[dpdk-dev] [PATCH v2] net/iavf: fix vertor interrupt number configuration error

There is a issue when iavf do vertor interrupt configuration, it will miss one interrupt vector which set admin queue interrupt when communicate with host PF. The AVF driver needs to send an extra vector number to the Linux PF to work around an issue with interrupt vector mapping. The admin queue n

Re: [dpdk-dev] [PATCH v2] drivers/virtio: fix duplicate naming of include guard

On Thu, Mar 21, 2019 at 10:09:53AM +, Andrius Sirvys wrote: > "The macro name '_VHOST_NET_USER_H' of this include guard is used > in 2 different header files." > > lib/librte_vhost/vhost_user.h has the same include guard. > Renamed the include guard in vhost.h to differentiate. > > Fixes: 6a8

[dpdk-dev] [PATCH v3] app/testpmd: fix support of hex string parser for flow API

There is need for users to set configuration of HEX number for RSS key. The key byte should be pass down as hex number not as char string. This patch enable cmdline flow parse HEX number, in order to not using string which pass ASIC number. Fixes: f4d623f96119 ("app/testpmd: fix missing RSS fields

[dpdk-dev] [PATCH v2] net/i40e: add warning info when no perfect RSS key

There need a warning info when no perfect RSS key is config, so i40e will use default key. Fixes: ecad87d22383 ("net/i40e: move RSS to flow API") Cc: sta...@dpdk.org Signed-off-by: Wei Zhao Tested-by: Peng Yuan --- v2: --update dev info message --- drivers/net/i40e/i40e_ethdev.c | 1 + 1 fil

[dpdk-dev] [PATCH v5 7/8] net/ice: support Rx scatter AVX2 vector

Signed-off-by: Wenzhuo Lu --- drivers/net/ice/ice_rxtx.c | 10 -- drivers/net/ice/ice_rxtx.h | 3 ++ drivers/net/ice/ice_rxtx_vec_avx2.c | 64 + 3 files changed, 74 insertions(+), 3 deletions(-) diff --git a/drivers/net/ice/ice_rxtx.c b/

[dpdk-dev] [PATCH v5 6/8] net/ice: support Rx AVX2 vector

Signed-off-by: Wenzhuo Lu --- drivers/net/ice/Makefile| 19 ++ drivers/net/ice/ice_rxtx.c | 16 +- drivers/net/ice/ice_rxtx.h | 2 + drivers/net/ice/ice_rxtx_vec_avx2.c | 622 drivers/net/ice/meson.build | 15 + 5 fil

[dpdk-dev] [PATCH v5 8/8] net/ice: support vector AVX2 in TX

Signed-off-by: Wenzhuo Lu --- doc/guides/nics/ice.rst| 18 doc/guides/rel_notes/release_19_05.rst | 4 + drivers/net/ice/ice_rxtx.c | 13 ++- drivers/net/ice/ice_rxtx.h | 2 + drivers/net/ice/ice_rxtx_vec_avx2.c| 158 +

[dpdk-dev] [PATCH v5 4/8] net/ice: support Rx scatter SSE vector

Signed-off-by: Wenzhuo Lu --- drivers/net/ice/ice_rxtx.c | 16 +++ drivers/net/ice/ice_rxtx.h | 2 ++ drivers/net/ice/ice_rxtx_vec_sse.c | 41 ++ 3 files changed, 55 insertions(+), 4 deletions(-) diff --git a/drivers/net/ice/ice_rx

[dpdk-dev] [PATCH v5 5/8] net/ice: support Tx SSE vector

Signed-off-by: Wenzhuo Lu --- doc/guides/nics/features/ice_vec.ini | 2 + drivers/net/ice/ice_rxtx.c| 17 + drivers/net/ice/ice_rxtx.h| 4 + drivers/net/ice/ice_rxtx_vec_common.h | 133 + drivers/net/ice/ice_rxtx_vec_sse.c| 135

[dpdk-dev] [PATCH v5 1/8] net/ice: fix Tx function setting

The TX setting functions is not called. Fixes: 17c7d0f9d6a4 ("net/ice: support basic Rx/Tx") Cc: sta...@dpdk.org Signed-off-by: Wenzhuo Lu --- drivers/net/ice/ice_ethdev.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/net/ice/ice_ethdev.c b/drivers/net/ice/ice_ethdev.c index a23c6

[dpdk-dev] [PATCH v5 3/8] net/ice: support vector SSE in RX

Signed-off-by: Wenzhuo Lu --- doc/guides/nics/features/ice_vec.ini | 33 +++ drivers/net/ice/Makefile | 3 + drivers/net/ice/ice_ethdev.c | 2 - drivers/net/ice/ice_ethdev.h | 2 + drivers/net/ice/ice_rxtx.c| 27 +- drivers/net/ice/ice_rxtx.h

[dpdk-dev] [PATCH v5 2/8] net/ice: add pointer for queue buffer release

Add function pointers of buffer releasing for RX and TX queues, for vector functions will be added for RX and TX. Signed-off-by: Wenzhuo Lu --- drivers/net/ice/ice_rxtx.c | 24 +++- drivers/net/ice/ice_rxtx.h | 5 + 2 files changed, 20 insertions(+), 9 deletions(-) diff

[dpdk-dev] [PATCH v5 0/8] Support vector instructions on ICE

Use SSE and AVX2 instructions in ICE RX and TX path. --- v2: - Updated feature doc. - Fixed checklog and checkpatch issues. v3: - Fixed potential compile issue on non-X86 platform. v4: - Removed compile configure, CONFIG_RTE_LIBRTE_ICE_INC_VECTOR. - Fixed checkpatch warnings. - Added more

[dpdk-dev] [PATCH v2] net/i40e: add warning info when no perfect RSS key

There need a warning info when no perfect RSS key is config, so i40e will use default key. Fixes: ecad87d22383 ("net/i40e: move RSS to flow API") Cc: sta...@dpdk.org Signed-off-by: Wei Zhao Tested-by: Peng Yuan --- v2: --update dev info message --- drivers/net/i40e/i40e_ethdev.c | 1 + 1 fil

Re: [dpdk-dev] [PATCH v3 1/5] net/af_xdp: introduce AF XDP PMD driver

On 03/21, Stephen Hemminger wrote: >On Thu, 21 Mar 2019 17:18:41 +0800 >Xiaolong Ye wrote: > >> +if (ret != 0) { >> +RTE_LOG(ERR, AF_XDP, "getsockopt() failed for >> XDP_STATISTICS.\n"); >> +return -1; > >You need to use the new dynamic log type

Re: [dpdk-dev] [PATCH v3 1/5] net/af_xdp: introduce AF XDP PMD driver

On 03/21, Stephen Hemminger wrote: >On Thu, 21 Mar 2019 17:18:41 +0800 >Xiaolong Ye wrote: > >> +for (i = 0; i < rcvd; i++) { >> +const struct xdp_desc *desc; >> +uint64_t addr; >> +uint32_t len; >> +void *pkt; >> + >> +desc = xsk_rin

Re: [dpdk-dev] [PATCH v3 1/5] net/af_xdp: introduce AF XDP PMD driver

On 03/21, Stephen Hemminger wrote: >On Thu, 21 Mar 2019 17:18:41 +0800 >Xiaolong Ye wrote: > >> + >> +static inline int >> +reserve_fill_queue(struct xsk_umem_info *umem, int reserve_size) >> +{ >> +struct xsk_ring_prod *fq = &umem->fq; >> +uint32_t idx; >> +void *addr = NULL; >> +

Re: [dpdk-dev] [PATCH v3 1/5] net/af_xdp: introduce AF XDP PMD driver

On 03/21, Stephen Hemminger wrote: >On Thu, 21 Mar 2019 17:18:41 +0800 >Xiaolong Ye wrote: > >> static void kick_tx(struct pkt_tx_queue *txq) >> +{ >> +struct xsk_umem_info *umem = txq->pair->umem; >> + >> +while (send(xsk_socket__fd(txq->pair->xsk), NULL, >> + 0, MSG_DONT

Re: [dpdk-dev] [PATCH v3 1/5] net/af_xdp: introduce AF XDP PMD driver

On 03/21, Stephen Hemminger wrote: >On Thu, 21 Mar 2019 17:18:41 +0800 >Xiaolong Ye wrote: > >> + >> +if (ret < 0) >> +return -EINVAL; >> + >> +return 0; > >You could propogate kernel errno into DPDK? > return (ret < 0) ? -errno : 0; > Sorry, could you share the advantag

Re: [dpdk-dev] [PATCH v6 1/2] eal/ticketlock: ticket based to improve fairness

Hi Konstantin, > -Original Message- > From: Ananyev, Konstantin > Sent: Wednesday, March 20, 2019 5:47 PM > To: Gavin Hu (Arm Technology China) ; dev@dpdk.org > Cc: nd ; step...@networkplumber.org; > jerin.ja...@caviumnetworks.com; tho...@monjalon.net; Honnappa > Nagarahalli ; Joyce Kong

Re: [dpdk-dev] [PATCH v3 1/5] net/af_xdp: introduce AF XDP PMD driver

On 03/21, Stephen Hemminger wrote: >On Thu, 21 Mar 2019 17:18:41 +0800 >Xiaolong Ye wrote: > >> +if (strnlen(value, IFNAMSIZ) > IFNAMSIZ - 1) { >> +RTE_LOG(ERR, AF_XDP, "Invalid name %s, should be less than " >> +"%u bytes.\n", value, IFNAMSIZ) > >Please don't b

Re: [dpdk-dev] [PATCH v3 1/5] net/af_xdp: introduce AF XDP PMD driver

On 03/21, Stephen Hemminger wrote: >On Thu, 21 Mar 2019 17:18:41 +0800 >Xiaolong Ye wrote: > >> + >> +strlcpy(ifr.ifr_name, if_name, IFNAMSIZ); >> +if (ioctl(sock, SIOCGIFINDEX, &ifr)) >> +goto error; >> + >> +if (ioctl(sock, SIOCGIFHWADDR, &ifr)) >> +goto error

Re: [dpdk-dev] [PATCH v3 1/5] net/af_xdp: introduce AF XDP PMD driver

On 03/21, Stephen Hemminger wrote: >On Thu, 21 Mar 2019 17:18:41 +0800 >Xiaolong Ye wrote: > >> + >> +RTE_PMD_REGISTER_VDEV(eth_af_xdp, pmd_af_xdp_drv); > >The convention in other network drivers is to use net_XXX in the vdev name. >In AF_XDP that would be: > >RTE_PMD_REGISTER_VDEV(net_af_xdp, pmd

Re: [dpdk-dev] [PATCH v4 3/8] net/ice: support vector SSE in RX

Hi Ferruh, > -Original Message- > From: Yigit, Ferruh > Sent: Friday, March 22, 2019 3:02 AM > To: Lu, Wenzhuo ; dev@dpdk.org > Subject: Re: [dpdk-dev] [PATCH v4 3/8] net/ice: support vector SSE in RX > > On 3/21/2019 6:26 AM, Wenzhuo Lu wrote: > > Signed-off-by: Wenzhuo Lu > > <...> >

Re: [dpdk-dev] [PATCH v4 8/8] net/ice: support vector AVX2 in TX

Hi Ferruh, > -Original Message- > From: Yigit, Ferruh > Sent: Friday, March 22, 2019 3:20 AM > To: Lu, Wenzhuo ; dev@dpdk.org > Subject: Re: [dpdk-dev] [PATCH v4 8/8] net/ice: support vector AVX2 in TX > > On 3/21/2019 6:26 AM, Wenzhuo Lu wrote: > > Signed-off-by: Wenzhuo Lu > > --- > >

Re: [dpdk-dev] [PATCH] app/testpmd: fix support of hex string parser for flow API

Hi, Konstantin > -Original Message- > From: Ananyev, Konstantin > Sent: Thursday, March 21, 2019 10:04 PM > To: Zhao1, Wei ; dev@dpdk.org > Cc: sta...@dpdk.org; Zhang, Qi Z ; > adrien.mazarg...@6wind.com > Subject: RE: [dpdk-dev] [PATCH] app/testpmd: fix support of hex string > parser for

Re: [dpdk-dev] [PATCH] app/testpmd: fix support of hex string parser for flow API

Hi, Stephen Hemminger > -Original Message- > From: Stephen Hemminger [mailto:step...@networkplumber.org] > Sent: Monday, March 18, 2019 11:27 PM > To: Zhao1, Wei > Cc: dev@dpdk.org; sta...@dpdk.org; Zhang, Qi Z ; > adrien.mazarg...@6wind.com > Subject: Re: [dpdk-dev] [PATCH] app/testpmd:

Re: [dpdk-dev] [PATCH] net/i40e: add warning info when no perfect RSS key

> -Original Message- > From: Kevin Traynor [mailto:ktray...@redhat.com] > Sent: Wednesday, March 20, 2019 8:21 PM > To: Zhao1, Wei ; dev@dpdk.org > Cc: Peng, Yuan ; sta...@dpdk.org; Zhang, Qi Z > > Subject: Re: [dpdk-dev] [PATCH] net/i40e: add warning info when no perfect > RSS key > >

[dpdk-dev] [PATCH] rte_ring: add newline to error message

Log message should end with newline. Fixes: 4e32101f9b01 ("ring: support freeing") Signed-off-by: Stephen Hemminger --- lib/librte_ring/rte_ring.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/lib/librte_ring/rte_ring.c b/lib/librte_ring/rte_ring.c index d215aceccf46..615

Re: [dpdk-dev] [PATCH v3 4/4] app/testpmd: display/clear forwarding stats on demand

On Thu, Mar 21, 2019 at 7:50 PM Ferruh Yigit wrote: > On 3/20/2019 10:02 AM, David Marchand wrote: > > Add a new "show/clear fwd stats all" command to display fwd and port > > statistics on the fly. > > > > To be able to do so, the (testpmd only) rte_port structure can't be used > > to maintain a

[dpdk-dev] [PATCH 2/2] net/bonding: fix oob access in "other" aggregator modes

From: Zhaohui slave aggregator_port_id is in [0, RTE_MAX_ETHPORTS-1] range. If RTE_MAX_ETHPORTS is > 8, we can hit out of bound accesses on agg_bandwidth[] and agg_count[] arrays. Fixes: 6d72657ce379 ("net/bonding: add other aggregator modes") Cc: sta...@dpdk.org Signed-off-by: Zhaohui Signed-

[dpdk-dev] [PATCH 1/2] net/bonding: fix more incorrect slave id types

From: Zhaohui mode_bond_id and mode_band_id are slave ids, stored on 16bits. Fixes: f8244c6399d9 ("ethdev: increase port id range") Cc: sta...@dpdk.org Signed-off-by: Zhaohui Signed-off-by: David Marchand --- drivers/net/bonding/rte_eth_bond_8023ad.c | 11 +-- 1 file changed, 5 inser

Re: [dpdk-dev] [PATCH 0/5] bonding fixes

On Thu, Mar 21, 2019 at 9:12 PM Ferruh Yigit wrote: > On 3/20/2019 11:47 AM, David Marchand wrote: > > Here is a first series of fixes on the bonding driver I caught while > > reviewing its code. > > > > For series, > Reviewed-by: Ferruh Yigit > > Series applied to dpdk-next-net/master, thanks.

[dpdk-dev] [PATCH] mem: don't use address hint for mapping unless requested

patch[1] added an address hint as starting address for 64 bit systems in case an explicit base virtual address was not set by the user. The justification for such hint was to help devices that work in VA mode and has a address range limitation to work smoothly with the eal memory subsystem. While

Re: [dpdk-dev] [PATCH 0/5] bonding fixes

On 3/20/2019 11:47 AM, David Marchand wrote: > Here is a first series of fixes on the bonding driver I caught while > reviewing its code. > For series, Reviewed-by: Ferruh Yigit Series applied to dpdk-next-net/master, thanks.

[dpdk-dev] [PATCH] rte_reciprocal: make arg to rte_reciprocal_divide_u64 const

The divisor is not modified here. Doesn't really matter for optimizaton since the function is inline already; but helps with expressing intent. Signed-off-by: Stephen Hemminger --- lib/librte_eal/common/include/rte_reciprocal.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/

Re: [dpdk-dev] [dpdk-stable] [PATCH] net/cxgbe: fix missing csum ol_flags and ptype

On 3/20/2019 11:48 AM, Rahul Lakkireddy wrote: > From: Vishal Kulkarni > > Checksum good offload flags are not being set and some of the > packet type flags are missing on received packets. So, rework > Rx path to set proper ol_flags and packet_type in mbufs. > > Fixes: 78fc1a716ae8 ("cxgbe: imp

Re: [dpdk-dev] [PATCH] net/cxgbe: remove unused code in Rx path

On 3/20/2019 11:49 AM, Rahul Lakkireddy wrote: > From: Vishal Kulkarni > > All Rx packet handling is done in process_responses() and hence > t4_ethrx_handler() never gets called. So, remove it. > > Signed-off-by: Vishal Kulkarni > Signed-off-by: Rahul Lakkireddy Applied to dpdk-next-net/maste

Re: [dpdk-dev] [PATCH 1/3] rte_ethdev: Add API function to read dev clock

On 3/20/2019 3:57 PM, Andrew Rybchenko wrote: > On 3/20/19 5:48 PM, Thomas Monjalon wrote: >> 19/03/2019 14:32, Yigit, Ferruh: >>> On 1/8/2019 11:30 AM, Tom Barbette wrote: Ferruh Yigit wrote: > Why timestamp offloading become useless? When timestamp offloading > enabled, > device

Re: [dpdk-dev] [PATCH v2] net/bonding: fix lacp negotiation failed

On 3/21/2019 10:22 AM, Liang Zhang wrote: > When monitor(port-mirroring) traffic from other lacp port-channel, > rx_machine_update may recieving other lacp negotiation packets. > Thus bond mode 4 will negotiation failed. > > Fixes: 112891cd27e5 ("net/bonding: add dedicated HW queues for LACP contr

Re: [dpdk-dev] [PATCH v4 8/8] net/ice: support vector AVX2 in TX

On 3/21/2019 6:26 AM, Wenzhuo Lu wrote: > Signed-off-by: Wenzhuo Lu > --- > doc/guides/nics/ice.rst| 17 > doc/guides/rel_notes/release_19_05.rst | 4 + > drivers/net/ice/ice_rxtx.c | 13 ++- > drivers/net/ice/ice_rxtx.h | 2 + > drivers/net/ice/

Re: [dpdk-dev] [PATCH 01/14] net/mlx5: add representor recognition on kernels 5.x

On Thu, 21 Mar 2019 15:31:36 + Slava Ovsiienko wrote: > Hi, Stephen > > > -Original Message- > > From: Stephen Hemminger > > Sent: Thursday, March 21, 2019 17:09 > > To: Shahaf Shuler > > Cc: Slava Ovsiienko ; dev@dpdk.org > > Subject: Re: [dpdk-dev] [PATCH 01/14] net/mlx5: add rep

Re: [dpdk-dev] [PATCH v4 3/8] net/ice: support vector SSE in RX

On 3/21/2019 6:26 AM, Wenzhuo Lu wrote: > Signed-off-by: Wenzhuo Lu <...> > @@ -11,3 +11,8 @@ sources = files( > > deps += ['hash'] > includes += include_directories('base') > + > +if arch_subdir == 'x86' > + dpdk_conf.set('RTE_LIBRTE_ICE_RX_ALLOW_BULK_ALLOC', 1) Setting this config opt

Re: [dpdk-dev] [PATCH v3] ethdev: check for invalid device name

On 3/15/2019 1:13 AM, Zhang, Qi Z wrote: > > >> -Original Message- >> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Stephen Hemminger >> Sent: Friday, March 15, 2019 12:21 AM >> To: dev@dpdk.org >> Cc: Stephen Hemminger >> Subject: [dpdk-dev] [PATCH v3] ethdev: check for invalid d

Re: [dpdk-dev] [PATCH v3 4/4] app/testpmd: display/clear forwarding stats on demand

On 3/20/2019 10:02 AM, David Marchand wrote: > Add a new "show/clear fwd stats all" command to display fwd and port > statistics on the fly. > > To be able to do so, the (testpmd only) rte_port structure can't be used > to maintain any statistics. > Moved the stats dump parts from stop_packet_forw

Re: [dpdk-dev] [PATCH v4 3/3] test/rwlock: amortize the cost of getting time

> > Instead of getting timestamp per iteration, amortize its > overhead can help to get more precise benchmarking results. > > Fixes: af75078fece3 ("first public release") > Cc: sta...@dpdk.org > > Signed-off-by: Joyce Kong > Reviewed-by: Gavin Hu > Reviewed-by: Ola Liljedahl > Reviewed-by

Re: [dpdk-dev] [PATCH v4 1/3] rwlock: reimplement with atomic builtins

> -Original Message- > From: Joyce Kong [mailto:joyce.k...@arm.com] > Sent: Wednesday, March 20, 2019 6:25 AM > To: dev@dpdk.org > Cc: n...@arm.com; jer...@marvell.com; Ananyev, Konstantin > ; chao...@linux.vnet.ibm.com; Richardson, > Bruce ; tho...@monjalon.net; > hemant.agra...@nxp.c

Re: [dpdk-dev] [PATCH v4 2/3] test/rwlock: add perf test case on all available cores

> > Add performance test on all available cores to benchmark > the scaling up performance of rwlock. > > Fixes: af75078fece3 ("first public release") > Cc: sta...@dpdk.org > > Suggested-by: Gavin Hu > Signed-off-by: Joyce Kong > -- Acked-by: Konstantin Ananyev > 2.7.4

Re: [dpdk-dev] [dpdk-stable] [PATCH] net/sfc: fix speed capabilities reported in device info

On 3/19/2019 4:36 PM, Andrew Rybchenko wrote: > Phy capabilities are bit offsets in libefx, but was used as bit masks. > > Fixes: d23f3a89ab54 ("net/sfc: support link speed and duplex settings") > Fixes: f82e33afbbb9 ("net/sfc: support link speeds up to 100G") > Cc: sta...@dpdk.org > > Signed-off

Re: [dpdk-dev] [PATCH] net/dpaa2: accept packets with checksum error

On 3/19/2019 1:10 PM, Shreyansh Jain wrote: > Until now, DPAA2 driver was configured to drop any packet which > was marked as malformed by hardware - which included those with > wrong checksum. > With this patch, that configuration has been removed - hereafter, > all packets arriving on a DPMAC lin

Re: [dpdk-dev] [dpdk-stable] [PATCH v7] net/tap: fix missing _SC_IOV_MAX

On 3/18/2019 6:20 PM, olegpoly123 wrote: > If the value _SC_IOV_MAX is missing, sysconf returns -1. > In this case, iov_max is set to a default value of 1024. > This should never happen except for redhat bug: >https://bugzilla.redhat.com/show_bug.cgi?id=1504165 > > Fixes: ec12df9504fe ("net/ta

Re: [dpdk-dev] [PATCH v2 1/2] app/testpmd: fix tx vlan and qinq dependency

On 3/18/2019 9:56 AM, Nithin Kumar Dabilpuram wrote: > Tx VLAN & QinQ insert enable need not depend on > Rx VLAN offload ETH_VLAN_EXTEND_OFFLOAD. > > Fixes: 6a34f91690d0 ("app/testpmd: fix error message when setting Tx VLAN") > Cc: xiao.w.w...@intel.com > > Signed-off-by: Nithin Dabilpuram <...

Re: [dpdk-dev] [dpdk-stable] [PATCH v2] net/nfp: fix possible buffer overflow

On 3/21/2019 10:10 AM, Alejandro Lucero wrote: > > > On Tue, Mar 19, 2019 at 5:43 PM Ferruh Yigit > wrote: > > On 3/12/2019 9:56 AM, Alejandro Lucero wrote: > > On Fri, Mar 8, 2019 at 10:28 AM Pallantla Poornima < > > pallantlax.poorn...@intel.com

Re: [dpdk-dev] [PATCH v6 1/1] ci: Introduce travis builds for github repositories

On 3/20/19 5:11 PM, Luca Boccassi wrote: On Wed, 2019-03-20 at 15:28 -0400, Michael Santana Francisco wrote: +matrix: + include: + - env: DEF_LIB="static" OPTS="-Denable_kmods=false" AARCH64=1 +compiler: gcc +addons: + apt: +packages: + - [libnuma-dev, linux-heade

Re: [dpdk-dev] [PATCH v3 1/5] net/af_xdp: introduce AF XDP PMD driver

On Thu, 21 Mar 2019 17:18:41 +0800 Xiaolong Ye wrote: > + > +RTE_PMD_REGISTER_VDEV(eth_af_xdp, pmd_af_xdp_drv); The convention in other network drivers is to use net_XXX in the vdev name. In AF_XDP that would be: RTE_PMD_REGISTER_VDEV(net_af_xdp, pmd_af_xdp_drv); About naming, I would just dro

Re: [dpdk-dev] [PATCH v3 1/5] net/af_xdp: introduce AF XDP PMD driver

On Thu, 21 Mar 2019 17:18:41 +0800 Xiaolong Ye wrote: > + > + strlcpy(ifr.ifr_name, if_name, IFNAMSIZ); > + if (ioctl(sock, SIOCGIFINDEX, &ifr)) > + goto error; > + > + if (ioctl(sock, SIOCGIFHWADDR, &ifr)) > + goto error; > + > + rte_memcpy(eth_addr, ifr.i

Re: [dpdk-dev] [PATCH 01/14] net/mlx5: add representor recognition on kernels 5.x

Hi, Stephen > -Original Message- > From: Stephen Hemminger > Sent: Thursday, March 21, 2019 17:09 > To: Shahaf Shuler > Cc: Slava Ovsiienko ; dev@dpdk.org > Subject: Re: [dpdk-dev] [PATCH 01/14] net/mlx5: add representor recognition > on kernels 5.x > > On Thu, 21 Mar 2019 12:13:50 +000

Re: [dpdk-dev] [PATCH v3 1/5] net/af_xdp: introduce AF XDP PMD driver

On Thu, 21 Mar 2019 17:18:41 +0800 Xiaolong Ye wrote: > + if (strnlen(value, IFNAMSIZ) > IFNAMSIZ - 1) { > + RTE_LOG(ERR, AF_XDP, "Invalid name %s, should be less than " > + "%u bytes.\n", value, IFNAMSIZ) Please don't break error message strings across multip

Re: [dpdk-dev] [PATCH v3 1/5] net/af_xdp: introduce AF XDP PMD driver

On Thu, 21 Mar 2019 17:18:41 +0800 Xiaolong Ye wrote: > + > + if (ret < 0) > + return -EINVAL; > + > + return 0; You could propogate kernel errno into DPDK? return (ret < 0) ? -errno : 0;

Re: [dpdk-dev] [PATCH v3 1/5] net/af_xdp: introduce AF XDP PMD driver

On Thu, 21 Mar 2019 17:18:41 +0800 Xiaolong Ye wrote: > + if (ret != 0) { > + RTE_LOG(ERR, AF_XDP, "getsockopt() failed for > XDP_STATISTICS.\n"); > + return -1; You need to use the new dynamic log types and not have a global logtype.

Re: [dpdk-dev] [PATCH v3 1/5] net/af_xdp: introduce AF XDP PMD driver

On Thu, 21 Mar 2019 17:18:41 +0800 Xiaolong Ye wrote: > static void kick_tx(struct pkt_tx_queue *txq) > +{ > + struct xsk_umem_info *umem = txq->pair->umem; > + > + while (send(xsk_socket__fd(txq->pair->xsk), NULL, > + 0, MSG_DONTWAIT) < 0) { > + /* some thin

Re: [dpdk-dev] [PATCH v3 1/5] net/af_xdp: introduce AF XDP PMD driver

On Thu, 21 Mar 2019 17:18:41 +0800 Xiaolong Ye wrote: > + for (i = 0; i < rcvd; i++) { > + const struct xdp_desc *desc; > + uint64_t addr; > + uint32_t len; > + void *pkt; > + > + desc = xsk_ring_cons__rx_desc(rx, idx_rx++); > +

Re: [dpdk-dev] [PATCH v3 1/5] net/af_xdp: introduce AF XDP PMD driver

On Thu, 21 Mar 2019 17:18:41 +0800 Xiaolong Ye wrote: > + > +static inline int > +reserve_fill_queue(struct xsk_umem_info *umem, int reserve_size) > +{ > + struct xsk_ring_prod *fq = &umem->fq; > + uint32_t idx; > + void *addr = NULL; > + int i, ret; > + > + ret = xsk_ring_pro

Re: [dpdk-dev] [PATCH 01/14] net/mlx5: add representor recognition on kernels 5.x

On Thu, 21 Mar 2019 12:13:50 + Shahaf Shuler wrote: > Hi Slava, > > Small comments below. Once fixed you can put my acked-by on the next version. > > Thursday, March 21, 2019 10:11 AM, Viacheslav Ovsiienko: > > Subject: [PATCH 01/14] net/mlx5: add representor recognition on kernels 5.x > >

Re: [dpdk-dev] [PATCH v1 1/6] ethdev: add min/max MTU to device info

On 3/21/2019 2:06 PM, Ferruh Yigit wrote: On 3/21/2019 12:50 PM, Ian Stokes wrote: On 3/19/2019 4:15 PM, Ferruh Yigit wrote: On 2/27/2019 9:45 PM, Ian Stokes wrote: From: Stephen Hemminger This addresses the usability issue raised by OVS at DPDK Userspace summit. It adds general min/max mtu

Re: [dpdk-dev] [PATCH v3 3/5] lib/mempool: allow page size aligned mempool

> -Original Message- > From: Ananyev, Konstantin > Sent: Thursday, March 21, 2019 10:01 PM > To: Ye, Xiaolong ; dev@dpdk.org > Cc: Zhang, Qi Z ; Karlsson, Magnus > ; Topel, Bjorn ; Ye, > Xiaolong > Subject: RE: [dpdk-dev] [PATCH v3 3/5] lib/mempool: allow page size aligned > mempool >

[dpdk-dev] [PATCH 3/3] net/mlx5: update modify header using Direct Verbs

This patch implements additional actions of packet header modifications. Add actions: - INC_TCP_SEQ - Increase sequence number in the outermost TCP header. - DEC_TCP_SEQ - Decrease sequence number in the outermost TCP header. - INC_TCP_ACK - Increase acknowledgment number in the outermost TCP

[dpdk-dev] [PATCH 1/3] ethdev: add actions to modify TCP header fields

Add actions: - INC_TCP_SEQ - Increase sequence number in the outermost TCP header. - DEC_TCP_SEQ - Decrease sequence number in the outermost TCP header. - INC_TCP_ACK - Increase acknowledgment number in the outermost TCP header. - DEC_TCP_ACK - Decrease acknowledgment number in the

[dpdk-dev] [PATCH 2/3] app/testpmd: add actions to modify TCP header fields

Add actions: - INC_TCP_SEQ - Increase sequence number in the outermost TCP header. - DEC_TCP_SEQ - Decrease sequence number in the outermost TCP header. - INC_TCP_ACK - Increase acknowledgment number in the outermost TCP header. - DEC_TCP_ACK - Decrease acknowledgment number in the

[dpdk-dev] [PATCH 0/3] add actions to modify header fields

Patch [1] implemented set of header modification actions in MLX PMD, based on ethdev and testpmd updates included in [2]. This series implements support of additional header modification actions, in ethdev, testpmd, and MLX5 PMD. Original work by Xiaoyu Min. [1] http://patches.dpdk.org/patch/493

Re: [dpdk-dev] [PATCH 05/10] net/virtio: refactor virtqueue structure

On 3/20/19 6:50 PM, Stephen Hemminger wrote: On Wed, 20 Mar 2019 12:40:26 +0800 Tiwei Bie wrote: I agree the vq_ prefix is not needed and I think the code is more readable in general seeing the packed/split name when using the struct. Please also consider that cosmetic changes in multiple

Re: [dpdk-dev] [RFC] net/virtio: remove prefix from virtqueue struct fields

On 3/21/19 3:02 PM, Jens Freimann wrote: On Thu, Mar 21, 2019 at 02:45:20PM +0100, Maxime Coquelin wrote: Most of 'virtqueue' struct fields are prefixed with 'vq_'. This redundant, this patch removes them all. Signed-off-by: Maxime Coquelin --- Hi, Following our discussions on removing the

Re: [dpdk-dev] [PATCH 14/14] net/mlx5: add source vport match to the ingress rules

> -Original Message- > From: Shahaf Shuler > Sent: Thursday, March 21, 2019 14:15 > To: Slava Ovsiienko ; dev@dpdk.org > Subject: RE: [PATCH 14/14] net/mlx5: add source vport match to the ingress > rules > > Thursday, March 21, 2019 10:11 AM, Viacheslav Ovsiienko: > > Subject: [PATCH 14/14

Re: [dpdk-dev] [PATCH 13/14] net/mlx5: update event handler for multiport IB devices

> -Original Message- > From: Shahaf Shuler > Sent: Thursday, March 21, 2019 14:15 > To: Slava Ovsiienko ; dev@dpdk.org > Subject: RE: [PATCH 13/14] net/mlx5: update event handler for multiport IB > devices > > Thursday, March 21, 2019 10:11 AM, Viacheslav Ovsiienko: > > Subject: [PATCH 13/

Re: [dpdk-dev] [PATCH v1 1/6] ethdev: add min/max MTU to device info

On 3/21/2019 12:50 PM, Ian Stokes wrote: > On 3/19/2019 4:15 PM, Ferruh Yigit wrote: >> On 2/27/2019 9:45 PM, Ian Stokes wrote: >>> From: Stephen Hemminger >>> >>> This addresses the usability issue raised by OVS at DPDK Userspace >>> summit. It adds general min/max mtu into device info. For compa

Re: [dpdk-dev] [PATCH] app/testpmd: fix support of hex string parser for flow API

Hi Wei, > > > > > > > > There is need for users to set configuration of HEX number for RSS > > > key. The key byte should be pass down as hex number not as char > > > string. This patch enable cmdline flow parse HEX number, in order to > > > not using string which pass ASIC number. > > > > > > F

Re: [dpdk-dev] [PATCH 12/14] net/mlx5: update install/uninstall int handler routines

> -Original Message- > From: Shahaf Shuler > Sent: Thursday, March 21, 2019 14:15 > To: Slava Ovsiienko ; dev@dpdk.org > Subject: RE: [PATCH 12/14] net/mlx5: update install/uninstall int handler > routines > > Thursday, March 21, 2019 10:11 AM, Viacheslav Ovsiienko: > > Subject: [PATCH 12/

Re: [dpdk-dev] [RFC] net/virtio: remove prefix from virtqueue struct fields

On Thu, Mar 21, 2019 at 02:45:20PM +0100, Maxime Coquelin wrote: Most of 'virtqueue' struct fields are prefixed with 'vq_'. This redundant, this patch removes them all. Signed-off-by: Maxime Coquelin --- Hi, Following our discussions on removing the 'vq_' prefix, I did the patch to see how it

Re: [dpdk-dev] [PATCH v3 3/5] lib/mempool: allow page size aligned mempool

> -Original Message- > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Xiaolong Ye > Sent: Thursday, March 21, 2019 9:19 AM > To: dev@dpdk.org > Cc: Zhang, Qi Z ; Karlsson, Magnus > ; Topel, Bjorn ; Ye, > Xiaolong > Subject: [dpdk-dev] [PATCH v3 3/5] lib/mempool: allow page size a

Re: [dpdk-dev] [PATCH v2 1/7] mbuf: new function to generate raw Tx offload value

Hi Shahaf, > Hi Konstantin, > > Wednesday, March 20, 2019 8:47 PM, Konstantin Ananyev: > > Subject: [dpdk-dev] [PATCH v2 1/7] mbuf: new function to generate raw Tx > > offload value > > > > Operations to set/update bit-fields often cause compilers to generate > > suboptimal code. > > To help avoi

[dpdk-dev] [RFC] net/virtio: remove prefix from virtqueue struct fields

Most of 'virtqueue' struct fields are prefixed with 'vq_'. This redundant, this patch removes them all. Signed-off-by: Maxime Coquelin --- Hi, Following our discussions on removing the 'vq_' prefix, I did the patch to see how it would look like. It looks like it does not prevent any lines to be

Re: [dpdk-dev] [PATCH v1 0/6] ethdev: add min/max MTU to device info

On 3/19/2019 4:30 PM, Ferruh Yigit wrote: On 2/27/2019 9:45 PM, Ian Stokes wrote: Building upon the discussion around [1], this series introduces MTU min and MTU max variables. It also provides updates to PMD implementations for ixgbe, i40e and IGB devices so that these variables are populated f

Re: [dpdk-dev] [PATCH 05/14] net/mlx5: add multiport IB device support to probing

Sorry, missed some comments. Here is my extra answers. > -Original Message- > From: Slava Ovsiienko > Sent: Thursday, March 21, 2019 14:54 > To: Shahaf Shuler ; dev@dpdk.org > Subject: RE: [PATCH 05/14] net/mlx5: add multiport IB device support to > probing > > > -Original Message

Re: [dpdk-dev] [PATCH 00/14] net/mlx5: add support for multiport IB devices

Hi, Shahaf, My special thanks for immediate review. PSB. With best regards, Slava > -Original Message- > From: Shahaf Shuler > Sent: Thursday, March 21, 2019 14:14 > To: Slava Ovsiienko ; dev@dpdk.org > Subject: RE: [PATCH 00/14] net/mlx5: add support for multiport IB devices > > Thursd

Re: [dpdk-dev] [PATCH 03/14] net/mlx5: modify get ifindex routine for multiport IB

> -Original Message- > From: Shahaf Shuler > Sent: Thursday, March 21, 2019 14:14 > To: Slava Ovsiienko ; dev@dpdk.org > Subject: RE: [PATCH 03/14] net/mlx5: modify get ifindex routine for multiport > IB > > Thursday, March 21, 2019 10:11 AM, Viacheslav Ovsiienko: > > Subject: [PATCH 03/14

Re: [dpdk-dev] [PATCH v1 2/6] net/i40e: set min and max MTU for i40e devices

On 3/19/2019 4:18 PM, Ferruh Yigit wrote: On 2/27/2019 9:45 PM, Ian Stokes wrote: This commit sets the min and max supported MTU values for i40e devices via the i40e_dev_info_get() function. Min MTU supported is set to ETHER_MIN_MTU and max mtu is calculated as the max packet length supported mi

Re: [dpdk-dev] [PATCH 05/14] net/mlx5: add multiport IB device support to probing

> -Original Message- > From: Shahaf Shuler > Sent: Thursday, March 21, 2019 14:15 > To: Slava Ovsiienko ; dev@dpdk.org > Subject: RE: [PATCH 05/14] net/mlx5: add multiport IB device support to > probing > > Thursday, March 21, 2019 10:11 AM, Viacheslav Ovsiienko: > > Subject: [PATCH 05/14]

Re: [dpdk-dev] [PATCH v1 1/6] ethdev: add min/max MTU to device info

On 3/19/2019 4:15 PM, Ferruh Yigit wrote: On 2/27/2019 9:45 PM, Ian Stokes wrote: From: Stephen Hemminger This addresses the usability issue raised by OVS at DPDK Userspace summit. It adds general min/max mtu into device info. For compatiablity, and to save space, it fits in a hole in existing

[dpdk-dev] DPDK Release Status Meeting 21/3/2019

Minutes 21 March 2019 - Agenda: * Release Dates * Subtrees * OvS * Coverity * Opens Participants: * Arm * Debian * Intel * Mellanox * RedHat Release Dates - * v19.05 dates, no change: * RC1: Friday, 29 March * Release: Friday, 10 May * Schedule web page

Re: [dpdk-dev] [PATCH 14/14] net/mlx5: add source vport match to the ingress rules

Thursday, March 21, 2019 10:11 AM, Viacheslav Ovsiienko: > Subject: [PATCH 14/14] net/mlx5: add source vport match to the ingress rules > > For E-Switch configurations over multiport Infiniband devices we should add > source vport match to correctly distribute traffic between representors. > > Si

Re: [dpdk-dev] [PATCH 13/14] net/mlx5: update event handler for multiport IB devices

Thursday, March 21, 2019 10:11 AM, Viacheslav Ovsiienko: > Subject: [PATCH 13/14] net/mlx5: update event handler for multiport IB > devices > > This patch modifies asynchronous event handler to support multiport > Infiniband devices. Handler queries the event parameters, including event > source p

Re: [dpdk-dev] [PATCH 12/14] net/mlx5: update install/uninstall int handler routines

Thursday, March 21, 2019 10:11 AM, Viacheslav Ovsiienko: > Subject: [PATCH 12/14] net/mlx5: update install/uninstall int handler routines > > We are implementing the support for multport Infiniband device withj > representors attached to these multiple ports. Asynchronous device event > notificati

Re: [dpdk-dev] [PATCH 11/14] net/mlx5: provide IB port for the object being created

Thursday, March 21, 2019 10:11 AM, Viacheslav Ovsiienko: > Subject: [PATCH 11/14] net/mlx5: provide IB port for the object being > created > > The code is updated to provide IB port index for the Verbs objects being > created - QP and Verbs Flows. > > Signed-off-by: Viacheslav Ovsiienko Acked-b

Re: [dpdk-dev] [PATCH 07/14] net/mlx5: switch to the names in the shared IB context

Thursday, March 21, 2019 10:11 AM, Viacheslav Ovsiienko: > Subject: [PATCH 07/14] net/mlx5: switch to the names in the shared IB > context > > The IB device names are moved from device private data to the shared > context, code involving the names is updated. > The IB port index treatment is added

Re: [dpdk-dev] [PATCH 08/14] net/mlx5: switch to the shared Protection Domain

Thursday, March 21, 2019 10:11 AM, Viacheslav Ovsiienko: > Subject: [PATCH 08/14] net/mlx5: switch to the shared Protection Domain > > The PMD code is updated to use Protected Domain from the the shared IB > device context. The Domain is shared between all devices belonging to the > same multiport

Re: [dpdk-dev] [PATCH 10/14] net/mlx5: switch to the shared IB device context

Thursday, March 21, 2019 10:11 AM, Viacheslav Ovsiienko: > Subject: [PATCH 10/14] net/mlx5: switch to the shared IB device context > > The code is updated to use the shared IB device context and device handles. > The IB device context is shared between reprentors created over the single > multipor

Re: [dpdk-dev] [PATCH 09/14] net/mlx5: switch to the shared context IB attributes

Thursday, March 21, 2019 10:11 AM, Viacheslav Ovsiienko: > Subject: [PATCH 09/14] net/mlx5: switch to the shared context IB attributes > > The code is updated to use the shared IB device attributes, located in the > shared IB context. It saves some memory if there are representors created > over t

Re: [dpdk-dev] [PATCH 06/14] net/mlx5: add IB shared context alloc/free functions

Thursday, March 21, 2019 10:11 AM, Viacheslav Ovsiienko: > Subject: [dpdk-dev] [PATCH 06/14] net/mlx5: add IB shared context > alloc/free functions > > The functions to allocate and free shared IB context for multiport is added. > The IB device context, Protection Domain, device attributes, Infini

Re: [dpdk-dev] [PATCH 01/14] net/mlx5: add representor recognition on kernels 5.x

Hi Slava, Small comments below. Once fixed you can put my acked-by on the next version. Thursday, March 21, 2019 10:11 AM, Viacheslav Ovsiienko: > Subject: [PATCH 01/14] net/mlx5: add representor recognition on kernels 5.x > > The master device and VF representors were distinguished by presence

Re: [dpdk-dev] [PATCH 04/14] net/mlx5: add getting IB ports number for multiport IB

Thursday, March 21, 2019 10:11 AM, Viacheslav Ovsiienko: > Subject: [dpdk-dev] [PATCH 04/14] net/mlx5: add getting IB ports number > for multiport IB > > There is the routine mlx5_nl_portnum() added to get the number of ports of > multiport Infiniband device. > It is assumed the Uplink/VF represen

  1   2   >