[PATCH v10 net-next 0/3] filter: add Extended BPF interpreter and converter, seccomp

[Alexei Starovoitov <ast@plumgrid.com>]

Hi All,

V1 patches:
http://thread.gmane.org/gmane.linux.kernel/1605783
V2 patches:
http://thread.gmane.org/gmane.linux.kernel/1642325
V3 patches:
http://thread.gmane.org/gmane.linux.kernel/1656538

V4 summary:
- addressed Daniel comments
- RFC for seccomp with extended BPF
- added extended BPF design doc

V5 summary:
- fixed commit one-liner, removed empty line
- added Hagen's ack

V6 summary:
- unrolled loop in populate_seccomp_data() to help gcc on arm
- removed empty line at the end of the file
- removed redundant (u32) cast in JSET
- fixed BPF_RVAL instead of BPF_SRC for BPF_RET in sk_convert_filter()
- updated commit log
- added Daniel's Reviewed-by
- added Kees's Reviewed-by

V7 summary:
1/3:
- addressed Dave's feedback regarding typecasting:
  added 'jited' flag to sk_filter and union for bpf_func/bpf_func_ext
- added a comment to sk_run_filter_ext() about ctx<->skb relation
- removed CPU specific code from sk_run_filter() and sk_run_filter_ext()
  because of that revised arm32 cache-hit bpf micro-bench numbers slightly
  slower, but seccomp and cache-miss arm32 numbers stayed the same
2/3 and 3/3: no changes

V8 summary:
1/3:
- fixed sk_get_filter() issue caught by Daniel:
  need to save old filter, so it can be returned via sk_get_filter()
  count memory out of socket optmem budget
- addressed Eric's feedback:
  removed 'notrace'
  replaced integer registers constants and stack size with #define
- retested with my own bpf/ebpf testuite, seccomp and Pavel's
  so_get_filter test from crtools/test/zdtm/live/static/
- trimmed cc list, since it looks too big
2/3 and 3/3: no changes

V9 summary:
1/3:
- addressed David's feedback:
- changed priority, so that bpf_jit_enable takes precedence over bpf_ext_enable
- made sk_run_filter_ext() static and private to filter.c
  and added 'ctx == seccomp' and 'ctx == skb' wrappers, so that
  compiler can do 'ctx' type verification at the call site.
  offending union in struct sk_filter now looks like:
  union {
    unsigned int (*bpf_func)(const struct sk_buff *skb,
                             const struct sock_filter *fp);
    unsigned int (*bpf_func_ext)(const struct sk_buff *skb, <<< was void* before
                                 const struct sock_filter_ext *fp);
  }
- kept 'unsigned jited:1', since that's my reading of 'bool vs bitfield' thread
2/3: call sk_run_filter_ext_seccomp(const struct seccomp_data*,...) instead of
     sk_run_filter_ext(void*,...) which is now private
3/3: no change

V10 summary:
1/1:
- addressed David's feedback:
  added conditional #define for bpf_jit_enable
  removed 64-bit requirement from XADD_DW ebpf insn
- silenced gcc warning in arch/arm/net/bpf_jit due to missing seccomp_data
- cleaned up stack[64] with stack[ARRAY_SIZE(stack)]
2/3 and 3/3: no changes

x86_64, i386 and arm32 look clean.

Thanks!

Alexei Starovoitov (3):
  filter: add Extended BPF interpreter and converter
  seccomp: convert seccomp to use extended BPF
  doc: filter: add Extended BPF documentation

 Documentation/networking/filter.txt |  181 ++++++++
 arch/arm/net/bpf_jit_32.c           |    3 +-
 arch/powerpc/net/bpf_jit_comp.c     |    3 +-
 arch/s390/net/bpf_jit_comp.c        |    3 +-
 arch/sparc/net/bpf_jit_comp.c       |    3 +-
 arch/x86/net/bpf_jit_comp.c         |    3 +-
 include/linux/filter.h              |   47 +-
 include/linux/netdevice.h           |    5 +
 include/linux/seccomp.h             |    1 -
 include/net/sock.h                  |    4 +-
 include/uapi/linux/filter.h         |   33 +-
 kernel/seccomp.c                    |  118 +++--
 net/core/filter.c                   |  857 ++++++++++++++++++++++++++++++++++-
 net/core/sysctl_net_core.c          |    7 +
 14 files changed, 1158 insertions(+), 110 deletions(-)

-- 
1.7.9.5