> -Original Message-
> From: Thomas Monjalon [mailto:tho...@monjalon.net]
> Sent: Wednesday, November 8, 2017 2:05 AM
> To: Singh, Jasvinder
> Cc: dev@dpdk.org
> Subject: compilation error in softnic PMD
>
> Hi,
>
> There is an error when compiling on SUSE11SP2:
>
> drivers/net/softnic/
> +
> +#define UNUSED_PARAMETER(x) ((void)(x))
> +static __rte_always_inline void
> +update_tail(struct rte_ring_headtail *ht, uint32_t old_val, uint32_t new_val,
> + uint32_t single, uint32_t enqueue)
> +{
> + UNUSED_PARAMETER(enqueue);
As a nit you can use __rte_unused parameter
These changes were planned for 17.11 but were proposed too late.
Postpone those to v18.02 instead.
Signed-off-by: Gaetan Rivet
---
The related series:
[PATCH v2 00/18] devargs cleanup
http://dpdk.org/ml/archives/dev/2017-October/078761.html
doc/guides/rel_notes/deprecation.rst | 4 ++--
1 fil
move the common part of rte_ring.h into rte_ring_generic.h
move the memory barrier part into update_tail()
no functional changes here
Signed-off-by: Jia He
Suggested-by: Jerin Jacob
Suggested-by: Ananyev, Konstantin
---
lib/librte_eventdev/rte_event_ring.h | 6 +-
lib/librte_ring/Makefile
We watched a rte panic of mbuf_autotest in our qualcomm arm64 server due
to a possible race condition.
To fix this race, there are 2 options as suggested by Jerin:
1. use rte_smp_rmb
2. use load_acquire/store_release(refer to [2]).
CONFIG_RTE_RING_USE_C11_MEM_MODEL is provided, and by default it i
Fix the build error due to improper handling of unions on SUSE11(gcc 4.5.1).
Fixes: 299a89de916a ("net/softnic: add TM capabilities ops")
DPDK/drivers/net/softnic/rte_eth_softnic_tm.c:588:3
error: unknown field 'nonleaf' specified in initializer compilation
terminated due to -Wfatal-errors.
Sign
On Wed, Nov 08, 2017 at 06:17:10AM +, Jia He wrote:
> for the code as follows:
> if (condition)
> rte_smp_rmb();
> else
> rte_smp_wmb();
> Without this patch, compiler will report this error:
> error: 'else' without a previous 'if'
>
> Signed-off-by: Jia He
> Signed-off-by: jia...
We watched a rte panic of mbuf_autotest in our qualcomm arm64 server.
In __rte_ring_move_cons_head()
...
do {
/* Restore n as it may change every loop */
n = max;
*old_head = r->cons.head;//1st load
const uint3
To fix the cpu reorder race condition in enque/deque, there are 2 options
suggested by Jerin:
1. use rte_smp_rmb
2. use load_acquire/store_release(refer to [1]).
for the 2nd option, CONFIG_RTE_RING_USE_C11_MEM_MODEL is provided, and by
default it is "y" only on arm64.
The reason why providing 2 op
for the code as follows:
if (condition)
rte_smp_rmb();
else
rte_smp_wmb();
Without this patch, compiler will report this error:
error: 'else' without a previous 'if'
Fixes: 84733fd0d75e ("eal/arm64: fix memory barrier definition")
Signed-off-by: Jia He
---
lib/librte_eal/common/i
When running l3fwd-power to test virtio rxq interrupt using vfio
pci noiommu mode, startup fails. In the function virtio_read_caps,
the code if (flags & PCI_MSIX_ENABLE) intends to double check
if vfio msix is enabled or not. However, it is not enable at that
stage. So use_msix is assigned to "0",
> -Original Message-
> From: Singh, Jasvinder
> Sent: Wednesday, November 8, 2017 10:25 AM
> To: dev@dpdk.org
> Cc: tho...@monjalon.net; Dumitrescu, Cristian
>
> Subject: [PATCH] net/softnic: fix build error on gcc4.5.1
>
> Fix the build error due to improper handling of unions on SUSE1
On 10/17/2017 05:24 PM, Shahaf Shuler wrote:
Update deprecation notice for the new ethdev offloads API.
Deprecation of the old offloads API is set to 18.05.
Signed-off-by: Shahaf Shuler
---
doc/guides/rel_notes/deprecation.rst | 14 --
1 file changed, 8 insertions(+), 6 deletions
"Burakov, Anatoly" wrote on 11/07/2017 02:54:24
PM:
> From: "Burakov, Anatoly"
> To: Thomas Monjalon
> Cc: dev@dpdk.org, Jonas Pfefferle ,
jianfeng@intel.com
> Date: 11/07/2017 02:54 PM
> Subject: Re: [dpdk-dev] [PATCH] mem: warn if address hint is not
respected
>
> On 06-Nov-17 8:26 PM, Th
Not all struct fields will be written and random data could
confuse readers.
Fixes: 92aa491b881e ("nfp: add statistics")
Coverity: 140755
Signed-off-by: Alejandro Lucero
---
drivers/net/nfp/nfp_net.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/net/nfp/nfp_net.c b/drivers/net/n
On Tue, Nov 7, 2017 at 5:26 PM, Ferruh Yigit wrote:
> On 11/7/2017 12:47 PM, Chas Williams wrote:
> > I will confess I haven't looked into the issue too hard since I have a
> > workaround. My first guess is that there is something going on with the
> IOMMU
> > and quiescing a PCI pass-through de
This patch improves Rx packet type offload report in case the device is
a virtual function device. L2 tunnel indications are not reported by
those devices and therefore should not be checked by the PMD.
Fixes: aee4a03fee4f ("net/mlx4: enhance Rx packet type offloads")
Signed-off-by: Moti Haimovsk
Reset device during init and close if bound to igb_uio.
Fixes: 369db3ae8e91 ("igb_uio: remove device reset in release")
Cc: sta...@dpdk.org
Signed-off-by: Shijith Thotton
---
Hi Thomas/Ferruh,
Please consider this patch for 17.11 as removing reset from igb_uio breaks
LiquidIO PMD[1]. Here I hav
If the function actually returns a null value, a null pointer
dereference will occur.
Fixes: dd63df2bfff3 ("net/nfp: add NSP symbol resolution command")
Coverity: 195013
Signed-off-by: Alejandro Lucero
---
drivers/net/nfp/nfp_nspu.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers
File descriptor is not released in any potential exit path
inside the function.
Fixes: f37d8a4b67b2 ("net/nfp: add NSP FW upload command")
Coverity: 195018
Signed-off-by: Alejandro Lucero
---
drivers/net/nfp/nfp_nspu.c | 4
1 file changed, 4 insertions(+)
diff --git a/drivers/net/nfp/nfp_
On Wed, Nov 08, 2017 at 09:54:37AM +, Jia He wrote:
> We watched a rte panic of mbuf_autotest in our qualcomm arm64 server
> due to a possible race condition.
>
> To fix this race, there are 2 options as suggested by Jerin: 1. use
> rte_smp_rmb 2. use load_acquire/store_release(refer to [2]).
The fstat function could return a value that indicates an error condition.
If this is not checked, the error condition may not be handled correctly.
Fixes: f37d8a4b67b2 ("net/nfp: add NSP FW upload command")
Coverity: 195019
Signed-off-by: Alejandro Lucero
---
drivers/net/nfp/nfp_nspu.c | 7 +++
We do not know how big can the BAR be, but we know anything less
than 1MB is an error. This BAR needs to be big enough for accessing
most of NFP internals.
Fixes: d12206e00590 ("net/nfp: add NSP user space interface")
Coverity: 195024
Signed-off-by: Alejandro Lucero
---
drivers/net/nfp/nfp_nfpu
This patch fixes the memory leaks in memzone_autotest. Those memory leaks
lead to failures in tests from the same testing group due to out of memory
problems. With introduction of rte_memzone_free() it is now possible to
free the memzone. Fix uses this API call to make a clean after each test
cas
Signed-off-by: Radu Nicolau
---
doc/guides/nics/features.rst | 17 +
doc/guides/nics/features/default.ini | 1 +
doc/guides/nics/features/ixgbe.ini| 2 ++
doc/guides/nics/features/ixgbe_vec.ini| 2 ++
doc/guides/nics/features/ixgbe_vf.ini | 2
Hi Zhiyong,
On 11/8/2017 7:03 PM, Zhiyong Yang wrote:
When running l3fwd-power to test virtio rxq interrupt using vfio
pci noiommu mode, startup fails. In the function virtio_read_caps,
the code if (flags & PCI_MSIX_ENABLE) intends to double check
if vfio msix is enabled or not. However, it is
Hi,
08/11/2017 14:26, Radu Nicolau:
> --- a/doc/guides/nics/features.rst
> +++ b/doc/guides/nics/features.rst
> @@ -900,6 +900,23 @@ Documentation describes performance values.
> See ``dpdk.org/doc/perf/*``.
>
>
> +.. _nic_features_inline_crypto_doc:
This anchor seems useless.
> +
> +Inline
On 11/8/2017 2:22 PM, Thomas Monjalon wrote:
Hi,
08/11/2017 14:26, Radu Nicolau:
--- a/doc/guides/nics/features.rst
+++ b/doc/guides/nics/features.rst
@@ -900,6 +900,23 @@ Documentation describes performance values.
See ``dpdk.org/doc/perf/*``.
+.. _nic_features_inline_crypto_doc:
Th
First, the received pointer was not checked before. Then the pointer
from malloc was not the one used in the existing check.
Fixes: ad60bca34899 ("net/nfp: read PF port MAC addr using NSP")
Coverity: 195027
Signed-off-by: Alejandro Lucero
---
drivers/net/nfp/nfp_nspu.c | 6 +-
1 file change
Memory allocated was not being released in any exit path.
Fixes: 48e2255f1b63 ("net/nfp: add NSP support for HW link configuration")
Coverity: 195030
Signed-off-by: Alejandro Lucero
---
drivers/net/nfp/nfp_nspu.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/net/nfp/nfp_nspu.c
Hi Moti,
On Wed, Nov 08, 2017 at 02:02:45PM +0200, Moti Haimovsky wrote:
> This patch improves Rx packet type offload report in case the device is
> a virtual function device. L2 tunnel indications are not reported by
> those devices and therefore should not be checked by the PMD.
>
> Fixes: aee4
Hi Bruce
On 11/8/2017 8:15 PM, Bruce Richardson Wrote:
On Wed, Nov 08, 2017 at 09:54:37AM +, Jia He wrote:
We watched a rte panic of mbuf_autotest in our qualcomm arm64 server
due to a possible race condition.
To fix this race, there are 2 options as suggested by Jerin: 1. use
rte_smp_rmb
08/11/2017 15:31, Radu Nicolau:
> On 11/8/2017 2:22 PM, Thomas Monjalon wrote:
> > 08/11/2017 14:26, Radu Nicolau:
> >> +
> >> +Inline crypto
> >> +-
> >> +
> >> +Supports inline crypto processing (eg. inline IPsec). See Security
> >> library for more details.
> >
> > As there are sev
Inline
> -Original Message-
> From: Adrien Mazarguil [mailto:adrien.mazarg...@6wind.com]
> Sent: Wednesday, November 8, 2017 4:58 PM
> To: Mordechay Haimovsky
> Cc: dev@dpdk.org
> Subject: Re: [PATCH v1] net/mlx4: improve Rx packet type offloads report
>
> Hi Moti,
>
> On Wed, Nov 08, 2
On 11/8/2017 3:13 PM, Thomas Monjalon wrote:
08/11/2017 15:31, Radu Nicolau:
On 11/8/2017 2:22 PM, Thomas Monjalon wrote:
08/11/2017 14:26, Radu Nicolau:
+
+Inline crypto
+-
+
+Supports inline crypto processing (eg. inline IPsec). See Security library for
more details.
As there
On Wed, Nov 08, 2017 at 03:33:57PM +, Mordechay Haimovsky wrote:
> Inline
>
> > -Original Message-
> > From: Adrien Mazarguil [mailto:adrien.mazarg...@6wind.com]
> > Sent: Wednesday, November 8, 2017 4:58 PM
> > To: Mordechay Haimovsky
> > Cc: dev@dpdk.org
> > Subject: Re: [PATCH v1]
-Original Message-
> Date: Wed, 8 Nov 2017 23:11:32 +0800
> From: Jia He
> To: Bruce Richardson
> Cc: jerin.ja...@caviumnetworks.com, dev@dpdk.org, olivier.m...@6wind.com,
> konstantin.anan...@intel.com, jianbo@arm.com, hemant.agra...@nxp.com
> Subject: Re: [PATCH v4 0/4] fix race co
Rawdevice Support in DPDK
-
This RFC describes support for rawdevices or generic device support in DPDK.
It is supported by following writeup accompanied by skeleton header file with
declarations.
Motivation
==
In terms of device flavor (type) support, DPDK curren
Raw device is a generalized interface for expanding non-generic devices
into DPDK framework. This library provides primitive interfaces which
enable creation of raw devices.
Signed-off-by: Hemant Agrawal
---
lib/librte_rawdev/Makefile | 53 +++
lib/librte_rawdev/rte_rawdev.c
Signed-off-by: Hemant Agrawal
---
config/common_base | 7 +++
lib/Makefile | 3 +++
2 files changed, 10 insertions(+)
diff --git a/config/common_base b/config/common_base
index 34f04a9..30ab741 100644
--- a/config/common_base
+++ b/config/common_base
@@ -793,6 +793,13 @@ CONFIG_RTE_LIB
> -Original Message-
> From: Jia He [mailto:hejia...@gmail.com]
> Sent: Wednesday, November 8, 2017 3:12 PM
> To: Richardson, Bruce
> Cc: jerin.ja...@caviumnetworks.com; dev@dpdk.org; olivier.m...@6wind.com;
> Ananyev, Konstantin ;
> jianbo@arm.com; hemant.agra...@nxp.com
> Subject:
This patch improves Rx packet type offload report in case the device is
a virtual function device.
In these devices we observed that the L2 tunnel flag is set also for
non-tunneled packets, this leads to a complete misinterpretation of the
packet type being received.
This issue occurs since the tun
On 11/06/2017 11:28 AM, Bruce Richardson wrote:
> Following agreement at the DPDK Technical Board meeting of 2017-10-13 [1],
> update the documentation with the ABI/API policy changes.
>
> [1] http://dpdk.org/ml/archives/dev/2017-October/079961.html
>
> Signed-off-by: Bruce Richardson
Acked-by:
Hello,
I've been doing some testing using the 8023ad link bonding driver on a system
with 4 10G i40e interfaces in the link bond. It's working fine, except that
when any of the links are overloaded, it starts dropping the LACPDUs, which is
rather unfortunate for many reasons.
While thinking ab
Hello,
I've been doing some testing using the 8023ad link bonding driver on a system
with 4 10G i40e interfaces in the link bond. One thing I've noticed is that if
any of the links are overloaded when I don't have dedicated control queues
enabled, it starts dropping LACPDUs on transmit. I quick
> > Fix the build error due to improper handling of unions on SUSE11(gcc 4.5.1).
> >
> > Fixes: 299a89de916a ("net/softnic: add TM capabilities ops")
> >
> > DPDK/drivers/net/softnic/rte_eth_softnic_tm.c:588:3
> > error: unknown field 'nonleaf' specified in initializer compilation
> > terminated
08/11/2017 19:47, Moti Haimovsky:
> This patch improves Rx packet type offload report in case the device is
> a virtual function device.
> In these devices we observed that the L2 tunnel flag is set also for
> non-tunneled packets, this leads to a complete misinterpretation of the
> packet type bei
08/11/2017 13:04, Shijith Thotton:
> Reset device during init and close if bound to igb_uio.
>
> Fixes: 369db3ae8e91 ("igb_uio: remove device reset in release")
> Cc: sta...@dpdk.org
>
> Signed-off-by: Shijith Thotton
> ---
> Hi Thomas/Ferruh,
>
> Please consider this patch for 17.11 as removin
The feature was added at the end of the table.
And the description was between the anchor _nic_features_timesync
and its title.
It is moved near related features with a new anchor.
It is also renamed from "mbuf fast free" to "fast mbuf free".
Fixes: d6f90afd3070 ("ethdev: add mbuf fast free Tx of
On 11/8/2017 12:51 PM, Thomas Monjalon wrote:
> The feature was added at the end of the table.
> And the description was between the anchor _nic_features_timesync
> and its title.
> It is moved near related features with a new anchor.
>
> It is also renamed from "mbuf fast free" to "fast mbuf free
Hi Bruce
On 11/8/2017 6:28 PM, Bruce Richardson Wrote:
On Wed, Nov 08, 2017 at 06:17:10AM +, Jia He wrote:
for the code as follows:
if (condition)
rte_smp_rmb();
else
rte_smp_wmb();
Without this patch, compiler will report this error:
error: 'else' without a previous 'if'
Hi Jianfeng,
Thanks for detailed reviews and comments. Next version will come soon according
to your suggestions.
Thanks
Zhiyong
> -Original Message-
> From: Tan, Jianfeng
> Sent: Wednesday, November 8, 2017 9:53 PM
> To: Yang, Zhiyong ; dev@dpdk.org
> Cc: y...@fridaylinux.org; maxime.c
Hi Jianfeng,
> -Original Message-
> From: Tan, Jianfeng
> Sent: Wednesday, November 8, 2017 9:53 PM
> To: Yang, Zhiyong ; dev@dpdk.org
> Cc: y...@fridaylinux.org; maxime.coque...@redhat.com
> Subject: Re: [PATCH v2] net/virtio: fix rxq intr config fails using vfio-pci
>
>
> Hi Zhiyong,
>
From: Jonas Pfefferle1 [mailto:j...@zurich.ibm.com]
Sent: 2017年11月7日 18:16
To: Chao Zhu
Cc: 'Burakov, Anatoly' ; bruce.richard...@intel.com;
dev@dpdk.org
Subject: RE: [dpdk-dev] Huge mapping secondary process linux
"Chao Zhu" mailto:chao...@linux.vnet.ibm.com> >
wrote on 11/07/2017 09
On 11/9/2017 9:22 AM, Jia He Wrote:
Hi Bruce
On 11/8/2017 6:28 PM, Bruce Richardson Wrote:
On Wed, Nov 08, 2017 at 06:17:10AM +, Jia He wrote:
for the code as follows:
if (condition)
rte_smp_rmb();
else
rte_smp_wmb();
Without this patch, compiler will report this error:
error: '
When running l3fwd-power to test virtio rxq interrupt using vfio
pci noiommu mode, startup fails. In the function virtio_read_caps,
the code if (flags & PCI_MSIX_ENABLE) intends to double check
if vfio msix is enabled or not. However, it is not enable at that
time. So use_msix is assigned to "0", n
The 11/09/2017 11:14, Jia He wrote:
>
>
> On 11/9/2017 9:22 AM, Jia He Wrote:
> >Hi Bruce
> >
> >
> >On 11/8/2017 6:28 PM, Bruce Richardson Wrote:
> >>On Wed, Nov 08, 2017 at 06:17:10AM +, Jia He wrote:
> >>>for the code as follows:
> >>>if (condition)
> >>>rte_smp_rmb();
> >>>else
> >>>
Hi,
When I attached a virtio device to ovs bridge in vhostuser type, the virtual
port does not have the mac address.
After checked the dpdk code, I found the 'mac' which is the member of struct
'virtio_net' is empty.
It only been assigned in case VHOST_USER_SEND_RARP of function
'vhost_user_msg
On 11/9/2017 10:11 AM, Yang, Zhiyong wrote:
Hi Jianfeng,
-Original Message-
From: Tan, Jianfeng
Sent: Wednesday, November 8, 2017 9:53 PM
To: Yang, Zhiyong ; dev@dpdk.org
Cc: y...@fridaylinux.org; maxime.coque...@redhat.com
Subject: Re: [PATCH v2] net/virtio: fix rxq intr config fails
On 11/9/2017 11:18 AM, Zhiyong Yang wrote:
When running l3fwd-power to test virtio rxq interrupt using vfio
pci noiommu mode, startup fails. In the function virtio_read_caps,
the code if (flags & PCI_MSIX_ENABLE) intends to double check
if vfio msix is enabled or not. However, it is not enable
> -Original Message-
> From: Tan, Jianfeng
> Sent: Thursday, November 9, 2017 11:47 AM
> To: Yang, Zhiyong ; dev@dpdk.org
> Cc: y...@fridaylinux.org
> Subject: Re: [PATCH v3] net/virtio: fix rxq intr config fails using vfio-pci
>
>
>
> On 11/9/2017 11:18 AM, Zhiyong Yang wrote:
> > Whe
On 11/9/2017 12:01 PM, Yang, Zhiyong wrote:
static int
+virtio_intr_enable(struct rte_eth_dev *dev) {
+ struct virtio_hw *hw = dev->data->dev_private;
+
+ if (rte_intr_enable(dev->intr_handle) < 0)
+ return -1;
+
+ if (!hw->virtio_user_dev)
+ hw
Hi Jianbo
On 11/9/2017 11:21 AM, Jianbo Liu Wrote:
The 11/09/2017 11:14, Jia He wrote:
On 11/9/2017 9:22 AM, Jia He Wrote:
Hi Bruce
On 11/8/2017 6:28 PM, Bruce Richardson Wrote:
On Wed, Nov 08, 2017 at 06:17:10AM +, Jia He wrote:
for the code as follows:
if (condition)
rte_smp_r
When running l3fwd-power to test virtio rxq interrupt using vfio
pci noiommu mode, startup fails. In the function virtio_read_caps,
the code if (flags & PCI_MSIX_ENABLE) intends to double check
if vfio msix is enabled or not. However, it is not enable at that
time. So use_msix is assigned to "0", n
The 11/09/2017 12:43, Jia He wrote:
> Hi Jianbo
>
>
> On 11/9/2017 11:21 AM, Jianbo Liu Wrote:
> >The 11/09/2017 11:14, Jia He wrote:
> >>
> >>On 11/9/2017 9:22 AM, Jia He Wrote:
> >>>Hi Bruce
> >>>
> >>>
> >>>On 11/8/2017 6:28 PM, Bruce Richardson Wrote:
> On Wed, Nov 08, 2017 at 06:17:10AM +0
When Rx interrupt is not enabled, there is no need to check if interrupt
allow others. It will cause VF cannot forwarding packets issue. This patch
fixes this issue.
Fixes: 96a9fd03c25f ("net/i40e: fix Rx queue interrupt mapping in VF")
Cc: sta...@dpdk.org
Signed-off-by: Xiaoyun Li
---
drivers/
> -Original Message-
> From: Yang, Zhiyong
> Sent: Thursday, November 9, 2017 12:46 PM
> To: dev@dpdk.org
> Cc: sta...@dpdk.org; Tan, Jianfeng; y...@fridaylinux.org;
> maxime.coque...@redhat.com; Yang, Zhiyong
> Subject: [PATCH v4] net/virtio: fix rxq intr config fails using vfio-pci
>
>
Signed-off-by: Rasesh Mody
---
doc/guides/nics/qede.rst | 59 ++
1 file changed, 39 insertions(+), 20 deletions(-)
diff --git a/doc/guides/nics/qede.rst b/doc/guides/nics/qede.rst
index 09a10be..84becc9 100644
--- a/doc/guides/nics/qede.rst
+++ b/doc
Signed-off-by: Abhinandan Gujjar
Signed-off-by: Nikhil Rao
---
lib/librte_eventdev/rte_eventdev.c | 25 +++
lib/librte_eventdev/rte_eventdev.h | 44 ++
lib/librte_eventdev/rte_eventdev_pmd.h | 32 +
3 files changed,
From: Harish Patil
Restore the default configuration as in previous releases and
add a debug msg.
Fixes: f07aa795c92a ("net/qede: disable per-VF Tx switching feature")
Signed-off-by: Harish Patil
Signed-off-by: Rasesh Mody
---
config/common_base |2 +-
drivers/net/qede/qede_e
Signed-off-by: Abhinandan Gujjar
Signed-off-by: Nikhil Rao
Signed-off-by: Gage Eads
---
lib/librte_eventdev/Makefile | 1 +
lib/librte_eventdev/rte_event_crypto_adapter.h | 474 +
2 files changed, 475 insertions(+)
create mode 100644 lib/librte_event
71 matches
Mail list logo
