22/10/2019 22:19, Honnappa Nagarahalli:
> From: Akhil Goyal
> > We can have 2 possible solutions to this situation
> >
> > 1. Arm host it somewhere and let people contribute to that.
> > 2. Integrate it inside DPDK repo.
>
> [Honnappa] I don't have any issues with the 2nd option.
So you want t
23/10/2019 04:50, Jerin Jacob:
> In past, there was a concern with this approach about maintaining the
> assembly code in dpdk.org. Is this concern still valid?
[...]
> DPDK does not define any such interface. It was pushed to external library
> for the reason mentioned above.
Yes it is questionab
Hi Andrew,
> -Original Message-
> From: Andrew Rybchenko
> Sent: Tuesday, October 22, 2019 2:38 PM
> To: Ori Kam ; Thomas Monjalon
> ; Ferruh Yigit
> Cc: dev@dpdk.org; jingjing...@intel.com; step...@networkplumber.org
> Subject: Re: [PATCH v4 02/15] ethdev: add support for hairpin queue
for SGMII interfaces, there can be 0 value
written on MAC registers.
This patch set the random MAC address for those
interfaces.
Signed-off-by: Gagandeep Singh
---
drivers/net/enetc/Makefile | 2 +-
drivers/net/enetc/enetc_ethdev.c | 31 +++
2 files changed, 32
dpaaX is used to maintain a local copy of PA->VA translations.
Using the rte_mem_virt2iova or rte_mem_virt2phy is expensive. This
library is an attempt to reduce the overall cost associated with
this translation.
This patch enables this dpaaX library by populating a dpaaX's
table for PA to VA tra
v2 change-log:
* dpaax integration added
* compilation fixed
v3 change-log:
* added missing BD ring alignment patch
v4 change-log:
* fixed meson build
v5 change-log:
* added NOTICE log level
* added fix line for BD ring alignment fix
* updated commit message for dpaaX patch
Gagandeep Singh (4):
enetc BD rings should be aligned to 128
instead of RTE_CACHE_LINE_SIZE.
Fixes: 469c6111a7 ("net/enetc: enable Rx and Tx")
Cc: sta...@dpdk.org
Signed-off-by: Gagandeep Singh
---
drivers/net/enetc/base/enetc_hw.h | 3 +++
drivers/net/enetc/enetc_ethdev.c | 8
2 files changed, 7 insertio
To display random MAC address as notice,
a log level NOTICE is added.
Signed-off-by: Gagandeep Singh
---
drivers/net/enetc/enetc_ethdev.c | 4 +++-
drivers/net/enetc/enetc_logs.h | 2 ++
2 files changed, 5 insertions(+), 1 deletion(-)
diff --git a/drivers/net/enetc/enetc_ethdev.c b/drivers/ne
Max queue indices ACTION_RSS_QUEUE_NUM , which limits testpmd actions
rss queue size, has worked for a long time.
As more powered PMD is merged, more rss queues are supported(e.g. intel
ice driver FDIR supports up to 128 rss queue numbers).
The original max queue indices number doesn't satisfy PM
> -Original Message-
> From: Cao, Yahui
> Sent: Wednesday, October 23, 2019 6:58 PM
> To: Yang, Qiming ; Lu, Wenzhuo
>
> Cc: dev@dpdk.org; Zhang, Qi Z ; Ye, Xiaolong
> ; Xing, Beilei ; Cao, Yahui
>
> Subject: [PATCH] net/ice: fix IPv6 dest mac unsupported issue
>
> Fixes: 2dbef0825ef7
Hi Jerin,
> -Original Message-
> From: Jerin Jacob
> Sent: Saturday, October 12, 2019 9:04 PM
> To: Joyce Kong (Arm Technology China)
> Cc: dpdk-dev ; nd ; tho...@monjalon.net;
> jer...@marvell.com; Honnappa Nagarahalli
> ; Gavin Hu (Arm Technology China)
> ; sta...@dpdk.org
> Subject: R
On Wed, Oct 23, 2019 at 2:37 AM Honnappa Nagarahalli
wrote:
>
> > >
> > >
> > > >
> > > > On Thu, 2019-08-01 at 07:48 +0800, Gavin Hu wrote:
> > > > > Arm N1 SDP is an infrastructure segment development platform based
> > > > > on armv8.2-a Neoverse N1 CPU. For more information, refer to:
> > > >
On Tue, Oct 22, 2019 at 10:21:43AM +0200, David Marchand wrote:
> On x86, iopl permissions are only available to root user (or users that
> have the CAP_SYS_RAWIO capability).
> But those permissions are only needed when the virtio devices accesses
> are done with inb/outb instructions, which is wh
On Wed, Oct 23, 2019 at 8:25 AM Joyce Kong wrote:
>
> There are a lot functions of bit operations scattered and
> duplicated in PMDs, consolidating them into a common API
> family is necessary. Furthermore, the bit operation is
> mostly applied to the IO devices, so use __ATOMIC_ACQ_REL
> to ensur
On Tue, Oct 22, 2019 at 3:12 PM Rao, Nikhil wrote:
>
>
> > -Original Message-
> > From: Jerin Jacob [mailto:jerinjac...@gmail.com]
> > Sent: Tuesday, October 22, 2019 2:15 PM
> > To: Rao, Nikhil
> > Cc: Nipun Gupta ; Jerin Jacob ;
> > dpdk-dev ; Pavan Nikhilesh ;
> > Sunil Kumar Kori ; Ri
Update the cross build tool version to common description.
And remove the command 'git checkout' when cross builing
which results in compiling error.
Fixes: 01add9da25cd ("doc: add cross compiling guide")
Cc: sta...@dpdk.org
Signed-off-by: Joyce Kong
---
doc/guides/linux_gsg/cross_build_dpdk_fo
>
> Remove its own bit operation APIs and use the common one, this can reduce
> the code duplication largely.
>
> Signed-off-by: Joyce Kong
> Reviewed-by: Gavin Hu
> ---
> drivers/net/axgbe/axgbe_common.h | 29 +
> drivers/net/axgbe/axgbe_ethdev.c | 14 +++-
Fixes: 2dbef0825ef7 ("net/ice: add FDIR create and destroy")
Signed-off-by: Yahui Cao
---
drivers/net/ice/ice_fdir_filter.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/ice/ice_fdir_filter.c
b/drivers/net/ice/ice_fdir_filter.c
index 80da6ee24..a85a02cd0 100644
--- a/drivers/n
> -Original Message-
> From: Ananyev, Konstantin
> Sent: Wednesday, October 23, 2019 06:52
> To: Olivier Matz ; dev@dpdk.org
> Cc: Andrew Rybchenko ; Richardson, Bruce
> ; Wang,
> Haiyue ; Jerin Jacob Kollanukkaran
> ; Wiles, Keith
> ; Morten Brørup ; Stephen
> Hemminger
> ; Thomas Monja
> > On Tue, Oct 15, 2019 at 1:20 PM Joyce Kong wrote:
> > >
> > > There are a lot functions of bit operations scattered and duplicated
> > > in PMDs, consolidating them into a common API family is necessary.
> > > Furthermore, the bit operation is mostly applied to the IO devices,
> > > so use __A
Hi Joyce,
Thanks for the patch, few comments.
>
> There are a lot functions of bit operations scattered and duplicated in PMDs,
> consolidating them into a common API family is necessary. Furthermore, the
> bit operation is mostly applied to the IO devices, so use __ATOMIC_ACQ_REL
> to
> > > -Original Message-
> > > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Joyce Kong
> > > Sent: Tuesday, October 15, 2019 9:50 AM
> > >
> > > There are a lot functions of bit operations scattered and duplicated
> > > in PMDs, consolidating them into a common API family is necessa
Remove its own bit operation APIs and use the common one,
this can reduce the code duplication largely.
Signed-off-by: Joyce Kong
Reviewed-by: Gavin Hu
---
drivers/net/bnx2x/bnx2x.c| 209 +++
drivers/net/bnx2x/bnx2x.h| 4 -
drivers/net/bnx2x/eco
Remove its own bit operation APIs and use the common one,
this can reduce the code duplication largely.
Signed-off-by: Joyce Kong
Reviewed-by: Gavin Hu
---
drivers/net/qede/base/bcm_osal.c | 20
drivers/net/qede/base/bcm_osal.h | 10 --
2 files changed, 4 insertions
Remove its own bit operation APIs and use the common one,
this can reduce the code duplication largely.
Signed-off-by: Joyce Kong
Reviewed-by: Joyce Kong
---
drivers/net/hinic/base/hinic_compat.h | 35 +--
drivers/net/hinic/hinic_pmd_ethdev.c | 16 --
Remove its own bit operation APIs and use the common one,
this can reduce the code duplication largely.
Signed-off-by: Joyce Kong
Reviewed-by: Gavin Hu
---
drivers/net/axgbe/axgbe_common.h | 29 +
drivers/net/axgbe/axgbe_ethdev.c | 14 +++---
drivers/net/axgb
Add test cases for set bit, clear bit, test and set bit,
test and clear bit operations.
Signed-off-by: Joyce Kong
Reviewed-by: Gavin Hu
---
app/test/Makefile | 1 +
app/test/test_io_bitops.c | 86 +++
2 files changed, 87 insertions(+)
create
There are a lot functions of bit operations scattered in PMDs,
consolidate them into a common API family and applied in different
PMDs to reduce code duplication.
v2:
1. Add doxygen comments for the rte bit operation API(suggested by Stephen
Hemminger).
2. Add test cases for common rte bit op
There are a lot functions of bit operations scattered and
duplicated in PMDs, consolidating them into a common API
family is necessary. Furthermore, the bit operation is
mostly applied to the IO devices, so use __ATOMIC_ACQ_REL
to ensure the ordering.
Signed-off-by: Joyce Kong
Reviewed-by: Gavin
On Wed, 23 Oct, 2019, 2:02 am Honnappa Nagarahalli, <
honnappa.nagaraha...@arm.com> wrote:
>
>
> >
> > From: Jerin Jacob
> >
> > Update the armv8 crypto PMD maintainership.
> >
> > https://github.com/caviumnetworks/armv8_crypto external crypto the
> library
> > will not be maintained and probabl
> Many features require to store data inside the mbuf. As the room in mbuf
> structure is limited, it is not possible to have a field for each
> feature. Also, changing fields in the mbuf structure can break the API
> or ABI.
>
> This commit addresses these issues, by enabling the dynamic regist
> > > > Added my comments inline with your draft.
> > > > [snip]..
> > > >
> > > > >
> > > > > Ok, then my suggestion:
> > > > > Let's at least write down all points about crypto-dev approach where
> > > > > we
> > > > > disagree and then probably try to resolve them one by one
> > > > > If we
On Tue, 22 Oct 2019 21:34:17 +0200
David Marchand wrote:
> RTE_EAL_ALLOW_INV_SOCKET_ID had been introduced and documented as used
> with xen dom0 support (dropped for some time now).
>
> Closely looking at this, the code was changed later and ensures that the
> socket id is in the [0..RTE_MAX_NU
> >
> >
> > >
> > > On Thu, 2019-08-01 at 07:48 +0800, Gavin Hu wrote:
> > > > Arm N1 SDP is an infrastructure segment development platform based
> > > > on armv8.2-a Neoverse N1 CPU. For more information, refer to:
> > > > https://community.arm.com/developer/tools-software/oss-platforms/w
> > > >
>
> From: Jerin Jacob
>
> Update the armv8 crypto PMD maintainership.
>
> https://github.com/caviumnetworks/armv8_crypto external crypto the library
> will not be maintained and probably removed soon therefor updating the PMD
> documentation to reflect the same.
>
> Signed-off-by: Jerin Jaco
Adding specific logic for eal.c to support parsing on
Windows.
Signed-off-by: Pallavi Kadam
Signed-off-by: Antara Ganesh Kolar
Reviewed-by: Ranjit Menon
Reviewed-by: Keith Wiles
---
lib/librte_eal/windows/eal/eal.c | 119 +--
1 file changed, 112 insertions(+), 7 de
Support for additional common files in meson build
to expand Windows EAL and to support the lcore parsing
feature on Windows.
Signed-off-by: Pallavi Kadam
Signed-off-by: Antara Ganesh Kolar
Reviewed-by: Ranjit Menon
Reviewed-by: Keith Wiles
---
lib/librte_eal/windows/eal/meson.build | 8 +
Adding a function to detect process type and include
header files to contain suitable function declarations.
Signed-off-by: Pallavi Kadam
Signed-off-by: Antara Ganesh Kolar
Reviewed-by: Ranjit Menon
Reviewed-by: Keith Wiles
---
lib/librte_eal/windows/eal/eal.c| 51
Adding dirent.h on Windows to support common code.
The original contribution is under MIT license.
Signed-off-by: Antara Ganesh Kolar
Signed-off-by: Pallavi Kadam
Reviewed-by: Ranjit Menon
Reviewed-by: Keith Wiles
---
lib/librte_eal/windows/eal/include/dirent.h | 668
1 f
Adding dlfcn.h on Windows to support common code.
Adding eal_filesystem.h to support functions and
path defines for files and directories on Windows.
Adding getopt.h to support parsing options on Windows.
Modified \common\include\arch\x86\rte_vect.h
to include SSE4 header for Windows.
Signed-of
Adding additional function definitions for pthread, cpuset
implementation, asprintf implementation, in order to support
common code.
Signed-off-by: Pallavi Kadam
Signed-off-by: Antara Ganesh Kolar
Reviewed-by: Ranjit Menon
Reviewed-by: Keith Wiles
---
lib/librte_eal/windows/eal/include/pthrea
Adding initial stub to support command line parsing
for lcore mask option on Windows.
Signed-off-by: Pallavi Kadam
Signed-off-by: Antara Ganesh Kolar
Reviewed-by: Ranjit Menon
Reviewed-by: Keith Wiles
---
lib/librte_eal/windows/eal/eal.c| 29 ++---
lib/librte_eal/w
Adding getopt.c file to support parsing option on
Windows.
The original contribution is under BSD-2 license.
Signed-off-by: Antara Ganesh Kolar
Signed-off-by: Pallavi Kadam
Reviewed-by: Ranjit Menon
Reviewed-by: Keith Wiles
---
lib/librte_eal/windows/eal/getopt.c| 498
Adding syslog.h on Windows for supporting common code.
This implementation has BSD-3-Clause licensing.
Signed-off-by: Antara Ganesh Kolar
Signed-off-by: Pallavi Kadam
Reviewed-by: Ranjit Menon
Reviewed-by: Keith Wiles
---
lib/librte_eal/windows/eal/include/syslog.h | 189
This patchset includes additional functionalities for Windows EAL
to support command-line parsing feature and EAL common code
on Windows.
This patchset can be applied to windpdk-next-dev branch in the draft repo.
v3 Changes:
Modified generic rte_vect to add Windows support.
Moved
From: Nic Chautru
Polling of a MMIO register could misreport the actual value
set dynamically in hardware as the variable was not set explicitly
to volatile integer.
Fixes: efd453698c49 ("baseband/fpga_lte_fec: add driver for FEC on FPGA")
Cc: nicolas.chau...@intel.com
Cc: sta...@dpdk.org
Signe
Failures found when running validation with FPGA HW and the related FPGA PMD
driver on latest code base pre 19.11.
v2: Adding Fixes: and cc: stable to commit messages. (There is no Bugzilla Id
for these)
Two bug fixes below :
- The first error is a fatal failure during probing which was missed
From: Nic Chautru
A change to PCI mapping assumption was missed earlier, this causes
probing to fail with the fpga_lte_fec PMD when checking for name
of the rte_driver (not set yet) instead of the rte_pci_driver.
Fixes: 391797f04208 ("drivers/bus: move driver assignment to end of probing")
Cc: t
Thanks Akhil for helping make progress on this discussion.
From: Akhil Goyal
Sent: Tuesday, October 22, 2019 6:03 AM
To: Honnappa Nagarahalli
Cc: dev@dpdk.org; hemant.agra...@nxp.com; jer...@marvell.com;
tho...@monjalon.net
Subject: Armv8_crypto PMD future.
Hi Honnappa,
As per the comments r
RTE_EAL_ALLOW_INV_SOCKET_ID had been introduced and documented as used
with xen dom0 support (dropped for some time now).
Closely looking at this, the code was changed later and ensures that the
socket id is in the [0..RTE_MAX_NUMA_NODES] range anyway.
Let's drop this dead code and the build opti
https://bugs.dpdk.org/show_bug.cgi?id=355
Bug ID: 355
Summary: Meson build failure
Product: DPDK
Version: unspecified
Hardware: ARM
OS: Linux
Status: UNCONFIRMED
Severity: major
Priority: Normal
On 22/10/2019 18:44, Abhishek Marathe wrote:
> Hi Kevin,
>
Hi Abhishek,
> We ran DPDK 18.11.2 and 18.11.3-rc1 and got the same results for both that is
> “PERF-DPDK-MULTICORE-PPS-F32” failed. With the current situation it seems
> like Multicore and DPDK 18.11.3 does not work well on Azure.
O
> -Original Message-
> From: dev On Behalf Of Ananyev, Konstantin
> Sent: Tuesday, October 22, 2019 5:00 PM
> To: 'Honnappa Nagarahalli' ; 'Jerin Jacob'
>
> Cc: 'David Christensen' ; 'olivier.m...@6wind.com'
> ; 'sthem...@microsoft.com'
> ; 'jer...@marvell.com' ;
> Richardson, Bruce
Hi Akhil,
> > > Added my comments inline with your draft.
> > > [snip]..
> > >
> > > >
> > > > Ok, then my suggestion:
> > > > Let's at least write down all points about crypto-dev approach where we
> > > > disagree and then probably try to resolve them one by one
> > > > If we fail to make
On Tue, 22 Oct 2019 16:50:40 +
"Jakub Grajciar -X (jgrajcia - PANTHEON TECHNOLOGIES at Cisco)"
wrote:
> > Why does this not use abstract unix domain socket naming?
> > That would be much less error prone, because then the socket would
> > disappear when all applications using it are closed.
>> >> + /* Read packet from eventdev */
>> >> + if (!rte_event_dequeue_burst(event_d_id, port_id,
>> >&ev, 1, 0))
>> >> + continue;
>> >Is not this unlikely `nb_burst == 0`
>> >
>>
>> Not necessarily refer
>> https://urldefense.proofpoint.com/v2/url?u=https-
>3A__ma
On Tue, Oct 22, 2019 at 6:34 PM Stephen Hemminger
wrote:
>
> On Tue, 22 Oct 2019 11:32:40 +0200
> David Marchand wrote:
>
> > + if (f == NULL) {
> > + f = default_log_stream;
> > + if (f == NULL) {
> > + /*
> > + * Grab the curr
> Why does this not use abstract unix domain socket naming?
> That would be much less error prone, because then the socket would
> disappear when all applications using it are closed.
How would that work with containers? I'll consider that for a new patch, maybe
it could be optional?
On Tue, Oct 22, 2019 at 6:30 PM Stephen Hemminger
wrote:
>
> On Tue, 22 Oct 2019 11:05:01 +0200
> David Marchand wrote:
>
> > On Wed, Oct 2, 2019 at 9:40 PM Stephen Hemminger
> > wrote:
> > > +struct lcore_config {
> > > + pthread_t thread_id; /**< pthread identifier */
> > > +
The VXLAN related definitions and structures are moved from
rte_ether.h to a new header file: rte_xvlan.h.
Also introducing a new define macro for VXLAN default port id:
RTE_VXLAN_DEFAULT_PORT
Signed-off-by: Flavia Musatescu
---
app/test-pmd/csumonly.c| 1 +
app/test-pmd/util.c
On 10/22/2019 5:08 PM, Jakub Grajciar wrote:
> Define MEMIF_SOCKET_UN_SIZE to size of unix domain socket address.
> Report error in case of longer path.
>
> Fixes: b923866c6974 ("net/memif: allow for full key size in socket name")
> Cc: step...@networkplumber.org
>
> Signed-off-by: Jakub Grajciar
On Tue, 22 Oct 2019 18:08:29 +0200
Jakub Grajciar wrote:
> Cc: step...@networkplumber.org
>
> Signed-off-by: Jakub Grajciar
> ---
> doc/guides/nics/memif.rst | 2 +-
> drivers/net/memif/memif_socket.c | 27 +++
> drivers/net/memif/memif_socket.h | 6 --
>
> -Original Message-
> From: Ferruh Yigit
> Sent: Tuesday, October 22, 2019 6:33 PM
> To: Jakub Grajciar -X (jgrajcia - PANTHEON TECHNOLOGIES at Cisco)
> ; dev@dpdk.org
> Cc: step...@networkplumber.org
> Subject: Re: [dpdk-dev] [PATCH] net/memif: fix invalid unix domain address
> length
On Tue, 22 Oct 2019 11:32:41 +0200
David Marchand wrote:
> No need to expose rte_logs, hide it and remove it from the current ABI.
>
> Signed-off-by: David Marchand
> ---
> lib/librte_eal/common/eal_common_log.c | 23 ---
> lib/librte_eal/common/include/rte_log.h | 20 +++-
On Tue, 22 Oct 2019 11:32:40 +0200
David Marchand wrote:
> + if (f == NULL) {
> + f = default_log_stream;
> + if (f == NULL) {
> + /*
> + * Grab the current value of stderr here, rather than
> + * just initi
On Tue, 22 Oct 2019 11:05:01 +0200
David Marchand wrote:
> On Wed, Oct 2, 2019 at 9:40 PM Stephen Hemminger
> wrote:
> > +struct lcore_config {
> > + pthread_t thread_id; /**< pthread identifier */
> > + int pipe_master2slave[2]; /**< communication pipe with master */
> > +
Define MEMIF_SOCKET_UN_SIZE to size of unix domain socket address.
Report error in case of longer path.
Fixes: b923866c6974 ("net/memif: allow for full key size in socket name")
Cc: step...@networkplumber.org
Signed-off-by: Jakub Grajciar
---
doc/guides/nics/memif.rst | 2 +-
drivers/n
> -Original Message-
> From: David Marchand
> Sent: Tuesday, October 22, 2019 6:17 PM
> To: Ananyev, Konstantin
> Cc: Gavin Hu (Arm Technology China) ; dev
> ; nd ; tho...@monjalon.net; Stephen
> Hemminger ; hemant.agra...@nxp.com;
> jer...@marvell.com; Pavan Nikhilesh ;
> Honnappa Nagara
> -Original Message-
> From: Ananyev, Konstantin
> Sent: Tuesday, October 22, 2019 5:37 PM
> To: David Marchand ; Gavin Hu (Arm
> Technology China)
> Cc: dev ; nd ; tho...@monjalon.net;
> Stephen Hemminger ;
> hemant.agra...@nxp.com; jer...@marvell.com; Pavan Nikhilesh
> ; Honnappa Nagar
> > I have applied your
> > suggestion in 6/6 in v6 along with my corrections. The rte_ring_elem test
> > cases are added in 3/6. I have verified that they are running
> > fine (they are done for 64b alone, will add more). Hopefully, there are no
> > more errors.
Applied v6 and re-run the test
>>
>> It's not a quantifier of each port, It across the eventdevice that the
>number of
>> event queues is equal to number of ethdevices used.
>>
>> This is to prevent event queues being overcrowded i.e. in case there
>is only one
>> event queue and multiple Eth devices then SW/HW will have a
>bot
On 10/22/2019 5:26 PM, Ting Xu wrote:
> This patch enables testpmd to forward GTP packet in csum fwd mode.
> A GTP header structure (without optional fields and extension header)
> is defined in new rte_gtp.h. A parser function in testpmd is added.
> GTPU and GTPC packets are both supported, with r
Signed-off-by: Bruce Richardson
Acked-by: Luca Boccassi
---
examples/meson.build| 3 ++-
examples/server_node_efd/{ => node}/meson.build | 9 ++---
2 files changed, 8 insertions(+), 4 deletions(-)
rename examples/server_node_efd/{ => node}/meson.build (60%)
diff
Signed-off-by: Bruce Richardson
---
examples/meson.build| 1 +
examples/vm_power_manager/guest_cli/meson.build | 4
2 files changed, 1 insertion(+), 4 deletions(-)
diff --git a/examples/meson.build b/examples/meson.build
index 8a15dafcf..5a235545a 100644
--- a/ex
Building the example with clang gives the error:
error: expression which evaluates to zero treated as a null pointer
constant of type 'const char *' [-Werror,-Wnon-literal-null-conversion]
lcore_id, UINT8);
^
This error is due to t
Signed-off-by: Bruce Richardson
Acked-by: Luca Boccassi
---
examples/meson.build | 1 +
.../pthread_shim/meson.build | 28 +++
2 files changed, 29 insertions(+)
create mode 100644 examples/performance-thread/pthread_shim/meson.build
di
When adding to the build, add in two missing includes that prevented build
on freebsd, rather than just duplicating the makefile restriction.
Signed-off-by: Bruce Richardson
Acked-by: Luca Boccassi
---
V3: add in missing headers for build compilation
---
examples/meson.build
Limited to x86_64 systems, as it fails to compile on any others and is
disabled in the examples makefile for non-x86_64 systems.
Signed-off-by: Bruce Richardson
Acked-by: Luca Boccassi
---
examples/meson.build | 3 ++-
.../l3fwd-thread/meson.build | 27
The warnings about functions not returning values can be removed from the
code by just adding an attribute to the function to specifies it doesn't
return. The GCC bug referenced in the makefile which prevents this from
working has been fixed for >10 years according to bugzilla.
Signed-off-by: Bruc
Since the code for the ethtool example was contained in subdirectories the
compilation of this example is different from most of the other apps, and
it had not been abled when the user requests a build with "-Dexamples=all".
To simplify the build with meson, the separate ethtool library is not bui
The examples/bpf directory does not contain an example app, but rather
example code for use with testpmd's BPF support. Therefore, we should not
attempt to build it when the user requests "examples=all". This also
synchronises the meson behaviour with make which similarly doesn't compile
up the cod
When build with meson, some examples were skipped when "-Dexamples=all"
parameter was passed. Ignoring examples slated for removal by other
patches[1], this set adds support for building the rest of the examples.
The only exception is "bpf" which is a set of code snippets rather than
code to be nat
Other than real PCI reads and writes to the device memory requiring
the io barriers, virtual pci memories are normal memory in the smp
configuration, and requires the smp barriers.
Since the smp barriers and io barriers are identical on x86 and PPC,
this change has only effect on aarch64.
As far
Armv8's peripheral coherence order is a total order on all reads and writes
to that peripheral.[1]
The Peripheral coherence order for a Memory-mapped peripheral signifies the
order in which accesses arrive at the endpoint. For a read or a write RW1
and a read or a write RW2 to the same peripheral
Other than real PCI reads and writes to the device memory requiring
the io barriers, virtual pci memories are normal memory in the smp
configuration, which requires the smp barriers.
Since the smp barriers and io barriers are identical on x86 and PPC,
this change has only effect on aarch64.
As fa
Armv8's peripheral coherence order is a total order on all reads and
writes to that peripheral, that makes a compiler barrier is enough for
abstracted rte io barrier.
For virtual PCI devices, the virtual device memory is actually normal
memory and the Hypervisor view of things takes precedence and
>-Original Message-
>From: Ferruh Yigit
>Sent: Tuesday, October 22, 2019 7:51 PM
>To: Andrew Rybchenko ; Pavan Nikhilesh
>Bhagavatula ; Jerin Jacob Kollanukkaran
>
>Cc: dev@dpdk.org; Adrien Mazarguil ;
>Thomas Monjalon ; Xiaolong Ye
>; Bruce Richardson
>
>Subject: Re: [dpdk-dev] [PATCH v12
On Tue, Oct 22, 2019 at 11:56 AM Shahaf Shuler wrote:
>
> Thursday, October 17, 2019 8:19 PM, Jerin Jacob:
> > Subject: Re: [dpdk-dev] [RFC PATCH 20.02] mbuf: hint PMD not to inline
> > packet
> >
> > On Thu, Oct 17, 2019 at 4:30 PM Shahaf Shuler
> > wrote:
> > >
> > > Thursday, October 17, 2019
> -Original Message-
> From: Akhil Goyal
> Sent: Tuesday, October 22, 2019 2:24 PM
> To: Trahe, Fiona ; dev@dpdk.org
> Cc: Kusztal, ArkadiuszX ; Dybkowski, AdamX
>
> Subject: RE: [PATCH v2] cryptodev: clarify wireless inputs in
> digest-encrypted cases
>
>
>
> >
> > Clarify constra
> -Original Message-
> From: Kusztal, ArkadiuszX
> Sent: Tuesday, October 22, 2019 3:22 PM
> To: dev@dpdk.org
> Cc: akhil.go...@nxp.com; Trahe, Fiona ; Kusztal,
> ArkadiuszX
> ; sta...@dpdk.org
> Subject: [PATCH] crypto/qat: fix aes cmac mininum digest size
>
> AES-CMAC is used in 3gpp
On 10/19/2019 12:48 AM, Ye Xiaolong wrote:
> On 09/30, Ciara Loftus wrote:
>> This patch enables the unaligned chunks feature for AF_XDP which allows
>> chunks to be placed at arbitrary places in the umem, as opposed to them
>> being required to be aligned to 2k. This allows for DPDK application
>>
AES-CMAC is used in 3gpp specifications hence it is needed
to support 4 byte digest.
Fixes: 91c1daa4e1f0 ("crypto/qat: support AES-CMAC")
Cc: sta...@dpdk.org
Signed-off-by: Arek Kusztal
---
drivers/crypto/qat/qat_sym_capabilities.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --g
On 10/22/2019 11:16 AM, Andrew Rybchenko wrote:
> Hi,
>
> @Pavan, see question below.
>
> On 10/21/19 6:34 PM, Ferruh Yigit wrote:
>> On 10/21/2019 4:19 PM, Pavan Nikhilesh Bhagavatula wrote:
>>> Hi Ferruh,
>>>
-Original Message-
From: Ferruh Yigit
Sent: Monday, October 21
This commit adds RSA tests to Intel QuickAssist Technology pmd
and OpenSSL pmd test suite for session and session-less cases
when PADDING_NONE selected
Signed-off-by: Arek Kusztal
---
app/test/test_cryptodev_asym.c | 140 --
app/test/test_cryptodev_rsa_test_vectors.h
This commit extends RSA implementation by CRT option
Signed-off-by: Arek Kusztal
---
doc/guides/cryptodevs/features/qat.ini | 1 +
doc/guides/rel_notes/release_19_11.rst | 2 +
.../qat/qat_adf/qat_pke_functionality_arrays.h | 9
drivers/crypto/qat/qat_asym.c
This commit adds rsa algorithm to asymmetric pmd
using pair (n, d) private key
Signed-off-by: Arek Kusztal
---
doc/guides/cryptodevs/features/qat.ini | 2 +
doc/guides/cryptodevs/qat.rst | 1 +
doc/guides/rel_notes/release_19_11.rst | 2 +
.../q
This commit adds asymmetric sessionless tests to mod exp.
Signed-off-by: Arek Kusztal
---
app/test/test_cryptodev_asym.c | 73 --
1 file changed, 49 insertions(+), 24 deletions(-)
diff --git a/app/test/test_cryptodev_asym.c b/app/test/test_cryptodev_asym.
This patchset adds session-less option, RSA algorithm, RSA-CRT algorithm
to Intel QuickAssist Technology PMD. It also adds session-less test cases
for those algorithms.
Test case for RSA signature with no padding will be sent in a later patch.
[1]crypto/qat: add sessionless implementation to asym
This patch adds option to use asymmetric crypto pmd with
session-less support.
Signed-off-by: Arek Kusztal
---
doc/guides/cryptodevs/features/qat.ini | 1 +
doc/guides/rel_notes/release_19_11.rst | 4 +
drivers/crypto/qat/qat_asym.c | 328 -
drivers/c
Hi Ferruh,
Can you please explain the problems in using kni dedicated mbuf alloc routines
while enabling kni iova=va mode. Please see the below discussion with Andrew.
He wanted to know the problems in having newer APIs.
I wanted to clarify ourselves about the need of mem pool patch(V11 1/4) an
1 - 100 of 176 matches
Mail list logo
