mirror of
https://git.FreeBSD.org/src.git
synced 2024-12-18 10:35:55 +00:00
Implement PLPMTUD blackhole detection (RFC 4821), inspired by code
from xnu sources. If we encounter a network where ICMP is blocked the Needs Frag indicator may not propagate back to us. Attempt to downshift the mss once to a preconfigured value. Default this feature to off for now while we do not have a full PLPMTUD implementation in our stack. Adds the following new sysctl's for control: net.inet.tcp.pmtud_blackhole_detection -- turns on/off this feature net.inet.tcp.pmtud_blackhole_mss -- mss to try for ipv4 net.inet.tcp.v6pmtud_blackhole_mss -- mss to try for ipv6 Adds the following new sysctl's for monitoring: -- Number of times the code was activated to attempt a mss downshift net.inet.tcp.pmtud_blackhole_activated -- Number of times the blackhole mss was used in an attempt to downshift net.inet.tcp.pmtud_blackhole_min_activated -- Number of times that we failed to connect after we downshifted the mss net.inet.tcp.pmtud_blackhole_failed Phabricator: https://reviews.freebsd.org/D506 Reviewed by: rpaulo bz MFC after: 2 weeks Relnotes: yes Sponsored by: Limelight Networks
This commit is contained in:
Sean Bruno
parent
19abdd0654
commit
f6f6703f27
Notes:
svn2git
2020-12-20 02:59:44 +00:00
svn path=/head/; revision=272720
@ -675,6 +675,12 @@ tcp_output(struct tcpcb *tp)
|
||||
|
||||
send:
|
||||
SOCKBUF_LOCK_ASSERT(&so->so_snd);
|
||||
if (len > 0) {
|
||||
if (len >= tp->t_maxseg)
|
||||
tp->t_flags2 |= TF2_PLPMTU_MAXSEGSNT;
|
||||
else
|
||||
tp->t_flags2 &= ~TF2_PLPMTU_MAXSEGSNT;
|
||||
}
|
||||
/*
|
||||
* Before ESTABLISHED, force sending of initial options
|
||||
* unless TCP set not to do any options.
|
||||
@ -1303,8 +1309,12 @@ tcp_output(struct tcpcb *tp)
|
||||
*
|
||||
* NB: Don't set DF on small MTU/MSS to have a safe fallback.
|
||||
*/
|
||||
if (V_path_mtu_discovery && tp->t_maxopd > V_tcp_minmss)
|
||||
if (V_path_mtu_discovery && tp->t_maxopd > V_tcp_minmss) {
|
||||
ip->ip_off |= htons(IP_DF);
|
||||
tp->t_flags2 |= TF2_PLPMTU_PMTUD;
|
||||
} else {
|
||||
tp->t_flags2 &= ~TF2_PLPMTU_PMTUD;
|
||||
}
|
||||
|
||||
if (tp->t_state == TCPS_SYN_SENT)
|
||||
TCP_PROBE5(connect__request, NULL, tp, ip, tp, th);
|
||||
|
||||
@ -66,6 +66,9 @@ __FBSDID("$FreeBSD$");
|
||||
#include <netinet/tcp_fsm.h>
|
||||
#include <netinet/tcp_timer.h>
|
||||
#include <netinet/tcp_var.h>
|
||||
#ifdef INET6
|
||||
#include <netinet6/tcp6_var.h>
|
||||
#endif
|
||||
#include <netinet/tcpip.h>
|
||||
#ifdef TCPDEBUG
|
||||
#include <netinet/tcp_debug.h>
|
||||
@ -127,6 +130,54 @@ SYSCTL_INT(_net_inet_tcp, OID_AUTO, rexmit_drop_options, CTLFLAG_RW,
|
||||
&tcp_rexmit_drop_options, 0,
|
||||
"Drop TCP options from 3rd and later retransmitted SYN");
|
||||
|
||||
static VNET_DEFINE(int, tcp_pmtud_blackhole_detect);
|
||||
#define V_tcp_pmtud_blackhole_detect VNET(tcp_pmtud_blackhole_detect)
|
||||
SYSCTL_INT(_net_inet_tcp, OID_AUTO, pmtud_blackhole_detection,
|
||||
CTLTYPE_INT|CTLFLAG_RW|CTLFLAG_VNET,
|
||||
&VNET_NAME(tcp_pmtud_blackhole_detect), 0,
|
||||
"Path MTU Discovery Black Hole Detection Enabled");
|
||||
|
||||
static VNET_DEFINE(int, tcp_pmtud_blackhole_activated);
|
||||
#define V_tcp_pmtud_blackhole_activated \
|
||||
VNET(tcp_pmtud_blackhole_activated)
|
||||
SYSCTL_INT(_net_inet_tcp, OID_AUTO, pmtud_blackhole_activated,
|
||||
CTLTYPE_INT|CTLFLAG_RD|CTLFLAG_VNET,
|
||||
&VNET_NAME(tcp_pmtud_blackhole_activated), 0,
|
||||
"Path MTU Discovery Black Hole Detection, Activation Count");
|
||||
|
||||
static VNET_DEFINE(int, tcp_pmtud_blackhole_activated_min_mss);
|
||||
#define V_tcp_pmtud_blackhole_activated_min_mss \
|
||||
VNET(tcp_pmtud_blackhole_activated_min_mss)
|
||||
SYSCTL_INT(_net_inet_tcp, OID_AUTO, pmtud_blackhole_activated_min_mss,
|
||||
CTLTYPE_INT|CTLFLAG_RD|CTLFLAG_VNET,
|
||||
&VNET_NAME(tcp_pmtud_blackhole_activated_min_mss), 0,
|
||||
"Path MTU Discovery Black Hole Detection, Activation Count at min MSS");
|
||||
|
||||
static VNET_DEFINE(int, tcp_pmtud_blackhole_failed);
|
||||
#define V_tcp_pmtud_blackhole_failed VNET(tcp_pmtud_blackhole_failed)
|
||||
SYSCTL_INT(_net_inet_tcp, OID_AUTO, pmtud_blackhole_failed,
|
||||
CTLTYPE_INT|CTLFLAG_RD|CTLFLAG_VNET,
|
||||
&VNET_NAME(tcp_pmtud_blackhole_failed), 0,
|
||||
"Path MTU Discovery Black Hole Detection, Failure Count");
|
||||
|
||||
#ifdef INET
|
||||
static VNET_DEFINE(int, tcp_pmtud_blackhole_mss) = 1200;
|
||||
#define V_tcp_pmtud_blackhole_mss VNET(tcp_pmtud_blackhole_mss)
|
||||
SYSCTL_INT(_net_inet_tcp, OID_AUTO, pmtud_blackhole_mss,
|
||||
CTLTYPE_INT|CTLFLAG_RW|CTLFLAG_VNET,
|
||||
&VNET_NAME(tcp_pmtud_blackhole_mss), 0,
|
||||
"Path MTU Discovery Black Hole Detection lowered MSS");
|
||||
#endif
|
||||
|
||||
#ifdef INET6
|
||||
static VNET_DEFINE(int, tcp_v6pmtud_blackhole_mss) = 1220;
|
||||
#define V_tcp_v6pmtud_blackhole_mss VNET(tcp_v6pmtud_blackhole_mss)
|
||||
SYSCTL_INT(_net_inet_tcp, OID_AUTO, v6pmtud_blackhole_mss,
|
||||
CTLTYPE_INT|CTLFLAG_RW|CTLFLAG_VNET,
|
||||
&VNET_NAME(tcp_v6pmtud_blackhole_mss), 0,
|
||||
"Path MTU Discovery IPv6 Black Hole Detection lowered MSS");
|
||||
#endif
|
||||
|
||||
#ifdef RSS
|
||||
static int per_cpu_timers = 1;
|
||||
#else
|
||||
@ -539,6 +590,7 @@ tcp_timer_rexmt(void * xtp)
|
||||
|
||||
ostate = tp->t_state;
|
||||
#endif
|
||||
|
||||
INP_INFO_RLOCK(&V_tcbinfo);
|
||||
inp = tp->t_inpcb;
|
||||
/*
|
||||
@ -640,6 +692,102 @@ tcp_timer_rexmt(void * xtp)
|
||||
rexmt = TCP_REXMTVAL(tp) * tcp_backoff[tp->t_rxtshift];
|
||||
TCPT_RANGESET(tp->t_rxtcur, rexmt,
|
||||
tp->t_rttmin, TCPTV_REXMTMAX);
|
||||
|
||||
if (V_tcp_pmtud_blackhole_detect && (tp->t_state == TCPS_ESTABLISHED)) {
|
||||
int optlen;
|
||||
#ifdef INET6
|
||||
int isipv6;
|
||||
#endif
|
||||
|
||||
if (((tp->t_flags2 & (TF2_PLPMTU_PMTUD|TF2_PLPMTU_MAXSEGSNT)) ==
|
||||
(TF2_PLPMTU_PMTUD|TF2_PLPMTU_MAXSEGSNT)) &&
|
||||
(tp->t_rxtshift <= 2)) {
|
||||
/*
|
||||
* Enter Path MTU Black-hole Detection mechanism:
|
||||
* - Disable Path MTU Discovery (IP "DF" bit).
|
||||
* - Reduce MTU to lower value than what we
|
||||
* negotiated with peer.
|
||||
*/
|
||||
/* Record that we may have found a black hole. */
|
||||
tp->t_flags2 |= TF2_PLPMTU_BLACKHOLE;
|
||||
|
||||
/* Keep track of previous MSS. */
|
||||
optlen = tp->t_maxopd - tp->t_maxseg;
|
||||
tp->t_pmtud_saved_maxopd = tp->t_maxopd;
|
||||
|
||||
/*
|
||||
* Reduce the MSS to blackhole value or to the default
|
||||
* in an attempt to retransmit.
|
||||
*/
|
||||
#ifdef INET6
|
||||
isipv6 = (tp->t_inpcb->inp_vflag & INP_IPV6) ? 1 : 0;
|
||||
if (isipv6 &&
|
||||
tp->t_maxopd > V_tcp_v6pmtud_blackhole_mss) {
|
||||
/* Use the sysctl tuneable blackhole MSS. */
|
||||
tp->t_maxopd = V_tcp_v6pmtud_blackhole_mss;
|
||||
V_tcp_pmtud_blackhole_activated++;
|
||||
} else if (isipv6) {
|
||||
/* Use the default MSS. */
|
||||
tp->t_maxopd = V_tcp_v6mssdflt;
|
||||
/*
|
||||
* Disable Path MTU Discovery when we switch to
|
||||
* minmss.
|
||||
*/
|
||||
tp->t_flags2 &= ~TF2_PLPMTU_PMTUD;
|
||||
V_tcp_pmtud_blackhole_activated_min_mss++;
|
||||
}
|
||||
#endif
|
||||
#if defined(INET6) && defined(INET)
|
||||
else
|
||||
#endif
|
||||
#ifdef INET
|
||||
if (tp->t_maxopd > V_tcp_pmtud_blackhole_mss) {
|
||||
/* Use the sysctl tuneable blackhole MSS. */
|
||||
tp->t_maxopd = V_tcp_pmtud_blackhole_mss;
|
||||
V_tcp_pmtud_blackhole_activated++;
|
||||
} else {
|
||||
/* Use the default MSS. */
|
||||
tp->t_maxopd = V_tcp_mssdflt;
|
||||
/*
|
||||
* Disable Path MTU Discovery when we switch to
|
||||
* minmss.
|
||||
*/
|
||||
tp->t_flags2 &= ~TF2_PLPMTU_PMTUD;
|
||||
V_tcp_pmtud_blackhole_activated_min_mss++;
|
||||
}
|
||||
#endif
|
||||
tp->t_maxseg = tp->t_maxopd - optlen;
|
||||
/*
|
||||
* Reset the slow-start flight size
|
||||
* as it may depend on the new MSS.
|
||||
*/
|
||||
if (CC_ALGO(tp)->conn_init != NULL)
|
||||
CC_ALGO(tp)->conn_init(tp->ccv);
|
||||
} else {
|
||||
/*
|
||||
* If further retransmissions are still unsuccessful
|
||||
* with a lowered MTU, maybe this isn't a blackhole and
|
||||
* we restore the previous MSS and blackhole detection
|
||||
* flags.
|
||||
*/
|
||||
if ((tp->t_flags2 & TF2_PLPMTU_BLACKHOLE) &&
|
||||
(tp->t_rxtshift > 4)) {
|
||||
tp->t_flags2 |= TF2_PLPMTU_PMTUD;
|
||||
tp->t_flags2 &= ~TF2_PLPMTU_BLACKHOLE;
|
||||
optlen = tp->t_maxopd - tp->t_maxseg;
|
||||
tp->t_maxopd = tp->t_pmtud_saved_maxopd;
|
||||
tp->t_maxseg = tp->t_maxopd - optlen;
|
||||
V_tcp_pmtud_blackhole_failed++;
|
||||
/*
|
||||
* Reset the slow-start flight size as it
|
||||
* may depend on the new MSS.
|
||||
*/
|
||||
if (CC_ALGO(tp)->conn_init != NULL)
|
||||
CC_ALGO(tp)->conn_init(tp->ccv);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
* Disable RFC1323 and SACK if we haven't got any response to
|
||||
* our third SYN to work-around some broken terminal servers
|
||||
|
||||
@ -200,6 +200,8 @@ struct tcpcb {
|
||||
u_int t_keepcnt; /* number of keepalives before close */
|
||||
|
||||
u_int t_tsomax; /* TSO total burst length limit in bytes */
|
||||
u_int t_pmtud_saved_maxopd; /* pre-blackhole MSS */
|
||||
u_int t_flags2; /* More tcpcb flags storage */
|
||||
|
||||
uint32_t t_ispare[6]; /* 5 UTO, 1 TBD */
|
||||
uint32_t t_tsomaxsegcount; /* TSO maximum segment count */
|
||||
@ -277,6 +279,13 @@ struct tcpcb {
|
||||
#define TCP_SIG_SPI 0x1000
|
||||
#endif /* TCP_SIGNATURE */
|
||||
|
||||
/*
|
||||
* Flags for PLPMTU handling, t_flags2
|
||||
*/
|
||||
#define TF2_PLPMTU_BLACKHOLE 0x00000001 /* Possible PLPMTUD Black Hole. */
|
||||
#define TF2_PLPMTU_PMTUD 0x00000002 /* Allowed to attempt PLPMTUD. */
|
||||
#define TF2_PLPMTU_MAXSEGSNT 0x00000004 /* Last seg sent was full seg. */
|
||||
|
||||
/*
|
||||
* Structure to hold TCP options that are only used during segment
|
||||
* processing (in tcp_input), but not held in the tcpcb.
|
||||
|
||||
Loading…
Reference in New Issue
Block a user