)]}' { "log": [ { "commit": "dd508ae2dbff0cfc7401eb6e278339fc56bc5033", "tree": "daa9f88a4e2e65e86b351ffa2d52dcc07e753c1e", "parents": [ "7801edb0b8b66e83c13623b483bc2e846c007c9d", "95cd34b42b43c0ed5a89a764e023189bfe7b1530" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 22 14:18:13 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 22 14:18:13 2009 -0800" }, "message": "Merge branch \u0027merge\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc\n\n* \u0027merge\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (36 commits)\n powerpc/gc/wii: Remove get_irq_desc()\n powerpc/gc/wii: hlwd-pic: convert irq_desc.lock to raw_spinlock\n powerpc/gamecube/wii: Fix off-by-one error in ugecon/usbgecko_udbg\n powerpc/mpic: Fix problem that affinity is not updated\n powerpc/mm: Fix stupid bug in subpge protection handling\n powerpc/iseries: use DECLARE_COMPLETION_ONSTACK for non-constant completion\n powerpc: Fix MSI support on U4 bridge PCIe slot\n powerpc: Handle VSX alignment faults correctly in little-endian mode\n powerpc/mm: Fix typo of cpumask_clear_cpu()\n powerpc/mm: Fix hash_utils_64.c compile errors with DEBUG enabled.\n powerpc: Convert BUG() to use unreachable()\n powerpc/pseries: Make declarations of cpu_hotplug_driver_lock() ANSI compatible.\n powerpc/pseries: Don\u0027t panic when H_PROD fails during cpu-online.\n powerpc/mm: Fix a WARN_ON() with CONFIG_DEBUG_PAGEALLOC and CONFIG_DEBUG_VM\n powerpc/defconfigs: Set HZ\u003d100 on pseries and ppc64 defconfigs\n powerpc/defconfigs: Disable token ring in powerpc defconfigs\n powerpc/defconfigs: Reduce 64bit vmlinux by making acenic and cramfs modules\n powerpc/pseries: Select XICS and PCI_MSI PSERIES\n powerpc/85xx: Wrong variable returned on error\n powerpc/iseries: Convert to proc_fops\n ...\n" }, { "commit": "3981e152864fcc1dbbb564e1f4c0ae11a09639d2", "tree": "76c767a9b25e294c3cc8edd9870304b845cabdd9", "parents": [ "aac3d39693529ca538e37ebdb6ed5d6432a697c7", "18374d89e5fe96772102f44f535efb1198d9be08" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sat Dec 19 09:48:14 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sat Dec 19 09:48:14 2009 -0800" }, "message": "Merge branch \u0027x86-fixes-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip\n\n* \u0027x86-fixes-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:\n x86, irq: Allow 0xff for /proc/irq/[n]/smp_affinity on an 8-cpu system\n Makefile: Unexport LC_ALL instead of clearing it\n x86: Fix objdump version check in arch/x86/tools/chkobjdump.awk\n x86: Reenable TSC sync check at boot, even with NONSTOP_TSC\n x86: Don\u0027t use POSIX character classes in gen-insn-attr-x86.awk\n Makefile: set LC_CTYPE, LC_COLLATE, LC_NUMERIC to C\n x86: Increase MAX_EARLY_RES; insufficient on 32-bit NUMA\n x86: Fix checking of SRAT when node 0 ram is not from 0\n x86, cpuid: Add \"volatile\" to asm in native_cpuid()\n x86, msr: msrs_alloc/free for CONFIG_SMP\u003dn\n x86, amd: Get multi-node CPU info from NodeId MSR instead of PCI config space\n x86: Add IA32_TSC_AUX MSR and use it\n x86, msr/cpuid: Register enough minors for the MSR and CPUID drivers\n initramfs: add missing decompressor error check\n bzip2: Add missing checks for malloc returning NULL\n bzip2/lzma/gzip: pre-boot malloc doesn\u0027t return NULL on failure\n" }, { "commit": "925cc71e512a29e2594bcc17dc58d0a0e9c4d524", "tree": "7240ccf6ba713cc180d388a28f00c1a43293bc14", "parents": [ "55639353a0035052d9ea6cfe4dde0ac7fcbb2c9f" ], "author": { "name": "Robert Jennings", "email": "rcj@linux.vnet.ibm.com", "time": "Thu Dec 17 14:44:38 2009 +0000" }, "committer": { "name": "Benjamin Herrenschmidt", "email": "benh@kernel.crashing.org", "time": "Fri Dec 18 14:53:36 2009 +1100" }, "message": "mm: Add notifier in pageblock isolation for balloon drivers\n\nMemory balloon drivers can allocate a large amount of memory which is not\nmovable but could be freed to accomodate memory hotplug remove.\n\nPrior to calling the memory hotplug notifier chain the memory in the\npageblock is isolated. Currently, if the migrate type is not\nMIGRATE_MOVABLE the isolation will not proceed, causing the memory removal\nfor that page range to fail.\n\nRather than failing pageblock isolation if the migrateteype is not\nMIGRATE_MOVABLE, this patch checks if all of the pages in the pageblock,\nand not on the LRU, are owned by a registered balloon driver (or other\nentity) using a notifier chain. If all of the non-movable pages are owned\nby a balloon, they can be freed later through the memory notifier chain\nand the range can still be isolated in set_migratetype_isolate().\n\nSigned-off-by: Robert Jennings \u003crcj@linux.vnet.ibm.com\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Brian King \u003cbrking@linux.vnet.ibm.com\u003e\nCc: Paul Mackerras \u003cpaulus@samba.org\u003e\nCc: Martin Schwidefsky \u003cschwidefsky@de.ibm.com\u003e\nCc: Gerald Schaefer \u003cgeralds@linux.vnet.ibm.com\u003e\nCc: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\n" }, { "commit": "55db493b65c7b6bb5d7bd3dd3c8a2fe13f5dc09c", "tree": "7f9203f43e7c81687c9aaa0213266bc7b2e89e35", "parents": [ "efc8e7f4c83dc85acbf5f54a8b1b24ae75b20aaa", "a4636818f8e0991f32d9528f39cf4f3d6a7d30a3" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Dec 17 17:00:20 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Dec 17 17:00:20 2009 -0800" }, "message": "Merge branch \u0027cpumask-cleanups\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux-2.6-for-linus\n\n* \u0027cpumask-cleanups\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux-2.6-for-linus:\n cpumask: rename tsk_cpumask to tsk_cpus_allowed\n cpumask: don\u0027t recommend set_cpus_allowed hack in Documentation/cpu-hotplug.txt\n cpumask: avoid dereferencing struct cpumask\n cpumask: convert drivers/idle/i7300_idle.c to cpumask_var_t\n cpumask: use modern cpumask style in drivers/scsi/fcoe/fcoe.c\n cpumask: avoid deprecated function in mm/slab.c\n cpumask: use cpu_online in kernel/perf_event.c\n" }, { "commit": "efc8e7f4c83dc85acbf5f54a8b1b24ae75b20aaa", "tree": "cf7df8a837b719623e13b3ab19e8cfce1e270883", "parents": [ "b5c96f89177b460ef89ecd777d5f2fefd4534d3f", "a00ae4d21b2fa9379914f270ffffd8d3bec55430" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Dec 17 16:58:26 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Dec 17 16:58:26 2009 -0800" }, "message": "Merge branch \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/security-testing-2.6\n\n* \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/security-testing-2.6:\n Keys: KEYCTL_SESSION_TO_PARENT needs TIF_NOTIFY_RESUME architecture support\n NOMMU: Optimise away the {dac_,}mmap_min_addr tests\n security/min_addr.c: make init_mmap_min_addr() static\n keys: PTR_ERR return of wrong pointer in keyctl_get_security()\n" }, { "commit": "dcc7cd011220d7425a265c9bbf04c5731dacec1b", "tree": "4c2244f6e6ce94e2698572e9d2df3baea8449c2a", "parents": [ "bf931a01a2c024a54204b4b02276af6e8d99a2c0", "b60e26a2f03d963f8c79ad7920d64abc4d38ecbc" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Dec 17 16:00:19 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Dec 17 16:00:19 2009 -0800" }, "message": "Merge branch \u0027kmemleak\u0027 of git://linux-arm.org/linux-2.6\n\n* \u0027kmemleak\u0027 of git://linux-arm.org/linux-2.6:\n kmemleak: fix kconfig for crc32 build error\n kmemleak: Reduce the false positives by checking for modified objects\n kmemleak: Show the age of an unreferenced object\n kmemleak: Release the object lock before calling put_object()\n kmemleak: Scan the _ftrace_events section in modules\n kmemleak: Simplify the kmemleak_scan_area() function prototype\n kmemleak: Do not use off-slab management with SLAB_NOLEAKTRACE\n" }, { "commit": "65a80b4c61f5b5f6eb0f5669c8fb120893bfb388", "tree": "44136f7130ad0a1074502afbfdf8b93efe35976e", "parents": [ "26b3c01f7debc1bbc3117bc9c9e016ca6f2e41d5" ], "author": { "name": "Hisashi Hifumi", "email": "hifumi.hisashi@oss.ntt.co.jp", "time": "Thu Dec 17 15:27:26 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Dec 17 15:45:32 2009 -0800" }, "message": "readahead: add blk_run_backing_dev\n\nI added blk_run_backing_dev on page_cache_async_readahead so readahead I/O\nis unpluged to improve throughput on especially RAID environment.\n\nThe normal case is, if page N become uptodate at time T(N), then T(N) \u003c\u003d\nT(N+1) holds. With RAID (and NFS to some degree), there is no strict\nordering, the data arrival time depends on runtime status of individual\ndisks, which breaks that formula. So in do_generic_file_read(), just\nafter submitting the async readahead IO request, the current page may well\nbe uptodate, so the page won\u0027t be locked, and the block device won\u0027t be\nimplicitly unplugged:\n\n if (PageReadahead(page))\n page_cache_async_readahead()\n if (!PageUptodate(page))\n goto page_not_up_to_date;\n //...\npage_not_up_to_date:\n lock_page_killable(page);\n\nTherefore explicit unplugging can help.\n\nFollowing is the test result with dd.\n\n#dd if\u003dtestdir/testfile of\u003d/dev/null bs\u003d16384\n\n-2.6.30-rc6\n1048576+0 records in\n1048576+0 records out\n17179869184 bytes (17 GB) copied, 224.182 seconds, 76.6 MB/s\n\n-2.6.30-rc6-patched\n1048576+0 records in\n1048576+0 records out\n17179869184 bytes (17 GB) copied, 206.465 seconds, 83.2 MB/s\n\n(7Disks RAID-0 Array)\n\n-2.6.30-rc6\n1054976+0 records in\n1054976+0 records out\n17284726784 bytes (17 GB) copied, 212.233 seconds, 81.4 MB/s\n\n-2.6.30-rc6-patched\n1054976+0 records out\n17284726784 bytes (17 GB) copied, 198.878 seconds, 86.9 MB/s\n\n(7Disks RAID-5 Array)\n\nThe patch was found to improve performance with the SCST scsi target\ndriver. See\nhttp://sourceforge.net/mailarchive/forum.php?thread_name\u003da0272b440906030714g67eabc5k8f847fb1e538cc62%40mail.gmail.com\u0026forum_name\u003dscst-devel\n\n[akpm@linux-foundation.org: unbust comment layout]\n[akpm@linux-foundation.org: \"fix\" CONFIG_BLOCK\u003dn]\nSigned-off-by: Hisashi Hifumi \u003chifumi.hisashi@oss.ntt.co.jp\u003e\nAcked-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nCc: Jens Axboe \u003cjens.axboe@oracle.com\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nTested-by: Ronald \u003cintercommit@gmail.com\u003e\nCc: Bart Van Assche \u003cbart.vanassche@gmail.com\u003e\nCc: Vladislav Bolkhovitin \u003cvst@vlnb.net\u003e\nCc: Randy Dunlap \u003crandy.dunlap@oracle.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "58463c1fe25f7c4183f30f06a5a86cb6cd9d8231", "tree": "62b52d0ccbf7fc258627492240fb1ca1770639cc", "parents": [ "f6325e30ebd6fc870315b017a5d4a6ab15bf790b" ], "author": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Thu Dec 17 11:43:12 2009 -0600" }, "committer": { "name": "Rusty Russell", "email": "rusty@rustcorp.com.au", "time": "Thu Dec 17 11:43:13 2009 +1030" }, "message": "cpumask: avoid deprecated function in mm/slab.c\n\nThese days we use cpumask_empty() which takes a pointer.\n\nSigned-off-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\nAcked-by: Christoph Lameter \u003ccl@linux-foundation.org\u003e\n" }, { "commit": "718deb6b61e34c200c1f2b706176d9aac334cb2d", "tree": "fdf37190a8663d507bc740a6fa21437c6c22e611", "parents": [ "bea4c899f2b5fad80099aea979780ef19f9b1987" ], "author": { "name": "Al Viro", "email": "viro@zeniv.linux.org.uk", "time": "Wed Dec 16 19:35:36 2009 -0500" }, "committer": { "name": "Al Viro", "email": "viro@zeniv.linux.org.uk", "time": "Wed Dec 16 19:48:48 2009 -0500" }, "message": "Fix breakage in shmem.c\n\nReplacing\n\terror \u003d 0;\n\tif (error)\n\t\top\nwith nothing is not quite an equivalent transformation ;-)\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n" }, { "commit": "329962503692b42d8088f31584e42d52db179d52", "tree": "fe8aa709fcbf6154e25c291ec569885a23e2eba1", "parents": [ "45a94d7cd45ed991914011919e7d40eb6d2546d1" ], "author": { "name": "Yinghai Lu", "email": "yinghai@kernel.org", "time": "Tue Dec 15 17:59:02 2009 -0800" }, "committer": { "name": "H. Peter Anvin", "email": "hpa@zytor.com", "time": "Wed Dec 16 16:43:37 2009 -0800" }, "message": "x86: Fix checking of SRAT when node 0 ram is not from 0\n\nFound one system that boot from socket1 instead of socket0, SRAT get rejected...\n\n[ 0.000000] SRAT: Node 1 PXM 0 0-a0000\n[ 0.000000] SRAT: Node 1 PXM 0 100000-80000000\n[ 0.000000] SRAT: Node 1 PXM 0 100000000-2080000000\n[ 0.000000] SRAT: Node 0 PXM 1 2080000000-4080000000\n[ 0.000000] SRAT: Node 2 PXM 2 4080000000-6080000000\n[ 0.000000] SRAT: Node 3 PXM 3 6080000000-8080000000\n[ 0.000000] SRAT: Node 4 PXM 4 8080000000-a080000000\n[ 0.000000] SRAT: Node 5 PXM 5 a080000000-c080000000\n[ 0.000000] SRAT: Node 6 PXM 6 c080000000-e080000000\n[ 0.000000] SRAT: Node 7 PXM 7 e080000000-10080000000\n...\n[ 0.000000] NUMA: Allocated memnodemap from 500000 - 701040\n[ 0.000000] NUMA: Using 20 for the hash shift.\n[ 0.000000] Adding active range (0, 0x2080000, 0x4080000) 0 entries of 3200 used\n[ 0.000000] Adding active range (1, 0x0, 0x96) 1 entries of 3200 used\n[ 0.000000] Adding active range (1, 0x100, 0x7f750) 2 entries of 3200 used\n[ 0.000000] Adding active range (1, 0x100000, 0x2080000) 3 entries of 3200 used\n[ 0.000000] Adding active range (2, 0x4080000, 0x6080000) 4 entries of 3200 used\n[ 0.000000] Adding active range (3, 0x6080000, 0x8080000) 5 entries of 3200 used\n[ 0.000000] Adding active range (4, 0x8080000, 0xa080000) 6 entries of 3200 used\n[ 0.000000] Adding active range (5, 0xa080000, 0xc080000) 7 entries of 3200 used\n[ 0.000000] Adding active range (6, 0xc080000, 0xe080000) 8 entries of 3200 used\n[ 0.000000] Adding active range (7, 0xe080000, 0x10080000) 9 entries of 3200 used\n[ 0.000000] SRAT: PXMs only cover 917504MB of your 1048566MB e820 RAM. Not used.\n[ 0.000000] SRAT: SRAT not used.\n\nthe early_node_map is not sorted because node0 with non zero start come first.\n\nso try to sort it right away after all regions are registered.\n\nalso fixs refression by 8716273c (x86: Export srat physical topology)\n\n-v2: make it more solid to handle cross node case like node0 [0,4g), [8,12g) and node1 [4g, 8g), [12g, 16g)\n-v3: update comments.\n\nReported-and-tested-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\nSigned-off-by: Yinghai Lu \u003cyinghai@kernel.org\u003e\nLKML-Reference: \u003c4B2579D2.3010201@kernel.org\u003e\nSigned-off-by: H. Peter Anvin \u003chpa@zytor.com\u003e\n" }, { "commit": "6e1415467614e854fee660ff6648bd10fa976e95", "tree": "2ae2e2f51eff0629bc0e26a97eac85483a7ba56f", "parents": [ "dd880fbe8e4792d1185a5101dc751f49eab0a509" ], "author": { "name": "David Howells", "email": "dhowells@redhat.com", "time": "Tue Dec 15 19:27:45 2009 +0000" }, "committer": { "name": "James Morris", "email": "jmorris@namei.org", "time": "Thu Dec 17 09:25:19 2009 +1100" }, "message": "NOMMU: Optimise away the {dac_,}mmap_min_addr tests\n\nIn NOMMU mode clamp dac_mmap_min_addr to zero to cause the tests on it to be\nskipped by the compiler. We do this as the minimum mmap address doesn\u0027t make\nany sense in NOMMU mode.\n\nmmap_min_addr and round_hint_to_min() can be discarded entirely in NOMMU mode.\n\nSigned-off-by: David Howells \u003cdhowells@redhat.com\u003e\nAcked-by: Eric Paris \u003ceparis@redhat.com\u003e\nSigned-off-by: James Morris \u003cjmorris@namei.org\u003e\n" }, { "commit": "d4220f987cf473c65a342ca69e3eb13dea919a49", "tree": "dbb004a9c805d6de3f6e3955398fee1084a29f16", "parents": [ "61cf693159d6a968a7014e24905143f71ed8ddcf", "f2c03debdfb387fa2e35cac6382779072b8b9209" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Dec 16 12:36:49 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Dec 16 12:36:49 2009 -0800" }, "message": "Merge branch \u0027hwpoison\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/ak/linux-mce-2.6\n\n* \u0027hwpoison\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/ak/linux-mce-2.6: (34 commits)\n HWPOISON: Remove stray phrase in a comment\n HWPOISON: Try to allocate migration page on the same node\n HWPOISON: Don\u0027t do early filtering if filter is disabled\n HWPOISON: Add a madvise() injector for soft page offlining\n HWPOISON: Add soft page offline support\n HWPOISON: Undefine short-hand macros after use to avoid namespace conflict\n HWPOISON: Use new shake_page in memory_failure\n HWPOISON: Use correct name for MADV_HWPOISON in documentation\n HWPOISON: mention HWPoison in Kconfig entry\n HWPOISON: Use get_user_page_fast in hwpoison madvise\n HWPOISON: add an interface to switch off/on all the page filters\n HWPOISON: add memory cgroup filter\n memcg: add accessor to mem_cgroup.css\n memcg: rename and export try_get_mem_cgroup_from_page()\n HWPOISON: add page flags filter\n mm: export stable page flags\n HWPOISON: limit hwpoison injector to known page types\n HWPOISON: add fs/device filters\n HWPOISON: return 0 to indicate success reliably\n HWPOISON: make semantics of IGNORED/DELAYED clear\n ...\n" }, { "commit": "bac5e54c29f352d962a2447d22735316b347b9f1", "tree": "7642993fa93164835ffaa2dacd341388193f1979", "parents": [ "529e89430d6c0d64db8ac474cb95e68e2527c79a", "c05c4edd876b7ae92787d1295868afcb89b6a348" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Dec 16 12:04:02 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Dec 16 12:04:02 2009 -0800" }, "message": "Merge branch \u0027master\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6\n\n* \u0027master\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6: (38 commits)\n direct I/O fallback sync simplification\n ocfs: stop using do_sync_mapping_range\n cleanup blockdev_direct_IO locking\n make generic_acl slightly more generic\n sanitize xattr handler prototypes\n libfs: move EXPORT_SYMBOL for d_alloc_name\n vfs: force reval of target when following LAST_BIND symlinks (try #7)\n ima: limit imbalance msg\n Untangling ima mess, part 3: kill dead code in ima\n Untangling ima mess, part 2: deal with counters\n Untangling ima mess, part 1: alloc_file()\n O_TRUNC open shouldn\u0027t fail after file truncation\n ima: call ima_inode_free ima_inode_free\n IMA: clean up the IMA counts updating code\n ima: only insert at inode creation time\n ima: valid return code from ima_inode_alloc\n fs: move get_empty_filp() deffinition to internal.h\n Sanitize exec_permission_lite()\n Kill cached_lookup() and real_lookup()\n Kill path_lookup_open()\n ...\n\nTrivial conflicts in fs/direct-io.c\n" }, { "commit": "c05c4edd876b7ae92787d1295868afcb89b6a348", "tree": "8dc4ce17c0a9be223a70e99d246035fee0a7168e", "parents": [ "2cfd30adf6130dab3fbb130eb5f7b1fd42a70e31" ], "author": { "name": "Christoph Hellwig", "email": "hch@lst.de", "time": "Wed Sep 23 15:07:30 2009 +0200" }, "committer": { "name": "Al Viro", "email": "viro@zeniv.linux.org.uk", "time": "Wed Dec 16 12:16:50 2009 -0500" }, "message": "direct I/O fallback sync simplification\n\nIn the case of direct I/O falling back to buffered I/O we sync data\ntwice currently: once at the end of generic_file_buffered_write using\nfilemap_write_and_wait_range and once a little later in\n__generic_file_aio_write using do_sync_mapping_range with all flags set.\n\nThe wait before write of the do_sync_mapping_range call does not make\nany sense, so just keep the filemap_write_and_wait_range call and move\nit to the right spot.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n" }, { "commit": "1c7c474c31aea6d5cb2fb35f31d9e9e91ae466b1", "tree": "89a5fd1146be1744ce3ac94789542841512315b8", "parents": [ "431547b3c4533b8c7fd150ab36980b9a3147797b" ], "author": { "name": "Christoph Hellwig", "email": "hch@lst.de", "time": "Tue Nov 03 16:44:44 2009 +0100" }, "committer": { "name": "Al Viro", "email": "viro@zeniv.linux.org.uk", "time": "Wed Dec 16 12:16:49 2009 -0500" }, "message": "make generic_acl slightly more generic\n\nNow that we cache the ACL pointers in the generic inode all the generic_acl\ncruft can go away and generic_acl.c can directly implement xattr handlers\ndealing with the full Posix ACL semantics for in-memory filesystems.\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n" }, { "commit": "431547b3c4533b8c7fd150ab36980b9a3147797b", "tree": "807ff2790f3c13c7c91ed2afd6d833032899482d", "parents": [ "ef26ca97e83052790940cbc444b01b0d17a813c1" ], "author": { "name": "Christoph Hellwig", "email": "hch@lst.de", "time": "Fri Nov 13 09:52:56 2009 +0000" }, "committer": { "name": "Al Viro", "email": "viro@zeniv.linux.org.uk", "time": "Wed Dec 16 12:16:49 2009 -0500" }, "message": "sanitize xattr handler prototypes\n\nAdd a flags argument to struct xattr_handler and pass it to all xattr\nhandler methods. This allows using the same methods for multiple\nhandlers, e.g. for the ACL methods which perform exactly the same action\nfor the access and default ACLs, just using a different underlying\nattribute. With a little more groundwork it\u0027ll also allow sharing the\nmethods for the regular user/trusted/secure handlers in extN, ocfs2 and\njffs2 like it\u0027s already done for xfs in this patch.\n\nAlso change the inode argument to the handlers to a dentry to allow\nusing the handlers mechnism for filesystems that require it later,\ne.g. cifs.\n\n[with GFS2 bits updated by Steven Whitehouse \u003cswhiteho@redhat.com\u003e]\n\nSigned-off-by: Christoph Hellwig \u003chch@lst.de\u003e\nReviewed-by: James Morris \u003cjmorris@namei.org\u003e\nAcked-by: Joel Becker \u003cjoel.becker@oracle.com\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n" }, { "commit": "0552f879d45cecc35d8e372a591fc5ed863bca58", "tree": "f3e0d76f7d5e7cf9a11ef4771294c7b4b552cd89", "parents": [ "7715b521222b6ebb6e927fa261ed91ed687fe454" ], "author": { "name": "Al Viro", "email": "viro@zeniv.linux.org.uk", "time": "Wed Dec 16 04:53:03 2009 -0500" }, "committer": { "name": "Al Viro", "email": "viro@zeniv.linux.org.uk", "time": "Wed Dec 16 12:16:47 2009 -0500" }, "message": "Untangling ima mess, part 1: alloc_file()\n\nThere are 2 groups of alloc_file() callers:\n\t* ones that are followed by ima_counts_get\n\t* ones giving non-regular files\nSo let\u0027s pull that ima_counts_get() into alloc_file();\nit\u0027s a no-op in case of non-regular files.\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n" }, { "commit": "2c48b9c45579a9b5e3e74694eebf3d2451f3dbd3", "tree": "cecbf786ae0650368a8136bdd90910e05d9b95c3", "parents": [ "a95161aaa801c18c52b2e7cf3d6b4b141c00a20a" ], "author": { "name": "Al Viro", "email": "viro@zeniv.linux.org.uk", "time": "Sun Aug 09 00:52:35 2009 +0400" }, "committer": { "name": "Al Viro", "email": "viro@zeniv.linux.org.uk", "time": "Wed Dec 16 12:16:42 2009 -0500" }, "message": "switch alloc_file() to passing struct path\n\n... and have the caller grab both mnt and dentry; kill\nleak in infiniband, while we are at it.\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n" }, { "commit": "4b42af81f0d7f95dff320f47d99c201925f406f5", "tree": "49829a9c58a5f7cac9a7b5e7efb22d6287794d72", "parents": [ "853b3da10d617f08340e5fe569c99e7b54f2a568" ], "author": { "name": "Al Viro", "email": "viro@zeniv.linux.org.uk", "time": "Wed Aug 05 18:25:56 2009 +0400" }, "committer": { "name": "Al Viro", "email": "viro@zeniv.linux.org.uk", "time": "Wed Dec 16 12:16:40 2009 -0500" }, "message": "switch shmem_file_setup() to alloc_file()\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n" }, { "commit": "aa20d489ceb024f91aae084ee00c47fc6a12255c", "tree": "1fc8e826114b1020d0e938d3b915e8a2016ded57", "parents": [ "9ab322caa347c4b580bcaf08f2253ea4cbd9e9ad" ], "author": { "name": "Bob Liu", "email": "lliubbo@gmail.com", "time": "Tue Dec 15 16:47:14 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Dec 16 07:20:08 2009 -0800" }, "message": "memcg: code clean, remove unused variable in mem_cgroup_resize_limit()\n\nVariable `progress\u0027 isn\u0027t used in mem_cgroup_resize_limit() any more.\nRemove it.\n\n[akpm@linux-foundation.org: cleanup]\nSigned-off-by: Bob Liu \u003clliubbo@gmail.com\u003e\nCc: Daisuke Nishimura \u003cnishimura@mxp.nes.nec.co.jp\u003e\nReviewed-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": "9ab322caa347c4b580bcaf08f2253ea4cbd9e9ad", "tree": "3d3344e4ab05fc1047465b439b5cc7f000c44ca2", "parents": [ "d31f56dbf8bafaacb0c617f9a6f137498d5c7aed" ], "author": { "name": "Daisuke Nishimura", "email": "nishimura@mxp.nes.nec.co.jp", "time": "Tue Dec 15 16:47:13 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Dec 16 07:20:07 2009 -0800" }, "message": "memcg: remove memcg_tasklist\n\nmemcg_tasklist was introduced at commit 7f4d454d(memcg: avoid deadlock\ncaused by race between oom and cpuset_attach) instead of cgroup_mutex to\nfix a deadlock problem. The cgroup_mutex, which was removed by the\ncommit, in mem_cgroup_out_of_memory() was originally introduced at commit\nc7ba5c9e (Memory controller: OOM handling).\n\nIIUC, the intention of this cgroup_mutex was to prevent task move during\nselect_bad_process() so that situations like below can be avoided.\n\n Assume cgroup \"foo\" has exceeded its limit and is about to trigger oom.\n 1. Process A, which has been in cgroup \"baa\" and uses large memory, is just\n moved to cgroup \"foo\". Process A can be the candidates for being killed.\n 2. Process B, which has been in cgroup \"foo\" and uses large memory, is just\n moved from cgroup \"foo\". Process B can be excluded from the candidates for\n being killed.\n\nBut these race window exists anyway even if we hold a lock, because\n__mem_cgroup_try_charge() decides wether it should trigger oom or not\noutside of the lock. So the original cgroup_mutex in\nmem_cgroup_out_of_memory and thus current memcg_tasklist has no use. And\nIMHO, those races are not so critical for users.\n\nThis patch removes it and make codes simpler.\n\nSigned-off-by: Daisuke Nishimura \u003cnishimura@mxp.nes.nec.co.jp\u003e\nCc: Balbir Singh \u003cbalbir@linux.vnet.ibm.com\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": "d31f56dbf8bafaacb0c617f9a6f137498d5c7aed", "tree": "88d095c2208d27362e58ff7431407040ead9d848", "parents": [ "57f9fd7d25ac9a0d7e3a4ced580e780ab4524e3b" ], "author": { "name": "Daisuke Nishimura", "email": "nishimura@mxp.nes.nec.co.jp", "time": "Tue Dec 15 16:47:12 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Dec 16 07:20:07 2009 -0800" }, "message": "memcg: avoid oom-killing innocent task in case of use_hierarchy\n\ntask_in_mem_cgroup(), which is called by select_bad_process() to check\nwhether a task can be a candidate for being oom-killed from memcg\u0027s limit,\nchecks \"curr-\u003euse_hierarchy\"(\"curr\" is the mem_cgroup the task belongs\nto).\n\nBut this check return true(it\u0027s false positive) when:\n\n\t\u003csome path\u003e/aa\t\tuse_hierarchy \u003d\u003d 0\t\u003c- hitting limit\n\t \u003csome path\u003e/aa/00\tuse_hierarchy \u003d\u003d 1\t\u003c- the task belongs to\n\nThis leads to killing an innocent task in aa/00. This patch is a fix for\nthis bug. And this patch also fixes the arg for\nmem_cgroup_print_oom_info(). We should print information of mem_cgroup\nwhich the task being killed, not current, belongs to.\n\nSigned-off-by: Daisuke Nishimura \u003cnishimura@mxp.nes.nec.co.jp\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": "57f9fd7d25ac9a0d7e3a4ced580e780ab4524e3b", "tree": "ff95e62e7326ba7e77903f7f767e9650c0d9b3dd", "parents": [ "a3032a2c15c6967f9f0c0c28375b1a5c833a3112" ], "author": { "name": "Daisuke Nishimura", "email": "nishimura@mxp.nes.nec.co.jp", "time": "Tue Dec 15 16:47:11 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Dec 16 07:20:07 2009 -0800" }, "message": "memcg: cleanup mem_cgroup_move_parent()\n\nmem_cgroup_move_parent() calls try_charge first and cancel_charge on\nfailure. IMHO, charge/uncharge(especially charge) is high cost operation,\nso we should avoid it as far as possible.\n\nThis patch tries to delay try_charge in mem_cgroup_move_parent() by\nre-ordering checks it does.\n\nAnd this patch renames mem_cgroup_move_account() to\n__mem_cgroup_move_account(), changes the return value of\n__mem_cgroup_move_account() from int to void, and adds a new\nwrapper(mem_cgroup_move_account()), which checks whether a @pc is valid\nfor moving account and calls __mem_cgroup_move_account().\n\nThis patch removes the last caller of trylock_page_cgroup(), so removes\nits definition too.\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@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": "a3032a2c15c6967f9f0c0c28375b1a5c833a3112", "tree": "32d279856032fd9d84ebd5d6746b2bd382baaac9", "parents": [ "d8046582d5ee24448800e71c6933fdb6813aa062" ], "author": { "name": "Daisuke Nishimura", "email": "nishimura@mxp.nes.nec.co.jp", "time": "Tue Dec 15 16:47:10 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Dec 16 07:20:07 2009 -0800" }, "message": "memcg: add mem_cgroup_cancel_charge()\n\nThere are some places calling both res_counter_uncharge() and css_put() to\ncancel the charge and the refcnt we have got by mem_cgroup_tyr_charge().\n\nThis patch introduces mem_cgroup_cancel_charge() and call it in those\nplaces.\n\nSigned-off-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nSigned-off-by: Daisuke Nishimura \u003cnishimura@mxp.nes.nec.co.jp\u003e\nReviewed-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": "d8046582d5ee24448800e71c6933fdb6813aa062", "tree": "857d014a850deee5ddb6da6550d81ce0122f03b1", "parents": [ "cdec2e4265dfa09490601b00aeabd8a8d4af30f0" ], "author": { "name": "KAMEZAWA Hiroyuki", "email": "kamezawa.hiroyu@jp.fujitsu.com", "time": "Tue Dec 15 16:47:09 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Dec 16 07:20:07 2009 -0800" }, "message": "memcg: make memcg\u0027s file mapped consistent with global VM\n\nIn global VM, FILE_MAPPED is used but memcg uses MAPPED_FILE. This makes\ngrep difficult. Replace memcg\u0027s MAPPED_FILE with FILE_MAPPED\n\nAnd in global VM, mapped shared memory is accounted into FILE_MAPPED.\nBut memcg doesn\u0027t. fix it.\nNote:\n page_is_file_cache() just checks SwapBacked or not.\n So, we need to check PageAnon.\n\nCc: Balbir Singh \u003cbalbir@in.ibm.com\u003e\nReviewed-by: Daisuke Nishimura \u003cnishimura@mxp.nes.nec.co.jp\u003e\nSigned-off-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "cdec2e4265dfa09490601b00aeabd8a8d4af30f0", "tree": "d120759b91e3e24d33f3d76010c9da990f115706", "parents": [ "569b846df54ffb2827b83ce3244c5f032394cba4" ], "author": { "name": "KAMEZAWA Hiroyuki", "email": "kamezawa.hiroyu@jp.fujitsu.com", "time": "Tue Dec 15 16:47:08 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Dec 16 07:20:07 2009 -0800" }, "message": "memcg: coalesce charging via percpu storage\n\nThis is a patch for coalescing access to res_counter at charging by percpu\ncaching. At charge, memcg charges 64pages and remember it in percpu\ncache. Because it\u0027s cache, drain/flush if necessary.\n\nThis version uses public percpu area.\n 2 benefits for using public percpu area.\n 1. Sum of stocked charge in the system is limited to # of cpus\n not to the number of memcg. This shows better synchonization.\n 2. drain code for flush/cpuhotplug is very easy (and quick)\n\nThe most important point of this patch is that we never touch res_counter\nin fast path. The res_counter is system-wide shared counter which is modified\nvery frequently. We shouldn\u0027t touch it as far as we can for avoiding\nfalse sharing.\n\nOn x86-64 8cpu server, I tested overheads of memcg at page fault by\nrunning a program which does map/fault/unmap in a loop. Running\na task per a cpu by taskset and see sum of the number of page faults\nin 60secs.\n\n[without memcg config]\n 40156968 page-faults # 0.085 M/sec ( +- 0.046% )\n 27.67 cache-miss/faults\n\n[root cgroup]\n 36659599 page-faults # 0.077 M/sec ( +- 0.247% )\n 31.58 cache miss/faults\n\n[in a child cgroup]\n 18444157 page-faults # 0.039 M/sec ( +- 0.133% )\n 69.96 cache miss/faults\n\n[ + coalescing uncharge patch]\n 27133719 page-faults # 0.057 M/sec ( +- 0.155% )\n 47.16 cache miss/faults\n\n[ + coalescing uncharge patch + this patch ]\n 34224709 page-faults # 0.072 M/sec ( +- 0.173% )\n 34.69 cache miss/faults\n\nChangelog (since Oct/2):\n - updated comments\n - replaced get_cpu_var() with __get_cpu_var() if possible.\n - removed mutex for system-wide drain. adds a counter instead of it.\n - removed CONFIG_HOTPLUG_CPU\n\nChangelog (old):\n - rebased onto the latest mmotm\n - moved charge size check before __GFP_WAIT check for avoiding unnecesary\n - added asynchronous flush routine.\n - fixed bugs pointed out by Nishimura-san.\n\n[akpm@linux-foundation.org: tweak comments]\n[nishimura@mxp.nes.nec.co.jp: don\u0027t do INIT_WORK() repeatedly against the same work_struct]\nSigned-off-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Balbir Singh \u003cbalbir@in.ibm.com\u003e\nSigned-off-by: Daisuke Nishimura \u003cnishimura@mxp.nes.nec.co.jp\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "569b846df54ffb2827b83ce3244c5f032394cba4", "tree": "77c5d373a5edf97710fab8777912971b99e84828", "parents": [ "cd9b45b78a61e8df250e69385c74e729e5b66abf" ], "author": { "name": "KAMEZAWA Hiroyuki", "email": "kamezawa.hiroyu@jp.fujitsu.com", "time": "Tue Dec 15 16:47:03 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Dec 16 07:20:07 2009 -0800" }, "message": "memcg: coalesce uncharge during unmap/truncate\n\nIn massive parallel enviroment, res_counter can be a performance\nbottleneck. One strong techinque to reduce lock contention is reducing\ncalls by coalescing some amount of calls into one.\n\nConsidering charge/uncharge chatacteristic,\n\t- charge is done one by one via demand-paging.\n\t- uncharge is done by\n\t\t- in chunk at munmap, truncate, exit, execve...\n\t\t- one by one via vmscan/paging.\n\nIt seems we have a chance to coalesce uncharges for improving scalability\nat unmap/truncation.\n\nThis patch is a for coalescing uncharge. For avoiding scattering memcg\u0027s\nstructure to functions under /mm, this patch adds memcg batch uncharge\ninformation to the task. A reason for per-task batching is for making use\nof caller\u0027s context information. We do batched uncharge (deleyed\nuncharge) when truncation/unmap occurs but do direct uncharge when\nuncharge is called by memory reclaim (vmscan.c).\n\nThe degree of coalescing depends on callers\n - at invalidate/trucate... pagevec size\n - at unmap ....ZAP_BLOCK_SIZE\n(memory itself will be freed in this degree.)\nThen, we\u0027ll not coalescing too much.\n\nOn x86-64 8cpu server, I tested overheads of memcg at page fault by\nrunning a program which does map/fault/unmap in a loop. Running\na task per a cpu by taskset and see sum of the number of page faults\nin 60secs.\n\n[without memcg config]\n 40156968 page-faults # 0.085 M/sec ( +- 0.046% )\n 27.67 cache-miss/faults\n[root cgroup]\n 36659599 page-faults # 0.077 M/sec ( +- 0.247% )\n 31.58 miss/faults\n[in a child cgroup]\n 18444157 page-faults # 0.039 M/sec ( +- 0.133% )\n 69.96 miss/faults\n[child with this patch]\n 27133719 page-faults # 0.057 M/sec ( +- 0.155% )\n 47.16 miss/faults\n\nWe can see some amounts of improvement.\n(root cgroup doesn\u0027t affected by this patch)\nAnother patch for \"charge\" will follow this and above will be improved more.\n\nChangelog(since 2009/10/02):\n - renamed filed of memcg_batch (as pages to bytes, memsw to memsw_bytes)\n - some clean up and commentary/description updates.\n - added initialize code to copy_process(). (possible bug fix)\n\nChangelog(old):\n - fixed !CONFIG_MEM_CGROUP case.\n - rebased onto the latest mmotm + softlimit fix patches.\n - unified patch for callers\n - added commetns.\n - make -\u003edo_batch as bool.\n - removed css_get() at el. We don\u0027t need it.\n\nSigned-off-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Balbir Singh \u003cbalbir@in.ibm.com\u003e\nCc: Daisuke Nishimura \u003cnishimura@mxp.nes.nec.co.jp\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "cd9b45b78a61e8df250e69385c74e729e5b66abf", "tree": "8cb92363dd4b936814de9a0823016889b3441fde", "parents": [ "6be4b78993498c253e99b12c4d0f7684a36955e2" ], "author": { "name": "Kirill A. Shutemov", "email": "kirill@shutemov.name", "time": "Tue Dec 15 16:47:01 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Dec 16 07:20:07 2009 -0800" }, "message": "memcg: fix memory.memsw.usage_in_bytes for root cgroup\n\nA memory cgroup has a memory.memsw.usage_in_bytes file. It shows the sum\nof the usage of pages and swapents in the cgroup. Presently the root\ncgroup\u0027s memsw.usage_in_bytes shows the wrong value - the number of\nswapents are not added.\n\nSo take MEM_CGROUP_STAT_SWAPOUT into account.\n\nSigned-off-by: Kirill A. Shutemov \u003ckirill@shutemov.name\u003e\nReviewed-by: Daisuke Nishimura \u003cnishimura@mxp.nes.nec.co.jp\u003e\nAcked-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: \u003cstable@kernel.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "4365a5676fa3aa1d5ae6c90c22a0044f09ba584e", "tree": "5b9914ccbdcf2aa695473421e71f6299fbe78cef", "parents": [ "3b4798cbc13dd8d1150aa6377f97f0e11450a67d" ], "author": { "name": "KAMEZAWA Hiroyuki", "email": "kamezawa.hioryu@jp.fujitsu.com", "time": "Tue Dec 15 16:45:33 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Dec 16 07:19:57 2009 -0800" }, "message": "oom-kill: fix NUMA constraint check with nodemask\n\nFix node-oriented allocation handling in oom-kill.c I myself think of this\nas a bugfix not as an ehnancement.\n\nIn these days, things are changed as\n - alloc_pages() eats nodemask as its arguments, __alloc_pages_nodemask().\n - mempolicy don\u0027t maintain its own private zonelists.\n (And cpuset doesn\u0027t use nodemask for __alloc_pages_nodemask())\n\nSo, current oom-killer\u0027s check function is wrong.\n\nThis patch does\n - check nodemask, if nodemask \u0026\u0026 nodemask doesn\u0027t cover all\n node_states[N_HIGH_MEMORY], this is CONSTRAINT_MEMORY_POLICY.\n - Scan all zonelist under nodemask, if it hits cpuset\u0027s wall\n this faiulre is from cpuset.\nAnd\n - modifies the caller of out_of_memory not to call oom if __GFP_THISNODE.\n This doesn\u0027t change \"current\" behavior. If callers use __GFP_THISNODE\n it should handle \"page allocation failure\" by itself.\n\n - handle __GFP_NOFAIL+__GFP_THISNODE path.\n This is something like a FIXME but this gfpmask is not used now.\n\n[akpm@linux-foundation.org: coding-style fixes]\nSigned-off-by: KAMEZAWA Hiroyuki \u003ckamezawa.hioryu@jp.fujitsu.com\u003e\nAcked-by: David Rientjes \u003crientjes@google.com\u003e\nCc: Daisuke Nishimura \u003cnishimura@mxp.nes.nec.co.jp\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": "3b4798cbc13dd8d1150aa6377f97f0e11450a67d", "tree": "3a805cae1557098ddd4386fd6117f4f0fde5123f", "parents": [ "8bea8672edfca7ec5f661cafb218f1205863b343" ], "author": { "name": "KOSAKI Motohiro", "email": "kosaki.motohiro@jp.fujitsu.com", "time": "Tue Dec 15 16:45:32 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Dec 16 07:19:57 2009 -0800" }, "message": "oom-kill: show virtual size and rss information of the killed process\n\nIn a typical oom analysis scenario, we frequently want to know whether the\nkilled process has a memory leak or not at the first step. This patch\nadds vsz and rss information to the oom log to help this analysis. To\nsave time for the debugging.\n\nexample:\n\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\nrsyslogd invoked oom-killer: gfp_mask\u003d0x201da, order\u003d0, oom_adj\u003d0\nPid: 1308, comm: rsyslogd Not tainted 2.6.32-rc6 #24\nCall Trace:\n[\u003cffffffff8132e35b\u003e] ?_spin_unlock+0x2b/0x40\n[\u003cffffffff810f186e\u003e] oom_kill_process+0xbe/0x2b0\n\n(snip)\n\n492283 pages non-shared\nOut of memory: kill process 2341 (memhog) score 527276 or a child\nKilled process 2341 (memhog) vsz:1054552kB, anon-rss:970588kB, file-rss:4kB\n\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\n ^\n |\n here\n\n[rientjes@google.com: fix race, add pid \u0026 comm to message]\nSigned-off-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nSigned-off-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": "f2c03debdfb387fa2e35cac6382779072b8b9209", "tree": "b43b03515fb32025ba81f0933a233f7c93c32470", "parents": [ "12686d153abff397fa0927c620d5a3de84910b72" ], "author": { "name": "Andi Kleen", "email": "andi@firstfloor.org", "time": "Wed Dec 16 12:20:01 2009 +0100" }, "committer": { "name": "Andi Kleen", "email": "ak@linux.intel.com", "time": "Wed Dec 16 12:20:01 2009 +0100" }, "message": "HWPOISON: Remove stray phrase in a comment\n\nBetter to have complete sentences.\n\nSigned-off-by: Andi Kleen \u003cak@linux.intel.com\u003e\n" }, { "commit": "12686d153abff397fa0927c620d5a3de84910b72", "tree": "3a6f19e38e99cded5067452693083ac76c63733f", "parents": [ "0d57eb8dfcb92e3dd928d792f4ed2b2fec680bb7" ], "author": { "name": "Andi Kleen", "email": "andi@firstfloor.org", "time": "Wed Dec 16 12:20:01 2009 +0100" }, "committer": { "name": "Andi Kleen", "email": "ak@linux.intel.com", "time": "Wed Dec 16 12:20:01 2009 +0100" }, "message": "HWPOISON: Try to allocate migration page on the same node\n\nSigned-off-by: Andi Kleen \u003cak@linux.intel.com\u003e\n" }, { "commit": "0d57eb8dfcb92e3dd928d792f4ed2b2fec680bb7", "tree": "2aaf6d64134d380b3f17efd3aebb09d453f09e1d", "parents": [ "afcf938ee0aac4ef95b1a23bac704c6fbeb26de6" ], "author": { "name": "Andi Kleen", "email": "andi@firstfloor.org", "time": "Wed Dec 16 12:20:01 2009 +0100" }, "committer": { "name": "Andi Kleen", "email": "ak@linux.intel.com", "time": "Wed Dec 16 12:20:01 2009 +0100" }, "message": "HWPOISON: Don\u0027t do early filtering if filter is disabled\n\nSigned-off-by: Andi Kleen \u003cak@linux.intel.com\u003e\n" }, { "commit": "afcf938ee0aac4ef95b1a23bac704c6fbeb26de6", "tree": "fa4fe6ac0638f0abb8f7ae729b4151b8ecc52052", "parents": [ "facb6011f3993947283fa15d039dacb4ad140230" ], "author": { "name": "Andi Kleen", "email": "andi@firstfloor.org", "time": "Wed Dec 16 12:20:00 2009 +0100" }, "committer": { "name": "Andi Kleen", "email": "ak@linux.intel.com", "time": "Wed Dec 16 12:20:00 2009 +0100" }, "message": "HWPOISON: Add a madvise() injector for soft page offlining\n\nProcess based injection is much easier to handle for test programs,\nwho can first bring a page into a specific state and then test.\nSo add a new MADV_SOFT_OFFLINE to soft offline a page, similar\nto the existing hard offline injector.\n\nSigned-off-by: Andi Kleen \u003cak@linux.intel.com\u003e\n" }, { "commit": "facb6011f3993947283fa15d039dacb4ad140230", "tree": "c317e401fa7c867e1652879627163331f43085ef", "parents": [ "2326c467df4ff814dc07cf1bdaa1e6e0a9c9f21c" ], "author": { "name": "Andi Kleen", "email": "andi@firstfloor.org", "time": "Wed Dec 16 12:20:00 2009 +0100" }, "committer": { "name": "Andi Kleen", "email": "ak@linux.intel.com", "time": "Wed Dec 16 12:20:00 2009 +0100" }, "message": "HWPOISON: Add soft page offline support\n\nThis is a simpler, gentler variant of memory_failure() for soft page\nofflining controlled from user space. It doesn\u0027t kill anything, just\ntries to invalidate and if that doesn\u0027t work migrate the\npage away.\n\nThis is useful for predictive failure analysis, where a page has\na high rate of corrected errors, but hasn\u0027t gone bad yet. Instead\nit can be offlined early and avoided.\n\nThe offlining is controlled from sysfs, including a new generic\nentry point for hard page offlining for symmetry too.\n\nWe use the page isolate facility to prevent re-allocation\nrace. Normally this is only used by memory hotplug. To avoid\nraces with memory allocation I am using lock_system_sleep().\nThis avoids the situation where memory hotplug is about\nto isolate a page range and then hwpoison undoes that work.\nThis is a big hammer currently, but the simplest solution\ncurrently.\n\nWhen the page is not free or LRU we try to free pages\nfrom slab and other caches. The slab freeing is currently\nquite dumb and does not try to focus on the specific slab\ncache which might own the page. This could be potentially\nimproved later.\n\nThanks to Fengguang Wu and Haicheng Li for some fixes.\n\n[Added fix from Andrew Morton to adapt to new migrate_pages prototype]\nSigned-off-by: Andi Kleen \u003cak@linux.intel.com\u003e\n" }, { "commit": "2326c467df4ff814dc07cf1bdaa1e6e0a9c9f21c", "tree": "7876b43b70a001a8f2d426b77ac6b85d378c7a76", "parents": [ "0474a60ec704324577782b1057d05b574388d552" ], "author": { "name": "Andi Kleen", "email": "andi@firstfloor.org", "time": "Wed Dec 16 12:20:00 2009 +0100" }, "committer": { "name": "Andi Kleen", "email": "ak@linux.intel.com", "time": "Wed Dec 16 12:20:00 2009 +0100" }, "message": "HWPOISON: Undefine short-hand macros after use to avoid namespace conflict\n\nSigned-off-by: Andi Kleen \u003cak@linux.intel.com\u003e\n" }, { "commit": "0474a60ec704324577782b1057d05b574388d552", "tree": "75c574fe9a64332aeed6c636bf6bd9e6485d1603", "parents": [ "fe194d3e100dea323d7b2de96d3b44d0c067ba7a" ], "author": { "name": "Andi Kleen", "email": "andi@firstfloor.org", "time": "Wed Dec 16 12:20:00 2009 +0100" }, "committer": { "name": "Andi Kleen", "email": "ak@linux.intel.com", "time": "Wed Dec 16 12:20:00 2009 +0100" }, "message": "HWPOISON: Use new shake_page in memory_failure\n\nshake_page handles more types of page caches than\nthe much simpler lru_add_drain_all:\n\n- slab (quite inefficiently for now)\n- any other caches with a shrinker callback\n- per cpu page allocator pages\n- per CPU LRU\n\nUse this call to try to turn pages into free or LRU pages.\nThen handle the case of the page becoming free after drain everything.\n\nSigned-off-by: Andi Kleen \u003cak@linux.intel.com\u003e\n" }, { "commit": "413f9efbc513d330f00352bb7cba060a729999d3", "tree": "4c7fb14ebea463826e6509f7c728fe4ff2a4c9eb", "parents": [ "d15f107d97bd74c74d8f5144843d372666ddbdac" ], "author": { "name": "Andi Kleen", "email": "andi@firstfloor.org", "time": "Wed Dec 16 12:20:00 2009 +0100" }, "committer": { "name": "Andi Kleen", "email": "ak@linux.intel.com", "time": "Wed Dec 16 12:20:00 2009 +0100" }, "message": "HWPOISON: mention HWPoison in Kconfig entry\n\nSigned-off-by: Andi Kleen \u003cak@linux.intel.com\u003e\n" }, { "commit": "d15f107d97bd74c74d8f5144843d372666ddbdac", "tree": "6c12d3c738c3118ccab724b5b984fc07c7e58082", "parents": [ "1bfe5febe34d2be2120803c10720e179186357c9" ], "author": { "name": "Andi Kleen", "email": "andi@firstfloor.org", "time": "Wed Dec 16 12:20:00 2009 +0100" }, "committer": { "name": "Andi Kleen", "email": "ak@linux.intel.com", "time": "Wed Dec 16 12:20:00 2009 +0100" }, "message": "HWPOISON: Use get_user_page_fast in hwpoison madvise\n\nThe previous version didn\u0027t take the mmap_sem before calling gup(),\nwhich is racy.\n\nUse get_user_pages_fast() instead which doesn\u0027t need any locks.\nThis is also faster of course, but then it doesn\u0027t really matter\nbecause this is just a testing path.\n\nBased on report from Nick Piggin.\nCc: npiggin@suse.de\n\nSigned-off-by: Andi Kleen \u003cak@linux.intel.com\u003e\n" }, { "commit": "1bfe5febe34d2be2120803c10720e179186357c9", "tree": "d4d8b1dacc375a1004ab1ed508333bc33e46d9a9", "parents": [ "4fd466eb46a6a917c317a87fb94bfc7252a0f7ed" ], "author": { "name": "Haicheng Li", "email": "haicheng.li@linux.intel.com", "time": "Wed Dec 16 12:19:59 2009 +0100" }, "committer": { "name": "Andi Kleen", "email": "ak@linux.intel.com", "time": "Wed Dec 16 12:19:59 2009 +0100" }, "message": "HWPOISON: add an interface to switch off/on all the page filters\n\nIn some use cases, user doesn\u0027t need extra filtering. E.g. user program\ncan inject errors through madvise syscall to its own pages, however it\nmight not know what the page state exactly is or which inode the page\nbelongs to.\n\nSo introduce an one-off interface \"corrupt-filter-enable\".\n\nEcho 0 to switch off page filters, and echo 1 to switch on the filters.\n[AK: changed default to 0]\n\nSigned-off-by: Haicheng Li \u003chaicheng.li@linux.intel.com\u003e\nSigned-off-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nSigned-off-by: Andi Kleen \u003cak@linux.intel.com\u003e\n" }, { "commit": "4fd466eb46a6a917c317a87fb94bfc7252a0f7ed", "tree": "003b28724241a22a41dc9ae067f30beadbf76e6a", "parents": [ "d324236b3333e87c8825b35f2104184734020d35" ], "author": { "name": "Andi Kleen", "email": "andi@firstfloor.org", "time": "Wed Dec 16 12:19:59 2009 +0100" }, "committer": { "name": "Andi Kleen", "email": "ak@linux.intel.com", "time": "Wed Dec 16 12:19:59 2009 +0100" }, "message": "HWPOISON: add memory cgroup filter\n\nThe hwpoison test suite need to inject hwpoison to a collection of\nselected task pages, and must not touch pages not owned by them and\nthus kill important system processes such as init. (But it\u0027s OK to\nmis-hwpoison free/unowned pages as well as shared clean pages.\nMis-hwpoison of shared dirty pages will kill all tasks, so the test\nsuite will target all or non of such tasks in the first place.)\n\nThe memory cgroup serves this purpose well. We can put the target\nprocesses under the control of a memory cgroup, and tell the hwpoison\ninjection code to only kill pages associated with some active memory\ncgroup.\n\nThe prerequisite for doing hwpoison stress tests with mem_cgroup is,\nthe mem_cgroup code tracks task pages _accurately_ (unless page is\nlocked). Which we believe is/should be true.\n\nThe benefits are simplification of hwpoison injector code. Also the\nmem_cgroup code will automatically be tested by hwpoison test cases.\n\nThe alternative interfaces pin-pfn/unpin-pfn can also delegate the\n(process and page flags) filtering functions reliably to user space.\nHowever prototype implementation shows that this scheme adds more\ncomplexity than we wanted.\n\nExample test case:\n\n\tmkdir /cgroup/hwpoison\n\n\tusemem -m 100 -s 1000 \u0026\n\techo `jobs -p` \u003e /cgroup/hwpoison/tasks\n\n\tmemcg_ino\u003d$(ls -id /cgroup/hwpoison | cut -f1 -d\u0027 \u0027)\n\techo $memcg_ino \u003e /debug/hwpoison/corrupt-filter-memcg\n\n\tpage-types -p `pidof init` --hwpoison # shall do nothing\n\tpage-types -p `pidof usemem` --hwpoison # poison its pages\n\n[AK: Fix documentation]\n[Add fix for problem noticed by Li Zefan \u003clizf@cn.fujitsu.com\u003e;\ndentry in the css could be NULL]\n\nCC: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCC: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nCC: Daisuke Nishimura \u003cnishimura@mxp.nes.nec.co.jp\u003e\nCC: Balbir Singh \u003cbalbir@linux.vnet.ibm.com\u003e\nCC: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCC: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nCC: Paul Menage \u003cmenage@google.com\u003e\nCC: Nick Piggin \u003cnpiggin@suse.de\u003e\nCC: Andi Kleen \u003candi@firstfloor.org\u003e\nSigned-off-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nSigned-off-by: Andi Kleen \u003cak@linux.intel.com\u003e\n" }, { "commit": "d324236b3333e87c8825b35f2104184734020d35", "tree": "e8ad6b50e50f975b692cc6a15d5812a51d0047ad", "parents": [ "e42d9d5d47961fb5db0be65b56dd52fe7b2421f1" ], "author": { "name": "Wu Fengguang", "email": "fengguang.wu@intel.com", "time": "Wed Dec 16 12:19:59 2009 +0100" }, "committer": { "name": "Andi Kleen", "email": "ak@linux.intel.com", "time": "Wed Dec 16 12:19:59 2009 +0100" }, "message": "memcg: add accessor to mem_cgroup.css\n\nSo that an outside user can free the reference count grabbed by\ntry_get_mem_cgroup_from_page().\n\nCC: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCC: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nCC: Daisuke Nishimura \u003cnishimura@mxp.nes.nec.co.jp\u003e\nCC: Balbir Singh \u003cbalbir@linux.vnet.ibm.com\u003e\nAcked-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nSigned-off-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nSigned-off-by: Andi Kleen \u003cak@linux.intel.com\u003e\n" }, { "commit": "e42d9d5d47961fb5db0be65b56dd52fe7b2421f1", "tree": "6a898c8d43ee0533581076342b9a7a97cca0509e", "parents": [ "478c5ffc0b50527bd2390f2daa46cc16276b8413" ], "author": { "name": "Wu Fengguang", "email": "fengguang.wu@intel.com", "time": "Wed Dec 16 12:19:59 2009 +0100" }, "committer": { "name": "Andi Kleen", "email": "ak@linux.intel.com", "time": "Wed Dec 16 12:19:59 2009 +0100" }, "message": "memcg: rename and export try_get_mem_cgroup_from_page()\n\nSo that the hwpoison injector can get mem_cgroup for arbitrary page\nand thus know whether it is owned by some mem_cgroup task(s).\n\n[AK: Merged with latest git tree]\n\nCC: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCC: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nCC: Daisuke Nishimura \u003cnishimura@mxp.nes.nec.co.jp\u003e\nCC: Balbir Singh \u003cbalbir@linux.vnet.ibm.com\u003e\nAcked-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nSigned-off-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nSigned-off-by: Andi Kleen \u003cak@linux.intel.com\u003e\n" }, { "commit": "478c5ffc0b50527bd2390f2daa46cc16276b8413", "tree": "f58f5be9760fd0e81567611cf6e9f9bc77d1d3cd", "parents": [ "1a9b5b7fe0c5dad8a635288882d36785dea742f9" ], "author": { "name": "Wu Fengguang", "email": "fengguang.wu@intel.com", "time": "Wed Dec 16 12:19:59 2009 +0100" }, "committer": { "name": "Andi Kleen", "email": "ak@linux.intel.com", "time": "Wed Dec 16 12:19:59 2009 +0100" }, "message": "HWPOISON: add page flags filter\n\nWhen specified, only poison pages if ((page_flags \u0026 mask) \u003d\u003d value).\n\n- corrupt-filter-flags-mask\n- corrupt-filter-flags-value\n\nThis allows stress testing of many kinds of pages.\n\nStrictly speaking, the buddy pages requires taking zone lock, to avoid\nsetting PG_hwpoison on a \"was buddy but now allocated to someone\" page.\nHowever we can just do nothing because we set PG_locked in the beginning,\nthis prevents the page allocator from allocating it to someone. (It will\nBUG() on the unexpected PG_locked, which is fine for hwpoison testing.)\n\n[AK: Add select PROC_PAGE_MONITOR to satisfy dependency]\n\nCC: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nSigned-off-by: Andi Kleen \u003cak@linux.intel.com\u003e\n" }, { "commit": "31d3d3484f9bd263925ecaa341500ac2df3a5d9b", "tree": "38f331f27f3b4bc537303fc90490b88d53e43710", "parents": [ "7c116f2b0dbac4a1dd051c7a5e8cef37701cafd4" ], "author": { "name": "Wu Fengguang", "email": "fengguang.wu@intel.com", "time": "Wed Dec 16 12:19:59 2009 +0100" }, "committer": { "name": "Andi Kleen", "email": "ak@linux.intel.com", "time": "Wed Dec 16 12:19:59 2009 +0100" }, "message": "HWPOISON: limit hwpoison injector to known page types\n\n__memory_failure()\u0027s workflow is\n\n\tset PG_hwpoison\n\t//...\n\tunset PG_hwpoison if didn\u0027t pass hwpoison filter\n\nThat could kill unrelated process if it happens to page fault on the\npage with the (temporary) PG_hwpoison. The race should be big enough to\nappear in stress tests.\n\nFix it by grabbing the page and checking filter at inject time. This\nalso avoids the very noisy \"Injecting memory failure...\" messages.\n\n- we don\u0027t touch madvise() based injection, because the filters are\n generally not necessary for it.\n- if we want to apply the filters to h/w aided injection, we\u0027d better to\n rearrange the logic in __memory_failure() instead of this patch.\n\nAK: fix documentation, use drain all, cleanups\n\nCC: Haicheng Li \u003chaicheng.li@intel.com\u003e\nSigned-off-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nSigned-off-by: Andi Kleen \u003cak@linux.intel.com\u003e\n" }, { "commit": "7c116f2b0dbac4a1dd051c7a5e8cef37701cafd4", "tree": "ac7f1e56551df46bc79e400a182a57f4eae5ddaf", "parents": [ "138ce286eb6ee6d39ca4fb50516e93adaf6b605f" ], "author": { "name": "Wu Fengguang", "email": "fengguang.wu@intel.com", "time": "Wed Dec 16 12:19:59 2009 +0100" }, "committer": { "name": "Andi Kleen", "email": "ak@linux.intel.com", "time": "Wed Dec 16 12:19:59 2009 +0100" }, "message": "HWPOISON: add fs/device filters\n\nFilesystem data/metadata present the most tricky-to-isolate pages.\nIt requires careful code review and stress testing to get them right.\n\nThe fs/device filter helps to target the stress tests to some specific\nfilesystem pages. The filter condition is block device\u0027s major/minor\nnumbers:\n - corrupt-filter-dev-major\n - corrupt-filter-dev-minor\nWhen specified (non -1), only page cache pages that belong to that\ndevice will be poisoned.\n\nThe filters are checked reliably on the locked and refcounted page.\n\nHaicheng: clear PG_hwpoison and drop bad page count if filter not OK\nAK: Add documentation\n\nCC: Haicheng Li \u003chaicheng.li@intel.com\u003e\nCC: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nSigned-off-by: Andi Kleen \u003cak@linux.intel.com\u003e\n" }, { "commit": "138ce286eb6ee6d39ca4fb50516e93adaf6b605f", "tree": "a3dc707a8daa6d28e1b1b0d8315dcc5c5339ed59", "parents": [ "d95ea51e3a7e9ee051d19f1dd283ca61d1aa5ec6" ], "author": { "name": "Wu Fengguang", "email": "fengguang.wu@intel.com", "time": "Wed Dec 16 12:19:58 2009 +0100" }, "committer": { "name": "Andi Kleen", "email": "ak@linux.intel.com", "time": "Wed Dec 16 12:19:58 2009 +0100" }, "message": "HWPOISON: return 0 to indicate success reliably\n\nReturn 0 to indicate success, when\n- action result is RECOVERED or DELAYED\n- no extra page reference\n\nNote that dirty swapcache pages are kept in swapcache, so can have one\nmore reference count.\n\nSigned-off-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nSigned-off-by: Andi Kleen \u003cak@linux.intel.com\u003e\n" }, { "commit": "d95ea51e3a7e9ee051d19f1dd283ca61d1aa5ec6", "tree": "c7bbafb931c9023dfaf1db8e4882a7154dc88ba0", "parents": [ "847ce401df392b0704369fd3f75df614ac1414b4" ], "author": { "name": "Wu Fengguang", "email": "fengguang.wu@intel.com", "time": "Wed Dec 16 12:19:58 2009 +0100" }, "committer": { "name": "Andi Kleen", "email": "ak@linux.intel.com", "time": "Wed Dec 16 12:19:58 2009 +0100" }, "message": "HWPOISON: make semantics of IGNORED/DELAYED clear\n\nChange semantics for\n- IGNORED: not handled; it may well be _unsafe_\n- DELAYED: to be handled later; it is _safe_\n\nWith this change,\n- IGNORED/FAILED mean (maybe) Error\n- DELAYED/RECOVERED mean Success\n\nSigned-off-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nSigned-off-by: Andi Kleen \u003cak@linux.intel.com\u003e\n" }, { "commit": "847ce401df392b0704369fd3f75df614ac1414b4", "tree": "7c5021386dedea0d12f8a05b00c5267c4d28e426", "parents": [ "8d22ba1b74aa9420b6032d856446564fb21f8090" ], "author": { "name": "Wu Fengguang", "email": "fengguang.wu@intel.com", "time": "Wed Dec 16 12:19:58 2009 +0100" }, "committer": { "name": "Andi Kleen", "email": "ak@linux.intel.com", "time": "Wed Dec 16 12:19:58 2009 +0100" }, "message": "HWPOISON: Add unpoisoning support\n\nThe unpoisoning interface is useful for stress testing tools to\nreclaim poisoned pages (to prevent OOM)\n\nThere is no hardware level unpoisioning, so this\ncannot be used for real memory errors, only for software injected errors.\n\nNote that it may leak pages silently - those who have been removed from\nLRU cache, but not isolated from page cache/swap cache at hwpoison time.\nEspecially the stress test of dirty swap cache pages shall reboot system\nbefore exhausting memory.\n\nAK: Fix comments, add documentation, add printks, rename symbol\n\nSigned-off-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nSigned-off-by: Andi Kleen \u003cak@linux.intel.com\u003e\n" }, { "commit": "8d22ba1b74aa9420b6032d856446564fb21f8090", "tree": "6c2e2d27e81d784faa0481500f1cecc613ff1167", "parents": [ "95d01fc664b9476e0d18e3d745bb209a42a33588" ], "author": { "name": "Wu Fengguang", "email": "fengguang.wu@intel.com", "time": "Wed Dec 16 12:19:58 2009 +0100" }, "committer": { "name": "Andi Kleen", "email": "ak@linux.intel.com", "time": "Wed Dec 16 12:19:58 2009 +0100" }, "message": "HWPOISON: detect free buddy pages explicitly\n\nMost free pages in the buddy system have no PG_buddy set.\nIntroduce is_free_buddy_page() for detecting them reliably.\n\nCC: Nick Piggin \u003cnpiggin@suse.de\u003e\nCC: Mel Gorman \u003cmel@linux.vnet.ibm.com\u003e\nSigned-off-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nSigned-off-by: Andi Kleen \u003cak@linux.intel.com\u003e\n" }, { "commit": "95d01fc664b9476e0d18e3d745bb209a42a33588", "tree": "0b6a46b0f2e13fb169e64ebf0b270a52c666e7f6", "parents": [ "dc2a1cbf7d862e9d0abea1d1b4c8712dfbb5a398" ], "author": { "name": "Wu Fengguang", "email": "fengguang.wu@intel.com", "time": "Wed Dec 16 12:19:58 2009 +0100" }, "committer": { "name": "Andi Kleen", "email": "ak@linux.intel.com", "time": "Wed Dec 16 12:19:58 2009 +0100" }, "message": "HWPOISON: remove the free buddy page handler\n\nThe buddy page has already be handled in the very beginning.\nSo remove redundant code.\n\nSigned-off-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nSigned-off-by: Andi Kleen \u003cak@linux.intel.com\u003e\n" }, { "commit": "dc2a1cbf7d862e9d0abea1d1b4c8712dfbb5a398", "tree": "7a0c08509e1bff29d5a0a2ba7f414878f024352b", "parents": [ "71f72525dfaaec012e23089c73331654ea7b12d3" ], "author": { "name": "Wu Fengguang", "email": "fengguang.wu@intel.com", "time": "Wed Dec 16 12:19:58 2009 +0100" }, "committer": { "name": "Andi Kleen", "email": "ak@linux.intel.com", "time": "Wed Dec 16 12:19:58 2009 +0100" }, "message": "HWPOISON: introduce delete_from_lru_cache()\n\nIntroduce delete_from_lru_cache() to\n- clear PG_active, PG_unevictable to avoid complains at unpoison time\n- move the isolate_lru_page() call back to the handlers instead of the\n entrance of __memory_failure(), this is more hwpoison filter friendly\n\nSigned-off-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nSigned-off-by: Andi Kleen \u003cak@linux.intel.com\u003e\n" }, { "commit": "71f72525dfaaec012e23089c73331654ea7b12d3", "tree": "70a8c7831ddab19be1ee8430611ad653f3e764f3", "parents": [ "db0480b3a61bd6ad86ead3b8bbad094ab0996932" ], "author": { "name": "Wu Fengguang", "email": "fengguang.wu@intel.com", "time": "Wed Dec 16 12:19:58 2009 +0100" }, "committer": { "name": "Andi Kleen", "email": "ak@linux.intel.com", "time": "Wed Dec 16 12:19:58 2009 +0100" }, "message": "HWPOISON: comment dirty swapcache pages\n\nAK: Improve comment\n\nSigned-off-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nSigned-off-by: Andi Kleen \u003cak@linux.intel.com\u003e\n" }, { "commit": "db0480b3a61bd6ad86ead3b8bbad094ab0996932", "tree": "31b3d85181201234694a19d05590d7c5084f89ed", "parents": [ "1668bfd5be9d8a52536c4865000fbbe065a3613b" ], "author": { "name": "Wu Fengguang", "email": "fengguang.wu@intel.com", "time": "Wed Dec 16 12:19:58 2009 +0100" }, "committer": { "name": "Andi Kleen", "email": "ak@linux.intel.com", "time": "Wed Dec 16 12:19:58 2009 +0100" }, "message": "HWPOISON: comment the possible set_page_dirty() race\n\nSigned-off-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nSigned-off-by: Andi Kleen \u003cak@linux.intel.com\u003e\n" }, { "commit": "1668bfd5be9d8a52536c4865000fbbe065a3613b", "tree": "85f060960de6e27f6933d56fcfd194b25ddbc460", "parents": [ "82ba011b9041dd31c15e4f63797b08aa0a288e61" ], "author": { "name": "Wu Fengguang", "email": "fengguang.wu@intel.com", "time": "Wed Dec 16 12:19:58 2009 +0100" }, "committer": { "name": "Andi Kleen", "email": "ak@linux.intel.com", "time": "Wed Dec 16 12:19:58 2009 +0100" }, "message": "HWPOISON: abort on failed unmap\n\nDon\u0027t try to isolate a still mapped page. Otherwise we will hit the\nBUG_ON(page_mapped(page)) in __remove_from_page_cache().\n\nSigned-off-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nSigned-off-by: Andi Kleen \u003cak@linux.intel.com\u003e\n" }, { "commit": "82ba011b9041dd31c15e4f63797b08aa0a288e61", "tree": "7fd48d31ab507007c37f89a9dc41256b8585d8db", "parents": [ "bd1ce5f91f545730df4af492f774d9d32f5da3cb" ], "author": { "name": "Andi Kleen", "email": "andi@firstfloor.org", "time": "Wed Dec 16 12:19:57 2009 +0100" }, "committer": { "name": "Andi Kleen", "email": "ak@linux.intel.com", "time": "Wed Dec 16 12:19:57 2009 +0100" }, "message": "HWPOISON: Turn ref argument into flags argument\n\nNow that \"ref\" is just a boolean turn it into\na flags argument. First step is only a single flag\nthat makes the code\u0027s intention more clear, but more\nmay follow.\n\nSigned-off-by: Andi Kleen \u003cak@linux.intel.com\u003e\n" }, { "commit": "bd1ce5f91f545730df4af492f774d9d32f5da3cb", "tree": "7d25f35cda1f37e30fd21bb2375f2693837d5ec5", "parents": [ "a7560fc80f33cab33176ee78f146df22b28e3338" ], "author": { "name": "Wu Fengguang", "email": "fengguang.wu@intel.com", "time": "Wed Dec 16 12:19:57 2009 +0100" }, "committer": { "name": "Andi Kleen", "email": "ak@linux.intel.com", "time": "Wed Dec 16 12:19:57 2009 +0100" }, "message": "HWPOISON: avoid grabbing the page count multiple times during madvise injection\n\nIf page is double referenced in madvise_hwpoison() and __memory_failure(),\nremove_mapping() will fail because it expects page_count\u003d2. Fix it by\nnot grabbing extra page count in __memory_failure().\n\nSigned-off-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nSigned-off-by: Andi Kleen \u003cak@linux.intel.com\u003e\n" }, { "commit": "a7560fc80f33cab33176ee78f146df22b28e3338", "tree": "1301b08559615aa5e7db0b11f03c98f3848c8142", "parents": [ "9b9a29ecd75e310f75a9243e1c3538ad34598fcb" ], "author": { "name": "Wu Fengguang", "email": "fengguang.wu@intel.com", "time": "Wed Dec 16 12:19:57 2009 +0100" }, "committer": { "name": "Andi Kleen", "email": "ak@linux.intel.com", "time": "Wed Dec 16 12:19:57 2009 +0100" }, "message": "HWPOISON: return ENXIO on invalid page number\n\nUse a different errno than the usual EIO for invalid page numbers.\nThis is mainly for better reporting for the injector.\n\nThis also avoids calling action_result() with invalid pfn.\n\nSigned-off-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nSigned-off-by: Andi Kleen \u003cak@linux.intel.com\u003e\n" }, { "commit": "9b9a29ecd75e310f75a9243e1c3538ad34598fcb", "tree": "170f130a050f28af8bc944a23409a8591ba6d7fe", "parents": [ "0e9052eb98a9986ec0669d030604f7a68f6df638" ], "author": { "name": "Wu Fengguang", "email": "fengguang.wu@intel.com", "time": "Wed Dec 16 12:19:57 2009 +0100" }, "committer": { "name": "Andi Kleen", "email": "ak@linux.intel.com", "time": "Wed Dec 16 12:19:57 2009 +0100" }, "message": "HWPOISON: remove the anonymous entry\n\n(PG_swapbacked \u0026\u0026 !PG_lru) pages should not happen.\nBetter to treat them as unknown pages.\n\nSigned-off-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nSigned-off-by: Andi Kleen \u003cak@linux.intel.com\u003e\n" }, { "commit": "588f9ce6ca61ecb4663ee6ef2f75d2d96c73151e", "tree": "4f68c55642c51312bdf6e49818b9889ec37a1ac3", "parents": [ "7bc98b97ed5dfe710025414de771baa674998892" ], "author": { "name": "Andi Kleen", "email": "andi@firstfloor.org", "time": "Wed Dec 16 12:19:57 2009 +0100" }, "committer": { "name": "Andi Kleen", "email": "ak@linux.intel.com", "time": "Wed Dec 16 12:19:57 2009 +0100" }, "message": "HWPOISON: Be more aggressive at freeing non LRU caches\n\nshake_page handles more types of page caches than lru_drain_all()\n\n- per cpu page allocator pages\n- per CPU LRU\n\nStops early when the page became free.\n\nUsed in followon patches.\n\nSigned-off-by: Andi Kleen \u003cak@linux.intel.com\u003e\n" }, { "commit": "ea637639591def87a54cea811cbac796980cb30d", "tree": "7ea3e4baf2ffade539ae30192521d331f8e863fa", "parents": [ "5dc37642cbce34619e4588a9f0bdad1d2f870956" ], "author": { "name": "Jie Zhang", "email": "jie.zhang@analog.com", "time": "Mon Dec 14 18:00:02 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:24 2009 -0800" }, "message": "nommu: fix malloc performance by adding uninitialized flag\n\nThe NOMMU code currently clears all anonymous mmapped memory. While this\nis what we want in the default case, all memory allocation from userspace\nunder NOMMU has to go through this interface, including malloc() which is\nallowed to return uninitialized memory. This can easily be a significant\nperformance penalty. So for constrained embedded systems were security is\nirrelevant, allow people to avoid clearing memory unnecessarily.\n\nThis also alters the ELF-FDPIC binfmt such that it obtains uninitialised\nmemory for the brk and stack region.\n\nSigned-off-by: Jie Zhang \u003cjie.zhang@analog.com\u003e\nSigned-off-by: Robin Getz \u003crgetz@blackfin.uclinux.org\u003e\nSigned-off-by: Mike Frysinger \u003cvapier@gentoo.org\u003e\nSigned-off-by: David Howells \u003cdhowells@redhat.com\u003e\nAcked-by: Paul Mundt \u003clethal@linux-sh.org\u003e\nAcked-by: Greg Ungerer \u003cgerg@snapgear.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "5dc37642cbce34619e4588a9f0bdad1d2f870956", "tree": "00165a3a0b3d768abaf83cf44642f09398b989cc", "parents": [ "d33b9f45bd24a6391bc05e2b5a13c1b5787ca9c2" ], "author": { "name": "Naoya Horiguchi", "email": "n-horiguchi@ah.jp.nec.com", "time": "Mon Dec 14 18:00:01 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:24 2009 -0800" }, "message": "mm hugetlb: add hugepage support to pagemap\n\nThis patch enables extraction of the pfn of a hugepage from\n/proc/pid/pagemap in an architecture independent manner.\n\nDetails\n-------\nMy test program (leak_pagemap) works as follows:\n - creat() and mmap() a file on hugetlbfs (file size is 200MB \u003d\u003d 100 hugepages,)\n - read()/write() something on it,\n - call page-types with option -p,\n - munmap() and unlink() the file on hugetlbfs\n\nWithout my patches\n------------------\n$ ./leak_pagemap\n flags page-count MB symbolic-flags long-symbolic-flags\n0x0000000000000000 1 0 __________________________________\n0x0000000000000804 1 0 __R________M______________________ referenced,mmap\n0x000000000000086c 81 0 __RU_lA____M______________________ referenced,uptodate,lru,active,mmap\n0x0000000000005808 5 0 ___U_______Ma_b___________________ uptodate,mmap,anonymous,swapbacked\n0x0000000000005868 12 0 ___U_lA____Ma_b___________________ uptodate,lru,active,mmap,anonymous,swapbacked\n0x000000000000586c 1 0 __RU_lA____Ma_b___________________ referenced,uptodate,lru,active,mmap,anonymous,swapbacked\n total 101 0\n\nThe output of page-types don\u0027t show any hugepage.\n\nWith my patches\n---------------\n$ ./leak_pagemap\n flags page-count MB symbolic-flags long-symbolic-flags\n0x0000000000000000 1 0 __________________________________\n0x0000000000030000 51100 199 ________________TG________________ compound_tail,huge\n0x0000000000028018 100 0 ___UD__________H_G________________ uptodate,dirty,compound_head,huge\n0x0000000000000804 1 0 __R________M______________________ referenced,mmap\n0x000000000000080c 1 0 __RU_______M______________________ referenced,uptodate,mmap\n0x000000000000086c 80 0 __RU_lA____M______________________ referenced,uptodate,lru,active,mmap\n0x0000000000005808 4 0 ___U_______Ma_b___________________ uptodate,mmap,anonymous,swapbacked\n0x0000000000005868 12 0 ___U_lA____Ma_b___________________ uptodate,lru,active,mmap,anonymous,swapbacked\n0x000000000000586c 1 0 __RU_lA____Ma_b___________________ referenced,uptodate,lru,active,mmap,anonymous,swapbacked\n total 51300 200\n\nThe output of page-types shows 51200 pages contributing to hugepages,\ncontaining 100 head pages and 51100 tail pages as expected.\n\n[akpm@linux-foundation.org: build fix]\nSigned-off-by: Naoya Horiguchi \u003cn-horiguchi@ah.jp.nec.com\u003e\nCc: Andi Kleen \u003cak@linux.intel.com\u003e\nCc: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nCc: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Andy Whitcroft \u003capw@canonical.com\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": "d33b9f45bd24a6391bc05e2b5a13c1b5787ca9c2", "tree": "c79c7a452a18f513efbbc807440812432778332f", "parents": [ "4f16fc107d9c9b8a72aa19b189a9216e90a7aaef" ], "author": { "name": "Naoya Horiguchi", "email": "n-horiguchi@ah.jp.nec.com", "time": "Mon Dec 14 17:59:59 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:24 2009 -0800" }, "message": "mm: hugetlb: fix hugepage memory leak in walk_page_range()\n\nMost callers of pmd_none_or_clear_bad() check whether the target page is\nin a hugepage or not, but walk_page_range() do not check it. So if we\nread /proc/pid/pagemap for the hugepage on x86 machine, the hugepage\nmemory is leaked as shown below. This patch fixes it.\n\nDetails\n\u003d\u003d\u003d\u003d\u003d\u003d\u003d\nMy test program (leak_pagemap) works as follows:\n - creat() and mmap() a file on hugetlbfs (file size is 200MB \u003d\u003d 100 hugepages,)\n - read()/write() something on it,\n - call page-types with option -p (walk around the page tables),\n - munmap() and unlink() the file on hugetlbfs\n\nWithout my patches\n------------------\n$ cat /proc/meminfo |grep \"HugePage\"\nHugePages_Total: 1000\nHugePages_Free: 1000\nHugePages_Rsvd: 0\nHugePages_Surp: 0\n$ ./leak_pagemap\n[snip output]\n$ cat /proc/meminfo |grep \"HugePage\"\nHugePages_Total: 1000\nHugePages_Free: 900\nHugePages_Rsvd: 0\nHugePages_Surp: 0\n$ ls /hugetlbfs/\n$\n\n100 hugepages are accounted as used while there is no file on hugetlbfs.\n\nWith my patches\n---------------\n$ cat /proc/meminfo |grep \"HugePage\"\nHugePages_Total: 1000\nHugePages_Free: 1000\nHugePages_Rsvd: 0\nHugePages_Surp: 0\n$ ./leak_pagemap\n[snip output]\n$ cat /proc/meminfo |grep \"HugePage\"\nHugePages_Total: 1000\nHugePages_Free: 1000\nHugePages_Rsvd: 0\nHugePages_Surp: 0\n$ ls /hugetlbfs\n$\n\nNo memory leaks.\n\nSigned-off-by: Naoya Horiguchi \u003cn-horiguchi@ah.jp.nec.com\u003e\nCc: Andi Kleen \u003cak@linux.intel.com\u003e\nCc: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nCc: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Andy Whitcroft \u003capw@canonical.com\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nCc: \u003cstable@kernel.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "4f16fc107d9c9b8a72aa19b189a9216e90a7aaef", "tree": "7d2cd426ab80a30d3fc7584605738ad39a8b24be", "parents": [ "536240f2bde98216feac87b4891d19a536b8884a" ], "author": { "name": "Naoya Horiguchi", "email": "n-horiguchi@ah.jp.nec.com", "time": "Mon Dec 14 17:59:58 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:24 2009 -0800" }, "message": "mm: hugetlb: fix hugepage memory leak in mincore()\n\nMost callers of pmd_none_or_clear_bad() check whether the target page is\nin a hugepage or not, but mincore() and walk_page_range() do not check it.\n So if we use mincore() on a hugepage on x86 machine, the hugepage memory\nis leaked as shown below. This patch fixes it by extending mincore()\nsystem call to support hugepages.\n\nDetails\n\u003d\u003d\u003d\u003d\u003d\u003d\u003d\nMy test program (leak_mincore) works as follows:\n - creat() and mmap() a file on hugetlbfs (file size is 200MB \u003d\u003d 100 hugepages,)\n - read()/write() something on it,\n - call mincore() for first ten pages and printf() the values of *vec\n - munmap() and unlink() the file on hugetlbfs\n\nWithout my patch\n----------------\n$ cat /proc/meminfo| grep \"HugePage\"\nHugePages_Total: 1000\nHugePages_Free: 1000\nHugePages_Rsvd: 0\nHugePages_Surp: 0\n$ ./leak_mincore\nvec[0] 0\nvec[1] 0\nvec[2] 0\nvec[3] 0\nvec[4] 0\nvec[5] 0\nvec[6] 0\nvec[7] 0\nvec[8] 0\nvec[9] 0\n$ cat /proc/meminfo |grep \"HugePage\"\nHugePages_Total: 1000\nHugePages_Free: 999\nHugePages_Rsvd: 0\nHugePages_Surp: 0\n$ ls /hugetlbfs/\n$\n\nReturn values in *vec from mincore() are set to 0, while the hugepage\nshould be in memory, and 1 hugepage is still accounted as used while\nthere is no file on hugetlbfs.\n\nWith my patch\n-------------\n$ cat /proc/meminfo| grep \"HugePage\"\nHugePages_Total: 1000\nHugePages_Free: 1000\nHugePages_Rsvd: 0\nHugePages_Surp: 0\n$ ./leak_mincore\nvec[0] 1\nvec[1] 1\nvec[2] 1\nvec[3] 1\nvec[4] 1\nvec[5] 1\nvec[6] 1\nvec[7] 1\nvec[8] 1\nvec[9] 1\n$ cat /proc/meminfo |grep \"HugePage\"\nHugePages_Total: 1000\nHugePages_Free: 1000\nHugePages_Rsvd: 0\nHugePages_Surp: 0\n$ ls /hugetlbfs/\n$\n\nReturn value in *vec set to 1 and no memory leaks.\n\n[akpm@linux-foundation.org: cleanup]\n[akpm@linux-foundation.org: build fix]\nSigned-off-by: Naoya Horiguchi \u003cn-horiguchi@ah.jp.nec.com\u003e\nCc: Andi Kleen \u003cak@linux.intel.com\u003e\nCc: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nCc: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Andy Whitcroft \u003capw@canonical.com\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nCc: \u003cstable@kernel.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "536240f2bde98216feac87b4891d19a536b8884a", "tree": "e4755bb36c232262a2ebadb055d8947acb39b672", "parents": [ "6927c1dd93fc982140f3a3742ac4b224cd3e02b2" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Mon Dec 14 17:59:56 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:24 2009 -0800" }, "message": "hugetlb: abort a hugepage pool resize if a signal is pending\n\nIf a user asks for a hugepage pool resize but specified a large number,\nthe machine can begin trashing. In response, they might hit ctrl-c but\nsignals are ignored and the pool resize continues until it fails an\nallocation. This can take a considerable amount of time so this patch\naborts a pool resize if a signal is pending.\n\nSuggested by Dave Hansen.\n\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: Dave Hansen \u003cdave@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": "6927c1dd93fc982140f3a3742ac4b224cd3e02b2", "tree": "c87db39ee74fcc825cf238ec289473f01f476897", "parents": [ "418b27ef50e7e9b0c2fbd88db804bf065e5eb1a6" ], "author": { "name": "Lee Schermerhorn", "email": "Lee.Schermerhorn@hp.com", "time": "Mon Dec 14 17:59:55 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:23 2009 -0800" }, "message": "mlock: replace stale comments in munlock_vma_page()\n\nCleanup stale comments on munlock_vma_page().\n\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nAcked-by: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\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": "418b27ef50e7e9b0c2fbd88db804bf065e5eb1a6", "tree": "24a4354bfa3bda6c763b859c235669c939c97ce4", "parents": [ "4eb2b1dcd598f8489130405c81c60c289896d92a" ], "author": { "name": "Lee Schermerhorn", "email": "Lee.Schermerhorn@hp.com", "time": "Mon Dec 14 17:59:54 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:23 2009 -0800" }, "message": "mm: remove unevictable_migrate_page function\n\nunevictable_migrate_page() in mm/internal.h is a relic of the since\nremoved UNEVICTABLE_LRU Kconfig option. This patch removes the function\nand open codes the test in migrate_page_copy().\n\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nReviewed-by: Christoph Lameter \u003ccl@linux-foundation.org\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" }, { "commit": "4eb2b1dcd598f8489130405c81c60c289896d92a", "tree": "87bf0dec35f55688595447de65eb95952eb3dabc", "parents": [ "70da2340fbc68e91e701762f785479ab495a0869" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Mon Dec 14 17:59:53 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:23 2009 -0800" }, "message": "hugetlb: acquire the i_mmap_lock before walking the prio_tree to unmap a page\n\nWhen the owner of a mapping fails COW because a child process is holding a\nreference, the children VMAs are walked and the page is unmapped. The\ni_mmap_lock is taken for the unmapping of the page but not the walking of\nthe prio_tree. In theory, that tree could be changing if the lock is not\nheld. This patch takes the i_mmap_lock properly for the duration of the\nprio_tree walk.\n\n[hugh.dickins@tiscali.co.uk: Spotted the problem in the first place]\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\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" }, { "commit": "c9d0bf241451a3ab7d02e1652c22b80cd7d93e8f", "tree": "f72d7eedf3fee82193407c7190321399833f422c", "parents": [ "62c0c2f198c1f2ead05c961e83ef486c45888325" ], "author": { "name": "Magnus Damm", "email": "damm@opensource.se", "time": "Mon Dec 14 17:59:49 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:21 2009 -0800" }, "message": "mm: uncached vma support with writenotify\n\nModify the generic mmap() code to keep the cache attribute in\nvma-\u003evm_page_prot regardless if writenotify is enabled or not. Without\nthis patch the cache configuration selected by f_op-\u003emmap() is overwritten\nif writenotify is enabled, making it impossible to keep the vma uncached.\n\nNeeded by drivers such as drivers/video/sh_mobile_lcdcfb.c which uses\ndeferred io together with uncached memory.\n\nSigned-off-by: Magnus Damm \u003cdamm@opensource.se\u003e\nCc: Nick Piggin \u003cnickpiggin@yahoo.com.au\u003e\nCc: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nCc: Paul Mundt \u003clethal@linux-sh.org\u003e\nCc: Jaya Kumar \u003cjayakumar.lkml@gmail.com\u003e\nCc: Arnd Bergmann \u003carnd@arndb.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "62c0c2f198c1f2ead05c961e83ef486c45888325", "tree": "d880a44df34d3cd14318efd1d5bee186a03cc841", "parents": [ "b39415b2731d7dec5e612d2d12595da82399eedf" ], "author": { "name": "Huang Shijie", "email": "shijie8@gmail.com", "time": "Mon Dec 14 17:59:48 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:21 2009 -0800" }, "message": "vmscan: simplify code\n\nSimplify the code for shrink_inactive_list().\n\nSigned-off-by: Huang Shijie \u003cshijie8@gmail.com\u003e\nReviewed-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nReviewed-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": "b39415b2731d7dec5e612d2d12595da82399eedf", "tree": "a8c59b1bc820d643d2e969f866a54147d7015c2e", "parents": [ "8aa043d74559556a661cb2eb6e64497eec86ec77" ], "author": { "name": "Rik van Riel", "email": "riel@redhat.com", "time": "Mon Dec 14 17:59:48 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:21 2009 -0800" }, "message": "vmscan: do not evict inactive pages when skipping an active list scan\n\nIn AIM7 runs, recent kernels start swapping out anonymous pages well\nbefore they should. This is due to shrink_list falling through to\nshrink_inactive_list if !inactive_anon_is_low(zone, sc), when all we\nreally wanted to do is pre-age some anonymous pages to give them extra\ntime to be referenced while on the inactive list.\n\nThe obvious fix is to make sure that shrink_list does not fall through to\nscanning/reclaiming inactive pages when we called it to scan one of the\nactive lists.\n\nThis change should be safe because the loop in shrink_zone ensures that we\nwill still shrink the anon and file inactive lists whenever we should.\n\n[kosaki.motohiro@jp.fujitsu.com: inactive_file_is_low() should be inactive_anon_is_low()]\nReported-by: Larry Woodman \u003clwoodman@redhat.com\u003e\nSigned-off-by: Rik van Riel \u003criel@redhat.com\u003e\nAcked-by: Johannes Weiner \u003channes@cmpxchg.org\u003e\nCc: Tomasz Chmielewski \u003cmangoo@wpkg.org\u003e\nSigned-off-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": "8aa043d74559556a661cb2eb6e64497eec86ec77", "tree": "73559e8b70d2f2d139ca3c404687873d34ff7b36", "parents": [ "9ae49fab239fb49de92a657c7426271e0793c4e1" ], "author": { "name": "Jan Beulich", "email": "JBeulich@novell.com", "time": "Mon Dec 14 17:59:46 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:20 2009 -0800" }, "message": "mm/bootmem.c: properly __init-annotate helper functions\n\nSigned-off-by: Jan Beulich \u003cjbeulich@novell.com\u003e\nCc: Johannes Weiner \u003channes@cmpxchg.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "caed0f486e582eeeb6e3546417fd758230fe4ad9", "tree": "203d4724dcfaae3ad4b349e1971bb3efc0da7db2", "parents": [ "23ce932a5e3ec3b9f06e92c8797d834d43abfb0f" ], "author": { "name": "KOSAKI Motohiro", "email": "kosaki.motohiro@jp.fujitsu.com", "time": "Mon Dec 14 17:59:45 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:20 2009 -0800" }, "message": "mm: simplify try_to_unmap_one()\n\nSWAP_MLOCK mean \"We marked the page as PG_MLOCK, please move it to\nunevictable-lru\". So, following code is easy confusable.\n\n if (vma-\u003evm_flags \u0026 VM_LOCKED) {\n ret \u003d SWAP_MLOCK;\n goto out_unmap;\n }\n\nPlus, if the VMA doesn\u0027t have VM_LOCKED, We don\u0027t need to check\nthe needed of calling mlock_vma_page().\n\nAlso, add some commentary to try_to_unmap_one().\n\nAcked-by: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nSigned-off-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": "23ce932a5e3ec3b9f06e92c8797d834d43abfb0f", "tree": "a966c72393e3f6111e383528055518e251eeda9c", "parents": [ "b76c8cfbff94263fdf2f408e94b78b049c24a9dc" ], "author": { "name": "Rakib Mullick", "email": "rakib.mullick@gmail.com", "time": "Mon Dec 14 17:59:44 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:20 2009 -0800" }, "message": "mm: fix section mismatch in memory_hotplug.c\n\n__free_pages_bootmem() is a __meminit function - which has been called\nfrom put_pages_bootmem thus causes a section mismatch warning.\n\n We were warned by the following warning:\n\n LD mm/built-in.o\nWARNING: mm/built-in.o(.text+0x26b22): Section mismatch in reference\nfrom the function put_page_bootmem() to the function\n.meminit.text:__free_pages_bootmem()\nThe function put_page_bootmem() references\nthe function __meminit __free_pages_bootmem().\nThis is often because put_page_bootmem lacks a __meminit\nannotation or the annotation of __free_pages_bootmem is wrong.\n\nSigned-off-by: Rakib Mullick \u003crakib.mullick@gmail.com\u003e\nCc: Yasunori Goto \u003cy-goto@jp.fujitsu.com\u003e\nCc: Badari Pulavarty \u003cpbadari@us.ibm.com\u003e\nCc: Johannes Weiner \u003channes@cmpxchg.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "b76c8cfbff94263fdf2f408e94b78b049c24a9dc", "tree": "2252a29e2cfaddf08060174afd635e5f8ab66c1f", "parents": [ "b4e655a4aaa327810110457cef92681447dd13e4" ], "author": { "name": "Larry Woodman", "email": "lwoodman@redhat.com", "time": "Mon Dec 14 17:59:37 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:20 2009 -0800" }, "message": "hugetlb: prevent deadlock in __unmap_hugepage_range() when alloc_huge_page() fails\n\nhugetlb_fault() takes the mm-\u003epage_table_lock spinlock then calls\nhugetlb_cow(). If the alloc_huge_page() in hugetlb_cow() fails due to an\ninsufficient huge page pool it calls unmap_ref_private() with the\nmm-\u003epage_table_lock held. unmap_ref_private() then calls\nunmap_hugepage_range() which tries to acquire the mm-\u003epage_table_lock.\n\n[\u003cffffffff810928c3\u003e] print_circular_bug_tail+0x80/0x9f\n [\u003cffffffff8109280b\u003e] ? check_noncircular+0xb0/0xe8\n [\u003cffffffff810935e0\u003e] __lock_acquire+0x956/0xc0e\n [\u003cffffffff81093986\u003e] lock_acquire+0xee/0x12e\n [\u003cffffffff8111a7a6\u003e] ? unmap_hugepage_range+0x3e/0x84\n [\u003cffffffff8111a7a6\u003e] ? unmap_hugepage_range+0x3e/0x84\n [\u003cffffffff814c348d\u003e] _spin_lock+0x40/0x89\n [\u003cffffffff8111a7a6\u003e] ? unmap_hugepage_range+0x3e/0x84\n [\u003cffffffff8111afee\u003e] ? alloc_huge_page+0x218/0x318\n [\u003cffffffff8111a7a6\u003e] unmap_hugepage_range+0x3e/0x84\n [\u003cffffffff8111b2d0\u003e] hugetlb_cow+0x1e2/0x3f4\n [\u003cffffffff8111b935\u003e] ? hugetlb_fault+0x453/0x4f6\n [\u003cffffffff8111b962\u003e] hugetlb_fault+0x480/0x4f6\n [\u003cffffffff8111baee\u003e] follow_hugetlb_page+0x116/0x2d9\n [\u003cffffffff814c31a7\u003e] ? _spin_unlock_irq+0x3a/0x5c\n [\u003cffffffff81107b4d\u003e] __get_user_pages+0x2a3/0x427\n [\u003cffffffff81107d0f\u003e] get_user_pages+0x3e/0x54\n [\u003cffffffff81040b8b\u003e] get_user_pages_fast+0x170/0x1b5\n [\u003cffffffff81160352\u003e] dio_get_page+0x64/0x14a\n [\u003cffffffff8116112a\u003e] __blockdev_direct_IO+0x4b7/0xb31\n [\u003cffffffff8115ef91\u003e] blkdev_direct_IO+0x58/0x6e\n [\u003cffffffff8115e0a4\u003e] ? blkdev_get_blocks+0x0/0xb8\n [\u003cffffffff810ed2c5\u003e] generic_file_aio_read+0xdd/0x528\n [\u003cffffffff81219da3\u003e] ? avc_has_perm+0x66/0x8c\n [\u003cffffffff81132842\u003e] do_sync_read+0xf5/0x146\n [\u003cffffffff8107da00\u003e] ? autoremove_wake_function+0x0/0x5a\n [\u003cffffffff81211857\u003e] ? security_file_permission+0x24/0x3a\n [\u003cffffffff81132fd8\u003e] vfs_read+0xb5/0x126\n [\u003cffffffff81133f6b\u003e] ? fget_light+0x5e/0xf8\n [\u003cffffffff81133131\u003e] sys_read+0x54/0x8c\n [\u003cffffffff81011e42\u003e] system_call_fastpath+0x16/0x1b\n\nThis can be fixed by dropping the mm-\u003epage_table_lock around the call to\nunmap_ref_private() if alloc_huge_page() fails, its dropped right below in\nthe normal path anyway. However, earlier in the that function, it\u0027s also\npossible to call into the page allocator with the same spinlock held.\n\nWhat this patch does is drop the spinlock before the page allocator is\npotentially entered. The check for page allocation failure can be made\nwithout the page_table_lock as well as the copy of the huge page. Even if\nthe PTE changed while the spinlock was held, the consequence is that a\nhuge page is copied unnecessarily. This resolves both the double taking\nof the lock and sleeping with the spinlock held.\n\n[mel@csn.ul.ie: Cover also the case where process can sleep with spinlock]\nSigned-off-by: Larry Woodman \u003clwooman@redhat.com\u003e\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nAcked-by: Adam Litke \u003cagl@us.ibm.com\u003e\nCc: Andy Whitcroft \u003capw@shadowen.org\u003e\nCc: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nCc: David Gibson \u003cdavid@gibson.dropbear.id.au\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "b4e655a4aaa327810110457cef92681447dd13e4", "tree": "86f32571acdf688874967c5e597319a4c05ee888", "parents": [ "d0f209f68f80f9a152799760c230019e7f270b2a" ], "author": { "name": "Andrew Morton", "email": "akpm@linux-foundation.org", "time": "Mon Dec 14 17:59:35 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:20 2009 -0800" }, "message": "mm: memory_hotplug: make offline_pages() static\n\nIt has no references outside memory_hotplug.c.\n\nCc: \"Rafael J. Wysocki\" \u003crjw@sisk.pl\u003e\nCc: Andi Kleen \u003candi@firstfloor.org\u003e\nCc: Gerald Schaefer \u003cgerald.schaefer@de.ibm.com\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Yasunori Goto \u003cy-goto@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": "d0f209f68f80f9a152799760c230019e7f270b2a", "tree": "83e4a6b2e15f50738572b31cfadb5fc0db17d2b7", "parents": [ "62b61f611eb5e20f7e9f8619bfd03bdfe8af6348" ], "author": { "name": "Hugh Dickins", "email": "hugh.dickins@tiscali.co.uk", "time": "Mon Dec 14 17:59:34 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:20 2009 -0800" }, "message": "ksm: remove unswappable max_kernel_pages\n\nNow that ksm pages are swappable, and the known holes plugged, remove\nmention of unswappable kernel pages from KSM documentation and comments.\n\nRemove the totalram_pages/4 initialization of max_kernel_pages. In fact,\nremove max_kernel_pages altogether - we can reinstate it if removal turns\nout to break someone\u0027s script; but if we later want to limit KSM\u0027s memory\nusage, limiting the stable nodes would not be an effective approach.\n\nSigned-off-by: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nCc: Izik Eidus \u003cieidus@redhat.com\u003e\nCc: Andrea Arcangeli \u003caarcange@redhat.com\u003e\nCc: Chris Wright \u003cchrisw@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": "62b61f611eb5e20f7e9f8619bfd03bdfe8af6348", "tree": "9f06fff7eb6530fbe90b4d998b91071133f6af25", "parents": [ "e9995ef978a7d5296fe04a9a2c5ca6e66d8bb4e5" ], "author": { "name": "Hugh Dickins", "email": "hugh.dickins@tiscali.co.uk", "time": "Mon Dec 14 17:59:33 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:20 2009 -0800" }, "message": "ksm: memory hotremove migration only\n\nThe previous patch enables page migration of ksm pages, but that soon gets\ninto trouble: not surprising, since we\u0027re using the ksm page lock to lock\noperations on its stable_node, but page migration switches the page whose\nlock is to be used for that. Another layer of locking would fix it, but\ndo we need that yet?\n\nDo we actually need page migration of ksm pages? Yes, memory hotremove\nneeds to offline sections of memory: and since we stopped allocating ksm\npages with GFP_HIGHUSER, they will tend to be GFP_HIGHUSER_MOVABLE\ncandidates for migration.\n\nBut KSM is currently unconscious of NUMA issues, happily merging pages\nfrom different NUMA nodes: at present the rule must be, not to use\nMADV_MERGEABLE where you care about NUMA. So no, NUMA page migration of\nksm pages does not make sense yet.\n\nSo, to complete support for ksm swapping we need to make hotremove safe.\nksm_memory_callback() take ksm_thread_mutex when MEM_GOING_OFFLINE and\nrelease it when MEM_OFFLINE or MEM_CANCEL_OFFLINE. But if mapped pages\nare freed before migration reaches them, stable_nodes may be left still\npointing to struct pages which have been removed from the system: the\nstable_node needs to identify a page by pfn rather than page pointer, then\nit can safely prune them when MEM_OFFLINE.\n\nAnd make NUMA migration skip PageKsm pages where it skips PageReserved.\nBut it\u0027s only when we reach unmap_and_move() that the page lock is taken\nand we can be sure that raised pagecount has prevented a PageAnon from\nbeing upgraded: so add offlining arg to migrate_pages(), to migrate ksm\npage when offlining (has sufficient locking) but reject it otherwise.\n\nSigned-off-by: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nCc: Izik Eidus \u003cieidus@redhat.com\u003e\nCc: Andrea Arcangeli \u003caarcange@redhat.com\u003e\nCc: Chris Wright \u003cchrisw@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": "e9995ef978a7d5296fe04a9a2c5ca6e66d8bb4e5", "tree": "df4324273856e06b8277b7e4a0fa9289eb8e6385", "parents": [ "407f9c8b0889ced1dbe2f9157e4e60c61329d5c9" ], "author": { "name": "Hugh Dickins", "email": "hugh.dickins@tiscali.co.uk", "time": "Mon Dec 14 17:59:31 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:20 2009 -0800" }, "message": "ksm: rmap_walk to remove_migation_ptes\n\nA side-effect of making ksm pages swappable is that they have to be placed\non the LRUs: which then exposes them to isolate_lru_page() and hence to\npage migration.\n\nAdd rmap_walk() for remove_migration_ptes() to use: rmap_walk_anon() and\nrmap_walk_file() in rmap.c, but rmap_walk_ksm() in ksm.c. Perhaps some\nconsolidation with existing code is possible, but don\u0027t attempt that yet\n(try_to_unmap needs to handle nonlinears, but migration pte removal does\nnot).\n\nrmap_walk() is sadly less general than it appears: rmap_walk_anon(), like\nremove_anon_migration_ptes() which it replaces, avoids calling\npage_lock_anon_vma(), because that includes a page_mapped() test which\nfails when all migration ptes are in place. That was valid when NUMA page\nmigration was introduced (holding mmap_sem provided the missing guarantee\nthat anon_vma\u0027s slab had not already been destroyed), but I believe not\nvalid in the memory hotremove case added since.\n\nFor now do the same as before, and consider the best way to fix that\nunlikely race later on. When fixed, we can probably use rmap_walk() on\nhwpoisoned ksm pages too: for now, they remain among hwpoison\u0027s various\nexceptions (its PageKsm test comes before the page is locked, but its\npage_lock_anon_vma fails safely if an anon gets upgraded).\n\nSigned-off-by: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nCc: Izik Eidus \u003cieidus@redhat.com\u003e\nCc: Andrea Arcangeli \u003caarcange@redhat.com\u003e\nCc: Chris Wright \u003cchrisw@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": "407f9c8b0889ced1dbe2f9157e4e60c61329d5c9", "tree": "30c0c9ad224a73de621bc23909cd89cd81eda1aa", "parents": [ "80e148226028257ec0a1909d99b2c40d0ffe17f2" ], "author": { "name": "Hugh Dickins", "email": "hugh.dickins@tiscali.co.uk", "time": "Mon Dec 14 17:59:30 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:19 2009 -0800" }, "message": "ksm: mem cgroup charge swapin copy\n\nBut ksm swapping does require one small change in mem cgroup handling.\nWhen do_swap_page()\u0027s call to ksm_might_need_to_copy() does indeed\nsubstitute a duplicate page to accommodate a different anon_vma (or a the\n!PageSwapCache check in mem_cgroup_try_charge_swapin().\n\nThat was returning success without charging, on the assumption that\npte_same() would fail after, which is not the case here. Originally I\nproposed that success, so that an unshrinkable mem cgroup at its limit\nwould not fail unnecessarily; but that\u0027s a minor point, and there are\nplenty of other places where we may fail an overallocation which might\nlater prove unnecessary. So just go ahead and do what all the other\nexceptions do: proceed to charge current mm.\n\nSigned-off-by: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nCc: Izik Eidus \u003cieidus@redhat.com\u003e\nCc: Andrea Arcangeli \u003caarcange@redhat.com\u003e\nCc: Chris Wright \u003cchrisw@redhat.com\u003e\nAcked-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.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": "80e148226028257ec0a1909d99b2c40d0ffe17f2", "tree": "1e3cae42144f5c80e215ba254e01bd6847ba1b36", "parents": [ "4035c07a895974d0ac06a56fe870ad293fc451a7" ], "author": { "name": "Hugh Dickins", "email": "hugh.dickins@tiscali.co.uk", "time": "Mon Dec 14 17:59:29 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:19 2009 -0800" }, "message": "ksm: share anon page without allocating\n\nWhen ksm pages were unswappable, it made no sense to include them in mem\ncgroup accounting; but now that they are swappable (although I see no\nstrict logical connection) the principle of least surprise implies that\nthey should be accounted (with the usual dissatisfaction, that a shared\npage is accounted to only one of the cgroups using it).\n\nThis patch was intended to add mem cgroup accounting where necessary; but\nturned inside out, it now avoids allocating a ksm page, instead upgrading\nan anon page to ksm - which brings its existing mem cgroup accounting with\nit. Thus mem cgroups don\u0027t appear in the patch at all.\n\nThis upgrade from PageAnon to PageKsm takes place under page lock (via a\nsomewhat hacky NULL kpage interface), and audit showed only one place\nwhich needed to cope with the race - page_referenced() is sometimes used\nwithout page lock, so page_lock_anon_vma() needs an ACCESS_ONCE() to be\nsure of getting anon_vma and flags together (no problem if the page goes\nksm an instant after, the integrity of that anon_vma list is unaffected).\n\nSigned-off-by: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nCc: Izik Eidus \u003cieidus@redhat.com\u003e\nCc: Andrea Arcangeli \u003caarcange@redhat.com\u003e\nCc: Chris Wright \u003cchrisw@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": "4035c07a895974d0ac06a56fe870ad293fc451a7", "tree": "b0cc7cabeb0b23d97d5bd5080836d57bc5ee4689", "parents": [ "db114b83ab6064d9b1d6ec5650e096c89bd95e25" ], "author": { "name": "Hugh Dickins", "email": "hugh.dickins@tiscali.co.uk", "time": "Mon Dec 14 17:59:27 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:19 2009 -0800" }, "message": "ksm: take keyhole reference to page\n\nThere\u0027s a lamentable flaw in KSM swapping: the stable_node holds a\nreference to the ksm page, so the page to be freed cannot actually be\nfreed until ksmd works its way around to removing the last rmap_item from\nits stable_node. Which in some configurations may take minutes: not quite\nresponsive enough for memory reclaim. And we don\u0027t want to twist KSM and\nits locking more tightly into the rest of mm. What a pity.\n\nBut although the stable_node needs to hold a pointer to the ksm page, does\nit actually need to raise the reference count of that page?\n\nNo. It would need to do so if struct pages were ordinary kmalloc\u0027ed\nobjects; but they are more stable than that, and reused in particular ways\naccording to particular rules.\n\nAccess to stable_node from its pointer in struct page is no problem, so\nlong as we never free a stable_node before the ksm page itself has been\nfreed. Access to struct page from its pointer in stable_node: reintroduce\nget_ksm_page(), and let that peep out through its keyhole (the stable_node\npointer to ksm page), to see if that struct page still holds the right key\nto open it (the ksm page mapping pointer back to this stable_node).\n\nThis relies upon the established way in which free_hot_cold_page() sets an\nanon (including ksm) page-\u003emapping to NULL; and relies upon no other user\nof a struct page to put something which looks like the original\nstable_node pointer (with two low bits also set) into page-\u003emapping. It\nalso needs get_page_unless_zero() technique pioneered by speculative\npagecache; and uses rcu_read_lock() to keep the guarantees that gives.\n\nThere are several drivers which put pointers of their own into page-\u003e\nmapping; but none of those could coincide with our stable_node pointers,\nsince KSM won\u0027t free a stable_node until it sees that the page has gone.\n\nThe only problem case found is the pagetable spinlock USE_SPLIT_PTLOCKS\nplaces in struct page (my own abuse): to accommodate GENERIC_LOCKBREAK\u0027s\nbreak_lock on 32-bit, that spans both page-\u003eprivate and page-\u003emapping.\nSince break_lock is only 0 or 1, again no confusion for get_ksm_page().\n\nBut what of DEBUG_SPINLOCK on 64-bit bigendian? When owner_cpu is 3\n(matching PageKsm low bits), it might see 0xdead4ead00000003 in page-\u003e\nmapping, which might coincide? We could get around that by... but a\nbetter answer is to suppress USE_SPLIT_PTLOCKS when DEBUG_SPINLOCK or\nDEBUG_LOCK_ALLOC, to stop bloating sizeof(struct page) in their case -\nalready proposed in an earlier mm/Kconfig patch.\n\nSigned-off-by: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nCc: Izik Eidus \u003cieidus@redhat.com\u003e\nCc: Andrea Arcangeli \u003caarcange@redhat.com\u003e\nCc: Chris Wright \u003cchrisw@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": "db114b83ab6064d9b1d6ec5650e096c89bd95e25", "tree": "15e289b25fec011238f6838c6aafa1ff5e293224", "parents": [ "5ad6468801d28c4d4ac9f48ec19297817c915f6a" ], "author": { "name": "Hugh Dickins", "email": "hugh.dickins@tiscali.co.uk", "time": "Mon Dec 14 17:59:25 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:19 2009 -0800" }, "message": "ksm: hold anon_vma in rmap_item\n\nFor full functionality, page_referenced_one() and try_to_unmap_one() need\nto know the vma: to pass vma down to arch-dependent flushes, or to observe\nVM_LOCKED or VM_EXEC. But KSM keeps no record of vma: nor can it, since\nvmas get split and merged without its knowledge.\n\nInstead, note page\u0027s anon_vma in its rmap_item when adding to stable tree:\nall the vmas which might map that page are listed by its anon_vma.\n\npage_referenced_ksm() and try_to_unmap_ksm() then traverse the anon_vma,\nfirst to find the probable vma, that which matches rmap_item\u0027s mm; but if\nthat is not enough to locate all instances, traverse again to try the\nothers. This catches those occasions when fork has duplicated a pte of a\nksm page, but ksmd has not yet come around to assign it an rmap_item.\n\nBut each rmap_item in the stable tree which refers to an anon_vma needs to\ntake a reference to it. Andrea\u0027s anon_vma design cleverly avoided a\nreference count (an anon_vma was free when its list of vmas was empty),\nbut KSM now needs to add that. Is a 32-bit count sufficient? I believe\nso - the anon_vma is only free when both count is 0 and list is empty.\n\nSigned-off-by: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nCc: Izik Eidus \u003cieidus@redhat.com\u003e\nCc: Andrea Arcangeli \u003caarcange@redhat.com\u003e\nCc: Chris Wright \u003cchrisw@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": "5ad6468801d28c4d4ac9f48ec19297817c915f6a", "tree": "edd8dc48693f43278d6fe1614aca2bf660d4dc10", "parents": [ "73848b4684e84a84cfd1555af78d41158f31e16b" ], "author": { "name": "Hugh Dickins", "email": "hugh.dickins@tiscali.co.uk", "time": "Mon Dec 14 17:59:24 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:19 2009 -0800" }, "message": "ksm: let shared pages be swappable\n\nInitial implementation for swapping out KSM\u0027s shared pages: add\npage_referenced_ksm() and try_to_unmap_ksm(), which rmap.c calls when\nfaced with a PageKsm page.\n\nMost of what\u0027s needed can be got from the rmap_items listed from the\nstable_node of the ksm page, without discovering the actual vma: so in\nthis patch just fake up a struct vma for page_referenced_one() or\ntry_to_unmap_one(), then refine that in the next patch.\n\nAdd VM_NONLINEAR to ksm_madvise()\u0027s list of exclusions: it has always been\nimplicit there (being only set with VM_SHARED, already excluded), but\nlet\u0027s make it explicit, to help justify the lack of nonlinear unmap.\n\nRely on the page lock to protect against concurrent modifications to that\npage\u0027s node of the stable tree.\n\nThe awkward part is not swapout but swapin: do_swap_page() and\npage_add_anon_rmap() now have to allow for new possibilities - perhaps a\nksm page still in swapcache, perhaps a swapcache page associated with one\nlocation in one anon_vma now needed for another location or anon_vma.\n(And the vma might even be no longer VM_MERGEABLE when that happens.)\n\nksm_might_need_to_copy() checks for that case, and supplies a duplicate\npage when necessary, simply leaving it to a subsequent pass of ksmd to\nrediscover the identity and merge them back into one ksm page.\nDisappointingly primitive: but the alternative would have to accumulate\nunswappable info about the swapped out ksm pages, limiting swappability.\n\nRemove page_add_ksm_rmap(): page_add_anon_rmap() now has to allow for the\nparticular case it was handling, so just use it instead.\n\nSigned-off-by: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nCc: Izik Eidus \u003cieidus@redhat.com\u003e\nCc: Andrea Arcangeli \u003caarcange@redhat.com\u003e\nCc: Chris Wright \u003cchrisw@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": "73848b4684e84a84cfd1555af78d41158f31e16b", "tree": "b71ba30e2b20cbc45740a38e9b5aa51b8c2ea60e", "parents": [ "08beca44dfb0ab008e365163df70dbd302ae1508" ], "author": { "name": "Hugh Dickins", "email": "hugh.dickins@tiscali.co.uk", "time": "Mon Dec 14 17:59:22 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:19 2009 -0800" }, "message": "ksm: fix mlockfreed to munlocked\n\nWhen KSM merges an mlocked page, it has been forgetting to munlock it:\nthat\u0027s been left to free_page_mlock(), which reports it in /proc/vmstat as\nunevictable_pgs_mlockfreed instead of unevictable_pgs_munlocked (and\nwhinges \"Page flag mlocked set for process\" in mmotm, whereas mainline is\nsilently forgiving). Call munlock_vma_page() to fix that.\n\nSigned-off-by: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nCc: Izik Eidus \u003cieidus@redhat.com\u003e\nCc: Andrea Arcangeli \u003caarcange@redhat.com\u003e\nCc: Chris Wright \u003cchrisw@redhat.com\u003e\nAcked-by: Rik van Riel \u003criel@redhat.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": "08beca44dfb0ab008e365163df70dbd302ae1508", "tree": "33f3ddf5460e139bd7fd37e8c08026a7d852c3da", "parents": [ "7b6ba2c7d3baf8cd9f888e05563dcc32e368baab" ], "author": { "name": "Hugh Dickins", "email": "hugh.dickins@tiscali.co.uk", "time": "Mon Dec 14 17:59:21 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:19 2009 -0800" }, "message": "ksm: stable_node point to page and back\n\nAdd a pointer to the ksm page into struct stable_node, holding a reference\nto the page while the node exists. Put a pointer to the stable_node into\nthe ksm page\u0027s -\u003emapping.\n\nThen we don\u0027t need get_ksm_page() while traversing the stable tree: the\npage to compare against is sure to be present and correct, even if it\u0027s no\nlonger visible through any of its existing rmap_items.\n\nAnd we can handle the forked ksm page case more efficiently: no need to\nmemcmp our way through the tree to find its match.\n\nSigned-off-by: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\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": "7b6ba2c7d3baf8cd9f888e05563dcc32e368baab", "tree": "89e62613a37d803e4a83b96559acca29526f9638", "parents": [ "6514d511dbe5a77b4bdc0a7e26fd679585112e1e" ], "author": { "name": "Hugh Dickins", "email": "hugh.dickins@tiscali.co.uk", "time": "Mon Dec 14 17:59:20 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:19 2009 -0800" }, "message": "ksm: separate stable_node\n\nThough we still do well to keep rmap_items in the unstable tree without a\nseparate tree_item at the node, for several reasons it becomes awkward to\nkeep rmap_items in the stable tree without a separate stable_node: lack of\nspace in the nicely-sized rmap_item, the need for an anchor as rmap_items\nare removed, the need for a node even when temporarily no rmap_items are\nattached to it.\n\nSo declare struct stable_node (rb_node to place it in the tree and\nhlist_head for the rmap_items hanging off it), and convert stable tree\nhandling to use it: without yet taking advantage of it. Note how one\nstable_tree_insert() of a node now has _two_ stable_tree_append()s of the\ntwo rmap_items being merged.\n\nSigned-off-by: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\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": "6514d511dbe5a77b4bdc0a7e26fd679585112e1e", "tree": "a3fcf75191b7900043172d147fc7ed8ea97f3b4a", "parents": [ "8dd3557a52f0bc8c960307721da307370ccad6fd" ], "author": { "name": "Hugh Dickins", "email": "hugh.dickins@tiscali.co.uk", "time": "Mon Dec 14 17:59:19 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:19 2009 -0800" }, "message": "ksm: singly-linked rmap_list\n\nFree up a pointer in struct rmap_item, by making the mm_slot\u0027s rmap_list a\nsingly-linked list: we always traverse that list sequentially, and we\ndon\u0027t even lose any prefetches (but should consider adding a few later).\nName it rmap_list throughout.\n\nDo we need to free up that pointer? Not immediately, and in the end, we\ncould continue to avoid it with a union; but having done the conversion,\nlet\u0027s keep it this way, since there\u0027s no downside, and maybe we\u0027ll want\nmore in future (struct rmap_item is a cache-friendly 32 bytes on 32-bit\nand 64 bytes on 64-bit, so we shall want to avoid expanding it).\n\nSigned-off-by: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\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": "8dd3557a52f0bc8c960307721da307370ccad6fd", "tree": "711a15d188b6679026ae818bd0635d271820ea7e", "parents": [ "31e855ea7173bdb0520f9684580423a9560f66e0" ], "author": { "name": "Hugh Dickins", "email": "hugh.dickins@tiscali.co.uk", "time": "Mon Dec 14 17:59:18 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:19 2009 -0800" }, "message": "ksm: cleanup some function arguments\n\nCleanup: make argument names more consistent from cmp_and_merge_page()\ndown to replace_page(), so that it\u0027s easier to follow the rmap_item\u0027s page\nand the matching tree_page and the merged kpage through that code.\n\nIn some places, e.g. break_cow(), pass rmap_item instead of separate mm\nand address.\n\ncmp_and_merge_page() initialize tree_page to NULL, to avoid a \"may be used\nuninitialized\" warning seen in one config by Anil SB.\n\nSigned-off-by: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\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": "31e855ea7173bdb0520f9684580423a9560f66e0", "tree": "20ff327e2a58929696946971a8201da559785338", "parents": [ "93d17715a5b960d34220f2edba3e6cee9b5b1c58" ], "author": { "name": "Hugh Dickins", "email": "hugh.dickins@tiscali.co.uk", "time": "Mon Dec 14 17:59:17 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:18 2009 -0800" }, "message": "ksm: remove redundancies when merging page\n\nThere is no need for replace_page() to calculate a write-protected prot\nvm_page_prot must already be write-protected for an anonymous page (see\nmm/memory.c do_anonymous_page() for similar reliance on vm_page_prot).\n\nThere is no need for try_to_merge_one_page() to get_page and put_page on\nnewpage and oldpage: in every case we already hold a reference to each of\nthem.\n\nBut some instinct makes me move try_to_merge_one_page()\u0027s unlock_page of\noldpage down after replace_page(): that doesn\u0027t increase contention on the\nksm page, and makes thinking about the transition easier.\n\nSigned-off-by: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\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": "93d17715a5b960d34220f2edba3e6cee9b5b1c58", "tree": "9ab08ff4169464bf5b8d86c8082296fd6e3d069b", "parents": [ "338fde90930eaa02f6f394daa23d35a410af5852" ], "author": { "name": "Hugh Dickins", "email": "hugh.dickins@tiscali.co.uk", "time": "Mon Dec 14 17:59:16 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:18 2009 -0800" }, "message": "ksm: three remove_rmap_item_from_tree cleanups\n\n1. remove_rmap_item_from_tree() is called as a precaution from\n various places: don\u0027t dirty the rmap_item cacheline unnecessarily,\n just mask the flags out of the address when they have been set.\n\n2. First get_next_rmap_item() removes an unstable rmap_item from its tree,\n then shortly afterwards cmp_and_merge_page() removes a stable rmap_item\n from its tree: it\u0027s easier just to do both at once (but definitely keep\n the BUG_ON(age \u003e 1) which guards against a future omission).\n\n3. When cmp_and_merge_page() moves an rmap_item from unstable to stable\n tree, it does its own rb_erase() and accounting: that\u0027s better\n expressed by remove_rmap_item_from_tree().\n\nSigned-off-by: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\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": "338fde90930eaa02f6f394daa23d35a410af5852", "tree": "6a230b458d12e33b4b3d531f977636d1a4813102", "parents": [ "ece74b2e7acfb71453f3f39948cc667434550dbb" ], "author": { "name": "KOSAKI Motohiro", "email": "kosaki.motohiro@jp.fujitsu.com", "time": "Mon Dec 14 17:59:15 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:18 2009 -0800" }, "message": "vmscan: make consistent of reclaim bale out between do_try_to_free_page and shrink_zone\n\nFix small inconsistent of \"\u003e\" and \"\u003e\u003d\".\n\nSigned-off-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nReviewed-by: Rik van Riel \u003criel@redhat.com\u003e\nReviewed-by: Minchan Kim \u003cminchan.kim@gmail.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": "ece74b2e7acfb71453f3f39948cc667434550dbb", "tree": "08749bc2d0a6169d1c1525c502a2faf13e84b244", "parents": [ "4f0ddfdffc8bef3a5eb9154734d68a6053194948" ], "author": { "name": "KOSAKI Motohiro", "email": "kosaki.motohiro@jp.fujitsu.com", "time": "Mon Dec 14 17:59:14 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:18 2009 -0800" }, "message": "vmscan: kill sc.swap_cluster_max\n\nNow, All caller of reclaim use swap_cluster_max as SWAP_CLUSTER_MAX.\nThen, we can remove it perfectly.\n\nSigned-off-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nReviewed-by: Rik van Riel \u003criel@redhat.com\u003e\nReviewed-by: Minchan Kim \u003cminchan.kim@gmail.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": "4f0ddfdffc8bef3a5eb9154734d68a6053194948", "tree": "ae86c67cbb9290b8f090a13022736c2b862f3630", "parents": [ "7b51755c3b38483b574d363d5ee587283c3f7999" ], "author": { "name": "KOSAKI Motohiro", "email": "kosaki.motohiro@jp.fujitsu.com", "time": "Mon Dec 14 17:59:13 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:18 2009 -0800" }, "message": "vmscan: zone_reclaim() don\u0027t use insane swap_cluster_max\n\nIn old days, we didn\u0027t have sc.nr_to_reclaim and it brought\nsc.swap_cluster_max misuse.\n\nhuge sc.swap_cluster_max might makes unnecessary OOM risk and no\nperformance benefit.\n\nNow, we can stop its insane thing.\n\nSigned-off-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nReviewed-by: Rik van Riel \u003criel@redhat.com\u003e\nReviewed-by: Minchan Kim \u003cminchan.kim@gmail.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": "7b51755c3b38483b574d363d5ee587283c3f7999", "tree": "29ac6d3b73f0a28488dabff03a7df948c0333906", "parents": [ "22fba33545b731408deab6e96b6e231ee05fd10b" ], "author": { "name": "KOSAKI Motohiro", "email": "kosaki.motohiro@jp.fujitsu.com", "time": "Mon Dec 14 17:59:12 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:18 2009 -0800" }, "message": "vmscan: kill hibernation specific reclaim logic and unify it\n\nshrink_all_zone() was introduced by commit d6277db4ab (swsusp: rework\nmemory shrinker) for hibernate performance improvement. and\nsc.swap_cluster_max was introduced by commit a06fe4d307 (Speed freeing\nmemory for suspend).\n\ncommit a06fe4d307 said\n\n Without the patch:\n Freed 14600 pages in 1749 jiffies \u003d 32.61 MB/s (Anomolous!)\n Freed 88563 pages in 14719 jiffies \u003d 23.50 MB/s\n Freed 205734 pages in 32389 jiffies \u003d 24.81 MB/s\n\n With the patch:\n Freed 68252 pages in 496 jiffies \u003d 537.52 MB/s\n Freed 116464 pages in 569 jiffies \u003d 798.54 MB/s\n Freed 209699 pages in 705 jiffies \u003d 1161.89 MB/s\n\nAt that time, their patch was pretty worth. However, Modern Hardware\ntrend and recent VM improvement broke its worth. From several reason, I\nthink we should remove shrink_all_zones() at all.\n\ndetail:\n\n1) Old days, shrink_zone()\u0027s slowness was mainly caused by stupid io-throttle\n at no i/o congestion.\n but current shrink_zone() is sane, not slow.\n\n2) shrink_all_zone() try to shrink all pages at a time. but it doesn\u0027t works\n fine on numa system.\n example)\n System has 4GB memory and each node have 2GB. and hibernate need 1GB.\n\n optimal)\n steal 500MB from each node.\n shrink_all_zones)\n steal 1GB from node-0.\n\n Oh, Cache balancing logic was broken. ;)\n Unfortunately, Desktop system moved ahead NUMA at nowadays.\n (Side note, if hibernate require 2GB, shrink_all_zones() never success\n on above machine)\n\n3) if the node has several I/O flighting pages, shrink_all_zones() makes\n pretty bad result.\n\n schenario) hibernate need 1GB\n\n 1) shrink_all_zones() try to reclaim 1GB from Node-0\n 2) but it only reclaimed 990MB\n 3) stupidly, shrink_all_zones() try to reclaim 1GB from Node-1\n 4) it reclaimed 990MB\n\n Oh, well. it reclaimed twice much than required.\n In the other hand, current shrink_zone() has sane baling out logic.\n then, it doesn\u0027t make overkill reclaim. then, we lost shrink_zones()\u0027s risk.\n\n4) SplitLRU VM always keep active/inactive ratio very carefully. inactive list only\n shrinking break its assumption. it makes unnecessary OOM risk. it obviously suboptimal.\n\nNow, shrink_all_memory() is only the wrapper function of do_try_to_free_pages().\nit bring good reviewability and debuggability, and solve above problems.\n\nside note: Reclaim logic unificication makes two good side effect.\n - Fix recursive reclaim bug on shrink_all_memory().\n it did forgot to use PF_MEMALLOC. it mean the system be able to stuck into deadlock.\n - Now, shrink_all_memory() got lockdep awareness. it bring good debuggability.\n\nSigned-off-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nReviewed-by: Rik van Riel \u003criel@redhat.com\u003e\nAcked-by: Rafael J. Wysocki \u003crjw@sisk.pl\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": "22fba33545b731408deab6e96b6e231ee05fd10b", "tree": "a522c19e19c2ce82f53ab781ec7901e3bdb8b200", "parents": [ "cba5dd7fa535b7684cba68e17ac8be5b0083dc3d" ], "author": { "name": "KOSAKI Motohiro", "email": "kosaki.motohiro@jp.fujitsu.com", "time": "Mon Dec 14 17:59:10 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:18 2009 -0800" }, "message": "vmscan: separate sc.swap_cluster_max and sc.nr_max_reclaim\n\nCurrently, sc.scap_cluster_max has double meanings.\n\n 1) reclaim batch size as isolate_lru_pages()\u0027s argument\n 2) reclaim baling out thresolds\n\nThe two meanings pretty unrelated. Thus, Let\u0027s separate it.\nthis patch doesn\u0027t change any behavior.\n\nSigned-off-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nReviewed-by: Rik van Riel \u003criel@redhat.com\u003e\nReviewed-by: Minchan Kim \u003cminchan.kim@gmail.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": "d99be1a8ecf377c2c9b3372d36411ad6547bbd4c", "tree": "844a156da951783a46f9cfd0e66858eae12e5f54", "parents": [ "a70caa8ba48f21f46d3b4e71b6b8d14080bbd57a" ], "author": { "name": "Hugh Dickins", "email": "hugh.dickins@tiscali.co.uk", "time": "Mon Dec 14 17:59:04 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:17 2009 -0800" }, "message": "mm: sigbus instead of abusing oom\n\nWhen do_nonlinear_fault() realizes that the page table must have been\ncorrupted for it to have been called, it does print_bad_pte() and returns\n... VM_FAULT_OOM, which is hard to understand.\n\nIt made some sense when I did it for 2.6.15, when do_page_fault() just\nkilled the current process; but nowadays it lets the OOM killer decide who\nto kill - so page table corruption in one process would be liable to kill\nanother.\n\nChange it to return VM_FAULT_SIGBUS instead: that doesn\u0027t guarantee that\nthe process will be killed, but is good enough for such a rare\nabnormality, accompanied as it is by the \"BUG: Bad page map\" message.\n\nAnd recent HWPOISON work has copied that code into do_swap_page(), when it\nfinds an impossible swap entry: fix that to VM_FAULT_SIGBUS too.\n\nSigned-off-by: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nCc: Izik Eidus \u003cieidus@redhat.com\u003e\nCc: Andrea Arcangeli \u003caarcange@redhat.com\u003e\nCc: Nick Piggin \u003cnpiggin@suse.de\u003e\nReviewed-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Rik van Riel \u003criel@redhat.com\u003e\nCc: Lee Schermerhorn \u003cLee.Schermerhorn@hp.com\u003e\nCc: Andi Kleen \u003candi@firstfloor.org\u003e\nReviewed-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nReviewed-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nReviewed-by: Minchan Kim \u003cminchan.kim@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": "a70caa8ba48f21f46d3b4e71b6b8d14080bbd57a", "tree": "2f6ab917400f82b9d16f1e945ba101a25f5d6281", "parents": [ "1cb1729b1385884648170d9d1d3aa0c66780d64b" ], "author": { "name": "Hugh Dickins", "email": "hugh.dickins@tiscali.co.uk", "time": "Mon Dec 14 17:59:02 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:17 2009 -0800" }, "message": "mm: stop ptlock enlarging struct page\n\nCONFIG_DEBUG_SPINLOCK adds 12 or 16 bytes to a 32- or 64-bit spinlock_t,\nand CONFIG_DEBUG_LOCK_ALLOC adds another 12 or 24 bytes to it: lockdep\nenables both of those, and CONFIG_LOCK_STAT adds 8 or 16 bytes to that.\n\nWhen 2.6.15 placed the split page table lock inside struct page (usually\nsized 32 or 56 bytes), only CONFIG_DEBUG_SPINLOCK was a possibility, and\nwe ignored the enlargement (but fitted in CONFIG_GENERIC_LOCKBREAK\u0027s 4 by\nletting the spinlock_t occupy both page-\u003eprivate and page-\u003emapping).\n\nShould these debugging options be allowed to double the size of a struct\npage, when only one minority use of the page (as a page table) needs to\nfit a spinlock in there? Perhaps not.\n\nTake the easy way out: switch off SPLIT_PTLOCK_CPUS when DEBUG_SPINLOCK or\nDEBUG_LOCK_ALLOC is in force. I\u0027ve sometimes tried to be cleverer,\nkmallocing a cacheline for the spinlock when it doesn\u0027t fit, but given up\neach time. Falling back to mm-\u003epage_table_lock (as we do when ptlock is\nnot split) lets lockdep check out the strictest path anyway.\n\nAnd now that some arches allow 8192 cpus, use 999999 for infinity.\n\n(What has this got to do with KSM swapping? It doesn\u0027t care about the\nsize of struct page, but may care about random junk in page-\u003emapping - to\nbe explained separately later.)\n\nSigned-off-by: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nCc: Izik Eidus \u003cieidus@redhat.com\u003e\nCc: Andrea Arcangeli \u003caarcange@redhat.com\u003e\nCc: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Rik van Riel \u003criel@redhat.com\u003e\nCc: Lee Schermerhorn \u003cLee.Schermerhorn@hp.com\u003e\nCc: Andi Kleen \u003candi@firstfloor.org\u003e\nCc: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nCc: Minchan Kim \u003cminchan.kim@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": "1cb1729b1385884648170d9d1d3aa0c66780d64b", "tree": "57b9e58d70f791f2737997bf56a2dad98378d54d", "parents": [ "af8e3354b4bbd1ee5a3a55d11a5e1fe37e77f0ba" ], "author": { "name": "Hugh Dickins", "email": "hugh.dickins@tiscali.co.uk", "time": "Mon Dec 14 17:59:01 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:17 2009 -0800" }, "message": "mm: pass address down to rmap ones\n\nKSM swapping will know where page_referenced_one() and try_to_unmap_one()\nshould look. It could hack page-\u003eindex to get them to do what it wants,\nbut it seems cleaner now to pass the address down to them.\n\nMake the same change to page_mkclean_one(), since it follows the same\npattern; but there\u0027s no real need in its case.\n\nSigned-off-by: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nCc: Izik Eidus \u003cieidus@redhat.com\u003e\nCc: Andrea Arcangeli \u003caarcange@redhat.com\u003e\nCc: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Rik van Riel \u003criel@redhat.com\u003e\nCc: Lee Schermerhorn \u003cLee.Schermerhorn@hp.com\u003e\nCc: Andi Kleen \u003candi@firstfloor.org\u003e\nCc: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nCc: Minchan Kim \u003cminchan.kim@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": "af8e3354b4bbd1ee5a3a55d11a5e1fe37e77f0ba", "tree": "8dc0ece80878d00409d4662c5fd1e28cd7fbbdd8", "parents": [ "53f79acb6ecb648afd63e0f13deba167f1a934df" ], "author": { "name": "Hugh Dickins", "email": "hugh.dickins@tiscali.co.uk", "time": "Mon Dec 14 17:58:59 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:17 2009 -0800" }, "message": "mm: CONFIG_MMU for PG_mlocked\n\nRemove three degrees of obfuscation, left over from when we had\nCONFIG_UNEVICTABLE_LRU. MLOCK_PAGES is CONFIG_HAVE_MLOCKED_PAGE_BIT is\nCONFIG_HAVE_MLOCK is CONFIG_MMU. rmap.o (and memory-failure.o) are only\nbuilt when CONFIG_MMU, so don\u0027t need such conditions at all.\n\nSomehow, I feel no compulsion to remove the CONFIG_HAVE_MLOCK* lines from\n169 defconfigs: leave those to evolve in due course.\n\nSigned-off-by: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nCc: Izik Eidus \u003cieidus@redhat.com\u003e\nCc: Andrea Arcangeli \u003caarcange@redhat.com\u003e\nCc: Nick Piggin \u003cnpiggin@suse.de\u003e\nReviewed-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Rik van Riel \u003criel@redhat.com\u003e\nCc: Lee Schermerhorn \u003cLee.Schermerhorn@hp.com\u003e\nCc: Andi Kleen \u003candi@firstfloor.org\u003e\nCc: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nCc: Minchan Kim \u003cminchan.kim@gmail.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" } ], "next": "53f79acb6ecb648afd63e0f13deba167f1a934df" }