NFP can handle IOVA as VA. It requires to check those IOVAs
being in the supported range what is done during initialization.
Signed-off-by: Alejandro Lucero
---
drivers/net/nfp/nfp_net.c | 6 --
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/drivers/net/nfp/nfp_net.c b/drivers
This patch removes unneeded include of rte_mempool.h in
two modules in examples/l3fwd.
Fixes: 26b5b020 ("examples/l3fwd: modularize")
Signed-off-by: Rami Rosen
---
examples/l3fwd/l3fwd_em.c | 1 -
examples/l3fwd/l3fwd_lpm.c | 1 -
2 files changed, 2 deletions(-)
diff --git a/examples/l3f
> On Jul 1, 2018, at 10:13 PM, Matan Azrad wrote:
>
> Starting from rdma-core v19, Mellanox OFED 4.4, the Verbs resources
> cleanup is properly activated in plug-out process while setting the
> MLX5_DEVICE_FATAL_CLEANUP environment variable to 1.
>
> Set the aforementioned variable to 1.
>
>
> On Jul 2, 2018, at 4:11 AM, Moti Haimovsky wrote:
>
> This patch adds support for building and running mlx5 PMD on
> 32bit systems such as i686.
>
> The main issue to tackle was handling the 32bit access to the UAR
> as quoted from the mlx5 PRM:
> QP and CQ DoorBells require 64-bit writes. F
The example code is showing how to use KNI, and can be found in
examples/kni/
The documentation guide for this example is explaining the code
to ease the understanding of the example.
And inside this documentation, there are a lot of examples code
which are copy/pasted. It is really too muc
The global variables rx_mode and fdir_conf
are not used in this test file.
Signed-off-by: Thomas Monjalon
---
test/test/test_link_bonding.c | 19 ---
1 file changed, 19 deletions(-)
diff --git a/test/test/test_link_bonding.c b/test/test/test_link_bonding.c
index 0ffd65090..d74c0
A new offload API has been introduced in DPDK 17.11.
This patchset resumes the work started by Ferruh (RFC)
to definitely drop the old offload API.
There are:
- 3 patches to remove some useless code where the old API was found.
- 1 patch to remove usage of old API
- 1 (big) patch to remove the ol
Some test applications and examples were not converted
to the new offload API introduced in 17.11.
For reference, see "Hardware Offload" in
doc/guides/prog_guide/poll_mode_drv.rst
Signed-off-by: Thomas Monjalon
---
app/test-eventdev/test_perf_common.c | 8 +
.../sample_app
From: Ferruh Yigit
In DPDK 17.11, the ethdev offloads API has changed:
commit cba7f53b717d ("ethdev: introduce Tx queue offloads API")
commit ce17eddefc20 ("ethdev: introduce Rx queue offloads API")
The new API is documented in the programmer's guide:
http://doc.dpdk.org/
The macro FM10K_SIMPLE_TX_FLAG was used with old Tx queue flags.
It is no longer used and was forgotten when cleaning old Tx flags.
Fixes: 1778ef67e2e7 ("net/fm10k: remove dependence on Tx queue flags")
Cc: sta...@dpdk.org
Signed-off-by: Thomas Monjalon
---
drivers/net/fm10k/fm10k.h | 3 ---
1
29/06/2018 03:11, Thomas Monjalon:
> 09/06/2018 00:41, Ferruh Yigit:
> > Cc: Shahaf Shuler
> >
> > Signed-off-by: Ferruh Yigit
>
> I start working on it.
> This is the list of remaining work on this patch:
> - rebase
> - add commit message (and fix title)
> - check git grep ET
On Wed, Jun 27, 2018 at 05:07:33PM +0200, Nelio Laranjeiro wrote:
> This start a series to re-work the flow engine in mlx5 to easily support
> flow conversion to Verbs or TC. This is necessary to handle both regular
> flows and representors flows.
>
> As the full file needs to be clean-up to re-w
On 6/29/2018 10:29 AM, John Daley wrote:
> Updated a few commits in the patchset per suggestions by Ferrus Yigit.
> thanks,
> John
>
> Hyong Youb Kim (12):
> net/enic: fix receive packet types
> net/enic: update the UDP RSS detection mechanism
> net/enic: do not overwrite admin Tx queue limi
On 6/8/2018 5:38 PM, Bruce Richardson wrote:
> The kni library is not supported on 32-bit so disable it for those
> builds using meson.
>
> Signed-off-by: Bruce Richardson
Acked-by: Ferruh Yigit
On 6/8/2018 5:38 PM, Bruce Richardson wrote:
> Rather than hard-coding the example app to be built only when a set of
> conditions are met, we can simplify things by having the app built when
> KNI library itself is available. That saves us duplicating the same set
> of restrictions on both library
On Wed, Jun 27, 2018 at 05:07:34PM +0200, Nelio Laranjeiro wrote:
> Drop queues are essentially used in flows due to Verbs API, the
> information if the fate of the flow is a drop or not is already present
> in the flow. Due to this, drop queues can be fully mapped on regular
> queues.
The title
> -Original Message-
> From: Yigit, Ferruh
> Sent: Tuesday, July 03, 2018 12:57 AM
> To: Maxime Coquelin ; Liu, Yong
> ; Bie, Tiwei
> Cc: Wang, Zhihong ; dev@dpdk.org
> Subject: Re: [dpdk-dev] [PATCH v5 7/9] net/virtio: support in-order Rx and
> Tx
>
> On 7/2/2018 5:53 PM, Maxime Coquel
On Wed, Jun 27, 2018 at 05:07:35PM +0200, Nelio Laranjeiro wrote:
> Previous work introduce verbs priorities, whereas the PMD is making
> translation between Flow priority into Verbs. Rename this to make more
> sense on what the PMD has to translate.
>
> Signed-off-by: Nelio Laranjeiro
> ---
Ack
> -Original Message-
> From: Maxime Coquelin [mailto:maxime.coque...@redhat.com]
> Sent: Monday, July 02, 2018 11:18 PM
> To: Liu, Yong ; Bie, Tiwei ;
> Yigit, Ferruh
> Cc: Wang, Zhihong ; dev@dpdk.org
> Subject: Re: [PATCH v5 8/9] net/virtio: add in-order Rx/Tx into selection
>
>
>
>
Hey Rahul,
Thank you, those two are the ways to achieve that.
Personally I prefer the option 1 but with a little bit difference, something
like:
struct rte_flow_action_of_set_nw_ipv4 {
uint32_t ipv4_addr;
uint8_t level; /* 0 - outer (default), 1 - inner, 2 -255
On Mon, Jul 02, 2018 at 05:25:43PM +0200, Maxime Coquelin wrote:
> In this v3, the main change is the removal of the Tx simple path.
> Indeed, this path is not compliant with the Virtio specification,
> so could cause problems with some host implementations.
>
> Since Marvin has introduced the in-
On Wed, Jun 27, 2018 at 04:49:53PM +0200, Maxime Coquelin wrote:
[...]
> @@ -1164,8 +1136,7 @@ rte_vhost_dequeue_burst(int vid, uint16_t queue_id,
>
> if (mbuf_is_consumed(zmbuf->mbuf)) {
> used_idx = vq->last_used_idx++ & (vq->size - 1);
Above
On Wed, Jun 27, 2018 at 04:49:54PM +0200, Maxime Coquelin wrote:
> CVE-2018-1059 fix makes sure gpa contiguous memory is
> also contiguous in hva space. Incidentally, it also makes
> sure it is contiguous in hpa space.
>
> So we can simplify the code by making gpa contiguous memory
> discontiguous
HW needs each pool to be mapped to an aura set of 16 auras.
Previously, pool to aura mapping was considered to be 1:1.
Fixes: 02fd6c744350 ("mempool/octeontx: support allocation")
Cc: sta...@dpdk.org
Signed-off-by: Pavan Nikhilesh
Acked-by: Santosh Shukla
Acked-by: Jerin Jacob
---
drivers/eve
On 07/03/2018 06:45 AM, Tiwei Bie wrote:
On Wed, Jun 27, 2018 at 04:49:54PM +0200, Maxime Coquelin wrote:
CVE-2018-1059 fix makes sure gpa contiguous memory is
also contiguous in hva space. Incidentally, it also makes
sure it is contiguous in hpa space.
So we can simplify the code by making
On 07/03/2018 05:28 AM, Tiwei Bie wrote:
On Wed, Jun 27, 2018 at 04:49:53PM +0200, Maxime Coquelin wrote:
[...]
@@ -1164,8 +1136,7 @@ rte_vhost_dequeue_burst(int vid, uint16_t queue_id,
if (mbuf_is_consumed(zmbuf->mbuf)) {
used_idx = vq->last_used_idx+
On 2018年07月02日 16:16, Maxime Coquelin wrote:
+static inline int
+vhost_enable_notify_split(struct vhost_virtqueue *vq, int enable)
+{
+ if (enable)
+ vq->used->flags &= ~VRING_USED_F_NO_NOTIFY;
+ else
+ vq->used->flags |= VRING_USED_F_NO_NOTIFY;
+
+
On 2018年07月02日 16:16, Maxime Coquelin wrote:
Signed-off-by: Maxime Coquelin
---
lib/librte_vhost/vhost.c | 73
lib/librte_vhost/vhost.h | 71 ++
lib/librte_vhost/vhost_user.c| 24 +
Hello Anoob,
Regards
Sunil Kumar
> -Original Message-
> From: Joseph, Anoob [mailto:anoob.jos...@caviumnetworks.com]
> Sent: Thursday, June 28, 2018 4:13 PM
> To: Sunil Kumar Kori ; Bruce Richardson
> ; Jerin Jacob
> ; Pablo de Lara
>
> Cc: Hemant Agrawal ; Narayana Prasad
> ; Nikhil Rao
On 07/03/2018 07:57 AM, Jason Wang wrote:
On 2018年07月02日 16:16, Maxime Coquelin wrote:
+static inline int
+vhost_enable_notify_split(struct vhost_virtqueue *vq, int enable)
+{
+ if (enable)
+ vq->used->flags &= ~VRING_USED_F_NO_NOTIFY;
+ else
+ vq->used->flags |= VRING_U
101 - 130 of 130 matches
Mail list logo
