This release contains changes listed below.
- Fast mbuf free feature support.
- Device argument to disable the LLQ.
- Simplification of the MTU verification.
Signed-off-by: Michal Krawczyk
---
drivers/net/ena/ena_ethdev.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a
> > From: Nipun Gupta
> >
> > Update and add maintainers for NXP devices and RAW device API
> >
> > Signed-off-by: Nipun Gupta
> Acked-by: Hemant Agrawal
Applied
07/06/2022 18:18, Veerasenareddy Burru:
> From: Thomas Monjalon
> > 07/06/2022 16:38, Ray Kinsella:
> > > Sathesh B Edara writes:
> > >
> > > > This patch renames octeon end point driver from octeontx_ep to
> > > > octeon_ep
> > > >
> > > > Signed-off-by: Sathesh B Edara
> > >
> > > Straight for
04/06/2022 18:31, Tomasz Duszynski:
> Allow building generic arm64 target using config/arm/arm64_armv8_linux_*
> config which works on both cn9k and cn10k by relaxing cache line size
> requirements a bit.
>
> While at it move cache line checks to common place.
>
> Signed-off-by: Tomasz Duszynski
Ths is early proposal on how to address some of the gcc-12
warnings. Most of these are related to rte_memcpy which can
simply be addressed by using regular memcpy instead.
Stephen Hemminger (8):
net/ena: fix warnings related to rte_memcpy and gcc-12
net/qede: fix gcc-12 rte_memcpy warnings
n
Rte_memcpy is not needed for small objects only used on control
path. Regular memcpy is as fast or faster and there is more
robust since static analysis etc knows what it does.
In this driver it was redefining all memcpy as rte_memcpy
which is even worse.
Signed-off-by: Stephen Hemminger
---
dr
The x86 version of rte_memcpy can cause warnings. The driver does
not need to use rte_memcpy for everything. Standard memcpy is
just as fast and safer; the compiler and static analysis tools
treat memcpy specially.
Signed-off-by: Stephen Hemminger
---
drivers/net/qede/base/bcm_osal.h | 3 +--
d
Using rte_memcpy is not necessary here. It also causes warnings
from derefencing past end of input.
Signed-off-by: Stephen Hemminger
---
app/test/test_ipfrag.c | 13 ++---
1 file changed, 6 insertions(+), 7 deletions(-)
diff --git a/app/test/test_ipfrag.c b/app/test/test_ipfrag.c
index
It is not necessary to use rte_memcpy here, and it can cause
warnings when gcc-12 detects that rte_memcpy will derference past
input data.
Signed-off-by: Stephen Hemminger
---
app/test/test_ipsec.c | 13 ++---
1 file changed, 6 insertions(+), 7 deletions(-)
diff --git a/app/test/test_ip
There is no good reason to always use rte_memcpy.
Regular memcpy is as fast or faster for small values and safer
since it won't reference past end of input. Also static analysis
tools know about regular memcpy and can analyze better.
Signed-off-by: Stephen Hemminger
---
drivers/net/ice/base/ice_
With gcc-12 it detects that this function could be passed a
queue > 1 which would cause out of bounds access.
Signed-off-by: Stephen Hemminger
---
drivers/net/enetfec/enet_ethdev.c | 5 +
1 file changed, 5 insertions(+)
diff --git a/drivers/net/enetfec/enet_ethdev.c
b/drivers/net/enetfec/e
Using rte_memcpy is not needed here. Just use memcpy() which
is safer and just as fast for this non-critical place.
Signed-off-by: Stephen Hemminger
---
lib/vhost/vhost_crypto.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/lib/vhost/vhost_crypto.c b/lib/vhost/vhost_crypto.
The function rte_memcpy can derference past source buffer which
will cause array out of bounds warnings. But there is no good reason
to use rte_memcpy instead of memcpy in this code. Memcpy is just
as fast for these small inputs, and compiler will optimize.
Signed-off-by: Stephen Hemminger
---
l
21/05/2022 09:05, Min Hu (Connor):
> From: Huisong Li
>
> After the driver probe is executed, the callback in application will
> be called. The callback in application may call some APIs which access the
What is the "callback in application" ?
Do you mean the callback on probing event like RTE_E
On 6/7/2022 5:43 PM, Michal Krawczyk wrote:
Hi,
this patchset contains 1 generic feature support (fast mbuf free), one
improvement (simplification of the MTU verification), and 1 new device
argument which enhances the ENA user's experience by allowing them to
disable the LLQ (Low Latency Queue)
MCS lock, PF lock and Ticket lock have no arch specific implementation,
there is no need for the extra redirection in headers.
Signed-off-by: David Marchand
---
Note: this was mentionned during the seqlock patch review, and I spotted
it again, while reviewing the RISC-V port, and I see the same f
On Tue, 7 Jun 2022 21:03:08 +0200
David Marchand wrote:
> MCS lock, PF lock and Ticket lock have no arch specific implementation,
> there is no need for the extra redirection in headers.
>
> Signed-off-by: David Marchand
> ---
> Note: this was mentionned during the seqlock patch review, and I
DDM -> Downstream Data Mover
MPU -> Mbuf Prefetch Unit
UDM -> Upstream Data Mover
Signed-off-by: Ed Czeck
---
devtools/words-case.txt | 3 +++
1 file changed, 3 insertions(+)
diff --git a/devtools/words-case.txt b/devtools/words-case.txt
index 2f1753bdc8..53e029a958 100644
--- a/devtools/words-
new firmware version for MPU (Mbuf Prefetch Unit)
remove device-level global operations
remove ark_mpu_reset_stats function
Signed-off-by: Ed Czeck
---
v2:
- document version compatibility between firmware and DPDK
- reword commit message
v4:
- clarify version compatibility note
- firmware chang
new firmware version for DDM (Downstream Data Mover)
remove device-level start, stop, and reset operations
add queue-based start, stop and reset as required by firmware
Signed-off-by: Ed Czeck
---
v2:
reword commit message
---
drivers/net/ark/ark_ddm.c | 80 +-
new firmware version for UDM (Upstream Data Mover)
remove device-level start, stop, and reset operations
add queue-based start, stop and reset as required by firmware
remove performance structs as they are not in the firmware module
Signed-off-by: Ed Czeck
---
v2: reword commit message
v3: inclu
detect and report completion errors from firmware
Signed-off-by: Ed Czeck
---
drivers/net/ark/ark_rqp.c | 6 --
drivers/net/ark/ark_rqp.h | 3 ++-
2 files changed, 6 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ark/ark_rqp.c b/drivers/net/ark/ark_rqp.c
index ef9ccd0706..efb9730fe6
update device list is doc
Signed-off-by: Ed Czeck
---
v3: clarification in doc for LTS support
v4: mention nee devices in release notes
---
doc/guides/nics/ark.rst| 4 +++-
doc/guides/rel_notes/release_22_07.rst | 2 ++
drivers/net/ark/ark_ethdev.c | 6 ++
3 files
Add capabilities field isvf to dev struct
Disable configuration calls as required by vf
Signed-off-by: Ed Czeck
---
v2: feature Arkville vf support in release notes
v3: feature new PCI device ids in release notes
v4: split release note
---
doc/guides/rel_notes/release_22_07.rst | 2 +
drivers/
Dmitry Kozlyuk (4):
usertools: add option to select hugetlbfs directory
usertools: add option to change mount point owner
doc: give specific instructions for running as non-root
doc: update instructions for running as non-root for MLX5
doc/guides/linux_gsg/enable_func.rst | 53 ++
dpdk-hugepages.py had /dev/hugepages hardcoded as the mount point.
It may be desirable to setup hugepage directory at another path,
for example, when using hugepages of multiple sizes in different
directories or when granting different permissions to mount points.
Add --directory/-d option to the s
Per mount(8), the previous owner and mode of the mount point
become invisible as long as this filesystem remains mounted.
Because dpdk-hugepages.py must be run as root,
the new owner would be root.
This is undesirable if the hugepage directory is being set up
by the administrator for an unprivilege
Reference the common guide for generic setup.
Remove excessive capabilities from the recommended list.
Cc: sta...@dpdk.org
Signed-off-by: Dmitry Kozlyuk
---
doc/guides/platform/mlx5.rst | 22 ++
1 file changed, 10 insertions(+), 12 deletions(-)
diff --git a/doc/guides/platf
The guide to run DPDK applications as non-root in Linux
did not provide specific instructions to configure the required access
and did not explain why each bit is needed.
The latter is important because running as non-root
is one of the ways to tighten security and grant minimal permissions.
Cc: s
On Wed, 8 Jun 2022 02:49:47 +0300
Dmitry Kozlyuk wrote:
>
> -def mount_huge(pagesize, mountpoint):
> +def mount_huge(pagesize, mountpoint, owner):
> '''Mount the huge TLB file system'''
> if mountpoint in get_mountpoints():
> print(mountpoint, "already mounted")
> @@ -180,6 +
On Wed, 8 Jun 2022 02:49:48 +0300
Dmitry Kozlyuk wrote:
> The guide to run DPDK applications as non-root in Linux
> did not provide specific instructions to configure the required access
> and did not explain why each bit is needed.
> The latter is important because running as non-root
> is one o
On Wed, 8 Jun 2022 02:49:49 +0300
Dmitry Kozlyuk wrote:
> Reference the common guide for generic setup.
> Remove excessive capabilities from the recommended list.
>
> Cc: sta...@dpdk.org
>
> Signed-off-by: Dmitry Kozlyuk
> ---
> doc/guides/platform/mlx5.rst | 22 ++
> 1 fi
From: Peng Zhang
The origin design is if error happen during the step 3 of given situation,
it will return error directly without retry. While in current patch, it
will retry at every interval time during certain time. If retry succeed,
rule can be continuously created.
The given situation as
In multi-cores cases for Rx timestamp offload, to avoid phc time being
frequently overwritten, move related variables from ice_adapter to
ice_rx_queue structure, and each queue will handle timestamp calculation
by itself.
Fixes: 953e74e6b73a ("net/ice: enable Rx timestamp on flex descriptor")
Fixe
https://bugs.dpdk.org/show_bug.cgi?id=1028
Bug ID: 1028
Summary: [dpdk-22.07] dynamic_queue/txq_setup: after set “port
0 txq 1 stop”, this stopped queue not display
transmits 255 packets
Product: DPDK
Version: uns
Hi Thomas,
> -Original Message-
> From: Thomas Monjalon
> Sent: 2022年6月7日 18:53
> To: Wu, WenxuanX
> Cc: Richardson, Bruce ; dev@dpdk.org;
> sta...@dpdk.org; david.march...@redhat.com
> Subject: Re: [PATCH] build: fix meson build when gcc >= 10.0
>
> 07/06/2022 04:56, wenxuanx...@intel.
Hi Ganapati,
Some comments inline.
> -Original Message-
> From: Ganapati Kundapura
> Sent: Tuesday, June 7, 2022 8:43 PM
> To: jerinjac...@gmail.com; dev@dpdk.org; Jayatheerthan, Jay
>
> Subject: [PATCH v4] eventdev: add adapter instance get API
>
> Added rte_event_eth_rx_adapter_ins
https://bugs.dpdk.org/show_bug.cgi?id=1009
gaodaxue (daxuex@intel.com) changed:
What|Removed |Added
Resolution|--- |FIXED
Status|UNCONF
101 - 138 of 138 matches
Mail list logo
