)]}'
{
  "log": [
    {
      "commit": "05be18241e83d2ac6b656c8f924e74b3998c173f",
      "tree": "4f0637e3fb5116fa259130b75a5dfdcb3e3335e7",
      "parents": [
        "518fbf9cdf17875d808596afd77fc115a6f942ca"
      ],
      "author": {
        "name": "Jan Seiffert",
        "email": "kaffeemonster@googlemail.com",
        "time": "Sun Apr 29 19:02:19 2012 +0000"
      },
      "committer": {
        "name": "David S. Miller",
        "email": "davem@davemloft.net",
        "time": "Mon Apr 30 13:40:50 2012 -0400"
      },
      "message": "bpf jit: Let the powerpc jit handle negative offsets\n\nNow the helper function from filter.c for negative offsets is exported,\nit can be used it in the jit to handle negative offsets.\n\nFirst modify the asm load helper functions to handle:\n- know positive offsets\n- know negative offsets\n- any offset\n\nthen the compiler can be modified to explicitly use these helper\nwhen appropriate.\n\nThis fixes the case of a negative X register and allows to lift\nthe restriction that bpf programs with negative offsets can\u0027t\nbe jited.\n\nTested-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nSigned-off-by: Jan Seiffert \u003ckaffeemonster@googlemail.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n"
    },
    {
      "commit": "0ca87f05ba8bdc6791c14878464efc901ad71e99",
      "tree": "c37e25b30c22adae633dcacb2236e83086887418",
      "parents": [
        "3aeb7d2243e55ddcad3c0b402e7b09619a67f5da"
      ],
      "author": {
        "name": "Matt Evans",
        "email": "matt@ozlabs.org",
        "time": "Wed Jul 20 15:51:00 2011 +0000"
      },
      "committer": {
        "name": "David S. Miller",
        "email": "davem@davemloft.net",
        "time": "Thu Jul 21 12:38:32 2011 -0700"
      },
      "message": "net: filter: BPF \u0027JIT\u0027 compiler for PPC64\n\nAn implementation of a code generator for BPF programs to speed up packet\nfiltering on PPC64, inspired by Eric Dumazet\u0027s x86-64 version.\n\nFilter code is generated as an ABI-compliant function in module_alloc()\u0027d mem\nwith stackframe \u0026 prologue/epilogue generated if required (simple filters don\u0027t\nneed anything more than an li/blr).  The filter\u0027s local variables, M[], live in\nregisters.  Supports all BPF opcodes, although \"complicated\" loads from negative\npacket offsets (e.g. SKF_LL_OFF) are not yet supported.\n\nThere are a couple of further optimisations left for future work; many-pass\nassembly with branch-reach reduction and a register allocator to push M[]\nvariables into volatile registers would improve the code quality further.\n\nThis currently supports big-endian 64-bit PowerPC only (but is fairly simple\nto port to PPC32 or LE!).\n\nEnabled in the same way as x86-64:\n\n\techo 1 \u003e /proc/sys/net/core/bpf_jit_enable\n\nOr, enabled with extra debug output:\n\n\techo 2 \u003e /proc/sys/net/core/bpf_jit_enable\n\nSigned-off-by: Matt Evans \u003cmatt@ozlabs.org\u003e\nAcked-by: Eric Dumazet \u003ceric.dumazet@gmail.com\u003e\nSigned-off-by: David S. Miller \u003cdavem@davemloft.net\u003e\n"
    }
  ]
}