On 3/12/21 8:46 PM, Thomas Monjalon wrote:
> Since rte_flow is the only API for filtering operations,
> the legacy driver interface filter_ctrl was too much complicated
> for the simple task of getting the struct rte_flow_ops.
>
> The filter type RTE_ETH_FILTER_GENERIC and
> the filter operarion R
for dpaa2
Acked-by: Hemant Agrawal
For dpaa2
Acked-by: Hemant Agrawal
15/03/2021 08:18, Andrew Rybchenko:
> On 3/12/21 8:46 PM, Thomas Monjalon wrote:
> > --- a/lib/librte_ethdev/rte_flow.c
> > +++ b/lib/librte_ethdev/rte_flow.c
> > @@ -255,18 +255,19 @@ rte_flow_ops_get(uint16_t port_id, struct
> > rte_flow_error *error)
> >
> > if (unlikely(!rte_eth_dev_is_v
The fstack will use secondary process to access the memory of
eth_dev_ops , and it wants to get the info of dev, but hinic
driver does not initialized it when in secondary process.
Fixes: 66f64dd6dc86 ("net/hinic: fix secondary process")
Cc: sta...@dpdk.org
Signed-off-by: Guoyang Zhou
---
driver
On 3/15/21 10:54 AM, Thomas Monjalon wrote:
> 15/03/2021 08:18, Andrew Rybchenko:
>> On 3/12/21 8:46 PM, Thomas Monjalon wrote:
>>> --- a/lib/librte_ethdev/rte_flow.c
>>> +++ b/lib/librte_ethdev/rte_flow.c
>>> @@ -255,18 +255,19 @@ rte_flow_ops_get(uint16_t port_id, struct
>>> rte_flow_error *erro
15/03/2021 09:43, Andrew Rybchenko:
> On 3/15/21 10:54 AM, Thomas Monjalon wrote:
> > 15/03/2021 08:18, Andrew Rybchenko:
> >> On 3/12/21 8:46 PM, Thomas Monjalon wrote:
> >>> --- a/lib/librte_ethdev/rte_flow.c
> >>> +++ b/lib/librte_ethdev/rte_flow.c
> >>> @@ -255,18 +255,19 @@ rte_flow_ops_get(ui
The configuration of FDIR input set should not be set
during flow validate. It should be set when flow create.
Signed-off-by: Murphy Yang
---
drivers/net/i40e/i40e_ethdev.h | 1 +
drivers/net/i40e/i40e_fdir.c | 88 +++
drivers/net/i40e/i40e_flow.c | 95 +++---
On 3/15/21 11:55 AM, Thomas Monjalon wrote:
> 15/03/2021 09:43, Andrew Rybchenko:
>> On 3/15/21 10:54 AM, Thomas Monjalon wrote:
>>> 15/03/2021 08:18, Andrew Rybchenko:
On 3/12/21 8:46 PM, Thomas Monjalon wrote:
> --- a/lib/librte_ethdev/rte_flow.c
> +++ b/lib/librte_ethdev/rte_flow.c
15/03/2021 10:08, Andrew Rybchenko:
> On 3/15/21 11:55 AM, Thomas Monjalon wrote:
> > 15/03/2021 09:43, Andrew Rybchenko:
> >> On 3/15/21 10:54 AM, Thomas Monjalon wrote:
> >>> 15/03/2021 08:18, Andrew Rybchenko:
> On 3/12/21 8:46 PM, Thomas Monjalon wrote:
> > --- a/lib/librte_ethdev/rte_
This series adds support for block cipher DIGEST_ENCRYPTED mode in
OCTEON TX, OCTEON TX2 PMDs and sample unit test application.
Tejasree Kondoj (2):
common/cpt: support DIGEST_ENCRYPTED mode
test/crypto: support block cipher DIGEST_ENCRYPTED mode
app/test/test_cryptodev_aes_test_vectors.h
Adding support for DIGEST_ENCRYPTED mode.
Signed-off-by: Tejasree Kondoj
---
doc/guides/cryptodevs/features/octeontx.ini | 1 +
doc/guides/cryptodevs/features/octeontx2.ini | 1 +
doc/guides/rel_notes/release_21_05.rst| 8
drivers/common/cpt/cpt_mcode_defines.h| 7 +++
Adding support for block cipher DIGEST_ENCRYPTED mode.
Signed-off-by: Tejasree Kondoj
---
app/test/test_cryptodev_aes_test_vectors.h | 589 +
app/test/test_cryptodev_blockcipher.c | 95 +++-
app/test/test_cryptodev_blockcipher.h | 10 +
3 files changed, 682 insert
Removing redundant field in a union.
Signed-off-by: Tejasree Kondoj
---
drivers/crypto/octeontx2/otx2_ipsec_po.h | 1 -
1 file changed, 1 deletion(-)
diff --git a/drivers/crypto/octeontx2/otx2_ipsec_po.h
b/drivers/crypto/octeontx2/otx2_ipsec_po.h
index 8a672a38ea..eda9f19738 100644
--- a/drive
This series adds lookaside IPsec UDP encapsulation and transport mode support.
The functionality has been tested with ipsec-secgw application running in
lookaside protocol offload mode.
Tejasree Kondoj (3):
crypto/octeontx2: add UDP encapsulation support
examples/ipsec-secgw: add UDP encapsula
Adding UDP encapsulation support for IPsec in
lookaside protocol mode.
Signed-off-by: Tejasree Kondoj
---
doc/guides/cryptodevs/octeontx2.rst | 1 +
doc/guides/rel_notes/release_21_05.rst| 5 +++
drivers/crypto/octeontx2/otx2_cryptodev_sec.c | 40 ++-
3 files
Adding lookaside IPsec UDP encapsulation support
for NAT traversal.
Added --udp-encap option for application to specify
if UDP encapsulation need to be enabled.
Example secgw command with UDP encapsultation enabled:
-c 0x1 -- -P -p 0x1 --config "(0,0,0)" -f ep0.cfg --udp-encap
Signed-off-by: Teja
Adding support for IPv4 lookaside IPsec transport mode.
Signed-off-by: Tejasree Kondoj
---
doc/guides/cryptodevs/octeontx2.rst | 1 +
drivers/crypto/octeontx2/otx2_cryptodev_ops.c | 7 +-
drivers/crypto/octeontx2/otx2_cryptodev_sec.c | 110 ++
drivers/crypto/octeont
On Fri, Mar 12, 2021 at 07:17:09PM +0100, Thomas Monjalon wrote:
> The main intent of this series is to provide a nice help
> for the --log-level option.
> More patches are added to improve options help in general.
>
>
> v3:
> - fix use of RTE_LOG_MAX
> - accept (with warning) log level h
On 08/03/2021 18:44, Jerin Jacob wrote:
> On Sun, Feb 21, 2021 at 3:41 AM wrote:
>>
>> From: Pavan Nikhilesh
>>
>> Fix ABI breakage due to event vector configuration by moving
>> the vector configuration into a new structure and having a separate
>> function for enabling the vector config on a
On Fri, Mar 12, 2021 at 02:20:06PM -0800, Tyler Retzlaff wrote:
> Introduce a meson option enable_driver_sdk when true installs internal
> driver headers for ethdev. this allows drivers that do not depend on
> stable api/abi to be built external to the dpdk source tree.
>
> Signed-off-by: Tyler Re
On Thu, Mar 11, 2021 at 7:43 AM Wang, Haiyue wrote:
> Like kernel use macro to do pio and mmio, maybe we can also to do so for
> making code clean:
>
> https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/lib/iomap.c
>
> #define IO_COND(addr, is_pio, is_mmio) do {
On 12/03/2021 18:17, Thomas Monjalon wrote:
> The option --log-level was not completely described in the usage text,
> and it was difficult to guess the names of the log types and levels.
>
> A new value "help" is accepted after --log-level to give more details
> about the syntax and listing th
Hi Vladimir,
> > + /* Add IPv4 and IPv6 hops to one array depending on type. */
> > + for (i = 0; i < nb_rx; i++) {
> > + if (type_arr[i])
> > + nh = (uint16_t)hopsv4[ipv4_arr_assem++];
> > + else
> > + nh = (uint16_t)hopsv6[ipv6_arr_as
On Mon, Mar 15, 2021 at 10:19:47AM +, Kinsella, Ray wrote:
>
>
> On 12/03/2021 18:17, Thomas Monjalon wrote:
> > The option --log-level was not completely described in the usage text,
> > and it was difficult to guess the names of the log types and levels.
> >
> > A new value "help" is accep
On 15/03/2021 10:31, Bruce Richardson wrote:
> On Mon, Mar 15, 2021 at 10:19:47AM +, Kinsella, Ray wrote:
>>
>>
>> On 12/03/2021 18:17, Thomas Monjalon wrote:
>>> The option --log-level was not completely described in the usage text,
>>> and it was difficult to guess the names of the log typ
On 3/15/21 12:40 PM, Bruce Richardson wrote:
> On Fri, Mar 12, 2021 at 07:17:09PM +0100, Thomas Monjalon wrote:
>> The main intent of this series is to provide a nice help
>> for the --log-level option.
>> More patches are added to improve options help in general.
>>
>>
>> v3:
>> - fix use of R
15/03/2021 11:42, Kinsella, Ray:
>
> On 15/03/2021 10:31, Bruce Richardson wrote:
> > On Mon, Mar 15, 2021 at 10:19:47AM +, Kinsella, Ray wrote:
> >>
> >>
> >> On 12/03/2021 18:17, Thomas Monjalon wrote:
> >>> The option --log-level was not completely described in the usage text,
> >>> and it
libpcap is already found and registered as a dependency by meson, and
the dependency is already correctly used in librte_port. This line is
just unnecessary.
It also has the side effect of messing with the meson link line: dpdk
link will be declared twice: manually and then through pkg-config. If
On 1/11/21 3:50 AM, Xia, Chenbo wrote:
> Hi Maxime,
>
>> -Original Message-
>> From: Maxime Coquelin
>> Sent: Tuesday, December 22, 2020 12:15 AM
>> To: dev@dpdk.org; Xia, Chenbo ; amore...@redhat.com;
>> david.march...@redhat.com; olivier.m...@6wind.com
>> Cc: Maxime Coquelin
>> Subj
Currently the l3fwd sample app supports LPM and EM lookup methods this
patchset implements the FIB library as another lookup method for l3fwd.
Instead of adding an individual flag for FIB, a new flag '--lookup' has
been added that allows the user to select their desired lookup method.
The flags '-E
The IPv6 subnets used were not within the 2001:200::/48 subnet
Changed to 2001:200:0:{0-7}::/64 where 0-7 is the port ID
Fixes: 37afe381bde4 ("examples/l3fwd: use reserved IP addresses")
Signed-off-by: Conor Walsh
Acked-by: Vladimir Medvedkin
---
examples/l3fwd/l3fwd_lpm.c | 26 +++
To prevent code duplication from the addition of lookup methods
the routes specified in lpm should be moved to a common header.
Signed-off-by: Conor Walsh
Acked-by: Konstantin Ananyev
Acked-by: Vladimir Medvedkin
---
examples/l3fwd/l3fwd_common_route.h | 48 +++
examples/l3fwd/
The purpose of this commit is to add the necessary function calls
and supporting infrastructure to allow the Forwarding Information Base
(FIB) library to be integrated into the l3fwd sample app.
Instead of adding an individual flag for FIB, a new flag '--lookup' has
been added that allows the user
This patch implements the Forwarding Information Base (FIB) library
in l3fwd using the function calls and infrastructure introduced in
the previous patch.
Signed-off-by: Conor Walsh
Acked-by: Konstantin Ananyev
---
examples/l3fwd/l3fwd_fib.c | 480 -
1 file c
The purpose of this patch is to update the l3fwd user guide to include
the changes proposed in this patchset.
Signed-off-by: Conor Walsh
---
doc/guides/sample_app_ug/l3_forward.rst | 113 +---
1 file changed, 100 insertions(+), 13 deletions(-)
diff --git a/doc/guides/sample_
On 3/13/2021 10:22 PM, Dmitry Kozlyuk wrote:
Networking header shim in Windows EAL conflicts with system headers and
tries to provide POSIX compatibility out of scope for DPDK.
Remove dependency on POSIX headers from libraries supported on Windows,
then replace shim with librte_net with workaroun
> -Original Message-
> From: David Marchand
> Sent: Monday, March 15, 2021 18:20
> To: Wang, Haiyue ; 谢华伟(此时此刻)
>
> Cc: maxime.coque...@redhat.com; Yigit, Ferruh ;
> dev@dpdk.org; Burakov, Anatoly
> ; xuemi...@nvidia.com; gr...@u256.net
> Subject: Re: [dpdk-dev] [PATCH v11 2/2] bus/pci:
Hello Jiawei,
On Fri, 12 Mar 2021 09:32:44 +
"Jiawei(Jonny) Wang" wrote:
> Hi Jan,
>
> > -Original Message-
> > From: Jan Viktorin
> > Sent: Friday, March 12, 2021 12:33 AM
> > To: Jiawei(Jonny) Wang
> > Cc: Slava Ovsiienko ; Asaf Penso
> > ; dev@dpdk.org; Ori Kam
> > Subject: Re
>
>
>
Hi Ferruh,
>
Have you seen the CI reported build errors:
> http://mails.dpdk.org/archives/test-report/2021-March/182361.html
>
> Briefly:
> ./lib/librte_net/rte_net.c:132:7: error: 'IPPROTO_GRE' undeclared
> ./lib/librte_net/rte_net.c:163:7: error: 'IPPROTO_IPIP' undeclared
>
This is becaus
https://bugs.dpdk.org/show_bug.cgi?id=661
Bug ID: 661
Summary: [mlx5] VLAN packets will not do RSS
Product: DPDK
Version: 19.11
Hardware: All
OS: All
Status: UNCONFIRMED
Severity: normal
Priority
https://bugs.dpdk.org/show_bug.cgi?id=661
Ali Alnubani (alia...@nvidia.com) changed:
What|Removed |Added
Resolution|--- |WONTFIX
Status|UNC
Hi,
> -Original Message-
> From: Christian Ehrhardt
> Sent: Wednesday, March 10, 2021 3:37 PM
> To: sta...@dpdk.org
> Cc: dev@dpdk.org; Abhishek Marathe ;
> Akhil Goyal ; Ali Alnubani ;
> benjamin.wal...@intel.com; David Christensen ;
> hariprasad.govindhara...@intel.com; Hemant Agrawal
>
This roadmap has been integrated in the web page
https://core.dpdk.org/roadmap/#2105
01/03/2021 20:17, Asaf Penso:
> Below is NVIDIA Mellanox's roadmap for DPDK21.05, on which we are currently
> working:
>
> rte_flow new APIs:
> ===
> [1]Support a new action offload which pe
The addition of a new driver is added to the web page:
https://core.dpdk.org/roadmap/#2105
04/03/2021 09:30, Jiawen Wu:
> There is Wangxun's roadmap for DPDK 21.05.
>
> Bug fixes:
> [1] fix TXGBE Rx drop statistics
> [2] fix TXGBE packet type
> [3] fix TXGBE IPsec
> [4] fix TXGBE backpla
On 1/11/21 6:39 AM, Xia, Chenbo wrote:
> Hi Maxime,
>
>> -Original Message-
>> From: Maxime Coquelin
>> Sent: Tuesday, December 22, 2020 12:15 AM
>> To: dev@dpdk.org; Xia, Chenbo ; amore...@redhat.com;
>> david.march...@redhat.com; olivier.m...@6wind.com
>> Cc: Maxime Coquelin
>> Subj
Update base driver to provide functionality required by vDPA driver.
Factor out helper functions to be shared by net and vDPA drivers.
v2:
- fix windows build breakage - do not build common/sfc_efx in the case
of windows
- remove undefined efx_virtio_* functions from version.map (since
EF
From: Vijay Srivastava
Add an API to query the virtqueue doorbell offset in the BAR for a VI.
For vDPA, the virtio net driver notifies the device directly by writing
doorbell. This API would be invoked from vDPA client driver.
Signed-off-by: Vijay Srivastava
Signed-off-by: Andrew Rybchenko
---
From: Vijay Srivastava
In the vDPA mode, only data path is offloaded in the hardware and
control path still goes through the hypervisor and it configures
virtqueues via vDPA driver so new virtqueue APIs are required.
Implement virtio init/fini and virtqueue create/destroy APIs.
Signed-off-by: V
From: Vijay Kumar Srivastava
Add an API to verify virtio features supported by device.
Signed-off-by: Vijay Kumar Srivastava
Signed-off-by: Andrew Rybchenko
---
drivers/common/sfc_efx/base/efx.h | 7
drivers/common/sfc_efx/base/efx_impl.h | 2 +
drivers/common/sfc_efx/base
From: Vijay Kumar Srivastava
Add EFSYS_HAS_UINT64 build dependency on EFSYS_OPT_VIRTIO.
virtio features are represented as bitmask in 64-bit unsigned
integer.
Signed-off-by: Vijay Kumar Srivastava
Signed-off-by: Andrew Rybchenko
---
drivers/common/sfc_efx/base/efx_check.h | 3 +++
1 file chan
From: Vijay Kumar Srivastava
Add an API to get virtio features supported by device.
Signed-off-by: Vijay Kumar Srivastava
Signed-off-by: Andrew Rybchenko
---
drivers/common/sfc_efx/base/efx.h | 14 ++
drivers/common/sfc_efx/base/efx_impl.h | 2 +
drivers/common/sfc_efx/base/
From: Vijay Kumar Srivastava
Driver would be probed only for the net device class.
Signed-off-by: Vijay Kumar Srivastava
Signed-off-by: Andrew Rybchenko
---
doc/guides/nics/sfc_efx.rst | 8
drivers/net/sfc/sfc.h| 1 +
drivers/net/sfc/sfc_ethdev.c | 7 +++
drivers/net/sfc
From: Vijay Kumar Srivastava
Device class argument would be used to select compatible driver.
Driver probe would be skipped for incompatible device class.
Signed-off-by: Vijay Kumar Srivastava
Signed-off-by: Andrew Rybchenko
---
drivers/common/sfc_efx/sfc_efx.c | 49
On 3/14/21 3:36 AM, Ferruh Yigit wrote:
> On 3/11/2021 11:03 AM, Andrew Rybchenko wrote:
>> From: Vijay Kumar Srivastava
>>
>> Move function to get efx family from net driver into common driver.
>>
>> Signed-off-by: Vijay Kumar Srivastava
>> Signed-off-by: Andrew Rybchenko
>
> <...>
>
>> diff --
From: Vijay Kumar Srivastava
Move function to get efx family from net driver into common driver.
Signed-off-by: Vijay Kumar Srivastava
Signed-off-by: Andrew Rybchenko
---
drivers/common/meson.build | 2 +-
drivers/common/sfc_efx/meson.build | 5 +++
drivers/common/sfc_efx/sfc_efx.c
On Wed, Mar 10, 2021 at 6:37 PM 谢华伟(此时此刻) wrote:
>
> virtio PMD assumes legacy device only supports PIO(port-mapped) BAR
> resource. This is wrong. As we need to create lots of devices, adn PIO
> resource on x86 is very limited, we expose MMIO(memory-mapped I/O) BAR.
>
> Kernel supports both PIO a
10/03/2021 23:20, Ferruh Yigit:
> Signed-off-by: Ferruh Yigit
> ---
> v2:
> * there won't be a new driver for dlb2.5
> * reword thash library support
Applied with minor updates for sorting things, thanks.
On 2021-03-07 14:04, Jerin Jacob wrote:
> On Fri, Feb 26, 2021 at 1:31 PM Mattias Rönnblom
> wrote:
>> On 2021-02-25 13:32, Jerin Jacob wrote:
>>> On Fri, Feb 19, 2021 at 12:00 AM Mattias Rönnblom
>>> wrote:
The purpose of the event dispatcher is primarily to decouple different
parts of
> -Original Message-
> From: dev On Behalf Of Mattias Rönnblom
> Sent: Monday, March 15, 2021 2:45 PM
> To: Jerin Jacob
> Cc: Jerin Jacob ; dpdk-dev ; Richardson,
> Bruce
> Subject: Re: [dpdk-dev] [RFC] eventdev: introduce event dispatcher
>
> On 2021-03-07 14:04, Jerin Jacob wrote:
> >
This series optimizes the cache usage of virtqueue struct,
by making a "fake" mbuf being dynamically allocated in Rx
virtnet struct, by removing a useless virtuque pointer
into the virtnet structs and by moving a few fields
to pack holes.
With these 3 patches, the virtqueue struct size goes from
5
This patch improves the error path of virtio_init_queue(),
by cleaning in reversing order all resources that have
been allocated.
Suggested-by: Chenbo Xia
Signed-off-by: Maxime Coquelin
---
drivers/net/virtio/virtio_ethdev.c | 19 +--
1 file changed, 13 insertions(+), 6 deletion
Vrings are part of the virtqueues, so we don't need
to have a pointer to it in Vrings descriptions.
Instead, let's just subtract from its offset to
calculate virtqueue address.
Signed-off-by: Maxime Coquelin
Reviewed-by: Chenbo Xia
---
drivers/net/virtio/virtio_ethdev.c| 36 +++
While it is worth clarifying whether the fake mbuf
in virtnet_rx struct is really necessary, it is sure
that it heavily impacts cache usage by being part of
the struct. Indeed, it uses two cachelines, and
requires alignement on a cacheline.
Before this series, it means it took 120 bytes in
virtnet
This patch optimizes packing of the virtuqueue
struct by moving fields around to fill holes.
Offset field is not used and so can be removed.
Signed-off-by: Maxime Coquelin
Reviewed-by: Chenbo Xia
---
drivers/net/virtio/virtqueue.h | 18 +-
1 file changed, 9 insertions(+), 9 del
On 2021/3/15 18:19, David Marchand wrote:
#else
#define IO_COND(addr, is_pio, is_mmio) do { \
is_mmio; \
} while (0)
#endif
We should not just copy/paste kernel code.
Plus here, this seems a bit overkill.
And there are other parts in thi
Support the PMD power management API in MLX5 driver.
The monitor policy of this API puts a CPU core to sleep until
a data in some monitored memory address is changed by the NIC.
Implement the get_monitor_addr function to return an address
of a CQE owner bit to monitor the arrival of a new packet.
use UINT64_MAX instead of -1ULL when manipulating uint64_t masks and
initializing sentinel values.
some compilers generate a warning when applying a '-' to an unsigned
literal so avoid this by initializing with unsigned preprocessor
definitions where appropriate.
Signed-off-by: Tyler Retzlaff
--
> Subject: Re: [PATCH v4 1/2] eal: error number enhancement for thread TLS
> API
>
> On Wed, Mar 10, 2021 at 02:48:55PM +0200, Tal Shnaiderman wrote:
> > add error number reporting to rte_errno in all functions in the
> > rte_thread_tls_* API.
> >
> > Suggested-by: Anatoly Burakov
> > Signed-off-
On Mon, Mar 15, 2021 at 4:20 PM Maxime Coquelin
wrote:
> @@ -604,15 +604,22 @@ virtio_init_queue(struct rte_eth_dev *dev, uint16_t
> queue_idx)
>
> if (VIRTIO_OPS(hw)->setup_queue(hw, vq) < 0) {
> PMD_INIT_LOG(ERR, "setup_queue failed");
> - return -EINVAL;
>
On 3/15/21 4:38 PM, David Marchand wrote:
> On Mon, Mar 15, 2021 at 4:20 PM Maxime Coquelin
> wrote:
>> @@ -604,15 +604,22 @@ virtio_init_queue(struct rte_eth_dev *dev, uint16_t
>> queue_idx)
>>
>> if (VIRTIO_OPS(hw)->setup_queue(hw, vq) < 0) {
>> PMD_INIT_LOG(ERR, "set
On Mon, Mar 15, 2021 at 4:20 PM Maxime Coquelin
wrote:
> @@ -550,10 +551,18 @@ virtio_init_queue(struct rte_eth_dev *dev, uint16_t
> queue_idx)
> goto free_hdr_mz;
> }
>
> + fake_mbuf = malloc(sizeof(*fake_mbuf));
> + if (!fake_m
On Mon, Mar 15, 2021 at 4:20 PM Maxime Coquelin
wrote:
>
> This patch optimizes packing of the virtuqueue
virtqueue ? and same typo in the title.
> struct by moving fields around to fill holes.
>
> Offset field is not used and so can be removed.
>
> Signed-off-by: Maxime Coquelin
> Reviewed-by:
When parsing the virtio net header and packet header for dequeue offload,
we need to perform sanity check on the packet header to ensure:
- No out-of-boundary memory access.
- The packet header and virtio_net header are valid and aligned.
Fixes: d0cf91303d73 ("vhost: add Tx offload capabilitie
Hi, Jan
Yes, bullet [4] explicitly requires to unbind VFs, and detach the netdevs from
the mlx5_core driver.
Otherwise, kernel driver refuses to be configured with switchdev mode in [5].
So, [4] can't be skipped.
After setting swithdev mode, VFs can be bound back (if it is needed, and these
one
On 3/15/2021 1:58 PM, Andrew Rybchenko wrote:
Update base driver to provide functionality required by vDPA driver.
Factor out helper functions to be shared by net and vDPA drivers.
v2:
- fix windows build breakage - do not build common/sfc_efx in the case
of windows
- remove undefined e
On Mon, 15 Mar 2021 11:52:13 +0100
Thomas Monjalon wrote:
> 15/03/2021 11:42, Kinsella, Ray:
> >
> > On 15/03/2021 10:31, Bruce Richardson wrote:
> > > On Mon, Mar 15, 2021 at 10:19:47AM +, Kinsella, Ray wrote:
> > >>
> > >>
> > >> On 12/03/2021 18:17, Thomas Monjalon wrote:
> > >>> Th
Hello Salva,
On Mon, 15 Mar 2021 15:53:51 +
Slava Ovsiienko wrote:
> Hi, Jan
>
> Yes, bullet [4] explicitly requires to unbind VFs, and detach the netdevs
> from the mlx5_core driver.
> Otherwise, kernel driver refuses to be configured with switchdev mode in [5].
> So, [4] can't be skippe
On Mon, Mar 15, 2021 at 4:52 PM Xiao Wang wrote:
>
> When parsing the virtio net header and packet header for dequeue offload,
> we need to perform sanity check on the packet header to ensure:
> - No out-of-boundary memory access.
> - The packet header and virtio_net header are valid and align
This series adds support for VXLAN and NVGRE encap as a sample actions with the
proper
documentation, this series depends on [1] for the documentation part.
[1]
http://patches.dpdk.org/project/dpdk/patch/1615774238-51875-1-git-send-email-jiaw...@nvidia.com/
Jiawei Wang (1):
app/testpmd: sto
From: Jiawei Wang
With the current code the VXLAN/NVGRE parsing routine
stored the configuration of the header on stack, this
might lead to overwriting the data on the stack.
This patch stores the external data of vxlan and nvgre encap
into global data as a pre-step to supporting vxlan and nvgre
Add support for VXLAN encap as a sample action
and validate it.
Signed-off-by: Salem Sol
---
drivers/net/mlx5/mlx5_flow_dv.c | 11 +++
1 file changed, 11 insertions(+)
diff --git a/drivers/net/mlx5/mlx5_flow_dv.c b/drivers/net/mlx5/mlx5_flow_dv.c
index 1a74d5ac2b..4b2db47e39 100644
---
Add support for rte_flow_action_vxlan_encap as a sample action.
The example of test-pmd command:
1. set vxlan ip-version ... vni ... udp-src ...
set raw_encap 1 eth src.../ ipv4.../...
set sample_actions 2 vxlan_encap / port_id id 0 / end
flow create 0 ... pattern eth / end actions
Add support for NVGRE encap as a sample action
and validate it.
Signed-off-by: Salem Sol
---
drivers/net/mlx5/mlx5_flow_dv.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/net/mlx5/mlx5_flow_dv.c b/drivers/net/mlx5/mlx5_flow_dv.c
index 4b2db47e39..590abdc822 100644
--- a/drivers/n
Add support for rte_flow_action_nvge_encap as a sample action.
The example of test-pmd command:
1. set nvgre ip-version ... tni ... ip-src ... ip-dst ...
set raw_encap 1 eth src... / ipv4... /...
set sample_actions 2 nvgre / port_id id 0 / end
flow create 0 ... pattern eth / end acti
Update documentation for sample action usage in testpmd utilizing
rte_flow_action_vxlan_encap and rte_flow_action_nvgre_encap and
show the command line example.
Signed-off-by: Salem Sol
---
doc/guides/testpmd_app_ug/testpmd_funcs.rst | 21 +
1 file changed, 21 insertions(+)
Updates the documentation with the added support for sample actions VXLAN
and NVGRE encap in E-Switch steering flow.
Signed-off-by: Salem Sol
---
doc/guides/nics/mlx5.rst | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/doc/guides/nics/mlx5.rst b/doc/guides/nics/mlx5.rst
i
From: Jan Viktorin
Signed-off-by: Jan Viktorin
---
doc/guides/nics/mlx5.rst | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/doc/guides/nics/mlx5.rst b/doc/guides/nics/mlx5.rst
index 7c50497fb..0a2dc3dee 100644
--- a/doc/guides/nics/mlx5.rst
+++ b/doc/guides/nics/mlx5.rst
From: Jan Viktorin
The step 4 is a contradiction. It advices to unbind the device from the
mlx5_core which removes the associated system network interface (e.g.
eth0). In the step 5, the same system network interface (e.g. eth0) is
required to exist.
Signed-off-by: Jan Viktorin
---
doc/guides/
On 3/15/21 4:50 PM, David Marchand wrote:
> On Mon, Mar 15, 2021 at 4:20 PM Maxime Coquelin
> wrote:
>> @@ -550,10 +551,18 @@ virtio_init_queue(struct rte_eth_dev *dev, uint16_t
>> queue_idx)
>> goto free_hdr_mz;
>> }
>>
>> + fake_mbuf = ma
> -Original Message-
> From: dev On Behalf Of Savinay Dharmappa
> Sent: Tuesday, March 9, 2021 4:10 PM
> To: Singh, Jasvinder ; Dumitrescu, Cristian
> ; dev@dpdk.org
> Cc: Dharmappa, Savinay
> Subject: [dpdk-dev] [PATCH v2] sched : Initialize tc ov watermark.
>
> tc ov watermark is ini
Vrings are part of the virtqueues, so we don't need
to have a pointer to it in Vrings descriptions.
Instead, let's just subtract from its offset to
calculate virtqueue address.
Signed-off-by: Maxime Coquelin
Reviewed-by: Chenbo Xia
---
drivers/net/virtio/virtio_ethdev.c| 36 +++
This series optimizes the cache usage of virtqueue struct,
by making a "fake" mbuf being dynamically allocated in Rx
virtnet struct, by removing a useless virtuque pointer
into the virtnet structs and by moving a few fields
to pack holes.
With these 3 patches, the virtqueue struct size goes from
5
This patch improves the error path of virtio_init_queue(),
by cleaning in reversing order all resources that have
been allocated.
Suggested-by: Chenbo Xia
Signed-off-by: Maxime Coquelin
---
drivers/net/virtio/virtio_ethdev.c | 15 ++-
1 file changed, 10 insertions(+), 5 deletions(-)
While it is worth clarifying whether the fake mbuf
in virtnet_rx struct is really necessary, it is sure
that it heavily impacts cache usage by being part of
the struct. Indeed, it uses two cachelines, and
requires alignment on a cacheline.
Before this series, it means it took 120 bytes in
virtnet_
This patch optimizes packing of the virtqueue
struct by moving fields around to fill holes.
Offset field is not used and so can be removed.
Signed-off-by: Maxime Coquelin
Reviewed-by: Chenbo Xia
---
drivers/net/virtio/virtqueue.h | 18 +-
1 file changed, 9 insertions(+), 9 dele
On Mon, Mar 15, 2021 at 5:46 PM Maxime Coquelin
wrote:
> @@ -612,6 +622,8 @@ virtio_init_queue(struct rte_eth_dev *dev, uint16_t
> queue_idx)
>
> clean_vq:
> hw->cvq = NULL;
> + rte_free(fake_mbuf);
> +free_sw_ring:
> rte_free(sw_ring);
> free_hdr_mz:
> rte_memzone
On 3/1/2021 4:38 PM, Stephen Hemminger wrote:
On Mon, 1 Mar 2021 11:10:01 +0300
Igor Ryzhov wrote:
Stephen,
No, I don't have a better proposal, but I think it is not correct to change
the behavior of KNI (making link down without a real response).
Even though we know that communicating with u
On Mon, Mar 15, 2021 at 5:46 PM Maxime Coquelin
wrote:
>
> This series optimizes the cache usage of virtqueue struct,
> by making a "fake" mbuf being dynamically allocated in Rx
> virtnet struct, by removing a useless virtuque pointer
> into the virtnet structs and by moving a few fields
> to pack
On 15/03/2021 15:59, Stephen Hemminger wrote:
> On Mon, 15 Mar 2021 11:52:13 +0100
> Thomas Monjalon wrote:
>
>> 15/03/2021 11:42, Kinsella, Ray:
>>>
>>> On 15/03/2021 10:31, Bruce Richardson wrote:
On Mon, Mar 15, 2021 at 10:19:47AM +, Kinsella, Ray wrote:
>
>
> On 12
1 - 100 of 153 matches
Mail list logo