Support for the new rx_nohandler statistic.
This code is designed to handle the case where the kernel reported statistic
structure is smaller than the larger structure in later releases (and vice
versa).
Signed-off-by: Stephen Hemminger
---
ip/ipaddress.c | 35
The while loop after err_slaves should use post-decrement; otherwise
we'll fail to do the kfrees for i==0, and will run into out-of-bounds
accesses if the setup above failed already at i==0.
The predecrement in the --port is ok, since ->vlan_filter is
(bizarrely) 1-indexed. But I'm changing 'if'
There are a few instances of
for (i = 0; i < FOO; ++i) {
ret = do_stuff(i)
if (ret)
goto err;
}
...
err:
while (--i)
undo_stuff(i);
At best, this fails to undo_stuff for i==0, but if i==0 was the case
that failed, we'll end up with an "infinite" loop in the error path
This change has been made with the goal that kernel functions should
return something more descriptive than -1 on failure.
A variable `err` has been introduced for storing error codes.
The return value of kzalloc on failure should return a -1 and not a
-ENOMEM. This was found using Coccinelle. A
When using device tree it is no more possible to reset the PHY at board
level. Furthermore, doing in the driver allows to power down the switch
when it is not used any more.
The patch introduces a new optional property "reset-gpios" denoting an
appropriate GPIO handle, e.g.:
reset-gpios = < 46
I ended up reverting this patch from iproute2 because the code in kernel
was not accepted upstream.
After it is upstream in kernel please resubmit
On Tuesday 09 February 2016 16:55:42 Karicheri, Muralidharan wrote:
>
> The descriptors are usable by different drivers, one driver may use it as
> buf ptr/ len, other for something else. So they should remain as generic
> and it is up to individual drivers to use it in whatever way it requires.
Prepare creating SPI reads and writes for other switch families.
The KS8995 family uses the straight forward
<8bit CMD><8bit ADDR>
sequence.
To be able to support KSZ8795 family, which uses
<3bit CMD><12bit ADDR><1 bit TR>
make the SPI command creation chip variant dependent.
Signed-off-by: Helmut Buchsbaum
---
.../devicetree/bindings/net/micrel-ks8995.txt| 20
1 file changed, 20 insertions(+)
create mode 100644 Documentation/devicetree/bindings/net/micrel-ks8995.txt
diff --git
Add support for MICREL KSZ8795CLX Integrated 5-Port, 10-/100-Managed
Ethernet Switch with Gigabit GMII/RGMII and MII/RMII interfaces.
Signed-off-by: Helmut Buchsbaum
---
drivers/net/phy/spi_ks8995.c | 29 +
1 file changed, 29 insertions(+)
Since the chip variant is now determined by spi_device_id, verify
family and chip id and determine the revision id.
Signed-off-by: Helmut Buchsbaum
---
drivers/net/phy/spi_ks8995.c | 118 +--
1 file changed, 80 insertions(+),
This patch series refactors the spi-ks8995 driver to finally add support
for the MICREL KSZ8795CLX. Additionally support for controlling a GPIO
line for resetting the switch is added.
Helmut
Changes since v2:
- use GPIO_ACTIVE_LOW according to Andrew's remark.
- use ePAPR compliant node name
Refactor to use spi_device_id table to facilitate easy
extendability.
Signed-off-by: Helmut Buchsbaum
---
drivers/net/phy/spi_ks8995.c | 42 --
1 file changed, 40 insertions(+), 2 deletions(-)
diff --git
This is the initial submission of an ethernet driver for
the Microchip LAN9352.
The LAN9352 is a 2-Port 10/100 Managed Ethernet Switch
with 16-Bit Non-PCI CPU Interface.
While the LAN9352 is a Managed Ethernet Switch, this driver
only supports a simple ethernet controller interface.
From: Alexandre TORGUE
Date: Wed, 3 Feb 2016 15:54:31 +0100
> STM32F429 Chip embeds a Synopsys 3.50a MAC IP.
> This series:
> -enhance current stmmac driver to control it (code already available)
> and
>adds basic glue for STM32F429 chip.
>
Replace 'goto' with 'return' to remove unnecessary check at label:
err_undo_flags.
The reason is that 'err_undo_flags' do two things for the first slave device:
1.revert bond mac address if it is set by the slave device.
2.revert bond device type if it's not ARPHRD_ETHER.
It's not necessary for
From: Hans Westgaard Ry
Date: Wed, 3 Feb 2016 09:26:57 +0100
> Devices may have limits on the number of fragments in an skb they support.
> Current codebase uses a constant as maximum for number of fragments one
> skb can hold and use.
> When enabling
From: skallam
Date: Wed, 3 Feb 2016 14:09:38 +0530
> From: Siva Reddy Kallam
>
> tg3_tso_bug() can hit a condition where the entire tx ring is not big
> enough to segment the GSO packet. For example, if MSS is very small,
> gso_segs can
From: George Spelvin [mailto:li...@horizon.com]
> Sent: 08 February 2016 20:13
> David Laight wrote:
> > I'd need convincing that unrolling the loop like that gives any significant
> > gain.
> > You have a dependency chain on the carry flag so have delays between the
> > 'adcq'
> > instructions
On 2/4/2016 5:18 AM, Amir Vadai" wrote:
> On Wed, Feb 03, 2016 at 01:28:37AM -0800, John Fastabend wrote:
>> This patch allows netdev drivers to consume cls_u32 offloads via
>> the ndo_setup_tc ndo op.
>>
>> This works aligns with how network drivers have been doing qdisc
>> offloads for mqprio.
From: Jiri Pirko
Date: Wed, 3 Feb 2016 09:57:03 +0100
> This patchset extends uapi to let the user know if an mdb entry is
> offloaded.
Series applied, but I really hope that it is safe to use that empry u8
slot for the flag field.
Thanks.
From: Govindarajulu Varadarajan
Date: Wed, 3 Feb 2016 14:40:44 +0530
> From: Sandeep Pillai
>
> Firmware posts the devcmd result in result ring. In case of timeout, driver
> does not increment the current result pointer and firmware could post the
>
This patch fixes an issue with unaligned accesses when using
eth_get_headlen on a page that was DMA aligned instead of being IP aligned.
The fact is when trying to check the length we don't need to be looking at
the flow label so we can reorder the checks to first check if we are
supposed to
On 2/4/2016 5:12 AM, Jamal Hadi Salim wrote:
>
> On 16-02-03 01:48 PM, Fastabend, John R wrote:
>
> BTW: For the record John, I empathize with you that we need to
> move. Please have patience - we are close; lets just get this resolved
> in Seville. I like your patches a lot and would love to
On Mon, Feb 08, 2016 at 06:35:34PM +0100, Helmut Buchsbaum wrote:
> When using device tree it is no more possible to reset the PHY at board
> level. Furthermore, doing in the driver allows to power down the switch
> when it is not used any more.
>
> The patch introduces a new optional property
From: Nikolay Aleksandrov
Date: Wed, 3 Feb 2016 13:17:01 +0100
> From: Nikolay Aleksandrov
>
> Currently the bonding allows to set ad_actor_system and prio while the
> bond device is down, but these are actually applied only if there aren't
>
From: Govindarajulu Varadarajan
Date: Wed, 3 Feb 2016 14:40:44 +0530
> From: Sandeep Pillai
>
> Firmware posts the devcmd result in result ring. In case of timeout, driver
> does not increment the current result pointer and firmware could post the
>
On 2/9/2016 11:07 AM, Helmut Buchsbaum wrote:
Signed-off-by: Helmut Buchsbaum
---
.../devicetree/bindings/net/micrel-ks8995.txt| 20
1 file changed, 20 insertions(+)
create mode 100644
On 16-02-09 03:40 AM, David Miller wrote:
From: Eric Dumazet
Date: Mon, 08 Feb 2016 14:57:40 -0800
Whole point of TLV is that it allows us to add new fields at the end of
the structures.
...
Look at iproute2, you were the one adding in 2004 code to cope with
On Fri, 2016-01-29 at 23:11 +0100, John Holland wrote:
> The Intel i211 LOM pcie ethernet controllers' iNVM operates as an
> OTP
> and has no externel EEPROM interface [1]. The following allows the
> driver to pickup the MAC address from a device tree blob when
> CONFIG_OF
> has been enabled.
>
[...]
>> Ah I should have annotated this in the commit msg. I turn the feature
>> off by default to enable it the user needs to run
>>
>> # ethtool -K ethx hw-tc-offload on
>>
>> this is just a habit of mine to leave new features off by default for
>> a bit until I work out some of the
From: Eric Dumazet
Date: Tue, 02 Feb 2016 19:31:12 -0800
> From: Eric Dumazet
>
> Petr Novopashenniy reported that ICMP redirects on SYN_RECV sockets
> were leading to RST.
>
> This is of course incorrect.
>
> A specific list of ICMP messages
From: Lorenzo Colitti
Date: Thu, 4 Feb 2016 01:17:12 +0900
> Without this, using SOCK_DESTROY in enforcing mode results in:
>
> SELinux: unrecognized netlink message type=21 for sclass=32
>
> Signed-off-by: Lorenzo Colitti
Applied, thanks Lorenzo.
From: Haiyang Zhang
Date: Tue, 2 Feb 2016 16:15:56 -0800
> We simulates a link down period for RNDIS_STATUS_NETWORK_CHANGE message to
> trigger DHCP renew. User daemons may need multiple seconds to trigger the
> link down event. (e.g. ifplugd: 5sec, network-manager:
On 02/08/2016 07:44 PM, Sergei Shtylyov wrote:
Hello.
On 02/08/2016 08:35 PM, Helmut Buchsbaum wrote:
Signed-off-by: Helmut Buchsbaum
---
.../devicetree/bindings/net/micrel-ks8995.txt| 20
1 file changed, 20 insertions(+)
create
From: Xin Long
Date: Wed, 3 Feb 2016 23:33:30 +0800
> Commit ed5a377d87dc ("sctp: translate host order to network order when
> setting a hmacid") corrected the hmacid byte-order when setting a hmacid.
> but the same issue also exists on getting a hmacid.
>
> We fix it by
On 2/4/2016 3:19 PM, Pablo Neira Ayuso wrote:
> On Thu, Feb 04, 2016 at 10:16:56AM +0100, Jiri Pirko wrote:
>> Wed, Feb 03, 2016 at 10:27:32AM CET, john.fastab...@gmail.com wrote:
>>>
>>> Also by adding get_parse_graph and set_parse_graph attributes as
>>> in my previous flow_api work we can build
From: Eric Dumazet
Date: Mon, 08 Feb 2016 14:57:40 -0800
> Whole point of TLV is that it allows us to add new fields at the end of
> the structures.
...
> Look at iproute2, you were the one adding in 2004 code to cope with
> various tcp_info sizes.
>
> So 12 years
This patch corrects the unaligned accesses seen on GRE TEB tunnels when
generating hash keys. Specifically what this patch does is make it so that
we force the use of skb_copy_bits when the GRE inner headers will be
unaligned due to NET_IP_ALIGNED being a non-zero value.
Signed-off-by: Alexander
On Monday 08 February 2016 22:51:38 Andrew Lunn wrote:
> On Mon, Feb 08, 2016 at 10:46:42PM +0100, Arnd Bergmann wrote:
> > On Monday 08 February 2016 21:21:13 Bernhard Walle wrote:
> > > We need that for a custom hardware that needs the reverse reset
> > > sequence.
> > >
> > > Signed-off-by:
EMAC reset internal tx ring pointer to zero at statup.
txbd_curr and txbd_dirty can be different from zero.
That cause ethernet transfer hang (no packets transmitted).
In order to reproduce, run on device:
ifconfig eth0 down
ifconfig eth0 up
Signed-off-by: Alexander Kochetkov
There is a race between arc_emac_tx() and arc_emac_tx_clean().
sk_buff got freed by arc_emac_tx_clean() while arc_emac_tx()
submitting sk_buff.
In order to free sk_buff arc_emac_tx_clean() checks:
if ((info & FOR_EMAC) || !txbd->data)
break;
...
dev_kfree_skb_irq(skb);
If
EMAC could be disabled, while there is some sb_buff
in use. That buffers got lost for linux.
In order to reproduce run on device during active ethernet work:
ifconfig eth0 down
Signed-off-by: Alexander Kochetkov
---
CC: sta...@vger.kernel.org # 3.18.x-
---
On Tue, Feb 9, 2016 at 3:14 PM, Alexander Duyck wrote:
> This patch corrects the unaligned accesses seen on GRE TEB tunnels when
> generating hash keys. Specifically what this patch does is make it so that
> we force the use of skb_copy_bits when the GRE inner headers will
Hello!
Here is a set of 3 patches what fix koops, memory leak and
rockchip EMAC hang. Tested on radxarock lite.
[PATCH 1/3] net: arc_emac: fix koops caused by sk_buff free
[PATCH 2/3] net: arc_emac: reset txbd_curr and txbd_dirty pointers
[PATCH 3/3] net: arc_emac: fix sk_buff leak
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 +++---
drivers/net/ethernet/cadence/macb.h
From: Grygorii Strashko
> Sent: 09 February 2016 13:58
> From: Arnd Bergmann
>
> The commit 899077791403 ("netcp: try to reduce type confusion in descriptors")
> introduces a regression in Kernel 4.5-rc1 and it breaks
> get/set_pad_info() functionality.
>
> The TI NETCP driver
From: Willem de Bruijn
Date: Wed, 3 Feb 2016 18:02:13 -0500
> From: Willem de Bruijn
>
> Extend PACKET_VNET_HDR socket option support to packet sockets with
> memory mapped rings.
>
> Patches 2 and 4 add support to tpacket_rcv and
On 16-02-09 06:24 AM, Fastabend, John R wrote:
On 2/4/2016 5:12 AM, Jamal Hadi Salim wrote:
On 16-02-03 01:48 PM, Fastabend, John R wrote:
Basically most hardware (or i should say driver implementations of
mostly TCAMS) allow you to add exactly the same filter as many times
as you want.
Currently our netdevice ops is a one static global variable which
is referenced by all mlx5e netdevice instances. This can be
problematic when different driver instances do not share same
HW capabilities (e.g SRIOV PF and VFs probed to the host).
Now we have two constant global netdevice ops
We added here a patch from Matan and Alaa for addressing Linus comments on
the mess w.r.t reserved field names in the driver/firmware auto-generated file.
Once the patch hits linus tree, we'll ask Doug to rebase his tree on that
rc so both net-next and rdma-next development for 4.6 will be done
[...]
>>
>> If you leave ht and order off the tc cli I believe 'tc' just
>> picks some semi-arbitrary ones for you. I've been in the habit
>> of always specifying them even for software filters.
>>
>
> The default table id is essentially 0x800. Default bucket is 0.
> "order" essentially is the
On Tue, Feb 2, 2016 at 11:13 PM, Jesper Dangaard Brouer
wrote:
> There are several techniques/concepts combined in this optimization.
> It is both a data-cache and instruction-cache optimization.
>
> First of all, this is primarily about delaying touching
> packet-data, which
Currently mlx5e_select_queue is redundant since num_tc is always 1.
Signed-off-by: Saeed Mahameed
---
drivers/net/ethernet/mellanox/mlx5/core/en_main.c |3 ---
1 files changed, 0 insertions(+), 3 deletions(-)
diff --git
> > +static void igb_read_mac_addr_dts(struct e1000_hw *hw)
> > +{
> > + const u8 *mac;
> > + struct device_node *dn;
> > +
> > + dn = of_find_compatible_node(NULL, NULL, "intel,i211");
Hi John
Would this also work for the i210?
If so, you normally use the compatible string
Hi Nikolay,
On Tue, Feb 09, 2016 at 12:14:39AM +0100, Nikolay Aleksandrov wrote:
> From: Nikolay Aleksandrov
>
> This patch implements support for the IFLA_BR_NF_CALL_(IP|IP6|ARP)TABLES
> attributes in iproute2 so it can change their values.
>
> Signed-off-by:
> > + dn = of_find_compatible_node(NULL, NULL, "intel,i211");
Humm, NULL, NULL. That means find the first node anywhere in the
device tree which matches. This is not going to work too well when you
have multiple i211s.
There is a way so specify a DT node is attached to a specific PCIe
From: Alexander Duyck
Date: Tue, 09 Feb 2016 02:49:54 -0800
> This patch fixes an issue with unaligned accesses when using
> eth_get_headlen on a page that was DMA aligned instead of being IP aligned.
> The fact is when trying to check the length we don't need to be looking
Acked-by: Raanan Avargil
--
Regards,
Raanan
-Original Message-
From: Intel-wired-lan [mailto:intel-wired-lan-boun...@lists.osuosl.org] On
Behalf Of Stefan Assmann
Sent: Wednesday, February 03, 2016 10:21
To: intel-wired-...@lists.osuosl.org
Cc:
From: Arnd Bergmann
The commit 899077791403 ("netcp: try to reduce type confusion in descriptors")
introduces a regression in Kernel 4.5-rc1 and it breaks
get/set_pad_info() functionality.
The TI NETCP driver uses pad0 and pad1 fields of knav_dma_desc to
store DMA/MEM buffer
On Tue, Feb 9, 2016 at 3:33 PM, Tom Herbert wrote:
> On Tue, Feb 9, 2016 at 3:14 PM, Alexander Duyck wrote:
>> This patch corrects the unaligned accesses seen on GRE TEB tunnels when
>> generating hash keys. Specifically what this patch does is make it
> -Original Message-
> From: David Miller [mailto:da...@davemloft.net]
> Sent: Tuesday, February 9, 2016 5:05 AM
> To: Haiyang Zhang
> Cc: netdev@vger.kernel.org; KY Srinivasan ;
> o...@aepfle.de; vkuzn...@redhat.com;
On 06/02/16 18:36, Eric W. Biederman wrote:
Robert Shearman writes:
It is sometimes desirable to present an MPLS transport network as a
single hop to traffic transiting it because it prevents confusion when
diagnosing failures. An example of where confusion can be
>-Original Message-
>From: David Laight [mailto:david.lai...@aculab.com]
>Sent: Tuesday, February 09, 2016 9:13 AM
>To: Strashko, Grygorii; netdev@vger.kernel.org; David S . Miller; Arnd Bergmann
>Cc: Cooper Jr., Franklin; Nori, Sekhar; linux-ker...@vger.kernel.org; Kwok,
>WingMan;
Murali Karicheri
Linux Kernel, Software Development
>-Original Message-
>From: David Laight [mailto:david.lai...@aculab.com]
>Sent: Tuesday, February 09, 2016 11:10 AM
>To: Karicheri, Muralidharan; Strashko, Grygorii; netdev@vger.kernel.org; David
>S . Miller;
>Arnd Bergmann
>Cc:
On Tue, Feb 9, 2016 at 3:14 PM, Alexander Duyck wrote:
> This patch corrects the unaligned accesses seen on GRE TEB tunnels when
> generating hash keys. Specifically what this patch does is make it so that
> we force the use of skb_copy_bits when the GRE inner headers will
From: Karicheri, Muralidharan
> Sent: 09 February 2016 16:10
...
> >In reality the 'pad' fields ought to be renamed - since they aren't pads.
> >Perhaps they should be a union?
> No. At the end of the descriptor, host software can add scratchpad which is
> not modified by the hardware, but is
Hi Dave,
I've split 23 patches out of my AF_RXRPC rewrite so far. If you look here:
http://git.kernel.org/cgit/linux/kernel/git/dhowells/linux-fs.git/log/?h=rxrpc-experimental
the penultimate patch is the remnant rewrite, the 23 patches below that are
ones I've split out of it.
Are
>-Original Message-
>From: David Laight [mailto:david.lai...@aculab.com]
>Sent: Tuesday, February 09, 2016 11:38 AM
>To: Karicheri, Muralidharan; Strashko, Grygorii; netdev@vger.kernel.org; David
>S . Miller;
>Arnd Bergmann
>Cc: Cooper Jr., Franklin; Nori, Sekhar;
On Sun, 7 Feb 2016 16:28:16 -0800
Roopa Prabhu wrote:
> From: Roopa Prabhu
>
> This patch adds support to add mpls multipath
> routes.
>
> example:
> ip -f mpls route add 100 \
> nexthop as 200 via inet 10.1.1.2 dev swp1 \
>
On Tue, 9 Feb 2016 00:14:19 +0100
Nikolay Aleksandrov wrote:
> From: Nikolay Aleksandrov
>
> Netlink returns the bridge_id and designated_root, we just need to
> make them visible.
>
> Signed-off-by: Nikolay Aleksandrov
Allow the MTU of geneve devices to be set to large values, in order to
exploit underlying networks with larger frame sizes.
GENEVE does not have a fixed encapsulation overhead (an openvswitch
rule can add variable length options), so there is no relevant maximum
MTU to enforce. A maximum of
Prior to 4.3, tunnel vports (vxlan, gre and geneve) could transmit
vxlan packets of any size, constrained only by the ability to send out
the resulting packets. 4.3 introduced netdevs corresponding to tunnel
vports. These netdevs have an MTU, which limits the size of a packet
that can be
Allow the MTU of vxlan devices without an underlying device to be set
to larger values (up to a maximum based on IP packet limits and vxlan
overhead).
Previously, their MTUs could not be set to higher than the
conventional ethernet value of 1500. This is a very arbitrary value
in the context of
Prior to 4.3, tunnel vports (vxlan, gre and geneve) could transmit
vxlan packets of any size, constrained only by the ability to send out
the resulting packets. 4.3 introduced netdevs corresponding to tunnel
vports. These netdevs have an MTU, which limits the size of a packet
that can be
From: Karicheri, Muralidharan
> Sent: 09 February 2016 16:19
> >...
> >> >In reality the 'pad' fields ought to be renamed - since they aren't pads.
> >> >Perhaps they should be a union?
> >
> >> No. At the end of the descriptor, host software can add scratchpad
> >> which is not modified by the
On Mon, 8 Feb 2016 17:13:58 +0100
Nikolay Aleksandrov wrote:
> From: Nikolay Aleksandrov
>
> It seems that I've made a mistake when I exported these, instead of a
> space in the end I've put a newline character which is wrong and breaks
> the
Provide an interface for the airplane-mode indicator be controlled from
userspace. User has to first acquire the control through
RFKILL_OP_AIRPLANE_MODE_ACQUIRE and keep the fd open for the whole time
it wants to be in control of the indicator. Closing the fd or using
The driver has often repeated pattern of reading a register, AND'ing and/or
OR'ing some bits and writing the value back. Factor the pattern out into
sh_eth_modify() -- this saves 84 bytes of code with ARM gcc 4.7.3.
While at it, update Cogent Embedded's copyright.
Signed-off-by: Sergei
From: David Howells
Date: Tue, 09 Feb 2016 16:31:01 +
> Are you okay with me sending some of them your way now so that you don't get a
> host all in one go, or would you prefer the mass invasion approach?
Please send them in reasonable chunks, thanks.
On 8 February 2016 at 17:53, Julian Calaby wrote:
>> + if (ev.op == RFKILL_OP_AIRPLANE_MODE_RELEASE) {
>> + if (rfkill_apm_owned && !data->is_apm_owner) {
>
> Are you sure this is correct?
>
> In the case that airplane mode isn't owned, the
>
From: Shannon Nelson
Date: Tue, 9 Feb 2016 09:42:45 -0800
> It seem to me this should be using eth_platform_get_mac_address(), a
> slightly more generic method to do this. See the i40e driver for an
> example, commit d9a84324e6 I believe.
+1
Hi Bernhard,
On Tue, Feb 9, 2016 at 6:01 PM, Bernhard Walle wrote:
> We need that for a custom hardware that needs the reverse reset
> sequence.
>
> Signed-off-by: Bernhard Walle
Looks good:
Reviewed-by: Fabio Estevam
The driver has often repeated pattern of reading a register, AND'ing and/or
OR'ing some bits and writing the value back. Factor the pattern out into
ravb_modify() -- this saves 260 bytes of code with ARM gcc 4.7.3.
While at it, update Cogent Embedded's copyrights.
Signed-off-by: Sergei
Hello.
Here's a set of 2 patches against DaveM's 'net-next.git' repo. We factor out
the often repeated pattern of reading a register, AND'ing and/or OR'ing some
bits, and then writing the value back.
[1/2] ravb: factor out register bit twiddling code
[2/2] sh_eth: factor out register bit
Hi All,
On Wed, Feb 10, 2016 at 8:36 AM, João Paulo Rechi Vita
wrote:
> Provide an interface for the airplane-mode indicator be controlled from
> userspace. User has to first acquire the control through
> RFKILL_OP_AIRPLANE_MODE_ACQUIRE and keep the fd open for the whole time
We need to use post-decrement to ensure that irq_dispose_mapping is
also called on priv->rxq[0]->irq_no; moreover, if one of the above for
loops failed already at i==0 (so we reach one of these labels with
that value of i), we'll enter an essentially infinite loop of
out-of-bounds accesses.
I'm running into a bug with kernel 4.4.0 where a VM-VM test between two
different baremetal hosts (HP Proliant dl360gen9s) has receive-side
throughput
that's about 25% lower than expected with a Mellanox ConnectX3-pro NIC.
The VMs
are connected over a VXLAN tunnel that I used OpenvSwitch
On 02/09/2016 07:47 PM, David Wragg wrote:
Allow the MTU of geneve devices to be set to large values, in order to
exploit underlying networks with larger frame sizes.
GENEVE does not have a fixed encapsulation overhead (an openvswitch
rule can add variable length options), so there is no
Sergei Shtylyov writes:
>The networking code formats comments:
>
> /* Like
> * this.
> */
Thanks. And I noticed another silly mistake. Will respin.
David
On Thu, Feb 4, 2016 at 10:35 AM, Craig Gallek wrote:
> From: Craig Gallek
>
> In order to support fast reuseport lookups in TCP, the hash function
> defined in struct proto must be capable of returning an error code.
> This patch changes the function
Allow the MTU of vxlan devices without an underlying device to be set
to larger values (up to a maximum based on IP packet limits and vxlan
overhead).
Previously, their MTUs could not be set to higher than the
conventional ethernet value of 1500. This is a very arbitrary value
in the context of
Allow the MTU of geneve devices to be set to large values, in order to
exploit underlying networks with larger frame sizes.
GENEVE does not have a fixed encapsulation overhead (an openvswitch
rule can add variable length options), so there is no relevant maximum
MTU to enforce. A maximum of
From: Craig Gallek
This change extends the fast SO_REUSEPORT socket lookup implemented
for UDP to TCP. Listener sockets with SO_REUSEPORT and the same
receive address are additionally added to an array for faster
random access. This means that only a single socket from the
From: David Decotigny
Signed-off-by: David Decotigny
---
drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 344
drivers/net/ethernet/mellanox/mlx4/en_main.c| 1 +
drivers/net/ethernet/mellanox/mlx4/mlx4_en.h| 1 +
3
From: Craig Gallek
This patch series complements an earlier series (6a5ef90c58da)
which added faster SO_REUSEPORT lookup for UDP sockets by
extending the feature to TCP sockets. It uses the same
array-based data structure which allows for socket selection
after finding the
From: Craig Gallek
In order to support fast reuseport lookups in TCP, the hash function
defined in struct proto must be capable of returning an error code.
This patch changes the function signature of all related hash functions
to return an integer and handles or propagates
From: Craig Gallek
This change extends the fast SO_REUSEPORT socket lookup implemented
for UDP to TCP. Listener sockets with SO_REUSEPORT and the same
receive address are additionally added to an array for faster
random access. This means that only a single socket from the
From: Craig Gallek
tcp_hdrlen is wasteful if you already have a pointer to struct tcphdr.
This splits the size calculation into a helper function that can be
used if a struct tcphdr is already available.
Signed-off-by: Craig Gallek
---
include/linux/tcp.h |
From: Craig Gallek
Unfortunately the existing test relied on packet payload in order to
map incoming packets to sockets. In order to get this to work with TCP,
TCP_FASTOPEN needed to be used.
Since the fast open path is slightly different than the standard TCP path,
I created
1 - 100 of 152 matches
Mail list logo