From: Hyong Youb Kim
Move a number of Rx functions to the header file so that the avx2
based Rx handler can use them.
Signed-off-by: Hyong Youb Kim
Reviewed-by: John Daley
---
v3: re-add Reviewed-by
drivers/net/enic/enic_rxtx.c| 263 +-
drivers/net/en
From: Hyong Youb Kim
Add the vectorized version of the no-scatter Rx handler. It aims to
process 8 descriptors per loop using AVX2 SIMD instructions. This
handler is in its own file enic_rxtx_vec_avx2.c, and makefile and
meson.build are modified to compile it when the compiler supports
AVX2. Unde
>
> Hi Honnappa,
>
> Reply inlined:
Hi Yipeng,
Thank you so much for reviewing.
>
> >-Original Message-
> >
> >Currently, reader-writer concurrency problems in rte_hash are
> >addressed using reader-writer locks. Use of reader-writer locks
> >results in following issues:
> >
This patch set was part of extendable hash table patch
set before V2. According to Bruce's comment, this patch set
is now separated from the original patch set for easier
review and merge.
https://mails.dpdk.org/archives/dev/2018-September/112555.html
This patch set fixes multiple issues/bugs from
The test_hash_readwrite.c was not in the meson.build file. This
commit adds the missing test into the file.
Fixes: 0eb3726ebcf1 ("test/hash: add test for read/write concurrency")
Cc: sta...@dpdk.org
Signed-off-by: Yipeng Wang
Acked-by: Bruce Richardson
---
test/test/meson.build | 1 +
1 file c
the multi-reader and multi-writer rte_hash unit test does not
work correctly with non-consecutive core ids. This commit
fixes the issue.
Fixes: 0eb3726ebcf1 ("test/hash: add test for read/write concurrency")
Cc: sta...@dpdk.org
Signed-off-by: Yipeng Wang
Tested-by: Bruce Richardson
Acked-by: Br
Edit the printf information when error happens to be more
accurate and informative.
Signed-off-by: Yipeng Wang
Acked-by: Bruce Richardson
---
test/test/test_hash_perf.c | 10 +-
1 file changed, 5 insertions(+), 5 deletions(-)
diff --git a/test/test/test_hash_perf.c b/test/test/test_has
Since the depth-first search of cuckoo path is removed, we do not
need the macro anymore which specifies the depth of the cuckoo
search.
Fixes: f2e3001b53ec ("hash: support read/write concurrency")
Cc: sta...@dpdk.org
Signed-off-by: Yipeng Wang
Acked-by: Bruce Richardson
---
lib/librte_hash/rt
The bucket size was changed from 4 to 8 but the corresponding
perf test was not changed accordingly.
In the test, the bucket size and number of buckets are used
to map to the underneath rte_hash structure. They are used
to test performance of two conditions: keys in primary
buckets only and keys i
rte_flow has 'group' attribute and 'jump' action in order to support
multiple groups. This feature is known as multi-table support ('chain' in
linux TC flower) in general because a group means a table of flows. Example
commands are:
flow create 0 transfer priority 1 ingress
pa
rte_flow has 'group' attribute and 'jump' action in order to support
multiple groups. This feature is known as multi-table support ('chain' in
linux TC flower) in general because a group means a table of flows. Example
commands are:
flow create 0 transfer priority 1 ingress
pa
rte_flow has 'group' attribute and 'jump' action in order to support
multiple groups. This feature is known as multi-table support ('chain' in
linux TC flower) in general because a group means a table of flows. Example
commands are:
flow create 0 transfer priority 1 ingress
pa
On Tue, Sep 25, 2018 at 07:51:06PM +0800, Xiaoyu Min wrote:
> Offload the following rte_flow actions by inserting accordingly
> E-Switch rules via TC Flower driver
>
> - RTE_FLOW_ACTION_TYPE_SET_IPV4_SRC
> - RTE_FLOW_ACTION_TYPE_SET_IPV4_DST
> - RTE_FLOW_ACTION_TYPE_SET_IPV6_SRC
> - RTE_FLOW_A
On Thu, Sep 27, 2018 at 11:40:59AM +0100, Anatoly Burakov wrote:
> When we allocate and use DPDK memory, we need to be able to
> differentiate between DPDK hugepage segments and segments that
> were made part of DPDK but are externally allocated. Add such
> a property to memseg lists.
>
> This bre
>-Original Message-
>From: dev [mailto:dev-boun...@dpdk.org] On Behalf Of Jananee Parthasarathy
>Sent: Wednesday, September 26, 2018 11:41 PM
>To: dev@dpdk.org
>Cc: Richardson, Bruce ; De Lara Guarch, Pablo
>; Pattan, Reshma
>; Somarowthu, Naga SureshX
>
>Subject: [dpdk-dev] [PATCH] test:
This patch set made two major optimizations over the current rte_hash
library.
First, it adds Extendable Bucket Table feature: a new structure that can
accommodate keys that failed to get inserted into the main hash table due to
the unlikely event of excessive hash collisions. The hash table bucke
This commit changes the hashing mechanism to "partial-key
hashing" to calculate bucket index and signature of key.
This is proposed in Bin Fan, et al's paper
"MemC3: Compact and Concurrent MemCache with Dumber Caching
and Smarter Hashing". Bascially the idea is to use "xor" to
derive alternative
In rte_hash_iterate, the reader lock did not protect the
while loop which checks empty entry. This created a race
condition that the entry may become empty when enters
the lock, then a wrong key data value would be read out.
This commit extends the protected region.
Fixes: f2e3001b53ec ("hash: su
In use cases that hash table capacity needs to be guaranteed,
the extendable bucket feature can be used to contain extra
keys in linked lists when conflict happens. This is similar
concept to the extendable bucket hash table in packet
framework.
This commit adds the extendable bucket feature. User
This commit changes the current rte_hash unit test to
test the extendable table feature and performance.
Signed-off-by: Yipeng Wang
---
test/test/test_hash.c | 159 +++--
test/test/test_hash_perf.c | 114 +++-
2 files chang
>-Original Message-
>From: Honnappa Nagarahalli [mailto:honnappa.nagaraha...@arm.com]
>> several times */ -#define BUCKET_SIZE 4
>> +#define BUCKET_SIZE 8
>May be we should add a comment to warn that it should be same as '
>RTE_HASH_BUCKET_ENTRIES'?
>
[Wang, Yipeng] Done in V4, Thanks for
>-Original Message-
>From: Honnappa Nagarahalli [mailto:honnappa.nagaraha...@arm.com]
>> Second, the patch set changes the current hashing algorithm to be "partial-
>> key hashing". Partial-key hashing is the concept from Bin Fan, et al.'s paper
>> "MemC3: Compact and Concurrent MemCache wi
>-Original Message-
>From: Honnappa Nagarahalli [mailto:honnappa.nagaraha...@arm.com]
>Sent: Wednesday, September 26, 2018 9:24 PM
>To: Wang, Yipeng1 ; Richardson, Bruce
>
>Cc: dev@dpdk.org; mic...@digirati.com.br
>Subject: RE: [PATCH v2 6/7] test/hash: implement extendable bucket hash
>-Original Message-
>From: Honnappa Nagarahalli [mailto:honnappa.nagaraha...@arm.com]
>Sent: Wednesday, September 26, 2018 9:24 PM
>To: Wang, Yipeng1 ; Richardson, Bruce
>
>Cc: dev@dpdk.org; mic...@digirati.com.br
>Subject: RE: [PATCH v2 7/7] hash: use partial-key hashing
>
>
>> +static in
>-Original Message-
>From: Honnappa Nagarahalli [mailto:honnappa.nagaraha...@arm.com]
>>
>> Extendable bucket table composes of buckets that can be linked list to
>> current
>> main table. When extendable bucket is enabled, the table utilization can
>> always acheive 100%.
>IMO, referring
Sure. Anyway there is an error log to indicate the error.
I will send v3 later. Thanks.
From: Stephen Hemminger [mailto:step...@networkplumber.org]
Sent: Friday, September 28, 2018 20:47
To: Li, Xiaoyun
Cc: Yigit, Ferruh ; Thomas Monjalon
; Zhang, Helin ;
damar...@cisco.com; Kinsella, Ray ; dev
From: Somnath Kotur
bnxt_start_xmit() was attempting to access an uninitialized ptr - txbd1
which would lead to segmentation fault.
Fix to initialize ptr to NULL and check for the same before access.
Fixes: f10258e39ec2 ("net/bnxt: fix HW Tx checksum offload check")
Cc: sta...@dpdk.org
Signed-o
The HW can support maximum frame length of 9600 bytes.
And we are currently capping the max frame size to 9500 bytes.
Fixes: daef48efe5e5 ("net/bnxt: support set MTU")
Cc: sta...@dpdk.org
Signed-off-by: Ajit Khaparde
---
drivers/net/bnxt/bnxt.h| 2 +-
drivers/net/bnxt/bnxt_ethdev.c | 1
Patchset against dpdk-next-net.
v1->v2:
net/bnxt: get rid of ff pools array and use the vnic info array instead
- Fix access to uninitialized variable.
- Rectify the wrong 'Fixes' reference.
net/bnxt: update HWRM version
- Update from 1.9.2.45 to version 1.9.2.53
v2->v3:
net/bnxt: update HWRM ve
From: Somnath Kotur
There was no direct association between the rxq's VNIC and the vnic_info[].
Explicitly associate the two in bnxt_mq_rx_configure().
Fixes: 0a256e4a548b ("net/bnxt: fix Rx ring count limitation")
Cc: sta...@dpdk.org
Signed-off-by: Somnath Kotur
--
v1->v2:
- Fix access to unin
Update the HWRM API to version 1.9.2.53
This is second part of the patch.
Signed-off-by: Ajit Khaparde
--
v1->v2:
Update from 1.9.2.45 to version 1.9.2.53
v2->v3:
Split the patch into smaller patches
---
drivers/net/bnxt/hsi_struct_def_dpdk.h | 1153
1 file changed, 1153
For hardware having multiple embedded management processors the firmware
has added support to indicate if the comm channel to the processor has
been enabled. If the channel is enabled, switch the CFA NTUPLE and EM
filtering commands to use the kong channel.
Signed-off-by: Ajit Khaparde
---
drive
This patch adds support extended port statistics like COS bytes,
packets, XON -> XOFF and XOFF -> XONÂ transitions in Tx and Rx path.
Signed-off-by: Ajit Khaparde
---
drivers/net/bnxt/bnxt.h| 8 ++
drivers/net/bnxt/bnxt_ethdev.c | 30 -
drivers/net/bnxt/bnxt_hwrm.c | 44 +++
From: yongping
While registering vf's event completion ring to FW, use the wrong
macro, FW doesn't set up the event completion ring successfully,
VF can't receive any async event.
Fixes: 4535cad39515 ("net/bnxt: handle VF/PF initialization appropriately")
Cc: sta...@dpdk.org
Signed-off-by: Yong
We need to set HWRM_CFA_L2_FILTER_ALLOC_INPUT_FLAGS_OUTERMOST bit in
L2_FILTER_ALLOC for filtering non-tunnel packets based on outermost MAC.
Fixes: f92735db1e4c ("net/bnxt: add L2 filter alloc/init/free")
Cc: sta...@dpdk.org
Signed-off-by: Ajit Khaparde
--
v1->v2:
Add "Fixes" to the commit mess
In the current model, VFs are not trusted.
So it is not allowed to send many HWRM commands.
Newer firmware has added support to allow VF to be trusted.
Now the VF queries if it is a trusted entity and based on that
it can send HWRM commands to the firmware.
Signed-off-by: Ajit Khaparde
---
drive
If a vnic is configured as default and the setting has not changed,
there is no need to issue this setting again to the FW.
Fixes: db678d5c2b54 ("net/bnxt: add HWRM VNIC configure")
Cc: sta...@dpdk.org
Signed-off-by: Ajit Khaparde
--
v1->v2:
Add "Fixes" to commit message
---
drivers/net/bnxt/bn
From: Bei Sun
Firmware sets pf pair in default VNIC cfg. If the VLAN strip
setting is not available at this time, it will not be
configured correctly in the CFA.
Set the desired VLAN strip mode before default VNIC configuration.
Fixes: 7fe5668d2ea3 ("net/bnxt: support VLAN filter and strip")
Cc:
When the firmware version and the driver HWRM version do not match,
we are logging some messages. These messages unnecessarily clutter
the logs and can add to the noise. We are logging the HWRM version
and the firmware version anyway. The difference in version numbers
can be gleaned from that. Remo
From: Xiaoxin Peng
Change polling interval for valid bit in bnxt_hwrm_send_message
Poll every 1us instead of 600us.
Fixes: 804e746c7b73 ("net/bnxt: add hardware resource manager init code")
Cc: sta...@dpdk.org
Signed-off-by: Xiaoxin Peng
Reviewed-by: Ajit Khaparde
---
drivers/net/bnxt/bnxt_h
> -Original Message-
> From: Xing, Beilei
> Sent: Friday, September 28, 2018 2:11 PM
> To: Zhang, Qi Z
> Cc: dev@dpdk.org; Yigit, Ferruh ; Wu, Jingjing
> ; Rawat, Anand ; Menon,
> Ranjit ; sta...@dpdk.org
> Subject: RE: [PATCH] net/i40e: fix send admin queue command before init
>
>
>
Some users want to use their own epoll instances to control both
DPDK rxq interrupt fds and their own other fds. So added a function
to get rxq interrupt fd based on port id and queue id.
Signed-off-by: Xiaoyun Li
---
v3:
* Since the API only wants to return fd, return fd or -1.
v2:
* Added mis
> -Original Message-
> From: Xing, Beilei
> Sent: Thursday, September 27, 2018 3:39 PM
> To: Zhang, Qi Z
> Cc: dev@dpdk.org; Yigit, Ferruh ; Zhang, Helin
> ; Zhang, Qi Z
> Subject: RE: [dpdk-dev] [PATCH 00/20] base code update
>
>
>
> > -Original Message-
> > From: dev [mail
> +:Pair Name: "avg_packet_thresh"
> +:Description: Threshold below which the frequency will be set to min for
> + the TRAFFIC policy. If the traffic rate is above this and below max, the
> + frequency will be set to medium.
> +:Type: integer
> +:Values: The number of packets below which the TRAF
> -Original Message-
> From: Li, Xiaoyun
> Sent: Thursday, September 27, 2018 5:22 PM
> To: dev@dpdk.org; Zhang, Qi Z ; Xing, Beilei
> ; Lu, Wenzhuo ; Wu, Jingjing
>
> Cc: Li, Xiaoyun
> Subject: [PATCH 0/2] remove unnecessary call of rte intr enable
>
> Since rte_intr_enable is called
If link handling periodic function is allowed to be called in interrupt
context, the periodic function can get called too frequently and exhaust
the retry credits to check link status.
This change makes sure link handling periodic function is not called in
interrupt context.
Fixes: 540a211084a7 (
This patch adds phy_lock, acquire/release the lock when performing
PHY transactions. Without this fix driver can run into synchronization
issues with management FW when modifying PHY settings.
Fixes: 540a211084a7 ("bnx2x: driver core")
Cc: sta...@dpdk.org
Signed-off-by: Rasesh Mody
---
drivers/
Fix to disable further fastpath/slowpath interrupts. These will be
enabled again by their respective handlers
Fixes: 540a211084a7 ("bnx2x: driver core")
Cc: sta...@dpdk.org
Signed-off-by: Rasesh Mody
---
drivers/net/bnx2x/bnx2x.c |6 ++
1 file changed, 6 insertions(+)
diff --git a/driv
Anatoly, thanks for your review, please see comment as below.
On 9/26/2018 8:28 PM, Burakov, Anatoly wrote:
On 17-Aug-18 11:51 AM, Jeff Guo wrote:
This patch will add req notifier processing to enable hotplug for vfio.
When device is be hotplug-out, the vfio kernel module will sent req
notifier
On 9/26/2018 8:22 PM, Burakov, Anatoly wrote:
On 17-Aug-18 11:51 AM, Jeff Guo wrote:
There are some extended interrupt types in vfio pci device except
from the
existing interrupts, such as err and req notifier, it could be useful
for
device error monitoring. And these corresponding interrupt
> -Original Message-
> From: Thomas Monjalon [mailto:tho...@monjalon.net]
> Sent: Wednesday, September 26, 2018 9:51 PM
> To: Zhang, Qi Z
> Cc: dev@dpdk.org; Burakov, Anatoly ; Yigit,
> Ferruh ; geoffrey...@gmail.com;
> ajit.khapa...@broadcom.com; sta...@dpdk.org
> Subject: Re: [dpdk-de
101 - 151 of 151 matches
Mail list logo
