Author: jch
Date: Mon Nov 12 17:57:12 2018
New Revision: 340375
URL: https://svnweb.freebsd.org/changeset/base/340375
Log:
cxgbe/netmap: Fix cxgbe netmap when interface is DOWN
A kernel panic can occur if the cxgbe interface is DOWN
when activating netmap. This patch prevents the driver
Author: jch
Date: Tue Oct 24 08:56:11 2017
New Revision: 324948
URL: https://svnweb.freebsd.org/changeset/base/324948
Log:
MFC r324179, r324193:
r324179:
Fix an infinite loop in tcp_tw_2msl_scan() when an INP_TIMEWAIT inp has
been destroyed before its tcptw with INVARIANTS undefined.
Hi Jonathan,
On 10/16/17 7:04 PM, Jonathan Looney wrote:
> I apologize for just getting to this, but your code just made it into my
> local tree.
>
> The non-INVARIANTS case looks incorrect. Because tw stays on the list,
> it can end up stuck at the front of the queue and block everything
> beh
On 10/2/17 1:12 PM, Gary Jennejohn wrote:
> On Sun, 1 Oct 2017 21:20:28 + (UTC)
> Julien Charbon wrote:
>
>> Author: jch
>> Date: Sun Oct 1 21:20:28 2017
>> New Revision: 324179
>> URL: https://svnweb.freebsd.org/changeset/base/324179
>>
>> Log:
Author: jch
Date: Mon Oct 2 09:45:17 2017
New Revision: 324193
URL: https://svnweb.freebsd.org/changeset/base/324193
Log:
Forgotten bits in r324179: Include sys/syslog.h if INVARIANTS is not defined
MFC after:1 week
X-MFC with: r324179
Pointy hat to:jch
Modified:
head
Author: jch
Date: Sun Oct 1 21:20:28 2017
New Revision: 324179
URL: https://svnweb.freebsd.org/changeset/base/324179
Log:
Fix an infinite loop in tcp_tw_2msl_scan() when an INP_TIMEWAIT inp has
been destroyed before its tcptw with INVARIANTS undefined.
This is a symmetric change of r3075
Hi,
On 8/16/16 3:21 PM, Randall Stewart via svn-src-all wrote:
>
> In theory it *could* be MFC’d to stable-10 and 11 but I am not sure we want
> to do that. I am
> told by Drew that it does improve performance since in stable-10 you are
> getting the INFO_WLOCK()
> but I am not sure if folks
Author: jch
Date: Thu Nov 24 14:48:46 2016
New Revision: 309108
URL: https://svnweb.freebsd.org/changeset/base/309108
Log:
MFC r286227, r286443:
r286227:
Decompose TCP INP_INFO lock to increase short-lived TCP connections
scalability:
- The existing TCP INP_INFO lock continues to
Author: jch
Date: Mon Nov 7 18:29:21 2016
New Revision: 308426
URL: https://svnweb.freebsd.org/changeset/base/308426
Log:
MFC r307966:
Remove an extraneous call to soisconnected() in syncache_socket(),
introduced with r261242. The useful and expected soisconnected()
call is done in tc
Author: jch
Date: Thu Nov 3 19:58:12 2016
New Revision: 308263
URL: https://svnweb.freebsd.org/changeset/base/308263
Log:
MFC r307966:
Remove an extraneous call to soisconnected() in syncache_socket(),
introduced with r261242. The useful and expected soisconnected()
call is done in tc
Author: jch
Date: Wed Oct 26 15:19:18 2016
New Revision: 307966
URL: https://svnweb.freebsd.org/changeset/base/307966
Log:
Remove an extraneous call to soisconnected() in syncache_socket(),
introduced with r261242. The useful and expected soisconnected()
call is done in tcp_do_segment().
Author: jch
Date: Tue Oct 25 12:58:36 2016
New Revision: 307906
URL: https://svnweb.freebsd.org/changeset/base/307906
Log:
MFC r307551:
Fix a double-free when an inp transitions to INP_TIMEWAIT state
after having been dropped.
This change enforces in_pcbdrop() logic in tcp_input():
Author: jch
Date: Tue Oct 25 12:53:14 2016
New Revision: 307905
URL: https://svnweb.freebsd.org/changeset/base/307905
Log:
MFC r307551:
Fix a double-free when an inp transitions to INP_TIMEWAIT state
after having been dropped.
This change enforces in_pcbdrop() logic in tcp_input():
Author: jch
Date: Tue Oct 18 07:16:49 2016
New Revision: 307551
URL: https://svnweb.freebsd.org/changeset/base/307551
Log:
Fix a double-free when an inp transitions to INP_TIMEWAIT state
after having been dropped.
This fixes enforces in_pcbdrop() logic in tcp_input():
"in_pcbdrop() i
Author: jch
Date: Sun Oct 9 21:35:12 2016
New Revision: 306925
URL: https://svnweb.freebsd.org/changeset/base/306925
Log:
MFC r306443:
Fix an issue with accept_filter introduced with r261242:
As a side effect of r261242 when using accept_filter the
first call to soisconnected() is d
Author: jch
Date: Sun Oct 9 21:02:33 2016
New Revision: 306922
URL: https://svnweb.freebsd.org/changeset/base/306922
Log:
MFC r306443:
Fix an issue with accept_filter introduced with r261242:
As a side effect of r261242 when using accept_filter the
first call to soisconnected() is d
Author: jch
Date: Thu Sep 29 11:18:48 2016
New Revision: 306443
URL: https://svnweb.freebsd.org/changeset/base/306443
Log:
Fix an issue with accept_filter introduced with r261242:
As a side effect of r261242 when using accept_filter the
first call to soisconnected() is done earlier in tcp
Author: jch
Date: Wed Jul 27 13:53:15 2016
New Revision: 303389
URL: https://svnweb.freebsd.org/changeset/base/303389
Log:
MFC r286873:
Make clear that TIME_WAIT timeout expiration is managed solely by
tcp_tw_2msl_scan().
Sponsored by: Verisign, Inc.
Modified:
stable/10/sys/netine
e TCP input
processing starvation in context of high SYN load (e.g. short-lived TCP
connections or SYN flood).
Submitted by: Julien Charbon
Reviewed by: adrian, hiren, jhb, Mike Bentkofsky
r272081:
Catch up with r271119.
Modified:
stable/10/sys/netinet/tcp_input.c
stable/1
Author: jch
Date: Wed Jul 27 06:31:40 2016
New Revision: 303365
URL: https://svnweb.freebsd.org/changeset/base/303365
Log:
MFC r273014:
A connection in TIME_WAIT state before calling close() actually did not
received any RST packet. Do not set error to ECONNRESET in this case.
Diffe
advice already in the code.
See the PR below for a full discussion of this change and its
measured effects.
PR: 183659
Submitted by: Julien Charbon
Reviewed by: jhb
Modified:
stable/10/sys/netinet/tcp_syncache.c
stable/10/sys/netinet/tcp_usrreq.c
Directory Properties
Hi guys,
On 19/09/15 10:55, Hans Petter Selasky wrote:
> On 09/18/15 22:33, Davide Italiano wrote:
>> On Thu, Sep 17, 2015 at 12:20 AM, Hans Petter Selasky
>> wrote:
>>> On 09/17/15 00:05, Gleb Smirnoff wrote:
>> [...] 2) Your commit message didn't explain what (if any) is the
>> use case
> fo
Author: jch
Date: Sun Aug 30 13:44:46 2015
New Revision: 287305
URL: https://svnweb.freebsd.org/changeset/base/287305
Log:
Revert r286880: If at first this change made sense, it turns out
it helps only the TCP timers callout(9) usage. As the benefit for
others callout(9) usages did not rea
Author: jch
Date: Sun Aug 30 13:44:39 2015
New Revision: 287304
URL: https://svnweb.freebsd.org/changeset/base/287304
Log:
Put r284245 back in place: If at first this fix was seen as a temporary
workaround for a callout(9) issue, it turns out it is instead the right
way to use callout in mp
Hi Konstantin,
On 27/08/15 19:19, Konstantin Belousov wrote:
> On Thu, Aug 27, 2015 at 06:28:03PM +0200, Julien Charbon wrote:
>> On 27/08/15 12:49, Konstantin Belousov wrote:
>>> On Wed, Aug 26, 2015 at 08:14:15PM +0200, Julien Charbon wrote:
>>>> As I said, I a
Hi Konstantin,
On 27/08/15 12:49, Konstantin Belousov wrote:
> On Wed, Aug 26, 2015 at 08:14:15PM +0200, Julien Charbon wrote:
>> As I said, I am not opposed to back out this change, callout(9) API in
>> mpsafe mode is a already complex/subtle API, it won't change too
Author: jch
Date: Thu Aug 27 10:43:35 2015
New Revision: 287200
URL: https://svnweb.freebsd.org/changeset/base/287200
Log:
Silent a compilation warning on callout_stop()
Modified:
head/sys/kern/kern_timeout.c
Modified: head/sys/kern/kern_timeout.c
Hi Hans,
On 26/08/15 20:31, Hans Petter Selasky wrote:
> On 08/26/15 20:14, Julien Charbon wrote:
>> Let say that if nobody screams until Friday 8/28, I will put back
>> r284245 and revert this change_and_ I will make this case clear in the
>> man page.
>
> If you
Author: jch
Date: Thu Aug 27 08:58:03 2015
New Revision: 287198
URL: https://svnweb.freebsd.org/changeset/base/287198
Log:
In callout_stop(), do not forget to initialize not_running variable.
Thanks to hselasky for noticing that.
Differential Revision:https://reviews.freebsd.org/D
Hi Hans,
On 26/08/15 18:31, Julien Charbon wrote:
> On 26/08/15 09:25, Hans Petter Selasky wrote:
>> On 08/18/15 12:15, Julien Charbon wrote:
>>> Author: jch
>>> Date: Tue Aug 18 10:15:09 2015
>>> New Revision: 286880
>>> URL: https://svnweb.
Author: jch
Date: Thu Aug 27 08:15:32 2015
New Revision: 287196
URL: https://svnweb.freebsd.org/changeset/base/287196
Log:
In callout_stop(), if a callout is both pending and currently
being serviced return 0 (fail) but it is applicable only
mpsafe callouts. Thanks to hselasky for finding t
Hi Hans,
On 26/08/15 10:12, Hans Petter Selasky wrote:
> On 08/26/15 09:25, Hans Petter Selasky wrote:
>> On 08/18/15 12:15, Julien Charbon wrote:
>>> Author: jch
>>> Date: Tue Aug 18 10:15:09 2015
>>> New Revision: 286880
>>> URL: https://svnweb.
Hi Hans,
On 26/08/15 09:25, Hans Petter Selasky wrote:
> On 08/18/15 12:15, Julien Charbon wrote:
>> Author: jch
>> Date: Tue Aug 18 10:15:09 2015
>> New Revision: 286880
>> URL: https://svnweb.freebsd.org/changeset/base/286880
>>
>> Log:
>>c
Author: jch
Date: Mon Aug 24 09:30:27 2015
New Revision: 287101
URL: https://svnweb.freebsd.org/changeset/base/287101
Log:
Revert r284245: "Fix a callout race condition introduced in TCP
timers callouts with r281599."
r281599 fixed a TCP timer race condition, but due a callout(9) bug
i
Hi Hans,
On 18/08/15 12:59, Hans Petter Selasky wrote:
> On 08/18/15 12:15, Julien Charbon wrote:
>> Author: jch
>> Date: Tue Aug 18 10:15:09 2015
>> New Revision: 286880
>> URL: https://svnweb.freebsd.org/changeset/base/286880
>>
>> Log:
>>c
Author: jch
Date: Tue Aug 18 10:15:09 2015
New Revision: 286880
URL: https://svnweb.freebsd.org/changeset/base/286880
Log:
callout_stop() should return 0 (fail) when the callout is currently
being serviced and indeed unstoppable.
A scenario to reproduce this case is:
- the callout is
Author: jch
Date: Tue Aug 18 08:27:26 2015
New Revision: 286873
URL: https://svnweb.freebsd.org/changeset/base/286873
Log:
Make clear that TIME_WAIT timeout expiration is managed solely by
tcp_tw_2msl_scan().
Sponsored by: Verisign, Inc.
Modified:
head/sys/netinet/tcp_timer.c
Modified
Author: jch
Date: Sat Aug 8 08:40:36 2015
New Revision: 286443
URL: https://svnweb.freebsd.org/changeset/base/286443
Log:
Fix a kernel assertion issue introduced with r286227:
Avoid too strict INP_INFO_RLOCK_ASSERT checks due to
tcp_notify() being called from in6_pcbnotify().
Reported
Author: jch
Date: Mon Aug 3 12:13:54 2015
New Revision: 286227
URL: https://svnweb.freebsd.org/changeset/base/286227
Log:
Decompose TCP INP_INFO lock to increase short-lived TCP connections
scalability:
- The existing TCP INP_INFO lock continues to protect the global inpcb list
stabil
Author: jch
Date: Thu Jun 11 13:44:06 2015
New Revision: 284261
URL: https://svnweb.freebsd.org/changeset/base/284261
Log:
MFC r284245:
Fix a callout race condition introduced in TCP timers callouts with r281599.
In TCP timer context, it is not enough to check callout_stop() return value
t
Hi John,
On 10/06/15 17:32, John Baldwin wrote:
> On 6/10/15 4:43 PM, Julien Charbon wrote:
>> Author: jch
>> Date: Wed Jun 10 20:43:07 2015
>> New Revision: 284245
>> URL: https://svnweb.freebsd.org/changeset/base/284245
>>
>> Log:
>> Fix a ca
Author: jch
Date: Wed Jun 10 20:43:07 2015
New Revision: 284245
URL: https://svnweb.freebsd.org/changeset/base/284245
Log:
Fix a callout race condition introduced in TCP timers callouts with r281599.
In TCP timer context, it is not enough to check callout_stop() return value
to decide if a c
Author: jch
Date: Fri May 15 12:35:18 2015
New Revision: 282968
URL: https://svnweb.freebsd.org/changeset/base/282968
Log:
MFC r279821:
In TCP, connect() can return incorrect error code EINVAL
instead of EADDRINUSE or ECONNREFUSED
PR: 196035
Author: jch
Date: Fri May 15 12:07:43 2015
New Revision: 282964
URL: https://svnweb.freebsd.org/changeset/base/282964
Log:
MFC: r280904, r280990, r281599
r280904:
Use appropriate timeout_t* instead of void* in tcp_timer_activate()
Suggested by: imp
Differe
Author: jch
Date: Thu Apr 16 10:00:06 2015
New Revision: 281599
URL: https://svnweb.freebsd.org/changeset/base/281599
Log:
Fix an old and well-documented use-after-free race condition in
TCP timers:
- Add a reference from tcpcb to its inpcb
- Defer tcpcb deletion until TCP timers have fi
Author: jch
Date: Thu Apr 2 14:43:07 2015
New Revision: 280990
URL: https://svnweb.freebsd.org/changeset/base/280990
Log:
Provide better debugging information in tcp_timer_activate() and
tcp_timer_active()
Differential Revision:https://reviews.freebsd.org/D2179
Suggested by:
Author: jch
Date: Tue Mar 31 10:17:13 2015
New Revision: 280904
URL: https://svnweb.freebsd.org/changeset/base/280904
Log:
Use appropriate timeout_t* instead of void* in tcp_timer_activate()
Suggested by: imp
Differential Revision:https://reviews.freebsd.org/D2154
Review
Author: jch
Date: Mon Mar 9 20:29:16 2015
New Revision: 279821
URL: https://svnweb.freebsd.org/changeset/base/279821
Log:
In TCP, connect() can return incorrect error code EINVAL
instead of EADDRINUSE or ECONNREFUSED
PR: https://bugs.freebsd.org/bugzilla/show_bug.cgi?id
Author: jch
Date: Tue Dec 2 11:47:26 2014
New Revision: 275402
URL: https://svnweb.freebsd.org/changeset/base/275402
Log:
MFC r264321, r264342, r264351, r264356, r273850, r274629:
Currently, the TCP slow timer can starve TCP input processing while it
walks the list of connections in TIME
Author: jch
Date: Mon Nov 17 14:56:02 2014
New Revision: 274629
URL: https://svnweb.freebsd.org/changeset/base/274629
Log:
Re-introduce padding fields removed with r264321 to keep
struct tcptw ABI unchanged.
Suggested by: jhb
Approved by: jhb (mentor)
MFC after:1 day
X-MFC-With
Author: jch
Date: Thu Oct 30 08:53:56 2014
New Revision: 273850
URL: https://svnweb.freebsd.org/changeset/base/273850
Log:
Fix a race condition in TCP timewait between tcp_tw_2msl_reuse() and
tcp_tw_2msl_scan(). This race condition drives unplanned timewait
timeout cancellation. Also simpl
Author: jch
Date: Sun Oct 12 23:01:25 2014
New Revision: 273014
URL: https://svnweb.freebsd.org/changeset/base/273014
Log:
A connection in TIME_WAIT state before calling close() actually did not
received any RST packet. Do not set error to ECONNRESET in this case.
Differential Revision:
(r272085)
@@ -179,6 +179,7 @@ ivoras [label="Ivan Voras\nivoras@FreeBS
jamie [label="Jamie Gritton\nja...@freebsd.org\n2009/01/28"]
jasone [label="Jason Evans\njas...@freebsd.org\n1999/03/03"]
jceel [label="Jakub Klama\njc...@freebsd.org\n2011/09/25"]
+jch [lab
Hi Gleb,
On 10/04/14 21:29, Gleb Smirnoff wrote:
one comment:
On Thu, Apr 10, 2014 at 06:15:35PM +, John Baldwin wrote:
J> +/*
J> + * Drop a refcount on an tw elevated using tw_pcbref(). Return
J> + * the tw lock released.
J> + */
J> +static int
J> +tw_pcbrele(struct tcptw *tw)
J> +{
54 matches
Mail list logo