Re: [net-next PATCH v2 2/2] e1000: bundle xdp xmit routines

On Fri, Sep 9, 2016 at 8:26 PM, John Fastabend wrote: > On 16-09-09 08:12 PM, Tom Herbert wrote: >> On Fri, Sep 9, 2016 at 6:40 PM, Alexei Starovoitov >> wrote: >>> On Fri, Sep 09, 2016 at 06:19:56PM -0700, Tom Herbert wrote: On Fri,

Re: [PATCH] ATM-iphase: Use kmalloc_array() in tx_init()

From: SF Markus Elfring Date: Fri, 9 Sep 2016 20:42:16 +0200 > From: Markus Elfring > Date: Fri, 9 Sep 2016 20:40:16 +0200 > > * Multiplications for the size determination of memory allocations > indicated that array data

Re: [PATCH v3 0/9] net-next: ethernet: add sun8i-emac driver

From: Corentin Labbe Date: Fri, 9 Sep 2016 14:45:08 +0200 > This patch series add the driver for sun8i-emac which handle the > Ethernet MAC present on Allwinner H3/A83T/A64 SoCs. Please don't post a patch series with some subset of the series marked as "RFC". I will

Re: [net-next PATCH v2 2/2] e1000: bundle xdp xmit routines

On Fri, Sep 09, 2016 at 08:12:52PM -0700, Tom Herbert wrote: > >> That probably means that the stack will always win out under load. > >> Trying to used the same queue where half of the packets are well > >> managed by a qdisc and half aren't is going to leave someone unhappy. > >> Maybe in the

Re: [PATCH net-next 0/4] alx: add msi-x support

From: Tobias Regnery Date: Fri, 9 Sep 2016 12:19:51 +0200 > This patchset adds msi-x support to the alx driver. It is a preparatory > series for multi queue support, which I am currently working on. As there > is no advantage over msi interrupts without multi queue

Re: [net-next PATCH v2 2/2] e1000: bundle xdp xmit routines

On 16-09-09 08:12 PM, Tom Herbert wrote: > On Fri, Sep 9, 2016 at 6:40 PM, Alexei Starovoitov > wrote: >> On Fri, Sep 09, 2016 at 06:19:56PM -0700, Tom Herbert wrote: >>> On Fri, Sep 9, 2016 at 6:12 PM, John Fastabend >>> wrote: On

Re: [net-next PATCH v2 2/2] e1000: bundle xdp xmit routines

On Fri, Sep 9, 2016 at 6:40 PM, Alexei Starovoitov wrote: > On Fri, Sep 09, 2016 at 06:19:56PM -0700, Tom Herbert wrote: >> On Fri, Sep 9, 2016 at 6:12 PM, John Fastabend >> wrote: >> > On 16-09-09 06:04 PM, Tom Herbert wrote: >> >> On

Re: [PATCH net-next 0/4] Some BPF helper cleanups

From: Daniel Borkmann Date: Fri, 9 Sep 2016 02:45:27 +0200 > This series contains a couple of misc cleanups and improvements > for BPF helpers. For details please see individual patches. We > let this also sit for a few days with Fengguang's kbuild test > robot, and there

Re: [PATCH net-next] ip_tunnel: do not clear l4 hashes

From: Eric Dumazet Date: Thu, 08 Sep 2016 15:40:48 -0700 > From: Eric Dumazet > > If skb has a valid l4 hash, there is no point clearing hash and force > a further flow dissection when a tunnel encapsulation is added. > > Signed-off-by: Eric

Re: [PATCH] drivers: net: phy: mdio-xgene: Add hardware dependency

From: Jean Delvare Date: Thu, 8 Sep 2016 16:25:15 +0200 > The mdio-xgene driver is only useful on X-Gene SoC. > > Signed-off-by: Jean Delvare Applied.

Re: [PATCH] ATM-ForeRunnerHE: Use kmalloc_array() in he_init_group()

From: SF Markus Elfring Date: Thu, 8 Sep 2016 15:50:05 +0200 > From: Markus Elfring > Date: Thu, 8 Sep 2016 15:43:37 +0200 > > * Multiplications for the size determination of memory allocations > indicated that array data

Re: [PATCH] ATM-ENI: Use kmalloc_array() in eni_start()

From: SF Markus Elfring Date: Thu, 8 Sep 2016 14:40:06 +0200 > From: Markus Elfring > Date: Thu, 8 Sep 2016 14:20:17 +0200 > > * A multiplication for the size determination of a memory allocation > indicated that an array data

Re: [PATCH net-next 0/7] rxrpc: Rewrite data and ack handling

From: David Howells Date: Thu, 08 Sep 2016 12:43:28 +0100 > This patch set constitutes the main portion of the AF_RXRPC rewrite. It > consists of five fix/helper patches: ... > And then there are two patches that form the main part: ... > With this, the majority of the

Re: pull-request: wireless-drivers 2016-09-08

From: Kalle Valo Date: Thu, 08 Sep 2016 14:31:56 +0300 > The following changes since commit bb87f02b7e4ccdb614a83cbf840524de81e9b321: > > Merge ath-current from ath.git (2016-08-29 21:39:04 +0300) > > are available in the git repository at: > > >

Re: [PATCH net] dwc_eth_qos: do not register semi-initialized device

From: Lars Persson Date: Thu, 8 Sep 2016 13:24:21 +0200 > We move register_netdev() to the end of dwceqos_probe() to close any > races where the netdev callbacks are called before the initialization > has finished. > > Reported-by: Pavel Andrianov >

Re: [PATCH net] sctp: identify chunks that need to be fragmented at IP level

From: Xin Long Date: Thu, 8 Sep 2016 17:54:11 +0800 > From: Marcelo Ricardo Leitner > > Previously, without GSO, it was easy to identify it: if the chunk didn't > fit and there was no data chunk in the packet yet, we could fragment at > IP

Re: [PATCH net] sctp: hold the transport before using it in sctp_hash_cmp

From: Xin Long Date: Thu, 8 Sep 2016 17:49:04 +0800 > Now sctp uses the transport without holding it in sctp_hash_cmp, > it can cause a use-after-free panic. As after it get transport from > hashtable, another CPU may free it, then the members it accesses > may be

Re: [PATCH] softirq: fix tasklet_kill() and its users

Ping !! On 8/24/2016 6:52 PM, Santosh Shilimkar wrote: Semantically the expectation from the tasklet init/kill API should be as below. tasklet_init() == Init and Enable scheduling tasklet_kill() == Disable scheduling and Destroy tasklet_init() API exibit above behavior but not the

Re: [net-next PATCH v2 2/2] e1000: bundle xdp xmit routines

On Fri, Sep 09, 2016 at 06:19:56PM -0700, Tom Herbert wrote: > On Fri, Sep 9, 2016 at 6:12 PM, John Fastabend > wrote: > > On 16-09-09 06:04 PM, Tom Herbert wrote: > >> On Fri, Sep 9, 2016 at 5:01 PM, John Fastabend > >> wrote: > >>> On

Re: [net-next PATCH v2 2/2] e1000: bundle xdp xmit routines

On Fri, Sep 9, 2016 at 6:12 PM, John Fastabend wrote: > On 16-09-09 06:04 PM, Tom Herbert wrote: >> On Fri, Sep 9, 2016 at 5:01 PM, John Fastabend >> wrote: >>> On 16-09-09 04:44 PM, Tom Herbert wrote: On Fri, Sep 9, 2016 at 2:29 PM, John

Re: [PATCH] via-velocity: remove null pointer check on array tdinfo->skb_dma

From: Colin King Date: Thu, 8 Sep 2016 10:04:24 +0100 > From: Colin Ian King > > tdinfo->skb_dma is a 7 element array of dma_addr_t hence cannot be > null, so the pull pointer check on tdinfo->skb_dma is redundant. > Remove it. > >

Re: [PATCH] qede: mark qede_set_features() static

From: Baoyou Xie Date: Thu, 8 Sep 2016 16:43:23 +0800 > We get 1 warning when building kernel with W=1: > drivers/net/ethernet/qlogic/qede/qede_main.c:2113:5: warning: no previous > prototype for 'qede_set_features' [-Wmissing-prototypes] > > In fact, this function is

Re: [PATCH net-next 1/1] net: phy: Fixed checkpatch errors for Microsemi PHYs.

From: Raju Lakkaraju Date: Thu, 8 Sep 2016 14:09:31 +0530 > From: Raju Lakkaraju > > The existing VSC85xx PHY driver did not follow the coding style and caused > "checkpatch" to complain. This commit fixes this. > > Signed-off-by:

Re: [PATCH] net: x25: remove null checks on arrays calling_ae and called_ae

From: Colin King Date: Thu, 8 Sep 2016 08:42:06 +0100 > From: Colin Ian King > > dtefacs.calling_ae and called_ae are both 20 element __u8 arrays and > cannot be null and hence are redundant checks. Remove these. > > Signed-off-by: Colin

Re: [net-next PATCH v2 2/2] e1000: bundle xdp xmit routines

On 16-09-09 06:04 PM, Tom Herbert wrote: > On Fri, Sep 9, 2016 at 5:01 PM, John Fastabend > wrote: >> On 16-09-09 04:44 PM, Tom Herbert wrote: >>> On Fri, Sep 9, 2016 at 2:29 PM, John Fastabend >>> wrote: e1000 supports a single TX queue

Re: [net-next PATCH v2 2/2] e1000: bundle xdp xmit routines

On Fri, Sep 9, 2016 at 5:01 PM, John Fastabend wrote: > On 16-09-09 04:44 PM, Tom Herbert wrote: >> On Fri, Sep 9, 2016 at 2:29 PM, John Fastabend >> wrote: >>> e1000 supports a single TX queue so it is being shared with the stack >>> when XDP

[PATCH -next] tipc: fix possible memory leak in tipc_udp_enable()

From: Wei Yongjun 'ub' is malloced in tipc_udp_enable() and should be freed before leaving from the error handling cases, otherwise it will cause memory leak. Fixes: ba5aa84a2d22 ("tipc: split UDP nl address parsing") Signed-off-by: Wei Yongjun

Re: [PATCH 8/9] selftests: move vDSO tests from Documentation/vDSO

Hi Shuah, [auto build test ERROR on linus/master] [also build test ERROR on v4.8-rc5 next-20160909] [if your patch is applied to the wrong git tree, please drop us a note to help improve the system] [Suggest to use git(>=2.9.0) format-patch --base= (or --base=auto for convenience) to rec

Re: [PATCH 6/9] selftests: move ptp tests from Documentation/ptp

Hi Shuah, [auto build test ERROR on linus/master] [also build test ERROR on v4.8-rc5 next-20160909] [if your patch is applied to the wrong git tree, please drop us a note to help improve the system] [Suggest to use git(>=2.9.0) format-patch --base= (or --base=auto for convenience) to rec

Re: [PATCH 4/9] selftests: move prctl tests from Documentation/prctl

Hi Shuah, [auto build test ERROR on linus/master] [also build test ERROR on v4.8-rc5 next-20160909] [if your patch is applied to the wrong git tree, please drop us a note to help improve the system] [Suggest to use git(>=2.9.0) format-patch --base= (or --base=auto for convenience) to rec

Re: [PATCH 1/9] selftests: move dnotify_test from Documentation/filesystems

Hi Shuah, [auto build test ERROR on linus/master] [also build test ERROR on v4.8-rc5 next-20160909] [if your patch is applied to the wrong git tree, please drop us a note to help improve the system] [Suggest to use git(>=2.9.0) format-patch --base= (or --base=auto for convenience) to rec

Re: [net-next PATCH v2 2/2] e1000: bundle xdp xmit routines

On 16-09-09 04:44 PM, Tom Herbert wrote: > On Fri, Sep 9, 2016 at 2:29 PM, John Fastabend > wrote: >> e1000 supports a single TX queue so it is being shared with the stack >> when XDP runs XDP_TX action. This requires taking the xmit lock to >> ensure we don't corrupt

Re: [PATCH 4/9] selftests: move prctl tests from Documentation/prctl

Hi Shuah, [auto build test ERROR on linus/master] [also build test ERROR on v4.8-rc5 next-20160909] [if your patch is applied to the wrong git tree, please drop us a note to help improve the system] [Suggest to use git(>=2.9.0) format-patch --base= (or --base=auto for convenience) to rec

Re: [patch net 0/2] mlxsw: couple of fixes

From: Jiri Pirko Date: Thu, 8 Sep 2016 08:16:00 +0200 > Couple of fixes from Ido and myself. Series applied, thanks Jiri.

Re: [RFC] bridge: MAC learning uevents

On 09/09/2016 01:51 AM, D. Herrendoerfer wrote: >> just like neighbor table modifications, it should be possible to listen for >> events with netlink. Doing it through uevent is the wrong model. > > I agree partially - but consider: > we plug hardware - we get an event > we remove hardware - we

Re: [PATCH net-next] macsec: set network devtype

From: Stephen Hemminger Date: Wed, 7 Sep 2016 14:07:32 -0700 > The netdevice type structure for macsec was being defined but never used. > To set the network device type the macro SET_NETDEV_DEVTYPE must be called. > Compile tested only, I don't use macsec. > >

Re: [PATCH net-next] rtnetlink: remove unused ifla_stats_policy

From: Stephen Hemminger Date: Wed, 7 Sep 2016 13:57:36 -0700 > This structure is defined but never used. Flagged with W=1 > > Signed-off-by: Stephen Hemminger Applied.

Re: [PATCH net 0/2] ip: fix creation flags reported in RTM_NEWROUTE events

From: Guillaume Nault Date: Wed, 7 Sep 2016 17:18:50 +0200 > Netlink messages sent to user-space upon RTM_NEWROUTE events have their > nlmsg_flags field inconsistently set. While the NLM_F_REPLACE and > NLM_F_APPEND bits are correctly handled, NLM_F_CREATE and NLM_F_EXCL >

Re: [net-next PATCH v2 2/2] e1000: bundle xdp xmit routines

On Fri, Sep 9, 2016 at 2:29 PM, John Fastabend wrote: > e1000 supports a single TX queue so it is being shared with the stack > when XDP runs XDP_TX action. This requires taking the xmit lock to > ensure we don't corrupt the tx ring. To avoid taking and dropping the >

Re: [net-next PATCH v2 2/2] e1000: bundle xdp xmit routines

On 16-09-09 02:29 PM, John Fastabend wrote: > e1000 supports a single TX queue so it is being shared with the stack > when XDP runs XDP_TX action. This requires taking the xmit lock to > ensure we don't corrupt the tx ring. To avoid taking and dropping the > lock per packet this patch adds a

Re: [net-next PATCH v2 1/2] e1000: add initial XDP support

On 16-09-09 03:04 PM, Eric Dumazet wrote: > On Fri, 2016-09-09 at 14:29 -0700, John Fastabend wrote: >> From: Alexei Starovoitov >> > > > So it looks like e1000_xmit_raw_frame() can return early, > say if there is no available descriptor. > >> +static void

[PATCH RFC 3/6] ila: Call library function alloc_bucket_locks

To allocate the array of bucket locks for the hash table we now call library function alloc_bucket_spinlocks. Signed-off-by: Tom Herbert --- net/ipv6/ila/ila_xlat.c | 36 +--- 1 file changed, 5 insertions(+), 31 deletions(-) diff --git

[PATCH RFC 6/6] ila: Resolver mechanism

Implement an ILA resolver. This uses LWT to implement the hook to a userspace resolver and tracks pending unresolved address using the backend net resolver. The idea is that the kernel sets an ILA resolver route to the SIR prefix, something like: ip route add ::/64 encap ila-resolve \

[PATCH RFC 5/6] net: Generic resolver backend

This patch implements the backend of a resolver, specifically it provides a means to track unresolved addresses and to time them out. The resolver is mostly a frontend to an rhashtable where the key of the table is whatever address type or object is tracked. A resolver instance is created by

[PATCH RFC 4/6] rhashtable: abstract out function to get hash

Split out most of rht_key_hashfn which is calculating the hash into its own function. This way the hash function can be called separately to get the hash value. Signed-off-by: Tom Herbert --- include/linux/rhashtable.h | 28 ++-- 1 file changed, 18

[PATCH RFC 0/6] net: ILA resolver and generic resolver backend

This patch sets implements an ILA host side resolver. This uses LWT to implement the hook to a userspace resolver and tracks pending unresolved address using the backend net resolver. This patch set contains: - An new library function to allocate an array of spinlocks for use with locking hash

[PATCH RFC 2/6] rhashtable: Call library function alloc_bucket_locks

To allocate the array of bucket locks for the hash table we now call library function alloc_bucket_spinlocks. This function is based on the old alloc_bucket_locks in rhashtable and should produce the same effect. Signed-off-by: Tom Herbert --- lib/rhashtable.c | 46

[PATCH RFC 1/6] spinlock: Add library function to allocate spinlock buckets array

Add two new library functions alloc_bucket_spinlocks and free_bucket_spinlocks. These are use to allocate and free an array of spinlocks that are useful as locks for hash buckets. The interface specifies the maximum number of spinlocks in the array as well as a CPU multiplier to derive the number

Re: [PATCH next 3/3] ipvlan: Introduce l3s mode

On Fri, Sep 9, 2016 at 3:26 PM, David Ahern wrote: > On 9/9/16 3:53 PM, Mahesh Bandewar wrote: >> diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig >> index 0c5415b05ea9..95edd1737ab5 100644 >> --- a/drivers/net/Kconfig >> +++ b/drivers/net/Kconfig >> @@ -149,6

[PATCH 5/9] selftests: Update prctl Makefile to work under selftests

Update prctl Makefile to work under selftests. prctl will not be run as part of selftests suite and will not included in install targets. They can be built separately for now. Signed-off-by: Shuah Khan --- tools/testing/selftests/prctl/Makefile | 19 ---

[PATCH 0/9] Move runnable code (tests) from Documentation to selftests

Move runnable code (tests) from Documentation to selftests and update Makefiles to work under selftests. Jon Corbet and I discussed this in an email thread and as per that discussion, this patch series moves all the tests that are under the Documentation directory to selftests. There is more

[PATCH 3/9] selftests: move .gitignore from Documentation/filesystems

Move .gitignore for dnotify_test from Documentation/filesystems to selftests/filesystems. Signed-off-by: Shuah Khan --- Documentation/filesystems/.gitignore | 1 - tools/testing/selftests/filesystems/.gitignore | 1 + 2 files changed, 1 insertion(+), 1

[PATCH 4/9] selftests: move prctl tests from Documentation/prctl

Move prctl tests from Documentation/prctl to selftests/prctl. Signed-off-by: Shuah Khan --- Documentation/prctl/.gitignore | 3 - Documentation/prctl/Makefile | 10 --- .../prctl/disable-tsc-ctxt-sw-stress-test.c| 97

[PATCH 7/9] selftests: Update ptp Makefile to work under selftests

Update ptp Makefile to work under selftests. ptp will not be run as part of selftests suite and will not included in install targets. They can be built separately for now. Signed-off-by: Shuah Khan --- tools/testing/selftests/ptp/Makefile | 12 ++-- 1 file

[PATCH 2/9] selftests: update filesystems Makefile to work under selftests

Update to work under selftests. dnotify_test will not be run as part of selftests suite and will not included in install targets. It can be built separately for now. Signed-off-by: Shuah Khan --- tools/testing/selftests/filesystems/Makefile | 10 ++ 1 file

[PATCH 1/9] selftests: move dnotify_test from Documentation/filesystems

Move dnotify_test from Documentation/filesystems to selftests/filesystems Signed-off-by: Shuah Khan --- Documentation/filesystems/Makefile | 5 Documentation/filesystems/dnotify_test.c | 34 --

[PATCH 9/9] selftests: Update vDSO Makefile to work under selftests

Update vDSO Makefile to work under selftests. vDSO will not be run as part of selftests suite and will not included in install targets. They can be built separately for now. Signed-off-by: Shuah Khan --- tools/testing/selftests/vDSO/Makefile | 29

[PATCH 6/9] selftests: move ptp tests from Documentation/ptp

Move ptp tests from Documentation/ptp to selftests/ptp. Signed-off-by: Shuah Khan --- Documentation/ptp/.gitignore | 1 - Documentation/ptp/Makefile | 8 - Documentation/ptp/testptp.c| 523 -

[PATCH 8/9] selftests: move vDSO tests from Documentation/vDSO

Move vDSO tests from Documentation/vDSO to selftests/vDSO. Signed-off-by: Shuah Khan --- Documentation/vDSO/.gitignore | 2 - Documentation/vDSO/Makefile| 17 -- Documentation/vDSO/parse_vdso.c| 269

Re: [PATCH next 3/3] ipvlan: Introduce l3s mode

On 9/9/16 3:53 PM, Mahesh Bandewar wrote: > diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig > index 0c5415b05ea9..95edd1737ab5 100644 > --- a/drivers/net/Kconfig > +++ b/drivers/net/Kconfig > @@ -149,6 +149,7 @@ config IPVLAN > tristate "IP-VLAN support" > depends on INET >

Re: [PATCH next 3/3] ipvlan: Introduce l3s mode

On Fri, Sep 9, 2016 at 3:07 PM, Rick Jones wrote: > On 09/09/2016 02:53 PM, Mahesh Bandewar wrote: > >> @@ -48,6 +48,11 @@ master device for the L2 processing and routing from >> that instance will be >> used before packets are queued on the outbound device. In this mode the

Re: [PATCH next 3/3] ipvlan: Introduce l3s mode

On 09/09/2016 02:53 PM, Mahesh Bandewar wrote: @@ -48,6 +48,11 @@ master device for the L2 processing and routing from that instance will be used before packets are queued on the outbound device. In this mode the slaves will not receive nor can send multicast / broadcast traffic. +4.3 L3S

Re: [net-next PATCH v2 1/2] e1000: add initial XDP support

On Fri, 2016-09-09 at 14:29 -0700, John Fastabend wrote: > From: Alexei Starovoitov > So it looks like e1000_xmit_raw_frame() can return early, say if there is no available descriptor. > +static void e1000_xmit_raw_frame(struct e1000_rx_buffer *rx_buffer_info, > +

[PATCH next 2/3] net: Add _nf_(un)register_hooks symbols

From: Mahesh Bandewar Add _nf_register_hooks() and _nf_unregister_hooks() calls which allow caller to hold RTNL mutex. Signed-off-by: Mahesh Bandewar --- include/linux/netfilter.h | 2 ++ net/netfilter/core.c | 51

[PATCH next 1/3] ipv6: Export p6_route_input_lookup symbol

From: Mahesh Bandewar Make ip6_route_input_lookup available outside of ipv6 the module similar to ip_route_input_noref in the IPv4 world. Signed-off-by: Mahesh Bandewar --- include/net/ip6_route.h | 3 +++ net/ipv6/route.c| 7 --- 2 files

[PATCH next 3/3] ipvlan: Introduce l3s mode

From: Mahesh Bandewar In a typical IPvlan L3 setup where master is in default-ns and each slave is into different (slave) ns. In this setup egress packet processing for traffic originating from slave-ns will hit all NF_HOOKs in slave-ns as well as default-ns. However same is

[PATCH next 0/3] ipvlan introduce l3s mode

From: Mahesh Bandewar Same old problem with new appraoch especially from suggestions from earlier patch-series. First thing is that this is introduced as a new mode rather than modifying the old (L3) mode. So the behavior of the existing modes is preserved as it is and the

[PULL] virtio: fixes for 4.8

The following changes since commit 3eab887a55424fc2c27553b7bfe32330df83f7b8: Linux 4.8-rc4 (2016-08-28 15:04:33 -0700) are available in the git repository at: git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost.git tags/for_linus for you to fetch changes up to

[net-next PATCH v2 2/2] e1000: bundle xdp xmit routines

e1000 supports a single TX queue so it is being shared with the stack when XDP runs XDP_TX action. This requires taking the xmit lock to ensure we don't corrupt the tx ring. To avoid taking and dropping the lock per packet this patch adds a bundling implementation to submit a bundle of packets to

[net-next PATCH v2 1/2] e1000: add initial XDP support

From: Alexei Starovoitov This patch adds initial support for XDP on e1000 driver. Note e1000 driver does not support page recycling in general which could be added as a further improvement. However XDP_DROP case will recycle. XDP_TX and XDP_PASS do not support recycling yet. I

[PATCH net-next] tcp: better use ooo_last_skb in tcp_data_queue_ofo()

From: Eric Dumazet Willem noticed that we could avoid an rbtree lookup if the the attempt to coalesce incoming skb to the last skb failed for some reason. Since most ooo additions are at the tail, this is definitely worth adding a test and fast path. Suggested-by: Willem

[PATCH] openvswitch: use alias for genetlink family names

When userspace tries to create datapaths and the module is not loaded, it will simply fail. With this patch, the module will be automatically loaded. Signed-off-by: Thadeu Lima de Souza Cascardo --- net/openvswitch/datapath.c | 4 1 file changed, 4 insertions(+) diff

[PATCH 2/2] openvswitch: use percpu flow stats

Instead of using flow stats per NUMA node, use it per CPU. When using megaflows, the stats lock can be a bottleneck in scalability. On a E5-2690 12-core system, usual throughput went from ~4Mpps to ~15Mpps when forwarding between two 40GbE ports with a single flow configured on the datapath.

[PATCH 1/2] openvswitch: fix flow stats accounting when node 0 is not possible

On a system with only node 1 as possible, all statistics is going to be accounted on node 0 as it will have a single writer. However, when getting and clearing the statistics, node 0 is not going to be considered, as it's not a possible node. Tested that statistics are not zero on a system with

[PATCH net-next 0/5] liquidio CN23XX VF support

Dave, Following is the initial patch series for adding support of VF functionality on CN23XX devices. Please apply patches in the following order as some of the patches depend on earlier patches. Raghu Vatsavayi (5): liquidio CN23XX: VF config support liquidio CN23XX: sriov enable liquidio

[PATCH net-next 1/5] liquidio CN23XX: VF config support

Adds support for VF configuration. It also limits the number of rings per VF based on total number of VFs configured. Signed-off-by: Derek Chickles Signed-off-by: Satanand Burla Signed-off-by: Felix Manlunas

Re: [PATCH] net: ip, diag -- Add diag interface for raw sockets

On Fri, Sep 09, 2016 at 12:55:13PM -0700, Eric Dumazet wrote: > > + > > + rep = nlmsg_new(sizeof(struct inet_diag_msg) + > > + sizeof(struct inet_diag_meminfo) + 64, > > + GFP_KERNEL); > > + if (!rep) > > There is a missing sock_put(sk) > > > +

[PATCH net-next 4/5] liquidio CN23XX: mailbox interrupt processing

Adds support for mailbox interrupt processing of various commands. Signed-off-by: Derek Chickles Signed-off-by: Satanand Burla Signed-off-by: Felix Manlunas Signed-off-by: Raghu Vatsavayi

[PATCH net-next 5/5] liquidio CN23XX: VF related operations

Adds support for VF related operations like mac address vlan and link changes. Signed-off-by: Derek Chickles Signed-off-by: Satanand Burla Signed-off-by: Felix Manlunas Signed-off-by:

[PATCH net-next 3/5] liquidio CN23XX: Mailbox support

Adds support for mailbox communication between PF and VF. Signed-off-by: Derek Chickles Signed-off-by: Satanand Burla Signed-off-by: Felix Manlunas Signed-off-by: Raghu Vatsavayi

[PATCH net-next 2/5] liquidio CN23XX: sriov enable

Adds support for enabling sriov on CN23XX cards. Signed-off-by: Derek Chickles Signed-off-by: Satanand Burla Signed-off-by: Felix Manlunas Signed-off-by: Raghu Vatsavayi

Re: [PATCH] net: ip, diag -- Add diag interface for raw sockets

On Fri, 2016-09-09 at 21:26 +0300, Cyrill Gorcunov wrote: ... > +static int raw_diag_dump_one(struct sk_buff *in_skb, > + const struct nlmsghdr *nlh, > + const struct inet_diag_req_v2 *r) > +{ > + struct raw_hashinfo *hashinfo =

Re: README: [PATCH RFC 11/11] net/mlx5e: XDP TX xmit more

On Thu, Sep 8, 2016 at 10:36 PM, Jesper Dangaard Brouer wrote: > On Thu, 8 Sep 2016 20:22:04 -0700 > Alexei Starovoitov wrote: > >> On Thu, Sep 08, 2016 at 10:11:47AM +0200, Jesper Dangaard Brouer wrote: >> > >> > I'm sorry but I have a problem

[PATCH] ATM-iphase: Use kmalloc_array() in tx_init()

From: Markus Elfring Date: Fri, 9 Sep 2016 20:40:16 +0200 * Multiplications for the size determination of memory allocations indicated that array data structures should be processed. Thus use the corresponding function "kmalloc_array". This issue was

[PATCH] net: ip, diag -- Add diag interface for raw sockets

In criu we are actively using diag interface to collect sockets present in the system when dumping applications. And while for unix, tcp, udp[lite], packet, netlink it works as expected, the raw sockets do not have. Thus add it. CC: David S. Miller CC: Eric Dumazet

RE: [PATCH v2] net: ethernet: renesas: sh_eth: add POST registers for rz

On 9/9/2016, Sergei Shtylyov wrote: > > sh_eth_private *mdp) { > > if (sh_eth_is_rz_fast_ether(mdp)) { > > sh_eth_tsu_write(mdp, 0, TSU_TEN); /* Disable all CAM entry */ > > + sh_eth_tsu_write(mdp, TSU_FWSLC_POSTENU | TSU_FWSLC_POSTENL, > > +

Re: Minimum MTU Mess

On Thu, Sep 08, 2016 at 03:24:13AM +0200, Andrew Lunn wrote: > > This is definitely going to require a few passes... (Working my way > > through every driver with an ndo_change_mtu wired up right now to > > see just how crazy this might get). > > It might be something Coccinelle can help you

[PATCH net-next] Revert "hv_netvsc: make inline functions static"

From: Stephen Hemminger These functions are used by other code misc-next tree. This reverts commit 30d1de08c87ddde6f73936c3350e7e153988fe02. Signed-off-by: Stephen Hemminger --- drivers/net/hyperv/netvsc.c | 85

Re: [PATCH v2] net: ethernet: renesas: sh_eth: add POST registers for rz

On 09/07/2016 09:57 PM, Chris Brandt wrote: Due to a mistake in the hardware manual, the FWSLC and POST1-4 registers were not documented and left out of the driver for RZ/A making the CAM feature non-operational. Additionally, when the offset values for POST1-4 are left blank, the driver

Re: [PATCH v2] net: ethernet: renesas: sh_eth: add POST registers for rz

Hello. On 09/07/2016 09:57 PM, Chris Brandt wrote: Due to a mistake in the hardware manual, the FWSLC and POST1-4 registers were not documented and left out of the driver for RZ/A making the CAM feature non-operational. Additionally, when the offset values for POST1-4 are left blank, the

Re: [PATCH 7/8] sctp: use IS_ENABLED() instead of checking for built-in or module

On Fri, Sep 09, 2016 at 08:43:19AM -0400, Javier Martinez Canillas wrote: > The IS_ENABLED() macro checks if a Kconfig symbol has been enabled either > built-in or as a module, use that macro instead of open coding the same. > > Using the macro makes the code more readable by helping abstract

Re: [PATCH net 1/6] sctp: remove the unnecessary state check in sctp_outq_tail

> I don't know, I still don't feel safe about it. I agree the socket lock keeps > the state from changing during a single transmission, which makes the use case > you are focused on correct. ok, :-) > > That said, have you considered the retransmit case? That is to say, if you > queue and flush

Re: [PATCH net-next] macsec: set network devtype

2016-09-08, 17:24:07 -0700, David Miller wrote: > From: Stephen Hemminger > Date: Wed, 7 Sep 2016 14:07:32 -0700 > > > The netdevice type structure for macsec was being defined but never used. > > To set the network device type the macro SET_NETDEV_DEVTYPE must be

Re: [iproute PATCH] macsec: fix input range of 'icvlen' parameter

2016-09-09, 16:02:22 +0200, Davide Caratti wrote: > the maximum possible ICV length in a MACsec frame is 16 octects, not 32: > fix get_icvlen() accordingly, so that a proper error message is displayed > in case input 'icvlen' is greater than 16. > > Signed-off-by: Davide Caratti

Re: [PATCH net] net_sched: act_mirred: full rcu conversion

On 16-09-08 10:26 PM, Cong Wang wrote: > On Thu, Sep 8, 2016 at 8:51 AM, Eric Dumazet wrote: >> On Thu, 2016-09-08 at 08:47 -0700, John Fastabend wrote: >> >>> Works for me. FWIW I find this plenty straightforward and don't really >>> see the need to make the hash table

Re: [PATCH net-next V7 4/4] net/sched: Introduce act_tunnel_key

On 16-09-09 06:19 AM, Eric Dumazet wrote: > On Thu, 2016-09-08 at 22:30 -0700, Cong Wang wrote: >> On Thu, Sep 8, 2016 at 9:15 AM, John Fastabend >> wrote: >>> >>> This should be rtnl_derefence(t->params) and drop the read_lock/unlock >>> pair. This is always called

Re: [RFC Patch net-next 5/6] net_sched: use rcu in fast path

On 16-09-08 10:54 PM, Cong Wang wrote: > On Thu, Sep 8, 2016 at 8:49 AM, John Fastabend > wrote: >> Agreed not sure why you would ever want to do a late binding and >> replace on a tc_mirred actions. But it is supported... > > I will let Jamal teach you on this, /me is

Re: [PATCH net-next v5] gso: Support partial splitting at the frag_list pointer

On Fri, Sep 9, 2016 at 12:25 AM, Steffen Klassert wrote: > Since commit 8a29111c7 ("net: gro: allow to build full sized skb") > gro may build buffers with a frag_list. This can hurt forwarding > because most NICs can't offload such packets, they need to be >

Re: [PATCH RFC 00/11] mlx5 RX refactoring and XDP support

On Wed, Sep 7, 2016 at 3:42 PM, Saeed Mahameed wrote: > Hi All, > > This patch set introduces some important data path RX refactoring > addressing mlx5e memory allocation/management improvements and XDP support. > > Submitting as RFC since we would like to get an early

Re: [iovisor-dev] README: [PATCH RFC 11/11] net/mlx5e: XDP TX xmit more

On Fri, Sep 9, 2016 at 6:22 AM, Alexei Starovoitov via iovisor-dev wrote: > On Thu, Sep 08, 2016 at 10:11:47AM +0200, Jesper Dangaard Brouer wrote: >> >> I'm sorry but I have a problem with this patch! > > is it because the variable is called 'xdp_doorbell'? >

  1   2   >