop_conf && opt->dccpop_type == t && - opt->dccpop_feat == feature) { - found = 1; - dccp_pr_debug("feature %d found\n", opt->dccpop_feat); + for (s = 0; s < slen; s++) + for (c = 0; c < clen; c++) + if (servlist[s] == clilist[c]) + return servlist[s]; + return -1; +} - /* XXX do sanity check */ +/** + * dccp_feat_prefer - Move preferred entry to the start of array + * Reorder the @array_len elements in @array so that @preferred_value comes + * first. Returns >0 to indicate that @preferred_value does occur in @array. + */ +static u8 dccp_feat_prefer(u8 preferred_value, u8 *array, u8 array_len) +{ + u8 i, does_occur = 0; - opt->dccpop_conf = 1; + if (array != NULL) { + for (i = 0; i < array_len; i++) + if (array[i] == preferred_value) { + array[i] = array[0]; + does_occur++; + } + if (does_occur) + array[0] = preferred_value; + } + return does_occur; +} - /* We got a confirmation---change the option */ - dccp_feat_update(sk, opt->dccpop_type, - opt->dccpop_feat, *val); +/** + * dccp_feat_reconcile - Reconcile SP preference lists + * @fval: SP list to reconcile into + * @arr: received SP preference list + * @len: length of @arr in bytes + * @is_server: whether this side is the server (and @fv is the server's list) + * @reorder: whether to reorder the list in @fv after reconciling with @arr + * When successful, > 0 is returned and the reconciled list is in @fval. + * A value of 0 means that negotiation failed (no shared entry). + */ +static int dccp_feat_reconcile(dccp_feat_val *fv, u8 *arr, u8 len, + bool is_server, bool reorder) +{ + int rc; - /* XXX check the return value of dccp_feat_update */ - break; - } + if (!fv->sp.vec || !arr) { + DCCP_CRIT("NULL feature value or array"); + return 0; + } + + if (is_server) + rc = dccp_feat_preflist_match(fv->sp.vec, fv->sp.len, arr, len); + else + rc = dccp_feat_preflist_match(arr, len, fv->sp.vec, fv->sp.len); + + if (!reorder) + return rc; + if (rc < 0) + return 0; + + /* + * Reorder list: used for activating features and in dccp_insert_fn_opt. + */ + return dccp_feat_prefer(rc, fv->sp.vec, fv->sp.len); +} + +/** + * dccp_feat_change_recv - Process incoming ChangeL/R options + * @fn: feature-negotiation list to update + * @is_mandatory: whether the Change was preceded by a Mandatory option + * @opt: %DCCPO_CHANGE_L or %DCCPO_CHANGE_R + * @feat: one of %dccp_feature_numbers + * @val: NN value or SP value/preference list + * @len: length of @val in bytes + * @server: whether this node is the server (1) or the client (0) + */ +static u8 dccp_feat_change_recv(struct list_head *fn, u8 is_mandatory, u8 opt, + u8 feat, u8 *val, u8 len, const bool server) +{ + u8 defval, type = dccp_feat_type(feat); + const bool local = (opt == DCCPO_CHANGE_R); + struct dccp_feat_entry *entry; + dccp_feat_val fval; - if (!opt->dccpop_conf) - all_confirmed = 0; + if (len == 0 || type == FEAT_UNKNOWN) /* 6.1 and 6.6.8 */ + goto unknown_feature_or_value; + + dccp_feat_print_opt(opt, feat, val, len, is_mandatory); + + /* + * Negotiation of NN features: Change R is invalid, so there is no + * simultaneous negotiation; hence we do not look up in the list. + */ + if (type == FEAT_NN) { + if (local || len > sizeof(fval.nn)) + goto unknown_feature_or_value; + + /* 6.3.2: "The feature remote MUST accept any valid value..." */ + fval.nn = dccp_decode_value_var(val, len); + if (!dccp_feat_is_valid_nn_val(feat, fval.nn)) + goto unknown_feature_or_value; + + return dccp_feat_push_confirm(fn, feat, local, &fval); } - /* fix re-transmit timer */ - /* XXX gotta make sure that no option negotiation occurs during - * connection shutdown. Consider that the CLOSEREQ is sent and timer is - * on. if all options are confirmed it might kill timer which should - * remain alive until close is received. + /* + * Unidirectional/simultaneous negotiation of SP features (6.3.1) */ - if (all_confirmed) { - dccp_pr_debug("clear feat negotiation timer %p\n", sk); - inet_csk_clear_xmit_timer(sk, ICSK_TIME_RETRANS); + entry = dccp_feat_list_lookup(fn, feat, local); + if (entry == NULL) { + /* + * No particular preferences have been registered. We deal with + * this situation by assuming that all valid values are equally + * acceptable, and apply the following checks: + * - if the peer's list is a singleton, we accept a valid value; + * - if we are the server, we first try to see if the peer (the + * client) advertises the default value. If yes, we use it, + * otherwise we accept the preferred value; + * - else if we are the client, we use the first list element. + */ + if (dccp_feat_clone_sp_val(&fval, val, 1)) + return DCCP_RESET_CODE_TOO_BUSY; + + if (len > 1 && server) { + defval = dccp_feat_default_value(feat); + if (dccp_feat_preflist_match(&defval, 1, val, len) > -1) + fval.sp.vec[0] = defval; + } else if (!dccp_feat_is_valid_sp_val(feat, fval.sp.vec[0])) { + kfree(fval.sp.vec); + goto unknown_feature_or_value; + } + + /* Treat unsupported CCIDs like invalid values */ + if (feat == DCCPF_CCID && !ccid_support_check(fval.sp.vec, 1)) { + kfree(fval.sp.vec); + goto not_valid_or_not_known; + } + + return dccp_feat_push_confirm(fn, feat, local, &fval); + + } else if (entry->state == FEAT_UNSTABLE) { /* 6.6.2 */ + return 0; } - if (!found) - dccp_pr_debug("%s(%d, ...) never requested\n", - dccp_feat_typename(type), feature); + if (dccp_feat_reconcile(&entry->val, val, len, server, true)) { + entry->empty_confirm = false; + } else if (is_mandatory) { + return DCCP_RESET_CODE_MANDATORY_ERROR; + } else if (entry->state == FEAT_INITIALISING) { + /* + * Failed simultaneous negotiation (server only): try to `save' + * the connection by checking whether entry contains the default + * value for @feat. If yes, send an empty Confirm to signal that + * the received Change was not understood - which implies using + * the default value. + * If this also fails, we use Reset as the last resort. + */ + WARN_ON(!server); + defval = dccp_feat_default_value(feat); + if (!dccp_feat_reconcile(&entry->val, &defval, 1, server, true)) + return DCCP_RESET_CODE_OPTION_ERROR; + entry->empty_confirm = true; + } + entry->needs_confirm = true; + entry->needs_mandatory = false; + entry->state = FEAT_STABLE; return 0; -} -EXPORT_SYMBOL_GPL(dccp_feat_confirm_recv); +unknown_feature_or_value: + if (!is_mandatory) + return dccp_push_empty_confirm(fn, feat, local); -void dccp_feat_clean(struct dccp_minisock *dmsk) +not_valid_or_not_known: + return is_mandatory ? DCCP_RESET_CODE_MANDATORY_ERROR + : DCCP_RESET_CODE_OPTION_ERROR; +} + +/** + * dccp_feat_confirm_recv - Process received Confirm options + * @fn: feature-negotiation list to update + * @is_mandatory: whether @opt was preceded by a Mandatory option + * @opt: %DCCPO_CONFIRM_L or %DCCPO_CONFIRM_R + * @feat: one of %dccp_feature_numbers + * @val: NN value or SP value/preference list + * @len: length of @val in bytes + * @server: whether this node is server (1) or client (0) + */ +static u8 dccp_feat_confirm_recv(struct list_head *fn, u8 is_mandatory, u8 opt, + u8 feat, u8 *val, u8 len, const bool server) { - struct dccp_opt_pend *opt, *next; + u8 *plist, plen, type = dccp_feat_type(feat); + const bool local = (opt == DCCPO_CONFIRM_R); + struct dccp_feat_entry *entry = dccp_feat_list_lookup(fn, feat, local); - list_for_each_entry_safe(opt, next, &dmsk->dccpms_pending, - dccpop_node) { - BUG_ON(opt->dccpop_val == NULL); - kfree(opt->dccpop_val); + dccp_feat_print_opt(opt, feat, val, len, is_mandatory); - if (opt->dccpop_sc != NULL) { - BUG_ON(opt->dccpop_sc->dccpoc_val == NULL); - kfree(opt->dccpop_sc->dccpoc_val); - kfree(opt->dccpop_sc); - } + if (entry == NULL) { /* nothing queued: ignore or handle error */ + if (is_mandatory && type == FEAT_UNKNOWN) + return DCCP_RESET_CODE_MANDATORY_ERROR; + + if (!local && type == FEAT_NN) /* 6.3.2 */ + goto confirmation_failed; + return 0; + } + + if (entry->state != FEAT_CHANGING) /* 6.6.2 */ + return 0; - kfree(opt); + if (len == 0) { + if (dccp_feat_must_be_understood(feat)) /* 6.6.7 */ + goto confirmation_failed; + /* + * Empty Confirm during connection setup: this means reverting + * to the `old' value, which in this case is the default. Since + * we handle default values automatically when no other values + * have been set, we revert to the old value by removing this + * entry from the list. + */ + dccp_feat_list_pop(entry); + return 0; } - INIT_LIST_HEAD(&dmsk->dccpms_pending); - list_for_each_entry_safe(opt, next, &dmsk->dccpms_conf, dccpop_node) { - BUG_ON(opt == NULL); - if (opt->dccpop_val != NULL) - kfree(opt->dccpop_val); - kfree(opt); + if (type == FEAT_NN) { + if (len > sizeof(entry->val.nn)) + goto confirmation_failed; + + if (entry->val.nn == dccp_decode_value_var(val, len)) + goto confirmation_succeeded; + + DCCP_WARN("Bogus Confirm for non-existing value\n"); + goto confirmation_failed; } - INIT_LIST_HEAD(&dmsk->dccpms_conf); -} -EXPORT_SYMBOL_GPL(dccp_feat_clean); + /* + * Parsing SP Confirms: the first element of @val is the preferred + * SP value which the peer confirms, the remainder depends on @len. + * Note that only the confirmed value need to be a valid SP value. + */ + if (!dccp_feat_is_valid_sp_val(feat, *val)) + goto confirmation_failed; + + if (len == 1) { /* peer didn't supply a preference list */ + plist = val; + plen = len; + } else { /* preferred value + preference list */ + plist = val + 1; + plen = len - 1; + } + + /* Check whether the peer got the reconciliation right (6.6.8) */ + if (dccp_feat_reconcile(&entry->val, plist, plen, server, 0) != *val) { + DCCP_WARN("Confirm selected the wrong value %u\n", *val); + return DCCP_RESET_CODE_OPTION_ERROR; + } + entry->val.sp.vec[0] = *val; + +confirmation_succeeded: + entry->state = FEAT_STABLE; + return 0; + +confirmation_failed: + DCCP_WARN("Confirmation failed\n"); + return is_mandatory ? DCCP_RESET_CODE_MANDATORY_ERROR + : DCCP_RESET_CODE_OPTION_ERROR; +} -/* this is to be called only when a listening sock creates its child. It is - * assumed by the function---the confirm is not duplicated, but rather it is - * "passed on". +/** + * dccp_feat_handle_nn_established - Fast-path reception of NN options + * @sk: socket of an established DCCP connection + * @mandatory: whether @opt was preceded by a Mandatory option + * @opt: %DCCPO_CHANGE_L | %DCCPO_CONFIRM_R (NN only) + * @feat: NN number, one of %dccp_feature_numbers + * @val: NN value + * @len: length of @val in bytes + * + * This function combines the functionality of change_recv/confirm_recv, with + * the following differences (reset codes are the same): + * - cleanup after receiving the Confirm; + * - values are directly activated after successful parsing; + * - deliberately restricted to NN features. + * The restriction to NN features is essential since SP features can have non- + * predictable outcomes (depending on the remote configuration), and are inter- + * dependent (CCIDs for instance cause further dependencies). */ -int dccp_feat_clone(struct sock *oldsk, struct sock *newsk) +static u8 dccp_feat_handle_nn_established(struct sock *sk, u8 mandatory, u8 opt, + u8 feat, u8 *val, u8 len) { - struct dccp_minisock *olddmsk = dccp_msk(oldsk); - struct dccp_minisock *newdmsk = dccp_msk(newsk); - struct dccp_opt_pend *opt; - int rc = 0; + struct list_head *fn = &dccp_sk(sk)->dccps_featneg; + const bool local = (opt == DCCPO_CONFIRM_R); + struct dccp_feat_entry *entry; + u8 type = dccp_feat_type(feat); + dccp_feat_val fval; - INIT_LIST_HEAD(&newdmsk->dccpms_pending); - INIT_LIST_HEAD(&newdmsk->dccpms_conf); + dccp_feat_print_opt(opt, feat, val, len, mandatory); - list_for_each_entry(opt, &olddmsk->dccpms_pending, dccpop_node) { - struct dccp_opt_pend *newopt; - /* copy the value of the option */ - u8 *val = kmemdup(opt->dccpop_val, opt->dccpop_len, GFP_ATOMIC); + /* Ignore non-mandatory unknown and non-NN features */ + if (type == FEAT_UNKNOWN) { + if (local && !mandatory) + return 0; + goto fast_path_unknown; + } else if (type != FEAT_NN) { + return 0; + } - if (val == NULL) - goto out_clean; + /* + * We don't accept empty Confirms, since in fast-path feature + * negotiation the values are enabled immediately after sending + * the Change option. + * Empty Changes on the other hand are invalid (RFC 4340, 6.1). + */ + if (len == 0 || len > sizeof(fval.nn)) + goto fast_path_unknown; - newopt = kmemdup(opt, sizeof(*newopt), GFP_ATOMIC); - if (newopt == NULL) { - kfree(val); - goto out_clean; - } + if (opt == DCCPO_CHANGE_L) { + fval.nn = dccp_decode_value_var(val, len); + if (!dccp_feat_is_valid_nn_val(feat, fval.nn)) + goto fast_path_unknown; + + if (dccp_feat_push_confirm(fn, feat, local, &fval) || + dccp_feat_activate(sk, feat, local, &fval)) + return DCCP_RESET_CODE_TOO_BUSY; + + /* set the `Ack Pending' flag to piggyback a Confirm */ + inet_csk_schedule_ack(sk); - /* insert the option */ - newopt->dccpop_val = val; - list_add_tail(&newopt->dccpop_node, &newdmsk->dccpms_pending); + } else if (opt == DCCPO_CONFIRM_R) { + entry = dccp_feat_list_lookup(fn, feat, local); + if (entry == NULL || entry->state != FEAT_CHANGING) + return 0; - /* XXX what happens with backlogs and multiple connections at - * once... + fval.nn = dccp_decode_value_var(val, len); + /* + * Just ignore a value that doesn't match our current value. + * If the option changes twice within two RTTs, then at least + * one CONFIRM will be received for the old value after a + * new CHANGE was sent. */ - /* the master socket no longer needs to worry about confirms */ - opt->dccpop_sc = NULL; /* it's not a memleak---new socket has it */ + if (fval.nn != entry->val.nn) + return 0; - /* reset state for a new socket */ - opt->dccpop_conf = 0; - } + /* Only activate after receiving the Confirm option (6.6.1). */ + dccp_feat_activate(sk, feat, local, &fval); - /* XXX not doing anything about the conf queue */ + /* It has been confirmed - so remove the entry */ + dccp_feat_list_pop(entry); -out: - return rc; + } else { + DCCP_WARN("Received illegal option %u\n", opt); + goto fast_path_failed; + } + return 0; -out_clean: - dccp_feat_clean(newdmsk); - rc = -ENOMEM; - goto out; -} +fast_path_unknown: + if (!mandatory) + return dccp_push_empty_confirm(fn, feat, local); -EXPORT_SYMBOL_GPL(dccp_feat_clone); +fast_path_failed: + return mandatory ? DCCP_RESET_CODE_MANDATORY_ERROR + : DCCP_RESET_CODE_OPTION_ERROR; +} -static int __dccp_feat_init(struct dccp_minisock *dmsk, u8 type, u8 feat, - u8 *val, u8 len) +/** + * dccp_feat_parse_options - Process Feature-Negotiation Options + * @sk: for general use and used by the client during connection setup + * @dreq: used by the server during connection setup + * @mandatory: whether @opt was preceded by a Mandatory option + * @opt: %DCCPO_CHANGE_L | %DCCPO_CHANGE_R | %DCCPO_CONFIRM_L | %DCCPO_CONFIRM_R + * @feat: one of %dccp_feature_numbers + * @val: value contents of @opt + * @len: length of @val in bytes + * + * Returns 0 on success, a Reset code for ending the connection otherwise. + */ +int dccp_feat_parse_options(struct sock *sk, struct dccp_request_sock *dreq, + u8 mandatory, u8 opt, u8 feat, u8 *val, u8 len) { - int rc = -ENOMEM; - u8 *copy = kmemdup(val, len, GFP_KERNEL); + struct dccp_sock *dp = dccp_sk(sk); + struct list_head *fn = dreq ? &dreq->dreq_featneg : &dp->dccps_featneg; + bool server = false; - if (copy != NULL) { - rc = dccp_feat_change(dmsk, type, feat, copy, len, GFP_KERNEL); - if (rc) - kfree(copy); + switch (sk->sk_state) { + /* + * Negotiation during connection setup + */ + case DCCP_LISTEN: + server = true; /* fall through */ + case DCCP_REQUESTING: + switch (opt) { + case DCCPO_CHANGE_L: + case DCCPO_CHANGE_R: + return dccp_feat_change_recv(fn, mandatory, opt, feat, + val, len, server); + case DCCPO_CONFIRM_R: + case DCCPO_CONFIRM_L: + return dccp_feat_confirm_recv(fn, mandatory, opt, feat, + val, len, server); + } + break; + /* + * Support for exchanging NN options on an established connection. + */ + case DCCP_OPEN: + case DCCP_PARTOPEN: + return dccp_feat_handle_nn_established(sk, mandatory, opt, feat, + val, len); } - return rc; + return 0; /* ignore FN options in all other states */ } -int dccp_feat_init(struct dccp_minisock *dmsk) +/** + * dccp_feat_init - Seed feature negotiation with host-specific defaults + * This initialises global defaults, depending on the value of the sysctls. + * These can later be overridden by registering changes via setsockopt calls. + * The last link in the chain is finalise_settings, to make sure that between + * here and the start of actual feature negotiation no inconsistencies enter. + * + * All features not appearing below use either defaults or are otherwise + * later adjusted through dccp_feat_finalise_settings(). + */ +int dccp_feat_init(struct sock *sk) { + struct list_head *fn = &dccp_sk(sk)->dccps_featneg; + u8 on = 1, off = 0; int rc; + struct { + u8 *val; + u8 len; + } tx, rx; + + /* Non-negotiable (NN) features */ + rc = __feat_register_nn(fn, DCCPF_SEQUENCE_WINDOW, 0, + sysctl_dccp_sequence_window); + if (rc) + return rc; - INIT_LIST_HEAD(&dmsk->dccpms_pending); - INIT_LIST_HEAD(&dmsk->dccpms_conf); + /* Server-priority (SP) features */ - /* CCID L */ - rc = __dccp_feat_init(dmsk, DCCPO_CHANGE_L, DCCPF_CCID, - &dmsk->dccpms_tx_ccid, 1); + /* Advertise that short seqnos are not supported (7.6.1) */ + rc = __feat_register_sp(fn, DCCPF_SHORT_SEQNOS, true, true, &off, 1); if (rc) - goto out; + return rc; + + /* RFC 4340 12.1: "If a DCCP is not ECN capable, ..." */ + rc = __feat_register_sp(fn, DCCPF_ECN_INCAPABLE, true, true, &on, 1); + if (rc) + return rc; + + /* + * We advertise the available list of CCIDs and reorder according to + * preferences, to avoid failure resulting from negotiating different + * singleton values (which always leads to failure). + * These settings can still (later) be overridden via sockopts. + */ + if (ccid_get_builtin_ccids(&tx.val, &tx.len) || + ccid_get_builtin_ccids(&rx.val, &rx.len)) + return -ENOBUFS; + + if (!dccp_feat_prefer(sysctl_dccp_tx_ccid, tx.val, tx.len) || + !dccp_feat_prefer(sysctl_dccp_rx_ccid, rx.val, rx.len)) + goto free_ccid_lists; - /* CCID R */ - rc = __dccp_feat_init(dmsk, DCCPO_CHANGE_R, DCCPF_CCID, - &dmsk->dccpms_rx_ccid, 1); + rc = __feat_register_sp(fn, DCCPF_CCID, true, false, tx.val, tx.len); if (rc) - goto out; + goto free_ccid_lists; - /* Ack ratio */ - rc = __dccp_feat_init(dmsk, DCCPO_CHANGE_L, DCCPF_ACK_RATIO, - &dmsk->dccpms_ack_ratio, 1); -out: + rc = __feat_register_sp(fn, DCCPF_CCID, false, false, rx.val, rx.len); + +free_ccid_lists: + kfree(tx.val); + kfree(rx.val); return rc; } -EXPORT_SYMBOL_GPL(dccp_feat_init); - -#ifdef CONFIG_IP_DCCP_DEBUG -const char *dccp_feat_typename(const u8 type) +int dccp_feat_activate_values(struct sock *sk, struct list_head *fn_list) { - switch(type) { - case DCCPO_CHANGE_L: return("ChangeL"); - case DCCPO_CONFIRM_L: return("ConfirmL"); - case DCCPO_CHANGE_R: return("ChangeR"); - case DCCPO_CONFIRM_R: return("ConfirmR"); - /* the following case must not appear in feature negotation */ - default: dccp_pr_debug("unknown type %d [BUG!]\n", type); + struct dccp_sock *dp = dccp_sk(sk); + struct dccp_feat_entry *cur, *next; + int idx; + dccp_feat_val *fvals[DCCP_FEAT_SUPPORTED_MAX][2] = { + [0 ... DCCP_FEAT_SUPPORTED_MAX-1] = { NULL, NULL } + }; + + list_for_each_entry(cur, fn_list, node) { + /* + * An empty Confirm means that either an unknown feature type + * or an invalid value was present. In the first case there is + * nothing to activate, in the other the default value is used. + */ + if (cur->empty_confirm) + continue; + + idx = dccp_feat_index(cur->feat_num); + if (idx < 0) { + DCCP_BUG("Unknown feature %u", cur->feat_num); + goto activation_failed; + } + if (cur->state != FEAT_STABLE) { + DCCP_CRIT("Negotiation of %s %s failed in state %s", + cur->is_local ? "local" : "remote", + dccp_feat_fname(cur->feat_num), + dccp_feat_sname[cur->state]); + goto activation_failed; + } + fvals[idx][cur->is_local] = &cur->val; } - return NULL; -} -EXPORT_SYMBOL_GPL(dccp_feat_typename); + /* + * Activate in decreasing order of index, so that the CCIDs are always + * activated as the last feature. This avoids the case where a CCID + * relies on the initialisation of one or more features that it depends + * on (e.g. Send NDP Count, Send Ack Vector, and Ack Ratio features). + */ + for (idx = DCCP_FEAT_SUPPORTED_MAX; --idx >= 0;) + if (__dccp_feat_activate(sk, idx, 0, fvals[idx][0]) || + __dccp_feat_activate(sk, idx, 1, fvals[idx][1])) { + DCCP_CRIT("Could not activate %d", idx); + goto activation_failed; + } -const char *dccp_feat_name(const u8 feat) -{ - static const char *feature_names[] = { - [DCCPF_RESERVED] = "Reserved", - [DCCPF_CCID] = "CCID", - [DCCPF_SHORT_SEQNOS] = "Allow Short Seqnos", - [DCCPF_SEQUENCE_WINDOW] = "Sequence Window", - [DCCPF_ECN_INCAPABLE] = "ECN Incapable", - [DCCPF_ACK_RATIO] = "Ack Ratio", - [DCCPF_SEND_ACK_VECTOR] = "Send ACK Vector", - [DCCPF_SEND_NDP_COUNT] = "Send NDP Count", - [DCCPF_MIN_CSUM_COVER] = "Min. Csum Coverage", - [DCCPF_DATA_CHECKSUM] = "Send Data Checksum", - }; - if (feat > DCCPF_DATA_CHECKSUM && feat < DCCPF_MIN_CCID_SPECIFIC) - return feature_names[DCCPF_RESERVED]; + /* Clean up Change options which have been confirmed already */ + list_for_each_entry_safe(cur, next, fn_list, node) + if (!cur->needs_confirm) + dccp_feat_list_pop(cur); - if (feat >= DCCPF_MIN_CCID_SPECIFIC) - return "CCID-specific"; + dccp_pr_debug("Activation OK\n"); + return 0; - return feature_names[feat]; +activation_failed: + /* + * We clean up everything that may have been allocated, since + * it is difficult to track at which stage negotiation failed. + * This is ok, since all allocation functions below are robust + * against NULL arguments. + */ + ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk); + ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk); + dp->dccps_hc_rx_ccid = dp->dccps_hc_tx_ccid = NULL; + dccp_ackvec_free(dp->dccps_hc_rx_ackvec); + dp->dccps_hc_rx_ackvec = NULL; + return -1; } - -EXPORT_SYMBOL_GPL(dccp_feat_name); -#endif /* CONFIG_IP_DCCP_DEBUG */ diff --git a/net/dccp/feat.h b/net/dccp/feat.h index e272222c7ac..0e75cebb218 100644 --- a/net/dccp/feat.h +++ b/net/dccp/feat.h @@ -3,38 +3,135 @@ /* * net/dccp/feat.h * - * An implementation of the DCCP protocol + * Feature negotiation for the DCCP protocol (RFC 4340, section 6) + * Copyright (c) 2008 Gerrit Renker <gerrit@erg.abdn.ac.uk> * Copyright (c) 2005 Andrea Bittau <a.bittau@cs.ucl.ac.uk> * - * 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. + * 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. */ - #include <linux/types.h> #include "dccp.h" -#ifdef CONFIG_IP_DCCP_DEBUG -extern const char *dccp_feat_typename(const u8 type); -extern const char *dccp_feat_name(const u8 feat); +/* + * Known limit values + */ +/* Ack Ratio takes 2-byte integer values (11.3) */ +#define DCCPF_ACK_RATIO_MAX 0xFFFF +/* Wmin=32 and Wmax=2^46-1 from 7.5.2 */ +#define DCCPF_SEQ_WMIN 32 +#define DCCPF_SEQ_WMAX 0x3FFFFFFFFFFFull +/* Maximum number of SP values that fit in a single (Confirm) option */ +#define DCCP_FEAT_MAX_SP_VALS (DCCP_SINGLE_OPT_MAXLEN - 2) + +enum dccp_feat_type { + FEAT_AT_RX = 1, /* located at RX side of half-connection */ + FEAT_AT_TX = 2, /* located at TX side of half-connection */ + FEAT_SP = 4, /* server-priority reconciliation (6.3.1) */ + FEAT_NN = 8, /* non-negotiable reconciliation (6.3.2) */ + FEAT_UNKNOWN = 0xFF /* not understood or invalid feature */ +}; + +enum dccp_feat_state { + FEAT_DEFAULT = 0, /* using default values from 6.4 */ + FEAT_INITIALISING, /* feature is being initialised */ + FEAT_CHANGING, /* Change sent but not confirmed yet */ + FEAT_UNSTABLE, /* local modification in state CHANGING */ + FEAT_STABLE /* both ends (think they) agree */ +}; + +/** + * dccp_feat_val - Container for SP or NN feature values + * @nn: single NN value + * @sp.vec: single SP value plus optional preference list + * @sp.len: length of @sp.vec in bytes + */ +typedef union { + u64 nn; + struct { + u8 *vec; + u8 len; + } sp; +} dccp_feat_val; + +/** + * struct feat_entry - Data structure to perform feature negotiation + * @val: feature's current value (SP features may have preference list) + * @state: feature's current state + * @feat_num: one of %dccp_feature_numbers + * @needs_mandatory: whether Mandatory options should be sent + * @needs_confirm: whether to send a Confirm instead of a Change + * @empty_confirm: whether to send an empty Confirm (depends on @needs_confirm) + * @is_local: feature location (1) or feature-remote (0) + * @node: list pointers, entries arranged in FIFO order + */ +struct dccp_feat_entry { + dccp_feat_val val; + enum dccp_feat_state state:8; + u8 feat_num; + + bool needs_mandatory, + needs_confirm, + empty_confirm, + is_local; + + struct list_head node; +}; -static inline void dccp_feat_debug(const u8 type, const u8 feat, const u8 val) +static inline u8 dccp_feat_genopt(struct dccp_feat_entry *entry) { - dccp_pr_debug("%s(%s (%d), %d)\n", dccp_feat_typename(type), - dccp_feat_name(feat), feat, val); + if (entry->needs_confirm) + return entry->is_local ? DCCPO_CONFIRM_L : DCCPO_CONFIRM_R; + return entry->is_local ? DCCPO_CHANGE_L : DCCPO_CHANGE_R; } -#else -#define dccp_feat_debug(type, feat, val) -#endif /* CONFIG_IP_DCCP_DEBUG */ - -extern int dccp_feat_change(struct dccp_minisock *dmsk, u8 type, u8 feature, - u8 *val, u8 len, gfp_t gfp); -extern int dccp_feat_change_recv(struct sock *sk, u8 type, u8 feature, - u8 *val, u8 len); -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_init(struct dccp_minisock *dmsk); +/** + * struct ccid_dependency - Track changes resulting from choosing a CCID + * @dependent_feat: one of %dccp_feature_numbers + * @is_local: local (1) or remote (0) @dependent_feat + * @is_mandatory: whether presence of @dependent_feat is mission-critical or not + * @val: corresponding default value for @dependent_feat (u8 is sufficient here) + */ +struct ccid_dependency { + u8 dependent_feat; + bool is_local:1, + is_mandatory:1; + u8 val; +}; + +/* + * Sysctls to seed defaults for feature negotiation + */ +extern unsigned long sysctl_dccp_sequence_window; +extern int sysctl_dccp_rx_ccid; +extern int sysctl_dccp_tx_ccid; + +int dccp_feat_init(struct sock *sk); +void dccp_feat_initialise_sysctls(void); +int dccp_feat_register_sp(struct sock *sk, u8 feat, u8 is_local, + u8 const *list, u8 len); +int dccp_feat_parse_options(struct sock *, struct dccp_request_sock *, + u8 mand, u8 opt, u8 feat, u8 *val, u8 len); +int dccp_feat_clone_list(struct list_head const *, struct list_head *); + +/* + * Encoding variable-length options and their maximum length. + * + * This affects NN options (SP options are all u8) and other variable-length + * options (see table 3 in RFC 4340). The limit is currently given the Sequence + * Window NN value (sec. 7.5.2) and the NDP count (sec. 7.7) option, all other + * options consume less than 6 bytes (timestamps are 4 bytes). + * When updating this constant (e.g. due to new internet drafts / RFCs), make + * sure that you also update all code which refers to it. + */ +#define DCCP_OPTVAL_MAXLEN 6 + +void dccp_encode_value_var(const u64 value, u8 *to, const u8 len); +u64 dccp_decode_value_var(const u8 *bf, const u8 len); +u64 dccp_feat_nn_get(struct sock *sk, u8 feat); + +int dccp_insert_option_mandatory(struct sk_buff *skb); +int dccp_insert_fn_opt(struct sk_buff *skb, u8 type, u8 feat, u8 *val, u8 len, + bool repeat_first); #endif /* _DCCP_FEAT_H */ diff --git a/net/dccp/input.c b/net/dccp/input.c index 08392ed86c2..3c8ec7d4a34 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -12,6 +12,7 @@ #include <linux/dccp.h> #include <linux/skbuff.h> +#include <linux/slab.h> #include <net/sock.h> @@ -27,7 +28,7 @@ static void dccp_enqueue_skb(struct sock *sk, struct sk_buff *skb) __skb_pull(skb, dccp_hdr(skb)->dccph_doff * 4); __skb_queue_tail(&sk->sk_receive_queue, skb); skb_set_owner_r(skb, sk); - sk->sk_data_ready(sk, 0); + sk->sk_data_ready(sk); } static void dccp_fin(struct sock *sk, struct sk_buff *skb) @@ -123,9 +124,9 @@ static int dccp_rcv_closereq(struct sock *sk, struct sk_buff *skb) return queued; } -static u8 dccp_reset_code_convert(const u8 code) +static u16 dccp_reset_code_convert(const u8 code) { - const u8 error_code[] = { + const u16 error_code[] = { [DCCP_RESET_CODE_CLOSED] = 0, /* normal termination */ [DCCP_RESET_CODE_UNSPECIFIED] = 0, /* nothing known */ [DCCP_RESET_CODE_ABORTED] = ECONNRESET, @@ -147,7 +148,7 @@ static u8 dccp_reset_code_convert(const u8 code) static void dccp_rcv_reset(struct sock *sk, struct sk_buff *skb) { - u8 err = dccp_reset_code_convert(dccp_hdr_reset(skb)->dccph_reset_code); + u16 err = dccp_reset_code_convert(dccp_hdr_reset(skb)->dccph_reset_code); sk->sk_err = err; @@ -159,13 +160,15 @@ 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 (dccp_msk(sk)->dccpms_send_ack_vector) - dccp_ackvec_check_rcv_ackno(dp->dccps_hc_rx_ackvec, sk, - 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) @@ -238,7 +241,8 @@ static int dccp_check_seqno(struct sock *sk, struct sk_buff *skb) dccp_update_gsr(sk, seqno); if (dh->dccph_type != DCCP_PKT_SYNC && - (ackno != DCCP_PKT_WITHOUT_ACK_SEQ)) + ackno != DCCP_PKT_WITHOUT_ACK_SEQ && + after48(ackno, dp->dccps_gar)) dp->dccps_gar = ackno; } else { unsigned long now = jiffies; @@ -256,9 +260,9 @@ static int dccp_check_seqno(struct sock *sk, struct sk_buff *skb) */ if (time_before(now, (dp->dccps_rate_last + sysctl_dccp_sync_ratelimit))) - return 0; + return -1; - DCCP_WARN("DCCP: Step 6 failed for %s packet, " + DCCP_WARN("Step 6 failed for %s packet, " "(LSWL(%llu) <= P.seqno(%llu) <= S.SWH(%llu)) and " "(P.ackno %s or LAWL(%llu) <= P.ackno(%llu) <= S.AWH(%llu), " "sending SYNC...\n", dccp_packet_name(dh->dccph_type), @@ -281,7 +285,7 @@ static int dccp_check_seqno(struct sock *sk, struct sk_buff *skb) } static int __dccp_rcv_established(struct sock *sk, struct sk_buff *skb, - const struct dccp_hdr *dh, const unsigned len) + const struct dccp_hdr *dh, const unsigned int len) { struct dccp_sock *dp = dccp_sk(sk); @@ -362,24 +366,15 @@ discard: } int dccp_rcv_established(struct sock *sk, struct sk_buff *skb, - const struct dccp_hdr *dh, const unsigned len) + const struct dccp_hdr *dh, const unsigned int len) { - struct dccp_sock *dp = dccp_sk(sk); - if (dccp_check_seqno(sk, skb)) goto discard; if (dccp_parse_options(sk, NULL, skb)) - goto discard; - - if (DCCP_SKB_CB(skb)->dccpd_ack_seq != DCCP_PKT_WITHOUT_ACK_SEQ) - dccp_event_ack_recv(sk, skb); + return 1; - 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 discard; + dccp_handle_ackvec_processing(sk, skb); dccp_deliver_input_to_ccids(sk, skb); return __dccp_rcv_established(sk, skb, dh, len); @@ -393,7 +388,7 @@ EXPORT_SYMBOL_GPL(dccp_rcv_established); static int dccp_rcv_request_sent_state_process(struct sock *sk, struct sk_buff *skb, const struct dccp_hdr *dh, - const unsigned len) + const unsigned int len) { /* * Step 4: Prepare sequence numbers in REQUEST @@ -411,50 +406,43 @@ static int dccp_rcv_request_sent_state_process(struct sock *sk, struct dccp_sock *dp = dccp_sk(sk); long tstamp = dccp_timestamp(); - /* Stop the REQUEST timer */ - inet_csk_clear_xmit_timer(sk, ICSK_TIME_RETRANS); - BUG_TRAP(sk->sk_send_head != NULL); - __kfree_skb(sk->sk_send_head); - sk->sk_send_head = NULL; - if (!between48(DCCP_SKB_CB(skb)->dccpd_ack_seq, dp->dccps_awl, dp->dccps_awh)) { dccp_pr_debug("invalid ackno: S.AWL=%llu, " - "P.ackno=%llu, S.AWH=%llu \n", + "P.ackno=%llu, S.AWH=%llu\n", (unsigned long long)dp->dccps_awl, (unsigned long long)DCCP_SKB_CB(skb)->dccpd_ack_seq, (unsigned long long)dp->dccps_awh); 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) */ + /* Obtain usec RTT sample from SYN exchange (used by TFRC). */ if (likely(dp->dccps_options_received.dccpor_timestamp_echo)) 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); + 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); @@ -475,6 +463,15 @@ 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); @@ -509,13 +506,25 @@ 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, struct sk_buff *skb, const struct dccp_hdr *dh, - const unsigned len) + const unsigned int len) { + struct dccp_sock *dp = dccp_sk(sk); + u32 sample = dp->dccps_options_received.dccpor_timestamp_echo; int queued = 0; switch (dh->dccph_type) { @@ -540,7 +549,14 @@ static int dccp_rcv_respond_partopen_state_process(struct sock *sk, if (sk->sk_state == DCCP_PARTOPEN) inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK); - dccp_sk(sk)->dccps_osr = DCCP_SKB_CB(skb)->dccpd_seq; + /* Obtain usec RTT sample from SYN exchange (used by TFRC). */ + if (likely(sample)) { + long delta = dccp_timestamp() - sample; + + dp->dccps_syn_rtt = dccp_sample_rtt(sk, 10 * delta); + } + + dp->dccps_osr = DCCP_SKB_CB(skb)->dccpd_seq; dccp_set_state(sk, DCCP_OPEN); if (dh->dccph_type == DCCP_PKT_DATAACK || @@ -556,7 +572,7 @@ static int dccp_rcv_respond_partopen_state_process(struct sock *sk, } int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, - struct dccp_hdr *dh, unsigned len) + struct dccp_hdr *dh, unsigned int len) { struct dccp_sock *dp = dccp_sk(sk); struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb); @@ -590,8 +606,6 @@ 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) @@ -600,30 +614,36 @@ 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) { - if (dccp_check_seqno(sk, skb)) - goto discard; - - /* - * Step 8: Process options and mark acknowledgeable - */ - if (dccp_parse_options(sk, NULL, skb)) - goto discard; - - if (dcb->dccpd_ack_seq != DCCP_PKT_WITHOUT_ACK_SEQ) - dccp_event_ack_recv(sk, skb); - - 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 discard; + /* Step 6: Check sequence numbers (omitted in LISTEN/REQUEST state) */ + if (sk->sk_state != DCCP_REQUESTING && dccp_check_seqno(sk, skb)) + goto discard; - 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, @@ -631,44 +651,22 @@ 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: - /* FIXME: do congestion control initialization */ - queued = dccp_rcv_request_sent_state_process(sk, skb, dh, len); if (queued >= 0) return queued; @@ -676,8 +674,12 @@ 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; @@ -708,6 +710,7 @@ EXPORT_SYMBOL_GPL(dccp_rcv_state_process); /** * dccp_sample_rtt - Validate and finalise computation of RTT sample * @delta: number of microseconds between packet and acknowledgment + * * The routine is kept generic to work in different contexts. It should be * called immediately when the ACK used for the RTT sample arrives. */ @@ -727,5 +730,3 @@ u32 dccp_sample_rtt(struct sock *sk, long delta) return delta; } - -EXPORT_SYMBOL_GPL(dccp_sample_rtt); diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 474075adbde..6ca645c4b48 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -12,6 +12,7 @@ #include <linux/dccp.h> #include <linux/icmp.h> +#include <linux/slab.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/random.h> @@ -25,6 +26,7 @@ #include <net/timewait_sock.h> #include <net/tcp_states.h> #include <net/xfrm.h> +#include <net/secure_seq.h> #include "ackvec.h" #include "ccid.h" @@ -32,21 +34,22 @@ #include "feat.h" /* - * This is the global socket data structure used for responding to + * The per-net dccp.v4_ctl_sk socket is used for responding to * the Out-of-the-blue (OOTB) packets. A control sock will be created * for this socket at the initialization time. */ -static struct socket *dccp_v4_ctl_socket; int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { + const struct sockaddr_in *usin = (struct sockaddr_in *)uaddr; struct inet_sock *inet = inet_sk(sk); struct dccp_sock *dp = dccp_sk(sk); - const struct sockaddr_in *usin = (struct sockaddr_in *)uaddr; - struct rtable *rt; + __be16 orig_sport, orig_dport; __be32 daddr, nexthop; - int tmp; + struct flowi4 *fl4; + struct rtable *rt; int err; + struct ip_options_rcu *inet_opt; dp->dccps_role = DCCP_ROLE_CLIENT; @@ -57,37 +60,43 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) return -EAFNOSUPPORT; nexthop = daddr = usin->sin_addr.s_addr; - if (inet->opt != NULL && inet->opt->srr) { + + inet_opt = rcu_dereference_protected(inet->inet_opt, + sock_owned_by_user(sk)); + if (inet_opt != NULL && inet_opt->opt.srr) { if (daddr == 0) return -EINVAL; - nexthop = inet->opt->faddr; + nexthop = inet_opt->opt.faddr; } - tmp = ip_route_connect(&rt, nexthop, inet->saddr, - RT_CONN_FLAGS(sk), sk->sk_bound_dev_if, - IPPROTO_DCCP, - inet->sport, usin->sin_port, sk, 1); - if (tmp < 0) - return tmp; + orig_sport = inet->inet_sport; + orig_dport = usin->sin_port; + fl4 = &inet->cork.fl.u.ip4; + rt = ip_route_connect(fl4, nexthop, inet->inet_saddr, + RT_CONN_FLAGS(sk), sk->sk_bound_dev_if, + IPPROTO_DCCP, + orig_sport, orig_dport, sk); + if (IS_ERR(rt)) + return PTR_ERR(rt); if (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST)) { ip_rt_put(rt); return -ENETUNREACH; } - if (inet->opt == NULL || !inet->opt->srr) - daddr = rt->rt_dst; + if (inet_opt == NULL || !inet_opt->opt.srr) + daddr = fl4->daddr; - if (inet->saddr == 0) - inet->saddr = rt->rt_src; - inet->rcv_saddr = inet->saddr; + if (inet->inet_saddr == 0) + inet->inet_saddr = fl4->saddr; + inet->inet_rcv_saddr = inet->inet_saddr; - inet->dport = usin->sin_port; - inet->daddr = daddr; + inet->inet_dport = usin->sin_port; + inet->inet_daddr = daddr; inet_csk(sk)->icsk_ext_hdr_len = 0; - if (inet->opt != NULL) - inet_csk(sk)->icsk_ext_hdr_len = inet->opt->optlen; + if (inet_opt) + inet_csk(sk)->icsk_ext_hdr_len = inet_opt->opt.optlen; /* * Socket identity is still unknown (sport may be zero). * However we set state to DCCP_REQUESTING and not releasing socket @@ -99,17 +108,21 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (err != 0) goto failure; - err = ip_route_newports(&rt, IPPROTO_DCCP, inet->sport, inet->dport, - sk); - if (err != 0) + rt = ip_route_newports(fl4, rt, orig_sport, orig_dport, + inet->inet_sport, inet->inet_dport, sk); + if (IS_ERR(rt)) { + err = PTR_ERR(rt); + rt = NULL; goto failure; - + } /* OK, now commit destination to socket. */ - sk_setup_caps(sk, &rt->u.dst); + sk_setup_caps(sk, &rt->dst); - dp->dccps_iss = secure_dccp_sequence_number(inet->saddr, inet->daddr, - inet->sport, inet->dport); - inet->id = dp->dccps_iss ^ jiffies; + dp->dccps_iss = secure_dccp_sequence_number(inet->inet_saddr, + inet->inet_daddr, + inet->inet_sport, + inet->inet_dport); + inet->inet_id = dp->dccps_iss ^ jiffies; err = dccp_connect(sk); rt = NULL; @@ -124,7 +137,7 @@ failure: dccp_set_state(sk, DCCP_CLOSED); ip_rt_put(rt); sk->sk_route_caps = 0; - inet->dport = 0; + inet->inet_dport = 0; goto out; } @@ -148,17 +161,10 @@ static inline void dccp_do_pmtu_discovery(struct sock *sk, if (sk->sk_state == DCCP_LISTEN) return; - /* We don't check in the destentry if pmtu discovery is forbidden - * on this route. We just assume that no packet_to_big packets - * are send back when pmtu discovery is not active. - * There is a small race when the user changes this flag in the - * route, but I think that's acceptable. - */ - if ((dst = __sk_dst_check(sk, 0)) == NULL) + dst = inet_csk_update_pmtu(sk, mtu); + if (!dst) return; - dst->ops->update_pmtu(dst, mtu); - /* Something is about to be wrong... Remember soft error * for the case, if this connection will not able to recover. */ @@ -168,6 +174,7 @@ static inline void dccp_do_pmtu_discovery(struct sock *sk, mtu = dst_mtu(dst); if (inet->pmtudisc != IP_PMTUDISC_DONT && + ip_sk_accept_pmtu(sk) && inet_csk(sk)->icsk_pmtu_cookie > mtu) { dccp_sync_mss(sk, mtu); @@ -182,6 +189,14 @@ static inline void dccp_do_pmtu_discovery(struct sock *sk, } /* else let the usual retransmit timer handle it */ } +static void dccp_do_redirect(struct sk_buff *skb, struct sock *sk) +{ + struct dst_entry *dst = __sk_dst_check(sk, 0); + + if (dst) + dst->ops->redirect(dst, sk, skb); +} + /* * This routine is called by the ICMP module when it gets some sort of error * condition. If err < 0 then the socket should be closed and the error @@ -197,8 +212,8 @@ static inline void dccp_do_pmtu_discovery(struct sock *sk, static void dccp_v4_err(struct sk_buff *skb, u32 info) { const struct iphdr *iph = (struct iphdr *)skb->data; - const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + - (iph->ihl << 2)); + const u8 offset = iph->ihl << 2; + const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset); struct dccp_sock *dp; struct inet_sock *inet; const int type = icmp_hdr(skb)->type; @@ -206,16 +221,19 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info) struct sock *sk; __u64 seq; int err; + struct net *net = dev_net(skb->dev); - if (skb->len < (iph->ihl << 2) + 8) { - ICMP_INC_STATS_BH(ICMP_MIB_INERRORS); + if (skb->len < offset + sizeof(*dh) || + skb->len < offset + __dccp_basic_hdr_len(dh)) { + ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS); return; } - sk = inet_lookup(&init_net, &dccp_hashinfo, iph->daddr, dh->dccph_dport, - iph->saddr, dh->dccph_sport, inet_iif(skb)); + sk = inet_lookup(net, &dccp_hashinfo, + iph->daddr, dh->dccph_dport, + iph->saddr, dh->dccph_sport, inet_iif(skb)); if (sk == NULL) { - ICMP_INC_STATS_BH(ICMP_MIB_INERRORS); + ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS); return; } @@ -229,7 +247,7 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info) * servers this needs to be solved differently. */ if (sock_owned_by_user(sk)) - NET_INC_STATS_BH(LINUX_MIB_LOCKDROPPEDICMPS); + NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS); if (sk->sk_state == DCCP_CLOSED) goto out; @@ -237,12 +255,15 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info) dp = dccp_sk(sk); seq = dccp_hdr_seq(dh); if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_LISTEN) && - !between48(seq, dp->dccps_swl, dp->dccps_swh)) { - NET_INC_STATS_BH(LINUX_MIB_OUTOFWINDOWICMPS); + !between48(seq, dp->dccps_awl, dp->dccps_awh)) { + NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } switch (type) { + case ICMP_REDIRECT: + dccp_do_redirect(skb, sk); + goto out; case ICMP_SOURCE_QUENCH: /* Just silently ignore these. */ goto out; @@ -282,10 +303,11 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info) * ICMPs are not backlogged, hence we cannot get an established * socket here. */ - BUG_TRAP(!req->sk); + WARN_ON(req->sk); - if (seq != dccp_rsk(req)->dreq_iss) { - NET_INC_STATS_BH(LINUX_MIB_OUTOFWINDOWICMPS); + if (!between48(seq, dccp_rsk(req)->dreq_iss, + dccp_rsk(req)->dreq_gss)) { + NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } /* @@ -344,13 +366,15 @@ static inline __sum16 dccp_v4_csum_finish(struct sk_buff *skb, return csum_tcpudp_magic(src, dst, skb->len, IPPROTO_DCCP, skb->csum); } -void dccp_v4_send_check(struct sock *sk, int unused, struct sk_buff *skb) +void dccp_v4_send_check(struct sock *sk, struct sk_buff *skb) { const struct inet_sock *inet = inet_sk(sk); struct dccp_hdr *dh = dccp_hdr(skb); dccp_csum_outgoing(skb); - dh->dccph_checksum = dccp_v4_csum_finish(skb, inet->saddr, inet->daddr); + dh->dccph_checksum = dccp_v4_csum_finish(skb, + inet->inet_saddr, + inet->inet_daddr); } EXPORT_SYMBOL_GPL(dccp_v4_send_check); @@ -380,39 +404,45 @@ struct sock *dccp_v4_request_recv_sock(struct sock *sk, struct sk_buff *skb, if (sk_acceptq_is_full(sk)) goto exit_overflow; - if (dst == NULL && (dst = inet_csk_route_req(sk, req)) == NULL) - goto exit; - newsk = dccp_create_openreq_child(sk, req, skb); if (newsk == NULL) - goto exit; - - sk_setup_caps(newsk, dst); + goto exit_nonewsk; newinet = inet_sk(newsk); ireq = inet_rsk(req); - newinet->daddr = ireq->rmt_addr; - newinet->rcv_saddr = ireq->loc_addr; - newinet->saddr = ireq->loc_addr; - newinet->opt = ireq->opt; + newinet->inet_daddr = ireq->ir_rmt_addr; + newinet->inet_rcv_saddr = ireq->ir_loc_addr; + newinet->inet_saddr = ireq->ir_loc_addr; + newinet->inet_opt = ireq->opt; ireq->opt = NULL; newinet->mc_index = inet_iif(skb); newinet->mc_ttl = ip_hdr(skb)->ttl; - newinet->id = jiffies; + newinet->inet_id = jiffies; + + if (dst == NULL && (dst = inet_csk_route_child_sock(sk, newsk, req)) == NULL) + goto put_and_exit; + + sk_setup_caps(newsk, dst); dccp_sync_mss(newsk, dst_mtu(dst)); - __inet_hash_nolisten(newsk); - __inet_inherit_port(sk, newsk); + if (__inet_inherit_port(sk, newsk) < 0) + goto put_and_exit; + __inet_hash_nolisten(newsk, NULL); return newsk; exit_overflow: - NET_INC_STATS_BH(LINUX_MIB_LISTENOVERFLOWS); -exit: - NET_INC_STATS_BH(LINUX_MIB_LISTENDROPS); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); +exit_nonewsk: dst_release(dst); +exit: + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); return NULL; +put_and_exit: + inet_csk_prepare_forced_close(newsk); + dccp_done(newsk); + goto exit; } EXPORT_SYMBOL_GPL(dccp_v4_request_recv_sock); @@ -430,7 +460,7 @@ static struct sock *dccp_v4_hnd_req(struct sock *sk, struct sk_buff *skb) if (req != NULL) return dccp_check_req(sk, skb, req, prev); - nsk = inet_lookup_established(&init_net, &dccp_hashinfo, + nsk = inet_lookup_established(sock_net(sk), &dccp_hashinfo, iph->saddr, dh->dccph_sport, iph->daddr, dh->dccph_dport, inet_iif(skb)); @@ -446,40 +476,40 @@ static struct sock *dccp_v4_hnd_req(struct sock *sk, struct sk_buff *skb) return sk; } -static struct dst_entry* dccp_v4_route_skb(struct sock *sk, +static struct dst_entry* dccp_v4_route_skb(struct net *net, struct sock *sk, struct sk_buff *skb) { struct rtable *rt; - struct flowi fl = { .oif = ((struct rtable *)skb->dst)->rt_iif, - .nl_u = { .ip4_u = - { .daddr = ip_hdr(skb)->saddr, - .saddr = ip_hdr(skb)->daddr, - .tos = RT_CONN_FLAGS(sk) } }, - .proto = sk->sk_protocol, - .uli_u = { .ports = - { .sport = dccp_hdr(skb)->dccph_dport, - .dport = dccp_hdr(skb)->dccph_sport } - } - }; - - security_skb_classify_flow(skb, &fl); - if (ip_route_output_flow(&init_net, &rt, &fl, sk, 0)) { - IP_INC_STATS_BH(IPSTATS_MIB_OUTNOROUTES); + const struct iphdr *iph = ip_hdr(skb); + struct flowi4 fl4 = { + .flowi4_oif = inet_iif(skb), + .daddr = iph->saddr, + .saddr = iph->daddr, + .flowi4_tos = RT_CONN_FLAGS(sk), + .flowi4_proto = sk->sk_protocol, + .fl4_sport = dccp_hdr(skb)->dccph_dport, + .fl4_dport = dccp_hdr(skb)->dccph_sport, + }; + + security_skb_classify_flow(skb, flowi4_to_flowi(&fl4)); + rt = ip_route_output_flow(net, &fl4, sk); + if (IS_ERR(rt)) { + IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES); return NULL; } - return &rt->u.dst; + return &rt->dst; } -static int dccp_v4_send_response(struct sock *sk, struct request_sock *req, - struct dst_entry *dst) +static int dccp_v4_send_response(struct sock *sk, struct request_sock *req) { int err = -1; struct sk_buff *skb; + struct dst_entry *dst; + struct flowi4 fl4; - /* First, grab a route. */ - - if (dst == NULL && (dst = inet_csk_route_req(sk, req)) == NULL) + dst = inet_csk_route_req(sk, &fl4, req); + if (dst == NULL) goto out; skb = dccp_make_response(sk, dst, req); @@ -487,11 +517,10 @@ static int dccp_v4_send_response(struct sock *sk, struct request_sock *req, const struct inet_request_sock *ireq = inet_rsk(req); struct dccp_hdr *dh = dccp_hdr(skb); - dh->dccph_checksum = dccp_v4_csum_finish(skb, ireq->loc_addr, - ireq->rmt_addr); - memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); - err = ip_build_and_send_pkt(skb, sk, ireq->loc_addr, - ireq->rmt_addr, + dh->dccph_checksum = dccp_v4_csum_finish(skb, ireq->ir_loc_addr, + ireq->ir_rmt_addr); + err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr, + ireq->ir_rmt_addr, ireq->opt); err = net_xmit_eval(err); } @@ -507,31 +536,33 @@ static void dccp_v4_ctl_send_reset(struct sock *sk, struct sk_buff *rxskb) const struct iphdr *rxiph; struct sk_buff *skb; struct dst_entry *dst; + struct net *net = dev_net(skb_dst(rxskb)->dev); + struct sock *ctl_sk = net->dccp.v4_ctl_sk; /* Never send a reset in response to a reset. */ if (dccp_hdr(rxskb)->dccph_type == DCCP_PKT_RESET) return; - if (((struct rtable *)rxskb->dst)->rt_type != RTN_LOCAL) + if (skb_rtable(rxskb)->rt_type != RTN_LOCAL) return; - dst = dccp_v4_route_skb(dccp_v4_ctl_socket->sk, rxskb); + dst = dccp_v4_route_skb(net, ctl_sk, rxskb); if (dst == NULL) return; - skb = dccp_ctl_make_reset(dccp_v4_ctl_socket, rxskb); + skb = dccp_ctl_make_reset(ctl_sk, rxskb); if (skb == NULL) goto out; rxiph = ip_hdr(rxskb); dccp_hdr(skb)->dccph_checksum = dccp_v4_csum_finish(skb, rxiph->saddr, rxiph->daddr); - skb->dst = dst_clone(dst); + skb_dst_set(skb, dst_clone(dst)); - bh_lock_sock(dccp_v4_ctl_socket->sk); - err = ip_build_and_send_pkt(skb, dccp_v4_ctl_socket->sk, + bh_lock_sock(ctl_sk); + err = ip_build_and_send_pkt(skb, ctl_sk, rxiph->daddr, rxiph->saddr, NULL); - bh_unlock_sock(dccp_v4_ctl_socket->sk); + bh_unlock_sock(ctl_sk); if (net_xmit_eval(err) == 0) { DCCP_INC_STATS_BH(DCCP_MIB_OUTSEGS); @@ -543,9 +574,15 @@ out: static void dccp_v4_reqsk_destructor(struct request_sock *req) { + dccp_feat_list_purge(&dccp_rsk(req)->dreq_featneg); kfree(inet_rsk(req)->opt); } +void dccp_syn_ack_timeout(struct sock *sk, struct request_sock *req) +{ +} +EXPORT_SYMBOL(dccp_syn_ack_timeout); + static struct request_sock_ops dccp_request_sock_ops __read_mostly = { .family = PF_INET, .obj_size = sizeof(struct dccp_request_sock), @@ -553,6 +590,7 @@ static struct request_sock_ops dccp_request_sock_ops __read_mostly = { .send_ack = dccp_reqsk_send_ack, .destructor = dccp_v4_reqsk_destructor, .send_reset = dccp_v4_ctl_send_reset, + .syn_ack_timeout = dccp_syn_ack_timeout, }; int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) @@ -564,8 +602,7 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb); /* Never answer to DCCP_PKT_REQUESTs send to broadcast or multicast */ - if (((struct rtable *)skb->dst)->rt_flags & - (RTCF_BROADCAST | RTCF_MULTICAST)) + if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) return 0; /* discard, don't send a reset here */ if (dccp_bad_service_code(sk, service)) { @@ -590,11 +627,12 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) goto drop; - req = reqsk_alloc(&dccp_request_sock_ops); + req = inet_reqsk_alloc(&dccp_request_sock_ops); 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)) @@ -604,23 +642,23 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) goto drop_and_free; ireq = inet_rsk(req); - ireq->loc_addr = ip_hdr(skb)->daddr; - ireq->rmt_addr = ip_hdr(skb)->saddr; - ireq->opt = NULL; + ireq->ir_loc_addr = ip_hdr(skb)->daddr; + ireq->ir_rmt_addr = ip_hdr(skb)->saddr; /* * Step 3: Process LISTEN state * * Set S.ISR, S.GSR, S.SWL, S.SWH from packet or Init Cookie * - * In fact we defer setting S.GSR, S.SWL, S.SWH to - * dccp_create_openreq_child. + * Setting S.SWL/S.SWH to is deferred to dccp_create_openreq_child(). */ dreq->dreq_isr = dcb->dccpd_seq; + dreq->dreq_gsr = dreq->dreq_isr; dreq->dreq_iss = dccp_v4_init_sequence(skb); + dreq->dreq_gss = dreq->dreq_iss; dreq->dreq_service = service; - if (dccp_v4_send_response(sk, req, NULL)) + if (dccp_v4_send_response(sk, req)) goto drop_and_free; inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT); @@ -740,8 +778,8 @@ int dccp_invalid_packet(struct sk_buff *skb) * If P.type is not Data, Ack, or DataAck and P.X == 0 (the packet * has short sequence numbers), drop packet and return */ - if (dh->dccph_type >= DCCP_PKT_DATA && - dh->dccph_type <= DCCP_PKT_DATAACK && dh->dccph_x == 0) { + if ((dh->dccph_type < DCCP_PKT_DATA || + dh->dccph_type > DCCP_PKT_DATAACK) && dh->dccph_x == 0) { DCCP_WARN("P.type (%s) not Data || [Data]Ack, while P.X == 0\n", dccp_packet_name(dh->dccph_type)); return 1; @@ -792,12 +830,10 @@ static int dccp_v4_rcv(struct sk_buff *skb) DCCP_SKB_CB(skb)->dccpd_seq = dccp_hdr_seq(dh); DCCP_SKB_CB(skb)->dccpd_type = dh->dccph_type; - dccp_pr_debug("%8.8s " - "src=%u.%u.%u.%u@%-5d " - "dst=%u.%u.%u.%u@%-5d seq=%llu", + dccp_pr_debug("%8.8s src=%pI4@%-5d dst=%pI4@%-5d seq=%llu", dccp_packet_name(dh->dccph_type), - NIPQUAD(iph->saddr), ntohs(dh->dccph_sport), - NIPQUAD(iph->daddr), ntohs(dh->dccph_dport), + &iph->saddr, ntohs(dh->dccph_sport), + &iph->daddr, ntohs(dh->dccph_dport), (unsigned long long) DCCP_SKB_CB(skb)->dccpd_seq); if (dccp_packet_without_ack(skb)) { @@ -811,9 +847,8 @@ static int dccp_v4_rcv(struct sk_buff *skb) /* Step 2: * Look up flow ID in table and get corresponding socket */ - sk = __inet_lookup(&init_net, &dccp_hashinfo, - iph->saddr, dh->dccph_sport, - iph->daddr, dh->dccph_dport, inet_iif(skb)); + sk = __inet_lookup_skb(&dccp_hashinfo, skb, + dh->dccph_sport, dh->dccph_dport); /* * Step 2: * If no socket ... @@ -881,7 +916,7 @@ discard_and_relse: goto discard_it; } -static struct inet_connection_sock_af_ops dccp_ipv4_af_ops = { +static const struct inet_connection_sock_af_ops dccp_ipv4_af_ops = { .queue_xmit = ip_queue_xmit, .send_check = dccp_v4_send_check, .rebuild_header = inet_sk_rebuild_header, @@ -917,8 +952,6 @@ static struct timewait_sock_ops dccp_timewait_sock_ops = { .twsk_obj_size = sizeof(struct inet_timewait_sock), }; -DEFINE_PROTO_INUSE(dccp_v4) - static struct proto dccp_v4_prot = { .name = "DCCP", .owner = THIS_MODULE, @@ -941,20 +974,22 @@ static struct proto dccp_v4_prot = { .orphan_count = &dccp_orphan_count, .max_header = MAX_DCCP_HEADER, .obj_size = sizeof(struct dccp_sock), + .slab_flags = SLAB_DESTROY_BY_RCU, .rsk_prot = &dccp_request_sock_ops, .twsk_prot = &dccp_timewait_sock_ops, - .hashinfo = &dccp_hashinfo, + .h.hashinfo = &dccp_hashinfo, #ifdef CONFIG_COMPAT .compat_setsockopt = compat_dccp_setsockopt, .compat_getsockopt = compat_dccp_getsockopt, #endif - REF_PROTO_INUSE(dccp_v4) }; -static struct net_protocol dccp_v4_protocol = { +static const struct net_protocol dccp_v4_protocol = { .handler = dccp_v4_rcv, .err_handler = dccp_v4_err, .no_policy = 1, + .netns_ok = 1, + .icmp_strict_tag_validation = 1, }; static const struct proto_ops inet_dccp_ops = { @@ -989,11 +1024,28 @@ static struct inet_protosw dccp_v4_protosw = { .protocol = IPPROTO_DCCP, .prot = &dccp_v4_prot, .ops = &inet_dccp_ops, - .capability = -1, - .no_check = 0, .flags = INET_PROTOSW_ICSK, }; +static int __net_init dccp_v4_init_net(struct net *net) +{ + if (dccp_hashinfo.bhash == NULL) + return -ESOCKTNOSUPPORT; + + return inet_ctl_sock_create(&net->dccp.v4_ctl_sk, PF_INET, + SOCK_DCCP, IPPROTO_DCCP, net); +} + +static void __net_exit dccp_v4_exit_net(struct net *net) +{ + inet_ctl_sock_destroy(net->dccp.v4_ctl_sk); +} + +static struct pernet_operations dccp_v4_ops = { + .init = dccp_v4_init_net, + .exit = dccp_v4_exit_net, +}; + static int __init dccp_v4_init(void) { int err = proto_register(&dccp_v4_prot, 1); @@ -1007,13 +1059,12 @@ static int __init dccp_v4_init(void) inet_register_protosw(&dccp_v4_protosw); - err = inet_csk_ctl_sock_create(&dccp_v4_ctl_socket, PF_INET, - SOCK_DCCP, IPPROTO_DCCP); + err = register_pernet_subsys(&dccp_v4_ops); if (err) - goto out_unregister_protosw; + goto out_destroy_ctl_sock; out: return err; -out_unregister_protosw: +out_destroy_ctl_sock: inet_unregister_protosw(&dccp_v4_protosw); inet_del_protocol(&dccp_v4_protocol, IPPROTO_DCCP); out_proto_unregister: @@ -1023,6 +1074,7 @@ out_proto_unregister: static void __exit dccp_v4_exit(void) { + unregister_pernet_subsys(&dccp_v4_ops); inet_unregister_protosw(&dccp_v4_protosw); inet_del_protocol(&dccp_v4_protocol, IPPROTO_DCCP); proto_unregister(&dccp_v4_prot); diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 490333d47c7..4db3c2a1679 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -14,6 +14,7 @@ #include <linux/module.h> #include <linux/random.h> +#include <linux/slab.h> #include <linux/xfrm.h> #include <net/addrconf.h> @@ -28,16 +29,16 @@ #include <net/transp_v6.h> #include <net/ip6_checksum.h> #include <net/xfrm.h> +#include <net/secure_seq.h> #include "dccp.h" #include "ipv6.h" #include "feat.h" -/* Socket used for sending RSTs and ACKs */ -static struct socket *dccp_v6_ctl_socket; +/* The per-net dccp.v6_ctl_sk is used for sending RSTs and ACKs */ -static struct inet_connection_sock_af_ops dccp_ipv6_mapped; -static struct inet_connection_sock_af_ops dccp_ipv6_af_ops; +static const struct inet_connection_sock_af_ops dccp_ipv6_mapped; +static const struct inet_connection_sock_af_ops dccp_ipv6_af_ops; static void dccp_v6_hash(struct sock *sk) { @@ -47,36 +48,29 @@ static void dccp_v6_hash(struct sock *sk) return; } local_bh_disable(); - __inet6_hash(sk); + __inet6_hash(sk, NULL); local_bh_enable(); } } /* add pseudo-header to DCCP checksum stored in skb->csum */ static inline __sum16 dccp_v6_csum_finish(struct sk_buff *skb, - struct in6_addr *saddr, - struct in6_addr *daddr) + const struct in6_addr *saddr, + const struct in6_addr *daddr) { return csum_ipv6_magic(saddr, daddr, skb->len, IPPROTO_DCCP, skb->csum); } -static inline void dccp_v6_send_check(struct sock *sk, int unused_value, - struct sk_buff *skb) +static inline void dccp_v6_send_check(struct sock *sk, struct sk_buff *skb) { struct ipv6_pinfo *np = inet6_sk(sk); struct dccp_hdr *dh = dccp_hdr(skb); dccp_csum_outgoing(skb); - dh->dccph_checksum = dccp_v6_csum_finish(skb, &np->saddr, &np->daddr); + dh->dccph_checksum = dccp_v6_csum_finish(skb, &np->saddr, &sk->sk_v6_daddr); } -static inline __u32 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr, - __be16 sport, __be16 dport ) -{ - return secure_tcpv6_sequence_number(saddr, daddr, sport, dport); -} - -static inline __u32 dccp_v6_init_sequence(struct sk_buff *skb) +static inline __u64 dccp_v6_init_sequence(struct sk_buff *skb) { return secure_dccpv6_sequence_number(ipv6_hdr(skb)->daddr.s6_addr32, ipv6_hdr(skb)->saddr.s6_addr32, @@ -86,20 +80,31 @@ static inline __u32 dccp_v6_init_sequence(struct sk_buff *skb) } static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, - int type, int code, int offset, __be32 info) + u8 type, u8 code, int offset, __be32 info) { - struct ipv6hdr *hdr = (struct ipv6hdr *)skb->data; + const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data; const struct dccp_hdr *dh = (struct dccp_hdr *)(skb->data + offset); + struct dccp_sock *dp; struct ipv6_pinfo *np; struct sock *sk; int err; __u64 seq; + struct net *net = dev_net(skb->dev); + + if (skb->len < offset + sizeof(*dh) || + skb->len < offset + __dccp_basic_hdr_len(dh)) { + ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev), + ICMP6_MIB_INERRORS); + return; + } - sk = inet6_lookup(&init_net, &dccp_hashinfo, &hdr->daddr, dh->dccph_dport, + sk = inet6_lookup(net, &dccp_hashinfo, + &hdr->daddr, dh->dccph_dport, &hdr->saddr, dh->dccph_sport, inet6_iif(skb)); if (sk == NULL) { - ICMP6_INC_STATS_BH(__in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); + ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev), + ICMP6_MIB_INERRORS); return; } @@ -110,64 +115,51 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, bh_lock_sock(sk); if (sock_owned_by_user(sk)) - NET_INC_STATS_BH(LINUX_MIB_LOCKDROPPEDICMPS); + NET_INC_STATS_BH(net, LINUX_MIB_LOCKDROPPEDICMPS); if (sk->sk_state == DCCP_CLOSED) goto out; + dp = dccp_sk(sk); + seq = dccp_hdr_seq(dh); + if ((1 << sk->sk_state) & ~(DCCPF_REQUESTING | DCCPF_LISTEN) && + !between48(seq, dp->dccps_awl, dp->dccps_awh)) { + NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); + goto out; + } + np = inet6_sk(sk); + if (type == NDISC_REDIRECT) { + struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie); + + if (dst) + dst->ops->redirect(dst, sk, skb); + goto out; + } + if (type == ICMPV6_PKT_TOOBIG) { struct dst_entry *dst = NULL; + if (!ip6_sk_accept_pmtu(sk)) + goto out; + if (sock_owned_by_user(sk)) goto out; if ((1 << sk->sk_state) & (DCCPF_LISTEN | DCCPF_CLOSED)) goto out; - /* icmp should have updated the destination cache entry */ - dst = __sk_dst_check(sk, np->dst_cookie); - if (dst == NULL) { - struct inet_sock *inet = inet_sk(sk); - struct flowi fl; - - /* BUGGG_FUTURE: Again, it is not clear how - to handle rthdr case. Ignore this complexity - for now. - */ - memset(&fl, 0, sizeof(fl)); - fl.proto = IPPROTO_DCCP; - ipv6_addr_copy(&fl.fl6_dst, &np->daddr); - ipv6_addr_copy(&fl.fl6_src, &np->saddr); - fl.oif = sk->sk_bound_dev_if; - fl.fl_ip_dport = inet->dport; - fl.fl_ip_sport = inet->sport; - security_sk_classify_flow(sk, &fl); - - err = ip6_dst_lookup(sk, &dst, &fl); - if (err) { - sk->sk_err_soft = -err; - goto out; - } - - err = xfrm_lookup(&dst, &fl, sk, 0); - if (err < 0) { - sk->sk_err_soft = -err; - goto out; - } - } else - dst_hold(dst); + dst = inet6_csk_update_pmtu(sk, ntohl(info)); + if (!dst) + goto out; - if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) { + if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) dccp_sync_mss(sk, dst_mtu(dst)); - } /* else let the usual retransmit timer handle it */ - dst_release(dst); goto out; } icmpv6_err_convert(type, code, &err); - seq = dccp_hdr_seq(dh); /* Might be for an request_sock */ switch (sk->sk_state) { struct request_sock *req, **prev; @@ -185,10 +177,11 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, * ICMPs are not backlogged, hence we cannot get an established * socket here. */ - BUG_TRAP(req->sk == NULL); + WARN_ON(req->sk != NULL); - if (seq != dccp_rsk(req)->dreq_iss) { - NET_INC_STATS_BH(LINUX_MIB_OUTOFWINDOWICMPS); + if (!between48(seq, dccp_rsk(req)->dreq_iss, + dccp_rsk(req)->dreq_gss)) { + NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } @@ -224,48 +217,34 @@ out: } -static int dccp_v6_send_response(struct sock *sk, struct request_sock *req, - struct dst_entry *dst) +static int dccp_v6_send_response(struct sock *sk, struct request_sock *req) { - struct inet6_request_sock *ireq6 = inet6_rsk(req); + struct inet_request_sock *ireq = inet_rsk(req); struct ipv6_pinfo *np = inet6_sk(sk); struct sk_buff *skb; - struct ipv6_txoptions *opt = NULL; - struct in6_addr *final_p = NULL, final; - struct flowi fl; + struct in6_addr *final_p, final; + struct flowi6 fl6; int err = -1; + struct dst_entry *dst; - memset(&fl, 0, sizeof(fl)); - fl.proto = IPPROTO_DCCP; - ipv6_addr_copy(&fl.fl6_dst, &ireq6->rmt_addr); - ipv6_addr_copy(&fl.fl6_src, &ireq6->loc_addr); - fl.fl6_flowlabel = 0; - fl.oif = ireq6->iif; - fl.fl_ip_dport = inet_rsk(req)->rmt_port; - fl.fl_ip_sport = inet_sk(sk)->sport; - security_req_classify_flow(req, &fl); - - if (dst == NULL) { - opt = np->opt; - - if (opt != NULL && opt->srcrt != NULL) { - const struct rt0_hdr *rt0 = (struct rt0_hdr *)opt->srcrt; - - ipv6_addr_copy(&final, &fl.fl6_dst); - ipv6_addr_copy(&fl.fl6_dst, rt0->addr); - final_p = &final; - } + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_proto = IPPROTO_DCCP; + fl6.daddr = ireq->ir_v6_rmt_addr; + fl6.saddr = ireq->ir_v6_loc_addr; + fl6.flowlabel = 0; + fl6.flowi6_oif = ireq->ir_iif; + fl6.fl6_dport = ireq->ir_rmt_port; + fl6.fl6_sport = htons(ireq->ir_num); + security_req_classify_flow(req, flowi6_to_flowi(&fl6)); - err = ip6_dst_lookup(sk, &dst, &fl); - if (err) - goto done; - if (final_p) - ipv6_addr_copy(&fl.fl6_dst, final_p); + final_p = fl6_update_dst(&fl6, np->opt, &final); - err = xfrm_lookup(&dst, &fl, sk, 0); - if (err < 0) - goto done; + dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + if (IS_ERR(dst)) { + err = PTR_ERR(dst); + dst = NULL; + goto done; } skb = dccp_make_response(sk, dst, req); @@ -273,31 +252,32 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req, struct dccp_hdr *dh = dccp_hdr(skb); dh->dccph_checksum = dccp_v6_csum_finish(skb, - &ireq6->loc_addr, - &ireq6->rmt_addr); - ipv6_addr_copy(&fl.fl6_dst, &ireq6->rmt_addr); - err = ip6_xmit(sk, skb, &fl, opt, 0); + &ireq->ir_v6_loc_addr, + &ireq->ir_v6_rmt_addr); + fl6.daddr = ireq->ir_v6_rmt_addr; + err = ip6_xmit(sk, skb, &fl6, np->opt, np->tclass); err = net_xmit_eval(err); } done: - if (opt != NULL && opt != np->opt) - sock_kfree_s(sk, opt, opt->tot_len); dst_release(dst); return err; } static void dccp_v6_reqsk_destructor(struct request_sock *req) { - if (inet6_rsk(req)->pktopts != NULL) - kfree_skb(inet6_rsk(req)->pktopts); + dccp_feat_list_purge(&dccp_rsk(req)->dreq_featneg); + kfree_skb(inet_rsk(req)->pktopts); } static void dccp_v6_ctl_send_reset(struct sock *sk, struct sk_buff *rxskb) { - struct ipv6hdr *rxip6h; + const struct ipv6hdr *rxip6h; struct sk_buff *skb; - struct flowi fl; + struct flowi6 fl6; + struct net *net = dev_net(skb_dst(rxskb)->dev); + struct sock *ctl_sk = net->dccp.v6_ctl_sk; + struct dst_entry *dst; if (dccp_hdr(rxskb)->dccph_type == DCCP_PKT_RESET) return; @@ -305,7 +285,7 @@ static void dccp_v6_ctl_send_reset(struct sock *sk, struct sk_buff *rxskb) if (!ipv6_unicast_destination(rxskb)) return; - skb = dccp_ctl_make_reset(dccp_v6_ctl_socket, rxskb); + skb = dccp_ctl_make_reset(ctl_sk, rxskb); if (skb == NULL) return; @@ -313,24 +293,24 @@ static void dccp_v6_ctl_send_reset(struct sock *sk, struct sk_buff *rxskb) dccp_hdr(skb)->dccph_checksum = dccp_v6_csum_finish(skb, &rxip6h->saddr, &rxip6h->daddr); - memset(&fl, 0, sizeof(fl)); - ipv6_addr_copy(&fl.fl6_dst, &rxip6h->saddr); - ipv6_addr_copy(&fl.fl6_src, &rxip6h->daddr); + memset(&fl6, 0, sizeof(fl6)); + fl6.daddr = rxip6h->saddr; + fl6.saddr = rxip6h->daddr; - fl.proto = IPPROTO_DCCP; - fl.oif = inet6_iif(rxskb); - fl.fl_ip_dport = dccp_hdr(skb)->dccph_dport; - fl.fl_ip_sport = dccp_hdr(skb)->dccph_sport; - security_skb_classify_flow(rxskb, &fl); + fl6.flowi6_proto = IPPROTO_DCCP; + fl6.flowi6_oif = inet6_iif(rxskb); + fl6.fl6_dport = dccp_hdr(skb)->dccph_dport; + fl6.fl6_sport = dccp_hdr(skb)->dccph_sport; + security_skb_classify_flow(rxskb, flowi6_to_flowi(&fl6)); /* sk = NULL, but it is safe for now. RST socket required. */ - if (!ip6_dst_lookup(NULL, &skb->dst, &fl)) { - if (xfrm_lookup(&skb->dst, &fl, NULL, 0) >= 0) { - ip6_xmit(dccp_v6_ctl_socket->sk, skb, &fl, NULL, 0); - DCCP_INC_STATS_BH(DCCP_MIB_OUTSEGS); - DCCP_INC_STATS_BH(DCCP_MIB_OUTRSTS); - return; - } + dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL); + if (!IS_ERR(dst)) { + skb_dst_set(skb, dst); + ip6_xmit(ctl_sk, skb, &fl6, NULL, 0); + DCCP_INC_STATS_BH(DCCP_MIB_OUTSEGS); + DCCP_INC_STATS_BH(DCCP_MIB_OUTRSTS); + return; } kfree_skb(skb); @@ -343,6 +323,7 @@ static struct request_sock_ops dccp6_request_sock_ops = { .send_ack = dccp_reqsk_send_ack, .destructor = dccp_v6_reqsk_destructor, .send_reset = dccp_v6_ctl_send_reset, + .syn_ack_timeout = dccp_syn_ack_timeout, }; static struct sock *dccp_v6_hnd_req(struct sock *sk,struct sk_buff *skb) @@ -360,7 +341,7 @@ static struct sock *dccp_v6_hnd_req(struct sock *sk,struct sk_buff *skb) if (req != NULL) return dccp_check_req(sk, skb, req, prev); - nsk = __inet6_lookup_established(&init_net, &dccp_hashinfo, + nsk = __inet6_lookup_established(sock_net(sk), &dccp_hashinfo, &iph->saddr, dh->dccph_sport, &iph->daddr, ntohs(dh->dccph_dport), inet6_iif(skb)); @@ -380,7 +361,7 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) { struct request_sock *req; struct dccp_request_sock *dreq; - struct inet6_request_sock *ireq6; + struct inet_request_sock *ireq; struct ipv6_pinfo *np = inet6_sk(sk); const __be32 service = dccp_hdr_request(skb)->dccph_req_service; struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb); @@ -409,7 +390,8 @@ 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)) @@ -418,37 +400,37 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) if (security_inet_conn_request(sk, skb, req)) goto drop_and_free; - ireq6 = inet6_rsk(req); - ipv6_addr_copy(&ireq6->rmt_addr, &ipv6_hdr(skb)->saddr); - ipv6_addr_copy(&ireq6->loc_addr, &ipv6_hdr(skb)->daddr); - ireq6->pktopts = NULL; + ireq = inet_rsk(req); + ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr; + ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr; if (ipv6_opt_accepted(sk, skb) || np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) { atomic_inc(&skb->users); - ireq6->pktopts = skb; + ireq->pktopts = skb; } - ireq6->iif = sk->sk_bound_dev_if; + ireq->ir_iif = sk->sk_bound_dev_if; /* So that link locals have meaning */ if (!sk->sk_bound_dev_if && - ipv6_addr_type(&ireq6->rmt_addr) & IPV6_ADDR_LINKLOCAL) - ireq6->iif = inet6_iif(skb); + ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL) + ireq->ir_iif = inet6_iif(skb); /* * Step 3: Process LISTEN state * * Set S.ISR, S.GSR, S.SWL, S.SWH from packet or Init Cookie * - * In fact we defer setting S.GSR, S.SWL, S.SWH to - * dccp_create_openreq_child. + * Setting S.SWL/S.SWH to is deferred to dccp_create_openreq_child(). */ dreq->dreq_isr = dcb->dccpd_seq; + dreq->dreq_gsr = dreq->dreq_isr; dreq->dreq_iss = dccp_v6_init_sequence(skb); + dreq->dreq_gss = dreq->dreq_iss; dreq->dreq_service = service; - if (dccp_v6_send_response(sk, req, NULL)) + if (dccp_v6_send_response(sk, req)) goto drop_and_free; inet6_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT); @@ -466,13 +448,11 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, struct request_sock *req, struct dst_entry *dst) { - struct inet6_request_sock *ireq6 = inet6_rsk(req); + struct inet_request_sock *ireq = inet_rsk(req); struct ipv6_pinfo *newnp, *np = inet6_sk(sk); struct inet_sock *newinet; - struct dccp_sock *newdp; struct dccp6_sock *newdp6; struct sock *newsk; - struct ipv6_txoptions *opt; if (skb->protocol == htons(ETH_P_IP)) { /* @@ -483,20 +463,17 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, return NULL; newdp6 = (struct dccp6_sock *)newsk; - newdp = dccp_sk(newsk); newinet = inet_sk(newsk); newinet->pinet6 = &newdp6->inet6; newnp = inet6_sk(newsk); memcpy(newnp, np, sizeof(struct ipv6_pinfo)); - ipv6_addr_set(&newnp->daddr, 0, 0, htonl(0x0000FFFF), - newinet->daddr); + ipv6_addr_set_v4mapped(newinet->inet_daddr, &newsk->sk_v6_daddr); - ipv6_addr_set(&newnp->saddr, 0, 0, htonl(0x0000FFFF), - newinet->saddr); + ipv6_addr_set_v4mapped(newinet->inet_saddr, &newnp->saddr); - ipv6_addr_copy(&newnp->rcv_saddr, &newnp->saddr); + newsk->sk_v6_rcv_saddr = newnp->saddr; inet_csk(newsk)->icsk_af_ops = &dccp_ipv6_mapped; newsk->sk_backlog_rcv = dccp_v4_do_rcv; @@ -520,44 +497,32 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, return newsk; } - opt = np->opt; if (sk_acceptq_is_full(sk)) goto out_overflow; if (dst == NULL) { - struct in6_addr *final_p = NULL, final; - struct flowi fl; - - memset(&fl, 0, sizeof(fl)); - fl.proto = IPPROTO_DCCP; - ipv6_addr_copy(&fl.fl6_dst, &ireq6->rmt_addr); - if (opt != NULL && opt->srcrt != NULL) { - const struct rt0_hdr *rt0 = (struct rt0_hdr *)opt->srcrt; - - ipv6_addr_copy(&final, &fl.fl6_dst); - ipv6_addr_copy(&fl.fl6_dst, rt0->addr); - final_p = &final; - } - ipv6_addr_copy(&fl.fl6_src, &ireq6->loc_addr); - fl.oif = sk->sk_bound_dev_if; - fl.fl_ip_dport = inet_rsk(req)->rmt_port; - fl.fl_ip_sport = inet_sk(sk)->sport; - security_sk_classify_flow(sk, &fl); - - if (ip6_dst_lookup(sk, &dst, &fl)) - goto out; - - if (final_p) - ipv6_addr_copy(&fl.fl6_dst, final_p); - - if ((xfrm_lookup(&dst, &fl, sk, 0)) < 0) + struct in6_addr *final_p, final; + struct flowi6 fl6; + + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_proto = IPPROTO_DCCP; + fl6.daddr = ireq->ir_v6_rmt_addr; + final_p = fl6_update_dst(&fl6, np->opt, &final); + fl6.saddr = ireq->ir_v6_loc_addr; + fl6.flowi6_oif = sk->sk_bound_dev_if; + fl6.fl6_dport = ireq->ir_rmt_port; + fl6.fl6_sport = htons(ireq->ir_num); + security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); + + dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + if (IS_ERR(dst)) goto out; } newsk = dccp_create_openreq_child(sk, req, skb); if (newsk == NULL) - goto out; + goto out_nonewsk; /* * No need to charge this sock to the relevant IPv6 refcnt debug socks @@ -571,31 +536,30 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, newdp6 = (struct dccp6_sock *)newsk; newinet = inet_sk(newsk); newinet->pinet6 = &newdp6->inet6; - newdp = dccp_sk(newsk); newnp = inet6_sk(newsk); memcpy(newnp, np, sizeof(struct ipv6_pinfo)); - ipv6_addr_copy(&newnp->daddr, &ireq6->rmt_addr); - ipv6_addr_copy(&newnp->saddr, &ireq6->loc_addr); - ipv6_addr_copy(&newnp->rcv_saddr, &ireq6->loc_addr); - newsk->sk_bound_dev_if = ireq6->iif; + newsk->sk_v6_daddr = ireq->ir_v6_rmt_addr; + newnp->saddr = ireq->ir_v6_loc_addr; + newsk->sk_v6_rcv_saddr = ireq->ir_v6_loc_addr; + newsk->sk_bound_dev_if = ireq->ir_iif; /* Now IPv6 options... First: no IPv4 options. */ - newinet->opt = NULL; + newinet->inet_opt = NULL; /* Clone RX bits */ newnp->rxopt.all = np->rxopt.all; /* Clone pktoptions received with SYN */ newnp->pktoptions = NULL; - if (ireq6->pktopts != NULL) { - newnp->pktoptions = skb_clone(ireq6->pktopts, GFP_ATOMIC); - kfree_skb(ireq6->pktopts); - ireq6->pktopts = NULL; + if (ireq->pktopts != NULL) { + newnp->pktoptions = skb_clone(ireq->pktopts, GFP_ATOMIC); + consume_skb(ireq->pktopts); + ireq->pktopts = NULL; if (newnp->pktoptions) skb_set_owner_r(newnp->pktoptions, newsk); } @@ -609,11 +573,8 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, * Yes, keeping reference count would be much more clever, but we make * one more one thing there: reattach optmem to newsk. */ - if (opt != NULL) { - newnp->opt = ipv6_dup_options(newsk, opt); - if (opt != np->opt) - sock_kfree_s(sk, opt, opt->tot_len); - } + if (np->opt != NULL) + newnp->opt = ipv6_dup_options(newsk, np->opt); inet_csk(newsk)->icsk_ext_hdr_len = 0; if (newnp->opt != NULL) @@ -622,20 +583,24 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, dccp_sync_mss(newsk, dst_mtu(dst)); - newinet->daddr = newinet->saddr = newinet->rcv_saddr = LOOPBACK4_IPV6; + newinet->inet_daddr = newinet->inet_saddr = LOOPBACK4_IPV6; + newinet->inet_rcv_saddr = LOOPBACK4_IPV6; - __inet6_hash(newsk); - inet_inherit_port(sk, newsk); + if (__inet_inherit_port(sk, newsk) < 0) { + inet_csk_prepare_forced_close(newsk); + dccp_done(newsk); + goto out; + } + __inet6_hash(newsk, NULL); return newsk; out_overflow: - NET_INC_STATS_BH(LINUX_MIB_LISTENOVERFLOWS); -out: - NET_INC_STATS_BH(LINUX_MIB_LISTENDROPS); - if (opt != NULL && opt != np->opt) - sock_kfree_s(sk, opt, opt->tot_len); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); +out_nonewsk: dst_release(dst); +out: + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); return NULL; } @@ -791,10 +756,8 @@ static int dccp_v6_rcv(struct sk_buff *skb) /* Step 2: * Look up flow ID in table and get corresponding socket */ - sk = __inet6_lookup(&init_net, &dccp_hashinfo, &ipv6_hdr(skb)->saddr, - dh->dccph_sport, - &ipv6_hdr(skb)->daddr, ntohs(dh->dccph_dport), - inet6_iif(skb)); + sk = __inet6_lookup_skb(&dccp_hashinfo, skb, + dh->dccph_sport, dh->dccph_dport); /* * Step 2: * If no socket ... @@ -867,8 +830,8 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct dccp_sock *dp = dccp_sk(sk); - struct in6_addr *saddr = NULL, *final_p = NULL, final; - struct flowi fl; + struct in6_addr *saddr = NULL, *final_p, final; + struct flowi6 fl6; struct dst_entry *dst; int addr_type; int err; @@ -881,17 +844,16 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, if (usin->sin6_family != AF_INET6) return -EAFNOSUPPORT; - memset(&fl, 0, sizeof(fl)); + memset(&fl6, 0, sizeof(fl6)); if (np->sndflow) { - fl.fl6_flowlabel = usin->sin6_flowinfo & IPV6_FLOWINFO_MASK; - IP6_ECN_flow_init(fl.fl6_flowlabel); - if (fl.fl6_flowlabel & IPV6_FLOWLABEL_MASK) { + fl6.flowlabel = usin->sin6_flowinfo & IPV6_FLOWINFO_MASK; + IP6_ECN_flow_init(fl6.flowlabel); + if (fl6.flowlabel & IPV6_FLOWLABEL_MASK) { struct ip6_flowlabel *flowlabel; - flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel); + flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (flowlabel == NULL) return -EINVAL; - ipv6_addr_copy(&usin->sin6_addr, &flowlabel->dst); fl6_sock_release(flowlabel); } } @@ -924,8 +886,8 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, return -EINVAL; } - ipv6_addr_copy(&np->daddr, &usin->sin6_addr); - np->flow_label = fl.fl6_flowlabel; + sk->sk_v6_daddr = usin->sin6_addr; + np->flow_label = fl6.flowlabel; /* * DCCP over IPv4 @@ -952,58 +914,40 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, icsk->icsk_af_ops = &dccp_ipv6_af_ops; sk->sk_backlog_rcv = dccp_v6_do_rcv; goto failure; - } else { - ipv6_addr_set(&np->saddr, 0, 0, htonl(0x0000FFFF), - inet->saddr); - ipv6_addr_set(&np->rcv_saddr, 0, 0, htonl(0x0000FFFF), - inet->rcv_saddr); } + ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr); + ipv6_addr_set_v4mapped(inet->inet_rcv_saddr, &sk->sk_v6_rcv_saddr); return err; } - if (!ipv6_addr_any(&np->rcv_saddr)) - saddr = &np->rcv_saddr; - - fl.proto = IPPROTO_DCCP; - ipv6_addr_copy(&fl.fl6_dst, &np->daddr); - ipv6_addr_copy(&fl.fl6_src, saddr ? saddr : &np->saddr); - fl.oif = sk->sk_bound_dev_if; - fl.fl_ip_dport = usin->sin6_port; - fl.fl_ip_sport = inet->sport; - security_sk_classify_flow(sk, &fl); + if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) + saddr = &sk->sk_v6_rcv_saddr; - if (np->opt != NULL && np->opt->srcrt != NULL) { - const struct rt0_hdr *rt0 = (struct rt0_hdr *)np->opt->srcrt; + fl6.flowi6_proto = IPPROTO_DCCP; + fl6.daddr = sk->sk_v6_daddr; + fl6.saddr = saddr ? *saddr : np->saddr; + fl6.flowi6_oif = sk->sk_bound_dev_if; + fl6.fl6_dport = usin->sin6_port; + fl6.fl6_sport = inet->inet_sport; + security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); - ipv6_addr_copy(&final, &fl.fl6_dst); - ipv6_addr_copy(&fl.fl6_dst, rt0->addr); - final_p = &final; - } + final_p = fl6_update_dst(&fl6, np->opt, &final); - err = ip6_dst_lookup(sk, &dst, &fl); - if (err) + dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + if (IS_ERR(dst)) { + err = PTR_ERR(dst); goto failure; - - if (final_p) - ipv6_addr_copy(&fl.fl6_dst, final_p); - - err = __xfrm_lookup(&dst, &fl, sk, XFRM_LOOKUP_WAIT); - if (err < 0) { - if (err == -EREMOTE) - err = ip6_dst_blackhole(sk, &dst, &fl); - if (err < 0) - goto failure; } if (saddr == NULL) { - saddr = &fl.fl6_src; - ipv6_addr_copy(&np->rcv_saddr, saddr); + saddr = &fl6.saddr; + sk->sk_v6_rcv_saddr = *saddr; } /* set the source address */ - ipv6_addr_copy(&np->saddr, saddr); - inet->rcv_saddr = LOOPBACK4_IPV6; + np->saddr = *saddr; + inet->inet_rcv_saddr = LOOPBACK4_IPV6; __ip6_dst_store(sk, dst, NULL, NULL); @@ -1012,7 +956,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, icsk->icsk_ext_hdr_len = (np->opt->opt_flen + np->opt->opt_nflen); - inet->dport = usin->sin6_port; + inet->inet_dport = usin->sin6_port; dccp_set_state(sk, DCCP_REQUESTING); err = inet6_hash_connect(&dccp_death_row, sk); @@ -1020,8 +964,9 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, goto late_failure; dp->dccps_iss = secure_dccpv6_sequence_number(np->saddr.s6_addr32, - np->daddr.s6_addr32, - inet->sport, inet->dport); + sk->sk_v6_daddr.s6_addr32, + inet->inet_sport, + inet->inet_dport); err = dccp_connect(sk); if (err) goto late_failure; @@ -1032,12 +977,12 @@ late_failure: dccp_set_state(sk, DCCP_CLOSED); __sk_dst_reset(sk); failure: - inet->dport = 0; + inet->inet_dport = 0; sk->sk_route_caps = 0; return err; } -static struct inet_connection_sock_af_ops dccp_ipv6_af_ops = { +static const struct inet_connection_sock_af_ops dccp_ipv6_af_ops = { .queue_xmit = inet6_csk_xmit, .send_check = dccp_v6_send_check, .rebuild_header = inet6_sk_rebuild_header, @@ -1058,7 +1003,7 @@ static struct inet_connection_sock_af_ops dccp_ipv6_af_ops = { /* * DCCP over IPv4 via INET6 API */ -static struct inet_connection_sock_af_ops dccp_ipv6_mapped = { +static const struct inet_connection_sock_af_ops dccp_ipv6_mapped = { .queue_xmit = ip_queue_xmit, .send_check = dccp_v4_send_check, .rebuild_header = inet_sk_rebuild_header, @@ -1092,18 +1037,16 @@ static int dccp_v6_init_sock(struct sock *sk) return err; } -static int dccp_v6_destroy_sock(struct sock *sk) +static void dccp_v6_destroy_sock(struct sock *sk) { dccp_destroy_sock(sk); - return inet6_destroy_sock(sk); + inet6_destroy_sock(sk); } static struct timewait_sock_ops dccp6_timewait_sock_ops = { .twsk_obj_size = sizeof(struct dccp6_timewait_sock), }; -DEFINE_PROTO_INUSE(dccp_v6) - static struct proto dccp_v6_prot = { .name = "DCCPv6", .owner = THIS_MODULE, @@ -1126,23 +1069,23 @@ static struct proto dccp_v6_prot = { .orphan_count = &dccp_orphan_count, .max_header = MAX_DCCP_HEADER, .obj_size = sizeof(struct dccp6_sock), + .slab_flags = SLAB_DESTROY_BY_RCU, .rsk_prot = &dccp6_request_sock_ops, .twsk_prot = &dccp6_timewait_sock_ops, - .hashinfo = &dccp_hashinfo, + .h.hashinfo = &dccp_hashinfo, #ifdef CONFIG_COMPAT .compat_setsockopt = compat_dccp_setsockopt, .compat_getsockopt = compat_dccp_getsockopt, #endif - REF_PROTO_INUSE(dccp_v6) }; -static struct inet6_protocol dccp_v6_protocol = { +static const struct inet6_protocol dccp_v6_protocol = { .handler = dccp_v6_rcv, .err_handler = dccp_v6_err, .flags = INET6_PROTO_NOPOLICY | INET6_PROTO_FINAL, }; -static struct proto_ops inet6_dccp_ops = { +static const struct proto_ops inet6_dccp_ops = { .family = PF_INET6, .owner = THIS_MODULE, .release = inet6_release, @@ -1172,10 +1115,28 @@ static struct inet_protosw dccp_v6_protosw = { .protocol = IPPROTO_DCCP, .prot = &dccp_v6_prot, .ops = &inet6_dccp_ops, - .capability = -1, .flags = INET_PROTOSW_ICSK, }; +static int __net_init dccp_v6_init_net(struct net *net) +{ + if (dccp_hashinfo.bhash == NULL) + return -ESOCKTNOSUPPORT; + + return inet_ctl_sock_create(&net->dccp.v6_ctl_sk, PF_INET6, + SOCK_DCCP, IPPROTO_DCCP, net); +} + +static void __net_exit dccp_v6_exit_net(struct net *net) +{ + inet_ctl_sock_destroy(net->dccp.v6_ctl_sk); +} + +static struct pernet_operations dccp_v6_ops = { + .init = dccp_v6_init_net, + .exit = dccp_v6_exit_net, +}; + static int __init dccp_v6_init(void) { int err = proto_register(&dccp_v6_prot, 1); @@ -1189,13 +1150,13 @@ static int __init dccp_v6_init(void) inet6_register_protosw(&dccp_v6_protosw); - err = inet_csk_ctl_sock_create(&dccp_v6_ctl_socket, PF_INET6, - SOCK_DCCP, IPPROTO_DCCP); + err = register_pernet_subsys(&dccp_v6_ops); if (err != 0) - goto out_unregister_protosw; + goto out_destroy_ctl_sock; out: return err; -out_unregister_protosw: + +out_destroy_ctl_sock: inet6_del_protocol(&dccp_v6_protocol, IPPROTO_DCCP); inet6_unregister_protosw(&dccp_v6_protosw); out_unregister_proto: @@ -1205,6 +1166,7 @@ out_unregister_proto: static void __exit dccp_v6_exit(void) { + unregister_pernet_subsys(&dccp_v6_ops); inet6_del_protocol(&dccp_v6_protocol, IPPROTO_DCCP); inet6_unregister_protosw(&dccp_v6_protosw); proto_unregister(&dccp_v6_prot); diff --git a/net/dccp/ipv6.h b/net/dccp/ipv6.h index 6eef81fdbe5..af259e15e7f 100644 --- a/net/dccp/ipv6.h +++ b/net/dccp/ipv6.h @@ -25,12 +25,10 @@ struct dccp6_sock { struct dccp6_request_sock { struct dccp_request_sock dccp; - struct inet6_request_sock inet6; }; struct dccp6_timewait_sock { struct inet_timewait_sock inet; - struct inet6_timewait_sock tw6; }; #endif /* _DCCP_IPV6_H */ diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index 027d1814e1a..c69eb9c4fbb 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -11,6 +11,7 @@ */ #include <linux/dccp.h> +#include <linux/gfp.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/timer.h> @@ -42,16 +43,6 @@ struct inet_timewait_death_row dccp_death_row = { 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_rx_ccid = sysctl_dccp_feat_rx_ccid; - dmsk->dccpms_tx_ccid = sysctl_dccp_feat_tx_ccid; - dmsk->dccpms_ack_ratio = sysctl_dccp_feat_ack_ratio; - dmsk->dccpms_send_ack_vector = sysctl_dccp_feat_send_ack_vector; - dmsk->dccpms_send_ndp_count = sysctl_dccp_feat_send_ndp_count; -} - void dccp_time_wait(struct sock *sk, int state, int timeo) { struct inet_timewait_sock *tw = NULL; @@ -62,15 +53,12 @@ void dccp_time_wait(struct sock *sk, int state, int timeo) if (tw != NULL) { const struct inet_connection_sock *icsk = inet_csk(sk); const int rto = (icsk->icsk_rto << 2) - (icsk->icsk_rto >> 1); -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) if (tw->tw_family == PF_INET6) { const struct ipv6_pinfo *np = inet6_sk(sk); - struct inet6_timewait_sock *tw6; - tw->tw_ipv6_offset = inet6_tw_offset(sk->sk_prot); - tw6 = inet6_twsk((struct sock *)tw); - ipv6_addr_copy(&tw6->tw_v6_daddr, &np->daddr); - ipv6_addr_copy(&tw6->tw_v6_rcv_saddr, &np->rcv_saddr); + tw->tw_v6_daddr = sk->sk_v6_daddr; + tw->tw_v6_rcv_saddr = sk->sk_v6_rcv_saddr; tw->tw_ipv6only = np->ipv6only; } #endif @@ -109,13 +97,12 @@ struct sock *dccp_create_openreq_child(struct sock *sk, * (* Generate a new socket and switch to that socket *) * Set S := new socket for this port pair */ - struct sock *newsk = inet_csk_clone(sk, req, GFP_ATOMIC); + struct sock *newsk = inet_csk_clone_lock(sk, req, GFP_ATOMIC); if (newsk != NULL) { - const struct dccp_request_sock *dreq = dccp_rsk(req); + struct dccp_request_sock *dreq = dccp_rsk(req); struct inet_connection_sock *newicsk = inet_csk(newsk); struct dccp_sock *newdp = dccp_sk(newsk); - struct dccp_minisock *newdmsk = dccp_msk(newsk); newdp->dccps_role = DCCP_ROLE_SERVER; newdp->dccps_hc_rx_ackvec = NULL; @@ -125,65 +112,34 @@ struct sock *dccp_create_openreq_child(struct sock *sk, newdp->dccps_timestamp_time = dreq->dreq_timestamp_time; newicsk->icsk_rto = DCCP_TIMEOUT_INIT; - if (dccp_feat_clone(sk, newsk)) - goto out_free; - - if (newdmsk->dccpms_send_ack_vector) { - newdp->dccps_hc_rx_ackvec = - dccp_ackvec_alloc(GFP_ATOMIC); - if (unlikely(newdp->dccps_hc_rx_ackvec == NULL)) - goto out_free; - } - - newdp->dccps_hc_rx_ccid = - ccid_hc_rx_new(newdmsk->dccpms_rx_ccid, - newsk, GFP_ATOMIC); - newdp->dccps_hc_tx_ccid = - ccid_hc_tx_new(newdmsk->dccpms_tx_ccid, - newsk, GFP_ATOMIC); - if (unlikely(newdp->dccps_hc_rx_ccid == NULL || - newdp->dccps_hc_tx_ccid == NULL)) { - dccp_ackvec_free(newdp->dccps_hc_rx_ackvec); - ccid_hc_rx_delete(newdp->dccps_hc_rx_ccid, newsk); - ccid_hc_tx_delete(newdp->dccps_hc_tx_ccid, newsk); -out_free: - /* It is still raw copy of parent, so invalidate - * destructor and make plain sk_free() */ - newsk->sk_destruct = NULL; - sk_free(newsk); - return NULL; - } - + INIT_LIST_HEAD(&newdp->dccps_featneg); /* * Step 3: Process LISTEN state * * 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 + * 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). */ - - /* See dccp_v4_conn_request */ - newdmsk->dccpms_sequence_window = req->rcv_wnd; - - newdp->dccps_gar = newdp->dccps_isr = dreq->dreq_isr; - dccp_update_gsr(newsk, dreq->dreq_isr); - newdp->dccps_iss = dreq->dreq_iss; - dccp_update_gss(newsk, dreq->dreq_iss); + newdp->dccps_gss = dreq->dreq_gss; + newdp->dccps_gar = newdp->dccps_iss; + newdp->dccps_isr = dreq->dreq_isr; + newdp->dccps_gsr = dreq->dreq_gsr; /* - * 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. + * Activate features: initialise CCIDs, sequence windows etc. */ - 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)); - + if (dccp_feat_activate_values(newsk, &dreq->dreq_featneg)) { + /* It is still raw copy of parent, so invalidate + * destructor and make plain sk_free() */ + newsk->sk_destruct = NULL; + sk_free(newsk); + return NULL; + } dccp_init_xmit_timers(newsk); DCCP_INC_STATS_BH(DCCP_MIB_PASSIVEOPENS); @@ -207,16 +163,15 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb, /* Check for retransmitted REQUEST */ if (dccp_hdr(skb)->dccph_type == DCCP_PKT_REQUEST) { - if (after48(DCCP_SKB_CB(skb)->dccpd_seq, dreq->dreq_isr)) { + if (after48(DCCP_SKB_CB(skb)->dccpd_seq, dreq->dreq_gsr)) { dccp_pr_debug("Retransmitted REQUEST\n"); - dreq->dreq_isr = DCCP_SKB_CB(skb)->dccpd_seq; + dreq->dreq_gsr = DCCP_SKB_CB(skb)->dccpd_seq; /* * Send another RESPONSE packet * To protect against Request floods, increment retrans * counter (backoff, monitored by dccp_response_timer). */ - req->retrans++; - req->rsk_ops->rtx_syn_ack(sk, req, NULL); + inet_rtx_syn_ack(sk, req); } /* Network Duplicate, discard packet */ return NULL; @@ -229,12 +184,14 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb, goto drop; /* Invalid ACK */ - if (DCCP_SKB_CB(skb)->dccpd_ack_seq != dreq->dreq_iss) { + if (!between48(DCCP_SKB_CB(skb)->dccpd_ack_seq, + dreq->dreq_iss, dreq->dreq_gss)) { dccp_pr_debug("Invalid ACK number: ack_seq=%llu, " - "dreq_iss=%llu\n", + "dreq_iss=%llu, dreq_gss=%llu\n", (unsigned long long) DCCP_SKB_CB(skb)->dccpd_ack_seq, - (unsigned long long) dreq->dreq_iss); + (unsigned long long) dreq->dreq_iss, + (unsigned long long) dreq->dreq_gss); goto drop; } @@ -280,13 +237,13 @@ int dccp_child_process(struct sock *parent, struct sock *child, /* Wakeup parent, send SIGIO */ if (state == DCCP_RESPOND && child->sk_state != state) - parent->sk_data_ready(parent, 0); + parent->sk_data_ready(parent); } else { /* Alas, it is possible again, because we do lookup * in main socket hash table and lock on listening * socket does not protect us more. */ - sk_add_backlog(child, skb); + __sk_add_backlog(child, skb); } bh_unlock_sock(child); @@ -296,21 +253,26 @@ int dccp_child_process(struct sock *parent, struct sock *child, EXPORT_SYMBOL_GPL(dccp_child_process); -void dccp_reqsk_send_ack(struct sk_buff *skb, struct request_sock *rsk) +void dccp_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, + struct request_sock *rsk) { DCCP_BUG("DCCP-ACK packets are never sent in LISTEN/RESPOND state"); } 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); - inet_rsk(req)->rmt_port = dccp_hdr(skb)->dccph_sport; - inet_rsk(req)->acked = 0; - req->rcv_wnd = sysctl_dccp_feat_sequence_window; - dreq->dreq_timestamp_echo = 0; + inet_rsk(req)->ir_rmt_port = dccp_hdr(skb)->dccph_sport; + inet_rsk(req)->ir_num = ntohs(dccp_hdr(skb)->dccph_dport); + inet_rsk(req)->acked = 0; + 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/options.c b/net/dccp/options.c index d2a84a2fece..9bce31886bd 100644 --- a/net/dccp/options.c +++ b/net/dccp/options.c @@ -23,23 +23,20 @@ #include "dccp.h" #include "feat.h" -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_ack_ratio = DCCPF_INITIAL_ACK_RATIO; -int sysctl_dccp_feat_send_ack_vector = DCCPF_INITIAL_SEND_ACK_VECTOR; -int sysctl_dccp_feat_send_ndp_count = DCCPF_INITIAL_SEND_NDP_COUNT; - -static u32 dccp_decode_value_var(const unsigned char *bf, const u8 len) +u64 dccp_decode_value_var(const u8 *bf, const u8 len) { - u32 value = 0; + u64 value = 0; + if (len >= DCCP_OPTVAL_MAXLEN) + value += ((u64)*bf++) << 40; + if (len > 4) + value += ((u64)*bf++) << 32; if (len > 3) - value += *bf++ << 24; + value += ((u64)*bf++) << 24; if (len > 2) - value += *bf++ << 16; + value += ((u64)*bf++) << 16; if (len > 1) - value += *bf++ << 8; + value += ((u64)*bf++) << 8; if (len > 0) value += *bf; @@ -57,14 +54,13 @@ 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 + (dh->dccph_doff * 4); struct dccp_options_received *opt_recv = &dp->dccps_options_received; unsigned char opt, len; - unsigned char *value; + unsigned char *uninitialized_var(value); u32 elapsed_time; __be32 opt_val; int rc; @@ -81,11 +77,11 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq, /* Check if this isn't a single byte option */ if (opt > DCCPO_MAX_RESERVED) { if (opt_ptr == opt_end) - goto out_invalid_option; + goto out_nonsensical_length; len = *opt_ptr++; - if (len < 3) - goto out_invalid_option; + if (len < 2) + goto out_nonsensical_length; /* * Remove the type and len fields, leaving * just the value size @@ -95,21 +91,16 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq, opt_ptr += len; if (opt_ptr > opt_end) - goto out_invalid_option; + goto out_nonsensical_length; } /* - * CCID-Specific Options (from RFC 4340, sec. 10.3): - * - * Option numbers 128 through 191 are for options sent from the - * HC-Sender to the HC-Receiver; option numbers 192 through 255 - * are for options sent from the HC-Receiver to the HC-Sender. - * * CCID-specific options are ignored during connection setup, as * negotiation may still be in progress (see RFC 4340, 10.3). - * + * The same applies to Ack Vectors, as these depend on the CCID. */ - if (dreq != NULL && opt >= 128) + if (dreq != NULL && (opt >= DCCPO_MIN_RX_CCID_SPECIFIC || + opt == DCCPO_ACK_VECTOR_0 || opt == DCCPO_ACK_VECTOR_1)) goto ignore_option; switch (opt) { @@ -122,50 +113,22 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq, mandatory = 1; break; case DCCPO_NDP_COUNT: - if (len > 3) + if (len > 6) goto out_invalid_option; opt_recv->dccpor_ndp = dccp_decode_value_var(value, len); - dccp_pr_debug("%s rx opt: NDP count=%d\n", dccp_role(sk), - opt_recv->dccpor_ndp); - break; - case DCCPO_CHANGE_L: - /* fall through */ - case DCCPO_CHANGE_R: - if (pkt_type == DCCP_PKT_DATA) - break; - if (len < 2) - goto out_invalid_option; - rc = dccp_feat_change_recv(sk, opt, *value, value + 1, - len - 1); - /* - * When there is a change error, change_recv is - * responsible for dealing with it. i.e. reply with an - * empty confirm. - * If the change was mandatory, then we need to die. - */ - if (rc && mandatory) - goto out_invalid_option; - break; - case DCCPO_CONFIRM_L: - /* fall through */ - case DCCPO_CONFIRM_R: - if (pkt_type == DCCP_PKT_DATA) - break; - if (len < 2) /* FIXME this disallows empty confirm */ - goto out_invalid_option; - if (dccp_feat_confirm_recv(sk, opt, *value, - value + 1, len - 1)) - goto out_invalid_option; + dccp_pr_debug("%s opt: NDP count=%llu\n", dccp_role(sk), + (unsigned long long)opt_recv->dccpor_ndp); break; - case DCCPO_ACK_VECTOR_0: - case DCCPO_ACK_VECTOR_1: - if (dccp_packet_without_ack(skb)) /* RFC 4340, 11.4 */ + case DCCPO_CHANGE_L ... DCCPO_CONFIRM_R: + if (pkt_type == DCCP_PKT_DATA) /* RFC 4340, 6 */ break; - - if (dccp_msk(sk)->dccpms_send_ack_vector && - dccp_ackvec_parse(sk, skb, &ackno, opt, value, len)) + if (len == 0) goto out_invalid_option; + rc = dccp_feat_parse_options(sk, dreq, mandatory, opt, + *value, value + 1, len - 1); + if (rc) + goto out_featneg_failed; break; case DCCPO_TIMESTAMP: if (len != 4) @@ -193,6 +156,8 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq, dccp_role(sk), ntohl(opt_val), (unsigned long long) DCCP_SKB_CB(skb)->dccpd_ack_seq); + /* schedule an Ack in case this sender is quiescent */ + inet_csk_schedule_ack(sk); break; case DCCPO_TIMESTAMP_ECHO: if (len != 4 && len != 6 && len != 8) @@ -249,23 +214,25 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq, dccp_pr_debug("%s rx opt: ELAPSED_TIME=%d\n", dccp_role(sk), elapsed_time); break; - case 128 ... 191: { - const u16 idx = value - options; - + case DCCPO_MIN_RX_CCID_SPECIFIC ... DCCPO_MAX_RX_CCID_SPECIFIC: if (ccid_hc_rx_parse_options(dp->dccps_hc_rx_ccid, sk, - opt, len, idx, - value) != 0) + pkt_type, opt, value, len)) goto out_invalid_option; - } break; - case 192 ... 255: { - const u16 idx = value - options; - + case DCCPO_ACK_VECTOR_0: + case DCCPO_ACK_VECTOR_1: + if (dccp_packet_without_ack(skb)) /* RFC 4340, 11.4 */ + break; + /* + * Ack vectors are processed by the TX CCID if it is + * interested. The RX CCID need not parse Ack Vectors, + * since it is only interested in clearing old state. + * Fall through. + */ + case DCCPO_MIN_TX_CCID_SPECIFIC ... DCCPO_MAX_TX_CCID_SPECIFIC: if (ccid_hc_tx_parse_options(dp->dccps_hc_tx_ccid, sk, - opt, len, idx, - value) != 0) + pkt_type, opt, value, len)) goto out_invalid_option; - } break; default: DCCP_CRIT("DCCP(%p): option %d(len=%d) not " @@ -281,20 +248,30 @@ ignore_option: if (mandatory) goto out_invalid_option; +out_nonsensical_length: + /* RFC 4340, 5.8: ignore option and all remaining option space */ return 0; out_invalid_option: DCCP_INC_STATS_BH(DCCP_MIB_INVALIDOPT); - DCCP_SKB_CB(skb)->dccpd_reset_code = DCCP_RESET_CODE_OPTION_ERROR; - DCCP_WARN("DCCP(%p): invalid option %d, len=%d", sk, opt, len); + rc = DCCP_RESET_CODE_OPTION_ERROR; +out_featneg_failed: + DCCP_WARN("DCCP(%p): Option %d (len=%d) error=%u\n", sk, opt, len, rc); + DCCP_SKB_CB(skb)->dccpd_reset_code = rc; + DCCP_SKB_CB(skb)->dccpd_reset_data[0] = opt; + DCCP_SKB_CB(skb)->dccpd_reset_data[1] = len > 0 ? value[0] : 0; + DCCP_SKB_CB(skb)->dccpd_reset_data[2] = len > 1 ? value[1] : 0; return -1; } EXPORT_SYMBOL_GPL(dccp_parse_options); -static void dccp_encode_value_var(const u32 value, unsigned char *to, - const unsigned int len) +void dccp_encode_value_var(const u64 value, u8 *to, const u8 len) { + if (len >= DCCP_OPTVAL_MAXLEN) + *to++ = (value & 0xFF0000000000ull) >> 40; + if (len > 4) + *to++ = (value & 0xFF00000000ull) >> 32; if (len > 3) *to++ = (value & 0xFF000000) >> 24; if (len > 2) @@ -305,14 +282,15 @@ static void dccp_encode_value_var(const u32 value, unsigned char *to, *to++ = (value & 0xFF); } -static inline int dccp_ndp_len(const int ndp) +static inline u8 dccp_ndp_len(const u64 ndp) { - return likely(ndp <= 0xFF) ? 1 : ndp <= 0xFFFF ? 2 : 3; + if (likely(ndp <= 0xFF)) + return 1; + return likely(ndp <= USHRT_MAX) ? 2 : (ndp <= UINT_MAX ? 4 : 6); } -int dccp_insert_option(struct sock *sk, struct sk_buff *skb, - const unsigned char option, - const void *value, const unsigned char len) +int dccp_insert_option(struct sk_buff *skb, const unsigned char option, + const void *value, const unsigned char len) { unsigned char *to; @@ -334,7 +312,7 @@ EXPORT_SYMBOL_GPL(dccp_insert_option); static int dccp_insert_option_ndp(struct sock *sk, struct sk_buff *skb) { struct dccp_sock *dp = dccp_sk(sk); - int ndp = dp->dccps_ndp_count; + u64 ndp = dp->dccps_ndp_count; if (dccp_non_data_packet(skb)) ++dp->dccps_ndp_count; @@ -365,49 +343,15 @@ static inline int dccp_elapsed_time_len(const u32 elapsed_time) return elapsed_time == 0 ? 0 : elapsed_time <= 0xFFFF ? 2 : 4; } -int dccp_insert_option_elapsed_time(struct sock *sk, struct sk_buff *skb, - u32 elapsed_time) -{ - const int elapsed_time_len = dccp_elapsed_time_len(elapsed_time); - const int len = 2 + elapsed_time_len; - unsigned char *to; - - if (elapsed_time_len == 0) - return 0; - - if (DCCP_SKB_CB(skb)->dccpd_opt_len + len > DCCP_MAX_OPT_LEN) - return -1; - - DCCP_SKB_CB(skb)->dccpd_opt_len += len; - - to = skb_push(skb, len); - *to++ = DCCPO_ELAPSED_TIME; - *to++ = len; - - if (elapsed_time_len == 2) { - const __be16 var16 = htons((u16)elapsed_time); - memcpy(to, &var16, 2); - } else { - const __be32 var32 = htonl(elapsed_time); - memcpy(to, &var32, 4); - } - - return 0; -} - -EXPORT_SYMBOL_GPL(dccp_insert_option_elapsed_time); - -int dccp_insert_option_timestamp(struct sock *sk, struct sk_buff *skb) +static int dccp_insert_option_timestamp(struct sk_buff *skb) { __be32 now = htonl(dccp_timestamp()); /* yes this will overflow but that is the point as we want a * 10 usec 32 bit timer which mean it wraps every 11.9 hours */ - return dccp_insert_option(sk, skb, DCCPO_TIMESTAMP, &now, sizeof(now)); + return dccp_insert_option(skb, DCCPO_TIMESTAMP, &now, sizeof(now)); } -EXPORT_SYMBOL_GPL(dccp_insert_option_timestamp); - static int dccp_insert_option_timestamp_echo(struct dccp_sock *dp, struct dccp_request_sock *dreq, struct sk_buff *skb) @@ -452,92 +396,141 @@ static int dccp_insert_option_timestamp_echo(struct dccp_sock *dp, return 0; } -static int dccp_insert_feat_opt(struct sk_buff *skb, u8 type, u8 feat, - u8 *val, u8 len) +static int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb) { - u8 *to; + struct dccp_sock *dp = dccp_sk(sk); + struct dccp_ackvec *av = dp->dccps_hc_rx_ackvec; + struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb); + const u16 buflen = dccp_ackvec_buflen(av); + /* Figure out how many options do we need to represent the ackvec */ + const u8 nr_opts = DIV_ROUND_UP(buflen, DCCP_SINGLE_OPT_MAXLEN); + u16 len = buflen + 2 * nr_opts; + u8 i, nonce = 0; + const unsigned char *tail, *from; + unsigned char *to; - if (DCCP_SKB_CB(skb)->dccpd_opt_len + len + 3 > DCCP_MAX_OPT_LEN) { - DCCP_WARN("packet too small for feature %d option!\n", feat); + if (dcb->dccpd_opt_len + len > DCCP_MAX_OPT_LEN) { + DCCP_WARN("Lacking space for %u bytes on %s packet\n", len, + dccp_packet_name(dcb->dccpd_type)); return -1; } + /* + * Since Ack Vectors are variable-length, we can not always predict + * their size. To catch exception cases where the space is running out + * on the skb, a separate Sync is scheduled to carry the Ack Vector. + */ + if (len > DCCPAV_MIN_OPTLEN && + len + dcb->dccpd_opt_len + skb->len > dp->dccps_mss_cache) { + DCCP_WARN("No space left for Ack Vector (%u) on skb (%u+%u), " + "MPS=%u ==> reduce payload size?\n", len, skb->len, + dcb->dccpd_opt_len, dp->dccps_mss_cache); + dp->dccps_sync_scheduled = 1; + return 0; + } + dcb->dccpd_opt_len += len; - DCCP_SKB_CB(skb)->dccpd_opt_len += len + 3; + to = skb_push(skb, len); + len = buflen; + from = av->av_buf + av->av_buf_head; + tail = av->av_buf + DCCPAV_MAX_ACKVEC_LEN; - to = skb_push(skb, len + 3); - *to++ = type; - *to++ = len + 3; - *to++ = feat; + for (i = 0; i < nr_opts; ++i) { + int copylen = len; - if (len) - memcpy(to, val, len); + if (len > DCCP_SINGLE_OPT_MAXLEN) + copylen = DCCP_SINGLE_OPT_MAXLEN; - dccp_pr_debug("%s(%s (%d), ...), length %d\n", - dccp_feat_typename(type), - dccp_feat_name(feat), feat, len); + /* + * 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 */ + if (from + copylen > tail) { + const u16 tailsize = tail - from; + + memcpy(to, from, tailsize); + to += tailsize; + len -= tailsize; + copylen -= tailsize; + from = av->av_buf; + } + + memcpy(to, from, copylen); + from += copylen; + to += copylen; + len -= copylen; + } + /* + * Each sent Ack Vector is recorded in the list, as per A.2 of RFC 4340. + */ + if (dccp_ackvec_update_records(av, dcb->dccpd_seq, nonce)) + return -ENOBUFS; return 0; } -static int dccp_insert_options_feat(struct sock *sk, struct sk_buff *skb) +/** + * dccp_insert_option_mandatory - Mandatory option (5.8.2) + * Note that since we are using skb_push, this function needs to be called + * _after_ inserting the option it is supposed to influence (stack order). + */ +int dccp_insert_option_mandatory(struct sk_buff *skb) { - struct dccp_sock *dp = dccp_sk(sk); - struct dccp_minisock *dmsk = dccp_msk(sk); - struct dccp_opt_pend *opt, *next; - int change = 0; - - /* confirm any options [NN opts] */ - list_for_each_entry_safe(opt, next, &dmsk->dccpms_conf, dccpop_node) { - dccp_insert_feat_opt(skb, opt->dccpop_type, - opt->dccpop_feat, opt->dccpop_val, - opt->dccpop_len); - /* fear empty confirms */ - if (opt->dccpop_val) - kfree(opt->dccpop_val); - kfree(opt); - } - INIT_LIST_HEAD(&dmsk->dccpms_conf); - - /* see which features we need to send */ - list_for_each_entry(opt, &dmsk->dccpms_pending, dccpop_node) { - /* see if we need to send any confirm */ - if (opt->dccpop_sc) { - dccp_insert_feat_opt(skb, opt->dccpop_type + 1, - opt->dccpop_feat, - opt->dccpop_sc->dccpoc_val, - opt->dccpop_sc->dccpoc_len); - - BUG_ON(!opt->dccpop_sc->dccpoc_val); - kfree(opt->dccpop_sc->dccpoc_val); - kfree(opt->dccpop_sc); - opt->dccpop_sc = NULL; - } + if (DCCP_SKB_CB(skb)->dccpd_opt_len >= DCCP_MAX_OPT_LEN) + return -1; - /* any option not confirmed, re-send it */ - if (!opt->dccpop_conf) { - dccp_insert_feat_opt(skb, opt->dccpop_type, - opt->dccpop_feat, opt->dccpop_val, - opt->dccpop_len); - change++; - } + DCCP_SKB_CB(skb)->dccpd_opt_len++; + *skb_push(skb, 1) = DCCPO_MANDATORY; + return 0; +} + +/** + * dccp_insert_fn_opt - Insert single Feature-Negotiation option into @skb + * @type: %DCCPO_CHANGE_L, %DCCPO_CHANGE_R, %DCCPO_CONFIRM_L, %DCCPO_CONFIRM_R + * @feat: one out of %dccp_feature_numbers + * @val: NN value or SP array (preferred element first) to copy + * @len: true length of @val in bytes (excluding first element repetition) + * @repeat_first: whether to copy the first element of @val twice + * + * The last argument is used to construct Confirm options, where the preferred + * value and the preference list appear separately (RFC 4340, 6.3.1). Preference + * lists are kept such that the preferred entry is always first, so we only need + * to copy twice, and avoid the overhead of cloning into a bigger array. + */ +int dccp_insert_fn_opt(struct sk_buff *skb, u8 type, u8 feat, + u8 *val, u8 len, bool repeat_first) +{ + u8 tot_len, *to; + + /* take the `Feature' field and possible repetition into account */ + if (len > (DCCP_SINGLE_OPT_MAXLEN - 2)) { + DCCP_WARN("length %u for feature %u too large\n", len, feat); + return -1; } - /* Retransmit timer. - * If this is the master listening sock, we don't set a timer on it. It - * should be fine because if the dude doesn't receive our RESPONSE - * [which will contain the CHANGE] he will send another REQUEST which - * will "retrnasmit" the change. - */ - if (change && dp->dccps_role != DCCP_ROLE_LISTEN) { - dccp_pr_debug("reset feat negotiation timer %p\n", sk); + if (unlikely(val == NULL || len == 0)) + len = repeat_first = false; + tot_len = 3 + repeat_first + len; - /* XXX don't reset the timer on re-transmissions. I.e. reset it - * only when sending new stuff i guess. Currently the timer - * never backs off because on re-transmission it just resets it! - */ - inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, - inet_csk(sk)->icsk_rto, DCCP_RTO_MAX); + if (DCCP_SKB_CB(skb)->dccpd_opt_len + tot_len > DCCP_MAX_OPT_LEN) { + DCCP_WARN("packet too small for feature %d option!\n", feat); + return -1; } + DCCP_SKB_CB(skb)->dccpd_opt_len += tot_len; + to = skb_push(skb, tot_len); + *to++ = type; + *to++ = tot_len; + *to++ = feat; + + if (repeat_first) + *to++ = *val; + if (len) + memcpy(to, val, len); return 0; } @@ -556,19 +549,30 @@ 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; - if (dmsk->dccpms_send_ndp_count && - dccp_insert_option_ndp(sk, skb)) + if (dp->dccps_send_ndp_count && dccp_insert_option_ndp(sk, skb)) return -1; - if (!dccp_packet_without_ack(skb)) { - if (dmsk->dccpms_send_ack_vector && - dccp_ackvec_pending(dp->dccps_hc_rx_ackvec) && - dccp_insert_option_ackvec(sk, skb)) + if (DCCP_SKB_CB(skb)->dccpd_type != DCCP_PKT_DATA) { + + /* Feature Negotiation */ + if (dccp_feat_insert_opts(dp, NULL, skb)) return -1; + + if (DCCP_SKB_CB(skb)->dccpd_type == DCCP_PKT_REQUEST) { + /* + * Obtain RTT sample from Request/Response exchange. + * This is currently used for TFRC initialisation. + */ + if (dccp_insert_option_timestamp(skb)) + return -1; + + } else if (dccp_ackvec_pending(sk) && + dccp_insert_option_ackvec(sk, skb)) { + return -1; + } } if (dp->dccps_hc_rx_insert_options) { @@ -577,21 +581,6 @@ int dccp_insert_options(struct sock *sk, struct sk_buff *skb) dp->dccps_hc_rx_insert_options = 0; } - /* Feature negotiation */ - /* Data packets can't do feat negotiation */ - if (DCCP_SKB_CB(skb)->dccpd_type != DCCP_PKT_DATA && - DCCP_SKB_CB(skb)->dccpd_type != DCCP_PKT_DATAACK && - dccp_insert_options_feat(sk, skb)) - return -1; - - /* - * Obtain RTT sample from Request/Response exchange. - * This is currently used in CCID 3 initialisation. - */ - if (DCCP_SKB_CB(skb)->dccpd_type == DCCP_PKT_REQUEST && - dccp_insert_option_timestamp(sk, skb)) - return -1; - if (dp->dccps_timestamp_echo != 0 && dccp_insert_option_timestamp_echo(dp, NULL, skb)) return -1; @@ -604,6 +593,13 @@ int dccp_insert_options_rsk(struct dccp_request_sock *dreq, struct sk_buff *skb) { DCCP_SKB_CB(skb)->dccpd_opt_len = 0; + if (dccp_feat_insert_opts(NULL, dreq, skb)) + return -1; + + /* Obtain RTT sample from Response/Ack exchange (used by TFRC). */ + if (dccp_insert_option_timestamp(skb)) + return -1; + if (dreq->dreq_timestamp_echo != 0 && dccp_insert_option_timestamp_echo(NULL, dreq, skb)) return -1; diff --git a/net/dccp/output.c b/net/dccp/output.c index 3b763db3d86..0248e8a3460 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -13,6 +13,7 @@ #include <linux/dccp.h> #include <linux/kernel.h> #include <linux/skbuff.h> +#include <linux/slab.h> #include <net/inet_sock.h> #include <net/sock.h> @@ -26,11 +27,13 @@ static inline void dccp_event_ack_sent(struct sock *sk) inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK); } -static void dccp_skb_entail(struct sock *sk, struct sk_buff *skb) +/* enqueue @skb on sk_send_head for retransmission, return clone to send now */ +static struct sk_buff *dccp_skb_entail(struct sock *sk, struct sk_buff *skb) { skb_set_owner_w(skb, sk); WARN_ON(sk->sk_send_head); sk->sk_send_head = skb; + return skb_clone(sk->sk_send_head, gfp_any()); } /* @@ -42,7 +45,7 @@ static void dccp_skb_entail(struct sock *sk, struct sk_buff *skb) static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb) { if (likely(skb != NULL)) { - const struct inet_sock *inet = inet_sk(sk); + struct inet_sock *inet = inet_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); struct dccp_sock *dp = dccp_sk(sk); struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb); @@ -53,8 +56,11 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb) dccp_packet_hdr_len(dcb->dccpd_type); int err, set_ack = 1; u64 ackno = dp->dccps_gsr; - - dccp_inc_seqno(&dp->dccps_gss); + /* + * Increment GSS here already in case the option code needs it. + * Update GSS for real only if option processing below succeeds. + */ + dcb->dccpd_seq = ADD48(dp->dccps_gss, 1); switch (dcb->dccpd_type) { case DCCP_PKT_DATA: @@ -66,6 +72,9 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb) case DCCP_PKT_REQUEST: set_ack = 0; + /* Use ISS on the first (non-retransmitted) Request. */ + if (icsk->icsk_retransmits == 0) + dcb->dccpd_seq = dp->dccps_iss; /* fall through */ case DCCP_PKT_SYNC: @@ -84,8 +93,6 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb) break; } - dcb->dccpd_seq = dp->dccps_gss; - if (dccp_insert_options(sk, skb)) { kfree_skb(skb); return -EPROTO; @@ -95,15 +102,15 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb) /* Build DCCP header and checksum it. */ dh = dccp_zeroed_hdr(skb, dccp_header_size); dh->dccph_type = dcb->dccpd_type; - dh->dccph_sport = inet->sport; - dh->dccph_dport = inet->dport; + dh->dccph_sport = inet->inet_sport; + dh->dccph_dport = inet->inet_dport; dh->dccph_doff = (dccp_header_size + dcb->dccpd_opt_len) / 4; dh->dccph_ccval = dcb->dccpd_ccval; dh->dccph_cscov = dp->dccps_pcslen; /* XXX For now we're using only 48 bits sequence numbers */ dh->dccph_x = 1; - dp->dccps_awh = dp->dccps_gss; + dccp_update_gss(sk, dcb->dccpd_seq); dccp_hdr_set_seq(dh, dp->dccps_gss); if (set_ack) dccp_hdr_set_ack(dccp_hdr_ack_bits(skb), ackno); @@ -112,6 +119,11 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb) case DCCP_PKT_REQUEST: dccp_hdr_request(skb)->dccph_req_service = dp->dccps_service; + /* + * Limit Ack window to ISS <= P.ackno <= GSS, so that + * only Responses to Requests we sent are considered. + */ + dp->dccps_awl = dp->dccps_iss; break; case DCCP_PKT_RESET: dccp_hdr_reset(skb)->dccph_reset_code = @@ -119,22 +131,21 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb) break; } - icsk->icsk_af_ops->send_check(sk, 0, skb); + icsk->icsk_af_ops->send_check(sk, skb); if (set_ack) dccp_event_ack_sent(sk); DCCP_INC_STATS(DCCP_MIB_OUTSEGS); - memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); - err = icsk->icsk_af_ops->queue_xmit(skb, 0); + err = icsk->icsk_af_ops->queue_xmit(sk, skb, &inet->cork.fl); return net_xmit_eval(err); } return -ENOBUFS; } /** - * dccp_determine_ccmps - Find out about CCID-specfic packet-size limits + * dccp_determine_ccmps - Find out about CCID-specific packet-size limits * We only consider the HC-sender CCID for setting the CCMPS (RFC 4340, 14.), * since the RX CCID is restricted to feedback packets (Acks), which are small * in comparison with the data traffic. A value of 0 means "no current CCMPS". @@ -153,21 +164,27 @@ unsigned int dccp_sync_mss(struct sock *sk, u32 pmtu) struct inet_connection_sock *icsk = inet_csk(sk); struct dccp_sock *dp = dccp_sk(sk); u32 ccmps = dccp_determine_ccmps(dp); - int cur_mps = ccmps ? min(pmtu, ccmps) : pmtu; + u32 cur_mps = ccmps ? min(pmtu, ccmps) : pmtu; /* Account for header lengths and IPv4/v6 option overhead */ cur_mps -= (icsk->icsk_af_ops->net_header_len + icsk->icsk_ext_hdr_len + sizeof(struct dccp_hdr) + sizeof(struct dccp_hdr_ext)); /* - * FIXME: this should come from the CCID infrastructure, where, say, - * TFRC will say it wants TIMESTAMPS, ELAPSED time, etc, for now lets - * put a rough estimate for NDP + TIMESTAMP + TIMESTAMP_ECHO + ELAPSED - * TIME + TFRC_OPT_LOSS_EVENT_RATE + TFRC_OPT_RECEIVE_RATE + padding to - * make it a multiple of 4 + * Leave enough headroom for common DCCP header options. + * This only considers options which may appear on DCCP-Data packets, as + * per table 3 in RFC 4340, 5.8. When running out of space for other + * options (eg. Ack Vector which can take up to 255 bytes), it is better + * to schedule a separate Ack. Thus we leave headroom for the following: + * - 1 byte for Slow Receiver (11.6) + * - 6 bytes for Timestamp (13.1) + * - 10 bytes for Timestamp Echo (13.3) + * - 8 bytes for NDP count (7.7, when activated) + * - 6 bytes for Data Checksum (9.3) + * - %DCCPAV_MIN_OPTLEN bytes for Ack Vector size (11.4, when enabled) */ - - cur_mps -= ((5 + 6 + 10 + 6 + 6 + 6 + 3) / 4) * 4; + cur_mps -= roundup(1 + 6 + 10 + dp->dccps_send_ndp_count * 8 + 6 + + (dp->dccps_hc_rx_ackvec ? DCCPAV_MIN_OPTLEN : 0), 4); /* And store cached results */ icsk->icsk_pmtu_cookie = pmtu; @@ -180,119 +197,197 @@ EXPORT_SYMBOL_GPL(dccp_sync_mss); void dccp_write_space(struct sock *sk) { - read_lock(&sk->sk_callback_lock); + struct socket_wq *wq; - if (sk->sk_sleep && waitqueue_active(sk->sk_sleep)) - wake_up_interruptible(sk->sk_sleep); + rcu_read_lock(); + wq = rcu_dereference(sk->sk_wq); + if (wq_has_sleeper(wq)) + wake_up_interruptible(&wq->wait); /* Should agree with poll, otherwise some programs break */ if (sock_writeable(sk)) sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT); - read_unlock(&sk->sk_callback_lock); + rcu_read_unlock(); } /** - * dccp_wait_for_ccid - Wait for ccid to tell us we can send a packet + * dccp_wait_for_ccid - Await CCID send permission * @sk: socket to wait for - * @skb: current skb to pass on for waiting - * @delay: sleep timeout in milliseconds (> 0) - * This function is called by default when the socket is closed, and - * when a non-zero linger time is set on the socket. For consistency + * @delay: timeout in jiffies + * + * This is used by CCIDs which need to delay the send time in process context. */ -static int dccp_wait_for_ccid(struct sock *sk, struct sk_buff *skb, int delay) +static int dccp_wait_for_ccid(struct sock *sk, unsigned long delay) { - struct dccp_sock *dp = dccp_sk(sk); DEFINE_WAIT(wait); - unsigned long jiffdelay; - int rc; + long remaining; - do { - dccp_pr_debug("delayed send by %d msec\n", delay); - jiffdelay = msecs_to_jiffies(delay); + prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); + sk->sk_write_pending++; + release_sock(sk); - prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE); + remaining = schedule_timeout(delay); - sk->sk_write_pending++; - release_sock(sk); - schedule_timeout(jiffdelay); - lock_sock(sk); - sk->sk_write_pending--; + lock_sock(sk); + sk->sk_write_pending--; + finish_wait(sk_sleep(sk), &wait); - if (sk->sk_err) - goto do_error; - if (signal_pending(current)) - goto do_interrupted; + if (signal_pending(current) || sk->sk_err) + return -1; + return remaining; +} - rc = ccid_hc_tx_send_packet(dp->dccps_hc_tx_ccid, sk, skb); - } while ((delay = rc) > 0); -out: - finish_wait(sk->sk_sleep, &wait); - return rc; - -do_error: - rc = -EPIPE; - goto out; -do_interrupted: - rc = -EINTR; - goto out; +/** + * dccp_xmit_packet - Send data packet under control of CCID + * Transmits next-queued payload and informs CCID to account for the packet. + */ +static void dccp_xmit_packet(struct sock *sk) +{ + int err, len; + struct dccp_sock *dp = dccp_sk(sk); + struct sk_buff *skb = dccp_qpolicy_pop(sk); + + if (unlikely(skb == NULL)) + return; + len = skb->len; + + if (sk->sk_state == DCCP_PARTOPEN) { + const u32 cur_mps = dp->dccps_mss_cache - DCCP_FEATNEG_OVERHEAD; + /* + * See 8.1.5 - Handshake Completion. + * + * For robustness we resend Confirm options until the client has + * entered OPEN. During the initial feature negotiation, the MPS + * is smaller than usual, reduced by the Change/Confirm options. + */ + if (!list_empty(&dp->dccps_featneg) && len > cur_mps) { + DCCP_WARN("Payload too large (%d) for featneg.\n", len); + dccp_send_ack(sk); + dccp_feat_list_purge(&dp->dccps_featneg); + } + + inet_csk_schedule_ack(sk); + inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK, + inet_csk(sk)->icsk_rto, + DCCP_RTO_MAX); + DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_DATAACK; + } else if (dccp_ack_pending(sk)) { + DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_DATAACK; + } else { + DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_DATA; + } + + err = dccp_transmit_skb(sk, skb); + if (err) + dccp_pr_debug("transmit_skb() returned err=%d\n", err); + /* + * Register this one as sent even if an error occurred. To the remote + * end a local packet drop is indistinguishable from network loss, i.e. + * any local drop will eventually be reported via receiver feedback. + */ + ccid_hc_tx_packet_sent(dp->dccps_hc_tx_ccid, sk, len); + + /* + * If the CCID needs to transfer additional header options out-of-band + * (e.g. Ack Vectors or feature-negotiation options), it activates this + * flag to schedule a Sync. The Sync will automatically incorporate all + * currently pending header options, thus clearing the backlog. + */ + if (dp->dccps_sync_scheduled) + dccp_send_sync(sk, dp->dccps_gsr, DCCP_PKT_SYNC); } -void dccp_write_xmit(struct sock *sk, int block) +/** + * dccp_flush_write_queue - Drain queue at end of connection + * Since dccp_sendmsg queues packets without waiting for them to be sent, it may + * happen that the TX queue is not empty at the end of a connection. We give the + * HC-sender CCID a grace period of up to @time_budget jiffies. If this function + * returns with a non-empty write queue, it will be purged later. + */ +void dccp_flush_write_queue(struct sock *sk, long *time_budget) { struct dccp_sock *dp = dccp_sk(sk); struct sk_buff *skb; + long delay, rc; + + while (*time_budget > 0 && (skb = skb_peek(&sk->sk_write_queue))) { + rc = ccid_hc_tx_send_packet(dp->dccps_hc_tx_ccid, sk, skb); - while ((skb = skb_peek(&sk->sk_write_queue))) { - int err = ccid_hc_tx_send_packet(dp->dccps_hc_tx_ccid, sk, skb); - - if (err > 0) { - if (!block) { - sk_reset_timer(sk, &dp->dccps_xmit_timer, - msecs_to_jiffies(err)+jiffies); - break; - } else - err = dccp_wait_for_ccid(sk, skb, err); - if (err && err != -EINTR) - DCCP_BUG("err=%d after dccp_wait_for_ccid", err); + switch (ccid_packet_dequeue_eval(rc)) { + case CCID_PACKET_WILL_DEQUEUE_LATER: + /* + * If the CCID determines when to send, the next sending + * time is unknown or the CCID may not even send again + * (e.g. remote host crashes or lost Ack packets). + */ + DCCP_WARN("CCID did not manage to send all packets\n"); + return; + case CCID_PACKET_DELAY: + delay = msecs_to_jiffies(rc); + if (delay > *time_budget) + return; + rc = dccp_wait_for_ccid(sk, delay); + if (rc < 0) + return; + *time_budget -= (delay - rc); + /* check again if we can send now */ + break; + case CCID_PACKET_SEND_AT_ONCE: + dccp_xmit_packet(sk); + break; + case CCID_PACKET_ERR: + skb_dequeue(&sk->sk_write_queue); + kfree_skb(skb); + dccp_pr_debug("packet discarded due to err=%ld\n", rc); } + } +} + +void dccp_write_xmit(struct sock *sk) +{ + struct dccp_sock *dp = dccp_sk(sk); + struct sk_buff *skb; - skb_dequeue(&sk->sk_write_queue); - if (err == 0) { - struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb); - const int len = skb->len; + while ((skb = dccp_qpolicy_top(sk))) { + int rc = ccid_hc_tx_send_packet(dp->dccps_hc_tx_ccid, sk, skb); - if (sk->sk_state == DCCP_PARTOPEN) { - /* See 8.1.5. Handshake Completion */ - inet_csk_schedule_ack(sk); - inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK, - inet_csk(sk)->icsk_rto, - DCCP_RTO_MAX); - dcb->dccpd_type = DCCP_PKT_DATAACK; - } else if (dccp_ack_pending(sk)) - dcb->dccpd_type = DCCP_PKT_DATAACK; - else - dcb->dccpd_type = DCCP_PKT_DATA; - - err = dccp_transmit_skb(sk, skb); - ccid_hc_tx_packet_sent(dp->dccps_hc_tx_ccid, sk, 0, len); - if (err) - DCCP_BUG("err=%d after ccid_hc_tx_packet_sent", - err); - } else { - dccp_pr_debug("packet discarded due to err=%d\n", err); - kfree_skb(skb); + switch (ccid_packet_dequeue_eval(rc)) { + case CCID_PACKET_WILL_DEQUEUE_LATER: + return; + case CCID_PACKET_DELAY: + sk_reset_timer(sk, &dp->dccps_xmit_timer, + jiffies + msecs_to_jiffies(rc)); + return; + case CCID_PACKET_SEND_AT_ONCE: + dccp_xmit_packet(sk); + break; + case CCID_PACKET_ERR: + dccp_qpolicy_drop(sk, skb); + dccp_pr_debug("packet discarded due to err=%d\n", rc); } } } -int dccp_retransmit_skb(struct sock *sk, struct sk_buff *skb) +/** + * dccp_retransmit_skb - Retransmit Request, Close, or CloseReq packets + * There are only four retransmittable packet types in DCCP: + * - Request in client-REQUEST state (sec. 8.1.1), + * - CloseReq in server-CLOSEREQ state (sec. 8.3), + * - Close in node-CLOSING state (sec. 8.3), + * - Acks in client-PARTOPEN state (sec. 8.1.5, handled by dccp_delack_timer()). + * This function expects sk->sk_send_head to contain the original skb. + */ +int dccp_retransmit_skb(struct sock *sk) { + WARN_ON(sk->sk_send_head == NULL); + if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk) != 0) return -EHOSTUNREACH; /* Routing failure or similar. */ - return dccp_transmit_skb(sk, (skb_cloned(skb) ? - pskb_copy(skb, GFP_ATOMIC): - skb_clone(skb, GFP_ATOMIC))); + /* this count is used to distinguish original and retransmitted skb */ + inet_csk(sk)->icsk_retransmits++; + + return dccp_transmit_skb(sk, skb_clone(sk->sk_send_head, GFP_ATOMIC)); } struct sk_buff *dccp_make_response(struct sock *sk, struct dst_entry *dst, @@ -311,30 +406,32 @@ struct sk_buff *dccp_make_response(struct sock *sk, struct dst_entry *dst, /* Reserve space for headers. */ skb_reserve(skb, sk->sk_prot->max_header); - skb->dst = dst_clone(dst); + skb_dst_set(skb, dst_clone(dst)); dreq = dccp_rsk(req); - if (inet_rsk(req)->acked) /* increase ISS upon retransmission */ - dccp_inc_seqno(&dreq->dreq_iss); + if (inet_rsk(req)->acked) /* increase GSS upon retransmission */ + dccp_inc_seqno(&dreq->dreq_gss); DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_RESPONSE; - DCCP_SKB_CB(skb)->dccpd_seq = dreq->dreq_iss; + DCCP_SKB_CB(skb)->dccpd_seq = dreq->dreq_gss; - if (dccp_insert_options_rsk(dreq, skb)) { - kfree_skb(skb); - return NULL; - } + /* Resolve feature dependencies resulting from choice of CCID */ + if (dccp_feat_server_ccid_dependencies(dreq)) + goto response_failed; + + if (dccp_insert_options_rsk(dreq, skb)) + goto response_failed; /* Build and checksum header */ dh = dccp_zeroed_hdr(skb, dccp_header_size); - dh->dccph_sport = inet_sk(sk)->sport; - dh->dccph_dport = inet_rsk(req)->rmt_port; + dh->dccph_sport = htons(inet_rsk(req)->ir_num); + dh->dccph_dport = inet_rsk(req)->ir_rmt_port; dh->dccph_doff = (dccp_header_size + DCCP_SKB_CB(skb)->dccpd_opt_len) / 4; dh->dccph_type = DCCP_PKT_RESPONSE; dh->dccph_x = 1; - dccp_hdr_set_seq(dh, dreq->dreq_iss); - dccp_hdr_set_ack(dccp_hdr_ack_bits(skb), dreq->dreq_isr); + dccp_hdr_set_seq(dh, dreq->dreq_gss); + dccp_hdr_set_ack(dccp_hdr_ack_bits(skb), dreq->dreq_gsr); dccp_hdr_response(skb)->dccph_resp_service = dreq->dreq_service; dccp_csum_outgoing(skb); @@ -343,12 +440,15 @@ struct sk_buff *dccp_make_response(struct sock *sk, struct dst_entry *dst, inet_rsk(req)->acked = 1; DCCP_INC_STATS(DCCP_MIB_OUTSEGS); return skb; +response_failed: + kfree_skb(skb); + return NULL; } EXPORT_SYMBOL_GPL(dccp_make_response); /* answer offending packet in @rcv_skb with Reset from control socket @ctl */ -struct sk_buff *dccp_ctl_make_reset(struct socket *ctl, struct sk_buff *rcv_skb) +struct sk_buff *dccp_ctl_make_reset(struct sock *sk, struct sk_buff *rcv_skb) { struct dccp_hdr *rxdh = dccp_hdr(rcv_skb), *dh; struct dccp_skb_cb *dcb = DCCP_SKB_CB(rcv_skb); @@ -358,11 +458,11 @@ struct sk_buff *dccp_ctl_make_reset(struct socket *ctl, struct sk_buff *rcv_skb) struct dccp_hdr_reset *dhr; struct sk_buff *skb; - skb = alloc_skb(ctl->sk->sk_prot->max_header, GFP_ATOMIC); + skb = alloc_skb(sk->sk_prot->max_header, GFP_ATOMIC); if (skb == NULL) return NULL; - skb_reserve(skb, ctl->sk->sk_prot->max_header); + skb_reserve(skb, sk->sk_prot->max_header); /* Swap the send and the receive. */ dh = dccp_zeroed_hdr(skb, dccp_hdr_reset_len); @@ -427,8 +527,9 @@ int dccp_send_reset(struct sock *sk, enum dccp_reset_codes code) /* * Do all connect socket setups that can be done AF independent. */ -static inline void dccp_connect_init(struct sock *sk) +int dccp_connect(struct sock *sk) { + struct sk_buff *skb; struct dccp_sock *dp = dccp_sk(sk); struct dst_entry *dst = __sk_dst_get(sk); struct inet_connection_sock *icsk = inet_csk(sk); @@ -438,31 +539,13 @@ static inline void dccp_connect_init(struct sock *sk) dccp_sync_mss(sk, dst_mtu(dst)); - /* - * 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. - */ - dccp_update_gss(sk, dp->dccps_iss); - dccp_set_seqno(&dp->dccps_awl, max48(dp->dccps_awl, dp->dccps_iss)); + /* do not connect if feature negotiation setup fails */ + if (dccp_feat_finalise_settings(dccp_sk(sk))) + return -EPROTO; - /* S.GAR - greatest valid acknowledgement number received on a non-Sync; - * initialized to S.ISS (sec. 8.5) */ + /* Initialise GAR as per 8.5; AWL/AWH are set in dccp_transmit_skb() */ dp->dccps_gar = dp->dccps_iss; - icsk->icsk_retransmits = 0; -} - -int dccp_connect(struct sock *sk) -{ - struct sk_buff *skb; - struct inet_connection_sock *icsk = inet_csk(sk); - - dccp_connect_init(sk); - skb = alloc_skb(sk->sk_prot->max_header, sk->sk_allocation); if (unlikely(skb == NULL)) return -ENOBUFS; @@ -472,11 +555,11 @@ int dccp_connect(struct sock *sk) DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_REQUEST; - dccp_skb_entail(sk, skb); - dccp_transmit_skb(sk, skb_clone(skb, GFP_KERNEL)); + dccp_transmit_skb(sk, dccp_skb_entail(sk, skb)); DCCP_INC_STATS(DCCP_MIB_ACTIVEOPENS); /* Timer for repeating the REQUEST until an answer. */ + icsk->icsk_retransmits = 0; inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, icsk->icsk_rto, DCCP_RTO_MAX); return 0; @@ -509,6 +592,7 @@ void dccp_send_ack(struct sock *sk) EXPORT_SYMBOL_GPL(dccp_send_ack); +#if 0 /* FIXME: Is this still necessary (11.3) - currently nowhere used by DCCP. */ void dccp_send_delayed_ack(struct sock *sk) { @@ -539,6 +623,7 @@ void dccp_send_delayed_ack(struct sock *sk) icsk->icsk_ack.timeout = timeout; sk_reset_timer(sk, &icsk->icsk_delack_timer, timeout); } +#endif void dccp_send_sync(struct sock *sk, const u64 ackno, const enum dccp_pkt_type pkt_type) @@ -561,6 +646,12 @@ void dccp_send_sync(struct sock *sk, const u64 ackno, DCCP_SKB_CB(skb)->dccpd_type = pkt_type; DCCP_SKB_CB(skb)->dccpd_ack_seq = ackno; + /* + * Clear the flag in case the Sync was scheduled for out-of-band data, + * such as carrying a long Ack Vector. + */ + dccp_sk(sk)->dccps_sync_scheduled = 0; + dccp_transmit_skb(sk, skb); } @@ -589,9 +680,7 @@ void dccp_send_close(struct sock *sk, const int active) DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_CLOSE; if (active) { - dccp_write_xmit(sk, 1); - dccp_skb_entail(sk, skb); - dccp_transmit_skb(sk, skb_clone(skb, prio)); + skb = dccp_skb_entail(sk, skb); /* * Retransmission timer for active-close: RFC 4340, 8.3 requires * to retransmit the Close/CloseReq until the CLOSING/CLOSEREQ @@ -604,6 +693,6 @@ void dccp_send_close(struct sock *sk, const int active) */ inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, DCCP_TIMEOUT_INIT, DCCP_RTO_MAX); - } else - dccp_transmit_skb(sk, skb); + } + dccp_transmit_skb(sk, skb); } diff --git a/net/dccp/probe.c b/net/dccp/probe.c index 7053bb827bc..595ddf0459d 100644 --- a/net/dccp/probe.c +++ b/net/dccp/probe.c @@ -30,6 +30,7 @@ #include <linux/module.h> #include <linux/kfifo.h> #include <linux/vmalloc.h> +#include <linux/gfp.h> #include <net/net_namespace.h> #include "dccp.h" @@ -42,67 +43,58 @@ static int bufsize = 64 * 1024; static const char procname[] = "dccpprobe"; -struct { - struct kfifo *fifo; +static struct { + struct kfifo fifo; spinlock_t lock; wait_queue_head_t wait; - struct timeval tstart; + struct timespec tstart; } dccpw; static void printl(const char *fmt, ...) { va_list args; int len; - struct timeval now; + struct timespec now; char tbuf[256]; va_start(args, fmt); - do_gettimeofday(&now); + getnstimeofday(&now); - now.tv_sec -= dccpw.tstart.tv_sec; - now.tv_usec -= dccpw.tstart.tv_usec; - if (now.tv_usec < 0) { - --now.tv_sec; - now.tv_usec += 1000000; - } + now = timespec_sub(now, dccpw.tstart); len = sprintf(tbuf, "%lu.%06lu ", (unsigned long) now.tv_sec, - (unsigned long) now.tv_usec); + (unsigned long) now.tv_nsec / NSEC_PER_USEC); len += vscnprintf(tbuf+len, sizeof(tbuf)-len, fmt, args); va_end(args); - kfifo_put(dccpw.fifo, tbuf, len); + kfifo_in_locked(&dccpw.fifo, tbuf, len, &dccpw.lock); wake_up(&dccpw.wait); } static int jdccp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t size) { - const struct dccp_minisock *dmsk = dccp_msk(sk); const struct inet_sock *inet = inet_sk(sk); - const struct ccid3_hc_tx_sock *hctx; - - if (dmsk->dccpms_tx_ccid == DCCPC_CCID3) - hctx = ccid3_hc_tx_sk(sk); - else - hctx = NULL; - - if (port == 0 || ntohs(inet->dport) == port || - ntohs(inet->sport) == port) { - if (hctx) - printl("%d.%d.%d.%d:%u %d.%d.%d.%d:%u %d %d %d %d %u " - "%llu %llu %d\n", - NIPQUAD(inet->saddr), ntohs(inet->sport), - NIPQUAD(inet->daddr), ntohs(inet->dport), size, - hctx->ccid3hctx_s, hctx->ccid3hctx_rtt, - hctx->ccid3hctx_p, hctx->ccid3hctx_x_calc, - hctx->ccid3hctx_x_recv >> 6, - hctx->ccid3hctx_x >> 6, hctx->ccid3hctx_t_ipi); + struct ccid3_hc_tx_sock *hc = NULL; + + if (ccid_get_current_tx_ccid(dccp_sk(sk)) == DCCPC_CCID3) + hc = ccid3_hc_tx_sk(sk); + + if (port == 0 || ntohs(inet->inet_dport) == port || + ntohs(inet->inet_sport) == port) { + if (hc) + printl("%pI4:%u %pI4:%u %d %d %d %d %u %llu %llu %d\n", + &inet->inet_saddr, ntohs(inet->inet_sport), + &inet->inet_daddr, ntohs(inet->inet_dport), size, + hc->tx_s, hc->tx_rtt, hc->tx_p, + hc->tx_x_calc, hc->tx_x_recv >> 6, + hc->tx_x >> 6, hc->tx_t_ipi); else - printl("%d.%d.%d.%d:%u %d.%d.%d.%d:%u %d\n", - NIPQUAD(inet->saddr), ntohs(inet->sport), - NIPQUAD(inet->daddr), ntohs(inet->dport), size); + printl("%pI4:%u %pI4:%u %d\n", + &inet->inet_saddr, ntohs(inet->inet_sport), + &inet->inet_daddr, ntohs(inet->inet_dport), + size); } jprobe_return(); @@ -118,8 +110,8 @@ static struct jprobe dccp_send_probe = { static int dccpprobe_open(struct inode *inode, struct file *file) { - kfifo_reset(dccpw.fifo); - do_gettimeofday(&dccpw.tstart); + kfifo_reset(&dccpw.fifo); + getnstimeofday(&dccpw.tstart); return 0; } @@ -140,12 +132,12 @@ static ssize_t dccpprobe_read(struct file *file, char __user *buf, return -ENOMEM; error = wait_event_interruptible(dccpw.wait, - __kfifo_len(dccpw.fifo) != 0); + kfifo_len(&dccpw.fifo) != 0); if (error) goto out_free; - cnt = kfifo_get(dccpw.fifo, tbuf, len); - error = copy_to_user(buf, tbuf, cnt); + cnt = kfifo_out_locked(&dccpw.fifo, tbuf, len, &dccpw.lock); + error = copy_to_user(buf, tbuf, cnt) ? -EFAULT : 0; out_free: vfree(tbuf); @@ -157,6 +149,7 @@ static const struct file_operations dccpprobe_fops = { .owner = THIS_MODULE, .open = dccpprobe_open, .read = dccpprobe_read, + .llseek = noop_llseek, }; static __init int dccpprobe_init(void) @@ -165,31 +158,35 @@ static __init int dccpprobe_init(void) init_waitqueue_head(&dccpw.wait); spin_lock_init(&dccpw.lock); - dccpw.fifo = kfifo_alloc(bufsize, GFP_KERNEL, &dccpw.lock); - if (IS_ERR(dccpw.fifo)) - return PTR_ERR(dccpw.fifo); - - if (!proc_net_fops_create(&init_net, procname, S_IRUSR, &dccpprobe_fops)) + if (kfifo_alloc(&dccpw.fifo, bufsize, GFP_KERNEL)) + return ret; + if (!proc_create(procname, S_IRUSR, init_net.proc_net, &dccpprobe_fops)) goto err0; ret = register_jprobe(&dccp_send_probe); + if (ret) { + ret = request_module("dccp"); + if (!ret) + ret = register_jprobe(&dccp_send_probe); + } + if (ret) goto err1; pr_info("DCCP watch registered (port=%d)\n", port); return 0; err1: - proc_net_remove(&init_net, procname); + remove_proc_entry(procname, init_net.proc_net); err0: - kfifo_free(dccpw.fifo); + kfifo_free(&dccpw.fifo); return ret; } module_init(dccpprobe_init); static __exit void dccpprobe_exit(void) { - kfifo_free(dccpw.fifo); - proc_net_remove(&init_net, procname); + kfifo_free(&dccpw.fifo); + remove_proc_entry(procname, init_net.proc_net); unregister_jprobe(&dccp_send_probe); } diff --git a/net/dccp/proto.c b/net/dccp/proto.c index e3f5d37b84b..de2c1e71930 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -20,6 +20,7 @@ #include <linux/if_arp.h> #include <linux/init.h> #include <linux/random.h> +#include <linux/slab.h> #include <net/checksum.h> #include <net/inet_sock.h> @@ -27,7 +28,6 @@ #include <net/xfrm.h> #include <asm/ioctls.h> -#include <asm/semaphore.h> #include <linux/spinlock.h> #include <linux/timer.h> #include <linux/delay.h> @@ -41,21 +41,39 @@ DEFINE_SNMP_STAT(struct dccp_mib, dccp_statistics) __read_mostly; EXPORT_SYMBOL_GPL(dccp_statistics); -atomic_t dccp_orphan_count = ATOMIC_INIT(0); - +struct percpu_counter dccp_orphan_count; EXPORT_SYMBOL_GPL(dccp_orphan_count); -struct inet_hashinfo __cacheline_aligned dccp_hashinfo = { - .lhash_lock = RW_LOCK_UNLOCKED, - .lhash_users = ATOMIC_INIT(0), - .lhash_wait = __WAIT_QUEUE_HEAD_INITIALIZER(dccp_hashinfo.lhash_wait), -}; - +struct inet_hashinfo dccp_hashinfo; EXPORT_SYMBOL_GPL(dccp_hashinfo); /* the maximum queue length for tx in packets. 0 is no limit */ int sysctl_dccp_tx_qlen __read_mostly = 5; +#ifdef CONFIG_IP_DCCP_DEBUG +static const char *dccp_state_name(const int state) +{ + static const char *const dccp_state_names[] = { + [DCCP_OPEN] = "OPEN", + [DCCP_REQUESTING] = "REQUESTING", + [DCCP_PARTOPEN] = "PARTOPEN", + [DCCP_LISTEN] = "LISTEN", + [DCCP_RESPOND] = "RESPOND", + [DCCP_CLOSING] = "CLOSING", + [DCCP_ACTIVE_CLOSEREQ] = "CLOSEREQ", + [DCCP_PASSIVE_CLOSE] = "PASSIVE_CLOSE", + [DCCP_PASSIVE_CLOSEREQ] = "PASSIVE_CLOSEREQ", + [DCCP_TIME_WAIT] = "TIME_WAIT", + [DCCP_CLOSED] = "CLOSED", + }; + + if (state >= DCCP_MAX_STATES) + return "INVALID STATE!"; + else + return dccp_state_names[state]; +} +#endif + void dccp_set_state(struct sock *sk, const int state) { const int oldstate = sk->sk_state; @@ -68,6 +86,9 @@ void dccp_set_state(struct sock *sk, const int state) case DCCP_OPEN: if (oldstate != DCCP_OPEN) DCCP_INC_STATS(DCCP_MIB_CURRESTAB); + /* Client retransmits all Confirm options until entering OPEN */ + if (oldstate == DCCP_PARTOPEN) + dccp_feat_list_purge(&dccp_sk(sk)->dccps_featneg); break; case DCCP_CLOSED: @@ -128,7 +149,7 @@ EXPORT_SYMBOL_GPL(dccp_done); const char *dccp_packet_name(const int type) { - static const char *dccp_packet_names[] = { + static const char *const dccp_packet_names[] = { [DCCP_PKT_REQUEST] = "REQUEST", [DCCP_PKT_RESPONSE] = "RESPONSE", [DCCP_PKT_DATA] = "DATA", @@ -149,38 +170,11 @@ const char *dccp_packet_name(const int type) EXPORT_SYMBOL_GPL(dccp_packet_name); -const char *dccp_state_name(const int state) -{ - static char *dccp_state_names[] = { - [DCCP_OPEN] = "OPEN", - [DCCP_REQUESTING] = "REQUESTING", - [DCCP_PARTOPEN] = "PARTOPEN", - [DCCP_LISTEN] = "LISTEN", - [DCCP_RESPOND] = "RESPOND", - [DCCP_CLOSING] = "CLOSING", - [DCCP_ACTIVE_CLOSEREQ] = "CLOSEREQ", - [DCCP_PASSIVE_CLOSE] = "PASSIVE_CLOSE", - [DCCP_PASSIVE_CLOSEREQ] = "PASSIVE_CLOSEREQ", - [DCCP_TIME_WAIT] = "TIME_WAIT", - [DCCP_CLOSED] = "CLOSED", - }; - - if (state >= DCCP_MAX_STATES) - return "INVALID STATE!"; - else - return dccp_state_names[state]; -} - -EXPORT_SYMBOL_GPL(dccp_state_name); - int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized) { struct dccp_sock *dp = dccp_sk(sk); - struct dccp_minisock *dmsk = dccp_msk(sk); struct inet_connection_sock *icsk = inet_csk(sk); - dccp_minisock_init(&dp->dccps_minisock); - icsk->icsk_rto = DCCP_TIMEOUT_INIT; icsk->icsk_syn_retries = sysctl_dccp_request_retries; sk->sk_state = DCCP_CLOSED; @@ -190,58 +184,22 @@ int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized) dp->dccps_rate_last = jiffies; dp->dccps_role = DCCP_ROLE_UNDEFINED; dp->dccps_service = DCCP_SERVICE_CODE_IS_ABSENT; - dp->dccps_l_ack_ratio = dp->dccps_r_ack_ratio = 1; + dp->dccps_tx_qlen = sysctl_dccp_tx_qlen; dccp_init_xmit_timers(sk); - /* - * FIXME: We're hardcoding the CCID, and doing this at this point makes - * the listening (master) sock get CCID control blocks, which is not - * necessary, but for now, to not mess with the test userspace apps, - * lets leave it here, later the real solution is to do this in a - * setsockopt(CCIDs-I-want/accept). -acme - */ - if (likely(ctl_sock_initialized)) { - int rc = dccp_feat_init(dmsk); - - if (rc) - return rc; - - if (dmsk->dccpms_send_ack_vector) { - dp->dccps_hc_rx_ackvec = dccp_ackvec_alloc(GFP_KERNEL); - if (dp->dccps_hc_rx_ackvec == NULL) - return -ENOMEM; - } - dp->dccps_hc_rx_ccid = ccid_hc_rx_new(dmsk->dccpms_rx_ccid, - sk, GFP_KERNEL); - dp->dccps_hc_tx_ccid = ccid_hc_tx_new(dmsk->dccpms_tx_ccid, - sk, GFP_KERNEL); - if (unlikely(dp->dccps_hc_rx_ccid == NULL || - dp->dccps_hc_tx_ccid == NULL)) { - ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk); - ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk); - if (dmsk->dccpms_send_ack_vector) { - dccp_ackvec_free(dp->dccps_hc_rx_ackvec); - dp->dccps_hc_rx_ackvec = NULL; - } - dp->dccps_hc_rx_ccid = dp->dccps_hc_tx_ccid = NULL; - return -ENOMEM; - } - } else { - /* control socket doesn't need feat nego */ - INIT_LIST_HEAD(&dmsk->dccpms_pending); - INIT_LIST_HEAD(&dmsk->dccpms_conf); - } - + INIT_LIST_HEAD(&dp->dccps_featneg); + /* control socket doesn't need feat nego */ + if (likely(ctl_sock_initialized)) + return dccp_feat_init(sk); return 0; } EXPORT_SYMBOL_GPL(dccp_init_sock); -int dccp_destroy_sock(struct sock *sk) +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 @@ -259,7 +217,7 @@ int 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; } @@ -268,9 +226,7 @@ int dccp_destroy_sock(struct sock *sk) dp->dccps_hc_rx_ccid = dp->dccps_hc_tx_ccid = NULL; /* clean up feature negotiation state */ - dccp_feat_clean(dmsk); - - return 0; + dccp_feat_list_purge(&dp->dccps_featneg); } EXPORT_SYMBOL_GPL(dccp_destroy_sock); @@ -280,6 +236,9 @@ static inline int dccp_listen_start(struct sock *sk, int backlog) struct dccp_sock *dp = dccp_sk(sk); dp->dccps_role = DCCP_ROLE_LISTEN; + /* do not start to listen if feature negotiation setup fails */ + if (dccp_feat_finalise_settings(dp)) + return -EPROTO; return inet_csk_listen_start(sk, backlog); } @@ -312,13 +271,15 @@ int dccp_disconnect(struct sock *sk, int flags) sk->sk_err = ECONNRESET; dccp_clear_xmit_timers(sk); + __skb_queue_purge(&sk->sk_receive_queue); + __skb_queue_purge(&sk->sk_write_queue); if (sk->sk_send_head != NULL) { __kfree_skb(sk->sk_send_head); sk->sk_send_head = NULL; } - inet->dport = 0; + inet->inet_dport = 0; if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) inet_reset_saddr(sk); @@ -330,7 +291,7 @@ int dccp_disconnect(struct sock *sk, int flags) inet_csk_delack_init(sk); __sk_dst_reset(sk); - BUG_TRAP(!inet->num || icsk->icsk_bind_hash); + WARN_ON(inet->inet_num && !icsk->icsk_bind_hash); sk->sk_error_report(sk); return err; @@ -351,7 +312,7 @@ unsigned int dccp_poll(struct file *file, struct socket *sock, unsigned int mask; struct sock *sk = sock->sk; - poll_wait(file, sk->sk_sleep, wait); + sock_poll_wait(file, sk_sleep(sk), wait); if (sk->sk_state == DCCP_LISTEN) return inet_csk_listen_poll(sk); @@ -375,7 +336,7 @@ unsigned int dccp_poll(struct file *file, struct socket *sock, mask |= POLLIN | POLLRDNORM; if (!(sk->sk_shutdown & SEND_SHUTDOWN)) { - if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk)) { + if (sk_stream_is_writeable(sk)) { mask |= POLLOUT | POLLWRNORM; } else { /* send SIGIO later */ set_bit(SOCK_ASYNC_NOSPACE, @@ -386,7 +347,7 @@ unsigned int dccp_poll(struct file *file, struct socket *sock, * wspace test but before the flags are set, * IO signal will be lost. */ - if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk)) + if (sk_stream_is_writeable(sk)) mask |= POLLOUT | POLLWRNORM; } } @@ -433,7 +394,7 @@ out: EXPORT_SYMBOL_GPL(dccp_ioctl); static int dccp_setsockopt_service(struct sock *sk, const __be32 service, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct dccp_sock *dp = dccp_sk(sk); struct dccp_service_list *sl = NULL; @@ -467,46 +428,88 @@ static int dccp_setsockopt_service(struct sock *sk, const __be32 service, return 0; } -/* byte 1 is feature. the rest is the preference list */ -static int dccp_setsockopt_change(struct sock *sk, int type, - struct dccp_so_feat __user *optval) +static int dccp_setsockopt_cscov(struct sock *sk, int cscov, bool rx) { - struct dccp_so_feat opt; - u8 *val; - int rc; + u8 *list, len; + int i, rc; - if (copy_from_user(&opt, optval, sizeof(opt))) - return -EFAULT; + if (cscov < 0 || cscov > 15) + return -EINVAL; + /* + * Populate a list of permissible values, in the range cscov...15. This + * is necessary since feature negotiation of single values only works if + * both sides incidentally choose the same value. Since the list starts + * lowest-value first, negotiation will pick the smallest shared value. + */ + if (cscov == 0) + return 0; + len = 16 - cscov; - val = kmalloc(opt.dccpsf_len, GFP_KERNEL); - if (!val) - return -ENOMEM; + list = kmalloc(len, GFP_KERNEL); + if (list == NULL) + return -ENOBUFS; - if (copy_from_user(val, opt.dccpsf_val, opt.dccpsf_len)) { - rc = -EFAULT; - goto out_free_val; - } + for (i = 0; i < len; i++) + list[i] = cscov++; - rc = dccp_feat_change(dccp_msk(sk), type, opt.dccpsf_feat, - val, opt.dccpsf_len, GFP_KERNEL); - if (rc) - goto out_free_val; + rc = dccp_feat_register_sp(sk, DCCPF_MIN_CSUM_COVER, rx, list, len); -out: + if (rc == 0) { + if (rx) + dccp_sk(sk)->dccps_pcrlen = cscov; + else + dccp_sk(sk)->dccps_pcslen = cscov; + } + kfree(list); return rc; +} + +static int dccp_setsockopt_ccid(struct sock *sk, int type, + char __user *optval, unsigned int optlen) +{ + u8 *val; + int rc = 0; + + if (optlen < 1 || optlen > DCCP_FEAT_MAX_SP_VALS) + return -EINVAL; + + val = memdup_user(optval, optlen); + if (IS_ERR(val)) + return PTR_ERR(val); + + lock_sock(sk); + if (type == DCCP_SOCKOPT_TX_CCID || type == DCCP_SOCKOPT_CCID) + rc = dccp_feat_register_sp(sk, DCCPF_CCID, 1, val, optlen); + + if (!rc && (type == DCCP_SOCKOPT_RX_CCID || type == DCCP_SOCKOPT_CCID)) + rc = dccp_feat_register_sp(sk, DCCPF_CCID, 0, val, optlen); + release_sock(sk); -out_free_val: kfree(val); - goto out; + return rc; } static int do_dccp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { struct dccp_sock *dp = dccp_sk(sk); int val, err = 0; - if (optlen < sizeof(int)) + switch (optname) { + case DCCP_SOCKOPT_PACKET_SIZE: + DCCP_WARN("sockopt(PACKET_SIZE) is deprecated: fix your app\n"); + return 0; + case DCCP_SOCKOPT_CHANGE_L: + case DCCP_SOCKOPT_CHANGE_R: + DCCP_WARN("sockopt(CHANGE_L/R) is deprecated: fix your app\n"); + return 0; + case DCCP_SOCKOPT_CCID: + case DCCP_SOCKOPT_RX_CCID: + case DCCP_SOCKOPT_TX_CCID: + return dccp_setsockopt_ccid(sk, optname, optval, optlen); + } + + if (optlen < (int)sizeof(int)) return -EINVAL; if (get_user(val, (int __user *)optval)) @@ -517,58 +520,43 @@ static int do_dccp_setsockopt(struct sock *sk, int level, int optname, lock_sock(sk); switch (optname) { - case DCCP_SOCKOPT_PACKET_SIZE: - DCCP_WARN("sockopt(PACKET_SIZE) is deprecated: fix your app\n"); - err = 0; - break; - case DCCP_SOCKOPT_CHANGE_L: - if (optlen != sizeof(struct dccp_so_feat)) - err = -EINVAL; - else - err = dccp_setsockopt_change(sk, DCCPO_CHANGE_L, - (struct dccp_so_feat __user *) - optval); - break; - case DCCP_SOCKOPT_CHANGE_R: - if (optlen != sizeof(struct dccp_so_feat)) - err = -EINVAL; - else - err = dccp_setsockopt_change(sk, DCCPO_CHANGE_R, - (struct dccp_so_feat __user *) - optval); - break; case DCCP_SOCKOPT_SERVER_TIMEWAIT: if (dp->dccps_role != DCCP_ROLE_SERVER) err = -EOPNOTSUPP; else dp->dccps_server_timewait = (val != 0); break; - case DCCP_SOCKOPT_SEND_CSCOV: /* sender side, RFC 4340, sec. 9.2 */ - if (val < 0 || val > 15) + case DCCP_SOCKOPT_SEND_CSCOV: + err = dccp_setsockopt_cscov(sk, val, false); + break; + case DCCP_SOCKOPT_RECV_CSCOV: + err = dccp_setsockopt_cscov(sk, val, true); + break; + case DCCP_SOCKOPT_QPOLICY_ID: + if (sk->sk_state != DCCP_CLOSED) + err = -EISCONN; + else if (val < 0 || val >= DCCPQ_POLICY_MAX) err = -EINVAL; else - dp->dccps_pcslen = val; + dp->dccps_qpolicy = val; break; - case DCCP_SOCKOPT_RECV_CSCOV: /* receiver side, RFC 4340 sec. 9.2.1 */ - if (val < 0 || val > 15) + case DCCP_SOCKOPT_QPOLICY_TXQLEN: + if (val < 0) err = -EINVAL; - else { - dp->dccps_pcrlen = val; - /* FIXME: add feature negotiation, - * ChangeL(MinimumChecksumCoverage, val) */ - } + else + dp->dccps_tx_qlen = val; break; default: err = -ENOPROTOOPT; break; } - release_sock(sk); + return err; } int dccp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { if (level != SOL_DCCP) return inet_csk(sk)->icsk_af_ops->setsockopt(sk, level, @@ -581,7 +569,7 @@ EXPORT_SYMBOL_GPL(dccp_setsockopt); #ifdef CONFIG_COMPAT int compat_dccp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { if (level != SOL_DCCP) return inet_csk_compat_setsockopt(sk, level, optname, @@ -644,6 +632,18 @@ static int do_dccp_getsockopt(struct sock *sk, int level, int optname, case DCCP_SOCKOPT_GET_CUR_MPS: val = dp->dccps_mss_cache; break; + case DCCP_SOCKOPT_AVAILABLE_CCIDS: + return ccid_getsockopt_builtin_ccids(sk, len, optval, optlen); + case DCCP_SOCKOPT_TX_CCID: + val = ccid_get_current_tx_ccid(dp); + if (val < 0) + return -ENOPROTOOPT; + break; + case DCCP_SOCKOPT_RX_CCID: + val = ccid_get_current_rx_ccid(dp); + if (val < 0) + return -ENOPROTOOPT; + break; case DCCP_SOCKOPT_SERVER_TIMEWAIT: val = dp->dccps_server_timewait; break; @@ -653,6 +653,12 @@ static int do_dccp_getsockopt(struct sock *sk, int level, int optname, case DCCP_SOCKOPT_RECV_CSCOV: val = dp->dccps_pcrlen; break; + case DCCP_SOCKOPT_QPOLICY_ID: + val = dp->dccps_qpolicy; + break; + case DCCP_SOCKOPT_QPOLICY_TXQLEN: + val = dp->dccps_tx_qlen; + break; case 128 ... 191: return ccid_hc_rx_getsockopt(dp->dccps_hc_rx_ccid, sk, optname, len, (u32 __user *)optval, optlen); @@ -695,6 +701,47 @@ int compat_dccp_getsockopt(struct sock *sk, int level, int optname, EXPORT_SYMBOL_GPL(compat_dccp_getsockopt); #endif +static int dccp_msghdr_parse(struct msghdr *msg, struct sk_buff *skb) +{ + struct cmsghdr *cmsg = CMSG_FIRSTHDR(msg); + + /* + * Assign an (opaque) qpolicy priority value to skb->priority. + * + * We are overloading this skb field for use with the qpolicy subystem. + * The skb->priority is normally used for the SO_PRIORITY option, which + * is initialised from sk_priority. Since the assignment of sk_priority + * to skb->priority happens later (on layer 3), we overload this field + * for use with queueing priorities as long as the skb is on layer 4. + * The default priority value (if nothing is set) is 0. + */ + skb->priority = 0; + + for (; cmsg != NULL; cmsg = CMSG_NXTHDR(msg, cmsg)) { + + if (!CMSG_OK(msg, cmsg)) + return -EINVAL; + + if (cmsg->cmsg_level != SOL_DCCP) + continue; + + if (cmsg->cmsg_type <= DCCP_SCM_QPOLICY_MAX && + !dccp_qpolicy_param_ok(skb->sk, cmsg->cmsg_type)) + return -EINVAL; + + switch (cmsg->cmsg_type) { + case DCCP_SCM_PRIORITY: + if (cmsg->cmsg_len != CMSG_LEN(sizeof(__u32))) + return -EINVAL; + skb->priority = *(__u32 *)CMSG_DATA(cmsg); + break; + default: + return -EINVAL; + } + } + return 0; +} + int dccp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t len) { @@ -710,8 +757,7 @@ int dccp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, lock_sock(sk); - if (sysctl_dccp_tx_qlen && - (sk->sk_write_queue.qlen >= sysctl_dccp_tx_qlen)) { + if (dccp_qpolicy_full(sk)) { rc = -EAGAIN; goto out_release; } @@ -739,8 +785,18 @@ int dccp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if (rc != 0) goto out_discard; - skb_queue_tail(&sk->sk_write_queue, skb); - dccp_write_xmit(sk,0); + rc = dccp_msghdr_parse(msg, skb); + if (rc != 0) + goto out_discard; + + dccp_qpolicy_push(sk, skb); + /* + * The xmit_timer is set if the TX CCID is rate-based and will expire + * when congestion control permits to release further packets into the + * network. Window-based CCIDs do not use this timer. + */ + if (!timer_pending(&dp->dccps_xmit_timer)) + dccp_write_xmit(sk); out_release: release_sock(sk); return rc ? : len; @@ -792,7 +848,7 @@ int dccp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, default: dccp_pr_debug("packet_type=%s\n", dccp_packet_name(dh->dccph_type)); - sk_eat_skb(sk, skb, 0); + sk_eat_skb(sk, skb, false); } verify_sock_status: if (sock_flag(sk, SOCK_DONE)) { @@ -845,9 +901,11 @@ verify_sock_status: len = -EFAULT; break; } + if (flags & MSG_TRUNC) + len = skb->len; found_fin_ok: if (!(flags & MSG_PEEK)) - sk_eat_skb(sk, skb, 0); + sk_eat_skb(sk, skb, false); break; } while (1); out: @@ -956,23 +1014,35 @@ void dccp_close(struct sock *sk, long timeout) if (data_was_unread) { /* Unread data was tossed, send an appropriate Reset Code */ - DCCP_WARN("DCCP: ABORT -- %u bytes unread\n", data_was_unread); + DCCP_WARN("ABORT with %u bytes unread\n", data_was_unread); dccp_send_reset(sk, DCCP_RESET_CODE_ABORTED); dccp_set_state(sk, DCCP_CLOSED); } else if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) { /* Check zero linger _after_ checking for unread data. */ sk->sk_prot->disconnect(sk, 0); } else if (sk->sk_state != DCCP_CLOSED) { + /* + * Normal connection termination. May need to wait if there are + * still packets in the TX queue that are delayed by the CCID. + */ + dccp_flush_write_queue(sk, &timeout); dccp_terminate_connection(sk); } + /* + * Flush write queue. This may be necessary in several cases: + * - we have been closed by the peer but still have application data; + * - abortive termination (unread data or zero linger time), + * - normal termination but queue could not be flushed within time limit + */ + __skb_queue_purge(&sk->sk_write_queue); + sk_stream_wait_close(sk, timeout); adjudge_to_death: state = sk->sk_state; sock_hold(sk); sock_orphan(sk); - atomic_inc(sk->sk_prot->orphan_count); /* * It is the last release_sock in its life. It will remove backlog. @@ -984,7 +1054,9 @@ adjudge_to_death: */ local_bh_disable(); bh_lock_sock(sk); - BUG_TRAP(!sock_owned_by_user(sk)); + WARN_ON(sock_owned_by_user(sk)); + + percpu_counter_inc(sk->sk_prot->orphan_count); /* Have we already been destroyed by a softirq or backlog? */ if (state != DCCP_CLOSED && sk->sk_state == DCCP_CLOSED) @@ -1010,33 +1082,17 @@ void dccp_shutdown(struct sock *sk, int how) EXPORT_SYMBOL_GPL(dccp_shutdown); -static int __init dccp_mib_init(void) +static inline int dccp_mib_init(void) { - int rc = -ENOMEM; - - dccp_statistics[0] = alloc_percpu(struct dccp_mib); - if (dccp_statistics[0] == NULL) - goto out; - - dccp_statistics[1] = alloc_percpu(struct dccp_mib); - if (dccp_statistics[1] == NULL) - goto out_free_one; - - rc = 0; -out: - return rc; -out_free_one: - free_percpu(dccp_statistics[0]); - dccp_statistics[0] = NULL; - goto out; - + dccp_statistics = alloc_percpu(struct dccp_mib); + if (!dccp_statistics) + return -ENOMEM; + return 0; } -static void dccp_mib_exit(void) +static inline void dccp_mib_exit(void) { - free_percpu(dccp_statistics[0]); - free_percpu(dccp_statistics[1]); - dccp_statistics[0] = dccp_statistics[1] = NULL; + free_percpu(dccp_statistics); } static int thash_entries; @@ -1044,8 +1100,8 @@ module_param(thash_entries, int, 0444); MODULE_PARM_DESC(thash_entries, "Number of ehash buckets"); #ifdef CONFIG_IP_DCCP_DEBUG -int dccp_debug; -module_param(dccp_debug, bool, 0444); +bool dccp_debug; +module_param(dccp_debug, bool, 0644); MODULE_PARM_DESC(dccp_debug, "Enable debug messages"); EXPORT_SYMBOL_GPL(dccp_debug); @@ -1055,14 +1111,21 @@ static int __init dccp_init(void) { unsigned long goal; int ehash_order, bhash_order, i; - int rc = -ENOBUFS; + int rc; + BUILD_BUG_ON(sizeof(struct dccp_skb_cb) > + FIELD_SIZEOF(struct sk_buff, cb)); + rc = percpu_counter_init(&dccp_orphan_count, 0); + if (rc) + goto out_fail; + rc = -ENOBUFS; + inet_hashinfo_init(&dccp_hashinfo); dccp_hashinfo.bind_bucket_cachep = kmem_cache_create("dccp_bind_bucket", sizeof(struct inet_bind_bucket), 0, SLAB_HWCACHE_ALIGN, NULL); if (!dccp_hashinfo.bind_bucket_cachep) - goto out; + goto out_free_percpu; /* * Size and allocate the main established and bind bucket @@ -1070,10 +1133,10 @@ static int __init dccp_init(void) * * The methodology is similar to that of the buffer cache. */ - if (num_physpages >= (128 * 1024)) - goal = num_physpages >> (21 - PAGE_SHIFT); + if (totalram_pages >= (128 * 1024)) + goal = totalram_pages >> (21 - PAGE_SHIFT); else - goal = num_physpages >> (23 - PAGE_SHIFT); + goal = totalram_pages >> (23 - PAGE_SHIFT); if (thash_entries) goal = (thash_entries * @@ -1081,13 +1144,14 @@ static int __init dccp_init(void) for (ehash_order = 0; (1UL << ehash_order) < goal; ehash_order++) ; do { - dccp_hashinfo.ehash_size = (1UL << ehash_order) * PAGE_SIZE / + unsigned long hash_size = (1UL << ehash_order) * PAGE_SIZE / sizeof(struct inet_ehash_bucket); - while (dccp_hashinfo.ehash_size & - (dccp_hashinfo.ehash_size - 1)) - dccp_hashinfo.ehash_size--; + + while (hash_size & (hash_size - 1)) + hash_size--; + dccp_hashinfo.ehash_mask = hash_size - 1; dccp_hashinfo.ehash = (struct inet_ehash_bucket *) - __get_free_pages(GFP_ATOMIC, ehash_order); + __get_free_pages(GFP_ATOMIC|__GFP_NOWARN, ehash_order); } while (!dccp_hashinfo.ehash && --ehash_order > 0); if (!dccp_hashinfo.ehash) { @@ -1095,10 +1159,8 @@ static int __init dccp_init(void) goto out_free_bind_bucket_cachep; } - for (i = 0; i < dccp_hashinfo.ehash_size; i++) { - INIT_HLIST_HEAD(&dccp_hashinfo.ehash[i].chain); - INIT_HLIST_HEAD(&dccp_hashinfo.ehash[i].twchain); - } + for (i = 0; i <= dccp_hashinfo.ehash_mask; i++) + INIT_HLIST_NULLS_HEAD(&dccp_hashinfo.ehash[i].chain, i); if (inet_ehash_locks_alloc(&dccp_hashinfo)) goto out_free_dccp_ehash; @@ -1112,7 +1174,7 @@ static int __init dccp_init(void) bhash_order > 0) continue; dccp_hashinfo.bhash = (struct inet_bind_hashbucket *) - __get_free_pages(GFP_ATOMIC, bhash_order); + __get_free_pages(GFP_ATOMIC|__GFP_NOWARN, bhash_order); } while (!dccp_hashinfo.bhash && --bhash_order >= 0); if (!dccp_hashinfo.bhash) { @@ -1137,40 +1199,52 @@ static int __init dccp_init(void) if (rc) goto out_ackvec_exit; + rc = ccid_initialize_builtins(); + if (rc) + goto out_sysctl_exit; + dccp_timestamping_init(); -out: - return rc; + + return 0; + +out_sysctl_exit: + dccp_sysctl_exit(); out_ackvec_exit: dccp_ackvec_exit(); out_free_dccp_mib: dccp_mib_exit(); out_free_dccp_bhash: free_pages((unsigned long)dccp_hashinfo.bhash, bhash_order); - dccp_hashinfo.bhash = NULL; out_free_dccp_locks: inet_ehash_locks_free(&dccp_hashinfo); out_free_dccp_ehash: free_pages((unsigned long)dccp_hashinfo.ehash, ehash_order); - dccp_hashinfo.ehash = NULL; out_free_bind_bucket_cachep: kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep); +out_free_percpu: + percpu_counter_destroy(&dccp_orphan_count); +out_fail: + dccp_hashinfo.bhash = NULL; + dccp_hashinfo.ehash = NULL; dccp_hashinfo.bind_bucket_cachep = NULL; - goto out; + return rc; } static void __exit dccp_fini(void) { + ccid_cleanup_builtins(); dccp_mib_exit(); free_pages((unsigned long)dccp_hashinfo.bhash, get_order(dccp_hashinfo.bhash_size * sizeof(struct inet_bind_hashbucket))); free_pages((unsigned long)dccp_hashinfo.ehash, - get_order(dccp_hashinfo.ehash_size * + get_order((dccp_hashinfo.ehash_mask + 1) * sizeof(struct inet_ehash_bucket))); inet_ehash_locks_free(&dccp_hashinfo); kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep); dccp_ackvec_exit(); dccp_sysctl_exit(); + percpu_counter_destroy(&dccp_orphan_count); } module_init(dccp_init); diff --git a/net/dccp/qpolicy.c b/net/dccp/qpolicy.c new file mode 100644 index 00000000000..63c30bfa470 --- /dev/null +++ b/net/dccp/qpolicy.c @@ -0,0 +1,137 @@ +/* + * net/dccp/qpolicy.c + * + * Policy-based packet dequeueing interface for DCCP. + * + * Copyright (c) 2008 Tomasz Grobelny <tomasz@grobelny.oswiecenia.net> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License v2 + * as published by the Free Software Foundation. + */ +#include "dccp.h" + +/* + * Simple Dequeueing Policy: + * If tx_qlen is different from 0, enqueue up to tx_qlen elements. + */ +static void qpolicy_simple_push(struct sock *sk, struct sk_buff *skb) +{ + skb_queue_tail(&sk->sk_write_queue, skb); +} + +static bool qpolicy_simple_full(struct sock *sk) +{ + return dccp_sk(sk)->dccps_tx_qlen && + sk->sk_write_queue.qlen >= dccp_sk(sk)->dccps_tx_qlen; +} + +static struct sk_buff *qpolicy_simple_top(struct sock *sk) +{ + return skb_peek(&sk->sk_write_queue); +} + +/* + * Priority-based Dequeueing Policy: + * If tx_qlen is different from 0 and the queue has reached its upper bound + * of tx_qlen elements, replace older packets lowest-priority-first. + */ +static struct sk_buff *qpolicy_prio_best_skb(struct sock *sk) +{ + struct sk_buff *skb, *best = NULL; + + skb_queue_walk(&sk->sk_write_queue, skb) + if (best == NULL || skb->priority > best->priority) + best = skb; + return best; +} + +static struct sk_buff *qpolicy_prio_worst_skb(struct sock *sk) +{ + struct sk_buff *skb, *worst = NULL; + + skb_queue_walk(&sk->sk_write_queue, skb) + if (worst == NULL || skb->priority < worst->priority) + worst = skb; + return worst; +} + +static bool qpolicy_prio_full(struct sock *sk) +{ + if (qpolicy_simple_full(sk)) + dccp_qpolicy_drop(sk, qpolicy_prio_worst_skb(sk)); + return false; +} + +/** + * struct dccp_qpolicy_operations - TX Packet Dequeueing Interface + * @push: add a new @skb to the write queue + * @full: indicates that no more packets will be admitted + * @top: peeks at whatever the queueing policy defines as its `top' + */ +static struct dccp_qpolicy_operations { + void (*push) (struct sock *sk, struct sk_buff *skb); + bool (*full) (struct sock *sk); + struct sk_buff* (*top) (struct sock *sk); + __be32 params; + +} qpol_table[DCCPQ_POLICY_MAX] = { + [DCCPQ_POLICY_SIMPLE] = { + .push = qpolicy_simple_push, + .full = qpolicy_simple_full, + .top = qpolicy_simple_top, + .params = 0, + }, + [DCCPQ_POLICY_PRIO] = { + .push = qpolicy_simple_push, + .full = qpolicy_prio_full, + .top = qpolicy_prio_best_skb, + .params = DCCP_SCM_PRIORITY, + }, +}; + +/* + * Externally visible interface + */ +void dccp_qpolicy_push(struct sock *sk, struct sk_buff *skb) +{ + qpol_table[dccp_sk(sk)->dccps_qpolicy].push(sk, skb); +} + +bool dccp_qpolicy_full(struct sock *sk) +{ + return qpol_table[dccp_sk(sk)->dccps_qpolicy].full(sk); +} + +void dccp_qpolicy_drop(struct sock *sk, struct sk_buff *skb) +{ + if (skb != NULL) { + skb_unlink(skb, &sk->sk_write_queue); + kfree_skb(skb); + } +} + +struct sk_buff *dccp_qpolicy_top(struct sock *sk) +{ + return qpol_table[dccp_sk(sk)->dccps_qpolicy].top(sk); +} + +struct sk_buff *dccp_qpolicy_pop(struct sock *sk) +{ + struct sk_buff *skb = dccp_qpolicy_top(sk); + + if (skb != NULL) { + /* Clear any skb fields that we used internally */ + skb->priority = 0; + skb_unlink(skb, &sk->sk_write_queue); + } + return skb; +} + +bool dccp_qpolicy_param_ok(struct sock *sk, __be32 param) +{ + /* check if exactly one bit is set */ + if (!param || (param & (param - 1))) + return false; + return (qpol_table[dccp_sk(sk)->dccps_qpolicy].params & param) == param; +} diff --git a/net/dccp/sysctl.c b/net/dccp/sysctl.c index 21295993fdb..53731e45403 100644 --- a/net/dccp/sysctl.c +++ b/net/dccp/sysctl.c @@ -18,76 +18,75 @@ #error This file should not be compiled without CONFIG_SYSCTL defined #endif +/* Boundary values */ +static int zero = 0, + one = 1, + u8_max = 0xFF; +static unsigned long seqw_min = DCCPF_SEQ_WMIN, + seqw_max = 0xFFFFFFFF; /* maximum on 32 bit */ + static struct ctl_table dccp_default_table[] = { { .procname = "seq_window", - .data = &sysctl_dccp_feat_sequence_window, - .maxlen = sizeof(sysctl_dccp_feat_sequence_window), + .data = &sysctl_dccp_sequence_window, + .maxlen = sizeof(sysctl_dccp_sequence_window), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_doulongvec_minmax, + .extra1 = &seqw_min, /* RFC 4340, 7.5.2 */ + .extra2 = &seqw_max, }, { .procname = "rx_ccid", - .data = &sysctl_dccp_feat_rx_ccid, - .maxlen = sizeof(sysctl_dccp_feat_rx_ccid), + .data = &sysctl_dccp_rx_ccid, + .maxlen = sizeof(sysctl_dccp_rx_ccid), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &u8_max, /* RFC 4340, 10. */ }, { .procname = "tx_ccid", - .data = &sysctl_dccp_feat_tx_ccid, - .maxlen = sizeof(sysctl_dccp_feat_tx_ccid), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "ack_ratio", - .data = &sysctl_dccp_feat_ack_ratio, - .maxlen = sizeof(sysctl_dccp_feat_ack_ratio), - .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 = "send_ndp", - .data = &sysctl_dccp_feat_send_ndp_count, - .maxlen = sizeof(sysctl_dccp_feat_send_ndp_count), + .data = &sysctl_dccp_tx_ccid, + .maxlen = sizeof(sysctl_dccp_tx_ccid), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &u8_max, /* RFC 4340, 10. */ }, { .procname = "request_retries", .data = &sysctl_dccp_request_retries, .maxlen = sizeof(sysctl_dccp_request_retries), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, + .extra2 = &u8_max, }, { .procname = "retries1", .data = &sysctl_dccp_retries1, .maxlen = sizeof(sysctl_dccp_retries1), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &u8_max, }, { .procname = "retries2", .data = &sysctl_dccp_retries2, .maxlen = sizeof(sysctl_dccp_retries2), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &u8_max, }, { .procname = "tx_qlen", .data = &sysctl_dccp_tx_qlen, .maxlen = sizeof(sysctl_dccp_tx_qlen), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, }, { .procname = "sync_ratelimit", @@ -97,13 +96,6 @@ static struct ctl_table dccp_default_table[] = { .proc_handler = proc_dointvec_ms_jiffies, }, - { .ctl_name = 0, } -}; - -static struct ctl_path dccp_path[] = { - { .procname = "net", .ctl_name = CTL_NET, }, - { .procname = "dccp", .ctl_name = NET_DCCP, }, - { .procname = "default", .ctl_name = NET_DCCP_DEFAULT, }, { } }; @@ -111,7 +103,7 @@ static struct ctl_table_header *dccp_table_header; int __init dccp_sysctl_init(void) { - dccp_table_header = register_sysctl_paths(dccp_path, + dccp_table_header = register_net_sysctl(&init_net, "net/dccp/default", dccp_default_table); return dccp_table_header != NULL ? 0 : -ENOMEM; @@ -120,7 +112,7 @@ int __init dccp_sysctl_init(void) void dccp_sysctl_exit(void) { if (dccp_table_header != NULL) { - unregister_sysctl_table(dccp_table_header); + unregister_net_sysctl_table(dccp_table_header); dccp_table_header = NULL; } } diff --git a/net/dccp/timer.c b/net/dccp/timer.c index 8703a792b56..1cd46a345cb 100644 --- a/net/dccp/timer.c +++ b/net/dccp/timer.c @@ -12,6 +12,7 @@ #include <linux/dccp.h> #include <linux/skbuff.h> +#include <linux/export.h> #include "dccp.h" @@ -38,7 +39,7 @@ static int dccp_write_timeout(struct sock *sk) if (sk->sk_state == DCCP_REQUESTING || sk->sk_state == DCCP_PARTOPEN) { if (icsk->icsk_retransmits != 0) - dst_negative_advice(&sk->sk_dst_cache); + dst_negative_advice(sk); retry_until = icsk->icsk_syn_retries ? : sysctl_dccp_request_retries; } else { @@ -63,7 +64,7 @@ static int dccp_write_timeout(struct sock *sk) Golden words :-). */ - dst_negative_advice(&sk->sk_dst_cache); + dst_negative_advice(sk); } retry_until = sysctl_dccp_retries2; @@ -87,33 +88,12 @@ static void dccp_retransmit_timer(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); - /* retransmit timer is used for feature negotiation throughout - * connection. In this case, no packet is re-transmitted, but rather an - * ack is generated and pending changes are placed into its options. - */ - if (sk->sk_send_head == NULL) { - dccp_pr_debug("feat negotiation retransmit timeout %p\n", sk); - if (sk->sk_state == DCCP_OPEN) - dccp_send_ack(sk); - goto backoff; - } - - /* - * sk->sk_send_head has to have one skb with - * DCCP_SKB_CB(skb)->dccpd_type set to one of the retransmittable DCCP - * packet types. The only packets eligible for retransmission are: - * -- Requests in client-REQUEST state (sec. 8.1.1) - * -- Acks in client-PARTOPEN state (sec. 8.1.5) - * -- CloseReq in server-CLOSEREQ state (sec. 8.3) - * -- Close in node-CLOSING state (sec. 8.3) */ - BUG_TRAP(sk->sk_send_head != NULL); - /* * More than than 4MSL (8 minutes) has passed, a RESET(aborted) was * sent, no need to retransmit, this sock is dead. */ if (dccp_write_timeout(sk)) - goto out; + return; /* * We want to know the number of packets retransmitted, not the @@ -122,30 +102,27 @@ static void dccp_retransmit_timer(struct sock *sk) if (icsk->icsk_retransmits == 0) DCCP_INC_STATS_BH(DCCP_MIB_TIMEOUTS); - if (dccp_retransmit_skb(sk, sk->sk_send_head) < 0) { + if (dccp_retransmit_skb(sk) != 0) { /* * Retransmission failed because of local congestion, * do not backoff. */ - if (icsk->icsk_retransmits == 0) + if (--icsk->icsk_retransmits == 0) icsk->icsk_retransmits = 1; inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, min(icsk->icsk_rto, TCP_RESOURCE_PROBE_INTERVAL), DCCP_RTO_MAX); - goto out; + return; } -backoff: icsk->icsk_backoff++; - icsk->icsk_retransmits++; icsk->icsk_rto = min(icsk->icsk_rto << 1, DCCP_RTO_MAX); inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, icsk->icsk_rto, DCCP_RTO_MAX); if (icsk->icsk_retransmits > sysctl_dccp_retries1) __sk_dst_reset(sk); -out:; } static void dccp_write_timer(unsigned long data) @@ -224,7 +201,7 @@ static void dccp_delack_timer(unsigned long data) if (sock_owned_by_user(sk)) { /* Try again later. */ icsk->icsk_ack.blocked = 1; - NET_INC_STATS_BH(LINUX_MIB_DELAYEDACKLOCKED); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_DELAYEDACKLOCKED); sk_reset_timer(sk, &icsk->icsk_delack_timer, jiffies + TCP_DELACK_MIN); goto out; @@ -254,39 +231,42 @@ static void dccp_delack_timer(unsigned long data) icsk->icsk_ack.ato = TCP_ATO_MIN; } dccp_send_ack(sk); - NET_INC_STATS_BH(LINUX_MIB_DELAYEDACKS); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_DELAYEDACKS); } out: bh_unlock_sock(sk); sock_put(sk); } -/* Transmit-delay timer: used by the CCIDs to delay actual send time */ -static void dccp_write_xmit_timer(unsigned long data) +/** + * dccp_write_xmitlet - Workhorse for CCID packet dequeueing interface + * See the comments above %ccid_dequeueing_decision for supported modes. + */ +static void dccp_write_xmitlet(unsigned long data) { struct sock *sk = (struct sock *)data; - struct dccp_sock *dp = dccp_sk(sk); bh_lock_sock(sk); if (sock_owned_by_user(sk)) - sk_reset_timer(sk, &dp->dccps_xmit_timer, jiffies+1); + sk_reset_timer(sk, &dccp_sk(sk)->dccps_xmit_timer, jiffies + 1); else - dccp_write_xmit(sk, 0); + dccp_write_xmit(sk); bh_unlock_sock(sk); - sock_put(sk); } -static void dccp_init_write_xmit_timer(struct sock *sk) +static void dccp_write_xmit_timer(unsigned long data) { - struct dccp_sock *dp = dccp_sk(sk); - - setup_timer(&dp->dccps_xmit_timer, dccp_write_xmit_timer, - (unsigned long)sk); + dccp_write_xmitlet(data); + sock_put((struct sock *)data); } void dccp_init_xmit_timers(struct sock *sk) { - dccp_init_write_xmit_timer(sk); + struct dccp_sock *dp = dccp_sk(sk); + + tasklet_init(&dp->dccps_xmitlet, dccp_write_xmitlet, (unsigned long)sk); + setup_timer(&dp->dccps_xmit_timer, dccp_write_xmit_timer, + (unsigned long)sk); inet_csk_init_xmit_timers(sk, &dccp_write_timer, &dccp_delack_timer, &dccp_keepalive_timer); } @@ -300,7 +280,7 @@ static ktime_t dccp_timestamp_seed; */ u32 dccp_timestamp(void) { - s64 delta = ktime_us_delta(ktime_get_real(), dccp_timestamp_seed); + u64 delta = (u64)ktime_us_delta(ktime_get_real(), dccp_timestamp_seed); do_div(delta, 10); return delta; |