[dpdk-dev] [RFC] testpmd: handle UFO packets

Mostly likely, we will make UFO as a kind of GSO engine. For short term, we can just call APIs in librte_ip_frag to fragment. To test: 1. start testpmd with two vhost port. $ set fwd csum $ start 2. start vm0 connected to vhost0; $ ifconfig xxx 1.1.1.1/24 up $ ethtool -K xxx ufo on 3. star

[dpdk-dev] [PATCH v2 2/7] crpyto/virtio: add crypto related session structure

This structure will be used in the following patches, especially at creating and destroying crypto sessions. Signed-off-by: Jay Zhou --- drivers/crypto/virtio/virtio_crypto_algs.h | 27 +++ 1 file changed, 27 insertions(+) create mode 100644 drivers/crypto/virtio/virtio_

[dpdk-dev] [PATCH v2 1/7] crypto/virtio: add virtio related fundamental functions

Since there are not have the common virtio library, we have to put these files here. They are basically the same with virtio net related files with some minor changes. Signed-off-by: Jay Zhou --- config/common_base | 20 ++ drivers/crypto/virtio/virtio_logs.h | 47 driver

[dpdk-dev] [PATCH v2 6/7] cryptodev: add function tests for virtio crypto PMD

Only RTE_CRYPTO_CIPHER_AES_CBC and RTE_CRYPTO_CIPHER_AES_CTR cipher algorithms are tested now, it is limited by the cryptodev-backend-builtin of qemu side. Signed-off-by: Jay Zhou --- test/test/test_cryptodev.c | 49 + test/test/test_cryptodev.h

[dpdk-dev] [PATCH v2 0/7] crypto: add virtio poll mode driver

This patch series introduce virtio crypto poll mode driver. Since it is limited by the backend of the virtio-crypto, this patch series only supports a limited subset of crypto services. Only the following algorithms are tested: Cipher algorithms: - RTE_CRYPTO_CIPHER_AES_CBC (128-bit, 192-bit an

[dpdk-dev] [PATCH v2 3/7] cryptodev/virtio: core code of crypto devices

The idea comes from QAT and virtio-net devices. Signed-off-by: Jay Zhou --- drivers/crypto/virtio/virtio_cryptodev.c | 1544 ++ drivers/crypto/virtio/virtio_cryptodev.h | 66 ++ drivers/crypto/virtio/virtio_rxtx.c | 533 +++ 3 files changed, 2143 inser

[dpdk-dev] [PATCH v2 5/7] cryptodev: add document for virtio crypto PMD

Signed-off-by: Jay Zhou --- doc/guides/cryptodevs/features/virtio.ini | 20 +++ doc/guides/cryptodevs/virtio.rst | 93 +++ 2 files changed, 113 insertions(+) create mode 100644 doc/guides/cryptodevs/features/virtio.ini create mode 100644 doc/guides/crypt

[dpdk-dev] [PATCH v2 4/7] crypto/virtio: add makefile

The virtio crypto PMD driver can be compiled now. Signed-off-by: Jay Zhou --- drivers/crypto/Makefile| 1 + drivers/crypto/virtio/Makefile | 31 ++ .../virtio/rte_pmd_virtio_crypto_version.map | 3 +++ mk/rte.app.mk

[dpdk-dev] [PATCH v2 7/7] MAINTAINERS: add myself as virtio crypto PMD maintainer

Signed-off-by: Jay Zhou --- MAINTAINERS | 6 ++ 1 file changed, 6 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 4f1f33b..3efc8df 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -718,6 +718,12 @@ F: drivers/crypto/snow3g/ F: doc/guides/cryptodevs/snow3g.rst F: doc/guides/cryptode

[dpdk-dev] [PATCH] net/enic: use memcpy to avoid strict aliasing warnings

From: Hyong Youb Kim Signed-off-by: Hyong Youb Kim Reviewed-by: John Daley --- drivers/net/enic/enic_clsf.c | 21 - 1 file changed, 8 insertions(+), 13 deletions(-) diff --git a/drivers/net/enic/enic_clsf.c b/drivers/net/enic/enic_clsf.c index 3ef1d0832..9d95201ec 100644 -

[dpdk-dev] [PATCH] net/enic: remove the VLAN filter handler

From: Hyong Youb Kim VIC does not support VLAN filtering at the moment. The firmware does accept the filter add/del commands and returns success. But, they are no-ops. To avoid confusion, remove the filter set handler so the app sees an error instead of silent failure. Also during the device con

[dpdk-dev] [PATCH] net/enic: add Rx/Tx queue configuration getters

From: Hyong Youb Kim Signed-off-by: Hyong Youb Kim Reviewed-by: John Daley --- drivers/net/enic/enic_ethdev.c | 76 -- 1 file changed, 65 insertions(+), 11 deletions(-) diff --git a/drivers/net/enic/enic_ethdev.c b/drivers/net/enic/enic_ethdev.c index e

[dpdk-dev] [PATCH] net/enic: remove 'extern' in .h file function declarations

Signed-off-by: John Daley --- drivers/net/enic/enic.h | 80 - 1 file changed, 40 insertions(+), 40 deletions(-) diff --git a/drivers/net/enic/enic.h b/drivers/net/enic/enic.h index c083985ee..e88af6bc9 100644 --- a/drivers/net/enic/enic.h +++ b/dri

[dpdk-dev] [PATCH] doc: describe Rx bytes counter behavior for enic

From: Hyong Youb Kim Signed-off-by: Hyong Youb Kim Reviewed-by: John Daley --- doc/guides/nics/enic.rst | 8 1 file changed, 8 insertions(+) diff --git a/doc/guides/nics/enic.rst b/doc/guides/nics/enic.rst index 7e19cf88a..0bc55936a 100644 --- a/doc/guides/nics/enic.rst +++ b/doc/gui

[dpdk-dev] [PATCH] net/enic: allocate stats DMA buffer upfront during probe

From: Hyong Youb Kim The driver provides a DMA buffer to the firmware when it requests port stats. The NIC then fills that buffer with latest stats. Currently, the driver allocates the DMA buffer the first time it requests stats and saves it for later use. This can lead to crashes when primary/se

[dpdk-dev] [PATCH] net/enic: support for meson

From: Hyong Youb Kim Signed-off-by: Hyong Youb Kim Reviewed-by: John Daley --- Note: check-git-log.sh seems to fail when files in drivers/net are included even if they are commited independently with the "drivers/net:" prefix. Commiting both files at once. Please ignore check-git-log.sh failur

[dpdk-dev] [PATCH] net/enic: support Rx queue interrupts

From: Hyong Youb Kim Enable rx queue interrupts if the app requests them, and vNIC has enough interrupt resources. Use interrupt vector 0 for link status and errors. Use vector 1 for rx queue 0, vector 2 for rx queue 1, and so on. So, with n rx queues, vNIC needs to have at n + 1 interrupts. For

[dpdk-dev] [PATCH] net/enic: heed the requested max Rx packet size

From: Hyong Youb Kim Currently, enic completely ignores the requested max Rx packet size (rxmode.max_rx_pkt_len). The desired behavior is that the NIC hardware drops packets larger than the requested size, even though they are still smaller than MTU. Cisco VIC does not have such a feature. But,

[dpdk-dev] [PATCH] net/enic: allow the user to change RSS settings

From: Hyong Youb Kim Currently, when more than 1 receive queues are configured, the driver always enables RSS with the driver's own default hash type, key, and RETA. The user is unable to change any of the RSS settings. Address this by implementing the ethdev RSS API as follows. Correctly report

[dpdk-dev] [dpdk-announce] FYI: CFP: FD.io mini-summit at ONS, March 26th

Sorry if this is a duplicate. Jim From: m...@lists.fd.io [mailto:m...@lists.fd.io] On Behalf Of Trishan de Lanerolle Sent: Thursday, February 22, 2018 12:48 PM To: m...@lists.fd.io Subject: [FD.io] CFP: FD.io mini-summit at ONS, March 26th Call for Proposals Open Join us at the FD.io

[dpdk-dev] [PATCH v2] doc: update mlx4 flow limitations

This patch updates mlx4 documentation with flow configuration limitations imposed by NIC hardware and PMD implementation Signed-off-by: Moti Haimovsky Signed-off-by: Ophir Munk --- v1: initial version (use testpmd examples) v2: enhance and add rte_flow examples doc/guides/nics/mlx4.rst | 383 +

Re: [dpdk-dev] [PATCH v1] net/mlx4: fix RSS actions with no parameters

Hi, Please see below > -Original Message- > From: Adrien Mazarguil [mailto:adrien.mazarg...@6wind.com] > Sent: Friday, February 23, 2018 6:53 PM > To: Ophir Munk > Cc: dev@dpdk.org; Thomas Monjalon ; Olga Shern > ; sta...@dpdk.org > Subject: Re: [PATCH v1] net/mlx4: fix RSS actions with n

Re: [dpdk-dev] [PATCH] net/qede: fix alloc from socket 0

-Original Message- From: Pascal Mazon Date: Friday, February 23, 2018 at 4:53 AM To: "dev@dpdk.org" , "Mody, Rasesh" , Harish Patil , "Shaikh, Shahed" Cc: "pascal.ma...@6wind.com" , "sta...@dpdk.org" Subject: [PATCH] net/qede: fix alloc from socket 0 >In case osal_dma_alloc_coherent() i

[dpdk-dev] [PATCH] net/mlx5: add bluefield device ID

Signed-off-by: Shahaf Shuler --- drivers/net/mlx5/mlx5.c | 4 drivers/net/mlx5/mlx5.h | 1 + 2 files changed, 5 insertions(+) diff --git a/drivers/net/mlx5/mlx5.c b/drivers/net/mlx5/mlx5.c index 61cb93101..5345bc46f 100644 --- a/drivers/net/mlx5/mlx5.c +++ b/drivers/net/mlx5/mlx5.c @@ -1027

[dpdk-dev] [PATCH] net/mlx5: fix tunnel offloads cap query

The query for the tunnel stateless offloads is wrongly implemented because of: 1. It was using the device id to query for the offloads. 2. It was using a compilation flag for Verbs which no longer exits. The main reason was lack of proper API from Verbs. Fixing the query to use rdma-core API. Th