)]}' { "log": [ { "commit": "ffd386a9a8273dcfa61705d0b349eebc7525ef87", "tree": "3a555f07c0df5b21eb2ee49fe57f71a76d0342f7", "parents": [ "03da30986793385af57eeca3296253c887b742e6", "099a19d91ca429944743d51bef8fee240e94d8e3" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Aug 04 15:17:52 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Aug 04 15:17:52 2010 -0700" }, "message": "Merge branch \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu\n\n* \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu:\n percpu: allow limited allocation before slab is online\n percpu: make @dyn_size always mean min dyn_size in first chunk init functions\n" }, { "commit": "5e83f6fbdb020b70c0e413312801424d13c58d68", "tree": "ca270178fa891813dbc47751c331fed975d3766c", "parents": [ "fe445c6e2cb62a566e1a89f8798de11459975710", "3444d7da1839b851eefedd372978d8a982316c36" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Aug 04 10:43:01 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Aug 04 10:43:01 2010 -0700" }, "message": "Merge branch \u0027kvm-updates/2.6.36\u0027 of git://git.kernel.org/pub/scm/virt/kvm/kvm\n\n* \u0027kvm-updates/2.6.36\u0027 of git://git.kernel.org/pub/scm/virt/kvm/kvm: (198 commits)\n KVM: VMX: Fix host GDT.LIMIT corruption\n KVM: MMU: using __xchg_spte more smarter\n KVM: MMU: cleanup spte set and accssed/dirty tracking\n KVM: MMU: don\u0027t atomicly set spte if it\u0027s not present\n KVM: MMU: fix page dirty tracking lost while sync page\n KVM: MMU: fix broken page accessed tracking with ept enabled\n KVM: MMU: add missing reserved bits check in speculative path\n KVM: MMU: fix mmu notifier invalidate handler for huge spte\n KVM: x86 emulator: fix xchg instruction emulation\n KVM: x86: Call mask notifiers from pic\n KVM: x86: never re-execute instruction with enabled tdp\n KVM: Document KVM_GET_SUPPORTED_CPUID2 ioctl\n KVM: x86: emulator: inc/dec can have lock prefix\n KVM: MMU: Eliminate redundant temporaries in FNAME(fetch)\n KVM: MMU: Validate all gptes during fetch, not just those used for new pages\n KVM: MMU: Simplify spte fetch() function\n KVM: MMU: Add gpte_valid() helper\n KVM: MMU: Add validate_direct_spte() helper\n KVM: MMU: Add drop_large_spte() helper\n KVM: MMU: Use __set_spte to link shadow pages\n ...\n" }, { "commit": "bbeb34062fbad287c949a945a516a0c15b179993", "tree": "cf29b50e076ba1ddc07d5b1292f243653a2f67a9", "parents": [ "6c3f6041172b78d5532c6bf3680d304e92ec2e66" ], "author": { "name": "Huang Ying", "email": "ying.huang@intel.com", "time": "Tue Jun 22 14:23:11 2010 +0800" }, "committer": { "name": "Avi Kivity", "email": "avi@redhat.com", "time": "Sun Aug 01 10:47:11 2010 +0300" }, "message": "KVM: Fix a race condition for usage of is_hwpoison_address()\n\nis_hwpoison_address accesses the page table, so the caller must hold\ncurrent-\u003emm-\u003emmap_sem in read mode. So fix its usage in hva_to_pfn of\nkvm accordingly.\n\nComment is_hwpoison_address to remind other users.\n\nReported-by: Avi Kivity \u003cavi@redhat.com\u003e\nSigned-off-by: Huang Ying \u003cying.huang@intel.com\u003e\nSigned-off-by: Avi Kivity \u003cavi@redhat.com\u003e\n" }, { "commit": "bf998156d24bcb127318ad5bf531ac3bdfcd6449", "tree": "616c19474d7cb626ff9eebc54f6753563a4322cd", "parents": [ "540ad6b62b3a188a53b51cac81d8a60d40e29fbd" ], "author": { "name": "Huang Ying", "email": "ying.huang@intel.com", "time": "Mon May 31 14:28:19 2010 +0800" }, "committer": { "name": "Avi Kivity", "email": "avi@redhat.com", "time": "Sun Aug 01 10:35:26 2010 +0300" }, "message": "KVM: Avoid killing userspace through guest SRAO MCE on unmapped pages\n\nIn common cases, guest SRAO MCE will cause corresponding poisoned page\nbe un-mapped and SIGBUS be sent to QEMU-KVM, then QEMU-KVM will relay\nthe MCE to guest OS.\n\nBut it is reported that if the poisoned page is accessed in guest\nafter unmapping and before MCE is relayed to guest OS, userspace will\nbe killed.\n\nThe reason is as follows. Because poisoned page has been un-mapped,\nguest access will cause guest exit and kvm_mmu_page_fault will be\ncalled. kvm_mmu_page_fault can not get the poisoned page for fault\naddress, so kernel and user space MMIO processing is tried in turn. In\nuser MMIO processing, poisoned page is accessed again, then userspace\nis killed by force_sig_info.\n\nTo fix the bug, kvm_mmu_page_fault send HWPOISON signal to QEMU-KVM\nand do not try kernel and user space MMIO processing for poisoned\npage.\n\n[xiao: fix warning introduced by avi]\n\nReported-by: Max Asbock \u003cmasbock@linux.vnet.ibm.com\u003e\nSigned-off-by: Huang Ying \u003cying.huang@intel.com\u003e\nSigned-off-by: Xiao Guangrong \u003cxiaoguangrong@cn.fujitsu.com\u003e\nSigned-off-by: Marcelo Tosatti \u003cmtosatti@redhat.com\u003e\nSigned-off-by: Avi Kivity \u003cavi@redhat.com\u003e\n" }, { "commit": "de51257aa301652876ab6e8f13ea4eadbe4a3846", "tree": "388ee39bed1d7e362438d047b57399a28e2617f8", "parents": [ "51c20fcced5badee0e2021c6c89f44aa3cbd72aa" ], "author": { "name": "Hugh Dickins", "email": "hughd@google.com", "time": "Fri Jul 30 10:58:26 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Jul 30 18:56:09 2010 -0700" }, "message": "mm: fix ia64 crash when gcore reads gate area\n\nDebian\u0027s ia64 autobuilders have been seeing kernel freeze or reboot\nwhen running the gdb testsuite (Debian bug 588574): dannf bisected to\n2.6.32 62eede62dafb4a6633eae7ffbeb34c60dba5e7b1 \"mm: ZERO_PAGE without\nPTE_SPECIAL\"; and reproduced it with gdb\u0027s gcore on a simple target.\n\nI\u0027d missed updating the gate_vma handling in __get_user_pages(): that\nhappens to use vm_normal_page() (nowadays failing on the zero page),\nyet reported success even when it failed to get a page - boom when\naccess_process_vm() tried to copy that to its intermediate buffer.\n\nFix this, resisting cleanups: in particular, leave it for now reporting\nsuccess when not asked to get any pages - very probably safe to change,\nbut let\u0027s not risk it without testing exposure.\n\nWhy did ia64 crash with 16kB pages, but succeed with 64kB pages?\nBecause setup_gate() pads each 64kB of its gate area with zero pages.\n\nReported-by: Andreas Barth \u003caba@not.so.argh.org\u003e\nBisected-by: dann frazier \u003cdannf@debian.org\u003e\nSigned-off-by: Hugh Dickins \u003chughd@google.com\u003e\nTested-by: dann frazier \u003cdannf@dannf.org\u003e\nCc: stable@kernel.org\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "b8ab9f82025adea77864115da73e70026fa4f540", "tree": "37d83932b99efd4aac2fccb2075a76bf0a147769", "parents": [ "9aebbdb637a73a6092e1456ebb4a2df32cc1f611" ], "author": { "name": "Yinghai Lu", "email": "yinghai@kernel.org", "time": "Tue Jul 20 13:24:31 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Jul 20 16:25:40 2010 -0700" }, "message": "x86,nobootmem: make alloc_bootmem_node fall back to other node when 32bit numa is used\n\nBorislav Petkov reported his 32bit numa system has problem:\n\n[ 0.000000] Reserving total of 4c00 pages for numa KVA remap\n[ 0.000000] kva_start_pfn ~ 32800 max_low_pfn ~ 375fe\n[ 0.000000] max_pfn \u003d 238000\n[ 0.000000] 8202MB HIGHMEM available.\n[ 0.000000] 885MB LOWMEM available.\n[ 0.000000] mapped low ram: 0 - 375fe000\n[ 0.000000] low ram: 0 - 375fe000\n[ 0.000000] alloc (nid\u003d8 100000 - 7ee00000) (1000000 - ffffffff) 1000 1000 \u003d\u003e 34e7000\n[ 0.000000] alloc (nid\u003d8 100000 - 7ee00000) (1000000 - ffffffff) 200 40 \u003d\u003e 34c9d80\n[ 0.000000] alloc (nid\u003d0 100000 - 7ee00000) (1000000 - ffffffffffffffff) 180 40 \u003d\u003e 34e6140\n[ 0.000000] alloc (nid\u003d1 80000000 - c7e60000) (1000000 - ffffffffffffffff) 240 40 \u003d\u003e 80000000\n[ 0.000000] BUG: unable to handle kernel paging request at 40000000\n[ 0.000000] IP: [\u003cc2c8cff1\u003e] __alloc_memory_core_early+0x147/0x1d6\n[ 0.000000] *pdpt \u003d 0000000000000000 *pde \u003d f000ff53f000ff00\n...\n[ 0.000000] Call Trace:\n[ 0.000000] [\u003cc2c8b4f8\u003e] ? __alloc_bootmem_node+0x216/0x22f\n[ 0.000000] [\u003cc2c90c9b\u003e] ? sparse_early_usemaps_alloc_node+0x5a/0x10b\n[ 0.000000] [\u003cc2c9149e\u003e] ? sparse_init+0x1dc/0x499\n[ 0.000000] [\u003cc2c79118\u003e] ? paging_init+0x168/0x1df\n[ 0.000000] [\u003cc2c780ff\u003e] ? native_pagetable_setup_start+0xef/0x1bb\n\nlooks like it allocates too much high address for bootmem.\n\nTry to cut limit with get_max_mapped()\n\nReported-by: Borislav Petkov \u003cborislav.petkov@amd.com\u003e\nTested-by: Conny Seidel \u003cconny.seidel@amd.com\u003e\nSigned-off-by: Yinghai Lu \u003cyinghai@kernel.org\u003e\nCc: \u003cstable@kernel.org\u003e\t\t[2.6.34.x]\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: \"H. Peter Anvin\" \u003chpa@zytor.com\u003e\nCc: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nCc: Johannes Weiner \u003channes@cmpxchg.org\u003e\nCc: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "a6aa62a0909b9ccb1f8b0d2653920ba071037972", "tree": "2df66e9a20cdb8fac10a1979c6b678e98ee67f0a", "parents": [ "c61284e99191b2284fb74dae6961d4d09e4e59e8" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Tue Jul 20 13:24:25 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Jul 20 16:25:40 2010 -0700" }, "message": "mm/vmscan.c: fix mapping use after free\n\nWe need lock_page_nosync() here because we have no reference to the\nmapping when taking the page lock.\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nReviewed-by: Johannes Weiner \u003channes@cmpxchg.org\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "7f8275d0d660c146de6ee3017e1e2e594c49e820", "tree": "884db927118b44102750b5168ee36ef4b8b5cb4e", "parents": [ "d0c6f6258478e1dba532bf7c28e2cd6e1047d3a4" ], "author": { "name": "Dave Chinner", "email": "dchinner@redhat.com", "time": "Mon Jul 19 14:56:17 2010 +1000" }, "committer": { "name": "Dave Chinner", "email": "david@fromorbit.com", "time": "Mon Jul 19 14:56:17 2010 +1000" }, "message": "mm: add context argument to shrinker callback\n\nThe current shrinker implementation requires the registered callback\nto have global state to work from. This makes it difficult to shrink\ncaches that are not global (e.g. per-filesystem caches). Pass the shrinker\nstructure to the callback so that users can embed the shrinker structure\nin the context the shrinker needs to operate on and get back to it in the\ncallback via container_of().\n\nSigned-off-by: Dave Chinner \u003cdchinner@redhat.com\u003e\nReviewed-by: Christoph Hellwig \u003chch@lst.de\u003e\n" }, { "commit": "46ac0cc92eedf92f7909e563ffcd2dbc4b914bc3", "tree": "25b9c293e4f9a33b8593f83c86f1db5ddf247ead", "parents": [ "2decd5a7cea2c1dae6418fe778857d43680a91aa", "9078370c0d2cfe4a905aa34f398bbb0d65921a2b" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Jul 19 13:18:34 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Jul 19 13:18:34 2010 -0700" }, "message": "Merge branch \u0027kmemleak\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/cmarinas/linux-2.6-cm\n\n* \u0027kmemleak\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/cmarinas/linux-2.6-cm:\n kmemleak: Add support for NO_BOOTMEM configurations\n kmemleak: Annotate false positive in init_section_page_cgroup()\n" }, { "commit": "9078370c0d2cfe4a905aa34f398bbb0d65921a2b", "tree": "0b0d3b1f2a9a6dd2f2deaae9fbf9c8c5509ac13c", "parents": [ "7952f98818d561ed0e11434a7a16acd9a7bae859" ], "author": { "name": "Catalin Marinas", "email": "catalin.marinas@arm.com", "time": "Mon Jul 19 11:54:15 2010 +0100" }, "committer": { "name": "Catalin Marinas", "email": "catalin.marinas@arm.com", "time": "Mon Jul 19 11:54:15 2010 +0100" }, "message": "kmemleak: Add support for NO_BOOTMEM configurations\n\nWith commits 08677214 and 59be5a8e, alloc_bootmem()/free_bootmem() and\nfriends use the early_res functions for memory management when\nNO_BOOTMEM is enabled. This patch adds the kmemleak calls in the\ncorresponding code paths for bootmem allocations.\n\nSigned-off-by: Catalin Marinas \u003ccatalin.marinas@arm.com\u003e\nAcked-by: Pekka Enberg \u003cpenberg@cs.helsinki.fi\u003e\nAcked-by: Yinghai Lu \u003cyinghai@kernel.org\u003e\nCc: H. Peter Anvin \u003chpa@zytor.com\u003e\nCc: stable@kernel.org\n" }, { "commit": "7952f98818d561ed0e11434a7a16acd9a7bae859", "tree": "b8e74d8a3aa9ac6939889487b8c46ce098c7d9f3", "parents": [ "815c4163b6c8ebf8152f42b0a5fd015cfdcedc78" ], "author": { "name": "Catalin Marinas", "email": "catalin.marinas@arm.com", "time": "Mon Jul 19 11:54:14 2010 +0100" }, "committer": { "name": "Catalin Marinas", "email": "catalin.marinas@arm.com", "time": "Mon Jul 19 11:54:14 2010 +0100" }, "message": "kmemleak: Annotate false positive in init_section_page_cgroup()\n\nThe pointer to the page_cgroup table allocated in\ninit_section_page_cgroup() is stored in section-\u003epage_cgroup as (base -\npfn). Since this value does not point to the beginning or inside the\nallocated memory block, kmemleak reports a false positive.\n\nThis was reported in bugzilla.kernel.org as #16297.\n\nSigned-off-by: Catalin Marinas \u003ccatalin.marinas@arm.com\u003e\nReported-by: Adrien Dessemond \u003cadrien.dessemond@gmail.com\u003e\nReviewed-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Pekka Enberg \u003cpenberg@cs.helsinki.fi\u003e\nCc: Andrew Morton \u003cakpm@linux-foundation.org\u003e\n" }, { "commit": "95f72d1ed41a66f1c1c29c24d479de81a0bea36f", "tree": "bd92b3804ff0bea083d69af0ede52f99ab34c0af", "parents": [ "1c5474a65bf15a4cb162dfff86d6d0b5a08a740c" ], "author": { "name": "Yinghai Lu", "email": "yinghai@kernel.org", "time": "Mon Jul 12 14:36:09 2010 +1000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Wed Jul 14 17:14:00 2010 +1000" }, "message": "lmb: rename to memblock\n\nvia following scripts\n\n FILES\u003d$(find * -type f | grep -vE \u0027oprofile|[^K]config\u0027)\n\n sed -i \\\n -e \u0027s/lmb/memblock/g\u0027 \\\n -e \u0027s/LMB/MEMBLOCK/g\u0027 \\\n $FILES\n\n for N in $(find . -name lmb.[ch]); do\n M\u003d$(echo $N | sed \u0027s/lmb/memblock/g\u0027)\n mv $N $M\n done\n\nand remove some wrong change like lmbench and dlmb etc.\n\nalso move memblock.c from lib/ to mm/\n\nSuggested-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nAcked-by: \"H. Peter Anvin\" \u003chpa@zytor.com\u003e\nAcked-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nAcked-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\nSigned-off-by: Yinghai Lu \u003cyinghai@kernel.org\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "c77e9e68269bf50573ce130b5d95ff6e539dbcf8", "tree": "99edc1b070717e18f5958f934bc3921cfed2ce1f", "parents": [ "31016e9941be85e8c487b1f3c45d253eda356715", "83ba7b071f30f7c01f72518ad72d5cd203c27502" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jul 08 08:06:40 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jul 08 08:06:40 2010 -0700" }, "message": "Merge branch \u0027for-linus\u0027 of git://git.kernel.dk/linux-2.6-block\n\n* \u0027for-linus\u0027 of git://git.kernel.dk/linux-2.6-block:\n writeback: simplify the write back thread queue\n writeback: split writeback_inodes_wb\n writeback: remove writeback_inodes_wbc\n fs-writeback: fix kernel-doc warnings\n splice: check f_mode for seekable file\n splice: direct_splice_actor() should not use pos in sd\n" }, { "commit": "83ba7b071f30f7c01f72518ad72d5cd203c27502", "tree": "4737320dcce72cfff4d87d835e4f78428eca7ef5", "parents": [ "edadfb10ba35da7253541e4155aa92eff758ebe6" ], "author": { "name": "Christoph Hellwig", "email": "hch@lst.de", "time": "Tue Jul 06 08:59:53 2010 +0200" }, "committer": { "name": "Jens Axboe", "email": "jaxboe@fusionio.com", "time": "Tue Jul 06 08:59:53 2010 +0200" }, "message": "writeback: simplify the write back thread queue\n\nFirst remove items from work_list as soon as we start working on them. This\nmeans we don\u0027t have to track any pending or visited state and can get\nrid of all the RCU magic freeing the work items - we can simply free\nthem once the operation has finished. Second use a real completion for\ntracking synchronous requests - if the caller sets the completion pointer\nwe complete it, otherwise use it as a boolean indicator that we can free\nthe work item directly. Third unify struct wb_writeback_args and struct\nbdi_work into a single data structure, wb_writeback_work. Previous we\nset all parameters into a struct wb_writeback_args, copied it into\nstruct bdi_work, copied it again on the stack to use it there. Instead\nof just allocate one structure dynamically or on the stack and use it\nall the way through the stack.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Jens Axboe \u003cjaxboe@fusionio.com\u003e\n" }, { "commit": "9c3a8ee8a1d72c5c0d7fbdf426d80e270ddfa54c", "tree": "fa131760a61f66afeede852622ede0d716965489", "parents": [ "06d738fa9155ff16dba3d7e501ba4581d01a98cb" ], "author": { "name": "Christoph Hellwig", "email": "hch@lst.de", "time": "Thu Jun 10 12:07:27 2010 +0200" }, "committer": { "name": "Jens Axboe", "email": "jaxboe@fusionio.com", "time": "Tue Jul 06 08:54:03 2010 +0200" }, "message": "writeback: remove writeback_inodes_wbc\n\nThis was just an odd wrapper around writeback_inodes_wb. Removing this\nalso allows to get rid of the bdi member of struct writeback_control\nwhich was rather out of place there.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Jens Axboe \u003cjaxboe@fusionio.com\u003e\n" }, { "commit": "5c0c165490e763eddcbb0b6c8c41ab5cc11ddea0", "tree": "729ad93071eaf065e7dfb7c7d94b0207b2eced8e", "parents": [ "56480287f9776adc5b1a7a335ef62a9b9879ad7f" ], "author": { "name": "Lee Schermerhorn", "email": "Lee.Schermerhorn@hp.com", "time": "Tue Jun 29 15:05:30 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Jun 29 15:29:31 2010 -0700" }, "message": "mempolicy: fix dangling reference to tmpfs superblock mpol\n\nMy patch to \"Factor out duplicate put/frees in mpol_shared_policy_init()\nto a common return path\"; and Dan Carpenter\u0027s fix thereto both left a\ndangling reference to the incoming tmpfs superblock mempolicy structure.\nA similar leak was introduced earlier when the nodemask was moved offstack\nto the scratch area despite the note in the comment block regarding the\nincoming ref.\n\nMove the remaining \u0027put of the incoming \"mpol\" to the common exit path to\ndrop the reference.\n\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nAcked-by: Dan Carpenter \u003cerror27@gmail.com\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nCc: Christoph Lameter \u003ccl@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": "4d845ebf4cf9e985b1704b1f08b37f744b4ede13", "tree": "d137f9220a1572c2e3b53ce38950314f5aeb82e4", "parents": [ "3c26c9d9597f982973b9b3a32364230096ab0d78" ], "author": { "name": "KAMEZAWA Hiroyuki", "email": "kamezawa.hiroyu@jp.fujitsu.com", "time": "Tue Jun 29 15:05:18 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Jun 29 15:29:30 2010 -0700" }, "message": "memcg: fix wake up in oom wait queue\n\nOOM-waitqueue should be waken up when oom_disable is canceled. This is a\nfix for 3c11ecf448eff8f1 (\"memcg: oom kill disable and oom status\").\n\nHow to test:\n Create a cgroup A...\n 1. set memory.limit and memory.memsw.limit to be small value\n 2. echo 1 \u003e /cgroup/A/memory.oom_control, this disables oom-kill.\n 3. run a program which must cause OOM.\n\nA program executed in 3 will sleep by oom_waiqueue in memcg. Then, how to\nwake it up is problem.\n\n 1. echo 0 \u003e /cgroup/A/memory.oom_control (enable OOM-killer)\n 2. echo big mem \u003e /cgroup/A/memory.memsw.limit_in_bytes(allow more swap)\n\netc..\n\nWithout the patch, a task in slept can not be waken up.\n\nSigned-off-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nAcked-by: Daisuke Nishimura \u003cnishimura@mxp.nes.nec.co.jp\u003e\nCc: Balbir Singh \u003cbalbir@in.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": "984bc9601f64fd341b8573021d7c999f1f1499a9", "tree": "06c616a6285b00d1e577902face3e8a986370b34", "parents": [ "57439f878afafefad8836ebf5c49da2a0a746105", "1b99973f1c82707e46e8cb9416865a1e955e8f8c" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Jun 29 10:42:52 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Jun 29 10:42:52 2010 -0700" }, "message": "Merge branch \u0027for-linus\u0027 of git://git.kernel.dk/linux-2.6-block\n\n* \u0027for-linus\u0027 of git://git.kernel.dk/linux-2.6-block:\n block: Don\u0027t count_vm_events for discard bio in submit_bio.\n cfq: fix recursive call in cfq_blkiocg_update_completion_stats()\n cfq-iosched: Fixed boot warning with BLK_CGROUP\u003dy and CFQ_GROUP_IOSCHED\u003dn\n cfq: Don\u0027t allow queue merges for queues that have no process references\n block: fix DISCARD_BARRIER requests\n cciss: set SCSI max cmd len to 16, as default is wrong\n cpqarray: fix two more wrong section type\n cpqarray: fix wrong __init type on pci probe function\n drbd: Fixed a race between disk-attach and unexpected state changes\n writeback: fix pin_sb_for_writeback\n writeback: add missing requeue_io in writeback_inodes_wb\n writeback: simplify and split bdi_start_writeback\n writeback: simplify wakeup_flusher_threads\n writeback: fix writeback_inodes_wb from writeback_inodes_sb\n writeback: enforce s_umount locking in writeback_inodes_sb\n writeback: queue work on stack in writeback_inodes_sb\n writeback: fix writeback completion notifications\n" }, { "commit": "099a19d91ca429944743d51bef8fee240e94d8e3", "tree": "55bdc0f25ecbf38240782fb1d9a80d33c0100eb6", "parents": [ "4ba6ce250e406b20bcd6f0f3aed6b3d80965e6c2" ], "author": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Sun Jun 27 18:50:00 2010 +0200" }, "committer": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Sun Jun 27 18:50:00 2010 +0200" }, "message": "percpu: allow limited allocation before slab is online\n\nThis patch updates percpu allocator such that it can serve limited\namount of allocation before slab comes online. This is primarily to\nallow slab to depend on working percpu allocator.\n\nTwo parameters, PERCPU_DYNAMIC_EARLY_SIZE and SLOTS, determine how\nmuch memory space and allocation map slots are reserved. If this\nreserved area is exhausted, WARN_ON_ONCE() will trigger and allocation\nwill fail till slab comes online.\n\nThe following changes are made to implement early alloc.\n\n* pcpu_mem_alloc() now checks slab_is_available()\n\n* Chunks are allocated using pcpu_mem_alloc()\n\n* Init paths make sure ai-\u003edyn_size is at least as large as\n PERCPU_DYNAMIC_EARLY_SIZE.\n\n* Initial alloc maps are allocated in __initdata and copied to\n kmalloc\u0027d areas once slab is online.\n\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\nCc: Christoph Lameter \u003ccl@linux-foundation.org\u003e\n" }, { "commit": "4ba6ce250e406b20bcd6f0f3aed6b3d80965e6c2", "tree": "3ae4cdd7c53626dca141bd32037a524a2bc3643c", "parents": [ "9983b6f0cf8263e51bcf4c8a9dc0c1ef175b3c60" ], "author": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Sun Jun 27 18:49:59 2010 +0200" }, "committer": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Sun Jun 27 18:49:59 2010 +0200" }, "message": "percpu: make @dyn_size always mean min dyn_size in first chunk init functions\n\nIn pcpu_build_alloc_info() and pcpu_embed_first_chunk(), @dyn_size was\nssize_t, -1 meant auto-size, 0 forced 0 and positive meant minimum\nsize. There\u0027s no use case for forcing 0 and the upcoming early alloc\nsupport always requires non-zero dynamic size. Make @dyn_size always\nmean minimum dyn_size.\n\nWhile at it, make pcpu_build_alloc_info() static which doesn\u0027t have\nany external caller as suggested by David Rientjes.\n\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\n" }, { "commit": "9983b6f0cf8263e51bcf4c8a9dc0c1ef175b3c60", "tree": "a9b7bacbdf8e30b931c2ebd849104b04b157d48d", "parents": [ "a92d3ff9e5dbd958d8008a3e7a573e988e370ca3" ], "author": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Fri Jun 18 11:44:31 2010 +0200" }, "committer": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Fri Jun 18 15:07:23 2010 +0200" }, "message": "percpu: fix first chunk match in per_cpu_ptr_to_phys()\n\nper_cpu_ptr_to_phys() determines whether the passed in @addr belongs\nto the first_chunk or not by just matching the address against the\naddress range of the base unit (unit0, used by cpu0). When an adress\nfrom another cpu was passed in, it will always determine that the\naddress doesn\u0027t belong to the first chunk even when it does. This\nmakes the function return a bogus physical address which may lead to\ncrash.\n\nThis problem was discovered by Cliff Wickman while investigating a\ncrash during kdump on a SGI UV system.\n\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\nReported-by: Cliff Wickman \u003ccpw@sgi.com\u003e\nTested-by: Cliff Wickman \u003ccpw@sgi.com\u003e\nCc: stable@kernel.org\n" }, { "commit": "a92d3ff9e5dbd958d8008a3e7a573e988e370ca3", "tree": "1fe26978d5ef6bbee063c3fb7b4e6b78280ab551", "parents": [ "7e27d6e778cd87b6f2415515d7127eba53fe5d02" ], "author": { "name": "Pavel V. Panteleev", "email": "pp_84@mail.ru", "time": "Thu Jun 17 10:07:25 2010 +0200" }, "committer": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Thu Jun 17 10:07:25 2010 +0200" }, "message": "percpu: fix trivial bugs in pcpu_build_alloc_info()\n\nFix the following two trivial bugs in pcpu_build_alloc_info()\n\n* we should memset group_cnt to 0 by size of group_cnt, not size of\n group_map (both are of the same size, so the bug isn\u0027t dangerous)\n\n* we can delete useless variable group_cnt_max.\n\nSigned-off-by: Pavel V. Panteleev \u003cpp_84@mail.ru\u003e\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\n" }, { "commit": "c5444198ca210498e8ac0ba121b4cd3537aa12f7", "tree": "c423d38fe1ac7f51a48e455a19ecbe2354811fca", "parents": [ "b8c2f3474f1077599ec6e90c2f263f17055cc3d8" ], "author": { "name": "Christoph Hellwig", "email": "hch@lst.de", "time": "Tue Jun 08 18:15:15 2010 +0200" }, "committer": { "name": "Jens Axboe", "email": "jaxboe@fusionio.com", "time": "Fri Jun 11 12:58:08 2010 +0200" }, "message": "writeback: simplify and split bdi_start_writeback\n\nbdi_start_writeback now never gets a superblock passed, so we can just remove\nthat case. And to further untangle the code and flatten the call stack\nsplit it into two trivial helpers for it\u0027s two callers.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Jens Axboe \u003cjaxboe@fusionio.com\u003e\n" }, { "commit": "d87815cb2090e07b0b0b2d73dc9740706e92c80c", "tree": "0e23b40fce5b09c94dab2bf773601b310d8d9b09", "parents": [ "254c8c2dbf0e06a560a5814eb90cb628adb2de66" ], "author": { "name": "Dave Chinner", "email": "dchinner@redhat.com", "time": "Wed Jun 09 10:37:20 2010 +1000" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Jun 08 18:12:44 2010 -0700" }, "message": "writeback: limit write_cache_pages integrity scanning to current EOF\n\nsync can currently take a really long time if a concurrent writer is\nextending a file. The problem is that the dirty pages on the address\nspace grow in the same direction as write_cache_pages scans, so if\nthe writer keeps ahead of writeback, the writeback will not\nterminate until the writer stops adding dirty pages.\n\nFor a data integrity sync, we only need to write the pages dirty at\nthe time we start the writeback, so we can stop scanning once we get\nto the page that was at the end of the file at the time the scan\nstarted.\n\nThis will prevent operations like copying a large file preventing\nsync from completing as it will not write back pages that were\ndirtied after the sync was started. This does not impact the\nexisting integrity guarantees, as any dirty page (old or new)\nwithin the EOF range at the start of the scan will still be\ncaptured.\n\nThis patch will not prevent sync from blocking on large writes into\nholes. That requires more complex intervention while this patch only\naddresses the common append-case of this sync holdoff.\n\nSigned-off-by: Dave Chinner \u003cdchinner@redhat.com\u003e\nReviewed-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "0b5649278e39a068aaf91399941bab1b4a4a3cc2", "tree": "3fd2c782385137f5b135c07149de772e207fdaf8", "parents": [ "8d7458daea2a6809d32418bf489b949d23de99ea" ], "author": { "name": "Dave Chinner", "email": "dchinner@redhat.com", "time": "Wed Jun 09 10:37:18 2010 +1000" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Jun 08 18:12:44 2010 -0700" }, "message": "writeback: pay attention to wbc-\u003enr_to_write in write_cache_pages\n\nIf a filesystem writes more than one page in -\u003ewritepage, write_cache_pages\nfails to notice this and continues to attempt writeback when wbc-\u003enr_to_write\nhas gone negative - this trace was captured from XFS:\n\n wbc_writeback_start: towrt\u003d1024\n wbc_writepage: towrt\u003d1024\n wbc_writepage: towrt\u003d0\n wbc_writepage: towrt\u003d-1\n wbc_writepage: towrt\u003d-5\n wbc_writepage: towrt\u003d-21\n wbc_writepage: towrt\u003d-85\n\nThis has adverse effects on filesystem writeback behaviour. write_cache_pages()\nneeds to terminate after a certain number of pages are written, not after a\ncertain number of calls to -\u003ewritepage are made. This is a regression\nintroduced by 17bc6c30cf6bfffd816bdc53682dd46fc34a2cf4 (\"vfs: Add\nno_nrwrite_index_update writeback control flag\"), but cannot be reverted\ndirectly due to subsequent bug fixes that have gone in on top of it.\n\nSigned-off-by: Dave Chinner \u003cdchinner@redhat.com\u003e\nReviewed-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "7f0d384cafabfbb56663ee6944c18fc0450fc5d6", "tree": "bf68721fb65b64392177f498a9ba61ef027b2b3d", "parents": [ "90ec7819737d42a0ad1c2df1ff56016facae3c6e", "01afaf61983d08ed1c9e5e8f2fcf4f40e9008033" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Jun 04 21:12:39 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Jun 04 21:12:39 2010 -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 Minix: Clean up left over label\n fix truncate inode time modification breakage\n fix setattr error handling in sysfs, configfs\n fcntl: return -EFAULT if copy_to_user fails\n wrong type for \u0027magic\u0027 argument in simple_fill_super()\n fix the deadlock in qib_fs\n mqueue doesn\u0027t need make_bad_inode()\n" }, { "commit": "d2dd328b7f7bc6cebe167648289337755944ad2a", "tree": "5d664a2db1ac209f7537452ddc02597972f7aa37", "parents": [ "c1518f12bab97a6d409a25aaccb02dc8895800f3", "1abec4fdbb142e3ccb6ce99832fae42129134a96" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Jun 04 15:37:44 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Jun 04 15:37:44 2010 -0700" }, "message": "Merge branch \u0027for-linus\u0027 of git://git.kernel.dk/linux-2.6-block\n\n* \u0027for-linus\u0027 of git://git.kernel.dk/linux-2.6-block: (27 commits)\n block: make blk_init_free_list and elevator_init idempotent\n block: avoid unconditionally freeing previously allocated request_queue\n pipe: change /proc/sys/fs/pipe-max-pages to byte sized interface\n pipe: change the privilege required for growing a pipe beyond system max\n pipe: adjust minimum pipe size to 1 page\n block: disable preemption before using sched_clock()\n cciss: call BUG() earlier\n Preparing 8.3.8rc2\n drbd: Reduce verbosity\n drbd: use drbd specific ratelimit instead of global printk_ratelimit\n drbd: fix hang on local read errors while disconnected\n drbd: Removed the now empty w_io_error() function\n drbd: removed duplicated #includes\n drbd: improve usage of MSG_MORE\n drbd: need to set socket bufsize early to take effect\n drbd: improve network latency, TCP_QUICKACK\n drbd: Revert \"drbd: Create new current UUID as late as possible\"\n brd: support discard\n Revert \"writeback: fix WB_SYNC_NONE writeback from umount\"\n Revert \"writeback: ensure that WB_SYNC_NONE writeback with sb pinned is sync\"\n ...\n" }, { "commit": "bb21c7ce18eff8e6e7877ca1d06c6db719376e3c", "tree": "555edaded1e0a771df406ce2b6b63368df6de6cd", "parents": [ "9e506f7adce8e6165a104d3d78fddd8ff0cdccf8" ], "author": { "name": "KOSAKI Motohiro", "email": "kosaki.motohiro@jp.fujitsu.com", "time": "Fri Jun 04 14:15:05 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Jun 04 15:21:45 2010 -0700" }, "message": "vmscan: fix do_try_to_free_pages() return value when priority\u003d\u003d0 reclaim failure\n\nGreg Thelen reported recent Johannes\u0027s stack diet patch makes kernel hang.\n His test is following.\n\n mount -t cgroup none /cgroups -o memory\n mkdir /cgroups/cg1\n echo $$ \u003e /cgroups/cg1/tasks\n dd bs\u003d1024 count\u003d1024 if\u003d/dev/null of\u003d/data/foo\n echo $$ \u003e /cgroups/tasks\n echo 1 \u003e /cgroups/cg1/memory.force_empty\n\nActually, This OOM hard to try logic have been corrupted since following\ntwo years old patch.\n\n\tcommit a41f24ea9fd6169b147c53c2392e2887cc1d9247\n\tAuthor: Nishanth Aravamudan \u003cnacc@us.ibm.com\u003e\n\tDate: Tue Apr 29 00:58:25 2008 -0700\n\n\t page allocator: smarter retry of costly-order allocations\n\nOriginal intention was \"return success if the system have shrinkable zones\nthough priority\u003d\u003d0 reclaim was failure\". But the above patch changed to\n\"return nr_reclaimed if .....\". Oh, That forgot nr_reclaimed may be 0 if\npriority\u003d\u003d0 reclaim failure.\n\nAnd Johannes\u0027s patch 0aeb2339e54e (\"vmscan: remove all_unreclaimable scan\ncontrol\") made it more corrupt. Originally, priority\u003d\u003d0 reclaim failure\non memcg return 0, but this patch changed to return 1. It totally\nconfused memcg.\n\nThis patch fixes it completely.\n\nReported-by: Greg Thelen \u003cgthelen@google.com\u003e\nSigned-off-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nAcked-by: Johannes Weiner \u003channes@cmpxchg.org\u003e\nAcked-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nTested-by: Greg Thelen \u003cgthelen@google.com\u003e\nAcked-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": "af5a30d8cfcfc561336f982b06345d6b815e0bb3", "tree": "eb4e6fb6873355a2a96b698aeb371eb058a88c87", "parents": [ "8718d36cf99f5acf0f37487557ec25aee54b930b" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Thu Jun 03 22:01:46 2010 +1000" }, "committer": { "name": "Al Viro", "email": "viro@zeniv.linux.org.uk", "time": "Fri Jun 04 17:16:30 2010 -0400" }, "message": "fix truncate inode time modification breakage\n\nmtime and ctime should be changed only if the file size has actually\nchanged. Patches changing ext2 and tmpfs from vmtruncate to new truncate\nsequence has caused regressions where they always update timestamps.\n\nThere is some strange cases in POSIX where truncate(2) must not update\ntimes unless the size has acutally changed, see 6e656be89.\n\nThis area is all still rather buggy in different ways in a lot of\nfilesystems and needs a cleanup and audit (ideally the vfs will provide\na simple attribute or call to direct all filesystems exactly which\nattributes to change). But coming up with the best solution will take a\nwhile and is not appropriate for rc anyway.\n\nSo fix recent regression for now.\n\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n" }, { "commit": "b4ca761577535b2b4d153689ee97342797dfff05", "tree": "29054d55508f1faa22ec32acf7c245751af03348", "parents": [ "28f4197e5d4707311febeec8a0eb97cb5fd93c97", "67a3e12b05e055c0415c556a315a3d3eb637e29e" ], "author": { "name": "Jens Axboe", "email": "jaxboe@fusionio.com", "time": "Tue Jun 01 12:42:12 2010 +0200" }, "committer": { "name": "Jens Axboe", "email": "jaxboe@fusionio.com", "time": "Tue Jun 01 12:42:12 2010 +0200" }, "message": "Merge branch \u0027master\u0027 into for-linus\n\nConflicts:\n\tfs/pipe.c\n\nSigned-off-by: Jens Axboe \u003cjaxboe@fusionio.com\u003e\n" }, { "commit": "0e3c9a2284f5417f196e327c254d0b84c9ee8929", "tree": "e3fb40ebe7d042b4b3c1042bc7f2edaf7fb6eee0", "parents": [ "f17625b318d9b151e7bd41e31223e9d89b2aaa77" ], "author": { "name": "Jens Axboe", "email": "jaxboe@fusionio.com", "time": "Tue Jun 01 11:08:43 2010 +0200" }, "committer": { "name": "Jens Axboe", "email": "jaxboe@fusionio.com", "time": "Tue Jun 01 11:08:43 2010 +0200" }, "message": "Revert \"writeback: fix WB_SYNC_NONE writeback from umount\"\n\nThis reverts commit e913fc825dc685a444cb4c1d0f9d32f372f59861.\n\nWe are investigating a hang associated with the WB_SYNC_NONE changes,\nso revert them for now.\n\nConflicts:\n\n\tfs/fs-writeback.c\n\tmm/page-writeback.c\n\nSigned-off-by: Jens Axboe \u003cjaxboe@fusionio.com\u003e\n" }, { "commit": "3b03117c5cfbb04175b688c79ea4155b8ef812d3", "tree": "5d2e3d0d7db98e2b47c7bb51be39bc4ced6a4d97", "parents": [ "fa7eadab4b4aec0139d2429e6f8d13375ff8a658", "0f1f694260e0d35b5ce7d471f6e679c3dd4d7d94" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sun May 30 12:46:17 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sun May 30 12:46:17 2010 -0700" }, "message": "Merge branch \u0027slub/urgent\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/penberg/slab-2.6\n\n* \u0027slub/urgent\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/penberg/slab-2.6:\n SLUB: Allow full duplication of kmalloc array for 390\n slub: move kmem_cache_node into it\u0027s own cacheline\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": "3889e6e76f66b7de208a1709d0fe530b21a2d384", "tree": "c5eb8e299df1a32ff1f179f04aa0ced273dee899", "parents": [ "3322e79a3860fd0d50e3c1879b2e98ac582c0ff6" ], "author": { "name": "npiggin@suse.de", "email": "npiggin@suse.de", "time": "Thu May 27 01:05:36 2010 +1000" }, "committer": { "name": "Al Viro", "email": "viro@zeniv.linux.org.uk", "time": "Thu May 27 22:15:51 2010 -0400" }, "message": "tmpfs: convert to use the new truncate convention\n\nCc: Christoph Hellwig \u003chch@lst.de\u003e\nAcked-by: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n" }, { "commit": "7bb46a6734a7e1ad4beaecc11cae7ed3ff81d30f", "tree": "e575d9c55e2a6ccc645dcb3ae2564de458b428f2", "parents": [ "7000d3c424e5bb350e502a477fb0e1ed42f8b10e" ], "author": { "name": "npiggin@suse.de", "email": "npiggin@suse.de", "time": "Thu May 27 01:05:33 2010 +1000" }, "committer": { "name": "Al Viro", "email": "viro@zeniv.linux.org.uk", "time": "Thu May 27 22:15:33 2010 -0400" }, "message": "fs: introduce new truncate sequence\n\nIntroduce a new truncate calling sequence into fs/mm subsystems. Rather than\nsetattr \u003e vmtruncate \u003e truncate, have filesystems call their truncate sequence\nfrom -\u003esetattr if filesystem specific operations are required. vmtruncate is\ndeprecated, and truncate_pagecache and inode_newsize_ok helpers introduced\npreviously should be used.\n\nsimple_setattr is introduced for simple in-ram filesystems to implement\nthe new truncate sequence. Eventually all filesystems should be converted\nto implement a setattr, and the default code in notify_change should go\naway.\n\nsimple_setsize is also introduced to perform just the ATTR_SIZE portion\nof simple_setattr (ie. changing i_size and trimming pagecache).\n\nTo implement the new truncate sequence:\n- filesystem specific manipulations (eg freeing blocks) must be done in\n the setattr method rather than -\u003etruncate.\n- vmtruncate can not be used by core code to trim blocks past i_size in\n the event of write failure after allocation, so this must be performed\n in the fs code.\n- convert usage of helpers block_write_begin, nobh_write_begin,\n cont_write_begin, and *blockdev_direct_IO* to use _newtrunc postfixed\n variants. These avoid calling vmtruncate to trim blocks (see previous).\n- inode_setattr should not be used. generic_setattr is a new function\n to be used to copy simple attributes into the generic inode.\n- make use of the better opportunity to handle errors with the new sequence.\n\nBig problem with the previous calling sequence: the filesystem is not called\nuntil i_size has already changed. This means it is not allowed to fail the\ncall, and also it does not know what the previous i_size was. Also, generic\ncode calling vmtruncate to truncate allocated blocks in case of error had\nno good way to return a meaningful error (or, for example, atomically handle\nblock deallocation).\n\nCc: Christoph Hellwig \u003chch@lst.de\u003e\nAcked-by: Jan Kara \u003cjack@suse.cz\u003e\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n" }, { "commit": "1b061d9247f71cd15edc4c4c4600191a903642c0", "tree": "30d92ca82d8286e7a45fba108230ecd23e61673b", "parents": [ "7ea8085910ef3dd4f3cad6845aaa2b580d39b115" ], "author": { "name": "Christoph Hellwig", "email": "hch@lst.de", "time": "Wed May 26 17:53:41 2010 +0200" }, "committer": { "name": "Al Viro", "email": "viro@zeniv.linux.org.uk", "time": "Thu May 27 22:06:06 2010 -0400" }, "message": "rename the generic fsync implementations\n\nWe don\u0027t name our generic fsync implementations very well currently.\nThe no-op implementation for in-memory filesystems currently is called\nsimple_sync_file which doesn\u0027t make too much sense to start with,\nthe the generic one for simple filesystems is called simple_fsync\nwhich can lead to some confusion.\n\nThis patch renames the generic file fsync method to generic_file_fsync\nto match the other generic_file_* routines it is supposed to be used\nwith, and the no-op implementation to noop_fsync to make it obvious\nwhat to expect. In addition add some documentation for both methods.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\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": "7d6e6d09de82cf6cff7fecdba55198b9f47b381c", "tree": "57b26da3bea0af63dd0b65cdcdde33fe5670a35f", "parents": [ "fd1197f1131a1f1d8bc192f9cfbbe17e305f17f3" ], "author": { "name": "Lee Schermerhorn", "email": "lee.schermerhorn@hp.com", "time": "Wed May 26 14:45:03 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu May 27 09:12:57 2010 -0700" }, "message": "numa: slab: use numa_mem_id() for slab local memory node\n\nExample usage of generic \"numa_mem_id()\":\n\nThe mainline slab code, since ~ 2.6.19, does not handle memoryless nodes\nwell. Specifically, the \"fast path\"--____cache_alloc()--will never\nsucceed as slab doesn\u0027t cache offnode object on the per cpu queues, and\nfor memoryless nodes, all memory will be \"off node\" relative to\nnuma_node_id(). This adds significant overhead to all kmem cache\nallocations, incurring a significant regression relative to earlier\nkernels [from before slab.c was reorganized].\n\nThis patch uses the generic topology function \"numa_mem_id()\" to return\nthe \"effective local memory node\" for the calling context. This is the\nfirst node in the local node\u0027s generic fallback zonelist-- the same node\nthat \"local\" mempolicy-based allocations would use. This lets slab cache\nthese \"local\" allocations and avoid fallback/refill on every allocation.\n\nN.B.: Slab will need to handle node and memory hotplug events that could\nchange the value returned by numa_mem_id() for any given node if recent\nchanges to address memory hotplug don\u0027t already address this. E.g., flush\nall per cpu slab queues before rebuilding the zonelists while the\n\"machine\" is held in the stopped state.\n\nPerformance impact on \"hackbench 400 process 200\"\n\n2.6.34-rc3-mmotm-100405-1609\t\tno-patch\tthis-patch\nia64 no memoryless nodes [avg of 10]: 11.713 11.637 ~0.65 diff\nia64 cpus all on memless nodes [10]: 228.259 26.484 ~8.6x speedup\n\nThe slowdown of the patched kernel from ~12 sec to ~28 seconds when\nconfigured with memoryless nodes is the result of all cpus allocating from\na single node\u0027s mm pagepool. The cache lines of the single node are\ndistributed/interleaved over the memory of the real physical nodes, but\nthe zone lock, list heads, ... of the single node with memory still each\nlive in a single cache line that is accessed from all processors.\n\nx86_64 [8x6 AMD] [avg of 40]:\t\t2.883\t 2.845\n\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Tejun Heo \u003ctj@kernel.org\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nCc: Eric Whitney \u003ceric.whitney@hp.com\u003e\nCc: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nCc: \"H. Peter Anvin\" \u003chpa@zytor.com\u003e\nCc: \"Luck, Tony\" \u003ctony.luck@intel.com\u003e\nCc: Pekka Enberg \u003cpenberg@cs.helsinki.fi\u003e\nCc: \u003clinux-arch@vger.kernel.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "7aac789885512388a66d47280d7e7777ffba1e59", "tree": "af4ac98260268889a422dd264102d2f15d5c1983", "parents": [ "3bccd996276b108c138e8176793a26ecef54d573" ], "author": { "name": "Lee Schermerhorn", "email": "lee.schermerhorn@hp.com", "time": "Wed May 26 14:45:00 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu May 27 09:12:57 2010 -0700" }, "message": "numa: introduce numa_mem_id()- effective local memory node id\n\nIntroduce numa_mem_id(), based on generic percpu variable infrastructure\nto track \"nearest node with memory\" for archs that support memoryless\nnodes.\n\nDefine API in \u003clinux/topology.h\u003e when CONFIG_HAVE_MEMORYLESS_NODES\ndefined, else stubs. Architectures will define HAVE_MEMORYLESS_NODES\nif/when they support them.\n\nArchs can override definitions of:\n\nnuma_mem_id() - returns node number of \"local memory\" node\nset_numa_mem() - initialize [this cpus\u0027] per cpu variable \u0027numa_mem\u0027\ncpu_to_mem() - return numa_mem for specified cpu; may be used as lvalue\n\nGeneric initialization of \u0027numa_mem\u0027 occurs in __build_all_zonelists().\nThis will initialize the boot cpu at boot time, and all cpus on change of\nnuma_zonelist_order, or when node or memory hot-plug requires zonelist\nrebuild. Archs that support memoryless nodes will need to initialize\n\u0027numa_mem\u0027 for secondary cpus as they\u0027re brought on-line.\n\n[akpm@linux-foundation.org: fix build]\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nSigned-off-by: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: Tejun Heo \u003ctj@kernel.org\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nCc: Eric Whitney \u003ceric.whitney@hp.com\u003e\nCc: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nCc: \"H. Peter Anvin\" \u003chpa@zytor.com\u003e\nCc: \"Luck, Tony\" \u003ctony.luck@intel.com\u003e\nCc: Pekka Enberg \u003cpenberg@cs.helsinki.fi\u003e\nCc: \u003clinux-arch@vger.kernel.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "7281201922a0063fa60804ce39c277fc98142a47", "tree": "4bf089d077b1055e54bc1411dcc0db121d01d9fa", "parents": [ "866707fc2721df8fee637fcf0239628b9231f9ea" ], "author": { "name": "Lee Schermerhorn", "email": "lee.schermerhorn@hp.com", "time": "Wed May 26 14:44:56 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu May 27 09:12:57 2010 -0700" }, "message": "numa: add generic percpu var numa_node_id() implementation\n\nRework the generic version of the numa_node_id() function to use the new\ngeneric percpu variable infrastructure.\n\nGuard the new implementation with a new config option:\n\n CONFIG_USE_PERCPU_NUMA_NODE_ID.\n\nArchs which support this new implemention will default this option to \u0027y\u0027\nwhen NUMA is configured. This config option could be removed if/when all\narchs switch over to the generic percpu implementation of numa_node_id().\nArch support involves:\n\n 1) converting any existing per cpu variable implementations to use\n this implementation. x86_64 is an instance of such an arch.\n 2) archs that don\u0027t use a per cpu variable for numa_node_id() will\n need to initialize the new per cpu variable \"numa_node\" as cpus\n are brought on-line. ia64 is an example.\n 3) Defining USE_PERCPU_NUMA_NODE_ID in arch dependent Kconfig--e.g.,\n when NUMA is configured. This is required because I have\n retained the old implementation by default to allow archs to\n be modified incrementally, as desired.\n\nSubsequent patches will convert x86_64 and ia64 to use this implemenation.\n\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Tejun Heo \u003ctj@kernel.org\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nReviewed-by: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nCc: Eric Whitney \u003ceric.whitney@hp.com\u003e\nCc: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nCc: \"H. Peter Anvin\" \u003chpa@zytor.com\u003e\nCc: \"Luck, Tony\" \u003ctony.luck@intel.com\u003e\nCc: Pekka Enberg \u003cpenberg@cs.helsinki.fi\u003e\nCc: \u003clinux-arch@vger.kernel.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "eac4068013a067f5fb63005033c13b27fbf6dfca", "tree": "f47075dda89aed758a60090ac392c57610005c2f", "parents": [ "80b5184cc537718122e036afe7e62d202b70d077" ], "author": { "name": "Akinobu Mita", "email": "akinobu.mita@gmail.com", "time": "Wed May 26 14:43:32 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu May 27 09:12:48 2010 -0700" }, "message": "slab: convert cpu notifier to return encapsulate errno value\n\nBy the previous modification, the cpu notifier can return encapsulate\nerrno value. This converts the cpu notifiers for slab.\n\nSigned-off-by: Akinobu Mita \u003cakinobu.mita@gmail.com\u003e\nCc: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nAcked-by: Pekka Enberg \u003cpenberg@cs.helsinki.fi\u003e\nCc: Matt Mackall \u003cmpm@selenic.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "6adef3ebe570bcde67fd6c16101451ddde5712b5", "tree": "0f60e2a4d01850ae33aee6cefc7a59845ede89a0", "parents": [ "2c488db27b614816024e7994117f599337de0f34" ], "author": { "name": "Jack Steiner", "email": "steiner@sgi.com", "time": "Wed May 26 14:42:49 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu May 27 09:12:44 2010 -0700" }, "message": "cpusets: new round-robin rotor for SLAB allocations\n\nWe have observed several workloads running on multi-node systems where\nmemory is assigned unevenly across the nodes in the system. There are\nnumerous reasons for this but one is the round-robin rotor in\ncpuset_mem_spread_node().\n\nFor example, a simple test that writes a multi-page file will allocate\npages on nodes 0 2 4 6 ... Odd nodes are skipped. (Sometimes it\nallocates on odd nodes \u0026 skips even nodes).\n\nAn example is shown below. The program \"lfile\" writes a file consisting\nof 10 pages. The program then mmaps the file \u0026 uses get_mempolicy(...,\nMPOL_F_NODE) to determine the nodes where the file pages were allocated.\nThe output is shown below:\n\n\t# ./lfile\n\t allocated on nodes: 2 4 6 0 1 2 6 0 2\n\nThere is a single rotor that is used for allocating both file pages \u0026 slab\npages. Writing the file allocates both a data page \u0026 a slab page\n(buffer_head). This advances the RR rotor 2 nodes for each page\nallocated.\n\nA quick confirmation seems to confirm this is the cause of the uneven\nallocation:\n\n\t# echo 0 \u003e/dev/cpuset/memory_spread_slab\n\t# ./lfile\n\t allocated on nodes: 6 7 8 9 0 1 2 3 4 5\n\nThis patch introduces a second rotor that is used for slab allocations.\n\nSigned-off-by: Jack Steiner \u003csteiner@sgi.com\u003e\nAcked-by: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: Pekka Enberg \u003cpenberg@cs.helsinki.fi\u003e\nCc: Paul Menage \u003cmenage@google.com\u003e\nCc: Jack Steiner \u003csteiner@sgi.com\u003e\nCc: Robin Holt \u003cholt@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "2c488db27b614816024e7994117f599337de0f34", "tree": "1ccfe14f5b2bede321004427babdad111a3b0c8e", "parents": [ "907860ed381a31b0102f362df67c1c5cae6ef050" ], "author": { "name": "Kirill A. Shutemov", "email": "kirill@shutemov.name", "time": "Wed May 26 14:42:47 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu May 27 09:12:44 2010 -0700" }, "message": "memcg: clean up memory thresholds\n\nIntroduce struct mem_cgroup_thresholds. It helps to reduce number of\nchecks of thresholds type (memory or mem+swap).\n\n[akpm@linux-foundation.org: repair comment]\nSigned-off-by: Kirill A. Shutemov \u003ckirill@shutemov.name\u003e\nCc: Phil Carmody \u003cext-phil.2.carmody@nokia.com\u003e\nCc: Balbir Singh \u003cbalbir@linux.vnet.ibm.com\u003e\nCc: Daisuke Nishimura \u003cnishimura@mxp.nes.nec.co.jp\u003e\nCc: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nAcked-by: Paul Menage \u003cmenage@google.com\u003e\nCc: Li Zefan \u003clizf@cn.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": "907860ed381a31b0102f362df67c1c5cae6ef050", "tree": "4f47a6fe898b1f45da505fc0c27d98e66d42aa46", "parents": [ "ac39cf8cb86c45eeac6a592ce0d58f9021a97235" ], "author": { "name": "Kirill A. Shutemov", "email": "kirill@shutemov.name", "time": "Wed May 26 14:42:46 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu May 27 09:12:44 2010 -0700" }, "message": "cgroups: make cftype.unregister_event() void-returning\n\nSince we are unable to handle an error returned by\ncftype.unregister_event() properly, let\u0027s make the callback\nvoid-returning.\n\nmem_cgroup_unregister_event() has been rewritten to be a \"never fail\"\nfunction. On mem_cgroup_usage_register_event() we save old buffer for\nthresholds array and reuse it in mem_cgroup_usage_unregister_event() to\navoid allocation.\n\nSigned-off-by: Kirill A. Shutemov \u003ckirill@shutemov.name\u003e\nAcked-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Phil Carmody \u003cext-phil.2.carmody@nokia.com\u003e\nCc: Balbir Singh \u003cbalbir@linux.vnet.ibm.com\u003e\nCc: Daisuke Nishimura \u003cnishimura@mxp.nes.nec.co.jp\u003e\nCc: Paul Menage \u003cmenage@google.com\u003e\nCc: Li Zefan \u003clizf@cn.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": "ac39cf8cb86c45eeac6a592ce0d58f9021a97235", "tree": "7321cafb0a1f8f2727c86f9d29159751df856c59", "parents": [ "315c1998e10527ff364a9883048455e609bc7232" ], "author": { "name": "akpm@linux-foundation.org", "email": "akpm@linux-foundation.org", "time": "Wed May 26 14:42:46 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu May 27 09:12:44 2010 -0700" }, "message": "memcg: fix mis-accounting of file mapped racy with migration\n\nFILE_MAPPED per memcg of migrated file cache is not properly updated,\nbecause our hook in page_add_file_rmap() can\u0027t know to which memcg\nFILE_MAPPED should be counted.\n\nBasically, this patch is for fixing the bug but includes some big changes\nto fix up other messes.\n\nNow, at migrating mapped file, events happen in following sequence.\n\n 1. allocate a new page.\n 2. get memcg of an old page.\n 3. charge ageinst a new page before migration. But at this point,\n no changes to new page\u0027s page_cgroup, no commit for the charge.\n (IOW, PCG_USED bit is not set.)\n 4. page migration replaces radix-tree, old-page and new-page.\n 5. page migration remaps the new page if the old page was mapped.\n 6. Here, the new page is unlocked.\n 7. memcg commits the charge for newpage, Mark the new page\u0027s page_cgroup\n as PCG_USED.\n\nBecause \"commit\" happens after page-remap, we can count FILE_MAPPED\nat \"5\", because we should avoid to trust page_cgroup-\u003emem_cgroup.\nif PCG_USED bit is unset.\n(Note: memcg\u0027s LRU removal code does that but LRU-isolation logic is used\n for helping it. When we overwrite page_cgroup-\u003emem_cgroup, page_cgroup is\n not on LRU or page_cgroup-\u003emem_cgroup is NULL.)\n\nWe can lose file_mapped accounting information at 5 because FILE_MAPPED\nis updated only when mapcount changes 0-\u003e1. So we should catch it.\n\nBTW, historically, above implemntation comes from migration-failure\nof anonymous page. Because we charge both of old page and new page\nwith mapcount\u003d0, we can\u0027t catch\n - the page is really freed before remap.\n - migration fails but it\u0027s freed before remap\nor .....corner cases.\n\nNew migration sequence with memcg is:\n\n 1. allocate a new page.\n 2. mark PageCgroupMigration to the old page.\n 3. charge against a new page onto the old page\u0027s memcg. (here, new page\u0027s pc\n is marked as PageCgroupUsed.)\n 4. page migration replaces radix-tree, page table, etc...\n 5. At remapping, new page\u0027s page_cgroup is now makrked as \"USED\"\n We can catch 0-\u003e1 event and FILE_MAPPED will be properly updated.\n\n And we can catch SWAPOUT event after unlock this and freeing this\n page by unmap() can be caught.\n\n 7. Clear PageCgroupMigration of the old page.\n\nSo, FILE_MAPPED will be correctly updated.\n\nThen, for what MIGRATION flag is ?\n Without it, at migration failure, we may have to charge old page again\n because it may be fully unmapped. \"charge\" means that we have to dive into\n memory reclaim or something complated. So, it\u0027s better to avoid\n charge it again. Before this patch, __commit_charge() was working for\n both of the old/new page and fixed up all. But this technique has some\n racy condtion around FILE_MAPPED and SWAPOUT etc...\n Now, the kernel use MIGRATION flag and don\u0027t uncharge old page until\n the end of migration.\n\nI hope this change will make memcg\u0027s page migration much simpler. This\npage migration has caused several troubles. Worth to add a flag for\nsimplification.\n\nReviewed-by: Daisuke Nishimura \u003cnishimura@mxp.nes.nec.co.jp\u003e\nTested-by: Daisuke Nishimura \u003cnishimura@mxp.nes.nec.co.jp\u003e\nReported-by: Daisuke Nishimura \u003cnishimura@mxp.nes.nec.co.jp\u003e\nSigned-off-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Balbir Singh \u003cbalbir@in.ibm.com\u003e\nCc: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: \"Kirill A. Shutemov\" \u003ckirill@shutemov.name\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "315c1998e10527ff364a9883048455e609bc7232", "tree": "081c072b7e7a48df369fd80142e611c3f36d3cfd", "parents": [ "5407a56257b6ade44fd9bcac972c99845b7413cd" ], "author": { "name": "Phil Carmody", "email": "ext-phil.2.carmody@nokia.com", "time": "Wed May 26 14:42:43 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu May 27 09:12:44 2010 -0700" }, "message": "mm: memcontrol - uninitialised return value\n\nOnly an out of memory error will cause ret to be set.\n\nSigned-off-by: Phil Carmody \u003cext-phil.2.carmody@nokia.com\u003e\nAcked-by: Kirill A. Shutemov \u003ckirill@shutemov.name\u003e\nCc: Balbir Singh \u003cbalbir@in.ibm.com\u003e\nCc: Daisuke Nishimura \u003cnishimura@mxp.nes.nec.co.jp\u003e\nAcked-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": "5407a56257b6ade44fd9bcac972c99845b7413cd", "tree": "833a55856af25fe9be5e8a871d89f43677eac512", "parents": [ "df64f81bb1e01cbef967a96642dacf208acb7e72" ], "author": { "name": "Phil Carmody", "email": "ext-phil.2.carmody@nokia.com", "time": "Wed May 26 14:42:42 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu May 27 09:12:43 2010 -0700" }, "message": "mm: remove unnecessary use of atomic\n\nThe bottom 4 hunks are atomically changing memory to which there are no\naliases as it\u0027s freshly allocated, so there\u0027s no need to use atomic\noperations.\n\nThe other hunks are just atomic_read and atomic_set, and do not involve\nany read-modify-write. The use of atomic_{read,set} doesn\u0027t prevent a\nread/write or write/write race, so if a race were possible (I\u0027m not saying\none is), then it would still be there even with atomic_set.\n\nSee:\nhttp://digitalvampire.org/blog/index.php/2007/05/13/atomic-cargo-cults/\n\nSigned-off-by: Phil Carmody \u003cext-phil.2.carmody@nokia.com\u003e\nAcked-by: Kirill A. Shutemov \u003ckirill@shutemov.name\u003e\nCc: Balbir Singh \u003cbalbir@in.ibm.com\u003e\nCc: Daisuke Nishimura \u003cnishimura@mxp.nes.nec.co.jp\u003e\nAcked-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": "df64f81bb1e01cbef967a96642dacf208acb7e72", "tree": "accb54ac130b2ac52b3d8644cb6585cf9730975c", "parents": [ "dc10e281f5fc42e288ab979294d1d5dc9743ae1b" ], "author": { "name": "David Rientjes", "email": "rientjes@google.com", "time": "Wed May 26 14:42:41 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu May 27 09:12:43 2010 -0700" }, "message": "memcg: make oom killer a no-op when no killable task can be found\n\nIt\u0027s pointless to try to kill current if select_bad_process() did not find\nan eligible task to kill in mem_cgroup_out_of_memory() since it\u0027s\nguaranteed that current is a member of the memcg that is oom and it is, by\ndefinition, unkillable.\n\nSigned-off-by: David Rientjes \u003crientjes@google.com\u003e\nAcked-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Balbir Singh \u003cbalbir@in.ibm.com\u003e\nCc: Li Zefan \u003clizf@cn.fujitsu.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": "87946a72283be3de936adc754b7007df7d3e6aeb", "tree": "0593c87ba36bae13d6a6d5dda65ebb41354954f8", "parents": [ "90254a65833b67502d14736410b3857a15535c67" ], "author": { "name": "Daisuke Nishimura", "email": "nishimura@mxp.nes.nec.co.jp", "time": "Wed May 26 14:42:39 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu May 27 09:12:43 2010 -0700" }, "message": "memcg: move charge of file pages\n\nThis patch adds support for moving charge of file pages, which include\nnormal file, tmpfs file and swaps of tmpfs file. It\u0027s enabled by setting\nbit 1 of \u003ctarget cgroup\u003e/memory.move_charge_at_immigrate.\n\nUnlike the case of anonymous pages, file pages(and swaps) in the range\nmmapped by the task will be moved even if the task hasn\u0027t done page fault,\ni.e. they might not be the task\u0027s \"RSS\", but other task\u0027s \"RSS\" that maps\nthe same file. And mapcount of the page is ignored(the page can be moved\neven if page_mapcount(page) \u003e 1). So, conditions that the page/swap\nshould be met to be moved is that it must be in the range mmapped by the\ntarget task and it must be charged to the old cgroup.\n\n[akpm@linux-foundation.org: coding-style fixes]\n[akpm@linux-foundation.org: fix warning]\nSigned-off-by: Daisuke Nishimura \u003cnishimura@mxp.nes.nec.co.jp\u003e\nAcked-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Balbir Singh \u003cbalbir@in.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": "90254a65833b67502d14736410b3857a15535c67", "tree": "e03ec501b4a585c0d112469f36100ec41a715345", "parents": [ "3c11ecf448eff8f12922c498b8274ce98587eb74" ], "author": { "name": "Daisuke Nishimura", "email": "nishimura@mxp.nes.nec.co.jp", "time": "Wed May 26 14:42:38 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu May 27 09:12:43 2010 -0700" }, "message": "memcg: clean up move charge\n\nThis patch cleans up move charge code by:\n\n- define functions to handle pte for each types, and make\n is_target_pte_for_mc() cleaner.\n\n- instead of checking the MOVE_CHARGE_TYPE_ANON bit, define a function\n that checks the bit.\n\nSigned-off-by: Daisuke Nishimura \u003cnishimura@mxp.nes.nec.co.jp\u003e\nAcked-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Balbir Singh \u003cbalbir@in.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": "3c11ecf448eff8f12922c498b8274ce98587eb74", "tree": "0a28aeef7759ead93ff58fd7db2fe61797523f7e", "parents": [ "9490ff275606da012d5b373342a49610ad61cb81" ], "author": { "name": "KAMEZAWA Hiroyuki", "email": "kamezawa.hiroyu@jp.fujitsu.com", "time": "Wed May 26 14:42:37 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu May 27 09:12:43 2010 -0700" }, "message": "memcg: oom kill disable and oom status\n\nThis adds a feature to disable oom-killer for memcg, if disabled, of\ncourse, tasks under memcg will stop.\n\nBut now, we have oom-notifier for memcg. And the world around memcg is\nnot under out-of-memory. memcg\u0027s out-of-memory just shows memcg hits\nlimit. Then, administrator or management daemon can recover the situation\nby\n\n\t- kill some process\n\t- enlarge limit, add more swap.\n\t- migrate some tasks\n\t- remove file cache on tmps (difficult ?)\n\nUnlike oom-killer, you can take enough information before killing tasks.\n(by gcore, or, ps etc.)\n\n[akpm@linux-foundation.org: coding-style fixes]\nSigned-off-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: 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\nCc: David Rientjes \u003crientjes@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": "9490ff275606da012d5b373342a49610ad61cb81", "tree": "037993e807654da633776066129b001f8bae7d1d", "parents": [ "dc98df5a1b7be402a0e1c71f1b89ccf249ac15ee" ], "author": { "name": "KAMEZAWA Hiroyuki", "email": "kamezawa.hiroyu@jp.fujitsu.com", "time": "Wed May 26 14:42:36 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu May 27 09:12:43 2010 -0700" }, "message": "memcg: oom notifier\n\nConsidering containers or other resource management softwares in userland,\nevent notification of OOM in memcg should be implemented. Now, memcg has\n\"threshold\" notifier which uses eventfd, we can make use of it for oom\nnotification.\n\nThis patch adds oom notification eventfd callback for memcg. The usage is\nvery similar to threshold notifier, but control file is memory.oom_control\nand no arguments other than eventfd is required.\n\n\t% cgroup_event_notifier /cgroup/A/memory.oom_control dummy\n\t(About cgroup_event_notifier, see Documentation/cgroup/)\n\nSigned-off-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: 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\nCc: David Rientjes \u003crientjes@google.com\u003e\nCc: Davide Libenzi \u003cdavidel@xmailserver.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "dc98df5a1b7be402a0e1c71f1b89ccf249ac15ee", "tree": "d54f48e26563eadd11114c787b5c27b4e44ebb19", "parents": [ "595f4b694c2424f2af6e1de74c955bbe9cd7b73d" ], "author": { "name": "KAMEZAWA Hiroyuki", "email": "kamezawa.hiroyu@jp.fujitsu.com", "time": "Wed May 26 14:42:36 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu May 27 09:12:43 2010 -0700" }, "message": "memcg: oom wakeup filter\n\nmemcg\u0027s oom waitqueue is a system-wide wait_queue (for handling\nhierarchy.) So, it\u0027s better to add custom wake function and do filtering\nin wake up path.\n\nThis patch adds a filtering feature for waking up oom-waiters. Hierarchy\nis properly handled.\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@in.ibm.com\u003e\nCc: Daisuke Nishimura \u003cnishimura@mxp.nes.nec.co.jp\u003e\nCc: David Rientjes \u003crientjes@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": "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": "3c7b204547bc3d342a4e31196fe14803581d279f", "tree": "87a3300d266eed413012efd0a985a72caad4a856", "parents": [ "0cae3457b1a6e88f31020272bcfd90c178716053" ], "author": { "name": "Bernd Schmidt", "email": "bernds_cb1@t-online.de", "time": "Tue May 25 23:43:00 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed May 26 08:19:23 2010 -0700" }, "message": "nommu: allow private mappings of read-only devices\n\nSlightly rearrange the logic that determines capabilities and vm_flags.\nDisable BDI_CAP_MAP_DIRECT in all cases if the device can\u0027t support the\nprotections. Allow private readonly mappings of readonly backing devices.\n\nSigned-off-by: Bernd Schmidt \u003cbernds_cb1@t-online.de\u003e\nSigned-off-by: Mike Frysinger \u003cvapier@gentoo.org\u003e\nAcked-by: David McCullough \u003cdavidm@snapgear.com\u003e\nAcked-by: Greg Ungerer \u003cgerg@uclinux.org\u003e\nAcked-by: Paul Mundt \u003clethal@linux-sh.org\u003e\nAcked-by: David Howells \u003cdhowells@redhat.com\u003e\nCc: Hugh Dickins \u003chughd@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": "0cae3457b1a6e88f31020272bcfd90c178716053", "tree": "71cf3f4049e9e80a5dd71219bd74061e8587a643", "parents": [ "b1cdc4670b9508fcd47a15fbd12f70d269880b37" ], "author": { "name": "Dan Carpenter", "email": "error27@gmail.com", "time": "Tue May 25 23:42:58 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed May 26 08:19:23 2010 -0700" }, "message": "mempolicy: ERR_PTR dereference in mpol_shared_policy_init()\n\nThe original code called mpol_put(new) while \"new\" was an ERR_PTR.\n\nSigned-off-by: Dan Carpenter \u003cerror27@gmail.com\u003e\nCc: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nAcked-by: David Rientjes \u003crientjes@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": "4eaf3f64397c3db3c5785eee508270d62a9fabd9", "tree": "bfd986a7e974876755ea6fe0de394199c68e2e36", "parents": [ "1f522509c77a5dea8dc384b735314f03908a6415" ], "author": { "name": "Haicheng Li", "email": "haicheng.li@linux.intel.com", "time": "Mon May 24 14:32:52 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:07:02 2010 -0700" }, "message": "mem-hotplug: fix potential race while building zonelist for new populated zone\n\nAdd global mutex zonelists_mutex to fix the possible race:\n\n CPU0 CPU1 CPU2\n(1) zone-\u003epresent_pages +\u003d online_pages;\n(2) build_all_zonelists();\n(3) alloc_page();\n(4) free_page();\n(5) build_all_zonelists();\n(6) __build_all_zonelists();\n(7) zone-\u003epageset \u003d alloc_percpu();\n\nIn step (3,4), zone-\u003epageset still points to boot_pageset, so bad\nthings may happen if 2+ nodes are in this state. Even if only 1 node\nis accessing the boot_pageset, (3) may still consume too much memory\nto fail the memory allocations in step (7).\n\nBesides, atomic operation ensures alloc_percpu() in step (7) will never fail\nsince there is a new fresh memory block added in step(6).\n\n[haicheng.li@linux.intel.com: hold zonelists_mutex when build_all_zonelists]\nSigned-off-by: Haicheng Li \u003chaicheng.li@linux.intel.com\u003e\nSigned-off-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nReviewed-by: Andi Kleen \u003candi.kleen@intel.com\u003e\nCc: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: Tejun Heo \u003ctj@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": "1f522509c77a5dea8dc384b735314f03908a6415", "tree": "4b848527b90877a8a64c46e8e2d76723405c319d", "parents": [ "319774e25fa4b7641bdc3b0a464dd84e62103347" ], "author": { "name": "Haicheng Li", "email": "haicheng.li@linux.intel.com", "time": "Mon May 24 14:32:51 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:07:01 2010 -0700" }, "message": "mem-hotplug: avoid multiple zones sharing same boot strapping boot_pageset\n\nFor each new populated zone of hotadded node, need to update its pagesets\nwith dynamically allocated per_cpu_pageset struct for all possible CPUs:\n\n 1) Detach zone-\u003epageset from the shared boot_pageset\n at end of __build_all_zonelists().\n\n 2) Use mutex to protect zone-\u003epageset when it\u0027s still\n shared in onlined_pages()\n\nOtherwises, multiple zones of different nodes would share same boot strapping\nboot_pageset for same CPU, which will finally cause below kernel panic:\n\n ------------[ cut here ]------------\n kernel BUG at mm/page_alloc.c:1239!\n invalid opcode: 0000 [#1] SMP\n ...\n Call Trace:\n [\u003cffffffff811300c1\u003e] __alloc_pages_nodemask+0x131/0x7b0\n [\u003cffffffff81162e67\u003e] alloc_pages_current+0x87/0xd0\n [\u003cffffffff81128407\u003e] __page_cache_alloc+0x67/0x70\n [\u003cffffffff811325f0\u003e] __do_page_cache_readahead+0x120/0x260\n [\u003cffffffff81132751\u003e] ra_submit+0x21/0x30\n [\u003cffffffff811329c6\u003e] ondemand_readahead+0x166/0x2c0\n [\u003cffffffff81132ba0\u003e] page_cache_async_readahead+0x80/0xa0\n [\u003cffffffff8112a0e4\u003e] generic_file_aio_read+0x364/0x670\n [\u003cffffffff81266cfa\u003e] nfs_file_read+0xca/0x130\n [\u003cffffffff8117b20a\u003e] do_sync_read+0xfa/0x140\n [\u003cffffffff8117bf75\u003e] vfs_read+0xb5/0x1a0\n [\u003cffffffff8117c151\u003e] sys_read+0x51/0x80\n [\u003cffffffff8103c032\u003e] system_call_fastpath+0x16/0x1b\n RIP [\u003cffffffff8112ff13\u003e] get_page_from_freelist+0x883/0x900\n RSP \u003cffff88000d1e78a8\u003e\n ---[ end trace 4bda28328b9990db ]\n\n[akpm@linux-foundation.org: merge fix]\nSigned-off-by: Haicheng Li \u003chaicheng.li@linux.intel.com\u003e\nSigned-off-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nReviewed-by: Andi Kleen \u003candi.kleen@intel.com\u003e\nReviewed-by: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: Tejun Heo \u003ctj@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": "319774e25fa4b7641bdc3b0a464dd84e62103347", "tree": "6865aee1b58fff5d7042fbdcb989ee7751660bcc", "parents": [ "0faa56389c793cda7f967117415717bbab24fe4e" ], "author": { "name": "Wu Fengguang", "email": "fengguang.wu@intel.com", "time": "Mon May 24 14:32:49 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:07:01 2010 -0700" }, "message": "mem-hotplug: separate setup_per_cpu_pageset() into separate functions\n\nNo behavior change here.\n\nMove some of setup_per_cpu_pageset() code into a new function\nsetup_zone_pageset() that will be useful for memory hotplug.\n\nSigned-off-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nSigned-off-by: Haicheng Li \u003chaicheng.li@linux.intel.com\u003e\nReviewed-by: Andi Kleen \u003candi.kleen@intel.com\u003e\nReviewed-by: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: Tejun Heo \u003ctj@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": "ff3d58c22b6827039983911d3460cf0c1657f8cc", "tree": "bed2f2f98760425976a45858326de80aa5e7760b", "parents": [ "fd23855e38d2a7275a786238459c070b4e9f7975" ], "author": { "name": "Akinobu Mita", "email": "akinobu.mita@gmail.com", "time": "Mon May 24 14:32:46 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:07:01 2010 -0700" }, "message": "highmem: remove unneeded #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT for debug_kmap_atomic()\n\nIn f4112de6b679d84bd9b9681c7504be7bdfb7c7d5 (\"mm: introduce\ndebug_kmap_atomic\") I said that debug_kmap_atomic() needs\nCONFIG_TRACE_IRQFLAGS_SUPPORT.\n\nIt was wrong. (I thought irqs_disabled() is only available when the\narchitecture has CONFIG_TRACE_IRQFLAGS_SUPPORT)\n\nRemove the #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT check to enable\nkmap_atomic() debugging for the architectures which do not have\nCONFIG_TRACE_IRQFLAGS_SUPPORT.\n\nReported-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Akinobu Mita \u003cakinobu.mita@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": "cf23422b9d76215316855253da491d4c9f294372", "tree": "5663d2519d83d830d24dffdf2571d58d3e55d3f6", "parents": [ "8b25c6d2231b978ccce9c401e771932bde79aa9f" ], "author": { "name": "minskey guo", "email": "chaohong_guo@linux.intel.com", "time": "Mon May 24 14:32:41 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:07:00 2010 -0700" }, "message": "cpu/mem hotplug: enable CPUs online before local memory online\n\nEnable users to online CPUs even if the CPUs belongs to a numa node which\ndoesn\u0027t have onlined local memory.\n\nThe zonlists(pg_data_t.node_zonelists[]) of a numa node are created either\nin system boot/init period, or at the time of local memory online. For a\nnuma node without onlined local memory, its zonelists are not initialized\nat present. As a result, any memory allocation operations executed by\nCPUs within this node will fail. In fact, an out-of-memory error is\ntriggered when attempt to online CPUs before memory comes to online.\n\nThis patch tries to create zonelists for such numa nodes, so that the\nmemory allocation for this node can be fallback\u0027ed to other nodes.\n\n[akpm@linux-foundation.org: remove unneeded export]\n[akpm@linux-foundation.org: coding-style fixes]\nSigned-off-by: minskey guo\u003cchaohong.guo@intel.com\u003e\nCc: Minchan Kim \u003cminchan.kim@gmail.com\u003e\nCc: Yasunori Goto \u003cy-goto@jp.fujitsu.com\u003e\nCc: Andi Kleen \u003candi@firstfloor.org\u003e\nCc: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: Tejun Heo \u003ctj@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": "8b25c6d2231b978ccce9c401e771932bde79aa9f", "tree": "13845799e14e49465de1529680df7def59dcfeb8", "parents": [ "0aeb2339e54e40d0788a7017ecaeac7f5271e262" ], "author": { "name": "Johannes Weiner", "email": "hannes@cmpxchg.org", "time": "Mon May 24 14:32:40 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:07:00 2010 -0700" }, "message": "vmscan: remove isolate_pages callback scan control\n\nFor now, we have global isolation vs. memory control group isolation, do\nnot allow the reclaim entry function to set an arbitrary page isolation\ncallback, we do not need that flexibility.\n\nAnd since we already pass around the group descriptor for the memory\ncontrol group isolation case, just use it to decide which one of the two\nisolator functions to use.\n\nThe decisions can be merged into nearby branches, so no extra cost there.\nIn fact, we save the indirect calls.\n\nSigned-off-by: Johannes Weiner \u003channes@cmpxchg.org\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: Rik van Riel \u003criel@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": "0aeb2339e54e40d0788a7017ecaeac7f5271e262", "tree": "66889ce248257e7e24c998a22994ccef222e4622", "parents": [ "142762bd8d8c46345e79f0f68d3374564306972f" ], "author": { "name": "Johannes Weiner", "email": "hannes@cmpxchg.org", "time": "Mon May 24 14:32:40 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:07:00 2010 -0700" }, "message": "vmscan: remove all_unreclaimable scan control\n\nThis scan control is abused to communicate a return value from\nshrink_zones(). Write this idiomatically and remove the knob.\n\nSigned-off-by: Johannes Weiner \u003channes@cmpxchg.org\u003e\nReviewed-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: Rik van Riel \u003criel@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": "142762bd8d8c46345e79f0f68d3374564306972f", "tree": "c33360b872883d24b068ba7b8f01466fccb9dfc9", "parents": [ "58a9d3d8db06ca2ec31f64ec49ab0aeb89971b85" ], "author": { "name": "Johannes Weiner", "email": "hannes@cmpxchg.org", "time": "Mon May 24 14:32:39 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:07:00 2010 -0700" }, "message": "mm: document follow_page()\n\nSigned-off-by: Johannes Weiner \u003channes@cmpxchg.org\u003e\nCc: Dan Carpenter \u003cerror27@gmail.com\u003e\nCc: Rik van Riel \u003criel@redhat.com\u003e\nCc: Izik Eidus \u003cieidus@redhat.com\u003e\nCc: Andrea Arcangeli \u003caarcange@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": "ec95f53aa6ed62ba68660cb19c8474ebe9025cce", "tree": "953ad71c8ee0373ca76f17ee9df65358ad2fe7b7", "parents": [ "5f53e76299ceebd68bdf9495e8ff80db77711236" ], "author": { "name": "KOSAKI Motohiro", "email": "kosaki.motohiro@jp.fujitsu.com", "time": "Mon May 24 14:32:38 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:07:00 2010 -0700" }, "message": "mm: introduce free_pages_prepare()\n\nfree_hot_cold_page() and __free_pages_ok() have very similar freeing\npreparation. Consolidate them.\n\n[akpm@linux-foundation.org: fix busted coding style]\nSigned-off-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nAcked-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "5f53e76299ceebd68bdf9495e8ff80db77711236", "tree": "2ecb8324a6593a49868161d85511cc14d474900a", "parents": [ "bf8abe8b926f7546eb763fd2a088fe461dde6317" ], "author": { "name": "KOSAKI Motohiro", "email": "kosaki.motohiro@jp.fujitsu.com", "time": "Mon May 24 14:32:37 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:07:00 2010 -0700" }, "message": "vmscan: page_check_references(): check low order lumpy reclaim properly\n\nIf vmscan is under lumpy reclaim mode, it have to ignore referenced bit\nfor making contenious free pages. but current page_check_references()\ndoesn\u0027t.\n\nFix it.\n\nSigned-off-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nReviewed-by: Minchan Kim \u003cminchan.kim@gmail.com\u003e\nCc: Rik van Riel \u003criel@redhat.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": "bf8abe8b926f7546eb763fd2a088fe461dde6317", "tree": "e9bba65d267d974c2c429b01dde393363789ee7f", "parents": [ "76a33fc380c9a65e01eb15b3b87c05863a0d51db" ], "author": { "name": "Huang Shijie", "email": "shijie8@gmail.com", "time": "Mon May 24 14:32:36 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:07:00 2010 -0700" }, "message": "readahead.c: fix comment\n\nFix a wrong comment over page_cache_async_readahead().\n\nSigned-off-by: Huang Shijie \u003cshijie8@gmail.com\u003e\nAcked-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": "76a33fc380c9a65e01eb15b3b87c05863a0d51db", "tree": "506db7a03eb41e245a859ac241ff0680097427e5", "parents": [ "6ec3a12712ac67ffa4b80d16e0767ffd2431a68d" ], "author": { "name": "Shaohua Li", "email": "shaohua.li@intel.com", "time": "Mon May 24 14:32:36 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:07:00 2010 -0700" }, "message": "vmscan: prevent get_scan_ratio() rounding errors\n\nget_scan_ratio() calculates percentage and if the percentage is \u003c 1%, it\nwill round percentage down to 0% and cause we completely ignore scanning\nanon/file pages to reclaim memory even the total anon/file pages are very\nbig.\n\nTo avoid underflow, we don\u0027t use percentage, instead we directly calculate\nhow many pages should be scaned. In this way, we should get several\nscanned pages for \u003c 1% percent.\n\nThis has some benefits:\n\n1. increase our calculation precision\n\n2. making our scan more smoothly. Without this, if percent[x] is\n underflow, shrink_zone() doesn\u0027t scan any pages and suddenly it scans\n all pages when priority is zero. With this, even priority isn\u0027t zero,\n shrink_zone() gets chance to scan some pages.\n\nNote, this patch doesn\u0027t really change logics, but just increase\nprecision. For system with a lot of memory, this might slightly changes\nbehavior. For example, in a sequential file read workload, without the\npatch, we don\u0027t swap any anon pages. With it, if anon memory size is\nbigger than 16G, we will see one anon page swapped. The 16G is calculated\nas PAGE_SIZE * priority(4096) * (fp/ap). fp/ap is assumed to be 1024\nwhich is common in this workload. So the impact sounds not a big deal.\n\nSigned-off-by: Shaohua Li \u003cshaohua.li@intel.com\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nAcked-by: Rik van Riel \u003criel@redhat.com\u003e\nCc: 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": "6ec3a12712ac67ffa4b80d16e0767ffd2431a68d", "tree": "7348f7ce38efe041429a2477706181686992e801", "parents": [ "4f92e2586b43a2402e116055d4edda704f911b5b" ], "author": { "name": "Greg Thelen", "email": "gthelen@google.com", "time": "Mon May 24 14:32:33 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:07:00 2010 -0700" }, "message": "mm: consider the entire user address space during node migration\n\nUse mm-\u003etask_size instead of TASK_SIZE to ensure that the entire user\naddress space is migrated. mm-\u003etask_size is independent of the calling\ntask context. TASK SIZE may be dependant on the address space size of the\ncalling process. Usage of TASK_SIZE can lead to partial address space\nmigration if the calling process was 32 bit and the migrating process was\n64 bit.\n\nHere is the test script used on 64 system with a 32 bit echo process:\n\n mount -t cgroup none /cgroup -o cpuset\n cd /cgroup\n\n mkdir 0\n echo 1 \u003e 0/cpuset.cpus\n echo 0 \u003e 0/cpuset.mems\n echo 1 \u003e 0/cpuset.memory_migrate\n\n mkdir 1\n echo 1 \u003e 1/cpuset.cpus\n echo 1 \u003e 1/cpuset.mems\n echo 1 \u003e 1/cpuset.memory_migrate\n\n echo $$ \u003e 0/tasks\n 64_bit_process \u0026\n pid\u003d$!\n\n echo $pid \u003e 1/tasks # This does not migrate all process pages without\n # this patch. If 64 bit echo is used or this patch is\n # applied, then the full address space of $pid is\n # migrated.\n\nTo check memory migration, I watched:\n grep MemUsed /sys/devices/system/node/node*/meminfo\n\nSigned-off-by: Greg Thelen \u003cgthelen@google.com\u003e\nAcked-by: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nReviewed-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Daisuke Nishimura \u003cnishimura@mxp.nes.nec.co.jp\u003e\nCc: Balbir Singh \u003cbalbir@in.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": "4f92e2586b43a2402e116055d4edda704f911b5b", "tree": "6a765ebeba951c02a7878bcea52a4769ad2e45c2", "parents": [ "5e7719058079a1423ccce56148b0aaa56b2df821" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Mon May 24 14:32:32 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:07:00 2010 -0700" }, "message": "mm: compaction: defer compaction using an exponential backoff when compaction fails\n\nThe fragmentation index may indicate that a failure is due to external\nfragmentation but after a compaction run completes, it is still possible\nfor an allocation to fail. There are two obvious reasons as to why\n\n o Page migration cannot move all pages so fragmentation remains\n o A suitable page may exist but watermarks are not met\n\nIn the event of compaction followed by an allocation failure, this patch\ndefers further compaction in the zone (1 \u003c\u003c compact_defer_shift) times.\nIf the next compaction attempt also fails, compact_defer_shift is\nincreased up to a maximum of 6. If compaction succeeds, the defer\ncounters are reset again.\n\nThe zone that is deferred is the first zone in the zonelist - i.e. the\npreferred zone. To defer compaction in the other zones, the information\nwould need to be stored in the zonelist or implemented similar to the\nzonelist_cache. This would impact the fast-paths and is not justified at\nthis time.\n\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: Rik van Riel \u003criel@redhat.com\u003e\nCc: Minchan Kim \u003cminchan.kim@gmail.com\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: 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": "5e7719058079a1423ccce56148b0aaa56b2df821", "tree": "3666cb3d5540dcaa3d8e7df8c293a0ad603a181c", "parents": [ "56de7263fcf3eb10c8dcdf8d59a9cec831795f3f" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Mon May 24 14:32:31 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:06:59 2010 -0700" }, "message": "mm: compaction: add a tunable that decides when memory should be compacted and when it should be reclaimed\n\nThe kernel applies some heuristics when deciding if memory should be\ncompacted or reclaimed to satisfy a high-order allocation. One of these\nis based on the fragmentation. If the index is below 500, memory will not\nbe compacted. This choice is arbitrary and not based on data. To help\noptimise the system and set a sensible default for this value, this patch\nadds a sysctl extfrag_threshold. The kernel will only compact memory if\nthe fragmentation index is above the extfrag_threshold.\n\n[randy.dunlap@oracle.com: Fix build errors when proc fs is not configured]\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nSigned-off-by: Randy Dunlap \u003crandy.dunlap@oracle.com\u003e\nCc: Rik van Riel \u003criel@redhat.com\u003e\nCc: Minchan Kim \u003cminchan.kim@gmail.com\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: 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": "56de7263fcf3eb10c8dcdf8d59a9cec831795f3f", "tree": "164637c0b678e20adfdcec4129563d9234faf405", "parents": [ "ed4a6d7f0676db50b5023cc01f6cda82a2f2a307" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Mon May 24 14:32:30 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:06:59 2010 -0700" }, "message": "mm: compaction: direct compact when a high-order allocation fails\n\nOrdinarily when a high-order allocation fails, direct reclaim is entered\nto free pages to satisfy the allocation. With this patch, it is\ndetermined if an allocation failed due to external fragmentation instead\nof low memory and if so, the calling process will compact until a suitable\npage is freed. Compaction by moving pages in memory is considerably\ncheaper than paging out to disk and works where there are locked pages or\nno swap. If compaction fails to free a page of a suitable size, then\nreclaim will still occur.\n\nDirect compaction returns as soon as possible. As each block is\ncompacted, it is checked if a suitable page has been freed and if so, it\nreturns.\n\n[akpm@linux-foundation.org: Fix build errors]\n[aarcange@redhat.com: fix count_vm_event preempt in memory compaction direct reclaim]\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nAcked-by: Rik van Riel \u003criel@redhat.com\u003e\nReviewed-by: Minchan Kim \u003cminchan.kim@gmail.com\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nSigned-off-by: Andrea Arcangeli \u003caarcange@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": "ed4a6d7f0676db50b5023cc01f6cda82a2f2a307", "tree": "6496343ba964e105cf30f8703714471f22edc806", "parents": [ "76ab0f530e4a01d4dc20cdc1d5e87753c579dc18" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Mon May 24 14:32:29 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:06:59 2010 -0700" }, "message": "mm: compaction: add /sys trigger for per-node memory compaction\n\nAdd a per-node sysfs file called compact. When the file is written to,\neach zone in that node is compacted. The intention that this would be\nused by something like a job scheduler in a batch system before a job\nstarts so that the job can allocate the maximum number of hugepages\nwithout significant start-up cost.\n\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nAcked-by: Rik van Riel \u003criel@redhat.com\u003e\nReviewed-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nReviewed-by: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nReviewed-by: Minchan Kim \u003cminchan.kim@gmail.com\u003e\nReviewed-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": "76ab0f530e4a01d4dc20cdc1d5e87753c579dc18", "tree": "8e1566df85e02f67876685c36d217fec4845f79f", "parents": [ "748446bb6b5a9390b546af38ec899c868a9dbcf0" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Mon May 24 14:32:28 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:06:59 2010 -0700" }, "message": "mm: compaction: add /proc trigger for memory compaction\n\nAdd a proc file /proc/sys/vm/compact_memory. When an arbitrary value is\nwritten to the file, all zones are compacted. The expected user of such a\ntrigger is a job scheduler that prepares the system before the target\napplication runs.\n\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nAcked-by: Rik van Riel \u003criel@redhat.com\u003e\nReviewed-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nReviewed-by: Minchan Kim \u003cminchan.kim@gmail.com\u003e\nReviewed-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nReviewed-by: Christoph Lameter \u003ccl@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": "748446bb6b5a9390b546af38ec899c868a9dbcf0", "tree": "4c27d0805a5e094b39ff938ad60dd270b953a79f", "parents": [ "c175a0ce7584e5b498fff8cbdb9aa7912aa9fbba" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Mon May 24 14:32:27 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:06:59 2010 -0700" }, "message": "mm: compaction: memory compaction core\n\nThis patch is the core of a mechanism which compacts memory in a zone by\nrelocating movable pages towards the end of the zone.\n\nA single compaction run involves a migration scanner and a free scanner.\nBoth scanners operate on pageblock-sized areas in the zone. The migration\nscanner starts at the bottom of the zone and searches for all movable\npages within each area, isolating them onto a private list called\nmigratelist. The free scanner starts at the top of the zone and searches\nfor suitable areas and consumes the free pages within making them\navailable for the migration scanner. The pages isolated for migration are\nthen migrated to the newly isolated free pages.\n\n[aarcange@redhat.com: Fix unsafe optimisation]\n[mel@csn.ul.ie: do not schedule work on other CPUs for compaction]\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nAcked-by: Rik van Riel \u003criel@redhat.com\u003e\nReviewed-by: Minchan Kim \u003cminchan.kim@gmail.com\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: 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": "c175a0ce7584e5b498fff8cbdb9aa7912aa9fbba", "tree": "dd924daef4a9e0ac9729c5b61c30b8e3cc96f971", "parents": [ "f1a5ab1210579e2d3ac8c0c227645823af5aafb0" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Mon May 24 14:32:26 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:06:59 2010 -0700" }, "message": "mm: move definition for LRU isolation modes to a header\n\nCurrently, vmscan.c defines the isolation modes for __isolate_lru_page().\nMemory compaction needs access to these modes for isolating pages for\nmigration. This patch exports them.\n\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nAcked-by: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: Rik van Riel \u003criel@redhat.com\u003e\nCc: Minchan Kim \u003cminchan.kim@gmail.com\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: 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": "f1a5ab1210579e2d3ac8c0c227645823af5aafb0", "tree": "c646a3d58150eab1a8280d02e6254ef6b90a6f37", "parents": [ "d7a5752c0c19750312efab3a2a80d350e11fa4a2" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Mon May 24 14:32:26 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:06:59 2010 -0700" }, "message": "mm: export fragmentation index via debugfs\n\nThe fragmentation fragmentation index, is only meaningful if an allocation\nwould fail and indicates what the failure is due to. A value of -1 such\nas in many of the examples above states that the allocation would succeed.\n If it would fail, the value is between 0 and 1. A value tending towards\n0 implies the allocation failed due to a lack of memory. A value tending\ntowards 1 implies it failed due to external fragmentation.\n\nFor the most part, the huge page size will be the size of interest but not\nnecessarily so it is exported on a per-order and per-zo basis via\n/sys/kernel/debug/extfrag/extfrag_index\n\n\u003e cat /sys/kernel/debug/extfrag/extfrag_index\nNode 0, zone DMA -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.00\nNode 0, zone Normal -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 -1.000 0.954\n\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nReviewed-by: Minchan Kim \u003cminchan.kim@gmail.com\u003e\nAcked-by: Rik van Riel \u003criel@redhat.com\u003e\nReviewed-by: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: 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": "d7a5752c0c19750312efab3a2a80d350e11fa4a2", "tree": "f604d9ae1d7f689e3314120e2d4edac36c1b5f22", "parents": [ "a8bef8ff6ea15fa4c67433cab0f5f3484574ef7c" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Mon May 24 14:32:25 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:06:59 2010 -0700" }, "message": "mm: export unusable free space index via debugfs\n\nThe unusable free space index measures how much of the available free\nmemory cannot be used to satisfy an allocation of a given size and is a\nvalue between 0 and 1. The higher the value, the more of free memory is\nunusable and by implication, the worse the external fragmentation is. For\nthe most part, the huge page size will be the size of interest but not\nnecessarily so it is exported on a per-order and per-zone basis via\n/sys/kernel/debug/extfrag/unusable_index.\n\n\u003e cat /sys/kernel/debug/extfrag/unusable_index\nNode 0, zone DMA 0.000 0.000 0.000 0.001 0.005 0.013 0.021 0.037 0.037 0.101 0.230\nNode 0, zone Normal 0.000 0.000 0.000 0.001 0.002 0.002 0.005 0.015 0.028 0.028 0.054\n\n[akpm@linux-foundation.org: Fix allnoconfig]\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nReviewed-by: Minchan Kim \u003cminchan.kim@gmail.com\u003e\nReviewed-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nReviewed-by: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: Rik van Riel \u003criel@redhat.com\u003e\nCc: 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": "a8bef8ff6ea15fa4c67433cab0f5f3484574ef7c", "tree": "3ea9c122e02f523379d4560ee2134124d097895c", "parents": [ "e9e96b39f932a065e14f5d5bab0797ae261d03b5" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Mon May 24 14:32:24 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:06:59 2010 -0700" }, "message": "mm: migration: avoid race between shift_arg_pages() and rmap_walk() during migration by not migrating temporary stacks\n\nPage migration requires rmap to be able to find all ptes mapping a page\nat all times, otherwise the migration entry can be instantiated, but it\nis possible to leave one behind if the second rmap_walk fails to find\nthe page. If this page is later faulted, migration_entry_to_page() will\ncall BUG because the page is locked indicating the page was migrated by\nthe migration PTE not cleaned up. For example\n\n kernel BUG at include/linux/swapops.h:105!\n invalid opcode: 0000 [#1] PREEMPT SMP\n ...\n Call Trace:\n [\u003cffffffff810e951a\u003e] handle_mm_fault+0x3f8/0x76a\n [\u003cffffffff8130c7a2\u003e] do_page_fault+0x44a/0x46e\n [\u003cffffffff813099b5\u003e] page_fault+0x25/0x30\n [\u003cffffffff8114de33\u003e] load_elf_binary+0x152a/0x192b\n [\u003cffffffff8111329b\u003e] search_binary_handler+0x173/0x313\n [\u003cffffffff81114896\u003e] do_execve+0x219/0x30a\n [\u003cffffffff8100a5c6\u003e] sys_execve+0x43/0x5e\n [\u003cffffffff8100320a\u003e] stub_execve+0x6a/0xc0\n RIP [\u003cffffffff811094ff\u003e] migration_entry_wait+0xc1/0x129\n\nThere is a race between shift_arg_pages and migration that triggers this\nbug. A temporary stack is setup during exec and later moved. If\nmigration moves a page in the temporary stack and the VMA is then removed\nbefore migration completes, the migration PTE may not be found leading to\na BUG when the stack is faulted.\n\nThis patch causes pages within the temporary stack during exec to be\nskipped by migration. It does this by marking the VMA covering the\ntemporary stack with an otherwise impossible combination of VMA flags.\nThese flags are cleared when the temporary stack is moved to its final\nlocation.\n\n[kamezawa.hiroyu@jp.fujitsu.com: idea for having migration skip temporary stacks]\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nReviewed-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nReviewed-by: Rik van Riel \u003criel@redhat.com\u003e\nAcked-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\nCc: Minchan Kim \u003cminchan.kim@gmail.com\u003e\nCc: Christoph Lameter \u003ccl@linux.com\u003e\nCc: Andrea Arcangeli \u003caarcange@redhat.com\u003e\nCc: Rik van Riel \u003criel@redhat.com\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nReviewed-by: 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": "e9e96b39f932a065e14f5d5bab0797ae261d03b5", "tree": "1164a4bf40c34715944b47da035ba823f1d8b60a", "parents": [ "3fe2011ff51e92500010a495df4be86745fbbda9" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Mon May 24 14:32:21 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:06:59 2010 -0700" }, "message": "mm: allow CONFIG_MIGRATION to be set without CONFIG_NUMA or memory hot-remove\n\nCONFIG_MIGRATION currently depends on CONFIG_NUMA or on the architecture\nbeing able to hot-remove memory. The main users of page migration such as\nsys_move_pages(), sys_migrate_pages() and cpuset process migration are\nonly beneficial on NUMA so it makes sense.\n\nAs memory compaction will operate within a zone and is useful on both NUMA\nand non-NUMA systems, this patch allows CONFIG_MIGRATION to be set if the\nuser selects CONFIG_COMPACTION as an option.\n\n[akpm@linux-foundation.org: Depend on CONFIG_HUGETLB_PAGE]\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nReviewed-by: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nReviewed-by: Rik van Riel \u003criel@redhat.com\u003e\nReviewed-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Minchan Kim \u003cminchan.kim@gmail.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": "3fe2011ff51e92500010a495df4be86745fbbda9", "tree": "f3dc07b9d41ce5ba15805c2d3b4bc0a1a7916832", "parents": [ "67b9509b2c68ae38cecb83a239881cb0ddf087dc" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Mon May 24 14:32:20 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:06:59 2010 -0700" }, "message": "mm: migration: allow the migration of PageSwapCache pages\n\nPageAnon pages that are unmapped may or may not have an anon_vma so are\nnot currently migrated. However, a swap cache page can be migrated and\nfits this description. This patch identifies page swap caches and allows\nthem to be migrated but ensures that no attempt to made to remap the pages\nwould would potentially try to access an already freed anon_vma.\n\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nReviewed-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nReviewed-by: Minchan Kim \u003cminchan.kim@gmail.com\u003e\nCc: Rik van Riel \u003criel@redhat.com\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Christoph Lameter \u003ccl@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": "67b9509b2c68ae38cecb83a239881cb0ddf087dc", "tree": "a8cee4f4bec57ab44a993ce81df2a10a4980f0f8", "parents": [ "7f60c214fd3a360461f3286c6908084f7f8b1950" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Mon May 24 14:32:19 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:06:58 2010 -0700" }, "message": "mm: migration: do not try to migrate unmapped anonymous pages\n\nrmap_walk_anon() was triggering errors in memory compaction that look like\nuse-after-free errors. The problem is that between the page being\nisolated from the LRU and rcu_read_lock() being taken, the mapcount of the\npage dropped to 0 and the anon_vma gets freed. This can happen during\nmemory compaction if pages being migrated belong to a process that exits\nbefore migration completes. Hence, the use-after-free race looks like\n\n 1. Page isolated for migration\n 2. Process exits\n 3. page_mapcount(page) drops to zero so anon_vma was no longer reliable\n 4. unmap_and_move() takes the rcu_lock but the anon_vma is already garbage\n 4. call try_to_unmap, looks up tha anon_vma and \"locks\" it but the lock\n is garbage.\n\nThis patch checks the mapcount after the rcu lock is taken. If the\nmapcount is zero, the anon_vma is assumed to be freed and no further\naction is taken.\n\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nAcked-by: Rik van Riel \u003criel@redhat.com\u003e\nReviewed-by: Minchan Kim \u003cminchan.kim@gmail.com\u003e\nReviewed-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Christoph Lameter \u003ccl@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": "7f60c214fd3a360461f3286c6908084f7f8b1950", "tree": "dba48cf988a22a40796187c7274f7903a288f7f4", "parents": [ "3f6c82728f4e31a97c3a1b32abccb512fed0b573" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Mon May 24 14:32:18 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:06:58 2010 -0700" }, "message": "mm: migration: share the anon_vma ref counts between KSM and page migration\n\nFor clarity of review, KSM and page migration have separate refcounts on\nthe anon_vma. While clear, this is a waste of memory. This patch gets\nKSM and page migration to share their toys in a spirit of harmony.\n\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nReviewed-by: Minchan Kim \u003cminchan.kim@gmail.com\u003e\nReviewed-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nReviewed-by: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nReviewed-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Rik van Riel \u003criel@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": "3f6c82728f4e31a97c3a1b32abccb512fed0b573", "tree": "4b577e789a5daef91e40d10bc71c8134b3874ae8", "parents": [ "e325c90ffc13b698fa2814102e05275b21c26bec" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Mon May 24 14:32:17 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:06:58 2010 -0700" }, "message": "mm: migration: take a reference to the anon_vma before migrating\n\nThis patchset is a memory compaction mechanism that reduces external\nfragmentation memory by moving GFP_MOVABLE pages to a fewer number of\npageblocks. The term \"compaction\" was chosen as there are is a number of\nmechanisms that are not mutually exclusive that can be used to defragment\nmemory. For example, lumpy reclaim is a form of defragmentation as was\nslub \"defragmentation\" (really a form of targeted reclaim). Hence, this\nis called \"compaction\" to distinguish it from other forms of\ndefragmentation.\n\nIn this implementation, a full compaction run involves two scanners\noperating within a zone - a migration and a free scanner. The migration\nscanner starts at the beginning of a zone and finds all movable pages\nwithin one pageblock_nr_pages-sized area and isolates them on a\nmigratepages list. The free scanner begins at the end of the zone and\nsearches on a per-area basis for enough free pages to migrate all the\npages on the migratepages list. As each area is respectively migrated or\nexhausted of free pages, the scanners are advanced one area. A compaction\nrun completes within a zone when the two scanners meet.\n\nThis method is a bit primitive but is easy to understand and greater\nsophistication would require maintenance of counters on a per-pageblock\nbasis. This would have a big impact on allocator fast-paths to improve\ncompaction which is a poor trade-off.\n\nIt also does not try relocate virtually contiguous pages to be physically\ncontiguous. However, assuming transparent hugepages were in use, a\nhypothetical khugepaged might reuse compaction code to isolate free pages,\nsplit them and relocate userspace pages for promotion.\n\nMemory compaction can be triggered in one of three ways. It may be\ntriggered explicitly by writing any value to /proc/sys/vm/compact_memory\nand compacting all of memory. It can be triggered on a per-node basis by\nwriting any value to /sys/devices/system/node/nodeN/compact where N is the\nnode ID to be compacted. When a process fails to allocate a high-order\npage, it may compact memory in an attempt to satisfy the allocation\ninstead of entering direct reclaim. Explicit compaction does not finish\nuntil the two scanners meet and direct compaction ends if a suitable page\nbecomes available that would meet watermarks.\n\nThe series is in 14 patches. The first three are not \"core\" to the series\nbut are important pre-requisites.\n\nPatch 1 reference counts anon_vma for rmap_walk_anon(). Without this\n\tpatch, it\u0027s possible to use anon_vma after free if the caller is\n\tnot holding a VMA or mmap_sem for the pages in question. While\n\tthere should be no existing user that causes this problem,\n\tit\u0027s a requirement for memory compaction to be stable. The patch\n\tis at the start of the series for bisection reasons.\nPatch 2 merges the KSM and migrate counts. It could be merged with patch 1\n\tbut would be slightly harder to review.\nPatch 3 skips over unmapped anon pages during migration as there are no\n\tguarantees about the anon_vma existing. There is a window between\n\twhen a page was isolated and migration started during which anon_vma\n\tcould disappear.\nPatch 4 notes that PageSwapCache pages can still be migrated even if they\n\tare unmapped.\nPatch 5 allows CONFIG_MIGRATION to be set without CONFIG_NUMA\nPatch 6 exports a \"unusable free space index\" via debugfs. It\u0027s\n\ta measure of external fragmentation that takes the size of the\n\tallocation request into account. It can also be calculated from\n\tuserspace so can be dropped if requested\nPatch 7 exports a \"fragmentation index\" which only has meaning when an\n\tallocation request fails. It determines if an allocation failure\n\twould be due to a lack of memory or external fragmentation.\nPatch 8 moves the definition for LRU isolation modes for use by compaction\nPatch 9 is the compaction mechanism although it\u0027s unreachable at this point\nPatch 10 adds a means of compacting all of memory with a proc trgger\nPatch 11 adds a means of compacting a specific node with a sysfs trigger\nPatch 12 adds \"direct compaction\" before \"direct reclaim\" if it is\n\tdetermined there is a good chance of success.\nPatch 13 adds a sysctl that allows tuning of the threshold at which the\n\tkernel will compact or direct reclaim\nPatch 14 temporarily disables compaction if an allocation failure occurs\n\tafter compaction.\n\nTesting of compaction was in three stages. For the test, debugging,\npreempt, the sleep watchdog and lockdep were all enabled but nothing nasty\npopped out. min_free_kbytes was tuned as recommended by hugeadm to help\nfragmentation avoidance and high-order allocations. It was tested on X86,\nX86-64 and PPC64.\n\nThs first test represents one of the easiest cases that can be faced for\nlumpy reclaim or memory compaction.\n\n1. Machine freshly booted and configured for hugepage usage with\n\ta) hugeadm --create-global-mounts\n\tb) hugeadm --pool-pages-max DEFAULT:8G\n\tc) hugeadm --set-recommended-min_free_kbytes\n\td) hugeadm --set-recommended-shmmax\n\n\tThe min_free_kbytes here is important. Anti-fragmentation works best\n\twhen pageblocks don\u0027t mix. hugeadm knows how to calculate a value that\n\twill significantly reduce the worst of external-fragmentation-related\n\tevents as reported by the mm_page_alloc_extfrag tracepoint.\n\n2. Load up memory\n\ta) Start updatedb\n\tb) Create in parallel a X files of pagesize*128 in size. Wait\n\t until files are created. By parallel, I mean that 4096 instances\n\t of dd were launched, one after the other using \u0026. The crude\n\t objective being to mix filesystem metadata allocations with\n\t the buffer cache.\n\tc) Delete every second file so that pageblocks are likely to\n\t have holes\n\td) kill updatedb if it\u0027s still running\n\n\tAt this point, the system is quiet, memory is full but it\u0027s full with\n\tclean filesystem metadata and clean buffer cache that is unmapped.\n\tThis is readily migrated or discarded so you\u0027d expect lumpy reclaim\n\tto have no significant advantage over compaction but this is at\n\tthe POC stage.\n\n3. In increments, attempt to allocate 5% of memory as hugepages.\n\t Measure how long it took, how successful it was, how many\n\t direct reclaims took place and how how many compactions. Note\n\t the compaction figures might not fully add up as compactions\n\t can take place for orders other than the hugepage size\n\nX86\t\t\t\tvanilla\t\tcompaction\nFinal page count 913 916 (attempted 1002)\npages reclaimed 68296 9791\n\nX86-64\t\t\t\tvanilla\t\tcompaction\nFinal page count: 901 902 (attempted 1002)\nTotal pages reclaimed: 112599 53234\n\nPPC64\t\t\t\tvanilla\t\tcompaction\nFinal page count: 93 94 (attempted 110)\nTotal pages reclaimed: 103216 61838\n\nThere was not a dramatic improvement in success rates but it wouldn\u0027t be\nexpected in this case either. What was important is that fewer pages were\nreclaimed in all cases reducing the amount of IO required to satisfy a\nhuge page allocation.\n\nThe second tests were all performance related - kernbench, netperf, iozone\nand sysbench. None showed anything too remarkable.\n\nThe last test was a high-order allocation stress test. Many kernel\ncompiles are started to fill memory with a pressured mix of unmovable and\nmovable allocations. During this, an attempt is made to allocate 90% of\nmemory as huge pages - one at a time with small delays between attempts to\navoid flooding the IO queue.\n\n vanilla compaction\nPercentage of request allocated X86 98 99\nPercentage of request allocated X86-64 95 98\nPercentage of request allocated PPC64 55 70\n\nThis patch:\n\nrmap_walk_anon() does not use page_lock_anon_vma() for looking up and\nlocking an anon_vma and it does not appear to have sufficient locking to\nensure the anon_vma does not disappear from under it.\n\nThis patch copies an approach used by KSM to take a reference on the\nanon_vma while pages are being migrated. This should prevent rmap_walk()\nrunning into nasty surprises later because anon_vma has been freed.\n\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nAcked-by: Rik van Riel \u003criel@redhat.com\u003e\nCc: Minchan Kim \u003cminchan.kim@gmail.com\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: 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": "e325c90ffc13b698fa2814102e05275b21c26bec", "tree": "dcb20cad204132e08476d3cb4da66f9a2e08b9fe", "parents": [ "1a5cb81465b66b74bf3d6ad36e5382238de6a132" ], "author": { "name": "David Rientjes", "email": "rientjes@google.com", "time": "Mon May 24 14:32:13 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:06:58 2010 -0700" }, "message": "mm: default to node zonelist ordering when nodes have only lowmem\n\nThere are two types of zonelist ordering methodologies:\n\n - node order, preferring allocations on a node to stay local to and\n\n - zone order, preferring allocations come from a higher zone to avoid\n allocating in lowmem zones even though they may not be local.\n\nThe ordering technique used by the kernel is configurable on the command\nline, but also has some logic to determine what the default should be.\n\nThis logic currently lacks knowledge of systems where a node may only have\nlowmem. For such systems, it is necessary to use node order so that\nGFP_KERNEL allocations may be satisfied by nodes consisting of only\nlowmem.\n\nIf zone order is used, GFP_KERNEL allocations to such nodes are actually\nallocated on a node with local affinity that includes ZONE_NORMAL.\n\nThis change defaults to node zonelist ordering if any node lacks\nZONE_NORMAL.\n\nTo force zone order, append \u0027numa_zonelist_order\u003dzone\u0027 to the kernel\ncommand line.\n\nSigned-off-by: David Rientjes \u003crientjes@google.com\u003e\nAcked-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: 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": "e48293fd75b3aa67f43ad6e3d2ff397caa55d58b", "tree": "8f163687833fb5e1fa84f72e2e72e1ab83aca91e", "parents": [ "25ef0e50cca790370ad7838e3ad74db6a6a2d829" ], "author": { "name": "Johannes Weiner", "email": "hannes@cmpxchg.org", "time": "Mon May 24 14:32:11 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:06:58 2010 -0700" }, "message": "mincore: do nested page table walks\n\nDo page table walks with the well-known nested loops we use in several\nother places already.\n\nThis avoids doing full page table walks after every pte range and also\nallows to handle unmapped areas bigger than one pte range in one go.\n\nSigned-off-by: Johannes Weiner \u003channes@cmpxchg.org\u003e\nCc: Andrea Arcangeli \u003caarcange@redhat.com\u003e\nCc: Naoya Horiguchi \u003cn-horiguchi@ah.jp.nec.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "25ef0e50cca790370ad7838e3ad74db6a6a2d829", "tree": "9fef482df352beaeeb0ae1c6a176448cf795d045", "parents": [ "f488401076c5570130c018e573f450a9a6c43365" ], "author": { "name": "Johannes Weiner", "email": "hannes@cmpxchg.org", "time": "Mon May 24 14:32:11 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:06:58 2010 -0700" }, "message": "mincore: pass ranges as start,end address pairs\n\nInstead of passing a start address and a number of pages into the helper\nfunctions, convert them to use a start and an end address.\n\nSigned-off-by: Johannes Weiner \u003channes@cmpxchg.org\u003e\nCc: Andrea Arcangeli \u003caarcange@redhat.com\u003e\nCc: Naoya Horiguchi \u003cn-horiguchi@ah.jp.nec.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "f488401076c5570130c018e573f450a9a6c43365", "tree": "0e704c52a45e44ba8cbb0dac529e9ad251d9edbd", "parents": [ "6a60f1b3588aef6ddceaa14192df475d430cce45" ], "author": { "name": "Johannes Weiner", "email": "hannes@cmpxchg.org", "time": "Mon May 24 14:32:10 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:06:58 2010 -0700" }, "message": "mincore: break do_mincore() into logical pieces\n\nSplit out functions to handle hugetlb ranges, pte ranges and unmapped\nranges, to improve readability but also to prepare the file structure for\nnested page table walks.\n\nNo semantic changes intended.\n\nSigned-off-by: Johannes Weiner \u003channes@cmpxchg.org\u003e\nCc: Andrea Arcangeli \u003caarcange@redhat.com\u003e\nCc: Naoya Horiguchi \u003cn-horiguchi@ah.jp.nec.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "6a60f1b3588aef6ddceaa14192df475d430cce45", "tree": "4469beefed2e610eef9204b1a4d63cddc5d9aae4", "parents": [ "c0ff7453bb5c7c98e0885fb94279f2571946f280" ], "author": { "name": "Johannes Weiner", "email": "hannes@cmpxchg.org", "time": "Mon May 24 14:32:09 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:06:58 2010 -0700" }, "message": "mincore: cleanups\n\nThis fixes some minor issues that bugged me while going over the code:\n\no adjust argument order of do_mincore() to match the syscall\no simplify range length calculation\no drop superfluous shift in huge tlb calculation, address is page aligned\no drop dead nr_huge calculation\no check pte_none() before pte_present()\no comment and whitespace fixes\n\nNo semantic changes intended.\n\nSigned-off-by: Johannes Weiner \u003channes@cmpxchg.org\u003e\nCc: Andrea Arcangeli \u003caarcange@redhat.com\u003e\nCc: Naoya Horiguchi \u003cn-horiguchi@ah.jp.nec.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\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": "708c1bbc9d0c3e57f40501794d9b0eed29d10fce", "tree": "4b19caf68c420b32abdf05af3d413b1320f04fbe", "parents": [ "971ada0f6659488c3f36aed4c6f7670ff5ce4368" ], "author": { "name": "Miao Xie", "email": "miaox@cn.fujitsu.com", "time": "Mon May 24 14:32:07 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:06:57 2010 -0700" }, "message": "mempolicy: restructure rebinding-mempolicy functions\n\nNick Piggin reported that the allocator may see an empty nodemask when\nchanging cpuset\u0027s mems[1]. It happens only on the kernel that do not do\natomic nodemask_t stores. (MAX_NUMNODES \u003e BITS_PER_LONG)\n\nBut I found that there is also a problem on the kernel that can do atomic\nnodemask_t stores. The problem is that the allocator can\u0027t find a node to\nalloc page when changing cpuset\u0027s mems though there is a lot of free\nmemory. The reason is like this:\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\nI can use the attached program reproduce it by the following step:\n\n# mkdir /dev/cpuset\n# mount -t cpuset cpuset /dev/cpuset\n# mkdir /dev/cpuset/1\n# echo `cat /dev/cpuset/cpus` \u003e /dev/cpuset/1/cpus\n# echo `cat /dev/cpuset/mems` \u003e /dev/cpuset/1/mems\n# echo $$ \u003e /dev/cpuset/1/tasks\n# numactl --membind\u003d`cat /dev/cpuset/mems` ./cpuset_mem_hog \u003cnr_tasks\u003e \u0026\n \u003cnr_tasks\u003e \u003d max(nr_cpus - 1, 1)\n# killall -s SIGUSR1 cpuset_mem_hog\n# ./change_mems.sh\n\nseveral hours later, oom will happen though there is a lot of free memory.\n\nThis patchset fixes this problem by expanding the nodes range first(set\nnewly allowed bits) and shrink it lazily(clear newly disallowed bits). So\nwe use a variable to tell the write-side task that read-side task is\nreading nodemask, and the write-side task clears newly disallowed nodes\nafter read-side task ends the current memory allocation.\n\nThis patch:\n\nIn order to fix no node to alloc memory, when we want to update mempolicy\nand mems_allowed, we expand the set of nodes first (set all the newly\nnodes) and shrink the set of nodes lazily(clean disallowed nodes), But the\nmempolicy\u0027s rebind functions may breaks the expanding.\n\nSo we restructure the mempolicy\u0027s rebind functions and split the rebind\nwork to two steps, just like the update of cpuset\u0027s mems: The 1st step:\nexpand the set of the mempolicy\u0027s nodes. The 2nd step: shrink the set of\nthe mempolicy\u0027s nodes. It is used when there is no real lock to protect\nthe mempolicy in the read-side. Otherwise we can do rebind work at once.\n\nIn order to implement it, we define\n\n\tenum mpol_rebind_step {\n\t\tMPOL_REBIND_ONCE,\n\t\tMPOL_REBIND_STEP1,\n\t\tMPOL_REBIND_STEP2,\n\t\tMPOL_REBIND_NSTEP,\n\t};\n\nIf the mempolicy needn\u0027t be updated by two steps, we can pass\nMPOL_REBIND_ONCE to the rebind functions. Or we can pass\nMPOL_REBIND_STEP1 to do the first step of the rebind work and pass\nMPOL_REBIND_STEP2 to do the second step work.\n\nBesides that, it maybe long time between these two step and we have to\nrelease the lock that protects mempolicy and mems_allowed. If we hold the\nlock once again, we must check whether the current mempolicy is under the\nrebinding (the first step has been done) or not, because the task may\nalloc a new mempolicy when we don\u0027t hold the lock. So we defined the\nfollowing flag to identify it:\n\n#define MPOL_F_REBINDING (1 \u003c\u003c 2)\n\nThe new functions will be used in the next patch.\n\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": "15d77835ac48dbc2d4884376ea6a08b65b1c40ba", "tree": "4bb094f030cedf8376a70a65f9271b571ba37562", "parents": [ "345ace9c797030e77da8ff211b9502370b9d81ab" ], "author": { "name": "Lee Schermerhorn", "email": "lee.schermerhorn@hp.com", "time": "Mon May 24 14:32:04 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:06:57 2010 -0700" }, "message": "mempolicy: factor mpol_shared_policy_init() return paths\n\nFactor out duplicate put/frees in mpol_shared_policy_init() to a common\nreturn path.\n\nSigned-off-by: 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: David Rientjes \u003crientjes@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": "345ace9c797030e77da8ff211b9502370b9d81ab", "tree": "5699b5b0b54412466b415ec581125e59f77d4b00", "parents": [ "b4652e8429100ba5c3ddb49499faa1188c98c246" ], "author": { "name": "Lee Schermerhorn", "email": "lee.schermerhorn@hp.com", "time": "Mon May 24 14:32:04 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:06:57 2010 -0700" }, "message": "mempolicy: rename policy_types and cleanup initialization\n\nRename \u0027policy_types[]\u0027 to \u0027policy_modes[]\u0027 to better match the array\ncontents.\n\nUse designated intializer syntax for policy_modes[].\n\nSigned-off-by: 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: David Rientjes \u003crientjes@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": "b4652e8429100ba5c3ddb49499faa1188c98c246", "tree": "55fa4fcdb8e8cf067b1474cc7068163e152f3075", "parents": [ "e17f74af351cce9a1bade7b33af179497fdf95cf" ], "author": { "name": "Lee Schermerhorn", "email": "lee.schermerhorn@hp.com", "time": "Mon May 24 14:32:03 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:06:57 2010 -0700" }, "message": "mempolicy: lose unnecessary loop variable in mpol_parse_str()\n\nWe don\u0027t really need the extra variable \u0027i\u0027 in mpol_parse_str(). The only\nuse is as the the loop variable. Then, it\u0027s assigned to \u0027mode\u0027. Just use\nmode, and loose the \u0027uninitialized_var()\u0027 macro.\n\nSigned-off-by: 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: David Rientjes \u003crientjes@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": "e17f74af351cce9a1bade7b33af179497fdf95cf", "tree": "99cce009bf299465a3b20594305ee209c8d85c3d", "parents": [ "1980050250fa052b1c24a19f9b3d82fae14d77f8" ], "author": { "name": "Lee Schermerhorn", "email": "lee.schermerhorn@hp.com", "time": "Mon May 24 14:32:02 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:06:57 2010 -0700" }, "message": "mempolicy: don\u0027t call mpol_set_nodemask() when no_context\n\nNo need to call mpol_set_nodemask() when we have no context for the\nmempolicy. This can occur when we\u0027re parsing a tmpfs \u0027mpol\u0027 mount option.\n Just save the raw nodemask in the mempolicy\u0027s w.user_nodemask member for\nuse when a tmpfs/shmem file is created. mpol_shared_policy_init() will\n\"contextualize\" the policy for the new file based on the creating task\u0027s\ncontext.\n\nSigned-off-by: 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: David Rientjes \u003crientjes@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": "1980050250fa052b1c24a19f9b3d82fae14d77f8", "tree": "96743238e6941bd7af113ebe9275f6892b374dd3", "parents": [ "6eb27e1fdf5781719a3d2e90e6c89fa012135c62" ], "author": { "name": "Bob Liu", "email": "lliubbo@gmail.com", "time": "Mon May 24 14:32:01 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:06:57 2010 -0700" }, "message": "mempolicy: remove redundant check\n\nLee\u0027s patch \"mempolicy: use MPOL_PREFERRED for system-wide default policy\"\nhas made the MPOL_DEFAULT only used in the memory policy APIs. So, no\nneed to check in __mpol_equal also. Also get rid of mpol_match_intent()\nand move its logic directly into __mpol_equal().\n\nSigned-off-by: Bob Liu \u003clliubbo@gmail.com\u003e\nAcked-by: David Rientjes \u003crientjes@google.com\u003e\nCc: Andi Kleen \u003candi@firstfloor.org\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": "6eb27e1fdf5781719a3d2e90e6c89fa012135c62", "tree": "23be89303ad69f5728f69665dfadf2b4dc45628c", "parents": [ "6d556294d5b27fb12f18be7495af45b6156a409e" ], "author": { "name": "Bob Liu", "email": "lliubbo@gmail.com", "time": "Mon May 24 14:32:00 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:06:57 2010 -0700" }, "message": "mempolicy: remove case MPOL_INTERLEAVE from policy_zonelist()\n\nIn policy_zonelist() mode MPOL_INTERLEAVE shouldn\u0027t happen, so fall\nthrough to BUG() instead of break to return. I also fixed the comment.\n\nSigned-off-by: Bob Liu \u003clliubbo@gmail.com\u003e\nAcked-by: David Rientjes \u003crientjes@google.com\u003e\nCc: Andi Kleen \u003candi@firstfloor.org\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": "6d556294d5b27fb12f18be7495af45b6156a409e", "tree": "cb8549b4a4dc53399abc596dcac4630b0d936abf", "parents": [ "e13861d822f8f443ca0c020ea8fc2dc01039cd63" ], "author": { "name": "Bob Liu", "email": "lliubbo@gmail.com", "time": "Mon May 24 14:31:59 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:06:57 2010 -0700" }, "message": "mempolicy: remove redundant code\n\n1. In funtion is_valid_nodemask(), varibable k will be inited to 0 in\n the following loop, needn\u0027t init to policy_zone anymore.\n\n2. (MPOL_F_STATIC_NODES | MPOL_F_RELATIVE_NODES) has already defined\n to MPOL_MODE_FLAGS in mempolicy.h.\n\nSigned-off-by: Bob Liu \u003clliubbo@gmail.com\u003e\nAcked-by: David Rientjes \u003crientjes@google.com\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "e13861d822f8f443ca0c020ea8fc2dc01039cd63", "tree": "0e1ccaa6a2d682f7636b9d5ef5d4c73a28074988", "parents": [ "4b50dc26a0a25a9d1998d206e1f7d849aa78063f" ], "author": { "name": "Minchan Kim", "email": "minchan.kim@gmail.com", "time": "Mon May 24 14:31:59 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:06:57 2010 -0700" }, "message": "mm: remove return value of putback_lru_pages()\n\nputback_lru_page() never can fail. So it doesn\u0027t matter count of \"the\nnumber of pages put back\".\n\nIn addition, users of this functions don\u0027t use return value.\n\nLet\u0027s remove unnecessary code.\n\nSigned-off-by: Minchan Kim \u003cminchan.kim@gmail.com\u003e\nReviewed-by: Rik van Riel \u003criel@redhat.com\u003e\nReviewed-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nReviewed-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": "4b50dc26a0a25a9d1998d206e1f7d849aa78063f", "tree": "892657690d555940ef854bc97aa47a45c2088bdf", "parents": [ "e48e67e08c340def3d0349c2910d23c7985fb6fa" ], "author": { "name": "Huang Shijie", "email": "shijie8@gmail.com", "time": "Mon May 24 14:31:58 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:06:57 2010 -0700" }, "message": "shmem: remove redundant code\n\nprep_new_page() will call set_page_private(page, 0) to initialise the\npage, so the code is redundant.\n\nSigned-off-by: Huang Shijie \u003cshijie8@gmail.com\u003e\nReviewed-by: Minchan Kim \u003cminchan.kim@gmail.com\u003e\nAcked-by: 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" } ], "next": "e48e67e08c340def3d0349c2910d23c7985fb6fa" }