Hi,
> -Original Message-
> From: dev On Behalf Of Dekel Peled
> Sent: Thursday, July 18, 2019 10:42 PM
> To: Yongseok Koh ; Slava Ovsiienko
> ; Shahaf Shuler
> Cc: Jack Min ; Ori Kam ;
> dev@dpdk.org
> Subject: [dpdk-dev] [PATCH] net/mlx5: fix define of added tunnel layer bit
>
> The ne
Hi,
> -Original Message-
> From: dev On Behalf Of Dekel Peled
> Sent: Thursday, July 18, 2019 10:42 PM
> To: Yongseok Koh ; Slava Ovsiienko
> ; Shahaf Shuler
> Cc: Jack Min ; Ori Kam ;
> dev@dpdk.org
> Subject: [dpdk-dev] [PATCH] net/mlx5: fix setting of item flags bitmap
>
> In functio
Hi,
> -Original Message-
> From: dev On Behalf Of Dekel Peled
> Sent: Thursday, July 18, 2019 10:41 PM
> To: Yongseok Koh ; Slava Ovsiienko
> ; Shahaf Shuler
> Cc: Ori Kam ; dev@dpdk.org; sta...@dpdk.org
> Subject: [dpdk-dev] [PATCH] net/mlx5: correct spelling mistakes in
> comments
>
Hi,
> -Original Message-
> From: dev On Behalf Of Dekel Peled
> Sent: Thursday, July 18, 2019 10:37 PM
> To: Matan Azrad ; Shahaf Shuler
>
> Cc: Ori Kam ; dev@dpdk.org
> Subject: [dpdk-dev] [PATCH] net/mlx4: correct spelling mistake in comment
>
> A spelling mistake was found in comment
The error path of interrupt install was done in any way.
Fix it to skip error path in case of success.
Fixes: 0134353a5951 ("net/mlx5: accelerate DV flow counter query")
Signed-off-by: Matan Azrad
---
drivers/net/mlx5/mlx5_ethdev.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net
> -Original Message-
> From: Matan Azrad
> Sent: Sunday, July 21, 2019 11:17
> To: Shahaf Shuler ; Yongseok Koh
> ; Slava Ovsiienko
> Cc: dev@dpdk.org
> Subject: [PATCH] net/mlx5: fix interrupt install
>
> The error path of interrupt install was done in any way.
> Fix it to skip error pa
Hi,
> -Original Message-
> From: dev On Behalf Of Matan Azrad
> Sent: Sunday, July 21, 2019 11:17 AM
> To: Shahaf Shuler ; Yongseok Koh
> ; Slava Ovsiienko
> Cc: dev@dpdk.org
> Subject: [dpdk-dev] [PATCH] net/mlx5: fix interrupt install
>
> The error path of interrupt install was done i
Hi Guys,
We have a failure in testpmd commands when parsing rte_flow commands as
following which were interduce by this patch:
This rule is a valid rule to be added to testpmd:
flow validate 0 priority 2 ingress group 0 pattern eth dst is
98:03:9B:5C:D9:00 / end actions queue index 0 / end
This patch introduces new mlx5 PMD devarg options:
- txq_inline_min - specifies minimal amount of data to be inlined into
WQE during Tx operations. NICs may require this minimal data amount
to operate correctly. The exact value may depend on NIC operation mode,
requested offloads, etc.
- tx
This patch removes the existing Tx datapath code
as preparation step before introducing the new
implementation. The following entities are being
removed:
- deprecated devargs support
- tx_burst() routines
- related PRM definitions
- SQ configuration code
- Tx routine selection code
- incompatible
This patchset introduces the new implementation of tx_burst
routine of mlx5 PMD. The existing implementation is based on the
several branches of tx_burst routines optimizied for most
common sets of Tx hardware offload, supported by Mellanox NICs.
It was not very easy to update, support and develop
This patch extends the NIC attributes query via DevX.
The appropriate interface structures are borrowed from
kernel driver headers and DevX calls are added to
mlx5_devx_cmd_query_hca_attr() routine.
Signed-off-by: Viacheslav Ovsiienko
---
drivers/net/mlx5/mlx5.h | 5 ++
drivers/net/m
This patch updates the Tx datapath control and configuration
structures and code for mananging Tx datapath settings.
Signed-off-by: Viacheslav Ovsiienko
---
drivers/net/mlx5/mlx5.c | 123 +
drivers/net/mlx5/mlx5.h | 2 +-
drivers/net/mlx5/mlx5_rxtx.c | 4 +-
This patch updates Tx datapath definitions, mostly hardware related.
The Tx descriptor structures are redefined with required fields,
size definitions are renamed to reflect the meanings in more
appropriate way. This is a preparation step before introducing
the new Tx datapath implementation.
Sign
This patch adds the implementation of tx_burst routine template.
The template supports all Tx offloads and multiple optimized
tx_burst routines can be generated by compiler from this one.
Signed-off-by: Viacheslav Ovsiienko
---
drivers/net/mlx5/mlx5_rxtx.c | 2958
This patch fills the tx_desc_lim.nb_seg_max and
tx_desc_lim.nb_mtu_seg_max fields of rte_eth_dev_info
structure to report thee maximal number of packet
segments, requested inline data configuration is
taken into account in conservative way.
Signed-off-by: Viacheslav Ovsiienko
---
drivers/net/mlx
Mellanox NICs support the wide set of Tx offloads. The supported
offloads are reported by the mlx5 PMD in rte_eth_dev_info tx_offload_capa
field. An application may choose any combination of supported offloads
and configure the device appropriately. Some of Tx offloads may be
not requested by appli
In mlx5 PMD the associated device index is retrieved via Netlink request to
underlying Infiniband device driver. This network device index is permanent
throughout the lifetime of device. We do not spawn the rte_eth_dev ports
without associated network device, and if network device is being unbound
This reverts commit e28111ac9864af09e826241a915dfff87a9c00ad.
The netlink requests are replaced by ifindex caching and
not needed anymore.
Signed-off-by: Viacheslav Ovsiienko
Fixes: e28111ac9864 ("net/mlx5: fix master device Netlink socket sharing")
---
drivers/net/mlx5/mlx5.h| 6 ---
The associated device index is retrieved via Netlink request to
underlying Infiniband device driver. This network device index
is permanent throughout the lifetime of device. We do not
spawn the rte_eth_dev ports without associated network device, and
if network device is being unbound we get the r
Ferruh Yigit writes:
> On 7/17/2019 7:42 PM, Stephen Hemminger wrote:
>> On Wed, 10 Jul 2019 16:31:59 -0400
>> Aaron Conole wrote:
>>
>>> Stephen Hemminger writes:
>>>
On Wed, 10 Jul 2019 15:13:02 -0400
Aaron Conole wrote:
> Stephen Hemminger writes:
>
>> On W
> -Original Message-
> From: Zhang, Xiao
> Sent: Sunday, July 21, 2019 1:02 AM
> To: dev@dpdk.org
> Cc: Lu, Wenzhuo ; Zhao1, Wei
> ; Zhang, Qi Z ; Zhang, Xiao
> ; sta...@dpdk.org
> Subject: [v2] net/e1000: fix buffer overrun while i219 processing DMA
> transactions
>
> Intel® 100/200 Ser
2019年7月12日(金) 11:22 Yasufumi Ogawa :
> On 2019/07/11 22:14, Burakov, Anatoly wrote:
> > On 11-Jul-19 12:57 PM, Yasufumi Ogawa wrote:
> >> On 2019/07/11 19:53, Burakov, Anatoly wrote:
> >>> On 11-Jul-19 11:31 AM, yasufu...@gmail.com wrote:
> From: Yasufumi Ogawa
>
> >>> <...>
> >>>
> >>>
https://bugs.dpdk.org/show_bug.cgi?id=334
Bug ID: 334
Summary: ConnectX-4/mlx5 crashes under high load in
rxq_cq_decompress_v()
Product: DPDK
Version: 18.11
Hardware: x86
OS: Linux
Status: UNCONF
> -Original Message-
> From: Xing, Beilei
> Sent: Friday, July 19, 2019 1:28 PM
> To: Zhang, Qi Z
> Cc: dev@dpdk.org
> Subject: [PATCH] net/ice: fix unsafe tailq element removal
>
> TAILQ_FOREACH macro is not safe to remove elements during iterating tailq
> lists. Replace it with TAILQ
Unit hang may occur if multiple descriptors are available in the rings
during reset or close. This state can be detected by configure status
by bit 8 in register. If the bit is set and there are pending
descriptors in one of the rings, we must flush them before reset or
close.
Cc: sta...@dpdk.org
On 07/22, Xiao Zhang wrote:
>Unit hang may occur if multiple descriptors are available in the rings
>during reset or close. This state can be detected by configure status
>by bit 8 in register. If the bit is set and there are pending
>descriptors in one of the rings, we must flush them before reset
> -Original Message-
> From: Ye, Xiaolong
> Sent: Monday, July 22, 2019 5:27 PM
> To: Zhang, Xiao
> Cc: dev@dpdk.org; Lu, Wenzhuo ; Zhao1, Wei
> ; sta...@dpdk.org
> Subject: Re: [dpdk-dev] [v6] net/e1000: fix i219 hang on reset/close
>
> On 07/22, Xiao Zhang wrote:
> >Unit hang may occ
Unit hang may occur if multiple descriptors are available in the rings
during reset or close. This state can be detected by configure status
by bit 8 in register. If the bit is set and there are pending
descriptors in one of the rings, we must flush them before reset or
close.
Fixes: 80580344("e10
> On Jul 21, 2019, at 7:24 AM, Viacheslav Ovsiienko
> wrote:
>
> This patch updates Tx datapath definitions, mostly hardware related.
> The Tx descriptor structures are redefined with required fields,
> size definitions are renamed to reflect the meanings in more
> appropriate way. This is a pre
> On Jul 21, 2019, at 7:24 AM, Viacheslav Ovsiienko
> wrote:
>
> This patch removes the existing Tx datapath code
> as preparation step before introducing the new
> implementation. The following entities are being
> removed:
>
> - deprecated devargs support
> - tx_burst() routines
> - related
> On Jul 21, 2019, at 7:24 AM, Viacheslav Ovsiienko
> wrote:
>
> This patch introduces new mlx5 PMD devarg options:
>
> - txq_inline_min - specifies minimal amount of data to be inlined into
> WQE during Tx operations. NICs may require this minimal data amount
> to operate correctly. The exac
> On Jul 21, 2019, at 7:24 AM, Viacheslav Ovsiienko
> wrote:
>
> Mellanox NICs support the wide set of Tx offloads. The supported
> offloads are reported by the mlx5 PMD in rte_eth_dev_info tx_offload_capa
> field. An application may choose any combination of supported offloads
> and configure t
> On Jul 21, 2019, at 7:24 AM, Viacheslav Ovsiienko
> wrote:
>
> This patch updates the Tx datapath control and configuration
> structures and code for mananging Tx datapath settings.
>
> Signed-off-by: Viacheslav Ovsiienko
> ---
Acked-by: Yongseok Koh
> drivers/net/mlx5/mlx5.c | 123
> On Jul 21, 2019, at 7:24 AM, Viacheslav Ovsiienko
> wrote:
>
> This patch extends the NIC attributes query via DevX.
> The appropriate interface structures are borrowed from
> kernel driver headers and DevX calls are added to
> mlx5_devx_cmd_query_hca_attr() routine.
>
> Signed-off-by: Viac
> \On Jul 21, 2019, at 7:25 AM, Viacheslav Ovsiienko
> wrote:
>
> This patch fills the tx_desc_lim.nb_seg_max and
> tx_desc_lim.nb_mtu_seg_max fields of rte_eth_dev_info
> structure to report thee maximal number of packet
> segments, requested inline data configuration is
> taken into account in
> On Jul 21, 2019, at 7:24 AM, Viacheslav Ovsiienko
> wrote:
>
> This patch adds the implementation of tx_burst routine template.
> The template supports all Tx offloads and multiple optimized
> tx_burst routines can be generated by compiler from this one.
>
> Signed-off-by: Viacheslav Ovsiienk
> On Jul 21, 2019, at 7:56 AM, Viacheslav Ovsiienko
> wrote:
>
> The associated device index is retrieved via Netlink request to
> underlying Infiniband device driver. This network device index
> is permanent throughout the lifetime of device. We do not
> spawn the rte_eth_dev ports without asso
> On Jul 21, 2019, at 7:56 AM, Viacheslav Ovsiienko
> wrote:
>
> This reverts commit e28111ac9864af09e826241a915dfff87a9c00ad.
> The netlink requests are replaced by ifindex caching and
> not needed anymore.
>
> Signed-off-by: Viacheslav Ovsiienko
> Fixes: e28111ac9864 ("net/mlx5: fix master
On 07/22, Xiao Zhang wrote:
>Unit hang may occur if multiple descriptors are available in the rings
>during reset or close. This state can be detected by configure status
>by bit 8 in register. If the bit is set and there are pending
>descriptors in one of the rings, we must flush them before reset
HI,
> On 7/18/2019 6:27 AM, Nithin Kumar Dabilpuram wrote:
> > Hi Ferruh,
> >
> > On 7/17/2019 10:21 PM, Ferruh Yigit wrote:
> >> External Email
> >>
> >> -
> >> - On 7/17/2019 1:30 PM, Nithin Dabilpuram wrote:
> >>> With the lates
On 7/22/2019 11:31 AM, Hemant Agrawal wrote:
> HI,
>> On 7/18/2019 6:27 AM, Nithin Kumar Dabilpuram wrote:
>>> Hi Ferruh,
>>>
>>> On 7/17/2019 10:21 PM, Ferruh Yigit wrote:
External Email
-
- On 7/17/2019 1:30
Unit hang may occur if multiple descriptors are available in the rings
during reset or close. This state can be detected by configure status
by bit 8 in register. If the bit is set and there are pending
descriptors in one of the rings, we must flush them before reset or
close.
Fixes: 80580344("e10
There is a bug in function ixgbevf_dev_info_get(), it do not
contain the reta table size get function for vf port, and this
will cause error when update reta for x550 vf port.
Cc: sta...@dpdk.org
Fixes: 2144f6630fca ("ixgbe: add redirection table size in device info")
Signed-off-by: wei zhao
---
This patch removes the unneccessary err prints when using
non-dpaa2 devices.
Fixes: e67a61614d0b ("bus/fslmc: support device iteration")
Signed-off-by: Hemant Agrawal
---
drivers/bus/fslmc/fslmc_bus.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/bus/fslmc/fslmc_bus
fslmc_vfio.c:387:36: note: format string is defined here
DPAA2_BUS_DEBUG("VFIO dmamap 0x%llx:0x%llx, size 0x%llx\n",
format ‘%llx’ expects argument of type ‘long long unsigned int’
argument 6 has type ‘__u64 {aka long unsigned int}’
Fixes: 2b5fa25708cf ("mempool/dpaa2: map external memory with VF
This patch removes the unneccessary err prints when using
non-dpaa devices.
Fixes: e79df833d3f6 ("bus/dpaa: support hotplug ops")
Signed-off-by: Hemant Agrawal
---
drivers/bus/dpaa/dpaa_bus.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/bus/dpaa/dpaa_bus.c b/driver
Hi Ferruh,
>
> On 7/16/2019 2:36 PM, Thomas Monjalon wrote:
> > 16/07/2019 13:40, Ferruh Yigit:
> >> On 7/15/2019 10:53 PM, Thomas Monjalon wrote:
> >>> 15/07/2019 10:44, Hemant Agrawal:
> Nipun Gupta (1):
> bus/fslmc: use cinh read for eqcr ci on ls1088 platform
>
> Sachin
48 matches
Mail list logo
