On Sat, 2021-09-18 at 09:50 +0300, Andrew Rybchenko wrote:
> On 9/17/21 5:28 PM, Xueming Li wrote:
> > Currently, most ethdev callback API use queue ID as parameter, but Rx
> > and Tx queue release callback use queue object which is used by Rx and
> > Tx burst data plane callback.
> >
> > To align
Some drivers don't need Rx and Tx queue release callback, make them
optional. Clean up empty queue release callbacks for some drivers.
Signed-off-by: Xueming Li
Reviewed-by: Andrew Rybchenko
---
app/test/virtual_pmd.c| 12
drivers/net/af_packet/rte_eth_af_packet.c | 7
This patch is a preparation of shared Rx queue feature[1]. Rxq object
could be shared among ports of a share group, a shared rxq object can't
tell which port it belongs to. This is the motativation to clean up
queue release callback API to use queue ID.
v2:
included new NFP PMD driver
v3:
- comm
Currently, most ethdev callback API use queue ID as parameter, but Rx
and Tx queue release callback use queue object which is used by Rx and
Tx burst data plane callback.
To align with other eth device queue configuration callbacks:
- queue release callbacks are changed to use queue ID
- all drive
On Sat, Sep 18, 2021 at 7:55 AM Dmitry Kozlyuk wrote:
>
> 2021-09-18 07:24 (UTC-0700), William Tu:
> > On Wed, Sep 15, 2021 at 12:05 PM Dmitry Kozlyuk
> > wrote:
> > >
> > > 2021-09-15 18:44 (UTC+), William Tu:
> > > > This patch enables building the ixgbe driver for Windows.
> > > > It also
2021-09-18 07:24 (UTC-0700), William Tu:
> On Wed, Sep 15, 2021 at 12:05 PM Dmitry Kozlyuk
> wrote:
> >
> > 2021-09-15 18:44 (UTC+), William Tu:
> > > This patch enables building the ixgbe driver for Windows.
> > > It also enables its dependencies on security and cryptodev.
> >
> > Tal Shn
From: Satha Rao
Implemented TM node, shaper profile, hierarchy_commit and
statistic operations.
Signed-off-by: Satha Rao
---
doc/guides/rel_notes/release_21_11.rst | 1 +
drivers/net/cnxk/cnxk_tm.c | 353 +
drivers/net/cnxk/cnxk_tm.h |
From: Satha Rao
Initial version of TM implementation added basic infrastructure,
tm node_get, capabilities operations and rate limit queue operation.
Signed-off-by: Satha Rao
---
drivers/net/cnxk/cnxk_ethdev.c | 2 +
drivers/net/cnxk/cnxk_ethdev.h | 3 +
drivers/net/cnxk/cnxk_tm.c | 32
From: Satha Rao
Platform specific TM tree hierarchy details are part of common cnxk
driver. This patch introduces missing HAL apis to return state of
TM hierarchy required to support ethdev TM operations inside cnxk PMD.
Signed-off-by: Satha Rao
---
drivers/common/cnxk/roc_model.h| 6
From: Satha Rao
Different TM handlers returns various platform specific errors,
this patch introduces new API to convert these internal error
types to RTE_TM* error types.
Also updated error message API with missed TM error types.
Signed-off-by: Satha Rao
---
drivers/common/cnxk/cnxk_utils.c |
From: Satha Rao
Add new macros to reflect HW shaper PPS limits. New API to validate
input rates for packet mode. Increase adjust value to support lesser
PPS (<61).
Signed-off-by: Satha Rao
---
drivers/common/cnxk/hw/nix.h | 3 ++
drivers/common/cnxk/roc_nix_priv.h | 1 +
driver
From: Satha Rao
Added new API to flush all SMQs related nix interface
Signed-off-by: Satha Rao
---
drivers/common/cnxk/hw/nix.h | 6 +
drivers/common/cnxk/roc_nix.h| 1 +
drivers/common/cnxk/roc_nix_tm_ops.c | 50
drivers/common/cnxk/v
From: Nithin Dabilpuram
Increase sched weight and shaper burst limit for cn10k.
Signed-off-by: Nithin Dabilpuram
---
drivers/common/cnxk/hw/nix.h | 13 +++
drivers/common/cnxk/roc_nix.h | 23 ++-
drivers/common/cnxk/roc_nix_priv.h | 11 ++
From: Satha Rao
For SDP interface all platforms supports up to 65535 frame size.
Updated api with new check for SDP interface.
Signed-off-by: Satha Rao
---
drivers/common/cnxk/hw/nix.h | 1 +
drivers/common/cnxk/roc_nix.c | 5 -
2 files changed, 5 insertions(+), 1 deletion(-)
diff --git
From: Satha Rao
Initial implementation of traffic management for CN9K and CN10K
platforms.
Nithin Dabilpuram (1):
common/cnxk: increase sched weight and shaper burst limit
Satha Rao (7):
common/cnxk: use different macros for sdp and lbk max frames
common/cnxk: flush smq
common/cnxk: han
On Wed, Sep 15, 2021 at 12:05 PM Dmitry Kozlyuk
wrote:
>
> 2021-09-15 18:44 (UTC+), William Tu:
> > This patch enables building the ixgbe driver for Windows.
> > It also enables its dependencies on security and cryptodev.
>
> Tal Shnaiderman posted patches for cryptodev and security today,
> s
this patch adds unit tests for per rx queue event buffer
Signed-off-by: Naga Harish K S V
---
app/test/test_event_eth_rx_adapter.c | 90
1 file changed, 90 insertions(+)
diff --git a/app/test/test_event_eth_rx_adapter.c
b/app/test/test_event_eth_rx_adapter.c
index
this patch implement the per queue event buffer after
required validations.
Signed-off-by: Naga Harish K S V
---
lib/eventdev/rte_event_eth_rx_adapter.c | 185 ++--
1 file changed, 138 insertions(+), 47 deletions(-)
diff --git a/lib/eventdev/rte_event_eth_rx_adapter.c
b/lib
To configure per queue event buffer size, applications sets
``rte_event_eth_rx_adapter_params::use_queue_event_buf`` flag
as true and is passed to `rte_event_eth_rx_adapter_create2` api.
The per queue event buffer size is populated in
``rte_event_eth_rx_adapter_queue_conf::event_buf_size`` and pa
this patch adds unit test for rte_event_eth_rx_adapter_create2 api
and validate all possible input combinations.
Signed-off-by: Naga Harish K S V
---
app/test/test_event_eth_rx_adapter.c | 53 +---
1 file changed, 49 insertions(+), 4 deletions(-)
diff --git a/app/test/te
Currently Rx event buffer is static array
with a default size of 192(6*BATCH_SIZE).
``rte_event_eth_rx_adapter_create2`` api is added which takes
``struct rte_event_eth_rx_adapter_params`` to configure event
buffer size in addition other params . The event buffer is
allocated dynamically at run ti
On Fri, Sep 17, 2021 at 8:07 PM Pai G, Sunil wrote:
>
> Hi Jerin,
HI Sunil,
>
>
>
> > > > Add a burst capacity check API to the dmadev library. This API is
> > > > useful to
> > > > applications which need to how many descriptors can be enqueued in
> > > > the
> > > > c
On Sat, Sep 18, 2021 at 6:36 AM Hu, Jiayu wrote:
>
> Hi Jerin,
>
> > -Original Message-
> > From: Jerin Jacob
> > Sent: Friday, September 17, 2021 9:55 PM
> > To: Richardson, Bruce
> > Cc: dpdk-dev ; Walsh, Conor ;
> > Laatz, Kevin ; fengchengwen
> > ; Jerin Jacob ;
> > Satananda Burla ;
That means a superfluous cast is removed and aliasing through a uint8_t
pointer is eliminated. Note that uint8_t doesn't have the same
strict-aliasing properties as unsigned char.
Also simplified the loop since a modern C compiler can speed up (i.e.
auto-vectorize) it in a similar way. For example
The current __rte_raw_cksum() function violates the C strict-aliasing
rules since it uses a uint8_t pointer to access a trailing byte.
This patch also fixes a superfluous cast, i.e.:
uintptr_t ptr = (uintptr_t)buf;
typedef uint16_t __attribute__((__may_alias__)) u16_p;
con
> -Original Message-
> From: Li, Xiaoyun
> Sent: Saturday, September 18, 2021 4:31 PM
> To: Zhang, AlvinX ; Ananyev, Konstantin
>
> Cc: dev@dpdk.org
> Subject: RE: [PATCH v3 1/2] app/testpmd: update forward engine beginning
>
> Hi
>
> > -Original Message-
> > From: Zhang, AlvinX
18/09/2021 05:24, Huisong Li:
> 在 2021/9/17 20:50, Thomas Monjalon 写道:
> > 17/09/2021 04:13, Huisong Li:
> >> 在 2021/9/16 18:36, Thomas Monjalon 写道:
> >>> 16/09/2021 10:01, Huisong Li:
> 在 2021/9/8 15:20, Thomas Monjalon 写道:
> > 08/09/2021 04:01, Huisong Li:
> >> 在 2021/9/7 16:53, Thom
Normally when closing the device the queue memzone should be
freed. But the memzone will be not freed, when device setup
ops like:
rte_eth_bond_slave_remove
-->__eth_bond_slave_remove_lock_free
>slave_remove
-->rte_eth_dev_internal_reset
>rte_eth_dev_rx_queue_config
-->eth_
Normally when closing the device the queue memzone should be
freed. But the memzone will be not freed, when device setup
ops like:
rte_eth_bond_slave_remove
-->__eth_bond_slave_remove_lock_free
>slave_remove
-->rte_eth_dev_internal_reset
>rte_eth_dev_rx_queue_config
-->eth_
Normally when closing the device the queue memzone should be
freed. But the memzone will be not freed, when device setup
ops like:
rte_eth_bond_slave_remove
-->__eth_bond_slave_remove_lock_free
>slave_remove
-->rte_eth_dev_internal_reset
>rte_eth_dev_rx_queue_config
-->eth_
Normally when closing the device the queue memzone should be
freed. But the memzone will be not freed, when device setup
ops like:
rte_eth_bond_slave_remove
-->__eth_bond_slave_remove_lock_free
>slave_remove
-->rte_eth_dev_internal_reset
>rte_eth_dev_rx_queue_config
-->eth_
This series for deleting HW rings when releasing queues for
igb, ixgbe, i40e, ice & em drivers.
---
v2:
* Update commit log
Yunjian Wang (4):
net/e1000: delete HW rings when releasing queues
net/ice: delete HW rings when releasing queues
net/i40e: delete HW rings when releasing queues
Hi
> -Original Message-
> From: Zhang, AlvinX
> Sent: Saturday, September 18, 2021 11:07
> To: Li, Xiaoyun ; Ananyev, Konstantin
>
> Cc: dev@dpdk.org; Zhang, AlvinX
> Subject: [PATCH v3 1/2] app/testpmd: update forward engine beginning
>
> For each forward engine, there may be some spe
Hi
> -Original Message-
> From: Zhang, AlvinX
> Sent: Saturday, September 18, 2021 11:07
> To: Li, Xiaoyun ; Ananyev, Konstantin
>
> Cc: dev@dpdk.org; Zhang, AlvinX ; sta...@dpdk.org
> Subject: [PATCH v3 2/2] app/testpmd: fix txonly forwording
>
> When random number of Tx segments is en
From: Zhihong Peng
AddressSanitizer (ASan) is a google memory error detect
standard tool. It could help to detect use-after-free and
{heap,stack,global}-buffer overflow bugs in C/C++ programs,
print detailed error information when error happens, large
improve debug efficiency.
By referring to it
> -Original Message-
> From: David Christensen
> Sent: Saturday, September 18, 2021 4:51 AM
> To: Peng, ZhihongX ; Burakov, Anatoly
> ; Ananyev, Konstantin
> ; step...@networkplumber.org
> Cc: dev@dpdk.org; Lin, Xueqin
> Subject: Re: [dpdk-dev] [PATCH] Enable AddressSanitizer feature on D
Lower values denote higher priority with 0 as the maximum.
The usage of priority in non-pipeline mode is wrong.
This patch fixed this issue in switch filter and added input
validation of priority in FDIR, RSS and ACL filter which
only support one priority level.
Fixes: 2321e34c23b3 ("net/ice: sup
Use the dynamic mbuf to register timestamp field and flag.
The ice has the feature to dump Rx timestamp value into dynamic
mbuf field by flex descriptor. This feature is turned on by dev
config "enable-rx-timestamp". Currently, it's only supported
under scalar path.
Signed-off-by: Simei Su
---
d
38 matches
Mail list logo
