Commit Graph

6414 Commits

Author SHA1 Message Date
rrs
3d80d57562 Opps committed the wrong ratelimit version in the
whitespace cleanup.. Restore it to the proper version.

Sponsored by:	Netfilx Inc.
2020-02-12 13:37:53 +00:00
rrs
9dd4070571 White space cleanup -- remove trailing tab's or spaces
from any line.

Sponsored by:	Netflix Inc.
2020-02-12 13:31:36 +00:00
rrs
ff3104416f Whitespace, remove from three files trailing white
space (leftover presents from emacs).

Sponsored by:	Netflix Inc.
2020-02-12 13:07:09 +00:00
rrs
7de3eab7e6 This small fix makes it so we properly follow
the RFC and only enable ECN when both the
CWR and ECT bits our set within the SYN packet.

Sponsored by:	Netflix Inc.
Differential Revision:	https://reviews.freebsd.org/D23645
2020-02-12 13:04:19 +00:00
rrs
a96435c96a Remove all trailing white space from the BBR/Rack fold. Bits
left around by emacs (thanks emacs).
2020-02-12 12:40:06 +00:00
rrs
243996fd94 Now that all of the stats framework is
in FreeBSD the bits that disabled stats
when netflix-stats is not defined is no longer
needed. Lets remove these bits so that we
will properly use stats per its definition
in BBR and Rack.

Sponsored by:	Netflix Inc
Differential Revision:	https://reviews.freebsd.org/D23088
2020-02-12 12:36:55 +00:00
tuexen
82256a2f7f Revert https://svnweb.freebsd.org/changeset/base/357761
This was suggested by cem@
2020-02-11 20:02:20 +00:00
tuexen
961ee09a81 Don't start an SCTP timer using a net, which has been removed.
Submitted by:		Taylor Brandstetter
MFC after:		1 week
2020-02-11 18:15:57 +00:00
tuexen
b9b8cedc37 Use an int instead of a bool variable, since bool is not supported
on all platforms the stack is running on in userland.
2020-02-11 14:00:27 +00:00
tuexen
56f8063a5d Stop the PMTU and HB timer when removing a net, not when freeing it.
Submitted by:		Taylor Brandstetter
MFC after:		1 week
2020-02-09 22:40:05 +00:00
tuexen
15dd098e15 Cleanup timer handling.
Submitted by:	Taylor Brandstetter
MFC after:	1 week
2020-02-09 22:05:41 +00:00
emaste
f238fb1582 Miscellaneous typo fixes
Submitted by:	Gordon Bergling <gbergling_gmail.com>
Differential Revision:	https://reviews.freebsd.org/D23453
2020-02-07 19:53:07 +00:00
tuexen
5006b9fa4a Remove unused timer.
Submitted by:		Taylor Brandstetter
2020-02-04 14:01:07 +00:00
tuexen
75567b779b Improve numbering of debug information.
Submitted by:		Taylor Brandstetter
MFC after:		1 week
2020-02-04 12:34:16 +00:00
cem
81ee8d183d netinet/libalias: Fix typo in debug message
No functional change.

PR:		243831
Submitted by:	Neel Chauhan <neel AT neelc DOT org>
Differential Revision:	https://reviews.freebsd.org/D23365
2020-02-03 05:19:44 +00:00
glebius
b257e560ce Fix missing NET_EPOCH_ENTER() when compiled with TCP_OFFLOAD.
Reported by:	Coverity
CID:		1413162
2020-01-29 22:48:18 +00:00
tuexen
95e8478f6f Fix build issues for the userland stack on 32-bit platforms.
Reported by:		Felix Weinrank
MFC after:		1 week
2020-01-28 10:09:05 +00:00
melifaro
0f2aacbaf5 Fix NOINET6 build after r357038.
Reported by:	AN <andy at neu.net>
2020-01-26 11:54:21 +00:00
tuexen
f779ce9ed3 Sending CWR after an RTO is according to RFC 3168 generally required
and not only for the DCTCP congestion control.

Submitted by:		Richard Scheffenegger
Reviewed by:		rgrimes, tuexen@, Cheng Cui
MFC after:		1 week
Differential Revision:	https://reviews.freebsd.org/D23119
2020-01-25 13:45:10 +00:00
tuexen
e6f7ffd056 Don't set the ECT codepoint on retransmitted packets during SACK loss
recovery. This is required by RFC 3168.

Submitted by:		Richard Scheffenegger
Reviewed by:		rgrimes@, tuexen@, Cheng Cui
MFC after:		1 week
Differential Revision:	https://reviews.freebsd.org/D23118
2020-01-25 13:34:29 +00:00
tuexen
bc51b4b2b5 As a TCP client only enable ECN when the corresponding sysctl variable
indicates that ECN should be negotiated for the client side.

Submitted by:		Richard Scheffenegger
Reviewed by:		rgrimes@, tuexen@
MFC after:		1 week
Differential Revision:	https://reviews.freebsd.org/D23228
2020-01-25 13:11:14 +00:00
tuexen
77b1d6dcde Don't delay the ACK for a TCP segment with the CWR flag set.
This allows the data sender to increase the CWND faster.

Submitted by:		Richard Scheffenegger
Reviewed by:		rgrimes@, tuexen@, Cheng Cui
MFC after:		1 week
Differential Revision:	https://reviews.freebsd.org/D22670
2020-01-24 22:50:23 +00:00
tuexen
68ae78ed36 The server side of TCP fast open relies on the delayed ACK timer to allow
including user data in the SYN-ACK. When DSACK support was added in
r347382, an immediate ACK was sent even for the received SYN with
user data. This patch fixes that and allows again to send user data with
the SYN-ACK.

Reported by:		Jeremy Harris
Reviewed by:		Richard Scheffenegger, rrs@
MFC after:		1 week
Sponsored by:		Netflix, Inc.
Differential Revision:	https://reviews.freebsd.org/D23212
2020-01-24 22:37:53 +00:00
glebius
9aa8e6fbcd Enter the network epoch when rack_output() is called in setsockopt(2). 2020-01-24 21:56:10 +00:00
melifaro
20aa310e22 Add support for RFC 6598/Carrier Grade NAT subnets. to libalias and ipfw.
In libalias, a new flag PKT_ALIAS_UNREGISTERED_RFC6598 is added.
 This is like PKT_ALIAS_UNREGISTERED_ONLY, but also is RFC 6598 aware.
Also, we add a new NAT option to ipfw called unreg_cgn, which is like
 unreg_only, but also is RFC 6598-aware.  The reason for the new
 flags/options is to avoid breaking existing networks, especially those
 which rely on RFC 6598 as an external address.

Submitted by:	Neel Chauhan <neel AT neelc DOT org>
MFC after:	2 weeks
Differential Revision:	https://reviews.freebsd.org/D22877
2020-01-24 20:35:41 +00:00
melifaro
40d93a3852 Bring indentation back to normal after r357038.
No functional changes.

MFC after:	3 weeks
2020-01-23 09:46:45 +00:00
melifaro
d49a1663d6 Fix epoch-related panic in ipdivert, ensuring in_broadcast() is called
within epoch.

Simplify gigantic div_output() by splitting it into 3 functions,
 handling preliminary setup, remote "ip[6]_output" case and
 local "netisr" case. Leave original indenting in most parts to ease
 diff comparison.  Indentation will be fixed by a followup commit.

Reported by:	Nick Hibma <nick at van-laarhoven.org>
Reviewed by:	glebius
Differential Revision:	https://reviews.freebsd.org/D23317
2020-01-23 09:14:28 +00:00
glebius
afbc3286fa Plug possible calls into ip6?_output() without network epoch from SCTP
bluntly adding epoch entrance into the macro that SCTP uses to call
ip6?_output().  This definitely will introduce several epoch recursions.

Reported by:	https://syzkaller.appspot.com/bug?id=79f03f574594a5be464997310896765c458ed80a
Reported by:	https://syzkaller.appspot.com/bug?id=07c6f52106cddbe356cc2b2f3664a1c51cc0dadf
2020-01-22 17:19:53 +00:00
bz
a177f76cd2 Fix NOINET kernels after r356983.
All gotos to the label are within the #ifdef INET section, which leaves
us with an unused label.  Cover the label under #ifdef INET as well to
avoid the warning and compile time error.
2020-01-22 15:06:59 +00:00
melifaro
b17accbc49 Bring back redirect route expiration.
Redirect (and temporal) route expiration was broken a while ago.
This change brings route expiration back, with unified IPv4/IPv6 handling code.

It introduces net.inet.icmp.redirtimeout sysctl, allowing to set
 an expiration time for redirected routes. It defaults to 10 minutes,
 analogues with net.inet6.icmp6.redirtimeout.

Implementation uses separate file, route_temporal.c, as route.c is already
 bloated with tons of different functions.
Internally, expiration is implemented as an per-rnh callout scheduled when
 route with non-zero rt_expire time is added or rt_expire is changed.
 It does not add any overhead when no temporal routes are present.

Callout traverses entire routing tree under wlock, scheduling expired routes
 for deletion and calculating the next time it needs to be run. The rationale
 for such implemention is the following: typically workloads requiring large
 amount of routes have redirects turned off already, while the systems with
 small amount of routes will not inhibit large overhead during tree traversal.

This changes also fixes netstat -rn display of route expiration time, which
 has been broken since the conversion from kread() to sysctl.

Reviewed by:	bz
MFC after:	3 weeks
Differential Revision:	https://reviews.freebsd.org/D23075
2020-01-22 13:53:18 +00:00
glebius
313adad5b8 Make in_pcbladdr() require network epoch entered by its callers. Together
with this widen network epoch coverage up to tcp_connect() and udp_connect().

Revisions from r356974 and up to this revision cover D23187.

Differential Revision:	https://reviews.freebsd.org/D23187
2020-01-22 06:10:41 +00:00
glebius
57cf9e8fd6 Remove extraneous NET_EPOCH_ASSERT - the full function is covered. 2020-01-22 06:07:27 +00:00
glebius
9aca735515 Re-absorb tcp_detach() back into tcp_usr_detach() as the comment suggests.
Not a functional change.
2020-01-22 06:06:27 +00:00
glebius
57981ac130 Don't enter network epoch in tcp_usr_detach. A PCB removal doesn't
require that.
2020-01-22 06:04:56 +00:00
glebius
2a7af08431 The network epoch changes in the TCP stack combined with old r286227,
actually make removal of a PCB not needing ipi_lock in any form.  The
ipi_list_lock is sufficient.
2020-01-22 06:03:45 +00:00
glebius
2e901d0ed4 tcp_usr_attach() doesn't need network epoch. in_pcbfree() and
in_pcbdetach() perform all necessary synchronization themselves.
2020-01-22 06:01:26 +00:00
glebius
a7f275d187 Relax locking requirements for in_pcballoc(). All pcbinfo fields
modified by this function are protected by the PCB list lock that is
acquired inside the function.

This could have been done even before epoch changes, after r286227.
2020-01-22 05:58:29 +00:00
glebius
1019be5656 Inline tcp_attach() into tcp_usr_attach(). Not a functional change. 2020-01-22 05:54:58 +00:00
glebius
b38bde736a Make tcp_output() require network epoch.
Enter the epoch before calling into tcp_output() from those
functions, that didn't do that before.

This eliminates a bunch of epoch recursions in TCP.
2020-01-22 05:53:16 +00:00
glebius
9879d0d15d Make ip6_output() and ip_output() require network epoch.
All callers that before may called into these functions
without network epoch now must enter it.
2020-01-22 05:51:22 +00:00
glebius
5fe4c30cb8 Add documenting NET_EPOCH_ASSERT() to tcp_drop(). 2020-01-22 02:38:46 +00:00
glebius
f58ea78da0 Add some documenting NET_EPOCH_ASSERTs. 2020-01-22 02:37:47 +00:00
tuexen
e51fa01579 Remove debug code not needed anymore.
Submitted by:		Richard Scheffenegger
Reviewed by:		tuexen@
MFC after:		1 week
Differential Revision:	https://reviews.freebsd.org/D23208
2020-01-16 17:15:06 +00:00
glebius
3402b0a5ce A miss from r356754. 2020-01-15 06:12:39 +00:00
glebius
5057bc60d0 Introduce NET_EPOCH_CALL() macro and use it everywhere where we free
data based on the network epoch.   The macro reverses the argument
order of epoch_call(9) - first function, then its argument. NFC
2020-01-15 06:05:20 +00:00
glebius
f4fefae588 Use official macro to enter/exit the network epoch. NFC 2020-01-15 05:48:36 +00:00
glebius
044cd3b935 Mechanically substitute assertion of in_epoch(net_epoch_preempt) to
NET_EPOCH_ASSERT(). NFC
2020-01-15 05:45:27 +00:00
glebius
9aa583df20 Stop header pollution and don't include if_var.h via in_pcb.h. 2020-01-15 03:41:15 +00:00
glebius
a470835e82 Since this code dereferences struct ifnet, it must include if_var.h
explicitly, not via header pollution.  While here move TCPSTATES
declaration right above the include that is going to make use of it.
2020-01-15 03:40:32 +00:00
glebius
c2e0b506d8 The non-preemptible network epoch identified by net_epoch isn't used.
This code definitely meant net_epoch_preempt.
2020-01-15 03:30:33 +00:00