Re: [dpdk-dev] [RFC] igb_uio: deprecate iomem and ioport mapping

On Thu, 1 Sep 2016 02:16:37 + Jianfeng Tan wrote: > Previously in igb_uio, iomem is mapped, and both ioport and io mem > are recorded into uio framework, which is duplicated and makes the > code too complex. > > For iomem, DPDK user space code never opens or reads

[dpdk-dev] [PATCH 00/56] Solarflare libefx-based PMD

On Wed, 23 Nov 2016 10:49:33 +0300 Andrew Rybchenko wrote: > I've tried to explain it above in item (2): > > >>> > > 2. Another Solarflare PMD with in-kernel part (for control operations) > is considered and could be added in the future. Code for data path > should be shared by

[dpdk-dev] Proposal for a new Committer model

why aren't some patches as marked trivial and accepted right away. On Fri, Nov 18, 2016 at 11:06 AM, Jerin Jacob < jerin.jacob at caviumnetworks.com> wrote: > On Fri, Nov 18, 2016 at 01:09:35PM -0500, Neil Horman wrote: > > On Thu, Nov 17, 2016 at 09:20:50AM +, Mcnamara, John wrote: > > >

[dpdk-dev] Clarification for eth_driver changes

I also think drv_flags should part of device not PCI. Most of the flags there like link state support are generic. If it isn't changed for this release will probably have to break ABI to fully support VMBUS

[dpdk-dev] [PATCH] net/qede: fix gcc compiler option checks

On Thu, 27 Oct 2016 23:37:57 -0700 Rasesh Mody wrote: > From: Rasesh Mody > > Using GCC_VERSION to check gcc version and decide whether to include > that compiler option. > > Fixes: ec94dbc57362 ("qede: add base driver") > Fixes: ecc7a5a27ffe ("net/qede/base: fix 32-bit build") > >

[dpdk-dev] KNI discussion in userspace event

On Fri, 28 Oct 2016 15:31:50 +0100 Ferruh Yigit wrote: > Discussed alternatives were: > * Tun/Tap > This won't be as fast as KNI and performance is an issue. That is a myth. Both require the some number of copies. TUN/TAP copies is a syscall and KNI copies is a kthread. Actually, the KNI

[dpdk-dev] [RFC PATCH v2 2/3] lib: add bitrate statistics library

On Fri, 28 Oct 2016 09:04:30 +0800 Remy Horton wrote: > + > +struct rte_stats_bitrate_s { > + uint64_t last_ibytes; > + uint64_t last_obytes; > + uint64_t peak_ibits; > + uint64_t peak_obits; > + uint64_t ewma_ibits; > + uint64_t ewma_obits; > +}; > + Reader/write access

[dpdk-dev] 17.02 Roadmap

On Mon, 10 Oct 2016 16:13:42 + "O'Driscoll, Tim" wrote: > We published our initial roadmap for 17.02 at the end of August. Since then > we've been doing more detailed planning and would like to provide an update > on the features that we plan to submit for this release. This is our current

[dpdk-dev] [PATCH v2 12/12] virtio: add Tso support

On Thu, 13 Oct 2016 16:18:39 +0800 Yuanhan Liu wrote: > On Mon, Oct 03, 2016 at 11:00:23AM +0200, Olivier Matz wrote: > > +/* When doing TSO, the IP length is not included in the pseudo header > > + * checksum of the packet given to the PMD, but for virtio it is > > + * expected. > > + */ > >

[dpdk-dev] [PATCH] eal: avoid unnecessary conflicts over rte_config file

On Thu, 13 Oct 2016 16:30:20 + "Van Haaren, Harry" wrote: > Hi, > > > From: John Ousterhout [mailto:ouster at cs.stanford.edu] > > > But, given the existence of the --file-prefix option, isn't it already > > unsafe for Collectd to check only for .rte_config? If it's important for > >

[dpdk-dev] [PATCH v7] net/virtio: add set_mtu in virtio

I think current patch is fine. If someone has later problem with it on some scenario we can fix the bug then. Please merge

[dpdk-dev] [PATCH v3 1/2] librte_ether: add internal callback functions

I know callbacks are needed, in fact even more are necessary. That is why I don't like this design. It expands the API for each event. I think something like the Linux kernel netlink callback mechanism that passes an event and device handle.

[dpdk-dev] [PATCH v3] ntnic: add PMD driver

I think that if the driver is just a shim for proprietary code, then the vendor should just maintain it out of tree. 6wind and windriver already do this.

[dpdk-dev] [PATCH] kni: fix build with kernel 4.8

On Thu, 8 Sep 2016 18:54:56 +0100 Ferruh Yigit wrote: > Linux kernel v4.8 removes macro DEFINE_PCI_DEVICE_TABLE > > Linux: 7e9321599011 ("treewide: remove references to the now unnecessary > DEFINE_PCI_DEVICE_TABLE") > > Added the macro to compatibility headers of the kni ethtool drivers. >

[dpdk-dev] [PATCH v9 00/25] Introducing rte_driver/rte_device generalization

On Thu, 8 Sep 2016 12:40:08 +0530 Shreyansh Jain wrote: > > Overall I like to see the clean separation. > > Are you sure you removed as much as possible from PCI? > > I am not very sure of what you mean. > > If you are referring to whether all PCI PMDs have been taken care of, I > think

[dpdk-dev] [PATCH] kni: unregister an unregisterd net_device could cause a kernel crash

On Fri, 9 Sep 2016 10:42:16 +0800 zhouyangchao wrote: > Signed-off-by: zhouyangchao > --- > lib/librte_eal/linuxapp/kni/kni_misc.c |3 +++ > 1 files changed, 3 insertions(+), 0 deletions(-) > > diff --git a/lib/librte_eal/linuxapp/kni/kni_misc.c >

[dpdk-dev] [PATCH] kni: unregister an unregisterd net_device could cause a kernel crash

On Fri, 9 Sep 2016 10:46:07 +0800 zhouyangchao wrote: > Signed-off-by: zhouyangchao > --- > lib/librte_eal/linuxapp/kni/kni_misc.c |4 +++- > 1 files changed, 3 insertions(+), 1 deletions(-) > > diff --git a/lib/librte_eal/linuxapp/kni/kni_misc.c >

[dpdk-dev] [PATCH v9 00/25] Introducing rte_driver/rte_device generalization

On Wed, 7 Sep 2016 19:37:52 +0530 Shreyansh Jain wrote: > Based on master (e22856313) > > Background: > === > > It includes two different patch-sets floated on ML earlier: > * Original patch series is from David Marchand [1], [2]. > `- This focused mainly on PCI (PDEV) part > `-

[dpdk-dev] [PATCH v2] virtio: enable indirect descriptors feature

On Tue, 6 Sep 2016 06:49:26 + "Pierre Pfister (ppfister)" wrote: > > Le 5 sept. 2016 ? 23:08, Stephen Hemminger > > a ?crit : > > > > On Mon, 5 Sep 2016 16:24:13 +0200 > > Maxime Coquelin wrote: > > > >> Thanks Pier

[dpdk-dev] [PATCH v2] virtio: enable indirect descriptors feature

efore negotiate = %x", hw->guest_features); Therefore INDIRECT descriptors were always disabled! Don't blame any commit. Use of indirect descriptors by DPDK did not happen until a later change. commit 6dc5de3a6aefba3946fe04368d93994db3f7a5fd Author: Stephen Hemminger Date:

[dpdk-dev] [PATCH] mbuf: fix atomic refcnt update synchronization

On Sat, 3 Sep 2016 00:31:50 +0800 Linzhe Lee wrote: > Thanks for reply, Stephen. > > > > I'm in x86-64, my cpu is `Intel(R) Xeon(R) CPU E5-2620 v3 @ 2.40GHz`. > > > > When allocation mbuf in program1, and transfer it to program2 for free > via ring, the program1 might meet assert in

[dpdk-dev] [PATCH] mbuf: fix atomic refcnt update synchronization

On Fri, 2 Sep 2016 13:25:06 +0800 lilinzhe wrote: > From: ??? > > chagne atomic ref update to always call atomic_add > > when mbuf is allocated by cpu1 and freed by cpu2. cpu1 cache may not be > updated by such a set operation. > causes refcnt reads incorrect values. What architecture are

[dpdk-dev] [dpdk-dev, RFC] drivers: advertise kmod dependencies in pmdinfo

On Thu, 1 Sep 2016 13:35:19 -0400 Neil Horman wrote: > On Thu, Sep 01, 2016 at 12:55:27PM +, Trahe, Fiona wrote: > > Hi Neil and Olivier, > > > > > -Original Message- > > > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Olivier Matz > > > Sent: Wednesday, August 31, 2016

[dpdk-dev] [PATCH 2/5] eal: extract function eal_parse_sysfs_valuef

On Thu, 1 Sep 2016 10:11:52 +0530 Shreyansh Jain wrote: > From: Jan Viktorin > > From: Jan Viktorin > > The eal_parse_sysfs_value function accepts a filename however, such > interface introduces race-conditions to the code. Introduce the > variant of this function that accepts an already

[dpdk-dev] [PATCH v2] eal: restrict cores detection

On Wed, 31 Aug 2016 03:07:10 + Jianfeng Tan wrote: > This patch uses pthread_getaffinity_np() to narrow down detected > cores before parsing coremask (-c), corelist (-l), and coremap > (--lcores). > > The purpose of this patch is to leave out these core related options > when DPDK

[dpdk-dev] [PATCH] Performance optimization of ACL build process

On Tue, 16 Aug 2016 17:01:27 +0300 Vladyslav Buslov wrote: > Hello, > > In our application we need to be able to allocate tens of thousands of ACLs > at runtime. > Testing revealed significant performance problems. We were able to track them > to memset in calloc function which caused

[dpdk-dev] support BCM5719 driver

On Tue, 30 Aug 2016 13:54:41 +0300 Keren Hochman wrote: > Hi, > > I tried to bind BCM5719 driver to DPDK compatible driver: (I tried both to > uio_pci_generic and igb_uio) > > Network devices using DPDK-compatible driver > > :03:00.2

[dpdk-dev] [PATCH v1] dpdk-devbind.py: Virtio interface issue.

On Mon, 29 Aug 2016 23:16:35 + "Dey, Souvik" wrote: > Hi, > > I already followed the 100% python way and submitted the v3 of this patch. > http://dpdk.org/dev/patchwork/patch/15378/ > How will your patch be different in solving the issue. There will always be > multiple ways to solving

[dpdk-dev] [PATCH v1] add mtu set in virtio

On Sun, 28 Aug 2016 22:43:54 + "Dey, Souvik" wrote: > Hi , > Currently as you have mentioned, I have changed the code to: > static int > virtio_mtu_set(struct rte_eth_dev *dev, uint16_t mtu) > { > struct virtio_hw *hw = dev->data->dev_private; > - if (unlikely(mtu <

[dpdk-dev] [PATCH v1] add mtu set in virtio

On Fri, 26 Aug 2016 20:54:28 -0400 souvikdey33 wrote: > This functionality is required mostly in the cloud infrastructure. > For example, if we use gre or vxlan network between compute and > controller, then we should not use 1500 mtu in the guest as with > encapsulation the sixe of the packet

[dpdk-dev] [PATCH 0/6] add Tx preparation

On Fri, 26 Aug 2016 18:22:52 +0200 Tomasz Kulasek wrote: > As discussed in that thread: > > http://dpdk.org/ml/archives/dev/2015-September/023603.html > > Different NIC models depending on HW offload requested might impose > different requirements on packets to be TX-ed in terms of: > > -

[dpdk-dev] [PATCH] ntnic: add PMD driver

On Fri, 26 Aug 2016 13:44:01 + Finn Christensen wrote: > +The NTNIC poll mode driver library (**librte_pmd_ntnic**) implements support > +for **Napatech NIC** 40/50 Gbps adapters. > +This PMD is implemented as a pure software virtual device and must be created > +by using the EAL

[dpdk-dev] [PATCH] fix to use index to HW queue assigned to PF instead of queus 0 - nb_rx_queues which belong to VF in SR-IOV configuration

On Fri, 26 Aug 2016 11:55:40 +0100 Ferruh Yigit wrote: > Hi Alex, > > On 8/26/2016 11:09 AM, azelezniak wrote: > > From: Alex Zelezniak > > > > Signed-off-by: Alex Zelezniak > > --- > > Thank you for the patch, not related to the patch content but related to > the patch format: > patch

[dpdk-dev] [PATCH v1] dpdk-devbind.py: Virtio interface issue.

On Wed, 24 Aug 2016 22:25:46 -0400 souvikdey33 wrote: > +#The path for virtio devices are different. Get the correct path. > + virtio = "/sys/bus/pci/devices/%s/" % dev_id > +cmd = " ls %s | grep 'virt' " %virtio > +virtio = commands.getoutput(cmd) > +virtio_sys_path =

[dpdk-dev] [PATCH v1] dpdk-devbind.py: Virtio interface issue.

On Wed, 24 Aug 2016 22:25:46 -0400 souvikdey33 wrote: > +#The path for virtio devices are different. Get the correct path. > + virtio = "/sys/bus/pci/devices/%s/" % dev_id > +cmd = " ls %s | grep 'virt' " %virtio > +virtio = commands.getoutput(cmd) I am not a python export but

[dpdk-dev] [PATCH] ethdev: add support for device offload capabilities

On Tue, 16 Apr 2013 14:42:33 +0200 Ivan Boule wrote: > + /* Default device offload capabilities to zero */ > + dev_info->rx_offload_capa = 0; > + dev_info->tx_offload_capa = 0; dev_info is already memset to 0 about 3 lines before this so this is unnecessary.

[dpdk-dev] [PATCH] pci: fix probing blacklisted device with RTE_PCI_DRV_MULTIPLE flag

On Tue, 16 Apr 2013 10:31:48 +0200 Julien Courtat wrote: > + if ((dr->drv_flags & RTE_PCI_DRV_MULTIPLE) && > + (!dev->blacklisted)) { parens around !dev->blacklisted are unnecessary

[dpdk-dev] [PATCH v2 0/6] various vmxnet3 fixes and enhancement

| 32 + > drivers/net/vmxnet3/vmxnet3_ring.h | 22 +++--- > drivers/net/vmxnet3/vmxnet3_rxtx.c | 59 + > 6 files changed, 158 insertions(+), 114 deletions(-) > These all look good to me. Acked-by: Stephen Hemminger

[dpdk-dev] help

On Fri, 19 Aug 2016 13:11:48 + wrote: > Hi , > > I needs to enable SMP(symmetrical multiprocessing) in DPDK PMD NIC Port . > > Please let me know the command to get the same > > Thanks > jayachandran > The information contained in this electronic message and any attachments to > this

[dpdk-dev] [PATCH 2/3] net/virtio_user: fix wrong sequence of messages

On Fri, 5 Aug 2016 11:36:42 + Jianfeng Tan wrote: > When virtio_user is used with VPP's native vhost user, it cannot > send/receive any packets. > > The root cause is that vpp-vhost-user translates the message > VHOST_USER_SET_FEATURES as puting this device into init state, > aka, zero all

[dpdk-dev] [PATCH 3/3] net/virtio_user: fix dev not freed after init error

On Fri, 5 Aug 2016 11:36:43 + Jianfeng Tan wrote: > diff --git a/drivers/net/virtio/virtio_user_ethdev.c > b/drivers/net/virtio/virtio_user_ethdev.c > index daef09b..62ccb0b 100644 > --- a/drivers/net/virtio/virtio_user_ethdev.c > +++ b/drivers/net/virtio/virtio_user_ethdev.c > @@ -313,6

[dpdk-dev] em1000 driver lockup in KVM

On Fri, 22 Jul 2016 14:19:29 -0700 Prabahar Radhakrishnan wrote: > Hi, >I was running a dpdk application with e1000 driver and I am facing a > rare driver lockup condition. Under this condition, what I am seeing is > that the Receive side locks up. The transmit side is fine. When I

[dpdk-dev] [PATCH] ethdev: support PCI domains

about names though. Acked-by: Stephen Hemminger

[dpdk-dev] [PATCH 05/12] mbuf: add new Rx checksum mbuf flags

On Thu, 21 Jul 2016 10:08:23 +0200 Olivier Matz wrote: > +/** > + * Deprecated. > + * Checking this flag alone is deprecated: check the 2 bits of > + * PKT_RX_L4_CKSUM_MASK. > + * This flag was set when the L4 checksum of a packet was detected as > + * wrong by the hardware. > + */ > +#define

[dpdk-dev] backtracing from within the code

On Fri, 24 Jun 2016 12:05:26 +0200 Thomas Monjalon wrote: > 2016-06-24 09:25, Dumitrescu, Cristian: > > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Catalin Vasile > > > I'm trying to add a feature to DPDK and I'm having a hard time printing a > > > backtrace. > > > I tried using

[dpdk-dev] [PATCH] net/virtio-user: fix implicit int to enum conversion

On Thu, 23 Jun 2016 07:40:20 + Jianfeng Tan wrote: > Implicit int to enum conversion is not allowed when icc is used as > the compiler. It raises the compiling error like, > /.../dpdk/drivers/net/virtio/virtio_user/vhost_user.c(257): > error #188: enumerated type mixed with

[dpdk-dev] PATCH] mbuf: rte_pktmbuf_dump: don't add 0x when using %p in format strings

On Mon, 20 Jun 2016 12:44:35 +0200 Simon Kagstrom wrote: > I.e., avoid dump messages with double 0x0x, e.g., > > dump mbuf at 0x0x7fac7b17c800, phys=17b17c880, buf_len=2176 > pkt_len=2064, ol_flags=0, nb_segs=1, in_port=255 > segment at 0x0x7fac7b17c800, data=0x0x7fac7b17c8f0,

[dpdk-dev] [PATCH v6 1/4] lib/librte_ether: support device reset

On Mon, 20 Jun 2016 14:44:11 +0530 Jerin Jacob wrote: > On Mon, Jun 20, 2016 at 02:24:27PM +0800, Wenzhuo Lu wrote: > > Add an API to reset the device. > > It's for VF device in this scenario, kernel PF + DPDK VF. > > When the PF port down->up, APP should call this API to > > reset VF port. Most

[dpdk-dev] [PATCH 2/8] lib/librte_ether: defind RX/TX lock mode

On Wed, 8 Jun 2016 07:34:43 + "Lu, Wenzhuo" wrote: > > > > The fact that it requires lots more locking inside each device driver > > implies to me > > this is not correct way to architect this. > It's a good question. This patch set doesn't follow the regular assumption of > DPDK. > But

[dpdk-dev] [PATCH 2/3] librte_eal: Import FreeBSD sys/tree.h into librte_eal/common

On Thu, 9 Jun 2016 02:53:53 +0200 Nikita Kozlov wrote: > This structure is used inside the rte_lpm6 lib for storing added rules. > It's imported from FreeBSD-10.3 from /usr/include/sys/tree.h, another > solution could have been to use on Linux the version from libbsd but it > would create an

[dpdk-dev] [PATCH 2/8] lib/librte_ether: defind RX/TX lock mode

On Mon, 6 Jun 2016 13:40:47 +0800 Wenzhuo Lu wrote: > Define lock mode for RX/TX queue. Because when resetting > the device we want the resetting thread to get the lock > of the RX/TX queue to make sure the RX/TX is stopped. > > Using next ABI macro for this ABI change as it has too > much

[dpdk-dev] [RFC] Yet another option for DPDK options

On Wed, 1 Jun 2016 17:18:26 +0100 Bruce Richardson wrote: > On Wed, Jun 01, 2016 at 10:58:41AM -0500, Jay Rolette wrote: > > On Wed, Jun 1, 2016 at 10:00 AM, Wiles, Keith > > wrote: > > > > > Started from the link below, but did not want to highjack the thread. > > >

[dpdk-dev] about rx checksum flags

On Tue, 31 May 2016 22:58:57 +0200 Olivier MATZ wrote: > Hi Stephen, > > On 05/31/2016 10:28 PM, Stephen Hemminger wrote: > > On Tue, 31 May 2016 21:11:59 +0200 > > Olivier MATZ wrote: > > > >> > >> > >> On 05/31/2016 10:09 AM, Yuanhan Liu

[dpdk-dev] about rx checksum flags

On Tue, 31 May 2016 21:11:59 +0200 Olivier MATZ wrote: > > > On 05/31/2016 10:09 AM, Yuanhan Liu wrote: > > On Mon, May 30, 2016 at 05:26:21PM +0200, Olivier Matz wrote: > >> PKT_RX_L4_CKSUM_NONE: the L4 checksum is not correct in the packet > >> data, but the integrity of the L4 header is

[dpdk-dev] [PATCH] mbuf: extend rte_mbuf_prefetch_part* to support more prefetching methods

On Tue, 31 May 2016 08:36:06 +0530 Jianbo Liu wrote: > Change the inline function to macro with parameters > > Signed-off-by: Jianbo Liu Going from typed (inline) to untyped (macro) is a step backwards in code safety.

[dpdk-dev] [PATCH v2 02/20] thunderx/nicvf: add pmd skeleton

On Sun, 29 May 2016 22:16:46 +0530 Jerin Jacob wrote: > + > +static struct itimerspec alarm_time = { > + .it_interval = { > + .tv_sec = 0, > + .tv_nsec = NICVF_INTR_POLL_INTERVAL_MS * 100, > + }, > + .it_value = { > + .tv_sec = 0, > +

[dpdk-dev] [PATCH v8 0/3] i40e: Add floating VEB support for i40e

On Wed, 25 May 2016 01:28:03 +0800 Zhe Tao wrote: > This patch-set add the support for floating VEB in i40e. > All the VFs VSIs can decide whether to connect to the legacy VEB/VEPA or > the floating VEB. When connect to the floating VEB a new floating VEB is > created. Now all the VFs need to

[dpdk-dev] [PATCH v4 3/9] librte_ether: add new fields to rte_eth_dev_info struct

On Mon, 23 May 2016 22:38:26 +0100 Reshma Pattan wrote: > Add new fields to rte_eth_dev_info struct > New fields nb_rx_queues and nb_tx_queues are added to > rte_eth_dev_info structure. > Changes to API rte_eth_dev_info_get() are done to update > these new fields to rte_eth_dev_info object. > >

[dpdk-dev] [PATCHv3 1/2] config/armv8a: disable igb_uio

On Wed, 11 May 2016 22:32:16 +0530 Jerin Jacob wrote: > On Wed, May 11, 2016 at 08:22:59AM -0700, Stephen Hemminger wrote: > > On Wed, 11 May 2016 19:17:58 +0530 > > Hemant Agrawal wrote: > > > > > IGB_UIO not supported for arm64 arch in kernel so disable. >

[dpdk-dev] [PATCHv3 1/2] config/armv8a: disable igb_uio

On Wed, 11 May 2016 19:17:58 +0530 Hemant Agrawal wrote: > IGB_UIO not supported for arm64 arch in kernel so disable. > > Signed-off-by: Hemant Agrawal > Reviewed-by: Santosh Shukla Really, I have use IGB_UIO on ARM64

[dpdk-dev] [PATCH] pci: Add the class_id support in pci probe

On Wed, 11 May 2016 14:08:15 +0800 Ziye Yang wrote: > This patch is used to add the class_id (class_code, > subclass_code, programming_interface) support for > pci_device probe. With this patch, it will be > flexible for users to probe a class of devices > by class_id. > > Signed-off-by: Ziye

[dpdk-dev] [PATCH v1] igu_uio: fix IOMMU domain issue

On Tue, 10 May 2016 19:21:41 +0800 Zhe Tao wrote: > Problem: > The following operations will cause the igb_uio based DPDK > operation failed. > --Any device assignment through the kvm_assign_device interface, > this can be the pci-assign method in QEMU > --VFIO group attachment operation(attach

[dpdk-dev] [PATCH 02/20] thunderx/nicvf: add pmd skeleton

On Sat, 7 May 2016 20:46:20 +0530 Jerin Jacob wrote: > + > +static inline struct nicvf* > +nicvf_pmd_priv(struct rte_eth_dev *eth_dev) > +{ > + return (struct nicvf *)eth_dev->data->dev_private; > +} Cast here is unnecessary because dev_private is void *

[dpdk-dev] [PATCH 02/20] thunderx/nicvf: add pmd skeleton

On Sat, 7 May 2016 20:46:20 +0530 Jerin Jacob wrote: > + > +static struct rte_pci_id pci_id_nicvf_map[] = { > + { Another table that should be const

[dpdk-dev] [PATCH 01/20] thunderx/nicvf/base: add hardware API for ThunderX nicvf inbuilt NIC

On Sat, 7 May 2016 20:46:19 +0530 Jerin Jacob wrote: > +static struct nicvf_reg_info nicvf_reg_tbl[] = { > + NICVF_REG_INFO(NIC_VF_CFG), > + NICVF_REG_INFO(NIC_VF_PF_MAILBOX_0_1), > + NICVF_REG_INFO(NIC_VF_INT), > + NICVF_REG_INFO(NIC_VF_INT_W1S), > +

[dpdk-dev] [PATCH v1] hash: add tsx support for cuckoo hash

On Fri, 6 May 2016 21:05:02 +0100 Shen Wei wrote: > --- a/lib/librte_hash/rte_cuckoo_hash.c > +++ b/lib/librte_hash/rte_cuckoo_hash.c > @@ -1,7 +1,7 @@ > /*- > * BSD LICENSE > * > - * Copyright(c) 2010-2015 Intel Corporation. All rights reserved. > + * Copyright(c) 2010-2016 Intel

[dpdk-dev] DPDK cpu layout script won't work on non x86

The format and layout of /proc/cpuinfo changes on different architectures, therefore the DPDK cpu_layout.py tool doesn't work. Could you please change the tool to use sysfs /sys/devices/system/cpu/cpuN/topology/ instead? Then the script would be portable and use the same files as the DPDK use

[dpdk-dev] [PATCH 1/5] bonding: replace spinlock with read/write lock

On Fri, 6 May 2016 11:32:19 +0100 Declan Doherty wrote: > On 05/05/16 18:12, Stephen Hemminger wrote: > > On Thu, 5 May 2016 16:14:56 +0100 > > Bernard Iremonger wrote: > > > >> Fixes: a45b288ef21a ("bond: support link status polling") > >> S

[dpdk-dev] [PATCH 1/2] mempool: add stack (fifo) mempool handler

Overall, this is ok, but why can't it be the default? Lots of little things should be cleaned up > +struct rte_mempool_common_stack > +{ > + /* Spinlock to protect access */ > + rte_spinlock_t sl; > + > + uint32_t size; > + uint32_t len; > + void *objs[]; > + > +#ifdef

[dpdk-dev] [PATCH 1/5] bonding: replace spinlock with read/write lock

On Thu, 5 May 2016 16:14:56 +0100 Bernard Iremonger wrote: > Fixes: a45b288ef21a ("bond: support link status polling") > Signed-off-by: Bernard Iremonger You know an uncontested reader/writer lock is significantly slower than a spinlock.

[dpdk-dev] [PATCH] virtio: fix segfault when transmit pkts

On Thu, 21 Apr 2016 12:36:10 + Jianfeng Tan wrote: > Issue: when using virtio nic to transmit pkts, it causes segment fault. > > How to reproduce: > a. start testpmd with vhost. > $testpmd -c 0x3 -n 4 --socket-mem 1024,0 --no-pci \ > --vdev 'eth_vhost0,iface=/tmp/sock0,queues=1' -- -i

[dpdk-dev] [PATCH 4/4] eal: add assert macro for debug

On Fri, 22 Apr 2016 15:08:50 -0700 Yuanhan Liu wrote: > On Fri, Apr 22, 2016 at 11:14:35PM +0200, Thomas Monjalon wrote: > > 2016-04-22 12:51, Yuanhan Liu: > > > On Fri, Apr 22, 2016 at 03:44:00PM +0200, Thomas Monjalon wrote: > > > > --- a/drivers/net/vmxnet3/vmxnet3_rxtx.c > > > > +++

[dpdk-dev] [PATCH] mem: fix overflowed return value

On Fri, 22 Apr 2016 12:44:18 +0200 Michal Kobylinski wrote: > Fix issue reported by Coverity. > > Coverity ID 13255: Overflowed return value: The return value will be too > small or even negative, likely resulting in unexpected behavior in a > caller that uses the return value. In

[dpdk-dev] [PATCH] cfgfile: fix integer overflow

On Fri, 22 Apr 2016 12:41:01 +0200 Michal Kobylinski wrote: > Fix issue reported by Coverity. > > Coverity ID 13289: Integer overflowed argument: The argument will be too > small or even negative, likely resulting in unexpected behavior (for > example, under-allocation in a memory allocation

[dpdk-dev] [PATCH 1/6] i40e: fix problematic dereference

On Thu, 21 Apr 2016 11:42:52 +0800 Helin Zhang wrote: > Fix issue reported by Coverity. > > Coverity ID 119267: Dereference before null check. > > Fixes: 8e109464c022 ("i40e: allow vector Rx and Tx usage") > > Signed-off-by: Helin Zhang > --- > drivers/net/i40e/i40e_rxtx.c | 10 +- >

[dpdk-dev] [PATCH] eal: fix unchecked return value from library

On Thu, 21 Apr 2016 13:56:57 +0200 Daniel Mrzyglod wrote: > + if (setsockopt(conn_sock, SOL_SOCKET, SO_LINGER, , sizeof(l)) > < 0) > + RTE_LOG(ERR, EAL, "Cannot set SO_LINGER option " > + "on listen socket (%s)\n", >

[dpdk-dev] perfomance of rte_lpm rule subsystem

On Tue, 19 Apr 2016 14:11:11 +0300 ? ??? wrote: > Hi. > > Doing some test with rte_lpm (adding/deleting bgp full table rules) I > noticed that > rule subsystem is very slow even considering that probably it was never > designed for using > in a data forwarding plane. So I want to

[dpdk-dev] librte_table build race with SYMLINK-FILE?

On Mon, 11 Apr 2016 12:46:16 +0200 Simon K?gstr?m wrote: > Hi! > > I'm upgrading from DPDK 2.1 to 16.04-rc4, and have a new build issue > which I didn't see before. It's in the librte_table and happens from > time to time (unfrequently) in my out-of-tree build. It looks like a > race between

[dpdk-dev] [PATCH v2] doc: fill nics features matrix for pcap

I wonder if this matrix would be better if auto-generated some how. Either statically from source scan, or dynamically via simple app?

[dpdk-dev] [PATCH] ixgbe: checkpatch cleanups

Run ixgbe driver through checkpatch and edit away all the nasty bits. Fix line spacing, some bad indentation, and in a couple of cases use short circuit (already there) return to lessen indentation. Signed-off-by: Stephen Hemminger --- v2 - fix more things found by checkpatch drivers/net

[dpdk-dev] vmxnet3 driver - vlan offload is on end descriptor

++] = start; > rxq->start_seg = NULL; > } > > Yes, your analysis and bug fix looks correct. The Linux driver checks for VLAN tag in the last (eop) segment. Acked-by: Stephen Hemminger

[dpdk-dev] [PATCH] ixgbe: cleanup whitespace and formatting issues

On Tue, 5 Apr 2016 00:57:16 + "Lu, Wenzhuo" wrote: > Hi Stephen, > > > -Original Message- > > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Stephen Hemminger > > Sent: Tuesday, April 5, 2016 12:14 AM > > To: Zhang, Helin; Ana

[dpdk-dev] [PATCH] ixgbe: cleanup whitespace and formatting issues

. Signed-off-by: Stephen Hemminger --- drivers/net/ixgbe/ixgbe_82599_bypass.c | 4 +- drivers/net/ixgbe/ixgbe_bypass.c | 6 +- drivers/net/ixgbe/ixgbe_bypass.h | 8 +- drivers/net/ixgbe/ixgbe_bypass_defines.h | 2 +- drivers/net/ixgbe/ixgbe_ethdev.c | 156

[dpdk-dev] [PATCH v5 00/10] qede: Add qede PMD

ber of Rx queues. Is it possible to have 8 Tx queues but only 2 Rx queues? I know bnx2x and some other drivers have that kind of restriction. Acked-by: Stephen Hemminger

[dpdk-dev] [PATCH v5 05/10] qede: Add core driver

On Thu, 31 Mar 2016 19:15:22 -0700 Rasesh Mody wrote: > +struct qed_filter_mcast_params { > + enum qed_filter_xcast_params_type type; > + uint8_t num; > + unsigned char mac[64][ETHER_ADDR_LEN]; > +}; Would prefer a #define constant for the maximum number of multicast addresses

[dpdk-dev] [PATCH v5 05/10] qede: Add core driver

On Thu, 31 Mar 2016 19:15:22 -0700 Rasesh Mody wrote: > +struct qed_filter_ucast_params { > + enum qed_filter_xcast_params_type type; > + uint8_t vlan_valid; > + uint16_t vlan; > + uint8_t mac_valid; > + unsigned char mac[ETHER_ADDR_LEN]; > +} __attribute__ ((__packed__));

[dpdk-dev] [PATCH v4 05/10] qede: Add core driver

On Thu, 31 Mar 2016 19:36:55 + Harish Patil wrote: > > > > >On Wed, 30 Mar 2016 22:16:51 + > >Harish Patil wrote: > > > >> > > >> >On Tue, 29 Mar 2016 22:28:20 -0700 > >> >Rasesh Mody wrote: > >> > > >> >> + > >> >> +static void qede_print_adapter_info(struct qede_dev *qdev) > >> >>

[dpdk-dev] [PATCH v4 05/10] qede: Add core driver

On Wed, 30 Mar 2016 22:16:51 + Harish Patil wrote: > > > >On Tue, 29 Mar 2016 22:28:20 -0700 > >Rasesh Mody wrote: > > > >> + > >> +static void qede_print_adapter_info(struct qede_dev *qdev) > >> +{ > >> + struct ecore_dev *edev = >edev; > >> + struct qed_dev_info *info =

[dpdk-dev] [PATCH] Fix KNI compilation under Wind River Linux 6.0 recent RCPLs.

On Wed, 30 Mar 2016 12:13:35 -0600 Lee Roberts wrote: > skb_set_hash() has been backported to recent Wind River Linux 6.0 RCPLs. > As a result, the corresponding stanza in kcompat.h must be removed. > Similar patches have already been applied for RHEL, SLES and Ubuntu. > > Wind River Linux does

[dpdk-dev] [PATCH v3 2/7] drivers/net/e1000: Suppress misleading indentation warning

On Wed, 30 Mar 2016 19:12:39 +0200 Thomas Monjalon wrote: > 2016-03-30 09:36, Stephen Hemminger: > > On Wed, 30 Mar 2016 10:06:36 -0400 > > Aaron Conole wrote: > > > --- a/drivers/net/e1000/Makefile > > > +++ b/drivers/net/e1000/Make

[dpdk-dev] [PATCH 1/4] lpm: allocation of an existing object should fail

On Wed, 30 Mar 2016 17:30:24 +0200 Olivier Matz wrote: > diff --git a/lib/librte_lpm/rte_lpm6.c b/lib/librte_lpm/rte_lpm6.c > index 4c44cd7..9877a30 100644 > --- a/lib/librte_lpm/rte_lpm6.c > +++ b/lib/librte_lpm/rte_lpm6.c > @@ -182,8 +182,11 @@ rte_lpm6_create(const char *name, int socket_id,

[dpdk-dev] [PATCH] vmxnet3: remove asserts that confuse coverity

These asserts are only for debugging and never fired during any testing, but they confuse coverity's null tracking. Signed-off-by: Stephen Hemminger --- drivers/net/vmxnet3/vmxnet3_rxtx.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/drivers/net/vmxnet3/vmxnet3_rxtx.c b/drivers/net

[dpdk-dev] [PATCH v4 05/10] qede: Add core driver

On Tue, 29 Mar 2016 22:28:20 -0700 Rasesh Mody wrote: > + > +void qede_config_rx_mode(struct rte_eth_dev *eth_dev) > +{ > + struct qede_dev *qdev = eth_dev->data->dev_private; > + struct ecore_dev *edev = >edev; > + /* TODO: - QED_FILTER_TYPE_UCAST */ > + enum

[dpdk-dev] [PATCH v4 05/10] qede: Add core driver

On Tue, 29 Mar 2016 22:28:20 -0700 Rasesh Mody wrote: > +static void qede_config_accept_any_vlan(struct qede_dev *qdev, bool action) > +{ > + struct ecore_dev *edev = >edev; > + struct qed_update_vport_params params; > + int rc; > + > + /* Proceed only if action actually needs to

[dpdk-dev] [PATCH v4 05/10] qede: Add core driver

On Tue, 29 Mar 2016 22:28:20 -0700 Rasesh Mody wrote: > +static void > +qede_alloc_etherdev(struct qede_dev *qdev, struct qed_dev_eth_info *info) > +{ > + rte_memcpy(>dev_info, info, sizeof(*info)); Why bother with rte_memcpy here? why not just assignment or memcpy()? > + qdev->num_tc

[dpdk-dev] [PATCH v4 05/10] qede: Add core driver

On Tue, 29 Mar 2016 22:28:20 -0700 Rasesh Mody wrote: > + > +static void > +qede_dev_info_get(struct rte_eth_dev *eth_dev, > + struct rte_eth_dev_info *dev_info) > +{ > + struct qede_dev *qdev = eth_dev->data->dev_private; > + struct ecore_dev *edev = >edev; > + > +

[dpdk-dev] [PATCH v4 05/10] qede: Add core driver

On Tue, 29 Mar 2016 22:28:20 -0700 Rasesh Mody wrote: > + > +static void qede_print_adapter_info(struct qede_dev *qdev) > +{ > + struct ecore_dev *edev = >edev; > + struct qed_dev_info *info = >dev_info.common; > + char ver_str[QED_DRV_VER_STR_SIZE] = { 0 }; > + > + RTE_LOG(INFO,

[dpdk-dev] [PATCH v3 2/7] drivers/net/e1000: Suppress misleading indentation warning

On Wed, 30 Mar 2016 10:06:36 -0400 Aaron Conole wrote: > The register read/write mphy functions have misleading whitespace around > the `locked` check. This cleanup merely preserves the existing functionality > and suppresses future gcc versions' "misleading indentation" warning. > >

[dpdk-dev] librte_pmd_ixgbe implementation of ixgbe_dev_rx_queue_count

On Tue, 29 Mar 2016 10:31:19 +0100 Bruce Richardson wrote: > On Mon, Mar 28, 2016 at 06:45:26PM -0700, Mohammad El-Shabani wrote: > > Hi, > > Looking into why it hurts performance, I see that ixgbe_dev_rx_queue_count > > is implemented a scan of elements of rx descriptors, which is very > >

[dpdk-dev] [PATCH 1/2] lib/librte_lpm: Fix anonymous union initialization issue

Making code run with picky compilers is good, as long as it doesn't break other (more modern) compilers. > + new_tbl8_entry.next_hop=next_hop; Please run your patches through checkpatch, it will warn about missing whitespace like this.

  1   2   3   4   5   6   7   8   9   10   >