)]}'
{
  "commit": "561920a0d2bb6d63343e83acfd784c0a77bd28d1",
  "tree": "7b87d9d867296d4a14e9b287129fcfd0b2cd1b47",
  "parents": [
    "e78042e5b83936b1d12a4b5bbb492bdd88ad76c6"
  ],
  "author": {
    "name": "Suresh Siddha",
    "email": "suresh.b.siddha@intel.com",
    "time": "Thu Oct 30 18:28:41 2008 +0100"
  },
  "committer": {
    "name": "Jens Axboe",
    "email": "jens.axboe@oracle.com",
    "time": "Thu Nov 06 08:41:56 2008 +0100"
  },
  "message": "generic-ipi: fix the smp_mb() placement\n\nsmp_mb() is needed (to make the memory operations visible globally) before\nsending the ipi on the sender and the receiver (on Alpha atleast) needs\nsmp_read_barrier_depends() in the handler before reading the call_single_queue\nlist in a lock-free fashion.\n\nOn x86, x2apic mode register accesses for sending IPI\u0027s don\u0027t have serializing\nsemantics. So the need for smp_mb() before sending the IPI becomes more\ncritical in x2apic mode.\n\nRemove the unnecessary smp_mb() in csd_flag_wait(), as the presence of that\nsmp_mb() doesn\u0027t mean anything on the sender, when the ipi receiver is not\ndoing any thing special (like memory fence) after clearing the CSD_FLAG_WAIT.\n\nSigned-off-by: Suresh Siddha \u003csuresh.b.siddha@intel.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n",
  "tree_diff": [
    {
      "type": "modify",
      "old_id": "f362a85537777619d1ef22602042fba351a75e7d",
      "old_mode": 33188,
      "old_path": "kernel/smp.c",
      "new_id": "75c8dde58c55fcdd2f0ae71f75ceb05213e0985e",
      "new_mode": 33188,
      "new_path": "kernel/smp.c"
    }
  ]
}