From: Lance Richardson
The function bnxt_vnic_rss_configure_thor() returns early when
all receive queues are stopped without releasing the hwrm
spinlock, which causes subsequent HWRM operations to hang. Fix
by ensuring that the lock is released before returning from
this function.
Fixes: 3841230
From: Lance Richardson
Controller-specific handling is required for Thor-based NICs when
stopping or starting a receive queue, otherwise packet reception
may not be reliably resumed when a stopped receive queue is
restarted:
- The VNIC default receive ring needs to be recomputed when a
rece
From: Lance Richardson
Receive queue state needs to reflect "started" state when rebuilding
the RSS table for Thor-based NICs. Move state update so that receive
queues being started are included in the RSS table.
Fixes: 38412304b50a ("net/bnxt: enable RSS for thor-based controllers")
Cc: sta...@
On Mon, Nov 4, 2019 at 2:50 PM Ajit Khaparde
wrote:
> v2->v3:
> Sending with updated the commit logs for patch 1 & 2
>
>
> Ajit Khaparde (1):
> net/bnxt: fix incorrect COS queue mapping
>
> Kalesh AP (2):
> net/bnxt: fix L4 checksum indication in non-vector Rx
> net/bnxt: fix a failure case
On Mon, Nov 4, 2019 at 3:02 PM Ajit Khaparde
wrote:
> This patch set fixes several problems involving stopping/starting
> receive queues in the bnxt PMD.
>
> --
> v1->v2: Updated commit logs for consistency.
>
> Lance Richardson (4):
> net/bnxt: fix RSS table update for start/stop rxq
> net/b
The original design is to use rte_mbuf::udata64 to save the metadata of
protocol extraction which has network protocol data fields and type, a
private API is used to decode this metadata. It is not so generic.
Use the new dynamic mbuf field and flags to handle protocol extraction.
Then the metadat
The original design is to use rte_mbuf::udata64 to save the metadata of
protocol extraction which has network protocol data fields and type, a
private API is used to decode this metadata. It is not so generic.
Use the new dynamic mbuf field and flags to handle protocol extraction.
Then the metadat
When doing a cross compiling it is common to use EXTRA_CFLAGS with
--sysroot option to point to alternate root filesystem. This already
works as expected for objects and executables, it just doesn't work
correctly for shared libraries.
When a shared library is linked using CC this flag needs to
be
On 11/04, Min JiaqiX wrote:
>Max frame size is not set to HW, so packets above the MTU
>do not get dropped by HW. The patch fixed the issue.
>
>Fixes: 50370662b727 ("net/ice: support device and queue ops")
>Cc: sta...@dpdk.org
>
>Signed-off-by: Min JiaqiX
>
>---
>v5:
>* Set `ICE_FRAME_SIZE_MAX` to
Yes, I know this bug, will fix it in the next version.
-Original Message-
From: Stillwell Jr, Paul M
Sent: Monday, November 4, 2019 23:03
To: Yang, Qiming ; dev@dpdk.org
Cc: Lu, Wenzhuo ; Yang, Qiming ;
sta...@dpdk.org
Subject: RE: [dpdk-dev] [PATCH] net/ice: fix link status recovery
>
To avoid wild pointer and memory leak, following resources management
should be added.
- Check if the FDIR Memzone already exists before reserving.
- Free FDIR memzone when teardown and other failure scenarios.
- Set pointers to NULL after free them.
- Release all counter resources when teardown.
Hi David,
> -Original Message-
> From: David Marchand
> Sent: Tuesday, November 5, 2019 2:18 AM
> To: Hemant Agrawal
>
> On Mon, Nov 4, 2019 at 12:24 PM Hemant Agrawal
> wrote:
> >
> > dpaa and dpaa2 config have evolved to be same. The same binaray
>
> binary*
>
> > can now work acro
Fixes: d5ea22e9f4a5 ("net/ice: configure HW FDIR rule")
Cc: beilei.x...@intel.com
Signed-off-by: Yahui Cao
---
drivers/net/ice/ice_fdir_filter.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ice/ice_fdir_filter.c
b/drivers/net/ice/ice_fdir_filter.c
index 736ccd
> -Original Message-
> From: Wang, ShougangX
> Sent: Tuesday, November 5, 2019 4:44 AM
> To: dev@dpdk.org
> Cc: Yang, Qiming ; Xing, Beilei
> ; Cao, Yahui ; Wang, ShougangX
> ; sta...@dpdk.org
> Subject: [PATCH] net/ice: fix memory release in FDIR
>
> To avoid wild pointer and memory le
This patch fix a kernel driver link status issue by recovering
link status when device stop.
Fixes: e6161345d8a9 ("net/ice: support link status change")
Cc: sta...@dpdk.org
Signed-off-by: Qiming Yang
---
drivers/net/ice/ice_ethdev.c | 26 +-
drivers/net/ice/ice_ethdev.h
This patch fix a kernel driver link status issue by recovering
link status when device stop.
Fixes: e6161345d8a9 ("net/ice: support link status change")
Cc: sta...@dpdk.org
Signed-off-by: Qiming Yang
---
drivers/net/ice/ice_ethdev.c | 27 ++-
drivers/net/ice/ice_ethdev.h
> -Original Message-
> From: Cao, Yahui
> Sent: Tuesday, November 5, 2019 7:37 PM
> To: Yang, Qiming ; Lu, Wenzhuo
>
> Cc: dev@dpdk.org; Zhang, Qi Z ; Cao, Yahui
> ; Ye, Xiaolong ; Xing, Beilei
>
> Subject: [PATCH] net/ice: fix tunnel profile existence check
>
The patch looks OK for
If first rule is issued and then the second rule is issued with the same
input set as first rule's, FDIR driver can't find there is an identical
input set.
Fixes: d5ea22e9f4a5 ("net/ice: configure HW FDIR rule")
Cc: beilei.x...@intel.com
Signed-off-by: Yahui Cao
---
drivers/net/ice/ice_fdir_fil
Hi, Beilei
> -Original Message-
> From: Xing, Beilei
> Sent: Tuesday, November 5, 2019 1:09 PM
> To: Wang, ShougangX ; dev@dpdk.org
> Cc: Yang, Qiming ; Cao, Yahui
> ; sta...@dpdk.org
> Subject: RE: [PATCH] net/ice: fix memory release in FDIR
>
>
>
> > -Original Message-
> > Fro
https://bugs.dpdk.org/show_bug.cgi?id=360
Bug ID: 360
Summary: FIPS application fails for AES-GCM test vectors with
non-zero AAD
Product: DPDK
Version: 19.08
Hardware: All
OS: All
Status: UNCONFI
On 11/4/19 9:37 PM, Ori Kam wrote:
>> -Original Message-
>> From: Andrew Rybchenko
>> Sent: Sunday, November 3, 2019 1:41 PM
>> To: Ori Kam ; Thomas Monjalon
>>
>> Cc: dev@dpdk.org; pbhagavat...@marvell.com; ferruh.yi...@intel.com;
>> jer...@marvell.com; John McNamara ; Marko
>> Kovacevic
1. Do not select vector path if DEV_RX_OFFLOAD_FLOW_MARK is required.
2. return error when a rte_flow rule require software mark action while
DEV_RX_OFFLOAD_FLOW_MARK is not configured.
Signed-off-by: Qi Zhang
---
This patch depends on patchset:
http://patchwork.dpdk.org/project/dpdk/list/?se
NIC address conflicts on 64K pagesize when using multiple NICs,
as system will mmap 64K pagesize for NIC,
but dev->mem_resource[i].len is 16K.
Signed-off-by: Beard-627
Signed-off-by: Eric wang
Acked-by: Wei Hu
Acked-by: Min Hu
---
drivers/bus/pci/linux/pci.c | 5 +
1 file changed, 5 ins
To avoid wild pointer and memory leak, following resources management
should be added.
- Check if the FDIR Memzone already exists before reserving.
- Free FDIR memzone when teardown and other failure scenarios.
Fixes: 84dc7a95a2d3 ("net/ice: enable flow director engine")
Cc: sta...@dpdk.org
Signe
Currently PMD doesn't check whether the user specified ethernet type is
conflicting with the followed IPv4/IPv6 items, which leads to HW refuse
to create rule, for example:
... pattern eth type is 0x86dd / ipv4 / end ...
ethernet type is IPv6 but IPv4 is following, this should be validated
as f
101 - 125 of 125 matches
Mail list logo
