Re: [dpdk-dev] [PATCH] net/sfc: add missing Rx descriptor status callback

Thomas, Ferruh, I've found out that the following patch is deferred in patchwork: https://dpdk.org/dev/patchwork/patch/40455/ It is critical under certain conditions since fix application crash. The patch is net/sfc local and just few lines - absolutely harmless. The only potential DPDK-wide eff

Re: [dpdk-dev] [PATCH] net/thunderx: add support for hardware first skip feature

On Monday 28 May 2018 07:14 PM, Ferruh Yigit wrote: > On 5/28/2018 1:57 PM, rkudurumalla wrote: >> This feature is used to create a hole between HEADROOM >> and actual data.Size of hole is specified in bytes as >> module param to pmd > > Can't mbuf private area be used? It is between HEADROOM a

Re: [dpdk-dev] [PATCH] rte_ring: clarify preemptable nature of ring algorithm

Agree Stephen. But rte_ring is not as basic as spinlock. IMO, existing note results in more questions than answers. From: Stephen Hemminger Sent: Tuesday, May 29, 2018 9:39 PM To: Honnappa Nagarahalli Cc: Olivier Matz ; dev@dpdk.org Subject: Re: [dpdk-dev] [PATCH] rte_ring: clarify preemptable

Re: [dpdk-dev] [dpdk-stable] [PATCH v5 1/2] mk: fix cross build errors

> -Original Message- > From: Bruce Richardson > Sent: Tuesday, May 29, 2018 11:00 PM > To: Thomas Monjalon > Cc: Gavin Hu ; dev@dpdk.org > Subject: Re: [dpdk-stable] [dpdk-dev] [PATCH v2 1/2] mk: fix cross build > errors > > On Tue, May 29, 2018 at 04:45:55PM +0200, Thomas Monjalon wro

Re: [dpdk-dev] [PATCH] rte_ring: clarify preemptable nature of ring algorithm

Spinlock has same problem On Tue, May 29, 2018, 1:06 AM Honnappa Nagarahalli < honnappa.nagaraha...@arm.com> wrote: > rte_ring implementation is not preemptable only under certain > circumstances. > This clarification is helpful for data plane and control plane > communication > using rte_ring. >

Re: [dpdk-dev] Stable ABI status of rte_meter_[t|s]rtcm_profile_config

On 05/28/2018 11:31 AM, Andy Green wrote: Hi - Between 18.02 and the putative 18.05 there were changes in the way the meter stuff deals with its config. I updated the related code in lagopus, but I get warnings about using the new APIs (it's the same for rte_meter_trtcm_profile_config())

Re: [dpdk-dev] [PATCH] net/i40e: fix link status update

29/05/2018 18:23, Fan Zhang: > This patch fixes link status update problem in interrupt mode. Please describe what is the "problem". I think you need to insert the Bugzilla ID here. > Fixes: eef2daf2e199 ("net/i40e: fix link update no wait") > Cc: sta...@dpdk.org

Re: [dpdk-dev] [dpdk-stable] [PATCH v2 1/2] mk: fix cross build errors

29/05/2018 18:20, Gavin Hu: > > > -Original Message- > > From: Bruce Richardson > > Sent: Tuesday, May 29, 2018 11:00 PM > > To: Thomas Monjalon > > Cc: Gavin Hu ; dev@dpdk.org > > Subject: Re: [dpdk-stable] [dpdk-dev] [PATCH v2 1/2] mk: fix cross build > > errors > > > > On Tue, May 29,

Re: [dpdk-dev] [PATCH v1] doc: add SPDX Licence to doc files

> -Original Message- > From: Hemant Agrawal [mailto:hemant.agra...@nxp.com] > Sent: Tuesday, May 29, 2018 4:25 AM > To: Mcnamara, John ; Kovacevic, Marko > ; Thomas Monjalon ; Yigit, > Ferruh > Cc: dev@dpdk.org > Subject: RE: [dpdk-dev] [PATCH v1] doc: add SPDX Licence to doc files > >

Re: [dpdk-dev] [PATCH] doc: document vhost performance regression

> -Original Message- > From: Maxime Coquelin [mailto:maxime.coque...@redhat.com] > Sent: Monday, May 28, 2018 12:32 PM > To: tho...@monjalon.net; Yigit, Ferruh ; Mcnamara, > John ; dev@dpdk.org > Cc: Maxime Coquelin > Subject: [PATCH] doc: document vhost performance regression > > Sign

Re: [dpdk-dev] [PATCH] doc: document bonding known issue

> -Original Message- > From: Nicolau, Radu > Sent: Monday, May 28, 2018 2:44 PM > To: dev@dpdk.org > Cc: tho...@monjalon.net; Yigit, Ferruh ; Mcnamara, > John ; Nicolau, Radu > Subject: [PATCH] doc: document bonding known issue > > Signed-off-by: Radu Nicolau Acked-by: John McNamara

Re: [dpdk-dev] [PATCH v2] doc: document known issues for multiprocess

> -Original Message- > From: Burakov, Anatoly > Sent: Tuesday, May 29, 2018 4:43 PM > To: dev@dpdk.org > Cc: Mcnamara, John ; Kovacevic, Marko > ; Yigit, Ferruh ; > tho...@monjalon.net > Subject: [PATCH v2] doc: document known issues for multiprocess > > Also, reference Bugzilla entry f

Re: [dpdk-dev] [PATCH v2] rte_ring: clarify preemptible nature of ring algorithm

I do not see the documentation regarding this in programmer's guide. -Original Message- From: Burakov, Anatoly Sent: Tuesday, May 29, 2018 4:10 AM To: Honnappa Nagarahalli ; olivier.m...@6wind.com Cc: dev@dpdk.org Subject: Re: [dpdk-dev] [PATCH v2] rte_ring: clarify preemptible nature of

[dpdk-dev] [PATCH] net/i40e: fix link status update

This patch fixes link status update problem in interrupt mode. Fixes: eef2daf2e199 ("net/i40e: fix link update no wait") Cc: sta...@dpdk.org Signed-off-by: Fan Zhang --- drivers/net/i40e/i40e_ethdev.c | 14 +++--- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/drivers/net

[dpdk-dev] Documentation bug or I am doing something wrong

Hi, I have a VM and a container running inside VM. I am creating virtio/vhost as described in the following link https://dpdk.org/doc/guides/howto/virtio_user_for_container_networking.html (1st issue) Ubuntu:latest or Ubuntu:16.04 doesn't come with 'libnuma1' installed by default. If I just have

Re: [dpdk-dev] [dpdk-stable] [PATCH v2 1/2] mk: fix cross build errors

> -Original Message- > From: Bruce Richardson > Sent: Tuesday, May 29, 2018 11:00 PM > To: Thomas Monjalon > Cc: Gavin Hu ; dev@dpdk.org > Subject: Re: [dpdk-stable] [dpdk-dev] [PATCH v2 1/2] mk: fix cross build > errors > > On Tue, May 29, 2018 at 04:45:55PM +0200, Thomas Monjalon wro

Re: [dpdk-dev] [PATCH v2] devtools: check orphan symbols in map files

27/05/2018 23:54, Thomas Monjalon: > The script check-symbol-maps.sh finds the symbols exported > in a map file but not referenced in the codebase. > > Suggested-by: Pavan Nikhilesh > Signed-off-by: Thomas Monjalon > --- > v2: > - rewrite Python script from Pavan in a smaller shell script >

Re: [dpdk-dev] Compiling RSS ebpf

Hi Sameeh, RSS ebpf source code compilation is planned for dpdk next releases. In order to compile the current tap_bpf_program.c code you will need definitions found in iproute2: https://git.kernel.org/pub/scm/network/iproute2/iproute2.git/ 1. Please clone iproute2 tree and make it acces

[dpdk-dev] [PATCH v2] doc: document known issues for multiprocess

Also, reference Bugzilla entry for keeping most current information in one place. Signed-off-by: Anatoly Burakov --- Notes: v2: clarify wording doc/guides/rel_notes/release_18_05.rst | 13 + 1 file changed, 13 insertions(+) diff --git a/doc/guides/rel_notes/release_18_05.rst

Re: [dpdk-dev] [PATCH v5] devtools: add test script for meson builds

29/05/2018 16:58, Richardson, Bruce: > > > -Original Message- > > From: Thomas Monjalon [mailto:tho...@monjalon.net] > > Sent: Tuesday, May 29, 2018 3:43 PM > > To: dev@dpdk.org > > Cc: Richardson, Bruce > > Subject: [PATCH v5] devtools: add test script for meson builds > > > > From: Bru

Re: [dpdk-dev] [PATCH v2] doc: add guides for patch fix issues

29/05/2018 13:01, Marko Kovacevic: > Added contribution guideline for adding tags > when sending patches that have been raised on > Bugzilla > > Signed-off-by: Marko Kovacevic > Acked-by: Ferruh Yigit Applied, thanks. Note: I have re-wrapped the text below: > +`Bugzilla

Re: [dpdk-dev] request to postpone release to tomorrow for an driver issue

On 5/29/2018 4:07 PM, Thomas Monjalon wrote: > 29/05/2018 17:06, Ferruh Yigit: >> Hi Thomas, >> >> We found an i40e link status issue, it has been described in bugzilla[1], but >> briefly when lsc interrupt is enabled, links status is not reliable. >> >> We are aware of the risk at this point and t

Re: [dpdk-dev] [dpdk-stable] [PATCH v5 1/2] mk: fix cross build errors

29/05/2018 12:43, Gavin Hu: > --- a/buildtools/pmdinfogen/Makefile > +++ b/buildtools/pmdinfogen/Makefile > -HOST_CFLAGS += $(WERROR_FLAGS) -g > +HOST_CFLAGS += -Wno-implicit-fallthrough $(WERROR_FLAGS) -g There is a compilation error with clang. Please see this comment: http://dpdk.org/ml

Re: [dpdk-dev] request to postpone release to tomorrow for an driver issue

29/05/2018 17:06, Ferruh Yigit: > Hi Thomas, > > We found an i40e link status issue, it has been described in bugzilla[1], but > briefly when lsc interrupt is enabled, links status is not reliable. > > We are aware of the risk at this point and the scope of the issue and change > is > limited to

[dpdk-dev] request to postpone release to tomorrow for an driver issue

Hi Thomas, We found an i40e link status issue, it has been described in bugzilla[1], but briefly when lsc interrupt is enabled, links status is not reliable. We are aware of the risk at this point and the scope of the issue and change is limited to the driver. There is already a fix but it is un

[dpdk-dev] [Bug 54] i40e port link status no updated for interrupt mode

https://dpdk.org/tracker/show_bug.cgi?id=54 Bug ID: 54 Summary: i40e port link status no updated for interrupt mode Product: DPDK Version: 18.05 Hardware: All OS: All Status: CONFIRMED Severity: major

Re: [dpdk-dev] [dpdk-stable] [PATCH v2 1/2] mk: fix cross build errors

On Tue, May 29, 2018 at 04:45:55PM +0200, Thomas Monjalon wrote: > 28/05/2018 15:24, Bruce Richardson: > > Would a simpler solution for this not be to put "-Wno-implicit-fallthrough" > > for pmdinfogen? GCC will not give a warning for an unrecognised "-Wno" > > flag when compiling, unless there are

Re: [dpdk-dev] [PATCH v5] devtools: add test script for meson builds

> -Original Message- > From: Thomas Monjalon [mailto:tho...@monjalon.net] > Sent: Tuesday, May 29, 2018 3:43 PM > To: dev@dpdk.org > Cc: Richardson, Bruce > Subject: [PATCH v5] devtools: add test script for meson builds > > From: Bruce Richardson > > To simplify testing with the meso

Re: [dpdk-dev] [dpdk-stable] [PATCH v2 1/2] mk: fix cross build errors

28/05/2018 15:24, Bruce Richardson: > Would a simpler solution for this not be to put "-Wno-implicit-fallthrough" > for pmdinfogen? GCC will not give a warning for an unrecognised "-Wno" > flag when compiling, unless there are other errors. This means we can just > use the flag without bothering wi

[dpdk-dev] [PATCH v5] devtools: add test script for meson builds

From: Bruce Richardson To simplify testing with the meson and ninja builds, we can add a script to set up and do multiple builds. Currently this script sets up: * clang and gcc builds * builds using static and shared linkage for binaries (libs are always built as both) * a build using the low

Re: [dpdk-dev] [RFC v2] vhost: new rte_vhost API proposal

> -Original Message- > From: Stefan Hajnoczi [mailto:stefa...@redhat.com] > Sent: Friday, May 25, 2018 12:06 PM > On Fri, May 18, 2018 at 03:01:05PM +0200, Dariusz Stojaczyk wrote: > > +struct rte_vhost2_msg { > > + uint32_t id; > > Is this what the vhost-user specification calls the

Re: [dpdk-dev] [PATCH v5 2/2] doc: add a guide doc for cross compiling from x86

Can you supersede your v4. :) After looking at the v5 looks good to me. Acked-by: Marko Kovacevic

[dpdk-dev] [PATCH v2] net/i40e: workaround for Fortville performance

The GL_SWR_PM_UP_THR value is not impacted from the link speed, its value is set according to the total number of ports for a better pipe-monitor configuration. All bellowing relevant device IDs are considered (NICs, LOMs, Mezz and Backplane): Device-ID ValueComments 0x1572 0x0303030

Re: [dpdk-dev] [PATCH] crypto/armv8: fix HMAC supported digest sizes

On 5/29/2018 4:15 PM, Anoob Joseph wrote: For HMAC algorithms (SHAx-HMAC), the supported digest sizes are not a fixed value, but a range between 1 and the maximum digest size for those algorithms. Fixes: 0f89def76127 ("crypto/armv8: fix HMAC supported key sizes") Cc: sta...@dpdk.org Signed-off-

Re: [dpdk-dev] [RFC] hot plug failure handle mechanism

On Thu, May 24, 2018 at 07:55:43AM +0100, Guo, Jia wrote: >The hot plug failure handle mechanism should be come across as bellow: > >1. Add a new bus ops “handle_hot-unplug”in bus to handle bus >read/write error, it is bus-specific and each > >kind of bus can implement its

[dpdk-dev] [PATCH v2] doc: add guides for patch fix issues

Added contribution guideline for adding tags when sending patches that have been raised on Bugzilla Signed-off-by: Marko Kovacevic Acked-by: Ferruh Yigit --- V2: removed accidental indents (Thomas) --- doc/guides/contributing/patches.rst | 21 +++-- 1 file changed, 19 inserti

Re: [dpdk-dev] [PATCH v2] devtools: add test script for meson builds

On Tue, May 29, 2018 at 12:38:14PM +0200, Thomas Monjalon wrote: > 28/05/2018 15:20, Bruce Richardson: > > On Mon, May 28, 2018 at 12:26:24PM +0200, Thomas Monjalon wrote: > > > 28/05/2018 11:33, Bruce Richardson: > > > > On Sat, May 26, 2018 at 11:32:53AM +0200, Thomas Monjalon wrote: > > > > > 25

[dpdk-dev] [PATCH] crypto/armv8: fix HMAC supported digest sizes

For HMAC algorithms (SHAx-HMAC), the supported digest sizes are not a fixed value, but a range between 1 and the maximum digest size for those algorithms. Fixes: 0f89def76127 ("crypto/armv8: fix HMAC supported key sizes") Cc: sta...@dpdk.org Signed-off-by: Anoob Joseph Signed-off-by: Sachin Saxe

Re: [dpdk-dev] [PATCH v1] doc: add guides for patch fix issues

> 28/05/2018 17:23, Marko Kovacevic: > > -`Coverity > > `_ > > -is a tool for static code analysis. > > -It is used as a cloud-based service used to scan the DPDK source > > code, -and alert developers of any potential defects in t

[dpdk-dev] [PATCH v5 0/2] *** cross gcc compile fix and add a guide doc ***

*** Correct two spelling errors in the doc *** Gavin Hu (2): mk: fix cross build errors doc: add a guide doc for cross compiling from x86 buildtools/pmdinfogen/Makefile | 2 +- .../linux_gsg/cross_build_dpdk_for_arm64.rst | 125 + doc/guides/li

[dpdk-dev] [PATCH v5 1/2] mk: fix cross build errors

The "-Wimplicit-fallthrough=2" option was introduced into gcc 7.0, it was enabled when the cross compiler gcc is greater than 7.0, but for the host side buildtools/pmdinfogen, if the native is older than 7.0, it should not be enabled. The fix is to simply enable -Wnoimplicit-fallthrough for pmdinf

[dpdk-dev] [PATCH v5 2/2] doc: add a guide doc for cross compiling from x86

This is the guide for cross compiling ARM64 DPDK from X86 hosts. Signed-off-by: Gavin Hu Reviewed-by: Steve Capper Reviewed-by: Honnappa Nagarahalli Reviewed-by: Marko Kovacevic Reviewed-by: Jerin Jacob Reviewed-by: Thomas Monjalon Reviewed-by: Bruce Richardson --- .../linux_gsg/cross_buil

Re: [dpdk-dev] [PATCH v2] devtools: add test script for meson builds

28/05/2018 15:20, Bruce Richardson: > On Mon, May 28, 2018 at 12:26:24PM +0200, Thomas Monjalon wrote: > > 28/05/2018 11:33, Bruce Richardson: > > > On Sat, May 26, 2018 at 11:32:53AM +0200, Thomas Monjalon wrote: > > > > 25/05/2018 17:18, Bruce Richardson: > > > > > On Fri, May 25, 2018 at 04:51:5

Re: [dpdk-dev] [PATCH v1] doc: add guides for patch fix issues

28/05/2018 17:23, Marko Kovacevic: > -`Coverity > `_ > -is a tool for static code analysis. > -It is used as a cloud-based service used to scan the DPDK source code, > -and alert developers of any potential defects in the source c

Re: [dpdk-dev] [PATCH 2/2] doc: add vxlan and nvgre tunnel update in release notes

> > Signed-off-by: Mohammad Abdul Awal > > Acked-by: John McNamara Series applied, thanks Note: moved upper to group ethdev features

Re: [dpdk-dev] [PATCH v1] doc: postpone devargs genericisation work

28/05/2018 18:10, Gaetan Rivet: > Device querying and declaration has been postponed to 18.08. > Additionally, while working on the feature, some changes previously > announced won't be enacted. > > Signed-off-by: Gaetan Rivet Applied, thanks

[dpdk-dev] [PATCH v2 2/2] vhost: improve batched copies performance

Instead of copying batch_copy_nb_elems into the stack, this patch uses it directly. Small performance gain of 3% is seen when running PVP benchmark. Signed-off-by: Maxime Coquelin --- lib/librte_vhost/virtio_net.c | 29 ++--- 1 file changed, 14 insertions(+), 15 deletion

[dpdk-dev] [PATCH v2 1/2] vhost: unify Rx mergeable and non-mergeable paths

This patch reworks the vhost enqueue path so that a single code path is used for both Rx mergeable or non-mergeable cases. Signed-off-by: Maxime Coquelin --- lib/librte_vhost/virtio_net.c | 347 +++--- 1 file changed, 23 insertions(+), 324 deletions(-) diff -

[dpdk-dev] [PATCH v2 0/2] Vhost: unitfy receive paths

Hi, This second version fixes the feature bit check in rxvq_is_mergeable(), and remove "mergeable" from rx funcs names. No difference is seen in the benchmarks This series is preliminary work to ease the integration of packed ring layout support. But even without packed ring layout, the result is

[dpdk-dev] DPDK techboard minutes of May 9

The Meeting on April 25 was cancelled because of Quorum was not present. Meeting notes for the DPDK technical board meeting held on 2018-05-09 Attendees: - Bruce Richardson - Ferruh Yigit - Hemant Agrawal - Jerin Jacob - Konstantin Ananyev - Olivier

Re: [dpdk-dev] [PATCH v2] rte_ring: clarify preemptible nature of ring algorithm

On 29-May-18 6:28 AM, Honnappa Nagarahalli wrote: rte_ring implementation is not preemptible only under certain circumstances. This clarification is helpful for data plane and control plane communication using rte_ring. Signed-off-by: Honnappa Nagarahalli Reviewed-by: Gavin Hu Reviewed-by: Ola

Re: [dpdk-dev] [PATCH v4 2/2] doc: add a guide doc for cross compiling from x86

> Signed-off-by: Gavin Hu > > .../linux_gsg/cross_build_dpdk_for_arm64.rst | 125 > + > doc/guides/linux_gsg/index.rst | 1 + > 2 files changed, 126 insertions(+) > > +Cross compile DPDK for ARM64 > + <...> > +Getting t

[dpdk-dev] [PATCH v1] net/i40e: workaround for Fortville performance

The GL_SWR_PM_UP_THR value is not impacted from the link speed, its value is set according to the total number of ports for a better pipe-monitor configuration. All bellowing relevant device IDs are considered (NICs, LOMs, Mezz and Backplane): Device-ID ValueComments 0x1572 0x0303030

[dpdk-dev] [PATCH 3/3] gso: add UDP/IPv4 GSO to the programmer guide

Signed-off-by: Jiayu Hu --- doc/guides/prog_guide/generic_segmentation_offload_lib.rst | 6 ++ 1 file changed, 6 insertions(+) diff --git a/doc/guides/prog_guide/generic_segmentation_offload_lib.rst b/doc/guides/prog_guide/generic_segmentation_offload_lib.rst index 9959f0d..cf700c5 100644 -

[dpdk-dev] [PATCH 2/3] app/testpmd: enable UDP GSO in the checksum forwarding engine

This patch enables GSO for UDP/IPv4 packets. Oversized UDP/IPv4 packets transmitted over a GSO-enabled port will undergo segmentation. Signed-off-by: Jiayu Hu --- app/test-pmd/cmdline.c | 5 +++-- app/test-pmd/csumonly.c | 2 ++ app/test-pmd/testpmd.c | 2 +- 3 files changed, 6 insertions(+),

[dpdk-dev] [PATCH 1/3] gso: support UDP/IPv4 fragmentation

This patch adds GSO support for UDP/IPv4 packets. Supported packets may include a single VLAN tag. UDP/IPv4 GSO doesn't check if input packets have correct checksums, and doesn't update checksums for output packets (the responsibility for this lies with the application). Additionally, UDP/IPv4 GSO

[dpdk-dev] [PATCH 0/3] Support UDP/IPv4 GSO

With the support of UDP Fragmentation Offload (UFO) and TCP Segmentation Offload (TSO) in virtio, VMs can exchange large UDP and TCP packets exceeding MTU between each other, which can greatly reduce per-packet processing overheads. When the destination of the large TCP and UDP packets is crossing

[dpdk-dev] [PATCH v4 2/2] doc: add a guide doc for cross compiling from x86

This is the guide for cross compiling ARM64 DPDK from X86 hosts. Signed-off-by: Gavin Hu Reviewed-by: Steve Capper Reviewed-by: Honnappa Nagarahalli Reviewed-by: Marko Kovacevic Reviewed-by: Jerin Jacob Reviewed-by: Thomas Monjalon Reviewed-by: Bruce Richardson --- .../linux_gsg/cross_buil

[dpdk-dev] [PATCH v4 1/2] mk: fix cross build errors

The "-Wimplicit-fallthrough=2" option was introduced into gcc 7.0, it was enabled when the cross compiler gcc is greater than 7.0, but for the host side buildtools/pmdinfogen, if the native is older than 7.0, it should not be enabled. The fix is to simply enable -Wnoimplicit-fallthrough for pmdinf

[dpdk-dev] [PATCH v4 0/2] *** cross gcc fix and guide doc ***

*** 1. Simply use -Wnoimplicit-fallthrough for pmdinfogen, other than gcc version check. *** *** 2. Make the doc in the correct format *** *** 3. Correct the rst index file *** Gavin Hu (2): mk: fix cross build errors doc: add a guide doc for cross compiling from x86 buildtools/pmdinfogen/M

[dpdk-dev] Query regarding mailbox interface (VFD relatated)

Hi, I was using testpmd in host and the testpmd in a VM with SRIOV VF's. Here the testpmd in host is acting as the PF. Does the testpmd on the host still need to run the 'polling loop' on the port since it is not coming in the datapath for the VF ? Thinking on the above lines, I tried to comment t