/*
* 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
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);
-
- if (avr != NULL)
- INIT_LIST_HEAD(&avr->avr_node);
+ struct dccp_ackvec *av = kmem_cache_zalloc(dccp_ackvec_slab, priority);
- 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(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);
}
/*
long gap;
long new_head;
- if (av->av_vec_len + packets > DCCP_MAX_ACKVEC_LEN)
+ if (av->av_vec_len + packets > DCCPAV_MAX_ACKVEC_LEN)
return -ENOBUFS;
gap = packets - 1;
if (new_head < 0) {
if (gap > 0) {
- memset(av->av_buf, DCCP_ACKVEC_STATE_NOT_RECEIVED,
+ memset(av->av_buf, DCCPAV_NOT_RECEIVED,
gap + new_head + 1);
gap = -new_head;
}
- new_head += DCCP_MAX_ACKVEC_LEN;
+ new_head += DCCPAV_MAX_ACKVEC_LEN;
}
av->av_buf_head = new_head;
if (gap > 0)
memset(av->av_buf + av->av_buf_head + 1,
- DCCP_ACKVEC_STATE_NOT_RECEIVED, gap);
+ DCCPAV_NOT_RECEIVED, gap);
av->av_buf[av->av_buf_head] = state;
av->av_vec_len += packets;
int dccp_ackvec_add(struct dccp_ackvec *av, const struct sock *sk,
const u64 ackno, const u8 state)
{
+ u8 *cur_head = av->av_buf + av->av_buf_head,
+ *buf_end = av->av_buf + DCCPAV_MAX_ACKVEC_LEN;
/*
* Check at the right places if the buffer is full, if it is, tell the
* caller to start dropping packets till the HC-Sender acks our ACK
/* See if this is the first ackno being inserted */
if (av->av_vec_len == 0) {
- av->av_buf[av->av_buf_head] = state;
+ *cur_head = state;
av->av_vec_len = 1;
} else if (after48(ackno, av->av_buf_ackno)) {
const u64 delta = dccp_delta_seqno(av->av_buf_ackno, ackno);
* Look if the state of this packet is the same as the
* previous ackno and if so if we can bump the head len.
*/
- if (delta == 1 &&
- dccp_ackvec_state(av, av->av_buf_head) == state &&
- dccp_ackvec_len(av, av->av_buf_head) < DCCP_ACKVEC_LEN_MASK)
- av->av_buf[av->av_buf_head]++;
+ if (delta == 1 && dccp_ackvec_state(cur_head) == state &&
+ dccp_ackvec_runlen(cur_head) < DCCPAV_MAX_RUNLEN)
+ *cur_head += 1;
else if (dccp_ackvec_set_buf_head_state(av, delta, state))
return -ENOBUFS;
} else {
* could reduce the complexity of this scan.)
*/
u64 delta = dccp_delta_seqno(ackno, av->av_buf_ackno);
- u32 index = av->av_buf_head;
while (1) {
- const u8 len = dccp_ackvec_len(av, index);
- const u8 av_state = dccp_ackvec_state(av, index);
+ const u8 len = dccp_ackvec_runlen(cur_head);
/*
* valid packets not yet in av_buf have a reserved
* entry, with a len equal to 0.
*/
- if (av_state == DCCP_ACKVEC_STATE_NOT_RECEIVED &&
- len == 0 && delta == 0) { /* Found our
- reserved seat! */
+ if (*cur_head == DCCPAV_NOT_RECEIVED && delta == 0) {
dccp_pr_debug("Found %llu reserved seat!\n",
(unsigned long long)ackno);
- av->av_buf[index] = state;
+ *cur_head = state;
goto out;
}
/* len == 0 means one packet */
goto out_duplicate;
delta -= len + 1;
- if (++index == DCCP_MAX_ACKVEC_LEN)
- index = 0;
+ if (++cur_head == buf_end)
+ cur_head = av->av_buf;
}
}
av->av_buf_ackno = ackno;
- av->av_time = ktime_get_real();
out:
return 0;
if (av->av_buf_head <= avr->avr_ack_ptr)
av->av_vec_len = avr->avr_ack_ptr - av->av_buf_head;
else
- av->av_vec_len = DCCP_MAX_ACKVEC_LEN - 1 -
+ av->av_vec_len = DCCPAV_MAX_ACKVEC_LEN - 1 -
av->av_buf_head + avr->avr_ack_ptr;
/* free records */
list_for_each_entry_safe_from(avr, next, &av->av_records, avr_node) {
- list_del_init(&avr->avr_node);
- dccp_ackvec_record_delete(avr);
+ list_del(&avr->avr_node);
+ kmem_cache_free(dccp_ackvec_record_slab, avr);
}
}
if (ackno == avr->avr_ack_seqno) {
dccp_pr_debug("%s ACK packet 0, len=%d, ack_seqno=%llu, "
"ack_ackno=%llu, ACKED!\n",
- dccp_role(sk), 1,
+ dccp_role(sk), avr->avr_ack_runlen,
(unsigned long long)avr->avr_ack_seqno,
(unsigned long long)avr->avr_ack_ackno);
dccp_ackvec_throw_record(av, avr);
*/
avr = list_entry(av->av_records.next, struct dccp_ackvec_record, avr_node);
while (i--) {
- const u8 rl = *vector & DCCP_ACKVEC_LEN_MASK;
+ const u8 rl = dccp_ackvec_runlen(vector);
u64 ackno_end_rl;
dccp_set_seqno(&ackno_end_rl, *ackno - rl);
break;
found:
if (between48(avr->avr_ack_seqno, ackno_end_rl, *ackno)) {
- const u8 state = *vector & DCCP_ACKVEC_STATE_MASK;
- if (state != DCCP_ACKVEC_STATE_NOT_RECEIVED) {
+ if (dccp_ackvec_state(vector) != DCCPAV_NOT_RECEIVED) {
dccp_pr_debug("%s ACK vector 0, len=%d, "
"ack_seqno=%llu, ack_ackno=%llu, "
"ACKED!\n",
return 0;
}
+/**
+ * dccp_ackvec_clear_state - Perform house-keeping / garbage-collection
+ * This routine is called when the peer acknowledges the receipt of Ack Vectors
+ * up to and including @ackno. While based on on section A.3 of RFC 4340, here
+ * are additional precautions to prevent corrupted buffer state. In particular,
+ * we use tail_ackno to identify outdated records; it always marks the earliest
+ * packet of group (2) in 11.4.2.
+ */
+void dccp_ackvec_clear_state(struct dccp_ackvec *av, const u64 ackno)
+ {
+ struct dccp_ackvec_record *avr, *next;
+ u8 runlen_now, eff_runlen;
+ s64 delta;
+
+ avr = dccp_ackvec_lookup(&av->av_records, ackno);
+ if (avr == NULL)
+ return;
+ /*
+ * Deal with outdated acknowledgments: this arises when e.g. there are
+ * several old records and the acks from the peer come in slowly. In
+ * that case we may still have records that pre-date tail_ackno.
+ */
+ delta = dccp_delta_seqno(av->av_tail_ackno, avr->avr_ack_ackno);
+ if (delta < 0)
+ goto free_records;
+ /*
+ * Deal with overlapping Ack Vectors: don't subtract more than the
+ * number of packets between tail_ackno and ack_ackno.
+ */
+ eff_runlen = delta < avr->avr_ack_runlen ? delta : avr->avr_ack_runlen;
+
+ runlen_now = dccp_ackvec_runlen(av->av_buf + avr->avr_ack_ptr);
+ /*
+ * The run length of Ack Vector cells does not decrease over time. If
+ * the run length is the same as at the time the Ack Vector was sent, we
+ * free the ack_ptr cell. That cell can however not be freed if the run
+ * length has increased: in this case we need to move the tail pointer
+ * backwards (towards higher indices), to its next-oldest neighbour.
+ */
+ if (runlen_now > eff_runlen) {
+
+ av->av_buf[avr->avr_ack_ptr] -= eff_runlen + 1;
+ av->av_buf_tail = __ackvec_idx_add(avr->avr_ack_ptr, 1);
+
+ /* This move may not have cleared the overflow flag. */
+ if (av->av_overflow)
+ av->av_overflow = (av->av_buf_head == av->av_buf_tail);
+ } else {
+ av->av_buf_tail = avr->avr_ack_ptr;
+ /*
+ * We have made sure that avr points to a valid cell within the
+ * buffer. This cell is either older than head, or equals head
+ * (empty buffer): in both cases we no longer have any overflow.
+ */
+ av->av_overflow = 0;
+ }
+
+ /*
+ * The peer has acknowledged up to and including ack_ackno. Hence the
+ * first packet in group (2) of 11.4.2 is the successor of ack_ackno.
+ */
+ av->av_tail_ackno = ADD48(avr->avr_ack_ackno, 1);
+
+free_records:
+ list_for_each_entry_safe_from(avr, next, &av->av_records, avr_node) {
+ list_del(&avr->avr_node);
+ kmem_cache_free(dccp_ackvec_record_slab, avr);
+ }
+}
+
int __init dccp_ackvec_init(void)
{
dccp_ackvec_slab = kmem_cache_create("dccp_ackvec",
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;
git://bbs.cooldavid.org / net-next-2.6.git / blobdiff