Author: jtl
Date: Wed Jun 19 13:55:00 2019
New Revision: 349192
URL: https://svnweb.freebsd.org/changeset/base/349192
Log:
Add the ability to limit how much the code will fragment the RACK send map
in response to SACKs. The default behavior is unchanged; however, the limit
can be activated b
Author: jtl
Date: Wed Jun 19 16:25:39 2019
New Revision: 349197
URL: https://svnweb.freebsd.org/changeset/base/349197
Log:
MFC r349192:
Add the ability to limit how much the code will fragment the RACK send map
in response to SACKs. The default behavior is unchanged; however, the
lim
Author: jtl
Date: Fri Aug 9 05:18:59 2019
New Revision: 350815
URL: https://svnweb.freebsd.org/changeset/base/350815
Log:
In m_pulldown(), before trying to prepend bytes to the subsequent mbuf,
ensure that the subsequent mbuf contains the remainder of the bytes
the caller sought. If this is
Author: jtl
Date: Sat Aug 10 00:01:25 2019
New Revision: 350828
URL: https://svnweb.freebsd.org/changeset/base/350828
Log:
MFC r350815:
In m_pulldown(), before trying to prepend bytes to the subsequent mbuf,
ensure that the subsequent mbuf contains the remainder of the bytes
the call
Author: jtl
Date: Sat Aug 10 00:02:45 2019
New Revision: 350829
URL: https://svnweb.freebsd.org/changeset/base/350829
Log:
MFC r350815:
In m_pulldown(), before trying to prepend bytes to the subsequent mbuf,
ensure that the subsequent mbuf contains the remainder of the bytes
the call
Author: jtl
Date: Sat Jun 8 18:26:48 2019
New Revision: 348810
URL: https://svnweb.freebsd.org/changeset/base/348810
Log:
Currently, MCA entries remain on an every-growing linked list. This means
that it becomes increasingly expensive to process a steady stream of
correctable errors. Additi
Hi Enji,
On Sat, Jun 8, 2019 at 3:58 PM Enji Cooper wrote:
> > Modified:
> > head/sys/x86/x86/mca.c
> >
> > Modified: head/sys/x86/x86/mca.c
> >
> ==
> > --- head/sys/x86/x86/mca.cSat Jun 8 17:49:17 2019(r34880
Author: jtl
Date: Wed Jun 12 16:06:31 2019
New Revision: 348996
URL: https://svnweb.freebsd.org/changeset/base/348996
Log:
The current IPMI KCS code is waiting 100us for all transitions (roughly
between each byte either sent or received). However, most transitions
actually complete in 2-3 mi
Author: jtl
Date: Fri Jun 10 19:06:11 2016
New Revision: 301814
URL: https://svnweb.freebsd.org/changeset/base/301814
Log:
Change the default build behavior so we don't compile extra TCP modules by
default. At least initially, the feature to support multiple TCP stacks is
aimed at supporting
On 6/13/16, 8:24 PM, "Bryan Drewery" wrote:
>no description found for WITH_EXTRA_TCP_STACKS, skipping
>A src.conf.5 handler is needed for this.
>
>
>Please add a WITH_EXTRA_TCP_STACKS file into tools/build/options, svn
>commit, svn up, and then
>run from that directory:
>
>./makeman > ../../../sha
Author: jtl
Date: Tue Jun 28 13:37:01 2016
New Revision: 302247
URL: https://svnweb.freebsd.org/changeset/base/302247
Log:
Document support for alternate TCP stacks.
Differential Revision:https://reviews.freebsd.org/D6940
Reviewed by: hiren
Approved by: re (gjb)
Sponsored by
Author: jtl
Date: Tue Jun 28 13:42:50 2016
New Revision: 302248
URL: https://svnweb.freebsd.org/changeset/base/302248
Log:
Regenerate for WITH_EXTRA_TCP_STACKS updates.
Approved by: re (gjb)
Sponsored by: Juniper Networks
Modified:
head/share/man/man5/src.conf.5
Modified: head/share/
Author: jtl
Date: Wed Jul 6 16:17:13 2016
New Revision: 302374
URL: https://svnweb.freebsd.org/changeset/base/302374
Log:
The TCPPCAP debugging feature caches recently-used mbufs for use in
debugging TCP connections. This commit provides a mechanism to free those
mbufs when the system is un
On 7/21/16, 3:34 AM, "owner-src-committ...@freebsd.org on behalf of Michal
Meloun" wrote:
> The API is part of still unstable, experimental INTRNG, so its not fixed we
> we can
> change it at any time, I think.
If INTRNG is unstable and experimental, why is it in the GENERIC kernel for
arm64
Author: jtl
Date: Thu Oct 6 15:57:15 2016
New Revision: 306766
URL: https://svnweb.freebsd.org/changeset/base/306766
Log:
Remove declaration of un-defined function tcp_seq_subtract().
Reviewed by: gnn
MFC after:1 week
Sponsored by: Juniper Networks, Netflix
Differential Revision
Author: jtl
Date: Thu Oct 6 16:00:48 2016
New Revision: 306767
URL: https://svnweb.freebsd.org/changeset/base/306767
Log:
Correctly calculate snd_max in persist case.
In the persist case, take the SYN and FIN flags into account when updating
the sequence space sent.
Reviewed by: gn
Author: jtl
Date: Thu Oct 6 16:09:45 2016
New Revision: 306768
URL: https://svnweb.freebsd.org/changeset/base/306768
Log:
If the new window size is less than the old window size, skip the
calculations to check if we should advertise a larger window.
Reviewed by: gnn
MFC after:2 we
Author: jtl
Date: Thu Oct 6 16:28:34 2016
New Revision: 306769
URL: https://svnweb.freebsd.org/changeset/base/306769
Log:
Remove "long" variables from the TCP stack (not including the modular
congestion control framework).
Reviewed by: gnn, lstewart (partial)
Sponsored by: Juniper Net
Author: jtl
Date: Fri Oct 7 10:47:32 2016
New Revision: 306802
URL: https://svnweb.freebsd.org/changeset/base/306802
Log:
MFC r296454:
Some cleanup in tcp_respond() in preparation for another change:
- Reorder variables by size
- Move initializer closer to where it is used
- Rem
Author: jtl
Date: Wed Oct 12 02:16:42 2016
New Revision: 307082
URL: https://svnweb.freebsd.org/changeset/base/307082
Log:
In the TCP stack, the hhook(9) framework provides hooks for kernel modules
to add actions that run when a TCP frame is sent or received on a TCP
session in the ESTABLISH
Author: jtl
Date: Wed Oct 12 02:30:33 2016
New Revision: 307083
URL: https://svnweb.freebsd.org/changeset/base/307083
Log:
Currently, when tcp_input() receives a packet on a session that matches a
TCPCB, it checks (so->so_options & SO_ACCEPTCONN) to determine whether or
not the socket is a l
Author: jtl
Date: Wed Oct 12 19:06:50 2016
New Revision: 307153
URL: https://svnweb.freebsd.org/changeset/base/307153
Log:
The TFO server-side code contains some changes that are not conditioned on
the TCP_RFC7413 kernel option. This change removes those few instructions
from the packet proc
Author: jtl
Date: Thu Oct 13 02:31:32 2016
New Revision: 307165
URL: https://svnweb.freebsd.org/changeset/base/307165
Log:
MFC r306766:
Remove declaration of un-defined function tcp_seq_subtract().
Modified:
stable/10/sys/netinet/tcp_var.h
Directory Properties:
stable/10/ (props chang
Author: jtl
Date: Thu Oct 13 02:32:41 2016
New Revision: 307166
URL: https://svnweb.freebsd.org/changeset/base/307166
Log:
MFC r306766:
Remove declaration of un-defined function tcp_seq_subtract().
Modified:
stable/11/sys/netinet/tcp_var.h
Directory Properties:
stable/11/ (props chang
Author: jtl
Date: Fri Oct 14 14:57:43 2016
New Revision: 307319
URL: https://svnweb.freebsd.org/changeset/base/307319
Log:
The code currently resets the keepalive timer each time a packet is
received on a TCP session that has entered the ESTABLISHED state. This
results in a lot of calls to r
Author: jtl
Date: Sat Oct 15 00:29:15 2016
New Revision: 307336
URL: https://svnweb.freebsd.org/changeset/base/307336
Log:
r307082 added the TCP_HHOOK kernel option and made some existing code only
compile when that option is configured. In tcp_destroy(), the error
variable is now only used
On Wed, May 23, 2018 at 7:13 PM, Matthew Macy wrote:
>
> On Wed, May 23, 2018 at 11:52 AM, John Baldwin wrote:
> > On Wednesday, May 23, 2018 05:00:05 PM Matt Macy wrote:
> >> Author: mmacy
> >> Date: Wed May 23 17:00:05 2018
> >> New Revision: 334104
> >> URL: https://svnweb.freebsd.org/changese
Author: jtl
Date: Fri Jun 1 16:47:39 2018
New Revision: 334490
URL: https://svnweb.freebsd.org/changeset/base/334490
Log:
Update the sysctl(9) manpage to indicate that is required
instead of . ( includes NULL, which is defined
with and not .)
Sponsored by: Netflix
Modified:
head/
On Wed, Jun 6, 2018 at 10:14 PM, Ravi Pokala wrote:
>
> -Original Message-
> From: on behalf of Mateusz Guzik <
mjgu...@gmail.com>
> Date: 2018-06-06, Wednesday at 09:01
> To: Ravi Pokala
> Cc: Mateusz Guzik , src-committers <
src-committ...@freebsd.org>, , <
svn-src-h...@freebsd.org>
>
Author: jtl
Date: Thu Jun 7 13:29:54 2018
New Revision: 334783
URL: https://svnweb.freebsd.org/changeset/base/334783
Log:
Fix a typo in vm_domain_set(). When a domain crosses into the severe range,
we need to set the domain bit from the vm_severe_domains bitset (instead
of clearing it).
On Fri, Jun 8, 2018 at 12:37 PM, hiren panchasara <
hi...@strugglingcoder.info> wrote:
> ps: I know we are not killing the default stack as of yet and just
> stopping active maintenance of it but just wanted to raise these
> (probably obvious) points.
We absolutely are not stopping active maintena
Author: jtl
Date: Fri Jun 8 19:35:24 2018
New Revision: 334853
URL: https://svnweb.freebsd.org/changeset/base/334853
Log:
Add a socket destructor callback. This allows kernel providers to set
callbacks to perform additional cleanup actions at the time a socket is
closed.
Michio Honda
Author: jtl
Date: Fri Jun 8 19:47:04 2018
New Revision: 334854
URL: https://svnweb.freebsd.org/changeset/base/334854
Log:
Create a symlink for sodtor_set(9) to the socket(9) man page.
Modified:
head/share/man/man9/Makefile
Modified: head/share/man/man9/Makefile
=
Author: jtl
Date: Mon Jun 11 14:27:19 2018
New Revision: 334949
URL: https://svnweb.freebsd.org/changeset/base/334949
Log:
Change RACK dependency on TCPHPTS from a build-time dependency to a load-
time dependency.
At present, RACK requires the TCPHPTS option to run. However, because
mod
Author: jtl
Date: Mon Jun 11 23:32:06 2018
New Revision: 334983
URL: https://svnweb.freebsd.org/changeset/base/334983
Log:
Fix a memory leak for the BIOCSETWF ioctl on kernels with the BPF_JITTER
option.
The BPF code was creating a compiled filter in the common filter-creation
path. Ho
Author: jtl
Date: Wed Jun 13 17:04:41 2018
New Revision: 335068
URL: https://svnweb.freebsd.org/changeset/base/335068
Log:
Make UMA and malloc(9) return non-executable memory in most cases.
Most kernel memory that is allocated after boot does not need to be
executable. There are a few ex
On Thu, Jun 14, 2018 at 7:12 PM Olivier Houchard wrote:
> On Fri, Jun 15, 2018 at 12:23:36AM +0200, Emmanuel Vadot wrote:
> > This brake module loading on armv7 and arm64
>
> I think I fixed it with r335182.
> Jonathan probably missed it because modules are differnt on amd64 (and
> mips), and th
On Tue, Jun 19, 2018 at 8:34 PM Conrad Meyer wrote:
> Please revert this patchset. It's not ready.
>
I'm not sure I understand the need to revert the patches. They may need
some refinement, but they also do provide some functionality upon which you
can build the tooling that Simon discussed.
U
On Wed, Jun 20, 2018 at 9:49 AM Stephen Kiernan
wrote:
> And I was working on those sets of changes, when work and family didn't
> steal away time. I was told that some discussion happened at BSDCan this
> year in such that veriexec should go in as-is so it would be there, which
is why
> the commi
On Mon, Jul 2, 2018 at 10:44 AM Steven Hartland <
steven.hartl...@multiplay.co.uk> wrote:
>
> You have M_WAITOK and a null check in this change
And, that's the same as the way it was before his commits. So, he did
exactly what he said he was doing and reverted his commits. I don't think
it is good
Author: jtl
Date: Thu Sep 26 15:02:34 2019
New Revision: 352744
URL: https://svnweb.freebsd.org/changeset/base/352744
Log:
Remove the unused sch parameter to the syncache_respond() function. The
use of this parameter was removed in r313330. This commit now removes
passing this now-unused par
Author: jtl
Date: Thu Sep 26 15:06:46 2019
New Revision: 352745
URL: https://svnweb.freebsd.org/changeset/base/352745
Log:
Access the syncache secret directly from the V_tcp_syncache variable,
rather than indirectly through the backpointer to the tcp_syncache
structure stored in the hashtabl
Author: jtl
Date: Thu Sep 26 15:18:57 2019
New Revision: 352746
URL: https://svnweb.freebsd.org/changeset/base/352746
Log:
Add new functionality to switch to using cookies exclusively when we the
syn cache overflows. Whether this is due to an attack or due to the system
having more legitimat
Author: jtl
Date: Tue Nov 10 18:12:09 2020
New Revision: 367573
URL: https://svnweb.freebsd.org/changeset/base/367573
Log:
When destroying a UMA zone which has a reserve (set with
uma_zone_reserve()), messages like the following appear on the console:
"Freed UMA keg (Test zone) was not empty
Author: jtl
Date: Sat Nov 14 14:50:34 2020
New Revision: 367680
URL: https://svnweb.freebsd.org/changeset/base/367680
Log:
Fix implicit automatic local port selection for IPv6 during connect calls.
When a user creates a TCP socket and tries to connect to the socket without
explicitly bind
Author: jtl
Date: Sat Nov 14 15:44:28 2020
New Revision: 367685
URL: https://svnweb.freebsd.org/changeset/base/367685
Log:
Add a regression test for the port-selection behavior fixed in r367680.
Reviewed by: markj, olivier, tuexen
Sponsored by: Netflix
Differential Revision:htt
Author: jtl
Date: Tue Nov 17 14:07:27 2020
New Revision: 367763
URL: https://svnweb.freebsd.org/changeset/base/367763
Log:
When copying types from one CTF container to another, ensure that we
always copy intrinsic data types before copying bitfields which are
based on those types. This ensur
On Tue, Nov 17, 2020 at 9:07 AM Jonathan T. Looney wrote:
> Author: jtl
> Date: Tue Nov 17 14:07:27 2020
> New Revision: 367763
> URL: https://svnweb.freebsd.org/changeset/base/367763
>
> Log:
> When copying types from one CTF container to another, ensure that we
> al
Author: jtl
Date: Fri Nov 20 17:26:02 2020
New Revision: 367905
URL: https://svnweb.freebsd.org/changeset/base/367905
Log:
When copying types from one CTF container to another, ensure that we
encode 0-length (i.e. "") structure and union member names as offset 0.
This ensures that we don't c
Author: jtl
Date: Fri Feb 1 15:38:20 2019
New Revision: 343662
URL: https://svnweb.freebsd.org/changeset/base/343662
Log:
Add bz@ as a co-mentor for thj@.
Approved by: core (implicit)
Modified:
svnadmin/conf/mentors
Modified: svnadmin/conf/mentors
=
Author: jtl
Date: Tue Apr 14 15:27:24 2020
New Revision: 359921
URL: https://svnweb.freebsd.org/changeset/base/359921
Log:
Make the path length of UNIX domain sockets specified by a #define.
Also, add a comment describing the historical context for this length.
Reviewed by: bz, jhb, kbow
Author: jtl
Date: Tue Apr 14 15:30:34 2020
New Revision: 359922
URL: https://svnweb.freebsd.org/changeset/base/359922
Log:
Print more detail as part of the sonewconn() overflow message.
When a socket's listen queue overflows, sonewconn() emits a debug-level
log message. These messages are
Author: jtl
Date: Tue Apr 14 15:38:18 2020
New Revision: 359923
URL: https://svnweb.freebsd.org/changeset/base/359923
Log:
Make sonewconn() overflow messages have per-socket rate-limits and values.
sonewconn() emits debug-level messages when a listen socket's queue
overflows. Currently, s
Author: jtl
Date: Thu Apr 16 20:07:34 2020
New Revision: 360019
URL: https://svnweb.freebsd.org/changeset/base/360019
Log:
Add a regression test for the changes in r359922 and r359923.
Note that the Python code has been tested on both Python 2.7 and 3.7.
Reviewed by: olivier
MFC aft
Author: jtl
Date: Thu Apr 16 20:17:24 2020
New Revision: 360020
URL: https://svnweb.freebsd.org/changeset/base/360020
Log:
Avoid calling protocol drain routines more than once per reclamation event.
mb_reclaim() calls the protocol drain routines for each protocol in each
domain. Some prot
On Sun, Apr 19, 2020 at 5:03 PM Enji Cooper wrote:
>
> > On Apr 16, 2020, at 1:07 PM, Jonathan T. Looney wrote:
> >
> > Author: jtl
> > Date: Thu Apr 16 20:07:34 2020
> > New Revision: 360019
> > URL: https://svnweb.freebsd.org/changeset/base/360019
>
Author: jtl
Date: Tue Oct 9 13:26:06 2018
New Revision: 339251
URL: https://svnweb.freebsd.org/changeset/base/339251
Log:
There are three places where we return from a function which entered an
epoch section without exiting that epoch section. This is bad for two
reasons: the epoch section
On Tue, Oct 9, 2018 at 11:02 AM John Baldwin wrote:
> Do we have some sort of simple per-thread epoch counter similar to
> td->td_locks that we could assert on in userret() and in the ithread loop
> when ithreads go to sleep to help catch leaked locks?
>
Yes: td->td_epochnest.
There are already
Author: jtl
Date: Tue Oct 16 00:48:18 2018
New Revision: 339373
URL: https://svnweb.freebsd.org/changeset/base/339373
Log:
Import CK as of commit 5221ae2f3722a78c7fc41e47069ad94983d3bccb.
This fixes two problems, one where epoch calls could occur before all
the readers had exited the epoch s
Author: jtl
Date: Tue Oct 16 00:50:00 2018
New Revision: 339374
URL: https://svnweb.freebsd.org/changeset/base/339374
Log:
Tag CK after import of commit 5221ae2f3722a78c7fc41e47069ad94983d3bccb.
Added:
vendor-sys/ck/20181014/
- copied from r339373, vendor-sys/ck/dist/
___
Author: jtl
Date: Tue Oct 16 02:30:13 2018
New Revision: 339375
URL: https://svnweb.freebsd.org/changeset/base/339375
Log:
Import CK as of commit 5221ae2f3722a78c7fc41e47069ad94983d3bccb.
This fixes two problems, one where epoch calls could occur before all
the readers had exited the epoch s
Author: jtl
Date: Tue Oct 16 14:41:09 2018
New Revision: 339378
URL: https://svnweb.freebsd.org/changeset/base/339378
Log:
In r338102, the TCP reassembly code was substantially restructured. Prior
to this change, the code sometimes used a temporary stack variable to hold
details of a TCP seg
Author: jtl
Date: Thu Oct 18 14:20:15 2018
New Revision: 339419
URL: https://svnweb.freebsd.org/changeset/base/339419
Log:
r334853 added a "socket destructor" callback. However, as implemented, it
was really a "socket close" callback.
Update the socket destructor functionality to run when
Author: jtl
Date: Fri Nov 2 19:14:15 2018
New Revision: 340077
URL: https://svnweb.freebsd.org/changeset/base/340077
Log:
m_pulldown() may reallocate n. Update the oip pointer after the
m_pulldown() call.
MFC after:2 weeks
Sponsored by: Netflix
Modified:
head/sys/netinet/ip_icmp
Nice find!
Jonathan
On Wed, Nov 7, 2018 at 6:28 PM Mark Johnston wrote:
> Author: markj
> Date: Wed Nov 7 23:28:11 2018
> New Revision: 340241
> URL: https://svnweb.freebsd.org/changeset/base/340241
>
> Log:
> Fix a use-after-free in swp_pager_meta_free().
>
> This was introduced in r32632
Author: jtl
Date: Fri Nov 16 18:32:48 2018
New Revision: 340483
URL: https://svnweb.freebsd.org/changeset/base/340483
Log:
Add some additional length checks to the IPv4 fragmentation code.
Specifically, block 0-length fragments, even when the MF bit is clear.
Also, ensure that every fragm
Author: jtl
Date: Mon Aug 6 17:36:57 2018
New Revision: 337384
URL: https://svnweb.freebsd.org/changeset/base/337384
Log:
Address concerns about CPU usage while doing TCP reassembly.
Currently, the per-queue limit is a function of the receive buffer
size and the MSS. In certain cases (s
Author: jtl
Date: Mon Aug 6 17:41:53 2018
New Revision: 337385
URL: https://svnweb.freebsd.org/changeset/base/337385
Log:
MFC r337384:
Address concerns about CPU usage while doing TCP reassembly.
Currently, the per-queue limit is a function of the receive buffer
size and the MSS. I
Author: jtl
Date: Mon Aug 6 17:46:28 2018
New Revision: 337386
URL: https://svnweb.freebsd.org/changeset/base/337386
Log:
MFC r337384:
Address concerns about CPU usage while doing TCP reassembly.
Currently, the per-queue limit is a function of the receive buffer
size and the MSS. I
Author: jtl
Date: Mon Aug 6 17:47:47 2018
New Revision: 337387
URL: https://svnweb.freebsd.org/changeset/base/337387
Log:
Address concerns about CPU usage while doing TCP reassembly.
Currently, the per-queue limit is a function of the receive buffer
size and the MSS. In certain cases (s
Author: jtl
Date: Mon Aug 6 17:48:46 2018
New Revision: 337388
URL: https://svnweb.freebsd.org/changeset/base/337388
Log:
Address concerns about CPU usage while doing TCP reassembly.
Currently, the per-queue limit is a function of the receive buffer
size and the MSS. In certain cases (s
Author: jtl
Date: Mon Aug 6 17:50:40 2018
New Revision: 337389
URL: https://svnweb.freebsd.org/changeset/base/337389
Log:
Address concerns about CPU usage while doing TCP reassembly.
Currently, the per-queue limit is a function of the receive buffer
size and the MSS. In certain cases (s
Author: jtl
Date: Mon Aug 6 18:42:37 2018
New Revision: 337390
URL: https://svnweb.freebsd.org/changeset/base/337390
Log:
Bump date after r337384.
Reported by: bz
Modified:
head/share/man/man4/tcp.4
Modified: head/share/man/man4/tcp.4
==
Author: jtl
Date: Mon Aug 6 18:46:09 2018
New Revision: 337391
URL: https://svnweb.freebsd.org/changeset/base/337391
Log:
MFC r337390: Bump date after r337384.
Modified:
stable/11/share/man/man4/tcp.4
Directory Properties:
stable/11/ (props changed)
Modified: stable/11/share/man/man4/tc
Author: jtl
Date: Mon Aug 6 18:47:03 2018
New Revision: 337392
URL: https://svnweb.freebsd.org/changeset/base/337392
Log:
MFC r337390: Bump date after r337384.
Modified:
stable/10/share/man/man4/tcp.4
Directory Properties:
stable/10/ (props changed)
Modified: stable/10/share/man/man4/tc
On Mon, Aug 6, 2018 at 2:16 PM Bjoern A. Zeeb <
bzeeb-li...@lists.zabbadoz.net> wrote:
>
> On 6 Aug 2018, at 17:36, Jonathan T. Looney wrote:
>
> > Author: jtl
> > Date: Mon Aug 6 17:36:57 2018
> > New Revision: 337384
> > URL: https://svnweb.freebs
Author: jtl
Date: Fri Apr 20 13:58:48 2018
New Revision: 332817
URL: https://svnweb.freebsd.org/changeset/base/332817
Log:
MFC r332120:
If a user closes the socket before we call tcp_usr_abort(), then
tcp_drop() may unlock the INP. Currently, tcp_usr_abort() does not
check for this
Author: jtl
Date: Fri Apr 20 14:01:08 2018
New Revision: 332818
URL: https://svnweb.freebsd.org/changeset/base/332818
Log:
MFC r331926:
r330675 introduced an extra window check in the LRO code to ensure it
captured and reported the highest window advertisement with the same
SEQ/ACK.
Author: jtl
Date: Fri Apr 20 14:21:37 2018
New Revision: 332819
URL: https://svnweb.freebsd.org/changeset/base/332819
Log:
MFC r331488:
This change adds a flag to the DAD entry to indicate whether it is
currently on the queue. This prevents accidentally doubly-removing a DAD
entry fr
Author: jtl
Date: Fri Apr 20 14:34:04 2018
New Revision: 332820
URL: https://svnweb.freebsd.org/changeset/base/332820
Log:
MFC r331484:
Remove some unneccessary variable sets in IPv6 code, as detected by
clang's static analyzer.
Sponsored by: Netflix, Inc.
Modified:
stable/11/sys
Author: jtl
Date: Fri Apr 20 14:47:02 2018
New Revision: 332821
URL: https://svnweb.freebsd.org/changeset/base/332821
Log:
MFC r331309:
If the INP lock is uncontested, avoid taking a reference and jumping
through the lock-switching hoops.
A few of the INP lookup operations that lo
Author: jtl
Date: Fri Apr 20 14:55:13 2018
New Revision: 332822
URL: https://svnweb.freebsd.org/changeset/base/332822
Log:
MFC r329071:
On bootup, the amd64 pmap initialization code creates page-table
mappings for the pages used for the kernel and some initial allocations
used for th
Author: jtl
Date: Fri Apr 20 15:05:48 2018
New Revision: 332823
URL: https://svnweb.freebsd.org/changeset/base/332823
Log:
MFC r329171:
Mark the pages used for the initial page-table entries as wired. This
makes them consistent with the way other page-table pages are allocated.
It al
Author: jtl
Date: Fri Apr 20 15:28:58 2018
New Revision: 332826
URL: https://svnweb.freebsd.org/changeset/base/332826
Log:
MFC r330510:
Prior to r329071, pmap_bootstrap() used pmap_kmem_choose() to round the
first available virtual address to a 2MB boundary. After r329071,
create_pag
Author: jtl
Date: Fri Apr 20 15:35:58 2018
New Revision: 332827
URL: https://svnweb.freebsd.org/changeset/base/332827
Log:
MFC r330511:
We shouldn't need to execute code in the recursive page table mappings;
therefore, it should be safe to set the NX bit on the PML4E for the
recursiv
Author: jtl
Date: Fri Apr 20 15:41:33 2018
New Revision: 332828
URL: https://svnweb.freebsd.org/changeset/base/332828
Log:
MFC r306768:
If the new window size is less than the old window size, skip the
calculations to check if we should advertise a larger window.
Modified:
stable/11/s
Author: jtl
Date: Fri Apr 20 15:44:29 2018
New Revision: 332829
URL: https://svnweb.freebsd.org/changeset/base/332829
Log:
MFC r307083:
Currently, when tcp_input() receives a packet on a session that matches a
TCPCB, it checks (so->so_options & SO_ACCEPTCONN) to determine whether or
not
Author: jtl
Date: Fri Apr 20 15:48:50 2018
New Revision: 332830
URL: https://svnweb.freebsd.org/changeset/base/332830
Log:
MFC r313447:
Ensure the idle thread's loop services interrupts in a timely way when
using the ACPI C1/mwait sleep method.
Previously, the mwait instruction wo
Author: jtl
Date: Fri Apr 20 15:55:09 2018
New Revision: 332831
URL: https://svnweb.freebsd.org/changeset/base/332831
Log:
MFC r314116:
Fix a panic during boot caused by inadequate locking of some vt(4) driver
data structures.
vt_change_font() calls vtbuf_grow() to change some vt
Author: jtl
Date: Fri Apr 20 18:37:19 2018
New Revision: 332834
URL: https://svnweb.freebsd.org/changeset/base/332834
Log:
MFC r314286:
Do some minimal work to better conform to the 802.3ad (LACP) standard.
In particular, don't set the synchronized bit for the peer unless it truly
ap
Author: jtl
Date: Fri Apr 20 20:09:42 2018
New Revision: 332840
URL: https://svnweb.freebsd.org/changeset/base/332840
Log:
MFC r319214:
Enforce the limit on ICMP messages before doing work to formulate the
response.
Delete an unneeded rate limit for UDP under IPv6. Because ICMP6
Author: jtl
Date: Fri Apr 20 20:16:42 2018
New Revision: 332841
URL: https://svnweb.freebsd.org/changeset/base/332841
Log:
MFC r319215:
Fix two places in the ICMP6 code where we could dereference a NULL pointer
in the icmp6_input() function.
When processing an ICMP6_ECHO_REQUEST,
Author: jtl
Date: Fri Apr 20 20:18:10 2018
New Revision: 332842
URL: https://svnweb.freebsd.org/changeset/base/332842
Log:
MFC r319216:
Fix an unnecessary/incorrect check in the PKTOPT_EXTHDRCPY macro.
This macro allocates memory and, if malloc does not return NULL, copies
data in
On Fri, Apr 20, 2018 at 2:20 PM, Dimitry Andric wrote:
>
> Author: dim
> Date: Fri Apr 20 18:20:55 2018
> New Revision: 332833
> URL: https://svnweb.freebsd.org/changeset/base/332833
>
> Log:
> Recommit r332501, with an additional upstream fix for "Cannot lower
> EFLAGS copy that lives out of
Author: jtl
Date: Sat Apr 21 17:05:00 2018
New Revision: 332860
URL: https://svnweb.freebsd.org/changeset/base/332860
Log:
When running with INVARIANTS, the kernel contains extra checks. However,
these assumptions may not hold true once we've panic'd. Therefore, the
checks hold less value a
Author: jtl
Date: Mon Apr 23 14:22:16 2018
New Revision: 332889
URL: https://svnweb.freebsd.org/changeset/base/332889
Log:
MFC r331745 (by np):
Fix RSS build (broken in r331309).
Sponsored by: Chelsio Communications
PR: 227691
Pointy-hat to:jtl
Modified:
st
Hi Mark,
Let me start by saying that I appreciate your well-reasoned response. (I
think) I understand your reasoning, I appreciate your well-explained
argument, and I respect your opinion. I just wanted to make that clear up
front.
On Sun, Apr 22, 2018 at 1:11 PM, Mark Johnston wrote:
>
> > All
On Mon, Apr 23, 2018 at 6:04 PM, John Baldwin wrote:
>
> I think this is actually a key question. In my experience to date I have
not
> encountered a large number of post-panic assertion failures. Given that
> we already break all locks and disable assertions for locks I'd be curious
> which ass
Author: jtl
Date: Tue Apr 24 18:47:35 2018
New Revision: 332958
URL: https://svnweb.freebsd.org/changeset/base/332958
Log:
Update r332860 by changing the default from suppressing post-panic
assertions to not suppressing post-panic assertions.
There are some post-panic assertions that are
On Thu, May 3, 2018 at 11:01 AM, Sean Bruno wrote:
>
> @@ -242,8 +241,8 @@ tf_cwnd(int ticks_since_cong, int rtt_ticks, unsigned
> {
>
> /* Equation 4 of I-D. */
> - return (((wmax * CUBIC_BETA) + (((THREE_X_PT2 * ticks_since_cong *
> - smss) << CUBIC_SHIFT) / TWO_SUB_PT2
1 - 100 of 199 matches
Mail list logo
