> -Original Message-
> From: Steve Yang
> Sent: Friday, November 13, 2020 8:47 AM
> To: dev@dpdk.org
> Cc: Yang, Qiming ; Xing, Beilei
> ; Wu, Jingjing ; Zhang, Qi Z
> ; Yang, SteveX
> Subject: [PATCH v3 1/2] net/iavf: fix reset VF doesn't notify PF to reset
>
> When VF closed, the VF
>-Original Message-
>From: Maxime Coquelin
>Sent: Friday, November 13, 2020 1:10 AM
>To: dev@dpdk.org; xuan.d...@intel.com; step...@networkplumber.org;
>NBU-Contact-Thomas Monjalon ; sta...@dpdk.org;
>chenbo@intel.com; Xueming(Steven) Li
>Cc: Maxime Coquelin
>Subject: [PATCH v4 3/
>-Original Message-
>From: Maxime Coquelin
>Sent: Friday, November 13, 2020 1:10 AM
>To: dev@dpdk.org; xuan.d...@intel.com; step...@networkplumber.org;
>NBU-Contact-Thomas Monjalon ; sta...@dpdk.org;
>chenbo@intel.com; Xueming(Steven) Li
>Cc: Maxime Coquelin
>Subject: [PATCH v4 1/
On Fri, Nov 13, 2020 at 2:20 AM Liu, Yong wrote:
> > Yes and this will also solve https://patchwork.dpdk.org/patch/83468/.
> > Thanks.
> >
>
> Agreed, original patch was intended to recover prefetch configuration in
> meson build.
> Please check http://patchwork.dpdk.org/patch/78451/.
> And it le
Hi Luca,
Thank you for taking the initiative. However, the patch fails to apply on my
system, and that's the reason I've been delaying my own):
$ git am \[kmods\ PATCH\ v2\]\ windows:\ normalize\ line-endings
Applying: windows: normalize line-endings
error: windows/virt2phys/virt2phys.sln: does
In the implementation of mlx5_hairpin_unbind, a copy-paste error was
inside. If a single peer Rx port needed to be unbound, it would be
bound again by mistake.
All the hardware resources were released when stopping the device and
no mess of the configuration was introduced. But when trying to unbi
> On Nov 11, 2020, at 7:18 AM, Juraj Linkeš wrote:
>
> The current way of specifying Arm configuration options is insufficient
> since we can't identify the SoC we're building for from the MIDR
> information. For example, we can't distinguish between N1SDP, Graviton2
> or Ampere Altra.
>
> Add
Hi Juraj,
The failure in Travis should be fixed by [1]. I think you can include
it in this series so that we get a clean build in Travis.
Ajit, Hemant, Vimal, Thomas,
Appreciate if you could test this series on your respective platforms.
We need testing on x86 as well.
[1] htt
>
> Add Arm SoC configuration to Arm meson.build and add a meson option to
> enable those options for native builds. This is preferable to specifying a
> cross
> file when doing aarch64 -> aarch64 builds, since the cross file specifies the
> toolchain as well.
>
> Signed-off-by: Juraj Linkeš
>
> Some Arm SoCs are not NUMA systems. Add the capability to disable NUMA
> for cross build and disabled NUMA in Arm cross files.
>
> Signed-off-by: Juraj Linkeš
Reviewed-by: Honnappa Nagarahalli
> ---
> config/arm/arm64_armada_linux_gcc | 1 +
> config/arm/arm64_bluefield_lin
>
> A few options that disabled drivers in the old makefiles were improperly
> ported to the meson build system. Fix this by adding a to the list of disabled
> drivers, similarly how the command line option works. Remove unneeded
> driver options ported from the old makefile system.
> Add suppor
>
> Add support for setting core count and numa nodes in cross files. The values
> specified in cross files will override the default values.
> Also add missing default values to Arm config.
>
> Signed-off-by: Juraj Linkeš
Reviewed-by: Honnappa Nagarahalli
> ---
> config/arm/arm64_armada_li
>
> Use generic configuration for the only build where it makes sense - the
> generic build. For other builds, if we don't know either of implementer ID or
> part number, the build is not supported.
> Add part numbers to cross files where fallback to generic configuration is
> assumed.
>
> Sign
>
> Use dictionary lookup instead of checking for existing variables, iterating
> over
> all elements in the list or checking lists for optional configuration. Move
> variable contents into the dictionary for variables that would be referenced
> only once.
> Fallback to generic part number if t
> -Original Message-
> From: Steve Yang
> Sent: Friday, November 13, 2020 8:47 AM
> To: dev@dpdk.org
> Cc: Yang, Qiming ; Xing, Beilei
> ; Wu, Jingjing ; Zhang, Qi Z
> ; Yang, SteveX
> Subject: [PATCH v3 2/2] net/iavf: fix the RSS error when VF port closed
>
> Check the VF RSS offload
> -Original Message-
> From: Xie, WeiX
> Sent: Friday, November 13, 2020 11:16 AM
> To: Yang, MurphyX ; dev@dpdk.org
> Cc: Yang, Qiming ; Zhang, Qi Z
> ; Yang, SteveX ; Rong, Leyi
> ; Lu, Wenzhuo ; Yang,
> MurphyX
> Subject: RE: [dpdk-dev] [PATCH v6] net/ice: fix outer checksum on cvl
> -Original Message-
> From: Sun, QinX
> Sent: Friday, November 13, 2020 11:35 AM
> To: Zhang, AlvinX ; Zhang, Qi Z
> ; Rong, Leyi ; Lu, Wenzhuo
>
> Cc: dev@dpdk.org; Zhang, AlvinX
> Subject: RE: [dpdk-dev] [PATCH v3] net/ice: support flow mark ID in avx512
> path
>
> Tested-by: Sun
>
> To allow per-build override of some settings, without having to change DPDK
> source-code files, i.e. rte_config.h, we can add an option to allow the user
> to
> pass in a file containing their own defines for the build.
I guess, the file format should be same as any header file.
One could
Tested-by: Chen, LingliX
Regards,
Chen, LingliX
> -Original Message-
> From: Walsh, Conor
> Sent: Thursday, November 12, 2020 7:36 PM
> To: Richardson, Bruce
> Cc: dev@dpdk.org; Chen, LingliX ; Walsh, Conor
>
> Subject: [PATCH v1] build: add Wformat to fix gcc compile error
>
> On so
Tested-by: Sun, QinX
Regards,
Sun Qin
> -Original Message-
> From: dev On Behalf Of Zhang,Alvin
> Sent: Friday, November 13, 2020 10:51 AM
> To: Zhang, Qi Z ; Rong, Leyi ;
> Lu, Wenzhuo
> Cc: dev@dpdk.org; Zhang, AlvinX
> Subject: [dpdk-dev] [PATCH v3] net/ice: support flow mark ID i
https://bugs.dpdk.org/show_bug.cgi?id=577
Bug ID: 577
Summary: x540-AT2: Can Flow Director filter fragmented packet ?
Product: DPDK
Version: 17.05
Hardware: x86
OS: Linux
Status: UNCONFIRMED
Severity: norm
Tested-by: Xie,WeiX < weix@intel.com>
Regards,
Xie Wei
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Murphy Yang
> Sent: Monday, November 9, 2020 2:07 PM
> To: dev@dpdk.org
> Cc: Yang, Qiming ; Zhang, Qi Z
> ; Yang, SteveX ; Rong, Leyi
> ; Lu, Wenzhuo ;
From: Alvin Zhang
Support flow director mark ID parsing from flexible Rx descriptor
in avx512 path.
Signed-off-by: Alvin Zhang
---
v2: Update codes according to comments.
v3: Rename the function ice_flex_rxd_to_fdir_flags_vec_avx with
ice_flex_rxd_to_fdir_flags_vec_avx512.
---
drivers/ne
From: Alvin Zhang
Support flow director mark ID parsing from flexible Rx descriptor
in avx512 path.
Signed-off-by: Alvin Zhang
Fixes: 7f85d5ebcfe1 ("net/ice: add AVX512 vector path")
---
v2: Update codes according to comments.
---
drivers/net/ice/ice_rxtx_vec_avx512.c | 65 ++
From: Alvin Zhang
Support flow director mark ID parsing from flexible Rx descriptor
in avx512 path.
Signed-off-by: Alvin Zhang
Fixes: 7f85d5ebcfe1 ("net/ice: add AVX512 vector path")
---
v1: Update codes according to comments.
---
drivers/net/ice/ice_rxtx_vec_avx512.c | 65 ++
From: Alvin Zhang
Support flow director mark ID parsing from flexible Rx descriptor
in avx512 path.
Signed-off-by: Alvin Zhang
Fixes: 7f85d5ebcfe1 ("net/ice: add AVX512 vector path")
---
drivers/net/ice/ice_rxtx_vec_avx512.c | 65 +--
1 file changed, 63 inserti
> -Original Message-
> From: David Marchand
> Sent: Thursday, November 12, 2020 4:58 PM
> To: Liu, Yong ; Maxime Coquelin
>
> Cc: Xia, Chenbo ; dev ; Richardson,
> Bruce
> Subject: Re: [dpdk-dev] [PATCH] net/virtio: enable packet data prefetch on
> x86
>
> On Thu, Nov 12, 2020 at 9:48
Check the VF RSS offload flag and ignore relative operation when
iavf hash uninit to avoid reset/close error.
Fixes: 7be10c3004be ("net/iavf: add RSS configuration for VF")
Signed-off-by: Steve Yang
---
drivers/net/iavf/iavf_hash.c | 6 ++
1 file changed, 6 insertions(+)
diff --git a/drive
When VF closed, the VF should notify PF to close/reset relative
resources from PF side.
Fixes: 22b123a36d07 ("net/avf: initialize PMD")
Signed-off-by: Steve Yang
---
drivers/common/iavf/iavf_prototype.h | 1 +
drivers/common/iavf/version.map | 1 +
drivers/net/iavf/iavf_ethdev.c |
When VF closed, the VF should notify PF to close/reset relative
resources from PF side.
Check the VF RSS offload flag and ignore relative operation when
iavf hash uninit to avoid reset/close error.
---
v3:
* changed code pattern for 'ice_hash_uninit'.
v2:
* split to 2 patches;
* added patch ba
> -Original Message-
> From: Wang, Haiyue
> Sent: Thursday, November 12, 2020 10:00 AM
> To: dev@dpdk.org
> Cc: Yigit, Ferruh ; Zhang, Qi Z
> ;
> Wang, Haiyue ; sta...@dpdk.org; Guo, Jia
> ; Zhao1, Wei ; Xing, Beilei
> ; Wei Dai ; Lu, Wenzhuo
>
> Subject: [PATCH v1] net/ixgbe: remove
12/11/2020 21:15, luca.bocca...@gmail.com:
> From: Dmitry Kozlyuk
>
> MSBuild XML files have to use CRLF line-endings, otherwise any change
> results in the whole file being rewritten with CRLF line-endings by
> Visual Studio. However, it's inconvenient to have such files checked-out
> with CLRF
> From: Akhil Goyal
>
> >
> > Hi Akhil,
> > Heads up on this doc update still to be applied.
> >
>
>
> > > > doc/guides/bbdevs/acc100.rst| 19 +++
> > > > doc/guides/bbdevs/fpga_5gnr_fec.rst | 19 +++
> > > > doc/guides/bbdevs/fpga_lte_fec.rst | 19
> Subject: Re: [dpdk-dev] [PATCH v2] windows: minor build fixes
>
>
> Missing / incorrect '--in-reply-to'. Please ignore - still learning the
> process!
>
> On 31/10/2020 06:43, Nick Connolly wrote:
> > Meson versions >= 0.54.0 include support for handling /implib with
> > msvc link. Specifying
> Subject: [dpdk-dev] [PATCH] compress/isal: check allocation in qp setup
>
> From: Yunjian Wang
>
> The function rte_zmalloc() could return NULL, the return value
> need to be checked.
>
> Fixes: dc49e6aa4879 ("compress/isal: add ISA-L compression functionality")
> Fixes: 7bf4f0630af6 ("compre
> This commit adds support to BBDEV for LDPC Code Block Group Transmission
> (CBGT) as defined in 3GPP TS 38.214. The following changes facilitate this:
> - add RTE_BBDEV_LDPC_[ENC/DEC]_CBGT feature flag
> - add CBGT input parameters to LDPC encode transport block op structure
> - add CBGT input an
> Updated AESNI MB and AESNI GCM PMD documentation guides
> with information about the latest Intel IPSec Multi-buffer
> library supported.
>
> Signed-off-by: Pablo de Lara
> ---
Applied to dpdk-next-crypto
Thanks.
> The print statement had a typo, "sesionless" should have been
> "sessionless". This is now fixed.
>
> Fixes: afcfa2fd0431 ("test/crypto: check session-less support")
> Cc: pablo.de.lara.gua...@intel.com
> Cc: sta...@dpdk.org
>
> Signed-off-by: Ciara Power
> ---
Applied to dpdk-next-crypto
Tha
> > This patch fixes bypassed out of place test for PMDs that support it.
> >
> > Fixes: 4868f6591c6f ("test/crypto: add cases for raw datapath API")
> > Cc: roy.fan.zh...@intel.com
> >
> > Signed-off-by: Fan Zhang
>
> Acked-by: Adam Dybkowski
>
> Thanks Fan for quick fixing action.
> Akhil,
> Fixes: 02dc5b7d58c7 ("doc: update ipsec-secgw guide and release notes")
> Cc: sta...@dpdk.org
>
> Signed-off-by: David Marchand
> ---
Applied to dpdk-next-crypto
Thanks.
>
> Hi Akhil,
> Heads up on this doc update still to be applied.
>
> > > doc/guides/bbdevs/acc100.rst| 19 +++
> > > doc/guides/bbdevs/fpga_5gnr_fec.rst | 19 +++
> > > doc/guides/bbdevs/fpga_lte_fec.rst | 19 +++
> > > 3 files changed, 5
> >
> > This series has code cleanup and improvements for OCTEON TX and OCTEON
> > TX2 crypto PMDs
> >
> > Archana Muniganti (4):
> > common/cpt: prepopulate word7 in sess
> > common/cpt: remove temporary variable
> > common/cpt: use predefined macros
> > common/cpt: remove redundant struct
On Wed, 2020-11-11 at 15:09 +, Luca Boccassi wrote:
> On Wed, 2020-11-11 at 15:03 +, Luca Boccassi wrote:
> > On Wed, 2020-11-11 at 16:02 +0100, Thomas Monjalon wrote:
> > > 29/10/2020 23:55, Dmitry Kozlyuk:
> > > > MSBuild XML files have to use CRLF line-endings, otherwise any change
> > >
From: Dmitry Kozlyuk
MSBuild XML files have to use CRLF line-endings, otherwise any change
results in the whole file being rewritten with CRLF line-endings by
Visual Studio. However, it's inconvenient to have such files checked-out
with CLRF in Unix environments.
Add suggested git configuration
From: Mike Baucom
Use comparison operator instead of incorrectly using the assignment
operator.
Coverity issue: 363566
Coverity issue: 363577
Fixes: 42c40f8902f7 ("net/bnxt: consolidate template table processing")
Cc: sta...@dpdk.org
Signed-off-by: Mike Baucom
Reviewed-by: Ajit Khaparde
---
12/11/2020 12:35, Conor Walsh:
> On some systems Wformat-nonliteral and Wformat-security could not be
> checked without Wformat also being specified. This patch adds Wformat
> to config/meson.build
>
> Signed-off-by: Conor Walsh
Please could you provide (in a v2) more informations about the erro
10/11/2020 16:40, David Marchand:
> checkpatches.sh current complains on a patch [1] adding
> ALLOW_EXPERIMENTAL_API in an example while this check is for app, lib
> and drivers directories:
>
> Warning in examples/ethtool/ethtool-app/Makefile:
> Using experimental build flag for in-tree compilati
12/11/2020 10:41, Bruce Richardson:
> This patch improves the installation of the examples when "ninja install" is
> run. It removes issues with the directory structure being flattened out, and
> removes from the install list any examples that are not buildable with built
> DPDK code.
>
> V4: resu
On 11/12/2020 3:29 PM, Ajit Khaparde wrote:
From: Mike Baucom
Use comparison operator instead of incorrectly using the assignment
operator.
Coverity issue: 363566
Coverity issue: 363577
Fixes: 42c40f8902f7 ("net/bnxt: consolidate template table processing")
Cc: sta...@dpdk.org
Signed-off-by:
On Thu, Nov 12, 2020 at 4:58 PM Cheng Jiang wrote:
>
> Fix vhost-switch compiling issue when ioat dependency is missing.
> Change 'RTE_x86' check into 'RTE_RAW_IOAT' check in meson build file.
> Use 'RTE_RAW_IOAT' to control conditional compiling in source file.
> Clean some codes.
>
> Fixes: abec
From: Pavan Nikhilesh
Fix SEGFAULT when nb_timer_adapters command line parameter is
set to 0.
Fixes: 98c6292105d4 ("app/eventdev: add options for event timer adapter")
Cc: sta...@dpdk.org
Signed-off-by: Pavan Nikhilesh
---
app/test-eventdev/evt_options.c | 4
1 file changed, 4 insertions
This patch fixes a file descriptor leak which happens
in the error path of vhost_user_set_log_base().
Fixes: 4796ad63ba1f ("examples/vhost: import userspace vhost application")
Cc: sta...@dpdk.org
Reported-by: Xuan Ding
Signed-off-by: Maxime Coquelin
Reviewed-by: Chenbo Xia
Reviewed-by: Xuemin
This patch fixes a file descriptor leak which happens
in the error path of vhost_user_set_vring_kick().
Fixes: 4796ad63ba1f ("examples/vhost: import userspace vhost application")
Cc: sta...@dpdk.org
Signed-off-by: Maxime Coquelin
Reviewed-by: Chenbo Xia
---
lib/librte_vhost/vhost_user.c | 6 ++
If an error is encountered before the memory regions are
parsed, the file descriptors for these shared buffers are
leaked.
This patch fixes this by closing the message file descriptors
on error, taking care of avoiding double closing of the file
descriptors. guest_pages is also freed, even though
This series fixes several leaks in Vhost-user requests
handling.
Thanks to Xuan Ding from Intel for reporting these
issues.
Changes in v4:
- Fix wrong return value in set_mem_table (Xueming)
Changes in v3:
- Remove the right closing of fds. (Chenbo)
Changes in v2:
- Fix typos in commit messages.
> -Original Message-
> From: Bruce Richardson
> Sent: Thursday, November 12, 2020 11:33 AM
> To: David Harton (dharton)
> Cc: dev@dpdk.org
> Subject: Re: [dpdk-dev] Eliminate config/rte_config.h?
>
> On Thu, Nov 12, 2020 at 03:48:20PM +, Bruce Richardson wrote:
> > On Thu, Nov 12, 20
>
> When doing Clang build with '-mcpu=native' on N1 platform, build failed
> with:
> ../lib/librte_eal/arm/include/rte_atomic_64.h:76:39:
> error: instruction requires: lse
> __ATOMIC128_CAS_OP(__cas_128_release, "caspl")
>
> This is because native detection for Neoverse N1 was added in
12/11/2020 10:41, Bruce Richardson:
> Rather than just installing all examples, we can use the build checks to
> filter out any examples that are missing dependencies or are otherwise
> unbuildable on the current system.
>
> Signed-off-by: Bruce Richardson
This patch does not say why unbuildable
On 11/11/20 8:57 AM, Xia, Chenbo wrote:
> Hi Xueming & Maxime,
>
>> -Original Message-
>> From: Xueming(Steven) Li
>> Sent: Wednesday, November 11, 2020 2:02 PM
>> To: Maxime Coquelin ; dev@dpdk.org; Ding, Xuan
>> ; step...@networkplumber.org; NBU-Contact-Thomas
>> Monjalon ; sta...@dp
> -Original Message-
> From: Maxime Leroy
> Sent: Thursday, November 12, 2020 17:39
> To: Matan Azrad ; Shahaf Shuler ;
> Slava Ovsiienko ; Alexander Kozyrev
>
> Cc: dev@dpdk.org; NBU-Contact-N?lio Laranjeiro
>
> Subject: [PATCH v2 1/2] net/mlx5: fix Rx queue count calculation
>
> The c
'uint64_t' is used to hold pointers in multiple locations in the
copy-mode code (used for kernels before 5.4). For a 32-bit build
this assumption is wrong and results in build errors. This commit
replaces such instances of 'uint64_t' with 'uintptr_t'.
While the copy-mode code will now compile for
On Wed, Nov 11, 2020 at 6:48 PM Juraj Linkeš wrote:
>
> The current way of specifying Arm configuration options is insufficient
> since we can't identify the SoC we're building for from the MIDR
> information. For example, we can't distinguish between N1SDP, Graviton2
> or Ampere Altra.
>
> Add a
On 11/11/20 7:06 AM, Xueming(Steven) Li wrote:
>> @@ -1012,16 +1018,13 @@ vhost_user_set_mem_table(struct virtio_net
>> **pdev, struct VhostUserMsg *msg,
>> if (memory->nregions > VHOST_MEMORY_MAX_NREGIONS) {
>> VHOST_LOG_CONFIG(ERR,
>> "too many memory reg
On 11/11/20 10:08 AM, Cheng Jiang wrote:
> Add checking return value of string split function to fix the
> coverity issue.
>
> Fixes: 3a04ecb21420 ("examples/vhost: add async vhost args parsing")
> Coverity issue: 363739
>
> Signed-off-by: Cheng Jiang
> ---
> v2: checked args_nr explicitly
>
On 11/12/20 4:49 PM, Cheng Jiang wrote:
> Fix vhost-switch compiling issue when ioat dependency is missing.
> Change 'RTE_x86' check into 'RTE_RAW_IOAT' check in meson build file.
> Use 'RTE_RAW_IOAT' to control conditional compiling in source file.
> Clean some codes.
>
> Fixes: abec60e7115d (
On 11/12/2020 8:36 AM, Jiawei Wang wrote:
When testpmd enabled the verbosity for the received packets, if two packets
was received at the same time, for example, sampling packet and normal
packet, the dump output of these packets may be overlapping due to multiple
core handled the multiple queues
On Thu, Nov 12, 2020 at 05:39:01PM +0100, Thomas Monjalon wrote:
> For consistency with other variables which can be set from the env,
> TEST_MESON_BUILD_VERBOSE and TEST_MESON_BUILD_VERY_VERBOSE
> are renamed
> DPDK_BUILD_TEST_VERBOSE and DPDK_BUILD_TEST_VERY_VERBOSE.
>
> The handling of the verb
For consistency with other variables which can be set from the env,
TEST_MESON_BUILD_VERBOSE and TEST_MESON_BUILD_VERY_VERBOSE
are renamed
DPDK_BUILD_TEST_VERBOSE and DPDK_BUILD_TEST_VERY_VERBOSE.
The handling of the verbosity level is also moved upper in the script,
closer to other initialization
On Thu, Nov 12, 2020 at 4:02 PM Ruifeng Wang wrote:
>
> When doing Clang build with '-mcpu=native' on N1 platform, build failed
> with:
> ../lib/librte_eal/arm/include/rte_atomic_64.h:76:39:
> error: instruction requires: lse
> __ATOMIC128_CAS_OP(__cas_128_release, "caspl")
>
> This is bec
Updated AESNI MB and AESNI GCM PMD documentation guides
with information about the latest Intel IPSec Multi-buffer
library supported.
Signed-off-by: Pablo de Lara
---
doc/guides/cryptodevs/aesni_gcm.rst| 6 +++---
doc/guides/cryptodevs/aesni_mb.rst | 6 +++---
doc/guides/rel_notes/releas
On Thu, Nov 12, 2020 at 03:48:20PM +, Bruce Richardson wrote:
> On Thu, Nov 12, 2020 at 03:39:10PM +, David Harton (dharton) wrote:
> > Hi folks,
> >
> >
> >
> > Been experimenting with DPDK 20.11 and the loss of the old "config"
> > hierarchy.
> >
> >
> >
> > I wonder if anyone consi
To allow per-build override of some settings, without having to change
DPDK source-code files, i.e. rte_config.h, we can add an option to allow
the user to pass in a file containing their own defines for the build.
Signed-off-by: Bruce Richardson
---
This is just a quick RFC to show what might be
On Thu, Nov 12, 2020 at 03:49:02PM +, Cheng Jiang wrote:
> Fix vhost-switch compiling issue when ioat dependency is missing.
> Change 'RTE_x86' check into 'RTE_RAW_IOAT' check in meson build file.
> Use 'RTE_RAW_IOAT' to control conditional compiling in source file.
> Clean some codes.
>
> Fix
Fix vhost-switch compiling issue when ioat dependency is missing.
Change 'RTE_x86' check into 'RTE_RAW_IOAT' check in meson build file.
Use 'RTE_RAW_IOAT' to control conditional compiling in source file.
Clean some codes.
Fixes: abec60e7115d ("examples/vhost: support vhost async data path")
Fixes:
> -Original Message-
> From: Bruce Richardson
> Sent: Thursday, November 12, 2020 11:02 PM
> To: Jiang, Cheng1
> Cc: maxime.coque...@redhat.com; Xia, Chenbo ;
> dev@dpdk.org; Fu, Patrick ; Yang, YvonneX
> ; david.march...@redhat.com; Hu, Jiayu
>
> Subject: Re: [PATCH v4] examples/vhos
On Thu, Nov 12, 2020 at 03:39:10PM +, David Harton (dharton) wrote:
> Hi folks,
>
>
>
> Been experimenting with DPDK 20.11 and the loss of the old "config"
> hierarchy.
>
>
>
> I wonder if anyone considered eliminating config/rte_config.h in favor of
> a config/dpdk_conf that can contain
Hi Slava,
On Wed, Nov 11, 2020 at 8:51 PM Slava Ovsiienko wrote:
>
> Hi, Maxime
>
> Thanks a lot for the patch. There is the comment for the entire series.
>
> [1]_
> >
> > First issue, when there are more than 8 CQEs to uncompress, the computation
> > done in this commit cannot work. Because
From: Didier Pallard
One entry may contain several segments, so 'used' must be multiplied
by number of segments per entry to properly reflect the queue usage.
Fixes: 8788fec1f269 ("net/mlx5: implement descriptor status API")
Signed-off-by: Didier Pallard
Signed-off-by: Maxime Leroy
---
driver
09/11/2020 11:01, David Marchand:
> On Tue, Oct 27, 2020 at 6:39 PM Bruce Richardson
> wrote:
> >
> > To test the installation process of DPDK using "ninja install"
> > test-meson-builds.sh builds a subset of the examples using "make". To allow
> > more flexibility for people testing, allow the se
The commit d2d57605522d ("net/mlx5: fix Rx queue count calculation") is
uncorrect because the count calculation is wrong for the next cqe:
Example:
Compressed Set of packets 1 | Compressed Set of packets 2
C | a | e0 | e1 | e2 | e3 | e4 | e5 | C | a | e0
There are 2 compressed set of packets
Hi folks,
Been experimenting with DPDK 20.11 and the loss of the old "config" hierarchy.
I wonder if anyone considered eliminating config/rte_config.h in favor of a
config/dpdk_conf that can contain the default values at the start of the file
but can be overridden with values later in the f
This patchset provides several bug fixes for rx queue count calculation for
mlx5 driver.
---
V2:
* squash first patch and second patch
* fix wrong init of used for compressed cqes
Didier Pallard (1):
net/mlx5: fix Rx descriptor status returned value
Maxime Leroy (1):
net/mlx5: fix Rx queue
12/11/2020 14:38, David Marchand:
> While testing Thomas patch on this script verbosity, I noticed that we
> load the x86-default environment after installing this target.
> I did not see any problem with it, yet we should load corresponding
> environment before installing a target.
Reworded first
On 11/11/2020 3:39 PM, Conor Walsh wrote:
When DPDK is compiled with gcc 7.5 with the optimization level set to 1
gcc sees the offset variable in txgbe_ethdev.c as possibly being
uninitialised. To correct this the final return statement in
txgbe_get_offset_by_id was simplified to return -1.
Sign
On Thu, Nov 12, 2020 at 01:47:54PM +, Cheng Jiang wrote:
> Fix vhost-switch compiling issue when ioat dependency is missing.
> Change 'RTE_x86' check into 'RTE_RAW_IOAT' check in meson build file.
> Use 'RTE_RAW_IOAT' to control conditional compiling in source file.
> Clean some codes.
>
> Fix
On Thu, Nov 12, 2020 at 02:48:52PM +0100, David Marchand wrote:
> On Thu, Nov 12, 2020 at 12:38 PM Bruce Richardson
> wrote:
> > > My only comment is about vm_power_manager which won't build without
> > > the internal librte_power header.
> > > It builds fine with meson, because I guess meson pull
Fix the detection of instruction pattern with multiple emits followed
by TX. Once detected, this is one of the instruction patterns that is
internally replaced with a single optimized instruction, as long as
none of the instructions to be replaced is referenced by a jump
instruction. The fix enforc
On Tue, Nov 10, 2020 at 3:36 PM Thomas Monjalon wrote:
> PKG_CONFIG_PATH=../dpdk-build/build-x86-default/meson-private \
> pkg-config --define-prefix --libs-only-L libdpdk
> -L/usr/local/lib
>
> Oh! I am testing on the build directory instead of installed one.
>
> PKG_CONFIG_PATH=../dpdk-build/bui
> > > According to the Technical Board decision
> > > (http://mails.dpdk.org/archives/dev/2020-November/191859.html),
> > > the mempool pointer in the mbuf struct is moved
> > > from the second to the first half.
> > > It may increase performance in some cases
> > > on systems having 64-byte cache
On Thu, Nov 12, 2020 at 3:22 PM Thomas Monjalon wrote:
>
> The variables DPDK_MESON_OPTIONS, PATH, PKG_CONFIG_PATH,
> CPPFLAGS, CFLAGS and LDFLAGS can be customized in the config file
> loaded by devtools/load-devel-config at each build.
> The configuration can be adjusted per target thanks to the
12/11/2020 14:08, Bruce Richardson:
> On Fri, Nov 06, 2020 at 06:28:54PM +0100, Thomas Monjalon wrote:
> > The default verbosity of test-meson-builds.sh is to be quiet.
> > In order to better apply the verbosity policy, some file descriptors
> > are open to redirect to stdout or /dev/null according
The variables DPDK_MESON_OPTIONS, PATH, PKG_CONFIG_PATH,
CPPFLAGS, CFLAGS and LDFLAGS can be customized in the config file
loaded by devtools/load-devel-config at each build.
The configuration can be adjusted per target thanks to the value set
in the DPDK_TARGET variable.
PKG_CONFIG_PATH is specif
Submitted v4 patch as per Bruce's suggestion.
> -Original Message-
> From: Bruce Richardson
> Sent: Thursday, November 12, 2020 8:02 PM
> To: Jiang, Cheng1
> Cc: David Marchand ; Maxime Coquelin
> ; Xia, Chenbo ;
> dev ; Fu, Patrick ; Yang, YvonneX
> ; Hu, Jiayu
> Subject: Re: [dpdk-dev
Fix vhost-switch compiling issue when ioat dependency is missing.
Change 'RTE_x86' check into 'RTE_RAW_IOAT' check in meson build file.
Use 'RTE_RAW_IOAT' to control conditional compiling in source file.
Clean some codes.
Fixes: abec60e7115d ("examples/vhost: support vhost async data path")
Fixes:
Currently, header reformat action uses the hash list 32-bit key generated
in header reformat register function directly. The key will not be
recalculated in the hash list function.
As the 64-bit key is composed of the 32-bit attributes and 32-bit reformat
buffer csum, the hash list function only g
On Thu, Nov 12, 2020 at 12:38 PM Bruce Richardson
wrote:
> > My only comment is about vm_power_manager which won't build without
> > the internal librte_power header.
> > It builds fine with meson, because I guess meson pulls this library
> > directory into the include flags of the example, but it
> -Original Message-
> From: Burakov, Anatoly [mailto:anatoly.bura...@intel.com]
> Sent: Thursday, November 12, 2020 7:40 PM
> To: wangyunjian ; dev@dpdk.org
> Cc: rsanfo...@gmail.com; Lilijun (Jerry) ; xudingke
> ; sta...@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH] malloc: cleanup coding st
While testing Thomas patch on this script verbosity, I noticed that we
load the x86-default environment after installing this target.
I did not see any problem with it, yet we should load corresponding
environment before installing a target.
Fixes: bd253daa7717 ("devtools: fix test of ninja instal
On 2020/11/10 20:42, David Marchand wrote:
On Tue, Nov 10, 2020 at 1:35 PM 谢华伟(此时此刻） wrote:
Previously there are different ways to get port address based on
different DPDK uio driver(IGB_UIO/UIO_PCI_GENERIC/VFIO), which is
actually not necessary.
This patch makes IO/MMIO port map/RW API more
On Wed, Nov 4, 2020 at 10:41 AM David Marchand
wrote:
>
> This script inspects an ELF file (binary or shared library) and its
> linked dependencies by following DT_NEEDED tags.
> So far a simple librte_pmd prefix was used as a filter.
> Now that we changed the driver library names, update this heu
1 - 100 of 144 matches
Mail list logo
