> -Original Message-
> From: Yongseok Koh
> Sent: Friday, November 09, 2018 1:07 AM
> To: Ophir Munk ; Adrien Mazarguil
> ; Andrew Rybchenko
>
> Cc: Ferruh Yigit ; dev@dpdk.org; Thomas Monjalon
> ; Asaf Penso ; Shahaf
> Shuler ; Olga Shern
> Subject: Re: [dpdk-dev] [PATCH v2] ethdev: d
-Original Message-
> Date: Fri, 9 Nov 2018 11:20:55 +0530
> From: "Dabilpuram, Nithin"
> To: "dev@dpdk.org" , "Jacob, Jerin"
> , "Czekaj, Maciej"
>
> CC: "Nilla, Subrahmanyam" ,
> "sta...@dpdk.org" , "Dabilpuram, Nithin"
>
> Subject: [PATCH] net/thunderx: fix Tx desc corruption in
Hi ethdev maintainers,
Support of drivers for the fields in rte_eth_stats is a bit random, and never
mentioned in the doc. A quick survey showed me :
ipackets : implemented by all drivers
ibytes : all except null, ring
ierror : all except af_packet, ark, avf, axgbe, fm10k, kni, null, pcap, rin
09/11/2018 09:28, Tom Barbette:
> Hi ethdev maintainers,
>
>
> Support of drivers for the fields in rte_eth_stats is a bit random, and never
> mentioned in the doc. A quick survey showed me :
>
>
> ipackets : implemented by all drivers
> ibytes : all except null, ring
> ierror : all except af_
This reverts the patch that enables default RSS action by setting
key=NULL and key_len=0.
In current testpmd implementation a key pointer must exist if
key_len!=0. For example, the following flow rule will cause a
segmentation fault:
flow create 0 actions rss queues 0 1 end key_len 40 / end
Fixes
Hi Wiles,
Thanks a lot for your reply, I'm not sure what you said "tx flush
threshold" exactly is. Is it in parameter of rte_eth_tx_queue_setup function to
init tx queue? If so, it's configured as
static struct rte_eth_txconf tx_conf =
{
.tx_thresh = {
.pthresh = TX_PTHRESH, // 36
.hthr
--- fix coding style of the previous patch
During procless startup, dpdk invokes clear_hugedir() to unlink all
hugepage files under /dev/hugepages. Then in map_all_hugepages(),
it invokes mmap to allocate and zero all the huge pages as configured
in /sys/kernel/mm/hugepages/xxx/nr_hugepages.
This
-Original Message-
> Date: Fri, 9 Nov 2018 01:34:25 +
> From: Honnappa Nagarahalli
> To: Jerin Jacob
> CC: "bruce.richard...@intel.com" ,
> "pablo.de.lara.gua...@intel.com" ,
> "dev@dpdk.org" , "yipeng1.w...@intel.com"
> , Dharmik Thakkar ,
> "Gavin Hu (Arm Technology China)" , nd
This reverts the patch that enables default RSS action by setting
key=NULL and key_len=0.
In current testpmd implementation a key pointer must exist if
key_len!=0. For example, the following flow rule will cause a
segmentation fault:
flow create 0 actions rss queues 0 1 end key_len 40 / end
Fixes
On 11/9/2018 6:27 AM, Christian Ehrhardt wrote:
> On Fri, Nov 9, 2018 at 12:01 AM Yongseok Koh wrote:
>>
>>
>>> On Nov 8, 2018, at 9:21 AM, Ferruh Yigit wrote:
>>>
>>> On 11/8/2018 3:59 PM, Thomas Monjalon wrote:
Hi,
We need to gather more information about this bug.
More belo
On 11/8/2018 11:01 PM, Yongseok Koh wrote:
>
>> On Nov 8, 2018, at 9:21 AM, Ferruh Yigit wrote:
>>
>> On 11/8/2018 3:59 PM, Thomas Monjalon wrote:
>>> Hi,
>>>
>>> We need to gather more information about this bug.
>>> More below.
>>>
>>> 07/11/2018 10:04, Wiles, Keith:
> On Nov 6, 2018, at 9:
Add user guide for debug and troubleshoot for common issues and bottleneck
found in various application models running on single or multi stages.
Signed-off-by: Vipin Varghese
Acked-by: Marko Kovacevic
---
V2:
- add offload flag check - Vipin Varghese
- change tab to space - Marko Kovacevic
Add svg for debug and troubleshoot guide for single or
multi stage applications.
Signed-off-by: Vipin Varghese
Acked-by: Marko Kovacevic
---
V2:
- add ACK from Marko - Vipin Varghese
---
doc/guides/howto/debug_troubleshoot_guide.rst | 264 +-
doc/guides/howto/img/dtg_consumer_
On 09.11.2018 12:38, Ophir Munk wrote:
> This reverts the patch that enables default RSS action by setting
> key=NULL and key_len=0.
> In current testpmd implementation a key pointer must exist if
> key_len!=0. For example, the following flow rule will cause a
> segmentation fault:
> flow create 0
09/11/2018 10:49, Ferruh Yigit:
> On 11/9/2018 6:27 AM, Christian Ehrhardt wrote:
> > On Fri, Nov 9, 2018 at 12:01 AM Yongseok Koh wrote:
> >>
> >>
> >>> On Nov 8, 2018, at 9:21 AM, Ferruh Yigit wrote:
> >>>
> >>> On 11/8/2018 3:59 PM, Thomas Monjalon wrote:
> Hi,
>
> We need to ga
On 11/7/18 10:01 AM, Tiwei Bie wrote:
Coverity issue: 302861
Fixes: 6ba1f63b5ab0 ("virtio: support specification 1.0")
Signed-off-by: Tiwei Bie
---
This patch can't be backported because it depends on the
API change introduced by below commit in this release.
commit e8d435f1f3a1 ("bus/pci:
On 11/7/18 10:01 AM, Tiwei Bie wrote:
The caller will guarantee that msg won't be null. Remove
the unneeded null pointer check which caused a Coverity
warning.
Coverity issue: 323484
Fixes: 8f972312b8f4 ("vhost: support vhost-user")
Cc: sta...@dpdk.org
Signed-off-by: Tiwei Bie
---
lib/lib
Hi Fan,
Could you please have a look at Mattias comments and reply?
Thanks in advance,
Maxime
On 10/30/18 8:38 PM, Mattias Rönnblom wrote:
On 2018-10-30 15:48, Fan Zhang wrote:
This patch fixes the zero copy enable problem for vhost crypto
sample application.
For some Crypto PMDs such as AES
V1:
Update the ring C11 library including the following changes:
1) On relaxed ordering platforms(like Arm64,PPPC), in ring C11 implementation,
loading head and tail might be reodered, this makes CAS(compare and retry
the flow if the head is outdated) not working as expected, the fix is to
Use case scenario:
1) Thread 1 is enqueuing. It reads prod.head and gets stalled for some
reasons (running out of cpu time, preempted,...)
2) Thread 2 is enqueuing. It succeeds in enqueuing and moves prod.head
forward.
3) Thread 3 is dequeuing. It succeeds in dequeuing and moves the cons.tail
When calling __atomic_compare_exchange_n, use relaxed ordering for the
success case, as multiple producers/consumers do not release updates to
each other so no need for acquire or release ordering.
Because the thread fence in place, ordering for the first iteration can be
relaxed.
Run the ring pe
On 08-Nov-18 8:38 PM, Rami Rosen wrote:
Hi, Anatoly,
This is really minor nitpick, but in case you decide to send V2, I
believe it should say
>> + if ret != 0:
>> + print("'lspci' not found - please install pciutils')
as the name of the package containing lspci is pciutils in cen
On 09-Nov-18 5:57 AM, tone.zhang wrote:
With a larger PAGE_SIZE it is possible for the MSI table to very
close to the end of the BAR s.t. when we align the start and end
of the MSI table to the PAGE_SIZE, the end offset of the MSI
table is out of the PCI BAR boundary.
This patch addresses the is
On 09-Nov-18 9:23 AM, jianmingfan wrote:
--- fix coding style of the previous patch
During procless startup, dpdk invokes clear_hugedir() to unlink all
hugepage files under /dev/hugepages. Then in map_all_hugepages(),
it invokes mmap to allocate and zero all the huge pages as configured
in /sys/
09/11/2018 11:03, Ferruh Yigit:
> On 11/8/2018 11:01 PM, Yongseok Koh wrote:
> >
> >> On Nov 8, 2018, at 9:21 AM, Ferruh Yigit wrote:
> >>
> >> On 11/8/2018 3:59 PM, Thomas Monjalon wrote:
> >>> Hi,
> >>>
> >>> We need to gather more information about this bug.
> >>> More below.
> >>>
> >>> 07/11
On Wed, 2018-11-07 at 18:27 +, Zhang, Qi Z wrote:
> > -Original Message-
> > From: Luca Boccassi [mailto:bl...@debian.org]
> > Sent: Wednesday, November 7, 2018 5:55 AM
> > To: Zhang, Qi Z ; Chas Williams <3chas3@gmail
> > .com>;
> > dev@dpdk.org
> > Cc: Lu, Wenzhuo ; Ananyev, Konstanti
The use of rte_memcpy_ptr was removed in revert below,
but it was missing removing the file arch/x86/rte_memcpy.c.
Fixes: d35cc1fe6a7a ("eal/x86: revert select optimized memcpy at run-time")
Cc: sta...@dpdk.org
Cc: xiaoyun...@intel.com
Signed-off-by: Thomas Monjalon
---
lib/librte_eal/common/ar
> The other option would be to push for implementing all basic stats
> in all drivers, and consider an unimplemented stat as a bug.
It may be impossible in some cases. I think imissed is not even reported by
hardware for mlx5 cards. Only an aggregate for all queues.
I'll add a "uint64_t stats_ca
On 09-Nov-18 12:20 PM, Burakov, Anatoly wrote:
On 09-Nov-18 9:23 AM, jianmingfan wrote:
--- fix coding style of the previous patch
During procless startup, dpdk invokes clear_hugedir() to unlink all
hugepage files under /dev/hugepages. Then in map_all_hugepages(),
it invokes mmap to allocate an
09/11/2018 14:17, Thomas Monjalon:
> 09/11/2018 11:03, Ferruh Yigit:
> > On 11/8/2018 11:01 PM, Yongseok Koh wrote:
> > >
> > >> On Nov 8, 2018, at 9:21 AM, Ferruh Yigit wrote:
> > >>
> > >> On 11/8/2018 3:59 PM, Thomas Monjalon wrote:
> > >>> Hi,
> > >>>
> > >>> We need to gather more informatio
On 11/6/18 5:22 PM, Fan Zhang wrote:
This patch fixes the incorrect packet content copy in the
chaining mode. Originally the content before cipher offset is
overwritten by all zeros. This patch fixes the problem by
making sure the correct write back source and destination
settings during set u
On 11/6/18 5:22 PM, Fan Zhang wrote:
This patch fixes the incorrect packet content copy in the
chaining mode. Originally the content before cipher offset is
overwritten by all zeros. This patch fixes the problem by
making sure the correct write back source and destination
settings during set u
On 11/6/18 7:40 AM, Tiwei Bie wrote:
Tiwei Bie (2):
vhost: fix IOVA access for packed ring
net/virtio-user: fix typo in error message
drivers/net/virtio/virtio_user_ethdev.c | 2 +-
lib/librte_vhost/virtio_net.c | 4 ++--
2 files changed, 3 insertions(+), 3 deletions(-)
On 11/7/18 10:01 AM, Tiwei Bie wrote:
Tiwei Bie (2):
net/virtio: fix unchecked return value
vhost: remove unneeded null pointer check
drivers/net/virtio/virtio_pci.c | 10 --
lib/librte_vhost/vhost_user.c | 2 +-
2 files changed, 9 insertions(+), 3 deletions(-)
Applie
Add user guide on debug and troubleshoot for common issues and bottleneck
found in various application models running on single or multi stages.
Signed-off-by: Vipin Varghese
Acked-by: Marko Kovacevic
---
V2:
- add offload flag check - Vipin Varghese
- change tab to space - Marko Kovacevic
-
Add svg for debug and troubleshoot guide for single or
multi stage applications.
Signed-off-by: Vipin Varghese
Acked-by: Marko Kovacevic
---
V2:
- add ACK from Marko - Vipin Varghese
---
doc/guides/howto/img/dtg_consumer_ring.svg| 19
doc/guides/howto/img/dtg_crypto.svg |
> > > > Agree. There are multiple micro-architectures in Arm eco-system.
> > > > We
> > > should establish few simple rules to make sure algorithms perform
> > > well on all the available platforms. I established few rules in VPP
> > > and they are working fine so far.
> > >
> > > Can you share tha
Currently, if configuration fails (for example if a 100G card is used with
an odd number of RX/TX queues) QEDE crashes due to a null pointer
dereference.
This commit fixes it by checking that the pointer is not NULL before
using it.
Fixes: 7105b24f4bb8 ("net/qede: fix memory alloc for multiple po
On Mon, Nov 05, 2018 at 05:39:11PM +, Bruce Richardson wrote:
> From: Yipeng Wang
>
> This patch adds back the local cache when TSX support is turned on.
>
> When TSX is turned on, free key-data slot ring would be contended by
> various TSX regions. The purpose of this commit is to reduce po
Fixes null pointer dereference issue raised by coverity.
Coverity issue: 325728, 325729, 325731, 325738
Fixes: 27b333b23237 ("examples/ip_pipeline: track table rules on add bulk")
Signed-off-by: Jasvinder Singh
---
examples/ip_pipeline/cli.c | 28 +---
1 file changed, 17
On Fri, 9 Nov 2018 14:03:25 +
"Burakov, Anatoly" wrote:
> On 09-Nov-18 12:20 PM, Burakov, Anatoly wrote:
> > On 09-Nov-18 9:23 AM, jianmingfan wrote:
> >> --- fix coding style of the previous patch
> >>
> >> During procless startup, dpdk invokes clear_hugedir() to unlink all
> >> hugepage f
On Fri, 09 Nov 2018 09:38:46 +0100
Thomas Monjalon wrote:
> 09/11/2018 09:28, Tom Barbette:
> > Hi ethdev maintainers,
> >
> >
> > Support of drivers for the fields in rte_eth_stats is a bit random, and
> > never mentioned in the doc. A quick survey showed me :
> >
> >
> > ipackets : impleme
> -Original Message-
> From: Guo, Jia
> Sent: Thursday, November 8, 2018 7:22 PM
> To: Zhang, Qi Z ; Xing, Beilei ;
> Kovacevic, Marko ; Mcnamara, John
>
> Cc: dev@dpdk.org; Zhang, Helin ; Wu, Jingjing
>
> Subject: Re: [PATCH V2] doc: add known PHY link up issue for i40e
>
>
> On 11/9
Copy and create the lock-free versions of lookup
functions.
This is an intermediate commit meant to ease the
review process.
Fixes: e605a1d36 ("hash: add lock-free r/w concurrency")
Cc: honnappa.nagaraha...@arm.com
Suggested-by: Jerin Jacob
Signed-off-by: Honnappa Nagarahalli
Reviewed-by: Ola L
The lock-free algorithm has caused significant lookup
performance regression for certain use cases. The
regression is attributed to the use of non-relaxed
memory orderings.
To address the issue, 2 versions of the lookup functions
are created. One that uses the RW lock and the one that
is lock-free
Remove the rw-lock calls from lock-free versions of lookup
functions.
This is an intermediate commit meant to ease the
review process.
Fixes: e605a1d36 ("hash: add lock-free r/w concurrency")
Cc: honnappa.nagaraha...@arm.com
Suggested-by: Jerin Jacob
Signed-off-by: Honnappa Nagarahalli
Reviewed
The lock-free algorithm has caused significant lookup
performance regression for certain use cases. The
regression is attributed to the use of non-relaxed
memory orderings. 2 versions of the lookup functions
are created. One that uses the RW lock and the one that
is lock-free. This restores the per
Remove the memory orderings from lookup functions using
rw-lock.
This is an intermediate commit meant to ease the
review process.
Fixes: e605a1d36 ("hash: add lock-free r/w concurrency")
Cc: honnappa.nagaraha...@arm.com
Suggested-by: Jerin Jacob
Signed-off-by: Honnappa Nagarahalli
Reviewed-by:
> -Original Message-
> From: Singh, Jasvinder
> Sent: Friday, November 9, 2018 4:12 PM
> To: dev@dpdk.org
> Cc: Dumitrescu, Cristian
> Subject: [PATCH] examples/ip_pipeline: fix null pointer deref
>
> Fixes null pointer dereference issue raised by coverity.
>
> Coverity issue: 325728,
On 11/9/2018 1:46 PM, Thomas Monjalon wrote:
> The use of rte_memcpy_ptr was removed in revert below,
> but it was missing removing the file arch/x86/rte_memcpy.c.
>
> Fixes: d35cc1fe6a7a ("eal/x86: revert select optimized memcpy at run-time")
> Cc: sta...@dpdk.org
> Cc: xiaoyun...@intel.com
>
>
On Thu, 08 Nov 2018 16:59:22 +0100
Thomas Monjalon wrote:
> Hi,
>
> We need to gather more information about this bug.
> More below.
>
> 07/11/2018 10:04, Wiles, Keith:
> > > On Nov 6, 2018, at 9:30 PM, Yongseok Koh wrote:
> > >> On Nov 5, 2018, at 6:06 AM, Wiles, Keith wrote:
> > >>> On
On 11/9/2018 2:27 PM, Thomas Monjalon wrote:
> 09/11/2018 14:17, Thomas Monjalon:
>> 09/11/2018 11:03, Ferruh Yigit:
>>> On 11/8/2018 11:01 PM, Yongseok Koh wrote:
> On Nov 8, 2018, at 9:21 AM, Ferruh Yigit wrote:
>
> On 11/8/2018 3:59 PM, Thomas Monjalon wrote:
>> Hi,
>>
On 11/9/2018 7:56 AM, Rahul Lakkireddy wrote:
> Patch 1 adds a missing PCI un-initialization function for CXGBEVF to
> fix resource leaks.
>
> Patch 2 fixes VLAN strip offload always being enabled without looking
> at Rx offload flags.
>
> Patch 3 fixes issue with redefined match items in flows b
On 11/9/2018 8:20 AM, Jerin Jacob wrote:
<...>
>> From: Subrahmanyam Nilla
>>
>> For performance reasons, word1 of send_hdr_s
>> sub descriptor was not cleared assuming it is always
>> having default value of zero since it comes from fixed
>> offsets of SQ buffer.
>> This is causing issues in case
On 11/8/2018 3:26 PM, Radu Nicolau wrote:
> When stopping a bonded port all slaves are deactivated. Attempting
> to deactivate a slave that was never activated will result in a segfault
> when mode 4 is used.
>
> Fixes: 7486331308f6 ("net/bonding: stop and deactivate slaves on stop")
> Cc: sta...@
On 11/8/2018 6:25 AM, Andrew Rybchenko wrote:
> On 11/8/18 5:09 AM, Wenzhuo Lu wrote:
>> The new configuration is stored during the process.
>> But the process may fail. We better rolling the
>> configuration back as the new one doesn't take effect.
>>
>> Signed-off-by: Wenzhuo Lu
>
> I would say
On 11/5/2018 9:08 PM, Qi Zhang wrote:
> Private vdev on secondary is never supported by the new shared
> device mode but pdump still relies on a private pcap PMD on secondary.
After your updates on hotplug multi process, isn't any virtual PMD added into
secondary will be added into primary too?
Is
> -Original Message-
> From: Yigit, Ferruh
> Sent: Friday, November 9, 2018 2:14 PM
> To: Zhang, Qi Z
> Cc: tho...@monjalon.net; dev@dpdk.org; Lin, Xueqin
>
> Subject: Re: [PATCH] net/pcap: enable data path on secondary
>
> On 11/5/2018 9:08 PM, Qi Zhang wrote:
> > Private vdev on seco
On 11/08/2018 10:26 AM, Radu Nicolau wrote:
When stopping a bonded port all slaves are deactivated. Attempting
to deactivate a slave that was never activated will result in a segfault
when mode 4 is used.
Fixes: 7486331308f6 ("net/bonding: stop and deactivate slaves on stop")
Cc: sta...@dpdk.
On 11/8/2018 9:38 PM, Stephen Hemminger wrote:
> On Thu, 8 Nov 2018 21:19:26 +
> "Mody, Rasesh" wrote:
>
>> Use rte_log() rather than RTE_LOG() for dynamic logging. Rearrange
>> dynamic log types to the top and configurable log types to bottom.
>> Remove unused RTE_LIBRTE_BNX2X_DEBUG_TX_FREE
On 10/12/2018 12:35 PM, Vipin Varghese wrote:
> With the latest release, support for vdev ethernet devices like pcap,
> tun and tap are been added. Hence collecting statistics using proc-info
> is possible now.
>
> Signed-off-by: Vipin Varghese
Reviewed-by: Ferruh Yigit
Applied to dpdk-next-ne
On 11/9/2018 9:40 PM, Chas Williams wrote:
>
>
> On 11/08/2018 10:26 AM, Radu Nicolau wrote:
>> When stopping a bonded port all slaves are deactivated. Attempting
>> to deactivate a slave that was never activated will result in a segfault
>> when mode 4 is used.
>>
>> Fixes: 7486331308f6 ("net/bo
On 11/7/2018 6:10 PM, Kevin Laatz wrote:
> Currently, telemetry is not working for shared builds in make.
>
> The --as-needed flag is preventing telemetry from being linked as there are
> no direct API calls from the app to telemetry. This is causing the
> --telemetry option to not be recognized b
Don't fail the build if pkg-config can't be found, instead print the
linker flag as it was doing before the change.
Fixes: b6b87939193a ("net/mlx5: use pkg-config to handle SUSE libmnl")
Cc: sta...@dpdk.org
Signed-off-by: Luca Boccassi
Reported-by: Thomas Monjalon
---
drivers/net/mlx5/Makefile
>From: Timothy Redaelli
>Sent: Friday, November 09, 2018 7:46 AM
>
>Currently, if configuration fails (for example if a 100G card is used with an
>odd
>number of RX/TX queues) QEDE crashes due to a null pointer dereference.
>
>This commit fixes it by checking that the pointer is not NULL before u
Hi Shally, Tomasz,
> > >> >> >> >+ /* Window size */
> > >> >> >> >+ if (test_data->window_sz != -1) {
> > >> >> >> >+ if (param_range_check(test_data->window_sz,
> > >> >> >> >+ &cap->window_size)
> > >> >> >> What if cap->window_size is 0 i.e. implementation default?
>
Below is my conclusion for this bug.
An expert of x86 is required to follow-up.
Summary:
- CPU: Intel Skylake
- Linux environment: Ubuntu 18.04
- Compiler: GCC 7 or 8
- Scenario: testpmd crashes when it starts forwarding
- Behaviour: AVX2 version of rte_memc
67 matches
Mail list logo
