On Mon, Jun 04, 2018 at 10:37:31AM -0700, Yongseok Koh wrote:
> rte_errno should be saved only if error has occurred because rte_errno
> could have garbage value.
>
> Fixes: a6d83b6a9209 ("net/mlx5: standardize on negative errno values")
> Cc: sta...@dpdk.org
>
> Signed-off-by: Yongseok Koh
> --
Hi everyone,
hope I can reach some DPDK developers in Taiwan via this mail.
If you're one you should definitely join our newly funded Out of The Box
Network Developers meetup:
https://www.meetup.com/Out-Of-The-Box-Network-Developers-Taipei
I will give a talk about "Fine-grained interaction contr
From: Sachin Saxena
Random corruptions observed on ARM platfoms with using
the dpdk library in shared mode with VPP software (plugin).
sing traditional TLS scheme resolved the issue.
Tested with VPP with DPDK as a plugin.
Signed-off-by: Sachin Saxena
---
mk/machine/armv8a/rte.vars.mk | 3 +++
Signed-off-by: Hemant Agrawal
---
lib/librte_eal/bsdapp/eal/eal.c | 22 +-
lib/librte_eal/common/include/rte_vfio.h | 40 +---
lib/librte_eal/linuxapp/eal/eal_vfio.c | 36 ++--
lib/librte_eal/rte_eal_version.map
Signed-off-by: Hemant Agrawal
---
lib/librte_mbuf/rte_mbuf.c | 2 +-
lib/librte_mbuf/rte_mbuf.h | 2 +-
lib/librte_mbuf/rte_mbuf_pool_ops.c | 10 +-
lib/librte_mbuf/rte_mbuf_pool_ops.h | 13 +
lib/librte_mbuf/rte_mbuf_version.map | 4 ++--
5 files chan
On 6/4/2018 8:22 AM, Jerin Jacob wrote:
ccache gcc -Idrivers/drivers@@tmp_rte_pmd_dpaa_sec@sta -Idrivers
In file included from ../drivers/bus/dpaa/include/fsl_usd.h:11,
from ../drivers/crypto/dpaa_sec/dpaa_sec.c:27:
../drivers/bus/dpaa/include/compat.h:53:
error: "__packed" re
On Mon, Jun 04, 2018 at 04:29:56PM +0200, Maxime Coquelin wrote:
> On 06/04/2018 01:55 PM, Tiwei Bie wrote:
> > On Fri, Jun 01, 2018 at 02:47:58PM +0200, Maxime Coquelin wrote:
[...]
> > > @@ -253,13 +246,15 @@ virtqueue_enqueue_xmit(struct virtnet_tx *txvq,
> > > struct rte_mbuf *cookie,
> > >
On Fri, May 25, 2018 at 12:10 PM, Thomas Monjalon wrote:
> 20/04/2018 11:53, Pablo de Lara:
>> Convert dual license headers with Intel and Dmitry Vyukov
>> names to SPDX.
>>
>> Signed-off-by: Pablo de Lara
>> ---
>> examples/performance-thread/common/lthread_pool.h | 68
>> +---
On 16/05/18 13:41, Ferruh Yigit wrote:
> Today after listening Colin's Static Analysis talk, I run cppcheck on
> v18.05-rc4
> code and it revealed some issues, sharing here for anyone to interested in
> fixing them. At least I encourage to check maintainers to check their own
> pieces.
>
> It is
Support rx of in direction packets only
Useful for apps that also tx to eth_pcap ports in order not to see them
echoed back in as rx when out direction is also captured
Signed-off-by: ido goshen
---
drivers/net/pcap/rte_eth_pcap.c | 34 +++---
1 file changed, 31 inser
01/06/2018 13:07, Thomas Monjalon:
> Signed-off-by: Thomas Monjalon
Applied
> ---
>
> The new release cycle is open, and it will be a short one!
>
> Please consider reviewing your peers, and contribute to respect
> the release schedule.
>
> If you think some patches are already ready for int
This patch renames u16 to u16_buf. u16 as a variable name causes a shadowed
declaration warning if, for example, the application also typedefs u16
(e.g. by including a header containing "typedef unsigned short u16") and
the application is built with -Wshadow.
Signed-off-by: Gage Eads
---
lib/lib
On Mon, 2018-06-04 at 09:58 +0100, Luca Boccassi wrote:
> Hi all,
>
> Here is a list of patches targeted for stable release 18.02.2. Please
> help review and test. The planned date for the final release is
> Thursday,
> the 14th of June. Before that, please shout if anyone has objections
> with th
https://dpdk.org/tracker/show_bug.cgi?id=61
Bug ID: 61
Summary: build fails when shared libs enabled and optimization
turned off
Product: DPDK
Version: 18.05
Hardware: All
OS: All
Status: CONFIRM
rte_errno should be saved only if error has occurred because rte_errno
could have garbage value.
Fixes: a6d83b6a9209 ("net/mlx5: standardize on negative errno values")
Cc: sta...@dpdk.org
Signed-off-by: Yongseok Koh
---
drivers/net/mlx5/mlx5_flow.c | 3 ++-
1 file changed, 2 insertions(+), 1 de
On 06/04/2018 01:59 PM, Tiwei Bie wrote:
On Fri, Jun 01, 2018 at 02:47:57PM +0200, Maxime Coquelin wrote:
Signed-off-by: Maxime Coquelin
---
drivers/net/virtio/virtio_ethdev.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/net/virtio/virtio_ethdev.c
b/drive
On 06/04/2018 01:55 PM, Tiwei Bie wrote:
On Fri, Jun 01, 2018 at 02:47:58PM +0200, Maxime Coquelin wrote:
Instead of checking the multiple Virtio features bits for
every packet, let's do the check once at configure time and
store it in virtio_hw struct.
Signed-off-by: Maxime Coquelin
---
This is fine but you are missing one bit. If a slave is added after you
can configured the MAC
addresses, you will need to replay the configured MAC addresses into that
slave.
It's not clear to me what the contract is between bonding and DPDK as far
as slave
removal. Just looking at the behavior
The Rx adapter stop call does not guarantee that the
SW service function will not execute after the
rte_event_eth_rx_adapter_stop() call.
Add a "started" flag to prevent the adapter from executing
if stop has been called.
Fixes: 9c38b704d280 ("eventdev: add eth Rx adapter implementation")
Signed-
-Original Message-
> Date: Mon, 4 Jun 2018 06:03:34 +
> From: Gavin Hu
> To: Jerin Jacob , Bruce Richardson
> , Thomas Monjalon
> CC: "dev@dpdk.org"
> Subject: RE: [dpdk-dev] [PATCH v5 2/2] doc: add a guide doc for cross
> compiling from x86
>
> See my inline comments:
>
> >
On Fri, Jun 01, 2018 at 02:47:56PM +0200, Maxime Coquelin wrote:
> This patch improves the Tx path selection depending on
> whether the application request for offloads, and on whether
> offload features have been negotiated.
>
> When the application doesn't request for Tx offload features,
> the
From: Rafal Kozik
Link speed should is not limited to 10Gb/s and it shouldn't be hardcoded.
They link speed is set to none instead and the applications shouldn't
rely on this value when using ENA PMD.
Fixes: 1173fca ("ena: add polling-mode driver")
Signed-off-by: Rafal Kozik
Acked-by: Michal
From: Rafal Kozik
ENA_MEM_ALLOC_NODE not need to use contiguous physical memory.
Also using memset without checking if allocation succeed can cause
segmentation fault.
To avoid both issue use rte_zmalloc_socket.
Fixes: 3d3edc265fc8 ("net/ena: make coherent memory allocation NUMA-aware")
Signed
From: Rafal Kozik
When use GENMASK_ULL(63,0) left shift by 64 bits is performed.
Shifting by number greater or equal then word length
is undefined operation and failed on some platforms.
Fixes: 9ba7981ec992 ("ena: add communication layer for DPDK")
Signed-off-by: Rafal Kozik
Acked-by: Michal K
The pointer received from rte_memzone_reserve from macro
ENA_MEM_ALLOC_COHERENT_NODE was not stored anywhere, and as a result
memory allocated by this macro could not been released.
Signed-off-by: Michal Krawczyk
---
drivers/net/ena/base/ena_plat_dpdk.h | 2 +-
1 file changed, 1 insertion(+), 1
From: Rafal Kozik
During initializing tx queues update Non-Uniform Memory Access
configuration in NIC firmware.
Signed-off-by: Rafal Kozik
Acked-by: Michal Krawczyk
---
drivers/net/ena/ena_ethdev.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/net/ena/ena_ethdev.c b/drivers/ne
From: Rafal Kozik
Need to check if memory allocation succeed before using it.
Using memset on NULL pointer cause segfault.
Fixes: 9ba7981ec992 ("ena: add communication layer for DPDK")
Signed-off-by: Rafal Kozik
Acked-by: Michal Krawczyk
---
drivers/net/ena/base/ena_plat_dpdk.h | 22
From: Rafal Kozik
Validate Tx req id during clearing completed packets.
If id is wrong, trigger NIC reset.
Signed-off-by: Rafal Kozik
Acked-by: Michal Krawczyk
---
drivers/net/ena/ena_ethdev.c | 25 +
1 file changed, 25 insertions(+)
diff --git a/drivers/net/ena/ena_e
From: Rafal Kozik
Adjust error checking and cleaning to Linux driver:
* add checking if MTU is to small,
* fix error messages (mismatched Rx and Tx),
* return error received from base driver or proper error
code instead of -1,
* in case of error release occupied resources,
* in case of Rx
From: Rafal Kozik
Add likely and unlikely statements to increase performance.
Signed-off-by: Rafal Kozik
Acked-by: Michal Krawczyk
---
drivers/net/ena/ena_ethdev.c | 8
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ena/ena_ethdev.c b/drivers/net/ena/ena_et
From: Rafal Kozik
Enable AENQ FATAL_ERROR and WARNING callbacks by setting flags
in aenq_groups. They are handled by "unimplemented handler".
If unimplemented handler is called, error is logged.
Signed-off-by: Rafal Kozik
Acked-by: Michal Krawczyk
---
drivers/net/ena/ena_ethdev.c | 7 +--
From: Rafal Kozik
Move configuration of IO queue numbers to separate function and take
into consideration max number of IO completion queues.
Signed-off-by: Rafal Kozik
Acked-by: Michal Krawczyk
---
drivers/net/ena/ena_ethdev.c | 21 -
1 file changed, 20 insertions(+), 1 d
From: Rafal Kozik
In function ena_infos_get driver provides information about minimal
and maximal number of Rx and Tx descriptors.
Signed-off-by: Rafal Kozik
Acked-by: Michal Krawczyk
---
drivers/net/ena/ena_ethdev.c | 13 +
1 file changed, 13 insertions(+)
diff --git a/drivers/n
From: Rafal Kozik
Function ena_check_and_linearize_mbuf check Tx mbuf for number of
segments and linearize (defragment) it if necessary. It is called
before sending each packet.
Information about maximum number of segments is stored per each ring.
Maximum number of segments supported by NIC is
This feature allows RX packets to be cleaned up out of order.
Signed-off-by: Michal Krawczyk
---
drivers/net/ena/ena_ethdev.c | 48
drivers/net/ena/ena_ethdev.h | 8 ++--
2 files changed, 50 insertions(+), 6 deletions(-)
diff --git a/drivers/net
From: Rafal Kozik
Add variable wd_state to make driver functional without keep alive
AENQ handler.
The watchdog will be executed only if the aenq group has keep alive
enabled.
Signed-off-by: Rafal Kozik
Acked-by: Michal Krawczyk
---
drivers/net/ena/ena_ethdev.c | 19 +++
drive
The admin queue can stop responding or became inactive due to unexpected
behaviour of the device. In that case, the whole device should be
restarted.
Signed-off-by: Michal Krawczyk
---
drivers/net/ena/ena_ethdev.c | 37 +
drivers/net/ena/ena_ethdev.h | 2 ++
Keep alive is executing AENQ interrupt periodically. It allows to check
health of the device and trigger reset event if the device will stop
responding.
To check for the state of the device, the DPDK application must call
rte_timer_manage().
Signed-off-by: Michal Krawczyk
---
drivers/net/ena/en
There is no need to check for restart all queues. It is sufficient to
check only previously initialized queues.
Signed-off-by: Michal Krawczyk
---
drivers/net/ena/ena_ethdev.c | 13 +
1 file changed, 9 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ena/ena_ethdev.c b/drivers
ENA PMD is only PMD which is using librte_timer. In linking routine
rte_timer is linked before PMDs, so if timers are not being used by the
applications, they are just cut out.
Signed-off-by: Michal Krawczyk
---
mk/rte.app.mk | 1 +
1 file changed, 1 insertion(+)
diff --git a/mk/rte.app.mk b/mk
Reset routine can be used by the DPDK application to reset the device in
case of receiving RTE_ETH_EVENT_INTR_RESET from the PMD.
The reset event is not triggered by the driver, yet. It will be added in
next commits to enable error recovery in case of misfunctioning of the
device.
Signed-off-by:
From: Rafal Kozik
When ENA notifications are provided ena_notification handler is called.
It checks if received value is not corrupted and if necessary it
reports proper warnings.
Data received from NIC is parsed in ena_update_hints. Fields for
storing those information was added to ena_adapter
To make the LSC interrupt working, the AENQ must be configured properly
in the ENA device. The AENQ interrupt is common for all maintance
interrupts - the proper handler is then executed depending on the
received descriptor.
Signed-off-by: Michal Krawczyk
---
drivers/net/ena/ena_ethdev.c | 52 ++
Lack of uninit routine could lead to memory leak.
Stop was added to fulfill allowed PMD operations.
Checks for the PMD states in the start and configure routine were
removed, as the upper layer is already checking for them.
The interrupt setup was moved from start to init function.
Signed-off-by
The ENA device is able to send MSI-X when it will complete an command
when polling mode is deactivated. Further, the same interrupt handler
will be used for the AENQ handling - services of the ENA device, that
allows to implement watchdog or lsc handler.
Signed-off-by: Michal Krawczyk
---
driver
The ENA driver was updated with the new features and few fixes and minor
changes are introduced.
First of all, the communication layer which is delivered by vendor was
updated - the version in the HEAD is a bit outdated now. ENA is able to
communicate with the driver through Admin queue by using ad
From: Rafal Kozik
The legacy LLQ should no longer be supported by the drivers, as this API
is deprecated. Because of that, it was removed from the driver.
Signed-off-by: Rafal Kozik
Signed-off-by: Michal Krawczyk
---
drivers/net/ena/ena_ethdev.c | 29 +
1 file chan
On Fri, Jun 01, 2018 at 02:47:57PM +0200, Maxime Coquelin wrote:
> Signed-off-by: Maxime Coquelin
> ---
> drivers/net/virtio/virtio_ethdev.c | 3 ++-
> 1 file changed, 2 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/net/virtio/virtio_ethdev.c
> b/drivers/net/virtio/virtio_ethdev.c
> ind
On Fri, Jun 01, 2018 at 02:47:58PM +0200, Maxime Coquelin wrote:
> Instead of checking the multiple Virtio features bits for
> every packet, let's do the check once at configure time and
> store it in virtio_hw struct.
>
> Signed-off-by: Maxime Coquelin
> ---
> drivers/net/virtio/virtio_ethdev.c
There might be situations (kind of attack when a lot of
fragmented packets are sent to a dpdk application in order
to flood the fragmentation table) when no additional mbufs
must be added to the fragmentations table since it already
contains to many of them. Currently there is no way to
determine t
A fragmented packets is supposed to live no longer than max_cycles,
but the lib deletes an expired packet only occasionally when it scans
a bucket to find an empty slot while adding a new packet.
Therefore a fragment might sit in the table forever.
Signed-off-by: Alex Kiselev
---
lib/librte_ip_f
Avoid NULL dereference by checking pointer before using it.
Note that the fixes tag is before the driver was renamed
to mvpp2, so the patch will not apply that far back.
Fixes: 3588aaa68eab ("net/mrvl: fix HIF objects allocation")
Signed-off-by: Tomasz Duszynski
---
drivers/net/mvpp2/mrvl_ethd
Hi all,
Here is a list of patches targeted for stable release 18.02.2. Please
help review and test. The planned date for the final release is Thursday,
the 14th of June. Before that, please shout if anyone has objections with these
patches being applied.
Also for the companies committed to runnin
Convert mvpp2 PMD to use dynamic logging.
Signed-off-by: Tomasz Duszynski
---
drivers/net/mvpp2/mrvl_ethdev.c | 147 +---
drivers/net/mvpp2/mrvl_ethdev.h | 8 +++
drivers/net/mvpp2/mrvl_flow.c | 32 -
drivers/net/mvpp2/mrvl_qos.c| 42 ++--
On Mon, 2018-06-04 at 05:24 +, Shreyansh Jain wrote:
> Hello Luca
>
> > -Original Message-
> > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Luca Boccassi
> > Sent: Thursday, May 31, 2018 3:57 PM
> > To: dev@dpdk.org
> > Cc: sta...@dpdk.org; tho...@monjalon.net
> > Subject: [dpd
-Original Message-
> Date: Mon, 4 Jun 2018 07:21:18 +
> From: bugzi...@dpdk.org
> To: dev@dpdk.org
> Subject: [dpdk-dev] [Bug 60] rte_event_port_unlink() causes subsequent
> events to end up in wrong port
>
> https://dpdk.org/tracker/show_bug.cgi?id=60
>
> Bug ID: 60
>
Sunday, June 3, 2018 5:15 PM, Ferruh Yigit:
> Subject: Re: [PATCH] ethdev: force RSS offload rules again
>
> On 6/3/2018 11:41 AM, Shahaf Shuler wrote:
> > Thursday, May 31, 2018 4:23 PM, Ferruh Yigit:
> >> Subject: [PATCH] ethdev: force RSS offload rules again
> >>
> >> PMDs should provide suppor
On 06/01/2018 02:47 PM, Maxime Coquelin wrote:
Below are benchmarks results when offloads are enabled at
"When *no* offload" should be read here...
device level.
Rx-mrg=off benchmarks:
++---+-+-+--+
|Run | PVP | Guest->Host | Host->
On Sun, Jun 03, 2018 at 06:29:13PM +0300, Moti Haimovsky wrote:
> This RFC and patch aim to add support for building mlx5 PMD on 32bit
> archs such as i686.
> The attached patch was not tested on 32bit environments and is given
> here for explanatory purposes.
>
> Prerequisites:
> * RDMA-core with
https://dpdk.org/tracker/show_bug.cgi?id=60
Bug ID: 60
Summary: rte_event_port_unlink() causes subsequent events to
end up in wrong port
Product: DPDK
Version: 17.11
Hardware: x86
OS: Linux
Statu
60 matches
Mail list logo
