lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAKgT0UdXqzAPWwtn7z=2LEaiKvPNEjpd++MwNvytpqfUSQZoeg@mail.gmail.com>
Date:	Wed, 1 Jun 2016 18:23:07 -0700
From:	Alexander Duyck <alexander.duyck@...il.com>
To:	Alexander Duyck <aduyck@...antis.com>
Cc:	Netdev <netdev@...r.kernel.org>, David Miller <davem@...emloft.net>
Subject: Re: [net-next PATCH 1/2] net: Add function to allow configuration of RPS

On Wed, Jun 1, 2016 at 6:17 PM, Alexander Duyck <aduyck@...antis.com> wrote:
> This patch gives drivers the ability to set their own default RPS
> configuration.  The general idea is to allow drivers that might benefit
> from enabling RPS an opportunity to configure it for themselves.
>
> Signed-off-by: Alexander Duyck <aduyck@...antis.com>
> ---
>  include/linux/netdevice.h |    9 ++++++++
>  net/core/dev.c            |   51 ++++++++++++++++++++++++++++++++++++++++++++-
>  net/core/net-sysfs.c      |   45 +++++++---------------------------------
>  3 files changed, 67 insertions(+), 38 deletions(-)
>
> diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
> index f45929ce8157..329d554c9219 100644
> --- a/include/linux/netdevice.h
> +++ b/include/linux/netdevice.h
> @@ -684,6 +684,15 @@ static inline void rps_record_sock_flow(struct rps_sock_flow_table *table,
>  bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, u32 flow_id,
>                          u16 filter_id);
>  #endif
> +int netif_set_rps_cpus(struct net_device *dev, const struct cpumask *mask,
> +                      u16 index);
> +#else
> +static inline int netif_set_rps_cpus(struct net_device *dev,
> +                                    const struct cpumask *mask,
> +                                    u16 index)
> +{
> +       return 0;
> +}
>  #endif /* CONFIG_RPS */
>
>  /* This structure contains an instance of an RX queue. */
> diff --git a/net/core/dev.c b/net/core/dev.c
> index 904ff431d570..efdcc917cf02 100644
> --- a/net/core/dev.c
> +++ b/net/core/dev.c
> @@ -1934,7 +1934,7 @@ static void netif_setup_tc(struct net_device *dev, unsigned int txq)
>                 return;
>         }
>
> -       /* Invalidated prio to tc mappings set to TC0 */
> +       /* Invaldated prio to tc mappings set to TC0 */
>         for (i = 1; i < TC_BITMASK + 1; i++) {
>                 int q = netdev_get_prio_tc_map(dev, i);
>

I just noticed that I fat fingered this when doing some last edits on
the patch.  So I will be submitting a v2.

For now I will leave this out here for review, and I will wait to see
if there are any other changes needed after others have had a chance
to look over the rest of this patch set.

- Alex

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ