)]}' { "log": [ { "commit": "4e60c86bd9e5a7110ed28874d0b6592186550ae8", "tree": "9fb60e9f49b44b293a0c0c7d9f40e1a354a22b5a", "parents": [ "627295e492638936e76f3d8fcb1e0a3367b88341" ], "author": { "name": "Andi Kleen", "email": "andi@firstfloor.org", "time": "Mon Aug 09 17:19:03 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Aug 09 20:44:58 2010 -0700" }, "message": "gcc-4.6: mm: fix unused but set warnings\n\nNo real bugs, just some dead code and some fixups.\n\nSigned-off-by: Andi Kleen \u003cak@linux.intel.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "003386fff3e02e51cea882e60f7d28290113964c", "tree": "253001a9a0fc609b757362708edc2dcaab9e2a14", "parents": [ "092405cdb66f060918160ae730640b449ed7b827", "51921cb746f56983db5a373ca68deb2b0d3ddf01" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sun May 30 09:16:14 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sun May 30 09:16:14 2010 -0700" }, "message": "Merge branch \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse\n\n* \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/fuse:\n mm: export generic_pipe_buf_*() to modules\n fuse: support splice() reading from fuse device\n fuse: allow splice to move pages\n mm: export remove_from_page_cache() to modules\n mm: export lru_cache_add_*() to modules\n fuse: support splice() writing to fuse device\n fuse: get page reference for readpages\n fuse: use get_user_pages_fast()\n fuse: remove unneeded variable\n" }, { "commit": "105a048a4f35f7a74c7cc20b36dd83658b6ec232", "tree": "043b1110cda0042ba35d8aae59382bb094d0af3f", "parents": [ "00b9b0af5887fed54e899e3b7f5c2ccf5e739def", "9aeead73782c4b8e2a91def36dbf95db28605c95" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu May 27 10:43:44 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu May 27 10:43:44 2010 -0700" }, "message": "Merge git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-unstable\n\n* git://git.kernel.org/pub/scm/linux/kernel/git/mason/btrfs-unstable: (27 commits)\n Btrfs: add more error checking to btrfs_dirty_inode\n Btrfs: allow unaligned DIO\n Btrfs: drop verbose enospc printk\n Btrfs: Fix block generation verification race\n Btrfs: fix preallocation and nodatacow checks in O_DIRECT\n Btrfs: avoid ENOSPC errors in btrfs_dirty_inode\n Btrfs: move O_DIRECT space reservation to btrfs_direct_IO\n Btrfs: rework O_DIRECT enospc handling\n Btrfs: use async helpers for DIO write checksumming\n Btrfs: don\u0027t walk around with task-\u003estate !\u003d TASK_RUNNING\n Btrfs: do aio_write instead of write\n Btrfs: add basic DIO read/write support\n direct-io: do not merge logically non-contiguous requests\n direct-io: add a hook for the fs to provide its own submit_bio function\n fs: allow short direct-io reads to be completed via buffered IO\n Btrfs: Metadata ENOSPC handling for balance\n Btrfs: Pre-allocate space for data relocation\n Btrfs: Metadata ENOSPC handling for tree log\n Btrfs: Metadata reservation for orphan inodes\n Btrfs: Introduce global metadata reservation\n ...\n" }, { "commit": "91803b499cca2fe558abad709ce83dc896b80950", "tree": "5665b06dcacf14c2e5e979ed1c7066633b259f80", "parents": [ "63a6440326e4cd01d6a663069208a0e68e9b833f" ], "author": { "name": "Jeff Moyer", "email": "jmoyer@redhat.com", "time": "Wed May 26 11:49:40 2010 -0400" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed May 26 10:20:27 2010 -0700" }, "message": "do_generic_file_read: clear page errors when issuing a fresh read of the page\n\nI/O errors can happen due to temporary failures, like multipath\nerrors or losing network contact with the iSCSI server. Because\nof that, the VM will retry readpage on the page.\n\nHowever, do_generic_file_read does not clear PG_error. This\ncauses the system to be unable to actually use the data in the\npage cache page, even if the subsequent readpage completes\nsuccessfully!\n\nThe function filemap_fault has had a ClearPageError before\nreadpage forever. This patch simply adds the same to\ndo_generic_file_read.\n\nSigned-off-by: Jeff Moyer \u003cjmoyer@redhat.com\u003e\nSigned-off-by: Rik van Riel \u003criel@redhat.com\u003e\nAcked-by: Larry Woodman \u003clwoodman@redhat.com\u003e\nCc: stable@kernel.org\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "c0ff7453bb5c7c98e0885fb94279f2571946f280", "tree": "8bb2b169a5145f0496575dbd2f48bb4b1c83f819", "parents": [ "708c1bbc9d0c3e57f40501794d9b0eed29d10fce" ], "author": { "name": "Miao Xie", "email": "miaox@cn.fujitsu.com", "time": "Mon May 24 14:32:08 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:06:57 2010 -0700" }, "message": "cpuset,mm: fix no node to alloc memory when changing cpuset\u0027s mems\n\nBefore applying this patch, cpuset updates task-\u003emems_allowed and\nmempolicy by setting all new bits in the nodemask first, and clearing all\nold unallowed bits later. But in the way, the allocator may find that\nthere is no node to alloc memory.\n\nThe reason is that cpuset rebinds the task\u0027s mempolicy, it cleans the\nnodes which the allocater can alloc pages on, for example:\n\n(mpol: mempolicy)\n\ttask1\t\t\ttask1\u0027s mpol\ttask2\n\talloc page\t\t1\n\t alloc on node0? NO\t1\n\t\t\t\t1\t\tchange mems from 1 to 0\n\t\t\t\t1\t\trebind task1\u0027s mpol\n\t\t\t\t0-1\t\t set new bits\n\t\t\t\t0\t \t clear disallowed bits\n\t alloc on node1? NO\t0\n\t ...\n\tcan\u0027t alloc page\n\t goto oom\n\nThis patch fixes this problem by expanding the nodes range first(set newly\nallowed bits) and shrink it lazily(clear newly disallowed bits). So we\nuse a variable to tell the write-side task that read-side task is reading\nnodemask, and the write-side task clears newly disallowed nodes after\nread-side task ends the current memory allocation.\n\n[akpm@linux-foundation.org: fix spello]\nSigned-off-by: Miao Xie \u003cmiaox@cn.fujitsu.com\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nCc: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: Paul Menage \u003cmenage@google.com\u003e\nCc: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nCc: Ravikiran Thirumalai \u003ckiran@scalex86.org\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: Andi Kleen \u003candi@firstfloor.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "e9d6c157385e4efa61cb8293e425c9d8beba70d3", "tree": "fca2452b46328c9005b8a4043a22b7b1b4d47d0c", "parents": [ "1f0a738868cbfe20ae53a00b7c302c04ef7ab8fc" ], "author": { "name": "KOSAKI Motohiro", "email": "kosaki.motohiro@jp.fujitsu.com", "time": "Mon May 24 14:31:48 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:06:56 2010 -0700" }, "message": "tmpfs: insert tmpfs cache pages to inactive list at first\n\nShaohua Li reported parallel file copy on tmpfs can lead to OOM killer.\nThis is regression of caused by commit 9ff473b9a7 (\"vmscan: evict\nstreaming IO first\"). Wow, It is 2 years old patch!\n\nCurrently, tmpfs file cache is inserted active list at first. This means\nthat the insertion doesn\u0027t only increase numbers of pages in anon LRU, but\nit also reduces anon scanning ratio. Therefore, vmscan will get totally\nconfused. It scans almost only file LRU even though the system has plenty\nunused tmpfs pages.\n\nHistorically, lru_cache_add_active_anon() was used for two reasons.\n1) Intend to priotize shmem page rather than regular file cache.\n2) Intend to avoid reclaim priority inversion of used once pages.\n\nBut we\u0027ve lost both motivation because (1) Now we have separate anon and\nfile LRU list. then, to insert active list doesn\u0027t help such priotize.\n(2) In past, one pte access bit will cause page activation. then to\ninsert inactive list with pte access bit mean higher priority than to\ninsert active list. Its priority inversion may lead to uninteded lru\nchun. but it was already solved by commit 645747462 (vmscan: detect\nmapped file pages used only once). (Thanks Hannes, you are great!)\n\nThus, now we can use lru_cache_add_anon() instead.\n\nSigned-off-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nReported-by: Shaohua Li \u003cshaohua.li@intel.com\u003e\nReviewed-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nReviewed-by: Johannes Weiner \u003channes@cmpxchg.org\u003e\nReviewed-by: Rik van Riel \u003criel@redhat.com\u003e\nReviewed-by: Minchan Kim \u003cminchan.kim@gmail.com\u003e\nAcked-by: Hugh Dickins \u003chughd@google.com\u003e\nCc: Henrique de Moraes Holschuh \u003chmh@hmh.eng.br\u003e\nCc: \u003cstable@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": "66f998f611897319b555364cefd5d6e88a205866", "tree": "3d2a46624bf6cf1ea1645cc8dad975af858dc114", "parents": [ "3fd0a5585eb98e074fb9934549c8d85c49756c0d" ], "author": { "name": "Josef Bacik", "email": "josef@redhat.com", "time": "Sun May 23 11:00:54 2010 -0400" }, "committer": { "name": "Chris Mason", "email": "chris.mason@oracle.com", "time": "Tue May 25 10:34:55 2010 -0400" }, "message": "fs: allow short direct-io reads to be completed via buffered IO\n\nThis is similar to what already happens in the write case. If we have a short\nread while doing O_DIRECT, instead of just returning, fallthrough and try to\nread the rest via buffered IO. BTRFS needs this because if we encounter a\ncompressed or inline extent during DIO, we need to fallback on buffered. If the\nextent is compressed we need to read the entire thing into memory and\nde-compress it into the users pages. I have tested this with fsx and everything\nworks great. Thanks,\n\nSigned-off-by: Josef Bacik \u003cjosef@redhat.com\u003e\nSigned-off-by: Chris Mason \u003cchris.mason@oracle.com\u003e\n" }, { "commit": "a52116aba5b3eed0ee41f70b794cc1937acd5cb8", "tree": "cedff5545f4cac8c2fd56fc0bd7a5e536cc677fd", "parents": [ "47846b0650f2f62fc4217cfb36efc94b8d919727" ], "author": { "name": "Miklos Szeredi", "email": "mszeredi@suse.cz", "time": "Tue May 25 15:06:06 2010 +0200" }, "committer": { "name": "Miklos Szeredi", "email": "mszeredi@suse.cz", "time": "Tue May 25 15:06:06 2010 +0200" }, "message": "mm: export remove_from_page_cache() to modules\n\nThis is needed to enable moving pages into the page cache in fuse with\nsplice(..., SPLICE_F_MOVE).\n\nSigned-off-by: Miklos Szeredi \u003cmszeredi@suse.cz\u003e\n" }, { "commit": "5a0e3ad6af8660be21ca98a971cd00f331318c05", "tree": "5bfb7be11a03176a87296a43ac6647975c00a1d1", "parents": [ "ed391f4ebf8f701d3566423ce8f17e614cde9806" ], "author": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Wed Mar 24 17:04:11 2010 +0900" }, "committer": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Tue Mar 30 22:02:32 2010 +0900" }, "message": "include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h\n\npercpu.h is included by sched.h and module.h and thus ends up being\nincluded when building most .c files. percpu.h includes slab.h which\nin turn includes gfp.h making everything defined by the two files\nuniversally available and complicating inclusion dependencies.\n\npercpu.h -\u003e slab.h dependency is about to be removed. Prepare for\nthis change by updating users of gfp and slab facilities include those\nheaders directly instead of assuming availability. As this conversion\nneeds to touch large number of source files, the following script is\nused as the basis of conversion.\n\n http://userweb.kernel.org/~tj/misc/slabh-sweep.py\n\nThe script does the followings.\n\n* Scan files for gfp and slab usages and update includes such that\n only the necessary includes are there. ie. if only gfp is used,\n gfp.h, if slab is used, slab.h.\n\n* When the script inserts a new include, it looks at the include\n blocks and try to put the new include such that its order conforms\n to its surrounding. It\u0027s put in the include block which contains\n core kernel includes, in the same order that the rest are ordered -\n alphabetical, Christmas tree, rev-Xmas-tree or at the end if there\n doesn\u0027t seem to be any matching order.\n\n* If the script can\u0027t find a place to put a new include (mostly\n because the file doesn\u0027t have fitting include block), it prints out\n an error message indicating which .h file needs to be added to the\n file.\n\nThe conversion was done in the following steps.\n\n1. The initial automatic conversion of all .c files updated slightly\n over 4000 files, deleting around 700 includes and adding ~480 gfp.h\n and ~3000 slab.h inclusions. The script emitted errors for ~400\n files.\n\n2. Each error was manually checked. Some didn\u0027t need the inclusion,\n some needed manual addition while adding it to implementation .h or\n embedding .c file was more appropriate for others. This step added\n inclusions to around 150 files.\n\n3. The script was run again and the output was compared to the edits\n from #2 to make sure no file was left behind.\n\n4. Several build tests were done and a couple of problems were fixed.\n e.g. lib/decompress_*.c used malloc/free() wrappers around slab\n APIs requiring slab.h to be added manually.\n\n5. The script was run on all .h files but without automatically\n editing them as sprinkling gfp.h and slab.h inclusions around .h\n files could easily lead to inclusion dependency hell. Most gfp.h\n inclusion directives were ignored as stuff from gfp.h was usually\n wildly available and often used in preprocessor macros. Each\n slab.h inclusion directive was examined and added manually as\n necessary.\n\n6. percpu.h was updated not to include slab.h.\n\n7. Build test were done on the following configurations and failures\n were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my\n distributed build env didn\u0027t work with gcov compiles) and a few\n more options had to be turned off depending on archs to make things\n build (like ipr on powerpc/64 which failed due to missing writeq).\n\n * x86 and x86_64 UP and SMP allmodconfig and a custom test config.\n * powerpc and powerpc64 SMP allmodconfig\n * sparc and sparc64 SMP allmodconfig\n * ia64 SMP allmodconfig\n * s390 SMP allmodconfig\n * alpha SMP allmodconfig\n * um on x86_64 SMP allmodconfig\n\n8. percpu.h modifications were reverted so that it could be applied as\n a separate patch and serve as bisection point.\n\nGiven the fact that I had only a couple of failures from tests on step\n6, I\u0027m fairly confident about the coverage of this conversion patch.\nIf there is a breakage, it\u0027s likely to be something in one of the arch\nheaders which should be easily discoverable easily on most builds of\nthe specific arch.\n\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\nGuess-its-ok-by: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: Ingo Molnar \u003cmingo@redhat.com\u003e\nCc: Lee Schermerhorn \u003cLee.Schermerhorn@hp.com\u003e\n" }, { "commit": "59e99e5b9706867f18d4a36c1e4645fbaacbec2e", "tree": "e977fb5eecccf1446296fd196072bd1287b0a92f", "parents": [ "06f9d8c2b50060543fb6e0af87ddb86e654dee6b" ], "author": { "name": "Jiri Slaby", "email": "jslaby@suse.cz", "time": "Fri Mar 05 13:41:44 2010 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sat Mar 06 11:26:24 2010 -0800" }, "message": "mm: use rlimit helpers\n\nMake sure compiler won\u0027t do weird things with limits. E.g. fetching them\ntwice may return 2 different values after writable limits are implemented.\n\nI.e. either use rlimit helpers added in\n3e10e716abf3c71bdb5d86b8f507f9e72236c9cd (\"resource: add helpers for\nfetching rlimits\") or ACCESS_ONCE if not applicable.\n\nSigned-off-by: Jiri Slaby \u003cjslaby@suse.cz\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "2ecdc82ef0b03e67ce5ecee79d0d108177a704df", "tree": "66887e3e0e7328c4030888905a713a995bb1654b", "parents": [ "270ba5f7c5dac0bfb564aa35a536fb31ad4075bd" ], "author": { "name": "Christoph Hellwig", "email": "hch@lst.de", "time": "Tue Jan 26 17:27:20 2010 +0100" }, "committer": { "name": "Al Viro", "email": "viro@zeniv.linux.org.uk", "time": "Wed Mar 03 14:07:55 2010 -0500" }, "message": "kill unused invalidate_inode_pages helper\n\nNo one is calling this anymore as everyone has switched to\ninvalidate_mapping_pages long time ago. Also update a few\nreferences to it in comments. nfs has two more, but I can\u0027t\neasily figure what they are actually referring to, so I left\nthem as-is.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n" }, { "commit": "931e80e4b3263db75c8e34f078d22f11bbabd3a3", "tree": "47c735f039d2c8623a1fc4d20333a9899ac8e99c", "parents": [ "bc173f7092c76a7967f135c2b3a54052ad99733b" ], "author": { "name": "anfei zhou", "email": "anfei.zhou@gmail.com", "time": "Tue Feb 02 13:44:02 2010 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Feb 02 18:11:21 2010 -0800" }, "message": "mm: flush dcache before writing into page to avoid alias\n\nThe cache alias problem will happen if the changes of user shared mapping\nis not flushed before copying, then user and kernel mapping may be mapped\ninto two different cache line, it is impossible to guarantee the coherence\nafter iov_iter_copy_from_user_atomic. So the right steps should be:\n\n\tflush_dcache_page(page);\n\tkmap_atomic(page);\n\twrite to page;\n\tkunmap_atomic(page);\n\tflush_dcache_page(page);\n\nMore precisely, we might create two new APIs flush_dcache_user_page and\nflush_dcache_kern_page to replace the two flush_dcache_page accordingly.\n\nHere is a snippet tested on omap2430 with VIPT cache, and I think it is\nnot ARM-specific:\n\n\tint val \u003d 0x11111111;\n\tfd \u003d open(\"abc\", O_RDWR);\n\taddr \u003d mmap(NULL, 4096, PROT_READ|PROT_WRITE, MAP_SHARED, fd, 0);\n\t*(addr+0) \u003d 0x44444444;\n\ttmp \u003d *(addr+0);\n\t*(addr+1) \u003d 0x77777777;\n\twrite(fd, \u0026val, sizeof(int));\n\tclose(fd);\n\nThe results are not always 0x11111111 0x77777777 at the beginning as expected. Sometimes we see 0x44444444 0x77777777.\n\nSigned-off-by: Anfei \u003canfei.zhou@gmail.com\u003e\nCc: Russell King \u003crmk@arm.linux.org.uk\u003e\nCc: Miklos Szeredi \u003cmiklos@szeredi.hu\u003e\nCc: Nick Piggin \u003cnickpiggin@yahoo.com.au\u003e\nCc: \u003clinux-arch@vger.kernel.org\u003e\nCc: \u003cstable@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": "0531b2aac59c2296570ac52bfc032ef2ace7d5e1", "tree": "4ca454bdc03c24654529bab9c882c1cd5f99a88c", "parents": [ "caf0801e0cc482497c14a9ce349469c33c60beec" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jan 27 09:20:03 2010 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jan 27 09:20:03 2010 -0800" }, "message": "mm: add new \u0027read_cache_page_gfp()\u0027 helper function\n\nIt\u0027s a simplified \u0027read_cache_page()\u0027 which takes a page allocation\nflag, so that different paths can control how aggressive the memory\nallocations are that populate a address space.\n\nIn particular, the intel GPU object mapping code wants to be able to do\na certain amount of own internal memory management by automatically\nshrinking the address space when memory starts getting tight. This\nallows it to dynamically use different memory allocation policies on a\nper-allocation basis, rather than depend on the (static) address space\ngfp policy.\n\nThe actual new function is a one-liner, but re-organizing the helper\nfunctions to the point where you can do this with a single line of code\nis what most of the patch is all about.\n\nTested-by: Chris Wilson \u003cchris@chris-wilson.co.uk\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "c05c4edd876b7ae92787d1295868afcb89b6a348", "tree": "8dc4ce17c0a9be223a70e99d246035fee0a7168e", "parents": [ "2cfd30adf6130dab3fbb130eb5f7b1fd42a70e31" ], "author": { "name": "Christoph Hellwig", "email": "hch@lst.de", "time": "Wed Sep 23 15:07:30 2009 +0200" }, "committer": { "name": "Al Viro", "email": "viro@zeniv.linux.org.uk", "time": "Wed Dec 16 12:16:50 2009 -0500" }, "message": "direct I/O fallback sync simplification\n\nIn the case of direct I/O falling back to buffered I/O we sync data\ntwice currently: once at the end of generic_file_buffered_write using\nfilemap_write_and_wait_range and once a little later in\n__generic_file_aio_write using do_sync_mapping_range with all flags set.\n\nThe wait before write of the do_sync_mapping_range call does not make\nany sense, so just keep the filemap_write_and_wait_range call and move\nit to the right spot.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n" }, { "commit": "94004ed726f38a841cc51f97c4a3f9eda9fbd0d9", "tree": "786689e9fc9e686a5b54c1a1b1efcbb7d043b5ab", "parents": [ "6b2f3d1f769be5779b479c37800229d9a4809fc3" ], "author": { "name": "Christoph Hellwig", "email": "hch@lst.de", "time": "Wed Sep 30 22:16:33 2009 +0200" }, "committer": { "name": "Jan Kara", "email": "jack@suse.cz", "time": "Thu Dec 10 15:02:50 2009 +0100" }, "message": "kill wait_on_page_writeback_range\n\nAll callers really want the more logical filemap_fdatawait_range interface,\nso convert them to use it and merge wait_on_page_writeback_range into\nfilemap_fdatawait_range.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Jan Kara \u003cjack@suse.cz\u003e\n" }, { "commit": "af901ca181d92aac3a7dc265144a9081a86d8f39", "tree": "380054af22521144fbe1364c3bcd55ad24c9bde4", "parents": [ "972b94ffb90ea6d20c589d9a47215df103388ddd" ], "author": { "name": "André Goddard Rosa", "email": "andre.goddard@gmail.com", "time": "Sat Nov 14 13:09:05 2009 -0200" }, "committer": { "name": "Jiri Kosina", "email": "jkosina@suse.cz", "time": "Fri Dec 04 15:39:55 2009 +0100" }, "message": "tree-wide: fix assorted typos all over the place\n\nThat is \"success\", \"unknown\", \"through\", \"performance\", \"[re|un]mapping\"\n, \"access\", \"default\", \"reasonable\", \"[con]currently\", \"temperature\"\n, \"channel\", \"[un]used\", \"application\", \"example\",\"hierarchy\", \"therefore\"\n, \"[over|under]flow\", \"contiguous\", \"threshold\", \"enough\" and others.\n\nSigned-off-by: André Goddard Rosa \u003candre.goddard@gmail.com\u003e\nSigned-off-by: Jiri Kosina \u003cjkosina@suse.cz\u003e\n" }, { "commit": "f0f37e2f77731b3473fa6bd5ee53255d9a9cdb40", "tree": "3c26d3ed1a453156e9c208ccb5567a8954dba064", "parents": [ "6f5071020d5ec89b5d095aa488db604adb921aec" ], "author": { "name": "Alexey Dobriyan", "email": "adobriyan@gmail.com", "time": "Sun Sep 27 22:29:37 2009 +0400" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sun Sep 27 11:39:25 2009 -0700" }, "message": "const: mark struct vm_struct_operations\n\n* mark struct vm_area_struct::vm_ops as const\n* mark vm_ops in AGP code\n\nBut leave TTM code alone, something is fishy there with global vm_ops\nbeing used.\n\nSigned-off-by: Alexey Dobriyan \u003cadobriyan@gmail.com\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "6c5daf012c9155aafd2c7973e4278766c30dfad0", "tree": "33959d7b36d03e1610615641a2940cb2de5e8603", "parents": [ "6d39b27f0ac7e805ae3bd9efa51d7da04bec0360", "c08d3b0e33edce28e9cfa7b64f7fe5bdeeb29248" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Sep 24 08:32:11 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Sep 24 08:32:11 2009 -0700" }, "message": "Merge branch \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6\n\n* \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6:\n truncate: use new helpers\n truncate: new helpers\n fs: fix overflow in sys_mount() for in-kernel calls\n fs: Make unload_nls() NULL pointer safe\n freeze_bdev: grab active reference to frozen superblocks\n freeze_bdev: kill bd_mount_sem\n exofs: remove BKL from super operations\n fs/romfs: correct error-handling code\n vfs: seq_file: add helpers for data filling\n vfs: remove redundant position check in do_sendfile\n vfs: change sb-\u003es_maxbytes to a loff_t\n vfs: explicitly cast s_maxbytes in fiemap_check_ranges\n libfs: return error code on failed attr set\n seq_file: return a negative error code when seq_path_root() fails.\n vfs: optimize touch_time() too\n vfs: optimization for touch_atime()\n vfs: split generic_forget_inode() so that hugetlbfs does not have to copy it\n fs/inode.c: add dev-id and inode number for debugging in init_special_inode()\n libfs: make simple_read_from_buffer conventional\n" }, { "commit": "db16826367fefcb0ddb93d76b66adc52eb4e6339", "tree": "626224c1eb1eb79c522714591f208b4fdbdcd9d4", "parents": [ "cd6045138ed1bb5d8773e940d51c34318eef3ef2", "465fdd97cbe16ef8727221857e96ef62dd352017" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Sep 24 07:53:22 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Sep 24 07:53:22 2009 -0700" }, "message": "Merge branch \u0027hwpoison\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/ak/linux-mce-2.6\n\n* \u0027hwpoison\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/ak/linux-mce-2.6: (21 commits)\n HWPOISON: Enable error_remove_page on btrfs\n HWPOISON: Add simple debugfs interface to inject hwpoison on arbitary PFNs\n HWPOISON: Add madvise() based injector for hardware poisoned pages v4\n HWPOISON: Enable error_remove_page for NFS\n HWPOISON: Enable .remove_error_page for migration aware file systems\n HWPOISON: The high level memory error handler in the VM v7\n HWPOISON: Add PR_MCE_KILL prctl to control early kill behaviour per process\n HWPOISON: shmem: call set_page_dirty() with locked page\n HWPOISON: Define a new error_remove_page address space op for async truncation\n HWPOISON: Add invalidate_inode_page\n HWPOISON: Refactor truncate to allow direct truncating of page v2\n HWPOISON: check and isolate corrupted free pages v2\n HWPOISON: Handle hardware poisoned pages in try_to_unmap\n HWPOISON: Use bitmask/action code for try_to_unmap behaviour\n HWPOISON: x86: Add VM_FAULT_HWPOISON handling to x86 page fault handler v2\n HWPOISON: Add poison check to page fault handling\n HWPOISON: Add basic support for poisoned pages in fault handler v3\n HWPOISON: Add new SIGBUS error codes for hardware poison signals\n HWPOISON: Add support for poison swap entries v2\n HWPOISON: Export some rmap vma locking to outside world\n ...\n" }, { "commit": "25d9e2d15286281ec834b829a4aaf8969011f1cd", "tree": "e4329a481ca197afae30f04335e023c7d04f7d67", "parents": [ "eca6f534e61919b28fb21aafbd1c2983deae75be" ], "author": { "name": "npiggin@suse.de", "email": "npiggin@suse.de", "time": "Fri Aug 21 02:35:05 2009 +1000" }, "committer": { "name": "al", "email": "al@dizzy.pdmi.ras.ru", "time": "Thu Sep 24 08:41:47 2009 -0400" }, "message": "truncate: new helpers\n\nIntroduce new truncate helpers truncate_pagecache and inode_newsize_ok.\nvmtruncate is also consolidated from mm/memory.c and mm/nommu.c and\ninto mm/truncate.c.\n\nReviewed-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n" }, { "commit": "4b02108ac1b3354a22b0d83c684797692efdc395", "tree": "9f65d6e8e35ddce940e7b9da6305cf5a19e5904e", "parents": [ "c6a7f5728a1db45d30df55a01adc130b4ab0327c" ], "author": { "name": "KOSAKI Motohiro", "email": "kosaki.motohiro@jp.fujitsu.com", "time": "Mon Sep 21 17:01:33 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Sep 22 07:17:27 2009 -0700" }, "message": "mm: oom analysis: add shmem vmstat\n\nRecently we encountered OOM problems due to memory use of the GEM cache.\nGenerally a large amuont of Shmem/Tmpfs pages tend to create a memory\nshortage problem.\n\nWe often use the following calculation to determine the amount of shmem\npages:\n\nshmem \u003d NR_ACTIVE_ANON + NR_INACTIVE_ANON - NR_ANON_PAGES\n\nhowever the expression does not consider isolated and mlocked pages.\n\nThis patch adds explicit accounting for pages used by shmem and tmpfs.\n\nSigned-off-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nAcked-by: Rik van Riel \u003criel@redhat.com\u003e\nReviewed-by: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nAcked-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nCc: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "6a46079cf57a7f7758e8b926980a4f852f89b34d", "tree": "efd72e830201370d6273bd436dda5a3c4cd6ed9b", "parents": [ "4db96cf077aa938b11fe7ac79ecc9b29ec00fbab" ], "author": { "name": "Andi Kleen", "email": "andi@firstfloor.org", "time": "Wed Sep 16 11:50:15 2009 +0200" }, "committer": { "name": "Andi Kleen", "email": "ak@linux.intel.com", "time": "Wed Sep 16 11:50:15 2009 +0200" }, "message": "HWPOISON: The high level memory error handler in the VM v7\n\nAdd the high level memory handler that poisons pages\nthat got corrupted by hardware (typically by a two bit flip in a DIMM\nor a cache) on the Linux level. The goal is to prevent everyone\nfrom accessing these pages in the future.\n\nThis done at the VM level by marking a page hwpoisoned\nand doing the appropriate action based on the type of page\nit is.\n\nThe code that does this is portable and lives in mm/memory-failure.c\n\nTo quote the overview comment:\n\nHigh level machine check handler. Handles pages reported by the\nhardware as being corrupted usually due to a 2bit ECC memory or cache\nfailure.\n\nThis focuses on pages detected as corrupted in the background.\nWhen the current CPU tries to consume corruption the currently\nrunning process can just be killed directly instead. This implies\nthat if the error cannot be handled for some reason it\u0027s safe to\njust ignore it because no corruption has been consumed yet. Instead\nwhen that happens another machine check will happen.\n\nHandles page cache pages in various states. The tricky part\nhere is that we can access any page asynchronous to other VM\nusers, because memory failures could happen anytime and anywhere,\npossibly violating some of their assumptions. This is why this code\nhas to be extremely careful. Generally it tries to use normal locking\nrules, as in get the standard locks, even if that means the\nerror handling takes potentially a long time.\n\nSome of the operations here are somewhat inefficient and have non\nlinear algorithmic complexity, because the data structures have not\nbeen optimized for this case. This is in particular the case\nfor the mapping from a vma to a process. Since this case is expected\nto be rare we hope we can get away with this.\n\nThere are in principle two strategies to kill processes on poison:\n- just unmap the data and wait for an actual reference before\nkilling\n- kill as soon as corruption is detected.\nBoth have advantages and disadvantages and should be used\nin different situations. Right now both are implemented and can\nbe switched with a new sysctl vm.memory_failure_early_kill\nThe default is early kill.\n\nThe patch does some rmap data structure walking on its own to collect\nprocesses to kill. This is unusual because normally all rmap data structure\nknowledge is in rmap.c only. I put it here for now to keep\neverything together and rmap knowledge has been seeping out anyways\n\nIncludes contributions from Johannes Weiner, Chris Mason, Fengguang Wu,\nNick Piggin (who did a lot of great work) and others.\n\nCc: npiggin@suse.de\nCc: riel@redhat.com\nSigned-off-by: Andi Kleen \u003cak@linux.intel.com\u003e\nAcked-by: Rik van Riel \u003criel@redhat.com\u003e\nReviewed-by: Hidehiro Kawai \u003chidehiro.kawai.ez@hitachi.com\u003e\n" }, { "commit": "18f2ee705d98034b0f229a3202d827468d4bffd9", "tree": "1da282e5eb90dc8e8a1e46214e0e7639138d3568", "parents": [ "2f3d675bcd4a84251d6e8eea8096ec8fc795e5d6" ], "author": { "name": "Jan Kara", "email": "jack@suse.cz", "time": "Tue Aug 18 18:43:15 2009 +0200" }, "committer": { "name": "Jan Kara", "email": "jack@suse.cz", "time": "Mon Sep 14 17:08:17 2009 +0200" }, "message": "vfs: Remove generic_osync_inode() and sync_page_range{_nolock}()\n\nRemove these three functions since nobody uses them anymore.\n\nSigned-off-by: Jan Kara \u003cjack@suse.cz\u003e\n" }, { "commit": "148f948ba877f4d3cdef036b1ff6d9f68986706a", "tree": "c07963f08bf8c2119ec00df64e4293e2e60acaa1", "parents": [ "eef99380679e20e7edc096aa4d8a98b875404d79" ], "author": { "name": "Jan Kara", "email": "jack@suse.cz", "time": "Mon Aug 17 19:52:36 2009 +0200" }, "committer": { "name": "Jan Kara", "email": "jack@suse.cz", "time": "Mon Sep 14 17:08:15 2009 +0200" }, "message": "vfs: Introduce new helpers for syncing after writing to O_SYNC file or IS_SYNC inode\n\nIntroduce new function for generic inode syncing (vfs_fsync_range) and use\nit from fsync() path. Introduce also new helper for syncing after a sync\nwrite (generic_write_sync) using the generic function.\n\nUse these new helpers for syncing from generic VFS functions. This makes\nO_SYNC writes to block devices acquire i_mutex for syncing. If we really\ncare about this, we can make block_fsync() drop the i_mutex and reacquire\nit before it returns.\n\nCC: Evgeniy Polyakov \u003czbr@ioremap.net\u003e\nCC: ocfs2-devel@oss.oracle.com\nCC: Joel Becker \u003cjoel.becker@oracle.com\u003e\nCC: Felix Blyakher \u003cfelixb@sgi.com\u003e\nCC: xfs@oss.sgi.com\nCC: Anton Altaparmakov \u003caia21@cantab.net\u003e\nCC: linux-ntfs-dev@lists.sourceforge.net\nCC: OGAWA Hirofumi \u003chirofumi@mail.parknet.co.jp\u003e\nCC: linux-ext4@vger.kernel.org\nCC: tytso@mit.edu\nAcked-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Jan Kara \u003cjack@suse.cz\u003e\n" }, { "commit": "eef99380679e20e7edc096aa4d8a98b875404d79", "tree": "358a39148e8513eed9ba6aaff13f6bf660a2ce1e", "parents": [ "918941a3f3d46c2a69971b4718aaf13b1be2f1a7" ], "author": { "name": "Christoph Hellwig", "email": "hch@lst.de", "time": "Thu Aug 20 17:43:41 2009 +0200" }, "committer": { "name": "Jan Kara", "email": "jack@suse.cz", "time": "Mon Sep 14 17:08:15 2009 +0200" }, "message": "vfs: Rename generic_file_aio_write_nolock\n\ngeneric_file_aio_write_nolock() is now used only by block devices and raw\ncharacter device. Filesystems should use __generic_file_aio_write() in case\ngeneric_file_aio_write() doesn\u0027t suit them. So rename the function to\nblkdev_aio_write() and move it to fs/blockdev.c.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Jan Kara \u003cjack@suse.cz\u003e\n" }, { "commit": "c7b50db21fe8c295092518e224d60b95e69da3b0", "tree": "ed73757b475462c4cfccdcf61d95929f4cb32637", "parents": [ "e4dd9de3c66bc7e26c5c7f149a060c5a67cf06a0" ], "author": { "name": "Jan Kara", "email": "jack@suse.cz", "time": "Tue Aug 18 16:18:20 2009 +0200" }, "committer": { "name": "Jan Kara", "email": "jack@suse.cz", "time": "Mon Sep 14 17:08:15 2009 +0200" }, "message": "vfs: Remove syncing from generic_file_direct_write() and generic_file_buffered_write()\n\ngeneric_file_direct_write() and generic_file_buffered_write() called\ngeneric_osync_inode() if it was called on O_SYNC file or IS_SYNC inode. But\nthis is superfluous since generic_file_aio_write() does the syncing as well.\nAlso XFS and OCFS2 which call these functions directly handle syncing\nthemselves. So let\u0027s have a single place where syncing happens:\ngeneric_file_aio_write().\n\nWe slightly change the behavior by syncing only the range of file to which the\nwrite happened for buffered writes but that should be all that is required.\n\nCC: ocfs2-devel@oss.oracle.com\nCC: Joel Becker \u003cjoel.becker@oracle.com\u003e\nCC: Felix Blyakher \u003cfelixb@sgi.com\u003e\nCC: xfs@oss.sgi.com\nSigned-off-by: Jan Kara \u003cjack@suse.cz\u003e\n" }, { "commit": "e4dd9de3c66bc7e26c5c7f149a060c5a67cf06a0", "tree": "3270180b085c86afe4834fba5567464cd3932eb8", "parents": [ "d3bccb6f4b886060aa0f58976b92b77d951f5434" ], "author": { "name": "Jan Kara", "email": "jack@suse.cz", "time": "Mon Aug 17 18:10:06 2009 +0200" }, "committer": { "name": "Jan Kara", "email": "jack@suse.cz", "time": "Mon Sep 14 17:08:14 2009 +0200" }, "message": "vfs: Export __generic_file_aio_write() and add some comments\n\nRename __generic_file_aio_write_nolock() to __generic_file_aio_write(), add\ncomments to write helpers explaining how they should be used and export\n__generic_file_aio_write() since it will be used by some filesystems.\n\nCC: ocfs2-devel@oss.oracle.com\nCC: Joel Becker \u003cjoel.becker@oracle.com\u003e\nAcked-by: Evgeniy Polyakov \u003czbr@ioremap.net\u003e\nReviewed-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Jan Kara \u003cjack@suse.cz\u003e\n" }, { "commit": "d3bccb6f4b886060aa0f58976b92b77d951f5434", "tree": "b5f9eb43890da173a078e883d51c23b8c27ceaa6", "parents": [ "86d710146fb9975f04c505ec78caa43d227c1018" ], "author": { "name": "Jan Kara", "email": "jack@suse.cz", "time": "Mon Aug 17 19:30:27 2009 +0200" }, "committer": { "name": "Jan Kara", "email": "jack@suse.cz", "time": "Mon Sep 14 17:08:14 2009 +0200" }, "message": "vfs: Introduce filemap_fdatawait_range\n\nThis simple helper saves some filesystems conversion from byte offset\nto page numbers and also makes the fdata* interface more complete.\n\nReviewed-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Jan Kara \u003cjack@suse.cz\u003e\n" }, { "commit": "c8236db9cd7aa492dcfcdcca702638e704abed49", "tree": "75eb83051298fd1f9df426cafaaa6d3c422d1b68", "parents": [ "a65e7bfcd74e4c0939f235d2bf9f48ddb3a57991" ], "author": { "name": "Josef Bacik", "email": "josef@redhat.com", "time": "Sun Jul 05 12:08:18 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Jul 06 13:57:03 2009 -0700" }, "message": "mm: mark page accessed before we write_end()\n\nIn testing a backport of the write_begin/write_end AOPs, a 10% re-read\nregression was noticed when running iozone. This regression was\nintroduced because the old AOPs would always do a mark_page_accessed(page)\nafter the commit_write, but when the new AOPs where introduced, the only\nplace this was kept was in pagecache_write_end().\n\nThis patch does the same thing in the generic case as what is done in\npagecache_write_end(), which is just to mark the page accessed before we\ndo write_end().\n\nSigned-off-by: Josef Bacik \u003cjbacik@redhat.com\u003e\nAcked-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "6484eb3e2a81807722c5f28efef94d8338b7b996", "tree": "10ce36f412c2ff0c7eb399af1a189f8e354f56db", "parents": [ "b3c466ce512923298ae8c0121d3e9f397a3f1210" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Tue Jun 16 15:31:54 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Jun 16 19:47:32 2009 -0700" }, "message": "page allocator: do not check NUMA node ID when the caller knows the node is valid\n\nCallers of alloc_pages_node() can optionally specify -1 as a node to mean\n\"allocate from the current node\". However, a number of the callers in\nfast paths know for a fact their node is valid. To avoid a comparison and\nbranch, this patch adds alloc_pages_exact_node() that only checks the nid\nwith VM_BUG_ON(). Callers that know their node is valid are then\nconverted.\n\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nReviewed-by: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nReviewed-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nReviewed-by: Pekka Enberg \u003cpenberg@cs.helsinki.fi\u003e\nAcked-by: Paul Mundt \u003clethal@linux-sh.org\u003e\t[for the SLOB NUMA bits]\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Nick Piggin \u003cnickpiggin@yahoo.com.au\u003e\nCc: Dave Hansen \u003cdave@linux.vnet.ibm.com\u003e\nCc: Lee Schermerhorn \u003cLee.Schermerhorn@hp.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "7ffc59b4d0bdfa00e882339f85b8a969bb7021e2", "tree": "6b6d96208f08bc394c8e64efed6767b9a95e7a6d", "parents": [ "61b7cbdba2f3c588a0cf3db574c562805454b09b" ], "author": { "name": "Wu Fengguang", "email": "fengguang.wu@intel.com", "time": "Tue Jun 16 15:31:38 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Jun 16 19:47:30 2009 -0700" }, "message": "readahead: enforce full sync mmap readahead size\n\nNow that we do readahead for sequential mmap reads, here is a simple\nevaluation of the impacts, and one further optimization.\n\nIt\u0027s an NFS-root debian desktop system, readahead size \u003d 60 pages.\nThe numbers are grabbed after a fresh boot into console.\n\napproach pgmajfault RA miss ratio mmap IO count avg IO size(pages)\n A 383 31.6% 383 11\n B 225 32.4% 390 11\n C 224 32.6% 307 13\n\ncase A: mmap sync/async readahead disabled\ncase B: mmap sync/async readahead enabled, with enforced full async readahead size\ncase C: mmap sync/async readahead enabled, with enforced full sync/async readahead size\nor:\nA \u003d vanilla 2.6.30-rc1\nB \u003d A plus mmap readahead\nC \u003d B plus this patch\n\nThe numbers show that\n- there are good possibilities for random mmap reads to trigger readahead\n- \u0027pgmajfault\u0027 is reduced by 1/3, due to the _async_ nature of readahead\n- case C can further reduce IO count by 1/4\n- readahead miss ratios are not quite affected\n\nThe theory is\n- readahead is _good_ for clustered random reads, and can perform\n _better_ than readaround because they could be _async_.\n- async readahead size is guaranteed to be larger than readaround\n size, and they are _async_, hence will mostly behave better\nHowever for B\n- sync readahead size could be smaller than readaround size, hence may\n make things worse by produce more smaller IOs\nwhich will be fixed by this patch.\n\nFinal conclusion:\n- mmap readahead reduced major faults by 1/3 and no obvious overheads;\n- mmap io can be further reduced by 1/4 with this patch.\n\nSigned-off-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "61b7cbdba2f3c588a0cf3db574c562805454b09b", "tree": "657756b1ab5dc5fd63b341d999d492b868f4309c", "parents": [ "10be0b372cac50e2e7a477852f98bf069a97a3fa" ], "author": { "name": "Wu Fengguang", "email": "fengguang.wu@intel.com", "time": "Tue Jun 16 15:31:36 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Jun 16 19:47:30 2009 -0700" }, "message": "readahead: remove redundant test in shrink_readahead_size_eio()\n\nSigned-off-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "d30a11004e3411909f2448546f036a011978062e", "tree": "c1980adb410d9fabd2c2eb8af9f0ed8ee4b656da", "parents": [ "2fad6f5deee5556f511eab58da78737a23ddb35d" ], "author": { "name": "Wu Fengguang", "email": "fengguang.wu@intel.com", "time": "Tue Jun 16 15:31:30 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Jun 16 19:47:29 2009 -0700" }, "message": "readahead: record mmap read-around states in file_ra_state\n\nMmap read-around now shares the same code style and data structure with\nreadahead code.\n\nThis also removes do_page_cache_readahead(). Its last user, mmap\nread-around, has been changed to call ra_submit().\n\nThe no-readahead-if-congested logic is dumped by the way. Users will be\npretty sensitive about the slow loading of executables. So it\u0027s\nunfavorable to disabled mmap read-around on a congested queue.\n\n[akpm@linux-foundation.org: coding-style fixes]\nCc: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Fengguang Wu \u003cwfg@mail.ustc.edu.cn\u003e\nCc: Ying Han \u003cyinghan@google.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "2fad6f5deee5556f511eab58da78737a23ddb35d", "tree": "eca8262062c4fda63cb3bd34f9478f3fbfd7f518", "parents": [ "70ac23cfa31f68289d4b720c6162b3929ab4de36" ], "author": { "name": "Wu Fengguang", "email": "fengguang.wu@intel.com", "time": "Tue Jun 16 15:31:29 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Jun 16 19:47:29 2009 -0700" }, "message": "readahead: enforce full readahead size on async mmap readahead\n\nWe need this in one particular case and two more general ones.\n\nNow we do async readahead for sequential mmap reads, and do it with the\nhelp of PG_readahead. For normal reads, PG_readahead is the sufficient\ncondition to do a sequential readahead. But unfortunately, for mmap\nreads, there is a tiny nuisance:\n\n[11736.998347] readahead-init0(process: sh/23926, file: sda1/w3m, offset\u003d0:4503599627370495, ra\u003d0+4-3) \u003d 4\n[11737.014985] readahead-around(process: w3m/23926, file: sda1/w3m, offset\u003d0:0, ra\u003d290+32-0) \u003d 17\n[11737.019488] readahead-around(process: w3m/23926, file: sda1/w3m, offset\u003d0:0, ra\u003d118+32-0) \u003d 32\n[11737.024921] readahead-interleaved(process: w3m/23926, file: sda1/w3m, offset\u003d0:2, ra\u003d4+6-6) \u003d 6\n~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ~~~~~~~~~~~~~\n\nAn unfavorably small readahead. The original dumb read-around size could\nbe more efficient.\n\nThat happened because ld-linux.so does a read(832) in L1 before mmap(),\nwhich triggers a 4-page readahead, with the second page tagged\nPG_readahead.\n\nL0: open(\"/lib/libc.so.6\", O_RDONLY) \u003d 3\nL1: read(3, \"\\177ELF\\2\\1\\1\\0\\0\\0\\0\\0\\0\\0\\0\\0\\3\\0\u003e\\0\\1\\0\\0\\0\\340\\342\"..., 832) \u003d 832\n~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\nL2: fstat(3, {st_mode\u003dS_IFREG|0755, st_size\u003d1420624, ...}) \u003d 0\nL3: mmap(NULL, 3527256, PROT_READ|PROT_EXEC, MAP_PRIVATE|MAP_DENYWRITE, 3, 0) \u003d 0x7fac6e51d000\nL4: mprotect(0x7fac6e671000, 2097152, PROT_NONE) \u003d 0\nL5: mmap(0x7fac6e871000, 20480, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 0x154000) \u003d 0x7fac6e871000\nL6: mmap(0x7fac6e876000, 16984, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_ANONYMOUS, -1, 0) \u003d 0x7fac6e876000\nL7: close(3) \u003d 0\n\nIn general, the PG_readahead flag will also be hit in cases\n\n- sequential reads\n\n- clustered random reads\n\nA full readahead size is desirable in both cases.\n\nCc: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nCc: Ying Han \u003cyinghan@google.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "70ac23cfa31f68289d4b720c6162b3929ab4de36", "tree": "d610e506a9247a22ba54c379d8abb58958ada6da", "parents": [ "ef00e08e26dd5d84271ef706262506b82195e752" ], "author": { "name": "Wu Fengguang", "email": "fengguang.wu@intel.com", "time": "Tue Jun 16 15:31:28 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Jun 16 19:47:29 2009 -0700" }, "message": "readahead: sequential mmap readahead\n\nAuto-detect sequential mmap reads and do readahead for them.\n\nThe sequential mmap readahead will be triggered when\n- sync readahead: it\u0027s a major fault and (prev_offset \u003d\u003d offset-1);\n- async readahead: minor fault on PG_readahead page with valid readahead state.\n\nThe benefits of doing readahead instead of read-around:\n- less I/O wait thanks to async readahead\n- double real I/O size and no more cache hits\n\nThe single stream case is improved a little.\nFor 100,000 sequential mmap reads:\n\n user system cpu total\n(1-1) plain -mm, 128KB readaround: 3.224 2.554 48.40% 11.838\n(1-2) plain -mm, 256KB readaround: 3.170 2.392 46.20% 11.976\n(2) patched -mm, 128KB readahead: 3.117 2.448 47.33% 11.607\n\nThe patched (2) has smallest total time, since it has no cache hit overheads\nand less I/O block time(thanks to async readahead). Here the I/O size\nmakes no much difference, since there\u0027s only one single stream.\n\nNote that (1-1)\u0027s real I/O size is 64KB and (1-2)\u0027s real I/O size is 128KB,\nsince the half of the read-around pages will be readahead cache hits.\n\nThis is going to make _real_ differences for _concurrent_ IO streams.\n\nCc: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nCc: Ying Han \u003cyinghan@google.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "ef00e08e26dd5d84271ef706262506b82195e752", "tree": "5f6cf72cf9bf0574ecfbd73f4ee5378d89298dd7", "parents": [ "51daa88ebd8e0d437289f589af29d4b39379ea76" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Jun 16 15:31:25 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Jun 16 19:47:29 2009 -0700" }, "message": "readahead: clean up and simplify the code for filemap page fault readahead\n\nThis shouldn\u0027t really change behavior all that much, but the single rather\ncomplex function with read-ahead inside a loop etc is broken up into more\nmanageable pieces.\n\nThe behaviour is also less subtle, with the read-ahead being done up-front\nrather than inside some subtle loop and thus avoiding the now unnecessary\nextra state variables (ie \"did_readaround\" is gone).\n\nFengguang: the code split in fact fixed a bug reported by Pavel Levshin:\nthe PGMAJFAULT accounting used to be bypassed when MADV_RANDOM is set, in\nwhich case the original code will directly jump to no_cached_page reading.\n\nCc: Pavel Levshin \u003clpk@581.spb.su\u003e\nCc: \u003cwli@movementarian.org\u003e\nCc: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "f7e839dd36fd940b0202cfb7d39b2a1b2dc59b1b", "tree": "5c99332a62aa8135bd58485e7f3c22634ecdc90c", "parents": [ "1ebf26a9b338534def47f307c6c8694b6dfc0a79" ], "author": { "name": "Wu Fengguang", "email": "fengguang.wu@intel.com", "time": "Tue Jun 16 15:31:20 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Jun 16 19:47:28 2009 -0700" }, "message": "readahead: move max_sane_readahead() calls into force_page_cache_readahead()\n\nImpact: code simplification.\n\nCc: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nCc: Ying Han \u003cyinghan@google.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "e767e0561d7fd2333df1921f1ab4176211f9036b", "tree": "3b936733f80ceb1ee61ce99f927d002d2296250e", "parents": [ "bd6daba909d8484bd2ccf6017db4028d7a420927" ], "author": { "name": "Daisuke Nishimura", "email": "nishimura@mxp.nes.nec.co.jp", "time": "Thu May 28 14:34:28 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri May 29 08:40:02 2009 -0700" }, "message": "memcg: fix deadlock between lock_page_cgroup and mapping tree_lock\n\nmapping-\u003etree_lock can be acquired from interrupt context. Then,\nfollowing dead lock can occur.\n\nAssume \"A\" as a page.\n\n CPU0:\n lock_page_cgroup(A)\n\t\tinterrupted\n\t\t\t-\u003e take mapping-\u003etree_lock.\n CPU1:\n take mapping-\u003etree_lock\n\t\t-\u003e lock_page_cgroup(A)\n\nThis patch tries to fix above deadlock by moving memcg\u0027s hook to out of\nmapping-\u003etree_lock. charge/uncharge of pagecache/swapcache is protected\nby page lock, not tree_lock.\n\nAfter this patch, lock_page_cgroup() is not called under mapping-\u003etree_lock.\n\nSigned-off-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nSigned-off-by: Daisuke Nishimura \u003cnishimura@mxp.nes.nec.co.jp\u003e\nCc: Balbir Singh \u003cbalbir@in.ibm.com\u003e\nCc: Daisuke Nishimura \u003cnishimura@mxp.nes.nec.co.jp\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "f69955855eac55a048d26a1618f50dfaa160a006", "tree": "b43b2d49ca568c4c591415d0f4a69812ca1a781f", "parents": [ "cd97824994042b809493807ea644ba26c0c23290" ], "author": { "name": "Chris Mason", "email": "chris.mason@oracle.com", "time": "Wed Apr 15 13:22:37 2009 -0400" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Apr 16 07:47:49 2009 -0700" }, "message": "Export filemap_write_and_wait_range\n\nThis wasn\u0027t exported before and is useful (used by the experimental ext3\ndata\u003dguarded code)\n\nSigned-off-by: Chris Mason \u003cchris.mason@oracle.com\u003e\nAcked-by: Theodore Tso \u003ctytso@mit.edu\u003e\nAcked-by: Jan Kara \u003cjack@suse.cz\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "697f619fc87aa9bf5b6c8c756f7ea54e950d5cd5", "tree": "54ab6110a9e9d497ed21bf7423ff21e070d6bbb4", "parents": [ "5dec8bfbdd4921522565a7b0e0c8760ae042ef6d" ], "author": { "name": "Randy Dunlap", "email": "randy.dunlap@oracle.com", "time": "Mon Apr 13 14:39:54 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Apr 13 15:04:30 2009 -0700" }, "message": "filemap: fix kernel-doc warnings\n\nFix filemap.c kernel-doc warnings:\n\nWarning(mm/filemap.c:575): No description found for parameter \u0027page\u0027\nWarning(mm/filemap.c:575): No description found for parameter \u0027waiter\u0027\n\nSigned-off-by: Randy Dunlap \u003crandy.dunlap@oracle.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "18bc0bbd162e3eb3e7ea2953c315ad4113a57164", "tree": "6c46e99774772b8ac0ef92633377f4328bd87dbf", "parents": [ "c09ee9d206994655d55de60222a3024702ad2055" ], "author": { "name": "Evgeniy Polyakov", "email": "zbr@ioremap.net", "time": "Mon Feb 09 17:02:42 2009 +0300" }, "committer": { "name": "Greg Kroah-Hartman", "email": "gregkh@suse.de", "time": "Fri Apr 03 14:53:36 2009 -0700" }, "message": "Staging: pohmelfs: kconfig/makefile and vfs changes.\n\nThis patch adds Kconfig and Makefile entries and exports to\nVFS functions to be used by POHMELFS.\n\nSigned-off-by: Evgeniy Polyakov \u003czbr@ioremap.net\u003e\nSigned-off-by: Greg Kroah-Hartman \u003cgregkh@suse.de\u003e\n\n" }, { "commit": "385e1ca5f21c4680ad6a46a3aa2ea8af99e99c92", "tree": "7d887b59d943c5dd62c9604b7ea37fd2d650df71", "parents": [ "b510882281d56873e1194021643b7c325336f84f" ], "author": { "name": "David Howells", "email": "dhowells@redhat.com", "time": "Fri Apr 03 16:42:39 2009 +0100" }, "committer": { "name": "David Howells", "email": "dhowells@redhat.com", "time": "Fri Apr 03 16:42:39 2009 +0100" }, "message": "CacheFiles: Permit the page lock state to be monitored\n\nAdd a function to install a monitor on the page lock waitqueue for a particular\npage, thus allowing the page being unlocked to be detected.\n\nThis is used by CacheFiles to detect read completion on a page in the backing\nfilesystem so that it can then copy the data to the waiting netfs page.\n\nSigned-off-by: David Howells \u003cdhowells@redhat.com\u003e\nAcked-by: Steve Dickson \u003csteved@redhat.com\u003e\nAcked-by: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\nAcked-by: Rik van Riel \u003criel@redhat.com\u003e\nAcked-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\nTested-by: Daire Byrne \u003cDaire.Byrne@framestore.com\u003e\n" }, { "commit": "266cf658efcf6ac33541a46740f74f50c79d2b6b", "tree": "5c83b0879892d509e598dfd54be3ba3679ecd348", "parents": [ "03fb3d2af96c2783c3a5bc03f3d984cf422f0e69" ], "author": { "name": "David Howells", "email": "dhowells@redhat.com", "time": "Fri Apr 03 16:42:36 2009 +0100" }, "committer": { "name": "David Howells", "email": "dhowells@redhat.com", "time": "Fri Apr 03 16:42:36 2009 +0100" }, "message": "FS-Cache: Recruit a page flags for cache management\n\nRecruit a page flag to aid in cache management. The following extra flag is\ndefined:\n\n (1) PG_fscache (PG_private_2)\n\n The marked page is backed by a local cache and is pinning resources in the\n cache driver.\n\nIf PG_fscache is set, then things that checked for PG_private will now also\ncheck for that. This includes things like truncation and page invalidation.\nThe function page_has_private() had been added to make the checks for both\nPG_private and PG_private_2 at the same time.\n\nSigned-off-by: David Howells \u003cdhowells@redhat.com\u003e\nAcked-by: Steve Dickson \u003csteved@redhat.com\u003e\nAcked-by: Trond Myklebust \u003cTrond.Myklebust@netapp.com\u003e\nAcked-by: Rik van Riel \u003criel@redhat.com\u003e\nAcked-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\nTested-by: Daire Byrne \u003cDaire.Byrne@framestore.com\u003e\n" }, { "commit": "f180053694b43d5714bf56cb95499a3c32ff155c", "tree": "00286fcc88d2842629b039da4009a1332b3a1719", "parents": [ "34754b69a6f87aa6aa2860525a82f12532f83afd" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Mar 02 11:00:57 2009 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Mar 02 11:06:49 2009 +0100" }, "message": "x86, mm: dont use non-temporal stores in pagecache accesses\n\nImpact: standardize IO on cached ops\n\nOn modern CPUs it is almost always a bad idea to use non-temporal stores,\nas the regression in this commit has shown it:\n\n 30d697f: x86: fix performance regression in write() syscall\n\nThe kernel simply has no good information about whether using non-temporal\nstores is a good idea or not - and trying to add heuristics only increases\ncomplexity and inserts fragility.\n\nThe regression on cached write()s took very long to be found - over two\nyears. So dont take any chances and let the hardware decide how it makes\nuse of its caches.\n\nThe only exception is drivers/gpu/drm/i915/i915_gem.c: there were we are\nabsolutely sure that another entity (the GPU) will pick up the dirty\ndata immediately and that the CPU will not touch that data before the\nGPU will.\n\nAlso, keep the _nocache() primitives to make it easier for people to\nexperiment with these details. There may be more clear-cut cases where\nnon-cached copies can be used, outside of filemap.c.\n\nCc: Salman Qazi \u003csqazi@google.com\u003e\nCc: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "3255aa2eb636a508fc82a73fabbb8aaf2ff23c0f", "tree": "2a602fb8f4fefe666e8daedf1e1f755800bd700a", "parents": [ "95f66b3770d6d0755b4a2d818c237574ffd74e4c" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Feb 25 08:21:52 2009 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Feb 25 10:20:03 2009 +0100" }, "message": "x86, mm: pass in \u0027total\u0027 to __copy_from_user_*nocache()\n\nImpact: cleanup, enable future change\n\nAdd a \u0027total bytes copied\u0027 parameter to __copy_from_user_*nocache(),\nand update all the callsites.\n\nThe parameter is not used yet - architecture code can use it to\nmore intelligently decide whether the copy should be cached or\nnon-temporal.\n\nCc: Salman Qazi \u003csqazi@google.com\u003e\nCc: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "6673e0c3fbeaed2cd08e2fd4a4aa97382d6fedb0", "tree": "eb33a94f5e4b0e035001f7c96ef44cade0fbb489", "parents": [ "ed6bb6194350dc6ae97a65dbf2d621a3dbe6bbe9" ], "author": { "name": "Heiko Carstens", "email": "heiko.carstens@de.ibm.com", "time": "Wed Jan 14 14:14:02 2009 +0100" }, "committer": { "name": "Heiko Carstens", "email": "heiko.carstens@de.ibm.com", "time": "Wed Jan 14 14:15:18 2009 +0100" }, "message": "[CVE-2009-0029] System call wrapper special cases\n\nSystem calls with an unsigned long long argument can\u0027t be converted with\nthe standard wrappers since that would include a cast to long, which in\nturn means that we would lose the upper 32 bit on 32 bit architectures.\nAlso semctl can\u0027t use the standard wrapper since it has a \u0027union\u0027\nparameter.\n\nSo we handle them as special case and add some extra wrappers instead.\n\nSigned-off-by: Heiko Carstens \u003cheiko.carstens@de.ibm.com\u003e\n" }, { "commit": "2ed7c03ec17779afb4fcfa3b8c61df61bd4879ba", "tree": "4e0fefd574bab5470a02edf439727f472a9663c6", "parents": [ "4c696ba7982501d43dea11dbbaabd2aa8a19cc42" ], "author": { "name": "Heiko Carstens", "email": "heiko.carstens@de.ibm.com", "time": "Wed Jan 14 14:13:54 2009 +0100" }, "committer": { "name": "Heiko Carstens", "email": "heiko.carstens@de.ibm.com", "time": "Wed Jan 14 14:15:14 2009 +0100" }, "message": "[CVE-2009-0029] Convert all system calls to return a long\n\nConvert all system calls to return a long. This should be a NOP since all\nconverted types should have the same size anyway.\nWith the exception of sys_exit_group which returned void. But that doesn\u0027t\nmatter since the system call doesn\u0027t return.\n\nSigned-off-by: Heiko Carstens \u003cheiko.carstens@de.ibm.com\u003e\n" }, { "commit": "2c26fdd70c3094fa3e84caf9ef434911933d5477", "tree": "06a3bafc12f5f8fd91d9ed1fca5ea0a632ef2004", "parents": [ "887007561ae58628f03aa9046949747c04f63be8" ], "author": { "name": "KAMEZAWA Hiroyuki", "email": "kamezawa.hiroyu@jp.fujitsu.com", "time": "Wed Jan 07 18:08:10 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jan 08 08:31:06 2009 -0800" }, "message": "memcg: revert gfp mask fix\n\nMy patch, memcg-fix-gfp_mask-of-callers-of-charge.patch changed gfp_mask\nof callers of charge to be GFP_HIGHUSER_MOVABLE for showing what will\nhappen at memory reclaim.\n\nBut in recent discussion, it\u0027s NACKed because it sounds ugly.\n\nThis patch is for reverting it and add some clean up to gfp_mask of\ncallers of charge. No behavior change but need review before generating\nHUNK in deep queue.\n\nThis patch also adds explanation to meaning of gfp_mask passed to charge\nfunctions in memcontrol.h.\n\nSigned-off-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Balbir Singh \u003cbalbir@in.ibm.com\u003e\nCc: Daisuke Nishimura \u003cnishimura@mxp.nes.nec.co.jp\u003e\nCc: Hugh Dickins \u003chugh@veritas.com\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "67d58ac47d25f7e2a105248a4aea6113131ab874", "tree": "5bf9440696b72ec0962d352c6d60b81929b79602", "parents": [ "856bf4d717feb8c55d4e2f817b71ebb70cfbc67b" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Jan 06 14:40:28 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Jan 06 15:59:09 2009 -0800" }, "message": "mm: pagecache gfp flags fix\n\nFrustratingly, gfp_t is really divided into two classes of flags. One are\nthe context dependent ones (can we sleep? can we enter filesystem? block\nsubsystem? should we use some extra reserves, etc.). The other ones are\nthe type of memory required and depend on how the algorithm is implemented\nrather than the point at which the memory is allocated (highmem? dma\nmemory? etc).\n\nSome of the functions which allocate a page and add it to page cache take\na gfp_t, but sometimes those functions or their callers aren\u0027t really\ndoing the right thing: when allocating pagecache page, the memory type\nshould be mapping_gfp_mask(mapping). When allocating radix tree nodes,\nthe memory type should be kernel mapped (not highmem) memory. The gfp_t\nargument should only really be needed for context dependent options.\n\nThis patch doesn\u0027t really solve that tangle in a nice way, but it does\nattempt to fix a couple of bugs.\n\n- find_or_create_page changes its radix-tree allocation to only include\n the main context dependent flags in order so the pagecache page may be\n allocated from arbitrary types of memory without affecting the\n radix-tree. In practice, slab allocations don\u0027t come from highmem\n anyway, and radix-tree only uses slab allocations. So there isn\u0027t a\n practical change (unless some fs uses GFP_DMA for pages).\n\n- grab_cache_page_nowait() is changed to allocate radix-tree nodes with\n GFP_NOFS, because it is not supposed to reenter the filesystem. This\n bug could cause lock recursion if a filesystem is not expecting the\n function to reenter the fs (as-per documentation).\n\nFilesystems should be careful about exactly what semantics they want and\nwhat they get when fiddling with gfp_t masks to allocate pagecache. One\nshould be as liberal as possible with the type of memory that can be used,\nand same for the the context specific flags.\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "48b47c561e41525061b5bc0cfd67d6367fd11dc4", "tree": "ae99a8cb55b4d2716847521953db4bddd66b8e8b", "parents": [ "48aae42556e5ea1ba0d8ddab25352706577af2ed" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Jan 06 14:40:22 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Jan 06 15:59:09 2009 -0800" }, "message": "mm: direct IO starvation improvement\n\nDirect IO can invalidate and sync a lot of pagecache pages in the mapping.\n A 4K direct IO will actually try to sync and/or invalidate the pagecache\nof the entire file, for example (which might be many GB or TB large).\n\nImprove this by doing range syncs. Also, memory no longer has to be\nunmapped to catch the dirty bits for syncing, as dirty bits would remain\ncoherent due to dirty mmap accounting.\n\nThis fixes the immediate DM deadlocks when doing direct IO reads to block\ndevice with a mounted filesystem, if only by papering over the problem\nsomewhat rather than addressing the fsync starvation cases.\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nReviewed-by: Jeff Moyer \u003cjmoyer@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": "05fe478dd04e02fa230c305ab9b5616669821dd3", "tree": "9b551aad196b66e5c773ed7619386a1bb5e14f41", "parents": [ "00266770b8b3a6a77f896ca501a0613739086832" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Jan 06 14:39:08 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Jan 06 15:58:59 2009 -0800" }, "message": "mm: write_cache_pages integrity fix\n\nIn write_cache_pages, nr_to_write is heeded even for data-integrity syncs,\nso the function will return success after writing out nr_to_write pages,\neven if that was not sufficient to guarantee data integrity.\n\nThe callers tend to set it to values that could break data interity\nsemantics easily in practice. For example, nr_to_write can be set to\nmapping-\u003enr_pages * 2, however if a file has a single, dirty page, then\nfsync is called, subsequent pages might be concurrently added and dirtied,\nthen write_cache_pages might writeout two of these newly dirty pages,\nwhile not writing out the old page that should have been written out.\n\nFix this by ignoring nr_to_write if it is a data integrity sync.\n\nThis is a data integrity bug.\n\nThe reason this has been done in the past is to avoid stalling sync\noperations behind page dirtiers.\n\n \"If a file has one dirty page at offset 1000000000000000 then someone\n does an fsync() and someone else gets in first and starts madly writing\n pages at offset 0, we want to write that page at 1000000000000000.\n Somehow.\"\n\nWhat we do today is return success after an arbitrary amount of pages are\nwritten, whether or not we have provided the data-integrity semantics that\nthe caller has asked for. Even this doesn\u0027t actually fix all stall cases\ncompletely: in the above situation, if the file has a huge number of pages\nin pagecache (but not dirty), then mapping-\u003enrpages is going to be huge,\neven if pages are being dirtied.\n\nThis change does indeed make the possibility of long stalls lager, and\nthat\u0027s not a good thing, but lying about data integrity is even worse. We\nhave to either perform the sync, or return -ELINUXISLAME so at least the\ncaller knows what has happened.\n\nThere are subsequent competing approaches in the works to solve the stall\nproblems properly, without compromising data integrity.\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: Chris Mason \u003cchris.mason@oracle.com\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": "bf3f3bc5e734706730c12a323f9b2068052aa1f0", "tree": "d93fb6beb0916cc10aeb5674578bfa3ac40371c9", "parents": [ "3340289ddf29ca75c3acfb3a6b72f234b2f74d5c" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Jan 06 14:38:55 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Jan 06 15:58:58 2009 -0800" }, "message": "mm: don\u0027t mark_page_accessed in fault path\n\nDoing a mark_page_accessed at fault-time, then doing SetPageReferenced at\nunmap-time if the pte is young has a number of problems.\n\nmark_page_accessed is supposed to be roughly the equivalent of a young pte\nfor unmapped references. Unfortunately it doesn\u0027t come with any context:\nafter being called, reclaim doesn\u0027t know who or why the page was touched.\n\nSo calling mark_page_accessed not only adds extra lru or PG_referenced\nmanipulations for pages that are already going to have pte_young ptes anyway,\nbut it also adds these references which are difficult to work with from the\ncontext of vma specific references (eg. MADV_SEQUENTIAL pte_young may not\nwish to contribute to the page being referenced).\n\nThen, simply doing SetPageReferenced when zapping a pte and finding it is\nyoung, is not a really good solution either. SetPageReferenced does not\ncorrectly promote the page to the active list for example. So after removing\nmark_page_accessed from the fault path, several mmap()+touch+munmap() would\nhave a very different result from several read(2) calls for example, which\nis not really desirable.\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nAcked-by: Johannes Weiner \u003channes@saeurebad.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "520c85346666d4d9a6fcaaa8450542302dc28b91", "tree": "9c9cc9e2493b606104dd8602302ae28258ebeac0", "parents": [ "e8c82c2e23e3527e0c9dc195e432c16784d270fa", "4ae8978cf92a96257cd8998a49e781be83571d64" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Jan 05 18:32:06 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Jan 05 18:32:06 2009 -0800" }, "message": "Merge branch \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6\n\n* \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6:\n inotify: fix type errors in interfaces\n fix breakage in reiserfs_new_inode()\n fix the treatment of jfs special inodes\n vfs: remove duplicate code in get_fs_type()\n add a vfs_fsync helper\n sys_execve and sys_uselib do not call into fsnotify\n zero i_uid/i_gid on inode allocation\n inode-\u003ei_op is never NULL\n ntfs: don\u0027t NULL i_op\n isofs check for NULL -\u003ei_op in root directory is dead code\n affs: do not zero -\u003ei_op\n kill suid bit only for regular files\n vfs: lseek(fd, 0, SEEK_CUR) race condition\n" }, { "commit": "7f5ff766a7babd72fc192125e12ef5570effff4c", "tree": "c41659d7614ea70c3dc853c6187f1860d030888b", "parents": [ "5b6f1eb97d462a45be3b30759758b5fdbb562c8c" ], "author": { "name": "Dmitri Monakhov", "email": "dmonakhov@openvz.org", "time": "Mon Dec 01 14:34:56 2008 -0800" }, "committer": { "name": "Al Viro", "email": "viro@zeniv.linux.org.uk", "time": "Mon Jan 05 11:53:07 2009 -0500" }, "message": "kill suid bit only for regular files\n\nWe don\u0027t have to do it because it is useless for non regular files.\nIn fact block device may trigger this path without dentry-\u003ed_inode-\u003ei_mutex.\n\n(akpm: concerns were expressed (by me) about S_ISDIR inodes)\n\nSigned-off-by: Dmitri Monakhov \u003cdmonakhov@openvz.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n" }, { "commit": "54566b2c1594c2326a645a3551f9d989f7ba3c5e", "tree": "b373f3283fe5e197d0df29cd6b645c35adf1076c", "parents": [ "e687d691cb3790d25e31c74f5941fd7c565e9df5" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Sun Jan 04 12:00:53 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sun Jan 04 13:33:20 2009 -0800" }, "message": "fs: symlink write_begin allocation context fix\n\nWith the write_begin/write_end aops, page_symlink was broken because it\ncould no longer pass a GFP_NOFS type mask into the point where the\nallocations happened. They are done in write_begin, which would always\nassume that the filesystem can be entered from reclaim. This bug could\ncause filesystem deadlocks.\n\nThe funny thing with having a gfp_t mask there is that it doesn\u0027t really\nallow the caller to arbitrarily tinker with the context in which it can be\ncalled. It couldn\u0027t ever be GFP_ATOMIC, for example, because it needs to\ntake the page lock. The only thing any callers care about is __GFP_FS\nanyway, so turn that into a single flag.\n\nAdd a new flag for write_begin, AOP_FLAG_NOFS. Filesystems can now act on\nthis flag in their write_begin function. Change __grab_cache_page to\naccept a nofs argument as well, to honour that flag (while we\u0027re there,\nchange the name to grab_cache_page_write_begin which is more instructive\nand does away with random leading underscores).\n\nThis is really a more flexible way to go in the end anyway -- if a\nfilesystem happens to want any extra allocations aside from the pagecache\nones in ints write_begin function, it may now use GFP_KERNEL (rather than\nGFP_NOFS) for common case allocations (eg. ocfs2_alloc_write_ctxt, for a\nrandom example).\n\n[kosaki.motohiro@jp.fujitsu.com: fix ubifs]\n[kosaki.motohiro@jp.fujitsu.com: fix fuse]\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nReviewed-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: \u003cstable@kernel.org\u003e\t\t[2.6.28.x]\nSigned-off-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\n[ Cleaned up the calling convention: just pass in the AOP flags\n untouched to the grab_cache_page_write_begin() function. That\n just simplifies everybody, and may even allow future expansion of the\n logic. - Linus ]\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "4e02ed4b4a2fae34aae766a5bb93ae235f60adb8", "tree": "bddfb61b7cc4a4007ae176ccb1ace5740b61da8d", "parents": [ "9b913735e53ab0da4a792bac0de8e178cc13dcfb" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Wed Oct 29 14:00:55 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Oct 30 11:38:45 2008 -0700" }, "message": "fs: remove prepare_write/commit_write\n\nNothing uses prepare_write or commit_write. Remove them from the tree\ncompletely.\n\n[akpm@linux-foundation.org: schedule simple_prepare_write() for unexporting]\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\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": "b7abea9630bc8ffc663a751e46680db25c4cdf8d", "tree": "b37d5ba073ccea31328812c74598872d49a85735", "parents": [ "073e587ec2cc377867e53d8b8959738a8e16cff6" ], "author": { "name": "KAMEZAWA Hiroyuki", "email": "kamezawa.hiroyu@jp.fujitsu.com", "time": "Sat Oct 18 20:28:09 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Oct 20 08:52:38 2008 -0700" }, "message": "memcg: make page-\u003emapping NULL before uncharge\n\nThis patch tries to make page-\u003emapping to be NULL before\nmem_cgroup_uncharge_cache_page() is called.\n\n\"page-\u003emapping \u003d\u003d NULL\" is a good check for \"whether the page is still\nradix-tree or not\". This patch also adds BUG_ON() to\nmem_cgroup_uncharge_cache_page();\n\nSigned-off-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nReviewed-by: Daisuke Nishimura \u003cnishimura@mxp.nes.nec.co.jp\u003e\nCc: Balbir Singh \u003cbalbir@linux.vnet.ibm.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "8413ac9d8c9a1366a4f57880723126cd24e5a5c3", "tree": "fcee6ff670dcfccf895a48e92d27f52902d34301", "parents": [ "a978d6f521063514812a7094dbe5036e056e4de3" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Sat Oct 18 20:26:59 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Oct 20 08:52:32 2008 -0700" }, "message": "mm: page lock use lock bitops\n\ntrylock_page, unlock_page open and close a critical section. Hence,\nwe can use the lock bitops to get the desired memory ordering.\n\nAlso, mark trylock as likely to succeed (and remove the annotation from\ncallers).\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "4f98a2fee8acdb4ac84545df98cccecfd130f8db", "tree": "035a2937f4c3e2f7b4269412041c073ac646937c", "parents": [ "b2e185384f534781fd22f5ce170b2ad26f97df70" ], "author": { "name": "Rik van Riel", "email": "riel@redhat.com", "time": "Sat Oct 18 20:26:32 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Oct 20 08:50:25 2008 -0700" }, "message": "vmscan: split LRU lists into anon \u0026 file sets\n\nSplit the LRU lists in two, one set for pages that are backed by real file\nsystems (\"file\") and one for pages that are backed by memory and swap\n(\"anon\"). The latter includes tmpfs.\n\nThe advantage of doing this is that the VM will not have to scan over lots\nof anonymous pages (which we generally do not want to swap out), just to\nfind the page cache pages that it should evict.\n\nThis patch has the infrastructure and a basic policy to balance how much\nwe scan the anon lists and how much we scan the file lists. The big\npolicy changes are in separate patches.\n\n[lee.schermerhorn@hp.com: collect lru meminfo statistics from correct offset]\n[kosaki.motohiro@jp.fujitsu.com: prevent incorrect oom under split_lru]\n[kosaki.motohiro@jp.fujitsu.com: fix pagevec_move_tail() doesn\u0027t treat unevictable page]\n[hugh@veritas.com: memcg swapbacked pages active]\n[hugh@veritas.com: splitlru: BDI_CAP_SWAP_BACKED]\n[akpm@linux-foundation.org: fix /proc/vmstat units]\n[nishimura@mxp.nes.nec.co.jp: memcg: fix handling of shmem migration]\n[kosaki.motohiro@jp.fujitsu.com: adjust Quicklists field of /proc/meminfo]\n[kosaki.motohiro@jp.fujitsu.com: fix style issue of get_scan_ratio()]\nSigned-off-by: Rik van Riel \u003criel@redhat.com\u003e\nSigned-off-by: Lee Schermerhorn \u003cLee.Schermerhorn@hp.com\u003e\nSigned-off-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nSigned-off-by: Hugh Dickins \u003chugh@veritas.com\u003e\nSigned-off-by: Daisuke Nishimura \u003cnishimura@mxp.nes.nec.co.jp\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "e533b227055598b1f7dc8503a3b4f36b14b9da8a", "tree": "28fec4125eac45c8e2fac75b3d10ff5cd987d2f6", "parents": [ "0999d978dcdcf59350dafa25afd70def9f924eee", "6b2ada82101a08e2830fb29d7dc9b858be637dd4" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Oct 16 15:17:40 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Oct 16 15:17:40 2008 -0700" }, "message": "Merge branch \u0027core-v28-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip\n\n* \u0027core-v28-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:\n do_generic_file_read: s/EINTR/EIO/ if lock_page_killable() fails\n softirq, warning fix: correct a format to avoid a warning\n softirqs, debug: preemption check\n x86, pci-hotplug, calgary / rio: fix EBDA ioremap()\n IO resources, x86: ioremap sanity check to catch mapping requests exceeding, fix\n IO resources, x86: ioremap sanity check to catch mapping requests exceeding the BAR sizes\n softlockup: Documentation/sysctl/kernel.txt: fix softlockup_thresh description\n dmi scan: warn about too early calls to dmi_check_system()\n generic: redefine resource_size_t as phys_addr_t\n generic: make PFN_PHYS explicitly return phys_addr_t\n generic: add phys_addr_t for holding physical addresses\n softirq: allocate less vectors\n IO resources: fix/remove printk\n printk: robustify printk, update comment\n printk: robustify printk, fix #2\n printk: robustify printk, fix\n printk: robustify printk\n\nFixed up conflicts in:\n\tarch/powerpc/include/asm/types.h\n\tarch/powerpc/platforms/Kconfig.cputype\nmanually.\n" }, { "commit": "0c6aa2639ea83bfb7f91d72118bad70b3f60012a", "tree": "7ed277716200bdd949491aad355a2edf6d0864f3", "parents": [ "b4d1d99fdd8b98fb03dfd6ef9b0ece220de38640" ], "author": { "name": "Krishna Kumar", "email": "krkumar2@in.ibm.com", "time": "Wed Oct 15 22:01:13 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Oct 16 11:21:29 2008 -0700" }, "message": "mm: do_generic_file_read() never gets a NULL \u0027filp\u0027 argument\n\nThe \u0027filp\u0027 argument to do_generic_file_read() is never NULL.\n\nSigned-off-by: Krishna Kumar \u003ckrkumar2@in.ibm.com\u003e\nReviewed-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\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": "85462323555dda749f1c5373a8d72679464c968d", "tree": "aeec1f9a2ad6665c70a88483cbe5e9a3a2f33536", "parents": [ "7591103c08abade60aeddb432ed0686ddd0de1c6" ], "author": { "name": "Oleg Nesterov", "email": "oleg@tv-sign.ru", "time": "Sun Jun 08 21:20:43 2008 +0400" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Oct 14 17:15:33 2008 +0200" }, "message": "do_generic_file_read: s/EINTR/EIO/ if lock_page_killable() fails\n\nIf lock_page_killable() fails because the task was killed by SIGKILL or\nany other fatal signal, do_generic_file_read() returns -EIO.\n\nThis seems to be OK, because in fact the userspace won\u0027t see this error,\nthe task will dequeue SIGKILL and exit.\n\nHowever, /sbin/init is different, it will dequeue SIGKILL, ignore it, and\nreturn to the user-space with the bogus -EIO.\n\nChange the code to return the error code from lock_page_killable(), -EINTR.\nThis doesn\u0027t fix the bug, but perhaps makes sense anyway. Imho, with this\nchange the code looks a bit more logical, and the \"good\" init should handle\nthe spurious EINTR or short read.\n\nAfaics we can also change lock_page_killable() to return -ERESTARTNOINTR,\nbut this can\u0027t prevent the short reads.\n\nSigned-off-by: Oleg Nesterov \u003coleg@tv-sign.ru\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "6ccfa806a9cfbbf1cd43d5b6aa47ef2c0eb518fd", "tree": "dd3f17e1aebc802b147627a4151add363f39b77c", "parents": [ "344c790e3821dac37eb742ddd0b611a300f78b9a" ], "author": { "name": "Hisashi Hifumi", "email": "hifumi.hisashi@oss.ntt.co.jp", "time": "Tue Sep 02 14:35:40 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Sep 02 19:21:37 2008 -0700" }, "message": "VFS: fix dio write returning EIO when try_to_release_page fails\n\nDio write returns EIO when try_to_release_page fails because bh is\nstill referenced.\n\nThe patch\n\n commit 3f31fddfa26b7594b44ff2b34f9a04ba409e0f91\n Author: Mingming Cao \u003ccmm@us.ibm.com\u003e\n Date: Fri Jul 25 01:46:22 2008 -0700\n\n jbd: fix race between free buffer and commit transaction\n\nwas merged into 2.6.27-rc1, but I noticed that this patch is not enough\nto fix the race.\n\nI did fsstress test heavily to 2.6.27-rc1, and found that dio write still\nsometimes got EIO through this test.\n\nThe patch above fixed race between freeing buffer(dio) and committing\ntransaction(jbd) but I discovered that there is another race, freeing\nbuffer(dio) and ext3/4_ordered_writepage.\n\n: background_writeout()\n -\u003ewrite_cache_pages()\n -\u003eext3_ordered_writepage()\n \t walk_page_buffers() -\u003e take a bh ref\n \t block_write_full_page() -\u003e unlock_page\n\t\t: \u003c- end_page_writeback\n : \u003c- race! (dio write-\u003etry_to_release_page fails)\n \t walk_page_buffers() -\u003erelease a bh ref\n\next3_ordered_writepage holds bh ref and does unlock_page remaining\ntaking a bh ref, so this causes the race and failure of\ntry_to_release_page.\n\nTo fix this race, I used the approach of falling back to buffered\nwrites if try_to_release_page() fails on a page.\n\n[akpm@linux-foundation.org: cleanups]\nSigned-off-by: Hisashi Hifumi \u003chifumi.hisashi@oss.ntt.co.jp\u003e\nCc: Chris Mason \u003cchris.mason@oracle.com\u003e\nCc: Jan Kara \u003cjack@suse.cz\u003e\nCc: Mingming Cao \u003ccmm@us.ibm.com\u003e\nCc: Zach Brown \u003czach.brown@oracle.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "529ae9aaa08378cfe2a4350bded76f32cc8ff0ce", "tree": "d3ae998f9876c72a83a022805103a92111852b21", "parents": [ "e9ba9698187ddbc0c5bfcf41de0349a662d23d02" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Sat Aug 02 12:01:03 2008 +0200" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Aug 04 21:31:34 2008 -0700" }, "message": "mm: rename page trylock\n\nConverting page lock to new locking bitops requires a change of page flag\noperation naming, so we might as well convert it to something nicer\n(!TestSetPageLocked_Lock \u003d\u003e trylock_page, SetPageLocked \u003d\u003e set_page_locked).\n\nThis also facilitates lockdeping of page lock.\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nAcked-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nAcked-by: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nAcked-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nAcked-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "94ad374a0751f40d25e22e036c37f7263569d24c", "tree": "d1bbf5d64c4eaee7bfefae22ad87b96967187cc8", "parents": [ "0056e65f9e28d83ee1a3fb4f7d0041e838f03c34" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jul 30 14:45:12 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Jul 30 14:50:18 2008 -0700" }, "message": "Fix off-by-one error in iov_iter_advance()\n\nThe iov_iter_advance() function would look at the iov-\u003eiov_len entry\neven though it might have iterated over the whole array, and iov was\npointing past the end. This would cause DEBUG_PAGEALLOC to trigger a\nkernel page fault if the allocation was at the end of a page, and the\nnext page was unallocated.\n\nThe quick fix is to just change the order of the tests: check that there\nis any iovec data left before we check the iov entry itself.\n\nThanks to Alexey Dobriyan for finding this case, and testing the fix.\n\nReported-and-tested-by: Alexey Dobriyan \u003cadobriyan@gmail.com\u003e\nCc: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nCc: \u003cstable@kernel.org\u003e [2.6.25.x, 2.6.26.x]\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "8ab22b9abb5c55413802e4adc9aa6223324547c3", "tree": "cff3319e1275e8a7c083d492889ec6bd0c7712d3", "parents": [ "d84a52f62f6a396ed77aa0052da74ca9e760b28a" ], "author": { "name": "Hisashi Hifumi", "email": "hifumi.hisashi@oss.ntt.co.jp", "time": "Mon Jul 28 15:46:36 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Jul 28 16:30:21 2008 -0700" }, "message": "vfs: pagecache usage optimization for pagesize!\u003dblocksize\n\nWhen we read some part of a file through pagecache, if there is a\npagecache of corresponding index but this page is not uptodate, read IO\nis issued and this page will be uptodate.\n\nI think this is good for pagesize \u003d\u003d blocksize environment but there is\nroom for improvement on pagesize !\u003d blocksize environment. Because in\nthis case a page can have multiple buffers and even if a page is not\nuptodate, some buffers can be uptodate.\n\nSo I suggest that when all buffers which correspond to a part of a file\nthat we want to read are uptodate, use this pagecache and copy data from\nthis pagecache to user buffer even if a page is not uptodate. This can\nreduce read IO and improve system throughput.\n\nI wrote a benchmark program and got result number with this program.\n\nThis benchmark do:\n\n 1: mount and open a test file.\n\n 2: create a 512MB file.\n\n 3: close a file and umount.\n\n 4: mount and again open a test file.\n\n 5: pwrite randomly 300000 times on a test file. offset is aligned\n by IO size(1024bytes).\n\n 6: measure time of preading randomly 100000 times on a test file.\n\nThe result was:\n\t2.6.26\n 330 sec\n\n\t2.6.26-patched\n 226 sec\n\nArch:i386\nFilesystem:ext3\nBlocksize:1024 bytes\nMemory: 1GB\n\nOn ext3/4, a file is written through buffer/block. So random read/write\nmixed workloads or random read after random write workloads are optimized\nwith this patch under pagesize !\u003d blocksize environment. This test result\nshowed this.\n\nThe benchmark program is as follows:\n\n#include \u003cstdio.h\u003e\n#include \u003csys/types.h\u003e\n#include \u003csys/stat.h\u003e\n#include \u003cfcntl.h\u003e\n#include \u003cunistd.h\u003e\n#include \u003ctime.h\u003e\n#include \u003cstdlib.h\u003e\n#include \u003cstring.h\u003e\n#include \u003csys/mount.h\u003e\n\n#define LEN 1024\n#define LOOP 1024*512 /* 512MB */\n\nmain(void)\n{\n\tunsigned long i, offset, filesize;\n\tint fd;\n\tchar buf[LEN];\n\ttime_t t1, t2;\n\n\tif (mount(\"/dev/sda1\", \"/root/test1/\", \"ext3\", 0, 0) \u003c 0) {\n\t\tperror(\"cannot mount\\n\");\n\t\texit(1);\n\t}\n\tmemset(buf, 0, LEN);\n\tfd \u003d open(\"/root/test1/testfile\", O_CREAT|O_RDWR|O_TRUNC);\n\tif (fd \u003c 0) {\n\t\tperror(\"cannot open file\\n\");\n\t\texit(1);\n\t}\n\tfor (i \u003d 0; i \u003c LOOP; i++)\n\t\twrite(fd, buf, LEN);\n\tclose(fd);\n\tif (umount(\"/root/test1/\") \u003c 0) {\n\t\tperror(\"cannot umount\\n\");\n\t\texit(1);\n\t}\n\tif (mount(\"/dev/sda1\", \"/root/test1/\", \"ext3\", 0, 0) \u003c 0) {\n\t\tperror(\"cannot mount\\n\");\n\t\texit(1);\n\t}\n\tfd \u003d open(\"/root/test1/testfile\", O_RDWR);\n\tif (fd \u003c 0) {\n\t\tperror(\"cannot open file\\n\");\n\t\texit(1);\n\t}\n\n\tfilesize \u003d LEN * LOOP;\n\tfor (i \u003d 0; i \u003c 300000; i++){\n\t\toffset \u003d (random() % filesize) \u0026 (~(LEN - 1));\n\t\tpwrite(fd, buf, LEN, offset);\n\t}\n\tprintf(\"start test\\n\");\n\ttime(\u0026t1);\n\tfor (i \u003d 0; i \u003c 100000; i++){\n\t\toffset \u003d (random() % filesize) \u0026 (~(LEN - 1));\n\t\tpread(fd, buf, LEN, offset);\n\t}\n\ttime(\u0026t2);\n\tprintf(\"%ld sec\\n\", t2-t1);\n\tclose(fd);\n\tif (umount(\"/root/test1/\") \u003c 0) {\n\t\tperror(\"cannot umount\\n\");\n\t\texit(1);\n\t}\n}\n\nSigned-off-by: Hisashi Hifumi \u003chifumi.hisashi@oss.ntt.co.jp\u003e\nCc: Nick Piggin \u003cnickpiggin@yahoo.com.au\u003e\nCc: Christoph Hellwig \u003chch@infradead.org\u003e\nCc: Jan Kara \u003cjack@ucw.cz\u003e\nCc: \u003clinux-ext4@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": "2f1936b87783a3a56c9441b27b9ba7a747f11e8e", "tree": "024a0f3da74ba6365f209d03685133760146149b", "parents": [ "c82e42da8a6b2f3a85dc4d4278cb8238702f8f64" ], "author": { "name": "Miklos Szeredi", "email": "mszeredi@suse.cz", "time": "Tue Jun 24 16:50:14 2008 +0200" }, "committer": { "name": "Al Viro", "email": "viro@zeniv.linux.org.uk", "time": "Sat Jul 26 20:53:16 2008 -0400" }, "message": "[patch 3/5] vfs: change remove_suid() to file_remove_suid()\n\nAll calls to remove_suid() are made with a file pointer, because\n(similarly to file_update_time) it is called when the file is written.\n\nClean up callers by passing in a file instead of a dentry.\n\nSigned-off-by: Miklos Szeredi \u003cmszeredi@suse.cz\u003e\n" }, { "commit": "19fd6231279be3c3bdd02ed99f9b0eb195978064", "tree": "ee09121054262d73c551b57114acd855b82a7a82", "parents": [ "a60637c85893e7191faaafa6a72e197c24386727" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Fri Jul 25 19:45:32 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sat Jul 26 12:00:06 2008 -0700" }, "message": "mm: spinlock tree_lock\n\nmapping-\u003etree_lock has no read lockers. convert the lock from an rwlock\nto a spinlock.\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Hugh Dickins \u003chugh@veritas.com\u003e\nCc: \"Paul E. McKenney\" \u003cpaulmck@us.ibm.com\u003e\nReviewed-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "a60637c85893e7191faaafa6a72e197c24386727", "tree": "fa3ec63f505e64d3b4a2be4efd9a5314ab5f6234", "parents": [ "e286781d5f2e9c846e012a39653a166e9d31777d" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Fri Jul 25 19:45:31 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sat Jul 26 12:00:06 2008 -0700" }, "message": "mm: lockless pagecache\n\nCombine page_cache_get_speculative with lockless radix tree lookups to\nintroduce lockless page cache lookups (ie. no mapping-\u003etree_lock on the\nread-side).\n\nThe only atomicity changes this introduces is that the gang pagecache\nlookup functions now behave as if they are implemented with multiple\nfind_get_page calls, rather than operating on a snapshot of the pages. In\npractice, this atomicity guarantee is not used anyway, and it is to\nreplace individual lookups, so these semantics are natural.\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Hugh Dickins \u003chugh@veritas.com\u003e\nCc: \"Paul E. McKenney\" \u003cpaulmck@us.ibm.com\u003e\nReviewed-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "e286781d5f2e9c846e012a39653a166e9d31777d", "tree": "14958fe6d8f3e0459c96c68b3034ea2433ab85ac", "parents": [ "47feff2c8eefe85099f87c43d3096855f0085ca0" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Fri Jul 25 19:45:30 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sat Jul 26 12:00:06 2008 -0700" }, "message": "mm: speculative page references\n\nIf we can be sure that elevating the page_count on a pagecache page will\npin it, we can speculatively run this operation, and subsequently check to\nsee if we hit the right page rather than relying on holding a lock or\notherwise pinning a reference to the page.\n\nThis can be done if get_page/put_page behaves consistently throughout the\nwhole tree (ie. if we \"get\" the page after it has been used for something\nelse, we must be able to free it with a put_page).\n\nActually, there is a period where the count behaves differently: when the\npage is free or if it is a constituent page of a compound page. We need\nan atomic_inc_not_zero operation to ensure we don\u0027t try to grab the page\nin either case.\n\nThis patch introduces the core locking protocol to the pagecache (ie.\nadds page_cache_get_speculative, and tweaks some update-side code to make\nit work).\n\nThanks to Hugh for pointing out an improvement to the algorithm setting\npage_count to zero when we have control of all references, in order to\nhold off speculative getters.\n\n[kamezawa.hiroyu@jp.fujitsu.com: fix migration_entry_wait()]\n[hugh@veritas.com: fix add_to_page_cache]\n[akpm@linux-foundation.org: repair a comment]\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: Jeff Garzik \u003cjeff@garzik.org\u003e\nCc: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Hugh Dickins \u003chugh@veritas.com\u003e\nCc: \"Paul E. McKenney\" \u003cpaulmck@us.ibm.com\u003e\nReviewed-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nSigned-off-by: Daisuke Nishimura \u003cnishimura@mxp.nes.nec.co.jp\u003e\nSigned-off-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nSigned-off-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nSigned-off-by: Hugh Dickins \u003chugh@veritas.com\u003e\nAcked-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "69029cd550284e32de13d6dd2f77b723c8a0e444", "tree": "b57b87e5025b6c01722f39302cb98d0dfcd58940", "parents": [ "e8589cc189f96b87348ae83ea4db38eaac624135" ], "author": { "name": "KAMEZAWA Hiroyuki", "email": "kamezawa.hiroyu@jp.fujitsu.com", "time": "Fri Jul 25 01:47:14 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Jul 25 10:53:37 2008 -0700" }, "message": "memcg: remove refcnt from page_cgroup\n\nmemcg: performance improvements\n\nPatch Description\n 1/5 ... remove refcnt fron page_cgroup patch (shmem handling is fixed)\n 2/5 ... swapcache handling patch\n 3/5 ... add helper function for shmem\u0027s memory reclaim patch\n 4/5 ... optimize by likely/unlikely ppatch\n 5/5 ... remove redundunt check patch (shmem handling is fixed.)\n\nUnix bench result.\n\n\u003d\u003d 2.6.26-rc2-mm1 + memory resource controller\nExecl Throughput 2915.4 lps (29.6 secs, 3 samples)\nC Compiler Throughput 1019.3 lpm (60.0 secs, 3 samples)\nShell Scripts (1 concurrent) 5796.0 lpm (60.0 secs, 3 samples)\nShell Scripts (8 concurrent) 1097.7 lpm (60.0 secs, 3 samples)\nShell Scripts (16 concurrent) 565.3 lpm (60.0 secs, 3 samples)\nFile Read 1024 bufsize 2000 maxblocks 1022128.0 KBps (30.0 secs, 3 samples)\nFile Write 1024 bufsize 2000 maxblocks 544057.0 KBps (30.0 secs, 3 samples)\nFile Copy 1024 bufsize 2000 maxblocks 346481.0 KBps (30.0 secs, 3 samples)\nFile Read 256 bufsize 500 maxblocks 319325.0 KBps (30.0 secs, 3 samples)\nFile Write 256 bufsize 500 maxblocks 148788.0 KBps (30.0 secs, 3 samples)\nFile Copy 256 bufsize 500 maxblocks 99051.0 KBps (30.0 secs, 3 samples)\nFile Read 4096 bufsize 8000 maxblocks 2058917.0 KBps (30.0 secs, 3 samples)\nFile Write 4096 bufsize 8000 maxblocks 1606109.0 KBps (30.0 secs, 3 samples)\nFile Copy 4096 bufsize 8000 maxblocks 854789.0 KBps (30.0 secs, 3 samples)\nDc: sqrt(2) to 99 decimal places 126145.2 lpm (30.0 secs, 3 samples)\n\n INDEX VALUES\nTEST BASELINE RESULT INDEX\n\nExecl Throughput 43.0 2915.4 678.0\nFile Copy 1024 bufsize 2000 maxblocks 3960.0 346481.0 875.0\nFile Copy 256 bufsize 500 maxblocks 1655.0 99051.0 598.5\nFile Copy 4096 bufsize 8000 maxblocks 5800.0 854789.0 1473.8\nShell Scripts (8 concurrent) 6.0 1097.7 1829.5\n \u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\n FINAL SCORE 991.3\n\n\u003d\u003d 2.6.26-rc2-mm1 + this set \u003d\u003d\nExecl Throughput 3012.9 lps (29.9 secs, 3 samples)\nC Compiler Throughput 981.0 lpm (60.0 secs, 3 samples)\nShell Scripts (1 concurrent) 5872.0 lpm (60.0 secs, 3 samples)\nShell Scripts (8 concurrent) 1120.3 lpm (60.0 secs, 3 samples)\nShell Scripts (16 concurrent) 578.0 lpm (60.0 secs, 3 samples)\nFile Read 1024 bufsize 2000 maxblocks 1003993.0 KBps (30.0 secs, 3 samples)\nFile Write 1024 bufsize 2000 maxblocks 550452.0 KBps (30.0 secs, 3 samples)\nFile Copy 1024 bufsize 2000 maxblocks 347159.0 KBps (30.0 secs, 3 samples)\nFile Read 256 bufsize 500 maxblocks 314644.0 KBps (30.0 secs, 3 samples)\nFile Write 256 bufsize 500 maxblocks 151852.0 KBps (30.0 secs, 3 samples)\nFile Copy 256 bufsize 500 maxblocks 101000.0 KBps (30.0 secs, 3 samples)\nFile Read 4096 bufsize 8000 maxblocks 2033256.0 KBps (30.0 secs, 3 samples)\nFile Write 4096 bufsize 8000 maxblocks 1611814.0 KBps (30.0 secs, 3 samples)\nFile Copy 4096 bufsize 8000 maxblocks 847979.0 KBps (30.0 secs, 3 samples)\nDc: sqrt(2) to 99 decimal places 128148.7 lpm (30.0 secs, 3 samples)\n\n INDEX VALUES\nTEST BASELINE RESULT INDEX\n\nExecl Throughput 43.0 3012.9 700.7\nFile Copy 1024 bufsize 2000 maxblocks 3960.0 347159.0 876.7\nFile Copy 256 bufsize 500 maxblocks 1655.0 101000.0 610.3\nFile Copy 4096 bufsize 8000 maxblocks 5800.0 847979.0 1462.0\nShell Scripts (8 concurrent) 6.0 1120.3 1867.2\n \u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\n FINAL SCORE 1004.6\n\nThis patch:\n\nRemove refcnt from page_cgroup().\n\nAfter this,\n\n * A page is charged only when !page_mapped() \u0026\u0026 no page_cgroup is assigned.\n\t* Anon page is newly mapped.\n\t* File page is added to mapping-\u003etree.\n\n * A page is uncharged only when\n\t* Anon page is fully unmapped.\n\t* File page is removed from LRU.\n\nThere is no change in behavior from user\u0027s view.\n\nThis patch also removes unnecessary calls in rmap.c which was used only for\nrefcnt mangement.\n\n[akpm@linux-foundation.org: fix warning]\n[hugh@veritas.com: fix shmem_unuse_inode charging]\nSigned-off-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Balbir Singh \u003cbalbir@in.ibm.com\u003e\nCc: \"Eric W. Biederman\" \u003cebiederm@xmission.com\u003e\nCc: Pavel Emelyanov \u003cxemul@openvz.org\u003e\nCc: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nCc: Hugh Dickins \u003chugh@veritas.com\u003e\nCc: YAMAMOTO Takashi \u003cyamamoto@valinux.co.jp\u003e\nCc: Paul Menage \u003cmenage@google.com\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nSigned-off-by: Hugh Dickins \u003chugh@veritas.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "3f31fddfa26b7594b44ff2b34f9a04ba409e0f91", "tree": "88994baf22f65dc4da0bef17ce61eda09c59db2a", "parents": [ "9ebfbe9f926553eabc21b4400918d1216b27ed0c" ], "author": { "name": "Mingming Cao", "email": "cmm@us.ibm.com", "time": "Fri Jul 25 01:46:22 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Jul 25 10:53:32 2008 -0700" }, "message": "jbd: fix race between free buffer and commit transaction\n\njournal_try_to_free_buffers() could race with jbd commit transaction when\nthe later is holding the buffer reference while waiting for the data\nbuffer to flush to disk. If the caller of journal_try_to_free_buffers()\nrequest tries hard to release the buffers, it will treat the failure as\nerror and return back to the caller. We have seen the directo IO failed\ndue to this race. Some of the caller of releasepage() also expecting the\nbuffer to be dropped when passed with GFP_KERNEL mask to the\nreleasepage()-\u003ejournal_try_to_free_buffers().\n\nWith this patch, if the caller is passing the __GFP_WAIT and __GFP_FS to\nindicating this call could wait, in case of try_to_free_buffers() failed,\nlet\u0027s waiting for journal_commit_transaction() to finish commit the\ncurrent committing transaction, then try to free those buffers again.\n\n[akpm@linux-foundation.org: coding-style fixes]\nSigned-off-by: Mingming Cao \u003ccmm@us.ibm.com\u003e\nReviewed-by: Badari Pulavarty \u003cpbadari@us.ibm.com\u003e\nAcked-by: Jan Kara \u003cjack@suse.cz\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "11fa977ecde652ab324dd79c179deb52e82a8df1", "tree": "5842dab40a3754f3f34223b50f9dcfa5dd67dfa0", "parents": [ "a858f7b2e9bb4eb665176dde5cf32eeaaf90f153" ], "author": { "name": "Hugh Dickins", "email": "hugh@veritas.com", "time": "Wed Jul 23 21:27:34 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jul 24 10:47:16 2008 -0700" }, "message": "generic_file_aio_read() cleanups\n\nAs akpm points out, there\u0027s really no need for generic_file_aio_read to\nmake a special case of count 0: just loop through nr_segs doing nothing.\nAnd as Harvey Harrison points out, there\u0027s no need to reset retval to 0\nwhere it\u0027s already 0.\n\nSetting count (or ocount) to 0 before calling generic_segment_checks is\nunnecessary too; but reluctantly I\u0027ll leave that removal to someone with a\nwider range of gcc versions to hand - 4.1.2 and 4.2.1 don\u0027t warn about it,\nbut perhaps others do - I forget which are the warniest versions.\n\nSigned-off-by: Hugh Dickins \u003chugh@veritas.com\u003e\nTested-by: Lawrence Greenfield \u003cleg@google.com\u003e\nCc: Christoph Rohland \u003chans-christoph.rohland@sap.com\u003e\nCc: Badari Pulavarty \u003cpbadari@us.ibm.com\u003e\nCc: Zach Brown \u003czach.brown@oracle.com\u003e\nCc: Nick Piggin \u003cnickpiggin@yahoo.com.au\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "a969e903a944f69309ee5cc9e7c7b08310d1151e", "tree": "fa8a26a8e9b870b3c4f9a876070de03e4901c579", "parents": [ "75353bed36cfbbfb55bbde0896bbf5a02d9ba355" ], "author": { "name": "Christoph Hellwig", "email": "hch@lst.de", "time": "Wed Jul 23 21:27:04 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jul 24 10:47:14 2008 -0700" }, "message": "kill generic_file_direct_IO()\n\ngeneric_file_direct_IO is a common helper around the invocation of\n-\u003edirect_IO. But there\u0027s almost nothing shared between the read and write\nside, so we\u0027re better off without this helper.\n\n[akpm@linux-foundation.org: coding-style fixes]\nSigned-off-by: 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": "f4c0a0fdfae708f7aa438c27a380ed4071294e11", "tree": "f729aa07b21c0d40c3c2c254b1a99c5b5879b92a", "parents": [ "9ddfc3dc75b5cc55ff3cfa586e962d252f1db9d3" ], "author": { "name": "Jan Kara", "email": "jack@suse.cz", "time": "Fri Jul 11 19:27:31 2008 -0400" }, "committer": { "name": "Theodore Ts\u0027o", "email": "tytso@mit.edu", "time": "Fri Jul 11 19:27:31 2008 -0400" }, "message": "vfs: export filemap_fdatawrite_range()\n\nMake filemap_fdatawrite_range() function public, so that it can later\nbe used in ordered mode rewrite by JBD/JBD2.\n\nSigned-off-by: Jan Kara \u003cjack@suse.cz\u003e\n" }, { "commit": "3ef0f720e47e895b613b0305eb0a483e3ec11f23", "tree": "e696a950d76c90199661515e1068fc00102a15bf", "parents": [ "3b73a223661ed137c5d3d2635f954382e94f5a43" ], "author": { "name": "Miklos Szeredi", "email": "mszeredi@suse.cz", "time": "Wed May 14 16:05:37 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed May 14 19:11:13 2008 -0700" }, "message": "mm: fix infinite loop in filemap_fault\n\nfilemap_fault will go into an infinite loop if -\u003ereadpage() fails\nasynchronously.\n\nAFAICS the bug was introduced by this commit, which removed the wait after the\nfinal readpage:\n\n commit d00806b183152af6d24f46f0c33f14162ca1262a\n Author: Nick Piggin \u003cnpiggin@suse.de\u003e\n Date: Thu Jul 19 01:46:57 2007 -0700\n\n mm: fix fault vs invalidate race for linear mappings\n\nFix by reintroducing the wait_on_page_locked() after -\u003ereadpage() to make sure\nthe page is up-to-date before jumping back to the beginning of the function.\n\nI\u0027ve noticed this while testing nfs exporting on fuse. The patch\nfixes it.\n\nSigned-off-by: Miklos Szeredi \u003cmszeredi@suse.cz\u003e\nCc: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "7f3d4ee108c184ab215036051087aaaaa8de7661", "tree": "373f4f928f0687ca84478964b43c26e3ec9cec70", "parents": [ "07416d29bcf608257f1e5280642dcbe0021518a3" ], "author": { "name": "Miklos Szeredi", "email": "mszeredi@suse.cz", "time": "Wed May 07 09:22:39 2008 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Wed May 07 09:29:00 2008 +0200" }, "message": "vfs: splice remove_suid() cleanup\n\ngeneric_file_splice_write() duplicates remove_suid() just because it\ndoesn\u0027t hold i_mutex. But it grabs i_mutex inside splice_from_pipe()\nanyway, so this is rather pointless.\n\nMove locking to generic_file_splice_write() and call remove_suid() and\n__splice_from_pipe() instead.\n\nSigned-off-by: Miklos Szeredi \u003cmszeredi@suse.cz\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "ac6aadb24b7d4f0e54246732e221c102073412bf", "tree": "1936c3e847fca977b8c0d650416c66655f7633ad", "parents": [ "f05111f50105ac479a008cf85749cf9c956453ea" ], "author": { "name": "Miklos Szeredi", "email": "mszeredi@suse.cz", "time": "Mon Apr 28 02:12:38 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Apr 28 08:58:20 2008 -0700" }, "message": "mm: rotate_reclaimable_page() cleanup\n\nClean up messy conditional calling of test_clear_page_writeback() from both\nrotate_reclaimable_page() and end_page_writeback().\n\nThe only user of rotate_reclaimable_page() is end_page_writeback() so this is\nOK.\n\nSigned-off-by: Miklos Szeredi \u003cmszeredi@suse.cz\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "7682486b3ee06f800d5b11033371c7c5e92e3057", "tree": "d0c2eda3204b085fc63200c787b2cf04f0298729", "parents": [ "6cb2a21049b8990df4576c5fce4d48d0206c22d5" ], "author": { "name": "Randy Dunlap", "email": "randy.dunlap@oracle.com", "time": "Wed Mar 19 17:00:40 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Mar 19 18:53:35 2008 -0700" }, "message": "mm: fix various kernel-doc comments\n\nFix various kernel-doc notation in mm/:\n\nfilemap.c: add function short description; convert 2 to kernel-doc\nfremap.c: change parameter \u0027prot\u0027 to @prot\npagewalk.c: change \"-\" in function parameters to \":\"\nslab.c: fix short description of kmem_ptr_validate()\nswap.c: fix description \u0026 parameters of put_pages_list()\nswap_state.c: fix function parameters\nvmalloc.c: change \"@returns\" to \"Returns:\" since that is not a parameter\n\nSigned-off-by: Randy Dunlap \u003crandy.dunlap@oracle.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "f7009264c519603b8ec67c881bd368a56703cfc9", "tree": "163c2fa590e3de5c9084f1cba5c1c2815dbd2dde", "parents": [ "21bbb39c376ce6beeeb549d155f0d53dc76ed000" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Mon Mar 10 11:43:59 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Mon Mar 10 18:01:20 2008 -0700" }, "message": "iov_iter_advance() fix\n\niov_iter_advance() skips over zero-length iovecs, however it does not properly\nterminate at the end of the iovec array. Fix this by checking against\ni-\u003ecount before we skip a zero-length iov.\n\nThe bug was reproduced with a test program that continually randomly creates\niovs to writev. The fix was also verified with the same program and also it\ncould verify that the correct data was contained in the file after each\nwritev.\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nTested-by: \"Kevin Coffman\" \u003ckwc@citi.umich.edu\u003e\nCc: \"Alexey Dobriyan\" \u003cadobriyan@gmail.com\u003e\nCc: \u003cstable@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": "3426fadfa20454f124203768857e8f18ab4909bd", "tree": "2f65a70ca42a9f02a4e2eebc816300dbafe0d749", "parents": [ "bf5a25e1fff88a1066e20cc7263329405e4939f6" ], "author": { "name": "Jesper Juhl", "email": "jesper.juhl@gmail.com", "time": "Mon Mar 10 01:12:08 2008 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Sun Mar 09 22:21:52 2008 -0700" }, "message": "Do not include linux/backing-dev.h twice\n\nDon\u0027t include linux/backing-dev.h twice in mm/filemap.c, it\u0027s pointless.\n\nSigned-off-by: Jesper Juhl \u003cjesper.juhl@gmail.com\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "b5606c2d4447e80b1d72406af4e78af1eda611d4", "tree": "ebdaa1a0aae4279b84af82651c16a8777f76bfe4", "parents": [ "fbf6bfca76d50abef478ba902b8597ecbadfd390" ], "author": { "name": "Harvey Harrison", "email": "harvey.harrison@gmail.com", "time": "Wed Feb 13 15:03:16 2008 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Wed Feb 13 16:21:18 2008 -0800" }, "message": "remove final fastcall users\n\nfastcall always expands to empty, remove it.\n\nSigned-off-by: Harvey Harrison \u003charvey.harrison@gmail.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "36e789144267105e0b3f2b9bca7db3184fce50dc", "tree": "cff6b92b2d54cf5e88db3f0fd71071a6b80b06f5", "parents": [ "7437a51b30743ff1488981a393fc9e67894bf757" ], "author": { "name": "Christoph Hellwig", "email": "hch@lst.de", "time": "Fri Feb 08 04:21:24 2008 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Fri Feb 08 09:22:39 2008 -0800" }, "message": "kill do_generic_mapping_read\n\ndo_generic_mapping_read was used by gfs2 for internals reads, but this use\nof the interface was rather suboptimal (as was the whole interface) and has\nbeen replaced by an internal helper now. This patch kills\ndo_generic_mapping_read and surrounding damage in preparation of additional\ncleanups for the buffered read path.\n\nSigned-off-by: 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": "2004dc8eec1b4f0692b3be87ea80c70faa44d619", "tree": "9458abfdecf29c08a33cccb845eb273c70ad49c5", "parents": [ "476aed3870b26735c4fcfdaa95420fa9e1de5119" ], "author": { "name": "Jan Kara", "email": "jack@suse.cz", "time": "Fri Feb 08 04:20:11 2008 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Fri Feb 08 09:22:32 2008 -0800" }, "message": "Use pgoff_t instead of unsigned long\n\nConvert variables containing page indexes to pgoff_t.\n\nSigned-off-by: Jan Kara \u003cjack@suse.cz\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "4c6bc8dd5a0932f2c0b30a5f0a124464b7f614d0", "tree": "90fda3b23ed1adb780ef063df4559ca929e6378a", "parents": [ "35c754d79f4da80d5e8972f6403dd26f7962fd88" ], "author": { "name": "Badari Pulavarty", "email": "pbadari@gmail.com", "time": "Thu Feb 07 00:14:05 2008 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Thu Feb 07 08:42:19 2008 -0800" }, "message": "mem-controller gfp-mask fix\n\nNeed to strip __GFP_HIGHMEM flag while passing to mem_container_cache_charge().\n\nSigned-off-by: Badari Pulavarty \u003cpbadari@us.ibm.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "35c754d79f4da80d5e8972f6403dd26f7962fd88", "tree": "5e497fd0ac832b5c832044d0267170d7144e1a0e", "parents": [ "044d66c1d2b1c5aa50b4d6d68c21c6c93dd678da" ], "author": { "name": "Balbir Singh", "email": "balbir@linux.vnet.ibm.com", "time": "Thu Feb 07 00:14:05 2008 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Thu Feb 07 08:42:19 2008 -0800" }, "message": "memory controller BUG_ON()\n\nMove mem_controller_cache_charge() above radix_tree_preload().\nradix_tree_preload() disables preemption, even though the gfp_mask passed\ncontains __GFP_WAIT, we cannot really do __GFP_WAIT allocations, thus we\nhit a BUG_ON() in kmem_cache_alloc().\n\nThis patch moves mem_controller_cache_charge() to above radix_tree_preload()\nfor cache charging.\n\nSigned-off-by: Balbir Singh \u003cbalbir@linux.vnet.ibm.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "e1a1cd590e3fcb0d2e230128daf2337ea55387dc", "tree": "eb660ab340c657a1eb595b2d4d8e8b62783bf6fb", "parents": [ "bed7161a519a2faef53e1bce1b47595e297c1d14" ], "author": { "name": "Balbir Singh", "email": "balbir@linux.vnet.ibm.com", "time": "Thu Feb 07 00:14:02 2008 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Thu Feb 07 08:42:19 2008 -0800" }, "message": "Memory controller: make charging gfp mask aware\n\nNick Piggin pointed out that swap cache and page cache addition routines\ncould be called from non GFP_KERNEL contexts. This patch makes the\ncharging routine aware of the gfp context. Charging might fail if the\ncgroup is over it\u0027s limit, in which case a suitable error is returned.\n\nThis patch was tested on a Powerpc box. I am still looking at being able\nto test the path, through which allocations happen in non GFP_KERNEL\ncontexts.\n\n[kamezawa.hiroyu@jp.fujitsu.com: problem with ZONE_MOVABLE]\nSigned-off-by: Balbir Singh \u003cbalbir@linux.vnet.ibm.com\u003e\nCc: Pavel Emelianov \u003cxemul@openvz.org\u003e\nCc: Paul Menage \u003cmenage@google.com\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: \"Eric W. Biederman\" \u003cebiederm@xmission.com\u003e\nCc: Nick Piggin \u003cnickpiggin@yahoo.com.au\u003e\nCc: Kirill Korotaev \u003cdev@sw.ru\u003e\nCc: Herbert Poetzl \u003cherbert@13thfloor.at\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nCc: Vaidyanathan Srinivasan \u003csvaidy@linux.vnet.ibm.com\u003e\nSigned-off-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "8697d33194faae6fdd6b2e799f6308aa00cfdf67", "tree": "edf6b3e4698b80aac6f1d1f2b9e5698ce8dfa6e5", "parents": [ "c7ba5c9e8176704bfac0729875fa62798037584d" ], "author": { "name": "Balbir Singh", "email": "balbir@linux.vnet.ibm.com", "time": "Thu Feb 07 00:13:59 2008 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Thu Feb 07 08:42:19 2008 -0800" }, "message": "Memory controller: add switch to control what type of pages to limit\n\nChoose if we want cached pages to be accounted or not. By default both are\naccounted for. A new set of tunables are added.\n\necho -n 1 \u003e mem_control_type\n\nswitches the accounting to account for only mapped pages\n\necho -n 3 \u003e mem_control_type\n\nswitches the behaviour back\n\n[bunk@kernel.org: mm/memcontrol.c: clenups]\n[akpm@linux-foundation.org: fix sparc32 build]\nSigned-off-by: Balbir Singh \u003cbalbir@linux.vnet.ibm.com\u003e\nCc: Pavel Emelianov \u003cxemul@openvz.org\u003e\nCc: Paul Menage \u003cmenage@google.com\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: \"Eric W. Biederman\" \u003cebiederm@xmission.com\u003e\nCc: Nick Piggin \u003cnickpiggin@yahoo.com.au\u003e\nCc: Kirill Korotaev \u003cdev@sw.ru\u003e\nCc: Herbert Poetzl \u003cherbert@13thfloor.at\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nCc: Vaidyanathan Srinivasan \u003csvaidy@linux.vnet.ibm.com\u003e\nSigned-off-by: Adrian Bunk \u003cbunk@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": "8a9f3ccd24741b50200c3f33d62534c7271f3dfc", "tree": "066aabd8d2952299501f067a91cbfd6f47ee62f6", "parents": [ "78fb74669e80883323391090e4d26d17fe29488f" ], "author": { "name": "Balbir Singh", "email": "balbir@linux.vnet.ibm.com", "time": "Thu Feb 07 00:13:53 2008 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Thu Feb 07 08:42:18 2008 -0800" }, "message": "Memory controller: memory accounting\n\nAdd the accounting hooks. The accounting is carried out for RSS and Page\nCache (unmapped) pages. There is now a common limit and accounting for both.\nThe RSS accounting is accounted at page_add_*_rmap() and page_remove_rmap()\ntime. Page cache is accounted at add_to_page_cache(),\n__delete_from_page_cache(). Swap cache is also accounted for.\n\nEach page\u0027s page_cgroup is protected with the last bit of the\npage_cgroup pointer, this makes handling of race conditions involving\nsimultaneous mappings of a page easier. A reference count is kept in the\npage_cgroup to deal with cases where a page might be unmapped from the RSS\nof all tasks, but still lives in the page cache.\n\nCredits go to Vaidyanathan Srinivasan for helping with reference counting work\nof the page cgroup. Almost all of the page cache accounting code has help\nfrom Vaidyanathan Srinivasan.\n\n[hugh@veritas.com: fix swapoff breakage]\n[akpm@linux-foundation.org: fix locking]\nSigned-off-by: Vaidyanathan Srinivasan \u003csvaidy@linux.vnet.ibm.com\u003e\nSigned-off-by: Balbir Singh \u003cbalbir@linux.vnet.ibm.com\u003e\nCc: Pavel Emelianov \u003cxemul@openvz.org\u003e\nCc: Paul Menage \u003cmenage@google.com\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: \"Eric W. Biederman\" \u003cebiederm@xmission.com\u003e\nCc: Nick Piggin \u003cnickpiggin@yahoo.com.au\u003e\nCc: Kirill Korotaev \u003cdev@sw.ru\u003e\nCc: Herbert Poetzl \u003cherbert@13thfloor.at\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nCc: \u003cValdis.Kletnieks@vt.edu\u003e\nSigned-off-by: Hugh Dickins \u003chugh@veritas.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "920c7a5d0c94b8ce740f1d76fa06422f2a95a757", "tree": "74ab4b9b5a6f4279b9b9d2a463c6700546ba0011", "parents": [ "1e548deb5d1630ca14ba04da04e3b6b3766178c7" ], "author": { "name": "Harvey Harrison", "email": "harvey.harrison@gmail.com", "time": "Mon Feb 04 22:29:26 2008 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Feb 05 09:44:18 2008 -0800" }, "message": "mm: remove fastcall from mm/\n\nfastcall is always defined to be empty, remove it\n\n[akpm@linux-foundation.org: coding-style fixes]\nSigned-off-by: Harvey Harrison \u003charvey.harrison@gmail.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "e2848a0efedef4dad52d1334d37f8719cd6268fd", "tree": "f5d2b600b1275793e7c490f34ae9ec902af138b5", "parents": [ "e31d9eb5c17ae3b80f9e9403f8a5eaf6dba879c9" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Mon Feb 04 22:29:10 2008 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Feb 05 09:44:17 2008 -0800" }, "message": "radix-tree: avoid atomic allocations for preloaded insertions\n\nMost pagecache (and some other) radix tree insertions have the great\nopportunity to preallocate a few nodes with relaxed gfp flags. But the\npreallocation is squandered when it comes time to allocate a node, we\ndefault to first attempting a GFP_ATOMIC allocation -- that doesn\u0027t\nnormally fail, but it can eat into atomic memory reserves that we don\u0027t\nneed to be using.\n\nAnother upshot of this is that it removes the sometimes highly contended\nzone-\u003elock from underneath tree_lock. Pagecache insertions are always\nperformed with a radix tree preload, and after this change, such a\nsituation will never fall back to kmem_cache_alloc within\nradix_tree_node_alloc.\n\nDavid Miller reports seeing this allocation fail on a highly threaded\nsparc64 system:\n\n[527319.459981] dd: page allocation failure. order:0, mode:0x20\n[527319.460403] Call Trace:\n[527319.460568] [00000000004b71e0] __slab_alloc+0x1b0/0x6a8\n[527319.460636] [00000000004b7bbc] kmem_cache_alloc+0x4c/0xa8\n[527319.460698] [000000000055309c] radix_tree_node_alloc+0x20/0x90\n[527319.460763] [0000000000553238] radix_tree_insert+0x12c/0x260\n[527319.460830] [0000000000495cd0] add_to_page_cache+0x38/0xb0\n[527319.460893] [00000000004e4794] mpage_readpages+0x6c/0x134\n[527319.460955] [000000000049c7fc] __do_page_cache_readahead+0x170/0x280\n[527319.461028] [000000000049cc88] ondemand_readahead+0x208/0x214\n[527319.461094] [0000000000496018] do_generic_mapping_read+0xe8/0x428\n[527319.461152] [0000000000497948] generic_file_aio_read+0x108/0x170\n[527319.461217] [00000000004badac] do_sync_read+0x88/0xd0\n[527319.461292] [00000000004bb5cc] vfs_read+0x78/0x10c\n[527319.461361] [00000000004bb920] sys_read+0x34/0x60\n[527319.461424] [0000000000406294] linux_sparc_syscall32+0x3c/0x40\n\nThe calltrace is significant: __do_page_cache_readahead allocates a number\nof pages with GFP_KERNEL, and hence it should have reclaimed sufficient\nmemory to satisfy GFP_ATOMIC allocations. However after the list of pages\ngoes to mpage_readpages, there can be significant intervals (including disk\nIO) before all the pages are inserted into the radix-tree. So the reserves\ncan easily be depleted at that point. The patch is confirmed to fix the\nproblem.\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: \"David S. Miller\" \u003cdavem@davemloft.net\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "124d3b7041f9a0ca7c43a6293e1cae4576c32fd5", "tree": "9b92dd8f99c10ae0a0931ce71f3e9a20b32b167b", "parents": [ "6598b60fd56ba5e915a001cc4e307880a94d19ae" ], "author": { "name": "Nick Piggin", "email": "nickpiggin@yahoo.com.au", "time": "Sat Feb 02 15:01:17 2008 +0100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sun Feb 03 07:55:39 2008 +1100" }, "message": "fix writev regression: pan hanging unkillable and un-straceable\n\nFrederik Himpe reported an unkillable and un-straceable pan process.\n\nZero length iovecs can go into an infinite loop in writev, because the\niovec iterator does not always advance over them.\n\nThe sequence required to trigger this is not trivial. I think it\nrequires that a zero-length iovec be followed by a non-zero-length iovec\nwhich causes a pagefault in the atomic usercopy. This causes the writev\ncode to drop back into single-segment copy mode, which then tries to\ncopy the 0 bytes of the zero-length iovec; a zero length copy looks like\na failure though, so it loops.\n\nPut a test into iov_iter_advance to catch zero-length iovecs. We could\njust put the test in the fallback path, but I feel it is more robust to\nskip over zero-length iovecs throughout the code (iovec iterator may be\nused in filesystems too, so it should be robust).\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "75659ca0c10992dcb39258518368a0f6f56e935d", "tree": "5d014ceb2f10158061a23d0d976f9a613d85e659", "parents": [ "fbdde7bd274d74729954190f99afcb1e3d9bbfba", "2dfe485a2c8afa54cb069fcf48476f6c90ea3fdf" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Feb 01 11:45:47 2008 +1100" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Feb 01 11:45:47 2008 +1100" }, "message": "Merge branch \u0027task_killable\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/willy/misc\n\n* \u0027task_killable\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/willy/misc: (22 commits)\n Remove commented-out code copied from NFS\n NFS: Switch from intr mount option to TASK_KILLABLE\n Add wait_for_completion_killable\n Add wait_event_killable\n Add schedule_timeout_killable\n Use mutex_lock_killable in vfs_readdir\n Add mutex_lock_killable\n Use lock_page_killable\n Add lock_page_killable\n Add fatal_signal_pending\n Add TASK_WAKEKILL\n exit: Use task_is_*\n signal: Use task_is_*\n sched: Use task_contributes_to_load, TASK_ALL and TASK_NORMAL\n ptrace: Use task_is_*\n power: Use task_is_*\n wait: Use TASK_NORMAL\n proc/base.c: Use task_is_*\n proc/array.c: Use TASK_REPORT\n perfmon: Use task_is_*\n ...\n\nFixed up conflicts in NFS/sunrpc manually..\n" }, { "commit": "3a6927906f1b2adf5a31b789322d32eb8559ada0", "tree": "ef5b9dce5fd1b27be027fcff0a749547e9319ff0", "parents": [ "3e3b3916a9c5c28a16528585478de19fea59816b" ], "author": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Wed Dec 19 14:05:13 2007 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Wed Dec 19 14:05:13 2007 -0800" }, "message": "Do dirty page accounting when removing a page from the page cache\n\nKrzysztof Oledzki noticed a dirty page accounting leak on some of his\nmachines, causing the machine to eventually lock up when the kernel\ndecided that there was too much dirty data, but nobody could actually\nwrite anything out to fix it.\n\nThe culprit turns out to be filesystems (cough ext3 with data\u003djournal\ncough) that re-dirty the page when the \"-\u003einvalidatepage()\" callback is\ncalled.\n\nFix it up by doing a final dirty page accounting check when we actually\nremove the page from the page cache.\n\nThis fixes bugzilla entry 9182:\n\n\thttp://bugzilla.kernel.org/show_bug.cgi?id\u003d9182\n\nTested-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nTested-by: Krzysztof Oledzki \u003colel@ans.pl\u003e\nCc: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nCc: Nick Piggin \u003cnickpiggin@yahoo.com.au\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "0b94e97a25d9b06ef17fca8da23169200bead1e2", "tree": "4f7d920d03e9532d93921831efe704a4b645a3b4", "parents": [ "2687a3569e40b1302f96698bcd6329aeb0ce3dd2" ], "author": { "name": "Matthew Wilcox", "email": "matthew@wil.cx", "time": "Thu Dec 06 11:19:57 2007 -0500" }, "committer": { "name": "Matthew Wilcox", "email": "willy@linux.intel.com", "time": "Thu Dec 06 17:35:48 2007 -0500" }, "message": "Use lock_page_killable\n\nReplacing lock_page with lock_page_killable in do_generic_mapping_read()\nallows us to kill `cat\u0027 of a file on an NFS-mounted filesystem\n\nSigned-off-by: Matthew Wilcox \u003cwilly@linux.intel.com\u003e\n" }, { "commit": "2687a3569e40b1302f96698bcd6329aeb0ce3dd2", "tree": "7bb5e1ffd807ef94b145f6829bf4326a98b8fd99", "parents": [ "f776d12dd16da1b0cd55a1240002c1b31f315d5d" ], "author": { "name": "Matthew Wilcox", "email": "matthew@wil.cx", "time": "Thu Dec 06 11:18:49 2007 -0500" }, "committer": { "name": "Matthew Wilcox", "email": "willy@linux.intel.com", "time": "Thu Dec 06 17:35:41 2007 -0500" }, "message": "Add lock_page_killable\n\nThis routine is like lock_page, but can be interrupted by a fatal signal\n\nSigned-off-by: Matthew Wilcox \u003cwilly@linux.intel.com\u003e\n" }, { "commit": "5307cc1aa53850f017c8053db034cf950b670ac9", "tree": "6fd2ff3fe382ba1aac5e8b6c703268200a80ed40", "parents": [ "bb374b7b938f73666c403b201b3dd48ec9fe118a" ], "author": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Wed Oct 31 09:19:46 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Wed Oct 31 09:19:46 2007 -0700" }, "message": "Remove broken ptrace() special-case code from file mapping\n\nThe kernel has for random historical reasons allowed ptrace() accesses\nto access (and insert) pages into the page cache above the size of the\nfile.\n\nHowever, Nick broke that by mistake when doing the new fault handling in\ncommit 54cb8821de07f2ffcd28c380ce9b93d5784b40d7 (\"mm: merge populate and\nnopage into fault (fixes nonlinear)\". The breakage caused a hang with\ngdb when trying to access the invalid page.\n\nThe ptrace \"feature\" really isn\u0027t worth resurrecting, since it really is\nwrong both from a portability _and_ from an internal page cache validity\nstandpoint. So this removes those old broken remnants, and fixes the\nptrace() hang in the process.\n\nNoticed and bisected by Duane Griffin, who also supplied a test-case\n(quoth Nick: \"Well that\u0027s probably the best bug report I\u0027ve ever had,\nthanks Duane!\").\n\nCc: Duane Griffin \u003cduaneg@dghda.com\u003e\nAcked-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "bdb76ef5a4bc8676a81034a443f1eda450b4babb", "tree": "b4ec8736e6d4bed26f96c94d5c7c8eec0896fcd0", "parents": [ "e58b7dab272ecee09cd7bafb89d6b224cd17bbe3" ], "author": { "name": "Zach Brown", "email": "zach.brown@oracle.com", "time": "Tue Oct 30 11:45:46 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 30 12:14:06 2007 -0700" }, "message": "dio: fix cache invalidation after sync writes\n\nCommit commit 65b8291c4000e5f38fc94fb2ca0cb7e8683c8a1b (\"dio: invalidate\nclean pages before dio write\") introduced a bug which stopped dio from\never invalidating the page cache after writes. It still invalidated it\nbefore writes so most users were fine.\n\nKarl Schendel reported ( http://lkml.org/lkml/2007/10/26/481 ) hitting\nthis bug when he had a buffered reader immediately reading file data\nafter an O_DIRECT wirter had written the data. The kernel issued\nread-ahead beyond the position of the reader which overlapped with the\nO_DIRECT writer. The failure to invalidate after writes caused the\nreader to see stale data from the read-ahead.\n\nThe following patch is originally from Karl. The following commentary\nis his:\n\n\tThe below 3rd try takes on your suggestion of just invalidating\n\tno matter what the retval from the direct_IO call. I ran it\n\tthru the test-case several times and it has worked every time.\n\tThe post-invalidate is probably still too early for async-directio,\n\tbut I don\u0027t have a testcase for that; just sync. And, this\n\twon\u0027t be any worse in the async case.\n\nI added a test to the aio-dio-regress repository which mimics Karl\u0027s IO\npattern. It verifed the bad behaviour and that the patch fixed it. I\nagree with Karl, this still doesn\u0027t help the case where a buffered\nreader follows an AIO O_DIRECT writer. That will require a bit more\nwork.\n\nThis gives up on the idea of returning EIO to indicate to userspace that\nstale data remains if the invalidation failed.\n\nSigned-off-by: Zach Brown \u003czach.brown@oracle.com\u003e\nCc: Karl Schendel \u003ckschendel@datallegro.com\u003e\nCc: Benjamin LaHaise \u003cbcrl@kvack.org\u003e\nCc: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nCc: Nick Piggin \u003cnickpiggin@yahoo.com.au\u003e\nCc: Leonid Ananiev \u003cleonid.i.ananiev@linux.intel.com\u003e\nCc: Chris Mason \u003cchris.mason@oracle.com\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "3a424f2d56613acfb9e583ec9c85a2be3e3af028", "tree": "6d01585f65282ed99e422345946c2692f19d96f4", "parents": [ "adb4ddbbfb90c302e78da68b3f015588ca45d7f3" ], "author": { "name": "Emil Medve", "email": "Emilian.Medve@Freescale.com", "time": "Wed Oct 24 14:18:32 2007 +0200" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Mon Oct 29 11:33:06 2007 +0100" }, "message": "Fix a build error when BLOCK\u003dn\n\nmm/filemap.c: In function \u0027__filemap_fdatawrite_range\u0027:\nmm/filemap.c:200: error: implicit declaration of function\n\u0027mapping_cap_writeback_dirty\u0027\n\nThis happens when we don\u0027t use/have any block devices and a NFS root\nfilesystem is used.\n\nmapping_cap_writeback_dirty() is defined in linux/backing-dev.h which\nused to be provided in mm/filemap.c by linux/blkdev.h until commit\nf5ff8422bbdd59f8c1f699df248e1b7a11073027 (Fix warnings with\n!CONFIG_BLOCK).\n\nSigned-off-by: Emil Medve \u003cEmilian.Medve@Freescale.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "8f731f7d83d6c6a3eeb32cce79bfcddbf7fac8cc", "tree": "706de5d8801259311a7a3b3987bc3b6e6511637d", "parents": [ "cb680c1be62e9898fc2ca2a89d9fdba7c84a5c81" ], "author": { "name": "Randy Dunlap", "email": "randy.dunlap@oracle.com", "time": "Thu Oct 18 23:39:28 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Fri Oct 19 11:53:35 2007 -0700" }, "message": "kernel-api docbook: fix content problems\n\nFix kernel-api docbook contents problems.\n\ndocproc: linux-2.6.23-git13/include/asm-x86/unaligned_32.h: No such file or directory\nWarning(linux-2.6.23-git13//include/linux/list.h:482): bad line: \t\t\tof list entry\nWarning(linux-2.6.23-git13//mm/filemap.c:864): No description found for parameter \u0027ra\u0027\nWarning(linux-2.6.23-git13//block/ll_rw_blk.c:3760): No description found for parameter \u0027req\u0027\nWarning(linux-2.6.23-git13//include/linux/input.h:1077): No description found for parameter \u0027private\u0027\nWarning(linux-2.6.23-git13//include/linux/input.h:1077): No description found for parameter \u0027cdev\u0027\n\nSigned-off-by: Randy Dunlap \u003crandy.dunlap@oracle.com\u003e\nCc: Jens Axboe \u003cjens.axboe@oracle.com\u003e\nCc: WU Fengguang \u003cwfg@mail.ustc.edu.cn\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" } ], "next": "53253383fde9e41bc07ad4d99f1c8b537fef71d6" }