netdev - Re: [net-next PATCH 0/9] sockmap UAPI updates and fixes

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] [day] [month] [year] [list]

Message-Id: <20170828.111340.995355526422443420.davem@davemloft.net>
Date:   Mon, 28 Aug 2017 11:13:40 -0700 (PDT)
From:   David Miller <davem@...emloft.net>
To:     john.fastabend@...il.com
Cc:     ast@...nel.org, daniel@...earbox.net, netdev@...r.kernel.org
Subject: Re: [net-next PATCH 0/9] sockmap UAPI updates and fixes

From: John Fastabend <john.fastabend@...il.com>
Date: Mon, 28 Aug 2017 07:09:45 -0700

> This series updates sockmap UAPI, adds additional test cases and
> provides a couple fixes.
> 
> First the UAPI changes. The original API added two sockmap specific
> API artifacts (a) a new map_flags field with a sockmap specific update
> command and (b) a new sockmap specific attach field in the attach data
> structure. After this series instead of attaching programs with a
> single command now two commands are used to attach programs to maps
> individually. This allows us to add new programs easily in the future
> and avoids any specific sockmap data structure additions. The
> map_flags field is also removed and instead we allow socks to be
> added to multiple maps that may or may not have programs attached.
> This allows users to decide if a sock should run a SK_SKB program type
> on receive based on the map it is attached to. This is a nice
> improvement. See patches for specific details.
> 
> More test cases were added to test above changes and also stress test
> the interface.
> 
> Finally two fixes/improvements were made. First a missing rcu
> section was added. Second now sockmap can build without KCM being
> used to trigger 'y' on CONFIG_STREAM_PARSER by selecting a new
> BPF config option.

Series applied, thanks John.