2015-11-12 14:05, Stephen Hemminger:
> Looking at the Coverity scan for DPDK, it looks like all the base
> drivers are marked to be ignored.
>
> Although the changes to base drivers should not be done directly through
> DPDK list. I think it is still valuable to have these driver scanned and
> not
2015-11-05 17:04, Stephen Hemminger:
> Several fields in ether statistics were tagged with comment that they
> were going to be deprecated, but comments don't cause compile warnings.
> Instead use Gcc attributes to force the issue.
>
> Of course to do that, all the drivers and tests which are usin
2015-11-05 17:04, Stephen Hemminger:
> Use deprecated attribute to highlight any use of fields that
> are marked as going away in the rte_ether device statistics.
The example app ip_pipeline does not compile.
I will add a patch to fix it.
Change the codes in vhost sample to test virtio offload feature.
These changes include,
1. add two test options: tx-csum and tso.
2. add virtio_tx_offload() function to test vhost TX offload feature for VM to
NIC case;
however, for VM to VM case, it doesn't need to call this function, the reas
Remove the ipv4_hdr structure defination in vhost sample.
The same structure has already defined in the rte_ip.h file, so we remove the
defination from the sample, and include that header file.
Signed-off-by: Jijiang Liu
---
examples/vhost/main.c | 15 +--
1 files changed, 1 inse
Add guest offload setting in vhost lib.
Refer to the feature bits description in the Virtual I/O Device (VIRTIO)
Version 1.0 below,
1. VIRTIO_NET_F_GUEST_CSUM (1) Driver handles packets with partial checksum.
2. If the VIRTIO_NET_F_GUEST_CSUM feature was negotiated, the
VIRTIO_NET_HDR_F_NEEDS
Add vhost TX offload(CSUM and TSO) support capabilities in vhost lib.
Refer to feature bits in Virtual I/O Device (VIRTIO) Version 1.0 below,
VIRTIO_NET_F_CSUM (0) Device handles packets with partial checksum. This
"checksum offload" is a common feature on modern network cards.
VIRTIO_NET_F_HOST
Adds virtio offload support in us-vhost.
The patch set adds the feature negotiation of checksum and TSO between us-vhost
and vanilla Linux virtio guest, and add these offload features support in the
vhost lib, and change vhost sample to test them.
v5 changes:
Add more clear descriptions to ex
>
> + if (rte_kvargs_count(kvlist, ETH_VHOST_IFACE_ARG) == 1) {
> + ret = rte_kvargs_process(kvlist, ETH_VHOST_IFACE_ARG,
> +&open_iface, &iface_name);
> + if (ret < 0)
> + goto out_free;
> + }
>
2015-11-12 09:38, Stephen Hemminger:
> On Thu, 12 Nov 2015 08:17:57 +0800
> Jianfeng Tan wrote:
>
> > This patch enables calculating space left in a hugetlbfs.
> > There are three sources to get the information: 1. from
> > sysfs; 2. from option size specified when mount; 3. use
> > statfs. We sh
On Thu, Nov 12, 2015 at 02:05:08PM -0800, Stephen Hemminger wrote:
> Looking at the Coverity scan for DPDK, it looks like all the base
> drivers are marked to be ignored.
>
> Although the changes to base drivers should not be done directly through
> DPDK list. I think it is still valuable to have
2015-11-05 17:04, Stephen Hemminger:
> The number of received multicast frames is useful and already
> available in many/most drivers. Therefore don't mark it as
> deprecated.
There are other useful stats in xstats.
The idea of this basic stats structure is to provide only
the really mandatory and
Hi folks,
With the addition of hot plug support we have been migrating away from
device discovery and attach at initialization time to a model where it
is controlled from a separate process. The separate process manages the
binding of devices to UIO and instructs the DPDK process when to
atta
2015-11-06 14:12, Harry van Haaren:
> This patchset modifies how queue statistics are presented by
> rte_eth_xstats_get() and each PMD's xstats_get().
>
> Generic stats from the rte_eth_stats struct are presented by rte, and each
> PMD can augment those stats with extra stats that are available (i
On Thu, Nov 12, 2015 at 12:02:33AM -0800, Rich Lane wrote:
> The guest could trigger this buffer overflow by creating a cycle of
> descriptors
> (which would also cause an infinite loop). The more common case is that
> vq->avail->idx jumps out of the range [last_used_idx, last_used_idx+256). This
> > This mini-series adds support for driver directory concept
> > based on idea by Thomas Monjalon back in February:
> > http://dpdk.org/ml/archives/dev/2015-February/013285.html
> >
> > In the process FreeBSD also gains plugin support (but untested).
> >
> > v4: - introduce error-early behavior f
> > Reorder
> > -M: Sergio Gonzalez Monroy
> > +M: Reshma Pattan
> > F: lib/librte_reorder/
> > F: doc/guides/prog_guide/reorder_lib.rst
> > F: app/test/test_reorder*
> Acked-by: Sergio Gonzalez Monroy
So you are replacing Sergio.
Any enhancement or feature planned?
2015-10-30 14:30, Sergio Gonzalez Monroy:
> On 21/10/2015 14:01, Sergio Gonzalez Monroy wrote:
> > On 21/10/2015 11:50, Reshma Pattan wrote:
> >> The reorder library unit test was performed under the assumption that
> >> the start
> >> sequence number was always 0.
> >> This is not the case anymor
It fixes the issue of trying to allocate more VSIs for VMDq than
hardware remaining. It adds a check of the hardware remaining
before allocating VSIs for VMDq.
Fixes: c80707a0fd9c ("i40e: fix VMDq pool limit")
Signed-off-by: Helin Zhang
---
drivers/net/i40e/i40e_ethdev.c | 7 +--
1 file cha
2015-11-06 15:08, johndale:
> Signed-off-by: johndale
Applied, thanks
On 11/11/2015 06:28 PM, Bruce Richardson wrote:
> On Wed, Nov 11, 2015 at 04:13:01PM +, Montorsi, Francesco wrote:
>> Hi,
>> Is there a way to permanently (i.e., have the configuration automatically
>> applied after reboot) bind a NIC port to DPDK?
>>
>> In case there's none, I'm thinking to s
On Thu, 5 Nov 2015 17:04:33 -0800
Stephen Hemminger wrote:
> The number of received multicast frames is useful and already
> available in many/most drivers. Therefore don't mark it as
> deprecated.
>
> Signed-off-by: Stephen Hemminger
> ---
> drivers/net/ixgbe/ixgbe_ethdev.c | 1 -
> lib/libr
This patch fixes a bug under lower version linux kernel, mmap()
fails when length is not aligned with hugepage size. mmap()
without flag of MAP_ANONYMOUS, should be called with length
argument aligned with hugepagesz at older longterm version
Linux, like 2.6.32 and 3.2.72, or mmap() will fail with
Looking at the Coverity scan for DPDK, it looks like all the base
drivers are marked to be ignored.
Although the changes to base drivers should not be done directly through
DPDK list. I think it is still valuable to have these driver scanned and
notify (badger) the vendors to fix there code.
Sinc
HI,
I've read the documentation and looked at the example acl app. What is the
best practice for deleting rules? The API looks like a new context needs
created and built. Is that true? Also, this is more of a confirmation, but
RTE_ACL_MAX_FIELDS is defined as 64, so I assume that for ipv
You can reproduce this with l2fwd and the vhost PMD.
You'll need this patch on top of the vhost PMD patches:
--- a/lib/librte_vhost/virtio-net.c
+++ b/lib/librte_vhost/virtio-net.c
@@ -471,7 +471,7 @@ reset_owner(struct vhost_device_ctx ctx)
return -1;
if (dev->flags & VIR
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Pablo de Lara
> Sent: Thursday, November 12, 2015 12:56 PM
> To: dev at dpdk.org
> Subject: [dpdk-dev] [PATCH v6 0/8] add sample ptp slave application
>
>
> Add a sample application that acts as a PTP slave usi
Hi,
On 12/11/2015 02:10, Jianfeng Tan wrote:
> This patch enables calculating space left in a hugetlbfs.
> There are three sources to get the information: 1. from
> sysfs; 2. from option size specified when mount; 3. use
> statfs. We should use the minimum one of these three sizes.
We could improv
From: "Chen Jing D(Mark)"
When the fm10k port is closed, both func tx_queue_clean() and
fm10k_tx_queue_release_mbufs_vec() will try to release buffer in
SW ring. The latter func won't do sanity check on those pointers
and cause crash.
The fix include 2 parts.
1. Remove Vector TX buffer release f
From: Daniel Mrzyglod
Add a sample app guide for the ptpclient application.
Signed-off-by: Daniel Mrzyglod
Signed-off-by: Pablo de Lara
Reviewed-by: John McNamara
---
doc/guides/sample_app_ug/img/ptpclient.svg | 524 +
doc/guides/sample_app_ug/index.rst |
From: Daniel Mrzyglod
Add a sample application that acts as a PTP slave using the
DPDK ieee1588 functions.
Signed-off-by: Daniel Mrzyglod
Signed-off-by: Pablo de Lara
Reviewed-by: John McNamara
---
MAINTAINERS| 4 +
examples/Makefile | 1 +
examples/ptpcl
Testpmd was only printing out second values when printing
RX/TX timestamp value, instead of both second and nanoseconds.
Since resolution of time counters is in nanoseconds,
testpmd should print out both.
Signed-off-by: Pablo de Lara
Reviewed-by: John McNamara
---
app/test-pmd/ieee1588fwd.c | 8
Add additional functions to support the existing IEEE1588
functionality and to enable getting, setting and adjusting
the device time.
Signed-off-by: Daniel Mrzyglod
Signed-off-by: Pablo de Lara
Reviewed-by: John McNamara
---
drivers/net/i40e/i40e_ethdev.c | 147
Add additional functions to support the existing IEEE1588
functionality and to enable getting, setting and adjusting
the device time.
Signed-off-by: Daniel Mrzyglod
Signed-off-by: Pablo de Lara
Reviewed-by: John McNamara
---
drivers/net/e1000/e1000_ethdev.h | 2 +
drivers/net/e1000/igb_ethde
From: Daniel Mrzyglod
Add additional functions to support the existing IEEE1588
functionality and to enable getting, setting and adjusting
the device time.
Signed-off-by: Daniel Mrzyglod
Signed-off-by: Pablo de Lara
Reviewed-by: John McNamara
---
drivers/net/ixgbe/ixgbe_ethdev.c | 187 ++
From: Daniel Mrzyglod
Add common functions and structures to handle time, and cycle counts
which will be used for PTP processing.
Signed-off-by: Daniel Mrzyglod
Signed-off-by: Pablo de Lara
Reviewed-by: John McNamara
---
lib/librte_eal/common/Makefile | 2 +-
lib/librte_eal/commo
From: Daniel Mrzyglod
Add additional functions to support the existing IEEE1588
functionality.
* rte_eth_timesync_write_time(): set the device clock time.
* rte_eth_timesync_read_time(): get the device clock time.
* rte_eth_timesync_adjust_time(): adjust the device clock time.
Signed-o
Add a sample application that acts as a PTP slave using the DPDK IEEE1588
functions.
Also add some additional IEEE1588 support functions to enable getting,
setting and adjusting the device time.
V5->v6:
- Moved common functionality for cyclecounter and time conversions
functions to lib/librt
Hi Tetsuya,
In my test I created 2 vdev using "--vdev
'eth_vhost0,iface=/tmp/sock0,queues=1' --vdev
'eth_vhost1,iface=/tmp/sock1,queues=1'", and the qemu message got handled in
wrong order.
The reason is that: 2 threads are created to handle message from 2 sockets, but
their fds are SHARED, so
> -Original Message-
> From: Thomas Monjalon [mailto:thomas.monjalon at 6wind.com]
> Sent: Thursday, November 12, 2015 7:19 PM
> To: Tan, Jianfeng
> Cc: dev at dpdk.org
> Subject: Re: [dpdk-dev] [PATCH v2] vhost: fix mmap failure as len not aligned
> with hugepage size
>
> 2015-11-12 06:
> --- a/MAINTAINERS
> +++ b/MAINTAINERS
> Cisco enic
> +M: John Daley
> +M: Sujith Sankar
> F: drivers/net/enic/
Welcome :)
Now as we officially have some maintainers for enic,
please could you consider writing doc/guides/nics/enic.rst?
Thanks
2015-11-12 12:10, Yuanhan Liu:
> Firstly, Chuangchun's email address's been invalid for a while.
>
> Secondly, I'd like to take the responsibility to review patches
> of virtio/vhost component.
[...]
> RedHat virtio
> M: Huawei Xie
> -M: Changchun Ouyang
> +M: Yuanhan Liu
> F: drivers/net/vi
> > Currently, we reset all fields of a device to zero when reset
> > happens, which is wrong, since for some fields like device_fh,
> > ifname, and virt_qp_nb, they should be same and be kept after
> > reset until the device is removed. And this is what's the new
> > helper function reset_device()
2015-11-10 10:25, Yuanhan Liu:
> On Mon, Nov 09, 2015 at 06:15:13PM -0800, Rich Lane wrote:
> > QEMU sends this message first when shutting down. There was previously no
> > way
> > for the dataplane to know that the virtio_net instance had become unusable
> > and
> > it would segfault when tryin
2015-11-12 06:04, Jianfeng Tan:
> - alignment = region[idx].blksz;
> - munmap((void *)(uintptr_t)
> - RTE_ALIGN_FLOOR(
> - region[idx].mapped_address, alignment),
> -
2015-11-12 15:09, Helin Zhang:
> It fixes the issue of trying to allocate more VSIs for VMDq than
> hardware remaining. It adds a check of the hardware remaining
> before allocating VSIs for VMDq.
>
> Fixes: c80707a0fd9c ("i40e: fix VMDq pool limit")
>
> Signed-off-by: Helin Zhang
Applied, than
Currently, we reset all fields of a device to zero when reset
happens, which is wrong, since for some fields like device_fh,
ifname, and virt_qp_nb, they should be same and be kept after
reset until the device is removed. And this is what's the new
helper function reset_device() for.
And use rte_z
Firstly, Chuangchun's email address's been invalid for a while.
Secondly, I'd like to take the responsibility to review patches
of virtio/vhost component.
Cc: Huawei Xie
Cc: Thomas Monjalon
Signed-off-by: Yuanhan Liu
---
MAINTAINERS | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff
Updated release notes about adding X722 support.
Signed-off-by: Helin Zhang
---
doc/guides/rel_notes/release_2_2.rst | 4
1 file changed, 4 insertions(+)
diff --git a/doc/guides/rel_notes/release_2_2.rst
b/doc/guides/rel_notes/release_2_2.rst
index 5636aad..5811c2f 100644
--- a/doc/guides
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of John McNamara
> Sent: Monday, November 2, 2015 5:46 PM
> To: dev at dpdk.org
> Subject: [dpdk-dev] [PATCH] examples/l3fwd: fix eth-dest commandline
> strncmp size
>
> Fix minor, and non critical, copy and past
This patch enables calculating space left in a hugetlbfs.
There are three sources to get the information: 1. from
sysfs; 2. from option size specified when mount; 3. use
statfs. We should use the minimum one of these three sizes.
Signed-off-by: Jianfeng Tan
---
Changes in v2:
- reword title
- f
> -Original Message-
> From: Wu, Jingjing
> Sent: Tuesday, November 10, 2015 3:11 AM
> To: dev at dpdk.org
> Cc: Wu, Jingjing; Zhang, Helin; Chilikin, Andrey
> Subject: [PATCH] doc: announce ABI change for struct rte_eth_fdir_flow
>
> Signed-off-by: Jingjing Wu
Acked-by: Andrey Chilikin
This patch enables calculating space left in a hugetlbfs.
There are three sources to get the information: 1. from
sysfs; 2. from option size specified when mount; 3. use
statfs. We should use the minimum one of these three sizes.
Signed-off-by: Jianfeng Tan
---
lib/librte_eal/linuxapp/eal/eal_hu
On Wed, Nov 11, 2015 at 09:31:14AM -0800, Stephen Hemminger wrote:
> On Wed, 11 Nov 2015 16:26:57 +0800
> Yuanhan Liu wrote:
>
> > On Wed, Nov 11, 2015 at 02:40:41PM +0800, Jijiang Liu wrote:
> > > Add vhost TX offload(CSUM and TSO) support capabilities.
> >
> > Claiming first that we support so
On Thu, 12 Nov 2015 08:17:57 +0800
Jianfeng Tan wrote:
> This patch enables calculating space left in a hugetlbfs.
> There are three sources to get the information: 1. from
> sysfs; 2. from option size specified when mount; 3. use
> statfs. We should use the minimum one of these three sizes.
>
>
This patch enables calculating space left in a hugetlbfs.
There are three sources to get the information: 1. from
sysfs; 2. from option size specified when mount; 3. use
statfs. We should use the minimum one of these three sizes.
Signed-off-by: Jianfeng Tan
---
lib/librte_eal/linuxapp/eal/eal_hu
Hi Jianfeng,
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Jianfeng Tan
> Sent: Thursday, November 12, 2015 12:18 AM
> To: dev at dpdk.org
> Subject: [dpdk-dev] [PATCH] mem: fix how to calculate space left in a
> hugetlbfs
>
> This patch enables calculatin
On 11/12/2015 1:04 PM, Tan, Jianfeng wrote:
> This patch fixes a bug under lower version linux kernel, mmap()
> fails when length is not aligned with hugepage size. mmap()
> without flag of MAP_ANONYMOUS, should be called with length
> argument aligned with hugepagesz at older longterm version
> Li
This patch fixes a bug under lower version linux kernel, mmap()
fails when length is not aligned with hugepage size. mmap()
without flag of MAP_ANONYMOUS, should be called with length
argument aligned with hugepagesz at older longterm version
Linux, like 2.6.32 and 3.2.72, or mmap() will fail with
> -Original Message-
> From: Wu, Jingjing
> Sent: Tuesday, November 10, 2015 11:50 AM
> To: dev at dpdk.org
> Cc: Wu, Jingjing; Zhang, Helin; Lu, Wenzhuo
> Subject: [PATCH] doc: announce ABI change for struct
> rte_eth_tunnel_filter_conf
>
> Signed-off-by: Jingjing Wu
Acked-by: Helin Z
> -Original Message-
> From: Wu, Jingjing
> Sent: Tuesday, November 10, 2015 11:11 AM
> To: dev at dpdk.org
> Cc: Wu, Jingjing; Zhang, Helin; Chilikin, Andrey
> Subject: [PATCH] doc: announce ABI change for struct rte_eth_fdir_flow
>
> Signed-off-by: Jingjing Wu
Acked-by: Helin Zhang
Hi,
> -Original Message-
> From: Wu, Jingjing
> Sent: Tuesday, November 10, 2015 11:50 AM
> To: dev at dpdk.org
> Cc: Wu, Jingjing ; Zhang, Helin
> ; Lu, Wenzhuo
> Subject: [PATCH] doc: announce ABI change for struct
> rte_eth_tunnel_filter_conf
>
> Signed-off-by: Jingjing Wu
Acked-by:
Hi,
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Jingjing Wu
> Sent: Tuesday, November 10, 2015 11:11 AM
> To: dev at dpdk.org
> Subject: [dpdk-dev] [PATCH] doc: announce ABI change for struct
> rte_eth_fdir_flow
>
> Signed-off-by: Jingjing Wu
Acked-by:
On 11/12/2015 10:35 AM, Tan, Jianfeng wrote:
>
>> -Original Message-
>> From: Xie, Huawei
>> Sent: Wednesday, November 11, 2015 11:57 AM
>> To: Tan, Jianfeng; dev at dpdk.org
>> Subject: Re: [dpdk-dev] [PATCH] vhost: fix mmap failure as len not aligned
>> with
>> hugepage size
>>
>> On 10/
> -Original Message-
> From: Xie, Huawei
> Sent: Wednesday, November 11, 2015 11:57 AM
> To: Tan, Jianfeng; dev at dpdk.org
> Subject: Re: [dpdk-dev] [PATCH] vhost: fix mmap failure as len not aligned
> with
> hugepage size
>
> On 10/30/2015 2:52 PM, Jianfeng Tan wrote:
> > This patch f
On Wed, Nov 11, 2015 at 8:10 PM, Yuanhan Liu
wrote:
> Currently, we reset all fields of a device to zero when reset
> happens, which is wrong, since for some fields like device_fh,
> ifname, and virt_qp_nb, they should be same and be kept after
> reset until the device is removed. And this is wha
> > ICC complains about enumerated types being mixed in link bonding driver,
> > as ETH_MQ_RX_RSS is an enum type of mq_mode and not a bitmask as it
> > was
> > being treated.
> >
> > Fixes: 734ce47f71e0 ("bonding: support RSS dynamic configuration")
> >
> > Signed-off-by: Tomasz Kulasek
>
> Ac
> > First patch contains changes in testpmd that allow to reproduce the issue.
> > Second patch is the actual fix.
> >
> > Konstantin Ananyev (2):
> > testpmd: add ability to split outgoing packets
> > ixgbe: fix TX hang when RS distance exceeds HW limit
>
> Series-acked-by: Pablo de Lara
A
> -Original Message-
> From: dev [mailto:dev-bounces at dpdk.org] On Behalf Of Montorsi, Francesco
> Sent: Wednesday, November 11, 2015 4:13 PM
> To: dev at dpdk.org
> Subject: [dpdk-dev] Permanently binding NIC ports with DPDK drivers
>
> Hi,
> Is there a way to permanently (i.e., have th
The guest could trigger this buffer overflow by creating a cycle of descriptors
(which would also cause an infinite loop). The more common case is that
vq->avail->idx jumps out of the range [last_used_idx, last_used_idx+256). This
happens nearly every time when restarting a DPDK app inside a VM con
70 matches
Mail list logo
