On Tue, Apr 18, 2017 at 01:22:27PM +0300, Shahaf Shuler wrote:
> Currently the argument process is done without indication which
> parameter was forced by the application and which one is on it
> default value.
> This becomes problematic when different features requires different
> defaults. For ex
Current virtio_dev_stop only disables interrupt and marks link down,
When it is invoked, tx/rx traffic flows still work. This is a strange
behavior. The patch supports the switch of flow.
Signed-off-by: Zhiyong Yang
---
Changes in V2:
Use the flag "started" introduced by yuanhan's applied patch,
We has already test on 16 node server, everything is fine, without any issue.
Testcase as follows:
I. with dpdk args -c 0xf, test pass
II. with 32 forward-lcores, each node with 2 lcores(total 16 nodes), test pass
III. with forward lcore id greater than 128, test pass
IV. with forward and mast
On Wed, Apr 19, 2017 at 06:21:59AM +, Tan, Jianfeng wrote:
>
>
> > I've expected it to be plain english, something like following:
> >
> > /*
> > * Return the physical address (or virtual address in case of
> > * virtio-user) of mbuf data buffer.
> > *
> > * The addre
> -Original Message-
> From: Yuanhan Liu [mailto:yuanhan@linux.intel.com]
> Sent: Wednesday, April 19, 2017 1:54 PM
> To: Tan, Jianfeng
> Cc: dev@dpdk.org; olivier.m...@6wind.com; sta...@dpdk.org
> Subject: Re: [PATCH v2] net/virtio-user: fix not working on 32-bit system
>
> On Wed,
On Fri, Apr 14, 2017 at 03:53:18PM +0800, Yuanhan Liu wrote:
> Like what we did for virtio PMD driver [0][1], we could also apply such
> trick to vhost, to avoid the memory write on net header when necessary.
>
> [0]: c9ea670c1dc7 ("net/virtio: fix performance regression due to TSO")
> [1]: 16994a
On Wed, Apr 19, 2017 at 02:30:33AM +, Jianfeng Tan wrote:
> virtio-user cannot work on 32-bit system as higher 32-bit of the
> addr field (64-bit) in the desc is filled with non-zero value
> which should not happen for a 32-bit system.
>
> In case of virtio-user, we use buf_addr of mbuf to fil
For zero copy mode, we need pin the mbuf to not let the underlaying PMD
driver (or the app) free the mbuf. Currently, only the heading mbuf is
pinned. However, the mbuf free function would try to free all mbufs
in the mbuf chain (-1 to the refcnt). This may lead the head mbuf being
still pinned, wh
Ok, yuanhan. I see.
> -Original Message-
> From: Yuanhan Liu [mailto:yuanhan@linux.intel.com]
> Sent: Wednesday, April 19, 2017 10:58 AM
> To: Yang, Zhiyong
> Cc: dev@dpdk.org; maxime.coque...@redhat.com
> Subject: Re: [PATCH 0/2] net/virtio: support to turn on/off the traffic flow
>
Hi,
Any more comments on this commit? Could it be merged? Compilation is still
failing..
Thursday, April 13, 2017 12:36 PM, Van Haaren, Harry:
> > From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Shahaf Shuler
> > Sent: Thursday, April 13, 2017 6:29 AM
> > To: thomas.monja...@6wind.com
> > C
When insmod "igb_uio" with "intr_mode=legacy and test link
status interrupt. Since INTx interrupt is not supported by
X710/XL710/XXV710, it will cause Input/Output error when
reading file descriptor.
Signed-off-by: Qiming Yang
Acked-by Jingjing Wu
Acked-by: John McNamara
---
v2 changes:
* move
On Wed, Apr 19, 2017 at 02:31:58AM +, Yang, Zhiyong wrote:
> Haha, you are right.
> I will rework it and send V2.
Note that the "started" field is added in one of my recent patch, to
addres the link status always being UP.
So you should pull the latest virtio code and make a patch there: you
Hi，yuanhan:
> -Original Message-
> From: Yuanhan Liu [mailto:yuanhan@linux.intel.com]
> Sent: Wednesday, April 19, 2017 10:03 AM
> To: Yang, Zhiyong
> Cc: dev@dpdk.org; maxime.coque...@redhat.com
> Subject: Re: [PATCH 0/2] net/virtio: support to turn on/off the traffic flow
>
virtio-user cannot work on 32-bit system as higher 32-bit of the
addr field (64-bit) in the desc is filled with non-zero value
which should not happen for a 32-bit system.
In case of virtio-user, we use buf_addr of mbuf to fill the
virtqueue desc addr. This is a regression bug. For 32-bit system,
On Fri, Apr 14, 2017 at 06:10:30AM +, Jianfeng Tan wrote:
> Previously, we miss to set intr_handle->fd which will be used as
> target file for epoll to check LSC.
>
> As a result, stdin (0) is used and intr thread keeps busy whenever
> data comes from stdin.
>
> To fix this, we use vhostfd as
On Fri, Apr 14, 2017 at 02:36:45PM +0800, Yuanhan Liu wrote:
> The virtio port link status will always be UP, even the port is stopped:
>
> testpmd> port stop 0
> Stopping ports...
> Checking link statuses...
> Port 0 Link Up - speed 1 Mbps - full-duplex
> Done
>
> The lin
On Mon, Apr 17, 2017 at 08:50:52AM +, Yang, Zhiyong wrote:
> Hi, yuanhan:
> Sorry for the delay reply due to my annual leave.
>
> > -Original Message-
> > From: Yuanhan Liu [mailto:yuanhan@linux.intel.com]
> > Sent: Thursday, April 6, 2017 12:00 PM
> > To: Yang, Zhiyong
> >
Hi Adrien,
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Adrien Mazarguil
> Sent: Friday, April 14, 2017 10:30 PM
> To: O'Driscoll, Tim
> Cc: dev@dpdk.org
> Subject: Re: [dpdk-dev] 17.08 Roadmap
>
> On Fri, Apr 14, 2017 at 01:27:13PM +, O'Driscoll, Tim wr
On Tue, Apr 18, 2017 at 10:20:41AM +0200, Maxime Coquelin wrote:
>
>
> On 04/17/2017 09:27 AM, Yuanhan Liu wrote:
> >A "return" is missing on error, which could lead to a "use after free"
> >issue (about var "conn").
> >
> >Fixes: 65388b43f592 ("vhost: fix fd leaks for vhost-user server mode")
>
> -Original Message-
> From: akhil.go...@nxp.com [mailto:akhil.go...@nxp.com]
> Sent: Monday, April 10, 2017 1:31 PM
> To: dev@dpdk.org
> Cc: Doherty, Declan; De Lara Guarch, Pablo; hemant.agra...@nxp.com;
> Mcnamara, John; nhor...@tuxdriver.com; thomas.monja...@6wind.com;
> Akhil Goyal
>
Signed-off-by: Thomas Monjalon
---
MAINTAINERS | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/MAINTAINERS b/MAINTAINERS
index b064a8e93..d04d4d671 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -21,7 +21,7 @@ Descriptions of section entries:
General Project Administra
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of De Lara Guarch,
> Pablo
> Sent: Tuesday, April 18, 2017 10:31 PM
> To: Zhang, Roy Fan; dev@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH] examples/l2fwd-crypto: add cryptodev
> mask option
>
>
>
> > -Original M
> -Original Message-
> From: Zhang, Roy Fan
> Sent: Tuesday, April 18, 2017 12:35 PM
> To: dev@dpdk.org
> Cc: De Lara Guarch, Pablo
> Subject: [PATCH] examples/l2fwd-crypto: add cryptodev mask option
>
> Previously, l2fwd-crypto application did not give user the
> flexibility to decide w
> -Original Message-
> From: De Lara Guarch, Pablo
> Sent: Monday, April 17, 2017 1:24 PM
> To: dev@dpdk.org
> Cc: sta...@dpdk.org; De Lara Guarch, Pablo
> Subject: [PATCH] examples/l2fwd-crypto: fix AEAD tests when AAD is zero
>
> For AEAD algorithms, additional authenticated data (AAD)
> -Original Message-
> From: De Lara Guarch, Pablo
> Sent: Monday, April 10, 2017 10:58 AM
> To: dev@dpdk.org
> Cc: sta...@dpdk.org; De Lara Guarch, Pablo
> Subject: [PATCH] app/crypto-perf: fix length for wireless algos
>
> When SNOW3G/KASUMI/ZUC algorithms are used, ciphering
> and aut
> -Original Message-
> From: De Lara Guarch, Pablo
> Sent: Wednesday, April 12, 2017 10:26 AM
> To: dev@dpdk.org
> Cc: Doherty, Declan; sta...@dpdk.org; De Lara Guarch, Pablo
> Subject: [PATCH] app/crypto-perf: fix AEAD tests when AAD is zero
>
> For AEAD algorithms, additional authentic
Thanks Ferruh, It all looks good and our tests pass
Acked-by: Ed Czeck
On 4/18/2017 7:27 PM, Ferruh Yigit wrote:
> There are two PMDs in next-net and not merged into main tree:
> - ARK
> - DPAA2
>
> These drivers also needs to get these updates.
latest next-net rebased on main tree to help development of these.
! next-net is broken now !
>
> And to prevent breaki
Signed-off-by: Ferruh Yigit
---
CC: Shepard Siegel
CC: Ed Czeck
CC: John Miller
---
drivers/net/ark/ark_ethdev.c | 44
1 file changed, 32 insertions(+), 12 deletions(-)
diff --git a/drivers/net/ark/ark_ethdev.c b/drivers/net/ark/ark_ethdev.c
index
Signed-off-by: Ferruh Yigit
---
CC: Jianfeng Tan
---
drivers/net/xenvirt/rte_eth_xenvirt.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/drivers/net/xenvirt/rte_eth_xenvirt.c
b/drivers/net/xenvirt/rte_eth_xenvirt.c
index 6ec8c08..7bd29fa 100644
--- a/drivers/net/xenvirt/rte_eth_xenvirt.c
There are two PMDs in next-net and not merged into main tree:
- ARK
- DPAA2
These drivers also needs to get these updates.
And to prevent breaking build these changes can be squashed into PMD
in next-net before integration. This means these changes needs to be
merged promptly.
ARK PMD updates ar
On 4/18/2017 3:00 PM, Ferruh Yigit wrote:
> eth_dev->device is now NULL, and accessing eth_dev->device->driver
> crashes.
> No need to set this value, removed completely.
>
> Fixes: 5d2aa461cbca ("vdev: use generic vdev struct for probe and remove")
>
> Signed-off-by: Ferruh Yigit
Applied to dp
On 4/18/2017 2:03 PM, Andrew Rybchenko wrote:
> Fixes: 4ec1fc3ba881 ("net/sfc: add basic stubs for RSS support on driver
> attach")
>
> Signed-off-by: Andrew Rybchenko
> Reviewed-by: Andy Moreton
Series applied to dpdk-next-net/master, thanks.
> -Original Message-
> From: Jain, Deepak K
> Sent: Tuesday, April 18, 2017 10:23 AM
> To: Kusztal, ArkadiuszX; dev@dpdk.org
> Cc: Trahe, Fiona; De Lara Guarch, Pablo; Griffin, John
> Subject: RE: [PATCH] crypto/qat: fix AES-GCM authentication length
>
>
> > -Original Message-
>
> -Original Message-
> From: Jain, Deepak K
> Sent: Tuesday, April 18, 2017 10:40 AM
> To: Kusztal, ArkadiuszX; dev@dpdk.org
> Cc: Trahe, Fiona; De Lara Guarch, Pablo; Griffin, John
> Subject: RE: [PATCH] crypto/qat: fix IV zero physical address
>
>
> > -Original Message-
> > Fr
On 4/18/2017 1:51 PM, Andrew Rybchenko wrote:
> Coverity issue: 1419717
> Fixes: a9825ccf5bb8 ("net/sfc: support flow API filters")
>
> Signed-off-by: Andrew Rybchenko
> Reviewed-by: Andy Moreton
Applied to dpdk-next-net/master, thanks.
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of De Lara Guarch,
> Pablo
> Sent: Tuesday, April 18, 2017 4:36 PM
> To: Zhang, Roy Fan; dev@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH v3] crypto/scheduler: improve
> commandline parsing
>
>
>
> > -Original Me
The change of _rte_eth_dev_callback_process has not been done in 17.05.
Let's postpone to 17.08.
Signed-off-by: Bernard Iremonger
---
doc/guides/rel_notes/deprecation.rst | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/doc/guides/rel_notes/deprecation.rst
b/doc/guides/re
The deprecation of the bypass functions in the ethdev has not been
done in 17.05. Let's postpone to 17.08.
Signed-off-by: Bernard Iremonger
---
doc/guides/rel_notes/deprecation.rst | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/doc/guides/rel_notes/deprecation.rst
b/doc/gui
> -Original Message-
> From: Zhang, Roy Fan
> Sent: Tuesday, April 18, 2017 2:12 PM
> To: De Lara Guarch, Pablo; dev@dpdk.org
> Cc: zbigniew.bo...@caviumnetworks.com;
> jerin.ja...@caviumnetworks.com; Doherty, Declan; De Lara Guarch, Pablo
> Subject: RE: [dpdk-dev] [PATCH 2/2] test/crypto
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of De Lara Guarch,
> Pablo
> Sent: Tuesday, April 18, 2017 12:41 PM
> To: dev@dpdk.org
> Cc: zbigniew.bo...@caviumnetworks.com;
> jerin.ja...@caviumnetworks.com; Doherty, Declan
> Subject: Re: [dpdk-dev] [PATCH 1/2]
> -Original Message-
> From: Zhang, Roy Fan
> Sent: Tuesday, April 18, 2017 12:28 PM
> To: dev@dpdk.org
> Cc: De Lara Guarch, Pablo
> Subject: [PATCH v3] crypto/scheduler: improve commandline parsing
>
> This patch improves the cryptodev scheduler PMD's commandline
> parsing capability.
On Tue, 18 Apr 2017 20:11:28 +0530, Santosh Shukla
wrote:
> Cc: sta...@dpdk.org
> Signed-off-by: Santosh Shukla
Series:
Acked-by: Olivier Matz
Note for Thomas when applying: you may want to remove one "test/" in
the title and remove the uppercase letter.
On 4/18/2017 3:22 PM, Olivier Matz wrote:
> The initialization of the default log level (from configuration) was
> removed by mistake in a previous commit. The global log level was
> wrongly set to debug when no --log-level argument was passed. Restore
> this initialization.
>
> Before:
> $ ./bu
On 4/18/2017 4:26 PM, Olivier MATZ wrote:
> Hi Ferruh,
>
> On Tue, 18 Apr 2017 16:00:45 +0100, Ferruh Yigit
> wrote:
>> On 4/18/2017 3:22 PM, Olivier Matz wrote:
>>> This field is only used in the initialization phase. Remove it since the
>>> global log level can also be retrieved using a public
CC'ing sta...@dpdk.org.
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of De Lara Guarch,
> Pablo
> Sent: Tuesday, April 18, 2017 4:24 PM
> To: Zhang, Roy Fan; dev@dpdk.org
> Cc: sta...@dpdk.com
> Subject: Re: [dpdk-dev] [PATCH v3] app/test-crypto-perf: fix crypto
Hi Ferruh,
On Tue, 18 Apr 2017 16:00:45 +0100, Ferruh Yigit wrote:
> On 4/18/2017 3:22 PM, Olivier Matz wrote:
> > This field is only used in the initialization phase. Remove it since the
> > global log level can also be retrieved using a public API:
> > rte_log_get_global_level().
> >
> > Signe
> -Original Message-
> From: Zhang, Roy Fan
> Sent: Tuesday, April 18, 2017 3:49 PM
> To: dev@dpdk.org
> Cc: De Lara Guarch, Pablo; sta...@dpdk.com
> Subject: [PATCH v3] app/test-crypto-perf: fix crypto operation resubmission
>
> This patch fixes the crypto operation resubmission problem
> -Original Message-
> From: Zhang, Roy Fan
> Sent: Tuesday, April 18, 2017 12:33 PM
> To: dev@dpdk.org
> Cc: De Lara Guarch, Pablo
> Subject: [PATCH v3] crypto/scheduler: fix Doxygen comments
>
> This patch adds the missing doxygen comments and updated
> inline comments to cryptodev sch
On 4/18/2017 3:22 PM, Olivier Matz wrote:
> This field is only used in the initialization phase. Remove it since the
> global log level can also be retrieved using a public API:
> rte_log_get_global_level().
>
> Signed-off-by: Olivier Matz
<...>
> diff --git a/lib/librte_eal/common/eal_common_l
Hi,
I think I might have found a bug in test-pmd, but I want to make sure.
One can set VLAN stripping to be on or off with "vlan set strip off/on
all" etc. Let's assume that user stops all ports ("port stop all"), then
modifies max-pkt-len and disbales VLAN stripping ("port config all
max-pkt
This patch fixes the crypto operation resubmission problem in crypto
perferformance test. Originally, when needed crypto ops amount is
smaller than the enqueued crypto ops in the last round, one or more
processed crypto operations will be re-enqueued.
Fixes: f8be1786b1b8 ("app/crypto-perf: introdu
Mempool_perf autotest currently does perf regression for:
* nochache
* cache
Introducing default_pool, mainly targeted for ext-mempool regression
test. Ext-mempool don't need 'cache' modes so only adding test-case
support for 'nocache' mode.
So to run ext-mempool perf regression, user has to se
Cc: sta...@dpdk.org
Signed-off-by: Santosh Shukla
---
v3 --> v4:
- removed extra mp local var.
- Includes nit changes refer
http://dpdk.org/dev/patchwork/patch/23680/
test/test/test_mempool_perf.c | 63 +--
1 file changed, 30 insertions(+), 33 deletio
Mempool_perf test not freeing pool memory.
Cc: sta...@dpdk.org
Signed-off-by: Santosh Shukla
Acked-by: Shreyansh Jain
---
v1 --> v2:
- Fix patch context
v2 -- v3 --> v4
- Done changes because of [1/3] patch
test/test/test_mempool_perf.c | 30 ++
1 file changed, 1
Hi Olivier,
On Tuesday 18 April 2017 07:12 PM, Olivier MATZ wrote:
> Hi Santosh,
>
> On Tue, 18 Apr 2017 14:04:46 +0530, Santosh Shukla
> wrote:
>> Cc: sta...@dpdk.org
>> Signed-off-by: Santosh Shukla
>> ---
>> v3:
>> - Cleanup code change as per discussion in
>>http://dpdk.org/dev/patch
This patch fixes the crypto operation resubmission problem in crypto
perferformance test. Originally, when needed crypto ops amount is
smaller than the enqueued crypto ops in the last round, one or more
processed crypto operations will be re-enqueued.
Fixes: f8be1786b1b8 ("app/crypto-perf: introdu
Check if virtual device name is NULL,
to avoid possible segmentation faults.
Fixes: 5d2aa461cbca ("vdev: use generic vdev struct for probe and remove")
Signed-off-by: Pablo de Lara
---
drivers/crypto/aesni_gcm/aesni_gcm_pmd.c | 2 ++
drivers/crypto/aesni_mb/rte_aesni_mb_pmd.c | 2 ++
drivers/
Crypto devices of the same type could be initialized
with the same name, since internally this name was suffixed
with an index.
Since commit ("vdev: make virtual bus use its
device struct"), this is not allowed anymore.
Therefore, there is no need to create an unique name
at device initializatio
First of all, I agree usage of IXGBE_FLAG_NEED_LINK_CONFIG to trigger link
setup when link is up again.
Both ixgbe_get_link_capabilities( ) and ixgbe_setup_link( ) calls different
sub-function for different ixgbe MAC type including 82598, 82599, X540 and X550
and so on.
I think ixgbe_setup_lin
Probably ought to also add a new command so that promiscuous mode can be
enabled if needed.
On 12/04/2017 20:58, Qi Zhang wrote:
Disable promiscuous mode by default since VLAN filter
does not work when promiscuous mode is enabled.
Signed-off-by: Qi Zhang
---
examples/ethtool/ethtool-app/main
When we pass --log-level=0, it disables the logs. This level is
not displayed properly by the function that dumps the registered log
types (it shows "unknown"). Show "disabled" instead.
Before:
./build/app/test --log-level=0
RTE>>dump_log_types
global log level is unknown
...
After:
.
It's better to initialize the internal config in rte_eal_init()
instead of eal_log_level_parse(), since this structure is not only
about logs.
Signed-off-by: Olivier Matz
---
lib/librte_eal/bsdapp/eal/eal.c | 3 ++-
lib/librte_eal/linuxapp/eal/eal.c | 3 ++-
2 files changed, 4 insertions(+), 2
Remove the printf displaying the log level at initialization. It
was introduced for debug purpose, but was not intended to be pushed.
Fixes: 845afe51e428 ("eal: change specific log levels at startup")
Reported-by: Ferruh Yigit
Signed-off-by: Olivier Matz
---
lib/librte_eal/common/eal_common_op
The initialization of the default log level (from configuration) was
removed by mistake in a previous commit. The global log level was
wrongly set to debug when no --log-level argument was passed. Restore
this initialization.
Before:
$ ./build/app/test
RTE>>dump_log_types
global log level is
This field is only used in the initialization phase. Remove it since the
global log level can also be retrieved using a public API:
rte_log_get_global_level().
Signed-off-by: Olivier Matz
---
lib/librte_eal/bsdapp/eal/eal.c| 2 --
lib/librte_eal/common/eal_common_log.c | 6
Fix misuse of regular expression functions, which was producing a
segfault.
After the patch, it works properly:
$ ./build/app/test --no-huge --log-level=pmd,3
RTE>>dump_log_types
[...]
id 30: user7, level is debug
id 31: user8, level is debug
id 32: pmd.i40e.init, level is critical
alloc_q and rx_q fifos holds physical address of the mbufs, and not able
to free those mbufs explicitly.
But kernel thread reads from rx_q and puts used mbufs into free_q (with
their virtual addresses.) And kernel thread stopped when application
close the /dev/kni file on exit. So rx_q has time to
Stop port before enabling QinQ.
Add commands to set inner and outer TPID's and start port.
Remove TPID's from flow validate and and flow create commands.
Signed-off-by: Bernard Iremonger
---
doc/guides/testpmd_app_ug/testpmd_funcs.rst | 33 ++---
1 file changed, 21 insert
eth_dev->device is now NULL, and accessing eth_dev->device->driver
crashes.
No need to set this value, removed completely.
Fixes: 5d2aa461cbca ("vdev: use generic vdev struct for probe and remove")
Signed-off-by: Ferruh Yigit
---
drivers/net/kni/rte_eth_kni.c | 1 -
1 file changed, 1 deletion(-
Hi Santosh,
On Tue, 18 Apr 2017 14:04:46 +0530, Santosh Shukla
wrote:
> Cc: sta...@dpdk.org
> Signed-off-by: Santosh Shukla
> ---
> v3:
> - Cleanup code change as per discussion in
>http://dpdk.org/dev/patchwork/patch/23262/
>
> test/test/test_mempool_perf.c | 61
>
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Beilei Xing
> Sent: Tuesday, April 18, 2017 9:46 AM
> To: Wu, Jingjing
> Cc: dev@dpdk.org
> Subject: [dpdk-dev] [PATCH] net/i40e: add check for invalid VF queue
> number
>
> Add check to avoid invalid VF queue num
Some Ethdev Hardware is capable of injecting the events(Ethernet packets)
to eventdev without the need for dedicated service cores on Rx path.
Since eventdev API is device capability agnostic, we need to address
three combinations of ethdev and eventdev PMD drivers.
1) Ethdev HW is not capable of
> -Original Message-
> From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Pablo de Lara
> Sent: Tuesday, April 18, 2017 12:40 PM
> To: dev@dpdk.org
> Cc: zbigniew.bo...@caviumnetworks.com;
> jerin.ja...@caviumnetworks.com; Doherty, Declan
> ; De Lara Guarch, Pablo
>
> Subject: [dpdk-dev]
Hi Ferruh,
On Fri, 14 Apr 2017 14:10:33 +0100, Ferruh Yigit wrote:
> On 4/5/2017 10:37 AM, Thomas Monjalon wrote:
> > 2017-04-04 18:27, Olivier Matz:
> >> Based on discussions done in [1] and in this thread, this patchset
> >> reorganizes
> >> the mbuf.
> >>
> >> The main changes are:
> >> - r
Fixes: 4ec1fc3ba881 ("net/sfc: add basic stubs for RSS support on driver
attach")
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
---
drivers/net/sfc/sfc_rx.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/net/sfc/sfc_rx.c b/drivers/net/sfc/sfc_rx.c
index ddf9217..9f51
RSS hash is computed by hardware if corresponding Rx filter (for
example, default Rx filters) has RSS flag set which is set if
the number of RSS channels is greater than zero.
Fixes: 4ec1fc3ba881 ("net/sfc: add basic stubs for RSS support on driver
attach")
Signed-off-by: Andrew Rybchenko
Revie
Enabled RSS enables RSS hash computation and provision in pseudo header.
It still makes sense for applications even if only one Rx queue is used.
Fixes: 4ec1fc3ba881 ("net/sfc: add basic stubs for RSS support on driver
attach")
Fixes: 088e17210a7a ("net/sfc: query RSS key and hash types config")
Hi Yuanhan,
On Thu, 6 Apr 2017 13:45:23 +0800, Yuanhan Liu
wrote:
> Hi Olivier,
>
> On Tue, Apr 04, 2017 at 06:28:05PM +0200, Olivier Matz wrote:
> > Change the size of m->port and m->nb_segs to 16 bits.
>
> But all the ethdev APIs are still using 8 bits. 16 bits won't really
> take effect w
Coverity issue: 1419717
Fixes: a9825ccf5bb8 ("net/sfc: support flow API filters")
Signed-off-by: Andrew Rybchenko
Reviewed-by: Andy Moreton
---
drivers/net/sfc/sfc_flow.c | 10 +-
1 file changed, 1 insertion(+), 9 deletions(-)
diff --git a/drivers/net/sfc/sfc_flow.c b/drivers/net/sfc/s
Hi Olivier,
> -Original Message-
> From: Olivier MATZ [mailto:olivier.m...@6wind.com]
> Sent: Tuesday, April 18, 2017 5:34 PM
> To: Shreyansh Jain
> Cc: dev@dpdk.org; tho...@monjalon.net; bruce.richard...@intel.com;
> john.mil...@atomicrules.com
> Subject: Re: [PATCH] mk: link ring mempoo
This is a rather simple handler that prints a message with the name of
the current event. It can be used to check PMD callback registration and
triggers.
Signed-off-by: Gaetan Rivet
---
app/test-pmd/testpmd.c | 47 +++
1 file changed, 47 insertions(+)
For drivers supporting the LSC event, enable it.
This allows to test LSC event support.
Add the --no-lsc-interrupt parameter to explicitly disable the link status
change interrupt.
Signed-off-by: Gaetan Rivet
---
app/test-pmd/parameters.c | 4
app/test-pmd/testpmd.c| 13 +
Enable device removal event for PMD supporting it.
Add the --no-rmv-interrupt parameter to explicitly disable it.
Signed-off-by: Gaetan Rivet
Signed-off-by: Elad Persiko
---
app/test-pmd/parameters.c | 4
app/test-pmd/testpmd.c| 43 +++
app/test
Extend the LSC event handling to support the device removal as well. The
Verbs library will send several related events, that can conflict
with the LSC event itself.
The event handling has thus been made capable of receiving and signaling
several event types at once.
Signed-off-by: Gaetan Rivet
This new event represents the sudden removal of a device from its bus.
The underlying resources exposed by the bus are expected not to be available
anymore. The application should thus be able to react and possibly clean up
related resources that it reserved for the removed device.
This event is d
This new API allows reacting to a device removal.
A device removal is the sudden disappearance of a device from its
bus.
PMDs implementing support for this notification guarantee that the removal
of the underlying device does not incur a risk to the application.
In particular, Rx/Tx bursts and al
On Thu, 13 Apr 2017 14:32:07 +0530, Shreyansh Jain
wrote:
> Signed-off-by: Shreyansh Jain
Fixes: 9a8e9b57f544 ("mempool: move ring handler as a driver")
Acked-by: Olivier Matz
> ---
> Context:
> From the discussion in [1], it was observed that application should
> have a default pool alrea
Hi Jianfeng,
On Tue, 18 Apr 2017 19:15:51 +0800, "Tan, Jianfeng"
wrote:
> On 4/18/2017 4:50 PM, Olivier MATZ wrote:
> > Hi Jianfeng,
> >
> > On Fri, 14 Apr 2017 13:33:49 +0800, "Tan, Jianfeng"
> > wrote:
> >> Hi Olivier,
> >>
> >> If I understand it correctly, this patch is to shift log leve
> -Original Message-
> From: De Lara Guarch, Pablo
> Sent: Tuesday, April 18, 2017 12:40 PM
> To: dev@dpdk.org
> Cc: zbigniew.bo...@caviumnetworks.com;
> jerin.ja...@caviumnetworks.com; Doherty, Declan; De Lara Guarch, Pablo
> Subject: [PATCH 1/2] test/crypto: create only one virtual devi
Since commit ("vdev: make virtual bus use
its device struct"), rte_eal_vdev_init cannot be called
with same name twice.
If several devices with the same driver are needed
(as in the crypto scheduler test), then driver name argument
has to be unique, concatenating the driver name and an index.
Si
Instead of creating two virtual devices per PMD, if they have not
been initialized from EAL already, create only one, as only the
first device is used for the crypto tests.
Signed-off-by: Pablo de Lara
---
test/test/test_cryptodev.c | 144 ++--
test/test/
Previously, l2fwd-crypto application did not give user the
flexibility to decide which crypto device(s) will be used.
In this patch, a new cryptodev_mask option is added to the
application. Same as portmask, the cryptodev_mask avails the
user to mask out the unwanted crypto devices in the system.
This patch adds the missing doxygen comments and updated
inline comments to cryptodev scheduler
Fixes: d58a3f312545 ("crypto/scheduler: add documentation")
Signed-off-by: Fan Zhang
Acked-by: John McNamara
---
v3:
- updated based on the comments
v2:
- fixed typo
doc/api/doxy-api-index.md
This patch improves the cryptodev scheduler PMD's commandline
parsing capability. Originally, the scheduler's slave option
requires the slave vdev(s) being declared prior to it. This
patch removes this limitation by storing the slave names
temporarily and attaching them later.
Signed-off-by: Fan Z
On Thu, Apr 6, 2017 at 11:10 AM, Burakov, Anatoly wrote:
> Hi Alejandro,
>
> > Yes, the code was not aware of that possibility. Being honest, I knew
> about that, but not in my mind when implementing the code. I have just
> cards where each PF even VF have their own VFIO group. This could be a
>
On 4/18/2017 4:50 PM, Olivier MATZ wrote:
Hi Jianfeng,
On Fri, 14 Apr 2017 13:33:49 +0800, "Tan, Jianfeng"
wrote:
Hi Olivier,
If I understand it correctly, this patch is to shift log level setting
earlier. But we did not remove the one in eal_parse_common_option(). So
we can see this param
This patch improves the cryptodev scheduler PMD's commandline
parsing capability. Originally, the scheduler's slave option
requires the slave vdev(s) being declared prior to it. This
patch removes this limitation by storing the slave names
temporarily and attaching them later.
This patch depends o
With the Enhanced multi packet send addition, the defaults were made
in order to get the maximum out of the box performance.
Features like tso, don't use the enhanced send, however the defaults
are still valid. This cause Tx queue creation to fail.
Fixes: aea00c008140 ("net/mlx5: add hardware TSO
Currently the argument process is done without indication which
parameter was forced by the application and which one is on it
default value.
This becomes problematic when different features requires different
defaults. For example, Enhanced multi packet send and TSO.
This commit modifies the argu
1 - 100 of 130 matches
Mail list logo
