In the root table, there is some limitation of total number of header
modify actions, 16 or 8 for each. But in other tables, there is no
such strict limitation. In an IPv6 case, the IP fields modifying
will occupy more actions than that in IPv4, so the total support
number should be increased in or
This patch fixes Windows build failure caused due to
'config: change ABI versioning to global' patch.
This patch can be merged in 19.11 release.
Signed-off-by: Bruce Richardson
Reviewed-by: Ranjit Menon
Tested-by: Pallavi Kadam
---
config/meson.build | 2 +-
meson.build| 1 +
2 files c
- Add note for sharing an adapter between DPDK and Linux drivers.
- Update the firmware version in example.
- Add Config note for potential error due to lack of memzone desciptor
count.
Signed-off-by: Rasesh Mody
---
doc/guides/nics/qede.rst | 27 ++-
1 file changed
Hi Ferruh,
>From: Ferruh Yigit
>Sent: Friday, November 22, 2019 6:33 AM
>
>External Email
>
>--
>On 11/22/2019 7:51 AM, Rasesh Mody wrote:
>> - Add note for Co-existence of DPDK and Linux drivers.
>> - Update the firmware versi
22/11/2019 12:53, Andrew Rybchenko:
> On 11/22/19 2:15 PM, Thomas Monjalon wrote:
> > 22/11/2019 11:12, Andrew Rybchenko:
> >> On 11/22/19 1:01 AM, Thomas Monjalon wrote:
> >>> 19/11/2019 13:12, Andrew Rybchenko:
> The deprecation notice is required since it adds more requirements
> when
Adding new API function to query the maximum key ID
that could possibly returned by rte_hash_add_key and
rte_hash_add_key_with_hash. When RTE_HASH_EXTRA_FLAGS_MULTI_WRITER_ADD
is set, the maximum key id is larger than the entry count specified
by the user.
Signed-off-by: Kumar Amber
---
lib/libr
On Fri, 22 Nov 2019 22:30:11 +0530
Gokul Bargaje wrote:
> Thank you for the clarification. But I am still unable to understand how
> exactly timestamp is calculated before assigning to a timestamp field.
> Could you please tell me the steps to calculate the timestamp in DPDK?
>
> I have to imple
Thank you for the clarification. But I am still unable to understand how
exactly timestamp is calculated before assigning to a timestamp field.
Could you please tell me the steps to calculate the timestamp in DPDK?
I have to implement the PIE AQM algorithm in DPDK and for that, I need to
calculate
On 11/21/2019 7:34 PM, pbhagavat...@marvell.com wrote:
> From: Pavan Nikhilesh
>
> Use rte_rand() instead of random() for better randomness.
>
> Coverity Issue: 337666
>
> Signed-off-by: Pavan Nikhilesh
Reviewed-by: Ferruh Yigit
Applied to dpdk-next-net/master, thanks.
On 22/11/2019 15:24, Thomas Monjalon wrote:
> 22/11/2019 16:12, Kevin Traynor:
>> On 19/11/2019 10:40, Thomas Monjalon wrote:
>>> 14/10/2019 17:55, David Marchand:
The api rte_intr_ack that has been introduced to fix a race condition
observed with (at least) qede drivers/hw.
This is
On 11/22/2019 12:06 PM, Wei Hu (Xavier) wrote:
> From: "Wei Hu (Xavier)"
>
> This series add some fixes for hns3 PMD driver.
>
> Chengchang Tang (1):
> net/hns3: fix the error length limit of maiblox response
>
> Hao Chen (1):
> net/hns3: fix RSS hardware configuration restore failure
>
>
22/11/2019 16:54, David Marchand:
> --- a/.ci/linux-build.sh
> +++ b/.ci/linux-build.sh
> +if [ "$AARCH64" != "1" ]; then
> +./devtools/test-null.sh
You are missing the build directory as first parameter,
otherwise it won't find testpmd.
One nit: ./ is probably useless.
+Cc: sta...@dpdk.org
>-Original Message-
>From: pbhagavat...@marvell.com
>Sent: Friday, November 22, 2019 9:14 PM
>To: Jerin Jacob Kollanukkaran ; Pavan Nikhilesh
>Bhagavatula
>Cc: dev@dpdk.org
>Subject: [dpdk-dev] [PATCH v3 1/5] event/octeontx2: fix TIM HW race
>condition
>
>From: Pavan
The EAL command-line reference section duplicated material covered in a
previous chapter, was out of date, and generally is unnecessary as options
are best queried directly by passing "--help" to a DPDK binary. Therefore
we can drop this section to avoid having to try and keep it up-to-date in
the
This patchset includes documentation updates for both the Linux and
FreeBSD Getting Started Guide Docs. The majority of changes are to add
information on building using meson and ninja, with some additional
cleanups being performed at the same time.
Bruce Richardson (8):
doc: update Linux GSG sy
Since the meson instructions are the simpler of the two sets, and also the
ones most future-proof, put those first in the user documentation with make
instructions following them.
Signed-off-by: Bruce Richardson
---
.../linux_gsg/cross_build_dpdk_for_arm64.rst | 32 ++-
1 file c
Update the documentation on building and running apps on FreeBSD, taking
account of having used meson for building. We can also update the section
on the command-line parameters, rather than claiming to be a complete list
of parameters, it should describe how to get the complete list and only
cover
The output of running the helloworld example on FreeBSD was a little
out-of-date and can be shortened by using the latest version of DPDK.
Update appropriately.
Signed-off-by: Bruce Richardson
---
doc/guides/freebsd_gsg/install_from_ports.rst | 56 ---
1 file changed, 22 insertio
Update the FreeBSD GSG doc with instructions for installing using meson and
ninja rather than make.
Signed-off-by: Bruce Richardson
---
doc/guides/freebsd_gsg/build_dpdk.rst | 164 +++---
1 file changed, 40 insertions(+), 124 deletions(-)
diff --git a/doc/guides/freebsd_gsg/
Add instructions on building DPDK and using the pkg-config file to the
linux GSG.
Signed-off-by: Bruce Richardson
---
doc/guides/linux_gsg/build_dpdk.rst | 94 +++--
1 file changed, 90 insertions(+), 4 deletions(-)
diff --git a/doc/guides/linux_gsg/build_dpdk.rst
b/doc/
FreeBSD 10 is now EOL and all testing with DPDK takes place on BSD versions
11 and 12, so we can just remove the note. The BSD ports are supported on
all non-EOL versions of BSD.
Signed-off-by: Bruce Richardson
---
doc/guides/freebsd_gsg/install_from_ports.rst | 6 --
1 file changed, 6 delet
Update the system requirements section of the doc to cover builds with
meson and ninja. This involves updating the package dependencies to include
meson, ninja and python 3.5, and also updating the optional dependencies
section to explain that the components are enabled/disabled automatically
by me
On Fri, Nov 22, 2019 at 2:56 PM Ferruh Yigit wrote:
>
> On 11/22/2019 1:48 PM, Thomas Monjalon wrote:
> > The script test-null.sh is supposed to do a quick and simple
> > run of testpmd with null PMD only, for sanity check.
> > As it is not supposed to test probing of any other PMD,
> > physical d
Try to start testpmd with two vdevs without hugepages.
This is a really basic check, but better than nothing.
Signed-off-by: David Marchand
---
.ci/linux-build.sh | 4
1 file changed, 4 insertions(+)
diff --git a/.ci/linux-build.sh b/.ci/linux-build.sh
index c570ba24e6..e37176e91c 100755
-
From: Pavan Nikhilesh
Update start timestamp periodically to prevent drift.
Signed-off-by: Pavan Nikhilesh
---
drivers/event/octeontx2/otx2_tim_evdev.c | 28 +++
drivers/event/octeontx2/otx2_tim_evdev.h | 7 --
drivers/event/octeontx2/otx2_tim_worker.c | 19 +
From: Pavan Nikhilesh
Update SSO internal XAQ buffers based on number of timers in event timer
adapter.
Signed-off-by: Pavan Nikhilesh
---
drivers/event/octeontx2/otx2_evdev.h | 6 +-
drivers/event/octeontx2/otx2_evdev_adptr.c | 84 +-
drivers/event/octeontx2/otx2_ti
From: Pavan Nikhilesh
Since TIM buckets are always aligned to 32B and our cache line size being
128B, we will always have a cache miss when reading current_chunk pointer.
Avoid the cache miss by storing the current_chunk pointer in the bucket
opposite to the current bucket.
Signed-off-by: Pavan
From: Pavan Nikhilesh
Fix HW race condition observed when timeout resolution is low (<5us).
When HW traverses a given TIM bucket it will clear chunk_remainder,
but since SW always decreases the chunk_remainder at the start of the
arm routine it might cause a race where SW updates chunk_remainder
From: Pavan Nikhilesh
Enable mempool cache for internal mempool to improve alloc performance.
Signed-off-by: Pavan Nikhilesh
---
drivers/event/octeontx2/otx2_tim_evdev.c | 4 ++--
drivers/event/octeontx2/otx2_tim_worker.h | 15 ++-
2 files changed, 16 insertions(+), 3 deletions(-
On 11/22/2019 12:06 PM, Wei Hu (Xavier) wrote:
> From: "Wei Hu (Xavier)"
>
> When the application using VF device exits abnormally, for example,
> when it is killed by 'kill -9', kernel PF netdev driver also stores
> the corresponding configuration table entries of VF device.
>
> This patch fixe
22/11/2019 16:12, Kevin Traynor:
> On 19/11/2019 10:40, Thomas Monjalon wrote:
> > 14/10/2019 17:55, David Marchand:
> >> The api rte_intr_ack that has been introduced to fix a race condition
> >> observed with (at least) qede drivers/hw.
> >> This is an experimental api in master but it still fixe
On 19/11/2019 10:40, Thomas Monjalon wrote:
> 14/10/2019 17:55, David Marchand:
>> The api rte_intr_ack that has been introduced to fix a race condition
>> observed with (at least) qede drivers/hw.
>> This is an experimental api in master but it still fixes a problem, so
>> I'd like to see this in
Adding new API function to query the maximum key ID
that could possibly returned by add_key_functions. When
multi_key_add flag set, the maximum key id is larger
than the entry count specified by the user.
Signed-off-by: Kumar Amber
---
lib/librte_hash/rte_cuckoo_hash.c| 15 +++
l
On 11/18/2019 2:29 PM, Gokul Bargaje wrote:
> Hi,
>
> The timestamp assigned to packet at the time of enqueue (value of timestamp
> field in mbuf), is it in milliseconds or microseconds or in cpu cycles?
The unit is not defined [1]. 'rte_eth_read_clock()' was added [2] to help
converting it to ti
22/11/2019 15:03, Gaëtan Rivet:
> Hi Thomas,
>
> On Fri, Nov 22, 2019 at 02:48:08PM +0100, Thomas Monjalon wrote:
> > The script test-null.sh is supposed to do a quick and simple
> > run of testpmd with null PMD only, for sanity check.
> > As it is not supposed to test probing of any other PMD,
>
On 11/22/2019 7:51 AM, Rasesh Mody wrote:
> - Add note for Co-existence of DPDK and Linux drivers.
> - Update the firmware version in example.
> - Add Config note for potential error due to lack of memzone desciptor
>count.
>
> Signed-off-by: Rasesh Mody
> ---
> doc/guides/nics/qede.rst |
From: "Wei Hu (Xavier)"
Ethernet minimum packet length is 64 bytes. If upper application
sends packets with less than 60 bytes in length(no CRC), driver
adds padding processing to avoid failure.
Fixes: bba636698316 ("net/hns3: support Rx/Tx and related operations")
Cc: sta...@dpdk.org
Signed-of
From: Chengchang Tang
This patch removes the macro 'HNS3_REG_MSG_DATA_OFFSET' which is used to
prevent the array from accessing violation and it limits the response data
length to be 4. but the limit value is too short to get some longer
information such as 6 byte MAC address.
This patch modify
From: Hao Chen
This patch fixes the bug that hardware configuration called
tc_size doesn't restore to the initial value when starting
the app, configuring PFC and then restarting the app,
because of the tc_mode didn't initial when rss is disabled.
Fixes: c37ca66f2b27 ("net/hns3: support RSS")
Cc
From: Huisong Li
Currently, port link status is "up" in VF driver after user calling the
rte_eth_dev_stop API. This is unreasonable.
Therefore, this patch adjusts the strategy of getting link status from
PF driver for VF. VF drvier should stop getting link status from PF by
canceling the alarm t
From: "Wei Hu (Xavier)"
When the application using VF device exits abnormally, for example,
when it is killed by 'kill -9', kernel PF netdev driver also stores
the corresponding configuration table entries of VF device.
This patch fixes it by adding message of deleting VF configuration
table ent
From: "Min Hu (Connor)"
When setting duplicate vlan, hns3 driver will also add vlan entry
to vlan linked list, and this is unreasonable.
This patch adds checking whether the VLAN to be added already exists
in the linked list and preventing adding duplicate vlan.
Fixes: 411d23b9eafb ("net/hns3:
From: "Wei Hu (Xavier)"
This series add some fixes for hns3 PMD driver.
Chengchang Tang (1):
net/hns3: fix the error length limit of maiblox response
Hao Chen (1):
net/hns3: fix RSS hardware configuration restore failure
Huisong Li (1):
net/hns3: fix the strategy of getting link status f
On 11/22/2019 10:43 AM, David Marchand wrote:
> Following [1], testpmd memory consumption has skyrocketted.
> The rte_port structure has gotten quite fat.
>
> struct rte_port {
> [...]
> struct rte_eth_rxconf rx_conf[65536];/* 266280 3145728 */
> /* --- cacheline 53312 boundary (34
Hi Thomas,
On Fri, Nov 22, 2019 at 02:48:08PM +0100, Thomas Monjalon wrote:
> The script test-null.sh is supposed to do a quick and simple
> run of testpmd with null PMD only, for sanity check.
> As it is not supposed to test probing of any other PMD,
> physical device probing is switched to white
On 11/22/2019 1:48 PM, Thomas Monjalon wrote:
> The script test-null.sh is supposed to do a quick and simple
> run of testpmd with null PMD only, for sanity check.
> As it is not supposed to test probing of any other PMD,
> physical device probing is switched to whitelist mode
> by using a fake PCI
The script test-null.sh is supposed to do a quick and simple
run of testpmd with null PMD only, for sanity check.
As it is not supposed to test probing of any other PMD,
physical device probing is switched to whitelist mode
by using a fake PCI address (0:0.0).
It will also help to keep memory usage
Hi Dekel,
On 15/08/2019 10:26, Dekel Peled wrote:
> Function mlx5_flow_validate_action_drop() checks if another fate
> action is already present in this flow rule, using
> defined value MLX5_FLOW_FATE_ACTIONS.
> This patch enhances the check using value
> (MLX5_FLOW_FATE_ACTIONS | MLX5_FLOW_FATE_E
On Fri, Nov 22, 2019 at 8:54 PM Andrew Rybchenko
wrote:
>
> On 11/22/19 2:15 PM, Thomas Monjalon wrote:
> > 22/11/2019 11:12, Andrew Rybchenko:
> >> On 11/22/19 1:01 AM, Thomas Monjalon wrote:
> >>> 19/11/2019 13:12, Andrew Rybchenko:
> The deprecation notice is required since it adds more re
On 11/22/2019 1:12 PM, Thomas Monjalon wrote:
> 22/11/2019 13:24, Ferruh Yigit:
>> On 11/22/2019 10:43 AM, David Marchand wrote:
>>> diff --git a/devtools/test-null.sh b/devtools/test-null.sh
>>> index 9f9a459f76..6e5b1ad529 100755
>>> --- a/devtools/test-null.sh
>>> +++ b/devtools/test-null.sh
>>>
22/11/2019 13:24, Ferruh Yigit:
> On 11/22/2019 10:43 AM, David Marchand wrote:
> > diff --git a/devtools/test-null.sh b/devtools/test-null.sh
> > index 9f9a459f76..6e5b1ad529 100755
> > --- a/devtools/test-null.sh
> > +++ b/devtools/test-null.sh
> > @@ -25,6 +25,6 @@ else
> > fi
> >
> > (sleep
On Fri, Nov 22, 2019 at 6:52 PM Olivier Matz wrote:
>
> Hi Jerin,
Hi Olivier,
>
> On Thu, Nov 21, 2019 at 12:24:24PM +, Jerin Jacob Kollanukkaran wrote:
> > mbuf autotest fails with 19.11-rc3
> >
> > $ echo "mbuf_autotest" | sudo ./build/app/test/dpdk-test -c 0x3
> >
> > EAL: Detected 56 lco
From: "Wei Hu (Xavier)"
This series add some fixes for hns3 PMD driver.
Chengchang Tang (1):
net/hns3: fix the error length limit of maiblox response
Hao Chen (1):
net/hns3: fix RSS hardware configuration restore failure
Huisong Li (1):
net/hns3: fix the strategy of getting link status f
From: "Wei Hu (Xavier)"
When the application using VF device exits abnormally, for example,
when it is killed by 'kill -9', kernel PF netdev driver also stores
the corresponding configuration table entries of VF device.
This patch fixes it by adding message of deleting VF configuration
table ent
From: Hao Chen
This patch fixes the bug that hardware configuration called
tc_size doesn't restore to the initial value when starting
the app, configuring PFC and then restarting the app,
because of the tc_mode didn't initial when rss is disabled.
Fixes: c37ca66f2b27 ("net/hns3: support RSS")
Cc
https://bugs.dpdk.org/show_bug.cgi?id=370
Bug ID: 370
Summary: Cannot hotplug VFIO devices if VFIO driver was not
loaded at init
Product: DPDK
Version: unspecified
Hardware: All
OS: All
Status: U
On 11/21/19 9:30 PM, Stephen Hemminger wrote:
> The rte_pktmbuf_dump should display offset, refcount, and vlan
> info since these are often useful during debugging.
>
> Signed-off-by: Stephen Hemminger
May be it would be a bit better to split cosmetic changes into
separate patch(es), but anyway
On 11/22/2019 9:19 AM, Ferruh Yigit wrote:
> On 11/21/2019 4:59 PM, Stephen Hemminger wrote:
>> On Thu, 21 Nov 2019 14:27:01 +0100
>> Alejandra Ostruszka wrote:
>>
>>> Corrected one typo and ip address.
>>>
>>> Signed-off-by: Andrzej Ostruszka
>>>
>>> Fixes: de96fe68ae95 ("net/tap: add basic flow
On 11/22/2019 10:43 AM, David Marchand wrote:
> diff --git a/devtools/test-null.sh b/devtools/test-null.sh
> index 9f9a459f76..6e5b1ad529 100755
> --- a/devtools/test-null.sh
> +++ b/devtools/test-null.sh
> @@ -25,6 +25,6 @@ else
> fi
>
> (sleep 1 && echo stop) |
> -$testpmd -c $coremask --no-h
On Wed, Nov 20, 2019 at 10:29 AM Thomas Monjalon wrote:
>
> The testpmd fails in memory allocation since some ethdev structs
> have been extended.
> Increasing memory allocation from 150 to 300 MB makes it working again.
>
> Fixes: 436b3a6b6e62 ("ethdev: reserve space in main structs for extension
On 11/22/19 2:15 PM, Thomas Monjalon wrote:
> 22/11/2019 11:12, Andrew Rybchenko:
>> On 11/22/19 1:01 AM, Thomas Monjalon wrote:
>>> 19/11/2019 13:12, Andrew Rybchenko:
The deprecation notice is required since it adds more requirements
when RTE flow mark and flag actions may be used and r
This patch functionally reverts the patch in fixes line to not have any
hardcoded library path in the final binary for the security reasons, in
case this binary distributed to production environment.
RPATH only added in RTE_DEVEL_BUILD case and this binary shouldn't
distributed, but still removing
22/11/2019 11:12, Andrew Rybchenko:
> On 11/22/19 1:01 AM, Thomas Monjalon wrote:
> > 19/11/2019 13:12, Andrew Rybchenko:
> >> The deprecation notice is required since it adds more requirements
> >> when RTE flow mark and flag actions may be used and require
> >> changes in applications.
> > I am s
Following [1], testpmd memory consumption has skyrocketted.
The rte_port structure has gotten quite fat.
struct rte_port {
[...]
struct rte_eth_rxconf rx_conf[65536];/* 266280 3145728 */
/* --- cacheline 53312 boundary (3411968 bytes) was 40 bytes ago --- */
struct rte_eth_txconf
On 11/22/19 1:01 AM, Thomas Monjalon wrote:
> 19/11/2019 13:12, Andrew Rybchenko:
>> The deprecation notice is required since it adds more requirements
>> when RTE flow mark and flag actions may be used and require
>> changes in applications.
> I am still not sure what is the best solution here.
>
Hi all,
Though large portion of DPDK code/scripts are now using SPDX license
tags, there are still some old files having full license text without SPDX
tags. Their original authors/copyright holders are either not responding or
not traceable.
Let's not wait for them forever. Followi
This patch adds top level SPDX license identifiers for some of the dpdk
source and scripts, where the copyright owners have not yet agreed to
replace the full BSD-3 license plate.
This patch also add SPDX license tag for some of files with no
previous license plates. (DPDK is BSD-3)
Signed-off-by
Hi Jerin,
On Thu, Nov 21, 2019 at 12:24:24PM +, Jerin Jacob Kollanukkaran wrote:
> mbuf autotest fails with 19.11-rc3
>
> $ echo "mbuf_autotest" | sudo ./build/app/test/dpdk-test -c 0x3
>
> EAL: Detected 56 lcore(s)
> EAL: Detected 2 NUMA nodes
> EAL: Multi-process socket /var/run/dpdk/rte/m
Acked-by: Hemant Agrawal
Hi Thomas,
Somehow the patchwork is not reflecting this ACK.
Please apply this patch.
Regards,
Hemant
> -Original Message-
> From: dev On Behalf Of Pavan Nikhilesh
> Bhagavatula
> Sent: Monday, November 11, 2019 6:52 PM
> To: Stephen Hemminger
> Cc: dev@dpdk.org
> Subject: Re: [dpdk-
On 11/21/2019 4:59 PM, Stephen Hemminger wrote:
> On Thu, 21 Nov 2019 14:27:01 +0100
> Alejandra Ostruszka wrote:
>
>> Corrected one typo and ip address.
>>
>> Signed-off-by: Andrzej Ostruszka
>>
>> Fixes: de96fe68ae95 ("net/tap: add basic flow API patterns and actions")
>> Cc: sta...@dpdk.org
>
> -Original Message-
> From: Thomas Monjalon
> Sent: Wednesday 20 November 2019 20:18
> To: Burakov, Anatoly
> Cc: dev@dpdk.org; Mcnamara, John ; Kinsella,
> Ray ; Richardson, Bruce
> ; david.march...@redhat.com
> Subject: Re: [dpdk-dev] [PATCH v8 00/12] Implement the new ABI policy
>
72 matches
Mail list logo
