On Mon, Jun 13, 2016 at 03:03:01PM +0300, Leon Romanovsky wrote:
> Hi Doug and David,
>
> This is Mellanox mlx5_core shared code for both net-next and RDMA
> trees for 4.8 kernel cycle.
>
> This mlx5_ifc update introduces following ConnectX-4 features.
>
> * netdev part:
> - MLX5_CQ_PERIOD_NUM_
On Tue, Jun 14, 2016 at 02:12:49AM -0400, David Miller wrote:
>
> A bare pull request does not work.
>
> You must post the actual patches so that they can be reviewed
> properly.
Sorry, It was first time attempt to get the sense for the proper procedure.
I will send the patch as a reply to this
Hello,
On Mon, 13 Jun 2016, Hannes Frederic Sowa wrote:
> Unfortunately because of bisectability I cannot split this patch. :(
>
> Signed-off-by: Hannes Frederic Sowa
> ---
> diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
> index b4d746943bc570..961d7905599150 100644
> --- a/driver
* Yuchung Cheng | 2016-06-13 15:38:24 [-0700]:
Hey Eric, Yuchung,
regarding the missed mdev_max_us: internal communication problem. Daniel well
respin a v2 removing the no longer required mdev_max_us.
>Thanks for the patch. I also have long wanted to evaluate Linux's RTO vs RFC's.
>
>Since this
A bare pull request does not work.
You must post the actual patches so that they can be reviewed
properly.
Hello,
On Mon, 13 Jun 2016, Hannes Frederic Sowa wrote:
> Signed-off-by: Hannes Frederic Sowa
> ---
> include/net/flow.h | 11 ---
> include/net/route.h | 8
> net/netfilter/ipvs/ip_vs_xmit.c | 9 +++--
> net/sctp/protocol.c |
Hello,
On Mon, 13 Jun 2016, Hannes Frederic Sowa wrote:
> - flowi4_init_output(fl4, oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE,
> -protocol, flow_flags, dst, src, dport, sport);
> + fl4->flowi4_oif = oif;
> + fl4->flowi4_iif = LOOPBACK_IFINDEX;
> + f
On Tue, Jun 14, 2016 at 4:50 AM, Shrikrishna Khare wrote:
> +++ b/drivers/net/vmxnet3/vmxnet3_defs.h
> @@ -81,6 +81,7 @@ enum {
> VMXNET3_CMD_RESERVED2,
> VMXNET3_CMD_RESERVED3,
> VMXNET3_CMD_SET_COALESCE,
> + VMXNET3_CMD_REGISTER_MEMREGS,
>
> VMXNET3_CMD_FIR
On Tue, Jun 14, 2016 at 4:50 AM, Shrikrishna Khare wrote:
> This patchset upgrades vmxnet3 to version 3.
Except for one patch, all the rest lack change-log, which makes it
somehow needlessly harder to review and maintain
> Shrikrishna Khare (7):
> vmxnet3: prepare for version 3 changes
> vmx
On Tue, Jun 14, 2016 at 12:00:04AM +0200, Paolo Abeni wrote:
> The commit 34166093639b ("tuntap: use common code for virtio_net_hdr
> and skb GSO conversion") replaced the tun code for header manipulation
> with the generic helpers. While doing so, it implictly moved the
> skb_partial_csum_set() in
The commit e858fae2b0b8 ("virtio_net: use common code for virtio_net_hdr
and skb GSO conversion") replaced the tun code for header manipulation
with the generic helpers. While doing so, it implictly moved the
skb_partial_csum_set() invocation after eth_type_trans(), which
invalidate the current gso
saw a debug splat:
net/include/net/sch_generic.h:287 suspicious rcu_dereference_check() usage!
other info that might help us debug this:
rcu_scheduler_active = 1, debug_locks = 0
2 locks held by kworker/2:1/710:
#0: ("events"){.+.+.+}, at: []
#1: ((&q->work)){+.+...}, at: []
process_one_wor
Acked-by:Vidya Sagar Ravipati
Validated this patch with various modules.
Replied from wrong email alias earlier.
On Thu, Jun 9, 2016 at 5:55 PM, David Decotigny wrote:
> From: David Decotigny
>
> More info with kernel commit 8d3f2806f8fb ("Merge branch
> 'ethtool-ksettings'").
>
> Note: The n
Acked-by:Vidya Sagar Ravipati
Validated this patch with various modules.
On Thu, Jun 9, 2016 at 5:55 PM, David Decotigny wrote:
> From: David Decotigny
>
> More info with kernel commit 8d3f2806f8fb ("Merge branch
> 'ethtool-ksettings'").
>
> Note: The new features implemented in this patch dep
sfq_reset() can use rtnl_kfree_skbs() instead of kfree_skb()
Signed-off-by: Eric Dumazet
---
net/sched/sch_sfq.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index a2e0b855d1c8..57d118b41cad 100644
--- a/net/sched/sch_sfq.c
+++ b/n
pie_change() can use rtnl_qdisc_drop() to benefit from
deferred freeing.
pie_reset() is already using qdisc_reset_queue()
Signed-off-by: Eric Dumazet
---
net/sched/sch_pie.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c
index 71ae3
Both htb_reset() and htb_destroy() can use __qdisc_reset_queue()
instead of __skb_queue_purge() to defer skb freeing of internal
queues.
Signed-off-by: Eric Dumazet
---
net/sched/sch_htb.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/net/sched/sch_htb.c b/net/sched/sch
Both hhf_reset() and hhf_change() can use rtnl_kfree_skbs()
Signed-off-by: Eric Dumazet
---
net/sched/sch_hhf.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c
index c51791848a38..c44593b8e65a 100644
--- a/net/sched/sch_hhf.c
+++
rtnl_kfree_skbs() can be used in tfifo_reset()
It would be nice if we could iterate through rb tree instead
of removing one skb at a time, and build a single skb chain.
But this is left for a future patch.
Signed-off-by: Eric Dumazet
---
net/sched/sch_netem.c | 4 +---
1 file changed, 1 inserti
codel_change() can use rtnl_qdisc_drop()
to defer expensive skb freeing after locks are released.
codel_reset() already has support for deferred skb freeing
because it uses qdisc_reset_queue()
Signed-off-by: Eric Dumazet
---
net/sched/sch_codel.c | 2 +-
1 file changed, 1 insertion(+), 1 deleti
Both fq_change() and fq_reset() can use rtnl_kfree_skbs()
Signed-off-by: Eric Dumazet
---
net/sched/sch_fq.c | 19 +--
1 file changed, 13 insertions(+), 6 deletions(-)
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index f49c81e91acd..6eb06674f778 100644
--- a/net/sched/sc
choke_reset() and choke_change() can use rtnl_qdisc_drop()
to defer expensive skb freeing after locks are released.
Signed-off-by: Eric Dumazet
---
net/sched/sch_choke.c | 8
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c
inde
Both fq_codel_change() and fq_codel_reset() can use rtnl_kfree_skbs()
Signed-off-by: Eric Dumazet
---
net/sched/sch_fq_codel.c | 17 +
1 file changed, 9 insertions(+), 8 deletions(-)
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index a302e8ef5498..2dc0a849515
qdisc are changed under RTNL protection and often
while blocking BH and root qdisc spinlock.
When lots of skbs need to be dropped, we free
them under these locks causing TX/RX freezes,
and more generally latency spikes.
This commit adds rtnl_kfree_skbs(), used to queue
skbs for deferred freeing.
qdiscs/classes are changed under RTNL protection and often
while blocking BH and root qdisc spinlock.
When lots of skbs need to be dropped, we free
them under these locks causing TX/RX freezes,
and more generally latency spikes.
I saw spikes of 50+ ms on quite fast hardware...
This patch series
On Mon, 2016-06-13 at 20:12 -0700, Eric Dumazet wrote:
>
> Have you tested this patch ?
Hmm, please ignore this question ;)
On Tue, 2016-06-14 at 02:43 +0100, Quentin Armitage wrote:
> When other settings are changed in the socket it is locked, so
> lock the socket before setting SK_CAN_REUSE.
>
> Signed-off-by: Quentin Armitage
> ---
> net/netfilter/ipvs/ip_vs_sync.c |2 ++
> 1 files changed, 2 insertions(+), 0
On Mon, Jun 13, 2016 at 11:08 PM, wrote:
> From: Wei Yongjun
>
> Fix to return a negative error code from the error handling
> case instead of 0, as done elsewhere in this function.
>
> Signed-off-by: Wei Yongjun
> ---
> net/sctp/protocol.c | 3 ++-
> 1 file changed, 2 insertions(+), 1 deletio
On Mon, Jun 13, 2016 at 5:28 PM, Tom Herbert wrote:
> On Mon, Jun 13, 2016 at 4:12 PM, Alexander Duyck
> wrote:
>> On Mon, Jun 13, 2016 at 3:17 PM, Tom Herbert wrote:
>>> On Mon, Jun 13, 2016 at 2:51 PM, Alexander Duyck
>>> wrote:
On Mon, Jun 13, 2016 at 1:36 PM, Tom Herbert wrote:
>
Hi,
[auto build test ERROR on ipvs-next/master]
[also build test ERROR on v4.7-rc3 next-20160609]
[if your patch is applied to the wrong git tree, please drop us a note to help
improve the system]
url:
https://github.com/0day-ci/linux/commits/Quentin-Armitage/ipvs-Enable-setting-IPv6-multica
Signed-off-by: Shrikrishna Khare
---
drivers/net/vmxnet3/Makefile | 4 ++--
drivers/net/vmxnet3/upt1_defs.h | 4 ++--
drivers/net/vmxnet3/vmxnet3_defs.h| 9 ++---
drivers/net/vmxnet3/vmxnet3_drv.c | 22 +-
drivers/net/vmxnet3/vmxnet3_ethtool.c |
Signed-off-by: Keyong Sun
Signed-off-by: Manoj Tammali
Signed-off-by: Shrikrishna Khare
---
drivers/net/vmxnet3/vmxnet3_defs.h| 33 ++-
drivers/net/vmxnet3/vmxnet3_drv.c | 54
drivers/net/vmxnet3/vmxnet3_ethtool.c | 160 ++
drivers/net/
Receive Data Ring buffer length is configurable via ethtool -G ethX rx-mini
Signed-off-by: Shrikrishna Khare
---
drivers/net/vmxnet3/vmxnet3_defs.h| 14 +++-
drivers/net/vmxnet3/vmxnet3_drv.c | 153 +++---
drivers/net/vmxnet3/vmxnet3_ethtool.c | 48 -
Signed-off-by: Shrikrishna Khare
---
drivers/net/vmxnet3/vmxnet3_drv.c | 7 ++-
drivers/net/vmxnet3/vmxnet3_int.h | 4 ++--
2 files changed, 8 insertions(+), 3 deletions(-)
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c
b/drivers/net/vmxnet3/vmxnet3_drv.c
index d0bcc1d9..c68fe49 100644
---
Signed-off-by: Guolin Yang
Signed-off-by: Shrikrishna Khare
---
drivers/net/vmxnet3/vmxnet3_defs.h | 17 +
1 file changed, 17 insertions(+)
diff --git a/drivers/net/vmxnet3/vmxnet3_defs.h
b/drivers/net/vmxnet3/vmxnet3_defs.h
index 274e145..c3a3164 100644
--- a/drivers/net/vmxne
This series of patches arise from discovering that:
ipvsadm --start-daemon backup --mcast-group IPv6_address ...
would always fail.
The first patch resolves the problem. The second and third patches are
optimizations that were noticed while investigating the original problem.
The fourth patch adds
Add new multicast parameters to log messages when sync daemons start.
Commits ("ipvs: add sync_maxlen parameter for the sync
daemon") and ("ipvs: add more mcast parameters for the
sync daemon") added additional multicast parameters, but didn't add
them to the log messages when the sync daemons s
Move the block testing result < 0 to avoid the test immediately
after setting result = 0
Signed-off-by: Quentin Armitage
---
net/netfilter/ipvs/ip_vs_sync.c |8
1 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_
When other settings are changed in the socket it is locked, so
lock the socket before setting SK_CAN_REUSE.
Signed-off-by: Quentin Armitage
---
net/netfilter/ipvs/ip_vs_sync.c |2 ++
1 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilte
Optimise starting sync daemons by using the result of the first call to
__dev_get_by_name() and pass the result or ifindex to subsequent functions
to avoid them having to call __dev_get_by_name() again.
Signed-off-by: Quentin Armitage
---
net/netfilter/ipvs/ip_vs_sync.c | 66 +-
When using HEAD from
https://git.kernel.org/cgit/utils/kernel/ipvsadm/ipvsadm.git/,
the command:
ipvsadm --start-daemon backup --mcast-interface eth0.60 --mcast-group ff01::1:81
fails with the error message:
Argument list too long
whereas both:
ipvsadm --start-daemon master --mcast-interface eth0
Signed-off-by: Guolin Yang
Signed-off-by: Shrikrishna Khare
---
drivers/net/vmxnet3/vmxnet3_defs.h | 22 +-
1 file changed, 21 insertions(+), 1 deletion(-)
diff --git a/drivers/net/vmxnet3/vmxnet3_defs.h
b/drivers/net/vmxnet3/vmxnet3_defs.h
index 8345e0c..a26a69d 100644
---
Signed-off-by: Sriram Rangarajan
Signed-off-by: Shrikrishna Khare
---
drivers/net/vmxnet3/vmxnet3_defs.h| 12 +++-
drivers/net/vmxnet3/vmxnet3_drv.c | 55 ++-
drivers/net/vmxnet3/vmxnet3_ethtool.c | 9 +++---
drivers/net/vmxnet3/vmxnet3_int.h | 7
This patchset upgrades vmxnet3 to version 3.
Changes in v2:
- Following patch is updated. See that patch for details:
Driver: Vmxnet3: Add support for get_coalesce, set_coalesce ethtool
Changes in v3:
- fix subject line to use vmxnet3: instead of Driver:Vmxnet3
- resubmit when net-next is o
TIPC based clusters are by default set up with full-mesh link
connectivity between all nodes. Those links are expected to provide
a short failure detection time, by default set to 1500 ms. Because
of this, the background load for neighbor monitoring in an N-node
cluster increases with a factor N on
On Mon, Jun 13, 2016 at 4:12 PM, Alexander Duyck
wrote:
> On Mon, Jun 13, 2016 at 3:17 PM, Tom Herbert wrote:
>> On Mon, Jun 13, 2016 at 2:51 PM, Alexander Duyck
>> wrote:
>>> On Mon, Jun 13, 2016 at 1:36 PM, Tom Herbert wrote:
On Mon, Jun 13, 2016 at 1:24 PM, Alexander Duyck
wrote:
1. Default VRF devices to not having a qdisc (IFF_NO_QUEUE). Users
can add one as desired.
2. Disable adding a VLAN to a VRF device.
3. Enable offloads and hardware features similar to other logical
devices (e.g., dummy, veth)
Change provides a significant boost in TCP stream Tx performanc
From: Vidya Sagar Ravipati
This patch series provides following support
a) Reorganized fields based out of SFF-8024 fields i.e. Identifier/
Encoding/Connector types which are common across SFP/SFP+ (SFF-8472)
and QSFP+/QSFP28 (SFF-8436/SFF-8636) modules into sff-common files.
b) Support for
From: Vidya Sagar Ravipati
This patch series provides following support
a) Reorganized fields based out of SFF-8024 fields i.e. Identifier/
Encoding/Connector types which are common across SFP/SFP+ (SFF-8472)
and QSFP+/QSFP28 (SFF-8436/SFF-8636) modules into sff-common files.
a) Support for
From: Vidya Sagar Ravipati
This covers kernel changes upto:
commit 3851112e4737cd52aaeda0ce8d084be9ee128106
Author: Vidya Sagar Ravipati
Date: Sun May 22 23:59:00 2016 -0700
ethtool: add support for 25G/50G/100G speed modes
This patch enhances ethtool link mode bitmap to include
On Mon, Jun 13, 2016 at 3:17 PM, Tom Herbert wrote:
> On Mon, Jun 13, 2016 at 2:51 PM, Alexander Duyck
> wrote:
>> On Mon, Jun 13, 2016 at 1:36 PM, Tom Herbert wrote:
>>> On Mon, Jun 13, 2016 at 1:24 PM, Alexander Duyck
>>> wrote:
On Mon, Jun 13, 2016 at 12:55 PM, Tom Herbert wrote:
>
On Mon, Jun 13, 2016 at 3:08 PM, Jamal Hadi Salim wrote:
> From: Jamal Hadi Salim
>
> This refers to commands to direct action access as follows:
>
> sudo tc actions add action drop index 12
> sudo tc actions add action pipe index 10
>
> And then dumping them like so:
> sudo tc actions ls action
On Mon, Jun 13, 2016 at 1:45 PM, Daniel Metz wrote:
> This patch adjusts Linux RTO calculation to be RFC6298 Standard
> compliant. MinRTO is no longer added to the computed RTO, RTO damping
> and overestimation are decreased.
>
> In RFC 6298 Standard TCP Retransmission Timeout (RTO) calculation th
On 6/13/16 2:47 PM, Hannes Frederic Sowa wrote:
Unfortunately because of bisectability I cannot split this patch. :(
Signed-off-by: Hannes Frederic Sowa
---
drivers/net/bonding/bond_main.c | 3 +--
drivers/net/gtp.c | 3 ++-
drivers/net/ppp/pptp.c | 2 +-
drivers/net/
On Mon, Jun 13, 2016 at 2:51 PM, Alexander Duyck
wrote:
> On Mon, Jun 13, 2016 at 1:36 PM, Tom Herbert wrote:
>> On Mon, Jun 13, 2016 at 1:24 PM, Alexander Duyck
>> wrote:
>>> On Mon, Jun 13, 2016 at 12:55 PM, Tom Herbert wrote:
On Mon, Jun 13, 2016 at 10:47 AM, Alexander Duyck
wrot
From: Jamal Hadi Salim
This refers to commands to direct action access as follows:
sudo tc actions add action drop index 12
sudo tc actions add action pipe index 10
And then dumping them like so:
sudo tc actions ls action gact
iproute2 worked because it depended on absence of TCA_ACT_TAB TLV
a
On 6/13/16 2:47 PM, Hannes Frederic Sowa wrote:
Signed-off-by: Hannes Frederic Sowa
---
include/net/flow.h | 11 ---
include/net/route.h | 8
net/netfilter/ipvs/ip_vs_xmit.c | 9 +++--
net/sctp/protocol.c | 10 --
4 files chang
On 6/13/16 2:47 PM, Hannes Frederic Sowa wrote:
No functional changes.
Signed-off-by: Hannes Frederic Sowa
---
include/net/flow.h | 21 -
include/net/route.h | 33 +++--
net/ipv4/inet_connection_sock.c | 41 ++
The commit 34166093639b ("tuntap: use common code for virtio_net_hdr
and skb GSO conversion") replaced the tun code for header manipulation
with the generic helpers. While doing so, it implictly moved the
skb_partial_csum_set() invocation after eth_type_trans(), which
invalidate the current gso sta
On Mon, Jun 13, 2016 at 2:08 PM, Hannes Frederic Sowa wrote:
> On 13.06.2016 21:47, Alexander Duyck wrote:
>> On Mon, Jun 13, 2016 at 10:57 AM, Hannes Frederic Sowa
>> wrote:
>>> Hi Alex,
>>>
>>> very cool series!
>>>
>>> On 13.06.2016 19:48, Alexander Duyck wrote:
diff --git a/include/linux
On 16-06-13 04:46 PM, Cong Wang wrote:
Cc: Jamal Hadi Salim
Signed-off-by: Cong Wang
Acked-by: Jamal Hadi Salim
cheers,
jamal
On 16-06-13 04:44 PM, Cong Wang wrote:
And avoid calling tcf_hash_check() twice.
Fixes: a57f19d30b2d ("net sched: ipt action fix late binding")
Cc: Jamal Hadi Salim
Signed-off-by: Cong Wang
Good catch.
Acked-by: Jamal Hadi Salim
cheers,
jamal
On 16-06-13 01:47 PM, Cong Wang wrote:
This function is just ->init(), rename it to make it obvious.
Cc: Jamal Hadi Salim
Signed-off-by: Cong Wang
Acked-by: Jamal Hadi Salim
cheers,
jamal
On 16-06-13 01:47 PM, Cong Wang wrote:
These should be gone when we removed CONFIG_NET_CLS_POLICE.
We can not totally remove them since they are exposed
to userspace.
Cc: Jamal Hadi Salim
Signed-off-by: Cong Wang
Acked-by: Jamal Hadi Salim
On 16-06-13 08:21 AM, Daniel Borkmann wrote:
Looks like nft_meta_set_eval() can already do that, but restricted
via pkt_type_ok(), so we can't play bad games with PACKET_LOOPBACK
et al. Wasn't aware of that. Hm, so if you want to make use of this
from tc as well, probably it makes sense to add
On Mon, Jun 13, 2016 at 1:36 PM, Tom Herbert wrote:
> On Mon, Jun 13, 2016 at 1:24 PM, Alexander Duyck
> wrote:
>> On Mon, Jun 13, 2016 at 12:55 PM, Tom Herbert wrote:
>>> On Mon, Jun 13, 2016 at 10:47 AM, Alexander Duyck
>>> wrote:
This patch merges the GENEVE and VXLAN code so that both
On Mon, Jun 13, 2016, at 00:18, David Ahern wrote:
> On 6/11/16 3:10 PM, Hannes Frederic Sowa wrote:
> > @@ -215,6 +216,9 @@ static int fib4_rule_configure(struct fib_rule *rule,
> > struct sk_buff *skb,
> > rule4->dst_len = frh->dst_len;
> > rule4->dstmask = inet_make_mask(rule4->dst_len)
On Mon 2016-06-13 17:10:02, João Paulo Rechi Vita wrote:
> On 13 June 2016 at 17:01, Pavel Machek wrote:
> > On Mon 2016-06-13 15:59:35, João Paulo Rechi Vita wrote:
> >> On 13 June 2016 at 15:00, Pavel Machek wrote:
> >> > Hi!
> >> >
> >> >> > João, that means you should send a patch to add the
On Mon, Jun 13, 2016 at 11:33 AM, Eric Dumazet wrote:
> From: Eric Dumazet
>
> Now prio_init() can return -ENOMEM, it also has to make sure
> any allocated qdiscs are freed, since the caller (qdisc_create()) wont
> call ->destroy() handler for us.
>
> More generally, we want a transactional behav
On Mon, 2016-06-13 at 22:45 +0200, Daniel Metz wrote:
> This patch adjusts Linux RTO calculation to be RFC6298 Standard
> compliant. MinRTO is no longer added to the computed RTO, RTO damping
> and overestimation are decreased.
>
> In RFC 6298 Standard TCP Retransmission Timeout (RTO) calculation
On 13 June 2016 at 17:01, Pavel Machek wrote:
> On Mon 2016-06-13 15:59:35, João Paulo Rechi Vita wrote:
>> On 13 June 2016 at 15:00, Pavel Machek wrote:
>> > Hi!
>> >
>> >> > João, that means you should send a patch to add the ::rfkill suffix.
>> >> >
>> >>
>> >> IMO "airplane" (or maybe "airpla
On 13.06.2016 21:47, Alexander Duyck wrote:
> On Mon, Jun 13, 2016 at 10:57 AM, Hannes Frederic Sowa
> wrote:
>> Hi Alex,
>>
>> very cool series!
>>
>> On 13.06.2016 19:48, Alexander Duyck wrote:
>>> diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
>>> index d101e4d904ba..e959b63
On Mon 2016-06-13 15:59:35, João Paulo Rechi Vita wrote:
> On 13 June 2016 at 15:00, Pavel Machek wrote:
> > Hi!
> >
> >> > João, that means you should send a patch to add the ::rfkill suffix.
> >> >
> >>
> >> IMO "airplane" (or maybe "airplane-mode") is a better suffix, as it
> >> reflects the la
A simple array based FIFO of pointers. Intended for net stack which
commonly has a single consumer/producer.
Signed-off-by: Michael S. Tsirkin
---
include/linux/ptr_ring.h | 264 +++
1 file changed, 264 insertions(+)
create mode 100644 include/linux/
A simple array based FIFO of pointers. Intended for net stack so uses
skbs for type safety. Implemented as a set of wrappers around ptr_ring.
Signed-off-by: Michael S. Tsirkin
---
include/linux/skb_array.h | 144 ++
1 file changed, 144 insertions(+)
Add ringtest based unit test for ptr ring.
Signed-off-by: Michael S. Tsirkin
---
tools/virtio/ringtest/ptr_ring.c | 192 +++
tools/virtio/ringtest/Makefile | 5 +-
2 files changed, 196 insertions(+), 1 deletion(-)
create mode 100644 tools/virtio/ringtest/
This is in response to the proposal by Jason to make tun
rx packet queue lockless using a circular buffer.
My testing seems to show that at least for the common usecase
in networking, which isn't lockless, circular buffer
with indices does not perform that well, because
each index access causes a c
This adds ring resize support. Seems to be necessary as
users such as tun allow userspace control over queue size.
If resize is used, this costs us ability to peek at queue without
consumer lock - should not be a big deal as peek and consumer are
usually run on the same CPU.
If ring is made bigge
Update skb_array after ptr_ring API changes.
Signed-off-by: Michael S. Tsirkin
---
include/linux/skb_array.h | 33 +
1 file changed, 29 insertions(+), 4 deletions(-)
diff --git a/include/linux/skb_array.h b/include/linux/skb_array.h
index c4c0902..678bfbf 100644
Unfortunately because of bisectability I cannot split this patch. :(
Signed-off-by: Hannes Frederic Sowa
---
drivers/net/bonding/bond_main.c | 3 +--
drivers/net/gtp.c | 3 ++-
drivers/net/ppp/pptp.c | 2 +-
drivers/net/vrf.c | 7 ---
include/net/ip.h
Probably out of laziness we encoded the RTO_ONLINK flag into the
lowest ToS bit to easier pass it around in the flowi structure (we
need one less argument to do so).
This series cleans it up and uses flowi4_scope correctly from nearly
the top-level, thus removing the need to encode the RTO_ONLINK
Signed-off-by: Hannes Frederic Sowa
---
include/net/flow.h | 11 ---
include/net/route.h | 8
net/netfilter/ipvs/ip_vs_xmit.c | 9 +++--
net/sctp/protocol.c | 10 --
4 files changed, 15 insertions(+), 23 deletions(-)
diff --git
No functional changes.
Signed-off-by: Hannes Frederic Sowa
---
include/net/flow.h | 21 -
include/net/route.h | 33 +++--
net/ipv4/inet_connection_sock.c | 41 +
net/ipv4/ip_output.c
Cc: Jamal Hadi Salim
Signed-off-by: Cong Wang
---
include/net/act_api.h | 4 ++--
net/sched/act_api.c | 8
net/sched/act_ife.c | 3 ++-
net/sched/act_ipt.c | 3 ++-
net/sched/act_mirred.c | 3 ++-
net/sched/act_simple.c | 3 ++-
net/sched/act_skbedit.c | 3 ++-
net/sched
This patch adjusts Linux RTO calculation to be RFC6298 Standard
compliant. MinRTO is no longer added to the computed RTO, RTO damping
and overestimation are decreased.
In RFC 6298 Standard TCP Retransmission Timeout (RTO) calculation the
calculated RTO is rounded up to the Minimum RTO (MinRTO), if
Allow drivers to pass flow arg to functions where the arg is not const
and allow the driver to make updates as needed (eg., setting oif).
Signed-off-by: David Ahern
---
drivers/net/vrf.c| 2 +-
include/net/l3mdev.h | 6 +++---
net/l3mdev/l3mdev.c | 2 +-
3 files changed, 5 insertions(+), 5
IPv6 multicast and link-local addresses require special handling by the
VRF driver. Rather than using the VRF device index and full FIB lookups,
packets to/from these addresses should use direct FIB lookups based on
the VRF device table.
Multicast routes do not make sense for the L3 master device
L3 master devices are virtual devices similar to the loopback
device. Link local and multicast routes for these devices do
not make sense. The ipv6 addrconf code already skips adding a
linklocal address; do the same for the mcast route.
Signed-off-by: David Ahern
---
net/ipv6/addrconf.c | 2 +-
And avoid calling tcf_hash_check() twice.
Fixes: a57f19d30b2d ("net sched: ipt action fix late binding")
Cc: Jamal Hadi Salim
Signed-off-by: Cong Wang
---
net/sched/act_ipt.c | 7 +--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
ind
IPv6 multicast and link-local addresses require special handling by the
VRF driver:
1. Rather than using the VRF device index and full FIB lookups,
packets to/from these addresses should use direct FIB lookups based on
the VRF device table.
2. fail sends/receives on a VRF device to/from a mu
On Mon, Jun 13, 2016 at 11:46:13AM +0300, Netanel Belgazal wrote:
> This is a driver for the forthcoming ENA family of networking devices.
Reviewed-by: Matt Wilson
> Signed-off-by: Netanel Belgazal
> ---
> Documentation/networking/00-INDEX |2 +
> Documentation/networking/e
On Mon, Jun 13, 2016 at 1:24 PM, Alexander Duyck
wrote:
> On Mon, Jun 13, 2016 at 12:55 PM, Tom Herbert wrote:
>> On Mon, Jun 13, 2016 at 10:47 AM, Alexander Duyck
>> wrote:
>>> This patch merges the GENEVE and VXLAN code so that both functions pass
>>> through a shared code path. This way we
On 13 June 2016 at 21:30, Arend van Spriel wrote:
> On 09-06-16 21:16, Arend van Spriel wrote:
>> On 26-05-16 01:44, Rafał Miłecki wrote:
>>> The old implementation was overcomplicated and slightly bugged in some
>>> corner cases.
>>>
>
> [...]
>
>>> New code is simpler, placed in file where it's
On Mon, Jun 13, 2016 at 12:55 PM, Tom Herbert wrote:
> On Mon, Jun 13, 2016 at 10:47 AM, Alexander Duyck wrote:
>> This patch merges the GENEVE and VXLAN code so that both functions pass
>> through a shared code path. This way we can start the effort of using a
>> single function on the network
Hi,
[auto build test ERROR on net/master]
[also build test ERROR on v4.7-rc3 next-20160609]
[if your patch is applied to the wrong git tree, please drop us a note to help
improve the system]
url:
https://github.com/0day-ci/linux/commits/Alexander-Duyck/Future-proof-tunnel-offload-handlers/20
On 13 June 2016 at 15:00, Pavel Machek wrote:
> Hi!
>
>> > João, that means you should send a patch to add the ::rfkill suffix.
>> >
>>
>> IMO "airplane" (or maybe "airplane-mode") is a better suffix, as it
>> reflects the label on the machine's chassis. I'll name it
>> "asus-wireless::airplane" a
On 6/13/16 12:40 PM, Mike Rapoport wrote:
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 9af0a98..9f8be96 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -482,10 +482,6 @@ static void receive_buf(struct virtnet_info *vi, struct
receive_queue *rq,
On Mon, Jun 13, 2016 at 10:47 AM, Alexander Duyck wrote:
> This patch merges the GENEVE and VXLAN code so that both functions pass
> through a shared code path. This way we can start the effort of using a
> single function on the network device drivers to handle both of these
> tunnel offload typ
On Mon, Jun 13, 2016 at 01:47:13PM +0200, Richard Cochran wrote:
> 3. ALSA support for tunable AD/DA clocks. The rate of the Listener's
>DA clock must match that of the Talker and the other Listeners.
>Either you adjust it in HW using a VCO or similar, or you do
>adaptive sample rate c
Hi,
[auto build test ERROR on net/master]
[also build test ERROR on v4.7-rc3 next-20160609]
[if your patch is applied to the wrong git tree, please drop us a note to help
improve the system]
url:
https://github.com/0day-ci/linux/commits/Alexander-Duyck/Future-proof-tunnel-offload-handlers/20
1 - 100 of 245 matches
Mail list logo
