)]}'
{
  "commit": "abf4868b8548cae18d4fe8bbfb4e207443be01be",
  "tree": "0a8900bb5413826bc1f3ac9ccc435c4750dfedab",
  "parents": [
    "f6d9dd237da400effb265f3554c64413f8a3e7b4"
  ],
  "author": {
    "name": "Peter Zijlstra",
    "email": "a.p.zijlstra@chello.nl",
    "time": "Fri Nov 20 22:19:49 2009 +0100"
  },
  "committer": {
    "name": "Ingo Molnar",
    "email": "mingo@elte.hu",
    "time": "Sat Nov 21 14:11:37 2009 +0100"
  },
  "message": "perf: Fix PERF_FORMAT_GROUP scale info\n\nAs Corey reported, the total_enabled and total_running times\ncould occasionally be 0, even though there were events counted.\n\nIt turns out this is because we record the times before reading\nthe counter while the latter updates the times.\n\nThis patch corrects that.\n\nWhile looking at this code I found that there is a lot of\nlocking iffyness around, the following patches correct most of\nthat.\n\nReported-by: Corey Ashford \u003ccjashfor@linux.vnet.ibm.com\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nLKML-Reference: \u003c20091120212508.685559857@chello.nl\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n",
  "tree_diff": [
    {
      "type": "modify",
      "old_id": "68fbf4ff68883d2bb86c4a2134101d713c359b9f",
      "old_mode": 33188,
      "old_path": "kernel/perf_event.c",
      "new_id": "9a18ff28ea5b6d2add93251d4269b92e7f771605",
      "new_mode": 33188,
      "new_path": "kernel/perf_event.c"
    }
  ]
}