linux_old1/net/dccp/options.c

621 lines
16 KiB
C
Raw Normal View History

/*
* net/dccp/options.c
*
* An implementation of the DCCP protocol
* Copyright (c) 2005 Aristeu Sergio Rozanski Filho <aris@cathedrallabs.org>
* Copyright (c) 2005 Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
* Copyright (c) 2005 Ian McDonald <ian.mcdonald@jandi.co.nz>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <linux/dccp.h>
#include <linux/module.h>
#include <linux/types.h>
#include <asm/unaligned.h>
#include <linux/kernel.h>
#include <linux/skbuff.h>
#include "ackvec.h"
#include "ccid.h"
#include "dccp.h"
#include "feat.h"
u64 dccp_decode_value_var(const u8 *bf, const u8 len)
{
u64 value = 0;
if (len >= DCCP_OPTVAL_MAXLEN)
value += ((u64)*bf++) << 40;
if (len > 4)
value += ((u64)*bf++) << 32;
if (len > 3)
value += ((u64)*bf++) << 24;
if (len > 2)
value += ((u64)*bf++) << 16;
if (len > 1)
value += ((u64)*bf++) << 8;
if (len > 0)
value += *bf;
return value;
}
/**
* dccp_parse_options - Parse DCCP options present in @skb
* @sk: client|server|listening dccp socket (when @dreq != NULL)
* @dreq: request socket to use during connection setup, or NULL
*/
int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq,
struct sk_buff *skb)
{
struct dccp_sock *dp = dccp_sk(sk);
const struct dccp_hdr *dh = dccp_hdr(skb);
const u8 pkt_type = DCCP_SKB_CB(skb)->dccpd_type;
u64 ackno = DCCP_SKB_CB(skb)->dccpd_ack_seq;
unsigned char *options = (unsigned char *)dh + dccp_hdr_len(skb);
unsigned char *opt_ptr = options;
const unsigned char *opt_end = (unsigned char *)dh +
(dh->dccph_doff * 4);
struct dccp_options_received *opt_recv = &dp->dccps_options_received;
unsigned char opt, len;
unsigned char *value;
u32 elapsed_time;
__be32 opt_val;
int rc;
int mandatory = 0;
memset(opt_recv, 0, sizeof(*opt_recv));
opt = len = 0;
while (opt_ptr != opt_end) {
opt = *opt_ptr++;
len = 0;
value = NULL;
/* Check if this isn't a single byte option */
if (opt > DCCPO_MAX_RESERVED) {
if (opt_ptr == opt_end)
goto out_nonsensical_length;
len = *opt_ptr++;
if (len < 2)
goto out_nonsensical_length;
/*
* Remove the type and len fields, leaving
* just the value size
*/
len -= 2;
value = opt_ptr;
opt_ptr += len;
if (opt_ptr > opt_end)
goto out_nonsensical_length;
}
/*
* 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 >= DCCPO_MIN_RX_CCID_SPECIFIC ||
opt == DCCPO_ACK_VECTOR_0 || opt == DCCPO_ACK_VECTOR_1))
goto ignore_option;
switch (opt) {
case DCCPO_PADDING:
break;
case DCCPO_MANDATORY:
if (mandatory)
goto out_invalid_option;
if (pkt_type != DCCP_PKT_DATA)
mandatory = 1;
break;
case DCCPO_NDP_COUNT:
if (len > 6)
goto out_invalid_option;
opt_recv->dccpor_ndp = dccp_decode_value_var(value, len);
dccp_pr_debug("%s opt: NDP count=%llu\n", dccp_role(sk),
(unsigned long long)opt_recv->dccpor_ndp);
break;
case DCCPO_CHANGE_L ... DCCPO_CONFIRM_R:
if (pkt_type == DCCP_PKT_DATA) /* RFC 4340, 6 */
break;
rc = dccp_feat_parse_options(sk, dreq, mandatory, opt,
*value, value + 1, len - 1);
if (rc)
goto out_featneg_failed;
break;
case DCCPO_ACK_VECTOR_0:
case DCCPO_ACK_VECTOR_1:
if (dccp_packet_without_ack(skb)) /* RFC 4340, 11.4 */
break;
dccp ccid-2: Phase out the use of boolean Ack Vector sysctl This removes the use of the sysctl and the minisock variable for the Send Ack Vector feature, which is now handled fully dynamically via feature negotiation; i.e. when CCID2 is enabled, Ack Vectors are automatically enabled (as per RFC 4341, 4.). Using a sysctl in parallel to this implementation would open the door to crashes, since much of the code relies on tests of the boolean minisock / sysctl variable. Thus, this patch replaces all tests of type if (dccp_msk(sk)->dccpms_send_ack_vector) /* ... */ with if (dp->dccps_hc_rx_ackvec != NULL) /* ... */ The dccps_hc_rx_ackvec is allocated by the dccp_hdlr_ackvec() when feature negotiation concluded that Ack Vectors are to be used on the half-connection. Otherwise, it is NULL (due to dccp_init_sock/dccp_create_openreq_child), so that the test is a valid one. The activation handler for Ack Vectors is called as soon as the feature negotiation has concluded at the * server when the Ack marking the transition RESPOND => OPEN arrives; * client after it has sent its ACK, marking the transition REQUEST => PARTOPEN. Adding the sequence number of the Response packet to the Ack Vector has been removed, since (a) connection establishment implies that the Response has been received; (b) the CCIDs only look at packets received in the (PART)OPEN state, i.e. this entry will always be ignored; (c) it can not be used for anything useful - to detect loss for instance, only packets received after the loss can serve as pseudo-dupacks. Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Acked-by: Ian McDonald <ian.mcdonald@jandi.co.nz>
2008-09-04 13:30:19 +08:00
if (dp->dccps_hc_rx_ackvec != NULL &&
dccp_ackvec_parse(sk, skb, &ackno, opt, value, len))
goto out_invalid_option;
break;
case DCCPO_TIMESTAMP:
if (len != 4)
goto out_invalid_option;
[DCCP]: Handle timestamps on Request/Response exchange separately In DCCP, timestamps can occur on packets anytime, CCID3 uses a timestamp(/echo) on the Request/Response exchange. This patch addresses the following situation: * timestamps are recorded on the listening socket; * Responses are sent from dccp_request_sockets; * suppose two connections reach the listening socket with very small time in between: * the first timestamp value gets overwritten by the second connection request. This is not really good, so this patch separates timestamps into * those which are received by the server during the initial handshake (on dccp_request_sock); * those which are received by the client or the client after connection establishment. As before, a timestamp of 0 is regarded as indicating that no (meaningful) timestamp has been received (in addition, a warning message is printed if hosts send 0-valued timestamps). The timestamp-echoing now works as follows: * when a timestamp is present on the initial Request, it is placed into dreq, due to the call to dccp_parse_options in dccp_v{4,6}_conn_request; * when a timestamp is present on the Ack leading from RESPOND => OPEN, it is copied over from the request_sock into the child cocket in dccp_create_openreq_child; * timestamps received on an (established) dccp_sock are treated as before. Since Elapsed Time is measured in hundredths of milliseconds (13.2), the new dccp_timestamp() function is used, as it is expected that the time between receiving the timestamp and sending the timestamp echo will be very small against the wrap-around time. As a byproduct, this allows smaller timestamping-time fields. Furthermore, inserting the Timestamp Echo option has been taken out of the block starting with '!dccp_packet_without_ack()', since Timestamp Echo can be carried on any packet (5.8 and 13.3). Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Acked-by: Ian McDonald <ian.mcdonald@jandi.co.nz> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-13 22:37:19 +08:00
/*
* RFC 4340 13.1: "The precise time corresponding to
* Timestamp Value zero is not specified". We use
* zero to indicate absence of a meaningful timestamp.
*/
opt_val = get_unaligned((__be32 *)value);
[DCCP]: Handle timestamps on Request/Response exchange separately In DCCP, timestamps can occur on packets anytime, CCID3 uses a timestamp(/echo) on the Request/Response exchange. This patch addresses the following situation: * timestamps are recorded on the listening socket; * Responses are sent from dccp_request_sockets; * suppose two connections reach the listening socket with very small time in between: * the first timestamp value gets overwritten by the second connection request. This is not really good, so this patch separates timestamps into * those which are received by the server during the initial handshake (on dccp_request_sock); * those which are received by the client or the client after connection establishment. As before, a timestamp of 0 is regarded as indicating that no (meaningful) timestamp has been received (in addition, a warning message is printed if hosts send 0-valued timestamps). The timestamp-echoing now works as follows: * when a timestamp is present on the initial Request, it is placed into dreq, due to the call to dccp_parse_options in dccp_v{4,6}_conn_request; * when a timestamp is present on the Ack leading from RESPOND => OPEN, it is copied over from the request_sock into the child cocket in dccp_create_openreq_child; * timestamps received on an (established) dccp_sock are treated as before. Since Elapsed Time is measured in hundredths of milliseconds (13.2), the new dccp_timestamp() function is used, as it is expected that the time between receiving the timestamp and sending the timestamp echo will be very small against the wrap-around time. As a byproduct, this allows smaller timestamping-time fields. Furthermore, inserting the Timestamp Echo option has been taken out of the block starting with '!dccp_packet_without_ack()', since Timestamp Echo can be carried on any packet (5.8 and 13.3). Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Acked-by: Ian McDonald <ian.mcdonald@jandi.co.nz> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-13 22:37:19 +08:00
if (unlikely(opt_val == 0)) {
DCCP_WARN("Timestamp with zero value\n");
break;
}
[DCCP]: Handle timestamps on Request/Response exchange separately In DCCP, timestamps can occur on packets anytime, CCID3 uses a timestamp(/echo) on the Request/Response exchange. This patch addresses the following situation: * timestamps are recorded on the listening socket; * Responses are sent from dccp_request_sockets; * suppose two connections reach the listening socket with very small time in between: * the first timestamp value gets overwritten by the second connection request. This is not really good, so this patch separates timestamps into * those which are received by the server during the initial handshake (on dccp_request_sock); * those which are received by the client or the client after connection establishment. As before, a timestamp of 0 is regarded as indicating that no (meaningful) timestamp has been received (in addition, a warning message is printed if hosts send 0-valued timestamps). The timestamp-echoing now works as follows: * when a timestamp is present on the initial Request, it is placed into dreq, due to the call to dccp_parse_options in dccp_v{4,6}_conn_request; * when a timestamp is present on the Ack leading from RESPOND => OPEN, it is copied over from the request_sock into the child cocket in dccp_create_openreq_child; * timestamps received on an (established) dccp_sock are treated as before. Since Elapsed Time is measured in hundredths of milliseconds (13.2), the new dccp_timestamp() function is used, as it is expected that the time between receiving the timestamp and sending the timestamp echo will be very small against the wrap-around time. As a byproduct, this allows smaller timestamping-time fields. Furthermore, inserting the Timestamp Echo option has been taken out of the block starting with '!dccp_packet_without_ack()', since Timestamp Echo can be carried on any packet (5.8 and 13.3). Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Acked-by: Ian McDonald <ian.mcdonald@jandi.co.nz> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-13 22:37:19 +08:00
if (dreq != NULL) {
dreq->dreq_timestamp_echo = ntohl(opt_val);
dreq->dreq_timestamp_time = dccp_timestamp();
} else {
opt_recv->dccpor_timestamp =
dp->dccps_timestamp_echo = ntohl(opt_val);
dp->dccps_timestamp_time = dccp_timestamp();
}
dccp_pr_debug("%s rx opt: TIMESTAMP=%u, ackno=%llu\n",
[DCCP]: Handle timestamps on Request/Response exchange separately In DCCP, timestamps can occur on packets anytime, CCID3 uses a timestamp(/echo) on the Request/Response exchange. This patch addresses the following situation: * timestamps are recorded on the listening socket; * Responses are sent from dccp_request_sockets; * suppose two connections reach the listening socket with very small time in between: * the first timestamp value gets overwritten by the second connection request. This is not really good, so this patch separates timestamps into * those which are received by the server during the initial handshake (on dccp_request_sock); * those which are received by the client or the client after connection establishment. As before, a timestamp of 0 is regarded as indicating that no (meaningful) timestamp has been received (in addition, a warning message is printed if hosts send 0-valued timestamps). The timestamp-echoing now works as follows: * when a timestamp is present on the initial Request, it is placed into dreq, due to the call to dccp_parse_options in dccp_v{4,6}_conn_request; * when a timestamp is present on the Ack leading from RESPOND => OPEN, it is copied over from the request_sock into the child cocket in dccp_create_openreq_child; * timestamps received on an (established) dccp_sock are treated as before. Since Elapsed Time is measured in hundredths of milliseconds (13.2), the new dccp_timestamp() function is used, as it is expected that the time between receiving the timestamp and sending the timestamp echo will be very small against the wrap-around time. As a byproduct, this allows smaller timestamping-time fields. Furthermore, inserting the Timestamp Echo option has been taken out of the block starting with '!dccp_packet_without_ack()', since Timestamp Echo can be carried on any packet (5.8 and 13.3). Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Acked-by: Ian McDonald <ian.mcdonald@jandi.co.nz> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-13 22:37:19 +08:00
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)
goto out_invalid_option;
opt_val = get_unaligned((__be32 *)value);
opt_recv->dccpor_timestamp_echo = ntohl(opt_val);
dccp_pr_debug("%s rx opt: TIMESTAMP_ECHO=%u, len=%d, "
"ackno=%llu", dccp_role(sk),
opt_recv->dccpor_timestamp_echo,
len + 2,
(unsigned long long)
DCCP_SKB_CB(skb)->dccpd_ack_seq);
value += 4;
if (len == 4) { /* no elapsed time included */
dccp_pr_debug_cat("\n");
break;
}
if (len == 6) { /* 2-byte elapsed time */
__be16 opt_val2 = get_unaligned((__be16 *)value);
elapsed_time = ntohs(opt_val2);
} else { /* 4-byte elapsed time */
opt_val = get_unaligned((__be32 *)value);
elapsed_time = ntohl(opt_val);
}
dccp_pr_debug_cat(", ELAPSED_TIME=%u\n", elapsed_time);
/* Give precedence to the biggest ELAPSED_TIME */
if (elapsed_time > opt_recv->dccpor_elapsed_time)
opt_recv->dccpor_elapsed_time = elapsed_time;
break;
case DCCPO_ELAPSED_TIME:
if (dccp_packet_without_ack(skb)) /* RFC 4340, 13.2 */
break;
if (len == 2) {
__be16 opt_val2 = get_unaligned((__be16 *)value);
elapsed_time = ntohs(opt_val2);
} else if (len == 4) {
opt_val = get_unaligned((__be32 *)value);
elapsed_time = ntohl(opt_val);
} else {
goto out_invalid_option;
}
if (elapsed_time > opt_recv->dccpor_elapsed_time)
opt_recv->dccpor_elapsed_time = elapsed_time;
dccp_pr_debug("%s rx opt: ELAPSED_TIME=%d\n",
dccp_role(sk), elapsed_time);
break;
case DCCPO_MIN_RX_CCID_SPECIFIC ... DCCPO_MAX_RX_CCID_SPECIFIC:
if (ccid_hc_rx_parse_options(dp->dccps_hc_rx_ccid, sk,
pkt_type, opt, value, len))
goto out_invalid_option;
break;
case DCCPO_MIN_TX_CCID_SPECIFIC ... DCCPO_MAX_TX_CCID_SPECIFIC:
if (ccid_hc_tx_parse_options(dp->dccps_hc_tx_ccid, sk,
pkt_type, opt, value, len))
goto out_invalid_option;
break;
default:
DCCP_CRIT("DCCP(%p): option %d(len=%d) not "
"implemented, ignoring", sk, opt, len);
break;
}
ignore_option:
if (opt != DCCPO_MANDATORY)
mandatory = 0;
}
/* mandatory was the last byte in option list -> reset connection */
if (mandatory)
goto out_invalid_option;
out_nonsensical_length:
/* RFC 4340, 5.8: ignore option and all remaining option space */
return 0;
out_invalid_option:
DCCP_INC_STATS_BH(DCCP_MIB_INVALIDOPT);
rc = DCCP_RESET_CODE_OPTION_ERROR;
out_featneg_failed:
DCCP_WARN("DCCP(%p): Option %d (len=%d) error=%u\n", sk, opt, len, rc);
DCCP_SKB_CB(skb)->dccpd_reset_code = rc;
DCCP_SKB_CB(skb)->dccpd_reset_data[0] = opt;
DCCP_SKB_CB(skb)->dccpd_reset_data[1] = len > 0 ? value[0] : 0;
DCCP_SKB_CB(skb)->dccpd_reset_data[2] = len > 1 ? value[1] : 0;
return -1;
}
EXPORT_SYMBOL_GPL(dccp_parse_options);
void dccp_encode_value_var(const u64 value, u8 *to, const u8 len)
{
if (len >= DCCP_OPTVAL_MAXLEN)
*to++ = (value & 0xFF0000000000ull) >> 40;
if (len > 4)
*to++ = (value & 0xFF00000000ull) >> 32;
if (len > 3)
*to++ = (value & 0xFF000000) >> 24;
if (len > 2)
*to++ = (value & 0xFF0000) >> 16;
if (len > 1)
*to++ = (value & 0xFF00) >> 8;
if (len > 0)
*to++ = (value & 0xFF);
}
static inline u8 dccp_ndp_len(const u64 ndp)
{
if (likely(ndp <= 0xFF))
return 1;
return likely(ndp <= USHORT_MAX) ? 2 : (ndp <= UINT_MAX ? 4 : 6);
}
int dccp_insert_option(struct sock *sk, struct sk_buff *skb,
const unsigned char option,
const void *value, const unsigned char len)
{
unsigned char *to;
if (DCCP_SKB_CB(skb)->dccpd_opt_len + len + 2 > DCCP_MAX_OPT_LEN)
return -1;
DCCP_SKB_CB(skb)->dccpd_opt_len += len + 2;
to = skb_push(skb, len + 2);
*to++ = option;
*to++ = len + 2;
memcpy(to, value, len);
return 0;
}
EXPORT_SYMBOL_GPL(dccp_insert_option);
static int dccp_insert_option_ndp(struct sock *sk, struct sk_buff *skb)
{
struct dccp_sock *dp = dccp_sk(sk);
u64 ndp = dp->dccps_ndp_count;
if (dccp_non_data_packet(skb))
++dp->dccps_ndp_count;
else
dp->dccps_ndp_count = 0;
if (ndp > 0) {
unsigned char *ptr;
const int ndp_len = dccp_ndp_len(ndp);
const int len = ndp_len + 2;
if (DCCP_SKB_CB(skb)->dccpd_opt_len + len > DCCP_MAX_OPT_LEN)
return -1;
DCCP_SKB_CB(skb)->dccpd_opt_len += len;
ptr = skb_push(skb, len);
*ptr++ = DCCPO_NDP_COUNT;
*ptr++ = len;
dccp_encode_value_var(ndp, ptr, ndp_len);
}
return 0;
}
static inline int dccp_elapsed_time_len(const u32 elapsed_time)
{
return elapsed_time == 0 ? 0 : elapsed_time <= 0xFFFF ? 2 : 4;
}
int dccp_insert_option_elapsed_time(struct sock *sk, struct sk_buff *skb,
u32 elapsed_time)
{
const int elapsed_time_len = dccp_elapsed_time_len(elapsed_time);
const int len = 2 + elapsed_time_len;
unsigned char *to;
if (elapsed_time_len == 0)
return 0;
if (DCCP_SKB_CB(skb)->dccpd_opt_len + len > DCCP_MAX_OPT_LEN)
return -1;
DCCP_SKB_CB(skb)->dccpd_opt_len += len;
to = skb_push(skb, len);
*to++ = DCCPO_ELAPSED_TIME;
*to++ = len;
if (elapsed_time_len == 2) {
const __be16 var16 = htons((u16)elapsed_time);
memcpy(to, &var16, 2);
} else {
const __be32 var32 = htonl(elapsed_time);
memcpy(to, &var32, 4);
}
return 0;
}
EXPORT_SYMBOL_GPL(dccp_insert_option_elapsed_time);
int dccp_insert_option_timestamp(struct sock *sk, struct sk_buff *skb)
{
__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));
}
EXPORT_SYMBOL_GPL(dccp_insert_option_timestamp);
[DCCP]: Handle timestamps on Request/Response exchange separately In DCCP, timestamps can occur on packets anytime, CCID3 uses a timestamp(/echo) on the Request/Response exchange. This patch addresses the following situation: * timestamps are recorded on the listening socket; * Responses are sent from dccp_request_sockets; * suppose two connections reach the listening socket with very small time in between: * the first timestamp value gets overwritten by the second connection request. This is not really good, so this patch separates timestamps into * those which are received by the server during the initial handshake (on dccp_request_sock); * those which are received by the client or the client after connection establishment. As before, a timestamp of 0 is regarded as indicating that no (meaningful) timestamp has been received (in addition, a warning message is printed if hosts send 0-valued timestamps). The timestamp-echoing now works as follows: * when a timestamp is present on the initial Request, it is placed into dreq, due to the call to dccp_parse_options in dccp_v{4,6}_conn_request; * when a timestamp is present on the Ack leading from RESPOND => OPEN, it is copied over from the request_sock into the child cocket in dccp_create_openreq_child; * timestamps received on an (established) dccp_sock are treated as before. Since Elapsed Time is measured in hundredths of milliseconds (13.2), the new dccp_timestamp() function is used, as it is expected that the time between receiving the timestamp and sending the timestamp echo will be very small against the wrap-around time. As a byproduct, this allows smaller timestamping-time fields. Furthermore, inserting the Timestamp Echo option has been taken out of the block starting with '!dccp_packet_without_ack()', since Timestamp Echo can be carried on any packet (5.8 and 13.3). Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Acked-by: Ian McDonald <ian.mcdonald@jandi.co.nz> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-13 22:37:19 +08:00
static int dccp_insert_option_timestamp_echo(struct dccp_sock *dp,
struct dccp_request_sock *dreq,
struct sk_buff *skb)
{
__be32 tstamp_echo;
unsigned char *to;
[DCCP]: Handle timestamps on Request/Response exchange separately In DCCP, timestamps can occur on packets anytime, CCID3 uses a timestamp(/echo) on the Request/Response exchange. This patch addresses the following situation: * timestamps are recorded on the listening socket; * Responses are sent from dccp_request_sockets; * suppose two connections reach the listening socket with very small time in between: * the first timestamp value gets overwritten by the second connection request. This is not really good, so this patch separates timestamps into * those which are received by the server during the initial handshake (on dccp_request_sock); * those which are received by the client or the client after connection establishment. As before, a timestamp of 0 is regarded as indicating that no (meaningful) timestamp has been received (in addition, a warning message is printed if hosts send 0-valued timestamps). The timestamp-echoing now works as follows: * when a timestamp is present on the initial Request, it is placed into dreq, due to the call to dccp_parse_options in dccp_v{4,6}_conn_request; * when a timestamp is present on the Ack leading from RESPOND => OPEN, it is copied over from the request_sock into the child cocket in dccp_create_openreq_child; * timestamps received on an (established) dccp_sock are treated as before. Since Elapsed Time is measured in hundredths of milliseconds (13.2), the new dccp_timestamp() function is used, as it is expected that the time between receiving the timestamp and sending the timestamp echo will be very small against the wrap-around time. As a byproduct, this allows smaller timestamping-time fields. Furthermore, inserting the Timestamp Echo option has been taken out of the block starting with '!dccp_packet_without_ack()', since Timestamp Echo can be carried on any packet (5.8 and 13.3). Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Acked-by: Ian McDonald <ian.mcdonald@jandi.co.nz> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-13 22:37:19 +08:00
u32 elapsed_time, elapsed_time_len, len;
if (dreq != NULL) {
elapsed_time = dccp_timestamp() - dreq->dreq_timestamp_time;
tstamp_echo = htonl(dreq->dreq_timestamp_echo);
dreq->dreq_timestamp_echo = 0;
} else {
elapsed_time = dccp_timestamp() - dp->dccps_timestamp_time;
tstamp_echo = htonl(dp->dccps_timestamp_echo);
dp->dccps_timestamp_echo = 0;
}
elapsed_time_len = dccp_elapsed_time_len(elapsed_time);
len = 6 + elapsed_time_len;
if (DCCP_SKB_CB(skb)->dccpd_opt_len + len > DCCP_MAX_OPT_LEN)
return -1;
DCCP_SKB_CB(skb)->dccpd_opt_len += len;
to = skb_push(skb, len);
*to++ = DCCPO_TIMESTAMP_ECHO;
*to++ = len;
memcpy(to, &tstamp_echo, 4);
to += 4;
if (elapsed_time_len == 2) {
const __be16 var16 = htons((u16)elapsed_time);
memcpy(to, &var16, 2);
} else if (elapsed_time_len == 4) {
const __be32 var32 = htonl(elapsed_time);
memcpy(to, &var32, 4);
}
return 0;
}
static int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb)
{
struct dccp_sock *dp = dccp_sk(sk);
struct dccp_ackvec *av = dp->dccps_hc_rx_ackvec;
dccp ccid-2: Implementation of circular Ack Vector buffer with overflow handling This completes the implementation of a circular buffer for Ack Vectors, by extending the current (linear array-based) implementation. The changes are: (a) An `overflow' flag to deal with the case of overflow. As before, dynamic growth of the buffer will not be supported; but code will be added to deal robustly with overflowing Ack Vector buffers. (b) A `tail_seqno' field. When naively implementing the algorithm of Appendix A in RFC 4340, problems arise whenever subsequent Ack Vector records overlap, which can bring the entire run length calculation completely out of synch. (This is documented on http://www.erg.abdn.ac.uk/users/gerrit/dccp/notes/\ ack_vectors/tracking_tail_ackno/ .) (c) The buffer lengthi is now computed dynamically (i.e. current fill level), as the span between head to tail. As a result, dccp_ackvec_pending() is now simpler - the #ifdef is no longer necessary since buf_empty is always true when IP_DCCP_ACKVEC is not configured. Note on overflow handling: ------------------------- The Ack Vector code previously simply started to drop packets when the Ack Vector buffer overflowed. This means that the userspace application will not be able to receive, only because of an Ack Vector storage problem. Furthermore, overflow may be transient, so that applications may later recover from the overflow. Recovering from dropped packets is more difficult (e.g. video key frames). Hence the patch uses a different policy: when the buffer overflows, the oldest entries are subsequently overwritten. This has a higher chance of recovery. Details are on http://www.erg.abdn.ac.uk/users/gerrit/dccp/notes/ack_vectors/ Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
2008-09-04 13:30:19 +08:00
const u16 buflen = dccp_ackvec_buflen(av);
/* Figure out how many options do we need to represent the ackvec */
dccp ccid-2: Implementation of circular Ack Vector buffer with overflow handling This completes the implementation of a circular buffer for Ack Vectors, by extending the current (linear array-based) implementation. The changes are: (a) An `overflow' flag to deal with the case of overflow. As before, dynamic growth of the buffer will not be supported; but code will be added to deal robustly with overflowing Ack Vector buffers. (b) A `tail_seqno' field. When naively implementing the algorithm of Appendix A in RFC 4340, problems arise whenever subsequent Ack Vector records overlap, which can bring the entire run length calculation completely out of synch. (This is documented on http://www.erg.abdn.ac.uk/users/gerrit/dccp/notes/\ ack_vectors/tracking_tail_ackno/ .) (c) The buffer lengthi is now computed dynamically (i.e. current fill level), as the span between head to tail. As a result, dccp_ackvec_pending() is now simpler - the #ifdef is no longer necessary since buf_empty is always true when IP_DCCP_ACKVEC is not configured. Note on overflow handling: ------------------------- The Ack Vector code previously simply started to drop packets when the Ack Vector buffer overflowed. This means that the userspace application will not be able to receive, only because of an Ack Vector storage problem. Furthermore, overflow may be transient, so that applications may later recover from the overflow. Recovering from dropped packets is more difficult (e.g. video key frames). Hence the patch uses a different policy: when the buffer overflows, the oldest entries are subsequently overwritten. This has a higher chance of recovery. Details are on http://www.erg.abdn.ac.uk/users/gerrit/dccp/notes/ack_vectors/ Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
2008-09-04 13:30:19 +08:00
const u8 nr_opts = DIV_ROUND_UP(buflen, DCCP_SINGLE_OPT_MAXLEN);
u16 len = buflen + 2 * nr_opts;
u8 i, nonce = 0;
const unsigned char *tail, *from;
unsigned char *to;
if (DCCP_SKB_CB(skb)->dccpd_opt_len + len > DCCP_MAX_OPT_LEN)
return -1;
DCCP_SKB_CB(skb)->dccpd_opt_len += len;
to = skb_push(skb, len);
dccp ccid-2: Implementation of circular Ack Vector buffer with overflow handling This completes the implementation of a circular buffer for Ack Vectors, by extending the current (linear array-based) implementation. The changes are: (a) An `overflow' flag to deal with the case of overflow. As before, dynamic growth of the buffer will not be supported; but code will be added to deal robustly with overflowing Ack Vector buffers. (b) A `tail_seqno' field. When naively implementing the algorithm of Appendix A in RFC 4340, problems arise whenever subsequent Ack Vector records overlap, which can bring the entire run length calculation completely out of synch. (This is documented on http://www.erg.abdn.ac.uk/users/gerrit/dccp/notes/\ ack_vectors/tracking_tail_ackno/ .) (c) The buffer lengthi is now computed dynamically (i.e. current fill level), as the span between head to tail. As a result, dccp_ackvec_pending() is now simpler - the #ifdef is no longer necessary since buf_empty is always true when IP_DCCP_ACKVEC is not configured. Note on overflow handling: ------------------------- The Ack Vector code previously simply started to drop packets when the Ack Vector buffer overflowed. This means that the userspace application will not be able to receive, only because of an Ack Vector storage problem. Furthermore, overflow may be transient, so that applications may later recover from the overflow. Recovering from dropped packets is more difficult (e.g. video key frames). Hence the patch uses a different policy: when the buffer overflows, the oldest entries are subsequently overwritten. This has a higher chance of recovery. Details are on http://www.erg.abdn.ac.uk/users/gerrit/dccp/notes/ack_vectors/ Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
2008-09-04 13:30:19 +08:00
len = buflen;
from = av->av_buf + av->av_buf_head;
tail = av->av_buf + DCCPAV_MAX_ACKVEC_LEN;
for (i = 0; i < nr_opts; ++i) {
int copylen = len;
if (len > DCCP_SINGLE_OPT_MAXLEN)
copylen = DCCP_SINGLE_OPT_MAXLEN;
/*
* RFC 4340, 12.2: Encode the Nonce Echo for this Ack Vector via
* its type; ack_nonce is the sum of all individual buf_nonce's.
*/
nonce ^= av->av_buf_nonce[i];
*to++ = DCCPO_ACK_VECTOR_0 + av->av_buf_nonce[i];
*to++ = copylen + 2;
/* Check if buf_head wraps */
if (from + copylen > tail) {
const u16 tailsize = tail - from;
memcpy(to, from, tailsize);
to += tailsize;
len -= tailsize;
copylen -= tailsize;
from = av->av_buf;
}
memcpy(to, from, copylen);
from += copylen;
to += copylen;
len -= copylen;
}
/*
* Each sent Ack Vector is recorded in the list, as per A.2 of RFC 4340.
*/
if (dccp_ackvec_update_records(av, DCCP_SKB_CB(skb)->dccpd_seq, nonce))
return -ENOBUFS;
return 0;
}
/**
* dccp_insert_option_mandatory - Mandatory option (5.8.2)
* Note that since we are using skb_push, this function needs to be called
* _after_ inserting the option it is supposed to influence (stack order).
*/
int dccp_insert_option_mandatory(struct sk_buff *skb)
{
if (DCCP_SKB_CB(skb)->dccpd_opt_len >= DCCP_MAX_OPT_LEN)
return -1;
DCCP_SKB_CB(skb)->dccpd_opt_len++;
*skb_push(skb, 1) = DCCPO_MANDATORY;
return 0;
}
/**
* dccp_insert_fn_opt - Insert single Feature-Negotiation option into @skb
* @type: %DCCPO_CHANGE_L, %DCCPO_CHANGE_R, %DCCPO_CONFIRM_L, %DCCPO_CONFIRM_R
* @feat: one out of %dccp_feature_numbers
* @val: NN value or SP array (preferred element first) to copy
* @len: true length of @val in bytes (excluding first element repetition)
* @repeat_first: whether to copy the first element of @val twice
* The last argument is used to construct Confirm options, where the preferred
* value and the preference list appear separately (RFC 4340, 6.3.1). Preference
* lists are kept such that the preferred entry is always first, so we only need
* to copy twice, and avoid the overhead of cloning into a bigger array.
*/
int dccp_insert_fn_opt(struct sk_buff *skb, u8 type, u8 feat,
u8 *val, u8 len, bool repeat_first)
{
u8 tot_len, *to;
/* take the `Feature' field and possible repetition into account */
if (len > (DCCP_SINGLE_OPT_MAXLEN - 2)) {
DCCP_WARN("length %u for feature %u too large\n", len, feat);
return -1;
}
if (unlikely(val == NULL || len == 0))
len = repeat_first = 0;
tot_len = 3 + repeat_first + len;
if (DCCP_SKB_CB(skb)->dccpd_opt_len + tot_len > DCCP_MAX_OPT_LEN) {
DCCP_WARN("packet too small for feature %d option!\n", feat);
return -1;
}
DCCP_SKB_CB(skb)->dccpd_opt_len += tot_len;
to = skb_push(skb, tot_len);
*to++ = type;
*to++ = tot_len;
*to++ = feat;
if (repeat_first)
*to++ = *val;
if (len)
memcpy(to, val, len);
return 0;
}
/* The length of all options needs to be a multiple of 4 (5.8) */
static void dccp_insert_option_padding(struct sk_buff *skb)
{
int padding = DCCP_SKB_CB(skb)->dccpd_opt_len % 4;
if (padding != 0) {
padding = 4 - padding;
memset(skb_push(skb, padding), 0, padding);
DCCP_SKB_CB(skb)->dccpd_opt_len += padding;
}
}
int dccp_insert_options(struct sock *sk, struct sk_buff *skb)
{
struct dccp_sock *dp = dccp_sk(sk);
DCCP_SKB_CB(skb)->dccpd_opt_len = 0;
if (dp->dccps_send_ndp_count && dccp_insert_option_ndp(sk, skb))
return -1;
if (DCCP_SKB_CB(skb)->dccpd_type != DCCP_PKT_DATA) {
/* Feature Negotiation */
if (dccp_feat_insert_opts(dp, NULL, skb))
return -1;
if (DCCP_SKB_CB(skb)->dccpd_type == DCCP_PKT_REQUEST) {
/*
* Obtain RTT sample from Request/Response exchange.
* This is currently used in CCID 3 initialisation.
*/
if (dccp_insert_option_timestamp(sk, skb))
return -1;
dccp ccid-2: Implementation of circular Ack Vector buffer with overflow handling This completes the implementation of a circular buffer for Ack Vectors, by extending the current (linear array-based) implementation. The changes are: (a) An `overflow' flag to deal with the case of overflow. As before, dynamic growth of the buffer will not be supported; but code will be added to deal robustly with overflowing Ack Vector buffers. (b) A `tail_seqno' field. When naively implementing the algorithm of Appendix A in RFC 4340, problems arise whenever subsequent Ack Vector records overlap, which can bring the entire run length calculation completely out of synch. (This is documented on http://www.erg.abdn.ac.uk/users/gerrit/dccp/notes/\ ack_vectors/tracking_tail_ackno/ .) (c) The buffer lengthi is now computed dynamically (i.e. current fill level), as the span between head to tail. As a result, dccp_ackvec_pending() is now simpler - the #ifdef is no longer necessary since buf_empty is always true when IP_DCCP_ACKVEC is not configured. Note on overflow handling: ------------------------- The Ack Vector code previously simply started to drop packets when the Ack Vector buffer overflowed. This means that the userspace application will not be able to receive, only because of an Ack Vector storage problem. Furthermore, overflow may be transient, so that applications may later recover from the overflow. Recovering from dropped packets is more difficult (e.g. video key frames). Hence the patch uses a different policy: when the buffer overflows, the oldest entries are subsequently overwritten. This has a higher chance of recovery. Details are on http://www.erg.abdn.ac.uk/users/gerrit/dccp/notes/ack_vectors/ Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
2008-09-04 13:30:19 +08:00
} else if (dccp_ackvec_pending(sk) &&
dccp_insert_option_ackvec(sk, skb)) {
return -1;
}
}
if (dp->dccps_hc_rx_insert_options) {
if (ccid_hc_rx_insert_options(dp->dccps_hc_rx_ccid, sk, skb))
return -1;
dp->dccps_hc_rx_insert_options = 0;
}
[DCCP]: Handle timestamps on Request/Response exchange separately In DCCP, timestamps can occur on packets anytime, CCID3 uses a timestamp(/echo) on the Request/Response exchange. This patch addresses the following situation: * timestamps are recorded on the listening socket; * Responses are sent from dccp_request_sockets; * suppose two connections reach the listening socket with very small time in between: * the first timestamp value gets overwritten by the second connection request. This is not really good, so this patch separates timestamps into * those which are received by the server during the initial handshake (on dccp_request_sock); * those which are received by the client or the client after connection establishment. As before, a timestamp of 0 is regarded as indicating that no (meaningful) timestamp has been received (in addition, a warning message is printed if hosts send 0-valued timestamps). The timestamp-echoing now works as follows: * when a timestamp is present on the initial Request, it is placed into dreq, due to the call to dccp_parse_options in dccp_v{4,6}_conn_request; * when a timestamp is present on the Ack leading from RESPOND => OPEN, it is copied over from the request_sock into the child cocket in dccp_create_openreq_child; * timestamps received on an (established) dccp_sock are treated as before. Since Elapsed Time is measured in hundredths of milliseconds (13.2), the new dccp_timestamp() function is used, as it is expected that the time between receiving the timestamp and sending the timestamp echo will be very small against the wrap-around time. As a byproduct, this allows smaller timestamping-time fields. Furthermore, inserting the Timestamp Echo option has been taken out of the block starting with '!dccp_packet_without_ack()', since Timestamp Echo can be carried on any packet (5.8 and 13.3). Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Acked-by: Ian McDonald <ian.mcdonald@jandi.co.nz> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-13 22:37:19 +08:00
if (dp->dccps_timestamp_echo != 0 &&
dccp_insert_option_timestamp_echo(dp, NULL, skb))
return -1;
dccp_insert_option_padding(skb);
return 0;
}
int dccp_insert_options_rsk(struct dccp_request_sock *dreq, struct sk_buff *skb)
{
DCCP_SKB_CB(skb)->dccpd_opt_len = 0;
if (dccp_feat_insert_opts(NULL, dreq, skb))
return -1;
if (dreq->dreq_timestamp_echo != 0 &&
dccp_insert_option_timestamp_echo(NULL, dreq, skb))
return -1;
dccp_insert_option_padding(skb);
return 0;
}