)]}'
{
  "commit": "93ce99e849433ede4ce8b410b749dc0cad1100b2",
  "tree": "0481209f97a05a3851f536b2e16bd2868f83d842",
  "parents": [
    "26a3e99160cfb06a0a33e25b9fb0d516e2cc680d"
  ],
  "author": {
    "name": "Venki Pallipadi",
    "email": "venkatesh.pallipadi@intel.com",
    "time": "Mon Nov 17 14:43:58 2008 -0800"
  },
  "committer": {
    "name": "Ingo Molnar",
    "email": "mingo@elte.hu",
    "time": "Tue Nov 18 00:15:02 2008 +0100"
  },
  "message": "x86: add rdtsc barrier to TSC sync check\n\nImpact: fix incorrectly marked unstable TSC clock\n\nPatch (commit 0d12cdd \"sched: improve sched_clock() performance\") has\na regression on one of the test systems here.\n\nWith the patch, I see:\n\n checking TSC synchronization [CPU#0 -\u003e CPU#1]:\n Measured 28 cycles TSC warp between CPUs, turning off TSC clock.\n Marking TSC unstable due to check_tsc_sync_source failed\n\nWhereas, without the patch syncs pass fine on all CPUs:\n\n checking TSC synchronization [CPU#0 -\u003e CPU#1]: passed.\n\nDue to this, TSC is marked unstable, when it is not actually unstable.\nThis is because syncs in check_tsc_wrap() goes away due to this commit.\n\nAs per the discussion on this thread, correct way to fix this is to add\nexplicit syncs as below?\n\nSigned-off-by: Venkatesh Pallipadi \u003cvenkatesh.pallipadi@intel.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n",
  "tree_diff": [
    {
      "type": "modify",
      "old_id": "9ffb01c31c40a8c9083e9949d065a442a62f46b7",
      "old_mode": 33188,
      "old_path": "arch/x86/kernel/tsc_sync.c",
      "new_id": "1c0dfbca87c18a05beb42cebaa8e9ffed6d508a1",
      "new_mode": 33188,
      "new_path": "arch/x86/kernel/tsc_sync.c"
    }
  ]
}