Re: [dpdk-dev] [PATCH] net/mlx4: fix Tx doorbell register unmap

Monday, April 8, 2019 9:23 PM, Yongseok Koh: > Subject: [dpdk-dev] [PATCH] net/mlx4: fix Tx doorbell register unmap > > If rdma-core library doesn't support remapping UAR registers, the register > shouldn't be unmapped on device stop. > > Fixes: 0203d33a1059 ("net/mlx4: support secondary process"

Re: [dpdk-dev] [PATCH] net/mlx5: fix cross compilation on aarch64

Monday, April 8, 2019 3:43 PM, Ori Kam: > Subject: [PATCH] net/mlx5: fix cross compilation on aarch64 > > In case of cross compilation on aarch64 we must add include for stdlib in > order to use the free function. > > Fixes: cbb66daa3c85 ("net/mlx5: prepare Direct Verbs for Direct Rule") > > Si

Re: [dpdk-dev] [PATCH v4 0/4] net/mlx: remove device register remap

Wednesday, April 10, 2019 2:13 AM, Yongseok Koh: > Subject: [PATCH v4 0/4] net/mlx: remove device register remap > > This patchset lifts the requirement of reserving huge virtual address space > and remapping device UAR register on to it in order to use the same address > between primary and secon

[dpdk-dev] [PATCH v7 13/14] raw/ifpga_rawdev: using prefix name for feature and its ops

From: Tianfei zhang Using prefix name "ifpga_" for feature and feature_ops data struct on ifpga base code, which is suggested by Yigit, Ferruh. Signed-off-by: Tianfei Zhang --- drivers/raw/ifpga_rawdev/base/ifpga_enumerate.c | 8 +-- drivers/raw/ifpga_rawdev/base/ifpga_feature_dev.c | 4 +-

[dpdk-dev] [PATCH v7 14/14] raw/ifpga_rawdev: add IPN3KE support for IFPGA Rawdev

Add Intel FPGA Acceleration NIC IPN3KE support for IFPGA Rawdev. Signed-off-by: Rosen Xu Signed-off-by: Tianfei Zhang Signed-off-by: Andy Pei --- drivers/raw/ifpga_rawdev/Makefile | 1 + drivers/raw/ifpga_rawdev/ifpga_rawdev.c | 248 +++- drivers/raw/ifpga_r

[dpdk-dev] [PATCH v7 12/14] raw/ifpga_rawdev: add version description on README

From: Tianfei zhang add verion description on READ about ifpga base code. Signed-off-by: Tianfei Zhang --- drivers/raw/ifpga_rawdev/base/README | 15 +++ 1 file changed, 15 insertions(+) diff --git a/drivers/raw/ifpga_rawdev/base/README b/drivers/raw/ifpga_rawdev/base/README inde

[dpdk-dev] [PATCH v7 11/14] raw/ifpga_rawdev: add eth group driver

From: Tianfei zhang There is two eth group devices in PAC N3000 card, each eth group include PHY device and MAC device. Exposing APIs for DPDK PMD driver to access those devices. Signed-off-by: Tianfei Zhang --- drivers/raw/ifpga_rawdev/base/Makefile| 1 + drivers/raw/ifpga_rawde

[dpdk-dev] [PATCH v7 10/14] raw/ifpga_rawdev: add I2C and at24 EEPROM driver

From: Tianfei zhang 1. Add Altera I2C master device driver 2. Add at24 eeprom driver which is i2c slave device 3. Introducing a new ops for opae_manager: opae_manager_networking_ops. This ops will include some networking operation by FPGA, like vBNG operation, MAC ROM operation and so on. Signed

[dpdk-dev] [PATCH v7 08/14] raw/ifpga_rawdev: store private features in FME and Port

From: Tianfei zhang Get private features attrubite like size, id, address after enumeration, and insert into FEM or Port dedicate list. when initial the private feature driver, we just compare the private feature id between the list and feature drivers array to match the proper drivers. This pa

[dpdk-dev] [PATCH v7 09/14] raw/ifpga_rawdev: add SPI and MAX10 device driver

From: Tianfei zhang There is a SPI bus link between A10 FPGA and MAX10 FPGA. MAX10 is in charge of board management, like power management, sensors, flash devices. Signed-off-by: Tianfei Zhang --- drivers/raw/ifpga_rawdev/base/Makefile | 3 + drivers/raw/ifpga_rawdev/base/ifpga_d

[dpdk-dev] [PATCH v7 07/14] raw/ifpga_rawdev: clean up code for ifpga share code

From: Tianfei zhang clean up code: 1. use opae_memcpy instead of memcpy 2. use opae_memset instead of memset 3. disable opae_adapter_dump by default Signed-off-by: Tianfei Zhang --- drivers/raw/ifpga_rawdev/base/ifpga_api.c | 2 +- drivers/raw/ifpga_rawdev/base/ifpga_feature_dev

[dpdk-dev] [PATCH v7 06/14] net/ipn3ke: add IPN3KE Flow of PMD driver

Add Intel FPGA Acceleration NIC IPN3KE Flow of PMD driver. Signed-off-by: Rosen Xu Signed-off-by: Andy Pei Signed-off-by: Dan Wei --- drivers/net/ipn3ke/Makefile |1 + drivers/net/ipn3ke/ipn3ke_ethdev.c |5 + drivers/net/ipn3ke/ipn3ke_ethdev.h |1 + drivers/ne

[dpdk-dev] [PATCH v7 03/14] net/ipn3ke: add IPN3KE ethdev PMD driver

Add Intel FPGA Acceleration NIC IPN3KE ethdev PMD driver. Signed-off-by: Rosen Xu Signed-off-by: Andy Pei Signed-off-by: Dan Wei --- MAINTAINERS | 6 + config/common_base| 4 + doc/guides/nics/features/ipn3ke.ini | 55

[dpdk-dev] [PATCH v7 04/14] net/ipn3ke: add IPN3KE representor of PMD driver

Add Intel FPGA Acceleration NIC IPN3KE representor of PMD driver. Signed-off-by: Rosen Xu Signed-off-by: Andy Pei Signed-off-by: Dan Wei --- drivers/net/ipn3ke/Makefile | 2 + drivers/net/ipn3ke/ipn3ke_ethdev.c | 4 +- drivers/net/ipn3ke/ipn3ke_ethdev.h | 25 + drive

[dpdk-dev] [PATCH v7 05/14] net/ipn3ke: add IPN3KE TM of PMD driver

Add Intel FPGA Acceleration NIC IPN3KE TM of PMD driver. Signed-off-by: Rosen Xu Signed-off-by: Andy Pei Signed-off-by: Dan Wei --- drivers/net/ipn3ke/Makefile |1 + drivers/net/ipn3ke/ipn3ke_ethdev.c |3 + drivers/net/ipn3ke/ipn3ke_ethdev.h |7 + drivers/net/

[dpdk-dev] [PATCH v7 01/14] bus/ifpga: add AFU shared data

AFU can be implemented into many different acceleration devices, these devices need shared data to store private information when they are handled by users. Signed-off-by: Rosen Xu Signed-off-by: Andy Pei --- drivers/bus/ifpga/rte_bus_ifpga.h | 7 +++ 1 file changed, 7 insertions(+) diff -

[dpdk-dev] [PATCH v7 00/14] Add patch set for IPN3KE

v7 updates: = - Fix Stephen comments v6 updates: == - Fix v5 comments - Fix TM Shaper rate issue v5 updates: == - Fix EXPERIMENTAL symbol definition issue v4 updates: == - Fix coding style issues v3 updates: == - Fix v2 comments - Update MAC BAR of

[dpdk-dev] [PATCH v7 02/14] bus/ifpga: add function for AFU search by name

In many scenarios, AFU is needed searched by name, this function add the feature. Signed-off-by: Rosen Xu Signed-off-by: Andy Pei --- drivers/bus/ifpga/ifpga_bus.c | 13 + drivers/bus/ifpga/rte_bus_ifpga.h | 9 + drivers/bus/ifpga/rte_bus_ifpga_versi

[dpdk-dev] 答复: [PATCH] lib/librte_kni: fix the type for mac address

Hi, Ferruh Sure, what you said is ok. Re-fix have upload at following link. https://patches.dpdk.org/patch/52526/ It generate another patchwork, is that OK? I am not sure about this, I have used --in-reply-to option when "git send-email". Thanks. Jie. -邮件原件- 发件人: Yigit, Ferruh 发送时间:

[dpdk-dev] [PATCH v2] kni: fix the type for MAC address

The type for MAC address should be unsigned. Fixes: 1cfe212ed17a ("kni: support MAC address change") Cc: sta...@dpdk.org Signed-off-by: Jie Pan --- kernel/linux/kni/kni_misc.c | 2 +- lib/librte_eal/linux/eal/include/rte_kni_common.h | 2 +- lib/librte_kni/rte_kni.h

Re: [dpdk-dev] [PATCH v6 03/14] net/ipn3ke: add IPN3KE ethdev PMD driver

> -Original Message- > From: Stephen Hemminger [mailto:step...@networkplumber.org] > Sent: Tuesday, April 09, 2019 23:19 > To: Xu, Rosen > Cc: dev@dpdk.org; Yigit, Ferruh ; Zhang, Tianfei > ; Wei, Dan ; Pei, Andy > ; Yang, Qiming ; Wang, > Haiyue ; Chen, Santos ; > Zhang, Zhang ; Lomarti

[dpdk-dev] [PATCH] net/enic: fix VLAN inner type matching for older hardware

The vlan pattern handler currently assumes the NIC always strips vlan header from the L2 buffer, regardless of the vlan strip setting. But, with older VIC models, the vlan header is actually present in the L2 buffer if stripping is disabled. So in this case, the inner ether type needs to be shifted

Re: [dpdk-dev] i40e rte_eth_link_get_nowait() on X722 returns wrong link_speed value 20000 instead of 10000

> -Original Message- > From: Martin Weiser [mailto:martin.wei...@allegro-packets.com] > Sent: Tuesday, April 9, 2019 7:21 PM > To: Xing, Beilei ; Zhang, Qi Z ; > dev@dpdk.org > Subject: Re: [dpdk-dev] i40e rte_eth_link_get_nowait() on X722 returns > wrong link_speed value 2 instead of

Re: [dpdk-dev] DPDK ABI/API Stability

> > Hi folks, > > Recently I started a discussion with the DPDK Technical Board on DPDK > ABI/API stability. This was born out informal feedback I had received from > a number of users of DPDK about ABI churn. In turn this feedback then > prompted an ABI analysis of DPDK using tools from abi-labo

Re: [dpdk-dev] [PATCH v1] net/virtio-user: fix return value check

Fix unchecked return value for fcntl. Coverity issue: 277210 Fixes: bd8f50a45d0f ("net/virtio-user: support server mode") Cc: sta...@dpdk.org Signed-off-by: Chenbo Xia --- Acked-by: Rami Rosen

Re: [dpdk-dev] [PATCH v1] app/testpmd: fix return value check

Fix unchecked return value issue for rte_eth_dev_configure. Coverity issue: 195021 Fixes: 2a977b891f99 ("app/testpmd: fix DCB configuration") Cc: sta...@dpdk.org Signed-off-by: Chenbo Xia --- Acked-by:

[dpdk-dev] [PATCH v1] app/testpmd: fix return value check

Fix unchecked return value issue for rte_eth_dev_configure. Coverity issue: 195021 Fixes: 2a977b891f99 ("app/testpmd: fix DCB configuration") Cc: sta...@dpdk.org Signed-off-by: Chenbo Xia --- app/test-pmd/testpmd.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/app/tes

[dpdk-dev] [PATCH v1] net/virtio-user: fix return value check

Fix unchecked return value for fcntl. Coverity issue: 277210 Fixes: bd8f50a45d0f ("net/virtio-user: support server mode") Cc: sta...@dpdk.org Signed-off-by: Chenbo Xia --- drivers/net/virtio/virtio_user/vhost_user.c | 5 - 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/drivers

Re: [dpdk-dev] [RFC 10/12] ethdev: add cast for bus_device

On Tue, 09 Apr 2019 22:14:08 +0200 Thomas Monjalon wrote: > 09/04/2019 21:06, Vivian Kong: > > Signed-off-by: Vivian Kong > > --- > > static inline int > > eth_dev_pci_specific_init(struct rte_eth_dev *eth_dev, void *bus_device) { > > - struct rte_pci_device *pci_dev = bus_device; > > + st

Re: [dpdk-dev] [PATCH v7 2/4] meson: add infra to support machine specific flags

> On Apr 9, 2019, at 5:40 PM, Yongseok Koh wrote: > >> >> On Apr 6, 2019, at 7:27 AM, jerinjac...@gmail.com wrote: >> >> From: Pavan Nikhilesh >> >> Currently, RTE_* flags are set based on the implementer ID but there might >> be some micro arch specific differences from the same vendor >>

Re: [dpdk-dev] [PATCH v2] app/testpmd: fix ether header size calculation

> -Original Message- > From: Yigit, Ferruh > Sent: Wednesday, April 10, 2019 4:59 AM > To: Pavan Nikhilesh Bhagavatula ; Jerin Jacob > Kollanukkaran ; Lin, Xueqin ; > Richardson, Bruce ; tho...@monjalon.net > Cc: dev@dpdk.org; Yao, Lei A ; Wang, FengqinX > > Subject: Re: [dpdk-dev] [PATC

Re: [dpdk-dev] [PATCH v7 2/4] meson: add infra to support machine specific flags

> On Apr 6, 2019, at 7:27 AM, jerinjac...@gmail.com wrote: > > From: Pavan Nikhilesh > > Currently, RTE_* flags are set based on the implementer ID but there might > be some micro arch specific differences from the same vendor > eg. CACHE_LINESIZE. Add support to set micro arch specific flags.

[dpdk-dev] [PATCH v4 4/4] net/mlx4: remove device register remap

UAR (User Access Region) register does not need to be remapped for primary process but it should be remapped only for secondary process. UAR register table is in the process private structure in rte_eth_devices[], (struct mlx4_proc_priv *)rte_eth_devices[port_id].process_private The actual

[dpdk-dev] [PATCH v4 3/4] net/mlx5: remove device register remap

UAR (User Access Region) register does not need to be remapped for primary process but it should be remapped only for secondary process. UAR register table is in the process private structure in rte_eth_devices[], (struct mlx5_proc_priv *)rte_eth_devices[port_id].process_private The actual

[dpdk-dev] [PATCH v4 1/4] net/mlx5: fix recursive inclusion of header file

mlx5.h includes mlx5_rxtx.h and mlx5_rxtx.h includes mlx5.h recursively. Signed-off-by: Yongseok Koh Acked-by: Shahaf Shuler --- drivers/net/mlx5/mlx5.h| 1 - drivers/net/mlx5/mlx5_flow.c | 5 +++-- drivers/net/mlx5/mlx5_flow_dv.c| 4 +++- drivers/net/mlx5/mlx5_flow_verbs.

[dpdk-dev] [PATCH v4 2/4] net/mlx5: remove redundant queue index

Queue index is redundantly stored for both Rx and Tx structures. E.g. txq_ctrl->idx and txq->stats.idx. Both are consolidated to single storage - rxq->idx and txq->idx. Also, rxq and txq are moved to the beginning of its control structure (rxq_ctrl and txq_ctrl) for cacheline alignment. Signed-of

[dpdk-dev] [PATCH v4 0/4] net/mlx: remove device register remap

This patchset lifts the requirement of reserving huge virtual address space and remapping device UAR register on to it in order to use the same address between primary and secondary process. v4: * add mlx4_proc_priv_[init|uninit]() to avoid duplicate code * remove the number of Rx queues from the

[dpdk-dev] [PATCH] examples/multi_process: fix buffer underrun

For client_server_mp, the total number of buffers for the mbuf mempool should be correctly calculated. Otherwise, having more clients will stop traffic. Fixes: af75078fece3 ("first public release") Cc: sta...@dpdk.org Signed-off-by: Yongseok Koh --- examples/multi_process/client_server_mp/mp_se

Re: [dpdk-dev] [PATCH v2 1/2] mbuf: fix big endian build

> > Compilation was failing when using a big endian toolchain: > > rte_mbuf.h:504:2: error: expected ',' or '}' before 'RTE_MBUF_L3_LEN_OFS' > > Fixes: 8d9c2c3a1f01 ("mbuf: add function to generate raw Tx offload value") > Cc: konstantin.anan...@intel.com > > Signed-off-by: Thomas Monjalon

Re: [dpdk-dev] [PATCH v2] app/testpmd: fix ether header size calculation

On 4/9/2019 10:45 AM, Pavan Nikhilesh Bhagavatula wrote: > From: Pavan Nikhilesh > > Fix ether header size calculation in Tx only mode. > > Coverity issue: 337684 > Fixes: 01b645dcff7f ("app/testpmd: move txonly prepare in separate function") > > Signed-off-by: Pavan Nikhilesh Reviewed-by: Fe

Re: [dpdk-dev] [PATCH] kni: implement header_ops parse method

On 4/8/2019 5:59 PM, Igor Ryzhov wrote: > Hi Ferruh, > > Can we proceed with this patch? > > Igor > > On Thu, Jan 24, 2019 at 9:05 PM Igor Ryzhov > wrote: > > Hi Ferruh, > > Ok, no problem. Generally, it is needed for all applications using > packet(7) >

Re: [dpdk-dev] [RFC 00/12] introduce s390x architecture

09/04/2019 21:06, Vivian Kong: > To build and run DPDK on Linux on IBM Z (s390x), big endian support > is added and s390x vector intrinics are used in the implementation > of DPDK libraries. > > I appreciate your feedback. I understand you worked on it during some time and you reveal it just now

Re: [dpdk-dev] [RFC 10/12] ethdev: add cast for bus_device

09/04/2019 21:06, Vivian Kong: > Signed-off-by: Vivian Kong > --- > static inline int > eth_dev_pci_specific_init(struct rte_eth_dev *eth_dev, void *bus_device) { > - struct rte_pci_device *pci_dev = bus_device; > + struct rte_pci_device *pci_dev = (struct rte_pci_device *) bus_device;

Re: [dpdk-dev] [RFC 11/12] mbuf: trivial fix

09/04/2019 21:06, Vivian Kong: > --- a/lib/librte_mbuf/rte_mbuf.h > +++ b/lib/librte_mbuf/rte_mbuf.h > @@ -500,7 +500,7 @@ enum { > RTE_MBUF_OUTL2_LEN_BITS, > #if RTE_BYTE_ORDER == RTE_BIG_ENDIAN > RTE_MBUF_L2_LEN_OFS = > - sizeof(uint64_t) * CHAR_BIT - RTE_MBUF_L2_

Re: [dpdk-dev] [RFC 09/12] doc: introduce s390x architecture

09/04/2019 21:06, Vivian Kong: > --- a/MAINTAINERS > +++ b/MAINTAINERS > +Linux on IBM Z (s390x) What is specific to Linux? If it's supported only with Linux, better to say it in the doc than in the MAINTAINERS file. > +M: Vivian Kong Your email above is wrong. > --- a/doc/guides/rel_notes/re

[dpdk-dev] [PATCH v2 0/2] fix big endian build

There are at least 4 issues when compiling with a big endian toolchain. 2 of them are fixed in this patchset. The remaining ones are in ice and bnxt PMDs. About ice, the error is: drivers/net/ice/base/ice_flex_pipe.c:302:8: error: ‘state.entry_idx’ may be used uninitialized in this functio

[dpdk-dev] [PATCH v2 2/2] net/enetc: fix big endian build

Compilation was failing when using a big endian toolchain: drivers/net/enetc/enetc_rxtx.c:92:21: error: passing argument 1 of 'rte_constant_bswap64' makes integer from pointer without a cast Fixes: 469c6111a799 ("net/enetc: enable Rx and Tx") Cc: g.si...@nxp.com Cc: sta...@dpdk.or

[dpdk-dev] [PATCH v2 1/2] mbuf: fix big endian build

Compilation was failing when using a big endian toolchain: rte_mbuf.h:504:2: error: expected ',' or '}' before 'RTE_MBUF_L3_LEN_OFS' Fixes: 8d9c2c3a1f01 ("mbuf: add function to generate raw Tx offload value") Cc: konstantin.anan...@intel.com Signed-off-by: Thomas Monjalon --- lib/librte_mbuf/r

[dpdk-dev] [PATCH 1/2] mbuf: fix big endian build

Compilation was failing when using a big endian toolchain: rte_mbuf.h:504:2: error: expected ‘,’ or ‘}’ before ‘RTE_MBUF_L3_LEN_OFS’ Fixes: 8d9c2c3a1f01 ("mbuf: add function to generate raw Tx offload value") Cc: konstantin.anan...@intel.com Signed-off-by: Thomas Monjalon --- lib/librte_mbuf/r

[dpdk-dev] [PATCH 0/2] fix big endian build

There are at least 4 issues when compiling with a big endian toolchain. 2 of them are fixed in this patchset. The remaining ones are in ice and bnxt PMDs. About ice, the error is: drivers/net/ice/base/ice_flex_pipe.c:302:8: error: ‘state.entry_idx’ may be used uninitialized in this functio

[dpdk-dev] [PATCH 2/2] net/enetc: fix big endian build

Compilation was failing when using a big endian toolchain: drivers/net/enetc/enetc_rxtx.c:92:21: error: passing argument 1 of ‘rte_constant_bswap64’ makes integer from pointer without a cast Fixes: 469c6111a799 ("net/enetc: enable Rx and Tx") Cc: g.si...@nxp.com Cc: sta...@dpdk.or

Re: [dpdk-dev] [PATCH] lib/librte_kni: fix the type for mac address

On 1/24/2019 3:53 AM, Jie Pan wrote: > The type for mac address in struct rte_kni_conf should be unsigned. > > Signed-off-by: Jie Pan > --- > lib/librte_kni/rte_kni.h | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > diff --git a/lib/librte_kni/rte_kni.h b/lib/librte_kni/rte_kni.h > i

Re: [dpdk-dev] [RFC 01/12] mk: introduce s390x architecture

On Tue, 2019-04-09 at 15:06 -0400, Vivian Kong wrote: > Add config and mk files to build DPDK on Linux on IBM Z (s390x). > > Signed-off-by: Vivian Kong < > vivk...@ca.ibm.com > > > --- > config/defconfig_s390x-native-linux-gcc| 1 + > config/defconfig_s390x-native-linuxapp-gcc | 33 > +++

Re: [dpdk-dev] [PATCH v3 3/4] net/mlx5: remove device register remap

> On Apr 7, 2019, at 10:48 PM, Shahaf Shuler wrote: > > Hi Koh, > > See small comments below. Same for mlx4 patch. > > > Friday, April 5, 2019 4:34 AM, Yongseok Koh: >> Subject: [dpdk-dev] [PATCH v3 3/4] net/mlx5: remove device register remap >> >> UAR (User Access Region) register does not

[dpdk-dev] [PATCH v2] drivers: dpaa: fix 'bman_pool' leak in dpaa_mbuf_create_pool

When 'rte_zmalloc' failed dpaa_mbuf_create_pool() forgets freeing 'bp' thus leading resource leak. This patch avoids this. Spotted by Coverity: CID 337679 Signed-off-by: Li Qiang --- drivers/mempool/dpaa/dpaa_mempool.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drive

[dpdk-dev] [PATCH] drivers: dpaa: fix 'bman_pool' leak in dpaa_mbuf_create_pool

When 'rte_zmalloc' failed dpaa_mbuf_create_pool() forgets freeing 'bp' thus leading resource leak. This patch avoids this. Spotted by Coverity: CID 337679 Signed-off-by: Li Qiang --- drivers/mempool/dpaa/dpaa_mempool.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drive

Re: [dpdk-dev] [PATCH] drivers: dpaa: fix 'bman_pool' leak in dpaa_mbuf_create_pool

Sorry this patch has an error, please see the v2. Thanks, Li Qiang Li Qiang 于2019年4月9日周二 下午10:33写道： > When 'rte_zmalloc' failed dpaa_mbuf_create_pool() forgets freeing > 'bp' thus leading resource leak. This patch avoids this. > > Spotted by Coverity: CID 337679 > > Signed-off-by: Li Qiang > -

[dpdk-dev] [PATCH] drivers: ifpga_rawdev: fix fd leak in rte_fpga_do_pr

In rte_fpga_do_pr() function, if 'stat' return error the 'file_fd' is never closed thus leading a fd leak. This patch avoids this. Spotted by Coverity: CID 27441 Signed-off-by: Li Qiang --- drivers/raw/ifpga_rawdev/ifpga_rawdev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git

[dpdk-dev] [RFC 12/12] test: miscellaneous test fixes

Minor test case fixes. Signed-off-by: Vivian Kong --- app/test/autotest_data.py | 2 +- app/test/test_cmdline.c | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/app/test/autotest_data.py b/app/test/autotest_data.py index db2527489..72c56e528 100644 --- a/app/test/auto

[dpdk-dev] [RFC 10/12] ethdev: add cast for bus_device

Signed-off-by: Vivian Kong --- lib/librte_ethdev/rte_ethdev_pci.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/librte_ethdev/rte_ethdev_pci.h b/lib/librte_ethdev/rte_ethdev_pci.h index 23257e986..80bd120b9 100644 --- a/lib/librte_ethdev/rte_ethdev_pci.h +++ b/lib/librt

[dpdk-dev] [RFC 11/12] mbuf: trivial fix

Signed-off-by: Vivian Kong --- lib/librte_mbuf/rte_mbuf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h index f7886dcb3..7dd2e7fb3 100644 --- a/lib/librte_mbuf/rte_mbuf.h +++ b/lib/librte_mbuf/rte_mbuf.h @@ -500,7 +500,

[dpdk-dev] [RFC 08/12] hash: add support for s390x architecture

Add big endian support for s390x architecture. Signed-off-by: Vivian Kong --- lib/librte_hash/rte_fbk_hash.h | 7 +++ 1 file changed, 7 insertions(+) diff --git a/lib/librte_hash/rte_fbk_hash.h b/lib/librte_hash/rte_fbk_hash.h index c4d6976d2..5e49950a7 100644 --- a/lib/librte_hash/rte_fbk_

[dpdk-dev] [RFC 09/12] doc: introduce s390x architecture

Signed-off-by: Vivian Kong --- MAINTAINERS| 9 + doc/guides/rel_notes/release_19_05.rst | 3 +++ 2 files changed, 12 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 9774344dd..6d4c51215 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -248,6 +248,15 @@

[dpdk-dev] [RFC 07/12] test: add support for s390x architecture

Add big endian support for s390x architecture. Signed-off-by: Vivian Kong --- app/test/test_cmdline_ipaddr.c | 13 +++- app/test/test_cmdline_num.c| 111 + app/test/test_xmmt_ops.h | 14 + 3 files changed, 137 insertions(+), 1 deletion(-) diff --g

[dpdk-dev] [RFC 05/12] examples/l3fwd: add support for s390x architecture

Add s390x specific implementation. Signed-off-by: Vivian Kong --- examples/l3fwd/l3fwd_em.c| 8 + examples/l3fwd/l3fwd_lpm_s390x.h | 137 examples/l3fwd/l3fwd_s390x.h | 259 +++ 3 files changed, 404 insertions(+) create mode 100644 exam

[dpdk-dev] [RFC 06/12] net/i40e: add support for s390x architecture

Enable i40e and i40e vector support on s390x. Signed-off-by: Vivian Kong --- doc/guides/nics/features/i40e.ini | 1 + doc/guides/nics/features/i40e_vec.ini | 1 + drivers/net/i40e/Makefile | 2 + drivers/net/i40e/i40e_rxtx_vec_s390x.c | 631 + 4 f

[dpdk-dev] [RFC 03/12] acl: add support for s390x architecture

Add big endian support for s390x architecture. Signed-off-by: Vivian Kong --- app/test-acl/main.c | 4 ++ lib/librte_acl/Makefile | 2 + lib/librte_acl/acl_bld.c| 69 +++-- lib/librte_acl/acl_gen.c| 9 + lib/librte_acl/acl_ru

[dpdk-dev] [RFC 04/12] lpm: add support for s390x architecture

Add big endian support for s390x architecture. Signed-off-by: Vivian Kong --- lib/librte_lpm/Makefile| 2 + lib/librte_lpm/meson.build | 2 +- lib/librte_lpm/rte_lpm.h | 2 + lib/librte_lpm/rte_lpm6.c | 26 ++- lib/librte_lpm/rte_lpm_s390x.h | 130 ++

[dpdk-dev] [RFC 02/12] eal: add support for s390x architecture

Implement DPDK EAL for s390x architecture. Signed-off-by: Vivian Kong --- .../common/arch/s390x/rte_cpuflags.c | 90 +++ lib/librte_eal/common/arch/s390x/rte_cycles.c | 11 +++ .../common/arch/s390x/rte_hypervisor.c| 11 +++ .../common/include/arch/s390x/rte_atom

[dpdk-dev] [RFC 01/12] mk: introduce s390x architecture

Add config and mk files to build DPDK on Linux on IBM Z (s390x). Signed-off-by: Vivian Kong --- config/defconfig_s390x-native-linux-gcc| 1 + config/defconfig_s390x-native-linuxapp-gcc | 33 ++ mk/arch/s390x/rte.vars.mk | 16 +++ mk/rte.cpuflags.

[dpdk-dev] [RFC 00/12] introduce s390x architecture

To build and run DPDK on Linux on IBM Z (s390x), big endian support is added and s390x vector intrinics are used in the implementation of DPDK libraries. I appreciate your feedback. Vivian Kong (12): mk: introduce s390x architecture eal: add support for s390x architecture acl: add support

Re: [dpdk-dev] [PATCH] app/testpmd: fix crash when doing port info of vdev

On Fri, 15 Feb 2019 17:36:46 -0800 Stephen Hemminger wrote: > From: Stephen Hemminger > > Noticed a SEGV in testpmd doing: > > show port info 1 > on Hyper-V with failsafe/tap PMD. > > A vdev may not have an associated device (i.e NULL) and therefore > testpmd should skip devargs in that cas

Re: [dpdk-dev] [PATCH 3/3] acl: adjust the tests

> > > > > > Hi Aaron, > > > > > > > >> > > > >> This makes the tests pass, and also ensures that on platforms where > > > >> the testing is supported, we can properly test the implementation > > > >> specific code. One edge case is when we run on x86_64 systems that > > > >> don't support AVX2,

[dpdk-dev] [PATCH v5 1/3] app/testpmd: add ability to set Tx IP and UDP parameters

This patch changes what testpmd uses as IP addresses when run in transmit only mode. The old code was using 192.168.0.1 -> 192.168.0.2 but these addresses are reserved for private Internet by RFC 1918. The new code uses 192.18.0.1 and 192.18.0.2 which are on the subnet reserved for performance tes

[dpdk-dev] [PATCH v5 3/3] examples/l3fwd: format the IP addresses for printing

The IP addresses should be formatted using standard routines rather than outputing in raw hex. Signed-off-by: Stephen Hemminger Acked-by: Bernard Iremonger --- examples/l3fwd/l3fwd_lpm.c | 15 ++- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/examples/l3fwd/l3fwd_l

[dpdk-dev] [PATCH v5 2/3] examples/l3fwd: use reserved IPv4/IPv6 addresses

The l3fwd example should use the IPv4 addresses defined in RFC5735 and the IPv6 addresses defined in RFC5180 for the L3 forwarding example Longest Prefix Match table. Signed-off-by: Stephen Hemminger --- examples/l3fwd/l3fwd_lpm.c | 34 ++ 1 file changed, 18 inser

[dpdk-dev] [PATCH v5 0/3] use RFC addresses in test applications

These patches get rid of the custom addresses used in testpmd and l3fwd, and instead uses values that are in the existing RFC's. v5 -- rebase to 19.05-rc1 and fix reword commit message Stephen Hemminger (3): app/testpmd: add ability to set Tx IP and UDP parameters examples/l3fwd: use reserved

Re: [dpdk-dev] [PATCH] kni: fix build for ndo_fdb_add in Linux 5.1

On Mon, Apr 08, 2019 at 03:22:26PM +0100, Ferruh Yigit wrote: > Build error seen with Linux kernel 5.1 and > when CONFIG_RTE_KNI_KMOD_ETHTOOL is enabled. > > Build error: > .../dpdk/build/build/kernel/linux/kni/igb_main.c:2352:18: > error: initialization of ... from incompatible pointer type ...

[dpdk-dev] [PATCH] doc: add guideines for initial PMD submission

This patch for DPDK Contributor's Guidelines indicates the repos against which a new PMD should be prepared; for new network ethernet PMDs it should be dpdk-next-net, and for new crypto PMDs it should be dpdk-next-crypto. Though this may seem obvious, it is not mentioned in DPDK documentation. Cc:

Re: [dpdk-dev] [PATCH v4 2/3] examples/l3fwd: use reserved IPv4/IPv6 addresses

On Mon, 8 Apr 2019 13:07:33 + "Iremonger, Bernard" wrote: > Hi Stephen, > > > -Original Message- > > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Stephen Hemminger > > Sent: Tuesday, April 2, 2019 9:39 PM > > To: dev@dpdk.org > > Cc: Stephen Hemminger > > Subject: [dpdk-dev]

Re: [dpdk-dev] [PATCH 3/3] acl: adjust the tests

> -Original Message- > From: Ananyev, Konstantin > Sent: Tuesday, April 9, 2019 5:03 PM > To: Aaron Conole > Cc: dev@dpdk.org; Jerin Jacob ; Gavin Hu > ; Richardson, Bruce ; > Michael Santana > Subject: RE: [PATCH 3/3] acl: adjust the tests > > > > > Hi Aaron, > > > > > >> > > >> Thi

Re: [dpdk-dev] [PATCH 3/3] acl: adjust the tests

> > > > Hi Aaron, > > > > > >> > > >> This makes the tests pass, and also ensures that on platforms where the > > >> testing is supported, we can properly test the implementation specific > > >> code. One edge case is when we run on x86_64 systems that don't support > > >> AVX2, but where the

[dpdk-dev] [Bug 249] kni cause a kernel crash on avx512 supported platform with gcc 8.3.1

https://bugs.dpdk.org/show_bug.cgi?id=249 Bug ID: 249 Summary: kni cause a kernel crash on avx512 supported platform with gcc 8.3.1 Product: DPDK Version: 18.11 Hardware: All OS: All Status: CONF

Re: [dpdk-dev] [PATCH 3/3] acl: adjust the tests

> > Hi Aaron, > > > >> > >> This makes the tests pass, and also ensures that on platforms where the > >> testing is supported, we can properly test the implementation specific > >> code. One edge case is when we run on x86_64 systems that don't support > >> AVX2, but where the compiler can gener

[dpdk-dev] [PATCH] examples/vm_power_manager: fix string null termination

After the read() the jason_data null termination is missing for the case "indent < 0", for "indent > 0" and "indent == 0" cases null termination is already handled. So add the missing case "indent < 0" to the existing "indent == 0" case to fix null termination. Coverity issue: 337680 Fixes: a6350

[dpdk-dev] [PATCH] net/af_xdp: enqueue buf ring when allocate Tx queue fails

When it fails to allocate enough slots in Tx queue for transmitting packets, we need to return the dequeued addrs to buf ring. Fixes: f1debd77efaf ("net/af_xdp: introduce AF_XDP PMD") Signed-off-by: Xiaolong Ye --- drivers/net/af_xdp/rte_eth_af_xdp.c | 1 + 1 file changed, 1 insertion(+) diff

Re: [dpdk-dev] [PATCH v6 03/14] net/ipn3ke: add IPN3KE ethdev PMD driver

Minor nits. > + > + (*rd_data) = rte_le_to_cpu_32(read_data); > + return 0; > +} Paren around *rd_data are unnecessary > + indirect_addrs = (volatile void *)(hw->eth_group_bar[eth_group_sel] + > + 0x10); cast is to void * is unnecesary + return ipn3ke_indirect_rea

Re: [dpdk-dev] [PATCH v2] app/test: replace TEST_SKIPPED with -ENOTSUP

Hi Ayuj, > -Original Message- > From: Ayuj Verma [mailto:ayve...@marvell.com] > Sent: Tuesday, April 9, 2019 12:34 PM > To: akhil.go...@nxp.com; Trahe, Fiona ; Kusztal, > ArkadiuszX > ; De Lara Guarch, Pablo > > Cc: shal...@marvell.com; ss...@marvell.com; kkotamar...@marvell.com; > ade

[dpdk-dev] [PATCH v2] doc/compress: clarify error handling on data-plane

Fixed some typos and clarified which errors should be returned when and why on the enqueue and dequeue APIs. Fixes: a584d3bea902 ("doc: add compressdev library guide") cc: sta...@dpdk.org Signed-off-by: Fiona Trahe --- v2 changes: - changed "0 or undefined" to just "undefined" as 0 is superfluo

Re: [dpdk-dev] [PATCH v2] app/test: replace TEST_SKIPPED with -ENOTSUP

On Tue, Apr 09, 2019 at 05:03:39PM +0530, Ayuj Verma wrote: > Return -ENOTSUP for unsupported tests > I disagree with this, since TEST_SKIPPED is the correct return value for unsupported test conditions IMHO. If part of the current infrastructure doesn't support that return value, I think the infr

Re: [dpdk-dev] [PATCH] net/af_xdp: free mbuf when allocate Tx queue fails

Hi, David On 04/09, David Marchand wrote: >On Tue, Apr 9, 2019 at 10:27 AM Xiaolong Ye wrote: > >> When we fail to allocate enough slots in tx queue for transmitting >> packets, we need to free the corresponding mbufs. >> > >You'd better let the application retry on its own... Make sense. > > >

Re: [dpdk-dev] [Bug 248] Bonding PMD: Invalid array dimension in TX burst for 802.3ad mode with fast queue leads to SEGFAULT

On Tue, Apr 9, 2019 at 4:45 PM wrote: > https://bugs.dpdk.org/show_bug.cgi?id=248 > > Bug ID: 248 >Summary: Bonding PMD: Invalid array dimension in TX burst for > 802.3ad mode with fast queue leads to SEGFAULT >Product: DPDK >Ver

[dpdk-dev] [Bug 248] Bonding PMD: Invalid array dimension in TX burst for 802.3ad mode with fast queue leads to SEGFAULT

https://bugs.dpdk.org/show_bug.cgi?id=248 Bug ID: 248 Summary: Bonding PMD: Invalid array dimension in TX burst for 802.3ad mode with fast queue leads to SEGFAULT Product: DPDK Version: 18.11 Hardware: All O

Re: [dpdk-dev] [PATCH v1] lib/power: fix buffer overrun coverity issues

On 9/4/2019 12:18 PM, Burakov, Anatoly wrote: On 09-Apr-19 10:22 AM, David Hunt wrote: A previous change removed the limit of 64 cores by moving away from 64-bit masks to char arrays. However this left a buffer overrun issue, where the max channels was defined as 64, and max cores was defined

Re: [dpdk-dev] [PATCH] vhost: fix passing destroyed device to destroy callback

On Tue, Apr 09, 2019 at 04:36:22PM +0300, Ilya Maximets wrote: Application should be able to obtain information like 'ifname' from the 'vid' passed to 'destroy_connection' callback. Currently, all the API calls with passed 'vid' fails with 'device not found'. Fixes: efba12a78ddf ("vhost: add use

Re: [dpdk-dev] [PATCH 1/2] crypto/caam_jr: fix the shared desc endianness

> -Original Message- > From: Gagandeep Singh > Sent: Monday, April 8, 2019 2:29 PM > To: dev@dpdk.org; Akhil Goyal > Cc: Gagandeep Singh > Subject: [PATCH 1/2] crypto/caam_jr: fix the shared desc endianness > > build a shared descriptor accordingly if core and > CAAM endianness is sam

Re: [dpdk-dev] [PATCH 2/2] crypto/caam_jr: fix total length in AUTH only sg case

> -Original Message- > From: Gagandeep Singh > Sent: Monday, April 8, 2019 2:30 PM > To: dev@dpdk.org; Akhil Goyal > Cc: Gagandeep Singh > Subject: [PATCH 2/2] crypto/caam_jr: fix total length in AUTH only sg case > > CAAM return wrong digest value in AUTH only sg test case > because

[dpdk-dev] [PATCH] vhost: fix passing destroyed device to destroy callback

Application should be able to obtain information like 'ifname' from the 'vid' passed to 'destroy_connection' callback. Currently, all the API calls with passed 'vid' fails with 'device not found'. Fixes: efba12a78ddf ("vhost: add user callbacks for socket open/close") Cc: sta...@dpdk.org Signed-o

[dpdk-dev] [PATCH v3] app/testbbdev: fix sprintf with snprintf or strlcpy

sprintf function is not secure as it doesn't check the length of string. More secure function snprintf and strlcpy is used. Fixes: f714a18885 ("app/testbbdev: add test application for bbdev") Cc: sta...@dpdk.org Signed-off-by: Pallantla Poornima Acked-by: Amr Mokhtar --- v3: Added Ack. v2: Used

[dpdk-dev] [dpdk-announce] DPDK 18.11.1 released

Hi all, Here is a new stable release: https://fast.dpdk.org/rel/dpdk-18.11.1.tar.xz The git tree is at: https://dpdk.org/browse/dpdk-stable/?h=18.11 Information about validation of the stable release: http://doc.dpdk.org/guides-18.11/rel_notes/release_18_11.html#validatio

  1   2   >