On 6/23/2021 7:43 PM, Andrew Rybchenko wrote:
On 6/23/21 4:39 PM, Ori Kam wrote:
Hi Jan,
-Original Message-
From: Jan Viktorin
Sent: Wednesday, June 23, 2021 12:18 PM
The struct rte_flow_action was missing from DPDK API documentation.
Signed-off-by: Jan Viktorin
---
lib/ethdev/
From: Kiran Kumar K
Adding autotest for cn9k and cn10k.
Signed-off-by: Kiran Kumar K
---
app/test/test_cryptodev_asym.c | 30 ++
doc/guides/cryptodevs/cnxk.rst | 17 +
2 files changed, 47 insertions(+)
diff --git a/app/test/test_cryptodev_asym.c b/a
Add asymmetric capabilities supported.
Signed-off-by: Anoob Joseph
---
doc/guides/cryptodevs/cnxk.rst| 6 +++
drivers/crypto/cnxk/cnxk_cryptodev_capabilities.c | 56 +++
2 files changed, 62 insertions(+)
diff --git a/doc/guides/cryptodevs/cnxk.rst b/doc/
From: Kiran Kumar K
Add asymmetric crypto datapath ops.
Signed-off-by: Kiran Kumar K
---
drivers/crypto/cnxk/cn10k_cryptodev_ops.c | 27 ++
drivers/crypto/cnxk/cn9k_cryptodev_ops.c | 29 +-
drivers/crypto/cnxk/cnxk_ae.h | 625 ++
3 files changed, 679
From: Kiran Kumar K
Add asymmetric crypto session ops.
Signed-off-by: Kiran Kumar K
---
doc/guides/cryptodevs/features/cn10k.ini | 13 ++
doc/guides/cryptodevs/features/cn9k.ini | 13 ++
drivers/crypto/cnxk/cn10k_cryptodev.c | 2 +
drivers/crypto/cnxk/cn10k_cryptodev_ops.c | 6 +-
Add support for asymmetric operations in crypto cnxk PMDs.
Following operations are supported,
- RSA
- DSA
- ECDSA
- ECPM
- Modular Exponentation
Depends-on: series-17482 ("Add CPT in Marvell CNXK common driver")
Depends-on: series-17483 ("Add Marvell CNXK crypto PMDs")
Depends-on: series-17484 ("
Add security capabilities supported by crypto cn10k PMD.
Signed-off-by: Anoob Joseph
Signed-off-by: Srujana Challa
Signed-off-by: Tejasree Kondoj
---
doc/guides/cryptodevs/cnxk.rst| 24 +
doc/guides/cryptodevs/features/cn10k.ini | 1 +
drivers/crypto/cnxk/c
From: Tejasree Kondoj
Add security handling in enqueue dequeue ops.
Signed-off-by: Anoob Joseph
Signed-off-by: Srujana Challa
Signed-off-by: Tejasree Kondoj
---
drivers/crypto/cnxk/cn10k_cryptodev_ops.c | 78 ++-
drivers/crypto/cnxk/cn10k_ipsec_la_ops.h | 74
From: Tejasree Kondoj
Add security session ops in cn10k crypto PMD.
Signed-off-by: Anoob Joseph
Signed-off-by: Archana Muniganti
Signed-off-by: Srujana Challa
Signed-off-by: Tejasree Kondoj
---
drivers/crypto/cnxk/cn10k_cryptodev.c | 2 +
drivers/crypto/cnxk/cn10k_ipsec.c | 275 ++
From: Srujana Challa
Add security ctx in cn10k crypto PMD.
Signed-off-by: Anoob Joseph
Signed-off-by: Srujana Challa
Signed-off-by: Tejasree Kondoj
---
drivers/crypto/cnxk/cn10k_cryptodev.c| 9 ++
drivers/crypto/cnxk/cnxk_cryptodev_sec.c | 47
driver
Add rte_security (lookaside protocol - IPsec) support in crypto_cn10k.
IPsec operations can be offloaded to CPT's SE and IE engines, which
can process IPsec protcol operations including atomic sequence number
increment (for outbound operations) and anti replay window check (for
inbound operations)
From: Tejasree Kondoj
Enable tests for cn9k & cn10k crypto PMDs.
Signed-off-by: Ankur Dwivedi
Signed-off-by: Anoob Joseph
Signed-off-by: Archana Muniganti
Signed-off-by: Tejasree Kondoj
---
app/test/meson.build | 2 ++
app/test/test_cryptodev.c | 14 ++
app/test/
From: Ankur Dwivedi
Add symmetric crypto capabilities for cn9k & cn10k.
Signed-off-by: Ankur Dwivedi
Signed-off-by: Anoob Joseph
Signed-off-by: Archana Muniganti
Signed-off-by: Tejasree Kondoj
---
doc/guides/cryptodevs/cnxk.rst| 46 ++
doc/guides/rel_notes/release_21_08
From: Tejasree Kondoj
Add support for digest support for various algorithms.
Signed-off-by: Ankur Dwivedi
Signed-off-by: Anoob Joseph
Signed-off-by: Archana Muniganti
Signed-off-by: Tejasree Kondoj
---
doc/guides/cryptodevs/features/cn10k.ini | 17 ++
doc/guides/cryptodevs/features/cn9k.i
From: Tejasree Kondoj
Add KASUMI decrypt support.
Signed-off-by: Ankur Dwivedi
Signed-off-by: Anoob Joseph
Signed-off-by: Archana Muniganti
Signed-off-by: Tejasree Kondoj
---
doc/guides/cryptodevs/features/cn10k.ini | 1 +
doc/guides/cryptodevs/features/cn9k.ini | 1 +
drivers/crypto/c
From: Tejasree Kondoj
Add KASUMI encrypt support.
Signed-off-by: Ankur Dwivedi
Signed-off-by: Anoob Joseph
Signed-off-by: Archana Muniganti
Signed-off-by: Tejasree Kondoj
---
drivers/crypto/cnxk/cnxk_se.h | 196 ++
1 file changed, 196 insertions(+)
d
From: Tejasree Kondoj
Add PDCP opcode which handles ZUC and SNOW3G.
Signed-off-by: Ankur Dwivedi
Signed-off-by: Anoob Joseph
Signed-off-by: Archana Muniganti
Signed-off-by: Tejasree Kondoj
---
doc/guides/cryptodevs/features/cn10k.ini | 2 +
doc/guides/cryptodevs/features/cn9k.ini | 2 +
From: Archana Muniganti
Add PDCP opcode which handles ZUC and SNOW3G.
Signed-off-by: Ankur Dwivedi
Signed-off-by: Anoob Joseph
Signed-off-by: Archana Muniganti
Signed-off-by: Tejasree Kondoj
---
drivers/crypto/cnxk/cnxk_se.h | 268 +-
1 file changed,
From: Archana Muniganti
Add flexi crypto cipher decrypt support in enqueue API. Flexi crypto
opcode covers a broad set of ciphers including variants of AES.
Signed-off-by: Ankur Dwivedi
Signed-off-by: Anoob Joseph
Signed-off-by: Archana Muniganti
Signed-off-by: Tejasree Kondoj
---
doc/guide
From: Archana Muniganti
Add flexi crypto cipher encrypt in enqueue API. Flexi crypto
opcode covers a broad set of ciphers including variants of AES.
Signed-off-by: Ankur Dwivedi
Signed-off-by: Anoob Joseph
Signed-off-by: Archana Muniganti
Signed-off-by: Tejasree Kondoj
---
drivers/crypto/cn
From: Archana Muniganti
Add support for chained operations in session.
Signed-off-by: Ankur Dwivedi
Signed-off-by: Anoob Joseph
Signed-off-by: Archana Muniganti
Signed-off-by: Tejasree Kondoj
---
doc/guides/cryptodevs/features/cn10k.ini | 2 ++
doc/guides/cryptodevs/features/cn9k.ini | 2
From: Archana Muniganti
Add support for AEAD operations in session.
Signed-off-by: Ankur Dwivedi
Signed-off-by: Anoob Joseph
Signed-off-by: Archana Muniganti
Signed-off-by: Tejasree Kondoj
---
drivers/crypto/cnxk/cnxk_cryptodev_ops.c | 3 ++
drivers/crypto/cnxk/cnxk_se.h| 64 ++
Add support for auth operations in session.
Signed-off-by: Ankur Dwivedi
Signed-off-by: Anoob Joseph
Signed-off-by: Archana Muniganti
Signed-off-by: Tejasree Kondoj
---
drivers/crypto/cnxk/cnxk_cryptodev_ops.c | 13 +++
drivers/crypto/cnxk/cnxk_se.h| 194 +
Add support for cipher operation in session.
Signed-off-by: Ankur Dwivedi
Signed-off-by: Anoob Joseph
Signed-off-by: Archana Muniganti
Signed-off-by: Tejasree Kondoj
---
drivers/crypto/cnxk/cnxk_cryptodev_ops.c | 3 +
drivers/crypto/cnxk/cnxk_se.h| 106 ++
Add dequeue_burst op in cn9k & cn10k.
Signed-off-by: Ankur Dwivedi
Signed-off-by: Anoob Joseph
Signed-off-by: Archana Muniganti
Signed-off-by: Tejasree Kondoj
---
doc/guides/cryptodevs/features/cn10k.ini | 3 +
doc/guides/cryptodevs/features/cn9k.ini | 3 +
drivers/crypto/cnxk/cn10k_cr
Add enqueue_burst op in cn9k & cn10k.
Signed-off-by: Ankur Dwivedi
Signed-off-by: Anoob Joseph
Signed-off-by: Archana Muniganti
Signed-off-by: Tejasree Kondoj
---
drivers/crypto/cnxk/cn10k_cryptodev.c | 2 +
drivers/crypto/cnxk/cn10k_cryptodev_ops.c | 189 ++
Add session ops
- sym_session_get_size
- sym_session_configure
- sym_session_clear
Signed-off-by: Ankur Dwivedi
Signed-off-by: Anoob Joseph
Signed-off-by: Archana Muniganti
Signed-off-by: Tejasree Kondoj
---
drivers/crypto/cnxk/cn10k_cryptodev_ops.c | 6 +-
drivers/crypto/cnxk/cn9k_cryptode
From: Ankur Dwivedi
Add ops for
- queue_pair_setup()
- queue_pair_release()
Signed-off-by: Ankur Dwivedi
Signed-off-by: Anoob Joseph
Signed-off-by: Archana Muniganti
Signed-off-by: Tejasree Kondoj
---
drivers/crypto/cnxk/cn10k_cryptodev_ops.c | 4 +-
drivers/crypto/cnxk/cn9k_cryptodev_ops
From: Ankur Dwivedi
Add ops for
- dev_configure()
- dev_start()
- dev_stop()
- dev_close()
- dev_infos_get()
Signed-off-by: Ankur Dwivedi
Signed-off-by: Anoob Joseph
Signed-off-by: Archana Muniganti
Signed-off-by: Tejasree Kondoj
---
drivers/crypto/cnxk/cn10k_cryptodev_ops.c | 21 +++--
From: Ankur Dwivedi
Add probe & remove for cn9k & cn10k crypto PMDs.
Signed-off-by: Ankur Dwivedi
Signed-off-by: Anoob Joseph >
Signed-off-by: Archana Muniganti
Signed-off-by: Tejasree Kondoj
---
drivers/crypto/cnxk/cn10k_cryptodev.c | 98 ++-
drivers/crypto/c
From: Ankur Dwivedi
Add driver skeleton for crypto_cn9k & crypto_cn10k PMDs leveraging cnxk
common framework.
Signed-off-by: Ankur Dwivedi
Signed-off-by: Anoob Joseph
Signed-off-by: Archana Muniganti
Signed-off-by: Tejasree Kondoj
---
MAINTAINERS | 9 +++
doc/
Add cnxk crypto PMDs supporting Marvell CN106XX SoC, based on 'common/cnxk'.
This series utilizes 'common/cnxk' to register cn9k & cn10k crypto PMDs and
add symmetric cryptographic features for the same.
Depends-on: series-17482 ("Add CPT in Marvell CNXK common driver")
Changes in v2:
- Added do
From: Ankur Dwivedi
The set key functions are added in roc.
Signed-off-by: Ankur Dwivedi
---
drivers/common/cnxk/meson.build | 1 +
drivers/common/cnxk/roc_se.c| 342
drivers/common/cnxk/roc_se.h| 8 +
drivers/common/cnxk/version.map | 2 +
From: Srujana Challa
Add code that can be leveraged across
lookaside and inline IPsec on cn10k.
Signed-off-by: Srujana Challa
Signed-off-by: Nithin Dabilpuram
Signed-off-by: Tejasree Kondoj
---
drivers/common/cnxk/cnxk_security.c | 468
drivers/common/cnx
From: Kiran Kumar Kokkilagadda
EC group static vectors are required for CPT asymmetric operations.
Signed-off-by: Anoob Joseph
Signed-off-by: Kiran Kumar Kokkilagadda
---
drivers/common/cnxk/meson.build | 1 +
drivers/common/cnxk/roc_ae.c| 142
d
From: Kiran Kumar Kokkilagadda
Add scalar FPM tables to be used for asymmetric operations.
Signed-off-by: Anoob Joseph
Signed-off-by: Kiran Kumar Kokkilagadda
---
drivers/common/cnxk/meson.build |1 +
drivers/common/cnxk/roc_ae_fpm_tables.c | 1140 +++
Add routine to initialize LMTLINE which facilitates instruction
submission to CPT. Add common macros required in the enqueue
operations.
Signed-off-by: Anoob Joseph
Signed-off-by: Ankur Dwivedi
---
drivers/common/cnxk/roc_cpt.c | 20
drivers/common/cnxk/roc_cpt.h | 32
From: Kiran Kumar Kokkilagadda
Microcode AE opcodes support asymmetric operations. Add defines
and structs defined by microcode.
Signed-off-by: Anoob Joseph
Signed-off-by: Kiran Kumar Kokkilagadda
---
drivers/common/cnxk/roc_ae.h | 56 +++
drivers/com
From: Srujana Challa
Microcode IE opcodes support IPsec operations. Add defines
and structs defined by microcode.
Signed-off-by: Anoob Joseph
Signed-off-by: Srujana Challa
Signed-off-by: Tejasree Kondoj
---
drivers/common/cnxk/roc_api.h | 2 +
drivers/common/cnxk/roc_ie.h | 19
From: Kiran Kumar Kokkilagadda
Microcode SE opcodes support symmetric operations. Add defines
and structs defined by microcode.
Signed-off-by: Anoob Joseph
Signed-off-by: Kiran Kumar Kokkilagadda
Signed-off-by: Vidya Sagar Velumuri
---
drivers/common/cnxk/roc_api.h | 3 +
drivers/common/cn
From: Vidya Sagar Velumuri
Add mbox to configure inbound & outbound inline IPsec.
Signed-off-by: Tejasree Kondoj
Signed-off-by: Vidya Sagar Velumuri
---
drivers/common/cnxk/roc_cpt.c | 61 ++
drivers/common/cnxk/roc_cpt.h | 5
drivers/common
From: Aakash Sasidharan
Add routine to flush context from CPT context processor cache.
Signed-off-by: Aakash Sasidharan
Signed-off-by: Vidya Sagar Velumuri
---
drivers/common/cnxk/roc_cpt.c | 18 ++
drivers/common/cnxk/roc_cpt.h | 1 +
drivers/common/cnxk/version.map |
From: Aakash Sasidharan
Add routines to fetch and dump CPT statistics and states.
Signed-off-by: Aakash Sasidharan
Signed-off-by: Srujana Challa
---
drivers/common/cnxk/meson.build | 1 +
drivers/common/cnxk/roc_cpt.c | 29 +++
drivers/common/cnxk/roc_cpt.h | 3 +
dr
From: Archana Muniganti
Add routines to init & fini CPT LFs. CPT LFs are
queues to the hardware enabling instruction submissions.
Signed-off-by: Anoob Joseph
Signed-off-by: Archana Muniganti
Signed-off-by: Vidya Sagar Velumuri
---
drivers/common/cnxk/roc_cpt.c | 357 +++
From: Vidya Sagar Velumuri
Add mailbox to configure tiemouts and thresholds in
CPT RXC unit.
Signed-off-by: Aakash Sasidharan
Signed-off-by: Vidya Sagar Velumuri
---
drivers/common/cnxk/roc_cpt.c | 27 +++
drivers/common/cnxk/roc_cpt.h | 10 ++
drivers/com
Add APIs to set & get CPT device.
Signed-off-by: Anoob Joseph
---
drivers/common/cnxk/roc_cpt.c | 8
drivers/common/cnxk/roc_idev.c | 21 +
drivers/common/cnxk/roc_idev.h | 3 +++
drivers/common/cnxk/roc_idev_priv.h | 2 ++
drivers/common/cnxk/vers
Add routines to init, fini, configure & clear CPT device.
Signed-off-by: Anoob Joseph
Signed-off-by: Archana Muniganti
Signed-off-by: Vidya Sagar Velumuri
---
drivers/common/cnxk/meson.build| 1 +
drivers/common/cnxk/roc_api.h | 3 +
drivers/common/cnxk/roc_cpt.c | 308 +
From: Srujana Challa
Updates Rx inline IPSEC mailbox message format to make it
sync with latest CPT PF driver.
Signed-off-by: Srujana Challa
---
drivers/common/cnxk/roc_mbox.h | 3 +++
1 file changed, 3 insertions(+)
diff --git a/drivers/common/cnxk/roc_mbox.h b/drivers/common/cnxk/roc_mbox.h
From: Vidya Sagar Velumuri
Add CPT hardware definitions. CPT is the hardware block on
cnxk family of processors, that can be used to offload
cryptographic operations.
Signed-off-by: Anoob Joseph
Signed-off-by: Vidya Sagar Velumuri
---
drivers/common/cnxk/hw/cpt.h | 291 +
This patchset adds initial support for CPT in common code for Marvell CN10K SoC.
CPT is the hardware cryptographic block available in 'cnxk' family SoC. CPT,
with its microcoded engines can support symmetric, asymmetric and IPsec
operations. CPT can associate with NIX (rte_ethdev) to enable inline
On Thu, 11 Mar 2021 21:01:13 +0800
Xueming Li wrote:
> + AUXILIAR_LOG(DEBUG, "Auxiliary device %s on NUMA socket %i\n",
> + dev->name, dev->device.numa_node);
Your log messages will be double spaced.
The macro is already adding a new line.
> +
> +#define AUXILIAR_LOG(le
> -Original Message-
> From: Thomas Monjalon
> Sent: Friday, June 25, 2021 12:19 AM
> To: Xueming(Steven) Li
> Cc: dev@dpdk.org; Wang Haiyue ; Kinsella Ray
>
> Subject: Re: [dpdk-dev] [PATCH v5 2/2] bus/auxiliary: introduce auxiliary bus
>
> 23/06/2021 02:03, Xueming Li:
> > +static
Hi Maxime,
> -Original Message-
> From: Maxime Coquelin
> Sent: Friday, June 18, 2021 10:04 PM
> To: dev@dpdk.org; david.march...@redhat.com; Xia, Chenbo
>
> Cc: Maxime Coquelin ; sta...@dpdk.org
> Subject: [PATCH v6 4/7] vhost: fix NUMA reallocation with multiqueue
>
> Since the Vhost
Hi Maxime,
> -Original Message-
> From: Maxime Coquelin
> Sent: Friday, June 18, 2021 10:04 PM
> To: dev@dpdk.org; david.march...@redhat.com; Xia, Chenbo
>
> Cc: Maxime Coquelin
> Subject: [PATCH v6 3/7] vhost: fix missing cache logging NUMA realloc
>
> When the guest allocates virtqu
> -Original Message-
> From: Maxime Coquelin
> Sent: Friday, June 18, 2021 10:04 PM
> To: dev@dpdk.org; david.march...@redhat.com; Xia, Chenbo
>
> Cc: Maxime Coquelin ; sta...@dpdk.org
> Subject: [PATCH v6 1/7] vhost: fix missing memory table NUMA realloc
>
> When the guest allocates vi
> -Original Message-
> From: Maxime Coquelin
> Sent: Friday, June 18, 2021 10:04 PM
> To: dev@dpdk.org; david.march...@redhat.com; Xia, Chenbo
>
> Cc: Maxime Coquelin ; sta...@dpdk.org
> Subject: [PATCH v6 2/7] vhost: fix missing guest pages table NUMA realloc
>
> When the guest allocat
Hi all,
We would like to start/stop a specific Rx/Tx queue of a ixgbevf device
and found that rx_queue_start/tx_queue_start operations are not
supported on ixgbevf driver.
I am wondering why this driver not support dynamic txq/rxq start/stop.
Is there any hardlimit to implement this?
Thanks very
On arm platform, the value in "/sys/.../cpuinfo_cur_freq" may not
be exactly the same as what was set when using CPPC cpufreq driver.
For other cpufreq driver, no need to round it currently, or else
this check will fail with turbo enabled. For example, with acpi_cpufreq,
cpuinfo_cur_freq can be 240
Currently in DPDK only acpi_cpufreq and pstate_cpufreq drivers are
supported, which are both not available on arm64 platforms. Add
support for cppc_cpufreq driver which works on most arm64 platforms.
Signed-off-by: Richael Zhuang
---
app/test/test_power.c | 3 +-
app/test/test_power_c
v5:
rebase on Anatoly's patch: http://dpdk.org/patch/94763
Richael Zhuang (2):
power: add support for cppc cpufreq
test/power: round cpuinfo cur freq only when using CPPC cpufreq
app/test/test_power.c | 3 +-
app/test/test_power_cpufreq.c | 26 +-
lib/power/meson.build
From: Narcisa Vasile
Fix count_cpu() to ensure it iterates through all the CPUs in a set.
count_cpu() iterates through the CPUs in the set 's' and counts the
selected ones.
Previously, it was incorrectly using the number of CPUSETS to iterate
through the CPUs.
Signed-off-by: Narcisa Vasile
---
2021-06-23 15:34 (UTC-0700), Jie Zhou:
> Function print_fdir_mask and print_fdir_flex_payload is only called
> when either i40e or ixgbe presents. Add #if defined to remove
> "unused function" compilation warning.
>
> Signed-off-by: Jie Zhou
> Signed-off-by: Jie Zhou
> Acked-by: Tal Shnaiderman
2021-06-23 15:34 (UTC-0700), Jie Zhou:
> - Make printf format OS independent
> - Replace htons with RTE_BE16
> - Replace POSIX specific inet_aton with OS independent inet_pton
> - Replace sleep with rte_delay_us_sleep
> - Repalce random with rte_rand
> - #ifndef mman related code for now
> -
2021-06-23 15:34 (UTC-0700), Jie Zhou:
> Add clock_gettime on Windows in rte_os_shim.h
>
> Signed-off-by: Jie Zhou
> Signed-off-by: Jie Zhou
Acked-by: Dmitry Kozlyuk
2021-06-23 15:34 (UTC-0700), Jie Zhou:
> Add required macros by testpmd on Windows in rte_os_shim.h
>
> Signed-off-by: Jie Zhou
> Signed-off-by: Jie Zhou
> Acked-by: Tal Shnaiderman
Acked-by: Dmitry Kozlyuk
2021-06-23 15:34 (UTC-0700), Jie Zhou:
> Enable building libraries that testpmd depends on for Windows
>
> Signed-off-by: Jie Zhou
> Signed-off-by: Jie Zhou
> ---
> lib/meson.build | 7 +++
> 1 file changed, 7 insertions(+)
>
> diff --git a/lib/meson.build b/lib/meson.build
> index 4a64756
On Thu, Jun 24, 2021 at 09:44:04PM +0300, Dmitry Kozlyuk wrote:
> 2021-06-24 08:45 (UTC-0700), Tyler Retzlaff:
> > On Wed, Jun 23, 2021 at 02:26:32PM -0700, Jie Zhou wrote:
> > > On Mon, Jun 21, 2021 at 02:30:53AM +0300, Dmitry Kozlyuk wrote:
> > > > -
> > > > void
> > > > fdir_set_flex_mask(po
Hi Nicolas,
I could equally ask is there is any concern with this being a tracked ABI?
The API has seen zero changes in two years - IMHO we'd need a very good reason
not standardize it.
As there has been ample opportunities for others to chime in.
git log --format=oneline --follow v19.11..v21.0
> On 24 Jun 2021, at 11:33, Kinsella, Ray wrote:
>
> Hi Cristian & Jasvinder,
>
> The following sched experimental symbols are present in both v21.05 and
> v19.11 release. These symbols should be considered for promotion to stable as
> part of the v22 ABI in DPDK 21.11, as they have been ex
2021-06-24 08:45 (UTC-0700), Tyler Retzlaff:
> On Wed, Jun 23, 2021 at 02:26:32PM -0700, Jie Zhou wrote:
> > On Mon, Jun 21, 2021 at 02:30:53AM +0300, Dmitry Kozlyuk wrote:
> > > -
> > > void
> > > fdir_set_flex_mask(portid_t port_id, struct rte_eth_fdir_flex_mask *cfg)
> > > {
> > > diff --gi
On 6/24/21 6:51 AM, David Marchand wrote:
On Tue, Jun 15, 2021 at 7:21 PM David Christensen
wrote:
Fix the IOMMU detection logic that looks for the "platform" field of
/proc/cpuinfo on POWER systems.
Fixes: 905215731833 ("bus/pci: support IOVA as VA on PowerNV systems")
Cc: sta...@dpdk.or
24/06/2021 18:02, Tyler Retzlaff:
> On Thu, Jun 24, 2021 at 08:54:49AM +0200, Thomas Monjalon wrote:
> > 23/06/2021 20:26, Tyler Retzlaff:
> > > // lib/eal/gcc/rte_toolchain_common.h
> > > #define __rte_noreturn __attribute__((noreturn))
> >
> > We should keep a macro in rte_common.h which trigger
23/06/2021 02:03, Xueming Li:
> +static int
> +rte_auxiliary_probe_one_driver(struct rte_auxiliary_driver *drv,
> +struct rte_auxiliary_device *dev)
[...]
> + AUXILIARY_LOG(DEBUG, "Probe driver: %s", drv->driver.name);
I think the debug log above is useless given th
On Wed, Jun 23, 2021 at 01:31:54PM -0700, David Christensen wrote:
> Replacing memcpy() with rte_memcpy() improved 64 byte packet
> performance by 33% on a POWER9 system and by 10% on an x86_64
> system.
>
> Signed-off-by: David Christensen
> ---
Acked-by: Tyler Retzlaff
On Thu, Jun 24, 2021 at 01:53:19PM +0200, David Marchand wrote:
> This hack was needed with the make build system.
> With meson, any private header from a library is visible as long as a
> dependency to this library is expressed.
>
> Signed-off-by: David Marchand
> ---
Acked-by: Tyler Retzlaff
On Thu, Jun 24, 2021 at 08:54:49AM +0200, Thomas Monjalon wrote:
> 23/06/2021 20:26, Tyler Retzlaff:
> > today rte_common.h defines common macros for use by dpdk and consuming
> > applications. most expansions are specific to the gcc toolchain.
> >
> > example
> > // lib/eal/include/rte_common.h
>
On 24-Jun-21 4:25 PM, Ananyev, Konstantin wrote:
I did a quick prototype for this, and i don't think it is going to work.
Callbacks with just "current value" as argument will be pretty limited
and will only really work for cases where we know what we are expecting.
However, for cases like even
On Wed, Jun 23, 2021 at 02:26:32PM -0700, Jie Zhou wrote:
> On Mon, Jun 21, 2021 at 02:30:53AM +0300, Dmitry Kozlyuk wrote:
> > -
> > void
> > fdir_set_flex_mask(portid_t port_id, struct rte_eth_fdir_flex_mask *cfg)
> > {
> > diff --git a/app/test-pmd/testpmd.h b/app/test-pmd/testpmd.h
> > index
Hi Ray,
That request was considered for 20.11. But this was deferred by the community
while waiting for other vendors who may be willing to contribute their own PMDs.
Any specific concern with this not being on a tracked ABI?
Thanks
Nic
> -Original Message-
> From: Kinsella, Ray
> Se
2021-06-24 15:45 (UTC+0100), Ferruh Yigit:
> As discussed in the technical board meeting
> https://mails.dpdk.org/archives/dev/2021-February/200012.html
>
> This is to record that new upstreamed devices tested adequately.
>
> Signed-off-by: Ferruh Yigit
> ---
> CC: John McNamara
> Cc: dev@dpdk.
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.
Cc: ray.kinse...@intel.com
Signed-off-by: Mohsin Kazmi
---
lib/net/rte_net.h |
> >> I did a quick prototype for this, and i don't think it is going to
> >> work.
> >>
> >> Callbacks with just "current value" as argument will be pretty limited
> >> and will only really work for cases where we know what we are
> >> expecting.
> >> However, for cas
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.
Cc: ray.kinse...@intel.com
Signed-off-by: Mohsin Kazmi
---
lib/net/rte_net.h |
On 24-Jun-21 3:57 PM, Ananyev, Konstantin wrote:
I did a quick prototype for this, and i don't think it is going to work.
Callbacks with just "current value" as argument will be pretty limited
and will only really work for cases where we know what we are expecting.
However, for cases like eve
> I did a quick prototype for this, and i don't think it is going to work.
>
> Callbacks with just "current value" as argument will be pretty limited
> and will only really work for cases where we know what we are expecting.
> However, for cases like event/dlb or net/mlx5
As discussed in the technical board meeting
https://mails.dpdk.org/archives/dev/2021-February/200012.html
This is to record that new upstreamed devices tested adequately.
Signed-off-by: Ferruh Yigit
---
CC: John McNamara
Cc: dev@dpdk.org
---
content/testing/_index.md | 4
1 file changed,
On 24-Jun-21 10:47 AM, Ananyev, Konstantin wrote:
I did a quick prototype for this, and i don't think it is going to work.
Callbacks with just "current value" as argument will be pretty limited
and will only really work for cases where we know what we are expecting.
However, for cases like
Sounds more than reasonable, +1 from me.
Ray K
On 24/06/2021 14:24, Ferruh Yigit wrote:
> On 6/24/2021 11:42 AM, Kinsella, Ray wrote:
>> Hi Ferruh,
>>
>> The following kni experimental symbols are present in both v21.05 and v19.11
>> release. These symbols should be considered for promotion to
On Tue, Jun 15, 2021 at 7:21 PM David Christensen
wrote:
>
> Fix the IOMMU detection logic that looks for the "platform" field of
> /proc/cpuinfo on POWER systems.
>
> Fixes: 905215731833 ("bus/pci: support IOVA as VA on PowerNV systems")
Cc: sta...@dpdk.org
>
> Signed-off-by: David Christensen
'rte_kni_update_link()' updates virtual KNI interface link using kernel
sysfs interface.
If the requested link status is same as interface link status, do not
update the link status but return with success.
Signed-off-by: Ferruh Yigit
---
Cc: Dan Gora
---
lib/kni/rte_kni.c | 5 -
lib/kni/
On Wed, Jun 16, 2021 at 6:26 PM wrote:
>
> From: Owen Hilyard
>
> The directory steam was not closed when the hugepage action was
> HUGEPAGE_CHECK_EXISTS. This caused a memory leak in some parts of
> the unit tests.
>
Fixes: 45f1b6e8680a ("app: add new tests on eal flags")
Cc: sta...@dpdk.org
On Wed, Jun 23, 2021 at 8:06 PM wrote:
>
> From: Owen Hilyard
>
> Fixes for a few memory leaks in the cmdline_autotest unit test.
>
> All of the leaks were related to not freeing the commandline struct
> after testing had completed.
>
> Fixes: dbb860e03e ("cmdline: tests")
Updated sha1.
Cc: sta..
On Thu, Jun 24, 2021 at 2:08 PM Olivier Matz wrote:
> > - if (cmdline_file_new(&ctx, "prompt", "/dev/null") == NULL) {
> > + cl = cmdline_file_new(&ctx, "prompt", "/dev/null");
> > + if (cl == NULL) {
> > printf("Error: failed to open /dev/null for reading!");
> > +
On 6/24/2021 11:42 AM, Kinsella, Ray wrote:
> Hi Ferruh,
>
> The following kni experimental symbols are present in both v21.05 and v19.11
> release. These symbols should be considered for promotion to stable as part
> of the v22 ABI in DPDK 21.11, as they have been experimental for >= 2yrs at
On Wed, Jun 23, 2021 at 5:17 PM wrote:
>
> From: Owen Hilyard
>
> ASAN found a stack buffer overflow in lib/rib/rte_rib6.c:get_dir.
> The fix for the stack buffer overflow was to make sure depth
> was always < 128, since when depth = 128 it caused the index
> into the ip address to be 16, which r
On Wed, Jun 23, 2021 at 7:07 PM wrote:
>
> From: Owen Hilyard
>
> Rules in a classify table were not freed if the table
> had a delete function.
>
> Fixes: be41ac2a3 ("flow_classify: introduce flow classify library")
Updated sha1 to be 12 characters.
Cc: sta...@dpdk.org
>
> Signed-off-by: Owen H
Hi Ray,
> --
> (correcting Goyals address, apologies for the resend)
>
> On 24/06/2021 11:28, Kinsella, Ray wrote:
> > Hi Declan and Goyal,
> >
> > The following security experimental symbols are present in both v21.05
> and v19.1
OK, thank Bruce
How about next week ?
PS: I still working on V2 and hope it as a basis for discussion.
On 2021/6/23 22:56, Bruce Richardson wrote:
> This is developing into quite a long discussion with multiple threads
> ongoing at the same time. Since it's getting relatively hard to follow (at
>
Good point, that one is very up to the lib maintainer to make that call.
Ray K
On 24/06/2021 13:14, David Marchand wrote:
> On Thu, Jun 24, 2021 at 12:31 PM Kinsella, Ray wrote:
>>
>> Hi Anatoly & Thomas,
>>
>> The following eal experimental symbols are present in both v21.05 and v19.11
>> rele
On Thu, Jun 24, 2021 at 12:31 PM Kinsella, Ray wrote:
>
> Hi Anatoly & Thomas,
>
> The following eal experimental symbols are present in both v21.05 and v19.11
> release. These symbols should be considered for promotion to stable as part
> of the v22 ABI in DPDK 21.11, as they have been experime
1 - 100 of 153 matches
Mail list logo
