HW implements completion queues(CQ) used to post completion reports upon
completion of work request.
Used for Rx and Tx datapath.
Add DevX command to create a CQ.
Signed-off-by: Matan Azrad
---
drivers/common/mlx5/mlx5_devx_cmds.c| 57
drivers/common/mlx5/mlx5_
Add support for the next features in virtq configuration:
VIRTIO_F_RING_PACKED,
VIRTIO_NET_F_HOST_TSO4,
VIRTIO_NET_F_HOST_TSO6,
VIRTIO_NET_F_CSUM,
VIRTIO_NET_F_GUEST_CSUM,
VIRTIO_F_VERSION_1,
These features support depends in the DevX capabilities re
In order to map the guest physical addresses used by the virtio device
guest side to the host physical addresses used by the HW as the host
side, memory regions are created.
By this way, for example, the HW can translate the addresses of the
packets posted by the guest and to take the packets from
Allow virtio queue type configuration in the RQ table.
The needed fields and configuration was added.
Signed-off-by: Matan Azrad
---
drivers/common/mlx5/mlx5_devx_cmds.c | 1 +
drivers/common/mlx5/mlx5_devx_cmds.h | 1 +
drivers/common/mlx5/mlx5_prm.h | 5 +++--
3 files changed, 5 insertio
The HW virtq object represents an emulated context for a VIRTIO_NET
virtqueue which was created and managed by a VIRTIO_NET driver as
defined in VIRTIO Specification.
Add support to prepare and release all the basic HW resources needed
the user virtqs emulation according to the rte_vhost configura
Add a steering object to be managed by a new file mlx5_vdpa_steer.c.
Allow promiscuous flow to scatter the device Rx packets to the virtio
queues using RSS action.
In order to allow correct RSS in L3 and L4, split the flow to 7 flows
as required by the device.
Signed-off-by: Matan Azrad
---
dr
In order to allow RQT size configuration which is limited to the
correct maximum value, add log_max_rqt_size for DevX capability
structure.
Signed-off-by: Matan Azrad
---
drivers/common/mlx5/mlx5_devx_cmds.c | 2 ++
drivers/common/mlx5/mlx5_devx_cmds.h | 1 +
2 files changed, 3 insertions(+)
di
The HW support only 4 bytes doorbell writing detection.
The virtio device set only 2 bytes when it rings the doorbell.
Map the virtio doorbell detected by the virtio queue kickfd to the HW
VAR space when it expects to get the virtio emulation doorbell.
Use the EAL interrupt mechanism to get notif
Add support for set_vring_state operation.
Using DevX API the virtq state can be changed as described in PRM:
enable - move to ready state.
disable - move to suspend state.
Signed-off-by: Matan Azrad
---
drivers/vdpa/mlx5/mlx5_vdpa.c | 23 ++-
drivers/v
RQ table can be changed to support different list of queues.
Add DevX command to modify DevX RQT object to point on new RQ list.
Signed-off-by: Matan Azrad
---
drivers/common/mlx5/mlx5_devx_cmds.c| 47 +
drivers/common/mlx5/mlx5_devx_cmds.h| 2 ++
Support dev_conf and dev_conf operations.
These operations allow vdpa traffic.
Signed-off-by: Matan Azrad
---
drivers/vdpa/mlx5/mlx5_vdpa.c | 51 +--
drivers/vdpa/mlx5/mlx5_vdpa.h | 1 +
2 files changed, 50 insertions(+), 2 deletions(-)
diff --git a/driv
The DevX TIR object configuration should get L3 and L4 protocols
expected to be forwarded by the TIR.
Add the PRM constant values needed to configure the L3 and L4 protocols.
Signed-off-by: Matan Azrad
---
drivers/common/mlx5/mlx5_prm.h | 10 ++
1 file changed, 10 insertions(+)
diff --
Add support for live migration feature by the HW:
Create a single Mkey that maps the memory address space of the
VHOST live migration log file.
Modify VIRTIO_NET_Q object and provide vhost_log_page,
dirty_bitmap_mkey, dirty_bitmap_size, dirty_bitmap_a
Both, net/mlx5 PMD and vdpa/mlx5 drivers can probe the same Mellanox
devices.
Skip net/mlx5 PMD probing while the device is in vDPA mode selected by
the device devargs provided by the user: vdpa=1.
Skip vdpa/mlx5 PMD probing while the device is not in vDPA mode selected by
the device devargs prov
Add new 4 Netlink commands to support enable/disable ROCE:
1. mlx5_nl_devlink_family_id_get to get the Devlink family ID of
Netlink general command.
2. mlx5_nl_enable_roce_get to get the ROCE current status.
3. mlx5_nl_driver_reload - to reload the device kernel d
Move Netlink mechanism and its dependecies from net/mlx5 to common/mlx5
in order to be ready to use by other mlx5 drivers.
The dependencies are BITFIELD defines, the ppc64 compilation workaround
for bool type and the function mlx5_translate_port_name.
Update build mechanism accordingly.
Signed-o
The Netlink commands interfaces is included in the mlx5.h file with a
lot of other PMD interfaces.
As an arrangement to make the Netlink commands shared with different
PMDs, this patch moves the Netlink interface to a new file called
mlx5_nl.h.
Move non Netlink pure vlan commands from mlx5_nl.c t
In order to support virtio queue creation by the FW, ROCE mode
should be disabled in the device.
Do it by netlink which is like the devlink tool commands:
1. devlink dev param set pci/[pci] name enable_roce value false
cmode driverinit
2. devlink dev reload pci/[pci]
Or
As an arrangment for Netlink command moving to the common library,
reduce the net/mlx5 dependecies.
Replace ethdev class command parameters.
Improve Netlink sequence number mechanism to be controlled by the
mlx5 Netlink mechanism.
Move mlx5_nl_check_switch_info to mlx5_nl.c since it is the only
refactor vdpa specific devargs parsing to more generic way
Signed-off-by: Ivan Dyukov
---
drivers/net/virtio/virtio_ethdev.c | 35 +-
1 file changed, 25 insertions(+), 10 deletions(-)
diff --git a/drivers/net/virtio/virtio_ethdev.c
b/drivers/net/virtio/virtio_ethdev
Some applications like pktgen use link_speed to calculate
transmit rate. It limits outcome traffic to hardcoded 10G.
This patch adds link_speed devarg which allows to configure
link_speed of virtio device.
Signed-off-by: Ivan Dyukov
---
drivers/net/virtio/virtio_ethdev.c | 101 +
pktgen cli does not show sequence help if it's wrong or incomplete
Signed-off-by: Ivan Dyukov
---
app/cli-functions.c | 7 +--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/app/cli-functions.c b/app/cli-functions.c
index f104781..f43d23e 100644
--- a/app/cli-functions.c
+++ b
Update detach routine to check the mbuf pool type.
Introduce the special internal version of detach routine to handle
the special case of pinned external bufferon mbuf freeing.
Signed-off-by: Shahaf Shuler
Signed-off-by: Viacheslav Ovsiienko
---
lib/librte_mbuf/rte_mbuf.h | 102
The routine rte_pktmbuf_priv_flags is introduced to fetch
the flags from the mbuf memory pool private structure
in unified fashion.
Signed-off-by: Viacheslav Ovsiienko
Acked-by: Olivier Matz
---
lib/librte_mbuf/rte_mbuf.h | 17 +
1 file changed, 17 insertions(+)
diff --git a/li
Today's pktmbuf pool contains only mbufs with no external buffers.
This means data buffer for the mbuf should be placed right after the
mbuf structure (+ the private data when enabled).
On some cases, the application would want to have the buffers allocated
from a different device in the platform.
In the Rx datapath the flags in the newly allocated mbufs
are all explicitly cleared but the EXT_ATTACHED_MBUF must be
preserved. It would allow to use mbuf pools with pre-attached
external data buffers.
The vectorized rx_burst routines are updated in order to
inherit the EXT_ATTACHED_MBUF from mb
The dedicated routine rte_pktmbuf_pool_create_extbuf() is
provided to create mbuf pool with data buffers located in
the pinned external memory. The application provides the
external memory description and routine initializes each
mbuf with appropriate virtual and physical buffer address.
It is enti
The new mbuf pool type is added to testpmd. To engage the
mbuf pool with externally attached data buffers the parameter
"--mp-alloc=xbuf" should be specified in testpmd command line.
The objective of this patch is just to test whether mbuf pool
with externally attached data buffers works OK. The m
The unit test (as part of test_mbuf application) will be provided as separated
patch.
With best regards, Slava
> -Original Message-
> From: dev On Behalf Of Viacheslav Ovsiienko
> Sent: Monday, January 20, 2020 19:23
> To: dev@dpdk.org
> Cc: Matan Azrad ; Raslan Darawsheh
> ; Ori Kam ;
Hi, Olivier
Great! Thanks a lot for the unit test template, this is very nice starting
point,
I will think what would be good to add for more thorough testing.
With best regards, Slava
> One more thing: it would be nice to have a functional test for this new
> feature. I did a very minimal one
On Mon, Dec 23, 2019 at 06:53:05AM +, Reshma Pattan wrote:
> Some unit tests has dependency on RING PMD,
> so this patch is trying to fix those and other
> closely related issues.
>
> 1)pdump, latency, bitrate, ring PMD and test_event_eth_tx_adapter
> unit tests are dependent on ring PMD, so c
Rather than having to explicitly list each and every driver to disable in a
build, we can use a small python script and the python glob library to
expand out the wildcards. This means that we can configure meson using e.g.
meson -Ddisable_drivers=crypto/*,event/* build
to do a build omitting
On Mon, Jan 20, 2020 at 05:23:20PM +, Viacheslav Ovsiienko wrote:
> Update detach routine to check the mbuf pool type.
> Introduce the special internal version of detach routine to handle
> the special case of pinned external bufferon mbuf freeing.
>
> Signed-off-by: Shahaf Shuler
> Signed-of
On Mon, Jan 20, 2020 at 05:30:45PM +, Slava Ovsiienko wrote:
> The unit test (as part of test_mbuf application) will be provided as
> separated patch.
OK, thanks
17/01/2020 20:14, jer...@marvell.com:
> From: Jerin Jacob
>
> Based on the techboard meeting held on 2019-11-06,
> It's been decided to disable all kmods by default from v20.02.
>
> http://mails.dpdk.org/archives/dev/2019-November/151763.html
>
> Signed-off-by: Jerin Jacob
> ---
> v2:
> - Upda
On Mon, Jan 20, 2020 at 05:23:21PM +, Viacheslav Ovsiienko wrote:
> The dedicated routine rte_pktmbuf_pool_create_extbuf() is
> provided to create mbuf pool with data buffers located in
> the pinned external memory. The application provides the
> external memory description and routine initiali
14/01/2020 11:40, Burakov, Anatoly:
> On 20-Dec-19 3:08 PM, Artur Trybula wrote:
> > In case of too low number of memzone segements user notification
> > was misleading. This patch improves the description by providing
> > better explanation about the cause.
> >
> > Signed-off-by: Artur Trybula
>
> -Original Message-
> From: Thomas Monjalon
> Sent: Monday, January 20, 2020 2:33 PM
> To: Trahe, Fiona ; Trybula, ArturX
> ; Mcnamara, John
> Cc: dev@dpdk.org; sta...@dpdk.org; shal...@marvell.com; Dybkowski, AdamX
> ; Danilewicz, MarcinX
> ; Akhil Goyal
> Subject: Re: [dpdk-stable]
On 12/2/2019 3:35 PM, David Marchand wrote:
> We are currently stuck with no option but recompile a DPDK if the system
> has more cores than RTE_MAX_LCORE.
> A bit of a pity when you get a system with more than 200+ cores and your
> testpmd has been built and packaged with RTE_MAX_LCORE == 128.
Ju
20/01/2020 18:37, Bruce Richardson:
> Rather than having to explicitly list each and every driver to disable in a
> build, we can use a small python script and the python glob library to
> expand out the wildcards. This means that we can configure meson using e.g.
>
> meson -Ddisable_drivers=c
Today's pktmbuf pool contains only mbufs with no external buffers.
This means data buffer for the mbuf should be placed right after the
mbuf structure (+ the private data when enabled).
On some cases, the application would want to have the buffers allocated
from a different device in the platform.
Update detach routine to check the mbuf pool type.
Introduce the special internal version of detach routine to handle
the special case of pinned external bufferon mbuf freeing.
Signed-off-by: Shahaf Shuler
Signed-off-by: Viacheslav Ovsiienko
Acked-by: Olivier Matz
---
lib/librte_mbuf/rte_mbuf.
The dedicated routine rte_pktmbuf_pool_create_extbuf() is
provided to create mbuf pool with data buffers located in
the pinned external memory. The application provides the
external memory description and routine initializes each
mbuf with appropriate virtual and physical buffer address.
It is enti
The new mbuf pool type is added to testpmd. To engage the
mbuf pool with externally attached data buffers the parameter
"--mp-alloc=xbuf" should be specified in testpmd command line.
The objective of this patch is just to test whether mbuf pool
with externally attached data buffers works OK. The m
In the Rx datapath the flags in the newly allocated mbufs
are all explicitly cleared but the EXT_ATTACHED_MBUF must be
preserved. It would allow to use mbuf pools with pre-attached
external data buffers.
The vectorized rx_burst routines are updated in order to
inherit the EXT_ATTACHED_MBUF from mb
The routine rte_pktmbuf_priv_flags is introduced to fetch
the flags from the mbuf memory pool private structure
in unified fashion.
Signed-off-by: Viacheslav Ovsiienko
Acked-by: Olivier Matz
---
lib/librte_mbuf/rte_mbuf.h | 17 +
1 file changed, 17 insertions(+)
diff --git a/li
On Mon, Jan 20, 2020 at 7:37 PM Yigit, Ferruh
wrote:
>
> On 12/2/2019 3:35 PM, David Marchand wrote:
> > We are currently stuck with no option but recompile a DPDK if the system
> > has more cores than RTE_MAX_LCORE.
> > A bit of a pity when you get a system with more than 200+ cores and your
> >
OCTEON TX2 isn't built for gcc 4.8.5 as the compiler emits
"internal compiler error" on aarch64. This causes the following
build error when OCTEON TX2 EP is enabled:
/usr/bin/ld: cannot find -lrte_common_octeontx2
collect2: error: ld returned 1 exit status
Fixes: 56d46d13f736 ("raw/octeontx2_
19/12/2019 12:25, jer...@marvell.com:
> From: Jerin Jacob
>
> Introduce EAL typedef for structure 1B, 2B, 4B, 8B alignment marking and
> a generic marker for a point in a structure.
>
> Signed-off-by: Jerin Jacob
> ---
>
> v2:
> - Changed __extension__ to RTE_STD_C11 (Thomas)
Actually I was
Without a git tree, the "guess" script from dpdk-ci will ignore all files
that are referenced in those sections and let a patchset land in any
subtree.
Changes in the EAL, mbuf, mempool... go through the main repository.
Signed-off-by: David Marchand
---
MAINTAINERS | 2 ++
1 file changed, 2 ins
On Mon, 20 Jan 2020 17:23:19 +
Viacheslav Ovsiienko wrote:
> The routine rte_pktmbuf_priv_flags is introduced to fetch
> the flags from the mbuf memory pool private structure
> in unified fashion.
>
> Signed-off-by: Viacheslav Ovsiienko
> Acked-by: Olivier Matz
> ---
> lib/librte_mbuf/rte
On Mon, 20 Jan 2020 19:16:24 +
Viacheslav Ovsiienko wrote:
> + ((user_mbp_priv->flags & RTE_PKTMBUF_POOL_F_PINNED_EXT_BUF) ?
> + sizeof(struct rte_mbuf_ext_shared_info) :
> + user_mbp_priv->mbuf_data_room_size
Should rte_pktmbuf_data_room_s
On Thu, Jan 16, 2020 at 4:47 AM Kalesh A P <
kalesh-anakkur.pura...@broadcom.com> wrote:
> From: Kalesh AP
>
> v1->v2: fixed the correct the commit ids in Fixes tag.
> v2->v3: shorten commit log and update commit ids for Fixes tag.
> v3->v4: addressed Ferruh's comment on Patch#1 and Pacth#9 and m
26/12/2019 17:24, Olivier Matz:
> On Thu, Dec 19, 2019 at 04:55:07PM +0530, jer...@marvell.com wrote:
> > From: Jerin Jacob
> >
> > Use new marker typedef available in EAL and remove private marker
> > typedef.
> >
> > Signed-off-by: Jerin Jacob
>
> Acked-by: Olivier Matz
Series applied, tha
20/01/2020 20:51, Ali Alnubani:
> OCTEON TX2 isn't built for gcc 4.8.5 as the compiler emits
> "internal compiler error" on aarch64. This causes the following
> build error when OCTEON TX2 EP is enabled:
>
> /usr/bin/ld: cannot find -lrte_common_octeontx2
> collect2: error: ld returned 1 exit
20/01/2020 21:43, Stephen Hemminger:
> On Mon, 20 Jan 2020 17:23:19 +
> Viacheslav Ovsiienko wrote:
>
> > The routine rte_pktmbuf_priv_flags is introduced to fetch
> > the flags from the mbuf memory pool private structure
> > in unified fashion.
> >
> > Signed-off-by: Viacheslav Ovsiienko
>
20/01/2020 20:16, Viacheslav Ovsiienko:
> Today's pktmbuf pool contains only mbufs with no external buffers.
> This means data buffer for the mbuf should be placed right after the
> mbuf structure (+ the private data when enabled).
>
> On some cases, the application would want to have the buffers
02/12/2019 16:35, David Marchand:
> We are currently stuck with no option but recompile a DPDK if the system
> has more cores than RTE_MAX_LCORE.
> A bit of a pity when you get a system with more than 200+ cores and your
> testpmd has been built and packaged with RTE_MAX_LCORE == 128.
>
> The --lc
A new DPDK release candidate is ready for testing:
https://git.dpdk.org/dpdk/tag/?id=v20.02-rc1
There are 374 new patches in this snapshot.
DPDK 20.02 will be tiny, as expected.
The release notes so far:
http://doc.dpdk.org/guides/rel_notes/release_20_02.html
Please think about up
Base on current fdir implementation for GTP-U, inner specification is
not supported, issue a rule for eth/ipv4/gtpu/ipv4 will also match
eth/ipv4/gtpu/ipv6, the patch add new pattern list to align with exist
implementation.
Fixes: efc16c621415 ("net/ice: support flow director GTPU tunnel")
Cc: sta
> -Original Message-
> From: Ferruh Yigit [mailto:ferruh.yi...@intel.com]
> Sent: Monday, January 20, 2020 8:43 PM
> To: wangyunjian ; dev@dpdk.org;
> keith.wi...@intel.com
> Cc: xudingke ; sta...@dpdk.org
> Subject: Re: [dpdk-stable] [dpdk-dev] [PATCH] net/tap: fix memory leak when
> unreg
The return check of function tap_lsc_intr_handle_set() is wrong, it should
be 0 or a positive number if success. So the intr_handle->intr_vec was not
been freed when tap_lsc_intr_handle_set() returned a positive number.
Fixes: 4870a8cdd968 ("net/tap: support Rx interrupt")
Cc: sta...@dpdk.org
Sig
The original PASSTHRU implementation is forwarding to queue 0. The
corrected implementation is forwarding to the next stage filter.
Fixes: f5cafa961fae ("net/ice: add flow director create and destroy")
Cc: sta...@dpdk.org
Signed-off-by: Yahui Cao
---
drivers/net/ice/base/ice_fdir.c | 9 ++
If there's no mark action when creating a FDIR rule,
there shouldn't be FDIR flags in mbuf.
Fixes: f5cafa961fae ("net/ice: add flow director create and destroy")
Fixes: bd984f155f49 ("net/ice/base: support FDIR")
Cc: sta...@dpdk.org
Signed-off-by: Beilei Xing
Acked-by: Qi Zhang
---
V2 change:
Hi Xiaojun,
Could you please help to improve the commit logs of all the 7 patches? They
look very similar, and info like below is not very helpful for reviewer, since
we already know which file you are adding.
"To support switch management, add the following files:
Add fm10k/switch/fm10k_debug.h
From: Chenmin Sun
This patch adds the capability of matching the outer IPv4
headers for GTPU flows
Fixes: efc16c621415 ("net/ice: support flow director GTPU tunnel")
Signed-off-by: Chenmin Sun
---
drivers/net/ice/base/ice_fdir.c | 4
drivers/net/ice/ice_fdir_filter.c | 3 ++-
2 files c
Hi Ferruh,
Can you review this patch?
Thanks,
Anoob
> -Original Message-
> From: dev On Behalf Of Anoob Joseph
> Sent: Tuesday, December 10, 2019 12:23 PM
> To: John McNamara ; Marko Kovacevic
> ; Ferruh Yigit
> Cc: Anoob Joseph ; Jerin Jacob Kollanukkaran
> ; Narayana Prasad Raju Athr
[AMD Official Use Only - Internal Distribution Only]
Looks good to me.
Acked-by: Ravi Kumar
Regards,
Ravi
>
>
>-Original Message-
>From: dev On Behalf Of Selwin Sebastian
>Sent: Tuesday, December 31, 2019 12:38 AM
>To: dev@dpdk.org
>Cc: Sebastian, Selwin
>Subject: [dpdk-dev] [PATCH
[AMD Public Use]
Looks good to me.
Acked-by: Ravi Kumar
Regards,
Ravi
>-Original Message-
>From: dev On Behalf Of Selwin Sebastian
>Sent: Monday, December 30, 2019 10:05 PM
>To: dev@dpdk.org
>Cc: Sebastian, Selwin
>Subject: [dpdk-dev] [PATCH v1] crypto/ccp: add support for new CCP
Hi Xiao,
Thank you! I will update the commit log and prepare a document to describe the
design and implementation.
Best regards,
Xiaojun
-Original Message-
From: Wang, Xiao W [mailto:xiao.w.w...@intel.com]
Sent: Tuesday, January 21, 2020 10:53 AM
To: Xiaojun Liu
Cc: dev@dpdk.org; Zhang
Hi, Stephen
I'm appreciated for the for reviewing.
> -Original Message-
> From: Stephen Hemminger
> Sent: Monday, January 20, 2020 22:44
> To: Slava Ovsiienko
> Cc: dev@dpdk.org; Matan Azrad ; Raslan Darawsheh
> ; Ori Kam ; Shahaf Shuler
> ; olivier.m...@6wind.com; tho...@mellanox.net
>
> -Original Message-
> From: Stephen Hemminger
> Sent: Monday, January 20, 2020 22:48
> To: Slava Ovsiienko
> Cc: dev@dpdk.org; Matan Azrad ; Raslan Darawsheh
> ; Ori Kam ; Shahaf Shuler
> ; olivier.m...@6wind.com; tho...@mellanox.net
> Subject: Re: [PATCH v6 3/5] mbuf: create packet pool
Hi,
Please also enable meson build for armv8 PMD.
There was a patch in last release which was not applied. That need a rebase and
can be included in this series if more changes need to be done for the changes
in this patchset.
http://patches.dpdk.org/patch/60499/
Please also update the release
Hi,
> -Original Message-
> From: Ferruh Yigit
> Sent: Monday, January 20, 2020 6:58 PM
> To: Alfredo Cardigliano ; John McNamara
> ; Marko Kovacevic
>
> Cc: dev@dpdk.org; Raslan Darawsheh
> Subject: Re: [dpdk-dev] [PATCH v5 11/17] net/ionic: add Rx filters support
>
> On 1/19/2020 3:53
101 - 174 of 174 matches
Mail list logo
