[dpdk-dev] [PATCH v6 08/11] eal: pci: introduce RTE_KDRV_VFIO_NOIOMMUi driver mode

On Thu, Jan 21, 2016 at 8:16 PM, Thomas Monjalon wrote: > 2016-01-21 17:34, Santosh Shukla: >> On Thu, Jan 21, 2016 at 4:58 PM, Thomas Monjalon >> wrote: >> > 2016-01-21 16:43, Santosh Shukla: >> >> David Marchand wrote: >> >> > This is a mode (specific to vfio), not a new kernel driver. >> >> >

[dpdk-dev] virtio ring layout changes for optimal single-stream performance

On Thu, Jan 21, 2016 at 04:38:36PM +0100, Cornelia Huck wrote: > On Thu, 21 Jan 2016 15:39:26 +0200 > "Michael S. Tsirkin" wrote: > > > Hi all! > > I have been experimenting with alternative virtio ring layouts, > > in order to speed up single stream performance. > > > > I have just posted a ben

[dpdk-dev] DPDK mbuf pool in SR-IOV env and one RX/TX queue

Hi, Is it possible for two or more processes to share the same mbuf_pool in SR-IOV with single rx/tx queue? char *eal_argv[] = {"fakeelf", "-c2", "-n4", "--proc-type=primary",}; int ret = rte_eal_init(4, eal_argv);

[dpdk-dev] [RFC PATCH 0/5] virtio: Add a new layer to abstract pci access method

On 2016/01/21 20:07, Tetsuya Mukawa wrote: > This patch series are not for upstreaming. > > It describe how to use a new access method abstraction of "virtio-pci.c". > Because of this, some patches are not for upstreaming. > > For example, below changes will be shared with Jianfeng's patches. > So

[dpdk-dev] [RFC PATCH 5/5] virtio: Extend virtio-net PMD to support container environment

virtio: Extend virtio-net PMD to support container environment The patch adds a new virtio-net PMD configuration that allows the PMD to work on host as if the PMD is in VM. Here is new configuration for virtio-net PMD. - CONFIG_RTE_LIBRTE_VIRTIO_HOST_MODE To use this mode, EAL needs physically co

[dpdk-dev] [RFC PATCH 4/5] EAL: Add new EAL "--shm" option.

This is a temporary patch to get EAL memory under 16T(1 << 44). The patch adds new EAL "--shm" option. If the option is specified, EAL will allocate one file from hugetlbfs. This memory is for sharing memory between DPDK applicaiton and QEMU ivhsmem device. Signed-off-by: Tetsuya Mukawa --- lib

[dpdk-dev] [RFC PATCH 3/5] virtio: Add a new layer to abstract pci access method

This patch addss function pointers to abstract pci access method. This abstraction layer will be used when virtio-net PMD supports container extension. The below functions abstract how to access to pci configuration space. struct virtio_pci_cfg_ops { int (*map)(...); void (*unm

[dpdk-dev] [RFC PATCH 2/5] virtio: move rte_eal_pci_unmap_device() to virtio_pci.c

To abstract pci access method, the patch moves below function to "virtio_pci.c". - rte_eal_pci_unmap_device() Signed-off-by: Tetsuya Mukawa --- drivers/net/virtio/virtio_ethdev.c | 2 +- drivers/net/virtio/virtio_pci.c| 11 +++ drivers/net/virtio/virtio_pci.h| 1 + 3 files cha

[dpdk-dev] [RFC PATCH 1/5] virtio: Change the parameter order of io_write8/16/32()

The patch change the parameter order of below functions. - io_write8() - io_write16() - io_write32() This changig are needed to add a new layer to abstract accessing method. Signed-off-by: Tetsuya Mukawa --- drivers/net/virtio/virtio_pci.c | 66 - 1 fil

[dpdk-dev] [RFC PATCH 0/5] virtio: Add a new layer to abstract pci access method

This patch series are not for upstreaming. It describe how to use a new access method abstraction of "virtio-pci.c". Because of this, some patches are not for upstreaming. For example, below changes will be shared with Jianfeng's patches. So these changes are just temporary. - "--shm" option to

[dpdk-dev] [PATCH 2/4] i40e: split function for input set change of hash and fdir

Hi Jingjing, > -Original Message- > From: Wu, Jingjing > Sent: Thursday, January 21, 2016 1:29 AM > To: Chilikin, Andrey; dev at dpdk.org > Cc: Zhang, Helin; Pei, Yulong; Ananyev, Konstantin > Subject: RE: [PATCH 2/4] i40e: split function for input set change of hash and > fdir > > Hi, An

[dpdk-dev] [dpdk-dev,1/2] ethdev: remove useless null checks

On Thu, 21 Jan 2016 12:57:10 +0100 David Marchand wrote: > We are in static functions and those passed arguments can't be NULL. > > Signed-off-by: David Marchand > > --- > lib/librte_ether/rte_ethdev.c | 15 --- > 1 file changed, 15 deletions(-) > > diff --git a/lib/librte_ether/r

[dpdk-dev] [PKTGEN] dumb question: how to start packet TX and set the payload

On 1/21/16, 1:00 PM, "Matthew Hall" wrote: >On Thu, Jan 21, 2016 at 03:05:38PM +, Wiles, Keith wrote: >> Forgot to answer this one. Pktgen does not allow the user to define the >> content of the packet per say only the fill pattern and what ever you >> configure the packet type to be. If yo

[dpdk-dev] [dpdk-dev, 2/2] ethdev: move code to common place in hotplug

2016-01-21 19:06, David Marchand: > On Thu, Jan 21, 2016 at 4:38 PM, Jan Viktorin > wrote: > > On Thu, 21 Jan 2016 12:57:11 +0100 > > David Marchand wrote: > > > [snip] > >> @@ -612,14 +599,25 @@ int > >> rte_eth_dev_attach(const char *devargs, uint8_t *port_id) > >> { > >> struct rte_pc

[dpdk-dev] [dpdk-dev, 2/2] ethdev: move code to common place in hotplug

On Thu, Jan 21, 2016 at 4:38 PM, Jan Viktorin wrote: > On Thu, 21 Jan 2016 12:57:11 +0100 > David Marchand wrote: > [snip] >> @@ -612,14 +599,25 @@ int >> rte_eth_dev_attach(const char *devargs, uint8_t *port_id) >> { >> struct rte_pci_addr addr; >> + int ret = -1; >> >> if ((d

[dpdk-dev] [PATCH 16/16] fm10k/base: add macro definitions that are needed

Some macros such as FM10K_RXINT_TIMER_SHIFT are removed in the share code drop, but they are needed in dpdk/fm10k. This patch put all these necessary macros into fm10k_osdep.h Signed-off-by: Wang Xiao W --- drivers/net/fm10k/base/fm10k_osdep.h | 30 ++ 1 file changed,

[dpdk-dev] [PATCH 15/16] fm10k: use default mailbox message handler for pf

The new share code makes fm10k_msg_update_pvid_pf function static, so we can not refer to it now in fm10k_ethdev.c. The registered pf handler is almost the same as the default pf handler, removing it has no impact on mailbox. Signed-off-by: Wang Xiao W --- drivers/net/fm10k/fm10k_ethdev.c | 17 +

[dpdk-dev] [PATCH 14/16] fm10k/base: minor cleanups

Some cleanups to better reflect the code that was actually pushed out to the upstream Linux community. Signed-off-by: Wang Xiao W --- drivers/net/fm10k/base/fm10k_mbx.h | 7 -- drivers/net/fm10k/base/fm10k_pf.h | 4 -- drivers/net/fm10k/base/fm10k_type.h | 132

[dpdk-dev] [PATCH 13/16] fm10k/base: move constants to the right of binary operators

The upstream Linux kernel community prefers constants are to the right of binary operators. Signed-off-by: Wang Xiao W --- drivers/net/fm10k/base/fm10k_pf.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/fm10k/base/fm10k_pf.c b/drivers/net/fm10k/base/fm10k

[dpdk-dev] [PATCH 12/16] fm10k/base: TLV structures must be 4byte aligned, not 1byte aligned

Per comments from an upstream patch, and looking at how TLV LE_STRUCT code works, we actually want these structures to be 4byte aligned, not 1byte aligned. In practice, 1byte alignment has worked so far because all our structures end up being a multiple of 4. But if a future TLV structure were adde

[dpdk-dev] [PATCH 11/16] fm10k/base: fix comment per upstream review changes

The comment here was changed during review of upstream patch, and the new wording is slightly more clear. Re-write the comment in SHARED code based on this new wording. Fix a number of mailbox comment issues with function header comments, lower-case acronyms (i.e. FIFO, TLV), incorrect function na

[dpdk-dev] [PATCH 10/16] fm10k/base: consistently use VLAN ID when referencing vid variables

The vid variable name is shorthand for VLAN ID, so we should use this in comments explaining what is happening. Signed-off-by: Wang Xiao W --- drivers/net/fm10k/base/fm10k_pf.c | 12 ++-- 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/net/fm10k/base/fm10k_pf.c b/d

[dpdk-dev] [PATCH 09/16] fm10k/base: allow removal of is_slot_appropriate function

The Linux Kernel provides the OS a call "pcie_get_minimum_link" which can crawl the PCIe tree and determine the actual minimum link speed of a device which is a more general check than provided by is_slot_appropriate. Thus, the upstream driver does not use or want the is_slot_appropriate function c

[dpdk-dev] [PATCH 08/16] fm10k/base: use memcpy for mac addr copy

Use memcpy instead of copying MAC address byte-by-byte. Signed-off-by: Wang Xiao W --- drivers/net/fm10k/base/fm10k_pf.c | 7 ++- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/drivers/net/fm10k/base/fm10k_pf.c b/drivers/net/fm10k/base/fm10k_pf.c index 7d48210..a1469aa 100644

[dpdk-dev] [PATCH 07/16] fm10k/base: do not use CamelCase

The upstream Linux kernel community prefers avoiding CamelCase in variables, function names, etc. Signed-off-by: Wang Xiao W --- drivers/net/fm10k/base/fm10k_type.h | 14 +++--- drivers/net/fm10k/fm10k_ethdev.c| 24 2 files changed, 19 insertions(+), 19 delet

[dpdk-dev] [PATCH 06/16] fm10k/base: use BIT macro instead of open-coded bit-shifting of 1

The upstream Linux kernel community prefers using the BIT macro over bit-shifting a 1. Similar to how this is handled in the i40e shared code, define a macro for OSes that do not already have it and wrap all that in LINUX_MACROS so that it can be stripped from the Linux driver. The upstream Linux

[dpdk-dev] [PATCH 05/16] fm10k/base: fix checkpatch warning

Cleanup lines over 80 characters. Cleanup useless else, checkpatch warns that else is not generally useful after a break or return. Signed-off-by: Wang Xiao W --- drivers/net/fm10k/base/fm10k_mbx.c | 2 +- drivers/net/fm10k/base/fm10k_pf.c | 19 ++- 2 files changed, 11 insertio

[dpdk-dev] [PATCH 04/16] fm10k/base: document ITR scale workaround in VF TDLEN register

Add comments which properly explain the undocumented use of bits in TDLEN register prior to VF initializing it to the correct value. Note that the mechanism is entirely software-defined and explain its purpose to help reduce confusion in the future. Signed-off-by: Wang Xiao W --- drivers/net/fm1

[dpdk-dev] [PATCH 03/16] fm10k/base: reset max_queues on init_hw_vf failure

VF drivers must detect how many queues are available. Previously, the driver assumed that each VF has at minimum 1 queue. This assumption is incorrect, since it is possible that the PF has not yet assigned the queues to the VF by the time the VF checks. To resolve this, we added a check first to en

[dpdk-dev] [PATCH 02/16] fm10k/base: use bitshift for itr_scale

Upstream community wishes us to use bitshift instead of a divisor, because this is faster, and prevents any need for a '0' check. In our case, this even works out because default Gen3 will be 0. Because of this, we are also able to remove the check for non-zero value in the vf code path since that

[dpdk-dev] [PATCH 01/16] fm10k/base: cleanup namespace pollution and correct typecast

Correct typecast in fm10k_update_xc_addr_pf. Make functions that are only referenced locally static. And fix the function header comment for fm10k_tlv_attr_nest_stop() while we're at it. Wrap fm10k_msg_data fm10k_iov_msg_data_pf[] in the new ifndef NO_DEFAULT_SRIOV_MSG_HANDLERS so that drivers w

[dpdk-dev] [PATCH 00/16] fm10k: update shared code from ND team

This shared code update patch set has passed the regression test. Wang Xiao W (16): fm10k/base: cleanup namespace pollution and correct typecast fm10k/base: use bitshift for itr_scale fm10k/base: reset max_queues on init_hw_vf failure fm10k/base: document ITR scale workaround in VF TDLEN r

[dpdk-dev] [PATCH] igb: set default thresholds correctly based on mac type

This brings the DPDK igb driver inline with the behavior used by the current Linux driver. The IGB hardware has several different MAC types and the threshold values that work vary based on the hardware. Since DPDK 1.8 it has been up to devices to provide the correct default configuration parameter

[dpdk-dev] [PKTGEN] additional terminal IO question

Keith, For the record, on my end (can only speak for myself) this is not a real problem. I work around it by using a different theme and live with it happily ever after. I just provided the input since I encountered it. /Arnon On Thu, Jan 21, 2016 at 5:27 PM, Wiles, Keith wrote: > > From: Arno

[dpdk-dev] [PATCH v6 08/11] eal: pci: introduce RTE_KDRV_VFIO_NOIOMMUi driver mode

On Thu, Jan 21, 2016 at 4:58 PM, Thomas Monjalon wrote: > 2016-01-21 16:43, Santosh Shukla: >> David Marchand wrote: >> > This is a mode (specific to vfio), not a new kernel driver. >> > >> Yes, Specific to VFIO and this is why noiommu appended after vfio i.e.. >> __VFIO and __VFIO_NOIOMMU. > > W

[dpdk-dev] [PKTGEN] additional terminal IO question

Keith, On my end I'm ending with black on black with Konsole 2.3.3 on Centos 6.5 starting as green on black. On Thu, Jan 21, 2016 at 4:55 PM, Wiles, Keith wrote: > On 1/20/16, 11:53 PM, "dev on behalf of Matthew Hall" < > dev-bounces at dpdk.org on behalf of mhall at mhcomputing.net> wrote: > >

[dpdk-dev] [PATCH v6 08/11] eal: pci: introduce RTE_KDRV_VFIO_NOIOMMUi driver mode

On Thu, Jan 21, 2016 at 4:02 PM, David Marchand wrote: > Santosh, > > On Tue, Jan 19, 2016 at 7:57 PM, Santosh Shukla > wrote: > > Adding RTE_KDRV_VFIO_NOIOMMU mode in kernel driver. Also including > > rte_vfio_is_noiommu() helper function. This function will parse > > /sys/bus/pci/device// and

[dpdk-dev] [dpdk-dev, 2/2] ethdev: move code to common place in hotplug

On Thu, 21 Jan 2016 12:57:11 +0100 David Marchand wrote: > Move these error logs and checks on detach capabilities in a common place. > > Signed-off-by: David Marchand > > --- > lib/librte_ether/rte_ethdev.c | 69 +-- > 1 file changed, 40 insertions(+),

[dpdk-dev] virtio ring layout changes for optimal single-stream performance

On Thu, 21 Jan 2016 15:39:26 +0200 "Michael S. Tsirkin" wrote: > Hi all! > I have been experimenting with alternative virtio ring layouts, > in order to speed up single stream performance. > > I have just posted a benchmark I wrote for the purpose, and a (partial) > alternative layout implementa

[dpdk-dev] [PATCH 0/2] Reduce DPDK initialization time

2015-11-22 14:13, Zhihong Wang: > This patch aims to reduce DPDK initialization time, which is important in > cases such as micro service. > > Changes are: > > 1. Reduce timer initialization time > > 2. Remove unnecessary hugepage zero-filling operations > > With this patch: > > 1. Timer init

[dpdk-dev] [PATCH v6 05/11] eal: pci: vfio: add rd/wr func for pci bar space

Introducing below api for pci bar space rd/wr. Currently used for pci iobar rd/wr. Api's are: - rte_eal_pci_read_bar - rte_eal_pci_write_bar virtio when used for vfio-mode then virtio driver will use these api to do rd/wr operation on ioport pci bar. Signed-off-by: Santosh Shukla --- v5-->v6: -

[dpdk-dev] [PATCH v6 02/11] eal/linux: never check iopl for arm

iopl() syscall not supported in linux-arm/arm64 so always return 0 value. Signed-off-by: Santosh Shukla Acked-by: Jan Viktorin Suggested-by: Stephen Hemminger --- v5 --> v5: - Renamed patch titled from "linuxapp: eal: arm: Always return 0 for rte_eal_iopl_init()" to current, Suggested by Dav

[dpdk-dev] [PATCH v6 08/11] eal: pci: introduce RTE_KDRV_VFIO_NOIOMMUi driver mode

2016-01-21 17:34, Santosh Shukla: > On Thu, Jan 21, 2016 at 4:58 PM, Thomas Monjalon > wrote: > > 2016-01-21 16:43, Santosh Shukla: > >> David Marchand wrote: > >> > This is a mode (specific to vfio), not a new kernel driver. > >> > > >> Yes, Specific to VFIO and this is why noiommu appended afte

[dpdk-dev] [PKTGEN] [PATCH 1/2] usage_pktgen.rst: multiple instances: clean up section intro

On 1/20/16, 11:50 PM, "dev on behalf of Matthew Hall" wrote: >Signed-off-by: Matthew Hall >--- > docs/source/usage_pktgen.rst | 18 +- > 1 file changed, 9 insertions(+), 9 deletions(-) > >diff --git a/docs/source/usage_pktgen.rst b/docs/source/usage_pktgen.rst >index 20bd314..efe8

[dpdk-dev] [PKTGEN] [PATCH 2/2] usage_pktgen.rst: multiple instances: clarify EAL options needed

On 1/20/16, 11:50 PM, "dev on behalf of Matthew Hall" wrote: >Signed-off-by: Matthew Hall >--- > docs/source/usage_pktgen.rst | 15 +++ > 1 file changed, 15 insertions(+) > >diff --git a/docs/source/usage_pktgen.rst b/docs/source/usage_pktgen.rst >index efe8aa4..223d033 100644 >--- a/

[dpdk-dev] virtio ring layout changes for optimal single-stream performance

Hi all! I have been experimenting with alternative virtio ring layouts, in order to speed up single stream performance. I have just posted a benchmark I wrote for the purpose, and a (partial) alternative layout implementation. This achieves 20-40% reduction in virtio overhead in the (default) pol

[dpdk-dev] [PATCH v5 05/11] eal: pci: vfio: add rd/wr func for pci bar space

On Thu, Jan 21, 2016 at 3:12 PM, David Marchand wrote: > Santosh, > > On Tue, Jan 19, 2016 at 12:46 PM, Santosh Shukla > wrote: >> Introducing below api for pci bar space rd/wr. Currently used for >> pci iobar rd/wr. >> >> Api's are: >> - rte_eal_pci_read_bar >> - rte_eal_pci_write_bar >> >> vir

[dpdk-dev] [PATCH v5 02/11] linuxapp: eal: arm: Always return 0 for rte_eal_iopl_init()

On Thu, Jan 21, 2016 at 3:11 PM, David Marchand wrote: > Hello Santosh, > > On Tue, Jan 19, 2016 at 12:46 PM, Santosh Shukla > wrote: > > iopl() syscall not supported in linux-arm/arm64 so always return 0 value. > > > > Signed-off-by: Santosh Shukla > > Acked-by: Jan Viktorin > > Suggested-by:

[dpdk-dev] [PKTGEN] additional terminal IO question

From: Arnon Warshavsky mailto:ar...@qwilt.com>> Date: Thursday, January 21, 2016 at 9:04 AM To: "Keith Wiles (Intel)" mailto:keith.wiles at intel.com>> Cc: Matthew Hall mailto:mhall at mhcomputing.net>>, "dev at dpdk.org" mailto:dev at dpdk.org>> Subject: Re: [dpdk-dev]

[dpdk-dev] [PATCH 2/2] i40e: Add floating VEB support in i40e

This patch 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 connect to floating VEB or legacy VEB, cannot connect to both of

[dpdk-dev] PATCH 1/2] i40e: support floating VEB config

Add the new floating related argument option in the EAL. using this parameter, all the samples can decide whether to use legacy VEB/VEPA, or floating VEB. Signed-off-by: Zhe Tao --- lib/librte_eal/common/eal_common_options.c | 4 lib/librte_eal/common/eal_internal_cfg.h | 1 + lib/librte

[dpdk-dev] [PATCH 0/2] Add floating VEB support for i40e

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 connect to floating VEB or legacy VEB, cannot connect to bot

[dpdk-dev] [PKTGEN] dumb question: how to start packet TX and set the payload

On Thu, Jan 21, 2016 at 07:44:21PM +, Wiles, Keith wrote: > What type of data do you want to add to the packets? Now it builds > IPv4/UDP/TCP packets, do you need to replace UDP or TCP or just add more > protocol layers? I perform content inspection of various types: IPv4 - supported IPv6 -

[dpdk-dev] [PKTGEN] dumb question: how to start packet TX and set the payload

On 1/21/16, 12:15 AM, "dev on behalf of Matthew Hall" wrote: >Hello, > >I was trying to just use the default PKT file, test/set_seq.pkt, like so: > >sudo "./app/app/${RTE_TARGET}/pktgen" \ >-l 2,3 \ >--master-lcore 2 \ >-n 2 \ >-m 1024 \ >-w 0a:00.1 \ >--no-shconf \ >--file-prefix pktgen \ >-- \

[dpdk-dev] [PKTGEN] fixing weird termio issues that complicate debugging

On 1/21/16, 2:46 AM, "Panu Matilainen" wrote: >On 01/20/2016 06:26 PM, Wiles, Keith wrote: >> On 1/20/16, 12:32 AM, "dev on behalf of Matthew Hall" > dpdk.org on behalf of mhall at mhcomputing.net> wrote: >> >>> Hello, >>> >>> Since the pktgen code is reindented I am finding time to read through

[dpdk-dev] [PKTGEN] fixing weird termio issues that complicate debugging

On Thu, Jan 21, 2016 at 11:00:14AM -0800, Stephen Hemminger wrote: > I would rip out the whole tty control and theming nonsense and then > just print one line copyright on startup. Personally, I might have put this sentiment more diplomatically, but a refactor effort such as this would make life

[dpdk-dev] [PKTGEN] dumb question: how to start packet TX and set the payload

On 1/21/16, 12:15 AM, "dev on behalf of Matthew Hall" wrote: >Hello, > >I was trying to just use the default PKT file, test/set_seq.pkt, like so: > >sudo "./app/app/${RTE_TARGET}/pktgen" \ >-l 2,3 \ >--master-lcore 2 \ BTW, the lowest core will be the master by default in the -c or -l option, so

[dpdk-dev] [PKTGEN] additional terminal IO question

On 1/20/16, 11:53 PM, "dev on behalf of Matthew Hall" wrote: >If I try using pktgen theme mode (-T) or unmodified, without commenting >out some of the stuff I mentioned I disabled for debugging in the >previous thread, it seems like it sets the pktgen prompt to be invisible >(black text on bla

[dpdk-dev] [PATCH 2/5] vhost: refactor virtio_dev_rx

Hi Yuanhan, 2015-12-14 2:47 GMT+01:00 Yuanhan Liu : > Right, I should move it in the beginning of this function. Any news about this refactoring ? -- J?r?me Jutteau, Tel : 0826.206.307 (poste 304) IMPORTANT: The information contained in this message may be privileged and confidential and protec

[dpdk-dev] [PATCH] i40e: add VEB switching support for i40e

VEB switching feature for i40e is used to enable the switching between the VSIs connect to the virtual bridge. The old implementation is setting the virtual bridge mode as VEPA which is port aggregation. Enable the switching ability by setting the loop back mode for the specific VSIs which conn

[dpdk-dev] [PKTGEN] dumb question: how to start packet TX and set the payload

On Thu, Jan 21, 2016 at 03:01:33PM +, Wiles, Keith wrote: > The problem is you used the same core (2) for the -m option. Core 2 is being > used for the keyboard, timer and screen output. This means you must have the > -m option starting with core 3 as in -m 3.0 and your problem should go away

[dpdk-dev] [PKTGEN] dumb question: how to start packet TX and set the payload

On Thu, Jan 21, 2016 at 03:05:38PM +, Wiles, Keith wrote: > Forgot to answer this one. Pktgen does not allow the user to define the > content of the packet per say only the fill pattern and what ever you > configure the packet type to be. If you would like to submit a patch for > adding user

[dpdk-dev] [PATCH 2/2] ethdev: move code to common place in hotplug

Move these error logs and checks on detach capabilities in a common place. Signed-off-by: David Marchand --- lib/librte_ether/rte_ethdev.c | 69 +-- 1 file changed, 40 insertions(+), 29 deletions(-) diff --git a/lib/librte_ether/rte_ethdev.c b/lib/librte_

[dpdk-dev] [PATCH 1/2] ethdev: remove useless null checks

We are in static functions and those passed arguments can't be NULL. Signed-off-by: David Marchand --- lib/librte_ether/rte_ethdev.c | 15 --- 1 file changed, 15 deletions(-) diff --git a/lib/librte_ether/rte_ethdev.c b/lib/librte_ether/rte_ethdev.c index af990e2..951fb1c 100644 ---

[dpdk-dev] [PATCH 0/2] minor cleanup in ethdev hotplug

It was first a preparation step for future patchsets, but I am not sure what will become of them, so sending this anyway since it does not hurt to clean this now. -- David Marchand David Marchand (2): ethdev: remove useless checks ethdev: move code to common place in hotplug lib/librte_et

[dpdk-dev] [PATCH v5 8/9] virtio: add 1.0 support

2016-01-19 16:12, Yuanhan Liu: > int > vtpci_init(struct rte_pci_device *dev, struct virtio_hw *hw) > { > - hw->vtpci_ops = &legacy_ops; > + hw->dev = dev; > + > + /* > +* Try if we can succeed reading virtio pci caps, which exists > +* only on modern pci device

[dpdk-dev] [PATCH v3] Patch introducing API to read/write Intel Architecture Model Specific Registers (MSR)...

On 01/21/2016 10:18 AM, Wojciech Andralojc wrote: > Patch reworked. > > Signed-off-by: Wojciech Andralojc > --- > lib/librte_eal/common/include/arch/x86/rte_msr.h | 88 + > lib/librte_eal/linuxapp/eal/Makefile | 1 + > lib/librte_eal/linuxapp/eal/arch/x86/rte_msr

[dpdk-dev] [PATCH v5 8/9] virtio: add 1.0 support

2016-01-19 16:12, Yuanhan Liu: > +#define IO_READ_DEF(nr_bits, type) \ > +static inline type \ > +io_read##nr_bits(type *addr) \ > +{ \ > + return *(volatile type *)addr; \ > +} > +

[dpdk-dev] [PATCH] no need to test for NULL when freeing

On Thu, Jan 21, 2016 at 12:30 PM, Thomas Monjalon wrote: > 2016-01-21 12:23, David Marchand: >> free() already handles NULL pointer. >> >> Signed-off-by: David Marchand >> --- >> app/test/test_devargs.c| 3 +- >> app/test/test_link_bonding.c |

[dpdk-dev] [PATCH] no need to test for NULL when freeing

2016-01-21 12:23, David Marchand: > free() already handles NULL pointer. > > Signed-off-by: David Marchand > --- > app/test/test_devargs.c| 3 +- > app/test/test_link_bonding.c | 6 ++-- > app/test/test_pci.c| 3

[dpdk-dev] [PATCH v6 08/11] eal: pci: introduce RTE_KDRV_VFIO_NOIOMMUi driver mode

2016-01-21 16:43, Santosh Shukla: > David Marchand wrote: > > This is a mode (specific to vfio), not a new kernel driver. > > > Yes, Specific to VFIO and this is why noiommu appended after vfio i.e.. > __VFIO and __VFIO_NOIOMMU. Woaaa! Your logic is really disappointing :) Specific to VFIO => app

[dpdk-dev] [PATCH] no need to test for NULL when freeing

free() already handles NULL pointer. Signed-off-by: David Marchand --- app/test/test_devargs.c| 3 +- app/test/test_link_bonding.c | 6 ++-- app/test/test_pci.c| 3 +- app/test/test_ring.c

[dpdk-dev] [PATCH v2 0/3] Keep-alive stats and doc fixes

On 21/01/2016 11:05, Harry van Haaren wrote: > This patchset contains: > 1. Fix variable naming consistency in sample guide > 2. Set last_seen time on core when it gets registered > 3. An xstats implementation for last-seen and current core status > > v2: > -Refactor to remove rte_ethdev.h includ

[dpdk-dev] [PATCH v6 08/11] eal: pci: introduce RTE_KDRV_VFIO_NOIOMMUi driver mode

Santosh, On Tue, Jan 19, 2016 at 7:57 PM, Santosh Shukla wrote: > Adding RTE_KDRV_VFIO_NOIOMMU mode in kernel driver. Also including > rte_vfio_is_noiommu() helper function. This function will parse > /sys/bus/pci/device// and make sure that > - vfio noiommu mode set in kernel driver > - pci devi

[dpdk-dev] [PATCH v6 02/11] eal/linux: never check iopl for arm

On Thu, Jan 21, 2016 at 11:26 AM, Santosh Shukla wrote: > iopl() syscall not supported in linux-arm/arm64 so always return 0 value. > > Signed-off-by: Santosh Shukla > Acked-by: Jan Viktorin > Suggested-by: Stephen Hemminger Acked-by: David Marchand -- David Marchand

[dpdk-dev] [PATCH v2 3/3] keepalive: add rte_keepalive_xstats_get() and example

This patch adds a function that exposes keepalive statistics using a rte_keepalive_xstats struct. The function provides the client API the opportunity to read last-seen and status of each core. Signed-off-by: Harry van Haaren --- doc/guides/rel_notes/release_2_3.rst| 6 doc/gui

[dpdk-dev] [PATCH v2 2/3] eal: add keepalive core register timestamp

This patch sets a timestamp on each lcore when it is registered for keepalive. This causes the first values read by the monitor to show time since the core was registered, instead of the delta between 0 and the timestamp counter. Signed-off-by: Harry van Haaren --- lib/librte_eal/common/rte_keep

[dpdk-dev] [PATCH v2 1/3] doc: fix keepalive sample app guide

This patch fixes some mismatches between the keepalive code and the docs. Struct names, and descriptions are not in line with the codebase. Fixes: e64833f2273a ("examples/l2fwd-keepalive: add sample application") Signed-off-by: Harry van Haaren --- doc/guides/sample_app_ug/keep_alive.rst | 19 +

[dpdk-dev] [PATCH v2 0/3] Keep-alive stats and doc fixes

This patchset contains: 1. Fix variable naming consistency in sample guide 2. Set last_seen time on core when it gets registered 3. An xstats implementation for last-seen and current core status v2: -Refactor to remove rte_ethdev.h include Harry van Haaren (3): doc: fix keepalive sample app gui

[dpdk-dev] [PKTGEN] fixing weird termio issues that complicate debugging

On Thu, 21 Jan 2016 15:03:37 + "Wiles, Keith" wrote: > On 1/21/16, 2:46 AM, "Panu Matilainen" wrote: > > >On 01/20/2016 06:26 PM, Wiles, Keith wrote: > >> On 1/20/16, 12:32 AM, "dev on behalf of Matthew Hall" >> dpdk.org on behalf of mhall at mhcomputing.net> wrote: > >> > >>> Hello, > >>>

[dpdk-dev] [PATCH v3] Patch introducing API to read/write Intel Architecture Model Specific Registers (MSR)...

Hi Panu, > -Original Message- > From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Panu Matilainen > Sent: Thursday, January 21, 2016 10:39 AM > To: Andralojc, WojciechX > Cc: dev at dpdk.org > Subject: Re: [dpdk-dev] [PATCH v3] Patch introducing API to read/write Intel > Architectur

[dpdk-dev] [PKTGEN] fixing weird termio issues that complicate debugging

On 01/20/2016 06:26 PM, Wiles, Keith wrote: > On 1/20/16, 12:32 AM, "dev on behalf of Matthew Hall" dpdk.org on behalf of mhall at mhcomputing.net> wrote: > >> Hello, >> >> Since the pktgen code is reindented I am finding time to read through it >> and experiment and see if I can get it working. >

[dpdk-dev] [PATCH v5 05/11] eal: pci: vfio: add rd/wr func for pci bar space

Santosh, On Tue, Jan 19, 2016 at 12:46 PM, Santosh Shukla wrote: > Introducing below api for pci bar space rd/wr. Currently used for > pci iobar rd/wr. > > Api's are: > - rte_eal_pci_read_bar > - rte_eal_pci_write_bar > > virtio when used for vfio-mode then virtio driver will use these api > to d

[dpdk-dev] [PATCH v5 02/11] linuxapp: eal: arm: Always return 0 for rte_eal_iopl_init()

Hello Santosh, On Tue, Jan 19, 2016 at 12:46 PM, Santosh Shukla wrote: > iopl() syscall not supported in linux-arm/arm64 so always return 0 value. > > Signed-off-by: Santosh Shukla > Acked-by: Jan Viktorin > Suggested-by: Stephen Hemminger I suppose when we will have more arches, this can be

[dpdk-dev] [PATCH v3] Patch introducing API to read/write Intel Architecture Model Specific Registers (MSR)...

Hi, 2016-01-21 08:18, Wojciech Andralojc: > Patch reworked. > > Signed-off-by: Wojciech Andralojc It cannot be applied without a proper commit log. Please reword also the title to make it shorter and similar to what you can find in the git history. You can find some help in the doc: h

[dpdk-dev] [PATCH 3/3] keepalive: add rte_keepalive_xstats() and example

Morning, On 20/01/2016 15:53, Harry van Haaren wrote: > This patch adds a function that exposes keepalive statistics > re-using the existing rte_eth_xstats struct. The function provides > the client API the opportunity to read last-seen and status of > each core. > > Signed-off-by: Harry van Haare

[dpdk-dev] where to find ethernet CRC when stripping is off

Hi Francesco, On 01/20/2016 06:15 PM, Montorsi, Francesco wrote: > Hi Ivan, > > >> -Original Message- >> You would be right... if the PMDs did not transparently strip the CRC in >> software when hardware CRC stripping is disabled at port configuration (as >> described above). >> See for in

[dpdk-dev] [PATCH v2] cfgfile: support looking up sections by index

On 01/19/2016 06:41 AM, Rich Lane wrote: > This is useful when sections have duplicate names. > > Signed-off-by: Rich Lane > --- > v1->v2: > - Added new symbol to version script. > > lib/librte_cfgfile/rte_cfgfile.c | 16 > lib/librte_cfgfile/rte_cfgfile.h |

[dpdk-dev] L3 Forwarding performance of DPDK on virtio

Hello! On 1/21/2016 7:51 AM, Clarylin L wrote: > I am running dpdk within a virtual guest as a L3 forwarder. > > > The VM has two ports connecting to two linux bridges (in turn connecting > two physical ports). DPDK is used to forward between these two ports (one > port connected to traffic gener

[dpdk-dev] [PATCH] eal: add function to check if primary proc alive

> From: Qiu, Michael > Sent: Thursday, January 21, 2016 6:14 AM > To: Van Haaren, Harry ; david.marchand at > 6wind.com > Cc: dev at dpdk.org > Subject: Re: [dpdk-dev] [PATCH] eal: add function to check if primary proc > alive > > As we could start up many primaries, how does your secondary proc

[dpdk-dev] PATCH 1/2] i40e: support floating VEB config

On 21/01/2016 08:29, David Marchand wrote: > Hello, > > On Thu, Jan 21, 2016 at 8:24 AM, Zhe Tao wrote: >> Add the new floating related argument option in the EAL. >> using this parameter, all the samples can decide whether to use legacy >> VEB/VEPA, >> or floating VEB. > > Not familiar with th

[dpdk-dev] PATCH 1/2] i40e: support floating VEB config

Hello, On Thu, Jan 21, 2016 at 8:24 AM, Zhe Tao wrote: > Add the new floating related argument option in the EAL. > using this parameter, all the samples can decide whether to use legacy > VEB/VEPA, > or floating VEB. Not familiar with this. Can you confirm this stuff make sense for anything b

[dpdk-dev] [PATCH v3] Patch introducing API to read/write Intel Architecture Model Specific Registers (MSR)...

Patch reworked. Signed-off-by: Wojciech Andralojc --- lib/librte_eal/common/include/arch/x86/rte_msr.h | 88 + lib/librte_eal/linuxapp/eal/Makefile | 1 + lib/librte_eal/linuxapp/eal/arch/x86/rte_msr.c | 116 +++ 3 files changed, 205 insertion

[dpdk-dev] [PKTGEN] additional terminal IO question

Black background gets me to the blind reset as well. Pktgen is the only tab I keep with non black background.. On Thu, Jan 21, 2016 at 7:53 AM, Matthew Hall wrote: > If I try using pktgen theme mode (-T) or unmodified, without commenting > out some of the stuff I mentioned I disabled for debuggi

[dpdk-dev] [PATCH] eal: add function to check if primary proc alive

On 1/20/2016 9:26 PM, Harry van Haaren wrote: > This patch adds a new function to the EAL API: > int rte_eal_primary_proc_alive(const char *path); > > The function indicates if a primary process is alive right now. > This functionality is implemented by testing for a write- > lock on the config fil

[dpdk-dev] [PATCH 3/4] virtio/vdev: add ways to interact with vhost

On 1/11/2016 2:43 AM, Tan, Jianfeng wrote: > + if (hw->type == VHOST_KERNEL) { > + struct vhost_vring_file file; > + > + file.fd = hw->backfd; > + nvqs = data->nb_rx_queues + data->nb_tx_queues; > + for (file.index = 0; file.index < nvqs; ++file.i

[dpdk-dev] [PATCH 1/4] mem: add --single-file to create single mem-backed file

On 1/11/2016 2:43 AM, Tan, Jianfeng wrote: [snip] > +#include > +#include > +#include > +#include Please remove unreferenced header files. > > #include > #include > @@ -92,6 +96,9 @@ > #include > #include > > +#define _GNU_SOURCE > +#include > + > #include "eal_private.h" [snip

[dpdk-dev] [PATCH 2/4] i40e: split function for input set change of hash and fdir

Hi, Andrey Thanks for your comments. You are correct, I removed the I40E_INSET_FLEX_PAYLOAD from valid fdir input set values, and this is one reason why I splited function for input set change of hash and and it is because all flex payload configuration can be set in struct rte_fdir_conf during d

[dpdk-dev] [PATCH 00/11] kill global pci device id list

Hello David Yes, long time ago, the same device IDs need to be filled in 3 or 4 places. Then it would be better to have a centralized one, to avoid missing any. And yes, it would be good to maintain device IDs per PMD. As basically we don't expose any base driver header files, and sometimes those