From: Dana Vardi
This patch fix wrong clear memory session pointer.
When call mrvl_crypto_pmd_sym_session_clear function,
it might cause the following error:
CRYPTODEV: set_sym_session_private_data() line 497:
Set private data for driver 1 not allowed
This fix set zeroes to mrvl_crypto_session
From: Michael Shamis
Increased AAD max size up to 64B and allowed AAD increment step
1B according to EIP197 token HW limitation.
In addition, some capabilities were found incorrect due to
running FIPS tests. The patch fix the capabilities.
Fixes: 8a61c83af2f ("crypto/mrvl: add mrvl crypto driver
From: Dana Vardi
For AEAD session and AES-GCM mode, IV offset will
set to include the Nonce.
In addition, the following operations order will define:
first encryption and then authentication.
Fixes: 8a61c83af2fa ("crypto/mrvl: add mrvl crypto driver")
Cc: sta...@dpdk.org
Signed-off-by: Dana Var
From: Michael Shamis
This patch provides the support for IPSec protocol
offload to the hardware.
Following security operations are added:
- session_create
- session_destroy
- capabilities_get
Signed-off-by: Michael Shamis
Reviewed-by: Liron Himi
Tested-by: Liron Himi
---
drivers/crypto/mvsam
> -Original Message-
> From: Yigit, Ferruh
> Sent: Tuesday, June 29, 2021 9:35 AM
> To: w...@dpdk.org
> Cc: dev@dpdk.org; Thomas Monjalon ; Mcnamara, John
> ; Dmitry Kozlyuk
> Subject: [PATCH v2] add testing requirement for new PMDs
>
> As discussed in the technical board meeting
> https
> -Original Message-
> From: David Marchand
> Sent: Wednesday, June 30, 2021 4:34 PM
> To: Burakov, Anatoly
> Cc: Lin, Xueqin ; Jerin Jacob ;
> Peng, ZhihongX ; Ananyev, Konstantin
> ; Stephen Hemminger
> ; dpdk-dev
> Subject: Re: [dpdk-dev] [RFC v2] porting AddressSanitizer feature to D
On Tue, Jun 15, 2021 at 12:54 AM wrote:
>
> From: Pavan Nikhilesh
>
> Shift is used to generate an 8-bit saturate value from the current
> aura used count. The shift value should be derived from the log2 of
> block count if it is greater than 256 else the shift should be 0.
>
> Fixes: 7bcc47cbe2f
The mlx5_mprq_alloc_mp function makes shifting to the numeric constant
1, for sending it as a parameter to rte_mempool_create function.
The rte_mempool_create function expects to get void pointer (uintptr_t,
might be 64-bit) and instead gets a 32-bit variable, because the
numeric constant size is
The mlx5_vdpa_event_qp_create function makes shifting to the numeric
constant 1, then multiplies it by another constant and finally assigns
it into a uint64_t variable.
The numeric constant type is an int with a 32-bit sign. if after
shifting , its MSB (bit of sign) will change, the uint64 variabl
The mlx5_compress_qp_setup function makes shifting to the numeric
constant 1, then sends it as a parameter to rte_calloc function.
The rte_calloc function expects to get size_t (might be 64 bit) and
instead gets a 32-bit variable, because the numeric constant size is a
32-bit.
In case the shift is
The constant representing the size of the metadata is defined as a
unsigned int variable with 32-bit.
Similarly the constant representing the maximal output is also defined
as a unsigned int variable with 32-bit.
There is potentially overflowing expression when those constants are
evaluated using
From: Pavan Nikhilesh
Add option to configure unique mempool for each ethernet device
port. Can be used with `pipeline_atq` and `pipeline_queue` tests.
Signed-off-by: Pavan Nikhilesh
---
v2 Changes:
- Fix compilation.
- Rebase on next-event.
app/test-eventdev/evt_common.h | 1 +
Currently PMD needs previous layer information in order to set
corresponding match field for MPLSoGRE or MPLSoUDP.
GRE_KEY item is missing as supported previous layer when translate
item MPLS, which causes flow[1] cannot match MPLS over GRE traffic.
According to RFC4023, MPLS over GRE tunnel with
Hi Maxime,
> -Original Message-
> From: Maxime Coquelin
> Sent: Tuesday, June 29, 2021 5:23 PM
> To: Ding, Xuan ; Xia, Chenbo
> Cc: dev@dpdk.org; Hu, Jiayu ; Pai G, Sunil
> ; Richardson, Bruce ; Van
> Haaren, Harry ; Liu, Yong ;
> Jiang, Cheng1
> Subject: Re: [PATCH v3] vhost: enable IO
> -Original Message-
> From: Min Hu (Connor)
> Sent: Wednesday, June 30, 2021 7:22 PM
> To: Yigit, Ferruh ; dev@dpdk.org; Thomas Monjalon
> ; Andrew Rybchenko
>
> Cc: Xing, Beilei ; Matan Azrad
> ; shah...@nvidia.com; viachesl...@nvidia.com
> Subject: Re: Question about 'rxm->hash.rss'
Hi, Slava
在 2021/6/30 19:44, Slava Ovsiienko 写道:
Hi,
-Original Message-
From: Min Hu (Connor)
Sent: Wednesday, June 30, 2021 14:22
To: Ferruh Yigit ; dev@dpdk.org; NBU-Contact-Thomas
Monjalon ; Andrew Rybchenko
Cc: Beilei Xing ; Matan Azrad ;
Shahaf Shuler ; Slava Ovsiienko
Subject:
Hi Jie,
2021-06-23 17:36 (UTC-0700), Jie Zhou:
> From: Jie Zhou
>
> lib/eal alarm APIs rte_eal_alarm_set and rte_eal_alarm_cancel
> on Windows do not check parameters to fail fast for invalid
> parameters, which captured by DPDK UT alarm_autotest.
Please use past tense to describe situation bef
> >
> > > >
> > > > As I mentioned earlier in this thread, GCC supports 2 types of
> > > > atomics. "Use GCC atomic builtins" does not help distinguish
> > > > between them. In "GCC's C11 atomic builtins" - "C11" indicates
> > > > which atomics we are using, "atomic builtins" indicates that we
>
On Wed, Jun 30, 2021 at 08:25:44PM +, Honnappa Nagarahalli wrote:
>
>
> > >
> > > As I mentioned earlier in this thread, GCC supports 2 types of
> > > atomics. "Use GCC atomic builtins" does not help distinguish between
> > > them. In "GCC's C11 atomic builtins" - "C11" indicates which atomic
> >
> > As I mentioned earlier in this thread, GCC supports 2 types of
> > atomics. "Use GCC atomic builtins" does not help distinguish between
> > them. In "GCC's C11 atomic builtins" - "C11" indicates which atomics
> > we are using, "atomic builtins" indicates that we are NOT using APIs
> > fro
On Tue, Jun 29, 2021 at 07:38:05PM +0100, Kinsella, Ray wrote:
>
>
> >> +Promotion to stable
> >> +~~~
> >> +
> >> +Ordinarily APIs marked as ``experimental`` will be promoted to the stable
> >> API
> >> +once a maintainer and/or the original contributor is satisfied that the
>
On Wed, Jun 30, 2021 at 03:14:51PM +, Raslan Darawsheh wrote:
>
> > -Original Message-
> > From: Ajit Khaparde
> > Sent: Wednesday, June 30, 2021 6:12 PM
> > To: Jerin Jacob
> > Cc: Andrew Rybchenko ; Ferruh Yigit
> > ; Ray Kinsella ; Neil Horman
> > ; dpdk-dev ; Andrew
> > Rybchenko
On Wed, Jun 30, 2021 at 07:06:31PM +, Honnappa Nagarahalli wrote:
>
>
> As I mentioned earlier in this thread, GCC supports 2 types of atomics. "Use
> GCC atomic builtins" does not help distinguish between them. In "GCC's C11
> atomic builtins" - "C11" indicates which atomics we are using,
On Wed, Jun 30, 2021 at 8:03 AM Jerin Jacob wrote:
>
> On Wed, Jun 30, 2021 at 7:28 PM Andrew Rybchenko
> wrote:
> >
> > On 6/30/21 12:21 PM, Ferruh Yigit wrote:
> > > Announce adding 'RTE_ETH_' prefix to all public ethdev macros/enums on
> > > v21.11.
> > > Backward compatibility macros will be
> > >
> > > 18/06/2021 01:26, Honnappa Nagarahalli:
> > > > > On Tue, Jun 15, 2021 at 09:54:51PM -0500, Joyce Kong wrote:
> > > > > > Since C11 memory model is adopted in DPDK now[1], use GCC's
> > > > > > atomic builtins in test cases.
> > > > >
> > > > > as previously discussed these atomics ar
On Tue, Jun 29, 2021 at 05:04:55PM +, Honnappa Nagarahalli wrote:
>
> >
> > 18/06/2021 01:26, Honnappa Nagarahalli:
> > > > On Tue, Jun 15, 2021 at 09:54:51PM -0500, Joyce Kong wrote:
> > > > > Since C11 memory model is adopted in DPDK now[1], use GCC's atomic
> > > > > builtins in test cases
Hi Akhil,
I believe the FreeBSD 13 failure appeared because new requirements
were added for drivers/event/octeontx.
The ABI reference was taken at the v21.05 release which was able to
build this driver at the time.
I will try to look for a way to produce a real ABI test.
Thanks,
Brandon
On Wed,
The `doc` target used `echo` as its command.
On Windows, `echo` is always a shell built-in, there is no binary.
Starting from meson 0.58, `run_target()` always searches for command
executable and no longer accepts `echo` as such on Windows.
Replace plain `echo` with a Python one-liner.
Fixes: d02a
Acked-by: Hemant Agrawal
On Tue, Jun 15, 2021 at 4:02 PM wrote:
>
> From: Pavan Nikhilesh
>
> Add option to configure unique mempool for each ethernet device
> port. Can be used with `pipeline_atq` and `pipeline_queue` tests.
>
> Signed-off-by: Pavan Nikhilesh
> ---
> app/test-eventdev/evt_common.h | 1 +
>
Modifies the scheduler tests in the crypto unit test suite
to replace the usage of the word 'slave' with the more
appropriate word 'worker'.
The scheduler test functions were modified as follows:
test_scheduler_attach_slave_op is now called
test_scheduler_attach_worker_op,
test_scheduler_detach_sl
On Mon, Jun 14, 2021 at 3:54 PM Mattias Rönnblom
wrote:
>
> Set the appropriate capability flags for the RX, crypto and timer
> eventdev adapters to use.
>
> Signed-off-by: Mattias Rönnblom
> Tested-by: Heng Wang
Applied to dpdk-next-net-eventdev/for-main. Thanks
> ---
> drivers/event/dsw/ds
> -Original Message-
> From: Ajit Khaparde
> Sent: Wednesday, June 30, 2021 6:12 PM
> To: Jerin Jacob
> Cc: Andrew Rybchenko ; Ferruh Yigit
> ; Ray Kinsella ; Neil Horman
> ; dpdk-dev ; Andrew
> Rybchenko ; NBU-Contact-Thomas Monjalon
> ; David Marchand ;
> Qi Z Zhang ; Raslan Darawsheh
On Wed, Jun 30, 2021 at 7:28 PM Andrew Rybchenko
wrote:
>
> On 6/30/21 12:21 PM, Ferruh Yigit wrote:
> > Announce adding 'RTE_ETH_' prefix to all public ethdev macros/enums on
> > v21.11.
> > Backward compatibility macros will be added on v21.11 and they will be
> > removed on v22.11.
> >
> > Sign
On Fri, Jun 18, 2021 at 12:51 PM Pavan Nikhilesh Bhagavatula
wrote:
>
>
>
> >-Original Message-
> >From: Ruifeng Wang
> >Sent: Thursday, June 10, 2021 12:55 PM
> >To: Pavan Nikhilesh Bhagavatula ; Shijith
> >Thotton
> >Cc: dev@dpdk.org; n...@arm.com; Ruifeng Wang
> >
> >Subject: [EXT] [P
Hi Mohsin,
Hope you are fine!
Please see my comments below.
On Wed, Jun 30, 2021 at 01:04:04PM +0200, Mohsin Kazmi wrote:
> Re: [PATCH v2] net: prepare the outer ipv4 hdr for checksum
I suggest to highlight that it this is the Intel-specific tx-prepare
function in the commit title. What about:
Fixed parameters on autotest functions by removing comments.
Fixes: 202d375c60bc ("app/test: add cryptodev unit and performance tests")
Fixes: 4ed1e79e7819 ("test/crypto: add tests for virtio-crypto")
Fixes: 3aafc423cf4d ("snow3g: add driver for SNOW 3G library")
Fixes: 27a1c4714d54 ("app/test: ad
On 6/30/21 12:21 PM, Ferruh Yigit wrote:
Announce adding 'RTE_ETH_' prefix to all public ethdev macros/enums on
v21.11.
Backward compatibility macros will be added on v21.11 and they will be
removed on v22.11.
Signed-off-by: Ferruh Yigit
---
Cc: Andrew Rybchenko
Cc: Thomas Monjalon
Cc: David
Add a simple unit test for checksum API.
Signed-off-by: Olivier Matz
---
MAINTAINERS | 1 +
app/test/autotest_data.py | 6 +
app/test/meson.build | 2 +
app/test/test_cksum.c | 271 ++
4 files changed, 280 insertions(+)
create mod
Since commit d5df2ae0428a ("net: fix unneeded replacement of TCP
checksum 0"), the functions rte_ipv4_udptcp_cksum() and
rte_ipv6_udptcp_cksum() can return either 0x or 0x when used to
verify a packet containing a valid checksum.
Since these functions should be used to calculate the checks
Since commit d5df2ae0428a ("net: fix unneeded replacement of TCP
checksum 0"), the functions rte_ipv4_udptcp_cksum() or
rte_ipv6_udptcp_cksum() can return either 0x or 0x when used to
verify a packet containing a valid checksum.
This new behavior broke the checksum verification in tap driv
When packet type is IPV4_EXT, the checksum is always marked as good in
the mbuf offload flags.
Since we know the header lengths, we can easily call
rte_ipv4_udptcp_cksum() in this case too.
Fixes: 8ae3023387e9 ("net/tap: add Rx/Tx checksum offload support")
Cc: sta...@dpdk.org
Signed-off-by: Oli
This patchset fixes the Rx checksum flags in net/tap
driver. The first two patches are the effective fixes.
The last 2 patches introduce a new checksum API to
verify a L4 checksum and its unt test, in order to
simplify the net/tap code, or any other code that has
the same needs.
v2:
* clarify wh
The current meson option 'machine' should only specify the ISA, which is
not sufficient for Arm, where setting ISA implies other settings as well
(and is used in Arm configuration as such).
Use the existing 'platform' meson option to differentiate the type of
the build (native/generic) and set ISA
Currently, private_data_offset for the sessionless is computed
wrongly which includes extra bytes added because of using
sizeof(struct rte_crypto_sym_xform) * 2) instead of
(sizeof(union rte_event_crypto_metadata)). Due to this buffer
overflow, the corruption was leading to test application
crash w
As hrxq struct has the indirect table pointer, while matching the
hrxq, better to use the hrxq indirect table instead of searching
from the list.
This commit optimizes the hrxq indirect table matching.
Signed-off-by: Suanming Mou
Acked-by: Matan Azrad
---
drivers/net/mlx5/mlx5_rxq.c | 18 +
This commit supports the list none local core operations with
an extra sub-list.
Signed-off-by: Suanming Mou
Acked-by: Matan Azrad
---
drivers/common/mlx5/mlx5_common_utils.c | 92 +
drivers/common/mlx5/mlx5_common_utils.h | 9 ++-
2 files changed, 71 insertions(+), 30
This commit supports the index pool none local core operations with
an extra cache.
Signed-off-by: Suanming Mou
Acked-by: Matan Azrad
---
drivers/net/mlx5/mlx5_utils.c | 75 +--
drivers/net/mlx5/mlx5_utils.h | 3 +-
2 files changed, 56 insertions(+), 22 deletion
This commit changes the index pool memory release configuration
to 0 when memory reclaim mode is not required.
Signed-off-by: Suanming Mou
Acked-by: Matan Azrad
---
drivers/net/mlx5/mlx5.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/net/mlx5/mlx5.c b/drivers/net/mlx5/mlx5.c
in
Currently, hash list uses the cache list as bucket list. The list
in the buckets have the same name, ctx and callbacks. This wastes
the memory.
This commit abstracts all the name, ctx and callback members in the
list to a constant struct and others to the inconstant struct, uses
the wrapper functi
Currently, all the hash list tables are allocated during start up.
Since different applications may only use dedicated limited actions,
optimized the hash list table allocate on demand will save initial
memory.
This commit optimizes hash list table allocate on demand.
Signed-off-by: Suanming Mou
This commit enables the tag and header modify action index pool
per-core cache in non-reclaim memory mode.
Signed-off-by: Suanming Mou
Acked-by: Matan Azrad
---
drivers/net/mlx5/mlx5.c | 4 +++-
drivers/net/mlx5/mlx5.h | 1 +
drivers/net/mlx5/mlx5_flow_dv.c | 3 ++-
3 files chan
Currently, the list's local cache instance memory is allocated with
the list. As the local cache instance array size is RTE_MAX_LCORE,
most of the cases the system will only have very limited cores.
allocate the instance memory individually per core will be more
economic to the memory.
This commit
With the new per core optimization to the list, the hash bucket size
can be tuned to a more accurate number.
This commit adjusts the hash bucket size.
Signed-off-by: Suanming Mou
---
drivers/net/mlx5/linux/mlx5_os.c | 2 +-
drivers/net/mlx5/mlx5.c | 2 +-
drivers/net/mlx5/mlx5_defs.h
From: Matan Azrad
Using the mlx5 list utility object in the hlist buckets.
This patch moves the list utility object to the common utility, creates
all the clone operations for all the hlist instances in the driver.
Also adjust all the utility callbacks to be generic for both list and
hlist.
Si
From: Matan Azrad
Modify header actions are allocated by mlx5_malloc which has a big
overhead of memory and allocation time.
One of the action types under the modify header object is SET_TAG,
The SET_TAG action is commonly not reused by the flows and each flow has
its own value.
Hence, the mlx
From: Matan Azrad
Currently, the list memory was allocated by the list API caller.
Move it to be allocated by the create API in order to save consistence
with the hlist utility.
Signed-off-by: Matan Azrad
Acked-by: Suanming Mou
---
drivers/net/mlx5/linux/mlx5_os.c | 105 +++
From: Matan Azrad
The atomic operation in the list utility no need a barriers because the
critical part are managed by RW lock.
Relax them.
Signed-off-by: Matan Azrad
Acked-by: Suanming Mou
---
drivers/net/mlx5/mlx5_utils.c | 12 ++--
1 file changed, 6 insertions(+), 6 deletions(-)
From: Matan Azrad
When a cache entry is allocated by lcore A and is released by lcore B,
the driver should synchronize the cache list access of lcore A.
The design decision is to manage a counter per lcore cache that will be
increased atomically when the non-original lcore decreases the referenc
From: Matan Azrad
The mlx5 internal list utility is thread safe.
In order to synchronize list access between the threads, a RW lock is
taken for the critical sections.
The create\remove\clone\clone_free operations are in the critical
sections.
These operations are heavy and make the critical s
From: Matan Azrad
When mlx5 list object is accessed by multiple cores, the list lock
counter is all the time written by all the cores what increases cache
misses in the memory caches.
In addition, when one thread accesses the list for add\remove\lookup
operation, all the other threads coming to
From: Matan Azrad
The internal mlx5 list tool is used mainly when the list objects need to
be synchronized between multiple threads.
The "cache" term is used in the internal mlx5 list API.
Next enhancements on this tool will use the "cache" term for per thread
cache management.
To prevent conf
The flow list is used to save the create flows and to be used only
when port closes all the flows need to be flushed.
This commit takes advantage of the index pool foreach operation to
flush all the allocated flows.
Signed-off-by: Suanming Mou
Acked-by: Matan Azrad
---
drivers/net/mlx5/linux/m
From: Matan Azrad
Define the types of the modify header action fields to be with the
minimum size needed for the optional values range.
Signed-off-by: Matan Azrad
Acked-by: Suanming Mou
---
drivers/common/mlx5/linux/mlx5_glue.h | 1 +
drivers/net/mlx5/linux/mlx5_flow_os.h | 3 ++-
drivers/n
In some cases, application may want to know all the allocated
index in order to apply some operations to the allocated index.
This commit adds the indexed pool functions to support foreach
operation.
Signed-off-by: Suanming Mou
Acked-by: Matan Azrad
---
drivers/net/mlx5/mlx5_utils.c | 86 +
For object which wants efficient index allocate and free, local
cache will be very helpful.
Two level cache is introduced to allocate and free the index more
efficient. One as local and the other as global. The global cache
is able to save all the allocated index. That means all the allocated
inde
Some ipool instances in the driver are used as ID\index allocator and
added other logic in order to work with limited index values.
Add a new configuration for ipool specify the maximum index value.
The ipool will ensure that no index bigger than the maximum value is
provided.
Use this configurat
This patch series optimize the flow insertion rate with adding
local cache to index pool and list.
For object which wants efficient index allocate and free, local
cache will be very helpful.
For index pool, two level cache is added, one as local and another
as global. The global cache is able to
On 12/10/2020 11:15 PM, dheemanth wrote:
> In order to improve performance, the KNI is made to
> support multiple fifos, So that multiple threads pinned
> to multiple cores can process packets in parallel.
>
Hi Dheemanth,
As far as I know, in KNI the bottle neck is in the kernel thread. In this
Hi Akhil,
This is a required feature from our customer. So could you help us merging it?
And we do not plan to remove this PMD - just put it to a new folder with common
code shared for all SW Intel-ipsec-mb based PMDs.
>From the user point of view everything will be the same including the EAL
> -Original Message-
> From: stable On Behalf Of Xueming Li
> Sent: Sunday, June 13, 2021 8:52 PM
> Cc: dev@dpdk.org; xuemi...@nvidia.com; ma...@nvidia.com; sta...@dpdk.org;
> Viacheslav Ovsiienko ; Maxime Coquelin
>
> Subject: [dpdk-stable] [PATCH] vdpa/mlx5: fix TSO offload without CSUM
> -Original Message-
> From: Maxime Coquelin
> Sent: Wednesday, June 30, 2021 12:11 AM
> To: dev@dpdk.org; Xia, Chenbo ;
> david.march...@redhat.com
> Cc: Maxime Coquelin
> Subject: [PATCH v7 0/7] vhost: Fix and improve NUMA reallocation
>
> This patch series first fixes missing realloca
Hi,
> -Original Message-
> From: Min Hu (Connor)
> Sent: Wednesday, June 30, 2021 14:22
> To: Ferruh Yigit ; dev@dpdk.org; NBU-Contact-Thomas
> Monjalon ; Andrew Rybchenko
>
> Cc: Beilei Xing ; Matan Azrad ;
> Shahaf Shuler ; Slava Ovsiienko
>
> Subject: Re: Question about 'rxm->hash.rs
Hi, Beilei, Matan, Shahaf, Viacheslav,
how about your opinion?
在 2021/6/30 17:34, Ferruh Yigit 写道:
On 6/30/2021 3:45 AM, Min Hu (Connor) wrote:
Hi, all
one question about 'rxm->hash.rss' and 'mb->hash.fdir'.
In Rx recv packets function,
'rxm->hash.rss' will report rss h
Proposing following two new fields for IPsec inner checksum
configuration in the structure ``rte_security_ipsec_sa_options``.
uint32_t ip_csum_enable : 1;
uint32_t l4_csum_enable : 1;
With these config options, per SA, application can specify if
the inner checksum(compute/verify) to be offloaded t
On 6/30/21 9:55 AM, David Marchand wrote:
> On Tue, Jun 29, 2021 at 6:11 PM Maxime Coquelin
> wrote:
>>
>> Inflight metadata are allocated using glibc's calloc.
>> This patch converts them to rte_zmalloc_socket to take
>> care of the NUMA affinity.
>
> About the title, maybe:
> vhost: use DPDK
Add inner packet IPv4 hdr and L4 checksum enable options
in conf. These will be used in case of protocol offload.
Per SA, application could specify whether the
checksum(compute/verify) can be offloaded to security device.
Signed-off-by: Archana Muniganti
---
lib/cryptodev/rte_crypto.h| 9 ++
Preparation the headers for the hardware offload
misses the outer ipv4 checksum offload.
It results in bad checksum computed by hardware NIC.
This patch fixes the issue by setting the outer ipv4
checksum field to 0.
Fixes: 4fb7e803eb1a ("ethdev: add Tx preparation")
Cc: sta...@dpdk.org
Signed-of
> Currently, there is a hard limitation on the PMD power management
> support that only allows it to support a single queue per lcore. This is
> not ideal as most DPDK use cases will poll multiple queues per core.
>
> The PMD power management mechanism relies on ethdev Rx callbacks, so it
> i
All,
Testing with dpdk v20.11.2-rc2 from Intel looks good, no critical issue is
found. All of them are known issues.
Below two issues has been fixed in 20.11.2-rc2:
1) Fedora34 GCC11 and Clang12 build failed.
2) dcf_lifecycle/handle_acl_filter_05: after reset port the mac changed.
# Basic Int
> Use the new multi-monitor intrinsic to allow monitoring multiple ethdev
> Rx queues while entering the energy efficient power state. The multi
> version will be used unconditionally if supported, and the UMWAIT one
> will only be used when multi-monitor is not supported by the hardware.
>
> S
CC Tianfei, who is maintainer.
> -Original Message-
> From: Hussin, Mohamad Noor Alim
> Sent: Wednesday, June 30, 2021 17:26
> To: Xu, Rosen
> Cc: dev@dpdk.org; Hussin, Mohamad Noor Alim
> ; Huang, Wei
> ; sta...@dpdk.org
> Subject: [PATCH v2] ifpga/base/meson: fix looking for librt
>
>
Hi Anatoly,
On 29/6/2021 4:48 PM, Anatoly Burakov wrote:
Currently, there is a hard limitation on the PMD power management
support that only allows it to support a single queue per lcore. This is
not ideal as most DPDK use cases will poll multiple queues per core.
The PMD power management mecha
On 6/30/2021 3:45 AM, Min Hu (Connor) wrote:
> Hi, all
> one question about 'rxm->hash.rss' and 'mb->hash.fdir'.
>
> In Rx recv packets function,
> 'rxm->hash.rss' will report rss hash result from Rx desc.
> 'rxm->hash.fdir' will report filter identifier from Rx desc.
>
> But
Announce adding 'RTE_ETH_' prefix to all public ethdev macros/enums on
v21.11.
Backward compatibility macros will be added on v21.11 and they will be
removed on v22.11.
Signed-off-by: Ferruh Yigit
---
Cc: Andrew Rybchenko
Cc: Thomas Monjalon
Cc: David Marchand
Cc: Qi Z Zhang
Cc: Raslan Daraws
On 6/30/2021 7:29 AM, David Marchand wrote:
> Hello Ferruh,
>
> On Tue, Jun 29, 2021 at 3:46 PM Ferruh Yigit wrote:
>>
>> Add 'RTE_ETH' namespace to all enums & macros in a backward compatible
>> way. The macros for backward compatibility can be removed in next LTS.
>>
>> Signed-off-by: Ferruh Yi
> Added support for crypto adapter OP_FORWARD mode.
>
> As OcteonTx CPT crypto completions could be out of order, each crypto op
> is enqueued to CPT, dequeued from CPT and enqueued to SSO one-by-one.
>
> Signed-off-by: Shijith Thotton
> ---
This patch shows a CI warning for FreeBSD, but was not
Hi Maxime,
> -Original Message-
> From: Maxime Coquelin
> Sent: Tuesday, June 29, 2021 10:39 PM
> To: Xia, Chenbo ; dev@dpdk.org;
> david.march...@redhat.com
> Subject: Re: [PATCH v6 3/7] vhost: fix missing cache logging NUMA realloc
>
>
>
> On 6/25/21 4:50 AM, Xia, Chenbo wrote:
> > H
Hi,
> -Original Message-
> From: Slava Ovsiienko
> Sent: Sunday, June 20, 2021 9:30 AM
> To: dev@dpdk.org
> Cc: Raslan Darawsheh ; Matan Azrad
> ; sta...@dpdk.org
> Subject: [PATCH] net/mlx5: fix TSO multi-segment inline length
>
> The inline data length for TSO ethernet segment should b
On Mon, Jun 28, 2021 at 4:22 PM Burakov, Anatoly
wrote:
>
> On 18-Jun-21 10:04 AM, David Marchand wrote:
> > On Fri, Jun 18, 2021 at 9:49 AM Lin, Xueqin wrote:
> Suggest listing demo code and tool capture information for user to try if
> >>> tool works, also add this part into doc.
>
>
> -Original Message-
> From: Burakov, Anatoly
> Sent: Monday, June 28, 2021 10:22 PM
> To: David Marchand ; Lin, Xueqin
>
> Cc: Jerin Jacob ; Peng, ZhihongX
> ; Ananyev, Konstantin
> ; Stephen Hemminger
> ; dpdk-dev
> Subject: Re: [dpdk-dev] [RFC v2] porting AddressSanitizer feature to D
On Tue, Jun 29, 2021 at 6:11 PM Maxime Coquelin
wrote:
>
> This patch series first fixes missing reallocations of some
> Virtqueue and device metadata.
>
> Then, it improves the numa_realloc function by using
> rte_realloc_socket API that takes care of the memcpy &
> freeing. The VQs NUMA IDs are
On Tue, Jun 29, 2021 at 6:11 PM Maxime Coquelin
wrote:
>
> Inflight metadata are allocated using glibc's calloc.
> This patch converts them to rte_zmalloc_socket to take
> care of the NUMA affinity.
About the title, maybe:
vhost: use DPDK allocations for inflight data
>
> Signed-off-by: Maxime C
On 6/30/21 9:24 AM, David Marchand wrote:
> On Tue, Jun 29, 2021 at 6:11 PM Maxime Coquelin
> wrote:
>>
>> Since the Vhost-user device initialization has been reworked,
>> enabling the application to start using the device as soon as
>> the first queue pair is ready, NUMA reallocation no more
>
Hi,
> -Original Message-
> From: Slava Ovsiienko
> Sent: Tuesday, June 22, 2021 7:41 PM
> To: dev@dpdk.org
> Cc: Raslan Darawsheh ; Matan Azrad
> ; Ali Alnubani ; sta...@dpdk.org
> Subject: [PATCH] net/mlx5: fix multi-segment inline for the first segment
>
> If the first segment in the m
Hi,
> -Original Message-
> From: Jiawei(Jonny) Wang
> Sent: Tuesday, June 29, 2021 10:00 AM
> To: Slava Ovsiienko ; Matan Azrad
> ; Ori Kam ; NBU-Contact-Thomas
> Monjalon ; Shahaf Shuler ;
> Xueming(Steven) Li
> Cc: dev@dpdk.org; Raslan Darawsheh ;
> sta...@dpdk.org
> Subject: [PATCH] n
Hi,
> -Original Message-
> From: Michael Baum
> Sent: Monday, June 28, 2021 6:06 PM
> To: dev@dpdk.org
> Cc: Matan Azrad ; Raslan Darawsheh
> ; Slava Ovsiienko ;
> sta...@dpdk.org
> Subject: [PATCH] common/mlx5: share memory free callback
>
> All the mlx5 drivers using MRs for data-path
Hi,
> -Original Message-
> From: Jiawei(Jonny) Wang
> Sent: Monday, June 28, 2021 1:58 PM
> To: Slava Ovsiienko ; Matan Azrad
> ; Ori Kam ; NBU-Contact-Thomas
> Monjalon ; Shahaf Shuler ;
> Alexander Kozyrev
> Cc: dev@dpdk.org; Raslan Darawsheh ;
> sta...@dpdk.org
> Subject: [PATCH] net/
This patch is to add vhost async dequeue data-path in vhost sample.
vswitch can leverage IOAT to accelerate vhost async dequeue data-path.
Signed-off-by: Wenwu Ma
---
doc/guides/sample_app_ug/vhost.rst | 9 +-
examples/vhost/ioat.c | 61 ++---
examples/vhost/ioat.h
From: Yuan Wang
This patch implements asynchronous dequeue data path for split ring.
A new asynchronous dequeue function is introduced. With this function,
the application can try to receive packets from the guest with
offloading large copies to the DMA engine, thus saving precious CPU
cycles.
S
1 - 100 of 111 matches
Mail list logo
