Modern Intel hardware adds an Always Running Timer (ART) that allows the
network and audio device clocks to precisely cross timestamp the device
clock with the system clock. This allows a precise correlation of the
device time and system time.
This patchset adds interfaces to the timekeeping code
In the current timekeeping code there isn't any interface to
atomically capture the current relationship between the system counter
and system time. ktime_get_snapshot() returns this triple (counter,
monotonic raw, realtime) in the system_time_snapshot struct.
Signed-off-by: Christopher S. Hall
[
The timekeeping code does not currently provide a way to translate
externally provided clocksource cycles to system time. The cycle count
is always provided by the result clocksource read() method internal to
the timekeeping code. The added function timekeeping_cycles_to_ns()
calculated a nanosecon
Another representative use case of time sync and the correlated
clocksource (in addition to PTP noted above) is PTP synchronized
audio.
In a streaming application, as an example, samples will be sent and/or
received by multiple devices with a presentation time that is in terms
of the PTP master cl
ACKNOWLEDGMENT: cross timestamp code was developed by Thomas Gleixner
. It has changed considerably and any mistakes are
mine.
The precision with which events on multiple networked systems can be
synchronized using, as an example, PTP (IEEE 1588, 802.1AS) is limited
by the precision of the cross t
Currently, network /system cross-timestamping is performed in the
PTP_SYS_OFFSET ioctl. The PTP clock driver reads gettimeofday() and
the gettime64() callback provided by the driver. The cross-timestamp
is best effort where the latency between the capture of system time
(getnstimeofday()) and the d
On modern Intel systems TSC is derived from the new Always Running Timer
(ART). ART can be captured simultaneous to the capture of
audio and network device clocks, allowing a correlation between timebases
to be constructed. Upon capture, the driver converts the captured ART
value to the appropriate
Modern Intel systems supports cross timestamping of the network device
clock and Always Running Timer (ART) in hardware. This allows the
device time and system time to be precisely correlated. The timestamp
pair is returned through e1000e_phc_get_syncdevicetime() used by
get_system_device_crosstst
The code in ktime_get_snapshot() is a superset of the code in
ktime_get_raw_and_real() code. Further, ktime_get_raw_and_real() is
called only by the PPS code, pps_get_ts(). Consolidate the
pps_get_ts() code into a single function calling ktime_get_snapshot()
and eliminate ktime_get_raw_and_real().
On Tue, 2016-02-09 at 16:29 -0800, David Decotigny wrote:
> From: David Decotigny
>
> This patch defines a new ETHTOOL_GSETTINGS/SSETTINGS API, handled by
> the new get_ksettings/set_ksettings callbacks. This API provides
> support for most legacy ethtool_cmd fields, adds support for larger
> lin
On Tue, 2016-02-09 at 16:29 -0800, David Decotigny wrote:
> From: David Decotigny
>
> This is mainly testing bitmap construction and conversion to/from u32[]
> for now.
>
> Tested:
> qemu i386, x86_64, ppc, ppc64 BE and LE, ARM.
>
> Signed-off-by: David Decotigny
[...]
> diff --git a/tools/t
Signed-off-by: Iyappan Subramanian
Signed-off-by: Khuong Dinh
Signed-off-by: Tanmay Inamdar
Tested-by: Toan Le
---
drivers/net/ethernet/apm/xgene/Makefile | 3 +-
drivers/net/ethernet/apm/xgene/xgene_enet_cle.c | 357 +++
drivers/net/ethernet/apm/xgene/xgene_ene
Signed-off-by: Iyappan Subramanian
Signed-off-by: Khuong Dinh
Signed-off-by: Tanmay Inamdar
Tested-by: Toan Le
---
drivers/net/ethernet/apm/xgene/xgene_enet_cle.c | 11 +-
drivers/net/ethernet/apm/xgene/xgene_enet_hw.c| 12 +
drivers/net/ethernet/apm/xgene/xgene_enet_hw.h| 5 +
d
Signed-off-by: Iyappan Subramanian
Signed-off-by: Khuong Dinh
Signed-off-by: Tanmay Inamdar
Tested-by: Toan Le
---
arch/arm64/boot/dts/apm/apm-shadowcat.dtsi | 8 +++-
arch/arm64/boot/dts/apm/apm-storm.dtsi | 8 +++-
2 files changed, 14 insertions(+), 2 deletions(-)
diff --git a/a
Signed-off-by: Iyappan Subramanian
Signed-off-by: Khuong Dinh
Signed-off-by: Tanmay Inamdar
Tested-by: Toan Le
---
drivers/net/ethernet/apm/xgene/xgene_enet_cle.c | 386 +++-
drivers/net/ethernet/apm/xgene/xgene_enet_cle.h | 41 +++
2 files changed, 422 insertions(+), 5 de
This patch set enables,
(i) Classifier engine that is used for parsing
through the packet and extracting a search string that is then used
to search a database to find associative data.
(ii) Receive Side Scaling (RSS) that does dynamic load
balancing of the CPUs by controlling the number of messa
On Wed, 23 Dec 2015 20:18:16 -0500
"David Rivshin (Allworx)" wrote:
> On Thu, 24 Dec 2015 00:34:49 +0100
> Nicolas Chauvet wrote:
>
> > 2015-12-23 22:54 GMT+01:00 David Rivshin (Allworx) <
> > drivshin.allw...@gmail.com>:
> >
> > > On Wed, 23 Dec 2015 22:20:58 +0100
> > > Nicolas Chauvet
On Tue, 2016-02-09 at 16:29 -0800, David Decotigny wrote:
> From: David Decotigny
>
> Aimed at transferring bitmaps to/from user-space in a 32/64-bit agnostic
> way.
>
> Tested:
> unit tests (next patch) on qemu i386, x86_64, ppc, ppc64 BE and LE,
> ARM.
>
> Signed-off-by: David Decotigny
From: David Rivshin
The cpsw-phy-sel driver supports only MII, RMII, and RGMII PHY modes,
and silently handled any other values as if MII was specified. In a
case where the PHY mode was incorrectly specified, or a bug elsewhere,
there would be no indication of a problem. If MII was the correct mo
On Fri, 2016-02-05 at 22:30 +, Rainer Weikusat wrote:
> The present unix_stream_read_generic contains various code sequences of
> the form
>
> err = -EDISASTER;
> if ()
> goto out;
[...]
I wish people would stop writing code like this. At one time it may
have been a useful micro-optimi
> From: Intel-wired-lan [intel-wired-lan-boun...@lists.osuosl.org] on behalf of
> Stefan Assmann [sassm...@kpanic.de]
> Sent: Wednesday, February 03, 2016 12:20 AM
> To: intel-wired-...@lists.osuosl.org
> Cc: netdev@vger.kernel.org; da...@davemloft.net; sassm...@kpanic.de
> Subject: [Intel-wired-
Thanks Florian,
Lots of good comments here. I'm working on fixes and I'll respond when I get
through it all.
Bryan
-Original Message-
From: Florian Fainelli [mailto:f.faine...@gmail.com]
Sent: Thursday, February 11, 2016 9:18 PM
To: Bryan Whitehead - C21958; da...@davemloft.net
Cc: net
> From: Intel-wired-lan [intel-wired-lan-boun...@lists.osuosl.org] on behalf of
> Stefan Assmann [sassm...@kpanic.de]
> Sent: Wednesday, February 03, 2016 12:20 AM
> To: intel-wired-...@lists.osuosl.org
> Cc: netdev@vger.kernel.org; da...@davemloft.net; sassm...@kpanic.de
> Subject: [Intel-wired-l
> From: Intel-wired-lan [intel-wired-lan-boun...@lists.osuosl.org] on behalf of
> Stefan Assmann [sassm...@kpanic.de]
> Sent: Wednesday, February 03, 2016 12:20 AM
> To: intel-wired-...@lists.osuosl.org
> Cc: netdev@vger.kernel.org; da...@davemloft.net; sassm...@kpanic.de
> Subject: [Intel-wired-l
On Wed, Feb 10, 2016 at 7:33 AM, Mahesh Bandewar wrote:
> From: Mahesh Bandewar
>
> Scrub skb before hitting the iptable hooks to ensure packets hit
> these hooks.
>
> Signed-off-by: Mahesh Bandewar
> ---
> v1: initial patch
> v2: resend
>
> drivers/net/ipvlan/ipvlan_core.c | 4 ++--
> 1 file c
When a port leaves a bridge, the bridge layer now restores its STP state
to Forwarding, if the device belong to a switchdev user.
Thus remove this redundant action from the DSA layer.
Signed-off-by: Vivien Didelot
---
net/dsa/slave.c | 17 -
1 file changed, 17 deletions(-)
diff
When a port leaves a bridge, the bridge layer sets its STP state to Disabled.
But switchdev users seem to need to restore its state to Forwarding to keep the
communication with the CPU port functional (see DSA and Rocker for instance).
br_set_state() tries to set the switchdev port state, if corr
Every call to br_set_state is followed by a call to br_log_state.
Directly call it within br_set_state instead.
Signed-off-by: Vivien Didelot
---
net/bridge/br_stp.c | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c
index b3cca12..
When a port leaves a bridge, the bridge layer puts its STP state to
Disabled. If the port is part of an hardware switch, the mode needs to
be set to Forwarding in order to restore communication with the CPU.
Call br_set_state() in del_nbp(), which only affects switchdev users.
Signed-off-by: Vivi
This fixes a regression in the bridge ageing time caused by:
commit c62987bbd8a1 ("bridge: push bridge setting ageing_time down to
switchdev")
There are users of Linux bridge which use the feature that if ageing time
is set to 0 it causes entries to never expire.
This feature is even listed on t
Hi Florian,
On Fri, Feb 12, 2016 at 10:56:04AM -0800, Florian Fainelli wrote:
> On 12/02/16 10:01, Clemens Gruber wrote:
> > Commit 113c74d83eef ("net: phy: turn carrier off on phy attach") breaks
> > the eth0 link coming up on all my i.MX6Q boards with a Marvell 88E1510.
> > If I then do a ifconf
Ben Hutchings writes:
> On Fri, 2016-02-12 at 20:17 +, Rainer Weikusat wrote:
[...]
I don't think this should apply when
receiving and sending sockets are identical. But that's just my
opinion. The other option would be to avoid the unix_state_double_lock
for sk == other.
John Valko wrote:
>Hi all,
>
>I have observed the following on CentOS 6 using the
>2.6.32-573.8.1.el6.x86_64 kernel as well as Ubuntu 15.10 with
>4.2.0-25-generic.. I have not yet tried with a vanilla kernel but with the
>large time/distro gap it didn't seem likely to be caused by distro
>changes
On Fri, 2016-02-12 at 20:17 +, Rainer Weikusat wrote:
> Ben Hutchings writes:
> > On Fri, 2016-02-12 at 13:25 +, Rainer Weikusat wrote:
> > > Philipp Hahn writes:
> > > > Hello Rainer,
> > > >
> > > > Am 11.02.2016 um 20:37 schrieb Rainer Weikusat:
> > > > > The unix_dgram_sendmsg routin
Ben Hutchings writes:
> On Fri, 2016-02-12 at 13:25 +, Rainer Weikusat wrote:
>> Philipp Hahn writes:
>> > Hello Rainer,
>> >
>> > Am 11.02.2016 um 20:37 schrieb Rainer Weikusat:
>> > > The unix_dgram_sendmsg routine use the following test
>> > >
>> > > if (unlikely(unix_peer(other) != sk &
On Fri, Feb 12, 2016 at 12:32:06PM -0600, Josh Poimboeuf wrote:
> What I actually see in the listing is:
>
> decl__percpu_prefix:__preempt_count
> je 1f:
>
> 1:
> call___preempt_schedule
>
> So it puts the "call ___preempt_schedule" in the slow path.
Ah
On Fri, 2016-02-12 at 13:25 +, Rainer Weikusat wrote:
> Philipp Hahn writes:
>
> > Hello Rainer,
> >
> > Am 11.02.2016 um 20:37 schrieb Rainer Weikusat:
> > > The unix_dgram_sendmsg routine use the following test
> > >
> > > if (unlikely(unix_peer(other) != sk && unix_recvq_full(other))) {
On Fri, Feb 12, 2016 at 9:24 AM, Fabio Estevam wrote:
> On Fri, Feb 12, 2016 at 1:20 PM, Rob Herring wrote:
>
>> This is what the gpio flags are for. Why can't you use that?
>
> This has already been discussed in v1:
> https://lkml.org/lkml/2016/2/8/867
Thanks. That's fine, but that detail shoul
If an skb was not MPLS initially then it may be GSO and in that case if it
became MPLS then GSO can't be performed because both MPLS and tunnels make
use of the inner_protocol field of struct skbuff in order to allow GSO to
be performed in the inner packet.
On the other hand if an skb was MPLS ini
Lino,
Regarding "a matching smp_rmb() in the irq handler"
There is a smp_wmb() in the irq handler, since in both cases we are forcing a
write operation on software_irq_signal.
I suppose using atomic operations on software_irq_signal would also work, but
this driver was based on
drivers/net/eth
On 12/02/16 10:01, Clemens Gruber wrote:
> Commit 113c74d83eef ("net: phy: turn carrier off on phy attach") breaks
> the eth0 link coming up on all my i.MX6Q boards with a Marvell 88E1510.
> If I then do a ifconfig eth0 down/up cycle I first get a MDIO read
> timeout but then the link becomes ready
On Fri, Feb 12, 2016 at 12:32:06PM -0600, Josh Poimboeuf wrote:
> On Fri, Feb 12, 2016 at 06:10:37PM +0100, Peter Zijlstra wrote:
> > On Fri, Feb 12, 2016 at 08:45:43AM -0600, Josh Poimboeuf wrote:
> > > On Fri, Feb 12, 2016 at 11:36:24AM +0100, Jiri Slaby wrote:
> > >
> > > This seems like a real
On Fri, Feb 12, 2016 at 06:10:37PM +0100, Peter Zijlstra wrote:
> On Fri, Feb 12, 2016 at 08:45:43AM -0600, Josh Poimboeuf wrote:
> > On Fri, Feb 12, 2016 at 11:36:24AM +0100, Jiri Slaby wrote:
> >
> > This seems like a real frame pointer bug caused by the following line in
> > arch/x86/include/as
Commit 113c74d83eef ("net: phy: turn carrier off on phy attach") breaks
the eth0 link coming up on all my i.MX6Q boards with a Marvell 88E1510.
If I then do a ifconfig eth0 down/up cycle I first get a MDIO read
timeout but then the link becomes ready and everything is back to
normal.
Without this s
Hi Marcin,
On mar., janv. 12 2016, Marcin Wojtas wrote:
> Hi Gregory,
>
> I have two remarks to my own code. Please let me know before patch v2,
> I will provide you with corrected version (I already did it locally).
I resumled my work on the subject yestaerdy, and I just remebered this
email
> At this point my plan is to just get a basic Ethernet controller
> driver submitted, and later work on switch features.
They are not really separable.
The linux way of dealing with switches is to model each port as a net
device. So you should have a lan0 device and a lan1 device for this
two p
This patchset simplifies the DSA layer.
A switch may support multiple bridges with the same hardware VLAN. Thus a check
such as dsa_bridge_check_vlan_range must be moved from the DSA layer to the
concerned driver.
The first purpose of this patchset is to help moving this check to the
mv88e6xxx dr
Add a per-port mv88e6xxx_priv_port structure to store per-port related
data, instead of adding several arrays of DSA_MAX_PORTS elements in the
mv88e6xxx_priv_state structure.
It currently only contains the port STP state.
Signed-off-by: Vivien Didelot
---
drivers/net/dsa/mv88e6xxx.c | 4 ++--
d
Some DSA drivers may or may not support multiple software bridges on top
of an hardware switch.
It is more convenient for them to access the bridge's net_device for
finer configuration.
Removing the need to craft and access a bitmask also simplifies the
code.
This patch changes the signature of
The DSA drivers now have access to the VLAN prepare phase and the bridge
net_device. It is easier to check for overlapping bridges from within
the driver. Thus add such check in mv88e6xxx_port_vlan_prepare.
Signed-off-by: Vivien Didelot
---
drivers/net/dsa/mv88e6xxx.c | 64 ++
DSA drivers may support multiple bridge groups with the same hardware
VLAN. The mv88e6xxx driver which cannot yet, already has its own check
for overlapping bridges. Thus remove the check from the DSA layer.
Signed-off-by: Vivien Didelot
---
net/dsa/slave.c | 50 -
On Fri, Feb 12, 2016 at 08:45:43AM -0600, Josh Poimboeuf wrote:
> On Fri, Feb 12, 2016 at 11:36:24AM +0100, Jiri Slaby wrote:
>
> This seems like a real frame pointer bug caused by the following line in
> arch/x86/include/asm/preempt.h:
>
> # define __preempt_schedule() asm ("call ___preempt_sc
On Fri, Feb 12, 2016 at 04:51:49PM +, bryan.whiteh...@microchip.com wrote:
> Hi Andrew,
>
> Sorry I still did not make this clear. And I'm not sure I understand your
> question so I'll try to explain again, but please give me feedback if it's
> still not clear.
>
> Also you can reference Fi
> -Original Message-
> From: David Miller [mailto:da...@davemloft.net]
> Sent: 12 February 2016 16:42
> To: Paul Durrant
> Cc: netdev@vger.kernel.org; xen-de...@lists.xenproject.org
> Subject: Re: [PATCH net-next v1 0/8] xen-netback: support toeplitz hashing
>
> From: Paul Durrant
> Date:
Florian,
I'm not familiar with the DSA subsystem. Can you refer me to documents about it?
Andrew,
I'm also not familiar with switchdev, or which is better in this case. Can you
refer me to documents about it?
At this point my plan is to just get a basic Ethernet controller driver
submitted, and
Hi Andrew,
Sorry I still did not make this clear. And I'm not sure I understand your
question so I'll try to explain again, but please give me feedback if it's
still not clear.
Also you can reference Figure 2-1 for an Internal Block Diagram on page 9 of
http://ww1.microchip.com/downloads/en/Dev
From: Corcodel Marian
Date: Fri, 12 Feb 2016 15:40:07 +0200
> How is status with this patch-is accepted or not?
> I'm interresed by this patch on order to send another patches wich
> depend this.
The patch is rejected. It will not be looked at further. It is dead.
And you can submit this patc
Hi,
I receive tons of these csum failure warnings. The patch mentioned here:
https://patchwork.ozlabs.org/patch/512005/
seems to work. Will something like that be integrated upstream?
Sebastian
From: Paul Durrant
Date: Fri, 12 Feb 2016 11:07:50 +
> Windows *requires* use of Teoplitz so your position completely rules
> out being able to support receive side scaling in Windows PV
> frontends on Linux kernel backends, not only for Xen but for any
> other hypervisor, which I think is to
Hi,
We have Intel 80003ES2LAN nics on SGI Altix XE310 servers (SuperMicro
Baseboard, with product name X7DGT). On those machines, one of the NIC
port is bridged internally with the BMC.
It seems that during the e1000e driver initialization (at boot time),
the NIC is reset, which causes the BMC to
Hello,
On Fri, Feb 12, 2016 at 01:10:18AM +0100, Alban Crequy wrote:
> Is there any plans to implement a similar cgroup2 path match in a
> cgroup classifier in tc?
That'd be great. I wanted to but couldn't figure out the heads and
tails after staring at the code for half an hour.
> I wonder if
Thomas reports:
T: Bus=01 Lev=01 Prnt=01 Port=03 Cnt=01 Dev#= 4 Spd=480 MxCh= 0
D: Ver= 2.00 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs= 1
P: Vendor=05c6 ProdID=6001 Rev=00.00
S: Manufacturer=USB Modem
S: Product=USB Modem
S: SerialNumber=1234567890ABCDEF
C: #Ifs= 5 Cfg#= 1 Atr=e0 MxPwr=5
On Fri, Feb 12, 2016 at 1:20 PM, Rob Herring wrote:
> This is what the gpio flags are for. Why can't you use that?
This has already been discussed in v1:
https://lkml.org/lkml/2016/2/8/867
On Tue, Feb 09, 2016 at 09:01:12PM +0100, Bernhard Walle wrote:
> We need that for a custom hardware that needs the reverse reset
> sequence.
>
> Signed-off-by: Bernhard Walle
> ---
> Changes compared to v1:
> - Add documentation to 'phy-reset-gpios' that flags are ignored
>as suggested by A
On Tue, Feb 09, 2016 at 12:07:16PM -0200, Sergio Prado wrote:
> Tested on Acqua A5 SoM (http://www.acmesystems.it/acqua).
>
> Signed-off-by: Sergio Prado
> ---
> Documentation/devicetree/bindings/net/macb.txt | 2 +
> drivers/net/ethernet/cadence/macb.c| 67
> ++
When using ethtool to set the speed for the device, verify that the
specified speed is valid within the active speedset.
Signed-off-by: Tom Lendacky
---
drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c | 16 ++--
1 file changed, 14 insertions(+), 2 deletions(-)
diff --git a/drivers/ne
Hi David,
I will fix it in next patch version.
I just find a corruption issue in stmmac driver, I will also fix it in
next version.
Best regards
Alex
2016-02-09 10:52 GMT+01:00 David Miller :
> From: Alexandre TORGUE
> Date: Wed, 3 Feb 2016 15:54:31 +0100
>
>> STM32F429 Chip embeds a Synopsys
Check to be sure that the Rx queue fifos are empty before stopping the
Rx DMA channels.
Signed-off-by: Tom Lendacky
---
drivers/net/ethernet/amd/xgbe/xgbe-common.h | 10 ++---
drivers/net/ethernet/amd/xgbe/xgbe-dev.c| 30 +++
2 files changed, 37 insertions(+),
This patch series try to unify the dst cache implementations currently
present in the kernel, namely in ip_tunnel.c and ip6_tunnel.c, introducing a
new generic implementation, replacing the existing ones, and then using
the new implementation in other tunnel devices which currently lack it.
The ne
Currently the netdev traffic class setup is only performed when invoked
through the ndo_setup_tc interface. However, the same setup should be
performed when the dcbnl interface (ieee_setets) is invoked. Rework the
netdev traffic class setup to be invokable through either interface and
also provide
Currently the auto-negotiation interrupt handling disables the irq
instead of masking off the interrupts. This was done because the phy
library was originally used to read and write the PCS registers, which
could not be performed in interrupt context. Now that the phy library is
no longer used to r
Currently the PFC flow control is enabled on all traffic classes if
one or more traffic classes request it. The PFC enable setting of the
traffic class should be used to determine whether to enable or disable
flow control for the traffic class.
Signed-off-by: Tom Lendacky
---
drivers/net/etherne
The driver is checking the pfc_en field of the ieee_pfc structure to
determine whether to associate a priority with a traffic class. This is
incorrect since the pfc_en field is for determining if PFC is enabled
for a traffic class.
The association of priority to traffic class does not depend on wh
Change from calling __napi_schedule to __napi_schedule_irqoff when running
in interrupt context or when called by netpoll with interrupts already
disabled. The Tx timer function will continue to use __napi_schedule.
Signed-off-by: Tom Lendacky
---
drivers/net/ethernet/amd/xgbe/xgbe-drv.c |4
Change from using napi_complete to napi_complete_done to allow for the
use of gro_flush_timeout in tuning network processing.
Signed-off-by: Tom Lendacky
---
drivers/net/ethernet/amd/xgbe/xgbe-drv.c |8
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethern
When the hardware is placed in promiscuous mode it will still perform
VLAN filtering and therefore may not pass all packets to the driver.
Disable all VLAN filtering when entering promiscuous mode and restore
VLAN filtering upon exit from promiscuous mode. In order to avoid adding
forward declarat
The following updates and fixes are included in this driver update series:
- Disable VLAN filtering in promiscuous mode
- Change from using napi_complete to napi_complete_done
- Use __napi_schedule_irqoff when running in interrupt context
- Verify ethtool speed setting is valid for the selected sp
On Fri, Feb 12, 2016 at 11:36:24AM +0100, Jiri Slaby wrote:
> On 01/21/2016, 11:49 PM, Josh Poimboeuf wrote:
> > This is v16 of the compile-time stack metadata validation patch set,
> > along with proposed fixes for most of the warnings it found. It's based
> > on the tip/master branch.
>
> Hi,
>
use generic dst implementation for both plain geneve devices and
lwtunnels.
In case of UDP traffic with datagram length below MTU this give
about 2% performance increase for plain geneve tunnel over ipv4,
about 65% performance increase for ipv6 tunnel.
Signed-off-by: Paolo Abeni
Suggested-and-Ac
In case of UDP traffic with datagram length
below MTU this give about 3% performance increase
when tunneling over ipv4 and about 70% when
tunneling over ipv6.
Signed-off-by: Paolo Abeni
Suggested-and-acked-by: Hannes Frederic Sowa
---
v2: move the dst_cache usage into the vxlan lookup functions
The current ip_tunnel cache implementation is prone to a race
that will cause the wrong dst to be cached on cuncurrent dst cache
miss and ip tunnel update via netlink.
Replacing with the generic implementation fix the issue.
Signed-off-by: Paolo Abeni
Suggested-and-acked-by: Hannes Frederic Sowa
In case of UDP traffic with datagram length
below MTU this give about 2% performance increase
when tunneling over ipv4 and about 60% when tunneling
over ipv6
Signed-off-by: Paolo Abeni
Suggested-and-acked-by: Hannes Frederic Sowa
---
v2: move the dst_cache inside the dst_metadata, so that it's
In case of UDP traffic with datagram length below MTU this
gives about 4% performance increase
Signed-off-by: Paolo Abeni
Suggested-and-Acked-by: Hannes Frederic Sowa
---
v2: codying style cleanup
---
net/ipv4/ip_gre.c | 13 ++---
1 file changed, 10 insertions(+), 3 deletions(-)
diff
This patch add a generic, lockless dst cache implementation.
The need for lock is avoided updating the dst cache fields
only in per cpu scope, and requiring that the cache manipulation
functions are invoked with the local bh disabled.
The refresh_ts and reset_ts fields are used to ensure the cache
This also fix a potential race into the existing tunnel code, which
could lead to the wrong dst to be permanenty cached:
CPU1: CPU2:
dst = ip6_route_output(...)
dst_cache_rese
Hi Dave,
here's first pull request for 4.6. We have a new kconfig option
CONFIG_IWLWIFI_PCIE_RTPM for iwlwifi runtime power management. wl12xxx
got device tree support for the spi bus and added a bindings document
for it. More info in the tag below.
Please let me know if you have any problems.
K
Hi Alexandre,
[auto build test WARNING on net/master]
[also build test WARNING on v4.5-rc3 next-20160212]
[if your patch is applied to the wrong git tree, please drop us a note to help
improving the system]
url:
https://github.com/0day-ci/linux/commits/Alexandre-TORGUE/Add-Ethernet-support
On Fri, Feb 12, 2016 at 9:53 AM, Claudio Scordino
wrote:
> Hi all.
>
> Suppose I have an application that needs to send the very same data to
> several sockets already connected. In this case, the application has
> to call the sendto() syscall several times:
>
> for(...)
>sen
netns_map_add() does a malloc of (sizeof (struct nsid_cache) +
strlen(name)) and then proceed with strcpy() of name into the
zero-length member at the end of the nsid_cache structure. The
nul-terminator is written outside of the allocated memory and may
overwrite the allocator's internal structure
On Thu, 2016-02-11 at 08:27 +0200, Corcodel Marian wrote:
> On probe stage what carrier to stop and rest two situation
> netif_carrier_* is slow and disturbing autonegociation process.
>
> Signed-off-by: Corcodel Marian
> ---
> drivers/net/ethernet/realtek/r8169.c | 3 ---
> 1 file changed,
Joseph Salisbury writes:
> On 02/05/2016 05:30 PM, Rainer Weikusat wrote:
>> The present unix_stream_read_generic contains various code sequences of
>> the form
>>
>> err = -EDISASTER;
>> if ()
>> goto out;
[...]
>> Change it such that err is only set if an error condition was detected.
[.
Philipp Hahn writes:
> Hello Rainer,
>
> Am 11.02.2016 um 20:37 schrieb Rainer Weikusat:
>> The unix_dgram_sendmsg routine use the following test
>>
>> if (unlikely(unix_peer(other) != sk && unix_recvq_full(other))) {
[...]
>> This isn't correct as the> specified address could have been bound
On 02/12/2016 11:18 AM, Sudip Mukherjee wrote:
The builds of allmodconfig of s390, m68k, tilegx, tilepro is failing
with the error:
drivers/net/phy/spi_ks8995.c:477:3: error: implicit declaration of function
'gpiod_set_value'
drivers/net/phy/spi_ks8995.c:477:19: error: implicit declaration o
In some configurations, this function uses more than the warning limit
of 1024 bytes:
drivers/net/wireless/ath/ath9k/ar9003_aic.c: In function
'ar9003_aic_cal_post_process':
drivers/net/wireless/ath/ath9k/ar9003_aic.c:434:1: error: the frame size of
1040 bytes is larger than 1024 bytes [-Werror=
> -Original Message-
> From: netdev-ow...@vger.kernel.org [mailto:netdev-
> ow...@vger.kernel.org] On Behalf Of David Miller
> Sent: 12 February 2016 10:54
> To: Paul Durrant
> Cc: netdev@vger.kernel.org; xen-de...@lists.xenproject.org
> Subject: Re: [PATCH net-next v1 0/8] xen-netback: sup
From: Paul Durrant
Date: Fri, 12 Feb 2016 10:13:17 +
> This patch series adds support for frontend-configurable toeplitz hashing
> in xen-netback (on the guest receive side). This support has been testing
> against a Windows frontend and has proven to be sufficient to pass the
> Microsoft HCK
From: Edward Cree
Date: Thu, 11 Feb 2016 20:46:00 +
> Re-tested VxLAN; everything else is unchanged from v4.
>
> Changes from v4:
> * Rebased series to fix conflicts with vxlan/vxlan6 merge.
>
> Changes from v3:
> * Fixed inverted checksum values introduced in v3.
> * Don't mangle zero c
From: Eric Dumazet
Date: Thu, 11 Feb 2016 16:28:48 -0800
> Big servers have bloated bind table, making very hard to succeed
> ephemeral port allocations, without special containers/namespace tricks.
>
> This patch series extends the strategy added in commit 07f4c90062f8
> ("tcp/dccp: try to not
The ks8995 phy driver just started using gpiod_* functions, which are
declared in linux/gpio/consumer.h, not linux/gpio.h, resulting in a
build failure in randconfig builds that do not have CONFIG_GPIOLIB
enabled:
drivers/net/phy/spi_ks8995.c: In function 'ks8995_probe':
drivers/net/phy/spi_ks8995
On 02/12/2016, 11:36 AM, Jiri Slaby wrote:
> It there some compilation flag missing? -f flags when compiling that file are:
> -falign-jumps=1
> -falign-loops=1
> -fconserve-stack
> -fno-asynchronous-unwind-tables
> -fno-common
> -fno-delete-null-pointer-checks
> -fno-inline-functions-called-once
>
1 - 100 of 116 matches
Mail list logo
