On Tue, 2020-12-15 at 07:18 +0200, Leon Romanovsky wrote:
> On Mon, Dec 14, 2020 at 11:15:01AM -0800, Joe Perches wrote:
> > I prefer revisions to single patches (as opposed to large patch series)
> > in the same thread.
>
> It depends which side you are in that game. From the reviewer point of
>
On 12/15/20 12:07 AM, Willem de Bruijn wrote:
> On Mon, Dec 14, 2020 at 3:56 PM Jakub Kicinski wrote:
>>
>> On Sun, 13 Dec 2020 20:59:54 -0500 Willem de Bruijn wrote:
>>> On Sun, Dec 13, 2020 at 2:37 PM Vasily Averin wrote:
>> On 12/11/20 6:37 PM, Vasily Averin wrote:
>>> It seems for me
> From: Alexander Duyck
> Sent: Tuesday, December 15, 2020 7:24 AM
>
> On Mon, Dec 14, 2020 at 1:49 PM Saeed Mahameed
> wrote:
> >
> > Hi Dave, Jakub, Jason,
> >
>
> Just to clarify a few things for myself. You mention virtualization and SR-IOV
> in your patch description but you cannot suppor
On Mon, 2020-12-14 at 17:53 -0800, Alexander Duyck wrote:
> On Mon, Dec 14, 2020 at 1:49 PM Saeed Mahameed
> wrote:
> > Hi Dave, Jakub, Jason,
> >
> > This series form Parav was the theme of this mlx5 release cycle,
> > we've been waiting anxiously for the auxbus infrastructure to make
> > it int
On Mon, Dec 14, 2020 at 09:37:34PM -0800, Joe Perches wrote:
> On Tue, 2020-12-15 at 07:18 +0200, Leon Romanovsky wrote:
> > On Mon, Dec 14, 2020 at 11:15:01AM -0800, Joe Perches wrote:
> > > I prefer revisions to single patches (as opposed to large patch series)
> > > in the same thread.
> >
> > I
Kdoc does not like it when multiline comment follows the networking
style of starting right on the first line:
include/linux/phy.h:869: warning: Function parameter or member 'config_intr'
not described in 'phy_driver'
Signed-off-by: Jakub Kicinski
---
include/linux/phy.h | 3 ++-
1 file change
From: Bongsu Jeon
Remove the unused NCI prop commands that s3fwrn5 driver doesn't use.
Signed-off-by: Bongsu Jeon
---
drivers/nfc/s3fwrn5/nci.c | 25 -
drivers/nfc/s3fwrn5/nci.h | 22 --
2 files changed, 47 deletions(-)
diff --git a/drivers/nfc/s3fw
From: Bongsu Jeon
Refactor the s3fwrn5 module.
1/2 is to remove the unneeded delay for NFC sleep.
2/2 is to remove the unused NCI prop commands.
ChangeLog:
v2:
- Update the commit messages.
Bongsu Jeon (2):
nfc: s3fwrn5: Remove the delay for NFC sleep
nfc: s3fwrn5: Remove unused NCI pro
From: Bongsu Jeon
Remove the delay for NFC sleep because the delay is only needed to
guarantee that the NFC is awake.
Signed-off-by: Bongsu Jeon
---
drivers/nfc/s3fwrn5/phy_common.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/nfc/s3fwrn5/phy_common.c b/drivers
On Tue, 2020-12-08 at 16:25 -0800, David Miller wrote:
> From: Zheng Yongjun
> Date: Tue, 8 Dec 2020 21:56:25 +0800
>
> > Simplify the return expression.
> >
> > Signed-off-by: Zheng Yongjun
>
> Applied.
>
Hey Dave, it's great to have you back!
I still don't see this patch in net-next, i wi
On Wed, 2020-12-09 at 15:01 +0800, Zou Wei wrote:
> Remove including that don't need it.
>
> Fixes: 17a7612b99e6 ("net/mlx5_core: Clean driver version and name")
> Signed-off-by: Zou Wei
> ---
Applied to net-next-mlx5.
Thanks!
This commit adds support for configuring HTB in offload mode. HTB
offload eliminates the single qdisc lock in the datapath and offloads
the algorithm to the NIC. The new 'offload' parameter is added to
enable this mode:
# tc qdisc replace dev eth0 root handle 1: htb offload
Classes are create
The existing qdiscs that set TCQ_F_MQROOT don't use sch_tree_lock.
However, hardware-offloaded HTB will start setting this flag while also
using sch_tree_lock.
The current implementation of sch_tree_lock basically locks on
qdisc->dev_queue->qdisc, and it works fine when the tree is attached to
som
This series adds support for HTB offload to the HTB qdisc, and adds
usage to mlx5 driver.
The previous RFCs are available at [1], [2].
The feature is intended to solve the performance bottleneck caused by
the single lock of the HTB qdisc, which prevents it from scaling well.
The HTB algorithm its
This commit adds support for statistics of offloaded HTB. Bytes and
packets counters for leaf and inner nodes are supported, the values are
taken from per-queue qdiscs, and the numbers that the user sees should
have the same behavior as the software (non-offloaded) HTB.
Signed-off-by: Maxim Mikity
On Tue, Dec 15, 2020 at 07:01:25AM +1100, Stephen Rothwell wrote:
> Hi all,
>
> On Thu, 26 Nov 2020 17:40:57 +1100 Stephen Rothwell
> wrote:
> >
> > After merging the net-next tree, today's linux-next build (htmldocs)
> > produced this warning:
> >
> > include/linux/phy.h:869: warning: Function
This commit adds support for HTB offload in the mlx5e driver.
Performance:
NIC: Mellanox ConnectX-6 Dx
CPU: Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz (24 cores with HT)
100 Gbit/s line rate, 500 UDP streams @ ~200 Mbit/s each
48 traffic classes, flower used for steering
No shaping (rat
HTB doesn't scale well because of contention on a single lock, and it
also consumes CPU. This patch adds support for offloading HTB to
hardware that supports hierarchical rate limiting.
This solution addresses two main problems of scaling HTB:
1. Contention by flow classification. Currently the f
> -Original Message-
> From: Willem de Bruijn [mailto:willemdebruijn.ker...@gmail.com]
> Sent: Tuesday, December 15, 2020 10:46 AM
> To: wangyunjian
> Cc: Network Development ; Michael S. Tsirkin
> ; Jason Wang ; Willem de Bruijn
> ; virtualizat...@lists.linux-foundation.org;
> Lilijun (Je
301 - 319 of 319 matches
Mail list logo
