On Wed, Aug 16, 2023 at 9:26 PM David Marchand
wrote:
>
> On Wed, Aug 16, 2023 at 8:30 PM Patrick Robb wrote:
> > On Wed, Aug 16, 2023 at 10:40 AM David Marchand
> > wrote:
> >>
> >> Patrick, Bruce,
> >>
> >> If it was reported, I either missed it or forgot about it, sorry.
> >> Can you (re)sha
> From: Tyler Retzlaff [mailto:roret...@linux.microsoft.com]
> Sent: Thursday, 17 August 2023 21.14
>
> On Thu, Aug 17, 2023 at 01:57:01PM +0200, Morten Brørup wrote:
> > > From: Tyler Retzlaff [mailto:roret...@linux.microsoft.com]
> > > Sent: Wednesday, 16 August 2023 23.39
> > >
> > > Refrain fr
Any news on that ? Thanks
Julien
On Thu, Aug 10, 2023 at 6:09 PM jhascoet wrote:
> From: Julien Hascoet
>
> In case of ring full state, we retry the enqueue
> operation in order to avoid mbuf loss.
>
> Fixes: af75078fece ("first public release")
>
> Signed-off-by: Julien Hascoet
> ---
> app/
On Mon, Jul 24, 2023 at 1:39 PM Amit Prakash Shukla
wrote:
>
> Introduce event DMA adapter APIs. This patch provides information
> on adapter modes and usage. Application can use this event adapter
> interface to transfer packets between DMA device and event device.
>
> Signed-off-by: Amit Prakash
Hi Anatoly,
Marvell CNXK DMA hardware also supports this feature, and it would be a good
feature to add. Thanks for introducing the feature. Please see inline.
Thanks,
Anoob
> -Original Message-
> From: Anatoly Burakov
> Sent: Friday, August 11, 2023 9:45 PM
> To: dev@dpdk.org; Chengwe
roc_dpi was using vfid as part of name for memzone allocation.
This led to memzone allocation failure in case of multiple
physical functions. vfid is not unique by itself since multiple
physical functions can have the same virtual function indices.
So use complete DBDF as part of memzone name to ma
Dmadev driver changes to align with dpdk spec.
Fixes: 681851b347ad ("dma/cnxk: support CN10K DMA engine")
Cc: sta...@dpdk.org
Signed-off-by: Amit Prakash Shukla
---
v2:
- Fix for bugs observed in v1.
- Squashed few commits.
v3:
- Resolved review suggestions.
- Code improvement.
drivers/dma/cn
Valid function pointers are set for DMA device operations
i.e. cn10k_dmadev_ops are used for all cn10k devices.
Signed-off-by: Radha Mohan Chintakuntla
---
v2:
- Fix for bugs observed in v1.
- Squashed few commits.
v3:
- Resolved review suggestions.
- Code improvement.
drivers/dma/cnxk/cnxk_dm
Use pfid and vfid of src_port for incoming DMA transfers and dst_port
for outgoing DMA transfers.
Signed-off-by: Radha Mohan Chintakuntla
Signed-off-by: Amit Prakash Shukla
---
v2:
- Fix for bugs observed in v1.
- Squashed few commits.
v3:
- Resolved review suggestions.
- Code improvement.
dr
To support multiple directions in same queue make use of multiple vchan
per queue. Each vchan can be configured in some direction and used.
Signed-off-by: Amit Prakash Shukla
Signed-off-by: Radha Mohan Chintakuntla
---
v2:
- Fix for bugs observed in v1.
- Squashed few commits.
v3:
- Resolved re
Code changes to realign dpi private structure based on vchan.
Changeset also resets DMA dev stats while starting dma device.
Signed-off-by: Amit Prakash Shukla
---
v2:
- Fix for bugs observed in v1.
- Squashed few commits.
v3:
- Resolved review suggestions.
- Code improvement.
drivers/dma/cnxk
From: Vamsi Attunuru
Adds a check to avoid tail wrap when completion desc ring
is full. Also patch increase max desc size to 2048.
Signed-off-by: Vamsi Attunuru
---
v2:
- Fix for bugs observed in v1.
- Squashed few commits.
v3:
- Resolved review suggestions.
- Code improvement.
drivers/dma/c
From: Vamsi Attunuru
last index value might lost the order when dma stats are reset
in between copy operations. Patch adds a variable to track the
completed count, that can be used to compute the last index, also
patch adds misc other fixes.
Signed-off-by: Vamsi Attunuru
---
v2:
- Fix for bugs
The only presence of RTE_MBUF_F_TX_IPV4 can't be used as an indicator
that a checksum offload has been requested by an application.
Check that RTE_MBUF_F_TX_IP_CKSUM or others flags have been set.
Fixes: 1e728b01120c ("net/iavf: rework Tx path")
Cc: sta...@dpdk.org
Signed-off-by: David Marchand
>
> On 2023/8/17 22:06, Stephen Hemminger wrote:
> > On Thu, 17 Aug 2023 05:06:20 +
> > Honnappa Nagarahalli wrote:
> >
> >> Hi Matan, Viacheslav,
> >>Tyler pointed out that the function __mlx5_hws_cnt_pool_enqueue_revert
> >> is accessing the ring private structure members
> (prod.hea
On Thu, Aug 17, 2023 at 07:52:36PM -0700, Stephen Hemminger wrote:
> The term abort is on the "Replace now" list of words.
> Use cancel instead.
>
I see cancel generally being used as a replacement throughout this
patchset, but I wonder if the use of th term could be confusing as it
doesn't strict
This series was triggered after investigating why the
eal_flags_file_prefix_autotest unit test was failing in the case of
statically built binaries [1]).
For now, I went with a simple (naive) approach and put all accesses to the
shared data under a single lock: ethdev maintainers, it is your turn
If no port is allocated, ethdev (from a primary process) can release the
memzone used to store port data.
This makes it possible for the DPDK memory allocator to release
associated resources back to the OS.
Signed-off-by: David Marchand
---
lib/ethdev/ethdev_driver.c | 6 ++
lib/ethdev/eth
ethdev currently uses two locks to protect access around
eth_dev_shared_data:
- one (process local) for avoiding multiple threads to reserve/lookup
the eth_dev_shared_data memzone,
- one (shared with other processes) for protecting port
allocation/destruction,
Simplify the logic and put everyt
On Mon, Jul 31, 2023 at 11:25 AM Ashwin Sekhar T K wrote:
>
> For non-EAL pthreads, rte_lcore_id() will not be valid.
> So, batch allocation cannot be used as we won't have a
> dedicated alloc buffer for the thread. So, fallback to
> bulk alloc in such cases.
>
> Fixes: 91531e63f43b ("mempool/cnxk
Add literal includes to copy code block while compiling. Having a copy
may lead to mismatch if code is updated without updating the doc.
Fixes: 40ff8c99ea99 ("doc: add details of security library")
Signed-off-by: Anoob Joseph
---
doc/guides/prog_guide/rte_security.rst | 65 +
Security library has definitions for configuration parameters of DOCSIS
and MACsec. Remove obsolete comments.
Signed-off-by: Anoob Joseph
---
doc/guides/prog_guide/rte_security.rst | 4
1 file changed, 4 deletions(-)
diff --git a/doc/guides/prog_guide/rte_security.rst
b/doc/guides/prog_gu
Add new API "rte_event_eth_rx_adapter_create_ext_with_params()" for
creating Rx adapter instance. This API is similar to
rte_event_eth_rx_adapter_create_ext() with an additional input
argument for adapter configuration parameters of type
"struct rte_event_eth_rx_adapter_params".
Signed-off-by: Nag
On 2023/8/18 17:05, Konstantin Ananyev wrote:
On 2023/8/17 22:06, Stephen Hemminger wrote:
On Thu, 17 Aug 2023 05:06:20 +
Honnappa Nagarahalli wrote:
Hi Matan, Viacheslav,
Tyler pointed out that the function __mlx5_hws_cnt_pool_enqueue_revert
is accessing the ring private struc
> -Original Message-
> From: Jerin Jacob
> Sent: Thursday, August 17, 2023 8:50 PM
> To: Naga Harish K, S V
> Cc: dev@dpdk.org; Carrillo, Erik G ; Gujjar,
> Abhinandan S ; McDaniel, Timothy
> ; pbhagavat...@marvell.com;
> sthot...@marvell.com; hemant.agra...@nxp.com;
> sachin.sax...@oss
On Tue, Aug 1, 2023 at 12:30 PM Srikanth Yalavarthi
wrote:
>
> Introduce event ML adapter APIs. This patch provides information
> on adapter modes and usage. Application can use this event adapter
> interface to transfer packets between ML device and event device.
>
> Signed-off-by: Srikanth Yalav
> -Original Message-
> From: Dariusz Sosnowski
> Sent: Friday, August 4, 2023 8:16 PM
> To: Matan Azrad ; Slava Ovsiienko
> ; Ori Kam ; Suanming Mou
> ; Jiawei(Jonny) Wang
> Cc: dev@dpdk.org
> Subject: [PATCH] net/mlx5: fix bond resource release
>
> When a port is spawned on top of mlx5
> From: David Marchand [mailto:david.march...@redhat.com]
> Sent: Friday, 18 August 2023 11.13
>
> This series was triggered after investigating why the
> eal_flags_file_prefix_autotest unit test was failing in the case of
> statically built binaries [1]).
>
> For now, I went with a simple (naive
On Wed, Aug 9, 2023 at 7:56 PM wrote:
>
> From: Pavan Nikhilesh
>
> A collection of event queues linked to an event port can be
> associated with a unique identifier called as a profile, multiple
> such profiles can be created based on the event device capability
> using the function `rte_event_p
Thanks. Good catch. Accepted.
> -Original Message-
> From: Tyler Retzlaff
> Sent: Friday, August 18, 2023 1:09 AM
> To: Mykola Kostenok
> Cc: dev@dpdk.org; Christian Koue Muf
> Subject: Re: [PATCH v2 1/8] net/ntnic: initial commit which adds register
> defines
>
> On Thu, Aug 17, 2023
On Fri, Aug 18, 2023 at 11:13 AM David Marchand
wrote:
> @@ -253,6 +255,10 @@ rte_eth_dev_release_port(struct rte_eth_dev *eth_dev)
> rte_free(eth_dev->data->dev_private);
> pthread_mutex_destroy(ð_dev->data->flow_ops_mutex);
> memset(eth_dev->data,
On 8/17/2023 3:18 PM, Konstantin Ananyev wrote:
>
>>> Caution: This message originated from an External Source. Use proper caution
>>> when opening attachments, clicking links, or responding.
>>>
>>>
>>> On Wed, Aug 16, 2023 at 11:59:59AM -0700, Sivaprasad Tummala wrote:
mwaitx allows EPYC pr
This series was triggered after investigating why the
eal_flags_file_prefix_autotest unit test was failing in the case of
statically built binaries [1]).
For now, I went with a simple (naive) approach and put all accesses to the
shared data under a single lock: ethdev maintainers, it is your turn
ethdev currently uses two locks to protect access around
eth_dev_shared_data:
- one (process local) for avoiding multiple threads to reserve/lookup
the eth_dev_shared_data memzone,
- one (shared with other processes) for protecting port
allocation/destruction,
Simplify the logic and put everyt
If no port is allocated, ethdev (from a primary process) can release the
memzone used to store port data.
This makes it possible for the DPDK memory allocator to release
associated resources back to the OS.
Signed-off-by: David Marchand
Acked-by: Morten Brørup
---
lib/ethdev/ethdev_driver.c |
test_dh_keygenration() changed to test_dh_key_generation()
Fixes: fc6c9066e40d ("test/crypto: add DH and DSA tests")
Fixes: da74df7d38c0 ("test/crypto: move test suite parameters to header file")
Cc: sunila.s...@caviumnetworks.com
Cc: ciara.po...@intel.com
Cc: sta...@dpdk.org
Signed-off-by: Siva
On Fri, Aug 18, 2023 at 02:25:14PM +0100, Ferruh Yigit wrote:
> On 8/17/2023 3:18 PM, Konstantin Ananyev wrote:
> >
> >>> Caution: This message originated from an External Source. Use proper
> >>> caution
> >>> when opening attachments, clicking links, or responding.
> >>>
> >>>
> >>> On Wed, Aug
From: Jack Min
Sent: Friday, August 18, 2023 12:57 AM
To: Honnappa Nagarahalli ; Stephen Hemminger
Cc: dev@dpdk.org; Matan Azrad ; viachesl...@nvidia.com; Tyler
Retzlaff ; Wathsala Wathawana Vithanage
; nd
Subject: Re: MLX5 PMD access ring library private data
On 2023/8/18 12:30, Honnappa Na
In case of IPv6 fragments are reassembled, then fragment
header will be removed from packet and next-header field in
IPv6 header will be updated to header followed by fragment header.
Fixes: a310577766d6 ("test/security: add inline IPsec reassembly cases")
Signed-off-by: Rahul Bhansali
---
app/
On Fri, 18 Aug 2023 10:08:58 +0100
Bruce Richardson wrote:
> On Thu, Aug 17, 2023 at 07:52:36PM -0700, Stephen Hemminger wrote:
> > The term abort is on the "Replace now" list of words.
> > Use cancel instead.
> >
> I see cancel generally being used as a replacement throughout this
> patchset,
The term 'abort' is on the inclusive namin Tier 1 word list
as replace when possible. It is possible to do this across
DPDK except the few places that directly call the lib C abort()
function.
v2 - drop changes to sfc since requires changes to base driver
- cleanup some checkpatch and missing s
The term abort is on the "Replace now" list of words.
Use cancel instead.
Signed-off-by: Stephen Hemminger
---
examples/l2fwd-jobstats/main.c | 2 +-
lib/jobstats/rte_jobstats.c| 2 +-
lib/jobstats/rte_jobstats.h| 9 -
lib/jobstats/version.map | 2 +-
4 files changed, 11 in
The term abort is on the Tier 1 "replace immediately" list.
Signed-off-by: Stephen Hemminger
---
.../comp_perf_test_cyclecount.c | 2 +-
.../comp_perf_test_throughput.c | 2 +-
app/test-compress-perf/comp_perf_test_verify.c | 2 +-
app/test/test_dmadev.c
Replace with cancel.
Signed-off-by: Stephen Hemminger
---
examples/pipeline/cli.c| 20 ++--
lib/pipeline/rte_swx_ctl.c | 29 +++--
lib/pipeline/rte_swx_ctl.h | 8
lib/pipeline/version.map | 2 +-
4 files changed, 30 insertions(+), 29 delet
Do the same thing but be better about wording.
Signed-off-by: Stephen Hemminger
---
drivers/net/vmxnet3/vmxnet3_rxtx.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/net/vmxnet3/vmxnet3_rxtx.c
b/drivers/net/vmxnet3/vmxnet3_rxtx.c
index 380f41f98be2..695a187718
Abort is on the Tier 1 non-inclusive word list.
Signed-off-by: Stephen Hemminger
---
drivers/event/dlb2/dlb2.c | 2 +-
drivers/event/dlb2/pf/base/dlb2_resource.c | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/event/dlb2/dlb2.c b/drivers/event/dlb2
Replace abort with cancel.
Signed-off-by: Stephen Hemminger
---
drivers/net/vdev_netvsc/vdev_netvsc.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/vdev_netvsc/vdev_netvsc.c
b/drivers/net/vdev_netvsc/vdev_netvsc.c
index c3e045d892b7..1a9c03c0f0b1 100644
---
Replace abort with cancel in netvsc.
The rndis.h was inherited from FreeBSD driver, but ok to change
it here.
Signed-off-by: Stephen Hemminger
---
drivers/net/netvsc/rndis.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/netvsc/rndis.h b/drivers/net/netvsc/rndis.
Since abort is on the Tier 1 list of words to replace;
just remove the unnecessary part of the log message.
Signed-off-by: Stephen Hemminger
---
drivers/net/ionic/ionic_dev_pci.c | 6 +++---
drivers/net/ionic/ionic_ethdev.c | 18 +-
drivers/net/ionic/ionic_lif.c | 2 +-
3
Don't use the term abort.
Signed-off-by: Stephen Hemminger
---
drivers/net/bnx2x/bnx2x.c | 18 +-
drivers/net/bnx2x/bnx2x_vfpf.c | 4 ++--
drivers/net/bnx2x/ecore_hsi.h | 6 +++---
drivers/net/bnx2x/ecore_reg.h | 20 ++--
4 files changed, 24 insertions(+)
Replace use of term abort with cancel in mlx5 common and driver code.
Signed-off-by: Stephen Hemminger
---
drivers/common/mlx5/mlx5_common_mr.c | 6 +++---
drivers/common/mlx5/mlx5_prm.h | 4 ++--
drivers/net/mlx5/hws/mlx5dr_rule.c | 8
drivers/net/mlx5/hws/mlx5dr_send.c | 2 +
The term abort is o the Tier 1 non-inclusive word list.
Replace it with cancel. This also impacts the CLI
for controlling this driver.
Signed-off-by: Stephen Hemminger
---
drivers/net/softnic/rte_eth_softnic_cli.c | 12 ++--
1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/
Avoid using the term abort since it is on Tier 1 word list.
Signed-off-by: Stephen Hemminger
---
drivers/net/mlx4/mlx4_mr.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/net/mlx4/mlx4_mr.c b/drivers/net/mlx4/mlx4_mr.c
index e95f45aa3e95..1bd47e05caeb 100644
--
Use cancel instead of abort.
Signed-off-by: Stephen Hemminger
---
drivers/net/axgbe/axgbe_common.h | 4 ++--
drivers/net/axgbe/axgbe_ethdev.h | 2 +-
drivers/net/axgbe/axgbe_i2c.c| 26 +-
3 files changed, 16 insertions(+), 16 deletions(-)
diff --git a/drivers/net/a
Recheck-request: iol-unit-amd64-testing, iol-compile-arm64-testing,
iol-broadcom-Functional
This email is a test for our (in development) email based retesting
framework. Please ignore.
On Mon, Jul 10, 2023 at 12:23 PM wrote:
> From: Jeremy Spewock
>
> This version of the series addresses comm
Recheck-request: iol-unit-arm64-testing
This email is a test for our (in development) email based retesting
framework. Please ignore.
On Mon, Jul 10, 2023 at 12:23 PM wrote:
> From: Jeremy Spewock
>
> added paramiko to the dependency files
>
> Signed-off-by: Jeremy Spewock
> ---
> dts/poetry
> Subject: [PATCH v2 07/13] net/netvsc: replace abort with cancel
>
> Replace abort with cancel in netvsc.
> The rndis.h was inherited from FreeBSD driver, but ok to change it here.
>
> Signed-off-by: Stephen Hemminger
> ---
> drivers/net/netvsc/rndis.h | 2 +-
> 1 file changed, 1 insertion(+),
On Fri, Aug 18, 2023 at 3:07 AM David Marchand
wrote:
> It is a "recurring" yet not so well known issue.
> This unit test fails if any part of the DPDK did not release all
> (hugepage backed) memory and associated hugepages before exiting.
>
> In your case here, there is a virtio-net device that
On Fri, Aug 18, 2023 at 6:33 PM Patrick Robb wrote:
>
> For your patch, it looks like there are actually more eal flags test
> failures:
> http://mails.dpdk.org/archives/test-report/2023-August/444170.html. In
> any case, for debugging purposes, I will do a run with
> the eal_flags_file_prefix_au
On 2023/8/18 21:59, Honnappa Nagarahalli wrote:
*From:* Jack Min
*Sent:* Friday, August 18, 2023 12:57 AM
*To:* Honnappa Nagarahalli ; Stephen
Hemminger
*Cc:* dev@dpdk.org; Matan Azrad ;
viachesl...@nvidia.com; Tyler Retzlaff ;
Wathsala Wathawana Vithanage ; nd
*Subject:* Re: MLX5 PMD acc
60 matches
Mail list logo
