[dpdk-dev] [PATCH] vhost_user: remove statement for non-existed function

vhost_user_host_notifier_ctrl is not existed anymore, its statement in header file should be removed accordingly. Fixes: 43f34e35663f ("vhost: provide helper for host notifier ctrl") Cc: xiao.w.w...@intel.com Cc: sta...@dpdk.org Signed-off-by: Xiaolong Ye --- lib/librte_vhost/vhost_user.h | 1 -

Re: [dpdk-dev] [PATCH v4 1/2] mbuf: add function returning default buffer address

On Thu, Jan 10, 2019 at 02:40:29PM -0800, Yongseok Koh wrote: > This patch introduces two new functions - rte_mbuf_buf_addr() and > rte_mbuf_data_addr_default(). > > rte_mbuf_buf_addr() reutrns the default buffer address of given mbuf which > comes after mbuf structure and private data. > > rte_m

Re: [dpdk-dev] [PATCH v8 10/10] doc: update ipsec-secgw guide and relelase notes

Hi Akhil, Thanks for considering, as mentioned it is suggestion from my end how the document could have been updated. Thanks Vipin Varghese > -Original Message- > From: Akhil Goyal > Sent: Friday, January 11, 2019 12:26 PM > To: Varghese, Vipin ; Ananyev, Konstantin > ; dev@dpdk.org >

Re: [dpdk-dev] [PATCH v4 1/2] mbuf: add function returning default buffer address

On Thu, Jan 10, 2019 at 11:40 PM Yongseok Koh wrote: > This patch introduces two new functions - rte_mbuf_buf_addr() and > rte_mbuf_data_addr_default(). > > rte_mbuf_buf_addr() reutrns the default buffer address of given mbuf which > returns > comes after mbuf structure and private data. > > r

Re: [dpdk-dev] [PATCH v3 1/2] mbuf: add function returning default buffer address

On 1/10/19 9:35 PM, Yongseok Koh wrote: This patch introduces two new functions - rte_mbuf_buf_addr() and rte_mbuf_data_addr_default(). rte_mbuf_buf_addr() reutrns the default buffer address of given mbuf which comes after mbuf structure and private data. rte_mbuf_data_addr_default() returns th

Re: [dpdk-dev] [RFC] function to parse packet headers

> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Andrew Rybchenko > On 1/11/19 3:11 AM, Stephen Hemminger wrote: > > > > All drivers that don't have hardware support for getting l2/l3 and > > ptype information should be calling rte_net_get_ptype() already. > > Is it documented somewhere? >

Re: [dpdk-dev] [RFC] function to parse packet headers

On 1/11/19 11:16 AM, Morten Brørup wrote: From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Andrew Rybchenko On 1/11/19 3:11 AM, Stephen Hemminger wrote: All drivers that don't have hardware support for getting l2/l3 and ptype information should be calling rte_net_get_ptype() already. Is it

Re: [dpdk-dev] [PATCH v4 1/2] mbuf: add function returning default buffer address

On Fri, Jan 11, 2019 at 9:11 AM David Marchand wrote: > On Thu, Jan 10, 2019 at 11:40 PM Yongseok Koh wrote: > diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h > >> index bc562dc8a9..5787616999 100644 >> --- a/lib/librte_mbuf/rte_mbuf.h >> +++ b/lib/librte_mbuf/rte_mbuf.h >>

Re: [dpdk-dev] [RFC] function to parse packet headers

Hi, On Fri, Jan 11, 2019 at 10:56:11AM +0300, Andrew Rybchenko wrote: > On 1/11/19 3:11 AM, Stephen Hemminger wrote: > > On Thu, 10 Jan 2019 03:03:24 +0200 > > Rami Rosen wrote: > > > > > Hi, Morten, > > > > > > > And regarding avoiding code duplicity, I'm pursuing Olivier about > > > > mergin

Re: [dpdk-dev] [PATCH v2] mbuf: fix compile by removing struct from function

Hi, On Thu, Jan 10, 2019 at 06:40:06PM +, Dumitrescu, Cristian wrote: > > > > -Original Message- > > From: Van Haaren, Harry > > Sent: Thursday, January 10, 2019 6:07 PM > > To: dev@dpdk.org > > Cc: Van Haaren, Harry ; Pattan, Reshma > > ; Dumitrescu, Cristian > > ; tho...@monjalon.n

Re: [dpdk-dev] [Patch v3 1/2] net/virtio: check head desc with correct wrap counter

On 1/10/19 10:47 PM, Jens Freimann wrote: In virtio_pq_send_command() we check for a used descriptor and wait in an idle loop until it becomes used. We can't use vq->used_wrap_counter here to check for the first descriptor we made available because the ring could have wrapped. Let's use the us

Re: [dpdk-dev] [Patch v3 2/2] net/virtio-user: ctrl vq support for packed

On 1/10/19 10:47 PM, Jens Freimann wrote: Add support to virtio-user for control virtqueues. Signed-off-by: Jens Freimann --- .../net/virtio/virtio_user/virtio_user_dev.c | 104 -- .../net/virtio/virtio_user/virtio_user_dev.h | 15 ++- drivers/net/virtio/virtio_user_et

Re: [dpdk-dev] [PATCH v5 06/12] vhost/crypto: use separate session mempools

On 1/10/19 3:50 PM, Fan Zhang wrote: This patch uses the two session mempool approach to vhost crypto. One mempool is for session header objects, and the other is for session private data. Signed-off-by: Fan Zhang Acked-by: Fiona Trahe --- lib/librte_vhost/rte_vhost_crypto.h | 9 ++---

Re: [dpdk-dev] [PATCH v1] net/i40e: perform basic validation on the VF messages

On 01/11/2019 02:53 AM, Varghese, Vipin wrote: > Hi Kevin, > > A question, since the patch is fixing issue for 'i40e vf' should not the > sections for 'known limitations' or 'i40e PMD' be updated too? > Hi Vipin, I don't think so, but it's a question for i40e maintainer. Kevin. > Thanks > V

[dpdk-dev] [PATCH v4 0/2] net/virtio-user: add packed vq support

Patch 1 fixes a bug in virtio_pq_send_command(). When we wait for a descriptor to be marked as used we need to consider that the ring might have wrapped and use the previous wrap counter. Patch 2 reverts the patch to error out when cq is used with packed vq and add support for packed virtqueues in

[dpdk-dev] [PATCH v4 1/2] net/virtio: check head desc with correct wrap counter

In virtio_pq_send_command() we check for a used descriptor and wait in an idle loop until it becomes used. We can't use vq->used_wrap_counter here to check for the first descriptor we made available because the ring could have wrapped. Let's use the used_wrap_counter that matches the state of the h

[dpdk-dev] [PATCH v4 2/2] net/virtio-user: ctrl vq support for packed

Add support to virtio-user for control virtqueues. Signed-off-by: Jens Freimann Reviewed-by: Maxime Coquelin --- .../net/virtio/virtio_user/virtio_user_dev.c | 102 -- .../net/virtio/virtio_user/virtio_user_dev.h | 15 ++- drivers/net/virtio/virtio_user_ethdev.c | 56 +

Re: [dpdk-dev] [RFC] function to parse packet headers

> -Original Message- > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Olivier Matz > Sent: Friday, January 11, 2019 8:36 AM > To: Andrew Rybchenko > Cc: Stephen Hemminger ; Rami Rosen > ; Thomas Monjalon > ; Morten Brørup ; > dev@dpdk.org; Yigit, Ferruh > Subject: Re: [dpdk-dev

Re: [dpdk-dev] [PATCH] build: mention -march in pkg-config description

On Fri, Jan 11, 2019 at 03:58:46AM +, Gavin Hu (Arm Technology China) wrote: > > > > -Original Message- > > From: dev On Behalf Of Luca Boccassi > > Sent: Friday, January 11, 2019 1:28 AM > > To: dev@dpdk.org > > Cc: bruce.richard...@intel.com; christian.ehrha...@canonical.com; Luca

Re: [dpdk-dev] [PATCH v4 0/2] net/virtio-user: add packed vq support

On 1/11/19 10:39 AM, Jens Freimann wrote: Patch 1 fixes a bug in virtio_pq_send_command(). When we wait for a descriptor to be marked as used we need to consider that the ring might have wrapped and use the previous wrap counter. Patch 2 reverts the patch to error out when cq is used with pac

Re: [dpdk-dev] [PATCH v9 1/6] app/procinfo: add support for show port

11/01/2019 04:57, Varghese, Vipin: > Hi Thomas > > snipped > > > +#include > > > > Is the crypto include really required in this patch? > Function 'show_port' requires the include file. Removing the same results > > In function 'show_port': > /home/saesrv02/Downloads/dpdksrc/procifno/dpdk/app/p

Re: [dpdk-dev] [PATCH v4 1/2] mbuf: add function returning default buffer address

11/01/2019 09:11, David Marchand: > On Thu, Jan 10, 2019 at 11:40 PM Yongseok Koh wrote: > > + * @warning > > + * @b EXPERIMENTAL: This API may change without prior notice. > > + * This will be used by rte_mbuf_to_baddr() which has redundant code once > > + * experimental tag is removed. > > Good

Re: [dpdk-dev] [PATCH 1/6] ring: change head and tail to pointer-width size

On 10-Jan-19 9:01 PM, Gage Eads wrote: For 64-bit architectures, doubling the head and tail index widths greatly increases the time it takes for them to wrap-around (with current CPU speeds, it won't happen within the author's lifetime). This is important in avoiding the ABA problem -- in which a

Re: [dpdk-dev] [PATCH 1/6] ring: change head and tail to pointer-width size

<...> + * Copyright(c) 2016-2019 Intel Corporation */ /** @@ -88,7 +88,7 @@ rte_event_ring_enqueue_burst(struct rte_event_ring *r, const struct rte_event *events, unsigned int n, uint16_t *free_space) { - uint32_t prod_head, prod_next; + uin

Re: [dpdk-dev] [PATCH v3] build: use generic march on arm64 when using 'default' machine

On Mon, 2019-01-07 at 14:11 +, Luca Boccassi wrote: > When building for generic distribution we need a stable baseline > architecture, or depending on the build worker the result will vary. > > Force the default flags if the user explicitly sets machine=default > at configuration time. > > Fi

Re: [dpdk-dev] [PATCH 1/6] ring: change head and tail to pointer-width size

On Fri, Jan 11, 2019 at 10:40:19AM +, Burakov, Anatoly wrote: > <...> > > > + * Copyright(c) 2016-2019 Intel Corporation > >*/ > > /** > > @@ -88,7 +88,7 @@ rte_event_ring_enqueue_burst(struct rte_event_ring *r, > > const struct rte_event *events, > > unsigned int

Re: [dpdk-dev] [PATCH v3 1/2] mbuf: add function returning default buffer address

On Fri, Jan 11, 2019 at 11:14:22AM +0300, Andrew Rybchenko wrote: > On 1/10/19 9:35 PM, Yongseok Koh wrote: > > This patch introduces two new functions - rte_mbuf_buf_addr() and > > rte_mbuf_data_addr_default(). > > > > rte_mbuf_buf_addr() reutrns the default buffer address of given mbuf which > >

Re: [dpdk-dev] [PATCH] test/crypto: don't attempt unsupported SGL tests on aesni mb PMD

> -Original Message- > From: Trahe, Fiona > Sent: Friday, December 21, 2018 12:02 AM > To: dev@dpdk.org > Cc: De Lara Guarch, Pablo ; Trahe, Fiona > ; Zhang, Roy Fan ; > akhil.go...@nxp.com > Subject: [PATCH] test/crypto: don't attempt unsupported SGL tests on aesni > mb PMD > > Remove

Re: [dpdk-dev] [PATCH v4 1/2] mbuf: add function returning default buffer address

On Fri, Jan 11, 2019 at 09:32:52AM +0100, David Marchand wrote: > On Fri, Jan 11, 2019 at 9:11 AM David Marchand > wrote: > > > On Thu, Jan 10, 2019 at 11:40 PM Yongseok Koh wrote: > > diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h > > > >> index bc562dc8a9..5787616999 1006

Re: [dpdk-dev] [dpdk-stable] [PATCH 2/2] build: use dependency() instead of find_library()

On Mon, 2019-01-07 at 16:55 +, Bruce Richardson wrote: > On Mon, Jan 07, 2019 at 04:39:34PM +, Luca Boccassi wrote: > > On Mon, 2019-01-07 at 14:28 +, Bruce Richardson wrote: > > > On Thu, Jan 03, 2019 at 06:57:25PM +0100, Luca Boccassi wrote: > > > > For libbsd, which is checked in a t

Re: [dpdk-dev] [PATCH] test/crypto: don't attempt unsupported SGL tests on aesni mb PMD

> -Original Message- > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of De Lara Guarch, > Pablo > Sent: Friday, January 11, 2019 11:05 AM > To: Trahe, Fiona ; dev@dpdk.org > Cc: Zhang, Roy Fan ; akhil.go...@nxp.com > Subject: Re: [dpdk-dev] [PATCH] test/crypto: don't attempt unsuppor

Re: [dpdk-dev] [PATCH v3 1/2] mbuf: add function returning default buffer address

Olivier, David, could you take a look at naming suggested below and share your thoughts. My fear is that rte_mbuf_buf_addr() is too generic and true for direct mbuf only. That's why I'd like to highlight it in the function name. Thanks, Andrew. On 1/11/19 2:03 PM, Yongseok Koh wrote: On Fri, J

Re: [dpdk-dev] [PATCH v2] mbuf: fix compile by removing struct from function

Converging discussion, +Stephen Hemminger wrote: > I believe this was done so that the compiler doesn't generate > bad code. > > If you reference the mbuf to get the fields then each operation becomes > a load shift and mask operation to get to the bitfield. But if they > are local then this is a

Re: [dpdk-dev] [PATCH 1/6] ring: change head and tail to pointer-width size

On 11-Jan-19 10:58 AM, Bruce Richardson wrote: On Fri, Jan 11, 2019 at 10:40:19AM +, Burakov, Anatoly wrote: <...> + * Copyright(c) 2016-2019 Intel Corporation */ /** @@ -88,7 +88,7 @@ rte_event_ring_enqueue_burst(struct rte_event_ring *r, const struct rte_event *eve

[dpdk-dev] [PATCH v3] mbuf: fix compile by making sched struct visible

Although C compilation works with the struct rte_mbuf_sched declared inside the struct rte_mbuf namespace, C++ fails to compile. This fix moves the rte_mbuf_sched struct up to the global namespace, instead of declaring it inside the struct mbuf namespace. The struct rte_mbuf_sched is being used on

Re: [dpdk-dev] [PATCH v3 1/2] mbuf: add function returning default buffer address

> On Jan 11, 2019, at 3:17 AM, Andrew Rybchenko > wrote: > > Olivier, David, > > could you take a look at naming suggested below and share your thoughts. > My fear is that rte_mbuf_buf_addr() is too generic and true for direct mbuf > only. That's why I'd like to highlight it in the function n

Re: [dpdk-dev] [PATCH] net/nfp: add CPP bridge as service

On 1/10/2019 11:55 AM, Alejandro Lucero wrote: > > > On Wed, Jan 9, 2019 at 4:15 PM Ferruh Yigit > wrote: > > On 1/9/2019 2:20 PM, Alejandro Lucero wrote: > > > > > > On Wed, Jan 9, 2019 at 10:54 AM Ferruh Yigit

[dpdk-dev] [PATCH] maintainers: resign from maintainership of distributor library

The distributor library doesn't see much in the way of changes, and Dave is well able to manage the library on his own, so remove my name against it in the MAINTAINERS file. Signed-off-by: Bruce Richardson --- MAINTAINERS | 1 - 1 file changed, 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINE

[dpdk-dev] [PATCH v3] lib/efd: fix to free tail queue entry after use

In rte_efd_create() allocated memory for tail queue entry but not freed. Added freeing the tail queue entry. Fixes: 56b6ef874f80 ("efd: new Elastic Flow Distributor library") Cc: sta...@dpdk.org Signed-off-by: Hari Kumar Vemula Acked-by: Reshma Pattan --- v3: Replaced TAILQ_FOREACH_SAFE with T

Re: [dpdk-dev] [dpdk-stable] [PATCH 2/2] build: use dependency() instead of find_library()

On Fri, Jan 11, 2019 at 11:10:28AM +, Luca Boccassi wrote: > On Mon, 2019-01-07 at 16:55 +, Bruce Richardson wrote: > > On Mon, Jan 07, 2019 at 04:39:34PM +, Luca Boccassi wrote: > > > On Mon, 2019-01-07 at 14:28 +, Bruce Richardson wrote: > > > > On Thu, Jan 03, 2019 at 06:57:25PM

Re: [dpdk-dev] [PATCH v3 1/2] mbuf: add function returning default buffer address

On Fri, Jan 11, 2019 at 02:17:04PM +0300, Andrew Rybchenko wrote: > Olivier, David, > > could you take a look at naming suggested below and share your thoughts. > My fear is that rte_mbuf_buf_addr() is too generic and true for direct mbuf > only. That's why I'd like to highlight it in the function

[dpdk-dev] [PATCH v2 00/20] NXP DPAA2 fixes and enhancements

(N: Original series was by Hemant - due to RC window timeline and his unavailability, respining on his behalf) This patch set covers following: 1. Fixes in the existing NXP DPAA2 bus and net pmd 2. New object (DPDMUX) support in NIC driver for better classification 3. Improvements to support

[dpdk-dev] [PATCH v2 01/20] bus/fslmc: fix to reset portal memory before use

From: Sachin Saxena Uninitialized portal memory is causing unwanted issues. Fixes: 293c0ca94c36 ("bus/fslmc: support memory backed portals with QBMAN 5.0") Cc: sta...@dpdk.org Signed-off-by: Sachin Saxena --- drivers/bus/fslmc/portal/dpaa2_hw_dpio.c | 2 ++ 1 file changed, 2 insertions(+) di

[dpdk-dev] [PATCH v2 04/20] net/dpaa2: fix bad check for not-null

From: Hemant Agrawal The check !dpaa2->cscn is not correct to check non-null value. Fixes: 5d9a1e4d23fe ("net/dpaa2: enhance queue memory cleanup") Cc: sta...@dpdk.org Signed-off-by: Hemant Agrawal --- drivers/net/dpaa2/dpaa2_ethdev.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) d

[dpdk-dev] [PATCH v2 02/20] bus/fslmc: fix the ring mode to use correct cache settings

From: Youri Querry The code was incorrectly using the cache inhibited access. It shall use cached enabled access for better performance. Fixes: 293c0ca94c36 ("bus/fslmc: support memory backed portals with QBMAN 5.0") Cc: sta...@dpdk.org Signed-off-by: Youri Querry --- drivers/bus/fslmc/qbman/

[dpdk-dev] [PATCH v2 03/20] bus/fslmc: fix to use correct physical core for logical core

From: Hemant Agrawal Existing code is using the lcore id as the physical core id. Add code to get the right physical id. Also, dpaa2 can not support one lcore mapping to multiple cpus, print err on such cases. Fixes: ce9efbf5bb09 ("bus/fslmc: support dynamic logging") Cc: sta...@dpdk.org Signe

[dpdk-dev] [PATCH v2 06/20] bus/fslmc: fix parse method for bus devices

Current code expects that bus->parse() would get a string containing the name of the bus. That is incorrect. bus->parse() is expected to have strings like: dpni.1,key=val dpio.2,key=val when user passed: -b fslmc:dpni.1,key=val This commit fixes this behavior. Fixes: 50245be05d1a ("bus/fsl

[dpdk-dev] [PATCH v2 05/20] bus/fslmc: fix to convert error msg to warning

From: Hemant Agrawal This is just a information. No need to print it as a error. Fixes: ce9efbf5bb09 ("bus/fslmc: support dynamic logging") Cc: sta...@dpdk.org Signed-off-by: Hemant Agrawal --- drivers/bus/fslmc/fslmc_vfio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/

[dpdk-dev] [PATCH v2 07/20] net/dpaa2: fix device init for secondary process

In order to support I/O from secondary process, the burst APIs and OPS APIs shall be mapped/plugged. Fixes: c147eae01cb3 ("net/dpaa2: introduce NXP DPAA2 driver") Cc: sta...@dpdk.org Signed-off-by: Shreyansh Jain --- drivers/net/dpaa2/dpaa2_ethdev.c | 9 - 1 file changed, 8 insertions(+

[dpdk-dev] [PATCH v2 08/20] net/dpaa2: enable optional timestamp in mbuf

From: Akhil Goyal This patch enables the population of timestamp field in mbuf on packet receive. It may give performance impact on LX2xxx platforms. So, it has been made optional for Lx2xxx platform. One shall call, rte_dpaa2_enable_ts() to enable it. Nothing is required for LS2 and LS1088 plat

[dpdk-dev] [PATCH v2 09/20] bus/fslmc: upgrade to latest qbman library

From: Hemant Agrawal This patch upgrades and sync the dpdk based qbman code with new version of qbman flib. Signed-off-by: Youri Querry Signed-off-by: Nipun Gupta Signed-off-by: Hemant Agrawal --- drivers/bus/fslmc/qbman/qbman_portal.c | 8 drivers/bus/fslmc/qbman/qbman_sys.h|

[dpdk-dev] [PATCH v2 10/20] bus/fslmc: add dynamic config for memback portal mode

From: Hemant Agrawal Add flag in portal init to adjust the qbman memory type, to decide between legacy portal mode or newly introduced memory backed portals. Signed-off-by: Roy Pledge Signed-off-by: Youri Querry Signed-off-by: Hemant Agrawal --- drivers/bus/fslmc/portal/dpaa2_hw_dpio.c

[dpdk-dev] [PATCH v2 13/20] net/dpaa2: add dpdmux mc flib

From: Nipun Gupta dpdmux object is added as a part of net driver as it is used to de-multiplex packets to separate interfaces on basis of specific rules. These rules can be configured from the software Signed-off-by: Nipun Gupta --- drivers/net/dpaa2/Makefile| 1 + drivers/net/dp

[dpdk-dev] [PATCH v2 11/20] bus/fslmc: rename portal pi index to consumer index

From: Hemant Agrawal This is to align with the latest qbman hw library Signed-off-by: Youri Querry Signed-off-by: Hemant Agrawal --- drivers/bus/fslmc/qbman/qbman_portal.c | 51 +++--- drivers/bus/fslmc/qbman/qbman_portal.h | 2 +- 2 files changed, 23 insertions(+), 30 de

[dpdk-dev] [PATCH v2 12/20] bus/fslmc: make portal func static

From: Hemant Agrawal Change QBMAN portal function to static as it is not exposed outside this file context. Signed-off-by: Hemant Agrawal --- drivers/bus/fslmc/portal/dpaa2_hw_dpio.c | 2 +- drivers/bus/fslmc/portal/dpaa2_hw_dpio.h | 2 -- 2 files changed, 1 insertion(+), 3 deletions(-) diff

[dpdk-dev] [PATCH v2 18/20] net/dpaa2: change reference to private device

The I/O threads for DPAA2 take their reference for bpool ID, the port ID and other info like qdid, from the rte_eth_dev. Further, to get this data during I/O operation, a reference of the RTE device is kept in the queue structure (dpaa2_queue). In case of secondary processes, rte_eth_dev is not sa

[dpdk-dev] [PATCH v2 14/20] bus/fslmc: add support for scanning DPDMUX object

From: Nipun Gupta Add support in bus and vfio to scan dpdmux type of objects Signed-off-by: Nipun Gupta --- drivers/bus/fslmc/fslmc_bus.c | 5 - drivers/bus/fslmc/fslmc_vfio.c | 2 ++ drivers/bus/fslmc/rte_fslmc.h | 1 + 3 files changed, 7 insertions(+), 1 deletion(-) diff --git a/drive

[dpdk-dev] [PATCH v2 15/20] net/dpaa2: add dpdmux initialization and configuration

From: Nipun Gupta This patch introduces an rte pmd API to configure dpdmux from the application. dpdmux can work in association with dpni as an additional distribution capability on the NIC. Signed-off-by: Nipun Gupta --- drivers/net/dpaa2/Makefile | 1 + drivers/net/dpaa2/d

[dpdk-dev] [PATCH v2 19/20] bus/fslmc: add support for secondary processes

Previously FSLMC bus only supported blacklisting of DPNI (eth), DPSECI (crypto) devices. With this patch, devices like DPIO, DPMCP, and other DP* can also be blacklisted/whitelisted. This is a required condition for secondary processes where the secondary needs to be passed a mutually exclusive li

[dpdk-dev] [PATCH v2 17/20] mempool/dpaa2: support saving context of buffer pool

Initial design was to have the buffer pool per process where a global static array stores the bpids. But, in case of secondary processes, this would not allow the I/O threads to translate the bpid in Rx'd packets. This patch moves the array to a global area (rte_malloc) and in case of Rx thread no

[dpdk-dev] [PATCH v2 20/20] bus/fslmc: add function to map any addr via VFIO

From: Pankaj Chauhan This is required to map any accelerator memory and PCI address to VFIO using QDMA. Signed-off-by: Minghuan Lian Signed-off-by: Pankaj Chauhan --- drivers/bus/fslmc/fslmc_vfio.c | 43 + drivers/bus/fslmc/fslmc_vfio.h | 1 + dr

[dpdk-dev] [PATCH v2 16/20] net/dpaa2: add API to support custom hash key

From: Nipun Gupta The DPAA2 hw can support a special offset based configuration to program distribution on hash. This is for all cases, which are not directly supported. e.g. HASH based distribution on inner ip header of a GRE tunnel. Signed-off-by: Nipun Gupta --- drivers/net/dpaa2/base/dpaa

Re: [dpdk-dev] [PATCH 20/20] bus/fslmc: add function to map any addr via VFIO

On 1/10/2019 9:58 AM, Shreyansh Jain wrote: > Hello Ferruh, > > Replying on behalf of Hemant... > > On 08/01/19 7:40 PM, Ferruh Yigit wrote: >> On 12/27/2018 6:23 AM, Hemant Agrawal wrote: >>> From: Pankaj Chauhan >>> >>> This is required to map any accelerator memory >>> and PCI address to VFIO

Re: [dpdk-dev] [RFC] function to parse packet headers

> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Ananyev, > Konstantin > > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Olivier Matz > > On Fri, Jan 11, 2019 at 10:56:11AM +0300, Andrew Rybchenko wrote: > > > On 1/11/19 3:11 AM, Stephen Hemminger wrote: > > > > On Thu, 10 Jan 2019 03:

Re: [dpdk-dev] [PATCH] net/nfp: add CPP bridge as service

On Fri, Jan 11, 2019 at 11:48 AM Ferruh Yigit wrote: > On 1/10/2019 11:55 AM, Alejandro Lucero wrote: > > > > > > On Wed, Jan 9, 2019 at 4:15 PM Ferruh Yigit > > wrote: > > > > On 1/9/2019 2:20 PM, Alejandro Lucero wrote: > > > > > > > > > On Wed, J

Re: [dpdk-dev] [PATCH 20/20] bus/fslmc: add function to map any addr via VFIO

On 11/01/19 5:28 PM, Ferruh Yigit wrote: > On 1/10/2019 9:58 AM, Shreyansh Jain wrote: >> Hello Ferruh, >> >> Replying on behalf of Hemant... >> >> On 08/01/19 7:40 PM, Ferruh Yigit wrote: >>> On 12/27/2018 6:23 AM, Hemant Agrawal wrote: From: Pankaj Chauhan [...] +DPDK_19.02 { +

[dpdk-dev] [PATCH v3 00/20] NXP DPAA2 fixes and enhancements

(N: Original series was by Hemant - due to RC window timeline and his unavailability, respining on his behalf) This patch set covers following: 1. Fixes in the existing NXP DPAA2 bus and net pmd 2. New object (DPDMUX) support in NIC driver for better classification 3. Improvements to support

[dpdk-dev] [PATCH v3 02/19] bus/fslmc: fix the ring mode to use correct cache settings

From: Youri Querry The code was incorrectly using the cache inhibited access. It shall use cached enabled access for better performance. Fixes: 293c0ca94c36 ("bus/fslmc: support memory backed portals with QBMAN 5.0") Cc: sta...@dpdk.org Signed-off-by: Youri Querry --- drivers/bus/fslmc/qbman/

[dpdk-dev] [PATCH v3 01/19] bus/fslmc: fix to reset portal memory before use

From: Sachin Saxena Uninitialized portal memory is causing unwanted issues. Fixes: 293c0ca94c36 ("bus/fslmc: support memory backed portals with QBMAN 5.0") Cc: sta...@dpdk.org Signed-off-by: Sachin Saxena --- drivers/bus/fslmc/portal/dpaa2_hw_dpio.c | 2 ++ 1 file changed, 2 insertions(+) di

[dpdk-dev] [PATCH v3 03/19] bus/fslmc: fix to use correct physical core for logical core

From: Hemant Agrawal Existing code is using the lcore id as the physical core id. Add code to get the right physical id. Also, dpaa2 can not support one lcore mapping to multiple cpus, print err on such cases. Fixes: ce9efbf5bb09 ("bus/fslmc: support dynamic logging") Cc: sta...@dpdk.org Signe

[dpdk-dev] [PATCH v3 04/19] net/dpaa2: fix bad check for not-null

From: Hemant Agrawal The check !dpaa2->cscn is not correct to check non-null value. Fixes: 5d9a1e4d23fe ("net/dpaa2: enhance queue memory cleanup") Cc: sta...@dpdk.org Signed-off-by: Hemant Agrawal --- drivers/net/dpaa2/dpaa2_ethdev.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) d

[dpdk-dev] [PATCH v3 06/19] bus/fslmc: fix parse method for bus devices

Current code expects that bus->parse() would get a string containing the name of the bus. That is incorrect. bus->parse() is expected to have strings like: dpni.1,key=val dpio.2,key=val when user passed: -b fslmc:dpni.1,key=val This commit fixes this behavior. Fixes: 50245be05d1a ("bus/fsl

[dpdk-dev] [PATCH v3 07/19] net/dpaa2: fix device init for secondary process

In order to support I/O from secondary process, the burst APIs and OPS APIs shall be mapped/plugged. Fixes: c147eae01cb3 ("net/dpaa2: introduce NXP DPAA2 driver") Cc: sta...@dpdk.org Signed-off-by: Shreyansh Jain --- drivers/net/dpaa2/dpaa2_ethdev.c | 9 - 1 file changed, 8 insertions(+

[dpdk-dev] [PATCH v3 08/19] net/dpaa2: enable optional timestamp in mbuf

From: Akhil Goyal This patch enables the population of timestamp field in mbuf on packet receive. It may give performance impact on LX2xxx platforms. So, it has been made optional for Lx2xxx platform. One shall call, rte_dpaa2_enable_ts() to enable it. Nothing is required for LS2 and LS1088 plat

[dpdk-dev] [PATCH v3 05/19] bus/fslmc: fix to convert error msg to warning

From: Hemant Agrawal This is just a information. No need to print it as a error. Fixes: ce9efbf5bb09 ("bus/fslmc: support dynamic logging") Cc: sta...@dpdk.org Signed-off-by: Hemant Agrawal --- drivers/bus/fslmc/fslmc_vfio.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/

[dpdk-dev] [PATCH v3 10/19] bus/fslmc: add dynamic config for memback portal mode

From: Hemant Agrawal Add flag in portal init to adjust the qbman memory type, to decide between legacy portal mode or newly introduced memory backed portals. Signed-off-by: Roy Pledge Signed-off-by: Youri Querry Signed-off-by: Hemant Agrawal --- drivers/bus/fslmc/portal/dpaa2_hw_dpio.c

[dpdk-dev] [PATCH v3 09/19] bus/fslmc: upgrade to latest qbman library

From: Hemant Agrawal This patch upgrades and sync the dpdk based qbman code with new version of qbman flib. Signed-off-by: Youri Querry Signed-off-by: Nipun Gupta Signed-off-by: Hemant Agrawal --- drivers/bus/fslmc/qbman/qbman_portal.c | 8 drivers/bus/fslmc/qbman/qbman_sys.h|

[dpdk-dev] [PATCH v3 11/19] bus/fslmc: rename portal pi index to consumer index

From: Hemant Agrawal This is to align with the latest qbman hw library Signed-off-by: Youri Querry Signed-off-by: Hemant Agrawal --- drivers/bus/fslmc/qbman/qbman_portal.c | 51 +++--- drivers/bus/fslmc/qbman/qbman_portal.h | 2 +- 2 files changed, 23 insertions(+), 30 de

[dpdk-dev] [PATCH v3 13/19] net/dpaa2: add dpdmux mc flib

From: Nipun Gupta dpdmux object is added as a part of net driver as it is used to de-multiplex packets to separate interfaces on basis of specific rules. These rules can be configured from the software Signed-off-by: Nipun Gupta --- drivers/net/dpaa2/Makefile| 1 + drivers/net/dp

[dpdk-dev] [PATCH v3 12/19] bus/fslmc: make portal func static

From: Hemant Agrawal Change QBMAN portal function to static as it is not exposed outside this file context. Signed-off-by: Hemant Agrawal --- drivers/bus/fslmc/portal/dpaa2_hw_dpio.c | 2 +- drivers/bus/fslmc/portal/dpaa2_hw_dpio.h | 2 -- 2 files changed, 1 insertion(+), 3 deletions(-) diff

[dpdk-dev] [PATCH v3 14/19] bus/fslmc: add support for scanning DPDMUX object

From: Nipun Gupta Add support in bus and vfio to scan dpdmux type of objects Signed-off-by: Nipun Gupta --- drivers/bus/fslmc/fslmc_bus.c | 5 - drivers/bus/fslmc/fslmc_vfio.c | 2 ++ drivers/bus/fslmc/rte_fslmc.h | 1 + 3 files changed, 7 insertions(+), 1 deletion(-) diff --git a/drive

[dpdk-dev] [PATCH v3 16/19] net/dpaa2: add API to support custom hash key

From: Nipun Gupta The DPAA2 hw can support a special offset based configuration to program distribution on hash. This is for all cases, which are not directly supported. e.g. HASH based distribution on inner ip header of a GRE tunnel. Signed-off-by: Nipun Gupta --- drivers/net/dpaa2/base/dpaa

[dpdk-dev] [PATCH v3 19/19] bus/fslmc: add support for secondary processes

Previously FSLMC bus only supported blacklisting of DPNI (eth), DPSECI (crypto) devices. With this patch, devices like DPIO, DPMCP, and other DP* can also be blacklisted/whitelisted. This is a required condition for secondary processes where the secondary needs to be passed a mutually exclusive li

[dpdk-dev] [PATCH v3 15/19] net/dpaa2: add dpdmux initialization and configuration

From: Nipun Gupta This patch introduces an rte pmd API to configure dpdmux from the application. dpdmux can work in association with dpni as an additional distribution capability on the NIC. Signed-off-by: Nipun Gupta --- drivers/net/dpaa2/Makefile | 1 + drivers/net/dpaa2/d

[dpdk-dev] [PATCH v3 18/19] net/dpaa2: change reference to private device

The I/O threads for DPAA2 take their reference for bpool ID, the port ID and other info like qdid, from the rte_eth_dev. Further, to get this data during I/O operation, a reference of the RTE device is kept in the queue structure (dpaa2_queue). In case of secondary processes, rte_eth_dev is not sa

[dpdk-dev] [PATCH v3 17/19] mempool/dpaa2: support saving context of buffer pool

Initial design was to have the buffer pool per process where a global static array stores the bpids. But, in case of secondary processes, this would not allow the I/O threads to translate the bpid in Rx'd packets. This patch moves the array to a global area (rte_malloc) and in case of Rx thread no

Re: [dpdk-dev] [PATCH] net/nfp: add CPP bridge as service

On 1/11/2019 12:15 PM, Alejandro Lucero wrote: > On Fri, Jan 11, 2019 at 11:48 AM Ferruh Yigit > wrote: > >> On 1/10/2019 11:55 AM, Alejandro Lucero wrote: >>> >>> >>> On Wed, Jan 9, 2019 at 4:15 PM Ferruh Yigit >> > wrote: >>> >>> On 1/9/2019 2:20 PM, Alejandro

[dpdk-dev] [PATCH v2 1/3] build: use static deps of libs for pkg-config libs.private

Dependencies of the RTE libraries were not being added to the Requires.private field of the pc file since the variable used for dynamic linking was passed to the related field of pkg.generate. Use the static one so that dependencies are included. Fixes: 57ae0ec62620 ("build: add dependency on tele

[dpdk-dev] [PATCH v2 2/3] build: use dependency() instead of find_library()

Whenever possible (if the library ships a pkg-config file) use meson's dependency() function to look for it, as it will automatically add it to the Requires.private list if needed, to allow for static builds to succeed for reverse dependencies of DPDK. Otherwise the recursive dependencies are not p

[dpdk-dev] [PATCH v2 3/3] build: bump minimum Meson to 0.47.1 and use dependency() for libbsd

Move libbsd inclusion to librte_eal, so that all other libraries and PMDs will inherit it, and librte_cmdline which is built before librte_eal. Bump Meson dependency to 0.47.1, to avoid bug where the linker flag of the dependency gets replicated again and again. Signed-off-by: Luca Boccassi --- v

Re: [dpdk-dev] [dpdk-stable] [PATCH 2/2] build: use dependency() instead of find_library()

On Fri, 2019-01-11 at 11:52 +, Bruce Richardson wrote: > On Fri, Jan 11, 2019 at 11:10:28AM +, Luca Boccassi wrote: > > On Mon, 2019-01-07 at 16:55 +, Bruce Richardson wrote: > > > On Mon, Jan 07, 2019 at 04:39:34PM +, Luca Boccassi wrote: > > > > On Mon, 2019-01-07 at 14:28 +,

Re: [dpdk-dev] [PATCH v3 1/2] mbuf: add function returning default buffer address

On Fri, Jan 11, 2019 at 12:57 PM Bruce Richardson < bruce.richard...@intel.com> wrote: > On Fri, Jan 11, 2019 at 02:17:04PM +0300, Andrew Rybchenko wrote: > > Olivier, David, > > > > could you take a look at naming suggested below and share your thoughts. > > My fear is that rte_mbuf_buf_addr() is

[dpdk-dev] [PATCH] ethdev: declare tx prepare api as not experimental

The tx prepare api was introduced at a time when the experimental api tag mechanism did not exist yet and is missing the tag. However, this api has been there since 17.02 and did not suffer any change since its introduction. Let's just remove the warning from the documentation. Signed-off-by: Dav

[dpdk-dev] [PATCH] net/nfp: add CPP bridge as service

The Netronome's Network Flow Processor chip is highly programmable with the goal of processing packets at high speed. Processing units and other chip components are available from the host through the PCIe CPP(Command Push Pull bus) interface. The NFP PF PMD configures a CPP handler for setting up

Re: [dpdk-dev] [PATCH v1] net/i40e: perform basic validation on the VF messages

Hi Vipin: > -Original Message- > From: Varghese, Vipin > Sent: Friday, January 11, 2019 10:54 AM > To: Kevin Traynor ; Wang, Haiyue > ; dev@dpdk.org; Zhang, Qi Z > Subject: RE: [dpdk-dev] [PATCH v1] net/i40e: perform basic validation on the > VF > messages > > Hi Kevin, > > A question,

Re: [dpdk-dev] [PATCH] ethdev: declare tx prepare api as not experimental

On 1/11/2019 1:14 PM, David Marchand wrote: > The tx prepare api was introduced at a time when the experimental api > tag mechanism did not exist yet and is missing the tag. > However, this api has been there since 17.02 and did not suffer any > change since its introduction. > > Let's just remove

Re: [dpdk-dev] [PATCH] ethdev: declare tx prepare api as not experimental

On 1/11/19 4:14 PM, David Marchand wrote: The tx prepare api was introduced at a time when the experimental api tag mechanism did not exist yet and is missing the tag. However, this api has been there since 17.02 and did not suffer any change since its introduction. Let's just remove the warning

Re: [dpdk-dev] [PATCH] vhost_user: remove statement for non-existed function

> vhost_user: remove statement for non-existed function s/vhost_user/vhost/ On Fri, Jan 11, 2019 at 04:05:41PM +0800, Xiaolong Ye wrote: > vhost_user_host_notifier_ctrl is not existed anymore, its statement in > header file should be removed accordingly. > > Fixes: 43f34e35663f ("vhost: provide

Re: [dpdk-dev] [EXT] [PATCH v3 5/6] spinlock: reimplement with atomic one-way barrier builtins

> -Original Message- > From: Jerin Jacob Kollanukkaran > Sent: Thursday, December 27, 2018 3:42 PM > To: Gavin Hu (Arm Technology China) ; > dev@dpdk.org > Cc: david.march...@redhat.com; chao...@linux.vnet.ibm.com; nd > ; bruce.richard...@intel.com; tho...@monjalon.net; > hemant.agra...@

Re: [dpdk-dev] [PATCH] ethdev: declare tx prepare api as not experimental

> -Original Message- > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of David Marchand > Sent: Friday, January 11, 2019 1:15 PM > To: dev@dpdk.org > Cc: tho...@monjalon.net; Yigit, Ferruh ; > arybche...@solarflare.com > Subject: [dpdk-dev] [PATCH] ethdev: declare tx prepare api as n

  1   2   >