Re: [dpdk-dev] [PATCH 0/2] add Tx prepare support for bonding device

在 2021/4/30 14:26, Chengchang Tang 写道: Hi，all Any comments？ On 2021/4/23 17:46, Chengchang Tang wrote: This patch set add Tx prepare for bonding device. Currently, the bonding driver has not implemented the callback of rte_eth_tx_prepare function. Therefore, the TX prepare function of the s

Re: [dpdk-dev] [PATCH v6 01/10] eal: add thread id and simple thread functions

On Thu, Apr 29, 2021 at 07:28:26PM +0300, Dmitry Kozlyuk wrote: > 2021-04-29 13:05 (UTC+0100), Kinsella, Ray: > > On 29/04/2021 08:44, Thomas Monjalon wrote: > > > 29/04/2021 02:50, Dmitry Kozlyuk: > > >> 2021-04-02 18:38 (UTC-0700), Narcisa Ana Maria Vasile: > > >>> --- /dev/null > > >>> +++ b

[dpdk-dev] [PATCH v3 5/6] net/hns3: log FDIR configuration

From: Chengwen Feng The rte flow interface does not support the API of the capability set. Therefore, fdir configuration logs are added to facilitate debugging. Signed-off-by: Chengwen Feng Signed-off-by: Min Hu (Connor) --- drivers/net/hns3/hns3_fdir.c | 13 + 1 file changed, 13

[dpdk-dev] [PATCH v3 4/6] net/hns3: improve IO path data cache usage

From: Chengwen Feng This patch improves data cache usage by: 1. Rearrange the rxq frequency accessed fields in the IO path to the first 128B. 2. Rearrange the txq frequency accessed fields in the IO path to the first 64B. 3. Make sure ptype table align cacheline size which is 128B instead of min

[dpdk-dev] [PATCH v3 6/6] net/hns3: fix vector Rx burst can't exceed 32

From: Chengwen Feng Currently, driver uses the macro HNS3_DEFAULT_RX_BURST whose value is 32 to limit the vector Rx burst size, as a result, the burst size can't exceed 32. This patch fixes this problem by support big burst size. Also adjust HNS3_DEFAULT_RX_BURST to 64 as it performs better than

[dpdk-dev] [PATCH v3 0/6] optimization and bugfix for hns3 PMD

This patch set contains one patch for performance optimization, this is: 'net/hns3: improve IO path data cache usage'. The others are bugfixes for hns3 PMD. Chengwen Feng (6): net/hns3: delete some unused capabilities net/hns3: modify write reg opt API impl net/hns3: use RTE DIM instead of A

[dpdk-dev] [PATCH v3 1/6] net/hns3: delete some unused capabilities

From: Chengwen Feng This patch deletes some unused capabilities, include: 1. Delete some unused firmware capabilities definition, which are: UDP_GSO, ATR, INT_QL, SIMPLE_BD, TX_PUSH, FEC and PAUSE. 2. Delete some unused driver capabilities definition, which are: UDP_GSO, TX_PUSH. 3. Also redefine

[dpdk-dev] [PATCH v3 3/6] net/hns3: use RTE DIM instead of ARRAY SIZE

From: Chengwen Feng This patch uses RTE_DIM() instead of ARRAY_SIZE(). Signed-off-by: Chengwen Feng Signed-off-by: Min Hu (Connor) --- drivers/net/hns3/hns3_cmd.c| 4 ++-- drivers/net/hns3/hns3_ethdev.h | 2 -- drivers/net/hns3/hns3_flow.c | 18 +- drivers/net/hns3/hns

[dpdk-dev] [PATCH v3 2/6] net/hns3: modify write reg opt API impl

From: Chengwen Feng This patch modifies hns3_write_reg_opt() API implementation because the rte_write32() already uses rte_io_wmb(). Signed-off-by: Chengwen Feng Signed-off-by: Min Hu (Connor) --- drivers/net/hns3/hns3_ethdev.h | 8 1 file changed, 4 insertions(+), 4 deletions(-) di

Re: [dpdk-dev] [PATCH 0/2] add Tx prepare support for bonding device

Hi，all Any comments？ On 2021/4/23 17:46, Chengchang Tang wrote: > This patch set add Tx prepare for bonding device. > > Currently, the bonding driver has not implemented the callback of > rte_eth_tx_prepare function. Therefore, the TX prepare function of the > slave devices will never be invoked.

Re: [dpdk-dev] [PATCH-V5] config/arm: restore support for Qualcomm servers

> -Original Message- > From: Thierry Herbelot > Sent: Thursday, April 29, 2021 5:16 PM > To: dev@dpdk.org > Cc: Thierry Herbelot ; Thomas Monjalon > ; Juraj Linkeš ; Honnappa > Nagarahalli ; Ruifeng Wang > > Subject: [PATCH-V5] config/arm: restore support for Qualcomm servers > > From

Re: [dpdk-dev] [PATCH v2 00/33] Marvell CNXK Event device Driver

On Mon, Apr 26, 2021 at 11:14 PM wrote: > > From: Pavan Nikhilesh > > This patchset adds support for Marvell CN106XX SoC based on 'common/cnxk' > driver. In future, CN9K a.k.a octeontx2 will also be supported by same > driver when code is ready and 'event/octeontx2' will be deprecated. > > v2 Cha

Re: [dpdk-dev] [PATCH v2 1/2] app/testpmd: add link speed check before port start

> -Original Message- > From: Huisong Li > Sent: Friday, April 30, 2021 12:04 > To: Li, Xiaoyun > Cc: Yigit, Ferruh ; dev@dpdk.org > Subject: Re: [dpdk-dev] [PATCH v2 1/2] app/testpmd: add link speed check > before port start > > > 在 2021/4/30 11:19, Li, Xiaoyun 写道: > >> -Original

[dpdk-dev] [PATCH 4/4] drivers/net/enetfec: add enqueue and dequeue support

This patch supported checksum offloads and add burst enqueue and dequeue operations to the enetfec PMD. Loopback mode is added, compile time flag 'ENETFEC_LOOPBACK' is used to enable this feature. By default loopback mode is disabled. Basic features added like promiscuous enable, basic stats. Sig

[dpdk-dev] [PATCH 3/4] drivers/net/enetfec: queue configuration

This patch added RX/TX queue configuration setup operations. On packet Rx the respective BD Ring status bit is set which is then used for packet processing. Signed-off-by: Sachin Saxena Signed-off-by: Apeksha Gupta --- drivers/net/enetfec/enet_ethdev.c | 223 ++ 1 fi

[dpdk-dev] [PATCH 2/4] drivers/net/enetfec: UIO support added

Implemented the fec-uio driver in kernel. enetfec PMD uses UIO interface to interact with kernel for PHY initialisation and for mapping the allocated memory of register & BD from kernel to DPDK which gives access to non-cacheble memory for BD. Signed-off-by: Sachin Saxena Signed-off-by: Apeksha G

[dpdk-dev] [PATCH 1/4] drivers/net/enetfec: Introduce NXP ENETFEC driver

ENET fec (Fast Ethernet Controller) is a network poll mode driver for NXP SoC imx8mmevk. This patch add skeleton for enetfec driver with probe and uintialisation functions Signed-off-by: Sachin Saxena Signed-off-by: Apeksha Gupta --- doc/guides/nics/enetfec.rst | 121

[dpdk-dev] [PATCH 0/4] drivers/net: add NXP ENETFEC driver

This patch series introduce the enetfec ethernet driver, ENET fec (Fast Ethernet Controller) is a network poll mode driver for the inbuilt NIC found in the NXP imx8mmevk Soc. An overview of the enetfec driver with probe and remove are in patch 1. Patch 2 design UIO so that user space directly comm

Re: [dpdk-dev] [PATCH 0/4] maintainers: update for igc/e1000/ixgbe/i40e

Thanks Ferruh, Thomas and drivers maintainers. Thanks all DPDK contributor! Good luck and see you somewhere! > -Original Message- > From: Yigit, Ferruh > Sent: Thursday, April 29, 2021 9:58 PM > To: Guo, Jia ; Xing, Beilei ; Wang, > Haiyue ; tho...@monjalon.net > Cc: Zhang, Qi Z ; dev@dp

Re: [dpdk-dev] [PATCH v2 1/2] app/testpmd: add link speed check before port start

在 2021/4/30 11:19, Li, Xiaoyun 写道: -Original Message- From: Min Hu (Connor) Sent: Wednesday, April 28, 2021 16:37 To: dev@dpdk.org Cc: Yigit, Ferruh ; Li, Xiaoyun Subject: [PATCH v2 1/2] app/testpmd: add link speed check before port start From: Huisong Li Currently, to check whethe

Re: [dpdk-dev] [PATCH v2 1/2] app/testpmd: add link speed check before port start

> -Original Message- > From: Min Hu (Connor) > Sent: Wednesday, April 28, 2021 16:37 > To: dev@dpdk.org > Cc: Yigit, Ferruh ; Li, Xiaoyun > Subject: [PATCH v2 1/2] app/testpmd: add link speed check before port start > > From: Huisong Li > > Currently, to check whether the configured

Re: [dpdk-dev] [PATCH v2] bonding: fix overflow check

在 2021/4/29 21:33, Ferruh Yigit 写道: On 4/27/2021 2:40 AM, Min Hu (Connor) wrote: Buffer 'test_params->slave_port_ids' of size 6 accessed may overflow, since its index 'i' can have value be is out of range. This patch fixed it. Fixes: 92073ef961ee ("bond: unit tests") Cc: sta...@dpdk.org Si

[dpdk-dev] LACP negotiation fails when LACP dedicated queue Is enabled for the X710 NIC

Hello, When I tried to use the x710 NIC whose driver is i40e to enable LACP dedicated queue, the LACP negotiation fails. GDB debugging shows that the current packet sending function type is VECTOR. After I forcibly change the packet sending function to another type, LACP negotiation succeeds

Re: [dpdk-dev] [PATCH v6 03/10] windows/eal: translate Windows errors to errno-style errors

On Thu, Apr 29, 2021 at 03:50:38AM +0300, Dmitry Kozlyuk wrote: > 2021-04-02 18:39 (UTC-0700), Narcisa Ana Maria Vasile: > > From: Narcisa Vasile > > > > Add function to translate Windows error codes to > > errno-style error codes. > > > > Signed-off-by: Narcisa Vasile > > Commit topic should

Re: [dpdk-dev] [PATCH v3 1/4] ethdev: fix integrity flow item

On Thu, Apr 29, 2021 at 11:37 AM Gregory Etelson wrote: > > Add integrity item definition to the rte_flow_desc_item array. > The new entry allows to build RTE flow item from a data > stored in rte_flow_item_integrity type. > > Fixes: b10a421a1f3b ("ethdev: add packet integrity check flow rules") >

Re: [dpdk-dev] [PATCH v1] test/ticketlock: use C11 atomic builtins for lcores sync

On Thu, 29 Apr 2021 21:10:04 + Honnappa Nagarahalli wrote: > > > > > > > > > Subject: Re: [dpdk-dev] [PATCH v1] test/ticketlock: use C11 atomic > > > > builtins for lcores sync > > > > > > > > On Wed, Apr 21, 2021 at 02:17:33AM -0500, Joyce Kong wrote: > > > > > Convert rte_atomic usage

Re: [dpdk-dev] Questions about API with no parameter check

On Thu, Apr 29, 2021 at 09:49:24PM +0300, Dmitry Kozlyuk wrote: > 2021-04-29 09:16 (UTC-0700), Tyler Retzlaff: > > On Wed, Apr 07, 2021 at 05:10:00PM +0100, Ferruh Yigit wrote: > > > On 4/7/2021 4:25 PM, Hemant Agrawal wrote: > > > >>+1 > > > >>But are we going to check all parameters? > > > >

Re: [dpdk-dev] [PATCH v1] test/ticketlock: use C11 atomic builtins for lcores sync

> > > > > Subject: Re: [dpdk-dev] [PATCH v1] test/ticketlock: use C11 atomic > > > builtins for lcores sync > > > > > > On Wed, Apr 21, 2021 at 02:17:33AM -0500, Joyce Kong wrote: > > > > Convert rte_atomic usages to C11 atomic builtins for lcores sync > > > > in ticketlock testcases. > > > > > >

Re: [dpdk-dev] [PATCH v2 1/4] mbuf: mark old offload flag as deprecated

On Thu, Apr 29, 2021 at 1:05 AM David Marchand wrote: > > PKT_RX_EIP_CKSUM_BAD has been declared deprecated but there was no > warning to applications still using it. > Fix this by marking as deprecated with the newly introduced > RTE_DEPRECATED. > > Fixes: e8a419d6de4b ("mbuf: rename outer IP che

Re: [dpdk-dev] [PATCH v6 06/10] eal: add thread lifetime management

2021-04-02 18:39 (UTC-0700), Narcisa Ana Maria Vasile: [...] > diff --git a/lib/librte_eal/windows/rte_thread.c > b/lib/librte_eal/windows/rte_thread.c > index f61103bbc..86bbd7bc2 100644 > --- a/lib/librte_eal/windows/rte_thread.c > +++ b/lib/librte_eal/windows/rte_thread.c > @@ -329,6 +329,131 @

Re: [dpdk-dev] [PATCH v2 4/4] vhost: fix offload flags in Rx path

On Thu, Apr 29, 2021 at 3:31 PM Maxime Coquelin wrote: > On 4/29/21 3:30 PM, Maxime Coquelin wrote: > >> The vhost library current configures Tx offloading (PKT_TX_*) on any > >> packet received from a guest virtio device which asks for some offloading. > >> > >> This is problematic, as Tx offload

Re: [dpdk-dev] [PATCH v2 4/4] vhost: fix offload flags in Rx path

On Thu, Apr 29, 2021 at 3:30 PM Maxime Coquelin wrote: > On 4/29/21 10:04 AM, David Marchand wrote: > > The vhost library current configures Tx offloading (PKT_TX_*) on any > > s/current/currently/ Ok. > > > packet received from a guest virtio device which asks for some offloading. > > > > This

Re: [dpdk-dev] [EXTERNAL] Re: [PATCH v5 5/9] app/testpmd: add clock_gettime_monotonic

On Wed, Apr 28, 2021 at 11:45:40AM +0300, Dmitry Kozlyuk wrote: > 2021-04-19 21:41 (UTC+0200), Thomas Monjalon: > > 19/04/2021 20:34, Tyler Retzlaff: > > > > > Originally and internally, the function was added into eal. But then > > > > > restricted the functionality just inside testpmd to avoid cu

Re: [dpdk-dev] [PATCH v1] test/ticketlock: use C11 atomic builtins for lcores sync

On Thu, Apr 29, 2021 at 07:17:06PM +, Honnappa Nagarahalli wrote: > > > > Subject: Re: [dpdk-dev] [PATCH v1] test/ticketlock: use C11 atomic builtins > > for lcores sync > > > > On Wed, Apr 21, 2021 at 02:17:33AM -0500, Joyce Kong wrote: > > > Convert rte_atomic usages to C11 atomic builtins

Re: [dpdk-dev] [PATCH v2 4/4] vhost: fix offload flags in Rx path

On Thu, Apr 29, 2021 at 8:39 PM Flavio Leitner wrote: > > - if (l4_hdr && hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) { > > + /* GSO request, save required information in mbuf */ > > + if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) { > > + /* Check unsupported modes */ > > +

Re: [dpdk-dev] [PATCH v1] test/ticketlock: use C11 atomic builtins for lcores sync

> Subject: Re: [dpdk-dev] [PATCH v1] test/ticketlock: use C11 atomic builtins > for lcores sync > > On Wed, Apr 21, 2021 at 02:17:33AM -0500, Joyce Kong wrote: > > Convert rte_atomic usages to C11 atomic builtins for lcores sync in > > ticketlock testcases. > > gcc atomic builtins aren't 'C11'

Re: [dpdk-dev] [PATCH v1] test/ticketlock: use C11 atomic builtins for lcores sync

On Wed, Apr 21, 2021 at 02:17:33AM -0500, Joyce Kong wrote: > Convert rte_atomic usages to C11 atomic builtins for lcores sync > in ticketlock testcases. gcc atomic builtins aren't 'C11' > > Signed-off-by: Joyce Kong > Reviewed-by: Honnappa Nagarahalli > Reviewed-by: Ruifeng Wang > --- the c

Re: [dpdk-dev] Questions about API with no parameter check

2021-04-29 09:16 (UTC-0700), Tyler Retzlaff: > On Wed, Apr 07, 2021 at 05:10:00PM +0100, Ferruh Yigit wrote: > > On 4/7/2021 4:25 PM, Hemant Agrawal wrote: > > >>+1 > > >>But are we going to check all parameters? > > > > > >+1 > > > > > >It may be better to limit the number of checks. > > > >

Re: [dpdk-dev] [PATCH v5 3/5] test/hash: add additional thash tests

On Thu, Apr 29, 2021 at 12:17:08PM +0300, Medvedkin, Vladimir wrote: > > Test Failed > > RTE>> > > --- stderr --- > > EAL: Detected 2 lcore(s) > > EAL: Detected 1 NUMA nodes > > EAL: Detected shared linkage of DPDK > > EAL: Multi-process socket /var/run/dpdk/thash_autotest/mp_socket > > EAL: Selec

Re: [dpdk-dev] [PATCH v2 4/4] vhost: fix offload flags in Rx path

On Thu, Apr 29, 2021 at 10:04:38AM +0200, David Marchand wrote: > The vhost library current configures Tx offloading (PKT_TX_*) on any > packet received from a guest virtio device which asks for some offloading. > > This is problematic, as Tx offloading is something that the application > must ask

[dpdk-dev] [PATCH v3 4/4] doc: add MLX5 PMD integrity item support

Add MLX5 PMD integrity item support to 21.05 release notes. Add MLX5 PMD integrity item limitations to the PMD records. Signed-off-by: Gregory Etelson Acked-by: Viacheslav Ovsiienko --- doc/guides/nics/mlx5.rst | 15 +++ doc/guides/rel_notes/release_21_02.rst | 1 +

[dpdk-dev] [PATCH v3 3/4] net/mlx5: support integrity flow item

MLX5 PMD supports the following integrity filters for outer and inner network headers: - l3_ok - l4_ok - ipv4_csum_ok - l4_csum_ok `level` values 0 and 1 reference outer headers. `level` > 1 reference inner headers. Flow rule items supplied by application must explicitly specify network headers r

[dpdk-dev] [PATCH v3 2/4] net/mlx5: update PRM definitions

Add integrity and IPv4 IHL bits to PRM file. Signed-off-by: Gregory Etelson Acked-by: Viacheslav Ovsiienko --- drivers/common/mlx5/mlx5_devx_cmds.c | 31 --- drivers/common/mlx5/mlx5_devx_cmds.h | 1 + drivers/common/mlx5/mlx5_prm.h | 37 +---

[dpdk-dev] [PATCH v3 1/4] ethdev: fix integrity flow item

Add integrity item definition to the rte_flow_desc_item array. The new entry allows to build RTE flow item from a data stored in rte_flow_item_integrity type. Fixes: b10a421a1f3b ("ethdev: add packet integrity check flow rules") Signed-off-by: Gregory Etelson Acked-by: Viacheslav Ovsiienko ---

[dpdk-dev] [PATCH v3 0/4] net/mlx5: add integrity flow item support

v2: Add MLX5 PMD integrity item support to 21.05 release notes. Use RTE_BIT64() macro in RTE_FLOW_ITEM_INTEGRITY_* definition. v3: Remove RTE_FLOW_ITEM_INTEGRITY_* bit masks. Acked-by: Viacheslav Ovsiienko Gregory Etelson (4): ethdev: fix integrity flow item net/mlx5: update PRM definitions

Re: [dpdk-dev] [PATCH v2] ethdev: add sanity checks in control APIs

On Thu, 29 Apr 2021 10:48:34 -0700 Tyler Retzlaff wrote: > On Tue, Apr 13, 2021 at 11:22:14AM +0800, Min Hu (Connor) wrote: > > This patch adds more sanity checks in control path APIs. > > > > Fixes: 214ed1acd125 ("ethdev: add iterator to match devargs input") > > Fixes: 3d98f921fbe9 ("ethdev: u

Re: [dpdk-dev] [PATCH] net/bnxt: fix initialization of filter struct

On Thu, Apr 29, 2021 at 9:43 AM Lance Richardson wrote: > > On Wed, Apr 28, 2021 at 6:04 PM Lance Richardson > wrote: > > > > Initialize filter structure to all zeroes on allocation. > > > > Fixes: 5ef3b79fdfe6 ("net/bnxt: support flow filter ops") > > Cc: sta...@dpdk.org > > Signed-off-by: Lance

Re: [dpdk-dev] [PATCH v2] ethdev: add sanity checks in control APIs

On Tue, Apr 13, 2021 at 11:22:14AM +0800, Min Hu (Connor) wrote: > This patch adds more sanity checks in control path APIs. > > Fixes: 214ed1acd125 ("ethdev: add iterator to match devargs input") > Fixes: 3d98f921fbe9 ("ethdev: unify prefix for static functions and > variables") > Fixes: 03661377

Re: [dpdk-dev] [PATCH] net/bnxt: fix initialization of filter struct

On Wed, Apr 28, 2021 at 6:04 PM Lance Richardson wrote: > > Initialize filter structure to all zeroes on allocation. > > Fixes: 5ef3b79fdfe6 ("net/bnxt: support flow filter ops") > Cc: sta...@dpdk.org > Signed-off-by: Lance Richardson > Reviewed-by: Ajit Kumar Khaparde > --- > drivers/net/bnxt/

Re: [dpdk-dev] [PATCH v7 1/5] eal: add sleep API

On Wed, Apr 07, 2021 at 09:31:43AM +0200, Morten Brørup wrote: > > I think it's just tradition from Linux/BSD developers not being used to > cross-platform development or having forgotten how to develop software for > deeply embedded systems without a standard O/S below. We use POSIX functions

Re: [dpdk-dev] [PATCH v4 1/2] ethdev: add new ext hdr for gtp psc

On Thu, Apr 08, 2021 at 02:29:56PM +0200, Olivier Matz wrote: > Hi Raslan, > > > +/** > > + * Optional extension for GTP with next_ext set to 0x85 > > + * defined based on RFC 38415-g30. > > + */ > > +__extension__ > > +struct rte_gtp_psc_hdr { > > + uint8_t ext_hdr_len; /**< PDU ext hdr len in

Re: [dpdk-dev] [PATCH v6 02/10] eal: add thread attributes

2021-04-29 09:48 (UTC+0200), Thomas Monjalon: > 29/04/2021 02:50, Dmitry Kozlyuk: > > 2021-04-02 18:39 (UTC-0700), Narcisa Ana Maria Vasile: > > > +int > > > +rte_thread_attr_init(rte_thread_attr_t *attr) > > > +{ > > > + if (attr == NULL) { > > > + RTE_LOG(DEBUG, EAL, > > > + "Un

Re: [dpdk-dev] [PATCH v6 01/10] eal: add thread id and simple thread functions

2021-04-29 13:05 (UTC+0100), Kinsella, Ray: > On 29/04/2021 08:44, Thomas Monjalon wrote: > > 29/04/2021 02:50, Dmitry Kozlyuk: > >> 2021-04-02 18:38 (UTC-0700), Narcisa Ana Maria Vasile: > >>> --- /dev/null > >>> +++ b/lib/librte_eal/windows/include/rte_windows_thread_types.h > >>> @@ -0,0 +1,

Re: [dpdk-dev] [PATCH 0/5] Features and bugfix for hns3 PMD

On 4/28/2021 8:20 AM, Min Hu (Connor) wrote: > This patch set contains one feature and four bugfixes for > hns3 PMD. > > Chengchang Tang (1): > net/hns3: select Tx prepare based on Tx offload > > Chengwen Feng (4): > net/hns3: support preferred burst size and queues in VF > net/hns3: log ti

Re: [dpdk-dev] Questions about API with no parameter check

On Wed, Apr 07, 2021 at 05:10:00PM +0100, Ferruh Yigit wrote: > On 4/7/2021 4:25 PM, Hemant Agrawal wrote: > >>+1 > >>But are we going to check all parameters? > > > >+1 > > > >It may be better to limit the number of checks. > > > > +1 to verify input for APIs. > > Why not do all, what is the dow

Re: [dpdk-dev] [PATCH v2 1/4] mbuf: mark old offload flag as deprecated

On Thu, Apr 29, 2021 at 4:05 AM David Marchand wrote: > > PKT_RX_EIP_CKSUM_BAD has been declared deprecated but there was no > warning to applications still using it. > Fix this by marking as deprecated with the newly introduced > RTE_DEPRECATED. > > Fixes: e8a419d6de4b ("mbuf: rename outer IP che

Re: [dpdk-dev] [PATCH V4 0/7] modifications about DCB forwarding configuration

On 4/28/2021 8:01 AM, Li, Xiaoyun wrote: >> -Original Message- >> From: Huisong Li >> Sent: Wednesday, April 28, 2021 14:41 >> To: dev@dpdk.org >> Cc: Yigit, Ferruh ; Li, Xiaoyun >> >> Subject: [PATCH V4 0/7] modifications about DCB forwarding configuration >> >> This patchset modifies s

Re: [dpdk-dev] [PATCH v6 01/10] eal: add thread id and simple thread functions

On Thu, Apr 29, 2021 at 01:05:05PM +0100, Kinsella, Ray wrote: > > > On 29/04/2021 08:44, Thomas Monjalon wrote: > > 29/04/2021 02:50, Dmitry Kozlyuk: > >> 2021-04-02 18:38 (UTC-0700), Narcisa Ana Maria Vasile: > >>> --- /dev/null > >>> +++ b/lib/librte_eal/windows/include/rte_windows_thread_type

Re: [dpdk-dev] [PATCH v2 07/16] common/mlx5: fix cypto bsf attr

Hi Raslan See below , need to squash this to " common/mlx5: adjust DevX MKEY fields for crypto" The one below it...missed that, sorry. From: Matan Azrad > From: Suanming Mou > > This commit should be squash to crypto en commit. > > Signed-off-by: Suanming Mou > --- > drivers/common/mlx5/ml

[dpdk-dev] [PATCH v2 15/15] crypto/mlx5: set feature flags and capabilities

From: Shiri Kuzin Add the supported capabilities to the crypto driver. Add supported feature flags. Add crypto driver documentation. Signed-off-by: Shiri Kuzin Signed-off-by: Matan Azrad --- doc/guides/cryptodevs/features/mlx5.ini | 37 ++ doc/guides/cryptodevs/index.rst | 1

[dpdk-dev] [PATCH v2 14/15] crypto/mlx5: add statistic get and reset operations

From: Suanming Mou This commit adds mlx5 crypto statistic get and reset operations. Signed-off-by: Suanming Mou Signed-off-by: Matan Azrad --- drivers/crypto/mlx5/mlx5_crypto.c | 39 --- 1 file changed, 36 insertions(+), 3 deletions(-) diff --git a/drivers/crypto/

[dpdk-dev] [PATCH v2 13/15] crypto/mlx5: add enqueue and dequeue operations

From: Suanming Mou The crypto operations are done with the WQE set which contains one UMR WQE and one rdma write WQE. Most segments of the WQE set are initialized properly during queue setup, only limited segments are initialized according to the crypto detail in the datapath process. This commi

[dpdk-dev] [PATCH v2 12/15] crypto/mlx5: add WQE set initialization

From: Suanming Mou Currently, HW handles the WQEs much faster than the software, Using the constant WQE set layout can initialize most of the WQE segments in advanced, and software only needs to configure very limited segments in datapath. This accelerates the software WQE organize in datapath.

[dpdk-dev] [PATCH v2 11/15] crypto/mlx5: add maximum segments device argument

From: Suanming Mou The mlx5 HW crypto operations are done by attaching crypto property to a memory region. Once done, every access to the memory via the crypto-enabled memory region will result with in-line encryption or decryption of the data. As a result, the design choice is to provide two ty

[dpdk-dev] [PATCH v2 10/15] crypto/mlx5: add keytag device argument

From: Suanming Mou A keytag is a piece of data encrypted together with a DEK. When a DEK is referenced by an MKEY.bsf through its index, the keytag is also supplied in the BSF as plaintext. The HW will decrypt the DEK (and the attached keytag) and will fail the operation if the keytags don't mat

[dpdk-dev] [PATCH v2 09/15] crypto/mlx5: adjust to the multiple data unit API

From: Shiri Kuzin In AES-XTS the data to be encrypted\decrypted does not have to be in multiples of 16B size, the unit of data is called data-unit. As a result of patch [1] a new field is added to the cipher capability, called dataunit_set, where the devices can report the range of supported dat

[dpdk-dev] [PATCH v2 08/15] crypto/mlx5: create login object using DevX

From: Shiri Kuzin To work with crypto engines that are marked with wrapped_import_method, a login session is required. A crypto login object needs to be created using DevX. The crypto login object contains: - The credential pointer. - The import_KEK pointer to be used for all sec

[dpdk-dev] [PATCH v2 07/15] crypto/mlx5: add memory region management

From: Shiri Kuzin Mellanox user space drivers don't deal with physical addresses as part of a memory protection mechanism. The device translates the given virtual address to a physical address using the given memory key as an address space identifier. That's why any mbuf virtual address is moved

[dpdk-dev] [PATCH v2 06/15] crypto/mlx5: add dev stop and start operations

From: Shiri Kuzin Add the dev_start function that is used to start a configured device. Add the dev_stop function that is used to stop a configured device. Both functions set the dev parameter as used and return 0. Signed-off-by: Shiri Kuzin Acked-by: Matan Azrad --- drivers/crypto/mlx5/mlx5

[dpdk-dev] [PATCH v2 05/15] crypto/mlx5: support queue pairs operations

From: Shiri Kuzin The HW queue pairs are a pair of send queue and receive queue of independent work queues packed together in one object for the purpose of transferring data between nodes of a network. Completion Queue is a FIFO queue of completed work requests. In crypto driver we use one QP i

[dpdk-dev] [PATCH v2 04/15] crypto/mlx5: add basic operations

From: Shiri Kuzin The basic dev control operations are configure, close and get info. Extended the existing support of configure and close: -mlx5_crypto_dev_configure- function used to configure device. -mlx5_crypto_dev_close- function used to close a configured device.

[dpdk-dev] [PATCH v2 03/15] crypto/mlx5: support session operations

From: Shiri Kuzin Sessions are used in symmetric transformations in order to prepare objects and data for packet processing stage. A mlx5 session includes iv_offset, pointer to mlx5_crypto_dek struct, bsf_size, bsf_p_type, encryption_order and encryption standard. Implement the next session ope

[dpdk-dev] [PATCH v2 02/15] crypto/mlx5: add DEK object management

From: Shiri Kuzin A DEK(Data encryption Key) is an mlx5 HW object which represents the cipher algorithm key. The DEKs are used during data encryption/decryption operations. In symmetric algorithms like AES-STS, we use the same DEK for both encryption and decryption. Use the mlx5 hash-list tool

[dpdk-dev] [PATCH v2 01/15] drivers: introduce mlx5 crypto PMD

From: Shiri Kuzin Add a new PMD for Nvidia devices- crypto PMD. The crypto PMD will be supported starting Nvidia ConnectX6 and BlueField2. The crypto PMD will add the support of encryption and decryption using the AES-XTS symmetric algorithm. The crypto PMD requires rdma-core and uses mlx5 Dev

[dpdk-dev] [PATCH v2 00/15] drivers: introduce mlx5 crypto PMD

Add a new PMD for Nvidia devices- crypto PMD. The crypto PMD will be supported on Nvidia ConnectX6 The crypto PMD will add the support of encryption and decryption using the AES-XTS symmetric algorithm. The crypto PMD requires rdma-core and uses mlx5 DevX. v2: Add data-path part. Shiri Kuzin (10

[dpdk-dev] [PATCH v2 16/16] common/mlx5: add UMR and RDMA write WQE defines

From: Suanming Mou This patch adds the struct defining UMR and RDMA write WQEs. Signed-off-by: Suanming Mou Signed-off-by: Matan Azrad --- drivers/common/mlx5/mlx5_prm.h | 187 + 1 file changed, 121 insertions(+), 66 deletions(-) diff --git a/drivers/common/ml

[dpdk-dev] [PATCH v2 15/16] common/mlx5: support register write access

From: Dekel Peled This patch adds support of write operation to NIC registers. Signed-off-by: Dekel Peled Acked-by: Matan Azrad --- drivers/common/mlx5/mlx5_devx_cmds.c | 67 +++- drivers/common/mlx5/mlx5_devx_cmds.h | 4 ++ drivers/common/mlx5/version.map | 21 +

[dpdk-dev] [PATCH v2 14/16] common/mlx5: add crypto register structs and defs

From: Dekel Peled Encryption key management requires use of several related registers. This patch adds the relevant structs and values, according to PRM definitions. Signed-off-by: Dekel Peled Acked-by: Matan Azrad --- drivers/common/mlx5/mlx5_prm.h | 41 ++ 1

[dpdk-dev] [PATCH v2 13/16] common/mlx5: support general obj CREDENTIAL create

From: Dekel Peled CREDENTIAL object is used for any crypto operation in wrapped mode. This patch add support of CREDENTIAL object create operation. Add reading of CREDENTIAL support capability. Add function to create general object type CREDENTIAL, using DevX API. Signed-off-by: Dekel Peled Ac

[dpdk-dev] [PATCH v2 12/16] common/mlx5: share get ib device match function

From: Shiri Kuzin The get_ib_device_match function iterates over the list of ib devices returned by the get_device_list glue function and returns the ib device matching the provided address. Since this function is in use by several drivers, in this patch we share the function in common part. Si

[dpdk-dev] [PATCH v2 11/16] common/mlx5: share hash list tool

From: Shiri Kuzin In order to use the hash list defined in net in other drivers, the hash list is moved to common utilities. In addition, the log definition was moved from the common utilities to a dedicated new log file in common in order to prevent a conflict. Signed-off-by: Shiri Kuzin Acke

[dpdk-dev] [PATCH v2 10/16] common/mlx5: add crypto BSF struct and defines

From: Dekel Peled This patch adds the struct defining crypto BSF segment of UMR WQE, and the related value definitions and offsets. Signed-off-by: Dekel Peled Acked-by: Matan Azrad --- drivers/common/mlx5/mlx5_prm.h | 66 ++ 1 file changed, 66 insertions(+) di

[dpdk-dev] [PATCH v2 09/16] common/mlx5: support general obj CRYPTO LOGIN create

From: Dekel Peled CRYPTO_LOGIN Object is used to login to the device as crypto user or crypto officer. Required in order to perform any crypto related control operations. This patch adds support of CRYPTO_LOGIN object create operation. Add reading of CRYPTO_LOGIN support capability. Add function

[dpdk-dev] [PATCH v2 08/16] common/mlx5: support general obj IMPORT KEK create

From: Dekel Peled IMPORT_KEK object is used to wrap (encrypt) critical security parameters, such as other keys and credentials, when those need to be passed between the device and the software. This patch add support of IMPORT_KEK object create operation. Add reading of IMPORT_KEK support capabi

[dpdk-dev] [PATCH v2 07/16] common/mlx5: fix cypto bsf attr

From: Suanming Mou This commit should be squash to crypto en commit. Signed-off-by: Suanming Mou --- drivers/common/mlx5/mlx5_devx_cmds.c | 4 1 file changed, 4 insertions(+) diff --git a/drivers/common/mlx5/mlx5_devx_cmds.c b/drivers/common/mlx5/mlx5_devx_cmds.c index 68a10b149a..7e3c8

[dpdk-dev] [PATCH v2 05/16] common/mlx5: support general object DEK create op

From: Dekel Peled Data Encryption Keys (DEKs) are the keys used for data encryption/decryption operations. Add reading of DEK support capability. Add function to create general object type DEK, using DevX API. Signed-off-by: Dekel Peled Acked-by: Matan Azrad --- drivers/common/mlx5/mlx5_devx

[dpdk-dev] [PATCH v2 06/16] common/mlx5: adjust DevX MKEY fields for crypto

From: Dekel Peled MKEY that will be used for crypto purposes must be created with crypto_en and remote access attributes. This patch adds support for them in the DevX MKEY context. Signed-off-by: Dekel Peled Acked-by: Matan Azrad --- drivers/common/mlx5/mlx5_devx_cmds.c | 5 + drivers/co

[dpdk-dev] [PATCH v2 04/16] common/mlx5: add HCA cap for AES-XTS crypto

From: Dekel Peled Update the PRM structure and HCA capabilities reading, to include relevant capabilities for AES-XTS crypto. Signed-off-by: Dekel Peled Acked-by: Matan Azrad --- drivers/common/mlx5/mlx5_devx_cmds.c | 3 +++ drivers/common/mlx5/mlx5_devx_cmds.h | 2 ++ drivers/common/mlx5/mlx

[dpdk-dev] [PATCH v2 03/16] common/mlx5: optimize read of general obj type caps

From: Dekel Peled General object types support is indicated in bitmap general_obj_types, which is part of HCA capabilities list. Currently this bitmap is read multiple times, and each time a different bit is extracted. This patch optimizes the code, reading the bitmap once into a local variable,

[dpdk-dev] [PATCH v2 02/16] common/mlx5: update GENEVE TLV OPT obj name

From: Dekel Peled Rename MLX5_OBJ_TYPE_GENEVE_TLV_OPT as MLX5_GENERAL_OBJ_TYPE_GENEVE_TLV_OPT, to align with other general objects names. Signed-off-by: Dekel Peled Acked-by: Matan Azrad --- drivers/common/mlx5/mlx5_devx_cmds.c | 2 +- drivers/common/mlx5/mlx5_prm.h | 4 ++-- 2 files ch

[dpdk-dev] [PATCH v2 00/16] mlx5 common part for crypto driver

The crypto PMD will be supported on Nvidia ConnectX6 The crypto PMD will add the support of encryption and decryption using the AES-XTS symmetric algorithm. The crypto PMD requires rdma-core and uses mlx5 DevX. This is the mlx5 common part that added support for DevX commands needed for crypto dr

[dpdk-dev] [PATCH v2 01/16] common/mlx5: remove redundant spaces in header file

From: Dekel Peled File drivers/common/mlx5/mlx5_prm.h includes structs representing data items as defined in PRM document. Some of these structs were copied as-is from kernel file mlx5_ifc.h. As result the structs are not all aligned with the same spacing. This patch removes redundant spaces and

Re: [dpdk-dev] [PATCH] net/bnxt: drop the unused attribute

On Thu, Apr 29, 2021 at 4:38 PM Ferruh Yigit wrote: > On 4/29/2021 5:20 AM, Kalesh Anakkur Purayil wrote: > > Hi Ferruh, > > > > On Wed, Apr 28, 2021 at 9:18 PM Ferruh Yigit > > wrote: > > > > On 4/23/2021 6:22 AM, Kalesh A P wrote: > > > From: Kalesh AP >

Re: [dpdk-dev] Use WFE for spinlock and ring

29/04/2021 16:28, Ruifeng Wang: > From: Thomas Monjalon > > 28/04/2021 11:30, Ruifeng Wang: > > > From: David Marchand > > > > On Sun, Apr 25, 2021 at 7:57 AM Ruifeng Wang > > > > wrote: > > > > > > > > > > The rte_wait_until_equal_xxx APIs abstract the functionality of > > > > > 'polling for a

[dpdk-dev] [PATCH-V5] config/arm: restore support for Qualcomm servers

>From the documentation: "The SoC configuration is a combination of implementer and CPU part number configuration and SoC-specific configuration." Align Qualcomm SoC configuration with the configuration of other server SoCs (eMAG, Kunpeng 9x0): add a soc configuration to the existing implementer

Re: [dpdk-dev] [PATCH v3 2/2] ring: use wfe to wait for ring tail update on aarch64

On Thu, 29 Apr 2021 14:35:35 + Ruifeng Wang wrote: > > -Original Message- > > From: Stephen Hemminger > > Sent: Thursday, April 29, 2021 1:17 AM > > To: Ruifeng Wang > > Cc: Honnappa Nagarahalli ; Konstantin > > Ananyev ; dev@dpdk.org; > > david.march...@redhat.com; tho...@monjalon.

Re: [dpdk-dev] [PATCH-V4] config/arm: restore support for Qualcomm servers

> -Original Message- > From: Thierry Herbelot > Sent: Thursday, April 29, 2021 6:07 PM > To: dev@dpdk.org > Cc: Thierry Herbelot ; tho...@monjalon.net; > Juraj Linkeš ; Honnappa Nagarahalli > ; Ruifeng Wang > > Subject: [PATCH-V4] config/arm: restore support for Qualcomm servers > > From

Re: [dpdk-dev] [PATCH v2 0/5] Fixes and supports for txgbe

On 4/29/2021 11:33 AM, Jiawen Wu wrote: > Fix some bugs, remove redundant code, add copyright. > > v2: > - Add a separate condition to enable and disable QINQ strip. > - Add support for VXLAN-GPE. > - Reword commit logs. > - Remove redundant 'retval' variable. > > Jiawen Wu (5): > net/txgbe: fi

Re: [dpdk-dev] [dpdk-stable] [PATCH v2 2/5] net/txgbe: fix VF MTU limit setting

On 4/29/2021 11:33 AM, Jiawen Wu wrote: > Add the dev_started check to remove the limitation of VF MTU setting. > When device is stopped, it is allowed to set MTU bigger than mbuf size. > Scattered rx may be enabled in next starting, exempt from setting in > EAL parameters. > I have reworded the

Re: [dpdk-dev] [PATCH v2 5/5] net/txgbe: add copyright owner

On 4/29/2021 11:33 AM, Jiawen Wu wrote: > All rights reserved by Beijing Wangxun Technology Co., Ltd. > Part of the code references Intel. > > Signed-off-by: Jiawen Wu Reviewed-by: Ferruh Yigit

  1   2   3   >