Re: [dpdk-dev] [PATCH 2/2] bus/vdev: fix hotplug twice

On 2/21/19 10:01 PM, Thomas Monjalon wrote: From: Raslan Darawsheh In case vdev was already probed, it shouldn't be probed again, and it should return -EEXIST as error. There are some checks in vdev_probe() and insert_vdev(), but a check was missing in vdev_plug(). The check is moved in vdev_pr

Re: [dpdk-dev] [PATCH] vhost: add virtio configuration space access socket messages

On 2019/2/25 下午3:51, Changpeng Liu wrote: This patch adds new vhost user messages GET_CONFIG and SET_CONFIG used to get/set virtio device's PCI configuration space. I think it's better to describe the reason for doing this. I believe vhost is transport independent. Thanks Signed-off-b

Re: [dpdk-dev] [PATCH 1/2] bus/vdev: fix debug message on probing

On 2/21/19 10:01 PM, Thomas Monjalon wrote: The log was printing the device name two times, first one being supposed to be the driver name. As we don't know yet the driver name, the log is simplified. Fixes: 9bf4901d1a11 ("bus/vdev: remove probe with driver name option") Cc: ferruh.yi...@intel.c

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

On 2/20/19 6:57 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 structure. The initial version sets max mtu

[dpdk-dev] [PATCH] vhost: add virtio configuration space access socket messages

This patch adds new vhost user messages GET_CONFIG and SET_CONFIG used to get/set virtio device's PCI configuration space. Signed-off-by: Changpeng Liu --- lib/librte_vhost/rte_vhost.h | 8 lib/librte_vhost/vhost_user.c | 44 +++ lib/librte_vhos

Re: [dpdk-dev] [PATCH] vhost: fix interrupt suppression for the split ring

On Fri, Feb 22, 2019 at 04:13:50PM +0800, Jiayu Hu wrote: > The VIRTIO_RING_F_EVENT_IDX feature of split ring might > be broken, as the value of signalled_used is unpredictable > after live migration or start up. This patch fixes it by > using signalled_used_valid. Seems you also need to invalidat

Re: [dpdk-dev] [PATCH] net/mlx5: call generic strlcpy

Checked on Fedora 28 Reviewed-by: Rami Rosen On Mon, Feb 25, 2019 at 12:42 AM Thomas Monjalon wrote: > The call to strlcpy uses either libc, libbsd or internal rte_strlcpy. > No need to call the DPDK flavor explictly. > > Signed-off-by: Thomas Monjalon > --- > drivers/net/mlx5/mlx5.c | 2 +-

Re: [dpdk-dev] [PATCH] app/compress-perf: call generic strlcpy

Checked on Fedora 28 Reviewed-by: Rami Rosen On Mon, Feb 25, 2019 at 12:42 AM Thomas Monjalon wrote: > The call to strlcpy uses either libc, libbsd or internal rte_strlcpy. > No need to call the DPDK flavor explictly. > > Signed-off-by: Thomas Monjalon > --- > app/test-compress-perf/comp_per

Re: [dpdk-dev] [PATCH] doc: fix PCI whitelist typo in prog guide

Reviewed-by: Rami Rosen On Mon, Feb 25, 2019 at 12:33 AM Thomas Monjalon wrote: > The placeholder for PCI address should be named DBDF > which stands for Domain/Bus/Device/Function. > > Fixes: 33af337773ac ("ethdev: add common devargs parser") > Cc: remy.hor...@intel.com > Cc: sta...@dpdk.org >

Re: [dpdk-dev] [PATCH] vhost: remove vhost-net requirements from generic vhost APIs

On Mon, Feb 25, 2019 at 12:35:55AM +0100, Dariusz Stojaczyk wrote: > From: Darek Stojaczyk > > The rte_vhost API to put data into virtqueues operates > on mbufs and hence it is strictly vhost-net specific. > External backends need to implement virtqueue handling > from scratch and that's just not

[dpdk-dev] [Bug 213] Fix the problem of KNI device (Net Stack kthread) keeps dropping packets (stats.tx_dropped++) and TX thread logs "KNI: Out of memory"

https://bugs.dpdk.org/show_bug.cgi?id=213 Bug ID: 213 Summary: Fix the problem of KNI device (Net Stack kthread) keeps dropping packets (stats.tx_dropped++) and TX thread logs "KNI: Out of memory" Product: DPDK Ve

Re: [dpdk-dev] RSS hashing support on ixgbevf

Hi, Gareth Bradshaw What you said is not a missing or code bug, because ixgbe do not support vf port to config his own RSS hash type. It is control by his pf host, it has the same hash type enable configuration as his pf host, so we do not need to expose That in vf code by " dev_info->flow_ty

[dpdk-dev] [PATCH] vhost: remove vhost-net requirements from generic vhost APIs

From: Darek Stojaczyk The rte_vhost API to put data into virtqueues operates on mbufs and hence it is strictly vhost-net specific. External backends need to implement virtqueue handling from scratch and that's just not possible without APIs to get/set vring base addresses. Those relevant APIs ar

Re: [dpdk-dev] [PATCH v2] devtools: add git log checks for DCB, TOS and TTL

29/01/2019 14:55, Ferruh Yigit: > Add case check to DCB, TOS and TTL abbreviations. > > Signed-off-by: Ferruh Yigit Applied, thanks

Re: [dpdk-dev] [PATCH v3] test/compress: add mbuf offset unit test

05/12/2018 15:38, Lee Daly: > added mbuf offset test to compressdev test suite, which tests > compression/decompression with a mbuf containing > an offset spanning across mulitple segments. > > V2: >- Change how test checks capalilites structure. > > V3: >- Change commit message. Better

[dpdk-dev] [PATCH] net/mlx5: call generic strlcpy

The call to strlcpy uses either libc, libbsd or internal rte_strlcpy. No need to call the DPDK flavor explictly. Signed-off-by: Thomas Monjalon --- drivers/net/mlx5/mlx5.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/mlx5/mlx5.c b/drivers/net/mlx5/mlx5.c index

[dpdk-dev] [PATCH] app/compress-perf: call generic strlcpy

The call to strlcpy uses either libc, libbsd or internal rte_strlcpy. No need to call the DPDK flavor explictly. Signed-off-by: Thomas Monjalon --- app/test-compress-perf/comp_perf_options_parse.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/app/test-compress-perf/comp

[dpdk-dev] [PATCH] doc: fix PCI whitelist typo in prog guide

The placeholder for PCI address should be named DBDF which stands for Domain/Bus/Device/Function. Fixes: 33af337773ac ("ethdev: add common devargs parser") Cc: remy.hor...@intel.com Cc: sta...@dpdk.org Signed-off-by: Thomas Monjalon --- doc/guides/prog_guide/poll_mode_drv.rst | 6 +++--- 1 file

Re: [dpdk-dev] [PATCH 0/4] fix test of some build options

13/02/2019 00:05, Thomas Monjalon: > When using the "make" system which allows a huge number of > build combinations, some options were not tested with > the script test-build.sh. > > > Thomas Monjalon (4): > mk: fix build of shared library with libbsd > devtools: add libelf dependency to bui

[dpdk-dev] [PATCH v1] mk: remove AVX512 disabled warning on non x86

AVX512 is a x86 specific feature, So, enable AVX512 warning only on x86. Signed-off-by: Jerin Jacob --- mk/toolchain/gcc/rte.toolchain-compat.mk | 2 ++ 1 file changed, 2 insertions(+) diff --git a/mk/toolchain/gcc/rte.toolchain-compat.mk b/mk/toolchain/gcc/rte.toolchain-compat.mk index dbddc9

[dpdk-dev] [PATCH v5 3/4] config: add thunderx2 machine config

Optimized configuration for Marvell thunderx2 SoC. Updated meson build to support Marvell thunderx2 SoC. Added meson cross compile target. Product details are here: https://www.marvell.com/server-processors/thunderx2-arm-processors/ Signed-off-by: Jerin Jacob Signed-off-by: Pavan Nikhilesh ---

[dpdk-dev] [PATCH v5 2/4] meson: add infra to support machine specific flags

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. Signed-off-by: Pavan Nikhilesh Signed-off-by: Jerin Jacob --- config/

[dpdk-dev] [PATCH v5 4/4] config: add octeontx2 machine config

Optimized configuration for Marvell octeontx2 SoC. Updated meson build to support Marvell octeontx2 SoC. Added meson cross build target for octeontx2. Signed-off-by: Jerin Jacob Signed-off-by: Pavan Nikhilesh --- config/arm/arm64_octeontx2_linuxapp_gcc | 15 config/arm/meson.buil

[dpdk-dev] [PATCH v5 1/4] mk: introduce helper to check valid compiler argument

Introduce rte_cc_has_argument() Makefile helper to check a given argument is support by the compiler. Example Usage: include $(RTE_SDK)/mk/rte.helper.mk MACHINE_CFLAGS += $(call rte_cc_has_argument, -mcpu=octeontx2) This would allow adding -mcpu=octeontx2 in MACHINE_CFLAGS if it is only supporte

Re: [dpdk-dev] [PATCH v2 2/4] ethdev: add siblings iterators

On 2/21/19 1:10 AM, Thomas Monjalon wrote: If multiple ports share the same hardware device (rte_device), they are siblings and can be found thanks to the new functions and loop macros. One iterator takes a port id as reference, while the other one directly refers to the parent device. The owner

Re: [dpdk-dev] [PATCH v2 1/4] ethdev: simplify port state comparisons

On 2/21/19 1:10 AM, Thomas Monjalon wrote: There are three states for an ethdev port. Checking that the port is unused looks simpler than checking it is neither attached nor removed. Signed-off-by: Thomas Monjalon It is not always equivalent (if/when more states added), but I think comparison

Re: [dpdk-dev] [PATCH 1/2] net/iavf: rename avf to iavf

> -Original Message- > From: Yigit, Ferruh > Sent: Saturday, February 23, 2019 12:43 AM > To: Rong, Leyi ; Wu, Jingjing ; > Lu, Wenzhuo ; > Zhang, Qi Z > Cc: dev@dpdk.org > Subject: Re: [dpdk-dev] [PATCH 1/2] net/iavf: rename avf to iavf > > On 2/22/2019 3:03 PM, Leyi Rong wrote: > > R

Re: [dpdk-dev] [PATCH 3/5] app/testpmd: add missing transmit errors stats

Hi David, Hello Konstantin, On Sat, Feb 16, 2019 at 1:50 PM Ananyev, Konstantin mailto:konstantin.anan...@intel.com>> wrote: > -Original Message- > From: Thomas Monjalon [mailto:tho...@monjalon.net] > Sent: Friday, February 15, 2019 7:39 PM > To: Ananyev, K

[dpdk-dev] [PATCH v2] net/mlx4: fix default flow rule create

Original patch changed logic of function mlx4_flow_merge_eth(). The setting of flow->promisc was wrongly removed. This patch adds the removed setting of flow->promisc, to restore the required behavior. Fixes: c0d239263156 ("net/mlx4: support flow w/o ETH spec and with VLAN") Cc: sta...@dpdk.org -

Re: [dpdk-dev] [PATCH 2/2] doc: rename avf to iavf

> -Original Message- > From: Yigit, Ferruh > Sent: Saturday, February 23, 2019 12:46 AM > To: Rong, Leyi ; Wu, Jingjing ; > Lu, Wenzhuo ; > Zhang, Qi Z > Cc: dev@dpdk.org > Subject: Re: [dpdk-dev] [PATCH 2/2] doc: rename avf to iavf > > On 2/22/2019 3:03 PM, Leyi Rong wrote: > > This p

Re: [dpdk-dev] [PATCH 1/2] net/iavf: rename avf to iavf

> -Original Message- > From: Yigit, Ferruh > Sent: Saturday, February 23, 2019 12:43 AM > To: Rong, Leyi ; Wu, Jingjing ; > Lu, Wenzhuo ; > Zhang, Qi Z > Cc: dev@dpdk.org > Subject: Re: [dpdk-dev] [PATCH 1/2] net/iavf: rename avf to iavf > > On 2/22/2019 3:03 PM, Leyi Rong wrote: > > R

[dpdk-dev] [PATCH] net/mlx4: fix default flow rule create

Original patch changed logic of function mlx4_flow_merge_eth(). The setting of flow->promisc was wrongly removed. This patch adds the removed setting of flow->promisc, to restore the required behavior. Fixes: c0d239263156 ("net/mlx4: support flow w/o ETH spec and with VLAN") Cc: sta...@mellanox.co