Re: [dpdk-dev] [20.08 PATCH] license: removing the dual prefix to avoid confusion

Hi Bruce, Will you please check it with Trishan and DPDK GB board? DPDK license indicates the correct license types in: http://git.dpdk.org/dpdk/tree/license/README However in exception files we added the keyword "Dual" - which is unnecessary and not part of standard SPDX definition.

Re: [dpdk-dev] [PATCH] net/bnxt: fix build issue

Hello Ajit, On Wed, Jul 29, 2020 at 2:48 AM Ajit Khaparde wrote: > I have submitted a patch [1]. With that memory management for > Extended Exact Match is simplified. We won't need any config or meson option > with that change. > Thanks for removing a build option :-). You can drop my patch then

Re: [dpdk-dev] [PATCH v3 1/8] net/dpaa: add support for fmlib in dpdk

Hi David > -Original Message- > From: David Marchand > Sent: Tuesday, July 28, 2020 7:12 PM > To: Hemant Agrawal > Cc: Thomas Monjalon ; Sachin Saxena > ; dev@dpdk.org; Ferruh Yigit > ; techbo...@dpdk.org > Subject: Re: [dpdk-dev] [PATCH v3 1/8] net/dpaa: add support for fmlib in > dpdk

[dpdk-dev] [PATCH v1 0/2] wrong pointer passed of ring

Fix wrong pointer passed problems when using rte_ring_[sp|mp]enqueue APIs to enqueue one element into the ring. Feifei Wang (2): ring: fix the misdescription of the param test/ring: fix wrong parameter passed to the enqueue APIs app/test/test_ring.h | 6 +++--- lib/librte_ring/rte_ring

[dpdk-dev] [PATCH v1 1/2] ring: fix the misdescription of the param

When enqueue one element to the ring, the param "obj" should be the object to be added into the ring. The object is of type void*. Fixes: af75078fece3 ("first public release") Cc: sta...@dpdk.org Signed-off-by: Feifei Wang Reviewed-by: Ruifeng Wang --- lib/librte_ring/rte_ring.h | 6 +++--- 1

[dpdk-dev] [PATCH v1 2/2] test/ring: fix wrong param passed to the enqueue APIs

When enqueue one element (object of type void*) to ring in the performance test, a pointer (the object to be enqueued) should be passed to rte_ring_[sp|mp]enqueue APIs, not the pointer to a table of void *pointers (objects). Fixes: a9fe152363e2 ("test/ring: add custom element size functional tests

Re: [dpdk-dev] [PATCH v2 2/3] net/vhost: fix queue update

> -Original Message- > From: Xia, Chenbo > Sent: 2020?7?29? 10:53 > To: Maxime Coquelin ; dev@dpdk.org; > ma...@mellanox.com; Liu, Yong ; Wang, Yinan > > Cc: tho...@monjalon.net; Yigit, Ferruh ; > david.march...@redhat.com > Subject: RE: [PATCH v2 2/3] net/vhost: fix queue update > >

Re: [dpdk-dev] [PATCH v2 0/3] Fix Vhost regressions

This patch can fix multi-queue performance drop issue and interrupt issue.Thanks! BR, Yinan > -Original Message- > From: Maxime Coquelin > Sent: 2020?7?29? 0:50 > To: dev@dpdk.org; ma...@mellanox.com; Xia, Chenbo > ; Liu, Yong ; Wang, Yinan > > Cc: tho...@monjalon.net; Yigit, Ferruh ;

[dpdk-dev] [PATCH v3] doc: add deprecation notice for sched changes

Add deprecation note for making changes in data structures and APIs in order to allow dynamic configuration of subport bandwidth profile. These changes are aligned as suggested in the RFC[1]. https://mails.dpdk.org/archives/dev/2020-July/175161.html Signed-off-by: Savinay Dharmappa Acked-by: Jas

Re: [dpdk-dev] [PATCH] net/bnxt: fix build issue

On Thu, Jul 9, 2020 at 1:15 AM David Marchand wrote: > In existing build env, RTE_LIBRTE_BNXT_PMD_SYSTEM is unset. > Testing against a n value does not work and we end up with a link issue: > > /usr/bin/ld: tf_core/tf_em_common.o: in function `tf_em_ext_common_alloc': > .../dpdk/drivers/net/bnxt/

[dpdk-dev] [PATCH] net/bnxt: remove EEM system memory support

From: Randy Schacher Remove the memory management scheme for Extended Exact Match using system memory. Using host memory scheme instead which was the default anyway. Fixes: b2da02480cb7 ("net/bnxt: support EEM system memory") Signed-off-by: Randy Schacher Signed-off-by: Ajit Khaparde Reviewed

[dpdk-dev] [PATCH v1] net/virtio-user: fix return value check

Setting the flags of tapfd may fail and the return value should be checked. Coverity issue: 140739 Fixes: e3b434818bbb ("net/virtio-user: support kernel vhost") Cc: sta...@dpdk.org Signed-off-by: Chenbo Xia --- drivers/net/virtio/virtio_user/vhost_kernel_tap.c | 5 - 1 file changed, 4 inser

Re: [dpdk-dev] [PATCH v2 2/3] net/vhost: fix queue update

> -Original Message- > From: Maxime Coquelin > Sent: Wednesday, July 29, 2020 12:50 AM > To: dev@dpdk.org; ma...@mellanox.com; Xia, Chenbo > ; Liu, Yong ; Wang, Yinan > > Cc: tho...@monjalon.net; Yigit, Ferruh ; > david.march...@redhat.com; Maxime Coquelin > > Subject: [PATCH v2 2/3] n

Re: [dpdk-dev] [PATCH v2 1/1] net: fix TSO packets checksum incorrect

Tested-by: Zhang, XiX Regards, Xie Wei -Original Message- From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Yuying Zhang Sent: Wednesday, July 29, 2020 1:10 AM To: dev@dpdk.org; olivier.m...@6wind.com; Zhang, Qi Z ; Yang, Qiming Cc: Zhang, Yuying Subject: [dpdk-dev] [PATCH v2 1/1]

[dpdk-dev] [PATCH v2] regex/mlx5: fix sq free check on enqueue

Free sq check had a bug, causing jobs to overwrite. Fixes: 8740ba5fe57f ("regex/mlx5: add enqueue implementation") Signed-off-by: Yuval Avnery Acked-by: Ori Kam --- drivers/regex/mlx5/mlx5_regex_fastpath.c | 5 + 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/regex/mlx

[dpdk-dev] [PATCH v5] vhost: fix async copy fail on multi-page buffers

Async copy fails when single ring buffer vector is splited on multiple physical pages. This happens because current hpa address translation function doesn't handle multi-page buffers. A new gpa to hpa address conversion function, which returns the hpa on the first hitting host pages, is implemented

Re: [dpdk-dev] [PATCH v4] vhost: fix async copy fail on multi-page buffers

Hi Maxime, > -Original Message- > From: Fu, Patrick > Sent: Wednesday, July 29, 2020 9:40 AM > To: 'Maxime Coquelin' ; dev@dpdk.org; Xia, > Chenbo > Subject: RE: [PATCH v4] vhost: fix async copy fail on multi-page buffers > > Hi Maxime, > > > -Original Message- > > From: Maxime

Re: [dpdk-dev] [PATCH v4] vhost: fix async copy fail on multi-page buffers

Hi Maxime, > -Original Message- > From: Maxime Coquelin > Sent: Tuesday, July 28, 2020 9:55 PM > To: Fu, Patrick ; dev@dpdk.org; Xia, Chenbo > > Subject: Re: [PATCH v4] vhost: fix async copy fail on multi-page buffers > > > > On 7/28/20 5:28 AM, patrick...@intel.com wrote: > > From: P

Re: [dpdk-dev] [PATCH] doc: vhost multi-queue reconnection known issue

Hi Ferruh, Thank you for your comments and fix. Regards, Xuan -Original Message- From: Ferruh Yigit Sent: Wednesday, July 29, 2020 1:40 AM To: Ding, Xuan ; maxime.coque...@redhat.com; Wang, Zhihong ; Xia, Chenbo Cc: dev@dpdk.org Subject: Re: [dpdk-dev] [PATCH] doc: vhost multi-queue

Re: [dpdk-dev] [PATCH 0/5] compiling ethdev lib under windows

On Thu, Jun 25, 2020 at 04:30:33PM +0300, Fady Bader wrote: > Added needed changes in order to get ethdev compiling under windows. > > Depends-on: series-10382 ("compile librte_net for windows") > > Fady Bader (5): > eal: added interrupts empty stubs > eal: updated export list for Windows >

Re: [dpdk-dev] DPDK PDUMP Issue

Snipped > Hi Team, > > With fix suggest in prev mail thread at testpmd side, PDUMP works with > testpmd. > > However when we try to run our own primary app with PDUMP as a secondary > process, PDUMP console comes up, however it does not capture any packets. > > Changes made at primary app side:

Re: [dpdk-dev] [PATCH v1] regex/mlx5: fix sq free check on enqueue

There is a bug here, will send another version > -Original Message- > From: Yuval Avnery > Sent: Tuesday, July 28, 2020 10:55 AM > To: Ori Kam > Cc: Thomas Monjalon ; dev@dpdk.org; Yuval > Avnery > Subject: [PATCH v1] regex/mlx5: fix sq free check on enqueue > > Free sq check had a bug

[dpdk-dev] iRE: [PATCH v6] net/ice: fix GTPU down/uplink and extension conflict

> -Original Message- > From: Su, Simei > Sent: Tuesday, July 28, 2020 7:08 PM > To: Zhang, Qi Z ; Xing, Beilei > Cc: dev@dpdk.org; Guo, Jia ; Su, Simei > > Subject: [PATCH v6] net/ice: fix GTPU down/uplink and extension conflict > > When adding a RSS rule with GTPU_DWN/UP, it will wr

Re: [dpdk-dev] [PATCH 0/2] fixes for ice driver

> -Original Message- > From: wangyunjian > Sent: Tuesday, July 28, 2020 9:11 PM > To: dev@dpdk.org > Cc: Yang, Qiming ; Zhang, Qi Z > ; jerry.lili...@huawei.com; xudin...@huawei.com; > Yunjian Wang > Subject: [dpdk-dev] [PATCH 0/2] fixes for ice driver > > From: Yunjian Wang > > Thi

Re: [dpdk-dev] [PATCH] net/i40e: fix a wrong bitmap free call

> -Original Message- > From: Sun, Chenmin > Sent: Tuesday, July 28, 2020 8:51 PM > To: Zhang, Qi Z ; Xing, Beilei > Cc: dev@dpdk.org; Sun, Chenmin > Subject: [PATCH] net/i40e: fix a wrong bitmap free call > > From: Chenmin Sun > > This patch fixes the coverity warning #361024. > rt

Re: [dpdk-dev] [PATCH v1] net/ice: fix TCP checksum offload failure

> -Original Message- > From: Wang, Haiyue > Sent: Tuesday, July 28, 2020 9:42 PM > To: dev@dpdk.org; Yang, Qiming ; Zhang, Qi Z > > Cc: Wang, Yinan ; Xu, Ting ; > Wang, Haiyue ; sta...@dpdk.org > Subject: [PATCH v1] net/ice: fix TCP checksum offload failure > > The L4LEN field of the

Re: [dpdk-dev] [PATCH v5 2/2] doc: update QAT PMD release notes

27/07/2020 12:14, Adam Dybkowski: > This patch updates 20.08 release notes inside > the part that describe changes in Intel QuickAssist PMD. > > Fixes: faa57df0b458 ("crypto/qat: support ChaCha20-Poly1305") > Fixes: 9904ff684981 ("common/qat: improve multi-process handling") > > Signed-off-by: Ad

Re: [dpdk-dev] [pull-request] next-eventdev 20.08 RC3

24/07/2020 07:27, Jerin Jacob Kollanukkaran: > http://dpdk.org/git/next/dpdk-next-eventdev Pulled, thanks

Re: [dpdk-dev] [PATCH v4 16/22] net/bnxt: fix table reference count for shadow tcam

On Tue, Jul 28, 2020 at 10:39 AM Ferruh Yigit wrote: > On 7/28/2020 6:33 PM, Ajit Khaparde wrote: > > > > > > On Tue, Jul 28, 2020 at 10:00 AM Ferruh Yigit > > wrote: > > > > On 7/28/2020 7:34 AM, Ajit Khaparde wrote: > > > From: Mike Baucom >

Re: [dpdk-dev] [PATCH v4 16/22] net/bnxt: fix table reference count for shadow tcam

On Tue, Jul 28, 2020 at 10:00 AM Ferruh Yigit wrote: > On 7/28/2020 7:34 AM, Ajit Khaparde wrote: > > From: Mike Baucom > > > > Moved setting the refcnt for shadow tcam and table entries to the > > allocation path only. The insert can be called multiple times for > > updates and was resetting t

[dpdk-dev] [pull-request] next-crypto 20.08 rc3

The following changes since commit f6d099d7da83fb973f6849161795d08842d0d328: common/mlx5: remove class check from class drivers (2020-07-28 19:01:30 +0200) are available in the Git repository at: http://dpdk.org/git/next/dpdk-next-crypto for you to fetch changes up to 431434216f9401316a340

Re: [dpdk-dev] [PATCH v5 0/2] common/qat: support GEN2 QAT device 200xx

> -Original Message- > From: Adam Dybkowski > Sent: Monday, July 27, 2020 3:44 PM > To: dev@dpdk.org; fiona.tr...@intel.com; Akhil Goyal > Cc: Adam Dybkowski > Subject: [PATCH v5 0/2] common/qat: support GEN2 QAT device 200xx > > This adds pci detection and documentation for Intel GE

Re: [dpdk-dev] [PATCH v2 0/3] armv8 crypto PMD

> > This series updated log system used by armv8 crypto PMD. > The config option used to enable and disable logs was removed, and > logs are always enabled. > Created dedicated log type for the PMD and not to use crypto dev > generic log type. > Series applied to dpdk-next-crypto Thanks.

Re: [dpdk-dev] [PATCH] metrics: make number of metrics names configurable

On Tue, 28 Jul 2020 11:24:58 +0100 Bruce Richardson wrote: > On Thu, Jul 02, 2020 at 10:28:52AM -0700, Stephen Hemminger wrote: > > The maximum number of metrics is hardcoded at 256. > > This severely limits the usefulness of the library. > > It should be configurable like other limits in DPDK. >

Re: [dpdk-dev] [PATCH v2 3/3] crypto/armv8: remove redundant assert definition

> No need to define assert function in PMD since RTE provides the same. > Remove private definition and use RTE_VERIFY instead. > > Suggested-by: David Marchand > Signed-off-by: Ruifeng Wang > --- > drivers/crypto/armv8/armv8_pmd_private.h | 8 > drivers/crypto/armv8/rte_armv8_pmd.c

Re: [dpdk-dev] [PATCH v2 1/3] crypto/armv8: remove log debug option

> Typo in debug log switch macro caused debug log cannot be enabled. > Since no log used in data path, remove the debug option entirely > and have logs always enabled. > > Resolved compilation error when debug log is enabled: > rte_armv8_pmd.c: In function ‘process_armv8_chained_op’: > rte_armv8_p

Re: [dpdk-dev] [PATCH v2 2/3] crypto/armv8: use dedicated log type

> armv8 crypto PMD used CRYPTODEV general log type. > Create a dedicated log type for the PMD to not pollute CRYPTODEV log type. > > Typo in crypto dev name macro caused unexpected device name in log. > Fixed the typo to log with correct device name. > > Fixes: 169ca3db550c ("crypto/armv8: add PM

Re: [dpdk-dev] [PATCH v1] app/crypto-perf: set mbuf lengths correctly for DOCSIS tests

Hi Pablo/David, > > Hi David, > > > Hi Pablo, > > > > > -Original Message- > > > From: De Lara Guarch, Pablo > > > Sent: Friday, July 17, 2020 8:04 PM > > > > @@ -48,6 +48,10 @@ cperf_set_ops_security(struct rte_crypto_op **ops, > > > > } else > > > >

Re: [dpdk-dev] [PATCH v2] app/crypto-perf: support security protocol in PMDCC mode

> > This patch adds support for DOCSIS and PDCP security protocols to the > pmd-cyclecount mode of the crypto performance tool. Adding this support > involves freeing the correct session type (i.e. security or cryptodev > session) when the test ends, depending on the op_type specified. > > Signed

[dpdk-dev] [PATCH v5 7/8] app/proc-info: add crypto security context info

From: Hemant Agrawal If crypto context is not present, no point in displaying it. This patch adds the crypto based security context info. Also improve the flag printing to SECURITY OFFLOAD from INLINE. Use common code for displaying crypto context information when doing show_ports and show_cryp

[dpdk-dev] [PATCH v5 5/8] app/proc-info: enhance mempool to print ops name

From: Hemant Agrawal Enhance the mempool details to also print the ops index and name Signed-off-by: Hemant Agrawal Signed-off-by: Stephen Hemminger --- app/proc-info/main.c | 5 + 1 file changed, 5 insertions(+) diff --git a/app/proc-info/main.c b/app/proc-info/main.c index 28838be882b9

[dpdk-dev] [PATCH v5 8/8] app/proc-info: provide way to request info on owned ports

There are cases where a port maybe owned by another (failsafe, netvsc, bond); but currently proc-info has no way to look at stats of those ports. This patch provides way for the user to explicitly ask for these ports. If no portmask is given the output is unchanged; it only shows the top level por

[dpdk-dev] [PATCH v5 4/8] app/proc-info: add more info to show_ports

Revise the display of port information to include more data and be more human friendly. * Display units for port speed, and decode link fields. * Show driver and device information * Show MAC address * Show flow control information * Combine lines if possible * Show all multicast mode

[dpdk-dev] [PATCH v5 6/8] app/proc-info: dump rx and tx descriptor info

Many drivers will report per queue info for both rx and tx as well as how many descriptors are in use. Signed-off-by: Stephen Hemminger Acked-by: Hemant Agrawal --- app/proc-info/main.c | 80 +--- 1 file changed, 67 insertions(+), 13 deletions(-) diff --

[dpdk-dev] [PATCH v5 1/8] app/proc-info: remove unused logtype #define

This logtype is defined but never used. Signed-off-by: Stephen Hemminger Acked-by: Hemant Agrawal --- app/proc-info/main.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/app/proc-info/main.c b/app/proc-info/main.c index abeca4aab438..69e3000616c0 100644 --- a/app/proc-info/main.c +++ b/ap

[dpdk-dev] [PATCH v5 2/8] app/proc-info: eliminate useless borders

Printing extra borders does not improve readability, and is just unnecessary. Putting TSC hz in header also makes no sense here. Signed-off-by: Stephen Hemminger Acked-by: Hemant Agrawal --- app/proc-info/main.c | 35 +++ 1 file changed, 7 insertions(+), 28 delet

[dpdk-dev] [PATCH v5 3/8] app/proc-info: hide EAL info messages

The DPDK EAL info messages at the start of a diagnostic application are not helpful to end user. Suppress them by setting log-level by default. Signed-off-by: Stephen Hemminger Acked-by: Hemant Agrawal --- app/proc-info/main.c | 10 ++ 1 file changed, 6 insertions(+), 4 deletions(-) di

[dpdk-dev] [PATCH v5 0/8] app/proc-info enhancements

The current proc-info command is useful for diagnosing issues with external DPDK applications, but the display is limited and somewhat ugly. This patchset adds some enhancements which show more info and suppress unnecessary stuff. v5 - add mempool name to queue info fix trailing whitespace v4

Re: [dpdk-dev] [PATCH v3] lib/librte_timer:fix corruption with reset

Hi Sarosh, Some comments in-line: > -Original Message- > From: Sarosh Arif > Sent: Friday, July 10, 2020 2:00 AM > To: rsanf...@akamai.com; Carrillo, Erik G ; > dev@dpdk.org > Cc: sta...@dpdk.org; Sarosh Arif ; > h.mikit...@gmail.com > Subject: [PATCH v3] lib/librte_timer:fix corruption

Re: [dpdk-dev] [PATCH v2 3/3] net/vhost: fix interrupt mode

From: Maxime Coquelin: > At .new_device() time, only the first vring pair is now ready, other vrings > are > consfigured later. > > Problem is that when application will setup and enable interrupts, only the > first queue pair Rx interrupt will be enabled. > > This patches fixes the issue by

[dpdk-dev] [PATCH 2/2] net/octeontx: fix Tx xmit command preparation

From: Pavan Nikhilesh When building send command for a given descriptor it expects it to contain the AURA identifier of the pool that it belongs to rather than the pool identifier itself. Fixes: 7f4116bdbb1c ("net/octeontx: add framework for Rx/Tx offloads") Cc: sta...@dpdk.org Signed-off-by: P

[dpdk-dev] [PATCH 1/2] mempool/octeontx: fix aura to pool mapping

From: Pavan Nikhilesh When sending commands to Kernel FPA PF driver, it expects the aura to be in the range of 0 to 16 for a given FPA pool. In OCTEON TX we map a pool,aura pair as single mempool handle, always set the aura id to 0 for a given FPA pool. Fixes: 179c7e893f64 ("mempool/octeontx: fi

[dpdk-dev] [PATCH] event/octeontx: validate events requested against available

From: Pavan Nikhilesh Validate events configured in ssopf against the total number of events configured across all the RX/TIM event adapters. Events available to ssopf can be reconfigured by passing the required amount to kernel bootargs and are only limited by DRAM size. Example: ssopf.

Re: [dpdk-dev] [PATCH v4 00/22] bnxt patches

On Mon, Jul 27, 2020 at 11:34 PM Ajit Khaparde wrote: > Some fixes, cleanups and changes to augment pre-existing > support in infrastructure > > Please apply > > v1->v2: > - Fixed some typos in patch [9/20]. > v2->v3: > - Fixed coding style issues in patch [15/20] to use __rte_attribute. > - U

[dpdk-dev] long initialization time for EAL init

Hi Team, Posting this query on behalf of Balaji as he was not able to send mail to dpdk-dev. We are using OVS 2.12.0 with DPDK 18.11.2 release on Ubuntu 16.04 LTS. We do observe long initialization time for EAL init ( ~10 seconds for EAL memory initialization). Below is our hardware an

[dpdk-dev] [PATCH v1] regex/mlx5: fix sq free check on enqueue

Free sq check had a bug, causing jobs to overwrite. Fixes: 8740ba5fe57f ("regex/mlx5: add enqueue implementation") Signed-off-by: Yuval Avnery Acked-by: Ori Kam --- drivers/regex/mlx5/mlx5_regex_fastpath.c | 5 + 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/drivers/regex/mlx

[dpdk-dev] [PATCH v1] common/mlx5: fix set regex register layout

Reserved field should be 0x60 instead of 0x40. Will fail FW check otherwise. Fixes: be4f4a8b8e3b ("regex/mlx5: add engine status check") Signed-off-by: Yuval Avnery Acked-by: Ori Kam --- drivers/common/mlx5/mlx5_prm.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/c

Re: [dpdk-dev] [PATCH] mbuf: replace c memcpy() code semantics with optimized rte_memcpy()

On Thu, 23 Jul 2020 12:02:40 +0500 Sarosh Arif wrote: > Since rte_memcpy is more optimized it should be used instead of memcpy > > Signed-off-by: Sarosh Arif The part in pkmbuf_pool_init is not performance critical. The layout of rte_mbuf_dynfield is sub optimal. struct rte_mbuf_dynfield {

Re: [dpdk-dev] [PATCH] doc: vhost multi-queue reconnection known issue

On 7/28/2020 2:33 AM, Xuan Ding wrote: > This patch added known issue for vhost multi-queue reconnection > with virtio-net/virtio-pmd. > > Signed-off-by: Xuan Ding > --- > doc/guides/rel_notes/known_issues.rst | 21 + > 1 file changed, 21 insertions(+) > > diff --git a/doc/g

Re: [dpdk-dev] [PATCH v4 16/22] net/bnxt: fix table reference count for shadow tcam

On 7/28/2020 6:33 PM, Ajit Khaparde wrote: > > > On Tue, Jul 28, 2020 at 10:00 AM Ferruh Yigit > wrote: > > On 7/28/2020 7:34 AM, Ajit Khaparde wrote: > > From: Mike Baucom > > > > > Moved setting the refcnt

[dpdk-dev] Fwd: Request for High Priority Features

-- Forwarded message - From: Owen Hilyard Date: Tue, Jul 28, 2020 at 8:04 AM Subject: Request for High Priority Features To: Hello Everyone, Those of us at the IOL have been working on new DTS test cases for a while now, and we are starting to get to the point where we've compl

Re: [dpdk-dev] [PATCH v1 1/3] eal: add API for bus close

On Tue, 28 Jul 2020 22:12:50 +0530 rohit@nxp.com wrote: > From: Rohit Raj > > As per the current code we have API for bus probe, but the > bus close API is missing. This breaks the multi process > scenarios as objects are not cleaned while terminating the > secondary processes. > > This pat

Re: [dpdk-dev] [20.08 PATCH] license: removing the dual prefix to avoid confusion

On Tue, 28 Jul 2020 11:28:40 +0530 Hemant Agrawal wrote: > This patch removes the dual keyword from dual license > definitions to avoid confusion. As the *dual* word is > not required to be added SPDX license. > > Signed-off-by: Hemant Agrawal > --- > license/exceptions.txt | 4 ++-- > 1 file

[dpdk-dev] [PATCH v2 1/1] net: fix TSO packets checksum incorrect

The ol_flags check lacks of flag for IPv6 which causes checksum flag configuration error while IPv6/TCP TSO packet is sent. This patch fixes the issue by adding PKT_TX_TCP_SEG flag. Fixes: 520059a41aa9 ("net: check fragmented headers in non-debug as well") Signed-off-by: Yuying Zhang --- lib/li

Re: [dpdk-dev] [PATCH v12 00/10] Improve mlx5 PMD driver framework for multiple classes

27/07/2020 19:47, Parav Pandit: > This series introduces mlx5 common driver layer to support multiple > class of devices for a single PCI device. Applied, thanks

Re: [dpdk-dev] DPDK PDUMP Issue

On Tue, 28 Jul 2020 16:41:38 + Dikshant Chitkara wrote: > Hi Stephen, > Our system has 2 sockets as seen from below : > > [root@flexran3 dchitkara]# lscpu > Architecture: x86_64 > CPU op-mode(s):32-bit, 64-bit > Byte Order:Little Endian > CPU(s):8

Re: [dpdk-dev] [PATCH v4 16/22] net/bnxt: fix table reference count for shadow tcam

On 7/28/2020 7:34 AM, Ajit Khaparde wrote: > From: Mike Baucom > > Moved setting the refcnt for shadow tcam and table entries to the > allocation path only. The insert can be called multiple times for > updates and was resetting the refcnt to 1 each time. Now multiple > insertion/modifications

[dpdk-dev] [PATCH v2 2/3] net/vhost: fix queue update

Now that the vhost library saves the guest notifications enablement value in its virtqueues metadata, it is not necessary to do it in the vring_state_changed callback. One effect of the patch is also to prevent possible deadlock happening in vhost library. Fixes: 604052ae5395 ("net/vhost: support

[dpdk-dev] [PATCH v2 1/3] vhost: fix guest notification setting

If rte_vhost_enable_guest_notification is called before the virtqueue is ready, the configuration is lost. This patch fixes this by saving the guest notification enablement value requested by the application, and apply it before the virtqueue is made ready to the application. Fixes: 604052ae5395

[dpdk-dev] [PATCH v2 3/3] net/vhost: fix interrupt mode

At .new_device() time, only the first vring pair is now ready, other vrings are consfigured later. Problem is that when application will setup and enable interrupts, only the first queue pair Rx interrupt will be enabled. This patches fixes the issue by setting the number of max interrupts to the

[dpdk-dev] [PATCH v2 0/3] Fix Vhost regressions

This series aims at fixing the regressions reported by Intel QE. I managed to reproduce the issues, and this series fixes them. The two first patches fix the performance regression. They have been tested by intel QE which confirms the fix. The third patch fixes the interrupt regression. I tested

[dpdk-dev] [PATCH v1 3/3] bus/fslmc: support bus close API

From: Rohit Raj This patch add support for closing the bus objects which were acquired In the bus probe. Some devices need to be cleaned while in both primary and secondary process and while some need to be cleaned only in case of primary process. The devices are closed as per the white list us

[dpdk-dev] [PATCH v1 1/3] eal: add API for bus close

From: Rohit Raj As per the current code we have API for bus probe, but the bus close API is missing. This breaks the multi process scenarios as objects are not cleaned while terminating the secondary processes. This patch adds a new API rte_bus_close() for cleanup of bus objects which were acqui

[dpdk-dev] [PATCH v1 2/3] examples/multi_process: cleanup bus objects while terminating app

From: Rohit Raj Certain bus objects may need to be closed and re-acquired while terminating and rerunning the client application. Hence a signal handler is required to catch the termination of the App and hence closing the bus objects. This patch adds the missing signal handler in the client app

[dpdk-dev] [PATCH v1] bus/fslmc: fix dpio close

From: Rohit Raj The current state of the DPIO object should be checked before trying to close/disable the object. Fixes: 293c0ca94c36 ("bus/fslmc: support memory backed portals with QBMAN 5.0") Cc: sta...@dpdk.org Signed-off-by: Rohit Raj --- drivers/bus/fslmc/portal/dpaa2_hw_dpio.c | 9 +

Re: [dpdk-dev] [PATCH] app/testpmd: fix txonly mode timestamp intitialization

> -Original Message- > From: dev On Behalf Of Viacheslav Ovsiienko > Sent: Monday, July 27, 2020 11:27 PM > To: dev@dpdk.org > Cc: ma...@mellanox.com; rasl...@mellanox.com; tho...@monjalon.net; > ferruh.yi...@intel.com > Subject: [dpdk-dev] [PATCH] app/testpmd: fix txonly mode timestamp >

Re: [dpdk-dev] DPDK PDUMP Issue

On Tue, 28 Jul 2020 14:51:58 + Dikshant Chitkara wrote: > Hi Team, > > With fix suggest in prev mail thread at testpmd side, PDUMP works with > testpmd. > > However when we try to run our own primary app with PDUMP as a secondary > process, PDUMP console comes up, however it does not capt

Re: [dpdk-dev] [dpdk-users] Difference in make exec-env: linuxapp and linux

Ok, thanks for the clarification. On Tue, Jul 28, 2020 at 3:31 PM Bruce Richardson wrote: > On Tue, Jul 28, 2020 at 03:23:48PM +0500, Ibtisam Tariq wrote: > > Hello. > > > > We have several targets in dpdk/config when compiling using MAKE. The > > dpdk target format is ARCH-MACHINE-EXECENV-TOOLC

Re: [dpdk-dev] [PATCH v10 01/10] eal: introduce macro for bit definition

28/07/2020 17:39, Honnappa Nagarahalli: > > On 28/07/20 10:24 +0200, Morten Brørup wrote: > > > > From: Honnappa Nagarahalli [mailto:honnappa.nagaraha...@arm.com] > > > > > > > --- a/lib/librte_eal/include/rte_bitops.h > > > > > > > +++ b/lib/librte_eal/include/rte_bitops.h > > > > > > > @@ -17,6 +

Re: [dpdk-dev] [PATCH v2] vdpa/ifc: fix vring update after device config

On 7/28/20 4:32 PM, Chenbo Xia wrote: > The device ready state in vhost lib is now defined as the state > that first queue pair is ready. And kick/callfd may be updated > by QEMU when ifc device is configured. > > Although now ifc driver only supports one queue pair, it still > has to update ca

Re: [dpdk-dev] [v3] vdpa/mlx5: fix event queue number query

On 7/28/20 2:32 PM, Xueming Li wrote: > Vdpa example failed on vq setup, the api to get event queue of specified > core failed. > > Internal api devx_query_eqn expects index of event queue vectors, no > need to use cpu id. As the doorbell handling thread is per device, it's > sufficient to use

Re: [dpdk-dev] [PATCH] net/virtio-user: fix virtio net status management

On 7/28/20 8:52 AM, Xiao Wang wrote: > Apart from the virtio status, there should be also a network related > status for link status management, current implementation mixes up these > two statuses. > > One issue caused by this mixup is when virtio-user running in server mode > and vhost as a c

Re: [dpdk-dev] [PATCH] doc: vhost multi-queue reconnection known issue

On 7/28/20 3:33 AM, Xuan Ding wrote: > This patch added known issue for vhost multi-queue reconnection > with virtio-net/virtio-pmd. > > Signed-off-by: Xuan Ding > --- > doc/guides/rel_notes/known_issues.rst | 21 + > 1 file changed, 21 insertions(+) Applied to dpdk-next-

Re: [dpdk-dev] [PATCH] vdpa/mlx5: fix completion queue initialization

On 7/27/20 4:29 PM, Xueming Li wrote: > Vdpa device failed to initialize 2nd VQ during setup. From FW syndrome, > unsupported CQE size was specified in CQ initialization attributes. > > The unsupported CQE size comes from uninitialized stack struct data, and > the struct has new fields defined

Re: [dpdk-dev] [PATCH] vdpa/mlx5: fix notification timing

On 7/27/20 4:00 PM, Matan Azrad wrote: > The issue is relevant only for the timer event modes: 0 and 1. > > When the HW finishes to consume a burst of the guest Rx descriptors, > it creates a CQE in the CQ. > When traffic stops, the mlx5 driver arms the CQ to get a notification > when a specifi

Re: [dpdk-dev] [PATCH] vdpa/mlx5: fix steering update in virtq unset

On 7/27/20 10:07 AM, Matan Azrad wrote: > When a virtq is destroyed by the driver, it must be removed from the > steering RQT which holds its reference. > > The driver didn't remove the virtq from RQT before destroying it what > caused HW syndrome in virtq unset. > > Remove the virtq from RQT

Re: [dpdk-dev] [PATCH] doc: add NIC supported by MLX5 vDPA driver

On 7/25/20 5:03 AM, Sergey Madaminov wrote: > Update the docs, adding MCX621102AN-ADAT to the list of NICs supported > by MLX5 vDPA driver. > > Signed-off-by: Sergey Madaminov > Suggested-by: William Tu > --- > doc/guides/vdpadevs/mlx5.rst | 1 + > 1 file changed, 1 insertion(+) Applied to

Re: [dpdk-dev] [PATCH v10 01/10] eal: introduce macro for bit definition

> > On 28/07/20 10:24 +0200, Morten Brørup wrote: > > + Ray and Neil as ABI Policy maintainers. > > > > > From: Honnappa Nagarahalli [mailto:honnappa.nagaraha...@arm.com] > > > Sent: Tuesday, July 28, 2020 4:19 AM > > > > > > > > > > > > > > > > > Subject: [dpdk-dev] [PATCH v10 01/10] eal: intr

Re: [dpdk-dev] [PATCH] vdpa/mlx5: fix live migration termination

On 7/24/20 2:07 PM, Matan Azrad wrote: > There are a lot of per virtq operations in the live migration > handling. > > Before the driver support for queue update, when a virtq was not valid, > all the LM handling was terminated. > > But now, when the driver supports queue update, the virtq can

Re: [dpdk-dev] [RFC v2 0/3] add rx buffer size for rte_eth_rxq_info

You're right pinging for reviews. That's the right time to look at next features for those who have completed their 20.08 tasks. Feel free to review other pending patches in the meantime. Some of the next features are classified as "Deferred" in patchwork: https://patches.dpdk.org/project/

Re: [dpdk-dev] [PATCH v1] vhost: fix async callback return type define

On 7/23/20 7:39 AM, patrick...@intel.com wrote: > From: Patrick Fu > > The async copy device callbacks are used by async APIs to transfer data > and check completion status. Async APIs return the number of packets > successfully processed to the caller applications and no error (negative) > va

Re: [dpdk-dev] [PATCH v2 0/2] update docs for vhost async APIs

On 7/22/20 5:01 PM, patrick...@intel.com wrote: > From: Patrick Fu > > update docs for vhost async APIs > > v2: > - fix typos in vhost_lib.rst > - minor rewording in vhost_lib.rst > - add more detailed API notes in release notes > - rebase the patch to 20.08 rc2 > > > Patrick Fu (2): >

Re: [dpdk-dev] [PATCH] vdpa/mlx5: fix the compatibility with MISC4

On 7/21/20 10:13 AM, Bing Zhao wrote: > When dynamic flex parser feature is introduced, the support for misc > parameters 4 of flow table entry (FTE) match set is needed. The > structure of "mlx5_ifc_fte_match_param_bits" is extended with > "mlx5_ifc_fte_match_set_misc4_bits" at the end of it. T

[dpdk-dev] [PATCH v3] doc: add deprecation notice for sched changes

Add deprecation note for making changes in data structures and APIs in order to allow dynamic configuration of subport bandwidth profile. These changes are aligned as suggested in the RFC[1]. https://mails.dpdk.org/archives/dev/2020-July/175161.html Signed-off-by: Savinay Dharmappa Acked-by: Jas

Re: [dpdk-dev] [PATCH v2] vdpa/ifc: fix vring update after device config

On 7/28/20 4:32 PM, Chenbo Xia wrote: > The device ready state in vhost lib is now defined as the state > that first queue pair is ready. And kick/callfd may be updated > by QEMU when ifc device is configured. > > Although now ifc driver only supports one queue pair, it still > has to update ca

Re: [dpdk-dev] [v3] vdpa/mlx5: fix event queue number query

On 7/28/20 2:32 PM, Xueming Li wrote: > Vdpa example failed on vq setup, the api to get event queue of specified > core failed. > > Internal api devx_query_eqn expects index of event queue vectors, no > need to use cpu id. As the doorbell handling thread is per device, it's > sufficient to use

Re: [dpdk-dev] [PATCH] net/virtio-user: fix virtio net status management

On 7/28/20 8:52 AM, Xiao Wang wrote: > Apart from the virtio status, there should be also a network related > status for link status management, current implementation mixes up these > two statuses. > > One issue caused by this mixup is when virtio-user running in server mode > and vhost as a c

Re: [dpdk-dev] [PATCH v4] vhost: fix async copy fail on multi-page buffers

On 7/28/20 5:28 AM, patrick...@intel.com wrote: > From: Patrick Fu > > Async copy fails when single ring buffer vector is splited on multiple > physical pages. This happens because current hpa address translation > function doesn't handle multi-page buffers. A new gpa to hpa address > conversi

[dpdk-dev] [PATCH v1] net/ice: fix TCP checksum offload failure

The L4LEN field of the Descriptor Header Offset for TCP should be the real length including the TCP options. Fixes: 17c7d0f9d6a4 ("net/ice: support basic Rx/Tx") Cc: sta...@dpdk.org Signed-off-by: Haiyue Wang --- drivers/net/ice/ice_rxtx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

Re: [dpdk-dev] [PATCH] mbuf: replace c memcpy() code semantics with optimized rte_memcpy()

Hi Sarosh, On Tue, Jul 28, 2020 at 06:30:46PM +0500, Sarosh Arif wrote: > Hello, > The following things made me think that rte_memcpy() is more optimized > than memcpy(): > 1. dpdk documentation recommends to use rte_memcpy() instead of memcpy(): > https://doc.dpdk.org/guides/prog_guide/writin

  1   2   >