)]}'
{
  "commit": "7f7bbbe50b8a28f4dfaa4cea939ddb50198c4a99",
  "tree": "6421bee762afd8f09c643e90860c4bdbe4dde93b",
  "parents": [
    "1ca4cb2418c04914e4661c059cf5b7b9262c645a"
  ],
  "author": {
    "name": "Benjamin Herrenschmidt",
    "email": "benh@kernel.crashing.org",
    "time": "Fri Oct 06 00:43:53 2006 -0700"
  },
  "committer": {
    "name": "Linus Torvalds",
    "email": "torvalds@g5.osdl.org",
    "time": "Fri Oct 06 08:53:40 2006 -0700"
  },
  "message": "[PATCH] page fault retry with NOPAGE_REFAULT\n\nAdd a way for a no_page() handler to request a retry of the faulting\ninstruction.  It goes back to userland on page faults and just tries again\nin get_user_pages().  I added a cond_resched() in the loop in that later\ncase.\n\nThe problem I have with signal and spufs is an actual bug affecting apps and I\ndon\u0027t see other ways of fixing it.\n\nIn addition, we are having issues with infiniband and 64k pages (related to\nthe way the hypervisor deals with some HV cards) that will require us to muck\naround with the MMU from within the IB driver\u0027s no_page() (it\u0027s a pSeries\nspecific driver) and return to the caller the same way using NOPAGE_REFAULT.\n\nAnd to add to this, the graphics folks have been following a new approach of\nmemory management that involves transparently swapping objects between video\nram and main meory.  To do that, they need installing PTEs from a no_page()\nhandler as well and that also requires returning with NOPAGE_REFAULT.\n\n(For the later, they are currently using io_remap_pfn_range to install one PTE\nfrom no_page() which is a bit racy, we need to add a check for the PTE having\nalready been installed afer taking the lock, but that\u0027s ok, they are only at\nthe proof-of-concept stage.  I\u0027ll send a patch adding a \"clean\" function to do\nthat, we can use that from spufs too and get rid of the sparsemem hacks we do\nto create struct page for SPEs.  Basically, that provides a generic solution\nfor being able to have no_page() map hardware devices, which is something that\nI think sound driver folks have been asking for some time too).\n\nAll of these things depend on having the NOPAGE_REFAULT exit path from\nno_page() handlers.\n\nSigned-off-by: Benjamin Herrenchmidt \u003cbenh@kernel.crashing.org\u003e\nCc: Hugh Dickins \u003chugh@veritas.com\u003e\nCc: Nick Piggin \u003cnickpiggin@yahoo.com.au\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": "b7966ab8cb6ac42ebd864c62542e01427d5b99eb",
      "old_mode": 33188,
      "old_path": "include/linux/mm.h",
      "new_id": "26146623be2f442949599451376e77b961d8d119",
      "new_mode": 33188,
      "new_path": "include/linux/mm.h"
    },
    {
      "type": "modify",
      "old_id": "9cf3f341a28a6cf4c53af58f01959a9cf7c23eb1",
      "old_mode": 33188,
      "old_path": "mm/memory.c",
      "new_id": "b5a4aadd961adff5839052fd72b3b2cc53c8a43c",
      "new_mode": 33188,
      "new_path": "mm/memory.c"
    }
  ]
}