)]}'
{
  "log": [
    {
      "commit": "f0cd2dbb6cf387c11f87265462e370bb5469299e",
      "tree": "21c9b6237dd9131763654a6cd715461177701607",
      "parents": [
        "d42d1dabf34bdd5ad832cb56a7338817aad8a052"
      ],
      "author": {
        "name": "Artem Bityutskiy",
        "email": "artem.bityutskiy@linux.intel.com",
        "time": "Wed Jul 25 18:11:59 2012 +0300"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Sat Aug 04 01:24:44 2012 +0400"
      },
      "message": "vfs: kill write_super and sync_supers\n\nFinally we can kill the \u0027sync_supers\u0027 kernel thread along with the\n\u0027-\u003ewrite_super()\u0027 superblock operation because all the users are gone.\nNow every file-system is supposed to self-manage own superblock and\nits dirty state.\n\nThe nice thing about killing this thread is that it improves power management.\nIndeed, \u0027sync_supers\u0027 is a source of monotonic system wake-ups - it woke up\nevery 5 seconds no matter what - even if there were no dirty superblocks and\neven if there were no file-systems using this service (e.g., btrfs and\njournalled ext4 do not need it). So it was wasting power most of the time. And\nbecause the thread was in the core of the kernel, all systems had to have it.\nSo I am quite happy to make it go away.\n\nInterestingly, this thread is a left-over from the pdflush kernel thread which\nwas a self-forking kernel thread responsible for all the write-back in old\nLinux kernels. It was turned into per-block device BDI threads, and\n\u0027sync_supers\u0027 was a left-over. Thus, R.I.P, pdflush as well.\n\nSigned-off-by: Artem Bityutskiy \u003cartem.bityutskiy@linux.intel.com\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "a0e881b7c189fa2bd76c024dbff91e79511c971d",
      "tree": "0c801918565b08921d21aceee5b326f64d998f5f",
      "parents": [
        "eff0d13f3823f35d70228cd151d2a2c89288ff32",
        "dbc6e0222d79e78925fe20733844a796a4b72cf9"
      ],
      "author": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Wed Aug 01 10:26:23 2012 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Wed Aug 01 10:26:23 2012 -0700"
      },
      "message": "Merge branch \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs\n\nPull second vfs pile from Al Viro:\n \"The stuff in there: fsfreeze deadlock fixes by Jan (essentially, the\n  deadlock reproduced by xfstests 068), symlink and hardlink restriction\n  patches, plus assorted cleanups and fixes.\n\n  Note that another fsfreeze deadlock (emergency thaw one) is *not*\n  dealt with - the series by Fernando conflicts a lot with Jan\u0027s, breaks\n  userland ABI (FIFREEZE semantics gets changed) and trades the deadlock\n  for massive vfsmount leak; this is going to be handled next cycle.\n  There probably will be another pull request, but that stuff won\u0027t be\n  in it.\"\n\nFix up trivial conflicts due to unrelated changes next to each other in\ndrivers/{staging/gdm72xx/usb_boot.c, usb/gadget/storage_common.c}\n\n* \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (54 commits)\n  delousing target_core_file a bit\n  Documentation: Correct s_umount state for freeze_fs/unfreeze_fs\n  fs: Remove old freezing mechanism\n  ext2: Implement freezing\n  btrfs: Convert to new freezing mechanism\n  nilfs2: Convert to new freezing mechanism\n  ntfs: Convert to new freezing mechanism\n  fuse: Convert to new freezing mechanism\n  gfs2: Convert to new freezing mechanism\n  ocfs2: Convert to new freezing mechanism\n  xfs: Convert to new freezing code\n  ext4: Convert to new freezing mechanism\n  fs: Protect write paths by sb_start_write - sb_end_write\n  fs: Skip atime update on frozen filesystem\n  fs: Add freezing handling to mnt_want_write() / mnt_drop_write()\n  fs: Improve filesystem freezing handling\n  switch the protection of percpu_counter list to spinlock\n  nfsd: Push mnt_want_write() outside of i_mutex\n  btrfs: Push mnt_want_write() outside of i_mutex\n  fat: Push mnt_want_write() outside of i_mutex\n  ...\n"
    },
    {
      "commit": "068535f1fef4c90aee23eb7b9b9a71c5b72d7cd0",
      "tree": "ca71858417d881bc8f72f4a2a7b035d041f7a43c",
      "parents": [
        "2d534926205db9ffce4bbbde67cb9b2cee4b835c"
      ],
      "author": {
        "name": "J. Bruce Fields",
        "email": "bfields@redhat.com",
        "time": "Wed Aug 01 07:56:16 2012 -0400"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Wed Aug 01 09:01:46 2012 -0700"
      },
      "message": "locks: remove unused lm_release_private\n\nIn commit 3b6e2723f32d (\"locks: prevent side-effects of\nlocks_release_private before file_lock is initialized\") we removed the\nlast user of lm_release_private without removing the field itself.\n\nSigned-off-by: J. Bruce Fields \u003cbfields@redhat.com\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n"
    },
    {
      "commit": "ac694dbdbc403c00e2c14d10bc7b8412cc378259",
      "tree": "e37328cfbeaf43716dd5914cad9179e57e84df76",
      "parents": [
        "a40a1d3d0a2fd613fdec6d89d3c053268ced76ed",
        "437ea90cc3afdca5229b41c6b1d38c4842756cb9"
      ],
      "author": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Tue Jul 31 19:25:39 2012 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Tue Jul 31 19:25:39 2012 -0700"
      },
      "message": "Merge branch \u0027akpm\u0027 (Andrew\u0027s patch-bomb)\n\nMerge Andrew\u0027s second set of patches:\n - MM\n - a few random fixes\n - a couple of RTC leftovers\n\n* emailed patches from Andrew Morton \u003cakpm@linux-foundation.org\u003e: (120 commits)\n  rtc/rtc-88pm80x: remove unneed devm_kfree\n  rtc/rtc-88pm80x: assign ret only when rtc_register_driver fails\n  mm: hugetlbfs: close race during teardown of hugetlbfs shared page tables\n  tmpfs: distribute interleave better across nodes\n  mm: remove redundant initialization\n  mm: warn if pg_data_t isn\u0027t initialized with zero\n  mips: zero out pg_data_t when it\u0027s allocated\n  memcg: gix memory accounting scalability in shrink_page_list\n  mm/sparse: remove index_init_lock\n  mm/sparse: more checks on mem_section number\n  mm/sparse: optimize sparse_index_alloc\n  memcg: add mem_cgroup_from_css() helper\n  memcg: further prevent OOM with too many dirty pages\n  memcg: prevent OOM with too many dirty pages\n  mm: mmu_notifier: fix freed page still mapped in secondary MMU\n  mm: memcg: only check anon swapin page charges for swap cache\n  mm: memcg: only check swap cache pages for repeated charging\n  mm: memcg: split swapin charge function into private and public part\n  mm: memcg: remove needless !mm fixup to init_mm when charging\n  mm: memcg: remove unneeded shmem charge type\n  ...\n"
    },
    {
      "commit": "a509bc1a9e487d952d9404318f7f990166ab57a7",
      "tree": "40a8f8a20877da8a5b855cfbc3813c0874605093",
      "parents": [
        "62c230bc1790923a1b35da03596a68a6c9b5b100"
      ],
      "author": {
        "name": "Mel Gorman",
        "email": "mgorman@suse.de",
        "time": "Tue Jul 31 16:44:57 2012 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Tue Jul 31 18:42:47 2012 -0700"
      },
      "message": "mm: swap: implement generic handler for swap_activate\n\nThe version of swap_activate introduced is sufficient for swap-over-NFS\nbut would not provide enough information to implement a generic handler.\nThis patch shuffles things slightly to ensure the same information is\navailable for aops-\u003eswap_activate() as is available to the core.\n\nNo functionality change.\n\nSigned-off-by: Mel Gorman \u003cmgorman@suse.de\u003e\nAcked-by: Rik van Riel \u003criel@redhat.com\u003e\nCc: Christoph Hellwig \u003chch@infradead.org\u003e\nCc: David S. Miller \u003cdavem@davemloft.net\u003e\nCc: Eric B Munson \u003cemunson@mgebm.net\u003e\nCc: Eric Paris \u003ceparis@redhat.com\u003e\nCc: James Morris \u003cjmorris@namei.org\u003e\nCc: Mel Gorman \u003cmgorman@suse.de\u003e\nCc: Mike Christie \u003cmichaelc@cs.wisc.edu\u003e\nCc: Neil Brown \u003cneilb@suse.de\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Sebastian Andrzej Siewior \u003csebastian@breakpoint.cc\u003e\nCc: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\nCc: Xiaotian Feng \u003cdfeng@redhat.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n"
    },
    {
      "commit": "62c230bc1790923a1b35da03596a68a6c9b5b100",
      "tree": "46b300a00929087627e029b0f4d53e486a97ba7f",
      "parents": [
        "18022c5d8627a7a9ba8097a0f238b513fae6f5b8"
      ],
      "author": {
        "name": "Mel Gorman",
        "email": "mgorman@suse.de",
        "time": "Tue Jul 31 16:44:55 2012 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Tue Jul 31 18:42:47 2012 -0700"
      },
      "message": "mm: add support for a filesystem to activate swap files and use direct_IO for writing swap pages\n\nCurrently swapfiles are managed entirely by the core VM by using -\u003ebmap to\nallocate space and write to the blocks directly.  This effectively ensures\nthat the underlying blocks are allocated and avoids the need for the swap\nsubsystem to locate what physical blocks store offsets within a file.\n\nIf the swap subsystem is to use the filesystem information to locate the\nblocks, it is critical that information such as block groups, block\nbitmaps and the block descriptor table that map the swap file were\nresident in memory.  This patch adds address_space_operations that the VM\ncan call when activating or deactivating swap backed by a file.\n\n  int swap_activate(struct file *);\n  int swap_deactivate(struct file *);\n\nThe -\u003eswap_activate() method is used to communicate to the file that the\nVM relies on it, and the address_space should take adequate measures such\nas reserving space in the underlying device, reserving memory for mempools\nand pinning information such as the block descriptor table in memory.  The\n-\u003eswap_deactivate() method is called on sys_swapoff() if -\u003eswap_activate()\nreturned success.\n\nAfter a successful swapfile -\u003eswap_activate, the swapfile is marked\nSWP_FILE and swapper_space.a_ops will proxy to\nsis-\u003eswap_file-\u003ef_mappings-\u003ea_ops using -\u003edirect_io to write swapcache\npages and -\u003ereadpage to read.\n\nIt is perfectly possible that direct_IO be used to read the swap pages but\nit is an unnecessary complication.  Similarly, it is possible that\n-\u003ewritepage be used instead of direct_io to write the pages but filesystem\ndevelopers have stated that calling writepage from the VM is undesirable\nfor a variety of reasons and using direct_IO opens up the possibility of\nwriting back batches of swap pages in the future.\n\n[a.p.zijlstra@chello.nl: Original patch]\nSigned-off-by: Mel Gorman \u003cmgorman@suse.de\u003e\nAcked-by: Rik van Riel \u003criel@redhat.com\u003e\nCc: Christoph Hellwig \u003chch@infradead.org\u003e\nCc: David S. Miller \u003cdavem@davemloft.net\u003e\nCc: Eric B Munson \u003cemunson@mgebm.net\u003e\nCc: Eric Paris \u003ceparis@redhat.com\u003e\nCc: James Morris \u003cjmorris@namei.org\u003e\nCc: Mel Gorman \u003cmgorman@suse.de\u003e\nCc: Mike Christie \u003cmichaelc@cs.wisc.edu\u003e\nCc: Neil Brown \u003cneilb@suse.de\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Sebastian Andrzej Siewior \u003csebastian@breakpoint.cc\u003e\nCc: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\nCc: Xiaotian Feng \u003cdfeng@redhat.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n"
    },
    {
      "commit": "18022c5d8627a7a9ba8097a0f238b513fae6f5b8",
      "tree": "57e0d0ec6a5369c56bd00957eb9c0e1220e62917",
      "parents": [
        "f981c5950fa85916ba49bea5d9a7a5078f47e569"
      ],
      "author": {
        "name": "Mel Gorman",
        "email": "mgorman@suse.de",
        "time": "Tue Jul 31 16:44:51 2012 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Tue Jul 31 18:42:47 2012 -0700"
      },
      "message": "mm: add get_kernel_page[s] for pinning of kernel addresses for I/O\n\nThis patch adds two new APIs get_kernel_pages() and get_kernel_page() that\nmay be used to pin a vector of kernel addresses for IO.  The initial user\nis expected to be NFS for allowing pages to be written to swap using\naops-\u003edirect_IO().  Strictly speaking, swap-over-NFS only needs to pin one\npage for IO but it makes sense to express the API in terms of a vector and\nadd a helper for pinning single pages.\n\nSigned-off-by: Mel Gorman \u003cmgorman@suse.de\u003e\nReviewed-by: Rik van Riel \u003criel@redhat.com\u003e\nCc: Christoph Hellwig \u003chch@infradead.org\u003e\nCc: David S. Miller \u003cdavem@davemloft.net\u003e\nCc: Eric B Munson \u003cemunson@mgebm.net\u003e\nCc: Eric Paris \u003ceparis@redhat.com\u003e\nCc: James Morris \u003cjmorris@namei.org\u003e\nCc: Mel Gorman \u003cmgorman@suse.de\u003e\nCc: Mike Christie \u003cmichaelc@cs.wisc.edu\u003e\nCc: Neil Brown \u003cneilb@suse.de\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Sebastian Andrzej Siewior \u003csebastian@breakpoint.cc\u003e\nCc: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\nCc: Xiaotian Feng \u003cdfeng@redhat.com\u003e\nCc: Mark Salter \u003cmsalter@redhat.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n"
    },
    {
      "commit": "08843b79fb35d33859e0f8f11a7318341076e4d1",
      "tree": "e56e122146985b359d50787e3d1df640c4582dfa",
      "parents": [
        "cc8362b1f6d724e46f515121d442779924b19fec",
        "2c142baa7b237584bae7dc28630851701497e1ef"
      ],
      "author": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Tue Jul 31 14:42:28 2012 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Tue Jul 31 14:42:28 2012 -0700"
      },
      "message": "Merge branch \u0027nfsd-next\u0027 of git://linux-nfs.org/~bfields/linux\n\nPull nfsd changes from J. Bruce Fields:\n \"This has been an unusually quiet cycle--mostly bugfixes and cleanup.\n  The one large piece is Stanislav\u0027s work to containerize the server\u0027s\n  grace period--but that in itself is just one more step in a\n  not-yet-complete project to allow fully containerized nfs service.\n\n  There are a number of outstanding delegation, container, v4 state, and\n  gss patches that aren\u0027t quite ready yet; 3.7 may be wilder.\"\n\n* \u0027nfsd-next\u0027 of git://linux-nfs.org/~bfields/linux: (35 commits)\n  NFSd: make boot_time variable per network namespace\n  NFSd: make grace end flag per network namespace\n  Lockd: move grace period management from lockd() to per-net functions\n  LockD: pass actual network namespace to grace period management functions\n  LockD: manage grace list per network namespace\n  SUNRPC: service request network namespace helper introduced\n  NFSd: make nfsd4_manager allocated per network namespace context.\n  LockD: make lockd manager allocated per network namespace\n  LockD: manage grace period per network namespace\n  Lockd: add more debug to host shutdown functions\n  Lockd: host complaining function introduced\n  LockD: manage used host count per networks namespace\n  LockD: manage garbage collection timeout per networks namespace\n  LockD: make garbage collector network namespace aware.\n  LockD: mark host per network namespace on garbage collect\n  nfsd4: fix missing fault_inject.h include\n  locks: move lease-specific code out of locks_delete_lock\n  locks: prevent side-effects of locks_release_private before file_lock is initialized\n  NFSd: set nfsd_serv to NULL after service destruction\n  NFSd: introduce nfsd_destroy() helper\n  ...\n"
    },
    {
      "commit": "d9c95bdd53a8d9116d269c91ce3d151472e6bcd6",
      "tree": "43559cf0897c98796df34a585ffab0ca02fa2576",
      "parents": [
        "1e8b212fe5dcee9d3dbb152d235f3c33458fb26e"
      ],
      "author": {
        "name": "Jan Kara",
        "email": "jack@suse.cz",
        "time": "Tue Jun 12 16:20:47 2012 +0200"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Tue Jul 31 09:45:54 2012 +0400"
      },
      "message": "fs: Remove old freezing mechanism\n\nNow that all users are converted, we can remove functions, variables, and\nconstants defined by the old freezing mechanism.\n\nBugLink: https://bugs.launchpad.net/bugs/897421\nTested-by: Kamal Mostafa \u003ckamal@canonical.com\u003e\nTested-by: Peter M. Petrakis \u003cpeter.petrakis@canonical.com\u003e\nTested-by: Dann Frazier \u003cdann.frazier@canonical.com\u003e\nTested-by: Massimo Morana \u003cmassimo.morana@canonical.com\u003e\nSigned-off-by: Jan Kara \u003cjack@suse.cz\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "5accdf82ba25cacefd6c1867f1704beb4d244cdd",
      "tree": "7125b01d9bf0f23d5c5eaed0cbafa9a1cbe544d5",
      "parents": [
        "d87aae2f3c8e90bd0fe03f5309b4d066b712b8ec"
      ],
      "author": {
        "name": "Jan Kara",
        "email": "jack@suse.cz",
        "time": "Tue Jun 12 16:20:34 2012 +0200"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Tue Jul 31 09:30:13 2012 +0400"
      },
      "message": "fs: Improve filesystem freezing handling\n\nvfs_check_frozen() tests are racy since the filesystem can be frozen just after\nthe test is performed. Thus in write paths we can end up marking some pages or\ninodes dirty even though the file system is already frozen. This creates\nproblems with flusher thread hanging on frozen filesystem.\n\nAnother problem is that exclusion between -\u003epage_mkwrite() and filesystem\nfreezing has been handled by setting page dirty and then verifying s_frozen.\nThis guaranteed that either the freezing code sees the faulted page, writes it,\nand writeprotects it again or we see s_frozen set and bail out of page fault.\nThis works to protect from page being marked writeable while filesystem\nfreezing is running but has an unpleasant artefact of leaving dirty (although\nunmodified and writeprotected) pages on frozen filesystem resulting in similar\nproblems with flusher thread as the first problem.\n\nThis patch aims at providing exclusion between write paths and filesystem\nfreezing. We implement a writer-freeze read-write semaphore in the superblock.\nActually, there are three such semaphores because of lock ranking reasons - one\nfor page fault handlers (-\u003epage_mkwrite), one for all other writers, and one of\ninternal filesystem purposes (used e.g. to track running transactions).  Write\npaths which should block freezing (e.g. directory operations, -\u003eaio_write(),\n-\u003epage_mkwrite) hold reader side of the semaphore. Code freezing the filesystem\ntakes the writer side.\n\nOnly that we don\u0027t really want to bounce cachelines of the semaphores between\nCPUs for each write happening. So we implement the reader side of the semaphore\nas a per-cpu counter and the writer side is implemented using s_writers.frozen\nsuperblock field.\n\n[AV: microoptimize sb_start_write(); we want it fast in normal case]\n\nBugLink: https://bugs.launchpad.net/bugs/897421\nTested-by: Kamal Mostafa \u003ckamal@canonical.com\u003e\nTested-by: Peter M. Petrakis \u003cpeter.petrakis@canonical.com\u003e\nTested-by: Dann Frazier \u003cdann.frazier@canonical.com\u003e\nTested-by: Massimo Morana \u003cmassimo.morana@canonical.com\u003e\nSigned-off-by: Jan Kara \u003cjack@suse.cz\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "800179c9b8a1e796e441674776d11cd4c05d61d7",
      "tree": "5760992f4453c35b57b2686d8b8d5caee239b637",
      "parents": [
        "3134f37e931d75931bdf6d4eacd82a3fd26eca7c"
      ],
      "author": {
        "name": "Kees Cook",
        "email": "keescook@chromium.org",
        "time": "Wed Jul 25 17:29:07 2012 -0700"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Sun Jul 29 21:37:58 2012 +0400"
      },
      "message": "fs: add link restrictions\n\nThis adds symlink and hardlink restrictions to the Linux VFS.\n\nSymlinks:\n\nA long-standing class of security issues is the symlink-based\ntime-of-check-time-of-use race, most commonly seen in world-writable\ndirectories like /tmp. The common method of exploitation of this flaw\nis to cross privilege boundaries when following a given symlink (i.e. a\nroot process follows a symlink belonging to another user). For a likely\nincomplete list of hundreds of examples across the years, please see:\nhttp://cve.mitre.org/cgi-bin/cvekey.cgi?keyword\u003d/tmp\n\nThe solution is to permit symlinks to only be followed when outside\na sticky world-writable directory, or when the uid of the symlink and\nfollower match, or when the directory owner matches the symlink\u0027s owner.\n\nSome pointers to the history of earlier discussion that I could find:\n\n 1996 Aug, Zygo Blaxell\n  http://marc.info/?l\u003dbugtraq\u0026m\u003d87602167419830\u0026w\u003d2\n 1996 Oct, Andrew Tridgell\n  http://lkml.indiana.edu/hypermail/linux/kernel/9610.2/0086.html\n 1997 Dec, Albert D Cahalan\n  http://lkml.org/lkml/1997/12/16/4\n 2005 Feb, Lorenzo Hernández García-Hierro\n  http://lkml.indiana.edu/hypermail/linux/kernel/0502.0/1896.html\n 2010 May, Kees Cook\n  https://lkml.org/lkml/2010/5/30/144\n\nPast objections and rebuttals could be summarized as:\n\n - Violates POSIX.\n   - POSIX didn\u0027t consider this situation and it\u0027s not useful to follow\n     a broken specification at the cost of security.\n - Might break unknown applications that use this feature.\n   - Applications that break because of the change are easy to spot and\n     fix. Applications that are vulnerable to symlink ToCToU by not having\n     the change aren\u0027t. Additionally, no applications have yet been found\n     that rely on this behavior.\n - Applications should just use mkstemp() or O_CREATE|O_EXCL.\n   - True, but applications are not perfect, and new software is written\n     all the time that makes these mistakes; blocking this flaw at the\n     kernel is a single solution to the entire class of vulnerability.\n - This should live in the core VFS.\n   - This should live in an LSM. (https://lkml.org/lkml/2010/5/31/135)\n - This should live in an LSM.\n   - This should live in the core VFS. (https://lkml.org/lkml/2010/8/2/188)\n\nHardlinks:\n\nOn systems that have user-writable directories on the same partition\nas system files, a long-standing class of security issues is the\nhardlink-based time-of-check-time-of-use race, most commonly seen in\nworld-writable directories like /tmp. The common method of exploitation\nof this flaw is to cross privilege boundaries when following a given\nhardlink (i.e. a root process follows a hardlink created by another\nuser). Additionally, an issue exists where users can \"pin\" a potentially\nvulnerable setuid/setgid file so that an administrator will not actually\nupgrade a system fully.\n\nThe solution is to permit hardlinks to only be created when the user is\nalready the existing file\u0027s owner, or if they already have read/write\naccess to the existing file.\n\nMany Linux users are surprised when they learn they can link to files\nthey have no access to, so this change appears to follow the doctrine\nof \"least surprise\". Additionally, this change does not violate POSIX,\nwhich states \"the implementation may require that the calling process\nhas permission to access the existing file\"[1].\n\nThis change is known to break some implementations of the \"at\" daemon,\nthough the version used by Fedora and Ubuntu has been fixed[2] for\na while. Otherwise, the change has been undisruptive while in use in\nUbuntu for the last 1.5 years.\n\n[1] http://pubs.opengroup.org/onlinepubs/9699919799/functions/linkat.html\n[2] http://anonscm.debian.org/gitweb/?p\u003dcollab-maint/at.git;a\u003dcommitdiff;h\u003df4114656c3a6c6f6070e315ffdf940a49eda3279\n\nThis patch is based on the patches in Openwall and grsecurity, along with\nsuggestions from Al Viro. I have added a sysctl to enable the protected\nbehavior, and documentation.\n\nSigned-off-by: Kees Cook \u003ckeescook@chromium.org\u003e\nAcked-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "e4fad8e5d220e3dfb1050eee752ee5058f29a232",
      "tree": "b56356fda1d1f4f47e1da63aa24080db999dafc1",
      "parents": [
        "b5bcdda32736b94a7d178d156d80a69f536ad468"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Sat Jul 21 15:33:25 2012 +0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Sun Jul 29 21:24:19 2012 +0400"
      },
      "message": "consolidate pipe file creation\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "5ccb0066f2d561549cc4d73d7f56b4ce3ca7a8a1",
      "tree": "43ca9eff5c94fc3609d858ce2a430c544fcc5f99",
      "parents": [
        "db9c4553412d72c6a05e0168d1d487f66e0660b3"
      ],
      "author": {
        "name": "Stanislav Kinsbursky",
        "email": "skinsbursky@parallels.com",
        "time": "Wed Jul 25 16:57:22 2012 +0400"
      },
      "committer": {
        "name": "J. Bruce Fields",
        "email": "bfields@redhat.com",
        "time": "Fri Jul 27 16:49:22 2012 -0400"
      },
      "message": "LockD: pass actual network namespace to grace period management functions\n\nPassed network namespace replaced hard-coded init_net\n\nSigned-off-by: Stanislav Kinsbursky \u003cskinsbursky@parallels.com\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@redhat.com\u003e\n"
    },
    {
      "commit": "765927b2d508712d320c8934db963bbe14c3fcec",
      "tree": "97acdb14fae285764def396c4ed01d4d5c93e76a",
      "parents": [
        "bf349a447059656ebe63fb4fd1ccb27ac1da22ad"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Tue Jun 26 21:58:53 2012 +0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Mon Jul 23 00:01:29 2012 +0400"
      },
      "message": "switch dentry_open() to struct path, make it grab references itself\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "e8b96eb5034a0ccebf36760f88e31ea3e3cdf1e4",
      "tree": "3ea1b85311b3d059f2bbf38e484aa2ce06bab017",
      "parents": [
        "4ea425b63a3dfeb7707fc7cc7161c11a51e871ed"
      ],
      "author": {
        "name": "Eric Sandeen",
        "email": "sandeen@redhat.com",
        "time": "Mon Apr 30 13:11:29 2012 -0500"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Mon Jul 23 00:00:15 2012 +0400"
      },
      "message": "vfs: allow custom EOF in generic_file_llseek code\n\nFor ext3/4 htree directories, using the vfs llseek function with\nSEEK_END goes to i_size like for any other file, but in reality\nwe want the maximum possible hash value.  Recent changes\nin ext4 have cut \u0026 pasted generic_file_llseek() back into fs/ext4/dir.c,\nbut replicating this core code seems like a bad idea, especially\nsince the copy has already diverged from the vfs.\n\nThis patch updates generic_file_llseek_size to accept\nboth a custom maximum offset, and a custom EOF position.  With this\nin place, ext4_dir_llseek can pass in the appropriate maximum hash\nposition for both maxsize and eof, and get what it wants.\n\nAs far as I know, this does not fix any bugs - nfs in the kernel\ndoesn\u0027t use SEEK_END, and I don\u0027t know of any user who does.  But\nsome ext4 folks seem keen on doing the right thing here, and I can\u0027t\nreally argue.\n\n(Patch also fixes up some comments slightly)\n\nSigned-off-by: Eric Sandeen \u003csandeen@redhat.com\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "5c0d6b60a0ba46d45020547eacf7199171920935",
      "tree": "7d9f99cc40981dc0872e1ac33317f48b9e1f2bfb",
      "parents": [
        "b3de653105180b57af90ef2f5b8441f085f4ff56"
      ],
      "author": {
        "name": "Jan Kara",
        "email": "jack@suse.cz",
        "time": "Tue Jul 03 16:45:31 2012 +0200"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Sun Jul 22 23:58:45 2012 +0400"
      },
      "message": "vfs: Create function for iterating over block devices\n\nSigned-off-by: Jan Kara \u003cjack@suse.cz\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "9249e17fe094d853d1ef7475dd559a2cc7e23d42",
      "tree": "fa80a6044c14b38994d232c0e05cb7365800adf2",
      "parents": [
        "f015f1267b23d3530d3f874243fb83cb5f443005"
      ],
      "author": {
        "name": "David Howells",
        "email": "dhowells@redhat.com",
        "time": "Mon Jun 25 12:55:37 2012 +0100"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Sat Jul 14 16:38:34 2012 +0400"
      },
      "message": "VFS: Pass mount flags to sget()\n\nPass mount flags to sget() so that it can use them in initialising a new\nsuperblock before the set function is called.  They could also be passed to the\ncompare function.\n\nSigned-off-by: David Howells \u003cdhowells@redhat.com\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "312b63fba9e88a0dcf800834b8ede8716bcc1e17",
      "tree": "a069e3b9ff142912fd09f09a22466707d31c6812",
      "parents": [
        "ebfc3b49a7ac25920cb5be5445f602e51d2ea559"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Sun Jun 10 18:09:36 2012 -0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Sat Jul 14 16:34:50 2012 +0400"
      },
      "message": "don\u0027t pass nameidata * to vfs_create()\n\nall we want is a boolean flag, same as the method gets now\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "ebfc3b49a7ac25920cb5be5445f602e51d2ea559",
      "tree": "c3241f875dd04ab9f63b4e7ded7ed206e4df1b9f",
      "parents": [
        "72bd866a01fc62ccbc466f3eb7599b14c937e96b"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Sun Jun 10 18:05:36 2012 -0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Sat Jul 14 16:34:47 2012 +0400"
      },
      "message": "don\u0027t pass nameidata to -\u003ecreate()\n\nboolean \"does it have to be exclusive?\" flag is passed instead;\nLocal filesystem should just ignore it - the object is guaranteed\nnot to be there yet.\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "00cd8dd3bf95f2cc8435b4cac01d9995635c6d0b",
      "tree": "d44be476ced0317ae79f28853734ebe2210ad38e",
      "parents": [
        "201f956e43d4542723514e024d948011dd766d43"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Sun Jun 10 17:13:09 2012 -0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Sat Jul 14 16:34:32 2012 +0400"
      },
      "message": "stop passing nameidata to -\u003elookup()\n\nJust the flags; only NFS cares even about that, but there are\nlegitimate uses for such argument.  And getting rid of that\ncompletely would require splitting -\u003elookup() into a couple\nof methods (at least), so let\u0027s leave that alone for now...\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "e45198a6ac24bd2c4ad4a43b670c2f1a23dd2df3",
      "tree": "d44f4217a8a556ac9ebb11cfc41c0e148fb1084c",
      "parents": [
        "2675a4eb6a9f1240098721c8a84ede28abd9d7b3"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Sun Jun 10 06:48:09 2012 -0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Sat Jul 14 16:33:45 2012 +0400"
      },
      "message": "make finish_no_open() return int\n\nnamely, 1 ;-)  That\u0027s what we want to return from -\u003eatomic_open()\ninstances after finish_no_open().\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "30d904947459cca2beb69e0110716f5248b31f2a",
      "tree": "024e2a913266377d234147b14b7eb37017546173",
      "parents": [
        "a4a3bdd778715999ddfeefdc52ab76254580fa76"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Fri Jun 22 12:40:19 2012 +0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Sat Jul 14 16:33:39 2012 +0400"
      },
      "message": "kill struct opendata\n\nJust pass struct file *.  Methods are happier that way...\nThere\u0027s no need to return struct file * from finish_open() now,\nso let it return int.  Next: saner prototypes for parts in\nnamei.c\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "d95852777bc8ba6b3ad3397d495c5f9dd8ca8383",
      "tree": "96e9d8b1d33c4f6f7b5ba5be0fa4fd8f77c7a67f",
      "parents": [
        "3d8a00d2099ebc6d5a6e95fadaf861709d9919a8"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Fri Jun 22 12:39:14 2012 +0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Sat Jul 14 16:33:35 2012 +0400"
      },
      "message": "make -\u003eatomic_open() return int\n\nChange of calling conventions:\nold\t\tnew\nNULL\t\t1\nfile\t\t0\nERR_PTR(-ve)\t-ve\n\nCaller *knows* that struct file *; no need to return it.\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "47237687d73cbeae1dd7a133c3fc3d7239094568",
      "tree": "1d267d03246f0a16cbff3c8221ee69dd1521f835",
      "parents": [
        "a8277b9baa6268de386529a33061775bc716198b"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Sun Jun 10 05:01:45 2012 -0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Sat Jul 14 16:33:31 2012 +0400"
      },
      "message": "-\u003eatomic_open() prototype change - pass int * instead of bool *\n\n... and let finish_open() report having opened the file via that sucker.\nNext step: don\u0027t modify od-\u003efilp at all.\n\n[AV: FILE_CREATE was already used by cifs; Miklos\u0027 fix folded]\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "d18e9008c377dc6a6d2166a6840bf3a23a5867fd",
      "tree": "6bbb29aea7e931b603bd4cea3cc74a0eda7b6379",
      "parents": [
        "54ef487241e863a6046536ac5b1fcd5d7cde86e5"
      ],
      "author": {
        "name": "Miklos Szeredi",
        "email": "mszeredi@suse.cz",
        "time": "Tue Jun 05 15:10:17 2012 +0200"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Sat Jul 14 16:33:04 2012 +0400"
      },
      "message": "vfs: add i_op-\u003eatomic_open()\n\nAdd a new inode operation which is called on the last component of an open.\nUsing this the filesystem can look up, possibly create and open the file in one\natomic operation.  If it cannot perform this (e.g. the file type turned out to\nbe wrong) it may signal this by returning NULL instead of an open struct file\npointer.\n\ni_op-\u003eatomic_open() is only called if the last component is negative or needs\nlookup.  Handling cached positive dentries here doesn\u0027t add much value: these\ncan be opened using f_op-\u003eopen().  If the cached file turns out to be invalid,\nthe open can be retried, this time using -\u003eatomic_open() with a fresh dentry.\n\nFor now leave the old way of using open intents in lookup and revalidate in\nplace.  This will be removed once all the users are converted.\n\nDavid Howells noticed that if -\u003eatomic_open() opens the file but does not create\nit, handle_truncate() will be called on it even if it is not a regular file.\nFix this by checking the file type in this case too.\n\nSigned-off-by: Miklos Szeredi \u003cmszeredi@suse.cz\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "b3d9b7a3c752dc4b6976a4ff7b8298887a5b734d",
      "tree": "ce0d4c84328890dd63c9c4cb3e281b6b3476f85f",
      "parents": [
        "9f713878f22e0b2d34d62df0ca55f65166375634"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Sat Jun 09 13:51:19 2012 -0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Sat Jul 14 16:32:55 2012 +0400"
      },
      "message": "vfs: switch i_dentry/d_alias to hlist\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "2f9d3df8aa1cc3c6db5cfa0bad3f0745e04cc27d",
      "tree": "f5cb17f1db0e8308eae0c7271c1d2dc86851c95d",
      "parents": [
        "f8f5701bdaf9134b1f90e5044a82c66324d2073f"
      ],
      "author": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Sun Jun 03 14:50:19 2012 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Sun Jun 03 14:50:19 2012 -0700"
      },
      "message": "vfs: move inode stat information closer together\n\nThe comment above it says \"Stat data, not accessed from path walking\",\nbut in fact some of inode fields we use for the common stat data was way\ndown at the end of the inode, causing unnecessary cache misses for the\ncommon stat operations.\n\nThe inode structure is pretty big, and this can change padding depending\non field width, but at least on the common 64-bit configurations this\ndoesn\u0027t change the size.  Some of our inode layout has historically been\nto tro to avoid unnecessary padding fields, but cache locality is at\nleast as important for layout, if not more.\n\nNoticed by looking at kernel profiles, and noticing that the \"i_blkbits\"\naccess stood out like a sore thumb.\n\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n"
    },
    {
      "commit": "1193755ac6328ad240ba987e6ec41d5e8baf0680",
      "tree": "40bf847d7e3ebaa57b107151d14e6cd1d280cc6d",
      "parents": [
        "4edebed86690eb8db9af3ab85baf4a34e73266cc",
        "0ef97dcfce4179a2eba046b855ee2f91d6f1b414"
      ],
      "author": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Fri Jun 01 10:34:35 2012 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Fri Jun 01 10:34:35 2012 -0700"
      },
      "message": "Merge branch \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs\n\nPull vfs changes from Al Viro.\n \"A lot of misc stuff.  The obvious groups:\n   * Miklos\u0027 atomic_open series; kills the damn abuse of\n     -\u003ed_revalidate() by NFS, which was the major stumbling block for\n     all work in that area.\n   * ripping security_file_mmap() and dealing with deadlocks in the\n     area; sanitizing the neighborhood of vm_mmap()/vm_munmap() in\n     general.\n   * -\u003eencode_fh() switched to saner API; insane fake dentry in\n     mm/cleancache.c gone.\n   * assorted annotations in fs (endianness, __user)\n   * parts of Artem\u0027s -\u003es_dirty work (jff2 and reiserfs parts)\n   * -\u003eupdate_time() work from Josef.\n   * other bits and pieces all over the place.\n\n  Normally it would\u0027ve been in two or three pull requests, but\n  signal.git stuff had eaten a lot of time during this cycle ;-/\"\n\nFix up trivial conflicts in Documentation/filesystems/vfs.txt (the\n\u0027truncate_range\u0027 inode method was removed by the VM changes, the VFS\nupdate adds an \u0027update_time()\u0027 method), and in fs/btrfs/ulist.[ch] (due\nto sparse fix added twice, with other changes nearby).\n\n* \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (95 commits)\n  nfs: don\u0027t open in -\u003ed_revalidate\n  vfs: retry last component if opening stale dentry\n  vfs: nameidata_to_filp(): don\u0027t throw away file on error\n  vfs: nameidata_to_filp(): inline __dentry_open()\n  vfs: do_dentry_open(): don\u0027t put filp\n  vfs: split __dentry_open()\n  vfs: do_last() common post lookup\n  vfs: do_last(): add audit_inode before open\n  vfs: do_last(): only return EISDIR for O_CREAT\n  vfs: do_last(): check LOOKUP_DIRECTORY\n  vfs: do_last(): make ENOENT exit RCU safe\n  vfs: make follow_link check RCU safe\n  vfs: do_last(): use inode variable\n  vfs: do_last(): inline walk_component()\n  vfs: do_last(): make exit RCU safe\n  vfs: split do_lookup()\n  Btrfs: move over to use -\u003eupdate_time\n  fs: introduce inode operation -\u003eupdate_time\n  reiserfs: get rid of resierfs_sync_super\n  reiserfs: mark the superblock as dirty a bit later\n  ...\n"
    },
    {
      "commit": "c3b2da314834499f34cba94f7053e55f6d6f92d8",
      "tree": "7012b569ee9e0781761a8eb388190979441583c7",
      "parents": [
        "033369d1af1264abc23bea2e174aa47cdd212f6f"
      ],
      "author": {
        "name": "Josef Bacik",
        "email": "josef@redhat.com",
        "time": "Mon Mar 26 09:59:21 2012 -0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Fri Jun 01 12:07:25 2012 -0400"
      },
      "message": "fs: introduce inode operation -\u003eupdate_time\n\nBtrfs has to make sure we have space to allocate new blocks in order to modify\nthe inode, so updating time can fail.  We\u0027ve gotten around this by having our\nown file_update_time but this is kind of a pain, and Christoph has indicated he\nwould like to make xfs do something different with atime updates.  So introduce\n-\u003eupdate_time, where we will deal with i_version an a/m/c time updates and\nindicate which changes need to be made.  The normal version just does what it\nhas always done, updates the time and marks the inode dirty, and then\nfilesystems can choose to do something different.\n\nI\u0027ve gone through all of the users of file_update_time and made them check for\nerrors with the exception of the fault code since it\u0027s complicated and I wasn\u0027t\nquite sure what to do there, also Jan is going to be pushing the file time\nupdates into page_mkwrite for those who have it so that should satisfy btrfs and\nmake it not a big deal to check the file_update_time() return code in the\ngeneric fault path. Thanks,\n\nSigned-off-by: Josef Bacik \u003cjosef@redhat.com\u003e\n"
    },
    {
      "commit": "08615d7d85e5aa02c05bf6c4dde87d940e7f85f6",
      "tree": "18906149d313d25914160aca21cedf54b3a7e818",
      "parents": [
        "9fdadb2cbaf4b482dfd6086e8bd3d2db071a1702",
        "0a4dd35c67b144d8ef9432120105f1aab9293ee9"
      ],
      "author": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Thu May 31 18:10:18 2012 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Thu May 31 18:10:18 2012 -0700"
      },
      "message": "Merge branch \u0027akpm\u0027 (Andrew\u0027s patch-bomb)\n\nMerge misc patches from Andrew Morton:\n\n - the \"misc\" tree - stuff from all over the map\n\n - checkpatch updates\n\n - fatfs\n\n - kmod changes\n\n - procfs\n\n - cpumask\n\n - UML\n\n - kexec\n\n - mqueue\n\n - rapidio\n\n - pidns\n\n - some checkpoint-restore feature work.  Reluctantly.  Most of it\n   delayed a release.  I\u0027m still rather worried that we don\u0027t have a\n   clear roadmap to completion for this work.\n\n* emailed from Andrew Morton \u003cakpm@linux-foundation.org\u003e: (78 patches)\n  kconfig: update compression algorithm info\n  c/r: prctl: add ability to set new mm_struct::exe_file\n  c/r: prctl: extend PR_SET_MM to set up more mm_struct entries\n  c/r: procfs: add arg_start/end, env_start/end and exit_code members to /proc/$pid/stat\n  syscalls, x86: add __NR_kcmp syscall\n  fs, proc: introduce /proc/\u003cpid\u003e/task/\u003ctid\u003e/children entry\n  sysctl: make kernel.ns_last_pid control dependent on CHECKPOINT_RESTORE\n  aio/vfs: cleanup of rw_copy_check_uvector() and compat_rw_copy_check_uvector()\n  eventfd: change int to __u64 in eventfd_signal()\n  fs/nls: add Apple NLS\n  pidns: make killed children autoreap\n  pidns: use task_active_pid_ns in do_notify_parent\n  rapidio/tsi721: add DMA engine support\n  rapidio: add DMA engine support for RIO data transfers\n  ipc/mqueue: add rbtree node caching support\n  tools/selftests: add mq_perf_tests\n  ipc/mqueue: strengthen checks on mqueue creation\n  ipc/mqueue: correct mq_attr_ok test\n  ipc/mqueue: improve performance of send/recv\n  selftests: add mq_open_tests\n  ...\n"
    },
    {
      "commit": "ac34ebb3a67e699edcb5ac72f19d31679369dfaa",
      "tree": "21785208005952128545c0d7804c2dddf177766f",
      "parents": [
        "ee62c6b2dc93c09585b51fad18449dc5edb9977f"
      ],
      "author": {
        "name": "Christopher Yeoh",
        "email": "cyeoh@au1.ibm.com",
        "time": "Thu May 31 16:26:42 2012 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Thu May 31 17:49:32 2012 -0700"
      },
      "message": "aio/vfs: cleanup of rw_copy_check_uvector() and compat_rw_copy_check_uvector()\n\nA cleanup of rw_copy_check_uvector and compat_rw_copy_check_uvector after\nchanges made to support CMA in an earlier patch.\n\nRather than having an additional check_access parameter to these\nfunctions, the first paramater type is overloaded to allow the caller to\nspecify CHECK_IOVEC_ONLY which means check that the contents of the iovec\nare valid, but do not check the memory that they point to.  This is used\nby process_vm_readv/writev where we need to validate that a iovec passed\nto the syscall is valid but do not want to check the memory that it points\nto at this point because it refers to an address space in another process.\n\nSigned-off-by: Chris Yeoh \u003cyeohc@au1.ibm.com\u003e\nReviewed-by: Oleg Nesterov \u003coleg@redhat.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n"
    },
    {
      "commit": "1d59d61f606547f0712aa6971f91f71154071c99",
      "tree": "cb2fd4b9ce3e3ee9440d566d43ea350221edfc8e",
      "parents": [
        "2d117403b30cd7301af60d7d54b279a9f566d10d"
      ],
      "author": {
        "name": "Trond Myklebust",
        "email": "Trond.Myklebust@netapp.com",
        "time": "Thu May 31 12:22:33 2012 -0400"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Thu May 31 11:41:36 2012 -0700"
      },
      "message": "NFS: Ensure that setattr and getattr wait for O_DIRECT write completion\n\nUse the same mechanism as the block devices are using, but move the\nhelper functions from fs/direct-io.c into fs/inode.c to remove the\ndependency on CONFIG_BLOCK.\n\nSigned-off-by: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\nCc: Christoph Hellwig \u003chch@infradead.org\u003e\nCc: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\nCc: Fred Isaman \u003ciisaman@netapp.com\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n"
    },
    {
      "commit": "17cf28afea2a1112f240a3a2da8af883be024811",
      "tree": "ed9e3eb9b1d44118a12e4ecdf369e3b9b3208be1",
      "parents": [
        "3f31d07571eeea18a7d34db9af21d2285b807a17"
      ],
      "author": {
        "name": "Hugh Dickins",
        "email": "hughd@google.com",
        "time": "Tue May 29 15:06:41 2012 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Tue May 29 16:22:23 2012 -0700"
      },
      "message": "mm/fs: remove truncate_range\n\nRemove vmtruncate_range(), and remove the truncate_range method from\nstruct inode_operations: only tmpfs ever supported it, and tmpfs has now\nconverted over to using the fallocate method of file_operations.\n\nUpdate Documentation accordingly, adding (setlease and) fallocate lines.\nAnd while we\u0027re in mm.h, remove duplicate declarations of shmem_lock() and\nshmem_file_setup(): everyone is now using the ones in shmem_fs.h.\n\nBased-on-patch-by: Cong Wang \u003camwang@redhat.com\u003e\nSigned-off-by: Hugh Dickins \u003chughd@google.com\u003e\nCc: Christoph Hellwig \u003chch@infradead.org\u003e\nCc: Cong Wang \u003camwang@redhat.com\u003e\nCc: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n"
    },
    {
      "commit": "90324cc1b11a211e37eabd8cb863e1a1561d6b1d",
      "tree": "c8b79c6850420a114ca6660c1b44fc486b1ba86d",
      "parents": [
        "fb8b00675eb6462aacab56bca31ed6107bda5314",
        "169ebd90131b2ffca74bb2dbe7eeacd39fb83714"
      ],
      "author": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Mon May 28 09:54:45 2012 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Mon May 28 09:54:45 2012 -0700"
      },
      "message": "Merge tag \u0027writeback\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/wfg/linux\n\nPull writeback tree from Wu Fengguang:\n \"Mainly from Jan Kara to avoid iput() in the flusher threads.\"\n\n* tag \u0027writeback\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/wfg/linux:\n  writeback: Avoid iput() from flusher thread\n  vfs: Rename end_writeback() to clear_inode()\n  vfs: Move waiting for inode writeback from end_writeback() to evict_inode()\n  writeback: Refactor writeback_single_inode()\n  writeback: Remove wb-\u003elist_lock from writeback_single_inode()\n  writeback: Separate inode requeueing after writeback\n  writeback: Move I_DIRTY_PAGES handling\n  writeback: Move requeueing when I_SYNC set to writeback_sb_inodes()\n  writeback: Move clearing of I_SYNC into inode_sync_complete()\n  writeback: initialize global_dirty_limit\n  fs: remove 8 bytes of padding from struct writeback_control on 64 bit builds\n  mm: page-writeback.c: local functions should not be exposed globally\n"
    },
    {
      "commit": "644473e9c60c1ff4f6351fed637a6e5551e3dce7",
      "tree": "10316518bedc735a2c6552886658d69dfd9f1eb0",
      "parents": [
        "fb827ec68446c83e9e8754fa9b55aed27ecc4661",
        "4b06a81f1daee668fbd6de85557bfb36dd36078f"
      ],
      "author": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Wed May 23 17:42:39 2012 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Wed May 23 17:42:39 2012 -0700"
      },
      "message": "Merge branch \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace\n\nPull user namespace enhancements from Eric Biederman:\n \"This is a course correction for the user namespace, so that we can\n  reach an inexpensive, maintainable, and reasonably complete\n  implementation.\n\n  Highlights:\n   - Config guards make it impossible to enable the user namespace and\n     code that has not been converted to be user namespace safe.\n\n   - Use of the new kuid_t type ensures the if you somehow get past the\n     config guards the kernel will encounter type errors if you enable\n     user namespaces and attempt to compile in code whose permission\n     checks have not been updated to be user namespace safe.\n\n   - All uids from child user namespaces are mapped into the initial\n     user namespace before they are processed.  Removing the need to add\n     an additional check to see if the user namespace of the compared\n     uids remains the same.\n\n   - With the user namespaces compiled out the performance is as good or\n     better than it is today.\n\n   - For most operations absolutely nothing changes performance or\n     operationally with the user namespace enabled.\n\n   - The worst case performance I could come up with was timing 1\n     billion cache cold stat operations with the user namespace code\n     enabled.  This went from 156s to 164s on my laptop (or 156ns to\n     164ns per stat operation).\n\n   - (uid_t)-1 and (gid_t)-1 are reserved as an internal error value.\n     Most uid/gid setting system calls treat these value specially\n     anyway so attempting to use -1 as a uid would likely cause\n     entertaining failures in userspace.\n\n   - If setuid is called with a uid that can not be mapped setuid fails.\n     I have looked at sendmail, login, ssh and every other program I\n     could think of that would call setuid and they all check for and\n     handle the case where setuid fails.\n\n   - If stat or a similar system call is called from a context in which\n     we can not map a uid we lie and return overflowuid.  The LFS\n     experience suggests not lying and returning an error code might be\n     better, but the historical precedent with uids is different and I\n     can not think of anything that would break by lying about a uid we\n     can\u0027t map.\n\n   - Capabilities are localized to the current user namespace making it\n     safe to give the initial user in a user namespace all capabilities.\n\n  My git tree covers all of the modifications needed to convert the core\n  kernel and enough changes to make a system bootable to runlevel 1.\"\n\nFix up trivial conflicts due to nearby independent changes in fs/stat.c\n\n* \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace: (46 commits)\n  userns:  Silence silly gcc warning.\n  cred: use correct cred accessor with regards to rcu read lock\n  userns: Convert the move_pages, and migrate_pages permission checks to use uid_eq\n  userns: Convert cgroup permission checks to use uid_eq\n  userns: Convert tmpfs to use kuid and kgid where appropriate\n  userns: Convert sysfs to use kgid/kuid where appropriate\n  userns: Convert sysctl permission checks to use kuid and kgids.\n  userns: Convert proc to use kuid/kgid where appropriate\n  userns: Convert ext4 to user kuid/kgid where appropriate\n  userns: Convert ext3 to use kuid/kgid where appropriate\n  userns: Convert ext2 to use kuid/kgid where appropriate.\n  userns: Convert devpts to use kuid/kgid where appropriate\n  userns: Convert binary formats to use kuid/kgid where appropriate\n  userns: Add negative depends on entries to avoid building code that is userns unsafe\n  userns: signal remove unnecessary map_cred_ns\n  userns: Teach inode_capable to understand inodes whose uids map to other namespaces.\n  userns: Fail exec for suid and sgid binaries with ids outside our user namespace.\n  userns: Convert stat to return values mapped from kuids and kgids\n  userns: Convert user specfied uids and gids in chown into kuids and kgid\n  userns: Use uid_eq gid_eq helpers when comparing kuids and kgids in the vfs\n  ...\n"
    },
    {
      "commit": "080399aaaf3531f5b8761ec0ac30ff98891e8686",
      "tree": "28ba8f41bb67a58992bc426dac7002983bc64e8f",
      "parents": [
        "a09ba13eefb155a00d8d50008a0c0a2406985ddd"
      ],
      "author": {
        "name": "Jeff Moyer",
        "email": "jmoyer@redhat.com",
        "time": "Fri May 11 16:34:10 2012 +0200"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Fri May 11 16:42:14 2012 +0200"
      },
      "message": "block: don\u0027t mark buffers beyond end of disk as mapped\n\nHi,\n\nWe have a bug report open where a squashfs image mounted on ppc64 would\nexhibit errors due to trying to read beyond the end of the disk.  It can\neasily be reproduced by doing the following:\n\n[root@ibm-p750e-02-lp3 ~]# ls -l install.img\n-rw-r--r-- 1 root root 142032896 Apr 30 16:46 install.img\n[root@ibm-p750e-02-lp3 ~]# mount -o loop ./install.img /mnt/test\n[root@ibm-p750e-02-lp3 ~]# dd if\u003d/dev/loop0 of\u003d/dev/null\ndd: reading `/dev/loop0\u0027: Input/output error\n277376+0 records in\n277376+0 records out\n142016512 bytes (142 MB) copied, 0.9465 s, 150 MB/s\n\nIn dmesg, you\u0027ll find the following:\n\nsquashfs: version 4.0 (2009/01/31) Phillip Lougher\n[   43.106012] attempt to access beyond end of device\n[   43.106029] loop0: rw\u003d0, want\u003d277410, limit\u003d277408\n[   43.106039] Buffer I/O error on device loop0, logical block 138704\n[   43.106053] attempt to access beyond end of device\n[   43.106057] loop0: rw\u003d0, want\u003d277412, limit\u003d277408\n[   43.106061] Buffer I/O error on device loop0, logical block 138705\n[   43.106066] attempt to access beyond end of device\n[   43.106070] loop0: rw\u003d0, want\u003d277414, limit\u003d277408\n[   43.106073] Buffer I/O error on device loop0, logical block 138706\n[   43.106078] attempt to access beyond end of device\n[   43.106081] loop0: rw\u003d0, want\u003d277416, limit\u003d277408\n[   43.106085] Buffer I/O error on device loop0, logical block 138707\n[   43.106089] attempt to access beyond end of device\n[   43.106093] loop0: rw\u003d0, want\u003d277418, limit\u003d277408\n[   43.106096] Buffer I/O error on device loop0, logical block 138708\n[   43.106101] attempt to access beyond end of device\n[   43.106104] loop0: rw\u003d0, want\u003d277420, limit\u003d277408\n[   43.106108] Buffer I/O error on device loop0, logical block 138709\n[   43.106112] attempt to access beyond end of device\n[   43.106116] loop0: rw\u003d0, want\u003d277422, limit\u003d277408\n[   43.106120] Buffer I/O error on device loop0, logical block 138710\n[   43.106124] attempt to access beyond end of device\n[   43.106128] loop0: rw\u003d0, want\u003d277424, limit\u003d277408\n[   43.106131] Buffer I/O error on device loop0, logical block 138711\n[   43.106135] attempt to access beyond end of device\n[   43.106139] loop0: rw\u003d0, want\u003d277426, limit\u003d277408\n[   43.106143] Buffer I/O error on device loop0, logical block 138712\n[   43.106147] attempt to access beyond end of device\n[   43.106151] loop0: rw\u003d0, want\u003d277428, limit\u003d277408\n[   43.106154] Buffer I/O error on device loop0, logical block 138713\n[   43.106158] attempt to access beyond end of device\n[   43.106162] loop0: rw\u003d0, want\u003d277430, limit\u003d277408\n[   43.106166] attempt to access beyond end of device\n[   43.106169] loop0: rw\u003d0, want\u003d277432, limit\u003d277408\n...\n[   43.106307] attempt to access beyond end of device\n[   43.106311] loop0: rw\u003d0, want\u003d277470, limit\u003d2774\n\nSquashfs manages to read in the end block(s) of the disk during the\nmount operation.  Then, when dd reads the block device, it leads to\nblock_read_full_page being called with buffers that are beyond end of\ndisk, but are marked as mapped.  Thus, it would end up submitting read\nI/O against them, resulting in the errors mentioned above.  I fixed the\nproblem by modifying init_page_buffers to only set the buffer mapped if\nit fell inside of i_size.\n\nCheers,\nJeff\n\nSigned-off-by: Jeff Moyer \u003cjmoyer@redhat.com\u003e\nAcked-by: Nick Piggin \u003cnpiggin@kernel.dk\u003e\n\n--\n\nChanges from v1-\u003ev2: re-used max_block, as suggested by Nick Piggin.\nSigned-off-by: Jens Axboe \u003caxboe@kernel.dk\u003e\n"
    },
    {
      "commit": "169ebd90131b2ffca74bb2dbe7eeacd39fb83714",
      "tree": "513136e110970da388680947c225ef8ca05a6dd7",
      "parents": [
        "dbd5768f87ff6fb0a4fe09c4d7b6c4a24de99430"
      ],
      "author": {
        "name": "Jan Kara",
        "email": "jack@suse.cz",
        "time": "Thu May 03 14:48:03 2012 +0200"
      },
      "committer": {
        "name": "Fengguang Wu",
        "email": "fengguang.wu@intel.com",
        "time": "Sun May 06 13:43:41 2012 +0800"
      },
      "message": "writeback: Avoid iput() from flusher thread\n\nDoing iput() from flusher thread (writeback_sb_inodes()) can create problems\nbecause iput() can do a lot of work - for example truncate the inode if it\u0027s\nthe last iput on unlinked file. Some filesystems depend on flusher thread\nprogressing (e.g. because they need to flush delay allocated blocks to reduce\nallocation uncertainty) and so flusher thread doing truncate creates\ninteresting dependencies and possibilities for deadlocks.\n\nWe get rid of iput() in flusher thread by using the fact that I_SYNC inode\nflag effectively pins the inode in memory. So if we take care to either hold\ni_lock or have I_SYNC set, we can get away without taking inode reference\nin writeback_sb_inodes().\n\nAs a side effect of these changes, we also fix possible use-after-free in\nwb_writeback() because inode_wait_for_writeback() call could try to reacquire\ni_lock on the inode that was already free.\n\nSigned-off-by: Jan Kara \u003cjack@suse.cz\u003e\nSigned-off-by: Fengguang Wu \u003cfengguang.wu@intel.com\u003e\n"
    },
    {
      "commit": "dbd5768f87ff6fb0a4fe09c4d7b6c4a24de99430",
      "tree": "42ea94ea733538f797aa745945fc43c4d1b89217",
      "parents": [
        "7994e6f7254354e03028a11f98a27bd67dace9f1"
      ],
      "author": {
        "name": "Jan Kara",
        "email": "jack@suse.cz",
        "time": "Thu May 03 14:48:02 2012 +0200"
      },
      "committer": {
        "name": "Fengguang Wu",
        "email": "fengguang.wu@intel.com",
        "time": "Sun May 06 13:43:41 2012 +0800"
      },
      "message": "vfs: Rename end_writeback() to clear_inode()\n\nAfter we moved inode_sync_wait() from end_writeback() it doesn\u0027t make sense\nto call the function end_writeback() anymore. Rename it to clear_inode()\nwhich well says what the function really does - set I_CLEAR flag.\n\nSigned-off-by: Jan Kara \u003cjack@suse.cz\u003e\nSigned-off-by: Fengguang Wu \u003cfengguang.wu@intel.com\u003e\n"
    },
    {
      "commit": "92361636e0153bd0cb22e7dfe3fc6287f6537c66",
      "tree": "8b7d8f91aa528c2bad8ff97c737b2612e414480a",
      "parents": [
        "5af662030e5db1a5560fd917250d5d688a6be586"
      ],
      "author": {
        "name": "Eric W. Biederman",
        "email": "ebiederm@xmission.com",
        "time": "Wed Feb 08 07:07:50 2012 -0800"
      },
      "committer": {
        "name": "Eric W. Biederman",
        "email": "ebiederm@xmission.com",
        "time": "Thu May 03 03:29:32 2012 -0700"
      },
      "message": "userns: Store uid and gid types in vfs structures with kuid_t and kgid_t types\n\nThe conversion of all of the users is not done yet there are too many to change\nin one go and leave the code reviewable. For now I change just the header and\na few trivial users and rely on CONFIG_UIDGID_STRICT_TYPE_CHECKS not being set\nto ensure that the code will still compile during the transition.\n\nHelper functions i_uid_read, i_uid_write, i_gid_read, i_gid_write are added\nso that in most cases filesystems can avoid the complexities of multiple user\nnamespaces and can concentrate on moving their raw numeric values into and\nout of the vfs data structures.\n\nAcked-by: Serge Hallyn \u003cserge.hallyn@canonical.com\u003e\nSigned-off-by: Eric W. Biederman \u003cebiederm@xmission.com\u003e\n"
    },
    {
      "commit": "1a48e2ac034d47ed843081c4523b63c46b46888b",
      "tree": "d3a32ac7ffc47b075a64701a2fd74e00bbccf84d",
      "parents": [
        "973c5914260d75292f71a4729753086b9e863d57"
      ],
      "author": {
        "name": "Eric W. Biederman",
        "email": "ebiederm@xmission.com",
        "time": "Mon Nov 14 16:24:06 2011 -0800"
      },
      "committer": {
        "name": "Eric W. Biederman",
        "email": "ebiederm@xmission.com",
        "time": "Sat Apr 07 17:02:46 2012 -0700"
      },
      "message": "userns: Replace the hard to write inode_userns with inode_capable.\n\nThis represents a change in strategy of how to handle user namespaces.\nInstead of tagging everything explicitly with a user namespace and bulking\nup all of the comparisons of uids and gids in the kernel,  all uids and gids\nin use will have a mapping to a flat kuid and kgid spaces respectively.  This\nallows much more of the existing logic to be preserved and in general\nallows for faster code.\n\nIn this new and improved world we allow someone to utiliize capabilities\nover an inode if the inodes owner mapps into the capabilities holders user\nnamespace and the user has capabilities in their user namespace.  Which\nis simple and efficient.\n\nMoving the fs uid comparisons to be comparisons in a flat kuid space\nfollows in later patches, something that is only significant if you\nare using user namespaces.\n\nAcked-by: Serge Hallyn \u003cserge.hallyn@canonical.com\u003e\nSigned-off-by: Eric W. Biederman \u003cebiederm@xmission.com\u003e\n"
    },
    {
      "commit": "5d32c88f0b94061b3af2e3ade92422407282eb12",
      "tree": "2e1f81aa47b2cf59625c8fba17199617e33802e6",
      "parents": [
        "43f63c8711ce02226b7bbdafeba7b8031faf3fb4",
        "dac23b0d0513916498d40412818bd2c581b365f7"
      ],
      "author": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Thu Apr 05 15:30:34 2012 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Thu Apr 05 15:30:34 2012 -0700"
      },
      "message": "Merge branch \u0027akpm\u0027 (Andrew\u0027s patch-bomb)\n\nMerge batch of fixes from Andrew Morton:\n \"The simple_open() cleanup was held back while I wanted for laggards to\n  merge things.\n\n  I still need to send a few checkpoint/restore patches.  I\u0027ve been\n  wobbly about merging them because I\u0027m wobbly about the overall\n  prospects for success of the project.  But after speaking with Pavel\n  at the LSF conference, it sounds like they\u0027re further toward\n  completion than I feared - apparently davem is at the \"has stopped\n  complaining\" stage regarding the net changes.  So I need to go back\n  and re-review those patchs and their (lengthy) discussion.\"\n\n* emailed from Andrew Morton \u003cakpm@linux-foundation.org\u003e: (16 patches)\n  memcg swap: use mem_cgroup_uncharge_swap fix\n  backlight: add driver for DA9052/53 PMIC v1\n  C6X: use set_current_blocked() and block_sigmask()\n  MAINTAINERS: add entry for sparse checker\n  MAINTAINERS: fix REMOTEPROC F: typo\n  alpha: use set_current_blocked() and block_sigmask()\n  simple_open: automatically convert to simple_open()\n  scripts/coccinelle/api/simple_open.cocci: semantic patch for simple_open()\n  libfs: add simple_open()\n  hugetlbfs: remove unregister_filesystem() when initializing module\n  drivers/rtc/rtc-88pm860x.c: fix rtc irq enable callback\n  fs/xattr.c:setxattr(): improve handling of allocation failures\n  fs/xattr.c:listxattr(): fall back to vmalloc() if kmalloc() failed\n  fs/xattr.c: suppress page allocation failure warnings from sys_listxattr()\n  sysrq: use SEND_SIG_FORCED instead of force_sig()\n  proc: fix mount -t proc -o AAA\n"
    },
    {
      "commit": "20955e891d828b2027281fe3295dae6af8e0423b",
      "tree": "551b8b4a3515f3b99e357e8cef5bc2e5d5051d50",
      "parents": [
        "7563ec4c211ba59c2331dc6b94a068250345c387"
      ],
      "author": {
        "name": "Stephen Boyd",
        "email": "sboyd@codeaurora.org",
        "time": "Thu Apr 05 14:25:09 2012 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Thu Apr 05 15:25:50 2012 -0700"
      },
      "message": "libfs: add simple_open()\n\ndebugfs and a few other drivers use an open-coded version of\nsimple_open() to pass a pointer from the file to the read/write file\nops.  Add support for this simple case to libfs so that we can remove\nthe many duplicate copies of this simple function.\n\nSigned-off-by: Stephen Boyd \u003csboyd@codeaurora.org\u003e\nCc: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\nCc: Julia Lawall \u003cJulia.Lawall@lip6.fr\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n"
    },
    {
      "commit": "66189be74ff5f9f3fd6444315b85be210d07cef2",
      "tree": "7a179ddd7e233668dbb108faf847ceb768d2e92c",
      "parents": [
        "9ebb389d0a03b4415fe9014f6922a2412cb1109c"
      ],
      "author": {
        "name": "Pavel Shilovsky",
        "email": "piastry@etersoft.ru",
        "time": "Wed Mar 28 21:56:19 2012 +0400"
      },
      "committer": {
        "name": "Steve French",
        "email": "sfrench@us.ibm.com",
        "time": "Sun Apr 01 13:54:27 2012 -0500"
      },
      "message": "CIFS: Fix VFS lock usage for oplocked files\n\nWe can deadlock if we have a write oplock and two processes\nuse the same file handle. In this case the first process can\u0027t\nunlock its lock if the second process blocked on the lock in the\nsame time.\n\nFix it by using posix_lock_file rather than posix_lock_file_wait\nunder cinode-\u003elock_mutex. If we request a blocking lock and\nposix_lock_file indicates that there is another lock that prevents\nus, wait untill that lock is released and restart our call.\n\nCc: stable@kernel.org\nAcked-by: Jeff Layton \u003cjlayton@redhat.com\u003e\nSigned-off-by: Pavel Shilovsky \u003cpiastry@etersoft.ru\u003e\nSigned-off-by: Steve French \u003csfrench@us.ibm.com\u003e\n"
    },
    {
      "commit": "71db34fc4330f7c784397acb9f1e6ee7f7b32eb2",
      "tree": "77dd08f6f778a799dcd0c48eb72d0742349df235",
      "parents": [
        "50483c3268918ee51a56d1baa39b9149d2d0d521",
        "797a9d797f8483bb67f265c761b76dcd5a077a23"
      ],
      "author": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Thu Mar 29 14:53:25 2012 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Thu Mar 29 14:53:25 2012 -0700"
      },
      "message": "Merge branch \u0027for-3.4\u0027 of git://linux-nfs.org/~bfields/linux\n\nPull nfsd changes from Bruce Fields:\n\nHighlights:\n - Benny Halevy and Tigran Mkrtchyan implemented some more 4.1 features,\n   moving us closer to a complete 4.1 implementation.\n - Bernd Schubert fixed a long-standing problem with readdir cookies on\n   ext2/3/4.\n - Jeff Layton performed a long-overdue overhaul of the server reboot\n   recovery code which will allow us to deprecate the current code (a\n   rather unusual user of the vfs), and give us some needed flexibility\n   for further improvements.\n - Like the client, we now support numeric uid\u0027s and gid\u0027s in the\n   auth_sys case, allowing easier upgrades from NFSv2/v3 to v4.x.\n\nPlus miscellaneous bugfixes and cleanup.\n\nThanks to everyone!\n\nThere are also some delegation fixes waiting on vfs review that I\nsuppose will have to wait for 3.5.  With that done I think we\u0027ll finally\nturn off the \"EXPERIMENTAL\" dependency for v4 (though that\u0027s mostly\nsymbolic as it\u0027s been on by default in distro\u0027s for a while).\n\nAnd the list of 4.1 todo\u0027s should be achievable for 3.5 as well:\n\n   http://wiki.linux-nfs.org/wiki/index.php/Server_4.0_and_4.1_issues\n\nthough we may still want a bit more experience with it before turning it\non by default.\n\n* \u0027for-3.4\u0027 of git://linux-nfs.org/~bfields/linux: (55 commits)\n  nfsd: only register cld pipe notifier when CONFIG_NFSD_V4 is enabled\n  nfsd4: use auth_unix unconditionally on backchannel\n  nfsd: fix NULL pointer dereference in cld_pipe_downcall\n  nfsd4: memory corruption in numeric_name_to_id()\n  sunrpc: skip portmap calls on sessions backchannel\n  nfsd4: allow numeric idmapping\n  nfsd: don\u0027t allow legacy client tracker init for anything but init_net\n  nfsd: add notifier to handle mount/unmount of rpc_pipefs sb\n  nfsd: add the infrastructure to handle the cld upcall\n  nfsd: add a header describing upcall to nfsdcld\n  nfsd: add a per-net-namespace struct for nfsd\n  sunrpc: create nfsd dir in rpc_pipefs\n  nfsd: add nfsd4_client_tracking_ops struct and a way to set it\n  nfsd: convert nfs4_client-\u003ecl_cb_flags to a generic flags field\n  NFSD: Fix nfs4_verifier memory alignment\n  NFSD: Fix warnings when NFSD_DEBUG is not defined\n  nfsd: vfs_llseek() with 32 or 64 bit offsets (hashes)\n  nfsd: rename \u0027int access\u0027 to \u0027int may_flags\u0027 in nfsd_open()\n  ext4: return 32/64-bit dir name hash according to usage type\n  fs: add new FMODE flags: FMODE_32bithash and FMODE_64bithash\n  ...\n"
    },
    {
      "commit": "69e1aaddd63104f37021d0b0f6abfd9623c9134c",
      "tree": "14ad49741b428d270b681694bb2df349465455b9",
      "parents": [
        "56b59b429b4c26e5e730bc8c3d837de9f7d0a966",
        "9d547c35799a4ddd235f1565cec2fff6c9263504"
      ],
      "author": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Wed Mar 28 10:02:55 2012 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Wed Mar 28 10:02:55 2012 -0700"
      },
      "message": "Merge tag \u0027ext4_for_linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4\n\nPull ext4 updates for 3.4 from Ted Ts\u0027o:\n \"Ext4 commits for 3.3 merge window; mostly cleanups and bug fixes\n\n  The changes to export dirty_writeback_interval are from Artem\u0027s s_dirt\n  cleanup patch series.  The same is true of the change to remove the\n  s_dirt helper functions which never got used by anyone in-tree.  I\u0027ve\n  run these changes by Al Viro, and am carrying them so that Artem can\n  more easily fix up the rest of the file systems during the next merge\n  window.  (Originally we had hopped to remove the use of s_dirt from\n  ext4 during this merge window, but his patches had some bugs, so I\n  ultimately ended dropping them from the ext4 tree.)\"\n\n* tag \u0027ext4_for_linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (66 commits)\n  vfs: remove unused superblock helpers\n  mm: export dirty_writeback_interval\n  ext4: remove useless s_dirt assignment\n  ext4: write superblock only once on unmount\n  ext4: do not mark superblock as dirty unnecessarily\n  ext4: correct ext4_punch_hole return codes\n  ext4: remove restrictive checks for EOFBLOCKS_FL\n  ext4: always set then trimmed blocks count into len\n  ext4: fix trimmed block count accunting\n  ext4: fix start and len arguments handling in ext4_trim_fs()\n  ext4: update s_free_{inodes,blocks}_count during online resize\n  ext4: change some printk() calls to use ext4_msg() instead\n  ext4: avoid output message interleaving in ext4_error_\u003cfoo\u003e()\n  ext4: remove trailing newlines from ext4_msg() and ext4_error() messages\n  ext4: add no_printk argument validation, fix fallout\n  ext4: remove redundant \"EXT4-fs: \" from uses of ext4_msg\n  ext4: give more helpful error message in ext4_ext_rm_leaf()\n  ext4: remove unused code from ext4_ext_map_blocks()\n  ext4: rewrite punch hole to use ext4_ext_remove_space()\n  jbd2: cleanup journal tail after transaction commit\n  ...\n"
    },
    {
      "commit": "ed2d265d1266736bd294332d7f649003943ae36e",
      "tree": "860e5b7bb72933e4a9abacdc2f2d75a0e6254e32",
      "parents": [
        "f1d38e423a697b7aa06e12d3ca4753bcc1aa3531",
        "6c03438edeb5c359af35f060ea016ca65671c269"
      ],
      "author": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Sat Mar 24 10:08:39 2012 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Sat Mar 24 10:08:39 2012 -0700"
      },
      "message": "Merge tag \u0027bug-for-3.4\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/paulg/linux\n\nPull \u003clinux/bug.h\u003e cleanup from Paul Gortmaker:\n \"The changes shown here are to unify linux\u0027s BUG support under the one\n  \u003clinux/bug.h\u003e file.  Due to historical reasons, we have some BUG code\n  in bug.h and some in kernel.h -- i.e.  the support for BUILD_BUG in\n  linux/kernel.h predates the addition of linux/bug.h, but old code in\n  kernel.h wasn\u0027t moved to bug.h at that time.  As a band-aid, kernel.h\n  was including \u003casm/bug.h\u003e to pseudo link them.\n\n  This has caused confusion[1] and general yuck/WTF[2] reactions.  Here\n  is an example that violates the principle of least surprise:\n\n      CC      lib/string.o\n      lib/string.c: In function \u0027strlcat\u0027:\n      lib/string.c:225:2: error: implicit declaration of function \u0027BUILD_BUG_ON\u0027\n      make[2]: *** [lib/string.o] Error 1\n      $\n      $ grep linux/bug.h lib/string.c\n      #include \u003clinux/bug.h\u003e\n      $\n\n  We\u0027ve included \u003clinux/bug.h\u003e for the BUG infrastructure and yet we\n  still get a compile fail! [We\u0027ve not kernel.h for BUILD_BUG_ON.] Ugh -\n  very confusing for someone who is new to kernel development.\n\n  With the above in mind, the goals of this changeset are:\n\n  1) find and fix any include/*.h files that were relying on the\n     implicit presence of BUG code.\n  2) find and fix any C files that were consuming kernel.h and hence\n     relying on implicitly getting some/all BUG code.\n  3) Move the BUG related code living in kernel.h to \u003clinux/bug.h\u003e\n  4) remove the asm/bug.h from kernel.h to finally break the chain.\n\n  During development, the order was more like 3-4, build-test, 1-2.  But\n  to ensure that git history for bisect doesn\u0027t get needless build\n  failures introduced, the commits have been reorderd to fix the problem\n  areas in advance.\n\n\t[1]  https://lkml.org/lkml/2012/1/3/90\n\t[2]  https://lkml.org/lkml/2012/1/17/414\"\n\nFix up conflicts (new radeon file, reiserfs header cleanups) as per Paul\nand linux-next.\n\n* tag \u0027bug-for-3.4\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/paulg/linux:\n  kernel.h: doesn\u0027t explicitly use bug.h, so don\u0027t include it.\n  bug: consolidate BUILD_BUG_ON with other bug code\n  BUG: headers with BUG/BUG_ON etc. need linux/bug.h\n  bug.h: add include of it to various implicit C users\n  lib: fix implicit users of kernel.h for TAINT_WARN\n  spinlock: macroize assert_spin_locked to avoid bug.h dependency\n  x86: relocate get/set debugreg fcns to include/asm/debugreg.\n"
    },
    {
      "commit": "9d547c35799a4ddd235f1565cec2fff6c9263504",
      "tree": "c210684cc48a701943a73a415a42797cef5a13fc",
      "parents": [
        "91913a2942d2b582c40673956dec1a9c71d32fe4"
      ],
      "author": {
        "name": "Artem Bityutskiy",
        "email": "artem.bityutskiy@linux.intel.com",
        "time": "Wed Mar 21 22:34:55 2012 -0400"
      },
      "committer": {
        "name": "Theodore Ts\u0027o",
        "email": "tytso@mit.edu",
        "time": "Wed Mar 21 22:34:55 2012 -0400"
      },
      "message": "vfs: remove unused superblock helpers\n\nRemove the \u0027sb_mark_dirty()\u0027, \u0027sb_mark_clean()\u0027 and \u0027sb_is_dirty()\u0027\nhelpers which are not used. I introduced them 2 years and the\nintention was to make all file-systems use them in order to be able to\noptimize \u0027sync_supers()\u0027.  However, Al Viro vetoed my patches at the\nend and asked me to push superblock management down to file-systems\nand get rid of the \u0027s_dirt\u0027 flag completely, as well as kill\n\u0027sync_supers()\u0027 altogether. Thus, remove the helpers.\n\nSigned-off-by: Artem Bityutskiy \u003cartem.bityutskiy@linux.intel.com\u003e\nCc: Al Viro \u003cviro@ZenIV.linux.org.uk\u003e\nSigned-off-by: \"Theodore Ts\u0027o\" \u003ctytso@mit.edu\u003e\n"
    },
    {
      "commit": "68ac1234fb949b66941d94dce4157742799fc581",
      "tree": "04059b7dbaed92d672b8ceef1fcf25c6185e06f8",
      "parents": [
        "40ffe67d2e89c7a475421d007becc11a2f88ea3d"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Mar 15 08:21:57 2012 -0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Tue Mar 20 21:29:41 2012 -0400"
      },
      "message": "switch touch_atime to struct path\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "9bcb4b733c22b7dbc4cf847e707ac98f751e9180",
      "tree": "f99c68d0b7d049d7a25706d23f224c734d0e1da1",
      "parents": [
        "e28e832c3e1e1197873cfd0b6ce86868cf5c391d"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Sun Feb 12 19:43:17 2012 -0500"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Tue Mar 20 21:29:33 2012 -0400"
      },
      "message": "vfs: turn generic_drop_inode() into static inline\n\nOnce upon a time it used to be much bigger, but these days there\u0027s\nno point whatsoever keeping it in fs/inode.c, especially since\nit\u0027s not even needed as initializer for -\u003edrop_inode() - it\u0027s the\ndefault and leaving -\u003edrop_inode NULL will do just as well.\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "8de52778798fe39660a8d6b26f290e0c93202761",
      "tree": "56384beb7863c1f338f2b66b509bf58eea5a99c2",
      "parents": [
        "c16fa4f2ad19908a47c63d8fa436a1178438c7e7"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Mon Feb 06 12:45:27 2012 -0500"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Tue Mar 20 21:29:32 2012 -0400"
      },
      "message": "vfs: check i_nlink limits in vfs_{mkdir,rename_dir,link}\n\nNew field of struct super_block - -\u003es_max_links.  Maximal allowed\nvalue of -\u003ei_nlink or 0; in the latter case all checks still need\nto be done in -\u003elink/-\u003emkdir/-\u003erename instances.  Note that this\nlimit applies both to directoris and to non-directories.\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "6a8a13e03861c0ab83ab07d573ca793cff0e5d00",
      "tree": "8a3587144828b60cb7472cdf0fa1398734303990",
      "parents": [
        "62aa2b537c6f5957afd98e29f96897419ed5ebab"
      ],
      "author": {
        "name": "Bernd Schubert",
        "email": "bernd.schubert@itwm.fraunhofer.de",
        "time": "Tue Mar 13 22:51:38 2012 -0400"
      },
      "committer": {
        "name": "Theodore Ts\u0027o",
        "email": "tytso@mit.edu",
        "time": "Tue Mar 13 22:51:38 2012 -0400"
      },
      "message": "fs: add new FMODE flags: FMODE_32bithash and FMODE_64bithash\n\nThose flags are supposed to be set by NFS readdir() to tell ext3/ext4\nto 32bit (NFSv2) or 64bit hash values (offsets) in seekdir().\n\nSigned-off-by: Bernd Schubert \u003cbernd.schubert@itwm.fraunhofer.de\u003e\nSigned-off-by: \"Theodore Ts\u0027o\" \u003ctytso@mit.edu\u003e\n"
    },
    {
      "commit": "187f1882b5b0748b3c4c22274663fdb372ac0452",
      "tree": "36283f258cf65f03599a045d48bb05d0ec27f3f9",
      "parents": [
        "50af5ead3b44ccf8bd2b4d2a50c1b610f557c480"
      ],
      "author": {
        "name": "Paul Gortmaker",
        "email": "paul.gortmaker@windriver.com",
        "time": "Wed Nov 23 20:12:59 2011 -0500"
      },
      "committer": {
        "name": "Paul Gortmaker",
        "email": "paul.gortmaker@windriver.com",
        "time": "Sun Mar 04 17:54:34 2012 -0500"
      },
      "message": "BUG: headers with BUG/BUG_ON etc. need linux/bug.h\n\nIf a header file is making use of BUG, BUG_ON, BUILD_BUG_ON, or any\nother BUG variant in a static inline (i.e. not in a #define) then\nthat header really should be including \u003clinux/bug.h\u003e and not just\nexpecting it to be implicitly present.\n\nWe can make this change risk-free, since if the files using these\nheaders didn\u0027t have exposure to linux/bug.h already, they would have\nbeen causing compile failures/warnings.\n\nSigned-off-by: Paul Gortmaker \u003cpaul.gortmaker@windriver.com\u003e\n"
    },
    {
      "commit": "6b6dc836a195e077e76977b6c020a73de411b46d",
      "tree": "59920a3aab6db4997f6b7a95c753219bdc12bd64",
      "parents": [
        "074b85175a43a23fdbde60f55feea636e0bf0f85"
      ],
      "author": {
        "name": "Jan Kara",
        "email": "jack@suse.cz",
        "time": "Fri Feb 10 11:03:00 2012 +0100"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Mon Feb 13 20:45:38 2012 -0500"
      },
      "message": "vfs: Provide function to get superblock and wait for it to thaw\n\nIn quota code we need to find a superblock corresponding to a device and wait\nfor superblock to be unfrozen. However this waiting has to happen without\ns_umount semaphore because that is required for superblock to thaw. So provide\na function in VFS for this to keep dances with s_umount where they belong.\n\n[AV: implementation switched to saner variant]\n\nSigned-off-by: Jan Kara \u003cjack@suse.cz\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "c1aab02dac690af7ff634d8e1cb3be6a04387eef",
      "tree": "9018361108b2c370d247452e4517937057bf9895",
      "parents": [
        "ac1e3d4f5c1097422c6e72aeae322033e9a8c803"
      ],
      "author": {
        "name": "Stephen Rothwell",
        "email": "sfr@canb.auug.org.au",
        "time": "Tue Jan 24 11:41:32 2012 +1100"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Mon Jan 23 17:17:45 2012 -0800"
      },
      "message": "migrate_mode.h is not exported to user mode\n\nso move its include into fs.h inside the __KERNEL__ protection.\n\nSigned-off-by: Stephen Rothwell \u003csfr@canb.auug.org.au\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n"
    },
    {
      "commit": "6536e3123e5d3371a6f52e32a3d0694bcc987702",
      "tree": "45212bcb96a33d3a40cd1c631d9670a1bae52c2b",
      "parents": [
        "dcd6c92267155e70a94b3927bce681ce74b80d1f"
      ],
      "author": {
        "name": "Andrew Morton",
        "email": "akpm@linux-foundation.org",
        "time": "Fri Jan 20 14:33:53 2012 -0800"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Mon Jan 23 08:38:47 2012 -0800"
      },
      "message": "mm: fix warnings regarding enum migrate_mode\n\nsparc64 allmodconfig:\n\nIn file included from include/linux/compat.h:15,\n                 from /usr/src/25/arch/sparc/include/asm/siginfo.h:19,\n                 from include/linux/signal.h:5,\n                 from include/linux/sched.h:73,\n                 from arch/sparc/kernel/asm-offsets.c:13:\ninclude/linux/fs.h:618: warning: parameter has incomplete type\n\nIt seems that my sparc64 compiler (gcc-3.4.5) doesn\u0027t like the forward\ndeclaration of enums.\n\nFix this by moving the \"enum migrate_mode\" definition into its own header\nfile.\n\nAcked-by: Mel Gorman \u003cmgorman@suse.de\u003e\nCc: Rik van Riel \u003criel@redhat.com\u003e\nCc: Andrea Arcangeli \u003caarcange@redhat.com\u003e\nCc: Minchan Kim \u003cminchan.kim@gmail.com\u003e\nCc: Dave Jones \u003cdavej@redhat.com\u003e\nCc: Jan Kara \u003cjack@suse.cz\u003e\nCc: Andy Isaacson \u003cadi@hexapodia.org\u003e\nCc: Nai Xia \u003cnai.xia@gmail.com\u003e\nCc: Johannes Weiner \u003cjweiner@redhat.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n"
    },
    {
      "commit": "b3c9dd182ed3bdcdaf0e42625a35924b0497afdc",
      "tree": "ad48ad4d923fee147c736318d0fad35b3755f4f5",
      "parents": [
        "83c2f912b43c3a7babbb6cb7ae2a5276c1ed2a3e",
        "5d381efb3d1f1ef10535a31ca0dd9b22fe1e1922"
      ],
      "author": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Sun Jan 15 12:24:45 2012 -0800"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Sun Jan 15 12:24:45 2012 -0800"
      },
      "message": "Merge branch \u0027for-3.3/core\u0027 of git://git.kernel.dk/linux-block\n\n* \u0027for-3.3/core\u0027 of git://git.kernel.dk/linux-block: (37 commits)\n  Revert \"block: recursive merge requests\"\n  block: Stop using macro stubs for the bio data integrity calls\n  blockdev: convert some macros to static inlines\n  fs: remove unneeded plug in mpage_readpages()\n  block: Add BLKROTATIONAL ioctl\n  block: Introduce blk_set_stacking_limits function\n  block: remove WARN_ON_ONCE() in exit_io_context()\n  block: an exiting task should be allowed to create io_context\n  block: ioc_cgroup_changed() needs to be exported\n  block: recursive merge requests\n  block, cfq: fix empty queue crash caused by request merge\n  block, cfq: move icq creation and rq-\u003eelv.icq association to block core\n  block, cfq: restructure io_cq creation path for io_context interface cleanup\n  block, cfq: move io_cq exit/release to blk-ioc.c\n  block, cfq: move icq cache management to block core\n  block, cfq: move io_cq lookup to blk-ioc.c\n  block, cfq: move cfqd-\u003eicq_list to request_queue and add request-\u003eelv.icq\n  block, cfq: reorganize cfq_io_context into generic and cfq specific parts\n  block: remove elevator_queue-\u003eops\n  block: reorder elevator switch sequence\n  ...\n\nFix up conflicts in:\n - block/blk-cgroup.c\n\tSwitch from can_attach_task to can_attach\n - block/cfq-iosched.c\n\tconflict with now removed cic index changes (we now use q-\u003eid instead)\n"
    },
    {
      "commit": "87192a2a49c475cf322cb143e0fa63b0102d8567",
      "tree": "70acf2fb1e4a9a3a62559ad9218278d2fb114599",
      "parents": [
        "ae55e1aaa7e2e57e538cb98cf617f511c5dc4f73"
      ],
      "author": {
        "name": "Andi Kleen",
        "email": "ak@linux.intel.com",
        "time": "Thu Jan 12 17:20:34 2012 -0800"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Thu Jan 12 20:13:12 2012 -0800"
      },
      "message": "vfs: cache request_queue in struct block_device\n\nThis makes it possible to get from the inode to the request_queue with one\nless cache miss.  Used in followon optimization.\n\nThe livetime of the pointer is the same as the gendisk.\n\nThis assumes that the queue will always stay the same in the gendisk while\nit\u0027s visible to block_devices.  I think that\u0027s safe correct?\n\nSigned-off-by: Andi Kleen \u003cak@linux.intel.com\u003e\nAcked-by: Jeff Moyer \u003cjmoyer@redhat.com\u003e\nCc: Jens Axboe \u003caxboe@kernel.dk\u003e\nCc: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n"
    },
    {
      "commit": "a6bc32b899223a877f595ef9ddc1e89ead5072b8",
      "tree": "a9529f7af2cf8e77bb6670acea32169c891a2b76",
      "parents": [
        "66199712e9eef5aede09dbcd9dfff87798a66917"
      ],
      "author": {
        "name": "Mel Gorman",
        "email": "mgorman@suse.de",
        "time": "Thu Jan 12 17:19:43 2012 -0800"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Thu Jan 12 20:13:09 2012 -0800"
      },
      "message": "mm: compaction: introduce sync-light migration for use by compaction\n\nThis patch adds a lightweight sync migrate operation MIGRATE_SYNC_LIGHT\nmode that avoids writing back pages to backing storage.  Async compaction\nmaps to MIGRATE_ASYNC while sync compaction maps to MIGRATE_SYNC_LIGHT.\nFor other migrate_pages users such as memory hotplug, MIGRATE_SYNC is\nused.\n\nThis avoids sync compaction stalling for an excessive length of time,\nparticularly when copying files to a USB stick where there might be a\nlarge number of dirty pages backed by a filesystem that does not support\n-\u003ewritepages.\n\n[aarcange@redhat.com: This patch is heavily based on Andrea\u0027s work]\n[akpm@linux-foundation.org: fix fs/nfs/write.c build]\n[akpm@linux-foundation.org: fix fs/btrfs/disk-io.c build]\nSigned-off-by: Mel Gorman \u003cmgorman@suse.de\u003e\nReviewed-by: Rik van Riel \u003criel@redhat.com\u003e\nCc: Andrea Arcangeli \u003caarcange@redhat.com\u003e\nCc: Minchan Kim \u003cminchan.kim@gmail.com\u003e\nCc: Dave Jones \u003cdavej@redhat.com\u003e\nCc: Jan Kara \u003cjack@suse.cz\u003e\nCc: Andy Isaacson \u003cadi@hexapodia.org\u003e\nCc: Nai Xia \u003cnai.xia@gmail.com\u003e\nCc: Johannes Weiner \u003cjweiner@redhat.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n"
    },
    {
      "commit": "b969c4ab9f182a6e1b2a0848be349f99714947b0",
      "tree": "dc1c6e4375cfec7b15f13a37307eba8a9e07f40f",
      "parents": [
        "7335084d446b83cbcb15da80497d03f0c1dc9e21"
      ],
      "author": {
        "name": "Mel Gorman",
        "email": "mgorman@suse.de",
        "time": "Thu Jan 12 17:19:34 2012 -0800"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Thu Jan 12 20:13:09 2012 -0800"
      },
      "message": "mm: compaction: determine if dirty pages can be migrated without blocking within -\u003emigratepage\n\nAsynchronous compaction is used when allocating transparent hugepages to\navoid blocking for long periods of time.  Due to reports of stalling,\nthere was a debate on disabling synchronous compaction but this severely\nimpacted allocation success rates.  Part of the reason was that many dirty\npages are skipped in asynchronous compaction by the following check;\n\n\tif (PageDirty(page) \u0026\u0026 !sync \u0026\u0026\n\t\tmapping-\u003ea_ops-\u003emigratepage !\u003d migrate_page)\n\t\t\trc \u003d -EBUSY;\n\nThis skips over all mapping aops using buffer_migrate_page() even though\nit is possible to migrate some of these pages without blocking.  This\npatch updates the -\u003emigratepage callback with a \"sync\" parameter.  It is\nthe responsibility of the callback to fail gracefully if migration would\nblock.\n\nSigned-off-by: Mel Gorman \u003cmgorman@suse.de\u003e\nReviewed-by: Rik van Riel \u003criel@redhat.com\u003e\nCc: Andrea Arcangeli \u003caarcange@redhat.com\u003e\nCc: Minchan Kim \u003cminchan.kim@gmail.com\u003e\nCc: Dave Jones \u003cdavej@redhat.com\u003e\nCc: Jan Kara \u003cjack@suse.cz\u003e\nCc: Andy Isaacson \u003cadi@hexapodia.org\u003e\nCc: Nai Xia \u003cnai.xia@gmail.com\u003e\nCc: Johannes Weiner \u003cjweiner@redhat.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n"
    },
    {
      "commit": "28d82dc1c4edbc352129f97f4ca22624d1fe61de",
      "tree": "a6fbd269d17134ff42597b4e02eba4345bf6d901",
      "parents": [
        "2ccd4f4d4737b37e21dd92c8c584c23cd87740a2"
      ],
      "author": {
        "name": "Jason Baron",
        "email": "jbaron@redhat.com",
        "time": "Thu Jan 12 17:17:43 2012 -0800"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Thu Jan 12 20:13:04 2012 -0800"
      },
      "message": "epoll: limit paths\n\nThe current epoll code can be tickled to run basically indefinitely in\nboth loop detection path check (on ep_insert()), and in the wakeup paths.\nThe programs that tickle this behavior set up deeply linked networks of\nepoll file descriptors that cause the epoll algorithms to traverse them\nindefinitely.  A couple of these sample programs have been previously\nposted in this thread: https://lkml.org/lkml/2011/2/25/297.\n\nTo fix the loop detection path check algorithms, I simply keep track of\nthe epoll nodes that have been already visited.  Thus, the loop detection\nbecomes proportional to the number of epoll file descriptor and links.\nThis dramatically decreases the run-time of the loop check algorithm.  In\none diabolical case I tried it reduced the run-time from 15 mintues (all\nin kernel time) to .3 seconds.\n\nFixing the wakeup paths could be done at wakeup time in a similar manner\nby keeping track of nodes that have already been visited, but the\ncomplexity is harder, since there can be multiple wakeups on different\ncpus...Thus, I\u0027ve opted to limit the number of possible wakeup paths when\nthe paths are created.\n\nThis is accomplished, by noting that the end file descriptor points that\nare found during the loop detection pass (from the newly added link), are\nactually the sources for wakeup events.  I keep a list of these file\ndescriptors and limit the number and length of these paths that emanate\nfrom these \u0027source file descriptors\u0027.  In the current implemetation I\nallow 1000 paths of length 1, 500 of length 2, 100 of length 3, 50 of\nlength 4 and 10 of length 5.  Note that it is sufficient to check the\n\u0027source file descriptors\u0027 reachable from the newly added link, since no\nother \u0027source file descriptors\u0027 will have newly added links.  This allows\nus to check only the wakeup paths that may have gotten too long, and not\nre-check all possible wakeup paths on the system.\n\nIn terms of the path limit selection, I think its first worth noting that\nthe most common case for epoll, is probably the model where you have 1\nepoll file descriptor that is monitoring n number of \u0027source file\ndescriptors\u0027.  In this case, each \u0027source file descriptor\u0027 has a 1 path of\nlength 1.  Thus, I believe that the limits I\u0027m proposing are quite\nreasonable and in fact may be too generous.  Thus, I\u0027m hoping that the\nproposed limits will not prevent any workloads that currently work to\nfail.\n\nIn terms of locking, I have extended the use of the \u0027epmutex\u0027 to all\nepoll_ctl add and remove operations.  Currently its only used in a subset\nof the add paths.  I need to hold the epmutex, so that we can correctly\ntraverse a coherent graph, to check the number of paths.  I believe that\nthis additional locking is probably ok, since its in the setup/teardown\npaths, and doesn\u0027t affect the running paths, but it certainly is going to\nadd some extra overhead.  Also, worth noting is that the epmuex was\nrecently added to the ep_ctl add operations in the initial path loop\ndetection code using the argument that it was not on a critical path.\n\nAnother thing to note here, is the length of epoll chains that is allowed.\nCurrently, eventpoll.c defines:\n\n/* Maximum number of nesting allowed inside epoll sets */\n#define EP_MAX_NESTS 4\n\nThis basically means that I am limited to a graph depth of 5 (EP_MAX_NESTS\n+ 1).  However, this limit is currently only enforced during the loop\ncheck detection code, and only when the epoll file descriptors are added\nin a certain order.  Thus, this limit is currently easily bypassed.  The\nnewly added check for wakeup paths, stricly limits the wakeup paths to a\nlength of 5, regardless of the order in which ep\u0027s are linked together.\nThus, a side-effect of the new code is a more consistent enforcement of\nthe graph depth.\n\nThus far, I\u0027ve tested this, using the sample programs previously\nmentioned, which now either return quickly or return -EINVAL.  I\u0027ve also\ntesting using the piptest.c epoll tester, which showed no difference in\nperformance.  I\u0027ve also created a number of different epoll networks and\ntested that they behave as expectded.\n\nI believe this solves the original diabolical test cases, while still\npreserving the sane epoll nesting.\n\nSigned-off-by: Jason Baron \u003cjbaron@redhat.com\u003e\nCc: Nelson Elhage \u003cnelhage@ksplice.com\u003e\nCc: Davide Libenzi \u003cdavidel@xmailserver.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n"
    },
    {
      "commit": "ef00f59c95fe6e002e7c6e3663cdea65e253f4cc",
      "tree": "8e84273162b7a743767098cc08b6c6eb2b041281",
      "parents": [
        "b1bd055d397e09f99dcef9b138ed104ff1812fcb"
      ],
      "author": {
        "name": "Martin K. Petersen",
        "email": "martin.petersen@oracle.com",
        "time": "Wed Jan 11 16:29:31 2012 +0100"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "axboe@kernel.dk",
        "time": "Wed Jan 11 16:29:31 2012 +0100"
      },
      "message": "block: Add BLKROTATIONAL ioctl\n\nIntroduce an ioctl which permits applications to query whether a block\ndevice is rotational.\n\nSigned-off-by: Martin K. Petersen \u003cmartin.petersen@oracle.com\u003e\nSigned-off-by: Jens Axboe \u003caxboe@kernel.dk\u003e\n"
    },
    {
      "commit": "8e8b87964bc8dc5c14b6543fc933b7725f07d3ac",
      "tree": "9a14c135741f3a8ba960ff97f060a58597604a6d",
      "parents": [
        "7ada4db88634429f4da690ad1c4eb73c93085f0c"
      ],
      "author": {
        "name": "Miklos Szeredi",
        "email": "mszeredi@suse.cz",
        "time": "Mon Nov 21 12:11:33 2011 +0100"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Fri Jan 06 23:20:13 2012 -0500"
      },
      "message": "vfs: prevent remount read-only if pending removes\n\nIf there are any inodes on the super block that have been unlinked\n(i_nlink \u003d\u003d 0) but have not yet been deleted then prevent the\nremounting the super block read-only.\n\nReported-by: Toshiyuki Okajima \u003ctoshi.okajima@jp.fujitsu.com\u003e\nSigned-off-by: Miklos Szeredi \u003cmszeredi@suse.cz\u003e\nTested-by: Toshiyuki Okajima \u003ctoshi.okajima@jp.fujitsu.com\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "7ada4db88634429f4da690ad1c4eb73c93085f0c",
      "tree": "ed1228f0bfa9d0050d746933595004d7c6e940f9",
      "parents": [
        "4ed5e82fe77f4147cf386327c9a63a2dd7eff518"
      ],
      "author": {
        "name": "Miklos Szeredi",
        "email": "mszeredi@suse.cz",
        "time": "Mon Nov 21 12:11:32 2011 +0100"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Fri Jan 06 23:20:12 2012 -0500"
      },
      "message": "vfs: count unlinked inodes\n\nAdd a new counter to the superblock that keeps track of unlinked but\nnot yet deleted inodes.\n\nDo not WARN_ON if set_nlink is called with zero count, just do a\nratelimited printk.  This happens on xfs and probably other\nfilesystems after an unclean shutdown when the filesystem reads inodes\nwhich already have zero i_nlink.  Reported by Christoph Hellwig.\n\nSigned-off-by: Miklos Szeredi \u003cmszeredi@suse.cz\u003e\nTested-by: Toshiyuki Okajima \u003ctoshi.okajima@jp.fujitsu.com\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "4ed5e82fe77f4147cf386327c9a63a2dd7eff518",
      "tree": "f4eaeefaf5d293014457892ac31f878eece07331",
      "parents": [
        "39f7c4db1d2d9e2e2a90abdf34811783089d217d"
      ],
      "author": {
        "name": "Miklos Szeredi",
        "email": "mszeredi@suse.cz",
        "time": "Mon Nov 21 12:11:31 2011 +0100"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Fri Jan 06 23:20:12 2012 -0500"
      },
      "message": "vfs: protect remounting superblock read-only\n\nCurrently remouting superblock read-only is racy in a major way.\n\nWith the per mount read-only infrastructure it is now possible to\nprevent most races, which this patch attempts.\n\nBefore starting the remount read-only, iterate through all mounts\nbelonging to the superblock and if none of them have any pending\nwrites, set sb-\u003es_readonly_remount.  This indicates that remount is in\nprogress and no further write requests are allowed.  If the remount\nsucceeds set MS_RDONLY and reset s_readonly_remount.\n\nIf the remounting is unsuccessful just reset s_readonly_remount.\nThis can result in transient EROFS errors, despite the fact the\nremount failed.  Unfortunately hodling off writes is difficult as\nremount itself may touch the filesystem (e.g. through load_nls())\nwhich would deadlock.\n\nA later patch deals with delayed writes due to nlink going to zero.\n\nSigned-off-by: Miklos Szeredi \u003cmszeredi@suse.cz\u003e\nTested-by: Toshiyuki Okajima \u003ctoshi.okajima@jp.fujitsu.com\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "39f7c4db1d2d9e2e2a90abdf34811783089d217d",
      "tree": "cbc3496ce21e26b5891bb4c4d4155853317ddfb3",
      "parents": [
        "34c80b1d93e6e20ca9dea0baf583a5b5510d92d4"
      ],
      "author": {
        "name": "Miklos Szeredi",
        "email": "mszeredi@suse.cz",
        "time": "Mon Nov 21 12:11:30 2011 +0100"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Fri Jan 06 23:20:12 2012 -0500"
      },
      "message": "vfs: keep list of mounts for each superblock\n\nKeep track of vfsmounts belonging to a superblock.  List is protected\nby vfsmount_lock.\n\nSigned-off-by: Miklos Szeredi \u003cmszeredi@suse.cz\u003e\nTested-by: Toshiyuki Okajima \u003ctoshi.okajima@jp.fujitsu.com\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "34c80b1d93e6e20ca9dea0baf583a5b5510d92d4",
      "tree": "7dcbf0a4e09464247e6992c8f44fcc872867bd3a",
      "parents": [
        "a6322de67b58a00e3a783ad9c87c2a11b2d67b47"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Dec 08 21:32:45 2011 -0500"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Fri Jan 06 23:19:54 2012 -0500"
      },
      "message": "vfs: switch -\u003eshow_options() to struct dentry *\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "a6322de67b58a00e3a783ad9c87c2a11b2d67b47",
      "tree": "526d8cb03b5f357bab06907eecad4c1d444a4934",
      "parents": [
        "d861c630e99febe5ce6055290085556c5b714b06"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Dec 08 21:37:57 2011 -0500"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Fri Jan 06 23:16:55 2012 -0500"
      },
      "message": "vfs: switch -\u003eshow_path() to struct dentry *\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "d861c630e99febe5ce6055290085556c5b714b06",
      "tree": "972fb0e89694197dbdbeca13920de08394abfe39",
      "parents": [
        "64132379d509184425672e0dce1ac0a031e3f2a5"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Dec 08 21:32:45 2011 -0500"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Fri Jan 06 23:16:54 2012 -0500"
      },
      "message": "vfs: switch -\u003eshow_devname() to struct dentry *\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "64132379d509184425672e0dce1ac0a031e3f2a5",
      "tree": "2b7191e0e37bf061b2000935c7cf78e6fb1f3c95",
      "parents": [
        "cdcf116d44e78c7216ba9f8be9af1cdfca7af728"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Thu Dec 08 20:51:13 2011 -0500"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Fri Jan 06 23:16:54 2012 -0500"
      },
      "message": "vfs: switch -\u003eshow_stats to struct dentry *\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "ece2ccb668046610189d88d6aaf05aeb09c988a1",
      "tree": "a0349945f7537de2aca420b47ced23b6294f8b65",
      "parents": [
        "d10577a8d86a0c735488d66d32289a6d66bcfa20",
        "a218d0fdc5f9004164ff151d274487f6799907d0",
        "ff01bb4832651c6d25ac509a06a10fcbd75c461c"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Fri Jan 06 23:15:54 2012 -0500"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Fri Jan 06 23:15:54 2012 -0500"
      },
      "message": "Merge branches \u0027vfsmount-guts\u0027, \u0027umode_t\u0027 and \u0027partitions\u0027 into Z\n"
    },
    {
      "commit": "a218d0fdc5f9004164ff151d274487f6799907d0",
      "tree": "24ea22ffb4aadb1fedff50c4a7fcb17af1981459",
      "parents": [
        "04fc66e789a896e684bfdca30208e57eb832dd96"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Mon Nov 21 14:59:34 2011 -0500"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Tue Jan 03 22:55:19 2012 -0500"
      },
      "message": "switch open and mkdir syscalls to umode_t\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "8d334acdd2c1f57c7a574c6f24d08e4c95582ff0",
      "tree": "195e9c55d2310fa81e7bd325a95481b33b9a2d4a",
      "parents": [
        "62bb109170375f82eb3c51c8080b72954f02dca7"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Sun Jul 24 23:21:59 2011 -0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Tue Jan 03 22:55:11 2012 -0500"
      },
      "message": "switch is_sxid() to umode_t\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "62bb109170375f82eb3c51c8080b72954f02dca7",
      "tree": "47d0a7b84c195b2267ed6803e4492eec6ec8478c",
      "parents": [
        "175a4eb7ea531cdbf6d574f5d5ba9aa0f5e8ed13"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Sun Jul 24 23:20:18 2011 -0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Tue Jan 03 22:55:11 2012 -0500"
      },
      "message": "switch inode_init_owner() to umode_t\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "1a67aafb5f72a436ca044293309fa7e6351d6a35",
      "tree": "d9e58600148de9d41b478cf815773b746647d15b",
      "parents": [
        "4acdaf27ebe2034c342f3be57ef49aed1ad885ef"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Tue Jul 26 01:52:52 2011 -0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Tue Jan 03 22:54:54 2012 -0500"
      },
      "message": "switch -\u003emknod() to umode_t\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "4acdaf27ebe2034c342f3be57ef49aed1ad885ef",
      "tree": "d89a876ee19cd88609a587f8aa6c464a52ee6d98",
      "parents": [
        "18bb1db3e7607e4a997d50991a6f9fa5b0f8722c"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Tue Jul 26 01:42:34 2011 -0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Tue Jan 03 22:54:53 2012 -0500"
      },
      "message": "switch -\u003ecreate() to umode_t\n\nvfs_create() ignores everything outside of 16bit subset of its\nmode argument; switching it to umode_t is obviously equivalent\nand it\u0027s the only caller of the method\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "18bb1db3e7607e4a997d50991a6f9fa5b0f8722c",
      "tree": "4ee4e584bc9a67f3ec14ce159d2d7d4a27e68d4a",
      "parents": [
        "8208a22bb8bd3c52ef634b4ff194f14892ab1713"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Tue Jul 26 01:41:39 2011 -0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Tue Jan 03 22:54:53 2012 -0500"
      },
      "message": "switch vfs_mkdir() and -\u003emkdir() to umode_t\n\nvfs_mkdir() gets int, but immediately drops everything that might not\nfit into umode_t and that\u0027s the only caller of -\u003emkdir()...\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "ff01bb4832651c6d25ac509a06a10fcbd75c461c",
      "tree": "bbfdebd317db97d346df78293566f36e883b1be9",
      "parents": [
        "94ea4158f1733e3b10cef067d535f504866e0c41"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Fri Sep 16 02:31:11 2011 -0400"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Tue Jan 03 22:54:07 2012 -0500"
      },
      "message": "fs: move code out of buffer.c\n\nMove invalidate_bdev, block_sync_page into fs/block_dev.c.  Export\nkill_bdev as well, so brd doesn\u0027t have to open code it.  Reduce\nbuffer_head.h requirement accordingly.\n\nRemoved a rather large comment from invalidate_bdev, as it looked a bit\nobsolete to bother moving.  The small comment replacing it says enough.\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: Al Viro \u003cviro@ZenIV.linux.org.uk\u003e\nCc: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "cf31e70d6cf93f19fe9bf1144966ef40991ac723",
      "tree": "39cdc07b9d46b17ef882ddeb5041f4faec808662",
      "parents": [
        "c972b4bc8331b432f51a5f1bc3ca7e020172717f"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Mon Jan 02 22:28:36 2012 -0500"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Tue Jan 03 22:53:07 2012 -0500"
      },
      "message": "vfs: new helper - vfs_ustat()\n\n... and bury user_get_super()/statfs_by_dentry() - they are\npurely internal now.\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "a5166169f9b920cae3c503910cb66a3ac5dd846d",
      "tree": "ba62f9f2227c4eff9ad6d473f674f72443fba0fb",
      "parents": [
        "5352d3b65ae6f38e71e16f704414c1db4b4f7228"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Mon Dec 12 22:53:00 2011 -0500"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Tue Jan 03 22:52:39 2012 -0500"
      },
      "message": "vfs: convert fs_supers to hlist\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "83aeeada7c69f35e5100b27ec354335597a7a488",
      "tree": "44644e68f303368feba7c8ba3e0e0991d6238ada",
      "parents": [
        "635697c663f38106063d5659f0cf2e45afcd4bb5"
      ],
      "author": {
        "name": "Konstantin Khlebnikov",
        "email": "khlebnikov@openvz.org",
        "time": "Thu Dec 08 14:33:54 2011 -0800"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Fri Dec 09 07:50:27 2011 -0800"
      },
      "message": "vmscan: use atomic-long for shrinker batching\n\nUse atomic-long operations instead of looping around cmpxchg().\n\n[akpm@linux-foundation.org: massage atomic.h inclusions]\nSigned-off-by: Konstantin Khlebnikov \u003ckhlebnikov@openvz.org\u003e\nCc: Dave Chinner \u003cdavid@fromorbit.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n"
    },
    {
      "commit": "02125a826459a6ad142f8d91c5b6357562f96615",
      "tree": "8c9d9860aef93917d9b8cc6d471fe68b58ce7a9d",
      "parents": [
        "5611cc4572e889b62a7b4c72a413536bf6a9c416"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Mon Dec 05 08:43:34 2011 -0500"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Tue Dec 06 23:57:18 2011 -0500"
      },
      "message": "fix apparmor dereferencing potentially freed dentry, sanitize __d_path() API\n\n__d_path() API is asking for trouble and in case of apparmor d_namespace_path()\ngetting just that.  The root cause is that when __d_path() misses the root\nit had been told to look for, it stores the location of the most remote ancestor\nin *root.  Without grabbing references.  Sure, at the moment of call it had\nbeen pinned down by what we have in *path.  And if we raced with umount -l, we\ncould have very well stopped at vfsmount/dentry that got freed as soon as\nprepend_path() dropped vfsmount_lock.\n\nIt is safe to compare these pointers with pre-existing (and known to be still\nalive) vfsmount and dentry, as long as all we are asking is \"is it the same\naddress?\".  Dereferencing is not safe and apparmor ended up stepping into\nthat.  d_namespace_path() really wants to examine the place where we stopped,\neven if it\u0027s not connected to our namespace.  As the result, it looked\nat -\u003ed_sb-\u003es_magic of a dentry that might\u0027ve been already freed by that point.\nAll other callers had been careful enough to avoid that, but it\u0027s really\na bad interface - it invites that kind of trouble.\n\nThe fix is fairly straightforward, even though it\u0027s bigger than I\u0027d like:\n\t* prepend_path() root argument becomes const.\n\t* __d_path() is never called with NULL/NULL root.  It was a kludge\nto start with.  Instead, we have an explicit function - d_absolute_root().\nSame as __d_path(), except that it doesn\u0027t get root passed and stops where\nit stops.  apparmor and tomoyo are using it.\n\t* __d_path() returns NULL on path outside of root.  The main\ncaller is show_mountinfo() and that\u0027s precisely what we pass root for - to\nskip those outside chroot jail.  Those who don\u0027t want that can (and do)\nuse d_path().\n\t* __d_path() root argument becomes const.  Everyone agrees, I hope.\n\t* apparmor does *NOT* try to use __d_path() or any of its variants\nwhen it sees that path-\u003emnt is an internal vfsmount.  In that case it\u0027s\ndefinitely not mounted anywhere and dentry_path() is exactly what we want\nthere.  Handling of sysctl()-triggered weirdness is moved to that place.\n\t* if apparmor is asked to do pathname relative to chroot jail\nand __d_path() tells it we it\u0027s not in that jail, the sucker just calls\nd_absolute_path() instead.  That\u0027s the other remaining caller of __d_path(),\nBTW.\n        * seq_path_root() does _NOT_ return -ENAMETOOLONG (it\u0027s stupid anyway -\nthe normal seq_file logics will take care of growing the buffer and redoing\nthe call of -\u003eshow() just fine).  However, if it gets path not reachable\nfrom root, it returns SEQ_SKIP.  The only caller adjusted (i.e. stopped\nignoring the return value as it used to do).\n\nReviewed-by: John Johansen \u003cjohn.johansen@canonical.com\u003e\nACKed-by: John Johansen \u003cjohn.johansen@canonical.com\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\nCc: stable@vger.kernel.org\n"
    },
    {
      "commit": "ea441d1104cf1efb471fa81bc91e9fd1e6ae29fd",
      "tree": "32b7c4f7c78af47936a604e3f4e13e8e61f834a0",
      "parents": [
        "c13344958780b4046305ee6235d686c846535529"
      ],
      "author": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Wed Nov 16 21:43:59 2011 -0500"
      },
      "committer": {
        "name": "Al Viro",
        "email": "viro@zeniv.linux.org.uk",
        "time": "Wed Nov 16 22:00:34 2011 -0500"
      },
      "message": "new helper: mount_subtree()\n\ntakes vfsmount and relative path, does lookup within that vfsmount\n(possibly triggering automounts) and returns the result as root\nof subtree suitable for return by -\u003emount() (i.e. a reference to\ndentry and an active reference to its superblock grabbed, superblock\nlocked exclusive).\n\nbtrfs and nfs switched to it instead of open-coding the sucker.\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n"
    },
    {
      "commit": "d211858837ff8d8e31942ca7d27e6e08b3b46f5e",
      "tree": "a8ec83a791066e64ad02052498dbe39ebefacab9",
      "parents": [
        "f1f8935a5c38a2c61e86a42bc971a2539eef2211",
        "f0023bc617ba600956b9226f1806033d7486c8ba"
      ],
      "author": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Wed Nov 02 11:41:01 2011 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Wed Nov 02 11:41:01 2011 -0700"
      },
      "message": "Merge branch \u0027for-next\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/hch/vfs-queue\n\n* \u0027for-next\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/hch/vfs-queue:\n  vfs: add d_prune dentry operation\n  vfs: protect i_nlink\n  filesystems: add set_nlink()\n  filesystems: add missing nlink wrappers\n  logfs: remove unnecessary nlink setting\n  ocfs2: remove unnecessary nlink setting\n  jfs: remove unnecessary nlink setting\n  hypfs: remove unnecessary nlink setting\n  vfs: ignore error on forced remount\n  readlinkat: ensure we return ENOENT for the empty pathname for normal lookups\n  vfs: fix dentry leak in simple_fill_super()\n"
    },
    {
      "commit": "f1f8935a5c38a2c61e86a42bc971a2539eef2211",
      "tree": "694950045f2f5d89507d7206cf6595e09cdfbd2c",
      "parents": [
        "34116645d912f65d7eb4508a1db3c9d0e45facb1",
        "f2a44523b20f323e4aef7c16261d34d6f0a4bf06"
      ],
      "author": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Wed Nov 02 10:06:20 2011 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Wed Nov 02 10:06:20 2011 -0700"
      },
      "message": "Merge branch \u0027for_linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4\n\n* \u0027for_linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (97 commits)\n  jbd2: Unify log messages in jbd2 code\n  jbd/jbd2: validate sb-\u003es_first in journal_get_superblock()\n  ext4: let ext4_ext_rm_leaf work with EXT_DEBUG defined\n  ext4: fix a syntax error in ext4_ext_insert_extent when debugging enabled\n  ext4: fix a typo in struct ext4_allocation_context\n  ext4: Don\u0027t normalize an falloc request if it can fit in 1 extent.\n  ext4: remove comments about extent mount option in ext4_new_inode()\n  ext4: let ext4_discard_partial_buffers handle unaligned range correctly\n  ext4: return ENOMEM if find_or_create_pages fails\n  ext4: move vars to local scope in ext4_discard_partial_page_buffers_no_lock()\n  ext4: Create helper function for EXT4_IO_END_UNWRITTEN and i_aiodio_unwritten\n  ext4: optimize locking for end_io extent conversion\n  ext4: remove unnecessary call to waitqueue_active()\n  ext4: Use correct locking for ext4_end_io_nolock()\n  ext4: fix race in xattr block allocation path\n  ext4: trace punch_hole correctly in ext4_ext_map_blocks\n  ext4: clean up AGGRESSIVE_TEST code\n  ext4: move variables to their scope\n  ext4: fix quota accounting during migration\n  ext4: migrate cleanup\n  ...\n"
    },
    {
      "commit": "a78ef704a8dd430225955f0709b22d4a6ba21deb",
      "tree": "ebd8f8a5a257077912b7cc38ecfdab43e1d7d73d",
      "parents": [
        "bfe8684869601dacfcb2cd69ef8cfd9045f62170"
      ],
      "author": {
        "name": "Miklos Szeredi",
        "email": "mszeredi@suse.cz",
        "time": "Fri Oct 28 14:13:30 2011 +0200"
      },
      "committer": {
        "name": "Christoph Hellwig",
        "email": "hch@serles.lst.de",
        "time": "Wed Nov 02 12:53:43 2011 +0100"
      },
      "message": "vfs: protect i_nlink\n\nPrevent direct modification of i_nlink by making it const and adding a\nnon-const __i_nlink alias.\n\nSigned-off-by: Miklos Szeredi \u003cmszeredi@suse.cz\u003e\nTested-by: Toshiyuki Okajima \u003ctoshi.okajima@jp.fujitsu.com\u003e\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\n"
    },
    {
      "commit": "bfe8684869601dacfcb2cd69ef8cfd9045f62170",
      "tree": "4e213aaa766b26f43f0f9ec7998a7745239d9377",
      "parents": [
        "6d6b77f163c7eabedbba00ed2abb7d4a570bff76"
      ],
      "author": {
        "name": "Miklos Szeredi",
        "email": "mszeredi@suse.cz",
        "time": "Fri Oct 28 14:13:29 2011 +0200"
      },
      "committer": {
        "name": "Christoph Hellwig",
        "email": "hch@serles.lst.de",
        "time": "Wed Nov 02 12:53:43 2011 +0100"
      },
      "message": "filesystems: add set_nlink()\n\nReplace remaining direct i_nlink updates with a new set_nlink()\nupdater function.\n\nSigned-off-by: Miklos Szeredi \u003cmszeredi@suse.cz\u003e\nTested-by: Toshiyuki Okajima \u003ctoshi.okajima@jp.fujitsu.com\u003e\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\n"
    },
    {
      "commit": "b9075fa968a0a4347aef35e235e2995c0e57dddd",
      "tree": "cf9f9716784e790d8a43339653256d9cf9178ff3",
      "parents": [
        "ae29bc92da01a2e9d278a9a58c3b307d41cc0254"
      ],
      "author": {
        "name": "Joe Perches",
        "email": "joe@perches.com",
        "time": "Mon Oct 31 17:11:33 2011 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Mon Oct 31 17:30:54 2011 -0700"
      },
      "message": "treewide: use __printf not __attribute__((format(printf,...)))\n\nStandardize the style for compiler based printf format verification.\nStandardized the location of __printf too.\n\nDone via script and a little typing.\n\n$ grep -rPl --include\u003d*.[ch] -w \"__attribute__\" * | \\\n  grep -vP \"^(tools|scripts|include/linux/compiler-gcc.h)\" | \\\n  xargs perl -n -i -e \u0027local $/; while (\u003c\u003e) { s/\\b__attribute__\\s*\\(\\s*\\(\\s*format\\s*\\(\\s*printf\\s*,\\s*(.+)\\s*,\\s*(.+)\\s*\\)\\s*\\)\\s*\\)/__printf($1, $2)/g ; print; }\u0027\n\n[akpm@linux-foundation.org: revert arch bits]\nSigned-off-by: Joe Perches \u003cjoe@perches.com\u003e\nCc: \"Kirill A. Shutemov\" \u003ckirill@shutemov.name\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n"
    },
    {
      "commit": "fcf634098c00dd9cd247447368495f0b79be12d1",
      "tree": "77fc98cd461bd52ba3b14e833d54a115ffbbd7bc",
      "parents": [
        "32ea845d5bafc37b7406bea1aee3005407cb0900"
      ],
      "author": {
        "name": "Christopher Yeoh",
        "email": "cyeoh@au1.ibm.com",
        "time": "Mon Oct 31 17:06:39 2011 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Mon Oct 31 17:30:44 2011 -0700"
      },
      "message": "Cross Memory Attach\n\nThe basic idea behind cross memory attach is to allow MPI programs doing\nintra-node communication to do a single copy of the message rather than a\ndouble copy of the message via shared memory.\n\nThe following patch attempts to achieve this by allowing a destination\nprocess, given an address and size from a source process, to copy memory\ndirectly from the source process into its own address space via a system\ncall.  There is also a symmetrical ability to copy from the current\nprocess\u0027s address space into a destination process\u0027s address space.\n\n- Use of /proc/pid/mem has been considered, but there are issues with\n  using it:\n  - Does not allow for specifying iovecs for both src and dest, assuming\n    preadv or pwritev was implemented either the area read from or\n  written to would need to be contiguous.\n  - Currently mem_read allows only processes who are currently\n  ptrace\u0027ing the target and are still able to ptrace the target to read\n  from the target. This check could possibly be moved to the open call,\n  but its not clear exactly what race this restriction is stopping\n  (reason  appears to have been lost)\n  - Having to send the fd of /proc/self/mem via SCM_RIGHTS on unix\n  domain socket is a bit ugly from a userspace point of view,\n  especially when you may have hundreds if not (eventually) thousands\n  of processes  that all need to do this with each other\n  - Doesn\u0027t allow for some future use of the interface we would like to\n  consider adding in the future (see below)\n  - Interestingly reading from /proc/pid/mem currently actually\n  involves two copies! (But this could be fixed pretty easily)\n\nAs mentioned previously use of vmsplice instead was considered, but has\nproblems.  Since you need the reader and writer working co-operatively if\nthe pipe is not drained then you block.  Which requires some wrapping to\ndo non blocking on the send side or polling on the receive.  In all to all\ncommunication it requires ordering otherwise you can deadlock.  And in the\nexample of many MPI tasks writing to one MPI task vmsplice serialises the\ncopying.\n\nThere are some cases of MPI collectives where even a single copy interface\ndoes not get us the performance gain we could.  For example in an\nMPI_Reduce rather than copy the data from the source we would like to\ninstead use it directly in a mathops (say the reduce is doing a sum) as\nthis would save us doing a copy.  We don\u0027t need to keep a copy of the data\nfrom the source.  I haven\u0027t implemented this, but I think this interface\ncould in the future do all this through the use of the flags - eg could\nspecify the math operation and type and the kernel rather than just\ncopying the data would apply the specified operation between the source\nand destination and store it in the destination.\n\nAlthough we don\u0027t have a \"second user\" of the interface (though I\u0027ve had\nsome nibbles from people who may be interested in using it for intra\nprocess messaging which is not MPI).  This interface is something which\nhardware vendors are already doing for their custom drivers to implement\nfast local communication.  And so in addition to this being useful for\nOpenMPI it would mean the driver maintainers don\u0027t have to fix things up\nwhen the mm changes.\n\nThere was some discussion about how much faster a true zero copy would\ngo. Here\u0027s a link back to the email with some testing I did on that:\n\nhttp://marc.info/?l\u003dlinux-mm\u0026m\u003d130105930902915\u0026w\u003d2\n\nThere is a basic man page for the proposed interface here:\n\nhttp://ozlabs.org/~cyeoh/cma/process_vm_readv.txt\n\nThis has been implemented for x86 and powerpc, other architecture should\nmainly (I think) just need to add syscall numbers for the process_vm_readv\nand process_vm_writev. There are 32 bit compatibility versions for\n64-bit kernels.\n\nFor arch maintainers there are some simple tests to be able to quickly\nverify that the syscalls are working correctly here:\n\nhttp://ozlabs.org/~cyeoh/cma/cma-test-20110718.tgz\n\nSigned-off-by: Chris Yeoh \u003cyeohc@au1.ibm.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: \"H. Peter Anvin\" \u003chpa@zytor.com\u003e\nCc: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nCc: Arnd Bergmann \u003carnd@arndb.de\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nCc: David Howells \u003cdhowells@redhat.com\u003e\nCc: James Morris \u003cjmorris@namei.org\u003e\nCc: \u003clinux-man@vger.kernel.org\u003e\nCc: \u003clinux-arch@vger.kernel.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n"
    },
    {
      "commit": "6cdbb0effc2f511ced23e46f2117e4b31d3d4a50",
      "tree": "a440c35498abfd171b619a398f1cee1b62be8219",
      "parents": [
        "80e675f906db54eb1ce3a9555cee5f45b5b72ab2"
      ],
      "author": {
        "name": "Theodore Ts\u0027o",
        "email": "tytso@mit.edu",
        "time": "Sat Oct 29 08:24:18 2011 -0400"
      },
      "committer": {
        "name": "Theodore Ts\u0027o",
        "email": "tytso@mit.edu",
        "time": "Sat Oct 29 08:24:18 2011 -0400"
      },
      "message": "fs: optimize out 16 bytes worth of padding in struct inode\n\nRearrange the fields in struct inode so that on an x86_64 system,\nfields that require 8-byte alignment don\u0027t end up causing 4-byte holes\nin the structure.  It reduces the size of struct inode from 568 bytes\nto 552 bytes.\n\nAlso move the fields protected by i_lock (i_blocks, i_bytes, and\ni_size) into the same cache line as i_lock.\n\nSigned-off-by: \"Theodore Ts\u0027o\" \u003ctytso@mit.edu\u003e\n"
    },
    {
      "commit": "f362f98e7c445643d27c610bb7a86b79727b592e",
      "tree": "399d9ebccdfbdfe9690ab1403a001d6f08e54b41",
      "parents": [
        "f793f2961170c0b49c1650e69e7825484159ce62",
        "f3c7691e8d30d88899b514675c7c86d19057b5fd"
      ],
      "author": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Fri Oct 28 10:49:34 2011 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Fri Oct 28 10:49:34 2011 -0700"
      },
      "message": "Merge branch \u0027for-next\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/hch/vfs-queue\n\n* \u0027for-next\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/hch/vfs-queue: (21 commits)\n  leases: fix write-open/read-lease race\n  nfs: drop unnecessary locking in llseek\n  ext4: replace cut\u0027n\u0027pasted llseek code with generic_file_llseek_size\n  vfs: add generic_file_llseek_size\n  vfs: do (nearly) lockless generic_file_llseek\n  direct-io: merge direct_io_walker into __blockdev_direct_IO\n  direct-io: inline the complete submission path\n  direct-io: separate map_bh from dio\n  direct-io: use a slab cache for struct dio\n  direct-io: rearrange fields in dio/dio_submit to avoid holes\n  direct-io: fix a wrong comment\n  direct-io: separate fields only used in the submission path from struct dio\n  vfs: fix spinning prevention in prune_icache_sb\n  vfs: add a comment to inode_permission()\n  vfs: pass all mask flags check_acl and posix_acl_permission\n  vfs: add hex format for MAY_* flag values\n  vfs: indicate that the permission functions take all the MAY_* flags\n  compat: sync compat_stats with statfs.\n  vfs: add \"device\" tag to /proc/self/mountstats\n  cleanup: vfs: small comment fix for block_invalidatepage\n  ...\n\nFix up trivial conflict in fs/gfs2/file.c (llseek changes)\n"
    },
    {
      "commit": "5760495a872d63a182962680a13c2af29235237c",
      "tree": "ab7ac2b0ec66006efbc27c318c89474a63d6e4d1",
      "parents": [
        "ef3d0fd27e90f67e35da516dafc1482c82939a60"
      ],
      "author": {
        "name": "Andi Kleen",
        "email": "ak@linux.intel.com",
        "time": "Thu Sep 15 16:06:50 2011 -0700"
      },
      "committer": {
        "name": "root",
        "email": "root@serles.lst.de",
        "time": "Fri Oct 28 14:58:59 2011 +0200"
      },
      "message": "vfs: add generic_file_llseek_size\n\nAdd a generic_file_llseek variant to the VFS that allows passing in\nthe maximum file size of the file system, instead of always\nusing maxbytes from the superblock.\n\nThis can be used to eliminate some cut\u0027n\u0027paste seek code in ext4.\n\nSigned-off-by: Andi Kleen \u003cak@linux.intel.com\u003e\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\n"
    },
    {
      "commit": "ef3d0fd27e90f67e35da516dafc1482c82939a60",
      "tree": "dea852eab2a52782867becffb11bce2577ed2b91",
      "parents": [
        "847cc6371ba820763773e993000410d6d8d23515"
      ],
      "author": {
        "name": "Andi Kleen",
        "email": "ak@linux.intel.com",
        "time": "Thu Sep 15 16:06:48 2011 -0700"
      },
      "committer": {
        "name": "root",
        "email": "root@serles.lst.de",
        "time": "Fri Oct 28 14:58:58 2011 +0200"
      },
      "message": "vfs: do (nearly) lockless generic_file_llseek\n\nThe i_mutex lock use of generic _file_llseek hurts.  Independent processes\naccessing the same file synchronize over a single lock, even though\nthey have no need for synchronization at all.\n\nUnder high utilization this can cause llseek to scale very poorly on larger\nsystems.\n\nThis patch does some rethinking of the llseek locking model:\n\nFirst the 64bit f_pos is not necessarily atomic without locks\non 32bit systems. This can already cause races with read() today.\nThis was discussed on linux-kernel in the past and deemed acceptable.\nThe patch does not change that.\n\nLet\u0027s look at the different seek variants:\n\nSEEK_SET: Doesn\u0027t really need any locking.\nIf there\u0027s a race one writer wins, the other loses.\n\nFor 32bit the non atomic update races against read()\nstay the same. Without a lock they can also happen\nagainst write() now.  The read() race was deemed\nacceptable in past discussions, and I think if it\u0027s\nok for read it\u0027s ok for write too.\n\n\u003d\u003e Don\u0027t need a lock.\n\nSEEK_END: This behaves like SEEK_SET plus it reads\nthe maximum size too. Reading the maximum size would have the\n32bit atomic problem. But luckily we already have a way to read\nthe maximum size without locking (i_size_read), so we\ncan just use that instead.\n\nWithout i_mutex there is no synchronization with write() anymore,\nhowever since the write() update is atomic on 64bit it just behaves\nlike another racy SEEK_SET.  On non atomic 32bit it\u0027s the same\nas SEEK_SET.\n\n\u003d\u003e Don\u0027t need a lock, but need to use i_size_read()\n\nSEEK_CUR: This has a read-modify-write race window\non the same file. One could argue that any application\ndoing unsynchronized seeks on the same file is already broken.\nBut for the sake of not adding a regression here I\u0027m\nusing the file-\u003ef_lock to synchronize this. Using this\nlock is much better than the inode mutex because it doesn\u0027t\nsynchronize between processes.\n\n\u003d\u003e So still need a lock, but can use a f_lock.\n\nThis patch implements this new scheme in generic_file_llseek.\nI dropped generic_file_llseek_unlocked and changed all callers.\n\nSigned-off-by: Andi Kleen \u003cak@linux.intel.com\u003e\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\n"
    },
    {
      "commit": "8522ca5818652c4da6808c66a307abce75462212",
      "tree": "dd127ea11faf379c3b4610eb9f15feee79cb802f",
      "parents": [
        "8fd90c8d1dacb5ff0f372217c97f57a9e61559cd"
      ],
      "author": {
        "name": "Aneesh Kumar K.V",
        "email": "aneesh.kumar@linux.vnet.ibm.com",
        "time": "Sun Oct 23 23:13:31 2011 +0530"
      },
      "committer": {
        "name": "root",
        "email": "root@serles.lst.de",
        "time": "Fri Oct 28 14:58:54 2011 +0200"
      },
      "message": "vfs: add hex format for MAY_* flag values\n\nWe are going to add more flags and having them in hex format\nmake it simpler\n\nAcked-by: J. Bruce Fields \u003cbfields@redhat.com\u003e\nAcked-by: David Howells \u003cdhowells@redhat.com\u003e\nSigned-off-by: Aneesh Kumar K.V \u003caneesh.kumar@linux.vnet.ibm.com\u003e\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\n"
    },
    {
      "commit": "1442d1678ca7e53574fd403ba7bee6f4125d920c",
      "tree": "fd053a849158d2c5b8345ced8982108825b85736",
      "parents": [
        "7e0bb71e75020348bee523720a0c2f04cc72f540",
        "345c284290cabb5484df909303e73d6def8ec8ec"
      ],
      "author": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Tue Oct 25 15:42:01 2011 +0200"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Tue Oct 25 15:42:01 2011 +0200"
      },
      "message": "Merge branch \u0027for-3.2\u0027 of git://linux-nfs.org/~bfields/linux\n\n* \u0027for-3.2\u0027 of git://linux-nfs.org/~bfields/linux: (103 commits)\n  nfs41: implement DESTROY_CLIENTID operation\n  nfsd4: typo logical vs bitwise negate for want_mask\n  nfsd4: allow NFS4_SHARE_SIGNAL_DELEG_WHEN_RESRC_AVAIL | NFS4_SHARE_PUSH_DELEG_WHEN_UNCONTENDED\n  nfsd4: seq-\u003estatus_flags may be used unitialized\n  nfsd41: use SEQ4_STATUS_BACKCHANNEL_FAULT when cb_sequence is invalid\n  nfsd4: implement new 4.1 open reclaim types\n  nfsd4: remove unneeded CLAIM_DELEGATE_CUR workaround\n  nfsd4: warn on open failure after create\n  nfsd4: preallocate open stateid in process_open1()\n  nfsd4: do idr preallocation with stateid allocation\n  nfsd4: preallocate nfs4_file in process_open1()\n  nfsd4: clean up open owners on OPEN failure\n  nfsd4: simplify process_open1 logic\n  nfsd4: make is_open_owner boolean\n  nfsd4: centralize renew_client() calls\n  nfsd4: typo logical vs bitwise negate\n  nfs: fix bug about IPv6 address scope checking\n  nfsd4: more robust ignoring of WANT bits in OPEN\n  nfsd4: move name-length checks to xdr\n  nfsd4: move access/deny validity checks to xdr code\n  ...\n"
    },
    {
      "commit": "fed678dc8a8b839c8189b5d889a94e865cd327dd",
      "tree": "d2bf10d2a4e4ca0a27ccd6f7ae40e8e259acfcfc",
      "parents": [
        "808bf29b9195c52239b9aaeda7c6082a0ddf07c6",
        "6c4867f6469964e34c5f4ee229a2a7f71a34c7ff"
      ],
      "author": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Wed Sep 21 13:20:21 2011 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Wed Sep 21 13:20:21 2011 -0700"
      },
      "message": "Merge branch \u0027for-linus\u0027 of git://git.kernel.dk/linux-block\n\n* \u0027for-linus\u0027 of git://git.kernel.dk/linux-block:\n  floppy: use del_timer_sync() in init cleanup\n  blk-cgroup: be able to remove the record of unplugged device\n  block: Don\u0027t check QUEUE_FLAG_SAME_COMP in __blk_complete_request\n  mm: Add comment explaining task state setting in bdi_forker_thread()\n  mm: Cleanup clearing of BDI_pending bit in bdi_forker_thread()\n  block: simplify force plug flush code a little bit\n  block: change force plug flush call order\n  block: Fix queue_flag update when rq_affinity goes from 2 to 1\n  block: separate priority boosting from REQ_META\n  block: remove READ_META and WRITE_META\n  xen-blkback: fixed indentation and comments\n  xen-blkback: Don\u0027t disconnect backend until state switched to XenbusStateClosed.\n"
    },
    {
      "commit": "e096d0c7e2e4e5893792db865dd065ac73cf1f00",
      "tree": "20e603f81a9f1a55d330cba670952b991d564e00",
      "parents": [
        "e33f2d238e2e53e264c758c0849423a9308eb63e"
      ],
      "author": {
        "name": "Josh Boyer",
        "email": "jwboyer@redhat.com",
        "time": "Thu Aug 25 07:48:12 2011 -0400"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Thu Aug 25 10:50:18 2011 -0700"
      },
      "message": "lockdep: Add helper function for dir vs file i_mutex annotation\n\nPurely in-memory filesystems do not use the inode hash as the dcache\ntells us if an entry already exists.  As a result, they do not call\nunlock_new_inode, and thus directory inodes do not get put into a\ndifferent lockdep class for i_sem.\n\nWe need the different lockdep classes, because the locking order for\ni_mutex is different for directory inodes and regular inodes.  Directory\ninodes can do \"readdir()\", which takes i_mutex *before* possibly taking\nmm-\u003emmap_sem (due to a page fault while copying the directory entry to\nuser space).\n\nIn contrast, regular inodes can be mmap\u0027ed, which takes mm-\u003emmap_sem\nbefore accessing i_mutex.\n\nThe two cases can never happen for the same inode, so no real deadlock\ncan occur, but without the different lockdep classes, lockdep cannot\nunderstand that.  As a result, if CONFIG_DEBUG_LOCK_ALLOC is set, this\ncan lead to false positives from lockdep like below:\n\n    find/645 is trying to acquire lock:\n     (\u0026mm-\u003emmap_sem){++++++}, at: [\u003cffffffff81109514\u003e] might_fault+0x5c/0xac\n\n    but task is already holding lock:\n     (\u0026sb-\u003es_type-\u003ei_mutex_key#15){+.+.+.}, at: [\u003cffffffff81149f34\u003e]\n    vfs_readdir+0x5b/0xb4\n\n    which lock already depends on the new lock.\n\n    the existing dependency chain (in reverse order) is:\n\n    -\u003e #1 (\u0026sb-\u003es_type-\u003ei_mutex_key#15){+.+.+.}:\n          [\u003cffffffff8108ac26\u003e] lock_acquire+0xbf/0x103\n          [\u003cffffffff814db822\u003e] __mutex_lock_common+0x4c/0x361\n          [\u003cffffffff814dbc46\u003e] mutex_lock_nested+0x40/0x45\n          [\u003cffffffff811daa87\u003e] hugetlbfs_file_mmap+0x82/0x110\n          [\u003cffffffff81111557\u003e] mmap_region+0x258/0x432\n          [\u003cffffffff811119dd\u003e] do_mmap_pgoff+0x2ac/0x306\n          [\u003cffffffff81111b4f\u003e] sys_mmap_pgoff+0x118/0x16a\n          [\u003cffffffff8100c858\u003e] sys_mmap+0x22/0x24\n          [\u003cffffffff814e3ec2\u003e] system_call_fastpath+0x16/0x1b\n\n    -\u003e #0 (\u0026mm-\u003emmap_sem){++++++}:\n          [\u003cffffffff8108a4bc\u003e] __lock_acquire+0xa1a/0xcf7\n          [\u003cffffffff8108ac26\u003e] lock_acquire+0xbf/0x103\n          [\u003cffffffff81109541\u003e] might_fault+0x89/0xac\n          [\u003cffffffff81149cff\u003e] filldir+0x6f/0xc7\n          [\u003cffffffff811586ea\u003e] dcache_readdir+0x67/0x205\n          [\u003cffffffff81149f54\u003e] vfs_readdir+0x7b/0xb4\n          [\u003cffffffff8114a073\u003e] sys_getdents+0x7e/0xd1\n          [\u003cffffffff814e3ec2\u003e] system_call_fastpath+0x16/0x1b\n\nThis patch moves the directory vs file lockdep annotation into a helper\nfunction that can be called by in-memory filesystems and has hugetlbfs\ncall it.\n\nSigned-off-by: Josh Boyer \u003cjwboyer@redhat.com\u003e\nAcked-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n"
    },
    {
      "commit": "5dc06c5a70b79a323152bec7e55783e705767e63",
      "tree": "8f008edc8574ecda04ee6deb13d69b489e8250b6",
      "parents": [
        "fcb8ce5cfe30ca9ca5c9a79cdfe26d1993e65e0c"
      ],
      "author": {
        "name": "Christoph Hellwig",
        "email": "hch@infradead.org",
        "time": "Tue Aug 23 14:49:55 2011 +0200"
      },
      "committer": {
        "name": "Jens Axboe",
        "email": "jaxboe@fusionio.com",
        "time": "Tue Aug 23 14:49:55 2011 +0200"
      },
      "message": "block: remove READ_META and WRITE_META\n\nReplace all occurnanced of the undocumented READ_META with READ | REQ_META\nand remove the unused WRITE_META define.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Jens Axboe \u003cjaxboe@fusionio.com\u003e\n"
    },
    {
      "commit": "778fc546f749c588aa2f6cd50215d2715c374252",
      "tree": "b3ffa04327884cd0491c3ee1677f0ffc589ebe9c",
      "parents": [
        "710b7216964d6455cf1b215c43b03a1a79008c7d"
      ],
      "author": {
        "name": "J. Bruce Fields",
        "email": "bfields@redhat.com",
        "time": "Tue Jul 26 18:25:49 2011 -0400"
      },
      "committer": {
        "name": "J. Bruce Fields",
        "email": "bfields@redhat.com",
        "time": "Fri Aug 19 13:25:34 2011 -0400"
      },
      "message": "locks: fix tracking of inprogress lease breaks\n\nWe currently use a bit in fl_flags to record whether a lease is being\nbroken, and set fl_type to the type (RDLCK or UNLCK) that it will\neventually have.  This means that once the lease break starts, we forget\nwhat the lease\u0027s type *used* to be.  Breaking a read lease will then\nresult in blocking read opens, even though there\u0027s no conflict--because\nthe lease type is now F_UNLCK and we can no longer tell whether it was\npreviously a read or write lease.\n\nSo, instead keep fl_type as the original type (the type which we\nenforce), and keep track of whether we\u0027re unlocking or merely\ndowngrading by replacing the single FL_INPROGRESS flag by\nFL_UNLOCK_PENDING and FL_DOWNGRADE_PENDING flags.\n\nTo get this right we also need to track separate downgrade and break\ntimes, to handle the case where a write-leased file gets conflicting\nopens first for read, then later for write.\n\n(I first considered just eliminating the downgrade behavior\ncompletely--nfsv4 doesn\u0027t need it, and nobody as far as I can tell\nactually uses it currently--but Jeremy Allison tells me that Windows\noplocks do behave this way, so Samba will probably use this some day.)\n\nReviewed-by: Jeff Layton \u003cjlayton@redhat.com\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@redhat.com\u003e\n"
    },
    {
      "commit": "710b7216964d6455cf1b215c43b03a1a79008c7d",
      "tree": "b0b356e3256ba52838a6373c4791721820d8fdaa",
      "parents": [
        "ab83fa4b49a54e6199b076b7d8c1808144e80f0d"
      ],
      "author": {
        "name": "J. Bruce Fields",
        "email": "bfields@redhat.com",
        "time": "Tue Jul 26 16:28:29 2011 -0400"
      },
      "committer": {
        "name": "J. Bruce Fields",
        "email": "bfields@redhat.com",
        "time": "Fri Aug 19 13:25:34 2011 -0400"
      },
      "message": "locks: move F_INPROGRESS from fl_type to fl_flags field\n\nF_INPROGRESS isn\u0027t exposed to userspace.  To me it makes more sense in\nfl_flags....\n\nReviewed-by: Jeff Layton \u003cjlayton@redhat.com\u003e\nSigned-off-by: J. Bruce Fields \u003cbfields@redhat.com\u003e\n"
    },
    {
      "commit": "3ddcd0569cd68f00f3beae9a7959b72918bb91f4",
      "tree": "3f7c591316560b1c22e2cc0700fbcd29aa3fbd7f",
      "parents": [
        "830c0f0edca67403d361fe976a25b17356c11f19"
      ],
      "author": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Sat Aug 06 22:45:50 2011 -0700"
      },
      "committer": {
        "name": "Linus Torvalds",
        "email": "torvalds@linux-foundation.org",
        "time": "Sat Aug 06 22:53:23 2011 -0700"
      },
      "message": "vfs: optimize inode cache access patterns\n\nThe inode structure layout is largely random, and some of the vfs paths\nreally do care.  The path lookup in particular is already quite D$\nintensive, and profiles show that accessing the \u0027inode-\u003ei_op-\u003exyz\u0027\nfields is quite costly.\n\nWe already optimized the dcache to not unnecessarily load the d_op\nstructure for members that are often NULL using the DCACHE_OP_xyz bits\nin dentry-\u003ed_flags, and this does something very similar for the inode\nops that are used during pathname lookup.\n\nIt also re-orders the fields so that the fields accessed by \u0027stat\u0027 are\ntogether at the beginning of the inode structure, and roughly in the\norder accessed.\n\nThe effect of this seems to be in the 1-2% range for an empty kernel\n\"make -j\" run (which is fairly kernel-intensive, mostly in filename\nlookup), so it\u0027s visible.  The numbers are fairly noisy, though, and\nlikely depend a lot on exact microarchitecture.  So there\u0027s more tuning\nto be done.\n\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n"
    }
  ],
  "next": "f2ee7abf4c40c8e6bffced923a7c01ea2d1f6c97"
}