Re: [dpdk-dev] [PATCH] vdpa/mlx5: use master core Id for vhost thread

On Tue, Jul 28, 2020 at 8:11 AM Xueming Li wrote: > > With latest rte api, vdpa example failed on vq setup, the api to get > event queue of specified core failed. > > The api to get event queue needs core id as input, but after > commit 67ae5936c4fc36 ("eal: fix lcore accessors for non-EAL threads

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

Re: [dpdk-dev] [PATCH] vdpa/mlx5: use master core Id for vhost thread

From: David Marchand > On Tue, Jul 28, 2020 at 8:11 AM Xueming Li > wrote: > > > > With latest rte api, vdpa example failed on vq setup, the api to get > > event queue of specified core failed. > > > > The api to get event queue needs core id as input, but after commit > > 67ae5936c4fc36 ("eal:

Re: [dpdk-dev] [PATCH v4 4/8] app/proc-info: add more info to show_ports

Will you please also print queue mempool info + printf("\t -- mempool name: %s\n", + (queue_info.mp == NULL) ? + "NULL" : queue_info.mp->name); -Original Message- From: Stephen Hemmin

Re: [dpdk-dev] [PATCH] vdpa/mlx5: use master core Id for vhost thread

On Tue, Jul 28, 2020 at 9:20 AM Matan Azrad wrote: > > > > From: David Marchand > > On Tue, Jul 28, 2020 at 8:11 AM Xueming Li > > wrote: > > > > > > With latest rte api, vdpa example failed on vq setup, the api to get > > > event queue of specified core failed. > > > > > > The api to get event q

Re: [dpdk-dev] [PATCH] vdpa/mlx5: use master core Id for vhost thread

From: David Marchand > On Tue, Jul 28, 2020 at 9:20 AM Matan Azrad wrote: > > > > > > > > From: David Marchand > > > On Tue, Jul 28, 2020 at 8:11 AM Xueming Li > > > wrote: > > > > > > > > With latest rte api, vdpa example failed on vq setup, the api to > > > > get event queue of specified core

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

> -Original Message- > From: Wang, Xiao W > Sent: Tuesday, July 28, 2020 2:52 PM > To: maxime.coque...@redhat.com > Cc: dev@dpdk.org; Wang, Zhihong ; Xia, Chenbo > ; Wang, Xiao W ; > sta...@dpdk.org > Subject: [PATCH] net/virtio-user: fix virtio net status management > > Apart from the

Re: [dpdk-dev] [PATCH] vdpa/mlx5: use master core Id for vhost thread

On Tue, Jul 28, 2020 at 9:30 AM Matan Azrad wrote: > > > > rte_lcore_to_cpu_id(-1) is supposed to return the current lcore id. > > > > As explained in the commitlog of 67ae5936c4fc36, for a non-EAL > > > > thread (which has no associated lcore by default) calling this > > > > function means lcore_

Re: [dpdk-dev] [PATCH] vdpa/mlx5: use master core Id for vhost thread

> -Original Message- > From: David Marchand > Sent: Tuesday, July 28, 2020 3:53 PM > To: Matan Azrad > Cc: Xueming(Steven) Li ; dev ; Asaf > Penso > Subject: Re: [dpdk-dev] [PATCH] vdpa/mlx5: use master core Id for vhost > thread > > On Tue, Jul 28, 2020 at 9:30 AM Matan Azrad wrote:

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

+ 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: introduce macro for > bit > > > definition > > > > > > > > There are several drivers wh

Re: [dpdk-dev] [PATCH] vdpa/mlx5: use master core Id for vhost thread

>From internal discussion, we found a misuse of the vector parameter in >devx_query_eqn Function, no cpu id is required, I'll come up with another version. > -Original Message- > From: dev On Behalf Of Xueming Li > Sent: Tuesday, July 28, 2020 2:11 PM > Cc: dev@dpdk.org; Asaf Penso > Su

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

Hi, > -Original Message- > From: Xia, Chenbo > Sent: Tuesday, July 28, 2020 10:32 PM > To: dev@dpdk.org > Cc: maxime.coque...@redhat.com; Yigit, Ferruh ; > Wang, Xiao W ; Xu, Rosen > Subject: [PATCH v2] vdpa/ifc: fix vring update after device config > > The device ready state in vhost l

Re: [dpdk-dev] [PATCH] vdpa/mlx5: use master core Id for vhost thread

Hi David We found that our kernel driver doesn't really need it and we didn't understand the internal API correctly. We will create v2 as fix to the vdpa code. Thank you for the review! Matan From: Xueming(Steven) Li: > > -Original Message- > > From: David Marchand > > Sent: Tuesday

Re: [dpdk-dev] [PATCH] vdpa/mlx5: use master core Id for vhost thread

On Tue, Jul 28, 2020 at 10:27 AM Matan Azrad wrote: > We found that our kernel driver doesn't really need it and we didn't > understand > the internal API correctly. > > We will create v2 as fix to the vdpa code. Ok cool. > > Thank you for the review! No problem, I was scared of a regression

[dpdk-dev] [PATCH v5] net/ice: fix GTPU down/uplink and extension conflict

When adding a RSS rule with GTPU_DWN/UP, it will write from top to bottom for profile due to firmware limitation. If a RSS rule with GTPU_EH already exists, then GTPU_DWN/UP packet will match GTPU_EH profile. This patch solves this issue by remembering a gtpu_eh RSS configure and removing it before

Re: [dpdk-dev] [PATCH] kni: fix kernel deadlock when using mlx devices

Hi, Didn't see this patch previously, but we came up with the same idea internally and also faced a hang during the application shutdown. We didn't dig deep, but it occurred in kni_release function. Igor On Mon, Jul 27, 2020 at 8:53 PM Stephen Hemminger < step...@networkplumber.org> wrote: > On

[dpdk-dev] [PATCH v1] net: fix TSO packet checksum incorrect

The ol_flags check lacks of PKT_TX_IPV6 which causes checksum flag configuration error while IPv6/TCP TSO packet is sent. This patch fixes the issue using PKT_TX_OFFLOAD_MASK. Fixes: 520059a41aa9 ("net: check fragmented headers in non-debug as well") Signed-off-by: Yuying Zhang --- lib/librte_n

Re: [dpdk-dev] [PATCH v2 1/2] doc: update guides for vhost async APIs

On 7/22/20 5:01 PM, patrick...@intel.com wrote: > From: Patrick Fu > > Update vhost guides to document vhost async APIs > > Signed-off-by: Patrick Fu > --- > doc/guides/prog_guide/vhost_lib.rst | 86 ++--- > 1 file changed, 77 insertions(+), 9 deletions(-) > Review

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

Hi, > -Original Message- > From: Xia, Chenbo > Sent: Tuesday, July 28, 2020 22:32 > To: dev@dpdk.org > Cc: maxime.coque...@redhat.com; Yigit, Ferruh ; > Wang, Xiao W ; Xu, Rosen > Subject: [PATCH v2] vdpa/ifc: fix vring update after device config > > The device ready state in vhost lib

Re: [dpdk-dev] [PATCH v2 2/2] doc: update release notes for vhost async APIs

On 7/22/20 5:01 PM, patrick...@intel.com wrote: > From: Patrick Fu > > Update 20.08 release notes to include vhost async APIs > > Signed-off-by: Patrick Fu > --- > doc/guides/rel_notes/release_20_08.rst | 6 ++ > 1 file changed, 6 insertions(+) > > diff --git a/doc/guides/rel_notes/rel

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] ethdev: fix RSS flow expansion in case of mismatch

Hi, PSB. > -Original Message- > From: Ori Kam > Sent: Monday, July 27, 2020 7:21 PM > To: Dekel Peled ; Raslan Darawsheh > ; Thomas Monjalon ; > ferruh.yi...@intel.com; Andrew Rybchenko > Cc: dev@dpdk.org; sta...@dpdk.org; Matan Azrad ; > Slava Ovsiienko > Subject: RE: [PATCH] ethdev: f

Re: [dpdk-dev] [PATCH v3 00/22] bnxt patches

On Mon, Jul 27, 2020 at 3:42 AM Ferruh Yigit wrote: > On 7/24/2020 5:48 PM, Ajit Khaparde wrote: > > > > > > On Thu, Jul 23, 2020 at 10:32 PM Ajit Khaparde < > ajit.khapa...@broadcom.com > > > wrote: > > > > Some fixes, cleanups and changes to augment pre-ex

[dpdk-dev] [v2] vdpa/mlx5: fix event queue number query

With latest rte api, vdpa example failed on vq setup, the api to get event queue of specified core failed. After commit 67ae5936c4fc36 ("eal: fix lcore accessors for non-EAL threads"), code of "vhost-event" thread to get current cpu id returns -1. On the other hand, internal api devx_query_eqn ex

Re: [dpdk-dev] [PATCH v3 09/22] net/bnxt: ignore VLAN priority mask

On Mon, Jul 27, 2020 at 3:30 AM Ferruh Yigit wrote: > On 7/24/2020 6:32 AM, Ajit Khaparde wrote: > > From: Kishore Padmanabha > > > > This is a work around for the OVS setting offload rules that > > are passing vlan priority mask as wild card and currently we > > do not support it. > > > > Signe

[dpdk-dev] [dpdk-dev v1] net/ice: fix gtpu teid hash

Refine gtpu teid hash rule mapping for GTPU_IP/GTPU_EH/GTPU_DWN/GTPU_UP. Fixes: 37e444b77814 ("net/ice: support hash for GTPU protocols") Signed-off-by: Jeff Guo --- drivers/net/ice/ice_hash.c | 24 +++- 1 file changed, 15 insertions(+), 9 deletions(-) diff --git a/drivers/

[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. v2: Removed config option to always enable log. Added new log type

[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_pmd.c:633:22: e

[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 PMD optimized fo

[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 | 2 +- 2 file

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] [PATCH v1] net: fix TSO packet checksum incorrect

Hi, On Tue, Jul 28, 2020 at 08:55:31AM +, Yuying Zhang wrote: > The ol_flags check lacks of PKT_TX_IPV6 which causes checksum > flag configuration error while IPv6/TCP TSO packet is sent. > This patch fixes the issue using PKT_TX_OFFLOAD_MASK. > > Fixes: 520059a41aa9 ("net: check fragmented h

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: introduce macro for > > b

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

On 7/28/2020 7:29 AM, Chengchang Tang wrote: > Friendly ping Hi Tang, Sorry for not making it clear, since it is a library change, the change is already late for this release (20.08), and it will be considered for next release. As current release out, we can continue the discussions. > > On 202

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(+) > > diff --

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] DPDK hugepage memory fragmentation

On 27-Jul-20 4:30 PM, Kamaraj P wrote: Hi Anatoly, Since we do not have the driver support of SRIOv with VFIO, we are using IGB_UIO . I believe it's coming :) Basically our application is crashing due to the buffer allocation failure. I believe because it didn't get a contiguous memory locat

Re: [dpdk-dev] [PATCH 20.11] usertools/dpdk-devbind: hide "if" value for non-network devs

On 27-Jul-20 2:44 PM, Bruce Richardson wrote: The "if", or interface, field in the status display of dpdk-devbind is only relevant for network interfaces, so don't display it for other device types. Signed-off-by: Bruce Richardson --- We should probably get away from using legacy string forma

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

Hi Maxime, > -Original Message- > From: Maxime Coquelin > Sent: Tuesday, July 28, 2020 5:10 PM > To: Fu, Patrick ; dev@dpdk.org; Xia, Chenbo > > Subject: Re: [PATCH v1] vhost: fix async callback return type define > > > > On 7/23/20 7:39 AM, patrick...@intel.com wrote: > > From: Patri

Re: [dpdk-dev] [dpdk-stable] [PATCH] doc: fix references to /dev/huge

On 05-Jul-20 9:44 PM, Thomas Monjalon wrote: 23/06/2020 07:55, Sarosh Arif: change /dev/huge to /dev/hugepages Bugzilla ID: 492 Signed-off-by: Sarosh Arif Please could you explain why /dev/hugepages must be used, in the commit log for the record? FYI, a similar change was done in the websit

Re: [dpdk-dev] [PATCH] common/mlx5: fix CPU detection for PCI relaxed ordering

24/07/2020 17:43, Matan Azrad: > Hi Thomas > > From: Thomas Monjalon: > > 19/07/2020 13:41, Matan Azrad: > > > > > > From: Thomas Monjalon: > > > > 19/07/2020 12:56, Matan Azrad: > > > > > > > > > > From: Thomas Monjalon > > > > > > The detection of the CPU was done in a constructor and shared in

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

Hello. We have several targets in dpdk/config when compiling using MAKE. The dpdk target format is ARCH-MACHINE-EXECENV-TOOLCHAIN where EXECENV can be linux, linuxapp, freebsd and bsdapp. What is the difference between linuxapp and linux? It seems the same because they both have the same .config

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

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. > > Fixes: 349950ddb9c5 ("metrics: add information metrics library")

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

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-TOOLCHAIN where EXECENV can > be linux, linuxapp, freebsd and bsdapp. What is the difference between > linu

[dpdk-dev] [PATCH v4 01/22] net/bnxt: add shadow and search capability to tcam

From: Mike Baucom - Add TCAM shadow tables for searching - Add Search API to allow reuse of TCAM entries Signed-off-by: Mike Baucom Reviewed-by: Randy Schacher Reviewed-by: Ajit Khaparde --- drivers/net/bnxt/tf_core/tf_core.c| 73 ++ drivers/net/bnxt/tf_core/tf_core.h| 101 +

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

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. - Updated commit messages. - Added a patch to fix a logic error [21/22]. -

[dpdk-dev] [PATCH v4 02/22] net/bnxt: add access to nat global register

From: Kishore Padmanabha Add support to enable or disable the NAT global registers. The NAT feature is enabled in hardware during initialization and disabled at deinitialization of the application. Signed-off-by: Kishore Padmanabha Reviewed-by: Michael Baucom Reviewed-by: Ajit Khaparde --- d

[dpdk-dev] [PATCH v4 05/22] net/bnxt: add TruFlow hash API

From: Mike Baucom Added TruFlow hash API for common hash uses across TruFlow core functions. Signed-off-by: Mike Baucom Reviewed-by: Farah Smith Reviewed-by: Kishore Padmanabha --- doc/guides/rel_notes/release_20_08.rst | 1 + drivers/net/bnxt/meson.build | 1 + drivers/net/bnx

[dpdk-dev] [PATCH v4 04/22] net/bnxt: modify ulp mapper to use tcam search

From: Mike Baucom modified ulp mappper to use the new tf_search_tcam_entry API. When search before allocation is requested, mapper calls tc_search_tcam_entry with the alloc flag. - On HIT, the result and tcam index is returned. - On MISS, the tcam index is returned but the result is created and

[dpdk-dev] [PATCH v4 03/22] net/bnxt: configure parif for offload miss rules

From: Kishore Padmanabha PARIF is handler to a partition of the physical port. For the offload miss rules, the parif miss path needs to be considered. The higher parif are reserved for handling this. Signed-off-by: Kishore Padmanabha Reviewed-by: Michael Baucom Reviewed-by: Ajit Khaparde ---

[dpdk-dev] [PATCH v4 11/22] net/bnxt: update shadow tcam to use TruFlow hash

From: Mike Baucom Removed the hash calculation from tf_shadow_tcam in favor of using a new common implementation. Signed-off-by: Mike Baucom Reviewed-by: Kishore Padmanabha Reviewed-by: Farah Smith Reviewed-by: Ajit Khaparde --- drivers/net/bnxt/tf_core/tf_shadow_tcam.c | 77 +--

[dpdk-dev] [PATCH v4 10/22] net/bnxt: add egress template with VLAN tag match

From: Kishore Padmanabha Added egress template with VLAN tag match Signed-off-by: Kishore Padmanabha Reviewed-by: Shahaji Bhosle --- .../net/bnxt/tf_ulp/ulp_template_db_class.c | 501 +- .../net/bnxt/tf_ulp/ulp_template_db_enum.h| 28 +- 2 files changed, 509 insertions(

[dpdk-dev] [PATCH v4 06/22] net/bnxt: fix mark id update to mbuf

From: Venkat Duvvuru When a packet is looped back from VF to VFR, it is marked to identify the VFR interface. However, this mark_id shouldn't be percolated up to the OVS as it is internal to pmd. This patch fixes it by skipping mark injection into mbuf if the packet is received on VFR interface.

[dpdk-dev] [PATCH v4 09/22] net/bnxt: ignore VLAN priority mask

From: Kishore Padmanabha This is a work around for the OVS setting offload rules that are passing vlan priority mask as wild card and currently we do not support it. Signed-off-by: Kishore Padmanabha Reviewed-by: Michael Baucom --- drivers/net/bnxt/tf_ulp/ulp_rte_parser.c | 15 +++

[dpdk-dev] [PATCH v4 08/22] net/bnxt: configure parif for the egress rules

From: Kishore Padmanabha The parif for the egress rules need to be dynamically configured based on the port type. PARIF is handler to a partition of the physical port. Signed-off-by: Kishore Padmanabha Reviewed-by: Michael Baucom --- drivers/net/bnxt/tf_ulp/ulp_def_rules.c | 11 ++-- dr

[dpdk-dev] [PATCH v4 07/22] net/bnxt: fix nat template

From: Kishore Padmanabha The template is updated to support additional combinations of NAT actions. Fixes: 2951f7f31112 ("net/bnxt: support NAT action items") Signed-off-by: Kishore Padmanabha Reviewed-by: Michael Baucom Reviewed-by: Ajit Khaparde --- drivers/net/bnxt/tf_ulp/ulp_template_db

[dpdk-dev] [PATCH v4 14/22] net/bnxt: fix port default rule create and destroy

From: Venkat Duvvuru Currently, the flow_ids of port_to_app/app_to_port & tx_cfa_action for the first port are getting over-written by the second port because these fields are stored in the ulp context which is common across the ports. This patch fixes the problem by having per port structure to

Re: [dpdk-dev] [PATCH] common/mlx5: fix CPU detection for PCI relaxed ordering

Hi Thomas From: Thomas Monjalon: > 24/07/2020 17:43, Matan Azrad: > > Hi Thomas > > > > From: Thomas Monjalon: > > > 19/07/2020 13:41, Matan Azrad: > > > > > > > > From: Thomas Monjalon: > > > > > 19/07/2020 12:56, Matan Azrad: > > > > > > > > > > > > From: Thomas Monjalon > > > > > > > The detect

[dpdk-dev] [PATCH v4 12/22] net/bnxt: add shadow table capability with search

From: Mike Baucom - Added Index Table shadow tables for searching - Added Search API to allow reuse of Table entries Signed-off-by: Mike Baucom Reviewed-by: Farah Smith --- drivers/net/bnxt/tf_core/tf_core.c| 66 +- drivers/net/bnxt/tf_core/tf_core.h| 79 ++- drivers/net/bnx

[dpdk-dev] [PATCH v4 13/22] net/bnxt: modify ulp mapper to use tbl search

From: Mike Baucom modified ulp mappper to use the new tf_search_tbl_entry API. When search before allocation is requested, mapper calls tc_search_tbl_entry with the alloc flag. - On HIT, the result and table index is returned. - On MISS, the table index is returned but the result is created and

[dpdk-dev] [PATCH v4 18/22] net/bnxt: add templates for search before alloc

From: Mike Baucom Search before alloc allows reuse of constrained resources such as tcam, encap, and source modifications. The new templates will search the entry and alloc only if necessary. Signed-off-by: Mike Baucom Reviewed-by: Venkat Duvvuru Reviewed-by: Ajit Khaparde --- drivers/net/b

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

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 will not change the reference count. Fixes: 3cf8fb975d

[dpdk-dev] [PATCH v4 19/22] net/bnxt: enable shadow tables during session open

From: Mike Baucom Turn on shadow memory in the core to allow search before allocate. This allows reuse of constrained resources. Signed-off-by: Mike Baucom Reviewed-by: Venkat Duvvuru Reviewed-by: Ajit Khaparde --- drivers/net/bnxt/tf_ulp/bnxt_ulp.c | 2 +- 1 file changed, 1 insertion(+), 1

[dpdk-dev] [PATCH v4 15/22] net/bnxt: fix FW rule deletion on representor create

From: Venkat Duvvuru Truflow stack adds VFR to VF and VF to VFR conduits when VF representor is created. However, in the ingress direction the VF's fw rules conflict with Truflow rules, resulting in not hitting the Truflow VFR rules. To fix this, fw is going to remove it’s VF rules when vf repres

[dpdk-dev] [PATCH v4 17/22] net/bnxt: add tcam table processing for search and alloc

From: Kishore Padmanabha Added support for tcam table processing to enable the search and allocate support. This also includes the tcam entry update support. Signed-off-by: Kishore Padmanabha Reviewed-by: Michael Baucom --- drivers/net/bnxt/tf_ulp/ulp_mapper.c | 317 -

[dpdk-dev] [PATCH v4 22/22] net/bnxt: fix build error with extra cflags

When we compile PMD with CFLAGS set to -O -g, build fails because of uninitialized error. This patch fixes it. Fixes: 1e46b3962620 ("net/bnxt: fill cfa action in Tx descriptor") Bugzilla ID: 509 Cc: step...@networkplumber.org Signed-off-by: Ajit Khaparde Reviewed-by: Somnath Kotur Reviewed-by:

[dpdk-dev] [PATCH v4 20/22] net/bnxt: cleanup VF-representor dev ops

From: Somnath Kotur No need to access rx_cfa_code, cfa_code_map from the VF-Rep functions anymore. Fixes: 322bd6e70272 ("net/bnxt: add port representor infrastructure") Reviewed-by: Venkat Duvvuru Signed-off-by: Somnath Kotur Reviewed-by: Ajit Khaparde --- doc/guides/nics/bnxt.rst | 46

[dpdk-dev] [PATCH v4 21/22] net/bnxt: fix if condition

The if condition in bnxt_restore_mac_filters needs to check for the result of logical AND. But it was not doing it resulting in an incorrect check. Fixes: b02f1573cd07 ("net/bnxt: restore MAC filters during reset recovery") Signed-off-by: Ajit Khaparde --- drivers/net/bnxt/bnxt_ethdev.c | 2 +-

Re: [dpdk-dev] [PATCH v2 0/4] some bugs fixes

On 7/25/2020 9:15 AM, Xiaoyun wang wrote: > These patches modify csum offload process, optimize Rx > performance for x86, set vhd type with 2 for no offset > in ovs offload scenario, make timeout not affected by > system time jump. > > -- > v1->v2: > - fix typo spelling > > v1: > - modify c

Re: [dpdk-dev] [PATCH] net/tap: avoid using SIGIO

> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Stephen Hemminger > Sent: Monday, July 27, 2020 9:44 PM > > On Mon, 27 Jul 2020 15:19:32 +0200 > Morten Brørup wrote: > > > > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Stephen > Hemminger > > > Sent: Wednesday, July 15, 2020 1:58

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

When adding a RSS rule with GTPU_DWN/UP, it will write from top to bottom for profile due to firmware limitation. If a RSS rule with GTPU_EH already exists, then GTPU_DWN/UP packet will match GTPU_EH profile. This patch solves this issue by remembering a gtpu_eh RSS configure and removing it before

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

Thanks a lot. BR. Bing > -Original Message- > From: Maxime Coquelin > Sent: Tuesday, July 28, 2020 3:15 PM > To: Bing Zhao ; Slava Ovsiienko > ; Matan Azrad > Cc: dev@dpdk.org > Subject: Re: [dpdk-dev] [PATCH] vdpa/mlx5: fix the compatibility with > MISC4 > > > > On 7/21/20 10:13 AM,

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

> From: Gaëtan Rivet [mailto:gr...@u256.net] > Sent: Tuesday, July 28, 2020 11:29 AM > > 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

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

Hi Ferruh, Thank you for your reply. I'm sorry to bother you while you are busy with the release. I know this change may only be accepted in the next release. I'd like to know what the community thinks about it. If there is no objection, I will send the patch after current release out. On 2020/7/

[dpdk-dev] [PATCH v1] net/mlx4: return EAGAIN on premature disable interrupt calls

RXQ interrupts under Linux are based on the epoll mechanism. An expected order of operations is as follows: 1. Call rte_eth_dev_rx_intr_enable(), to arm the CQ for receiving events on data input. 2. Block on rte_epoll_wait() with an array of file descriptors representing the CQ events. Upon data ar

Re: [dpdk-dev] [v2] vdpa/mlx5: fix event queue number query

On Tue, Jul 28, 2020 at 11:23 AM Xueming Li wrote: > > With latest rte api, vdpa example failed on vq setup, the api to get > event queue of specified core failed. > > After > commit 67ae5936c4fc36 ("eal: fix lcore accessors for non-EAL threads"), > code of "vhost-event" thread to get current cpu

Re: [dpdk-dev] [v2] vdpa/mlx5: fix event queue number query

> -Original Message- > From: David Marchand > Sent: Tuesday, July 28, 2020 8:05 PM > To: Xueming(Steven) Li > Cc: dev ; a...@dpdk.org; Maxime Coquelin > > Subject: Re: [dpdk-dev] [v2] vdpa/mlx5: fix event queue number query > > On Tue, Jul 28, 2020 at 11:23 AM Xueming Li wrote: > > >

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

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 default event queue. This patch uses the default id(

[dpdk-dev] [PATCH] net/hinic: fix return value of null not checked

From: Yunjian Wang The function rte_zmalloc() could return NULL, the return value need to be checked. Fixes: f4ca3fd54c4d ("net/hinic: create and destroy flow director filter") Cc: sta...@dpdk.org Signed-off-by: Yunjian Wang --- drivers/net/hinic/hinic_pmd_flow.c | 12 1 file cha

Re: [dpdk-dev] [PATCH v1] net/mlx4: return EAGAIN on premature disable interrupt calls

Hi, > -Original Message- > From: Ophir Munk > Sent: Tuesday, July 28, 2020 2:54 PM > To: dev@dpdk.org > Cc: Raslan Darawsheh ; Ophir Munk > ; Matan Azrad > Subject: [PATCH v1] net/mlx4: return EAGAIN on premature disable interrupt > calls > > RXQ interrupts under Linux are based on the

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

From: Yunjian Wang This series include two fixes patches for ice driver. Yunjian Wang (2): net/ice: fix memory leak when releasing vsi net/ice: fix return value of null not checked drivers/net/ice/ice_ethdev.c | 37 +++- 1 file changed, 28 insertions(+), 9 d

[dpdk-dev] [PATCH 1/2] net/ice: fix memory leak when releasing vsi

From: Yunjian Wang At the end of the vsi release, we should free the 'rss_lut' and 'rss_key' for the vsi. Fixes: 50370662b727 ("net/ice: support device and queue ops") Cc: sta...@dpdk.org Signed-off-by: Yunjian Wang --- drivers/net/ice/ice_ethdev.c | 10 ++ 1 file changed, 6 insertion

[dpdk-dev] [PATCH 2/2] net/ice: fix return value of null not checked

From: Yunjian Wang The function rte_zmalloc() could return NULL, the return value need to be checked. Fixes: 50370662b727 ("net/ice: support device and queue ops") Cc: sta...@dpdk.org Signed-off-by: Yunjian Wang --- drivers/net/ice/ice_ethdev.c | 27 ++- 1 file changed

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

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/writing_efficient_code.html 2. Here some benchmarks are available: https://software.

Re: [dpdk-dev] [dpdk-stable] [PATCH] net/hinic: fix return value of null not checked

On 7/28/2020 1:34 PM, wangyunjian wrote: > From: Yunjian Wang > > The function rte_zmalloc() could return NULL, the return > value need to be checked. > > Fixes: f4ca3fd54c4d ("net/hinic: create and destroy flow director filter") > Cc: sta...@dpdk.org > > Signed-off-by: Yunjian Wang Reviewed-

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 v3 1/8] net/dpaa: add support for fmlib in dpdk

Hello Hemant, On Mon, Jul 20, 2020 at 6:50 AM Hemant Agrawal wrote: > >Why dropping this codebase in DPDK instead of pulling it as a dependency? > [Hemant] >I don't like seeing DPDK becoming a pile of code duplicated from > somewhere else. > [Hemant] We are not using the library as it is and mak

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] 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(+) > > diff --git a/doc/

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

[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 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

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] [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 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

[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] 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

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 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] [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/

  1   2   >