Hi Thomas,
Please apply this patch.
Regards,
Hemant
On Wed, Jun 6, 2018 at 5:39 PM Hemant Agrawal wrote:
>
> Christian,
> Will you please ack it? A ack from canonical is must to change the
> license (even if it is just the style).
Sorry Hemant for the extra delay, I was on PTO a
On Thu, Aug 1, 2019 at 7:25 AM Takeshi T Yoshimura wrote:
> Okay. I should have set the --log-level=lib.*:debug. Here is the log.
>
> Starting SPDK v19.10-pre / DPDK 19.08.0-rc3 initialization...
> [ DPDK EAL parameters: identify --no-shconf -c 0x1 -n 1 -m 0
> --log-level=lib.eal:6 --log-level=li
On tis, 2019-07-30 at 21:21 +0200, David Marchand wrote:
>
> We are really close to -rc3.
> Can you send a review or test tag?
>
Tested-by: Johan Källström
Reviewed-by: Johan Källström
I might be to late for that. Tested the patch on the v19.08-rc3 tag.
BR
Johan
On Wed, Jul 31, 2019 at 9:57 PM Michael Santana Francisco
wrote:
>
> On Wed, Jul 31, 2019 at 2:56 PM David Marchand
> wrote:
> >
> > Following removal of -c and -n options, the array should have been
> > shrunk to avoid launch_proc to access unitialised strings.
> >
> > Fixes: b4dbacdb1ad7 ("test
Hi Akhil,
> >
> > > > > >
> > > > > > 30/07/2019 10:48, Akhil Goyal:
> > > > > > > > 30/07/2019 09:20, Akhil Goyal:
> > > > > > > > > > 30/07/2019 07:55, Akhil Goyal:
> > > > > > > > > > > > > > > All the functionality of the legacy code path in
> > > > > > > > > > > > > > > now
> > available
>
The patch [Fixes] sets the default value of required minimal
inline data to 0 bytes. On some configurations (depends
on switchdev/legacy settings and FW version/settings)
the ConnectX-4LX NIC requires minimal 18 bytes of
Tx descriptor inline data to operate correctly.
Wrongly set to 0 default valu
The debug assert wrongly triggers on the inline data 18B,
this should be passed successfully.
Fixes: 18a1c20044c0 ("net/mlx5: implement Tx burst template")
Signed-off-by: Viacheslav Ovsiienko
---
drivers/net/mlx5/mlx5_rxtx.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/dr
HI,
> On 7/26/19 2:25 PM, Olivier Matz wrote:
> > Hi,
> >
> > On Thu, Jul 25, 2019 at 04:36:45PM +0530, Hemant Agrawal wrote:
> >> When using RTE_PKTMBUF_HEADROOM as 0, virito ethdev driver throws
> >> compilation error
> >> virtio_ethdev.c:1851:2: note: in expansion of macro ‘RTE_BUILD_BUG_ON’
> >
>
> Left-shift of an integer constant is represented as 'int' type, but a left
> shift of 1 by 31 bits in 'int' is undefined. Use the U suffix to force
> a representation as unsigned.
>
> Caught while running with ubsan under gcc.
>
> Fixes: dc276b5780c2 ("acl: new library")
> Cc: Konstantin An
> - Are the (below) devices bound to vfio-pci or any other kmod at this point
> of the init?
Yes, vfio-pci is bound to 0030:01:00.0 in the log.
> - Is the spdk_nvme driver loaded at this point?
No, spdk just attempts to initialize dpdk at this point.
After the initialization finishes, spdk prob
On Wed, Jul 31, 2019 at 12:10:55PM -0400, Aaron Conole wrote:
> Aaron Conole writes:
>
> > Bruce Richardson writes:
> >
> >> On Wed, Jul 31, 2019 at 10:50:29AM -0400, Aaron Conole wrote:
> >>> From: Michael Santana
> >>>
> >>> Currently many unit tests fail when running tests under shared buil
On Thu, Aug 1, 2019 at 10:46 AM Takeshi T Yoshimura wrote:
>
> > - Are the (below) devices bound to vfio-pci or any other kmod at this point
> > of the init?
>
> Yes, vfio-pci is bound to 0030:01:00.0 in the log.
>
> > - Is the spdk_nvme driver loaded at this point?
>
> No, spdk just attempts to
Fixes: c41a04958b ("net/memif: support multi-process")
Signed-off-by: Phil Yang
Reviewed-by: Gavin Hu
---
drivers/net/memif/rte_eth_memif.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/memif/rte_eth_memif.c
b/drivers/net/memif/rte_eth_memif.c
index bcda426..a
During an if-condition evaluation, a 2-bit flag evaluates to 'true' for
'0x1', '0x2' and '0x3'. Thus, from this perspective these flags are
indistinguishable. To make them distinct, respective bits must be
extracted with a mask and then checked for strict equality.
Specifically here, even if `PKT_
czw., 1 sie 2019 o 13:45 Maciej Bielski napisał(a):
>
> During an if-condition evaluation, a 2-bit flag evaluates to 'true' for
> '0x1', '0x2' and '0x3'. Thus, from this perspective these flags are
> indistinguishable. To make them distinct, respective bits must be
> extracted with a mask and then
The memory tests currently check that, for normal mode (not legacy mode),
there is no memory left behind when exiting.
The problem is that if a ethdev port is allocated when scanning pci
devices (even if the driver probe fails like when you have a virtio
management interface attached to the kernel
On Thu, Aug 1, 2019 at 2:28 PM David Marchand wrote:
>
> The memory tests currently check that, for normal mode (not legacy mode),
> there is no memory left behind when exiting.
>
> The problem is that if a ethdev port is allocated when scanning pci
> devices (even if the driver probe fails like w
In order to prepare for a long term stable API, the mbuf library
has to change: allowing more features as dynamic fields,
and fixing the lack of rte_ prefix in the namespace.
The namespace fix should not break the compatibility by keeping
some aliases during few releases to give time for migration.
Hello Anatoly,
On Wed, Jul 31, 2019 at 5:36 AM Takeshi Yoshimura wrote:
>
> Commit b76fafb174d2 ("eal: fix IOVA mode selection as VA for PCI
> drivers") breaks ppc apps with no IOVA configs (or RTE_IOVA_DC)
> because of the inconsistency of user's request and the result of
> device capability for
On Thu, Aug 01, 2019 at 02:29:21PM +0200, David Marchand wrote:
> On Thu, Aug 1, 2019 at 2:28 PM David Marchand
> wrote:
> >
> > The memory tests currently check that, for normal mode (not legacy mode),
> > there is no memory left behind when exiting.
> >
> > The problem is that if a ethdev port
MLX5 PMD limits the number of SW steering tables to 32.
This patch updates the limit to 65535, to allow wide range of values.
Fixes: e2b4925ef7c1 ("net/mlx5: support Direct Rules E-Switch")
v2: remove Cc to stable release, not relevant for this fix.
Signed-off-by: Dekel Peled
---
drivers/net/m
Hey Gaëtan,
On Thu, Aug 1, 2019 at 3:22 PM Gaëtan Rivet wrote:
>
> On Thu, Aug 01, 2019 at 02:29:21PM +0200, David Marchand wrote:
> > On Thu, Aug 1, 2019 at 2:28 PM David Marchand
> > wrote:
> > >
> > > The memory tests currently check that, for normal mode (not legacy mode),
> > > there is no
On Thu, Aug 1, 2019 at 3:24 PM David Marchand wrote:
>
> Hey Gaëtan,
>
> On Thu, Aug 1, 2019 at 3:22 PM Gaëtan Rivet wrote:
> >
> > On Thu, Aug 01, 2019 at 02:29:21PM +0200, David Marchand wrote:
> > > On Thu, Aug 1, 2019 at 2:28 PM David Marchand
> > > wrote:
> > > >
> > > > The memory tests c
Given the fact that dev parameter is used in ice_dev_configure.
Fixes: 50370662b727 ("net/ice: support device and queue ops")
Cc: sta...@dpdk.org
Cc: wenzhuo...@intel.com
Signed-off-by: Xiaolong Ye
---
drivers/net/ice/ice_ethdev.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --gi
From: Kalesh AP
Fixed a check in bnxt_alloc_hwrm_rx_ring() while initializing
the rx ring.
Driver should not change "deferred_start" status of rx/tx queues.
It should get the status in queue_setup_op() and use that value.
Fixes: a51076c20ecb46d ("net/bnxt: fix rxq start")
Signed-off-by: Kalesh
Bruce Richardson writes:
> On Wed, Jul 31, 2019 at 12:10:55PM -0400, Aaron Conole wrote:
>> Aaron Conole writes:
>>
>> > Bruce Richardson writes:
>> >
>> >> On Wed, Jul 31, 2019 at 10:50:29AM -0400, Aaron Conole wrote:
>> >>> From: Michael Santana
>> >>>
>> >>> Currently many unit tests fail
From: Kalesh AP
Fixed a check in bnxt_alloc_hwrm_rx_ring() while initializing
the rx ring.
Driver should not change "deferred_start" status of rx/tx queues.
It should get the status in queue_setup_op() and use that value.
Fixes: 9b63c6fd70e3 ("net/bnxt: support Rx/Tx queue start/stop")
Signed-
On Thu, Aug 01, 2019 at 11:40:33AM -0400, Aaron Conole wrote:
> Bruce Richardson writes:
>
> > On Wed, Jul 31, 2019 at 12:10:55PM -0400, Aaron Conole wrote:
> >> Aaron Conole writes:
> >>
> >> > Bruce Richardson writes:
> >> >
> >> >> On Wed, Jul 31, 2019 at 10:50:29AM -0400, Aaron Conole wrot
On Wed, Jul 31, 2019 at 10:50:29AM -0400, Aaron Conole wrote:
> From: Michael Santana
>
> Currently many unit tests fail when running tests under shared builds.
> This happens because of missing driver dependencies. This is fixed by
> explicitly linking in missing drivers for the test application
Yes, thank you for the patch, acked.
The "txq_inline_min" value was not set for ConnectX-5 to 0 as default.
At the TX queue setup time the "txq_inline_min" is checked against
MLX5_ARG_UNSET
and default value 0 is set:
txq_set_params()
...
inlen_mode = (config->txq_inline_min == MLX5_ARG_UNSET)
From: Vamsi Attunuru
Octeontx2 PMD's mailbox client uses HW memory to send messages
to mailbox server in the admin function Linux kernel driver.
The device memory used for the mailbox communication needs to
be qualified as volatile memory type to avoid unaligned device
memory accesses because of
From: Viacheslav Ovsiienko
> The debug assert wrongly triggers on the inline data 18B, this should be
> passed successfully.
>
> Fixes: 18a1c20044c0 ("net/mlx5: implement Tx burst template")
>
> Signed-off-by: Viacheslav Ovsiienko
Acked-by: Matan Azrad
> ---
> drivers/net/mlx5/mlx5_rxtx.c
From: Tianfei zhang
Every defined bit in FME_ERROR0 is RW1C. Other reserved bits are always
0 when readout and it will plan to be RW1C if needed in future.
So it is safe just write the read back value to clear all the errors.
Signed-off-by: Tianfei zhang
---
drivers/raw/ifpga_rawdev/base/ifpga
From: Tianfei zhang
Add irq support for ifpga FME globle error, port error and uint unit.
We implmented this feature by vfio interrupt mechanism.
Signed-off-by: Tianfei zhang
---
drivers/raw/ifpga_rawdev/base/ifpga_feature_dev.c | 61 +++
drivers/raw/ifpga_rawdev/base/ifpga
This patch set adds PCIe AER disable and IRQ support for ipn3ke.
Disable PCIe AER is very useful when FPGA reload. IRQ is used
very widely in interrupt process.
For ipn3ke is connect to CPU with PCIe switch, driver needs to
scan all PCIe devices of ipn3ke, it also can get all i40e of card,
so ipn3
From: Tianfei zhang
This patch exposes SEU error information to application then application
could compare this information (128bit) with its own SMH file to know
if this SEU is a fatal error or not.
Signed-off-by: Tianfei zhang
---
drivers/raw/ifpga_rawdev/base/ifpga_defines.h | 5 ++-
d
From: Tianfei zhang
In PAC N3000 card, this is a BMC chip which using MAX10 FPGA
to manage the board configuration, like sensors, flash controller,
QSFP, powers. And this is a SPI bus connected between A10 FPGA and
MAX10, we can access the MAX10 registers over this SPI bus.
In BMC, there are abo
From: Tianfei Zhang
The length of send buffer of SPI bus should be 4bytes align.
Signed-off-by: Tianfei Zhang
---
.../raw/ifpga_rawdev/base/opae_spi_transaction.c | 40 +++---
1 file changed, 36 insertions(+), 4 deletions(-)
diff --git a/drivers/raw/ifpga_rawdev/base/opae_sp
In ipn3ke, each FPGA network side port bonding to an i40e pf,
each i40e pf link status should get data from FPGA network,
side port. This patch provide bonding relationship.
Signed-off-by: Rosen Xu
---
drivers/net/i40e/base/i40e_type.h | 3 +++
drivers/net/i40e/i40e_ethdev.c| 34 +++
From: Tianfei zhang
The sensor devices are connected in MAX10 FPGA. we used the
device tree to describe those sensor devices. Parse the device
tree to get the sensor devices and add them into a list.
Signed-off-by: Tianfei zhang
---
drivers/raw/ifpga_rawdev/base/opae_intel_max10.c | 279 ++
From: Tianfei zhang
Update the SEU registser definition.
Signed-off-by: Tianfei zhang
---
drivers/raw/ifpga_rawdev/base/ifpga_defines.h | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/raw/ifpga_rawdev/base/ifpga_defines.h
b/drivers/raw/ifpga_rawdev/base/ifpga_de
From: Tianfei Zhang
Introducing sensor APIs to PMD driver for PAC N3000 card.
Those sensor APIs:
1. opae_mgr_for_each_sensor()
2. opae_mgr_get_sensor_by_name()
3. opae_mgr_get_sensor_by_id()
4. opae_mgr_get_sensor_value_by_name()
5. opae_mgr_get_sensor_value_by_id()
6. opae_mgr_get_sensor_value(
The ipn3ke board FPGA and i40e BDF scan has added in ifpga_rawdev,
so it doesn't need to provide configuration for i40e port bonding.
Signed-off-by: Rosen Xu
---
drivers/net/ipn3ke/Makefile | 2 +
drivers/net/ipn3ke/ipn3ke_ethdev.c | 289
drive
From: Tianfei zhang
Add SEU interrupt support for FPGA.
Signed-off-by: Tianfei zhang
Signed-off-by: Rosen Xu
---
drivers/raw/ifpga_rawdev/ifpga_rawdev.c | 246
1 file changed, 246 insertions(+)
diff --git a/drivers/raw/ifpga_rawdev/ifpga_rawdev.c
b/drivers/r
Add PCIe BDF devices tree scan for ipn3ke.
Signed-off-by: Rosen Xu
---
drivers/raw/ifpga_rawdev/ifpga_rawdev.c | 553 +++-
drivers/raw/ifpga_rawdev/ifpga_rawdev.h | 16 +
2 files changed, 562 insertions(+), 7 deletions(-)
diff --git a/drivers/raw/ifpga_rawdev/ifpga_
rte_panic causes a backtrace (which is uniformative since all
these calls are in main). Instead use rte_exit and try and make the
messages informative.
Signed-off-by: Stephen Hemminger
---
app/test-pmd/testpmd.c | 14 --
1 file changed, 8 insertions(+), 6 deletions(-)
diff --git a/a
Small fixes to testpmd, found while trying to get testpmd
to work correctly as secondary process. Fixing that goes deeper
and another set of patches to do that will come (for 19.11).
Stephen Hemminger (3):
testpmd: allow configuring log level on command line
testpmd: block secondary process
Since testpmd has several issues which keep it from working correctly
as a secondary process; abort if user tries to do it, rather than
running into later problems.
Signed-off-by: Stephen Hemminger
---
app/test-pmd/testpmd.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/app/test-pmd/tes
Since testpmd registers log type after processing command
line arguments, it is not possible to do:
# testpmd --log-level='testpmd:info' ...
Fix this by initializing logtype first.
Signed-off-by: Stephen Hemminger
---
app/test-pmd/testpmd.c | 8
1 file changed, 4 insertions(+), 4 del
The client_server_mp application does not work correctly
with failsafe or other devices using port ownership.
v5 - change logic in server_mp for evaluating port mask
v4 - fix checkpatch warning
add patches to fix style issues and use ether format addr
v3 - merge both patches in one series
From: Stephen Hemminger
The mp_client crashes if run on Azure or any system where ethdev
ports are owned. In that case, the tx_buffer and tx_stats for the
real port were initialized correctly, but the wrong port was used.
For example if the server has Ports 3 and 5. Then calling
rte_eth_tx_buffe
From: Stephen Hemminger
The mp_server incorrectly allows a port mask that included hidden
ports and which later caused either lost packets or failed initialization.
This fixes explicitly checking that each bit in portmask is a
valid port before using it.
Fixes: 5b7ba31148a8 ("ethdev: add port o
No need to use snprintf to print ethernet address.
Signed-off-by: Stephen Hemminger
---
.../client_server_mp/mp_server/main.c | 32 ++-
1 file changed, 9 insertions(+), 23 deletions(-)
diff --git a/examples/multi_process/client_server_mp/mp_server/main.c
b/examples/mult
Lots of little style complaints from checkpatch.
Signed-off-by: Stephen Hemminger
---
.../client_server_mp/mp_server/args.c | 37 -
.../client_server_mp/mp_server/init.c | 79 +++
.../client_server_mp/mp_server/main.c | 44 ++-
3 files chan
Hi Bruce, Neil,
We had this patch in our internal tree that was intended to fix
-Wimplicit-fallthrough related error due to Host and Target GCC mismatch.
But I just verified both combination of GCC in Make and Meson seems like it has
already been addressed somewhere down the line.
So, I'm dropp
> -Original Message-
> From: David Christensen
> Sent: Thursday, August 1, 2019 21:24
> To: Slava Ovsiienko
> Cc: dev@dpdk.org
> Subject: Re: [PATCH] net/mlx5: txq_inline_min not set for ConnectX-5
> adapters
>
> > Yes, thank you for the patch, acked.
> >
> > The "txq_inline_min" value w
> -Original Message-
> From: vattun...@marvell.com
> Sent: Thursday, August 1, 2019 11:59 PM
> To: dev@dpdk.org
> Cc: tho...@monjalon.net; Jerin Jacob Kollanukkaran ;
> Vamsi Krishna Attunuru ; Nithin Kumar
> Dabilpuram
> Subject: [dpdk-dev] [PATCH v1 1/1] common/octeontx2: fix unaligned
> -Original Message-
> From: dev On Behalf Of Rosen Xu
> Sent: Friday, August 2, 2019 6:49 AM
> To: dev@dpdk.org
> Cc: ferruh.yi...@intel.com; tianfei.zh...@intel.com; rosen...@intel.com;
> andy@intel.com; david.lomart...@intel.com; qi.z.zh...@intel.com;
> xiaolong...@intel.com
> Subje
> -Original Message-
> From: dev On Behalf Of Rosen Xu
> Sent: Friday, August 2, 2019 6:49 AM
> To: dev@dpdk.org
> Cc: ferruh.yi...@intel.com; tianfei.zh...@intel.com; rosen...@intel.com;
> andy@intel.com; david.lomart...@intel.com; qi.z.zh...@intel.com;
> xiaolong...@intel.com
> Subje
From: Vamsi Attunuru
Octeontx2 PMD's mailbox client uses device memory to send messages
to mailbox server in the admin function Linux kernel driver.
The device memory used for the mailbox communication needs to
be qualified as volatile memory type to avoid unaligned device
memory accesses because
Hi Stephen
One more small comment inline
From: Stephen Hemminger
> Sent: Friday, August 2, 2019 5:58 AM
> To: dev@dpdk.org
> Cc: Stephen Hemminger
> Subject: [dpdk-dev] [PATCH v5 1/4]
> examples/multi_process/client_server_mp: check port validity
>
> From: Stephen Hemminger
>
> The mp_serve
Hi Akhil, Adrien, Declan, Pablo,
Can you review this proposal and share your feedback?
Thanks,
Anoob
> -Original Message-
> From: Anoob Joseph
> Sent: Wednesday, July 24, 2019 7:47 PM
> To: Akhil Goyal ; Adrien Mazarguil
> ; Declan Doherty
> ; Pablo de Lara
> ; Thomas Monjalon
>
> Cc:
From: Jerin Jacob
Fix the following doc build warning by correcting path.
doc/guides/rel_notes/release_18_05.rst:285:
WARNING: unknown document: ../rawdevs/ifpga_rawdev
Fixes: 473c88f9b391 ("drivers/raw: remove rawdev from directory names")
Signed-off-by: Jerin Jacob
---
doc/guides/rel_notes
> -Original Message-
> From: vattun...@marvell.com
> Sent: Friday, August 2, 2019 9:50 AM
> To: dev@dpdk.org
> Cc: tho...@monjalon.net; Jerin Jacob Kollanukkaran ;
> Vamsi Krishna Attunuru ; Nithin Kumar
> Dabilpuram
> Subject: [dpdk-devPATCH v2 1/1] common/octeontx2: fix unaligned mbox
>
From: Vamsi Attunuru
Octeontx2 PMD's mailbox client uses device memory to send messages
to mailbox server in the admin function Linux kernel driver.
The device memory used for the mailbox communication needs to
be qualified as volatile memory type to avoid unaligned device
memory accesses because
Signed-off-by: Maxime Coquelin
---
lib/librte_vhost/iotlb.c | 32 ++--
lib/librte_vhost/iotlb.h | 33 +++--
2 files changed, 5 insertions(+), 60 deletions(-)
diff --git a/lib/librte_vhost/iotlb.c b/lib/librte_vhost/iotlb.c
index fcf9e9861..
66 matches
Mail list logo
