)]}'
{
  "commit": "66d43e98ea6ff291cd4e524386bfb99105feb180",
  "tree": "56cff27261a3f9b16022c9ec8d53e4913f758eb9",
  "parents": [
    "ff9569bc5558e958777fd43580f2ccd83733cdf6"
  ],
  "author": {
    "name": "Haren Myneni",
    "email": "haren@us.ibm.com",
    "time": "Mon Dec 12 00:37:39 2005 -0800"
  },
  "committer": {
    "name": "Linus Torvalds",
    "email": "torvalds@g5.osdl.org",
    "time": "Mon Dec 12 08:57:45 2005 -0800"
  },
  "message": "[PATCH] fix in __alloc_bootmem_core() when there is no free page in first node\u0027s memory\n\nHitting BUG_ON() in __alloc_bootmem_core() when there is no free page\navailable in the first node\u0027s memory.  For the case of kdump on PPC64\n(Power 4 machine), the captured kernel is used two memory regions - memory\nfor TCE tables (tce-base and tce-size at top of RAM and reserved) and\ncaptured kernel memory region (crashk_base and crashk_size).  Since we\nreserve the memory for the first node, we should be returning from\n__alloc_bootmem_core() to search for the next node (pg_dat).\n\nCurrently, find_next_zero_bit() is returning the n^th bit (eidx) when there\nis no free page.  Then, test_bit() is failed since we set 0xff only for the\nactual size initially (init_bootmem_core()) even though rounded up to one\npage for bdata-\u003enode_bootmem_map.  We are hitting the BUG_ON after failing\nto enter second \"for\" loop.\n\nSigned-off-by: Haren Myneni \u003charen@us.ibm.com\u003e\nCc: Andy Whitcroft \u003capw@shadowen.org\u003e\nCc: Dave Hansen \u003chaveblue@us.ibm.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n",
  "tree_diff": [
    {
      "type": "modify",
      "old_id": "e8c567177dcf83e0b8d7352c581c0565c400844c",
      "old_mode": 33188,
      "old_path": "mm/bootmem.c",
      "new_id": "16b9465eb4ebb385114558dcacdaf7af21678612",
      "new_mode": 33188,
      "new_path": "mm/bootmem.c"
    }
  ]
}