diff options
Diffstat (limited to 'net/dccp')
34 files changed, 2334 insertions, 1931 deletions
diff --git a/net/dccp/Kconfig b/net/dccp/Kconfig index ad6dffd9070..8c0ef71bed2 100644 --- a/net/dccp/Kconfig +++ b/net/dccp/Kconfig @@ -1,6 +1,6 @@ menuconfig IP_DCCP - tristate "The DCCP Protocol (EXPERIMENTAL)" - depends on INET && EXPERIMENTAL + tristate "The DCCP Protocol" + depends on INET ---help--- Datagram Congestion Control Protocol (RFC 4340) @@ -49,7 +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 2991efcc8de..5c8362b037e 100644 --- a/net/dccp/Makefile +++ b/net/dccp/Makefile @@ -1,7 +1,7 @@ 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 # diff --git a/net/dccp/ackvec.c b/net/dccp/ackvec.c index 01e4d39fa23..ba07824af4c 100644 --- a/net/dccp/ackvec.c +++ b/net/dccp/ackvec.c @@ -1,444 +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/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 u8 nr_opts = DIV_ROUND_UP(av->av_vec_len, DCCP_SINGLE_OPT_MAXLEN); - u16 len = av->av_vec_len + 2 * nr_opts, i; - u32 elapsed_time; - 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_SINGLE_OPT_MAXLEN) - copylen = DCCP_SINGLE_OPT_MAXLEN; - - *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 av_state = dccp_ackvec_state(av, index); - /* - * valid packets not yet in av_buf have a reserved - * entry, with a len equal to 0. - */ - if (av_state == DCCP_ACKVEC_STATE_NOT_RECEIVED && - len == 0 && delta == 0) { /* Found our - reserved seat! */ - 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; + 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; + } + + 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; -out_duplicate: - /* Duplicate packet */ - dccp_pr_debug("Received a dup or already considered lost " - "packet: %llu\n", (unsigned long long)ackno); - return -EILSEQ; + av->av_buf[av->av_buf_head] = state; + av->av_buf_ackno = seqno; + + if (num_packets > 1) + dccp_ackvec_reserve_seats(av, num_packets - 1); } -static void dccp_ackvec_throw_record(struct dccp_ackvec *av, - struct dccp_ackvec_record *avr) +/** + * dccp_ackvec_input - Register incoming packet in the buffer + */ +void dccp_ackvec_input(struct dccp_ackvec *av, struct sk_buff *skb) { - struct dccp_ackvec_record *next; + u64 seqno = DCCP_SKB_CB(skb)->dccpd_seq; + enum dccp_ackvec_states state = DCCPAV_RECEIVED; - /* 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; + if (dccp_ackvec_is_empty(av)) { + dccp_ackvec_add_new(av, 1, seqno, state); + av->av_tail_ackno = seqno; - /* 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); - } -} + } else { + s64 num_packets = dccp_delta_seqno(av->av_buf_ackno, seqno); + u8 *current_head = av->av_buf + av->av_buf_head; -void dccp_ackvec_check_rcv_ackno(struct dccp_ackvec *av, struct sock *sk, - const u64 ackno) -{ - struct dccp_ackvec_record *avr; + if (num_packets == 1 && + dccp_ackvec_state(current_head) == state && + dccp_ackvec_runlen(current_head) < DCCPAV_MAX_RUNLEN) { - /* - * 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 */ + *current_head += 1; + av->av_buf_ackno = seqno; + + } 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; + } - dccp_set_seqno(ackno, ackno_end_rl - 1); - ++vector; + /* + * The peer has acknowledged up to and including ack_ackno. Hence the + * first packet in group (2) of 11.4.2 is the successor of ack_ackno. + */ + av->av_tail_ackno = ADD48(avr->avr_ack_ackno, 1); + +free_records: + list_for_each_entry_safe_from(avr, next, &av->av_records, avr_node) { + list_del(&avr->avr_node); + kmem_cache_free(dccp_ackvec_record_slab, avr); } } -int 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_SINGLE_OPT_MAXLEN) - 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) { @@ -448,10 +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 7ea557b7c6b..3284bfa988c 100644 --- a/net/dccp/ackvec.h +++ b/net/dccp/ackvec.h @@ -3,9 +3,9 @@ /* * net/dccp/ackvec.h * - * An implementation of the DCCP protocol + * An implementation of Ack Vectors for the DCCP protocol + * Copyright (c) 2007 University of Aberdeen, Scotland, UK * Copyright (c) 2005 Arnaldo Carvalho de Melo <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. @@ -13,99 +13,126 @@ #include <linux/dccp.h> #include <linux/compiler.h> -#include <linux/ktime.h> #include <linux/list.h> #include <linux/types.h> -/* We can spread an ack vector across multiple options */ -#define DCCP_MAX_ACKVEC_LEN (DCCP_SINGLE_OPT_MAXLEN * 2) +/* + * Ack Vector buffer space is static, in multiples of %DCCP_SINGLE_OPT_MAXLEN, + * the maximum size of a single Ack Vector. Setting %DCCPAV_NUM_ACKVECS to 1 + * will be sufficient for most cases of low Ack Ratios, using a value of 2 gives + * more headroom if Ack Ratio is higher or when the sender acknowledges slowly. + * 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) /* Estimated minimum average Ack Vector length - used for updating MPS */ #define DCCPAV_MIN_OPTLEN 16 -#define DCCP_ACKVEC_STATE_RECEIVED 0 -#define DCCP_ACKVEC_STATE_ECN_MARKED (1 << 6) -#define DCCP_ACKVEC_STATE_NOT_RECEIVED (3 << 6) +/* Threshold for coping with large bursts of losses */ +#define DCCPAV_BURST_THRESH (DCCPAV_MAX_ACKVEC_LEN / 8) -#define DCCP_ACKVEC_STATE_MASK 0xC0 /* 11000000 */ -#define DCCP_ACKVEC_LEN_MASK 0x3F /* 00111111 */ +enum dccp_ackvec_states { + DCCPAV_RECEIVED = 0x00, + DCCPAV_ECN_MARKED = 0x40, + DCCPAV_RESERVED = 0x80, + DCCPAV_NOT_RECEIVED = 0xC0 +}; +#define DCCPAV_MAX_RUNLEN 0x3F -/** struct dccp_ackvec - ack vector - * - * This data structure is the one defined in RFC 4340, Appendix A. - * - * @av_buf_head - circular buffer head - * @av_buf_tail - circular buffer tail - * @av_buf_ackno - ack # of the most recent packet acknowledgeable in the - * buffer (i.e. %av_buf_head) - * @av_buf_nonce - the one-bit sum of the ECN Nonces on all packets acked - * by the buffer with State 0 - * - * Additionally, the HC-Receiver must keep some information about the - * Ack Vectors it has recently sent. For each packet sent carrying an - * Ack Vector, it remembers four variables: +static inline u8 dccp_ackvec_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; - -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); +int dccp_ackvec_init(void); +void dccp_ackvec_exit(void); -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); +struct dccp_ackvec *dccp_ackvec_alloc(const gfp_t priority); +void dccp_ackvec_free(struct dccp_ackvec *av); -extern int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb); +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_pending(const struct dccp_ackvec *av) +static inline bool dccp_ackvec_is_empty(const struct dccp_ackvec *av) { - return av->av_vec_len; + return av->av_overflow == 0 && av->av_buf_head == av->av_buf_tail; } + +/** + * 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; +}; + +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 49d27c556be..597557254dd 100644 --- a/net/dccp/ccid.c +++ b/net/dccp/ccid.c @@ -11,6 +11,8 @@ * published by the Free Software Foundation. */ +#include <linux/slab.h> + #include "ccid.h" #include "ccids/lib/tfrc.h" @@ -44,6 +46,7 @@ bool ccid_support_check(u8 const *ccid_array, u8 array_len) * 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) @@ -116,7 +119,7 @@ static int ccid_activate(struct ccid_operations *ccid_ops) if (ccid_ops->ccid_hc_tx_slab == NULL) goto out_free_rx_slab; - pr_info("CCID: Activated CCID %d (%s)\n", + pr_info("DCCP: Activated CCID %d (%s)\n", ccid_ops->ccid_id, ccid_ops->ccid_name); err = 0; out: @@ -134,7 +137,7 @@ static void ccid_deactivate(struct ccid_operations *ccid_ops) ccid_kmem_cache_destroy(ccid_ops->ccid_hc_rx_slab); ccid_ops->ccid_hc_rx_slab = NULL; - pr_info("CCID: Deactivated CCID %d (%s)\n", + pr_info("DCCP: Deactivated CCID %d (%s)\n", ccid_ops->ccid_id, ccid_ops->ccid_name); } diff --git a/net/dccp/ccid.h b/net/dccp/ccid.h index 6df6f8ac963..6eb837a47b5 100644 --- a/net/dccp/ccid.h +++ b/net/dccp/ccid.h @@ -62,22 +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, @@ -97,8 +93,8 @@ extern struct ccid_operations ccid2_ops; extern struct ccid_operations ccid3_ops; #endif -extern int ccid_initialize_builtins(void); -extern void ccid_cleanup_builtins(void); +int ccid_initialize_builtins(void); +void ccid_cleanup_builtins(void); struct ccid { struct ccid_operations *ccid_ops; @@ -110,12 +106,12 @@ static inline void *ccid_priv(const struct ccid *ccid) return (void *)ccid->ccid_priv; } -extern bool ccid_support_check(u8 const *ccid_array, u8 array_len); -extern int ccid_get_builtin_ccids(u8 **ccid_array, u8 *array_len); -extern int ccid_getsockopt_builtin_ccids(struct sock *sk, int len, - char __user *, int __user *); +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 *); -extern struct ccid *ccid_new(const u8 id, struct sock *sk, bool rx); +struct ccid *ccid_new(const u8 id, struct sock *sk, bool rx); static inline int ccid_get_current_rx_ccid(struct dccp_sock *dp) { @@ -135,23 +131,51 @@ static inline int ccid_get_current_tx_ccid(struct dccp_sock *dp) return ccid->ccid_ops->ccid_id; } -extern void ccid_hc_rx_delete(struct ccid *ccid, struct sock *sk); -extern void ccid_hc_tx_delete(struct ccid *ccid, struct sock *sk); +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, @@ -168,27 +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, @@ -218,7 +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; @@ -229,7 +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 8408398cd44..8ba3fc9d6d1 100644 --- a/net/dccp/ccids/Kconfig +++ b/net/dccp/ccids/Kconfig @@ -1,5 +1,4 @@ -menu "DCCP CCIDs Configuration (EXPERIMENTAL)" - depends on EXPERIMENTAL +menu "DCCP CCIDs Configuration" config IP_DCCP_CCID2_DEBUG bool "CCID-2 debugging messages" @@ -12,7 +11,7 @@ config IP_DCCP_CCID2_DEBUG If in doubt, say N. config IP_DCCP_CCID3 - bool "CCID-3 (TCP-Friendly) (EXPERIMENTAL)" + 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 @@ -47,37 +46,6 @@ config IP_DCCP_CCID3_DEBUG If in doubt, say N. -config IP_DCCP_CCID3_RTO - int "Use higher bound for nofeedback timer" - default 100 - depends on IP_DCCP_CCID3 && EXPERIMENTAL - ---help--- - Use higher lower bound for nofeedback timer expiration. - - The TFRC nofeedback timer normally expires after the maximum of 4 - RTTs and twice the current send interval (RFC 3448, 4.3). On LANs - with a small RTT this can mean a high processing load and reduced - performance, since then the nofeedback timer is triggered very - frequently. - - This option enables to set a higher lower bound for the nofeedback - value. Values in units of milliseconds can be set here. - - A value of 0 disables this feature by enforcing the value specified - in RFC 3448. The following values have been suggested as bounds for - experimental use: - * 16-20ms to match the typical multimedia inter-frame interval - * 100ms as a reasonable compromise [default] - * 1000ms corresponds to the lower TCP RTO bound (RFC 2988, 2.4) - - The default of 100ms is a compromise between a large value for - efficient DCCP implementations, and a small value to avoid disrupting - the network in times of congestion. - - The purpose of the nofeedback timer is to slow DCCP down when there - is serious network congestion: experimenting with larger values should - therefore not be performed on WANs. - config IP_DCCP_TFRC_LIB def_bool y if IP_DCCP_CCID3 diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c index a47a8c918ee..f053198e730 100644 --- a/net/dccp/ccids/ccid2.c +++ b/net/dccp/ccids/ccid2.c @@ -23,60 +23,16 @@ /* * This implementation should follow RFC 4341 */ +#include <linux/slab.h> #include "../feat.h" -#include "../ccid.h" -#include "../dccp.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 *hc) -{ - int len = 0; - int pipe = 0; - struct ccid2_seq *seqp = hc->tx_seqh; - - /* there is data in the chain */ - if (seqp != hc->tx_seqt) { - seqp = seqp->ccid2s_prev; - len++; - if (!seqp->ccid2s_acked) - pipe++; - - while (seqp != hc->tx_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 != hc->tx_pipe); - ccid2_pr_debug("len of chain=%d\n", len); - - do { - seqp = seqp->ccid2s_prev; - len++; - } while (seqp != hc->tx_seqh); - - ccid2_pr_debug("total len=%d\n", len); - BUG_ON(len != hc->tx_seqbufc * CCID2_SEQBUF_LEN); -} #else #define ccid2_pr_debug(format, a...) -#define ccid2_hc_tx_check_sanity(hc) #endif static int ccid2_hc_tx_alloc_seq(struct ccid2_hc_tx_sock *hc) @@ -122,17 +78,13 @@ static int ccid2_hc_tx_alloc_seq(struct ccid2_hc_tx_sock *hc) static int ccid2_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb) { - struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); - - if (hc->tx_pipe < hc->tx_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)->tx_cwnd, 2); /* @@ -145,29 +97,40 @@ 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 > DCCPF_ACK_RATIO_MAX) - val = DCCPF_ACK_RATIO_MAX; + 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 *hc, long val) +static void ccid2_change_l_seq_window(struct sock *sk, u64 val) { - ccid2_pr_debug("change SRTT to %ld\n", val); - hc->tx_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 *hc = ccid2_hc_tx_sk(sk); - long s; + const bool sender_was_blocked = ccid2_cwnd_network_limited(hc); bh_lock_sock(sk); if (sock_owned_by_user(sk)) { @@ -177,23 +140,17 @@ static void ccid2_hc_tx_rto_expire(unsigned long data) ccid2_pr_debug("RTO_EXPIRE\n"); - ccid2_hc_tx_check_sanity(hc); - /* back-off timer */ hc->tx_rto <<= 1; - - s = hc->tx_rto / HZ; - if (s > 60) - hc->tx_rto = 60 * HZ; - - ccid2_start_rto_timer(sk); + if (hc->tx_rto > DCCP_RTO_MAX) + hc->tx_rto = DCCP_RTO_MAX; /* adjust pipe, cwnd etc */ hc->tx_ssthresh = hc->tx_cwnd / 2; if (hc->tx_ssthresh < 2) hc->tx_ssthresh = 2; - hc->tx_cwnd = 1; - hc->tx_pipe = 0; + hc->tx_cwnd = 1; + hc->tx_pipe = 0; /* clear state about stuff we sent */ hc->tx_seqt = hc->tx_seqh; @@ -203,33 +160,108 @@ static void ccid2_hc_tx_rto_expire(unsigned long data) hc->tx_rpseq = 0; hc->tx_rpdupack = -1; ccid2_change_l_ack_ratio(sk, 1); - ccid2_hc_tx_check_sanity(hc); + + /* 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) +{ + hc->tx_expected_wnd = (3 * hc->tx_expected_wnd + new_wnd) / 4; +} + +/* 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; - ccid2_pr_debug("setting RTO timeout=%ld\n", hc->tx_rto); + ccid2_check_l_ack_ratio(sk); +} - BUG_ON(timer_pending(&hc->tx_rtotimer)); - sk_reset_timer(sk, &hc->tx_rtotimer, jiffies + hc->tx_rto); +/* 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, int more, unsigned int len) +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 *hc = ccid2_hc_tx_sk(sk); + const u32 now = ccid2_time_stamp; struct ccid2_seq *next; - hc->tx_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); + + hc->tx_lsndtime = now; + hc->tx_pipe += 1; + + /* 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 = jiffies; + hc->tx_seqh->ccid2s_sent = now; next = hc->tx_seqh->ccid2s_next; /* check if we need to alloc more space */ @@ -295,221 +327,190 @@ static void ccid2_hc_tx_packet_sent(struct sock *sk, int more, unsigned int len) } #endif - /* setup RTO timer */ - if (!timer_pending(&hc->tx_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 = hc->tx_seqt; while (seqp != hc->tx_seqh) { - ccid2_pr_debug("out seq=%llu acked=%d time=%lu\n", + 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(hc); #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 *hc = 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, &hc->tx_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 *hc = ccid2_hc_tx_sk(sk); - - 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) { + 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; - } - - /* update RTO */ - if (hc->tx_srtt == -1 || - time_after(jiffies, hc->tx_lastrtt + hc->tx_srtt)) { - unsigned long r = (long)jiffies - (long)seqp->ccid2s_sent; - int s; - - /* first measurement */ - if (hc->tx_srtt == -1) { - ccid2_pr_debug("R: %lu Time=%lu seq=%llu\n", - r, jiffies, - (unsigned long long)seqp->ccid2s_seq); - ccid2_change_srtt(hc, r); - hc->tx_rttvar = r >> 1; - } else { - /* RTTVAR */ - long tmp = hc->tx_srtt - r; - long srtt; - - if (tmp < 0) - tmp *= -1; - - tmp >>= 2; - hc->tx_rttvar *= 3; - hc->tx_rttvar >>= 2; - hc->tx_rttvar += tmp; - - /* SRTT */ - srtt = hc->tx_srtt; - srtt *= 7; - srtt >>= 3; - tmp = r >> 3; - srtt += tmp; - ccid2_change_srtt(hc, srtt); } - s = hc->tx_rttvar << 2; - /* clock granularity is 1 when based on jiffies */ - if (!s) - s = 1; - hc->tx_rto = hc->tx_srtt + s; - - /* must be at least a second */ - s = hc->tx_rto / HZ; - /* DCCP doesn't require this [but I like it cuz my code sux] */ -#if 1 - if (s < 1) - hc->tx_rto = HZ; -#endif - /* max 60 seconds */ - if (s > 60) - hc->tx_rto = HZ * 60; - - hc->tx_lastrtt = jiffies; - - ccid2_pr_debug("srtt: %ld rttvar: %ld rto: %ld (HZ=%d) R=%lu\n", - hc->tx_srtt, hc->tx_rttvar, - hc->tx_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 *hc = 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 (hc->tx_pipe == 0) - DCCP_BUG("pipe == 0"); - else - hc->tx_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 (hc->tx_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 *hc = ccid2_hc_tx_sk(sk); - if (time_before(seqp->ccid2s_sent, hc->tx_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; } - hc->tx_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); - /* Avoid spurious timeouts resulting from Ack Ratio > cwnd */ - if (dccp_sk(sk)->dccps_l_ack_ratio > hc->tx_cwnd) - ccid2_change_l_ack_ratio(sk, hc->tx_cwnd); + 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); + + 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 *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(hc); /* check reverse path congestion */ seqno = DCCP_SKB_CB(skb)->dccpd_seq; @@ -533,24 +534,27 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) 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 (hc->tx_seqh == hc->tx_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, hc->tx_high_ack)) @@ -574,16 +578,16 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) 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. @@ -602,24 +606,22 @@ 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 == hc->tx_seqt) { done = 1; @@ -631,7 +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; @@ -676,7 +677,7 @@ 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 == hc->tx_seqt) break; @@ -694,7 +695,16 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) hc->tx_seqt = hc->tx_seqt->ccid2s_next; } - ccid2_hc_tx_check_sanity(hc); + /* 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) @@ -706,12 +716,9 @@ static int ccid2_hc_tx_init(struct ccid *ccid, struct sock *sk) /* RFC 4341, 5: initialise ssthresh to arbitrarily high (max) value */ 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. - */ - hc->tx_cwnd = clamp(4380U / dp->dccps_mss_cache, 2U, 4U); + /* 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(hc->tx_cwnd, 2); @@ -722,15 +729,13 @@ static int ccid2_hc_tx_init(struct ccid *ccid, struct sock *sk) if (ccid2_hc_tx_alloc_seq(hc)) return -ENOMEM; - hc->tx_rto = 3 * HZ; - ccid2_change_srtt(hc, -1); - hc->tx_rttvar = -1; + hc->tx_rto = DCCP_TIMEOUT_INIT; hc->tx_rpdupack = -1; - hc->tx_last_cong = jiffies; + 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(hc); + INIT_LIST_HEAD(&hc->tx_av_chunks); return 0; } @@ -739,7 +744,7 @@ static void ccid2_hc_tx_exit(struct sock *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 < hc->tx_seqbufc; i++) kfree(hc->tx_seqbuf[i]); @@ -748,32 +753,29 @@ static void ccid2_hc_tx_exit(struct sock *sk) 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 *hc = ccid2_hc_rx_sk(sk); - switch (DCCP_SKB_CB(skb)->dccpd_type) { - case DCCP_PKT_DATA: - case DCCP_PKT_DATAACK: - hc->rx_data++; - if (hc->rx_data >= dp->dccps_r_ack_ratio) { - dccp_send_ack(sk); - hc->rx_data = 0; - } - break; + 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; } } 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_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, + .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 diff --git a/net/dccp/ccids/ccid2.h b/net/dccp/ccids/ccid2.h index 1ec6a30103b..18c97543e52 100644 --- a/net/dccp/ccids/ccid2.h +++ b/net/dccp/ccids/ccid2.h @@ -18,18 +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; @@ -38,13 +43,29 @@ struct ccid2_seq { #define CCID2_SEQBUF_LEN 1024 #define CCID2_SEQBUF_MAX 128 +/* + * 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_lastrtt: time RTT was last measured + * @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 tx_cwnd; @@ -55,19 +76,49 @@ struct ccid2_hc_tx_sock { int tx_seqbufc; struct ccid2_seq *tx_seqh; struct ccid2_seq *tx_seqt; - long tx_rto; - long tx_srtt; - long tx_rttvar; - unsigned long tx_lastrtt; + + /* 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; - unsigned long tx_last_cong; + 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 rx_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 bcd7632299f..119c04317d4 100644 --- a/net/dccp/ccids/ccid3.c +++ b/net/dccp/ccids/ccid3.c @@ -38,7 +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...) @@ -54,7 +54,6 @@ static const char *ccid3_tx_state_name(enum ccid3_hc_tx_states state) [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]; @@ -91,19 +90,17 @@ static inline u64 rfc3390_initial_rate(struct sock *sk) 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 *hc) { - /* Calculate new t_ipi = s / X_inst (X_inst is in 64 * bytes/second) */ hc->tx_t_ipi = scaled_div32(((u64)hc->tx_s) << 6, hc->tx_x); - /* Calculate new delta by delta = min(t_ipi / 2, t_gran / 2) */ - hc->tx_delta = min_t(u32, hc->tx_t_ipi / 2, TFRC_OPSYS_HALF_TIME_GRAN); - - ccid3_pr_debug("t_ipi=%u, delta=%u, s=%u, X=%u\n", hc->tx_t_ipi, - hc->tx_delta, hc->tx_s, (unsigned)(hc->tx_x >> 6)); + 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 *hc, ktime_t now) @@ -116,6 +113,7 @@ static u32 ccid3_hc_tx_idle_rtt(struct ccid3_hc_tx_sock *hc, ktime_t now) /** * 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 @@ -156,17 +154,19 @@ static void ccid3_hc_tx_update_x(struct sock *sk, ktime_t *stamp) 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)(hc->tx_x >> 6), hc->tx_x_calc, - (unsigned)(hc->tx_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(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 *hc, int len) { @@ -208,19 +208,22 @@ 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_pr_debug("%s(%p, state=%s) - entry\n", dccp_role(sk), sk, ccid3_tx_state_name(hc->tx_state)); + /* 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); - else if (hc->tx_state != TFRC_SSTATE_NO_FBACK) - goto out; /* * 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 (hc->tx_t_rto == 0 || /* no feedback received yet */ - hc->tx_p == 0) { + if (hc->tx_t_rto == 0 || hc->tx_p == 0) { /* halve send rate directly */ hc->tx_x = max(hc->tx_x / 2, @@ -237,8 +240,6 @@ 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(hc->tx_p && !hc->tx_x_calc); - if (hc->tx_x_calc > (hc->tx_x_recv >> 5)) hc->tx_x_recv = max(hc->tx_x_recv / 2, @@ -256,7 +257,7 @@ static void ccid3_hc_tx_no_feedback_timer(unsigned long data) * Set new timeout for the nofeedback timer. * See comments in packet_recv() regarding the value of t_RTO. */ - if (unlikely(hc->tx_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(hc->tx_t_rto, 2 * hc->tx_t_ipi); @@ -269,11 +270,12 @@ out: 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) { @@ -290,8 +292,7 @@ static int ccid3_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb) if (unlikely(skb->len == 0)) return -EBADMSG; - switch (hc->tx_state) { - case TFRC_SSTATE_NO_SENT: + 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; @@ -326,27 +327,22 @@ static int ccid3_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb) 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: + + } 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)hc->tx_delta >= 1000) - return (u32)delay / 1000L; + if (delay >= TFRC_T_DELTA) + return (u32)delay / USEC_PER_MSEC; ccid3_hc_tx_update_win_count(hc, now); - break; - case TFRC_SSTATE_TERM: - DCCP_BUG("%s(%p) - Illegal state TERM", dccp_role(sk), sk); - return -EINVAL; } /* prepare to send now (add options etc.) */ @@ -355,11 +351,10 @@ static int ccid3_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb) /* set the nominal send time for the next following packet */ hc->tx_t_nom = ktime_add_us(hc->tx_t_nom, hc->tx_t_ipi); - return 0; + 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 *hc = ccid3_hc_tx_sk(sk); @@ -372,48 +367,34 @@ static void ccid3_hc_tx_packet_sent(struct sock *sk, int more, static void ccid3_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) { struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk); - struct ccid3_options_received *opt_recv; + 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 (hc->tx_state != TFRC_SSTATE_FBACK && - hc->tx_state != TFRC_SSTATE_NO_FBACK) - return; - - opt_recv = &hc->tx_options_received; - now = ktime_get_real(); - - /* Estimate RTT from history if ACK number is valid */ - r_sample = tfrc_tx_hist_rtt(hc->tx_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); - return; - } - - /* Update receive rate in units of 64 * bytes/second */ - hc->tx_x_recv = opt_recv->ccid3or_receive_rate; - hc->tx_x_recv <<= 6; - - /* 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 */ - hc->tx_p = 0; - else /* can not exceed 100% */ - hc->tx_p = scaled_div(1, pinv); /* - * Validate new RTT sample and update moving average + * 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). */ - r_sample = dccp_sample_rtt(sk, r_sample); + 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 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 allowed sending rate X as per draft rfc3448bis-00, 4.2/3 */ @@ -448,8 +429,8 @@ done_computing_x: "p=%u, X_calc=%u, X_recv=%u, X=%u\n", dccp_role(sk), sk, hc->tx_rtt, r_sample, hc->tx_s, hc->tx_p, hc->tx_x_calc, - (unsigned)(hc->tx_x_recv >> 6), - (unsigned)(hc->tx_x >> 6)); + (unsigned int)(hc->tx_x_recv >> 6), + (unsigned int)(hc->tx_x >> 6)); /* unschedule no feedback timer */ sk_stop_timer(sk, &hc->tx_no_feedback_timer); @@ -461,13 +442,12 @@ 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. */ - hc->tx_t_rto = max_t(u32, 4 * hc->tx_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) @@ -482,66 +462,41 @@ done_computing_x: 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 *hc = ccid3_hc_tx_sk(sk); - struct ccid3_options_received *opt_recv; __be32 opt_val; - opt_recv = &hc->tx_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) @@ -559,42 +514,37 @@ static void ccid3_hc_tx_exit(struct sock *sk) { struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk); - ccid3_hc_tx_set_state(sk, TFRC_SSTATE_TERM); 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 *hc; - - /* Listen socks doesn't have a private CCID block */ - if (sk->sk_state == DCCP_LISTEN) - return; - - hc = ccid3_hc_tx_sk(sk); - info->tcpi_rto = hc->tx_t_rto; - info->tcpi_rtt = hc->tx_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 *hc; + 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; - - hc = ccid3_hc_tx_sk(sk); switch (optname) { case DCCP_SOCKOPT_CCID_TX_INFO: - if (len < sizeof(hc->tx_tfrc)) + if (len < sizeof(tfrc)) return -EINVAL; - len = sizeof(hc->tx_tfrc); - val = &hc->tx_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; @@ -624,7 +574,6 @@ static const char *ccid3_rx_state_name(enum ccid3_hc_rx_states state) 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]; @@ -650,14 +599,9 @@ static void ccid3_hc_rx_send_feedback(struct sock *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(hc->rx_state == TFRC_RSTATE_TERM)) - return; - - now = ktime_get_real(); - switch (fbtype) { case CCID3_FBACK_INITIAL: hc->rx_x_recv = 0; @@ -701,23 +645,21 @@ 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 *hc; + 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; - hc = ccid3_hc_rx_sk(sk); - if (dccp_packet_without_ack(skb)) return 0; 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; @@ -749,10 +691,11 @@ static u32 ccid3_first_li(struct sock *sk) 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 = hc->rx_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(hc->rx_s, hc->rx_rtt); @@ -862,46 +805,31 @@ static void ccid3_hc_rx_exit(struct sock *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(&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 *hc; - - /* Listen socks doesn't have a private CCID block */ - if (sk->sk_state == DCCP_LISTEN) - return; - - hc = ccid3_hc_rx_sk(sk); - info->tcpi_ca_state = hc->rx_state; + info->tcpi_ca_state = ccid3_hc_rx_sk(sk)->rx_state; info->tcpi_options |= TCPI_OPT_TIMESTAMPS; - info->tcpi_rcv_rtt = hc->rx_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 *hc; + 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; - - hc = 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 = hc->rx_x_recv; rx_info.tfrcrx_rtt = hc->rx_rtt; - rx_info.tfrcrx_p = hc->rx_pinv == 0 ? ~0U : - scaled_div(1, hc->rx_pinv); + rx_info.tfrcrx_p = tfrc_invert_loss_event_rate(hc->rx_pinv); len = sizeof(rx_info); val = &rx_info; break; diff --git a/net/dccp/ccids/ccid3.h b/net/dccp/ccids/ccid3.h index 03263577665..1a9933c2967 100644 --- a/net/dccp/ccids/ccid3.h +++ b/net/dccp/ccids/ccid3.h @@ -42,35 +42,36 @@ #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, }; /** @@ -90,19 +91,16 @@ enum ccid3_hc_tx_states { * @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_delta: Send timer delta (RFC 3448, 4.6) in usecs * @tx_hist: Packet history - * @tx_options_received: Parsed set of retrieved options */ struct ccid3_hc_tx_sock { - struct tfrc_tx_info tx_tfrc; -#define tx_x tx_tfrc.tfrctx_x -#define tx_x_recv tx_tfrc.tfrctx_x_recv -#define tx_x_calc tx_tfrc.tfrctx_x_calc -#define tx_rtt tx_tfrc.tfrctx_rtt -#define tx_p tx_tfrc.tfrctx_p -#define tx_t_rto tx_tfrc.tfrctx_rto -#define tx_t_ipi tx_tfrc.tfrctx_ipi + 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; @@ -110,9 +108,7 @@ struct ccid3_hc_tx_sock { struct timer_list tx_no_feedback_timer; ktime_t tx_t_ld; ktime_t tx_t_nom; - u32 tx_delta; struct tfrc_tx_hist_entry *tx_hist; - struct ccid3_options_received tx_options_received; }; static inline struct ccid3_hc_tx_sock *ccid3_hc_tx_sk(const struct sock *sk) @@ -126,21 +122,16 @@ static inline struct ccid3_hc_tx_sock *ccid3_hc_tx_sk(const struct sock *sk) 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 - * @rx_x_recv: Receiver estimate of send rate (RFC 3448 4.3) - * @rx_rtt: Receiver estimate of rtt (non-standard) - * @rx_p: Current loss event rate (RFC 3448 5.4) * @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_tstamp_last_ack: 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 diff --git a/net/dccp/ccids/lib/loss_interval.c b/net/dccp/ccids/lib/loss_interval.c index 8fc3cbf7907..57f9fd78c4d 100644 --- a/net/dccp/ccids/lib/loss_interval.c +++ b/net/dccp/ccids/lib/loss_interval.c @@ -116,7 +116,7 @@ u8 tfrc_lh_update_i_mean(struct tfrc_loss_hist *lh, struct sk_buff *skb) cur->li_length = len; tfrc_lh_calc_i_mean(lh); - return (lh->i_mean < old_i_mean); + return lh->i_mean < old_i_mean; } /* Determine if `new_loss' does begin a new loss interval [RFC 4342, 10.2] */ @@ -133,6 +133,7 @@ static inline u8 tfrc_lh_is_new_loss(struct tfrc_loss_interval *cur, * @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, diff --git a/net/dccp/ccids/lib/loss_interval.h b/net/dccp/ccids/lib/loss_interval.h index d1d2f5383b7..57f631a86cc 100644 --- a/net/dccp/ccids/lib/loss_interval.h +++ b/net/dccp/ccids/lib/loss_interval.h @@ -65,9 +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 3a4f414e94a..08df7a3acb3 100644 --- a/net/dccp/ccids/lib/packet_history.c +++ b/net/dccp/ccids/lib/packet_history.c @@ -38,18 +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 */ @@ -71,15 +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()); @@ -107,24 +86,6 @@ void tfrc_tx_hist_purge(struct tfrc_tx_hist_entry **headp) *headp = NULL; } -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; -} - - /* * Receiver History Routines */ @@ -354,6 +315,7 @@ 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. @@ -426,7 +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) diff --git a/net/dccp/ccids/lib/packet_history.h b/net/dccp/ccids/lib/packet_history.h index 7df6c529999..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) @@ -123,20 +139,17 @@ static inline bool tfrc_rx_hist_loss_pending(const struct tfrc_rx_hist *h) return h->loss_count > 0; } -extern void tfrc_rx_hist_add_packet(struct tfrc_rx_hist *h, - const struct sk_buff *skb, const u64 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, const u64 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 4902029854d..62b5828acde 100644 --- a/net/dccp/ccids/lib/tfrc.c +++ b/net/dccp/ccids/lib/tfrc.c @@ -4,10 +4,11 @@ * Copyright (c) 2007 The University of Aberdeen, Scotland, UK * Copyright (c) 2007 Arnaldo Carvalho de Melo <acme@redhat.com> */ +#include <linux/moduleparam.h> #include "tfrc.h" #ifdef CONFIG_IP_DCCP_TFRC_DEBUG -int tfrc_debug; +bool tfrc_debug; module_param(tfrc_debug, bool, 0644); MODULE_PARM_DESC(tfrc_debug, "Enable TFRC debug messages"); #endif diff --git a/net/dccp/ccids/lib/tfrc.h b/net/dccp/ccids/lib/tfrc.h index 01bb48e96c2..40ee7d62b65 100644 --- a/net/dccp/ccids/lib/tfrc.h +++ b/net/dccp/ccids/lib/tfrc.h @@ -21,7 +21,7 @@ #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...) @@ -55,20 +55,21 @@ 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); -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); +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); -extern int tfrc_li_init(void); -extern void tfrc_li_exit(void); +int tfrc_li_init(void); +void tfrc_li_exit(void); #ifdef CONFIG_IP_DCCP_TFRC_LIB -extern int tfrc_lib_init(void); -extern void tfrc_lib_exit(void); +int tfrc_lib_init(void); +void tfrc_lib_exit(void); #else #define tfrc_lib_init() (0) #define tfrc_lib_exit() diff --git a/net/dccp/ccids/lib/tfrc_equation.c b/net/dccp/ccids/lib/tfrc_equation.c index 22ca1cf0eb5..88ef98285be 100644 --- a/net/dccp/ccids/lib/tfrc_equation.c +++ b/net/dccp/ccids/lib/tfrc_equation.c @@ -611,6 +611,7 @@ static inline u32 tfrc_binsearch(u32 fval, u8 small) * @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). */ u32 tfrc_calc_x(u16 s, u32 R, u32 p) @@ -659,6 +660,7 @@ u32 tfrc_calc_x(u16 s, u32 R, u32 p) /** * 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) @@ -687,3 +689,17 @@ u32 tfrc_calc_x_reverse_lookup(u32 fvalue) index = tfrc_binsearch(fvalue, 0); return (index + 1) * 1000000 / TFRC_CALC_X_ARRSIZE; } + +/** + * 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 5ef32c2f0d6..c67816647cc 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -39,7 +39,7 @@ "%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) @@ -53,7 +53,7 @@ extern struct inet_hashinfo dccp_hashinfo; 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 @@ -75,7 +75,7 @@ extern void dccp_time_wait(struct sock *sk, int state, int timeo); * 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 @@ -84,7 +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 @@ -93,9 +93,6 @@ 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; @@ -153,18 +150,27 @@ static inline u64 max48(const u64 seq1, const u64 seq2) } /** - * dccp_loss_free - Evaluates condition for data loss from RFC 4340, 7.7.1 - * @s1: start sequence number - * @s2: end sequence number + * 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 - * Returns true if the sequence range s1...s2 has no data loss. */ -static inline bool dccp_loss_free(const u64 s1, const u64 s2, const u64 ndp) +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); - return (u64)delta <= ndp + 1; + 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 { @@ -189,17 +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 @@ -223,101 +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); +int dccp_retransmit_skb(struct sock *sk); -extern void dccp_send_ack(struct sock *sk); -extern void dccp_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, - 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); + +/* + * 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); -extern void dccp_init_xmit_timers(struct sock *sk); +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 int dccp_reqsk_init(struct request_sock *rq, struct dccp_sock const *dp, - struct sk_buff const *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 void 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, unsigned 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, unsigned 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 sock *sk, - 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) @@ -338,12 +346,13 @@ 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 defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) struct inet6_skb_parm h6; #endif } header; @@ -412,9 +421,27 @@ static inline void dccp_update_gsr(struct sock *sk, u64 seq) { struct dccp_sock *dp = dccp_sk(sk); - dp->dccps_gsr = seq; + 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); } @@ -425,41 +452,41 @@ static inline void dccp_update_gss(struct sock *sk, u64 seq) dp->dccps_gss = seq; /* Ack validity window depends on local Sequence Window value (7.5.1) */ dp->dccps_awl = SUB48(ADD48(dp->dccps_gss, 1), dp->dccps_l_seq_win); + /* Adjust AWL so that it is not below ISS - see comment above for SWL */ + if (before48(dp->dccps_awl, dp->dccps_iss)) + dp->dccps_awl = dp->dccps_iss; dp->dccps_awh = dp->dccps_gss; } +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 || - (dp->dccps_hc_rx_ackvec != NULL && - dccp_ackvec_pending(dp->dccps_hc_rx_ackvec)) || - inet_csk_ack_scheduled(sk); + return dccp_ackvec_pending(sk) || inet_csk_ack_scheduled(sk); } -extern int dccp_feat_finalise_settings(struct dccp_sock *dp); -extern int dccp_feat_server_ccid_dependencies(struct dccp_request_sock *dreq); -extern int dccp_feat_insert_opts(struct dccp_sock*, struct dccp_request_sock*, - struct sk_buff *skb); -extern int dccp_feat_activate_values(struct sock *sk, struct list_head *fn); -extern void dccp_feat_list_purge(struct list_head *fn_list); - -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 b21f261da75..028fc43aacb 100644 --- a/net/dccp/diag.c +++ b/net/dccp/diag.c @@ -48,11 +48,23 @@ static void dccp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, dccp_get_info(sk, _info); } +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 = { - .idiag_hashinfo = &dccp_hashinfo, + .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) @@ -71,4 +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 972b8dc918d..9733ddbc96c 100644 --- a/net/dccp/feat.c +++ b/net/dccp/feat.c @@ -12,6 +12,7 @@ * ----------- * 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. @@ -22,6 +23,7 @@ * 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" @@ -342,6 +344,21 @@ static int __dccp_feat_activate(struct sock *sk, const int idx, 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) { @@ -430,6 +447,7 @@ static struct dccp_feat_entry *dccp_feat_list_lookup(struct list_head *fn_list, * @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 * @@ -474,8 +492,8 @@ static int dccp_feat_push_change(struct list_head *fn_list, u8 feat, u8 local, new->feat_num = feat; new->is_local = local; new->state = FEAT_INITIALISING; - new->needs_confirm = 0; - new->empty_confirm = 0; + new->needs_confirm = false; + new->empty_confirm = false; new->val = *fval; new->needs_mandatory = mandatory; @@ -488,6 +506,7 @@ static int dccp_feat_push_change(struct list_head *fn_list, u8 feat, u8 local, * @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, @@ -501,12 +520,12 @@ static int dccp_feat_push_confirm(struct list_head *fn_list, u8 feat, u8 local, new->feat_num = feat; new->is_local = local; new->state = FEAT_STABLE; /* transition in 6.6.2 */ - new->needs_confirm = 1; + 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 = 0; + new->needs_mandatory = false; return 0; } @@ -649,11 +668,22 @@ int dccp_feat_insert_opts(struct dccp_sock *dp, struct dccp_request_sock *dreq, return -1; if (pos->needs_mandatory && dccp_insert_option_mandatory(skb)) return -1; - /* - * Enter CHANGING after transmitting the Change option (6.6.2). - */ - if (pos->state == FEAT_INITIALISING) - pos->state = FEAT_CHANGING; + + 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; } @@ -664,6 +694,7 @@ int dccp_feat_insert_opts(struct dccp_sock *dp, struct dccp_request_sock *dreq, * @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, @@ -729,16 +760,72 @@ int dccp_feat_register_sp(struct sock *sk, u8 feat, u8 is_local, 0, list, len); } -/* Analogous to dccp_feat_register_sp(), but for non-negotiable values */ -int dccp_feat_register_nn(struct sock *sk, u8 feat, u64 val) +/** + * 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) { - /* any changes must be registered before establishing the connection */ - if (sk->sk_state != DCCP_CLOSED) - return -EISCONN; - if (dccp_feat_type(feat) != FEAT_NN) + 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; - return __feat_register_nn(&dccp_sk(sk)->dccps_featneg, feat, 0, val); + + 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); + } + + 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 @@ -849,6 +936,7 @@ static const struct ccid_dependency *dccp_feat_ccid_deps(u8 ccid, bool is_local) * @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) @@ -872,6 +960,7 @@ static int dccp_feat_propagate_ccid(struct list_head *fn, u8 id, bool is_local) /** * 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. @@ -1074,7 +1163,7 @@ static u8 dccp_feat_change_recv(struct list_head *fn, u8 is_mandatory, u8 opt, } if (dccp_feat_reconcile(&entry->val, val, len, server, true)) { - entry->empty_confirm = 0; + entry->empty_confirm = false; } else if (is_mandatory) { return DCCP_RESET_CODE_MANDATORY_ERROR; } else if (entry->state == FEAT_INITIALISING) { @@ -1090,10 +1179,10 @@ static u8 dccp_feat_change_recv(struct list_head *fn, u8 is_mandatory, u8 opt, 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 = 1; + entry->empty_confirm = true; } - entry->needs_confirm = 1; - entry->needs_mandatory = 0; + entry->needs_confirm = true; + entry->needs_mandatory = false; entry->state = FEAT_STABLE; return 0; @@ -1196,6 +1285,101 @@ confirmation_failed: } /** + * 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). + */ +static u8 dccp_feat_handle_nn_established(struct sock *sk, u8 mandatory, u8 opt, + u8 feat, u8 *val, u8 len) +{ + 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; + + dccp_feat_print_opt(opt, feat, val, len, mandatory); + + /* 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; + } + + /* + * 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; + + 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); + + } else if (opt == DCCPO_CONFIRM_R) { + entry = dccp_feat_list_lookup(fn, feat, local); + if (entry == NULL || entry->state != FEAT_CHANGING) + return 0; + + 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. + */ + if (fval.nn != entry->val.nn) + return 0; + + /* Only activate after receiving the Confirm option (6.6.1). */ + dccp_feat_activate(sk, feat, local, &fval); + + /* It has been confirmed - so remove the entry */ + dccp_feat_list_pop(entry); + + } else { + DCCP_WARN("Received illegal option %u\n", opt); + goto fast_path_failed; + } + return 0; + +fast_path_unknown: + if (!mandatory) + return dccp_push_empty_confirm(fn, feat, local); + +fast_path_failed: + return mandatory ? DCCP_RESET_CODE_MANDATORY_ERROR + : DCCP_RESET_CODE_OPTION_ERROR; +} + +/** * 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 @@ -1204,6 +1388,7 @@ confirmation_failed: * @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, @@ -1230,6 +1415,14 @@ int dccp_feat_parse_options(struct sock *sk, struct dccp_request_sock *dreq, 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 0; /* ignore FN options in all other states */ } diff --git a/net/dccp/feat.h b/net/dccp/feat.h index f96721619de..0e75cebb218 100644 --- a/net/dccp/feat.h +++ b/net/dccp/feat.h @@ -107,14 +107,13 @@ extern unsigned long sysctl_dccp_sequence_window; extern int sysctl_dccp_rx_ccid; extern int sysctl_dccp_tx_ccid; -extern int dccp_feat_init(struct sock *sk); -extern void dccp_feat_initialise_sysctls(void); -extern int dccp_feat_register_sp(struct sock *sk, u8 feat, u8 is_local, - u8 const *list, u8 len); -extern int dccp_feat_register_nn(struct sock *sk, u8 feat, u64 val); -extern int dccp_feat_parse_options(struct sock *, struct dccp_request_sock *, - u8 mand, u8 opt, u8 feat, u8 *val, u8 len); -extern int dccp_feat_clone_list(struct list_head const *, struct list_head *); +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. @@ -128,10 +127,11 @@ extern int dccp_feat_clone_list(struct list_head const *, struct list_head *); */ #define DCCP_OPTVAL_MAXLEN 6 -extern void dccp_encode_value_var(const u64 value, u8 *to, const u8 len); -extern u64 dccp_decode_value_var(const u8 *bf, const u8 len); +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); -extern int dccp_insert_option_mandatory(struct sk_buff *skb); -extern int dccp_insert_fn_opt(struct sk_buff *skb, u8 type, u8 feat, - u8 *val, u8 len, bool repeat_first); +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 7648f316310..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 (dp->dccps_hc_rx_ackvec != NULL) - 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)) return 1; - if (DCCP_SKB_CB(skb)->dccpd_ack_seq != DCCP_PKT_WITHOUT_ACK_SEQ) - dccp_event_ack_recv(sk, skb); - - if (dp->dccps_hc_rx_ackvec != NULL && - dccp_ackvec_add(dp->dccps_hc_rx_ackvec, sk, - DCCP_SKB_CB(skb)->dccpd_seq, - 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 @@ -414,7 +409,7 @@ static int dccp_rcv_request_sent_state_process(struct sock *sk, 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); @@ -429,7 +424,7 @@ static int dccp_rcv_request_sent_state_process(struct sock *sk, if (dccp_parse_options(sk, NULL, skb)) 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)); @@ -440,20 +435,14 @@ static int dccp_rcv_request_sent_state_process(struct sock *sk, kfree_skb(sk->sk_send_head); sk->sk_send_head = NULL; - dp->dccps_isr = DCCP_SKB_CB(skb)->dccpd_seq; - dccp_update_gsr(sk, dp->dccps_isr); /* - * SWL and AWL are initially adjusted so that they are not less than - * the initial Sequence Numbers received and sent, respectively: - * SWL := max(GSR + 1 - floor(W/4), ISR), - * AWL := max(GSS - W' + 1, ISS). - * These adjustments MUST be applied only at the beginning of the - * connection. - * - * AWL was adjusted in dccp_v4_connect -acme + * Set ISR, GSR from packet. ISS was set in dccp_v{4,6}_connect + * and GSS in dccp_transmit_skb(). Setting AWL/AWH and SWL/SWH + * is done as part of activating the feature values below, since + * these settings depend on the local/remote Sequence Window + * features, which were undefined or not confirmed until now. */ - dccp_set_seqno(&dp->dccps_swl, - max48(dp->dccps_swl, dp->dccps_isr)); + dp->dccps_gsr = dp->dccps_isr = DCCP_SKB_CB(skb)->dccpd_seq; dccp_sync_mss(sk, icsk->icsk_pmtu_cookie); @@ -532,8 +521,10 @@ unable_to_proceed: 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) { @@ -558,7 +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 || @@ -574,7 +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); @@ -616,30 +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 && sk->sk_state != DCCP_RESPOND) { - if (dccp_check_seqno(sk, skb)) - goto discard; - - /* - * Step 8: Process options and mark acknowledgeable - */ - if (dccp_parse_options(sk, NULL, skb)) - return 1; - - if (dcb->dccpd_ack_seq != DCCP_PKT_WITHOUT_ACK_SEQ) - dccp_event_ack_recv(sk, skb); - - if (dp->dccps_hc_rx_ackvec != NULL && - dccp_ackvec_add(dp->dccps_hc_rx_ackvec, sk, - DCCP_SKB_CB(skb)->dccpd_seq, - 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, @@ -647,41 +651,21 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, * S.state := TIMEWAIT * Set TIMEWAIT timer * Drop packet and return - */ + */ if (dh->dccph_type == DCCP_PKT_RESET) { dccp_rcv_reset(sk, skb); return 0; - /* - * Step 7: Check for unexpected packet types - * If (S.is_server and P.type == Response) - * or (S.is_client and P.type == Request) - * or (S.state == RESPOND and P.type == Data), - * Send Sync packet acknowledging P.seqno - * Drop packet and return - */ - } else if ((dp->dccps_role != DCCP_ROLE_CLIENT && - dh->dccph_type == DCCP_PKT_RESPONSE) || - (dp->dccps_role == DCCP_ROLE_CLIENT && - dh->dccph_type == DCCP_PKT_REQUEST) || - (sk->sk_state == DCCP_RESPOND && - dh->dccph_type == DCCP_PKT_DATA)) { - dccp_send_sync(sk, dcb->dccpd_seq, DCCP_PKT_SYNC); - goto discard; - } else if (dh->dccph_type == DCCP_PKT_CLOSEREQ) { + } else if (dh->dccph_type == DCCP_PKT_CLOSEREQ) { /* Step 13 */ if (dccp_rcv_closereq(sk, skb)) return 0; goto discard; - } else if (dh->dccph_type == DCCP_PKT_CLOSE) { + } else if (dh->dccph_type == DCCP_PKT_CLOSE) { /* Step 14 */ if (dccp_rcv_close(sk, skb)) return 0; goto discard; } switch (sk->sk_state) { - case DCCP_CLOSED: - dcb->dccpd_reset_code = DCCP_RESET_CODE_NO_CONNECTION; - return 1; - case DCCP_REQUESTING: queued = dccp_rcv_request_sent_state_process(sk, skb, dh, len); if (queued >= 0) @@ -690,8 +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; @@ -722,6 +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. */ diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 4071eaf2b36..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" @@ -39,13 +41,15 @@ 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; @@ -56,37 +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->inet_saddr, - RT_CONN_FLAGS(sk), sk->sk_bound_dev_if, - IPPROTO_DCCP, - inet->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->inet_saddr == 0) - inet->inet_saddr = rt->rt_src; + inet->inet_saddr = fl4->saddr; inet->inet_rcv_saddr = inet->inet_saddr; 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 @@ -98,13 +108,15 @@ 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->inet_sport, - inet->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->inet_saddr, inet->inet_daddr, @@ -149,17 +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. */ @@ -169,6 +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); @@ -183,6 +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 @@ -247,6 +261,9 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info) } switch (type) { + case ICMP_REDIRECT: + dccp_do_redirect(skb, sk); + goto out; case ICMP_SOURCE_QUENCH: /* Just silently ignore these. */ goto out; @@ -288,7 +305,8 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info) */ WARN_ON(req->sk); - if (seq != dccp_rsk(req)->dreq_iss) { + if (!between48(seq, dccp_rsk(req)->dreq_iss, + dccp_rsk(req)->dreq_gss)) { NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } @@ -348,7 +366,7 @@ 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); @@ -386,39 +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->inet_daddr = ireq->rmt_addr; - newinet->inet_rcv_saddr = ireq->loc_addr; - newinet->inet_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->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)); + if (__inet_inherit_port(sk, newsk) < 0) + goto put_and_exit; __inet_hash_nolisten(newsk, NULL); - __inet_inherit_port(sk, newsk); return newsk; exit_overflow: 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); - dst_release(dst); return NULL; +put_and_exit: + inet_csk_prepare_forced_close(newsk); + dccp_done(newsk); + goto exit; } EXPORT_SYMBOL_GPL(dccp_v4_request_recv_sock); @@ -456,35 +480,35 @@ 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 = skb_rtable(skb)->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(net, &rt, &fl, sk, 0)) { + 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 request_values *rv_unused) +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; - dst = inet_csk_route_req(sk, req); + dst = inet_csk_route_req(sk, &fl4, req); if (dst == NULL) goto out; @@ -493,10 +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); - 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); } @@ -554,6 +578,11 @@ static void dccp_v4_reqsk_destructor(struct request_sock *req) 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), @@ -561,6 +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) @@ -612,22 +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->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); @@ -958,6 +989,7 @@ static const struct net_protocol dccp_v4_protocol = { .err_handler = dccp_v4_err, .no_policy = 1, .netns_ok = 1, + .icmp_strict_tag_validation = 1, }; static const struct proto_ops inet_dccp_ops = { @@ -992,7 +1024,6 @@ static struct inet_protosw dccp_v4_protosw = { .protocol = IPPROTO_DCCP, .prot = &dccp_v4_prot, .ops = &inet_dccp_ops, - .no_check = 0, .flags = INET_PROTOSW_ICSK, }; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index af3394df63b..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> @@ -28,6 +29,7 @@ #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" @@ -53,29 +55,22 @@ static void dccp_v6_hash(struct sock *sk) /* 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, @@ -87,7 +82,7 @@ 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, 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; @@ -135,51 +130,31 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, 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->inet_dport; - fl.fl_ip_sport = inet->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(net, &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; } @@ -204,7 +179,8 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, */ WARN_ON(req->sk != NULL); - if (seq != dccp_rsk(req)->dreq_iss) { + if (!between48(seq, dccp_rsk(req)->dreq_iss, + dccp_rsk(req)->dreq_gss)) { NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } @@ -241,64 +217,49 @@ out: } -static int dccp_v6_send_response(struct sock *sk, struct request_sock *req, - struct request_values *rv_unused) +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_rsk(req)->loc_port; - security_req_classify_flow(req, &fl); - - 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(sock_net(sk), &dst, &fl, sk, 0); - if (err < 0) + 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); if (skb != NULL) { 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; } @@ -306,15 +267,14 @@ done: static void dccp_v6_reqsk_destructor(struct request_sock *req) { dccp_feat_list_purge(&dccp_rsk(req)->dreq_featneg); - if (inet6_rsk(req)->pktopts != NULL) - kfree_skb(inet6_rsk(req)->pktopts); + 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; @@ -333,25 +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(ctl_sk, &dst, &fl)) { - if (xfrm_lookup(net, &dst, &fl, NULL, 0) >= 0) { - skb_dst_set(skb, dst); - ip6_xmit(ctl_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); @@ -364,6 +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) @@ -401,7 +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); @@ -440,36 +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); + 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); @@ -487,13 +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)) { /* @@ -504,18 +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_v4mapped(newinet->inet_daddr, &newnp->daddr); + ipv6_addr_set_v4mapped(newinet->inet_daddr, &newsk->sk_v6_daddr); 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; @@ -539,44 +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_rsk(req)->loc_port; - 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(sock_net(sk), &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 @@ -590,31 +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); } @@ -628,11 +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) @@ -644,18 +586,21 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, newinet->inet_daddr = newinet->inet_saddr = LOOPBACK4_IPV6; newinet->inet_rcv_saddr = LOOPBACK4_IPV6; + if (__inet_inherit_port(sk, newsk) < 0) { + inet_csk_prepare_forced_close(newsk); + dccp_done(newsk); + goto out; + } __inet6_hash(newsk, NULL); - __inet_inherit_port(sk, newsk); return newsk; out_overflow: 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); - if (opt != NULL && opt != np->opt) - sock_kfree_s(sk, opt, opt->tot_len); - dst_release(dst); return NULL; } @@ -885,8 +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; @@ -899,17 +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); } } @@ -942,8 +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 @@ -972,52 +916,37 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, goto failure; } ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr); - ipv6_addr_set_v4mapped(inet->inet_rcv_saddr, &np->rcv_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->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(sock_net(sk), &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); + np->saddr = *saddr; inet->inet_rcv_saddr = LOOPBACK4_IPV6; __ip6_dst_store(sk, dst, NULL, NULL); @@ -1035,7 +964,7 @@ 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, + sk->sk_v6_daddr.s6_addr32, inet->inet_sport, inet->inet_dport); err = dccp_connect(sk); 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 0d508c359fa..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> @@ -52,15 +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 @@ -99,7 +97,7 @@ 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) { struct dccp_request_sock *dreq = dccp_rsk(req); @@ -120,30 +118,20 @@ struct sock *dccp_create_openreq_child(struct sock *sk, * * Choose S.ISS (initial seqno) or set from Init Cookies * Initialize S.GAR := S.ISS - * Set S.ISR, S.GSR, S.SWL, S.SWH from packet or Init Cookies + * 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). */ - newdp->dccps_gar = newdp->dccps_iss = dreq->dreq_iss; - dccp_update_gss(newsk, dreq->dreq_iss); - + newdp->dccps_iss = dreq->dreq_iss; + newdp->dccps_gss = dreq->dreq_gss; + newdp->dccps_gar = newdp->dccps_iss; newdp->dccps_isr = dreq->dreq_isr; - dccp_update_gsr(newsk, dreq->dreq_isr); - - /* - * SWL and AWL are initially adjusted so that they are not less than - * the initial Sequence Numbers received and sent, respectively: - * SWL := max(GSR + 1 - floor(W/4), ISR), - * AWL := max(GSS - W' + 1, ISS). - * These adjustments MUST be applied only at the beginning of the - * connection. - */ - dccp_set_seqno(&newdp->dccps_swl, - max48(newdp->dccps_swl, newdp->dccps_isr)); - dccp_set_seqno(&newdp->dccps_awl, - max48(newdp->dccps_awl, newdp->dccps_iss)); + newdp->dccps_gsr = dreq->dreq_gsr; /* - * Activate features after initialising the sequence numbers, - * since CCID initialisation may depend on GSS, ISR, ISS etc. + * Activate features: initialise CCIDs, sequence windows etc. */ if (dccp_feat_activate_values(newsk, &dreq->dreq_featneg)) { /* It is still raw copy of parent, so invalidate @@ -175,16 +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; @@ -197,12 +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; } @@ -248,7 +237,7 @@ 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 @@ -277,10 +266,10 @@ int dccp_reqsk_init(struct request_sock *req, { struct dccp_request_sock *dreq = dccp_rsk(req); - inet_rsk(req)->rmt_port = dccp_hdr(skb)->dccph_sport; - inet_rsk(req)->loc_port = dccp_hdr(skb)->dccph_dport; - inet_rsk(req)->acked = 0; - 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); diff --git a/net/dccp/options.c b/net/dccp/options.c index 1b08cae9c65..9bce31886bd 100644 --- a/net/dccp/options.c +++ b/net/dccp/options.c @@ -54,7 +54,6 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq, struct dccp_sock *dp = dccp_sk(sk); const struct dccp_hdr *dh = dccp_hdr(skb); const u8 pkt_type = DCCP_SKB_CB(skb)->dccpd_type; - u64 ackno = DCCP_SKB_CB(skb)->dccpd_ack_seq; unsigned char *options = (unsigned char *)dh + dccp_hdr_len(skb); unsigned char *opt_ptr = options; const unsigned char *opt_end = (unsigned char *)dh + @@ -96,18 +95,11 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq, } /* - * 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; @@ -131,19 +123,13 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq, case DCCPO_CHANGE_L ... DCCPO_CONFIRM_R: if (pkt_type == DCCP_PKT_DATA) /* RFC 4340, 6 */ break; + 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_ACK_VECTOR_0: - case DCCPO_ACK_VECTOR_1: - if (dccp_packet_without_ack(skb)) /* RFC 4340, 11.4 */ - break; - if (dp->dccps_hc_rx_ackvec != NULL && - dccp_ackvec_parse(sk, skb, &ackno, opt, value, len)) - goto out_invalid_option; - break; case DCCPO_TIMESTAMP: if (len != 4) goto out_invalid_option; @@ -170,6 +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) @@ -226,23 +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 " @@ -296,12 +286,11 @@ static inline u8 dccp_ndp_len(const u64 ndp) { if (likely(ndp <= 0xFF)) return 1; - return likely(ndp <= USHORT_MAX) ? 2 : (ndp <= UINT_MAX ? 4 : 6); + 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; @@ -354,49 +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) @@ -441,6 +396,83 @@ static int dccp_insert_option_timestamp_echo(struct dccp_sock *dp, return 0; } +static int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb) +{ + 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 (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; + + to = skb_push(skb, len); + len = buflen; + from = av->av_buf + av->av_buf_head; + tail = av->av_buf + DCCPAV_MAX_ACKVEC_LEN; + + for (i = 0; i < nr_opts; ++i) { + int copylen = len; + + if (len > DCCP_SINGLE_OPT_MAXLEN) + copylen = DCCP_SINGLE_OPT_MAXLEN; + + /* + * 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; +} + /** * dccp_insert_option_mandatory - Mandatory option (5.8.2) * Note that since we are using skb_push, this function needs to be called @@ -463,6 +495,7 @@ int dccp_insert_option_mandatory(struct sk_buff *skb) * @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 @@ -480,7 +513,7 @@ int dccp_insert_fn_opt(struct sk_buff *skb, u8 type, u8 feat, } if (unlikely(val == NULL || len == 0)) - len = repeat_first = 0; + len = repeat_first = false; tot_len = 3 + repeat_first + len; if (DCCP_SKB_CB(skb)->dccpd_opt_len + tot_len > DCCP_MAX_OPT_LEN) { @@ -531,13 +564,12 @@ int dccp_insert_options(struct sock *sk, struct sk_buff *skb) if (DCCP_SKB_CB(skb)->dccpd_type == DCCP_PKT_REQUEST) { /* * Obtain RTT sample from Request/Response exchange. - * This is currently used in CCID 3 initialisation. + * This is currently used for TFRC initialisation. */ - if (dccp_insert_option_timestamp(sk, skb)) + if (dccp_insert_option_timestamp(skb)) return -1; - } else if (dp->dccps_hc_rx_ackvec != NULL && - dccp_ackvec_pending(dp->dccps_hc_rx_ackvec) && + } else if (dccp_ackvec_pending(sk) && dccp_insert_option_ackvec(sk, skb)) { return -1; } @@ -564,6 +596,10 @@ int dccp_insert_options_rsk(struct dccp_request_sock *dreq, struct sk_buff *skb) 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 d6bb753bf6a..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); @@ -128,21 +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); - 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". @@ -194,120 +197,173 @@ 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_has_sleeper(sk)) - 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 ((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); - } + while (*time_budget > 0 && (skb = skb_peek(&sk->sk_write_queue))) { + rc = ccid_hc_tx_send_packet(dp->dccps_hc_tx_ccid, sk, skb); - skb_dequeue(&sk->sk_write_queue); - if (err == 0) { - struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb); - const int len = skb->len; - - if (sk->sk_state == DCCP_PARTOPEN) { - 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); - 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); + 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; + + while ((skb = dccp_qpolicy_top(sk))) { + int rc = ccid_hc_tx_send_packet(dp->dccps_hc_tx_ccid, sk, 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); } } } @@ -353,10 +409,10 @@ struct sk_buff *dccp_make_response(struct sock *sk, struct dst_entry *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; /* Resolve feature dependencies resulting from choice of CCID */ if (dccp_feat_server_ccid_dependencies(dreq)) @@ -368,14 +424,14 @@ struct sk_buff *dccp_make_response(struct sock *sk, struct dst_entry *dst, /* Build and checksum header */ dh = dccp_zeroed_hdr(skb, dccp_header_size); - dh->dccph_sport = inet_rsk(req)->loc_port; - 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); @@ -471,8 +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); @@ -482,22 +539,12 @@ static inline void dccp_connect_init(struct sock *sk) dccp_sync_mss(sk, dst_mtu(dst)); - /* 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); - /* do not connect if feature negotiation setup fails */ if (dccp_feat_finalise_settings(dccp_sk(sk))) return -EPROTO; - dccp_connect_init(sk); + /* Initialise GAR as per 8.5; AWL/AWH are set in dccp_transmit_skb() */ + dp->dccps_gar = dp->dccps_iss; skb = alloc_skb(sk->sk_prot->max_header, sk->sk_allocation); if (unlikely(skb == NULL)) @@ -508,11 +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; @@ -599,6 +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); } @@ -627,9 +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 @@ -642,6 +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 f5b3464f124..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" @@ -148,6 +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) @@ -158,18 +160,23 @@ static __init int dccpprobe_init(void) spin_lock_init(&dccpw.lock); if (kfifo_alloc(&dccpw.fifo, bufsize, GFP_KERNEL)) return ret; - if (!proc_net_fops_create(&init_net, procname, S_IRUSR, &dccpprobe_fops)) + if (!proc_create(procname, S_IRUSR, init_net.proc_net, &dccpprobe_fops)) goto err0; - try_then_request_module((ret = register_jprobe(&dccp_send_probe)) == 0, - "dccp"); + 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); return ret; @@ -179,7 +186,7 @@ module_init(dccpprobe_init); static __exit void dccpprobe_exit(void) { kfifo_free(&dccpw.fifo); - proc_net_remove(&init_net, procname); + 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 aa4cef374fd..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> @@ -49,6 +50,30 @@ 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; @@ -145,30 +170,6 @@ const char *dccp_packet_name(const int type) EXPORT_SYMBOL_GPL(dccp_packet_name); -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]; -} - -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); @@ -183,7 +184,7 @@ 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); @@ -311,7 +312,7 @@ unsigned int dccp_poll(struct file *file, struct socket *sock, unsigned int mask; struct sock *sk = sock->sk; - sock_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); @@ -335,7 +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, @@ -346,7 +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; } } @@ -472,14 +473,9 @@ static int dccp_setsockopt_ccid(struct sock *sk, int type, if (optlen < 1 || optlen > DCCP_FEAT_MAX_SP_VALS) return -EINVAL; - val = kmalloc(optlen, GFP_KERNEL); - if (val == NULL) - return -ENOMEM; - - if (copy_from_user(val, optval, optlen)) { - kfree(val); - return -EFAULT; - } + 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) @@ -536,6 +532,20 @@ static int do_dccp_setsockopt(struct sock *sk, int level, int optname, 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_qpolicy = val; + break; + case DCCP_SOCKOPT_QPOLICY_TXQLEN: + if (val < 0) + err = -EINVAL; + else + dp->dccps_tx_qlen = val; + break; default: err = -ENOPROTOOPT; break; @@ -643,6 +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); @@ -685,6 +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) { @@ -700,8 +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; } @@ -729,8 +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; @@ -782,7 +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)) { @@ -839,7 +905,7 @@ verify_sock_status: 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: @@ -948,16 +1014,29 @@ 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: @@ -1005,13 +1084,15 @@ EXPORT_SYMBOL_GPL(dccp_shutdown); static inline int dccp_mib_init(void) { - return snmp_mib_init((void __percpu **)dccp_statistics, - sizeof(struct dccp_mib)); + dccp_statistics = alloc_percpu(struct dccp_mib); + if (!dccp_statistics) + return -ENOMEM; + return 0; } static inline void dccp_mib_exit(void) { - snmp_mib_free((void __percpu **)dccp_statistics); + free_percpu(dccp_statistics); } static int thash_entries; @@ -1019,7 +1100,7 @@ module_param(thash_entries, int, 0444); MODULE_PARM_DESC(thash_entries, "Number of ehash buckets"); #ifdef CONFIG_IP_DCCP_DEBUG -int dccp_debug; +bool dccp_debug; module_param(dccp_debug, bool, 0644); MODULE_PARM_DESC(dccp_debug, "Enable debug messages"); @@ -1078,10 +1159,8 @@ static int __init dccp_init(void) goto out_free_bind_bucket_cachep; } - for (i = 0; i <= dccp_hashinfo.ehash_mask; i++) { + for (i = 0; i <= dccp_hashinfo.ehash_mask; i++) INIT_HLIST_NULLS_HEAD(&dccp_hashinfo.ehash[i].chain, i); - INIT_HLIST_NULLS_HEAD(&dccp_hashinfo.ehash[i].twchain, i); - } if (inet_ehash_locks_alloc(&dccp_hashinfo)) goto out_free_dccp_ehash; 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 563943822e5..53731e45403 100644 --- a/net/dccp/sysctl.c +++ b/net/dccp/sysctl.c @@ -20,8 +20,10 @@ /* Boundary values */ static int zero = 0, + one = 1, u8_max = 0xFF; -static unsigned long seqw_min = 32; +static unsigned long seqw_min = DCCPF_SEQ_WMIN, + seqw_max = 0xFFFFFFFF; /* maximum on 32 bit */ static struct ctl_table dccp_default_table[] = { { @@ -31,6 +33,7 @@ static struct ctl_table dccp_default_table[] = { .mode = 0644, .proc_handler = proc_doulongvec_minmax, .extra1 = &seqw_min, /* RFC 4340, 7.5.2 */ + .extra2 = &seqw_max, }, { .procname = "rx_ccid", @@ -56,7 +59,7 @@ static struct ctl_table dccp_default_table[] = { .maxlen = sizeof(sysctl_dccp_request_retries), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, + .extra1 = &one, .extra2 = &u8_max, }, { @@ -96,18 +99,11 @@ static struct ctl_table dccp_default_table[] = { { } }; -static struct ctl_path dccp_path[] = { - { .procname = "net", }, - { .procname = "dccp", }, - { .procname = "default", }, - { } -}; - 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; @@ -116,7 +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 bbfeb5eae46..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, sk); + 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, sk); + dst_negative_advice(sk); } retry_until = sysctl_dccp_retries2; @@ -237,32 +238,35 @@ out: 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); } @@ -276,7 +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; |