ocelot_qsys.h is missing the SPDX identfier, fix that.
Signed-off-by: Alexandre Belloni
---
drivers/net/ethernet/mscc/ocelot_qsys.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/mscc/ocelot_qsys.h
b/drivers/net/ethernet/mscc/ocelot_qsys.h
index aa7267d
On Thu, 2018-05-17 at 21:23 +0200, Alexandre Belloni wrote:
> ocelot_qsys.h is missing the SPDX identfier, fix that.
>
> Signed-off-by: Alexandre Belloni
Only the copyright holders should ideally be modifying
these and also removing other license content.
For instance, what's the real intent he
Add informative messages for error paths related to adding a
VLAN to a device.
Signed-off-by: David Ahern
---
net/8021q/vlan.c | 11 ---
net/8021q/vlan.h | 3 ++-
net/8021q/vlan_netlink.c | 45 ++---
3 files changed, 44 insertions(
On Thu, May 17, 2018 at 7:36 AM, Petr Machata wrote:
> __gre6_xmit() pushes GRE headers before handing over to ip6_tnl_xmit()
> for generic IP-in-IP processing. However it doesn't make sure that there
> is enough headroom to push the header to. That can lead to the panic
> cited below. (Reproducer
net/sched: add action inheritdsfield to skbmod
The new action inheritdsfield copies the field DS of
IPv4 and IPv6 packets into skb->prioriry. This enables
later classification of packets based on the DS field.
Original idea by Jamal Hadi Salim
Signed-off-by: Qiaobin Fu
Reviewed-by: Michel Mach
kselftest net pmtu.sh skipped due to missing dependencies ?
This is an open issues on all devices running linux-mainline and linux-next.
[ 105.064609] test_bpf: test_skb_segment: success in skb_segment!
[ 105.648758] IPv6: ADDRCONF(NETDEV_UP): veth_a: link is not ready
[ 105.692738] IPv6: ADDRC
On Thu, May 17, 2018 at 7:36 AM, Petr Machata wrote:
> dev->needed_headroom is not primed until ip6_tnl_xmit(), so it starts
> out zero. Thus the call to skb_cow_head() fails to actually make sure
> there's enough headroom to push the ERSPAN headers to. That can lead to
> the panic cited below. (R
On 17/05/2018 12:28:59-0700, Joe Perches wrote:
> On Thu, 2018-05-17 at 21:23 +0200, Alexandre Belloni wrote:
> > ocelot_qsys.h is missing the SPDX identfier, fix that.
> >
> > Signed-off-by: Alexandre Belloni
>
> Only the copyright holders should ideally be modifying
> these and also removing o
From: Yuchung Cheng
Date: Wed, 16 May 2018 16:40:09 -0700
> This patch set implements the features correspond to the
> draft-ietf-tcpm-rack-03 version of the RACK draft.
> https://datatracker.ietf.org/meeting/101/materials/slides-101-tcpm-update-on-tcp-rack-00
>
> 1. SACK: implement equivalent D
On Thu, May 17, 2018 at 7:36 AM, Petr Machata wrote:
> Split a reusable function ip6gre_tnl_copy_tnl_parm() from
> ip6gre_tnl_change(). This will allow ERSPAN-specific code to
> reuse the common parts while customizing the behavior for ERSPAN.
>
> Signed-off-by: Petr Machata
> ---
LGTM.
Acked-by
On Thu, May 17, 2018 at 7:36 AM, Petr Machata wrote:
> The function ip6gre_tnl_link_config() is used for setting up
> configuration of both ip6gretap and ip6erspan tunnels. Split the
> function into the common part and the route-lookup part. The latter then
> takes the calculated header length as
On Thu, May 17, 2018 at 7:36 AM, Petr Machata wrote:
> Extract from ip6gre_changelink() a reusable function
> ip6gre_changelink_common(). This will allow introduction of
> ERSPAN-specific _changelink() function with not a lot of code
> duplication.
>
> Signed-off-by: Petr Machata
> ---
LGTM.
Ack
From: William Tu
Date: Wed, 16 May 2018 17:24:32 -0700
> ERSPAN only support version 1 and 2. When packets send to an
> erspan device which does not have proper version number set,
> drop the packet. In real case, we observe multicast packets
> sent to the erspan pernet device, erspan0, which d
On Thu, May 17, 2018 at 7:36 AM, Petr Machata wrote:
> Extract from ip6gre_newlink() a reusable function
> ip6gre_newlink_common(). The ip6gre_tnl_link_config() call needs to be
> made customizable for ERSPAN, thus reorder it with calls to
> ip6_tnl_change_mtu() and dev_hold(), and extract the who
From: Tonghao Zhang
Date: Wed, 16 May 2018 19:09:23 -0700
> Introduce an new common helper to avoid redundancy.
>
> Signed-off-by: Tonghao Zhang
Applied to net-next, thanks.
On Thu, May 17, 2018 at 7:36 AM, Petr Machata wrote:
> Even though ip6erspan_tap_init() sets up hlen and tun_hlen according to
> what ERSPAN needs, it goes ahead to call ip6gre_tnl_link_config() which
> overwrites these settings with GRE-specific ones.
>
> Similarly for changelink callbacks, which
From: YueHaibing
Date: Thu, 17 May 2018 11:46:41 +0800
> As documented in Documentation/timers/timers-howto.txt,
> replace msleep(1) with usleep_range().
>
> Signed-off-by: YueHaibing
Applied, thank you.
From: Hemanth Puranik
Date: Thu, 17 May 2018 13:58:00 +0530
> Currently we use non-NUMA aware allocation for TPD and RRD buffers,
> this patch modifies to use NUMA friendly allocation.
>
> Signed-off-by: Hemanth Puranik
> ---
> drivers/net/ethernet/qualcomm/emac/emac-mac.c | 6 --
> 1 file
Most of the TI drivers build just fine with COMPILE_TEST, cpmac (AR7) is
the exception because it uses a header file from
arch/mips/include/asm/mach-ar7/ar7.h and keystone netcp which requires
help from drivers/soc/ti/ for queue management helpers.
Signed-off-by: Florian Fainelli
---
drivers/net
The Freescale FEC driver builds fine with COMPILE_TEST, so make that
possible.
Signed-off-by: Florian Fainelli
---
drivers/net/ethernet/freescale/Kconfig| 2 +-
drivers/net/ethernet/freescale/fec.h | 2 +-
drivers/net/ethernet/freescale/fec_main.c | 2 +-
3 files changed, 3 insertions(+
Hi David,
This patch series includes more drivers to be build tested with COMPILE_TEST
enabled. This helps cover some of the issues I just ran into with missing
a driver *sigh*.
Chanves in v3:
- drop the TI Keystone NETCP driver from the COMPILE_TEST additions
Changes in v2:
- allow FEC to bui
Those drivers build just fine with COMPILE_TEST, so make that possible.
Signed-off-by: Florian Fainelli
---
drivers/net/phy/Kconfig | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index 0e2305ccc91f..343989f9f9d9 100644
--
From: Kalle Valo
Date: Thu, 17 May 2018 11:44:34 +0300
> here's a pull request to net-next for 4.18. I forgot to mention in the
> signed tag was that one id is added to include/linux/mmc/sdio_ids.h but
> that was acked by Ulf.
>
> I suspect hat because of my merge of wireless-drivers into
> wire
From: Antoine Tenart
Date: Thu, 17 May 2018 10:29:29 +0200
> @Dave: patches 7 to 10 should go through the mvebu tree (Gregory in
> Cc.) to avoid any conflict with the other mvebu dt patches taken during
> this cycle.
>
> The series is based on today's net-next.
Ok, patches 1-6 applied to net-ne
On 05/17/2018 11:57 AM, Martin KaFai Lau wrote:
> On Thu, May 17, 2018 at 08:54:10AM -0700, John Fastabend wrote:
>> Add tests for BPF_PROG_TYPE_SK_MSG to test_verifier for read access
>> to new sk fields.
>>
>> Signed-off-by: John Fastabend
>> ---
[...]
>> +{
>> +"invalid read
On 05/17/2018 11:17 AM, Martin KaFai Lau wrote:
> On Thu, May 17, 2018 at 08:54:04AM -0700, John Fastabend wrote:
>> Currently sk_msg programs only have access to the raw data. However,
>> it is often useful when building policies to have the policies specific
>> to the socket endpoint. This allows
From: Antoine Tenart
Date: Thu, 17 May 2018 10:34:27 +0200
> From: Yan Markman
>
> Prevent flood of RX error prints during heavy traffic with weak signal
> in link by checking net_ratelimit() before using netdev_err().
>
> Signed-off-by: Yan Markman
> [Antoine: small rework, commit message]
>
From: Antoine Tenart
Date: Thu, 17 May 2018 10:34:26 +0200
> From: Yan Markman
>
> Remove special stop/start handling from the set_mac_address callback.
> All this special care is not needed, and can be removed. It also
> simplifies the up/down status in the driver and helps avoiding possible
>
From: Antoine Tenart
Date: Thu, 17 May 2018 10:34:25 +0200
> From: Yan Markman
>
> Avoid repeating the check for free aggregated descriptors when it
> already failed at the beginning of the function.
>
> Signed-off-by: Yan Markman
> [Antoine: commit message]
> Signed-off-by: Antoine Tenart
From: Jiri Pirko
Date: Thu, 17 May 2018 12:06:43 +0200
> From: Jiri Pirko
>
> Don't store repr pointer to reprs array until the representor is
> successfully created. This avoids message about "representor
> destruction" even when it was never created. Also it cleans-up the flow.
> Also, check
From: Eric Dumazet
Date: Thu, 17 May 2018 03:54:21 -0700
> syzkaller found that following program crashes the host :
>
> {
> int fd = socket(AF_SMC, SOCK_STREAM, 0);
> int val = 1;
>
> listen(fd, 0);
> shutdown(fd, SHUT_RDWR);
> setsockopt(fd, 6, TCP_NODELAY, &val, 4);
> }
>
> Simply
From: Dan Carpenter
Date: Thu, 17 May 2018 15:33:36 +0300
> We recently refactored this code and introduced a static checker
> warning. Smatch complains that if cmd->index is zero then we would
> underflow the arrays. That's obviously true.
>
> The question is whether we prevent cmd->index fro
On Thu, 2018-05-17 at 14:50 -0400, David Miller wrote:
> I'm surprised this problem wasn't discovered sooner. How exactly did you
> discover it? Did you actually see it trigger or is this purely from code
> inspection?
Honestly, I'm not sure how it got uncovered, but it was observed at
runtime.
> The platform data assumes there is a network device named "eth0" as the
> parent device, yes I know this is terrible, but unfortunately we don't
> have anything better at this point
That is something we need to solve. With DT, it is easy, we have a
phandle to a device, and the name does not matt
From: Roman Mashak
Date: Thu, 17 May 2018 09:12:49 -0400
> Reported-by: Vlad Buslov
> Reported-by: Davide Caratti
> Signed-off-by: Roman Mashak
Applied.
From: Andrea Greco
Date: Thu, 17 May 2018 15:05:29 +0200
> + /* Will be set by userspace during if setup */
> + dev->dev_addr[0] = 0;
Hmmm... really?
Also, every error path from this point forward will leak 'dev'.
On 05/16/2018 11:46 PM, John Fastabend wrote:
> In the sockmap design BPF programs (SK_SKB_STREAM_PARSER and
> SK_SKB_STREAM_VERDICT) are attached to the sockmap map type and when
> a sock is added to the map the programs are used by the socket.
> However, sockmap updates from both userspace and BP
On 05/17/2018 07:39 PM, Jesper Dangaard Brouer wrote:
> Commit 0a6748740368 ("selftests/bpf: Only run tests if !bpf_disabled")
> forgot to check return value of fopen.
>
> This caused some confusion, when running test_verifier (from
> tools/testing/selftests/bpf/) on an older kernel (< v4.4) as it
On 05/17/2018 10:47 AM, Eric Dumazet wrote:
> + /* compress ack timer : 5 % of srtt, but no more than 1 ms */
> +
> + delay = min_t(unsigned long, NSEC_PER_MSEC,
> + tp->rcv_rtt_est.rtt_us * (NSEC_PER_USEC >> 3)/20);
>
Yuchung suggested that we use min(rtt, rcv_rtt), a
From: Petr Machata
Date: Thu, 17 May 2018 16:36:04 +0200
> This series mends some problems in headroom management in ip6_gre
> module. The current code base has the following three closely-related
> problems:
>
> - ip6gretap tunnels neglect to ensure there's enough writable headroom
> before p
From: Matt Mullins
Date: Thu, 17 May 2018 20:28:46 +
> On Thu, 2018-05-17 at 14:50 -0400, David Miller wrote:
>> I'm surprised this problem wasn't discovered sooner. How exactly did you
>> discover it? Did you actually see it trigger or is this purely from code
>> inspection?
>
> Honestly,
Fixes: c12b395a4664 ("gre: Support GRE over IPv6")
Fixes: e41c7c68ea77 ("ip6erspan: make sure enough headroom at xmit.")
Fixes: 5a963eb61b7c ("ip6_gre: Add ERSPAN native tunnel support")
Fixes: 5a963eb61b7c ("ip6_gre: Add ERSPAN native tunnel support")
Fixes: 5a963eb61b7c ("ip6_gre: Add ERSPAN native tunnel support")
Fixes: 5a963eb61b7c ("ip6_gre: Add ERSPAN native tunnel support")
Fixes: 5a963eb61b7c ("ip6_gre: Add ERSPAN native tunnel support")
Thu, May 17, 2018 at 09:14:32PM CEST, f.faine...@gmail.com wrote:
>On 05/17/2018 10:39 AM, Jiri Pirko wrote:
That is compiled inside "fixed_phy", isn't it?
>>>
>>> It matches what CONFIG_FIXED_PHY is, so if it's built-in it also becomes
>>> built-in, if is modular, it is also modular, this was
On 05/17/2018 04:04 PM, Gustavo A. R. Silva wrote:
> This patchset aims to fix an uninitialized variable issue and
> a double-free issue in __sock_map_ctx_update_elem.
>
> Both issues were reported by Coverity.
>
> Thanks.
>
> Gustavo A. R. Silva (2):
> bpf: sockmap, fix uninitialized variable
When a system is under memory presure (high usage with fragments),
the original 256KB ICM chunk allocations will likely trigger kernel
memory management to enter slow path doing memory compact/migration
ops in order to complete high order memory allocations.
When that happens, user processes calli
On Fri, 16 Mar 2018 05:00:28 -0400
Richard Guy Briggs wrote:
> Implement the proc fs write to set the audit container ID of a
> process, emitting an AUDIT_CONTAINER record to document the event.
>
> This is a write from the container orchestrator task to a proc entry
> of the form /proc/PID/cont
On Thu, May 17, 2018 at 10:17:59AM -0700, Y Song wrote:
> On Wed, May 16, 2018 at 2:04 PM, Sean Young wrote:
> > This is simple test over rc-loopback.
> >
> > Signed-off-by: Sean Young
> > ---
> > tools/bpf/bpftool/prog.c | 1 +
> > tools/include/uapi/linux/bpf.h
From: Jeff Kirsher
Date: Thu, 17 May 2018 09:37:26 -0700
> This series contains updates to ixgbe, ixgbevf and ice drivers.
>
> Cathy Zhou resolves sparse warnings by using the force attribute.
>
> Mauro S M Rodrigues fixes a bug where IRQs were not freed if a PCI error
> recovery system opts to
David Miller writes:
> Series applied, thank you.
Hi David, I forgot to add Fixes lines to the individual patches. I
replied to the e-mails with those. Let me know if you want me to send a
v2 with that and the Acked-by's.
> Those reproducable test cases in the various commit messages are
> pret
On 05/17/2018 01:31 PM, Daniel Borkmann wrote:
> On 05/16/2018 11:46 PM, John Fastabend wrote:
>> In the sockmap design BPF programs (SK_SKB_STREAM_PARSER and
>> SK_SKB_STREAM_VERDICT) are attached to the sockmap map type and when
>> a sock is added to the map the programs are used by the socket.
>
If the user were to only attach one of the parse or verdict programs
then it is possible a subsequent sockmap update could incorrectly
decrement the refcnt on the program. This happens because in the
rollback logic, after an error, we have to decrement the program
reference count when its been incr
In the sockmap design BPF programs (SK_SKB_STREAM_PARSER,
SK_SKB_STREAM_VERDICT and SK_MSG_VERDICT) are attached to the sockmap
map type and when a sock is added to the map the programs are used by
the socket. However, sockmap updates from both userspace and BPF
programs can happen concurrently wit
From: Willem de Bruijn
Date: Thu, 17 May 2018 13:13:29 -0400
> From: Willem de Bruijn
>
> Device features may change during transmission. In particular with
> corking, a device may toggle scatter-gather in between allocating
> and writing to an skb.
>
> Do not unconditionally assume that !NETI
From: Manish Chopra
Date: Thu, 17 May 2018 12:05:00 -0700
> This patch makes use of build_skb() throughout in driver's receieve
> data path [HW gro flow and non HW gro flow]. With this, driver can
> build skb directly from the page segments which are already mapped
> to the hardware instead of al
On Thu, May 17, 2018 at 10:48:55PM +0200, Jiri Pirko wrote:
> Thu, May 17, 2018 at 09:14:32PM CEST, f.faine...@gmail.com wrote:
> >On 05/17/2018 10:39 AM, Jiri Pirko wrote:
> That is compiled inside "fixed_phy", isn't it?
> >>>
> >>> It matches what CONFIG_FIXED_PHY is, so if it's built-in it
From: David Ahern
Date: Thu, 17 May 2018 12:29:47 -0700
> Add informative messages for error paths related to adding a
> VLAN to a device.
>
> Signed-off-by: David Ahern
Applied, thanks David.
On Fri, 16 Mar 2018 05:00:30 -0400
Richard Guy Briggs wrote:
> Create a new audit record AUDIT_CONTAINER_INFO to document the
> container ID of a process if it is present.
As mentioned in a previous email, I think AUDIT_CONTAINER is more
suitable for the container record. One more comment below.
Hi Daniel,
On 05/17/2018 03:51 PM, Daniel Borkmann wrote:
On 05/17/2018 04:04 PM, Gustavo A. R. Silva wrote:
This patchset aims to fix an uninitialized variable issue and
a double-free issue in __sock_map_ctx_update_elem.
Both issues were reported by Coverity.
Thanks.
Gustavo A. R. Silva (2)
From: Florian Fainelli
Date: Thu, 17 May 2018 13:07:42 -0700
> Hi David,
>
> This patch series includes more drivers to be build tested with COMPILE_TEST
> enabled. This helps cover some of the issues I just ran into with missing
> a driver *sigh*.
>
> Chanves in v3:
>
> - drop the TI Keystone
On 05/17/2018 01:53 PM, Qing Huang wrote:
> When a system is under memory presure (high usage with fragments),
> the original 256KB ICM chunk allocations will likely trigger kernel
> memory management to enter slow path doing memory compact/migration
> ops in order to complete high order memory a
Add tests for BPF_PROG_TYPE_SK_MSG to test_verifier for read access
to new sk fields.
Signed-off-by: John Fastabend
Acked-by: Martin KaFai Lau
---
tools/include/uapi/linux/bpf.h |8 ++
tools/testing/selftests/bpf/test_verifier.c | 115 +++
2 files chang
Currently sk_msg programs only have access to the raw data. However,
it is often useful when building policies to have the policies specific
to the socket endpoint. This allows using the socket tuple as input
into filters, etc.
This patch adds ctx access to the sock fields.
Signed-off-by: John Fa
In this series we add the ability for sk msg programs to read basic
sock information about the sock they are attached to. The second
patch adds the tests to the selftest test_verifier.
One obseration that I had from writing this seriess is lots of the
./net/core/filter.c code is almost duplicated
From: Petr Machata
Date: Fri, 18 May 2018 00:03:58 +0300
> David Miller writes:
>
>> Series applied, thank you.
>
> Hi David, I forgot to add Fixes lines to the individual patches. I
> replied to the e-mails with those. Let me know if you want me to send a
> v2 with that and the Acked-by's.
W
On Thu, May 17, 2018 at 01:44:11AM +0200, Daniel Borkmann wrote:
> Recently during testing, I ran into the following panic:
>
> [ 207.892422] Internal error: Accessing user space memory outside
> uaccess.h routines: 9604 [#1] SMP
> [ 207.901637] Modules linked in: binfmt_misc [...]
>
On Tue, 15 May 2018 21:06:15 +0200 Björn Töpel wrote:
> From: Magnus Karlsson
>
> Here, the zero-copy ndo is implemented. As a shortcut, the existing
> XDP Tx rings are used for zero-copy. This means that and XDP program
> cannot redirect to an AF_XDP enabled XDP Tx ring.
This "shortcut" is n
On 2018-05-17 17:09, Steve Grubb wrote:
> On Fri, 16 Mar 2018 05:00:30 -0400
> Richard Guy Briggs wrote:
>
> > Create a new audit record AUDIT_CONTAINER_INFO to document the
> > container ID of a process if it is present.
>
> As mentioned in a previous email, I think AUDIT_CONTAINER is more
> su
On 5/17/2018 2:14 PM, Eric Dumazet wrote:
On 05/17/2018 01:53 PM, Qing Huang wrote:
When a system is under memory presure (high usage with fragments),
the original 256KB ICM chunk allocations will likely trigger kernel
memory management to enter slow path doing memory compact/migration
ops in
When TCP receives an out-of-order packet, it immediately sends
a SACK packet, generating network load but also forcing the
receiver to send 1-MSS pathological packets, increasing its
RTX queue length/depth, and thus processing time.
Wifi networks suffer from this aggressive behavior, but generally
This per netns sysctl allows for TCP SACK compression fine-tuning.
Its default value is 1,000,000, or 1 ms to meet TSO autosizing period.
Signed-off-by: Eric Dumazet
---
Documentation/networking/ip-sysctl.txt | 7 +++
include/net/netns/ipv4.h | 1 +
net/ipv4/sysctl_net_ipv4.c
This per netns sysctl allows for TCP SACK compression fine-tuning.
This limits number of SACK that can be compressed.
Using 0 disables SACK compression.
Signed-off-by: Eric Dumazet
---
Documentation/networking/ip-sysctl.txt | 6 ++
include/net/netns/ipv4.h | 1 +
net/ipv4/sy
This counter tracks number of ACK packets that the host has not sent,
thanks to ACK compression.
Sample output :
$ nstat -n;sleep 1;nstat|egrep
"IpInReceives|IpOutRequests|TcpInSegs|TcpOutSegs|TcpExtTCPAckCompressed"
IpInReceives123250 0.0
IpOutRequests
When TCP receives an out-of-order packet, it immediately sends
a SACK packet, generating network load but also forcing the
receiver to send 1-MSS pathological packets, increasing its
RTX queue length/depth, and thus processing time.
Wifi networks suffer from this aggressive behavior, but generally
Hi,
Again thanks for a thoughtful review. This will definitely will improve
the code.
On Thu, May 17, 2018 at 10:02:52AM -0700, Y Song wrote:
> On Wed, May 16, 2018 at 2:04 PM, Sean Young wrote:
> > Add support for BPF_PROG_RAWIR_EVENT. This type of BPF program can call
> > rc_keydown() to repor
Socket can not disappear under us.
Signed-off-by: Eric Dumazet
Acked-by: Neal Cardwell
---
include/net/tcp.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index
6deb540297ccaa1f05ce633efe313d1ca2c15dd9..511bd0fde1dc1dd842598d083905b04
As explained in commit 9f9843a751d0 ("tcp: properly handle stretch
acks in slow start"), TCP stacks have to consider how many packets
are acknowledged in one single ACK, because of GRO, but also
because of ACK compression or losses.
We plan to add SACK compression in the following patch, we
must t
David Miller writes:
> Luckily for you, your Fixes: tags went out before I pushed, so I could
> actually fix up the commit messages and add the tags.
I was hoping that would be the case.
Thanks,
Petr
On 2018-05-17 17:00, Steve Grubb wrote:
> On Fri, 16 Mar 2018 05:00:28 -0400
> Richard Guy Briggs wrote:
>
> > Implement the proc fs write to set the audit container ID of a
> > process, emitting an AUDIT_CONTAINER record to document the event.
> >
> > This is a write from the container orchestr
While removing queues from the XPS map, the individual CPU ID
alone was used to index the CPUs map, this should be changed to also
factor in the traffic class mapping for the CPU-to-queue lookup.
Fixes: 184c449f91fe ("net: Add support for XPS with QoS via traffic classes")
Signed-off-by: Amritha N
On Thu, May 17, 2018 at 5:47 PM Eric Dumazet wrote:
> When TCP receives an out-of-order packet, it immediately sends
> a SACK packet, generating network load but also forcing the
> receiver to send 1-MSS pathological packets, increasing its
> RTX queue length/depth, and thus processing time.
> W
On Thu, May 17, 2018 at 5:47 PM Eric Dumazet wrote:
> This per netns sysctl allows for TCP SACK compression fine-tuning.
> Its default value is 1,000,000, or 1 ms to meet TSO autosizing period.
> Signed-off-by: Eric Dumazet
> ---
Acked-by: Neal Cardwell
Thanks!
neal
On Thu, May 17, 2018 at 5:47 PM Eric Dumazet wrote:
> This per netns sysctl allows for TCP SACK compression fine-tuning.
> This limits number of SACK that can be compressed.
> Using 0 disables SACK compression.
> Signed-off-by: Eric Dumazet
> ---
Acked-by: Neal Cardwell
Thanks!
neal
On 05/17/2018 02:08 PM, Andrew Lunn wrote:
> On Thu, May 17, 2018 at 10:48:55PM +0200, Jiri Pirko wrote:
>> Thu, May 17, 2018 at 09:14:32PM CEST, f.faine...@gmail.com wrote:
>>> On 05/17/2018 10:39 AM, Jiri Pirko wrote:
>> That is compiled inside "fixed_phy", isn't it?
>
> It matches wh
On Thu, May 17, 2018 at 2:57 PM, Neal Cardwell wrote:
> On Thu, May 17, 2018 at 5:47 PM Eric Dumazet wrote:
>
>> When TCP receives an out-of-order packet, it immediately sends
>> a SACK packet, generating network load but also forcing the
>> receiver to send 1-MSS pathological packets, increasing
Hello
Greetings to you please i have a business proposal for you contact me
for more detailes asap thanks.
Best Regards,
Miss.Zeliha ömer faruk
Esentepe Mahallesi Büyükdere
Caddesi Kristal Kule Binasi
No:215
Sisli - Istanbul, Turkey
Even if commit 1d27732f411d ("net: dsa: setup and teardown ports") indicated
that registering a devlink instance for unused ports is not a problem, and this
is true, this can be confusing nonetheless, so let's not do it.
Fixes: 1d27732f411d ("net: dsa: setup and teardown ports")
Reported-by: Jiri
From: David Ahern
Using iproute2 to create a bridge and add 4094 vlans to it can take from
2 to 3 *minutes*. The reason is the extraneous call to ll_name_to_index.
ll_name_to_index results in an ioctl(SIOCGIFINDEX) call which in turn
invokes dev_load. If the index does not exist, which it won't w
On 05/17/2018 06:09 PM, David Ahern wrote:
> Add check that egress MTU can handle packet to be forwarded. If
> the MTU is less than the packet lenght, return 0 meaning the
> packet is expected to continue up the stack for help - eg.,
> fragmenting the packet or sending an ICMP.
>
> Signed-off-by:
On 05/17/2018 03:16 PM, Florian Fainelli wrote:
> Even if commit 1d27732f411d ("net: dsa: setup and teardown ports") indicated
> that registering a devlink instance for unused ports is not a problem, and
> this
> is true, this can be confusing nonetheless, so let's not do it.
>
> Fixes: 1d27732f4
On 05/17/2018 11:06 PM, John Fastabend wrote:
> If the user were to only attach one of the parse or verdict programs
> then it is possible a subsequent sockmap update could incorrectly
> decrement the refcnt on the program. This happens because in the
> rollback logic, after an error, we have to de
On Thu, 17 May 2018 16:22:37 -0600
dsah...@kernel.org wrote:
> From: David Ahern
>
> Using iproute2 to create a bridge and add 4094 vlans to it can take from
> 2 to 3 *minutes*. The reason is the extraneous call to ll_name_to_index.
> ll_name_to_index results in an ioctl(SIOCGIFINDEX) call which
On Thu, May 17, 2018 at 03:06:36PM -0700, Florian Fainelli wrote:
> On 05/17/2018 02:08 PM, Andrew Lunn wrote:
> > On Thu, May 17, 2018 at 10:48:55PM +0200, Jiri Pirko wrote:
> >> Thu, May 17, 2018 at 09:14:32PM CEST, f.faine...@gmail.com wrote:
> >>> On 05/17/2018 10:39 AM, Jiri Pirko wrote:
> >>>
On 5/17/2018 12:05 PM, Florian Fainelli wrote:
> On 05/15/2018 06:26 PM, Amritha Nambiar wrote:
>> Extend transmit queue sysfs attribute to configure Rx queue map
>> per Tx queue. By default no receive queues are configured for the
>> Tx queue.
>>
>> - /sys/class/net/eth0/queues/tx-*/xps_rxqs
>
>
On 05/17/2018 03:40 PM, Andrew Lunn wrote:
> On Thu, May 17, 2018 at 03:06:36PM -0700, Florian Fainelli wrote:
>> On 05/17/2018 02:08 PM, Andrew Lunn wrote:
>>> On Thu, May 17, 2018 at 10:48:55PM +0200, Jiri Pirko wrote:
Thu, May 17, 2018 at 09:14:32PM CEST, f.faine...@gmail.com wrote:
> O
201 - 300 of 364 matches
Mail list logo
