aboutsummaryrefslogtreecommitdiff
path: root/net/dccp
diff options
context:
space:
mode:
Diffstat (limited to 'net/dccp')
-rw-r--r--net/dccp/ackvec.c4
-rw-r--r--net/dccp/ccid.h86
-rw-r--r--net/dccp/ccids/Kconfig31
-rw-r--r--net/dccp/ccids/ccid2.c310
-rw-r--r--net/dccp/ccids/ccid2.h40
-rw-r--r--net/dccp/ccids/ccid3.c272
-rw-r--r--net/dccp/ccids/ccid3.h51
-rw-r--r--net/dccp/ccids/lib/loss_interval.c2
-rw-r--r--net/dccp/ccids/lib/packet_history.c39
-rw-r--r--net/dccp/ccids/lib/packet_history.h22
-rw-r--r--net/dccp/ccids/lib/tfrc.h1
-rw-r--r--net/dccp/ccids/lib/tfrc_equation.c14
-rw-r--r--net/dccp/dccp.h61
-rw-r--r--net/dccp/feat.c10
-rw-r--r--net/dccp/feat.h1
-rw-r--r--net/dccp/input.c33
-rw-r--r--net/dccp/ipv4.c14
-rw-r--r--net/dccp/ipv6.c40
-rw-r--r--net/dccp/minisocks.c30
-rw-r--r--net/dccp/options.c49
-rw-r--r--net/dccp/output.c227
-rw-r--r--net/dccp/probe.c1
-rw-r--r--net/dccp/proto.c85
-rw-r--r--net/dccp/timer.c27
24 files changed, 670 insertions, 780 deletions
diff --git a/net/dccp/ackvec.c b/net/dccp/ackvec.c
index 01e4d39fa232..92a6fcb40d7d 100644
--- a/net/dccp/ackvec.c
+++ b/net/dccp/ackvec.c
@@ -82,7 +82,7 @@ int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb)
elapsed_time = delta / 10;
if (elapsed_time != 0 &&
- dccp_insert_option_elapsed_time(sk, skb, elapsed_time))
+ dccp_insert_option_elapsed_time(skb, elapsed_time))
return -1;
avr = dccp_ackvec_record_new();
@@ -201,7 +201,7 @@ static inline int dccp_ackvec_set_buf_head_state(struct dccp_ackvec *av,
const unsigned int packets,
const unsigned char state)
{
- unsigned int gap;
+ long gap;
long new_head;
if (av->av_vec_len + packets > DCCP_MAX_ACKVEC_LEN)
diff --git a/net/dccp/ccid.h b/net/dccp/ccid.h
index 6df6f8ac9636..75c3582a7678 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,
@@ -138,20 +134,48 @@ static inline int ccid_get_current_tx_ccid(struct dccp_sock *dp)
extern void ccid_hc_rx_delete(struct ccid *ccid, struct sock *sk);
extern 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,
diff --git a/net/dccp/ccids/Kconfig b/net/dccp/ccids/Kconfig
index 8408398cd44e..0581143cb800 100644
--- a/net/dccp/ccids/Kconfig
+++ b/net/dccp/ccids/Kconfig
@@ -47,37 +47,6 @@ 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 9b3ae9922be1..6576eae9e779 100644
--- a/net/dccp/ccids/ccid2.c
+++ b/net/dccp/ccids/ccid2.c
@@ -25,59 +25,14 @@
*/
#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;
#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)
@@ -123,12 +78,9 @@ 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)
@@ -156,19 +108,11 @@ static void ccid2_change_l_ack_ratio(struct sock *sk, u32 val)
dp->dccps_l_ack_ratio = val;
}
-static void ccid2_change_srtt(struct ccid2_hc_tx_sock *hc, long val)
-{
- ccid2_pr_debug("change SRTT to %ld\n", val);
- hc->tx_srtt = val;
-}
-
-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)) {
@@ -178,23 +122,17 @@ 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;
@@ -204,23 +142,18 @@ 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)
-{
- struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk);
-
- ccid2_pr_debug("setting RTO timeout=%ld\n", hc->tx_rto);
-
- BUG_ON(timer_pending(&hc->tx_rtotimer));
- sk_reset_timer(sk, &hc->tx_rtotimer, jiffies + hc->tx_rto);
-}
-
-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);
@@ -230,7 +163,7 @@ static void ccid2_hc_tx_packet_sent(struct sock *sk, int more, unsigned int len)
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 = ccid2_time_stamp;
next = hc->tx_seqh->ccid2s_next;
/* check if we need to alloc more space */
@@ -296,23 +229,20 @@ 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
}
@@ -378,17 +308,87 @@ out_invalid_option:
return -1;
}
-static void ccid2_hc_tx_kill_rto_timer(struct sock *sk)
+/**
+ * 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 void ccid2_rtt_estimator(struct sock *sk, const long mrtt)
{
struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk);
+ long m = mrtt ? : 1;
- sk_stop_timer(sk, &hc->tx_rtotimer);
- ccid2_pr_debug("deleted RTO timer\n");
+ 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);
+ /*
+ * This neutralises RTO increase when RTT < SRTT - mdev
+ * (see P. Sarolahti, A. Kuznetsov,"Congestion Control
+ * in Linux TCP", USENIX 2002, pp. 49-62).
+ */
+ if (m > 0)
+ m >>= 3;
+ } else {
+ m -= (hc->tx_mdev >> 2);
+ }
+ hc->tx_mdev += m;
+
+ 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;
+ }
+
+ /*
+ * 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);
+ }
+ }
+
+ /*
+ * 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;
+
+ 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);
@@ -402,93 +402,27 @@ static inline void ccid2_new_ack(struct sock *sk,
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);
-
- if (hc->tx_pipe == 0)
- DCCP_BUG("pipe == 0");
- else
- hc->tx_pipe--;
-
- 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);
@@ -502,6 +436,7 @@ 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);
u64 ackno, seqno;
struct ccid2_seq *seqp;
unsigned char *vector;
@@ -510,7 +445,6 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb)
int done = 0;
unsigned int maxincr = 0;
- ccid2_hc_tx_check_sanity(hc);
/* check reverse path congestion */
seqno = DCCP_SKB_CB(skb)->dccpd_seq;
@@ -620,7 +554,7 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb)
seqp->ccid2s_acked = 1;
ccid2_pr_debug("Got ack for %llu\n",
(unsigned long long)seqp->ccid2s_seq);
- ccid2_hc_tx_dec_pipe(sk);
+ hc->tx_pipe--;
}
if (seqp == hc->tx_seqt) {
done = 1;
@@ -677,7 +611,7 @@ 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;
@@ -695,7 +629,15 @@ 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);
+
+ /* 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);
}
static int ccid2_hc_tx_init(struct ccid *ccid, struct sock *sk)
@@ -707,12 +649,8 @@ 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);
/* Make sure that Ack Ratio is enabled and within bounds. */
max_ratio = DIV_ROUND_UP(hc->tx_cwnd, 2);
@@ -723,15 +661,11 @@ 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 = ccid2_time_stamp;
setup_timer(&hc->tx_rtotimer, ccid2_hc_tx_rto_expire,
(unsigned long)sk);
-
- ccid2_hc_tx_check_sanity(hc);
return 0;
}
@@ -740,7 +674,7 @@ 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]);
diff --git a/net/dccp/ccids/ccid2.h b/net/dccp/ccids/ccid2.h
index 1ec6a30103bb..25cb6b216eda 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;
@@ -42,7 +47,12 @@ struct ccid2_seq {
* 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_rpseq: last consecutive seqno
* @tx_rpdupack: dupacks since rpseq
*/
@@ -55,17 +65,27 @@ 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;
+
u64 tx_rpseq;
int tx_rpdupack;
- unsigned long tx_last_cong;
+ u32 tx_last_cong;
u64 tx_high_ack;
};
+static inline bool ccid2_cwnd_network_limited(struct ccid2_hc_tx_sock *hc)
+{
+ return hc->tx_pipe >= hc->tx_cwnd;
+}
+
struct ccid2_hc_rx_sock {
int rx_data;
};
diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c
index d3235899c7e3..3d604e1349c0 100644
--- a/net/dccp/ccids/ccid3.c
+++ b/net/dccp/ccids/ccid3.c
@@ -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 +90,16 @@ 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));
+ ccid3_pr_debug("t_ipi=%u, s=%u, X=%u\n", hc->tx_t_ipi,
+ hc->tx_s, (unsigned)(hc->tx_x >> 6));
}
static u32 ccid3_hc_tx_idle_rtt(struct ccid3_hc_tx_sock *hc, ktime_t now)
@@ -211,16 +207,19 @@ static void ccid3_hc_tx_no_feedback_timer(unsigned long data)
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,
@@ -256,7 +255,7 @@ 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 +268,11 @@ 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 +289,7 @@ 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 +324,22 @@ 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 +348,10 @@ 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 +364,34 @@ 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
*/
@@ -461,13 +439,12 @@ 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 +459,41 @@ 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 +511,36 @@ 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;
+ 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 +570,6 @@ 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 +595,9 @@ 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 +641,21 @@ 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 +687,11 @@ 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 +801,31 @@ 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 032635776653..1a9933c29672 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 8fc3cbf79071..497723c4d4bb 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] */
diff --git a/net/dccp/ccids/lib/packet_history.c b/net/dccp/ccids/lib/packet_history.c
index 3a4f414e94a0..de8fe294bf0b 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
*/
diff --git a/net/dccp/ccids/lib/packet_history.h b/net/dccp/ccids/lib/packet_history.h
index 7df6c5299999..7ee4a9d9d335 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);
/* Subtraction a-b modulo-16, respects circular wrap-around */
#define SUB16(a, b) (((a) + 16 - (b)) & 0xF)
diff --git a/net/dccp/ccids/lib/tfrc.h b/net/dccp/ccids/lib/tfrc.h
index 01bb48e96c2e..f8ee3f549770 100644
--- a/net/dccp/ccids/lib/tfrc.h
+++ b/net/dccp/ccids/lib/tfrc.h
@@ -57,6 +57,7 @@ static inline u32 tfrc_ewma(const u32 avg, const u32 newval, const u8 weight)
extern u32 tfrc_calc_x(u16 s, u32 R, u32 p);
extern u32 tfrc_calc_x_reverse_lookup(u32 fvalue);
+extern 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);
diff --git a/net/dccp/ccids/lib/tfrc_equation.c b/net/dccp/ccids/lib/tfrc_equation.c
index 22ca1cf0eb55..a052a4377e26 100644
--- a/net/dccp/ccids/lib/tfrc_equation.c
+++ b/net/dccp/ccids/lib/tfrc_equation.c
@@ -687,3 +687,17 @@ 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 a10a61a1ded2..a8ed459508b2 100644
--- a/net/dccp/dccp.h
+++ b/net/dccp/dccp.h
@@ -153,18 +153,27 @@ 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 {
@@ -234,8 +243,9 @@ extern void dccp_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
extern 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);
+extern void dccp_write_xmit(struct sock *sk);
+extern void dccp_write_space(struct sock *sk);
+extern void dccp_flush_write_queue(struct sock *sk, long *time_budget);
extern void dccp_init_xmit_timers(struct sock *sk);
static inline void dccp_clear_xmit_timers(struct sock *sk)
@@ -246,7 +256,6 @@ static inline void dccp_clear_xmit_timers(struct sock *sk)
extern 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);
extern void dccp_set_state(struct sock *sk, const int state);
extern void dccp_done(struct sock *sk);
@@ -415,6 +424,23 @@ static inline void dccp_update_gsr(struct sock *sk, u64 seq)
dp->dccps_gsr = seq;
/* Sequence validity window depends on remote Sequence Window (7.5.1) */
dp->dccps_swl = SUB48(ADD48(dp->dccps_gsr, 1), dp->dccps_r_seq_win / 4);
+ /*
+ * Adjust SWL so that it is not below ISR. In contrast to RFC 4340,
+ * 7.5.1 we perform this check beyond the initial handshake: W/W' are
+ * always > 32, so for the first W/W' packets in the lifetime of a
+ * connection we always have to adjust SWL.
+ * A second reason why we are doing this is that the window depends on
+ * the feature-remote value of Sequence Window: nothing stops the peer
+ * from updating this value while we are busy adjusting SWL for the
+ * first W packets (we would have to count from scratch again then).
+ * Therefore it is safer to always make sure that the Sequence Window
+ * is not artificially extended by a peer who grows SWL downwards by
+ * continually updating the feature-remote Sequence-Window.
+ * If sequence numbers wrap it is bad luck. But that will take a while
+ * (48 bit), and this measure prevents Sequence-number attacks.
+ */
+ if (before48(dp->dccps_swl, dp->dccps_isr))
+ dp->dccps_swl = dp->dccps_isr;
dp->dccps_swh = ADD48(dp->dccps_gsr, (3 * dp->dccps_r_seq_win) / 4);
}
@@ -425,14 +451,16 @@ 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_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 &&
+ return (dp->dccps_hc_rx_ackvec != NULL &&
dccp_ackvec_pending(dp->dccps_hc_rx_ackvec)) ||
inet_csk_ack_scheduled(sk);
}
@@ -446,16 +474,11 @@ 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 int dccp_insert_option_elapsed_time(struct sk_buff *skb, u32 elapsed);
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);
+extern 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);
diff --git a/net/dccp/feat.c b/net/dccp/feat.c
index df7dd26cf07e..568def952722 100644
--- a/net/dccp/feat.c
+++ b/net/dccp/feat.c
@@ -730,16 +730,6 @@ 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)
-{
- /* any changes must be registered before establishing the connection */
- if (sk->sk_state != DCCP_CLOSED)
- return -EISCONN;
- if (dccp_feat_type(feat) != FEAT_NN)
- return -EINVAL;
- return __feat_register_nn(&dccp_sk(sk)->dccps_featneg, feat, 0, val);
-}
/*
* Tracking features whose value depend on the choice of CCID
diff --git a/net/dccp/feat.h b/net/dccp/feat.h
index f96721619def..e56a4e5e634e 100644
--- a/net/dccp/feat.h
+++ b/net/dccp/feat.h
@@ -111,7 +111,6 @@ 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 *);
diff --git a/net/dccp/input.c b/net/dccp/input.c
index 6beb6a7d6fba..265985370fa1 100644
--- a/net/dccp/input.c
+++ b/net/dccp/input.c
@@ -259,7 +259,7 @@ static int dccp_check_seqno(struct sock *sk, struct sk_buff *skb)
sysctl_dccp_sync_ratelimit)))
return 0;
- 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),
@@ -430,7 +430,7 @@ 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));
@@ -441,20 +441,14 @@ 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);
@@ -535,6 +529,8 @@ static int dccp_rcv_respond_partopen_state_process(struct sock *sk,
const struct dccp_hdr *dh,
const unsigned len)
{
+ struct dccp_sock *dp = dccp_sk(sk);
+ u32 sample = dp->dccps_options_received.dccpor_timestamp_echo;
int queued = 0;
switch (dh->dccph_type) {
@@ -559,7 +555,14 @@ 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 ||
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index d9b11ef8694c..3f69ea114829 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -105,7 +105,7 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
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,
@@ -392,7 +392,7 @@ struct sock *dccp_v4_request_recv_sock(struct sock *sk, struct sk_buff *skb,
newsk = dccp_create_openreq_child(sk, req, skb);
if (newsk == NULL)
- goto exit;
+ goto exit_nonewsk;
sk_setup_caps(newsk, dst);
@@ -409,16 +409,20 @@ struct sock *dccp_v4_request_recv_sock(struct sock *sk, struct sk_buff *skb,
dccp_sync_mss(newsk, dst_mtu(dst));
+ if (__inet_inherit_port(sk, newsk) < 0) {
+ sock_put(newsk);
+ goto 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;
}
@@ -475,7 +479,7 @@ static struct dst_entry* dccp_v4_route_skb(struct net *net, struct sock *sk,
return NULL;
}
- return &rt->u.dst;
+ return &rt->dst;
}
static int dccp_v4_send_response(struct sock *sk, struct request_sock *req,
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 091698899594..dca711df9b60 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -248,7 +248,7 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *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 in6_addr *final_p, final;
struct flowi fl;
int err = -1;
struct dst_entry *dst;
@@ -265,13 +265,7 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req,
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;
- }
+ final_p = fl6_update_dst(&fl, opt, &final);
err = ip6_dst_lookup(sk, &dst, &fl);
if (err)
@@ -545,19 +539,13 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
goto out_overflow;
if (dst == NULL) {
- struct in6_addr *final_p = NULL, final;
+ struct in6_addr *final_p, 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;
- }
+ final_p = fl6_update_dst(&fl, opt, &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;
@@ -576,7 +564,7 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
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
@@ -644,18 +632,22 @@ 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) {
+ sock_put(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;
}
@@ -885,7 +877,7 @@ 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 in6_addr *saddr = NULL, *final_p, final;
struct flowi fl;
struct dst_entry *dst;
int addr_type;
@@ -988,13 +980,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
fl.fl_ip_sport = inet->inet_sport;
security_sk_classify_flow(sk, &fl);
- if (np->opt != NULL && np->opt->srcrt != NULL) {
- const struct rt0_hdr *rt0 = (struct rt0_hdr *)np->opt->srcrt;
-
- ipv6_addr_copy(&final, &fl.fl6_dst);
- ipv6_addr_copy(&fl.fl6_dst, rt0->addr);
- final_p = &final;
- }
+ final_p = fl6_update_dst(&fl, np->opt, &final);
err = ip6_dst_lookup(sk, &dst, &fl);
if (err)
diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index 128b089d3aef..d7041a0963af 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -121,30 +121,18 @@ struct sock *dccp_create_openreq_child(struct sock *sk,
*
* Choose S.ISS (initial seqno) or set from Init Cookies
* Initialize S.GAR := S.ISS
- * Set S.ISR, S.GSR, S.SWL, S.SWH from packet or Init Cookies
- */
- newdp->dccps_gar = newdp->dccps_iss = dreq->dreq_iss;
- dccp_update_gss(newsk, dreq->dreq_iss);
-
- newdp->dccps_isr = dreq->dreq_isr;
- dccp_update_gsr(newsk, dreq->dreq_isr);
-
- /*
- * SWL and AWL are initially adjusted so that they are not less than
- * the initial Sequence Numbers received and sent, respectively:
- * SWL := max(GSR + 1 - floor(W/4), ISR),
- * AWL := max(GSS - W' + 1, ISS).
- * These adjustments MUST be applied only at the beginning of the
- * connection.
+ * Set S.ISR, S.GSR from packet (or Init Cookies)
+ *
+ * Setting AWL/AWH and SWL/SWH happens as part of the feature
+ * activation below, as these windows all depend on the local
+ * and remote Sequence Window feature values (7.5.2).
*/
- dccp_set_seqno(&newdp->dccps_swl,
- max48(newdp->dccps_swl, newdp->dccps_isr));
- dccp_set_seqno(&newdp->dccps_awl,
- max48(newdp->dccps_awl, newdp->dccps_iss));
+ newdp->dccps_gss = newdp->dccps_iss = dreq->dreq_iss;
+ newdp->dccps_gar = newdp->dccps_iss;
+ newdp->dccps_gsr = newdp->dccps_isr = dreq->dreq_isr;
/*
- * Activate features after initialising the sequence numbers,
- * since CCID initialisation may depend on GSS, ISR, ISS etc.
+ * Activate features: initialise CCIDs, sequence windows etc.
*/
if (dccp_feat_activate_values(newsk, &dreq->dreq_featneg)) {
/* It is still raw copy of parent, so invalidate
diff --git a/net/dccp/options.c b/net/dccp/options.c
index 07395f861d35..cd3061813009 100644
--- a/net/dccp/options.c
+++ b/net/dccp/options.c
@@ -96,18 +96,11 @@ 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;
@@ -170,6 +163,8 @@ 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 +221,15 @@ 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_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 "
@@ -299,9 +286,8 @@ static inline u8 dccp_ndp_len(const u64 ndp)
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;
@@ -354,8 +340,7 @@ 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)
+int dccp_insert_option_elapsed_time(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;
@@ -386,17 +371,15 @@ int dccp_insert_option_elapsed_time(struct sock *sk, struct sk_buff *skb,
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)
@@ -531,9 +514,9 @@ 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 &&
@@ -564,6 +547,10 @@ 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 aadbdb58758b..45b91853f5ae 100644
--- a/net/dccp/output.c
+++ b/net/dccp/output.c
@@ -209,108 +209,150 @@ void dccp_write_space(struct sock *sk)
}
/**
- * 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;
+
+ prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+ sk->sk_write_pending++;
+ release_sock(sk);
+
+ remaining = schedule_timeout(delay);
+
+ lock_sock(sk);
+ sk->sk_write_pending--;
+ finish_wait(sk_sleep(sk), &wait);
+
+ if (signal_pending(current) || sk->sk_err)
+ return -1;
+ return remaining;
+}
+
+/**
+ * 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 = skb_dequeue(&sk->sk_write_queue);
+
+ if (unlikely(skb == NULL))
+ return;
+ len = skb->len;
- do {
- dccp_pr_debug("delayed send by %d msec\n", delay);
- jiffdelay = msecs_to_jiffies(delay);
+ 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);
+ }
- prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+ 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;
+ }
- sk->sk_write_pending++;
- release_sock(sk);
- schedule_timeout(jiffdelay);
- lock_sock(sk);
- sk->sk_write_pending--;
+ 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 (sk->sk_err)
- goto do_error;
- if (signal_pending(current))
- goto do_interrupted;
+/**
+ * dccp_flush_write_queue - Drain queue at end of connection
+ * Since dccp_sendmsg queues packets without waiting for them to be sent, it may
+ * happen that the TX queue is not empty at the end of a connection. We give the
+ * HC-sender CCID a grace period of up to @time_budget jiffies. If this function
+ * returns with a non-empty write queue, it will be purged later.
+ */
+void dccp_flush_write_queue(struct sock *sk, long *time_budget)
+{
+ struct dccp_sock *dp = dccp_sk(sk);
+ struct sk_buff *skb;
+ long delay, rc;
+ while (*time_budget > 0 && (skb = skb_peek(&sk->sk_write_queue))) {
rc = ccid_hc_tx_send_packet(dp->dccps_hc_tx_ccid, sk, skb);
- } while ((delay = rc) > 0);
-out:
- finish_wait(sk_sleep(sk), &wait);
- return rc;
-
-do_error:
- rc = -EPIPE;
- goto out;
-do_interrupted:
- rc = -EINTR;
- goto out;
+
+ 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, int block)
+void dccp_write_xmit(struct sock *sk)
{
struct dccp_sock *dp = dccp_sk(sk);
struct sk_buff *skb;
while ((skb = skb_peek(&sk->sk_write_queue))) {
- int err = ccid_hc_tx_send_packet(dp->dccps_hc_tx_ccid, sk, skb);
-
- if (err > 0) {
- if (!block) {
- sk_reset_timer(sk, &dp->dccps_xmit_timer,
- msecs_to_jiffies(err)+jiffies);
- break;
- } else
- err = dccp_wait_for_ccid(sk, skb, err);
- if (err && err != -EINTR)
- DCCP_BUG("err=%d after dccp_wait_for_ccid", err);
- }
+ int 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:
+ 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:
+ skb_dequeue(&sk->sk_write_queue);
kfree_skb(skb);
+ dccp_pr_debug("packet discarded due to err=%d\n", rc);
}
}
}
@@ -474,8 +516,9 @@ 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);
@@ -485,22 +528,12 @@ 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))
@@ -516,6 +549,7 @@ int dccp_connect(struct sock *sk)
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;
@@ -630,7 +664,6 @@ 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));
/*
diff --git a/net/dccp/probe.c b/net/dccp/probe.c
index 078e48d442fd..33d0e6297c21 100644
--- a/net/dccp/probe.c
+++ b/net/dccp/probe.c
@@ -149,6 +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)
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index b03ecf6b2bb0..ef343d53fcea 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -50,6 +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;
@@ -146,30 +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);
@@ -473,14 +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)
@@ -731,7 +726,13 @@ int dccp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
goto out_discard;
skb_queue_tail(&sk->sk_write_queue, skb);
- dccp_write_xmit(sk,0);
+ /*
+ * 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;
@@ -949,16 +950,29 @@ 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:
@@ -1007,7 +1021,8 @@ EXPORT_SYMBOL_GPL(dccp_shutdown);
static inline int dccp_mib_init(void)
{
return snmp_mib_init((void __percpu **)dccp_statistics,
- sizeof(struct dccp_mib));
+ sizeof(struct dccp_mib),
+ __alignof__(struct dccp_mib));
}
static inline void dccp_mib_exit(void)
diff --git a/net/dccp/timer.c b/net/dccp/timer.c
index 1a9aa05d4dc4..7587870b7040 100644
--- a/net/dccp/timer.c
+++ b/net/dccp/timer.c
@@ -237,32 +237,35 @@ 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);
}
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-03 03:56:05 +0000