This patch-set add the support for floating VEB in i40e.
All the VFs VSIs can decide whether to connect to the legacy VEB/VEPA or
the floating VEB. When connect to the floating VEB a new floating VEB is
created. Now all the VFs need to connect to floating VEB or legacy VEB,
cannot connect to both o
Add the new floating related argument option in the devarg.
Using this parameter, all the samples can decide whether to use legacy VEB/VEPA
or floating VEB.
To enable this feature, the user should pass a devargs parameter to the EAL
like "-w 84:00.0,enable_floating=1", and the application will make
This patch add the support for floating VEB in i40e.
All the VFs VSIs can decide whether to connect to the legacy VEB/VEPA or
the floating VEB. When connect to the floating VEB a new floating VEB is
created. Now all the VFs need to connect to floating VEB or legacy VEB,
cannot connect to both of th
To enable this feature, the user should pass a devargs parameter to the EAL
like "-w 84:00.0,enable_floating=1", and the application will make sure the PMD
will use the floating VEB feature for all the VFs created by this PF device.
Also you can specifiy which VF need to connect to this floating v
Hi,
> -Original Message-
> From: Hiroyuki Mikita [mailto:h.mikita89 at gmail.com]
> Sent: Tuesday, May 24, 2016 10:48 PM
> To: Lu, Wenzhuo
> Cc: dev at dpdk.org
> Subject: [PATCH] e1000: fix build with clang
>
> GCC_VERSION is empty in case of clang:
> /bin/sh: line 0: test: -ge: u
On Tue, May 24, 2016 at 10:42:56AM +0100, Bruce Richardson wrote:
> On Tue, May 24, 2016 at 01:11:26PM +0800, Yuanhan Liu wrote:
> > On Mon, May 23, 2016 at 06:06:21PM +0100, Ferruh Yigit wrote:
> > > On 5/23/2016 2:24 PM, Yuanhan Liu wrote:
> > > > On Fri, May 20, 2016 at 11:37:47AM +0100, Bruce R
Hi,
ping ...
Later on I want to look at it again once we upgraded to more recent
releases of the software components involved, but those have to be made
ready to use first :-/
But the description is good and I wonder if anybody else could reproduce
this and/or would have a hint on where this migh
Hi again,
another forgotten case.
I currently I lack the HW to fully reproduce this, but the video summary is
pretty good and shows the issue in an impressive way.
Also the description is good and here as well I wonder if anybody else
could reproduce this.
Any hints / insights are welcome.
P.S.
From: Zyta Szpak
Version 2 of fixing the fixed register width assumption.
rte_eth_dev_get_reg_length and rte_eth_dev_get_reg callbacks
do not provide register size to the app in any way. It is
needed to allocate proper number of bytes before retrieving
registers content with rte_eth_dev_get_reg.
From: Zyta Szpak
Version 2 of fixing the fixed register width assumption.
Not every device uses 32-bit wide register. The app was allocating too
little space for 64-bit registers which resulted in memory corruption.
This commit resolves this by getting the size of register in bytes for
a specific
There is no external function call or any barrier in the loop,
the used->idx would only be retrieved once.
Signed-off-by: Huawei Xie
---
drivers/net/virtio/virtio_ethdev.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/net/virtio/virtio_ethdev.c
b/drivers/net/virt
On 5/25/2016 4:12 PM, Xie, Huawei wrote:
> There is no external function call or any barrier in the loop,
> the used->idx would only be retrieved once.
>
> Signed-off-by: Huawei Xie
> ---
> drivers/net/virtio/virtio_ethdev.c | 3 ++-
> 1 file changed, 2 insertions(+), 1 deletion(-)
>
> diff --git
On 05/24/2016 10:41 PM, Neil Horman wrote:
> Hey all-
> So heres attempt number 2 at a method for exporting PMD hardware support
> information. As we discussed previously, the consensus seems to be that pmd
> information should be:
>
> 1) Able to be interrogated on any ELF binary (applicatio
On Wed, May 25, 2016 at 08:25:20AM +, Xie, Huawei wrote:
> On 5/25/2016 4:12 PM, Xie, Huawei wrote:
> > There is no external function call or any barrier in the loop,
> > the used->idx would only be retrieved once.
> >
> > Signed-off-by: Huawei Xie
> > ---
> > drivers/net/virtio/virtio_ethdev
2016-05-04 10:15, David Marchand:
> On Tue, May 3, 2016 at 9:15 PM, Jan Viktorin
> wrote:
> > A bug has been detected by valgrind:
[...]
> > strlen(t->command) + strlen("#") + ONE_FOR_ZERO
> >
> > Fixes: 727909c59231 ("app/test: introduce dynamic commands list")
> >
> > Signed-off-by: Jan Viktor
2016-03-07 15:00, Ravi Kerur:
> v1:
> This patch adds memcmp functionality using AVX and SSE
> intrinsics provided by Intel. For other architectures
> supported by DPDK regular memcmp function is used.
Anyone to review this patch please? Zhihong?
This patch enables AES counter mode algorithm support to l2fwd-crypto
sample application.
This patch depends on the following patches:
"qat: add AES counter mode capability"
(http://dpdk.org/dev/patchwork/patch/12464/)
"app/test: add test cases for AES CTR"
(http://dpdk.org/dev/patchwork/patch/12
Fixes ba7b86b1 ("doc: add l2fwd-crypto sample app guide")
Corrected a typo in application name.
Corrected authentication algorithm to fit the sample 16-byte
authentication key.
Signed-off-by: Fan Zhang
---
doc/guides/sample_app_ug/l2_forward_crypto.rst | 4 ++--
1 file changed, 2 insertions(+)
This patch enables AES-XCBC-MAC authentication algorithm support to
l2fwd-crypto sample application.
Signed-off-by: Fan Zhang
---
examples/l2fwd-crypto/main.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/examples/l2fwd-crypto/main.c b/examples/l2fwd-crypto/main.c
index d4e2d8d..dccba79
CC Pablo, testpmd maintainer
Pablo,
This patchset looks really valuable to improve performance debugging.
Would you have time to dig into a review please?
2016-05-05 18:46, Zhihong Wang:
> This patch enables vhost/virtio pmd performance loopback test in testpmd.
> All the features are for genera
2016-05-05 18:46, Zhihong Wang:
> --- a/app/test-pmd/testpmd.h
> +++ b/app/test-pmd/testpmd.h
> extern struct fwd_engine io_fwd_engine;
> +extern struct fwd_engine io_retry_fwd_engine;
> extern struct fwd_engine mac_fwd_engine;
> extern struct fwd_engine mac_retry_fwd_engine;
> extern struct fw
2016-05-05 18:46, Zhihong Wang:
> This patch enables configurable tx_first burst number.
>
> Use "start tx_first (burst_num)" to specify how many bursts of packets to
> be sent before forwarding start, or "start tx_first" like before for the
> default 1 burst send.
The idea here is to fill the lo
In cross-compiling mode CC can be aarch64-*-linux-gnu-gcc
instead of just gcc
Signed-off-by: Jerin Jacob
---
drivers/net/qede/Makefile | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/qede/Makefile b/drivers/net/qede/Makefile
index c9b3b1c..10ced84 100644
--- a/dri
2016-05-05 18:46, Zhihong Wang:
> This patch removes constraints in rxq handling when multiqueue is enabled
> to handle all the rxqs.
>
> Current testpmd forces a dedicated core for each rxq, some rxqs may be
> ignored when core number is less than rxq number, and that causes confusion
> and incon
2016-05-05 18:47, Zhihong Wang:
> This patch show topology at forwarding start.
>
> "show config fwd" also does this, but showing it directly can reduce the
> possibility of misconfiguration.
[...]
> - fwd_config_setup();
> + fwd_config_display();
> rxtx_config_display();
Having _di
On Wed, May 25, 2016 at 11:34:24AM +0300, Michael S. Tsirkin wrote:
> On Wed, May 25, 2016 at 08:25:20AM +, Xie, Huawei wrote:
> > On 5/25/2016 4:12 PM, Xie, Huawei wrote:
> > > There is no external function call or any barrier in the loop,
> > > the used->idx would only be retrieved once.
> >
2016-05-05 18:47, Zhihong Wang:
> This patch updates documentation for testpmd.
Please avoid such doc update patch.
It is preferred to have the doc changes in the patch changing the code.
Thanks for the good work!
On Wed, May 25, 2016 at 10:47:30AM +0100, Bruce Richardson wrote:
> On Wed, May 25, 2016 at 11:34:24AM +0300, Michael S. Tsirkin wrote:
> > On Wed, May 25, 2016 at 08:25:20AM +, Xie, Huawei wrote:
> > > On 5/25/2016 4:12 PM, Xie, Huawei wrote:
> > > > There is no external function call or any b
On Wed, May 25, 2016 at 12:50:02PM +0300, Michael S. Tsirkin wrote:
> On Wed, May 25, 2016 at 10:47:30AM +0100, Bruce Richardson wrote:
> > On Wed, May 25, 2016 at 11:34:24AM +0300, Michael S. Tsirkin wrote:
> > > On Wed, May 25, 2016 at 08:25:20AM +, Xie, Huawei wrote:
> > > > On 5/25/2016 4:1
2016-05-24 12:22, Stephen Hemminger:
> kvargs are a very awkward API to use in a portable application.
> Good for Intel testing NIC's bad for DPDK users.
Yes. The alternative would be to have some driver-specific API.
We can live with devargs until driver API is introduced.
2016-05-24 21:38, Huawei Xie:
> We keep a common vq structure, containing only vq related fields,
> and then split others into RX, TX and control queue respectively.
>
> Signed-off-by: Huawei Xie
Is it a v2? There is neither changelog nor v2 in the title.
2016-05-24 09:25, Daniel Mrzyglod:
> Fixes: 71d35259ff67 ("i40e: tear down flow director")
> Coverity ID 13198
FYI, in recent commits I've started to standardize the coverity reports
like that:
Coverity issue: X
Fixes: ...
Please spread the word.
> - dev->devargs->type != RTE_DEVTYPE_WHITELISTED_PCI) {
> + (!dev->devargs ||
> + dev->devargs->type != RTE_DEVTYPE_WHITELISTED_PCI)) {
Should the title be something like "fix crash ..."?
I would also add
Reported-by: Vincent Li
Hi Thomas,
I had a quick look through these tests and it will need some effort to rework
them to run in shorter time.
I agree to remove this suite from the fast_test as long as it gets exercised in
other test paths.
Regards,
Tomasz
> -Original Message-
> From: Dumitrescu, Cristian
> Se
Hi,
I think, your issue connected to one mentioned in this threads:
http://openvswitch.org/pipermail/dev/2016-May/071115.html
http://openvswitch.org/pipermail/dev/2016-May/071517.html
You're welcome to join discussion in the first thread.
Best regards, Ilya Maximets.
On Wed, May 25, 2016 at 11:32:06AM +0300, Panu Matilainen wrote:
> On 05/24/2016 10:41 PM, Neil Horman wrote:
> > Hey all-
> > So heres attempt number 2 at a method for exporting PMD hardware support
> > information. As we discussed previously, the consensus seems to be that pmd
> > informatio
2016-05-25 11:06, Kantecki, Tomasz:
> I had a quick look through these tests and it will need some effort to rework
> them to run in shorter time.
> I agree to remove this suite from the fast_test as long as it gets exercised
> in other test paths.
Is it possible to split them in
- short
2016-05-25 12:41, Yuanhan Liu:
> On Tue, May 24, 2016 at 10:42:56AM +0100, Bruce Richardson wrote:
> > On Tue, May 24, 2016 at 01:11:26PM +0800, Yuanhan Liu wrote:
> > > On Mon, May 23, 2016 at 06:06:21PM +0100, Ferruh Yigit wrote:
> > > > On 5/23/2016 2:24 PM, Yuanhan Liu wrote:
> > > > > On Fri,
2016-05-24 23:48, Hiroyuki Mikita:
> GCC_VERSION is empty in case of clang:
> /bin/sh: line 0: test: -ge: unary operator expected
>
> It is the same issue as http://dpdk.org/dev/patchwork/patch/5994/
I did this patch but it looks broken for cross-compiler.
Please fix it. Thanks
On Fri, May 06, 2016 at 11:55:46AM +0530, Jianbo Liu wrote:
> use ARM NEON intrinsic to implement ixgbe vPMD
>
> Signed-off-by: Jianbo Liu
> ---
> drivers/net/ixgbe/Makefile | 4 +
> drivers/net/ixgbe/ixgbe_rxtx_vec_neon.c | 561
>
> 2 files chang
On Wed, May 25, 2016 at 05:59:38PM +0530, Jerin Jacob wrote:
> On Fri, May 06, 2016 at 11:55:46AM +0530, Jianbo Liu wrote:
> > use ARM NEON intrinsic to implement ixgbe vPMD
> >
> > Signed-off-by: Jianbo Liu
> > ---
> > drivers/net/ixgbe/Makefile | 4 +
> > drivers/net/ixgbe/ixgbe
'noon,
Was expecting rte_eth_dev_get_reg_width() itself to default to
sizeof(uint32_t) rather than -ENOTSUP, but that is purely personal taste
which others might disagree with. You'll also need a documentation
update & Fixes: line.
On 25/05/2016 07:36, zr at semihalf.com wrote:
> From: Zyta S
On 25/05/2016 07:36, zr at semihalf.com wrote:
> From: Zyta Szpak
[..]
> Signed-off-by: Zyta Szpak
> ---
> examples/ethtool/lib/rte_ethtool.c | 6 +-
> 1 file changed, 5 insertions(+), 1 deletion(-)
Acked-by: Remy Horton
2016-05-24 15:41, Neil Horman:
> pmdinfogen is a tool used to parse object files and build json strings for
> use in
> later determining hardware support in a dso or application binary. pmdinfo
> looks for the non-exported symbol names this_pmd_name and this_pmd_tbl
> (where n is a integer counte
This patch improve generate_random_key() function by replacing rand()
function with reading from /dev/urandom.
CID 120136 : Calling risky function (DC.WEAK_CRYPTO)
dont_call: rand should not be used for security related applications, as
linear congruential algorithms are too easy to break
Coverit
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Christian
> Ehrhardt
> Sent: Wednesday, May 25, 2016 7:06 AM
> To: Martinx - ?
> Cc: ; dev
> Subject: Re: [dpdk-dev] Crashing OVS+DPDK at the host, from inside of
> a KVM Guest
>
> Hi,
> ping ...
>
> La
On Fri, May 13, 2016 at 03:45:50PM -0700, Stephen Hurd wrote:
> Initial skeleton simply fails init.
> Add nic guide and tie into build system.
>
> Signed-off-by: Stephen Hurd
> ---
> MAINTAINERS | 5 ++
> config/common_base | 5
On 5/25/2016 6:08 PM, Thomas Monjalon wrote:
> Is it a v2? There is neither changelog nor v2 in the title.
Yes, forget to add v2. Mainly rebase against Yuanhan's tree. Besides, to
make the patch simple and focused, use the old queue setup.
On Fri, May 13, 2016 at 03:45:51PM -0700, Stephen Hurd wrote:
> Start adding HWRM support.
> Initial commit just performs necessary HWRM queries for init, then
> fails as before.
>
> Thee used HWRM calls so far:
> bnxt_hwrm_func_qcaps:
> Queries device capabilities.
>
> bnxt_hwrm_ver_get:
>
On Fri, May 13, 2016 at 03:45:52PM -0700, Stephen Hurd wrote:
> Move init() cleanup into uninit() function
> Fix .dev_private_size
> Add require hwrm calls:
> bnxt_hwrm_func_driver_register()
> bnxt_hwrm_func_driver_unregister()
>
> Signed-off-by: Stephen Hurd
> Reviewed-by: Ajit Kuma
On 5/25/2016 6:01 PM, Richardson, Bruce wrote:
> On Wed, May 25, 2016 at 12:50:02PM +0300, Michael S. Tsirkin wrote:
>> On Wed, May 25, 2016 at 10:47:30AM +0100, Bruce Richardson wrote:
>>> On Wed, May 25, 2016 at 11:34:24AM +0300, Michael S. Tsirkin wrote:
On Wed, May 25, 2016 at 08:25:20AM +
On Fri, May 13, 2016 at 03:45:54PM -0700, Stephen Hurd wrote:
> This adds the bnxt_hwrm_port_phy_cfg() HWRM call, and copies required
> information into the new struct bnxt_link_info.
>
> Signed-off-by: Stephen Hurd
> Reviewed-by: Ajit Kumar Khaparde
> ---
> drivers/net/bnxt/bnxt.h
On 5/25/2016 2:06 PM, Christian Ehrhardt wrote:
> Hi,
> ping ...
>
> Later on I want to look at it again once we upgraded to more recent
> releases of the software components involved, but those have to be made
> ready to use first :-/
>
> But the description is good and I wonder if anybody else co
2016-05-26 00:25, Hiroyuki Mikita:
> GCC_VERSION is empty in case of clang:
> /bin/sh: line 0: test: -ge: unary operator expected
>
> It is the same issue as http://dpdk.org/dev/patchwork/patch/5994/
>
> Fixes: 366113dbfb69 ("e1000: suppress misleading indentation warning")
>
> Signed-off-
On Fri, May 13, 2016 at 03:45:55PM -0700, Stephen Hurd wrote:
> Add functions to allocate, initialize, and free vnics.
>
> Signed-off-by: Stephen Hurd
> Reviewed-by: Ajit Kumar Khaparde
> ---
Can you perhaps explain what is meant by vnics in this context. Does this patch
need a doc update to de
2016-05-24 15:41, Neil Horman:
> Modify the PMD_REGISTER_DRIVER macro, adding a name argument to it. The
> addition of a name argument creates a token that can be used for subsequent
> macros in the creation of unique symbol names to export additional bits of
> information for use by the pmdinfoge
On Fri, May 13, 2016 at 03:45:56PM -0700, Stephen Hurd wrote:
> Declare ring structures and a ring free() function.
>
Are these rings used for packet RX and TX or something else?
> Signed-off-by: Stephen Hurd
> Reviewed-by: Ajit Kumar Khaparde
> ---
> drivers/net/bnxt/Makefile| 1 +
> dr
On 5/25/2016 10:41 AM, Jerin Jacob wrote:
> In cross-compiling mode CC can be aarch64-*-linux-gnu-gcc
> instead of just gcc
>
> Signed-off-by: Jerin Jacob
> ---
> drivers/net/qede/Makefile | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/drivers/net/qede/Makefile b/drive
2016-05-24 15:41, Neil Horman:
> --- a/mk/internal/rte.compile-pre.mk
> +++ b/mk/internal/rte.compile-pre.mk
> @@ -80,7 +80,8 @@ C_TO_O_STR = $(subst ','\'',$(C_TO_O)) #'# fix syntax
> highlight
> C_TO_O_DISP = $(if $(V),"$(C_TO_O_STR)"," HOSTCC $(@)")
> else
> C_TO_O = $(CC) -Wp,-MD,$(call ob
2016-05-24 15:41, Neil Horman:
> Note that, in the case of dynamically linked applications, pmdinfo.py will
> scan
> for implicitly linked PMDs by searching the specified binaries .dynamic
> section
> for DT_NEEDED entries that contain the substring librte_pmd.
I don't know any DPDK app dynamica
On Wed, May 25, 2016 at 03:21:19PM +0200, Thomas Monjalon wrote:
> 2016-05-24 15:41, Neil Horman:
> > pmdinfogen is a tool used to parse object files and build json strings for
> > use in
> > later determining hardware support in a dso or application binary. pmdinfo
> > looks for the non-exported
2016-05-25 18:01, Ferruh Yigit:
> On 5/25/2016 10:41 AM, Jerin Jacob wrote:
> > In cross-compiling mode CC can be aarch64-*-linux-gnu-gcc
> > instead of just gcc
> >
> > Signed-off-by: Jerin Jacob
> > ---
> > -ifneq (,$(filter gcc gcc48,$(CC)))
> > +ifneq (,$(filter %gcc %gcc48,$(CC)))
>
> What
On Fri, May 13, 2016 at 03:45:57PM -0700, Stephen Hurd wrote:
> Structures, macros, and functions for working with completion rings
> in the driver.
>
Can you add a bit more info in the commit message - and possibly in the docs
too - about what completion rings are and how they are used. Even a f
On Wed, May 25, 2016 at 06:20:06PM +0200, Thomas Monjalon wrote:
> 2016-05-24 15:41, Neil Horman:
> > Modify the PMD_REGISTER_DRIVER macro, adding a name argument to it. The
> > addition of a name argument creates a token that can be used for subsequent
> > macros in the creation of unique symbol
2016-05-25 13:22, Neil Horman:
> On Wed, May 25, 2016 at 03:21:19PM +0200, Thomas Monjalon wrote:
> > 2016-05-24 15:41, Neil Horman:
> > > --- a/GNUmakefile
> > > +++ b/GNUmakefile
> > > -ROOTDIRS-y := lib drivers app
> > > +ROOTDIRS-y := buildtools lib drivers app
> >
> > Why a new directory?
> >
On Wed, May 25, 2016 at 07:08:19PM +0200, Thomas Monjalon wrote:
> 2016-05-24 15:41, Neil Horman:
> > --- a/mk/internal/rte.compile-pre.mk
> > +++ b/mk/internal/rte.compile-pre.mk
> > @@ -80,7 +80,8 @@ C_TO_O_STR = $(subst ','\'',$(C_TO_O)) #'# fix syntax
> > highlight
> > C_TO_O_DISP = $(if $(V)
>
> @@ -817,6 +821,9 @@ rte_pmd_vhost_devinit(const char *name, const char
> *params)
> int ret = 0;
> char *iface_name;
> uint16_t queues;
> + uint64_t flags = 0;
> + int client_mode;
> + int reconnect;
>
client_mode and reconnect are not initialized if t
On Wed, May 25, 2016 at 07:22:39PM +0200, Thomas Monjalon wrote:
> 2016-05-24 15:41, Neil Horman:
> > Note that, in the case of dynamically linked applications, pmdinfo.py will
> > scan
> > for implicitly linked PMDs by searching the specified binaries .dynamic
> > section
> > for DT_NEEDED entri
On Fri, May 13, 2016 at 03:45:58PM -0700, Stephen Hurd wrote:
> Add the L2 filter structure and the alloc/init/free functions for
> dealing with them.
>
The DPDK ethdev API has filtering APIs, but this code is not made accessible
via those APIs. If that link is added via later patches, then that
Hi,
While running the QAT PMD tests, a system hang is observed when this commit is
used.
rte_mempool_virt2phy is used in qat_crypto.c.
regards,
Deepak
-Original Message-
From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Olivier Matz
Sent: Wednesday, May 18, 2016 12:05 PM
To: dev at
2016-05-25 13:40, Neil Horman:
> On Wed, May 25, 2016 at 07:08:19PM +0200, Thomas Monjalon wrote:
> > 2016-05-24 15:41, Neil Horman:
> > > + echo MODGEN $@; \
> > > + OBJF=`readlink -f $@`; \
> > > + ${RTE_OUTPUT}/buildtools/pmdinfogen \$$OBJF \$$OBJF.mod.c; \
> >
> > Maybe
2016-05-25 13:47, Neil Horman:
> On Wed, May 25, 2016 at 07:22:39PM +0200, Thomas Monjalon wrote:
> > 2016-05-24 15:41, Neil Horman:
> > > Note that, in the case of dynamically linked applications, pmdinfo.py
> > > will scan
> > > for implicitly linked PMDs by searching the specified binaries .dyn
On Wed, May 25, 2016 at 07:39:30PM +0200, Thomas Monjalon wrote:
> 2016-05-25 13:22, Neil Horman:
> > On Wed, May 25, 2016 at 03:21:19PM +0200, Thomas Monjalon wrote:
> > > 2016-05-24 15:41, Neil Horman:
> > > > --- a/GNUmakefile
> > > > +++ b/GNUmakefile
> > > > -ROOTDIRS-y := lib drivers app
> >
> I suppose this has to do with what is expected usage of the PKT_RX_VLAN_PKT
> offload flag. Is it set only for VLAN packets with the
> VLAN stripped or should always be set if VLAN is/was present in the received
> packet. It seems that different DPDK drivers are
> behaving differently which wi
2016-05-25 15:13, Neil Horman:
> On Wed, May 25, 2016 at 07:39:30PM +0200, Thomas Monjalon wrote:
> > 2016-05-25 13:22, Neil Horman:
> > > On Wed, May 25, 2016 at 03:21:19PM +0200, Thomas Monjalon wrote:
> > > > 2016-05-24 15:41, Neil Horman:
> > > > > +include $(RTE_SDK)/mk/rte.buildtools.mk
> > >
Hi Deepak,
On 05/25/2016 07:51 PM, Jain, Deepak K wrote:
> Hi,
>
> While running the QAT PMD tests, a system hang is observed when this commit
> is used.
>
> rte_mempool_virt2phy is used in qat_crypto.c.
>From what I see in the code, the second argument of the function
rte_mempool_virt2phy(mp,
On Wed, May 25, 2016 at 08:56:25PM +0200, Thomas Monjalon wrote:
> 2016-05-25 13:40, Neil Horman:
> > On Wed, May 25, 2016 at 07:08:19PM +0200, Thomas Monjalon wrote:
> > > 2016-05-24 15:41, Neil Horman:
> > > > + echo MODGEN $@; \
> > > > + OBJF=`readlink -f $@`; \
> >
I could reproduce the issue and this can be fixed as below
Firstly, the throughput issues observed with other VMs when a new VM is started
can be fixed using the patch in the thread
http://openvswitch.org/pipermail/dev/2016-May/071615.html. I have put up an
explanation in this thread for the c
On Wed, May 25, 2016 at 09:39:43PM +0200, Thomas Monjalon wrote:
> 2016-05-25 15:13, Neil Horman:
> > On Wed, May 25, 2016 at 07:39:30PM +0200, Thomas Monjalon wrote:
> > > 2016-05-25 13:22, Neil Horman:
> > > > On Wed, May 25, 2016 at 03:21:19PM +0200, Thomas Monjalon wrote:
> > > > > 2016-05-24 1
2016-05-25 15:43, Neil Horman:
> On Wed, May 25, 2016 at 08:56:25PM +0200, Thomas Monjalon wrote:
> > 2016-05-25 13:40, Neil Horman:
> > > On Wed, May 25, 2016 at 07:08:19PM +0200, Thomas Monjalon wrote:
> > > > 2016-05-24 15:41, Neil Horman:
> > > > > + echo MODGEN $@; \
> > > > > +
Hi All,
My system configuration is
==>#. SuperMicro 1U
- BIOS: 1.0a
- Processor: Intel(R) Xeon(R) CPU D-1540 @ 2.00GHz
- Onboard NIC: Intel(R) X552/X557-AT (2x10G)
- Firmware-version: 0x81cf
- Device ID (PF/VF): 8086:15ad /8086:15a8
- kernel driver version: 4.2.5 (ixgbe)
On Wed, May 25, 2016 at 10:04:11PM +0200, Thomas Monjalon wrote:
> 2016-05-25 15:43, Neil Horman:
> > On Wed, May 25, 2016 at 08:56:25PM +0200, Thomas Monjalon wrote:
> > > 2016-05-25 13:40, Neil Horman:
> > > > On Wed, May 25, 2016 at 07:08:19PM +0200, Thomas Monjalon wrote:
> > > > > 2016-05-24 1
If device configuration failed due to a lack of resources, like if
there were more queues requested than available, the queue release
function is called with NULL pointers which were being dereferenced.
Skip releasing queues if they are NULL pointers. Also, if configuration
fails due to lack of re
Bruce, is it better at this point to modify the existing patch that adds
bnxt.rst or to create a follow-on patch?
On Wed, May 25, 2016 at 8:02 AM, Bruce Richardson <
bruce.richardson at intel.com> wrote:
> On Fri, May 13, 2016 at 03:45:50PM -0700, Stephen Hurd wrote:
> > Initial skeleton simply f
Signed-off-by: Rich Lane
---
drivers/net/af_packet/rte_eth_af_packet.c | 20 +++-
1 file changed, 19 insertions(+), 1 deletion(-)
diff --git a/drivers/net/af_packet/rte_eth_af_packet.c
b/drivers/net/af_packet/rte_eth_af_packet.c
index f17bd7e..2d7f344 100644
--- a/drivers/net/af
On Wed, May 25, 2016 at 8:05 AM, Bruce Richardson <
bruce.richardson at intel.com> wrote:
>
> Checkpatch also highlights a few minor issues that might be worth
> addressing.
>
> CHECK:SPACING: spaces preferred around that '<<' (ctx:VxV)
> #137: FILE: drivers/net/bnxt/bnxt.h:94:
> +#define BN
If device configuration failed due to a lack of resources, like if
there were more queues requested than available, the queue release
function is called with NULL pointers which were being dereferenced.
Skip releasing queues if they are NULL pointers. Also, if configuration
fails due to lack of re
Hi Wenzhuo,
Thanks for the reply.
?As par datasheet, if flow director filter matches then RSS won't impact as
RSS is the last filter to be applied on received packet.
But just to confirm, i tried and still issue persist. Any other thing that
you think i can try, please let me know.
Thanks.
On
88 matches
Mail list logo