Date:   Wed, 12 Dec 2018 14:09:47 +0100
From:   Magnus Karlsson <magnus.karlsson@...el.com>
To:     magnus.karlsson@...el.com, bjorn.topel@...el.com, ast@...nel.org,
        daniel@...earbox.net, netdev@...r.kernel.org,
        jakub.kicinski@...ronome.com, bjorn.topel@...il.com,
        qi.z.zhang@...el.com
Cc:     brouer@...hat.com
Subject: [PATCH bpf-next v2 0/2] libbpf: adding AF_XDP support

This patch proposes to add AF_XDP support to libbpf. The main reason for
this is to facilitate writing applications that use AF_XDP by offering
higher-level APIs that hide many of the details of the AF_XDP
uapi. This is in the same vein as libbpf facilitates XDP adoption by
offering easy-to-use higher level interfaces of XDP
functionality. Hopefully this will facilitate adoption of AF_XDP, make
applications using it simpler and smaller, and finally also make it
possible for applications to benefit from optimizations in the AF_XDP
user space access code. Previously, people just copied and pasted the
code from the sample application into their application, which is not
desirable.

The proposed interface is composed of two parts:

* Low-level access interface to the four rings and the packet
* High-level control plane interface for creating and setting up umems
  and AF_XDP sockets.

The sample program has been updated to use this new interface and in
that process it lost roughly 300 lines of code. I cannot detect any
performance degradations due to the use of this library instead of the
previous functions that were inlined in the sample application. But I
did measure this on a slower machine and not the Broadwell that we
normally use.

One question:

* The libbpf internal struct for the rings are exposed in the libbpf.h
  header file for performance reasons as it is important that the
  application writer has full control on where it is allocated, for
  example on the stack or in a struct together with counters that are
  frequently used. Is there some way to achieve this flexibility but
  still hide this struct from the user? This would allow more
  flexibility for future optimizations.

In a future release, I am planning on adding a higher level data plane
interface too. This will be based around recvmsg and sendmsg with the
use of struct iovec for batching, without the user having to know
anything about the underlying four rings of an AF_XDP socket. There
will be one semantic difference though from the standard recvmsg and
that is that the kernel will fill in the iovecs instead of the
application. But the rest should be the same as the libc versions so
that application writers feel at home.

Patch 1: adds AF_XDP support in libbpf
Patch 2: updates the xdpsock sample application to use the libbpf functions.

Changes v1 to v2:
  * Fixed cleanup of library state on error.
  * Moved API to initial version
  * Prefixed all public functions by xsk__ instead of xsk_
  * Added comment about changed default ring sizes, batch size and umem
    size in the sample application commit message
  * The library now only creates an Rx or Tx ring if the respective
    parameter is != NULL

I based this patch set on bpf-next commit e5c504858a18
("selftests/bpf: skip verifier sockmap tests on kernels without support")

Thanks: Magnus

Magnus Karlsson (2):
  libbpf: add support for using AF_XDP sockets
  samples/bpf: convert xdpsock to use libbpf for AF_XDP access

 samples/bpf/xdpsock_user.c        | 585 +++++++++++---------------------------
 tools/include/uapi/linux/if_xdp.h |  78 +++++
 tools/lib/bpf/Build               |   2 +-
 tools/lib/bpf/Makefile            |   5 +-
 tools/lib/bpf/README.rst          |  11 +-
 tools/lib/bpf/libbpf.h            |  93 ++++++
 tools/lib/bpf/libbpf.map          |   9 +
 tools/lib/bpf/xsk.c               | 568 ++++++++++++++++++++++++++++++++++++
 8 files changed, 928 insertions(+), 423 deletions(-)
 create mode 100644 tools/include/uapi/linux/if_xdp.h
 create mode 100644 tools/lib/bpf/xsk.c

--
2.7.4

Powered by blists - more mailing lists