> X86 always allows unaligned access. Irregardless of what tools say.
> Why impose additional overhead in performance critical code.
Let me preface my response by saying that I'm not a C compiler developer.
Hopefully someone who is will read this and chime in.
I agree that X86 allows unaligned st
Calls to rte_memcpy_generic could result in unaligned loads/stores for
1 < n < 16. This is undefined behavior according to the C standard,
and it gets flagged by the clang undefined behavior sanitizer.
rte_memcpy_generic is called with unaligned src and dst addresses.
When 1 < n < 16, the code wou
As a side note, and to follow up on Stephen's indication that this is
'performance critical code', I think it might be worthwhile to
revisit/revalidate the current implementation of rte_memcpy. There's a
good thread here that mentions rte_memcpy, and its performance on at
least one platform/archite
To optimize datapath, the mlx5 pmd checked for mark action on flow
creation, and flagged possible destination rxqs (through queue/RSS
actions), then it enabled the mark action logic only for flagged rxqs.
Mark action didn't work if no queue/rss action was in the same flow,
even when the user use m
On Sun, 16 Jan 2022 09:09:49 -0500
Luc Pelletier wrote:
> > X86 always allows unaligned access. Irregardless of what tools say.
> > Why impose additional overhead in performance critical code.
>
> Let me preface my response by saying that I'm not a C compiler developer.
> Hopefully someone who
On Sun, 16 Jan 2022 09:33:19 -0500
Luc Pelletier wrote:
> As a side note, and to follow up on Stephen's indication that this is
> 'performance critical code', I think it might be worthwhile to
> revisit/revalidate the current implementation of rte_memcpy. There's a
> good thread here that mention
> From: Stephen Hemminger [mailto:step...@networkplumber.org]
> Sent: Sunday, 16 January 2022 17.34
>
> On Sun, 16 Jan 2022 09:33:19 -0500
> Luc Pelletier wrote:
>
> > As a side note, and to follow up on Stephen's indication that this is
> > 'performance critical code', I think it might be worth
This patch removes coverity defect CID 374380:
Null pointer dereferences (REVERSE_INULL)
Coverity issue: CID 374380
Fixes: 918fd2f1466b ("crypto/ipsec_mb: move aesni_mb PMD")
Cc: roy.fan.zh...@intel.com
Signed-off-by: Piotr Bronowski
---
drivers/crypto/ipsec_mb/ipsec_mb_private.h | 4 ++--
1 f
Calls to rte_memcpy_generic could result in unaligned loads/stores for
1 < n < 16. This is undefined behavior according to the C standard,
and it gets flagged by the clang undefined behavior sanitizer.
rte_memcpy_generic is called with unaligned src and dst addresses.
When 1 < n < 16, the code wou
> -Original Message-
> From: Pei, Andy
> Sent: Friday, January 14, 2022 3:57 PM
> To: dev@dpdk.org
> Cc: Xia, Chenbo
> Subject: [PATCH v2] vhost: add log for VHOST_USER_SET_VRING_BASE
>
> This patch adds log for vring related info in handling of vhost message
> VHOST_USER_SET_VRING_BASE,
Add support of ANY software type on switch filter for steering all kinds
of common packets to specific queue or drop all kinds of common packets.
Signed-off-by: Yuying Zhang
---
drivers/net/ice/base/ice_flex_pipe.c | 72 +++-
drivers/net/ice/base/ice_flex_pipe.h | 5
This patch supports drop any and steer all to queue in switch
filter. Support new rte_flow pattern any to handle all packets.
The usage is listed below.
1. drop any:
flow create 0 ingress pattern any / end actions drop / end
All packets received in port 0 will be dropped.
2. steer all to queue:
f
> -Original Message-
> From: Yunjian Wang
> Sent: Saturday, January 8, 2022 3:53 PM
> To: dev@dpdk.org
> Cc: maxime.coque...@redhat.com; Xia, Chenbo ;
> dingxiaoxi...@huawei.com; xudin...@huawei.com; Yunjian Wang
> ; sta...@dpdk.org
> Subject: [dpdk-dev] [PATCH] net/virtio-user: check fd f
These patches supports to clear in-flight packets for async dequeue and
introduces thread-safe version of this function.
note: The patches depends on the following patches
(http://patches.dpdk.org/project/dpdk/patch/20220101001244.90147-2-xuan.d...@intel.com/)
(http://patches.dpdk.org/project/dpdk
rte_vhost_clear_queue_thread_unsafe() supports to clear
in-flight packets for async enqueue only. But after
supporting async dequeue, this API should support async dequeue too.
This patch also adds the thread-safe version of this API,
the difference between the two API is that thread safety uses l
This patch allows vhost_clear_queue_thread_unsafe() to clear
in-flight dequeue packets.
Signed-off-by: Yuan Wang
---
examples/vhost/main.c | 8
1 file changed, 8 insertions(+)
diff --git a/examples/vhost/main.c b/examples/vhost/main.c
index 04a85262bc..050f983fd6 100644
--- a/examples/
Hi Chenbo,
Please see replies inline.
Thanks,
Jiayu
> -Original Message-
> From: Xia, Chenbo
> > diff --git a/examples/vhost/main.c b/examples/vhost/main.c
> > index 33d023aa39..44073499bc 100644
> > --- a/examples/vhost/main.c
> > +++ b/examples/vhost/main.c
> > @@ -24,8 +24,9 @@
> >
Acked by: Selwin Sebastian
-Original Message-
From: Namburu, Chandu-babu
Sent: Monday, January 10, 2022 12:08 PM
To: dev@dpdk.org; david.march...@redhat.com; ferruh.yi...@intel.com
Cc: Sebastian, Selwin ; arsalan_a...@mentor.com;
sta...@dpdk.org
Subject: RE: [PATCH v2] net/axgbe: use P
All the RSS rules should be cleared before creating default
RSS rules for VF, otherwise duplicated rules will cause error.
Fixes: 5ea614254332("net/iavf: fix VF reset for RSS")
Cc: sta...@dpdk.org
Signed-off-by: Wenjun Wu
---
This is a DPDK 20.11 only patch, since the deployment has been impleme
As per design document, RTE_ARCH is the name of the architecture.
However, the definition was missing on Arm with meson build.
It impacts applications that refers to this string.
Added for Arm builds.
Fixes: b1d48c41189a ("build: support ARM with meson")
Cc: sta...@dpdk.org
Signed-off-by: Ruifen
20 matches
Mail list logo
