)]}'
{
  "commit": "f69b17d7e745d8edd7c0d90390cbaa77e63c5ea3",
  "tree": "d903954135e29cd882220180d39cef1df30795b8",
  "parents": [
    "dfbbe89e197a77f2c8046a51c74e33e35f878080"
  ],
  "author": {
    "name": "Lai Jiangshan",
    "email": "laijs@cn.fujitsu.com",
    "time": "Fri Mar 20 17:40:06 2009 +0800"
  },
  "committer": {
    "name": "Ingo Molnar",
    "email": "mingo@elte.hu",
    "time": "Tue Mar 31 00:09:37 2009 +0200"
  },
  "message": "rcu: rcu_barrier VS cpu_hotplug: Ensure callbacks in dead cpu are migrated to online cpu\n\ncpu hotplug may happen asynchronously, some rcu callbacks are maybe\nstill on dead cpu, rcu_barrier() also needs to wait for these rcu\ncallbacks to complete, so we must ensure callbacks in dead cpu are\nmigrated to online cpu.\n\nPaul E. McKenney\u0027s review:\n\n  Good stuff, Lai!!!  Simpler than any of the approaches that I was\n  considering, and, better yet, independent of the underlying RCU\n  implementation!!!\n\n  I was initially worried that wake_up() might wake only one of two\n  possible wait_event()s, namely rcu_barrier() and the CPU_POST_DEAD code,\n  but the fact that wait_event() clears WQ_FLAG_EXCLUSIVE avoids that issue.\n  I was also worried about the fact that different RCU implementations have\n  different mappings of call_rcu(), call_rcu_bh(), and call_rcu_sched(), but\n  this is OK as well because we just get an extra (harmless) callback in the\n  case that they map together (for example, Classic RCU has call_rcu_sched()\n  mapping to call_rcu()).\n\n  Overlap of CPU-hotplug operations is prevented by cpu_add_remove_lock,\n  and any stray callbacks that arrive (for example, from irq handlers\n  running on the dying CPU) either are ahead of the CPU_DYING callbacks on\n  the one hand (and thus accounted for), or happened after the rcu_barrier()\n  started on the other (and thus don\u0027t need to be accounted for).\n\nSigned-off-by: Lai Jiangshan \u003claijs@cn.fujitsu.com\u003e\nReviewed-by: Paul E. McKenney \u003cpaulmck@linux.vnet.ibm.com\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nLKML-Reference: \u003c49C36476.1010400@cn.fujitsu.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n",
  "tree_diff": [
    {
      "type": "modify",
      "old_id": "cae8a059cf47f4fab142b001c5f4d25ec8e95006",
      "old_mode": 33188,
      "old_path": "kernel/rcupdate.c",
      "new_id": "2c7b8457d0d234203517f7aa6a1ddc6b724ef447",
      "new_mode": 33188,
      "new_path": "kernel/rcupdate.c"
    }
  ]
}
