On Tue, Dec 3, 2019 at 10:15 PM Aaron Conole wrote:
>
> The service_valid call is used without properly bounds checking the
> input parameter. Almost all instances of the service_valid call are
> inside a for() loop that prevents excessive walks, but some of the
> public APIs don't bounds check a
On Wed, Dec 4, 2019 at 9:33 AM David Marchand wrote:
>
> On Tue, Dec 3, 2019 at 10:15 PM Aaron Conole wrote:
> >
> > The service_valid call is used without properly bounds checking the
> > input parameter. Almost all instances of the service_valid call are
> > inside a for() loop that prevents e
On Tue, Dec 3, 2019 at 4:27 PM Laatz, Kevin wrote:
> > Build targets in project: 1019
> > WARNING: Project specifies a minimum meson_version '>= 0.47.1' but
> > uses features which were added in newer versions:
> > * 0.48.0: {'console arg in custom_target'}
> > * 0.50.0: {'install arg in confi
On Wed, Dec 04, 2019 at 01:13:20PM +0800, Li Feng wrote:
> This msg is used to notify qemu that should get the config of backend.
>
> For example, vhost-user-blk uses this msg to notify guest os the
> compacity of backend has changed.
>
> Signed-off-by: Li Feng
> ---
> v2:
> * Fix a little log t
Hi Tiwei,
Thanks for your reply.
Yes, this new API currently is for vhost-user-blk in the SPDK project.
There is a patch in SPDK to use this API.
Thanks,
Feng Li
Tiwei Bie 于2019年12月4日周三 下午5:30写道：
>
> On Wed, Dec 04, 2019 at 01:13:20PM +0800, Li Feng wrote:
> > This msg is used to notify qemu t
Those libraries have been missed when switching to global ABI version.
Fixes: cba806e07d6f ("build: change ABI versioning to global")
Cc: sta...@dpdk.org
Signed-off-by: David Marchand
---
drivers/net/mlx4/Makefile| 2 +-
drivers/net/mlx4/meson.build | 2 +-
drivers/net/mlx5/Makefile| 2
On Wed, Dec 04, 2019 at 09:47:31AM +0100, David Marchand wrote:
> On Tue, Dec 3, 2019 at 4:27 PM Laatz, Kevin wrote:
> > > Build targets in project: 1019
> > > WARNING: Project specifies a minimum meson_version '>= 0.47.1' but
> > > uses features which were added in newer versions:
> > > * 0.48.
Fixed title s/unitialized/uninitialized/
On Wed, Nov 27, 2019 at 11:32 PM Stephen Hemminger
wrote:
>
> Valgrind reports that eal interrupt thread is calling epoll_ctl
> with uninitialized data. Trivial to fix by initializing it.
Added a note on it being a Valgrind false positive.
> Fixes: af7
On Wed, Dec 04, 2019 at 09:47:31AM +0100, David Marchand wrote:
> On Tue, Dec 3, 2019 at 4:27 PM Laatz, Kevin wrote:
> > > Build targets in project: 1019
> > > WARNING: Project specifies a minimum meson_version '>= 0.47.1' but
> > > uses features which were added in newer versions:
> > > * 0.48.
On Wed, Dec 4, 2019 at 12:56 PM Neil Horman wrote:
>
> On Wed, Dec 04, 2019 at 09:47:31AM +0100, David Marchand wrote:
> > On Tue, Dec 3, 2019 at 4:27 PM Laatz, Kevin wrote:
> > > > Build targets in project: 1019
> > > > WARNING: Project specifies a minimum meson_version '>= 0.47.1' but
> > > > u
On 12/4/19 2:12 PM, David Marchand wrote:
> Fixed title s/unitialized/uninitialized/
>
> On Wed, Nov 27, 2019 at 11:32 PM Stephen Hemminger
> wrote:
>>
>> Valgrind reports that eal interrupt thread is calling epoll_ctl
>> with uninitialized data. Trivial to fix by initializing it.
>
> Added a n
On Wed, Dec 4, 2019 at 1:17 PM Andrew Rybchenko
wrote:
>
> On 12/4/19 2:12 PM, David Marchand wrote:
> > Fixed title s/unitialized/uninitialized/
> >
> > On Wed, Nov 27, 2019 at 11:32 PM Stephen Hemminger
> > wrote:
> >>
> >> Valgrind reports that eal interrupt thread is calling epoll_ctl
> >> wi
In current PMD implementation, the RSS action is performed on L3 and L4,
including SRC and DST fields.
For some applications it can be useful to perform RSS on SRC only or on DST
only.
This RFC suggest use of existing rte_ethdev definitions to enhance RSS action
support in MLX5 PMD:
#define ETH
On Tue, 2019-12-03 at 23:59 +0800, Xiaolong Ye wrote:
> kernel_dir option in meson build is equivalent to RTE_KERNELDIR in
> make
> system, for cross-compilation case, users would specify it as local
> kernel src dir like
>
> //target-arm_glibc/linux-arm/linux-4.19.81/
>
> Current meson build wou
Hi Param,
Adding atomic operations to setting/clearing comp ctxt won't help, as
there is no race there. The admin queue is designed this way, that
only single completion context can be held, so you should serialize
access to the rte_eth_stats_get().
If you won't do that, the 2nd thread will try to
This RFC describes the update of MLX5 PMD, in order to support GTP tunnel type.
Update will include the support of matching on GTP item, fields msg_type and
teid.
GTP item validation function flow_dv_validate_item_gtp() will be implemented.
This function will:
Check that there is no tunnel layer
- RTE_FLOW_ITEM_TYPE_L2TPV3: matches a L2TPv3 header
Signed-off-by: Rory Sexton
Signed-off-by: Dariusz Jagus
---
app/test-pmd/cmdline_flow.c | 28 +
doc/guides/prog_guide/rte_flow.rst | 8 ++
doc/guides/testpmd_app_ug/testpmd_funcs.rst | 4 +++
Signed-off-by: Rory Sexton
Signed-off-by: Dariusz Jagus
---
drivers/net/i40e/i40e_ethdev.c | 11 ++-
drivers/net/i40e/i40e_ethdev.h | 9 ++
drivers/net/i40e/i40e_fdir.c | 34 +
drivers/net/i40e/i40e_flow.c | 55 ++
4 files changed,
On 12/04, Luca Boccassi wrote:
>On Tue, 2019-12-03 at 23:59 +0800, Xiaolong Ye wrote:
>> kernel_dir option in meson build is equivalent to RTE_KERNELDIR in
>> make
>> system, for cross-compilation case, users would specify it as local
>> kernel src dir like
>>
>> //target-arm_glibc/linux-arm/linux
From: Pavan Nikhilesh
This patchset adds support for event mode in l3fwd.
The poll mode is still the default mode of operation.
The following new command line parameters are added:
--mode: Dictates the mode of operation either poll or event. If unset then
by default poll mode is used.
From: Sunil Kumar Kori
Add framework to enable event device as a producer of packets.
To switch between event mode and poll mode the following options
have been added:
`--mode="eventdev"` or `--mode="poll"`
Also, allow the user to select the schedule type to be either
RTE_SCHED_TYPE_ORDER
From: Sunil Kumar Kori
Add infra to split eventdev framework based on event Tx adapter
capability.
If event Tx adapter has internal port capability then we use
`rte_event_eth_tx_adapter_enqueue` to transmitting packets else
we use a SINGLE_LINK event queue to enqueue packets to a service
core whi
From: Sunil Kumar Kori
Add event device queue and port setup based on event eth Tx adapter
capabilities.
Signed-off-by: Sunil Kumar Kori
---
examples/l3fwd/l3fwd_event.c | 28 +-
examples/l3fwd/l3fwd_event.h | 1 +
examples/l3fwd/l3fwd_event_generic.c |
From: Sunil Kumar Kori
Add ethernet port Rx/Tx queue setup for event device which are later
used for setting up event eth Rx/Tx adapters.
Signed-off-by: Sunil Kumar Kori
---
examples/l3fwd/l3fwd.h | 10 +++
examples/l3fwd/l3fwd_event.c | 129 ++-
examples
From: Pavan Nikhilesh
Add event eth Rx/Tx adapter setup for both generic and internal port
event device pipelines.
Signed-off-by: Sunil Kumar Kori
Signed-off-by: Pavan Nikhilesh
---
examples/l3fwd/l3fwd_event.c | 3 +
examples/l3fwd/l3fwd_event.h | 1 +
example
From: Pavan Nikhilesh
Add event device configuration based on the capabilities of the
probed event device.
Signed-off-by: Pavan Nikhilesh
---
examples/l3fwd/l3fwd_event.c | 3 +
examples/l3fwd/l3fwd_event.h | 36 ++
examples/l3fwd/l3fwd_event_generic.c
From: Pavan Nikhilesh
Add em main loop for handling events based on capabilities of the
event device.
Signed-off-by: Pavan Nikhilesh
---
examples/l3fwd/l3fwd.h | 10 ++
examples/l3fwd/l3fwd_em.c| 177 +++
examples/l3fwd/l3fwd_em.h|
From: Pavan Nikhilesh
Update l3fwd user guide to include event device related information.
Signed-off-by: Pavan Nikhilesh
---
doc/guides/sample_app_ug/l3_forward.rst | 76 +++--
1 file changed, 70 insertions(+), 6 deletions(-)
diff --git a/doc/guides/sample_app_ug/l3_forwa
From: Pavan Nikhilesh
Add graceful teardown that addresses both event mode and poll mode.
Signed-off-by: Pavan Nikhilesh
---
examples/l3fwd/main.c | 49 ++-
1 file changed, 34 insertions(+), 15 deletions(-)
diff --git a/examples/l3fwd/main.c b/examples/
From: Pavan Nikhilesh
Add service core setup when eventdev and Rx/Tx adapter don't have
internal port capability.
Signed-off-by: Pavan Nikhilesh
---
examples/l3fwd/l3fwd_event.c | 6 +++
examples/l3fwd/main.c| 93
2 files changed, 99 insertions(+)
From: Pavan Nikhilesh
Add lpm main loop for handling events based on capabilities of the
event device.
Signed-off-by: Pavan Nikhilesh
---
examples/l3fwd/l3fwd.h | 9 ++
examples/l3fwd/l3fwd_event.c | 9 ++
examples/l3fwd/l3fwd_event.h | 5 +
examples/l3fwd/l3fwd_lpm.c | 231 +
Previous fix gives hiccups to gcc on RHEL 7.6:
== Build lib/librte_eal/linux/eal
CC eal_interrupts.o
...lib/librte_eal/linux/eal/eal_interrupts.c: In function
‘eal_intr_thread_main’:
...lib/librte_eal/linux/eal/eal_interrupts.c:1048:9: error: missing
initializer for field ‘events’ of ‘struct
Currently there are a couple of limitations on the logging system: Most
of the logs are compiled out and both datapath and controlpath logs
share the same loglevel.
This patch tries to help fix that situation by:
- Splitting control plane and data plane logs
- Making control plane logs dynamic whi
On Wed, Dec 04, 2019 at 10:18:21PM +0800, Ye Xiaolong wrote:
> On 12/04, Luca Boccassi wrote:
> >On Tue, 2019-12-03 at 23:59 +0800, Xiaolong Ye wrote:
> >> kernel_dir option in meson build is equivalent to RTE_KERNELDIR in
> >> make
> >> system, for cross-compilation case, users would specify it as
On Wed, Dec 4, 2019 at 8:13 PM wrote:
>
> From: Pavan Nikhilesh
>
> This patchset adds support for event mode in l3fwd.
> The poll mode is still the default mode of operation.
>
> The following new command line parameters are added:
> --mode: Dictates the mode of operation either poll or event.
Any update on this patch?
On 19 Nov 2019, at 14:45, Eelco Chaudron wrote:
During a kernel PF reset, this event is propagated to the VF.
The DPDK VF PMD will execute the reset task before the PF is done
with his. This results in the admin queue message not being responded
to leaving the port in
All buffers and ring info should be written before tail register update.
This patch relocates the write memory barrier before updating tail register
to avoid potential issues.
Fixes: 11b5c7daf019 ("raw/ntb: add enqueue and dequeue functions")
Cc: sta...@dpdk.org
Signed-off-by: Xiaoyun Li
---
dr
In prerequisites of ntb guide, the correct flag when loading igb_uio
module should be `wc_activate=1`, not `wc_active=1`.
Fixes: 11b5c7daf019 ("raw/ntb: add enqueue and dequeue functions")
Cc: sta...@dpdk.org
Signed-off-by: Xiaoyun Li
---
doc/guides/rawdevs/ntb.rst | 4 ++--
1 file changed, 2 i
On Wed, 4 Dec 2019 16:00:02 +0100
David Marchand wrote:
> + struct epoll_event ev;
This needs to be initialized (like it was above) or it will cause
warnings with valgrind about uninitialized data in system calls.
This file was missing SPDX tag. Convert BSD boilerplate
to license tag.
Signed-off-by: Stephen Hemminger
---
app/test/test_timer_racecond.c | 34 +++---
1 file changed, 3 insertions(+), 31 deletions(-)
diff --git a/app/test/test_timer_racecond.c b/app/test/test_timer
This file still had original BSD boilerplate text.
Replace it with SPDX tag.
Signed-off-by: Stephen Hemminger
---
devtools/cocci.sh | 30 +-
1 file changed, 1 insertion(+), 29 deletions(-)
diff --git a/devtools/cocci.sh b/devtools/cocci.sh
index 8b17a8cebac3..77b7447
Trivial file was missing any license.
Signed-off-by: Stephen Hemminger
---
devtools/load-devel-config | 2 ++
1 file changed, 2 insertions(+)
diff --git a/devtools/load-devel-config b/devtools/load-devel-config
index 380c79db41eb..ca1bc21b55e3 100644
--- a/devtools/load-devel-config
+++ b/devto
These are tests and scripts with missing SPDX tags.
Stephen Hemminger (5):
app/test: add SPDX tag to timer test
devtools: add license tag to cocci.sh
devtools: add SPDX tag to load-devel-config
examples/ipsecgw: add SPDX license tag
examples/performance-thread: add mising SPDX tag
app/
This example had no license.
Signed-off-by: Stephen Hemminger
---
examples/performance-thread/l3fwd-thread/test.sh | 2 ++
1 file changed, 2 insertions(+)
diff --git a/examples/performance-thread/l3fwd-thread/test.sh
b/examples/performance-thread/l3fwd-thread/test.sh
index b7718b6223b0..43ff10
This trivial file had no license info.
Signed-off-by: Stephen Hemminger
---
.../ipsec-secgw/test/trs_aesgcm_inline_crypto_fallback_defs.sh | 1 +
.../ipsec-secgw/test/tun_aesgcm_inline_crypto_fallback_defs.sh | 1 +
2 files changed, 2 insertions(+)
diff --git
a/examples/ipsec-secgw/test/tr
On Wed, Dec 4, 2019 at 4:37 PM Stephen Hemminger
wrote:
>
> On Wed, 4 Dec 2019 16:00:02 +0100
> David Marchand wrote:
>
> > + struct epoll_event ev;
> This needs to be initialized (like it was above) or it will cause
> warnings with valgrind about uninitialized data in syste
On Wed, 4 Dec 2019 16:00:02 +0100
David Marchand wrote:
> Previous fix gives hiccups to gcc on RHEL 7.6:
>
> == Build lib/librte_eal/linux/eal
> CC eal_interrupts.o
> ...lib/librte_eal/linux/eal/eal_interrupts.c: In function
> ‘eal_intr_thread_main’:
> ...lib/librte_eal/linux/eal/eal_interr
On Thu, Nov 28, 2019 at 08:45:42AM -0800, Stephen Hemminger wrote:
> On Thu, 28 Nov 2019 08:10:23 +
> Harman Kalra wrote:
>
> > On Wed, Nov 27, 2019 at 04:03:19PM -0800, Stephen Hemminger wrote:
> > > External Email
> > >
> > >
> On 2 Dec 2019, at 17:33, Stephen Hemminger wrote:
>
> On Tue, 15 Oct 2019 10:22:20 +0200
> Alfredo Cardigliano wrote:
>
>> Add hardware structures and message commands definitions for
>> Pensando network adapters.
>>
>> Signed-off-by: Alfredo Cardigliano
>> Reviewed-by: Shannon Nelson
>
The multicast set list function now has a return value, which is checked
by the calling functions. A rollback occurs on detection of failure, to
realign local config with the device config.
The error print statement in the function had included the port_id and
mc_addr_nb values in the wrong order,
On 12/4/2019 4:38 PM, Ciara Power wrote:
> The multicast set list function now has a return value, which is checked
> by the calling functions. A rollback occurs on detection of failure, to
> realign local config with the device config.
>
> The error print statement in the function had included th
On Wed, Dec 4, 2019 at 4:00 PM David Marchand wrote:
>
> Previous fix gives hiccups to gcc on RHEL 7.6:
>
> == Build lib/librte_eal/linux/eal
> CC eal_interrupts.o
> ...lib/librte_eal/linux/eal/eal_interrupts.c: In function
> ‘eal_intr_thread_main’:
> ...lib/librte_eal/linux/eal/eal_interrupts
We recently started to get random failures on the common_autotest ut with
clang on Ubuntu 16.04.6.
Example: https://travis-ci.com/DPDK/dpdk/jobs/263177424
Wrong rte_log2_u64(0) val 0, expected
Test Failed
The ut passes 0 to log2() to get an expected value.
Quoting log2 / log(3) manual:
David Marchand writes:
> We recently started to get random failures on the common_autotest ut with
> clang on Ubuntu 16.04.6.
>
> Example: https://travis-ci.com/DPDK/dpdk/jobs/263177424
>
> Wrong rte_log2_u64(0) val 0, expected
> Test Failed
>
> The ut passes 0 to log2() to get an expect
On Wed, Dec 04, 2019 at 05:43:50PM +0800, Li Feng wrote:
> Hi Tiwei,
> Thanks for your reply.
> Yes, this new API currently is for vhost-user-blk in the SPDK project.
I see. Thanks for the clarification.
In this case, it should be declared in rte_vhost.h instead
of vhost_user.h which is an interna
Tiwei Bie 于2019年12月5日周四 上午10:06写道：
>
> On Wed, Dec 04, 2019 at 05:43:50PM +0800, Li Feng wrote:
> > Hi Tiwei,
> > Thanks for your reply.
> > Yes, this new API currently is for vhost-user-blk in the SPDK project.
>
> I see. Thanks for the clarification.
> In this case, it should be declared in rte_
On Thu, Dec 05, 2019 at 12:01:55PM +0800, Li Feng wrote:
> Tiwei Bie 于2019年12月5日周四 上午10:06写道：
> > On Wed, Dec 04, 2019 at 05:43:50PM +0800, Li Feng wrote:
> > > Hi Tiwei,
> > > Thanks for your reply.
> > > Yes, this new API currently is for vhost-user-blk in the SPDK project.
> >
> > I see. Thanks
This msg is used to notify qemu that should get the config of backend.
For example, vhost-user-blk uses this msg to notify guest os the
compacity of backend has changed.
Signed-off-by: Li Feng
---
v3:
* Move the declare to rte_vhost.h
* Add the symbol in rte_vhost_version.map
v2:
* Fix a little
58 matches
Mail list logo
