Re: [dpdk-dev] DTS Workgroup: MoM 06/09/2021

Hi Lijuan, I've given you the permissions, can you try now? Juraj > -Original Message- > From: dts On Behalf Of Tu, Lijuan > Sent: Wednesday, June 16, 2021 7:37 AM > To: Honnappa Nagarahalli ; Aaron Conole > ; Lincoln Lavoie ; Owen Hilyard > ; dev@dpdk.org; d...@dpdk.org > Cc: nd ; nd

[dpdk-dev] [PATCH] bus/pci: fix leak for unbound devices

For devices not bound to any Linux kernel module, we leak a pci object since it is never added to the PCI bus device list. Fixes: c79a1c67465d ("bus/pci: optimize bus scan") Cc: sta...@dpdk.org Reported-by: Owen Hilyard Signed-off-by: David Marchand --- drivers/bus/pci/linux/pci.c | 2 +- 1 fi

Re: [dpdk-dev] [PATCH v1] net/ice: fix RSS for L2 packet

> -Original Message- > From: Wu, Wenjun1 > Sent: Thursday, June 10, 2021 10:30 AM > To: dev@dpdk.org; Yang, Qiming ; Zhang, Qi Z > > Cc: Wu, Wenjun1 > Subject: [PATCH v1] net/ice: fix RSS for L2 packet > > L2 RSS support was deleted by mistake during code refactoring. This patch adds

Re: [dpdk-dev] [RFC 00/14] mlx5: support SubFunction

On Tue, Jun 15, 2021 at 12:47:13PM +, Parav Pandit wrote: > > But for some devices like our dma devices, > > it's just using mdev: > > > > https://www.spinics.net/lists/kvm/msg244417.html > Possibly yes. Some devices might live on mdev bus. > You should wait for kernel patches to be merged as

Re: [dpdk-dev] [RFC v3 0/6] Add mdev (Mediated device) support in DPDK

On Tue, Jun 15, 2021 at 09:48:24AM +0200, Thomas Monjalon wrote: > 15/06/2021 04:49, Xia, Chenbo: > > From: Thomas Monjalon > > > 01/06/2021 05:06, Chenbo Xia: > > > > Hi everyone, > > > > > > > > This is a draft implementation of the mdev (Mediated device [1]) > > > > support in DPDK PCI bus driv

[dpdk-dev] [PATCH] net/ice: fix integer overflow when computing max_pkt_len

The len variable, used in the computation of max_pkt_len could overflow, if used to store the result of the following computation: ICE_SUPPORT_CHAIN_NUM * rxq->rx_buf_len Since, we could define the mbuf size to have a large value (i.e 13312), and ICE_SUPPORT_CHAIN_NUM is defined as 5, the computa

[dpdk-dev] [Bug 738] dpdk-ethtool has emory leak

https://bugs.dpdk.org/show_bug.cgi?id=738 Bug ID: 738 Summary: dpdk-ethtool has emory leak Product: DPDK Version: unspecified Hardware: All OS: All Status: UNCONFIRMED Severity: normal Priority:

Re: [dpdk-dev] DTS Workgroup: MoM 06/09/2021

Hi Honnappa, I can't edit the file "DTS DPDK modifications", could you give me access? > -Original Message- > From: Honnappa Nagarahalli > Sent: 2021年6月16日 13:30 > To: Aaron Conole ; Tu, Lijuan ; > Lincoln Lavoie ; Owen Hilyard > ; dev@dpdk.org; d...@dpdk.org > Cc: nd ; Honnappa Nagaraha

[dpdk-dev] DTS Workgroup: MoM 06/09/2021

Attendees: Aaron Conole Honnappa Nagarahalli Lijuan Tu Lincoln Lavoie Owen Hilyard The meeting announcements are sent to dev@dpdk.org. Minutes: 1) The work item related discussions are captured in [1] Action Items: 1) Review [2] and understand how the code changes can be removed. Categorize the

Re: [dpdk-dev] [PATCH] ixgbe: Add runtime tx/rx queue setup for X550

Hi, Qi, OK, thanks indeed for the explanation, appreciated😊 BTW, I see patch is Superseded, does that mean it is not needed, or need update? > 1. why only enable this for x550, is it because you only need this or you > already know other ixgbe device has the limitation? I’m using this x550 devi

[dpdk-dev] [PATCH 2/2] net/tap: replace offload_capa function with define

Since the offload values are always the same, these can just be data instead of code. Signed-off-by: Stephen Hemminger --- drivers/net/tap/rte_eth_tap.c | 34 +- 1 file changed, 13 insertions(+), 21 deletions(-) diff --git a/drivers/net/tap/rte_eth_tap.c b/driver

[dpdk-dev] [PATCH 1/2] net/tap: remove useless offload capa functions

Since these always return 0, they were doing nothing useful. Signed-off-by: Stephen Hemminger --- drivers/net/tap/rte_eth_tap.c | 24 ++-- 1 file changed, 2 insertions(+), 22 deletions(-) diff --git a/drivers/net/tap/rte_eth_tap.c b/drivers/net/tap/rte_eth_tap.c index 573598

[dpdk-dev] [PATCH 0/2] net/tap: remove useless offload setup

This looks like some infrastructure that was set for some future change that never happened. Remove it. Stephen Hemminger (2): tap: remove useless offload capa functions tap: replace offload_capa function with define drivers/net/tap/rte_eth_tap.c | 58 +-- 1 f

[dpdk-dev] [PATCH v1 14/14] common/mlx5: clean up legacy PCI bus driver

Clean up legacy PCI bus driver since all mlx5 PMDs moved to new common PCI bus driver. Signed-off-by: Xueming Li --- drivers/common/mlx5/linux/mlx5_common_os.h | 1 - drivers/common/mlx5/mlx5_common.c | 1 - drivers/common/mlx5/mlx5_common.h | 1 + drivers/common/mlx5/mlx

[dpdk-dev] [PATCH v1 12/14] vdpa/mlx5: support SubFunction

From: Thomas Monjalon Supports SubFunction on auxiliary bus. SF probe devargs: auxiliary:mlx5_core.sf.,class=vdpa Signed-off-by: Thomas Monjalon --- doc/guides/vdpadevs/mlx5.rst | 10 ++ drivers/vdpa/mlx5/mlx5_vdpa.c | 8 ++-- 2 files changed, 16 insertions(+), 2 deletions(-)

[dpdk-dev] [PATCH v1 13/14] compress/mlx5: migrate to common driver

To support auxiliary bus, upgrades driver to use mlx5 common driver structure. Signed-off-by: Xueming Li --- drivers/compress/mlx5/mlx5_compress.c | 71 ++- 1 file changed, 15 insertions(+), 56 deletions(-) diff --git a/drivers/compress/mlx5/mlx5_compress.c b/drivers/co

[dpdk-dev] [PATCH v1 11/14] vdpa/mlx5: remove PCI specifics

From: Thomas Monjalon Removes PCI specific driver, replaces with common class driver. Signed-off-by: Thomas Monjalon --- drivers/vdpa/mlx5/mlx5_vdpa.c | 119 ++ drivers/vdpa/mlx5/mlx5_vdpa.h | 1 - 2 files changed, 34 insertions(+), 86 deletions(-) diff --git

[dpdk-dev] [PATCH v1 10/14] vdpa/mlx5: define driver name as macro

From: Thomas Monjalon Uses macro for pmd driver name. Signed-off-by: Thomas Monjalon --- drivers/vdpa/mlx5/mlx5_vdpa.c | 9 + 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/drivers/vdpa/mlx5/mlx5_vdpa.c b/drivers/vdpa/mlx5/mlx5_vdpa.c index 8b5bfd8c3d..5ab7c525c2 100644

[dpdk-dev] [PATCH v1 09/14] regex/mlx5: migrate to common driver

To support auxiliary bus, upgrades driver to use mlx5 common driver structure. Signed-off-by: Xueming Li --- drivers/regex/mlx5/mlx5_regex.c | 49 - drivers/regex/mlx5/mlx5_regex.h | 1 - 2 files changed, 18 insertions(+), 32 deletions(-) diff --git a/drivers/re

[dpdk-dev] [PATCH v1 08/14] net/mlx5: check max Verbs port number

Verbs API doesn't support Device port number larger than 255 by design. Adds check and fails probing with proper error log. Signed-off-by: Xueming Li --- drivers/net/mlx5/linux/mlx5_os.c | 6 ++ 1 file changed, 6 insertions(+) diff --git a/drivers/net/mlx5/linux/mlx5_os.c b/drivers/net/mlx5

[dpdk-dev] [PATCH v1 07/14] net/mlx5: support SubFunction

This patch introduces SF support. Similar to VF, SF on auxiliary bus is a portion of hardware PF, no representor or bonding parameters for SF. Devargs to support SF: -a auxiliary:mlx5_core.sf.8,dv_flow_en=1 New global syntax to support SF: -a bus=auxiliary,name=mlx5_core.sf.8/class=eth/driver=mlx

[dpdk-dev] [PATCH v1 06/14] net/mlx5: migrate to bus-agnostic common driver

To support SubFunction based on auxiliary bus, common driver supports new bus-agnostic driver. This patch migrates net driver to new common driver. Signed-off-by: Xueming Li --- drivers/net/mlx5/linux/mlx5_os.c | 46 ++-- drivers/net/mlx5/linux/mlx5_os.h | 3 --- dr

[dpdk-dev] [PATCH v1 05/14] net/mlx5: remove PCI dependency

To support more bus types, remove PCI dependency where possible. Signed-off-by: Xueming Li --- drivers/net/mlx5/linux/mlx5_ethdev_os.c | 2 +- drivers/net/mlx5/linux/mlx5_os.c| 4 ++-- drivers/net/mlx5/mlx5.c | 24 +++- drivers/net/mlx5/mlx5.h

[dpdk-dev] [PATCH v1 04/14] common/mlx5: get PCI device address from any bus

From: Thomas Monjalon A function is exported to allow retrieving the PCI address of the parent PCI device of a Sub-Function in auxiliary bus sysfs. The function mlx5_dev_to_pci_str() is accepting both PCI and auxiliary devices. In case of a PCI device, it is simply using the device name. The fun

[dpdk-dev] [PATCH v1 03/14] common/mlx5: support auxiliary bus

This patch adds auxiliary bus driver and delegate to registered internal mlx5 common device drivers, i.e. eth, vdpa... Current major target is to support SubFunction on auxiliary bus. As a limitation of current driver, numa node of device is detected from PCI bus of device symbol link, will remov

[dpdk-dev] [PATCH v1 02/14] common/mlx5: move description of PCI sysfs functions

From: Thomas Monjalon The Linux-specific functions mlx5_get_pci_addr() and mlx5_get_ifname_sysfs() are better described in the .h file. The requirement for using mlx5_get_pci_addr() is explicit: the node /device must exist in the provided sysfs path. Signed-off-by: Thomas Monjalon --- drivers

[dpdk-dev] [PATCH v1 01/14] common/mlx5: add common device driver

To support auxiliary bus, introduces common device driver and callbacks, suppose to replace current mlx5 common PCI bus driver. mlx5 common PCI bus driver still used by mlx5 eth, vDPA and regex PMD, will remove once all PMD drivers adapt to new common driver. Signed-off-by: Xueming Li --- drive

[dpdk-dev] [PATCH v1 00/14] net/mlx5: support Sub-Function

Sub-Function [1] is a portion of the PCI device, a SF netdev has its own dedicated queues(txq, rxq). A SF shares PCI level resources with other SFs and/or with its parent PCI function. Auxiliary bus is the fundamental of SF. This patch set introduces Sub-Function support for mlx5 PMD driver includ

[dpdk-dev] [PATCH v1 2/2] devtools: auto detect branch to search fix patches

Current fix scan scripts scanned specified range in current(HEAD) branch. When users run it in an earlier branch, few patches were scanned. This patch introduces optional argument, auto detects from range if not provided. Fixes: 752d8e097ec1 ("scripts: show fixes with release version of bug") Cc

[dpdk-dev] [PATCH v1 1/2] devtools: fix version pattern for fix search

When scanning fixes from current(HEAD) branch, local tags were included and reported as version. For example: $ git tag --contains --merged 20.11_backport_202010506 // user tag v20.11 v20.11.1 This patch matches DPDK officail version pattern in search, selects the most early tag. Offici

[dpdk-dev] [Bug 737] dpdk test_mbuf has heap-buffer-overflow

https://bugs.dpdk.org/show_bug.cgi?id=737 Bug ID: 737 Summary: dpdk test_mbuf has heap-buffer-overflow Product: DPDK Version: unspecified Hardware: All OS: All Status: UNCONFIRMED Severity: normal

[dpdk-dev] [Bug 727] [build]Some branch build failed on Fedora34 with gcc 11/clang12

https://bugs.dpdk.org/show_bug.cgi?id=727 longfengx.li...@intel.com (longfengx.li...@intel.com) changed: What|Removed |Added Status|UNCONFIRMED |RESOLVED

[dpdk-dev] [Bug 735] [asan] driver bonding has memory leak

https://bugs.dpdk.org/show_bug.cgi?id=735 Bug ID: 735 Summary: [asan] driver bonding has memory leak Product: DPDK Version: unspecified Hardware: All OS: All Status: UNCONFIRMED Severity: normal

[dpdk-dev] [PATCH v2 8/8] test/rcu: use GCC atomic builtins for data sync

Covert rte_atomic usages to GCC atomic builtins in rcu_perf testcases. Signed-off-by: Joyce Kong Reviewed-by: Ruifeng Wang Acked-by: Stephen Hemminger --- app/test/test_rcu_qsbr_perf.c | 98 +-- 1 file changed, 49 insertions(+), 49 deletions(-) diff --git a/app

[dpdk-dev] [PATCH v2 7/8] test/service_cores: use GCC atomic builtins for lock sync

Convert rte_atomic usages to GCC atomic builtins for lock sync in service core testcases. Signed-off-by: Joyce Kong Reviewed-by: Ruifeng Wang Acked-by: Stephen Hemminger --- app/test/test_service_cores.c | 36 +++ 1 file changed, 20 insertions(+), 16 deletions(-

[dpdk-dev] [PATCH v2 6/8] test/mempool_perf: use GCC atomic builtins for lcores sync

Convert rte_atomic usages to GCC atomic builtins for lcores sync in mempool_perf testcases. Meanwhile, remove unnecessary synchro init as it would be set to 0 when launching cores. Signed-off-by: Joyce Kong Reviewed-by: Ruifeng Wang Acked-by: Stephen Hemminger --- app/test/test_mempool_perf.c

[dpdk-dev] [PATCH v2 5/8] test/mempool: remove unused variable for lcores sync

Remove the unused synchro variable as there is no lcores sync in mempool function test. Signed-off-by: Joyce Kong Reviewed-by: Ruifeng Wang Acked-by: Stephen Hemminger --- app/test/test_mempool.c | 5 - 1 file changed, 5 deletions(-) diff --git a/app/test/test_mempool.c b/app/test/test_me

[dpdk-dev] [PATCH v2 4/8] test/mcslock: use GCC atomic builtins for lcores sync

Convert rte_atomic usages to GCC atomic builtins for lcores sync in mcslock testcases. Signed-off-by: Joyce Kong Reviewed-by: Ruifeng Wang Acked-by: Stephen Hemminger --- app/test/test_mcslock.c | 14 ++ 1 file changed, 6 insertions(+), 8 deletions(-) diff --git a/app/test/test_mc

[dpdk-dev] [PATCH v2 3/8] test/rwlock: use GCC atomic builtins for lcores sync

Convert rte_atomic usages to GCC atomic builtins for lcores sync in rwlock testcases. Signed-off-by: Joyce Kong Reviewed-by: Ruifeng Wang Acked-by: Stephen Hemminger --- app/test/test_rwlock.c | 10 -- 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/app/test/test_rwlock.c

[dpdk-dev] [PATCH v2 2/8] test/spinlock: use GCC atomic builtins for lcores sync

Convert rte_atomic usages to GCC atomic builtins for lcores sync in spinlock testcases. Signed-off-by: Joyce Kong Reviewed-by: Ruifeng Wang Acked-by: Stephen Hemminger --- app/test/test_spinlock.c | 9 - 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/app/test/test_spinlo

[dpdk-dev] [PATCH v2 1/8] test/ticketlock: use GCC atomic builtins for lcores sync

Convert rte_atomic usages to GCC atomic builtins for lcores sync in ticketlock testcases. Signed-off-by: Joyce Kong Reviewed-by: Ruifeng Wang Reviewed-by: Honnappa Nagarahalli Acked-by: Stephen Hemminger --- app/test/test_ticketlock.c | 10 -- 1 file changed, 4 insertions(+), 6 deleti

[dpdk-dev] [PATCH v2 0/8] use GCC's C11 atomic builtins for test

Since C11 memory model is adopted in DPDK now[1], use GCC's atomic builtins in test cases. [1] https://www.dpdk.org/blog/2021/03/26/dpdk-adopts-the-c11-memory-model/ v2: Use rte_wait_until_equal() instead of original sync loops. v1: The initial version. Joyce Kong (8): test/ticketlock: u

Re: [dpdk-dev] [RFC PATCH] dmadev: introduce DMA device library

> -Original Message- > From: dev On Behalf Of Chengwen Feng > Sent: Tuesday, June 15, 2021 21:22 > To: tho...@monjalon.net; Yigit, Ferruh > Cc: dev@dpdk.org; nipun.gu...@nxp.com; hemant.agra...@nxp.com; > maxime.coque...@redhat.com; > honnappa.nagaraha...@arm.com; jer...@marvell.com; dav

[dpdk-dev] [PATCH 2/2] net/ice: fix VXLAN flow director creation error

From: Dapeng Yu In original implementation, error returned when creating VXLAN flow director with SCTP or TCP as layer 4 protocol of inner segment. There are several root causes for the error: 1. ice_fdir_input_set_hdrs() set ICE_FLOW_SEG_HDR_UDP into protocol header flag of inner segment of VXL

[dpdk-dev] [PATCH 1/2] net/ice/base: fix VXLAN flow director creation error

From: Dapeng Yu In original implementation, error returned when creating VXLAN flow director with SCTP or TCP as layer 4 protocol of inner segment. There are several root causes for the error: 1. ice_fdir_udp4_vxlan_pkt[] is not adapted to the TCP and SCTP protocol. Its length cannot hold TCP he

Re: [dpdk-dev] [PATCH] ixgbe: Add runtime tx/rx queue setup for X550

Hi Jianyue: I think you can ignore those warning. Below are couple questions for this patch: 1. why only enable this for x550, is it because you only need this or you already know other ixgbe device has the limitation? 2 . As the patch expose the new feature of the driver, could you provide

Re: [dpdk-dev] [PATCH v2 00/58] enhancements to host based flow table management

On Sat, Jun 12, 2021 at 5:06 PM Ajit Khaparde wrote: > > This patchset adds flow table management support for > Thor network adapter and introduces enhancements to > the existing flow table management functionality. > > v1->v2: > - Rebased against latest dpdk-next-net-brcm for-next-net branch. >

Re: [dpdk-dev] [PATCH] gpudev: introduce memory API

15/06/2021 20:24, Ferruh Yigit: > On 6/8/2021 7:34 AM, Thomas Monjalon wrote: > > 08/06/2021 06:10, Jerin Jacob: > >> On Mon, Jun 7, 2021 at 10:17 PM Thomas Monjalon > >> wrote: > >>> > >>> 07/06/2021 15:54, Jerin Jacob: > On Mon, Jun 7, 2021 at 4:13 PM Thomas Monjalon > wrote: >

Re: [dpdk-dev] [PATCH] gpudev: introduce memory API

On 6/8/2021 7:34 AM, Thomas Monjalon wrote: > 08/06/2021 06:10, Jerin Jacob: >> On Mon, Jun 7, 2021 at 10:17 PM Thomas Monjalon wrote: >>> >>> 07/06/2021 15:54, Jerin Jacob: On Mon, Jun 7, 2021 at 4:13 PM Thomas Monjalon wrote: > 07/06/2021 09:20, Wang, Haiyue: >> From: Honnappa Naga

[dpdk-dev] [PATCH] bus/pci: Fix PowerNV platform detection logic

Fix the IOMMU detection logic that looks for the "platform" field of /proc/cpuinfo on POWER systems. Fixes: 905215731833 ("bus/pci: support IOVA as VA on PowerNV systems") Signed-off-by: David Christensen --- drivers/bus/pci/linux/pci.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) dif

Re: [dpdk-dev] [RFC 2/2] app/testpmd: support VXLAN last 8-bits field matching

Hi Rongwei, As per VxLAN RFC 7348- Reserved fields (24 bits and 8 bits): MUST be set to zero on transmission and ignored on receipt. I hope this criteria will be met for external packets. On 5/31/2021 3:49 PM, rongwei liu wrote: Add a new testp

Re: [dpdk-dev] [RFC PATCH] dmadev: introduce DMA device library

On Tue, Jun 15, 2021 at 09:22:07PM +0800, Chengwen Feng wrote: > This patch introduces 'dmadevice' which is a generic type of DMA > device. > > The APIs of dmadev library exposes some generic operations which can > enable configuration and I/O with the DMA devices. > > Signed-off-by: Chengwen Fen

Re: [dpdk-dev] [PATCH] bus: clarify log for non-NUMA-aware devices

On Tue, 15 Jun 2021 13:51:55 +0300 Dmitry Kozlyuk wrote: > diff --git a/drivers/bus/pci/pci_common.c b/drivers/bus/pci/pci_common.c > index 35d7d092d1..bf06f81229 100644 > --- a/drivers/bus/pci/pci_common.c > +++ b/drivers/bus/pci/pci_common.c > @@ -190,7 +190,7 @@ rte_pci_probe_one_driver(struct

Re: [dpdk-dev] [PATCH v2 53/62] net/cnxk: support for rss in rte_flow

On Mon, Jun 7, 2021 at 11:39 PM Nithin Dabilpuram wrote: > > From: Satheesh Paul > > Added support for rss action in rte_flow code based on ROC. > > Signed-off-by: Satheesh Paul > --- > drivers/net/cnxk/cnxk_rte_flow.c | 72 > +++- Looks like we missed updat

Re: [dpdk-dev] [PATCH] parray: introduce internal API for dynamic arrays

> > 15/06/2021 12:08, Ananyev, Konstantin: > > > 15/06/2021 11:33, Ananyev, Konstantin: > > > > > 14/06/2021 17:48, Jerin Jacob: > > > > > > On Mon, Jun 14, 2021 at 8:29 PM Ananyev, Konstantin > > > > > > wrote: > > > > > > > I had only a quick look at your approach so far. > > > > > > > But fr

[dpdk-dev] [PATCH v2 3/3] vhost: handle memory hotplug for async vhost

From: Jiayu Hu When the guest memory is hotplugged, the vhost application which enables DMA acceleration must stop DMA transfers before the vhost re-maps the guest memory. This patch is to notify the vhost application of stopping DMA transfers. Signed-off-by: Jiayu Hu --- lib/vhost/vhost_user

[dpdk-dev] [PATCH v2 2/3] examples/vhost: handle memory hotplug for async vhost

When the guest memory is hotplugged, the vhost application which enables DMA acceleration must stop DMA transfers before the vhost re-maps the guest memory. To accomplish that, we need to do these changes in the vhost sample: 1. add inflight pkt count. 2. add vring_state_changed() callback. 3. add

[dpdk-dev] [PATCH v2 1/3] vhost: add unsafe API to drain pkts in async vhost

Applications need to stop DMA transfers and finish all the in-flight pkts when in VM memory hot-plug case and async vhost is used. This patch is to provide an unsafe API to drain in-flight pkts which are submitted to DMA engine in vhost async data path. Signed-off-by: Cheng Jiang --- lib/vhost/r

[dpdk-dev] [PATCH v2 0/3] vhost: handle memory hotplug for async vhost

When the guest memory is hotplugged, the vhost application which enables DMA acceleration must stop DMA transfers before the vhost re-maps the guest memory. This patch set is to provide an unsafe API to drain in-flight pkts which are submitted to DMA engine in vhost async data path, and notify the

Re: [dpdk-dev] [PATCH] parray: introduce internal API for dynamic arrays

15/06/2021 12:08, Ananyev, Konstantin: > > 15/06/2021 11:33, Ananyev, Konstantin: > > > > 14/06/2021 17:48, Jerin Jacob: > > > > > On Mon, Jun 14, 2021 at 8:29 PM Ananyev, Konstantin > > > > > wrote: > > > > > > I had only a quick look at your approach so far. > > > > > > But from what I can read,

Re: [dpdk-dev] [PATCH v4] mbuf: fix reset on mbuf free

> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Olivier Matz > Sent: Wednesday, 13 January 2021 14.28 [snip] > Fixes: 8f094a9ac5d7 ("mbuf: set mbuf fields while in pool") > Cc: sta...@dpdk.org > > Signed-off-by: Olivier Matz > Acked-by: Morten Brørup > Acked-by: Ajit Khaparde > Acked-b

Re: [dpdk-dev] mbuf next field belongs in the first cacheline

> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Bruce Richardson > Sent: Tuesday, 15 June 2021 15.05 > > On Tue, Jun 15, 2021 at 02:16:27PM +0200, Morten Brørup wrote: > > MBUF and MLX5 maintainers, > > > > I'm picking up an old discussion, which you might consider pursuing. > Feel free to

[dpdk-dev] [RFC PATCH] dmadev: introduce DMA device library

This patch introduces 'dmadevice' which is a generic type of DMA device. The APIs of dmadev library exposes some generic operations which can enable configuration and I/O with the DMA devices. Signed-off-by: Chengwen Feng --- lib/dmadev/rte_dmadev.h | 531 +++

Re: [dpdk-dev] mbuf next field belongs in the first cacheline

On Tue, Jun 15, 2021 at 02:16:27PM +0200, Morten Brørup wrote: > MBUF and MLX5 maintainers, > > I'm picking up an old discussion, which you might consider pursuing. Feel > free to ignore, if you consider this discussion irrelevant or already closed > and done with. > > The Techboard has previou

[dpdk-dev] [PATCH] devtools: fix file listing in maintainers check

When having multiple working trees, the main one has a .git directory while attached trees have a .git file. Thus the git check should work for both file and directory. In the case there is no working tree (.git not readable), the command "find" is used and should be able to list paths with wildca

Re: [dpdk-dev] [PATCH v2 51/62] net/cnxk: add ethdev firmware version get

On Mon, Jun 7, 2021 at 11:39 PM Nithin Dabilpuram wrote: > > From: Satha Rao > > Add callback to get ethdev firmware version. > > Signed-off-by: Satha Rao > +int > +cnxk_nix_fw_version_get(struct rte_eth_dev *eth_dev, char *fw_version, > + size_t fw_size) > +{ > + st

Re: [dpdk-dev] [RFC 00/14] mlx5: support SubFunction

> From: Xia, Chenbo > Sent: Tuesday, June 15, 2021 4:49 PM > > > > > > Just FYI: > > > > > > We are introducing a new mdev bus for DPDK: > > > http://patchwork.dpdk.org/project/dpdk/cover/20210601030644.3318-1- > > > chenbo@intel.com/ > > > > > I am yet to read about it. But I am not sure w

Re: [dpdk-dev] [PATCH v2 49/62] net/cnxk: add initial version of rte flow support

On Mon, Jun 7, 2021 at 11:39 PM Nithin Dabilpuram wrote: > > From: Kiran Kumar K > > Adding initial version of rte_flow support for cnxk family device. > Supported rte_flow ops are flow_validate, flow_create, flow_crstroy, > flow_flush, flow_query, flow_isolate. > > Signed-off-by: Kiran Kumar K

Re: [dpdk-dev] [PATCH v2 38/62] net/cnxk: add flow ctrl set/get ops

On Mon, Jun 7, 2021 at 11:37 PM Nithin Dabilpuram wrote: > > From: Sunil Kumar Kori > > Patch implements set and get operations for flow control. > > Signed-off-by: Sunil Kumar Kori > --- > + > + /* Check if TX pause frame is already enabled or not */ > + if (fc->tx_pause ^ tx_pause

Re: [dpdk-dev] [PATCH v2 14/62] net/cnxk: add link status update support

On Mon, Jun 7, 2021 at 11:35 PM Nithin Dabilpuram wrote: > > Add link status update callback to get current > link status. > > Signed-off-by: Nithin Dabilpuram > --- > doc/guides/nics/cnxk.rst | 1 + > doc/guides/nics/features/cnxk.ini | 2 + > doc/guides/nics/features/cnxk_

Re: [dpdk-dev] [PATCH v2 13/62] net/cnxk: add device configuration operation

On Mon, Jun 7, 2021 at 11:34 PM Nithin Dabilpuram wrote: > > Add device configuration op for CN9K and CN10K. Most of the > device configuration is common between two platforms except for > some supported offloads. > > Signed-off-by: Nithin Dabilpuram > +static int > +nix_restore_queue_cfg(struct

Re: [dpdk-dev] [PATCH v2 10/62] net/cnxk: add platform specific probe and remove

On Mon, Jun 7, 2021 at 11:34 PM Nithin Dabilpuram wrote: > > Add platform specific probe and remove callbacks for CN9K > and CN10K which use common probe and remove functions. > Register ethdev driver for CN9K and CN10K. > > Signed-off-by: Nithin Dabilpuram Reviewed-by: Jerin Jacob > --- > d

[dpdk-dev] [PATCH v14] app/testpmd: support multi-process

This patch adds multi-process support for testpmd. The test cmd example as follows: the primary cmd: ./dpdk-testpmd -a xxx --proc-type=auto -l 0-1 -- -i \ --rxq=4 --txq=4 --num-procs=2 --proc-id=0 the secondary cmd: ./dpdk-testpmd -a xxx --proc-type=auto -l 2-3 -- -i \ --rxq=4 --txq=4 --num-procs=

Re: [dpdk-dev] [RFC PATCH v2 2/3] example/qos_sched: add PIE support

> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Liguzinski, > WojciechX > Sent: Tuesday, 15 June 2021 11.02 [snip] > diff --git a/config/rte_config.h b/config/rte_config.h > index 590903c07d..48132f27df 100644 > --- a/config/rte_config.h > +++ b/config/rte_config.h > @@ -89,7 +89,6 @@ > #

[dpdk-dev] mbuf next field belongs in the first cacheline

MBUF and MLX5 maintainers, I'm picking up an old discussion, which you might consider pursuing. Feel free to ignore, if you consider this discussion irrelevant or already closed and done with. The Techboard has previously discussed the organization of the mbuf fields. Ref: http://mails.dpdk.or

Re: [dpdk-dev] [PATCH v13] app/testpmd: support multi-process

Hi, Andrew, see replies below, and others without no reply will be fixed in v14. 在 2021/6/8 16:42, Andrew Rybchenko 写道: @Thomas, @Ferruh, please, see question below. On 4/22/21 4:18 AM, Min Hu (Connor) wrote: This patch adds multi-process support for testpmd. The test cmd example as fo

Re: [dpdk-dev] [PATCH v2 6/6] vhost: convert inflight data to DPDK allocation API

On 6/15/21 11:25 AM, David Marchand wrote: > On Tue, Jun 15, 2021 at 10:43 AM Maxime Coquelin > wrote: >> @@ -559,6 +559,31 @@ numa_realloc(struct virtio_net *dev, int index) >> vq->log_cache = lc; >> } >> >> + if (vq->resubmit_inflight) { >> + struct

Re: [dpdk-dev] [RFC 00/14] mlx5: support SubFunction

Hi Parav, > -Original Message- > From: Parav Pandit > Sent: Tuesday, June 15, 2021 1:43 PM > To: Xia, Chenbo ; NBU-Contact-Thomas Monjalon > ; Yigit, Ferruh > Cc: Xueming(Steven) Li ; Slava Ovsiienko > ; dev@dpdk.org; Jason Gunthorpe > Subject: RE: [dpdk-dev] [RFC 00/14] mlx5: support S

Re: [dpdk-dev] [PATCH] bus: clarify log for non-NUMA-aware devices

> -Original Message- > From: Dmitry Kozlyuk > Sent: Tuesday, June 15, 2021 6:44 PM > To: dev@dpdk.org > Cc: Xueming(Steven) Li ; sta...@dpdk.org; Marcin Wojtas > ; Michal Krawczyk > ; Guy Tzalik ; Evgeny Schemeilin > ; Igor Chauskin > ; Stephen Hemminger ; > NBU-Contact-longli ; Serg

[dpdk-dev] [PATCH v2 32/32] raw/cnxk_bphy: support for bphy selftest

Add support for performing selftest. Signed-off-by: Jakub Palider Signed-off-by: Tomasz Duszynski --- doc/guides/rawdevs/cnxk_bphy.rst | 7 +- drivers/raw/cnxk_bphy/cnxk_bphy.c | 124 ++ 2 files changed, 127 insertions(+), 4 deletions(-) diff --git a/doc/guides/r

[dpdk-dev] [PATCH v2 31/32] raw/cnxk_bphy: support for registering bphy irq handlers

Custom irq handlers may be registered/removed on demand. Since registration and removal are related they are in the same patch. Signed-off-by: Jakub Palider Signed-off-by: Tomasz Duszynski --- doc/guides/rawdevs/cnxk_bphy.rst | 13 drivers/raw/cnxk_bphy/cnxk_bphy.c | 11 ++

[dpdk-dev] [PATCH v2 30/32] raw/cnxk_bphy: support for retrieving bphy device memory

Allow user to retrieve baseband phy memory resources. Signed-off-by: Jakub Palider Signed-off-by: Tomasz Duszynski --- doc/guides/rawdevs/cnxk_bphy.rst | 10 + drivers/raw/cnxk_bphy/cnxk_bphy.c | 3 +++ drivers/raw/cnxk_bphy/cnxk_bphy_irq.c | 8 +++ drivers/raw/cnxk_bphy/

[dpdk-dev] [PATCH v2 29/32] raw/cnxk_bphy: support for reading number of bphy irqs

Add support for retrieving maximum number of interrupts. Signed-off-by: Jakub Palider Signed-off-by: Tomasz Duszynski --- drivers/raw/cnxk_bphy/cnxk_bphy_irq.c | 12 drivers/raw/cnxk_bphy/cnxk_bphy_irq.h | 1 + 2 files changed, 13 insertions(+) diff --git a/drivers/raw/cnxk_bphy/

[dpdk-dev] [PATCH v2 28/32] raw/cnxk_bphy: support for interrupt init and cleanup

Add support for interrupt initialization and cleanup. Internally interrupt initialization performs low level setup that allows custom interrupt handler registration later on. Interrupt initialization and cleanup are related hence they are in the same patch. Signed-off-by: Jakub Palider Signed-of

[dpdk-dev] [PATCH v2 27/32] raw/cnxk_bphy: support for bphy dequeue operation

Add support for dequeueing responses to previously enqueued messages. Signed-off-by: Jakub Palider Signed-off-by: Tomasz Duszynski --- drivers/raw/cnxk_bphy/cnxk_bphy.c | 20 1 file changed, 20 insertions(+) diff --git a/drivers/raw/cnxk_bphy/cnxk_bphy.c b/drivers/raw/cnx

[dpdk-dev] [PATCH v2 26/32] raw/cnxk_bphy: support for bphy enqueue operation

Add preliminary support for enqueue operation. Signed-off-by: Jakub Palider Signed-off-by: Tomasz Duszynski --- drivers/raw/cnxk_bphy/cnxk_bphy.c| 26 ++ drivers/raw/cnxk_bphy/rte_pmd_bphy.h | 13 + 2 files changed, 39 insertions(+) diff --git a/drivers/

[dpdk-dev] [PATCH v2 25/32] raw/cnxk_bphy: support for reading bphy queue count

Add support for reading number of available queues from baseband phy. Currently only single queue is supported. Signed-off-by: Jakub Palider Signed-off-by: Tomasz Duszynski --- drivers/raw/cnxk_bphy/cnxk_bphy.c | 9 + drivers/raw/cnxk_bphy/cnxk_bphy_irq.h | 7 +++ 2 files change

[dpdk-dev] [PATCH v2 24/32] raw/cnxk_bphy: support for reading bphy queue configuration

Add support for reading baseband phy queue configuration. Signed-off-by: Jakub Palider Signed-off-by: Tomasz Duszynski --- drivers/raw/cnxk_bphy/cnxk_bphy.c | 17 + 1 file changed, 17 insertions(+) diff --git a/drivers/raw/cnxk_bphy/cnxk_bphy.c b/drivers/raw/cnxk_bphy/cnxk_bph

[dpdk-dev] [PATCH v2 23/32] raw/cnxk_bphy: add baseband PHY skeleton driver

Add baseband phy skeleton driver. Baseband phy is a hardware subsystem accelerating 5G/LTE related tasks. Note this driver isn't involved into any sort baseband protocol processing. Instead it just provides means for configuring hardware. Signed-off-by: Jakub Palider Signed-off-by: Tomasz Duszyns

[dpdk-dev] [PATCH v2 22/32] common/cnxk: support for registering bphy irq

Add support for registering user supplied baseband phy irq handler. Signed-off-by: Jakib Palider Signed-off-by: Tomasz Duszynski --- drivers/common/cnxk/roc_bphy_irq.c | 38 ++ drivers/common/cnxk/roc_bphy_irq.h | 11 + drivers/common/cnxk/version.map| 1

[dpdk-dev] [PATCH v2 21/32] common/cnxk: support for clearing bphy irq handler

Add support for clearing previously register baseband phy irq handler. Signed-off-by: Jakub Palider Signed-off-by: Tomasz Duszynski --- drivers/common/cnxk/roc_bphy_irq.c | 66 ++ drivers/common/cnxk/roc_bphy_irq.h | 2 + drivers/common/cnxk/version.map| 1 + 3

[dpdk-dev] [PATCH v2 20/32] common/cnxk: support for setting bphy irq handler

Add support for setting custom baseband phy irq handler. Signed-off-by: Jakub Palider Signed-off-by: Tomasz Duszynski --- drivers/common/cnxk/roc_bphy_irq.c | 121 +++ drivers/common/cnxk/roc_bphy_irq.h | 5 ++ drivers/common/cnxk/roc_io.h | 9 ++ drivers

[dpdk-dev] [PATCH v2 19/32] common/cnxk: support for removing irq stack

Add support for removing existing irq stack. Signed-off-by: Jakub Palider Signed-off-by: Tomasz Duszynski --- drivers/common/cnxk/roc_bphy_irq.c | 30 ++ drivers/common/cnxk/roc_bphy_irq.h | 1 + drivers/common/cnxk/version.map| 1 + 3 files changed, 32 inserti

[dpdk-dev] [PATCH v2 18/32] common/cnxk: support for retrieving irq stack

Add support for retrieving irq stack. If stack does not exist then it gets created. Signed-off-by: Jakub Palider Signed-off-by: Tomasz Duszynski --- drivers/common/cnxk/roc_bphy_irq.c | 62 ++ drivers/common/cnxk/roc_bphy_irq.h | 1 + drivers/common/cnxk/version.map

[dpdk-dev] [PATCH v2 17/32] common/cnxk: support for checking irq availability

Add support for checking whether given irq is available. Signed-off-by: Jakub Palider Signed-off-by: Tomasz Duszynski --- drivers/common/cnxk/roc_bphy_irq.c | 9 + drivers/common/cnxk/roc_bphy_irq.h | 2 ++ drivers/common/cnxk/version.map| 1 + 3 files changed, 12 insertions(+) dif

[dpdk-dev] [PATCH v2 16/32] common/cnxk: support for baseband PHY irq setup

Add support for initializing baseband phy irqs. While at it also add support for reverting back to the default state. Signed-off-by: Jakub Palider Signed-off-by: Tomasz Duszynski --- drivers/common/cnxk/meson.build| 1 + drivers/common/cnxk/roc_bphy_irq.c | 96 +

[dpdk-dev] [PATCH v2 15/32] common/cnxk: support for device init and fini

Add support for device init and fini. It merely saves baseband phy state container in a globally accessible resource chest. Signed-off-by: Jakub Palider Signed-off-by: Tomasz Duszynski --- drivers/common/cnxk/meson.build | 1 + drivers/common/cnxk/roc_api.h | 4 +++ drivers/common/c

[dpdk-dev] [PATCH v2 14/32] raw/cnxk_bphy: support for performing selftest

Add support for performing selftest operation. Signed-off-by: Tomasz Duszynski Signed-off-by: Jakub Palider --- doc/guides/rawdevs/cnxk_bphy.rst | 19 +- drivers/raw/cnxk_bphy/cnxk_bphy_cgx.c | 2 + drivers/raw/cnxk_bphy/cnxk_bphy_cgx.h | 10 + drivers/raw/cnxk_bphy/cnxk

[dpdk-dev] [PATCH v2 13/32] raw/cnxk_bphy: support for dequeue operation

Add support for dequeueing responses to previously enqueued messages. Signed-off-by: Tomasz Duszynski Signed-off-by: Jakub Palider --- drivers/raw/cnxk_bphy/cnxk_bphy_cgx.c | 27 +++ 1 file changed, 27 insertions(+) diff --git a/drivers/raw/cnxk_bphy/cnxk_bphy_cgx.c b/

[dpdk-dev] [PATCH v2 12/32] raw/cnxk_bphy: support for enqueue operation

Add support for enqueueing messages. Signed-off-by: Tomasz Duszynski Signed-off-by: Jakub Palider --- doc/guides/rawdevs/cnxk_bphy.rst | 68 drivers/raw/cnxk_bphy/cnxk_bphy_cgx.c | 112 ++ drivers/raw/cnxk_bphy/meson.build | 1 + drivers/raw/

  1   2   >