)]}'
{
  "commit": "dfbf4a1bc319f0f9a31e39b2da1fa5c55e85af89",
  "tree": "0b9dd19406c53a93452dd345bb05f76aa712a757",
  "parents": [
    "cb4ad1ffc7c0d8ea7dc8cd8ba303d83551716d46"
  ],
  "author": {
    "name": "Ingo Molnar",
    "email": "mingo@elte.hu",
    "time": "Wed Apr 23 09:24:06 2008 +0200"
  },
  "committer": {
    "name": "Ingo Molnar",
    "email": "mingo@elte.hu",
    "time": "Mon May 05 23:56:18 2008 +0200"
  },
  "message": "sched: fix cpu clock\n\nDavid Miller pointed it out that nothing in cpu_clock() sets\nprev_cpu_time. This caused __sync_cpu_clock() to be called\nall the time - against the intention of this code.\n\nThe result was that in practice we hit a global spinlock every\ntime cpu_clock() is called - which - even though cpu_clock()\nis used for tracing and debugging, is suboptimal.\n\nWhile at it, also:\n\n- move the irq disabling to the outest layer,\n  this should make cpu_clock() warp-free when called with irqs\n  enabled.\n\n- use long long instead of cycles_t - for platforms where cycles_t\n  is 32-bit.\n\nReported-by: David Miller \u003cdavem@davemloft.net\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n",
  "tree_diff": [
    {
      "type": "modify",
      "old_id": "f98f75f3c708414d14d60f49a6cc81a5c79d25e3",
      "old_mode": 33188,
      "old_path": "kernel/sched.c",
      "new_id": "9457106b18af066182da7476c86125dbad191ddc",
      "new_mode": 33188,
      "new_path": "kernel/sched.c"
    }
  ]
}