On Tue, Mar 12, 2019 at 10:42:39AM -0700, Stephen Hemminger wrote:
> On Tue, 12 Mar 2019 15:13:07 +0800
> Tiwei Bie wrote:
>
> > The multiqueue support in virtio-user with vhost kernel backend
> > is broken when tap name isn't specified by users explicitly,
> > because the tap name returned by io
On Tue, Mar 12, 2019 at 03:54:09PM +0100, Maxime Coquelin wrote:
> rte_vhost_driver_set_protocol_features API is to be used
> by external backends to advertize vhost-user protocol
> features it supports.
>
> It has to be called after rte_vhost_driver_register() and
> before rte_vhost_driver_start(
The return value from bus->find_device is a rte_device
which is not safe to cast to a rte_vdev_device structure.
It doesn't really matter since only being checked for NULL
but static checkers might find a bug here.
Signed-off-by: Stephen Hemminger
---
drivers/net/vdev_netvsc/vdev_netvsc.c | 7 ++
Add target git sub-tree information for libraries, this is mainly to
reduce apply failures of the patches by automating target sub-tree
selection for a patch for automation.
Also can be useful for developers to define which tree to base their
patches for specific library.
Plan for DPDK Community
help
-- Original --
From: "dev-request";
Date: Wed, Mar 13, 2019 04:51 AM
To: "dev";
Subject: dev Digest, Vol 238, Issue 42
Send dev mailing list submissions to
dev@dpdk.org
To subscribe or unsubscribe via the World Wide Web, visit
https
On Tue, 12 Mar 2019 21:51:37 +0100
Thomas Monjalon wrote:
> 12/03/2019 21:46, Luca Boccassi:
> > On Tue, 2019-03-12 at 19:12 +, Kevin Traynor wrote:
> > > So what to do with short term stables? Some choices could be:
> > >
> > > - continue with short term stables for n.02/05/08
> > > - ad-
> Bruce Richardson (6):
> eal/bsdapp: rename to freebsd
> eal/linuxapp: rename to linux
> build/linux: rename macro from LINUXAPP to LINUX
> build/freebsd: rename macro from BSDPAPP to FREEBSD
> build/meson: change linuxapp to linux in meson cross files
> build: allow linux and freebsd
12/03/2019 21:46, Luca Boccassi:
> On Tue, 2019-03-12 at 19:12 +, Kevin Traynor wrote:
> > So what to do with short term stables? Some choices could be:
> >
> > - continue with short term stables for n.02/05/08
> > - ad-hoc support for short term stables where community have an
> > interest
>
On Tue, 2019-03-12 at 19:12 +, Kevin Traynor wrote:
> Hi All,
>
> This is about short term stable maintenance, ~3 months based on
> n.02/05/08 DPDK. It is **not** referring/impacting DPDK LTS,
> maintained
> for ~2 years based on n.11 DPDK.
>
> The effort and usefulness of short term stable m
From: Pavan Nikhilesh
Start ethdev after the Rx/Tx adapter setup is complete as in some
architectures it might lead to undefined behaviour or events being
dropped.
Signed-off-by: Pavan Nikhilesh
---
v3 Changes:
- add the same changes in examples/eventdev_pipeline
examples/eventdev_pipeline/
From: Pavan Nikhilesh
EventDev i.e consumer needs to be started before starting the
event producers.
Update documentation of EventDev and EventDev adapters.
Signed-off-by: Pavan Nikhilesh
---
v2 Changes: Add Notes to doxygen API.
doc/guides/prog_guide/event_crypto_adapter.rst | 5 +
From: Pavan Nikhilesh
Start event producers after eventdev i.e. consumer is started as in some
architectures it might lead to undefined behaviour or events being
dropped.
Signed-off-by: Pavan Nikhilesh
Reviewed-by: Jerin Jacob
---
app/test-eventdev/test_perf_atq.c | 31 +
12/03/2019 20:25, Jerin Jacob Kollanukkaran:
> On Fri, 2019-03-01 at 18:28 +0100, Thomas Monjalon wrote:
> > External Email
> >
> > ---
> > ---
> > 01/03/2019 18:05, Ferruh Yigit:
> > > On 10/11/2017 3:33 PM, jerin.jacob at caviumnetw
Original vlan offload code declared callbacks, but did not
> enable the feature offload bit
>
> Cc: sta...@dpdk.org
> Fixes: f7c2c2c8c558 ("net/atlantic: implement VLAN filters and offloads")
> Signed-off-by: Igor Russkikh
> ---
> Reviewed-by: Rami Rosen
>
>
The octeontx driver is creating vdev with name "OCTEONTX_PMD"
which is an artifact from how RTE_PMD_REGISTER_VDEV arguments
work.
Change to use the same convention as all the other network
driverse ("net_octeontx").
Signed-off-by: Stephen Hemminger
---
drivers/net/octeontx/octeontx_ethdev.h |
On Fri, 2019-03-01 at 18:28 +0100, Thomas Monjalon wrote:
> External Email
>
> ---
> ---
> 01/03/2019 18:05, Ferruh Yigit:
> > On 10/11/2017 3:33 PM, jerin.jacob at caviumnetworks.com (Jerin
> > Jacob) wrote:
> > > From: Thomas Monjal
Hi All,
This is about short term stable maintenance, ~3 months based on
n.02/05/08 DPDK. It is **not** referring/impacting DPDK LTS, maintained
for ~2 years based on n.11 DPDK.
The effort and usefulness of short term stable maintenance was raised
previously and in the last DPDK Release meeting [1
On Tue, 2019-01-15 at 21:12 +0800, Joyce Kong wrote:
> From: Gavin Hu
>
> The __sync builtin based implementation generates full memory
> barriers
> ('dmb ish') on Arm platforms. Using C11 atomic builtins to generate
> one
> way barriers.
>
> Here is the assembly code of __sync_compare_and_swap
On Tue, 12 Mar 2019 15:13:07 +0800
Tiwei Bie wrote:
> The multiqueue support in virtio-user with vhost kernel backend
> is broken when tap name isn't specified by users explicitly,
> because the tap name returned by ioctl(TUNSETIFF) isn't saved
> properly, and multiple tap interfaces will be crea
On Tue, 12 Mar 2019 18:07:42 +0200
Rami Rosen wrote:
> This patch fixes rte_ethdev header file to use the correct method name,
> namely to use rte_eth_dev_info_get() instead of
> rte_eth_dev_infos_get().
>
> Fixes: a4996bd89c42 ("ethdev: new Rx/Tx offloads API")
> Fixes: 4f5701f28bd4 ("examples
The fslmc bus code was duplicating the device name and
doing extra initialization. The code can be simplified
to just use the device name directly.
Compile tested only; do not have this hardware.
Signed-off-by: Stephen Hemminger
---
drivers/bus/fslmc/fslmc_bus.c | 38 +++
When fslmc is built as part of a general distribution, the
bus code will log errors when other devices are present.
This could confuse users it is not an error.
Fixes: 50245be05d1a ("bus/fslmc: support device blacklisting")
Signed-off-by: Stephen Hemminger
---
drivers/bus/fslmc/fslmc_bus.c | 2
These were sent previously but not picked up.
Resending and adding nxp maintainers.
Stephen Hemminger (2):
bus/fslmc: don't log error for other devices
bus/fslmc: remove unneeded strdup
drivers/bus/fslmc/fslmc_bus.c | 40 ---
1 file changed, 13 insertions(+),
Change log:
-V1: First version of the patch.
-V2: Update the commit message to describe the ordering of detailed memory
accesses.
-V3: As suggested by Konstantin Ananyev, remove the rte_smp_rmb for enqueue
case, as there is a control dependency in place, making rmb unnecessary. For
dequeue
From: gavin hu
In weak memory models, like arm64, reading the prod.tail may get
reordered after reading the ring slots, which corrupts the ring and
stale data is observed.
This issue was reported by NXP on 8-A72 DPAA2 board. The problem is most
likely caused by missing the acquire semantics when
There is a corner case in which driver won't post
receive buffers when driver has processed all received packets
in single loop (i.e. hw_consumer == sw_consumer) and then
HW will start dropping packets since it did not see new receive
buffers posted.
This corner case is seen when size of Rx ring i
On 12.03.2019 17:54, Maxime Coquelin wrote:
> External backends may have specific requests to handle, and so
> we don't want the vhost-user lib to handle these requests as
> errors.
>
> This patch also changes the experimental API by introducing
> RTE_VHOST_MSG_RESULT_NOT_HANDLED so that vhost-use
This patch fixes rte_ethdev header file to use the correct method name,
namely to use rte_eth_dev_info_get() instead of
rte_eth_dev_infos_get().
Fixes: a4996bd89c42 ("ethdev: new Rx/Tx offloads API")
Fixes: 4f5701f28bd4 ("examples: fix RSS hash function configuration")
Signed-off-by: Rami Rosen
Hi, Ferruh
Thanks for your review.
On 03/11, Ferruh Yigit wrote:
>On 3/1/2019 8:09 AM, Xiaolong Ye wrote:
>> Add a new PMD driver for AF_XDP which is a proposed faster version of
>> AF_PACKET interface in Linux. More info about AF_XDP, please refer to [1]
>> [2].
>>
>> This is the vanilla versio
Max number of xstats items was returned instead of actual number
of filled in records.
Cc: sta...@dpdk.org
Fixes: fbe059e87209 ("net/atlantic: implement device statistics")
Signed-off-by: Igor Russkikh
---
drivers/net/atlantic/atl_ethdev.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-
Original vlan offload code declared callbacks, but did not
enable the feature offload bit
Cc: sta...@dpdk.org
Fixes: f7c2c2c8c558 ("net/atlantic: implement VLAN filters and offloads")
Signed-off-by: Igor Russkikh
---
drivers/net/atlantic/atl_ethdev.c | 3 ++-
1 file changed, 2 insertions(+), 1 d
Default rxtx logging used ERR level, that caused logger to always
trigger. That may cause perf degradation even if logger was not enabled but
compiled in.
Signed-off-by: Igor Russkikh
---
drivers/net/atlantic/atl_rxtx.c | 16
1 file changed, 4 insertions(+), 12 deletions(-)
dif
In case link speed is re configured after port start, it does not
takes the requested speed value, but instead just sets full autoneg
mask.
Cc: sta...@dpdk.org
Fixes: 7943ba05f67c ("net/atlantic: add link status and interrupt management")
Signed-off-by: Igor Russkikh
---
drivers/net/atlantic/atl
From: Pavel Belous
Fixes: ce4e8d418097 ("net/atlantic: implement EEPROM get/set")
Cc: sta...@dpdk.org
Signed-off-by: Igor Russkikh
Signed-off-by: Pavel Belous
---
.../net/atlantic/hw_atl/hw_atl_utils_fw2x.c | 28 ---
1 file changed, 24 insertions(+), 4 deletions(-)
diff --gi
From: Pavel Belous
Default dev addr is replaced with magic field from the request.
Length is allowed to be less than maximum.
SMBUS access bit definitions also better organised now.
Signed-off-by: Igor Russkikh
Signed-off-by: Pavel Belous
---
drivers/net/atlantic/atl_ethdev.c | 25
From: Pavel Belous
Found by Coverity scan. This is a real memory corruption.
There is no need in extra RTE_ALIGN macros since the
request/result structures are 4-byte aligned by definition.
Cc: sta...@dpdk.org
Fixes: ce4e8d418097 ("net/atlantic: implement EEPROM get/set")
Coverity issue: 323518
Found by Coverity scan. Checks are useless
because at these code places err is always zero.
Signed-off-by: Igor Russkikh
---
drivers/net/atlantic/hw_atl/hw_atl_utils.c | 5 +
1 file changed, 1 insertion(+), 4 deletions(-)
diff --git a/drivers/net/atlantic/hw_atl/hw_atl_utils.c
b/drivers/ne
Found by coverity scan.
Fixes: 7906661edac6 ("net/atlantic: add b0 hardware layer")
Coverity issue: 323512
Signed-off-by: Igor Russkikh
---
drivers/net/atlantic/hw_atl/hw_atl_b0.c | 6 +-
1 file changed, 1 insertion(+), 5 deletions(-)
diff --git a/drivers/net/atlantic/hw_atl/hw_atl_b0.c
b/
These are just convention breakage on rte_errno,
no real harm from that.
Cc: sta...@dpdk.org
Signed-off-by: Igor Russkikh
Fixes: 2b1472d7150c ("net/atlantic: implement Tx path")
---
drivers/net/atlantic/atl_rxtx.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/ne
The patchset mainly fixes some Coverity issues,
couple of minor bugs and overflows.
It also improves eeprom get/set logic with ability of custom
device address and dump length.
v3: added coverity ids where known
v2: better git log, line lengths, Fixes tags.
Igor Russkikh (7):
net/atlantic: f
On 03/11, Ferruh Yigit wrote:
>On 3/1/2019 8:09 AM, Xiaolong Ye wrote:
>> When create rte_mempool, flags can be parsed from command line.
>> Now, it is possible for testpmd to create a af_xdp friendly
>> mempool (which enable zero copy).
>>
>> Signed-off-by: Qi Zhang
>> Signed-off-by: Xiaolong Ye
The goals of this series is to provide more flexibility to external
backends to implement their specific vhost-user request handling
without having to patch vhost-user library.
First patch implements a new API for external backend to advertize
its specific protocol features to vhost-user master.
External backends may have specific requests to handle, and so
we don't want the vhost-user lib to handle these requests as
errors.
This patch also changes the experimental API by introducing
RTE_VHOST_MSG_RESULT_NOT_HANDLED so that vhost-user lib
can report an error if a message is handled neithe
rte_vhost_driver_set_protocol_features API is to be used
by external backends to advertize vhost-user protocol
features it supports.
It has to be called after rte_vhost_driver_register() and
before rte_vhost_driver_start().
Example of usage to advertize VHOST_USER_PROTOCOL_F_FOOBAR
protocol featu
On Fri, 2019-03-08 at 15:56 +0800, Gavin Hu wrote:
> ---
> ---
> The __sync builtin based implementation generates full memory
> barriers
> ('dmb ish') on Arm platforms. Using C11 atomic builtins to generate
> one way
> barriers.
>
>
"Parthasarathy, JananeeX M" writes:
> Hi
>
>>-Original Message-
>>From: Parthasarathy, JananeeX M
>>Sent: Tuesday, February 19, 2019 6:33 PM
>>To: Aaron Conole ; Poornima, PallantlaX
>>
>>Cc: dev@dpdk.org; Pattan, Reshma ; Rao, Nikhil
>>; sta...@dpdk.org
>>Subject: RE: [dpdk-dev] [PATCH]
> Improved MAC swap performance for ARM platform.
> The improvement was achieved by using neon intrinsics to save CPU cycles
> and doing swap for four packets at a time.
> The optimization had 15% - 20% throughput boost in testpmd MAC swap
> mode.
>
> Signed-off-by: Ruifeng Wang
> Reviewed-by: Ga
On 3/12/19 8:13 AM, Tiwei Bie wrote:
The multiqueue support in virtio-user with vhost kernel backend
is broken when tap name isn't specified by users explicitly,
because the tap name returned by ioctl(TUNSETIFF) isn't saved
properly, and multiple tap interfaces will be created in this
case. Fi
> -Original Message-
> From: dev On Behalf Of Konstantin Ananyev
> Sent: Thursday, March 7, 2019 7:43 PM
> To: dev@dpdk.org
> Cc: akhil.go...@nxp.com; umesh.kar...@caviumnetworks.com;
> pablo.de.lara.gua...@intel.com; shally.ve...@caviumnetworks.com;
> Konstantin Ananyev
> Subject: [dp
> On 12-Mar-19 10:20 AM, Bruce Richardson wrote:
>> On Tue, Mar 12, 2019 at 05:54:39PM +0800, Jason Wang wrote:
>>>
>>> On 2019/3/12 下午5:42, Thanneeru Srinivasulu wrote:
Thanks Bruce..
On Tue, Mar 12, 2019 at 3:08 PM Bruce Richardson
wrote:
> On Tue, Mar 12, 2019 at 10:57:5
On 12-Mar-19 1:47 AM, Lilijun (Jerry, Cloud Networking) wrote:
Hi Anatoly,
-Original Message-
From: Burakov, Anatoly [mailto:anatoly.bura...@intel.com]
Sent: Friday, March 08, 2019 5:38 PM
To: Lilijun (Jerry, Cloud Networking) ;
dev@dpdk.org
Cc: jerry.zh...@intel.com; ian.sto...@intel.c
On 12-Mar-19 10:20 AM, Bruce Richardson wrote:
On Tue, Mar 12, 2019 at 05:54:39PM +0800, Jason Wang wrote:
On 2019/3/12 下午5:42, Thanneeru Srinivasulu wrote:
Thanks Bruce..
On Tue, Mar 12, 2019 at 3:08 PM Bruce Richardson
wrote:
On Tue, Mar 12, 2019 at 10:57:55AM +0530, Thanneeru Srinivasulu
There is no guarantee that pthread_self() returns the thread ID or that
pthread_t is an integer. The thread ID is not that useful so simply
remove it.
This fixes the following warning when building with musl libc:
../lib/librte_eal/linuxapp/eal/eal_dev.c: In function 'sigbus_handler':
../lib/libr
The swab16/swab32/swab64 are Linux specific and nog GNU libc specific.
Keep the check for __GLIBC__ just in case other GNU systems depends on
this (Hurd or GNU/kFreeBSD).
This fixes a build error with musl libc.
Signed-off-by: Natanael Copa
---
v1 -> v2 fixed coding style issues reported by che
On Tue, Mar 12, 2019 at 05:54:39PM +0800, Jason Wang wrote:
>
> On 2019/3/12 下午5:42, Thanneeru Srinivasulu wrote:
> > Thanks Bruce..
> >
> > On Tue, Mar 12, 2019 at 3:08 PM Bruce Richardson
> > wrote:
> > > On Tue, Mar 12, 2019 at 10:57:55AM +0530, Thanneeru Srinivasulu wrote:
> > > > Hi Everyon
Current code is not properly giving the RSS information
regarding the redirection table.
Fixes: 934e4c60fbff ("nfp: add RSS")
Cc: sta...@dpdk.org
Signed-off-by: Alejandro Lucero
---
drivers/net/nfp/nfp_net.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/nfp/nfp
When piping the ninja command through cat, we lose the error value from
the call to ninja in the case of failure. This prevents the script from
exiting at the first broken build. Fix this by setting the "pipefail"
shell option.
Fixes: 4bcb9b768604 ("devtools: add verbose option to meson build test
define the macros so we can remove various #if defined(RTE_ARCH_X86)
Ref: https://bugs.dpdk.org/show_bug.cgi?id=35#c6
Signed-off-by: Natanael Copa
---
v1 -> v2 fixed coding style issues reported by checkpatch
drivers/bus/pci/linux/pci_uio.c | 54 +++--
1 file chang
Add a fallback for non-GNU libc systems like musl libc for the
non-standard functions outl_p, outw_p and outb_p.
This ifixes the following buildtime errors when building with musl libc:
pci_uio.c:(.text+0xaa1): undefined reference to `outw_p'
pci_uio.c:(.text+0xac5): undefined reference to `outl_
When piping the ninja command through cat, we lose the error value from
the call to ninja in the case of failure. This prevents the script from
exiting at the first broken build Fix this by setting the "pipefile"
shell option.
Fixes: 4bcb9b768604 ("devtools: add verbose option to meson build test
On Fri, Mar 8, 2019 at 10:28 AM Pallantla Poornima <
pallantlax.poorn...@intel.com> wrote:
> sprintf function is not secure as it doesn't check the length of string.
> More secure function snprintf is used.
>
> Fixes: 896c265ef9 ("net/nfp: use new CPP interface")
> Fixes: c4171b520b ("net/nfp: sup
On 2019/3/12 下午5:42, Thanneeru Srinivasulu wrote:
Thanks Bruce..
On Tue, Mar 12, 2019 at 3:08 PM Bruce Richardson
wrote:
On Tue, Mar 12, 2019 at 10:57:55AM +0530, Thanneeru Srinivasulu wrote:
Hi Everyone.
I did attached pice to Guest VM using vfio-pci with qemu command, and then
tried bin
This patch adds new test structure for modexp
and modinv for asymmetric cryptography
This patch depends on following patchsets:
[1] - crypotodev: add result field to modular operations
(http://patchwork.dpdk.org/cover/50255/)
[2] - Add PMD for asymmetric cryptography operations
using Intel QuickAs
This patch adds new test structure for modexp
and modinv for asymmetric cryptography
Signed-off-by: Damian Nowak
---
test/test/test_cryptodev.h | 1 +
test/test/test_cryptodev_asym.c | 319 +
test/test/test_cryptodev_mod_test_vectors.h | 966 +++
Thanks Bruce..
On Tue, Mar 12, 2019 at 3:08 PM Bruce Richardson
wrote:
>
> On Tue, Mar 12, 2019 at 10:57:55AM +0530, Thanneeru Srinivasulu wrote:
> > Hi Everyone.
> >
> > I did attached pice to Guest VM using vfio-pci with qemu command, and then
> > tried binding the pcie bdf with vfio-pci, obse
On Tue, Mar 12, 2019 at 10:57:55AM +0530, Thanneeru Srinivasulu wrote:
> Hi Everyone.
>
> I did attached pice to Guest VM using vfio-pci with qemu command, and then
> tried binding the pcie bdf with vfio-pci, observing binding failure with
> vfio-pci.
>
> Where as when tryied with igb_uio, every
va2pa depends on the physical address and virtual address offset of
current mbuf. It may get the wrong physical address of next mbuf which
allocated in another hugepage segment.
In rte_mempool_populate_default(), trying to allocate whole block of
contiguous memory could be failed. Then, it would r
On Mon, 2019-03-11 at 13:52 +, Jerin Jacob Kollanukkaran wrote:
> On Mon, 2019-03-11 at 06:51 +, Jerin Jacob Kollanukkaran wrote:
> > On Mon, 2019-02-04 at 07:18 +, Pallantla Poornima wrote:
> > > %'16"PRIu64" %s "
> > > diff --git a/drivers/event/opdl/opdl_evdev_xstats.c
> > > b/driver
On Mon, 2019-03-11 at 06:49 +, Pavan Nikhilesh Bhagavatula wrote:
> From: Pavan Nikhilesh
>
> Previously, the total number of event timers per adapter was set to
> an
> arbitrary value, set it to mempool size instead as it defines the max
> event timers that can be armed.
>
> Signed-off-by:
Hi
>-Original Message-
>From: Parthasarathy, JananeeX M
>Sent: Tuesday, February 19, 2019 6:33 PM
>To: Aaron Conole ; Poornima, PallantlaX
>
>Cc: dev@dpdk.org; Pattan, Reshma ; Rao, Nikhil
>; sta...@dpdk.org
>Subject: RE: [dpdk-dev] [PATCH] test/eventdev: fix sprintf with snprintf
>
>
>
>>
The multiqueue support in virtio-user with vhost kernel backend
is broken when tap name isn't specified by users explicitly,
because the tap name returned by ioctl(TUNSETIFF) isn't saved
properly, and multiple tap interfaces will be created in this
case. Fix this by saving the dynamically allocated
71 matches
Mail list logo
