)]}'
{
  "log": [
    {
      "commit": "1189be6508d45183013ddb82b18f4934193de274",
      "tree": "58924481b4de56699e4a884dce8dc601e71cf7d1",
      "parents": [
        "287e5d6fcccfa38b953cebe307e1ddfd32363355"
      ],
      "author": {
        "name": "Paul Mackerras",
        "email": "paulus@samba.org",
        "time": "Thu Oct 11 20:37:10 2007 +1000"
      },
      "committer": {
        "name": "Paul Mackerras",
        "email": "paulus@samba.org",
        "time": "Fri Oct 12 14:05:17 2007 +1000"
      },
      "message": "[POWERPC] Use 1TB segments\n\nThis makes the kernel use 1TB segments for all kernel mappings and for\nuser addresses of 1TB and above, on machines which support them\n(currently POWER5+, POWER6 and PA6T).\n\nWe detect that the machine supports 1TB segments by looking at the\nibm,processor-segment-sizes property in the device tree.\n\nWe don\u0027t currently use 1TB segments for user addresses \u003c 1T, since\nthat would effectively prevent 32-bit processes from using huge pages\nunless we also had a way to revert to using 256MB segments.  That\nwould be possible but would involve extra complications (such as\nkeeping track of which segment size was used when HPTEs were inserted)\nand is not addressed here.\n\nParts of this patch were originally written by Ben Herrenschmidt.\n\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n"
    },
    {
      "commit": "7f2c85777db26c120821bc1c9b8273a30a705a09",
      "tree": "49f2f0ea2208e98b9a5998bccc34ec0d13b8e533",
      "parents": [
        "b41848031ac16aee8d045e86f0b7ad3ba97e961e"
      ],
      "author": {
        "name": "Ishizaki Kou",
        "email": "kou.ishizaki@toshiba.co.jp",
        "time": "Tue Oct 02 18:23:46 2007 +1000"
      },
      "committer": {
        "name": "Paul Mackerras",
        "email": "paulus@samba.org",
        "time": "Wed Oct 03 13:25:28 2007 +1000"
      },
      "message": "[POWERPC] Celleb: New HTAB Guest OS Interface on Beat\n\nThis changes the Celleb code to work with new Guest OS Interface\nto tweak HTAB on Beat. It detects old and new Guest OS Interfaces\nautomatically.\n\nSigned-off-by: Kou Ishizaki \u003cKou.Ishizaki@toshiba.co.jp\u003e\nAcked-by: Arnd Bergmann \u003carnd.bergmann@de.ibm.com\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n"
    },
    {
      "commit": "67439b76f29cb278bb3412fc873b980fc65110c9",
      "tree": "d70c627453d429f63c777769f5596184c001fe39",
      "parents": [
        "5628244059976009151d41c2798855290753d8d5"
      ],
      "author": {
        "name": "Michael Neuling",
        "email": "mikey@neuling.org",
        "time": "Fri Aug 03 11:55:39 2007 +1000"
      },
      "committer": {
        "name": "Paul Mackerras",
        "email": "paulus@samba.org",
        "time": "Fri Aug 03 19:36:01 2007 +1000"
      },
      "message": "[POWERPC] Fixes for the SLB shadow buffer code\n\nOn a machine with hardware 64kB pages and a kernel configured for a\n64kB base page size, we need to change the vmalloc segment from 64kB\npages to 4kB pages if some driver creates a non-cacheable mapping in\nthe vmalloc area.  However, we never updated with SLB shadow buffer.\nThis fixes it.  Thanks to paulus for finding this.\n\nAlso added some write barriers to ensure the shadow buffer contents\nare always consistent.\n\nSigned-off-by: Michael Neuling \u003cmikey@neuling.org\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n"
    },
    {
      "commit": "b7abc5c53e3c65b8e931bd96db2d08ba670e111a",
      "tree": "73e0a02db68d570e875b57acb3d08e9ae85473ac",
      "parents": [
        "7ccb4a662462616f6be5053e26b79580e02f1529"
      ],
      "author": {
        "name": "Sachin P. Sant",
        "email": "sachinp@in.ibm.com",
        "time": "Thu Jun 14 15:31:34 2007 +1000"
      },
      "committer": {
        "name": "Paul Mackerras",
        "email": "paulus@samba.org",
        "time": "Mon Jun 25 17:03:33 2007 +1000"
      },
      "message": "[POWERPC] Fix Kexec/Kdump for power6\n\nOn Power machines supporting VRMA, Kexec/Kdump does not work.\nVRMA (virtual real-mode area) means that accesses with IR/DR \u003d 0\n(i.e. the MMU \"off\") actually still go through the hash table,\nusing entries put there by the hypervisor.\n\nThis means that when we clear out the hash table on kexec, we need to\nmake sure these entries are left untouched.\n\nThis also adds plpar_pte_read_raw() on the lines of\nplpar_pte_remove_raw().\n\nSigned-off-by : Sachin Sant \u003csachinp@in.ibm.com\u003e\nSigned-off-by : Mohan Kumar M \u003cmohan@in.ibm.com\u003e\nAcked-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nAcked-by: Olof Johansson \u003colof@lixom.net\u003e\n\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n"
    },
    {
      "commit": "8e561e7eda02819c711a75b64a000bf34948cdbb",
      "tree": "ecbb09ccf6095006bb2d98172c0bac33c78e598d",
      "parents": [
        "9c709f3b62ee8ee0dfadf358e361802cab7eea7a"
      ],
      "author": {
        "name": "David Gibson",
        "email": "david@gibson.dropbear.id.au",
        "time": "Wed Jun 13 14:52:56 2007 +1000"
      },
      "committer": {
        "name": "Paul Mackerras",
        "email": "paulus@samba.org",
        "time": "Thu Jun 14 22:30:16 2007 +1000"
      },
      "message": "[POWERPC] Kill typedef-ed structs for hash PTEs and BATs\n\nUsing typedefs to rename structure types if frowned on by CodingStyle.\nHowever, we do so for the hash PTE structure on both ppc32 (where it\u0027s\ncalled \"PTE\") and ppc64 (where it\u0027s called \"hpte_t\").  On ppc32 we\nalso have such a typedef for the BATs (\"BAT\").\n\nThis removes this unhelpful use of typedefs, in the process\nbringing ppc32 and ppc64 closer together, by using the name \"struct\nhash_pte\" in both cases.\n\nSigned-off-by: David Gibson \u003cdavid@gibson.dropbear.id.au\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n"
    },
    {
      "commit": "2454c7e98c0dd0aff29dfe1ee369801507f4d6a5",
      "tree": "3f95e3254d698a84cab15059ad4819919e99f593",
      "parents": [
        "de1132173a81ae11aaa6af11ed9ded5f0c565c87"
      ],
      "author": {
        "name": "Paul Mackerras",
        "email": "paulus@samba.org",
        "time": "Thu May 10 15:28:44 2007 +1000"
      },
      "committer": {
        "name": "Paul Mackerras",
        "email": "paulus@samba.org",
        "time": "Thu May 10 21:28:13 2007 +1000"
      },
      "message": "[POWERPC] Fix warning in hpte_decode(), and generalize it\n\nThis adds the necessary support to hpte_decode() to handle 1TB\nsegments and 16GB pages, and removes an uninitialized value\nwarning on avpn.\n\nWe don\u0027t have any code to generate HPTEs for 1TB segments or 16GB\npages yet, so this is mostly for completeness, and to fix the\nwarning.\n\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\nAcked-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n"
    },
    {
      "commit": "d0f13e3c20b6fb73ccb467bdca97fa7cf5a574cd",
      "tree": "a2de01a21dbb28449893102742e6b516a519c03e",
      "parents": [
        "16f1c746755836aa823658000493cdab8ce7b098"
      ],
      "author": {
        "name": "Benjamin Herrenschmidt",
        "email": "benh@kernel.crashing.org",
        "time": "Tue May 08 16:27:27 2007 +1000"
      },
      "committer": {
        "name": "Paul Mackerras",
        "email": "paulus@samba.org",
        "time": "Wed May 09 16:35:00 2007 +1000"
      },
      "message": "[POWERPC] Introduce address space \"slices\"\n\nThe basic issue is to be able to do what hugetlbfs does but with\ndifferent page sizes for some other special filesystems; more\nspecifically, my need is:\n\n - Huge pages\n\n - SPE local store mappings using 64K pages on a 4K base page size\nkernel on Cell\n\n - Some special 4K segments in 64K-page kernels for mapping a dodgy\ntype of powerpc-specific infiniband hardware that requires 4K MMU\nmappings for various reasons I won\u0027t explain here.\n\nThe main issues are:\n\n - To maintain/keep track of the page size per \"segment\" (as we can\nonly have one page size per segment on powerpc, which are 256MB\ndivisions of the address space).\n\n - To make sure special mappings stay within their allotted\n\"segments\" (including MAP_FIXED crap)\n\n - To make sure everybody else doesn\u0027t mmap/brk/grow_stack into a\n\"segment\" that is used for a special mapping\n\nSome of the necessary mechanisms to handle that were present in the\nhugetlbfs code, but mostly in ways not suitable for anything else.\n\nThe patch relies on some changes to the generic get_unmapped_area()\nthat just got merged.  It still hijacks hugetlb callbacks here or\nthere as the generic code hasn\u0027t been entirely cleaned up yet but\nthat shouldn\u0027t be a problem.\n\nSo what is a slice ?  Well, I re-used the mechanism used formerly by our\nhugetlbfs implementation which divides the address space in\n\"meta-segments\" which I called \"slices\".  The division is done using\n256MB slices below 4G, and 1T slices above.  Thus the address space is\ndivided currently into 16 \"low\" slices and 16 \"high\" slices.  (Special\ncase: high slice 0 is the area between 4G and 1T).\n\nDoing so simplifies significantly the tracking of segments and avoids\nhaving to keep track of all the 256MB segments in the address space.\n\nWhile I used the \"concepts\" of hugetlbfs, I mostly re-implemented\neverything in a more generic way and \"ported\" hugetlbfs to it.\n\nSlices can have an associated page size, which is encoded in the mmu\ncontext and used by the SLB miss handler to set the segment sizes.  The\nhash code currently doesn\u0027t care, it has a specific check for hugepages,\nthough I might add a mechanism to provide per-slice hash mapping\nfunctions in the future.\n\nThe slice code provide a pair of \"generic\" get_unmapped_area() (bottomup\nand topdown) functions that should work with any slice size.  There is\nsome trickiness here so I would appreciate people to have a look at the\nimplementation of these and let me know if I got something wrong.\n\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n"
    },
    {
      "commit": "8d2169e8d6b8a91413df33bc402e0f602ceaabcc",
      "tree": "4de3e19d8cd9a09049e531e4cc1f02b2328b943c",
      "parents": [
        "173ba87b9584e4cba41ce9a06916eba80baa1bf4"
      ],
      "author": {
        "name": "David Gibson",
        "email": "david@gibson.dropbear.id.au",
        "time": "Fri Apr 27 11:53:52 2007 +1000"
      },
      "committer": {
        "name": "Paul Mackerras",
        "email": "paulus@samba.org",
        "time": "Fri Apr 27 21:14:26 2007 +1000"
      },
      "message": "[POWERPC] Prepare for splitting up mmu.h by MMU type\n\nCurrently asm-powerpc/mmu.h has definitions for the 64-bit hash based\nMMU.  If CONFIG_PPC64 is not set, it instead includes asm-ppc/mmu.h\nwhich contains a particularly horrible mess of #ifdefs giving the\ndefinitions for all the various 32-bit MMUs.\n\nIt would be nice to have the low level definitions for each MMU type\nneatly in their own separate files.  It would also be good to wean\narch/powerpc off dependence on the old asm-ppc/mmu.h.\n\nThis patch makes a start on such a cleanup by moving the definitions\nfor the 64-bit hash MMU to their own file, asm-powerpc/mmu_hash64.h.\nDefinitions for the other MMUs still all come from asm-ppc/mmu.h,\nhowever each MMU type can now be one-by-one moved over to their own\nfile, in the process cleaning them up stripping them of cruft no\nlonger necessary in arch/powerpc.\n\nSigned-off-by: David Gibson \u003cdavid@gibson.dropbear.id.au\u003e\nSigned-off-by: Paul Mackerras \u003cpaulus@samba.org\u003e\n"
    }
  ]
}