When running checkpatch.sh, it generates the following error
on some linux distributions(like Debian) with Dash as the
default shell interpreter.
trap: SIGINT: bad trap
The fix is to replace SIGINT with INT signal, it works for
both bash and dash.
Fixes: 4bec48184e ("devtools: add checks for ABI
From: "Charles (Chas) Williams"
>From the Intel Ethernet Controller X710/XXV710/XL710 Specifiction
Update:
Starting from NVM 5.02, if the Set Local LLDP MIB command is
received while the DCBx specific agent is stopped, the command
returns an EPERM error. If the command is received wh
This reverts commit 7546dc4a1331340ecb665af9af0a005bb8b657c8.
In i40e FDIR PMD code for checking programming status,
when the action of add FDIR filter is ok, i40e NIC will
not write back to programming status descriptor, so if
PMD code check DD is not done after period of time dealy,
it means the
This reverts commit 7546dc4a1331340ecb665af9af0a005bb8b657c8.
In i40e FDIR PMD code for checking programming status,
when the action of add FDIR filter is ok, i40e NIC will
not write back to programming status descriptor, so if
PMD code check DD is not done after period of time dealy,
it means the
In i40e FDIR PMD code for checking programming status,
when the action of add FDIR filter is ok, i40e NIC will
not write back to programming status descriptor, so if
PMD code check DD is not done after period of time dealy,
it means the add or remove filter action is ok. It only write
back descript
On Mon, Jul 30, 2018 at 10:43:37AM +0200, Maxime Coquelin wrote:
> On 07/30/2018 10:28 AM, Tiwei Bie wrote:
> > Add the missing param "server" to param string.
> > Also add the missing spaces after params.
> >
> > Fixes: bd8f50a45d0f ("net/virtio-user: support server mode")
> > Cc: sta...@dpdk.org
Hi,
Thanks for explaining the use case. I now understand and I agree that replacing
stale entries during insertion is an interesting and useful addition to this
library.
My concern is still that it may be not a good practice to expose the bucketized
structure of the rte_hash. For example, in
Hi
> -Original Message-
> From: Lu, Wenzhuo
> Sent: Wednesday, August 1, 2018 09:19
> To: Li, Xiaoyun ; Wu, Jingjing
> Cc: dev@dpdk.org; sta...@dpdk.org
> Subject: RE: [PATCH] net/avf: fix missing offload capabilities
>
> Hi Xiaoyun,
>
>
> > -Original Message-
> > From: Li, Xia
Hi Xiaoyun,
> -Original Message-
> From: Li, Xiaoyun
> Sent: Wednesday, July 25, 2018 3:15 PM
> To: Lu, Wenzhuo ; Wu, Jingjing
>
> Cc: dev@dpdk.org; Li, Xiaoyun ; sta...@dpdk.org
> Subject: [PATCH] net/avf: fix missing offload capabilities
>
> There are several tx/rx offload capabilitie
> -Original Message-
> From: Coyle, David
> Sent: Tuesday, July 31, 2018 10:25 PM
> To: Van Haaren, Harry ; dev@dpdk.org
> Cc: Richardson, Bruce ; sta...@dpdk.org;
> tho...@monjalon.net; Xing, Beilei ; Zhang, Qi Z
>
> Subject: RE: [PATCH v2] net/i40e: fix avx2 driver check for rx rearm
When running testpmd with an mlx5 device and then executing at testpmd
prompt in a raw: "port start all" followed by "port stop all"
a new file named /var/tmp/net_mlx5_ is created as a result
of creating a new unix domain socket (used for communication between
the primary and secondary processes).
Hi Reshma,
01/08/2018 00:18, Reshma Pattan:
> v10: fixed clang compiler issues and freed latency stats memzone in latency
> stats unit tests.
> v9: rebased ontop of latest autotest changes and added new tests to the
> autotest list
> v8: renamed commit headline and freed the metrics memzone for b
Hi,
> -Original Message-
> From: Thomas Monjalon [mailto:tho...@monjalon.net]
> Sent: Tuesday, July 31, 2018 6:06 PM
> To: Pattan, Reshma ; Somarowthu, Naga SureshX
>
> Cc: dev@dpdk.org; Burakov, Anatoly ;
> Parthasarathy, JananeeX M
> Subject: Re: [dpdk-dev] [PATCH v9 3/5] test: add uni
From: Reshma Pattan
added bitrate, latency and pdump lib unit tests to
autotest list.
Signed-off-by: Reshma Pattan
---
test/test/autotest_data.py | 18 ++
1 file changed, 18 insertions(+)
diff --git a/test/test/autotest_data.py b/test/test/autotest_data.py
index 3f856ff57..2f7
From: Naga Suresh Somarowthu
Unit Test Cases added for latencystats library.
Signed-off-by: Naga Suresh Somarowthu
Reviewed-by: Reshma Pattan
---
test/test/Makefile| 1 +
test/test/test_latencystats.c | 229 ++
2 files changed, 230 inserti
From: Naga Suresh Somarowthu
Unit Test Cases for BitRate library.
Signed-off-by: Naga Suresh Somarowthu
Reviewed-by: Reshma Pattan
Reviewed-by: Remy Horton
---
test/test/Makefile| 1 +
test/test/test_bitratestats.c | 229 ++
2 files chang
From: Naga Suresh Somarowthu
Unit test cases are added for pdump library.
Primary process will act as server, forks a child secondary process.
Secondary process acts as client.
Server will do pdump init to serve any pdump client requests.
Server will create a vdev, send/receive packets continuous
From: Naga Suresh Somarowthu
Added ring pmd based packet rx/tx helper functions
for verifying Latency, Bitrate and pdump lib UTs.
Signed-off-by: Naga Suresh Somarowthu
Reviewed-by: Reshma Pattan
Reviewed-by: Anatoly Burakov
---
test/test/Makefile| 1 +
test/test/sample_pack
From: Reshma Pattan
1/5: add helper functions for tests using ring-PMD Rx/Tx
2/5: unit test cases added for bitrate library
3/5: unit test cases added for latencystats library
4/5: unit test cases added for pdump library
5/5: added new unit tests to autotest list
Patches 2/5,3/5 depends on 1/5
P
From: Hyong Youb Kim
The NIC persists the vxlan port number across vNIC init/de-init
(e.g. restart testpmd). So, explicitly reset the setting to the
default value (4789) as part of the initialization.
Fixes: 8a4efd17410c ("net/enic: add handlers to add/delete vxlan port number")
Signed-off-by:
From: Hyong Youb Kim
The NIC persists the vxlan port number across vNIC init/de-init
(e.g. restart testpmd). So, explicitly reset the setting to the
default value (4789) as part of the initialization.
Fixes: 8a4efd17410c ("net/enic: add handlers to add/delete vxlan port number")
Signed-off-by:
On Tue, 31 Jul 2018 18:48:40 +0200
Adrien Mazarguil wrote:
> On Tue, Jul 31, 2018 at 09:30:54AM -0700, Stephen Hemminger wrote:
> > Declaring variables as register in C is a leftover from an earlier
> > era (like cassette tape decks in cars).
>
> I don't agree here. It's a hint for compilers a
31/07/2018 18:40, Reshma Pattan:
> From: Naga Suresh Somarowthu
>
> Unit Test Cases added for latencystats library.
>
> Signed-off-by: Naga Suresh Somarowthu
> Reviewed-by: Reshma Pattan
> ---
Compilation error with clang:
> + struct rte_metric_name names[NUM_STATS] = { 0 };
test_latenc
31/07/2018 17:09, Dumitrescu, Cristian:
> From: Thomas Monjalon [mailto:tho...@monjalon.net]
> >
> > Cristian, review please?
> >
> > 10/07/2018 17:33, Ben Shelton:
> > > The node parent update API function may be used to update the
> > > priority/weight of an existing node. Update the documenta
On Tue, Jul 31, 2018 at 09:30:54AM -0700, Stephen Hemminger wrote:
> Declaring variables as register in C is a leftover from an earlier
> era (like cassette tape decks in cars).
I don't agree here. It's a hint for compilers and developers that the
address of such variables won't be needed (and can
Hi Thomas,
> -Original Message-
> From: Thomas Monjalon [mailto:tho...@monjalon.net]
> Sent: Tuesday, July 31, 2018 3:57 PM
> To: Somarowthu, Naga SureshX
> Cc: dev@dpdk.org; Horton, Remy ; Pattan, Reshma
>
> Subject: Re: [dpdk-dev] [PATCH v8 0/4] add unit tests for bitrate, latency and
From: Reshma Pattan
added bitrate, latency and pdump lib unit tests to
autotest list.
Signed-off-by: Reshma Pattan
---
test/test/autotest_data.py | 18 ++
1 file changed, 18 insertions(+)
diff --git a/test/test/autotest_data.py b/test/test/autotest_data.py
index 3f856ff57..2f7
From: Naga Suresh Somarowthu
Unit Test Cases for BitRate library.
Signed-off-by: Naga Suresh Somarowthu
Reviewed-by: Reshma Pattan
Reviewed-by: Remy Horton
---
test/test/Makefile| 1 +
test/test/test_bitratestats.c | 229 ++
2 files chang
From: Naga Suresh Somarowthu
Unit test cases are added for pdump library.
Primary process will act as server, forks a child secondary process.
Secondary process acts as client.
Server will do pdump init to serve any pdump client requests.
Server will create a vdev, send/receive packets continuous
From: Naga Suresh Somarowthu
Unit Test Cases added for latencystats library.
Signed-off-by: Naga Suresh Somarowthu
Reviewed-by: Reshma Pattan
---
test/test/Makefile| 1 +
test/test/test_latencystats.c | 216 ++
2 files changed, 217 inserti
From: Naga Suresh Somarowthu
Added ring pmd based packet rx/tx helper functions
for verifying Latency, Bitrate and pdump lib UTs.
Signed-off-by: Naga Suresh Somarowthu
Reviewed-by: Reshma Pattan
Reviewed-by: Anatoly Burakov
---
test/test/Makefile| 1 +
test/test/sample_pack
From: Reshma Pattan
1/5: add helper functions for tests using ring-PMD Rx/Tx
2/5: unit test cases added for bitrate library
3/5: unit test cases added for latencystats library
4/5: unit test cases added for pdump library
5/5: added new unit tests to autotest list
Patches 2/5,3/5 depends on 1/5
P
As far as I can tell, DPDK does not destroy secondary process fbarray files -
i.e. those whose names end with "_". With enough secondary processes and
memory usage per application, and after enough repeat executions, these can
take up a significant amount of space. Is the user expected to clean
On Tue, 31 Jul 2018 16:01:19 +
"Mcnamara, John" wrote:
> > -Original Message-
> > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Stephen Hemminger
> > Sent: Tuesday, July 31, 2018 4:14 PM
> > To: nhor...@tuxdriver.com
> > Cc: dev@dpdk.org; Stephen Hemminger
> > Subject: [dpdk-d
The register keyword is redundant with modern compilers.
Signed-off-by: Stephen Hemminger
---
drivers/net/mlx5/mlx5_mr.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/mlx5/mlx5_mr.c b/drivers/net/mlx5/mlx5_mr.c
index 1d1bcb5fe028..b8fb6c0b9f0d 100644
--- a/drive
No need for register keyword with modern compilers.
Signed-off-by: Stephen Hemminger
---
drivers/net/ark/ark_ethdev_rx.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ark/ark_ethdev_rx.c b/drivers/net/ark/ark_ethdev_rx.c
index 16f0d11ecac5..19e10955103e 1006
Signed-off-by: Stephen Hemminger
---
drivers/net/mlx4/mlx4_mr.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/mlx4/mlx4_mr.c b/drivers/net/mlx4/mlx4_mr.c
index d23d3c613ea7..6869cfb6e6ef 100644
--- a/drivers/net/mlx4/mlx4_mr.c
+++ b/drivers/net/mlx4/mlx4_mr.c
@@
Declaring variables as register in C is a leftover from an earlier
era (like cassette tape decks in cars).
Stephen Hemminger (5):
qat: remove redundant C register keyword
qede: remove register from declaraitons
ark: remove register keyword
mlx5: no need for register keyword
mlx4: remove
Modern C compilers do register assignment automatically.
Remove redundant register modifier.
Signed-off-by: Stephen Hemminger
---
drivers/net/qede/qede_rxtx.c | 8
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/net/qede/qede_rxtx.c b/drivers/net/qede/qede_rxtx.c
i
Modern C compilers ignore the register keyword and do automatic
register assignment.
Signed-off-by: Stephen Hemminger
---
drivers/common/qat/qat_qp.c | 10 +-
drivers/crypto/qat/qat_sym.c | 2 +-
2 files changed, 6 insertions(+), 6 deletions(-)
diff --git a/drivers/common/qat/qat_qp.c
This commit adds the missing Rx jumbo frame support advertisement
in Rx offload capabilities.
Signed-off-by: Moti Haimovsky
---
drivers/net/mlx4/mlx4_rxq.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/net/mlx4/mlx4_rxq.c b/drivers/net/mlx4/mlx4_rxq.c
index e8bef1
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Stephen Hemminger
> Sent: Tuesday, July 31, 2018 4:14 PM
> To: nhor...@tuxdriver.com
> Cc: dev@dpdk.org; Stephen Hemminger
> Subject: [dpdk-dev] [PATCH] devtools: check_symbol_change requires bash
>
> The syntax o
The syntax of check_symbol_change uses some bash syntax.
It does not run correctly on Debian where /bin/sh is not the
same as /bin/bash.
Fixes: 4bec48184e33 ("devtools: add checks for ABI symbol addition")
Signed-off-by: Stephen Hemminger
---
devtools/check-symbol-change.sh | 2 +-
1 file change
> -Original Message-
> From: Thomas Monjalon [mailto:tho...@monjalon.net]
> Sent: Tuesday, July 31, 2018 4:06 PM
> To: Dumitrescu, Cristian
> Cc: dev@dpdk.org; Shelton, Benjamin H
> Subject: Re: [dpdk-dev] [PATCH] ethdev: Clarify usage of TM node parent
> update API function
>
> Crist
This test will not be up streamed in 18.08.
V2, containing a fix for this error, will be sent for 18.11.
> -Original Message-
> From: Thomas Monjalon [mailto:tho...@monjalon.net]
> Sent: Tuesday, July 31, 2018 4:02 PM
> To: Daly, Lee
> Cc: dev@dpdk.org; De Lara Guarch, Pablo ;
> Trahe, Fi
Cristian, review please?
10/07/2018 17:33, Ben Shelton:
> The node parent update API function may be used to update the
> priority/weight of an existing node. Update the documentation to
> indicate that this use case is supported.
>
> Signed-off-by: Ben Shelton
[...]
> /**
> * Traffic manage
24/07/2018 16:06, Lee Daly:
> From: "Daly, Lee"
>
> Added offset test, which tests compression/decompression with a buffer
> containing an offset spanning across multiple segments.
>
> Signed-off-by: Lee Daly
There is a compilation error (with GCC 8).
> + if ((capab->comp_feature_flags &
27/07/2018 16:26, Naga Suresh Somarowthu:
> Naga Suresh Somarowthu (4):
> test: add helper functions for tests using ring-PMD Rx/Tx
> test: add unit tests for bitrate library
> test: add unit tests for latencystats library
> test: add unit test for pdump library
The patch 2 does not apply
> On Jul 31, 2018, at 1:09 AM, Fu, Qiaobin wrote:
>
> Hi Yipeng,
>
> Thanks for the feedbacks!
>
>> On Jul 30, 2018, at 4:24 PM, Wang, Yipeng1 wrote:
>>
>> Hi, Qiaobin,
>>
>> Thanks for the patch. If I understand correctly your use case is to use hash
>> table as a "cache" that new entri
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Cristian Dumitrescu
> Sent: Tuesday, July 31, 2018 3:49 PM
> To: dev@dpdk.org
> Subject: [dpdk-dev] [PATCH] examples/ip_pipeline: fix RSS
>
> Fix for RSS issue triggered by latest changes in ethdev layer.
>
> S
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Cristian Dumitrescu
> Sent: Tuesday, July 31, 2018 3:49 PM
> To: dev@dpdk.org
> Subject: [dpdk-dev] [PATCH] examples/ip_pipeline: fix RSS
>
> Fix for RSS issue triggered by latest changes in ethdev layer.
>
> Si
Fix for RSS issue triggered by latest changes in ethdev layer.
Signed-off-by: Cristian Dumitrescu
---
examples/ip_pipeline/link.c | 9 +++--
1 file changed, 3 insertions(+), 6 deletions(-)
diff --git a/examples/ip_pipeline/link.c b/examples/ip_pipeline/link.c
index 2ccfea4..392a890 100644
-
After adding RSS hash offload check, default rss_hf will fail on devices
that do not support all bits. This will lead to dcb config failure. The
patch fixes this issue by reading current valid rss_conf from the device.
Fixes: 8863a1fbfc66 ("ethdev: add supported hash function check")
Fixes: 1a5724
27/07/2018 11:40, Reshma Pattan:
> Previously, unit tests were running in groups. There were technical
> reasons why that was the case (mostly having to do with limiting memory),
> but it was hard to maintain and update the autotest script.
> In 18.05, limiting of memory at DPDK startup was no long
-Original Message-
From: Van Haaren, Harry
Sent: Monday, July 30, 2018 6:34 PM
To: dev@dpdk.org
Cc: Van Haaren, Harry ; Richardson, Bruce
; sta...@dpdk.org; tho...@monjalon.net; Coyle,
David ; Xing, Beilei ; Zhang, Qi
Z
Subject: [PATCH v2] net/i40e: fix avx2 driver check for rx rear
test_pmd_ring_pair_create_attach() uses an uninitialized
struct rte_eth_conf object
Fixes: 51f567129c94 ("app/test: add pmd_ring")
Cc: sta...@dpdk.org
Signed-off-by: Radu Nicolau
---
test/test/test_pmd_ring.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/test/test/test_pmd_ring.c b/test
From: Shally Verma
Replace macros by static inline functions in openssl
compatibility layer. These changes are based on
the feedback given on openssl PMD patch V5 here:
Link: https://patches.dpdk.org/patch/43273/#84042
Ashish Gupta (1):
crypto/openssl: replace macros by static inline function
Replace macros by static inline functions in openssl version
compatibility layer
Signed-off-by: Sunila Sahu
Signed-off-by: Shally Verma
Signed-off-by: Ashish Gupta
---
drivers/crypto/openssl/compat.h | 265 ++-
drivers/crypto/openssl/rte_openssl_pmd.c |
On 7/31/2018 1:21 PM, Gavin Hu wrote:
Currently only one buffer pool is configured and in use,
looping for up to maxmum 8 times is unnecessary and might
be buggy as assigned uninititalized values.
The fix is to loop for the configured times with initialize
with valid values.
Fixes: 16bbc98a3e (
On Tue, Jul 31, 2018 at 3:27 PM Timothy Redaelli
wrote:
> Stripping binaries at build time is usually a bad thing since it makes
> impossible to generate (split) debug symbols and this can lead to a more
> difficult debugging.
>
> CC: Adrien Mazarguil
> Fixes: 59b91bec12c6 ("net/mlx5: spawn rdma
On Tue, Jul 31, 2018 at 3:26 PM Timothy Redaelli
wrote:
> Stripping binaries at build time is usually a bad thing since it makes
> impossible to generate (split) debug symbols and this can lead to a more
> difficult debugging.
>
> CC: Adrien Mazarguil
> Fixes: 27cea11686ff ("net/mlx4: spawn rdma
On Tue, 2018-07-31 at 15:15 +0200, Timothy Redaelli wrote:
> Stripping binaries at build time is usually a bad thing since it
> makes
> impossible to generate (split) debug symbols and this can lead to a
> more
> difficult debugging.
>
> CC: Adrien Mazarguil
> Fixes: 27cea11686ff ("net/mlx4: spaw
On Tue, 2018-07-31 at 15:15 +0200, Timothy Redaelli wrote:
> Stripping binaries at build time is usually a bad thing since it
> makes
> impossible to generate (split) debug symbols and this can lead to a
> more
> difficult debugging.
>
> CC: Adrien Mazarguil
> Fixes: 59b91bec12c6 ("net/mlx5: spaw
Stripping binaries at build time is usually a bad thing since it makes
impossible to generate (split) debug symbols and this can lead to a more
difficult debugging.
CC: Adrien Mazarguil
Fixes: 59b91bec12c6 ("net/mlx5: spawn rdma-core dependency plug-in")
Signed-off-by: Timothy Redaelli
---
dri
Stripping binaries at build time is usually a bad thing since it makes
impossible to generate (split) debug symbols and this can lead to a more
difficult debugging.
CC: Adrien Mazarguil
Fixes: 27cea11686ff ("net/mlx4: spawn rdma-core dependency plug-in")
Signed-off-by: Timothy Redaelli
---
dri
Hi Thomas,
This is my reply.
> -Original Message-
> From: Thomas Monjalon [mailto:tho...@monjalon.net]
> Sent: Friday, July 27, 2018 1:42
> To: Xu, Rosen
> Cc: dev@dpdk.org; Yigit, Ferruh ;
> or...@mellanox.com; Gilmore, Walter E ;
> Zhang, Qi Z ; sta...@dpdk.org
> Subject: Re: [dpdk-dev
Rte_fdir_conf of rte_eth_conf should be initialized before
port initialization. It is a workaround solution when working
with Intel I40e.
Fixes: 4a3ef59a10c8 ("examples/flow_filtering: add simple demo of flow API")
Cc: sta...@dpdk.org
Signed-off-by: Rosen Xu
Acked-by: Ori Kam
Reviewed-by: Ferru
27/07/2018 00:10, Arnon Warshavsky:
> This patch adds a new function that is called
> per every checked patch,
> and alerts for new instances of rte_panic/rte_exit.
> The check excludes comments, and alerts in the case
> of a positive balance between additions and removals.
>
> Signed-off-by: Arno
> + awk -v FOLDERS="lib net drivers" \
>
> I don't know why net is listed as a root directory here?
> I am going to apply the patch without the "net" directory. OK?
>
Yes please. Its not necessarily root rather in any location of the path,
but having added drivers, net is now redundant.
thank
27/07/2018 00:10, Arnon Warshavsky:
> + # refrain from new additions of rte_panic() and rte_exit()
> + # under lib and net
> + # multiple folders and expressions are separated by spaces
> + awk -v FOLDERS="lib net drivers" \
I don't know why net is listed as a root directory here?
Currently, DPDK will skip mapping some areas (or even an entire BAR)
if MSI-X table happens to be in them but is smaller than page size.
Kernels 4.16+ will allow mapping MSI-X BARs [1], and will report this
as a capability flag. Capability flags themselves are also only
supported since kernel 4.6
On 31-Jul-18 10:38 AM, Takeshi Yoshimura wrote:
2018-07-30 20:17 GMT+09:00 Anatoly Burakov :
Currently, DPDK will skip mapping some areas (or even an entire BAR)
if MSI-X happens to be in it but is smaller than page address.
Kernels 4.16+ will allow mapping MSI-X BARs [1], and will report this
This commit fixes an offset check in decompression which was checking
destination offset size against dst data_len rather than checking
against dst pkt_len as required.
Fixes:788e748d3845 ("compress/isal: support chained mbufs")
Signed-off-by: Lee Daly
---
drivers/compress/isal/isal_compress_pm
Recently, off the list, Keith pointed out that the rte_rawdev_queue_count
API was incomplete - only the declaration existed but no definition. This
is an old miss (and embarassingly, almost two release cycle long miss!)
This patch adds that and the relevant unit test case.
Ferruh: Though I am sen
Rawdev queue count API prototype was declared, but the definition was
missing from the library. This patch implements the function.
This API is used to query the device about the count of queues it has
been configured with.
Fixes: c88b3f2558ed ("rawdev: introduce raw device library")
Cc: shreyans
Use the rte_rawdev_queue_count API in skeleton and add its unit test
case.
Signed-off-by: Shreyansh Jain
---
drivers/raw/skeleton_rawdev/skeleton_rawdev.c | 13 +
drivers/raw/skeleton_rawdev/skeleton_rawdev_test.c | 13 +
2 files changed, 26 insertions(+)
diff --git
2018-07-30 20:17 GMT+09:00 Anatoly Burakov :
> Currently, DPDK will skip mapping some areas (or even an entire BAR)
> if MSI-X happens to be in it but is smaller than page address.
>
> Kernels 4.16+ will allow mapping MSI-X BARs [1], and will report this
> as a capability flag. Capability flags the
>>
>> I think the end result we're hoping for is something like pseudo code
>> below,
>> (keep in mind that the event/sw has a service-core thread running it, so
>> no
>> application code there):
>>
>> int worker_poll = 1;
>>
>> worker() {
>> while
-Original Message-
> Date: Tue, 31 Jul 2018 08:09:05 +
> From: "Elo, Matias (Nokia - FI/Espoo)"
> To: Jerin Jacob
> CC: "Van Haaren, Harry" , "dev@dpdk.org"
>
> Subject: Re: [dpdk-dev] eventdev: method for finding out unlink status
> x-mailer: Apple Mail (2.3445.9.1)
>
>
>
>
If the "port config all crc-strip on" command is issued,
The DEV_RX_OFFLOAD_KEEP_CRC offload flag should be cleared.
If the "port config all crc-strip off command is issued,
The DEV_RX_OFFLOAD_KEEP_CRC offload flag should be set.
Fixes: 70815c9ecadd ("ethdev: add new offload flag to keep CRC")
Si
Very simple version of vhost-user driver in vhost sample will be used if
builtin-net-driver option is enabled. This driver is based on generic
vhost lib APIs. Unfortunately, the implementation is incompatible with
QEMU as protocol feature is not supported.
Signed-off-by: Marvin Liu
diff --git a/
I think the end result we're hoping for is something like pseudo code
below,
(keep in mind that the event/sw has a service-core thread running it, so no
application code there):
int worker_poll = 1;
worker() {
while(worker_poll) {
// e
The below commit has added a graph based expansion logic for RSS rule to
satisfy Verbs requirements. With this logic, for example, the rule:
flow create 0 ingress pattern eth / end actions rss queues 0 1 end types
ipv4-tcp ipv6-tcp end / end
will be expanded into the rules:
flow create 0 ingress
Sunday, July 29, 2018 1:44 PM, Shahaf Shuler:
> Subject: [dpdk-dev] [PATCH] net/mlx5: fix flow count action for shared
> counters
>
> According to commit fb8fd96d4251 ("ethdev: add shared counter to flow
> API") the counter id should be taken into account only when the shared flag
> is set.
>
> F
Currently only one buffer pool is configured and in use,
looping for up to maxmum 8 times is unnecessary and might
be buggy as assigned uninititalized values.
The fix is to loop for the configured times with initialize
with valid values.
Fixes: 16bbc98a3e ("bus/fslmc: update MC to 10.3.x")
Cc: st
On Thu, Jul 26, 2018 at 10:27:38PM +0800, Marvin Liu wrote:
> Option builtin-net-driver is used to demonstrate how to implement
> vhost-user driver based on vhost lib APIs. Unfortunately, very simple
> vhost driver in vhost sample is incompatible with QEMU as protocol
> feature not supported.
>
>
86 matches
Mail list logo
