)]}' { "log": [ { "commit": "55cfaa3cbdd29c4919ecb5fb8965c310f357e48c", "tree": "914fad20ce59c42bd3781820c8fb73286581a5ae", "parents": [ "1f64d69c7ad2e48e697493e45590679f7a69b7b2" ], "author": { "name": "Zeng Zhaoming", "email": "zengzm.kernel@gmail.com", "time": "Thu Dec 02 14:31:13 2010 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Dec 02 14:51:14 2010 -0800" }, "message": "mm/mempolicy.c: add rcu read lock to protect pid structure\n\nfind_task_by_vpid() should be protected by rcu_read_lock(), to prevent\nfree_pid() reclaiming pid.\n\nSigned-off-by: Zeng Zhaoming \u003czengzm.kernel@gmail.com\u003e\nCc: \"Paul E. McKenney\" \u003cpaulmck@us.ibm.com\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "800416f799e0723635ac2d720ad4449917a1481c", "tree": "75f18c93accdfd4b5f58ac3172a336607bde508b", "parents": [ "0851668fdd97e526b2a41f794b785c204dd3d3e0" ], "author": { "name": "Eric Dumazet", "email": "eric.dumazet@gmail.com", "time": "Wed Oct 27 19:33:43 2010 +0200" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Oct 28 10:04:30 2010 -0700" }, "message": "numa: fix slab_node(MPOL_BIND)\n\nWhen a node contains only HighMem memory, slab_node(MPOL_BIND)\ndereferences a NULL pointer.\n\n[ This code seems to go back all the way to commit 19770b32609b: \"mm:\n filter based on a nodemask as well as a gfp_mask\". Which was back in\n April 2008, and it got merged into 2.6.26. - Linus ]\n\nSigned-off-by: Eric Dumazet \u003ceric.dumazet@gmail.com\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: Christoph Lameter \u003ccl@linux.com\u003e\nCc: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nCc: stable@kernel.org\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "0def08e3acc2c9c934e4671487029aed52202d42", "tree": "5c1259f85b0ab08cb3e421f6104bee832a956413", "parents": [ "74e3f3c3391d81a959f58a1191a560703a4415b4" ], "author": { "name": "Vasiliy Kulikov", "email": "segooon@gmail.com", "time": "Tue Oct 26 14:21:32 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Oct 26 16:52:06 2010 -0700" }, "message": "mm/mempolicy.c: check return code of check_range\n\nFunction check_range may return ERR_PTR(...). Check for it.\n\nSigned-off-by: Vasiliy Kulikov \u003csegooon@gmail.com\u003e\nAcked-by: David Rientjes \u003crientjes@google.com\u003e\nReviewed-by: Christoph Lameter \u003ccl@linux.com\u003e\nReviewed-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "cf608ac19c95804dc2df43b1f4f9e068aa9034ab", "tree": "a84d37df2b0bb57bd9a4b0b466726f5343fa5448", "parents": [ "e4455abb50a19562dbfdc51a8424fda9b588bd6d" ], "author": { "name": "Minchan Kim", "email": "minchan.kim@gmail.com", "time": "Tue Oct 26 14:21:29 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Oct 26 16:52:06 2010 -0700" }, "message": "mm: compaction: fix COMPACTPAGEFAILED counting\n\nPresently update_nr_listpages() doesn\u0027t have a role. That\u0027s because lists\npassed is always empty just after calling migrate_pages. The\nmigrate_pages cleans up page list which have failed to migrate before\nreturning by aaa994b3.\n\n [PATCH] page migration: handle freeing of pages in migrate_pages()\n\n Do not leave pages on the lists passed to migrate_pages(). Seems that we will\n not need any postprocessing of pages. This will simplify the handling of\n pages by the callers of migrate_pages().\n\nAt that time, we thought we don\u0027t need any postprocessing of pages. But\nthe situation is changed. The compaction need to know the number of\nfailed to migrate for COMPACTPAGEFAILED stat\n\nThis patch makes new rule for caller of migrate_pages to call\nputback_lru_pages. So caller need to clean up the lists so it has a\nchance to postprocess the pages. [suggested by Christoph Lameter]\n\nSigned-off-by: Minchan Kim \u003cminchan.kim@gmail.com\u003e\nCc: Hugh Dickins \u003chughd@google.com\u003e\nCc: Andi Kleen \u003candi@firstfloor.org\u003e\nReviewed-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nReviewed-by: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nAcked-by: Christoph Lameter \u003ccl@linux.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "596d7cfa2be6284512915609f01b7fe2f4df5d02", "tree": "7acfea30efdce5fb17da4302e567059bcae915eb", "parents": [ "251060006003b79b788f8ce5a827ee5354a42910" ], "author": { "name": "KOSAKI Motohiro", "email": "kosaki.motohiro@jp.fujitsu.com", "time": "Mon Aug 09 17:19:01 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Aug 09 20:44:58 2010 -0700" }, "message": "mempolicy: reduce stack size of migrate_pages()\n\nmigrate_pages() is using \u003e500 bytes stack. Reduce it.\n\n mm/mempolicy.c: In function \u0027sys_migrate_pages\u0027:\n mm/mempolicy.c:1344: warning: the frame size of 528 bytes is larger than 512 bytes\n\n[akpm@linux-foundation.org: don\u0027t play with a might-be-NULL pointer]\nSigned-off-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nReviewed-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nReviewed-by: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "6f48d0ebd907ae419387f27b602ee98870cfa7bb", "tree": "355bd8b616f5a78d8adabe5b9631d7aad970dbaa", "parents": [ "5e9d834a0e0c0485dfa487281ab9650fc37a3bb5" ], "author": { "name": "David Rientjes", "email": "rientjes@google.com", "time": "Mon Aug 09 17:18:52 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Aug 09 20:44:56 2010 -0700" }, "message": "oom: select task from tasklist for mempolicy ooms\n\nThe oom killer presently kills current whenever there is no more memory\nfree or reclaimable on its mempolicy\u0027s nodes. There is no guarantee that\ncurrent is a memory-hogging task or that killing it will free any\nsubstantial amount of memory, however.\n\nIn such situations, it is better to scan the tasklist for nodes that are\nallowed to allocate on current\u0027s set of nodes and kill the task with the\nhighest badness() score. This ensures that the most memory-hogging task,\nor the one configured by the user with /proc/pid/oom_adj, is always\nselected in such scenarios.\n\nSigned-off-by: David Rientjes \u003crientjes@google.com\u003e\nReviewed-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "5c0c165490e763eddcbb0b6c8c41ab5cc11ddea0", "tree": "729ad93071eaf065e7dfb7c7d94b0207b2eced8e", "parents": [ "56480287f9776adc5b1a7a335ef62a9b9879ad7f" ], "author": { "name": "Lee Schermerhorn", "email": "Lee.Schermerhorn@hp.com", "time": "Tue Jun 29 15:05:30 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Jun 29 15:29:31 2010 -0700" }, "message": "mempolicy: fix dangling reference to tmpfs superblock mpol\n\nMy patch to \"Factor out duplicate put/frees in mpol_shared_policy_init()\nto a common return path\"; and Dan Carpenter\u0027s fix thereto both left a\ndangling reference to the incoming tmpfs superblock mempolicy structure.\nA similar leak was introduced earlier when the nodemask was moved offstack\nto the scratch area despite the note in the comment block regarding the\nincoming ref.\n\nMove the remaining \u0027put of the incoming \"mpol\" to the common exit path to\ndrop the reference.\n\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nAcked-by: Dan Carpenter \u003cerror27@gmail.com\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nCc: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "0cae3457b1a6e88f31020272bcfd90c178716053", "tree": "71cf3f4049e9e80a5dd71219bd74061e8587a643", "parents": [ "b1cdc4670b9508fcd47a15fbd12f70d269880b37" ], "author": { "name": "Dan Carpenter", "email": "error27@gmail.com", "time": "Tue May 25 23:42:58 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed May 26 08:19:23 2010 -0700" }, "message": "mempolicy: ERR_PTR dereference in mpol_shared_policy_init()\n\nThe original code called mpol_put(new) while \"new\" was an ERR_PTR.\n\nSigned-off-by: Dan Carpenter \u003cerror27@gmail.com\u003e\nCc: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nAcked-by: David Rientjes \u003crientjes@google.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "6ec3a12712ac67ffa4b80d16e0767ffd2431a68d", "tree": "7348f7ce38efe041429a2477706181686992e801", "parents": [ "4f92e2586b43a2402e116055d4edda704f911b5b" ], "author": { "name": "Greg Thelen", "email": "gthelen@google.com", "time": "Mon May 24 14:32:33 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:07:00 2010 -0700" }, "message": "mm: consider the entire user address space during node migration\n\nUse mm-\u003etask_size instead of TASK_SIZE to ensure that the entire user\naddress space is migrated. mm-\u003etask_size is independent of the calling\ntask context. TASK SIZE may be dependant on the address space size of the\ncalling process. Usage of TASK_SIZE can lead to partial address space\nmigration if the calling process was 32 bit and the migrating process was\n64 bit.\n\nHere is the test script used on 64 system with a 32 bit echo process:\n\n mount -t cgroup none /cgroup -o cpuset\n cd /cgroup\n\n mkdir 0\n echo 1 \u003e 0/cpuset.cpus\n echo 0 \u003e 0/cpuset.mems\n echo 1 \u003e 0/cpuset.memory_migrate\n\n mkdir 1\n echo 1 \u003e 1/cpuset.cpus\n echo 1 \u003e 1/cpuset.mems\n echo 1 \u003e 1/cpuset.memory_migrate\n\n echo $$ \u003e 0/tasks\n 64_bit_process \u0026\n pid\u003d$!\n\n echo $pid \u003e 1/tasks # This does not migrate all process pages without\n # this patch. If 64 bit echo is used or this patch is\n # applied, then the full address space of $pid is\n # migrated.\n\nTo check memory migration, I watched:\n grep MemUsed /sys/devices/system/node/node*/meminfo\n\nSigned-off-by: Greg Thelen \u003cgthelen@google.com\u003e\nAcked-by: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nReviewed-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Daisuke Nishimura \u003cnishimura@mxp.nes.nec.co.jp\u003e\nCc: Balbir Singh \u003cbalbir@in.ibm.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "c0ff7453bb5c7c98e0885fb94279f2571946f280", "tree": "8bb2b169a5145f0496575dbd2f48bb4b1c83f819", "parents": [ "708c1bbc9d0c3e57f40501794d9b0eed29d10fce" ], "author": { "name": "Miao Xie", "email": "miaox@cn.fujitsu.com", "time": "Mon May 24 14:32:08 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:06:57 2010 -0700" }, "message": "cpuset,mm: fix no node to alloc memory when changing cpuset\u0027s mems\n\nBefore applying this patch, cpuset updates task-\u003emems_allowed and\nmempolicy by setting all new bits in the nodemask first, and clearing all\nold unallowed bits later. But in the way, the allocator may find that\nthere is no node to alloc memory.\n\nThe reason is that cpuset rebinds the task\u0027s mempolicy, it cleans the\nnodes which the allocater can alloc pages on, for example:\n\n(mpol: mempolicy)\n\ttask1\t\t\ttask1\u0027s mpol\ttask2\n\talloc page\t\t1\n\t alloc on node0? NO\t1\n\t\t\t\t1\t\tchange mems from 1 to 0\n\t\t\t\t1\t\trebind task1\u0027s mpol\n\t\t\t\t0-1\t\t set new bits\n\t\t\t\t0\t \t clear disallowed bits\n\t alloc on node1? NO\t0\n\t ...\n\tcan\u0027t alloc page\n\t goto oom\n\nThis patch fixes this problem by expanding the nodes range first(set newly\nallowed bits) and shrink it lazily(clear newly disallowed bits). So we\nuse a variable to tell the write-side task that read-side task is reading\nnodemask, and the write-side task clears newly disallowed nodes after\nread-side task ends the current memory allocation.\n\n[akpm@linux-foundation.org: fix spello]\nSigned-off-by: Miao Xie \u003cmiaox@cn.fujitsu.com\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nCc: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: Paul Menage \u003cmenage@google.com\u003e\nCc: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nCc: Ravikiran Thirumalai \u003ckiran@scalex86.org\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: Andi Kleen \u003candi@firstfloor.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "708c1bbc9d0c3e57f40501794d9b0eed29d10fce", "tree": "4b19caf68c420b32abdf05af3d413b1320f04fbe", "parents": [ "971ada0f6659488c3f36aed4c6f7670ff5ce4368" ], "author": { "name": "Miao Xie", "email": "miaox@cn.fujitsu.com", "time": "Mon May 24 14:32:07 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:06:57 2010 -0700" }, "message": "mempolicy: restructure rebinding-mempolicy functions\n\nNick Piggin reported that the allocator may see an empty nodemask when\nchanging cpuset\u0027s mems[1]. It happens only on the kernel that do not do\natomic nodemask_t stores. (MAX_NUMNODES \u003e BITS_PER_LONG)\n\nBut I found that there is also a problem on the kernel that can do atomic\nnodemask_t stores. The problem is that the allocator can\u0027t find a node to\nalloc page when changing cpuset\u0027s mems though there is a lot of free\nmemory. The reason is like this:\n\n(mpol: mempolicy)\n\ttask1\t\t\ttask1\u0027s mpol\ttask2\n\talloc page\t\t1\n\t alloc on node0? NO\t1\n\t\t\t\t1\t\tchange mems from 1 to 0\n\t\t\t\t1\t\trebind task1\u0027s mpol\n\t\t\t\t0-1\t\t set new bits\n\t\t\t\t0\t \t clear disallowed bits\n\t alloc on node1? NO\t0\n\t ...\n\tcan\u0027t alloc page\n\t goto oom\n\nI can use the attached program reproduce it by the following step:\n\n# mkdir /dev/cpuset\n# mount -t cpuset cpuset /dev/cpuset\n# mkdir /dev/cpuset/1\n# echo `cat /dev/cpuset/cpus` \u003e /dev/cpuset/1/cpus\n# echo `cat /dev/cpuset/mems` \u003e /dev/cpuset/1/mems\n# echo $$ \u003e /dev/cpuset/1/tasks\n# numactl --membind\u003d`cat /dev/cpuset/mems` ./cpuset_mem_hog \u003cnr_tasks\u003e \u0026\n \u003cnr_tasks\u003e \u003d max(nr_cpus - 1, 1)\n# killall -s SIGUSR1 cpuset_mem_hog\n# ./change_mems.sh\n\nseveral hours later, oom will happen though there is a lot of free memory.\n\nThis patchset fixes this problem by expanding the nodes range first(set\nnewly allowed bits) and shrink it lazily(clear newly disallowed bits). So\nwe use a variable to tell the write-side task that read-side task is\nreading nodemask, and the write-side task clears newly disallowed nodes\nafter read-side task ends the current memory allocation.\n\nThis patch:\n\nIn order to fix no node to alloc memory, when we want to update mempolicy\nand mems_allowed, we expand the set of nodes first (set all the newly\nnodes) and shrink the set of nodes lazily(clean disallowed nodes), But the\nmempolicy\u0027s rebind functions may breaks the expanding.\n\nSo we restructure the mempolicy\u0027s rebind functions and split the rebind\nwork to two steps, just like the update of cpuset\u0027s mems: The 1st step:\nexpand the set of the mempolicy\u0027s nodes. The 2nd step: shrink the set of\nthe mempolicy\u0027s nodes. It is used when there is no real lock to protect\nthe mempolicy in the read-side. Otherwise we can do rebind work at once.\n\nIn order to implement it, we define\n\n\tenum mpol_rebind_step {\n\t\tMPOL_REBIND_ONCE,\n\t\tMPOL_REBIND_STEP1,\n\t\tMPOL_REBIND_STEP2,\n\t\tMPOL_REBIND_NSTEP,\n\t};\n\nIf the mempolicy needn\u0027t be updated by two steps, we can pass\nMPOL_REBIND_ONCE to the rebind functions. Or we can pass\nMPOL_REBIND_STEP1 to do the first step of the rebind work and pass\nMPOL_REBIND_STEP2 to do the second step work.\n\nBesides that, it maybe long time between these two step and we have to\nrelease the lock that protects mempolicy and mems_allowed. If we hold the\nlock once again, we must check whether the current mempolicy is under the\nrebinding (the first step has been done) or not, because the task may\nalloc a new mempolicy when we don\u0027t hold the lock. So we defined the\nfollowing flag to identify it:\n\n#define MPOL_F_REBINDING (1 \u003c\u003c 2)\n\nThe new functions will be used in the next patch.\n\nSigned-off-by: Miao Xie \u003cmiaox@cn.fujitsu.com\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nCc: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: Paul Menage \u003cmenage@google.com\u003e\nCc: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nCc: Ravikiran Thirumalai \u003ckiran@scalex86.org\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: Andi Kleen \u003candi@firstfloor.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "15d77835ac48dbc2d4884376ea6a08b65b1c40ba", "tree": "4bb094f030cedf8376a70a65f9271b571ba37562", "parents": [ "345ace9c797030e77da8ff211b9502370b9d81ab" ], "author": { "name": "Lee Schermerhorn", "email": "lee.schermerhorn@hp.com", "time": "Mon May 24 14:32:04 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:06:57 2010 -0700" }, "message": "mempolicy: factor mpol_shared_policy_init() return paths\n\nFactor out duplicate put/frees in mpol_shared_policy_init() to a common\nreturn path.\n\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nCc: Ravikiran Thirumalai \u003ckiran@scalex86.org\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "345ace9c797030e77da8ff211b9502370b9d81ab", "tree": "5699b5b0b54412466b415ec581125e59f77d4b00", "parents": [ "b4652e8429100ba5c3ddb49499faa1188c98c246" ], "author": { "name": "Lee Schermerhorn", "email": "lee.schermerhorn@hp.com", "time": "Mon May 24 14:32:04 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:06:57 2010 -0700" }, "message": "mempolicy: rename policy_types and cleanup initialization\n\nRename \u0027policy_types[]\u0027 to \u0027policy_modes[]\u0027 to better match the array\ncontents.\n\nUse designated intializer syntax for policy_modes[].\n\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nCc: Ravikiran Thirumalai \u003ckiran@scalex86.org\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "b4652e8429100ba5c3ddb49499faa1188c98c246", "tree": "55fa4fcdb8e8cf067b1474cc7068163e152f3075", "parents": [ "e17f74af351cce9a1bade7b33af179497fdf95cf" ], "author": { "name": "Lee Schermerhorn", "email": "lee.schermerhorn@hp.com", "time": "Mon May 24 14:32:03 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:06:57 2010 -0700" }, "message": "mempolicy: lose unnecessary loop variable in mpol_parse_str()\n\nWe don\u0027t really need the extra variable \u0027i\u0027 in mpol_parse_str(). The only\nuse is as the the loop variable. Then, it\u0027s assigned to \u0027mode\u0027. Just use\nmode, and loose the \u0027uninitialized_var()\u0027 macro.\n\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nCc: Ravikiran Thirumalai \u003ckiran@scalex86.org\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "e17f74af351cce9a1bade7b33af179497fdf95cf", "tree": "99cce009bf299465a3b20594305ee209c8d85c3d", "parents": [ "1980050250fa052b1c24a19f9b3d82fae14d77f8" ], "author": { "name": "Lee Schermerhorn", "email": "lee.schermerhorn@hp.com", "time": "Mon May 24 14:32:02 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:06:57 2010 -0700" }, "message": "mempolicy: don\u0027t call mpol_set_nodemask() when no_context\n\nNo need to call mpol_set_nodemask() when we have no context for the\nmempolicy. This can occur when we\u0027re parsing a tmpfs \u0027mpol\u0027 mount option.\n Just save the raw nodemask in the mempolicy\u0027s w.user_nodemask member for\nuse when a tmpfs/shmem file is created. mpol_shared_policy_init() will\n\"contextualize\" the policy for the new file based on the creating task\u0027s\ncontext.\n\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nCc: Ravikiran Thirumalai \u003ckiran@scalex86.org\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "1980050250fa052b1c24a19f9b3d82fae14d77f8", "tree": "96743238e6941bd7af113ebe9275f6892b374dd3", "parents": [ "6eb27e1fdf5781719a3d2e90e6c89fa012135c62" ], "author": { "name": "Bob Liu", "email": "lliubbo@gmail.com", "time": "Mon May 24 14:32:01 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:06:57 2010 -0700" }, "message": "mempolicy: remove redundant check\n\nLee\u0027s patch \"mempolicy: use MPOL_PREFERRED for system-wide default policy\"\nhas made the MPOL_DEFAULT only used in the memory policy APIs. So, no\nneed to check in __mpol_equal also. Also get rid of mpol_match_intent()\nand move its logic directly into __mpol_equal().\n\nSigned-off-by: Bob Liu \u003clliubbo@gmail.com\u003e\nAcked-by: David Rientjes \u003crientjes@google.com\u003e\nCc: Andi Kleen \u003candi@firstfloor.org\u003e\nCc: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "6eb27e1fdf5781719a3d2e90e6c89fa012135c62", "tree": "23be89303ad69f5728f69665dfadf2b4dc45628c", "parents": [ "6d556294d5b27fb12f18be7495af45b6156a409e" ], "author": { "name": "Bob Liu", "email": "lliubbo@gmail.com", "time": "Mon May 24 14:32:00 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:06:57 2010 -0700" }, "message": "mempolicy: remove case MPOL_INTERLEAVE from policy_zonelist()\n\nIn policy_zonelist() mode MPOL_INTERLEAVE shouldn\u0027t happen, so fall\nthrough to BUG() instead of break to return. I also fixed the comment.\n\nSigned-off-by: Bob Liu \u003clliubbo@gmail.com\u003e\nAcked-by: David Rientjes \u003crientjes@google.com\u003e\nCc: Andi Kleen \u003candi@firstfloor.org\u003e\nCc: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "6d556294d5b27fb12f18be7495af45b6156a409e", "tree": "cb8549b4a4dc53399abc596dcac4630b0d936abf", "parents": [ "e13861d822f8f443ca0c020ea8fc2dc01039cd63" ], "author": { "name": "Bob Liu", "email": "lliubbo@gmail.com", "time": "Mon May 24 14:31:59 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 25 08:06:57 2010 -0700" }, "message": "mempolicy: remove redundant code\n\n1. In funtion is_valid_nodemask(), varibable k will be inited to 0 in\n the following loop, needn\u0027t init to policy_zone anymore.\n\n2. (MPOL_F_STATIC_NODES | MPOL_F_RELATIVE_NODES) has already defined\n to MPOL_MODE_FLAGS in mempolicy.h.\n\nSigned-off-by: Bob Liu \u003clliubbo@gmail.com\u003e\nAcked-by: David Rientjes \u003crientjes@google.com\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "5a0e3ad6af8660be21ca98a971cd00f331318c05", "tree": "5bfb7be11a03176a87296a43ac6647975c00a1d1", "parents": [ "ed391f4ebf8f701d3566423ce8f17e614cde9806" ], "author": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Wed Mar 24 17:04:11 2010 +0900" }, "committer": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Tue Mar 30 22:02:32 2010 +0900" }, "message": "include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h\n\npercpu.h is included by sched.h and module.h and thus ends up being\nincluded when building most .c files. percpu.h includes slab.h which\nin turn includes gfp.h making everything defined by the two files\nuniversally available and complicating inclusion dependencies.\n\npercpu.h -\u003e slab.h dependency is about to be removed. Prepare for\nthis change by updating users of gfp and slab facilities include those\nheaders directly instead of assuming availability. As this conversion\nneeds to touch large number of source files, the following script is\nused as the basis of conversion.\n\n http://userweb.kernel.org/~tj/misc/slabh-sweep.py\n\nThe script does the followings.\n\n* Scan files for gfp and slab usages and update includes such that\n only the necessary includes are there. ie. if only gfp is used,\n gfp.h, if slab is used, slab.h.\n\n* When the script inserts a new include, it looks at the include\n blocks and try to put the new include such that its order conforms\n to its surrounding. It\u0027s put in the include block which contains\n core kernel includes, in the same order that the rest are ordered -\n alphabetical, Christmas tree, rev-Xmas-tree or at the end if there\n doesn\u0027t seem to be any matching order.\n\n* If the script can\u0027t find a place to put a new include (mostly\n because the file doesn\u0027t have fitting include block), it prints out\n an error message indicating which .h file needs to be added to the\n file.\n\nThe conversion was done in the following steps.\n\n1. The initial automatic conversion of all .c files updated slightly\n over 4000 files, deleting around 700 includes and adding ~480 gfp.h\n and ~3000 slab.h inclusions. The script emitted errors for ~400\n files.\n\n2. Each error was manually checked. Some didn\u0027t need the inclusion,\n some needed manual addition while adding it to implementation .h or\n embedding .c file was more appropriate for others. This step added\n inclusions to around 150 files.\n\n3. The script was run again and the output was compared to the edits\n from #2 to make sure no file was left behind.\n\n4. Several build tests were done and a couple of problems were fixed.\n e.g. lib/decompress_*.c used malloc/free() wrappers around slab\n APIs requiring slab.h to be added manually.\n\n5. The script was run on all .h files but without automatically\n editing them as sprinkling gfp.h and slab.h inclusions around .h\n files could easily lead to inclusion dependency hell. Most gfp.h\n inclusion directives were ignored as stuff from gfp.h was usually\n wildly available and often used in preprocessor macros. Each\n slab.h inclusion directive was examined and added manually as\n necessary.\n\n6. percpu.h was updated not to include slab.h.\n\n7. Build test were done on the following configurations and failures\n were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my\n distributed build env didn\u0027t work with gcov compiles) and a few\n more options had to be turned off depending on archs to make things\n build (like ipr on powerpc/64 which failed due to missing writeq).\n\n * x86 and x86_64 UP and SMP allmodconfig and a custom test config.\n * powerpc and powerpc64 SMP allmodconfig\n * sparc and sparc64 SMP allmodconfig\n * ia64 SMP allmodconfig\n * s390 SMP allmodconfig\n * alpha SMP allmodconfig\n * um on x86_64 SMP allmodconfig\n\n8. percpu.h modifications were reverted so that it could be applied as\n a separate patch and serve as bisection point.\n\nGiven the fact that I had only a couple of failures from tests on step\n6, I\u0027m fairly confident about the coverage of this conversion patch.\nIf there is a breakage, it\u0027s likely to be something in one of the arch\nheaders which should be easily discoverable easily on most builds of\nthe specific arch.\n\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\nGuess-its-ok-by: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: Ingo Molnar \u003cmingo@redhat.com\u003e\nCc: Lee Schermerhorn \u003cLee.Schermerhorn@hp.com\u003e\n" }, { "commit": "c6b6ef8bb05af632889c5536513b9f4004961f73", "tree": "85f90f246fa1da0d47c48c43a735bbfac33c542e", "parents": [ "7198f3c9b13c7aa1e5d9f7ff74c0ea303174feff" ], "author": { "name": "Lee Schermerhorn", "email": "lee.schermerhorn@hp.com", "time": "Tue Mar 23 13:35:41 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Mar 24 16:31:22 2010 -0700" }, "message": "mempolicy: fix get_mempolicy() for relative and static nodes\n\nDiscovered while testing other mempolicy changes:\n\nget_mempolicy() does not handle static/relative mode flags correctly.\nReturn the value that the user specified so that it can be restored\nvia set_mempolicy() if desired.\n\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nCc: Ravikiran Thirumalai \u003ckiran@scalex86.org\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "926f2ae04f183098cf9a30521776fb2759c8afeb", "tree": "2d8583f77478557d508068ccb9bcc62cdc81920d", "parents": [ "12821f5fb942e795f8009ece14bde868893bd811" ], "author": { "name": "KOSAKI Motohiro", "email": "kosaki.motohiro@jp.fujitsu.com", "time": "Tue Mar 23 13:35:32 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Mar 24 16:31:21 2010 -0700" }, "message": "tmpfs: cleanup mpol_parse_str()\n\nmpol_parse_str() made lots \u0027err\u0027 variable related bug. Because it is ugly\nand reviewing unfriendly.\n\nThis patch simplifies it.\n\nSigned-off-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Ravikiran Thirumalai \u003ckiran@scalex86.org\u003e\nCc: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nAcked-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\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": "12821f5fb942e795f8009ece14bde868893bd811", "tree": "6b83232e845bf8427d7ad313ac31aa910ff6d1f7", "parents": [ "d69b2e63e9172afb4d07c305601b79a55509ac4c" ], "author": { "name": "KOSAKI Motohiro", "email": "kosaki.motohiro@jp.fujitsu.com", "time": "Tue Mar 23 13:35:31 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Mar 24 16:31:21 2010 -0700" }, "message": "tmpfs: handle MPOL_LOCAL mount option properly\n\ncommit 71fe804b6d5 (mempolicy: use struct mempolicy pointer in\nshmem_sb_info) added mpol\u003dlocal mount option. but its feature is broken\nsince it was born. because such code always return 1 (i.e. mount\nfailure).\n\nThis patch fixes it.\n\nSigned-off-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Ravikiran Thirumalai \u003ckiran@scalex86.org\u003e\nCc: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nAcked-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\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": "d69b2e63e9172afb4d07c305601b79a55509ac4c", "tree": "b1abae07eaa3427dedca17427100664cdccf8a38", "parents": [ "413b43deab8377819aba1dbad2abf0c15d59b491" ], "author": { "name": "KOSAKI Motohiro", "email": "kosaki.motohiro@jp.fujitsu.com", "time": "Tue Mar 23 13:35:30 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Mar 24 16:31:21 2010 -0700" }, "message": "tmpfs: mpol\u003dbind:0 don\u0027t cause mount error.\n\nCurrently, following mount operation cause mount error.\n\n% mount -t tmpfs -ompol\u003dbind:0 none /tmp\n\nBecause commit 71fe804b6d5 (mempolicy: use struct mempolicy pointer in\nshmem_sb_info) corrupted MPOL_BIND parse code.\n\nThis patch restore the needed one.\n\nSigned-off-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Ravikiran Thirumalai \u003ckiran@scalex86.org\u003e\nCc: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nAcked-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\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": "413b43deab8377819aba1dbad2abf0c15d59b491", "tree": "07ed7302b20b620f09c479e36c6fd7bd02559860", "parents": [ "8c363afe94b885d39ae2e93e41680282a470ad84" ], "author": { "name": "Ravikiran G Thirumalai", "email": "kiran@scalex86.org", "time": "Tue Mar 23 13:35:28 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Mar 24 16:31:21 2010 -0700" }, "message": "tmpfs: fix oops on mounts with mpol\u003ddefault\n\nFix an \u0027oops\u0027 when a tmpfs mount point is mounted with the mpol\u003ddefault\nmempolicy.\n\nUpon remounting a tmpfs mount point with \u0027mpol\u003ddefault\u0027 option, the mount\ncode crashed with a null pointer dereference. The initial problem report\nwas on 2.6.27, but the problem exists in mainline 2.6.34-rc as well. On\nexamining the code, we see that mpol_new returns NULL if default mempolicy\nwas requested. This \u0027NULL\u0027 mempolicy is accessed to store the node mask\nresulting in oops.\n\nThe following patch fixes it.\n\nSigned-off-by: Ravikiran Thirumalai \u003ckiran@scalex86.org\u003e\nSigned-off-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nAcked-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\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": "4e3eaddd142e2142c048c5052a0a9d2604fccfc6", "tree": "5bc45a286502e54e790c54948f22364c5afd9d89", "parents": [ "8655e7e3ddec60603c4f6c14cdf642e2ba198df8", "b97c4bc16734a2e597dac7f91ee9eb78f4aeef9a" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sat Mar 13 14:43:01 2010 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sat Mar 13 14:43:01 2010 -0800" }, "message": "Merge branch \u0027core-fixes-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip\n\n* \u0027core-fixes-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:\n locking: Make sparse work with inline spinlocks and rwlocks\n x86/mce: Fix RCU lockdep splats\n rcu: Increase RCU CPU stall timeouts if PROVE_RCU\n ftrace: Replace read_barrier_depends() with rcu_dereference_raw()\n rcu: Suppress RCU lockdep warnings during early boot\n rcu, ftrace: Fix RCU lockdep splat in ftrace_perf_buf_prepare()\n rcu: Suppress __mpol_dup() false positive from RCU lockdep\n rcu: Make rcu_read_lock_sched_held() handle !PREEMPT\n rcu: Add control variables to lockdep_rcu_dereference() diagnostics\n rcu, cgroup: Relax the check in task_subsys_state() as early boot is now handled by lockdep-RCU\n rcu: Use wrapper function instead of exporting tasklist_lock\n sched, rcu: Fix rcu_dereference() for RCU-lockdep\n rcu: Make task_subsys_state() RCU-lockdep checks handle boot-time use\n rcu: Fix holdoff for accelerated GPs for last non-dynticked CPU\n x86/gart: Unexport gart_iommu_aperture\n\nFix trivial conflicts in kernel/trace/ftrace.c\n" }, { "commit": "da0aa138944311e6745a00ac3d88f03e8d9a46c4", "tree": "f8a88b12652fb2e4ed6775b0cc32da837ca2d949", "parents": [ "d96ae5309165d9ed7c008a178238977b73595cd9" ], "author": { "name": "KOSAKI Motohiro", "email": "kosaki.motohiro@jp.fujitsu.com", "time": "Fri Mar 05 13:41:59 2010 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sat Mar 06 11:26:25 2010 -0800" }, "message": "mm/mempolicy.c: fix indentation of the comments of do_migrate_pages\n\nCurrently, do_migrate_pages() have very long comment and this is not\nindent properly. I often misunderstand it is function starting commnents\nand confused it.\n\nthis patch fixes it.\n\nnote: this patch doesn\u0027t break 80 column rule. I guess original\n author intended this indentaion, but an accident corrupted it.\n\nSigned-off-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nReviewed-by: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "9d8cebd4bcd7c3878462fdfda34bbcdeb4df7ef4", "tree": "0f0a6dadb4430aef18f1491003d70d9351d7b619", "parents": [ "93e4a89a8c987189b168a530a331ef6d0fcf07a7" ], "author": { "name": "KOSAKI Motohiro", "email": "kosaki.motohiro@jp.fujitsu.com", "time": "Fri Mar 05 13:41:57 2010 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sat Mar 06 11:26:25 2010 -0800" }, "message": "mm: fix mbind vma merge problem\n\nStrangely, current mbind() doesn\u0027t merge vma with neighbor vma although it\u0027s possible.\nUnfortunately, many vma can reduce performance...\n\nThis patch fixes it.\n\n reproduced program\n ----------------------------------------------------------------\n #include \u003cnumaif.h\u003e\n #include \u003cnuma.h\u003e\n #include \u003csys/mman.h\u003e\n #include \u003cstdio.h\u003e\n #include \u003cunistd.h\u003e\n #include \u003cstdlib.h\u003e\n #include \u003cstring.h\u003e\n\n static unsigned long pagesize;\n\n int main(int argc, char** argv)\n {\n \tvoid* addr;\n \tint ch;\n \tint node;\n \tstruct bitmask *nmask \u003d numa_allocate_nodemask();\n \tint err;\n \tint node_set \u003d 0;\n \tchar buf[128];\n\n \twhile ((ch \u003d getopt(argc, argv, \"n:\")) !\u003d -1){\n \t\tswitch (ch){\n \t\tcase \u0027n\u0027:\n \t\t\tnode \u003d strtol(optarg, NULL, 0);\n \t\t\tnuma_bitmask_setbit(nmask, node);\n \t\t\tnode_set \u003d 1;\n \t\t\tbreak;\n \t\tdefault:\n \t\t\t;\n \t\t}\n \t}\n \targc -\u003d optind;\n \targv +\u003d optind;\n\n \tif (!node_set)\n \t\tnuma_bitmask_setbit(nmask, 0);\n\n \tpagesize \u003d getpagesize();\n\n \taddr \u003d mmap(NULL, pagesize*3, PROT_READ|PROT_WRITE,\n \t\t MAP_ANON|MAP_PRIVATE, 0, 0);\n \tif (addr \u003d\u003d MAP_FAILED)\n \t\tperror(\"mmap \"), exit(1);\n\n \tfprintf(stderr, \"pid \u003d %d \\n\" \"addr \u003d %p\\n\", getpid(), addr);\n\n \t/* make page populate */\n \tmemset(addr, 0, pagesize*3);\n\n \t/* first mbind */\n \terr \u003d mbind(addr+pagesize, pagesize, MPOL_BIND, nmask-\u003emaskp,\n \t\t nmask-\u003esize, MPOL_MF_MOVE_ALL);\n \tif (err)\n \t\terror(\"mbind1 \");\n\n \t/* second mbind */\n \terr \u003d mbind(addr, pagesize*3, MPOL_DEFAULT, NULL, 0, 0);\n \tif (err)\n \t\terror(\"mbind2 \");\n\n \tsprintf(buf, \"cat /proc/%d/maps\", getpid());\n \tsystem(buf);\n\n \treturn 0;\n }\n ----------------------------------------------------------------\n\nresult without this patch\n\n\taddr \u003d 0x7fe26ef09000\n\t[snip]\n\t7fe26ef09000-7fe26ef0a000 rw-p 00000000 00:00 0\n\t7fe26ef0a000-7fe26ef0b000 rw-p 00000000 00:00 0\n\t7fe26ef0b000-7fe26ef0c000 rw-p 00000000 00:00 0\n\t7fe26ef0c000-7fe26ef0d000 rw-p 00000000 00:00 0\n\n\t\u003d\u003e 0x7fe26ef09000-0x7fe26ef0c000 have three vmas.\n\nresult with this patch\n\n\taddr \u003d 0x7fc9ebc76000\n\t[snip]\n\t7fc9ebc76000-7fc9ebc7a000 rw-p 00000000 00:00 0\n\t7fffbe690000-7fffbe6a5000 rw-p 00000000\t00:00 0\t[stack]\n\n\t\u003d\u003e 0x7fc9ebc76000-0x7fc9ebc7a000 have only one vma.\n\n[minchan.kim@gmail.com: fix file offset passed to vma_merge()]\nSigned-off-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nReviewed-by: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: Nick Piggin \u003cnickpiggin@yahoo.com.au\u003e\nCc: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nCc: Andrea Arcangeli \u003caarcange@redhat.com\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nSigned-off-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": "99ee4ca746dda71326db7645463b4075ac1d665c", "tree": "ffee1bb0da458f7067a3207df0507be98dea7764", "parents": [ "e6033e3b307fcfae08408e0673266db38392bda4" ], "author": { "name": "Paul E. McKenney", "email": "paulmck@linux.vnet.ibm.com", "time": "Wed Mar 03 17:50:17 2010 -0800" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Mar 04 12:07:34 2010 +0100" }, "message": "rcu: Suppress __mpol_dup() false positive from RCU lockdep\n\nCommon code is used during task creation and after the task has\nstarted running. RCU protection is not needed during task\ncreation because no other CPU has access to the\nunder-construction task. Provide the RCU protection anyway to\nsuppress the false positive, as there does not appear to be a\ngood way for the common code to recognize that the task is only\naccessible to the CPU creating it.\n\nSigned-off-by: Paul E. McKenney \u003cpaulmck@linux.vnet.ibm.com\u003e\nCc: Paul Menage \u003cmenage@google.com\u003e\nCc: laijs@cn.fujitsu.com\nCc: dipankar@in.ibm.com\nCc: mathieu.desnoyers@polymtl.ca\nCc: josh@joshtriplett.org\nCc: dvhltc@us.ibm.com\nCc: niv@us.ibm.com\nCc: peterz@infradead.org\nCc: rostedt@goodmis.org\nCc: Valdis.Kletnieks@vt.edu\nCc: dhowells@redhat.com\nLKML-Reference: \u003c1267667418-32233-2-git-send-email-paulmck@linux.vnet.ibm.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\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": "06808b0827e1cd14eedc96bac2655d5b37ac246c", "tree": "8f7b52a4af1532ed414631f68b99a059e299d83f", "parents": [ "c1e6c8d074ea3621106548654cc244d2edc12ead" ], "author": { "name": "Lee Schermerhorn", "email": "lee.schermerhorn@hp.com", "time": "Mon Dec 14 17:58:21 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:12 2009 -0800" }, "message": "hugetlb: derive huge pages nodes allowed from task mempolicy\n\nThis patch derives a \"nodes_allowed\" node mask from the numa mempolicy of\nthe task modifying the number of persistent huge pages to control the\nallocation, freeing and adjusting of surplus huge pages when the pool page\ncount is modified via the new sysctl or sysfs attribute\n\"nr_hugepages_mempolicy\". The nodes_allowed mask is derived as follows:\n\n* For \"default\" [NULL] task mempolicy, a NULL nodemask_t pointer\n is produced. This will cause the hugetlb subsystem to use\n node_online_map as the \"nodes_allowed\". This preserves the\n behavior before this patch.\n* For \"preferred\" mempolicy, including explicit local allocation,\n a nodemask with the single preferred node will be produced.\n \"local\" policy will NOT track any internode migrations of the\n task adjusting nr_hugepages.\n* For \"bind\" and \"interleave\" policy, the mempolicy\u0027s nodemask\n will be used.\n* Other than to inform the construction of the nodes_allowed node\n mask, the actual mempolicy mode is ignored. That is, all modes\n behave like interleave over the resulting nodes_allowed mask\n with no \"fallback\".\n\nSee the updated documentation [next patch] for more information\nabout the implications of this patch.\n\nExamples:\n\nStarting with:\n\n\tNode 0 HugePages_Total: 0\n\tNode 1 HugePages_Total: 0\n\tNode 2 HugePages_Total: 0\n\tNode 3 HugePages_Total: 0\n\nDefault behavior [with or without this patch] balances persistent\nhugepage allocation across nodes [with sufficient contiguous memory]:\n\n\tsysctl vm.nr_hugepages[_mempolicy]\u003d32\n\nyields:\n\n\tNode 0 HugePages_Total: 8\n\tNode 1 HugePages_Total: 8\n\tNode 2 HugePages_Total: 8\n\tNode 3 HugePages_Total: 8\n\nOf course, we only have nr_hugepages_mempolicy with the patch,\nbut with default mempolicy, nr_hugepages_mempolicy behaves the\nsame as nr_hugepages.\n\nApplying mempolicy--e.g., with numactl [using \u0027-m\u0027 a.k.a.\n\u0027--membind\u0027 because it allows multiple nodes to be specified\nand it\u0027s easy to type]--we can allocate huge pages on\nindividual nodes or sets of nodes. So, starting from the\ncondition above, with 8 huge pages per node, add 8 more to\nnode 2 using:\n\n\tnumactl -m 2 sysctl vm.nr_hugepages_mempolicy\u003d40\n\nThis yields:\n\n\tNode 0 HugePages_Total: 8\n\tNode 1 HugePages_Total: 8\n\tNode 2 HugePages_Total: 16\n\tNode 3 HugePages_Total: 8\n\nThe incremental 8 huge pages were restricted to node 2 by the\nspecified mempolicy.\n\nSimilarly, we can use mempolicy to free persistent huge pages\nfrom specified nodes:\n\n\tnumactl -m 0,1 sysctl vm.nr_hugepages_mempolicy\u003d32\n\nyields:\n\n\tNode 0 HugePages_Total: 4\n\tNode 1 HugePages_Total: 4\n\tNode 2 HugePages_Total: 16\n\tNode 3 HugePages_Total: 8\n\nThe 8 huge pages freed were balanced over nodes 0 and 1.\n\n[rientjes@google.com: accomodate reworked NODEMASK_ALLOC]\nSigned-off-by: David Rientjes \u003crientjes@google.com\u003e\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nAcked-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nReviewed-by: Andi Kleen \u003candi@firstfloor.org\u003e\nCc: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Randy Dunlap \u003crandy.dunlap@oracle.com\u003e\nCc: Nishanth Aravamudan \u003cnacc@us.ibm.com\u003e\nCc: Adam Litke \u003cagl@us.ibm.com\u003e\nCc: Andy Whitcroft \u003capw@canonical.com\u003e\nCc: Eric Whitney \u003ceric.whitney@hp.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": "6d9c285a632b39ab83c6ae14cbff0e606d4042ee", "tree": "e8d334046befcce98abd9ac8bd5350597fe5a59f", "parents": [ "ee32398fda8ab9867cf8d5469d6e83de5f5c1f7c" ], "author": { "name": "KOSAKI Motohiro", "email": "kosaki.motohiro@jp.fujitsu.com", "time": "Mon Dec 14 17:58:11 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 15 08:53:12 2009 -0800" }, "message": "mm: move inc_zone_page_state(NR_ISOLATED) to just isolated place\n\nChristoph pointed out inc_zone_page_state(NR_ISOLATED) should be placed\nin right after isolate_page().\n\nThis patch does it.\n\nReviewed-by: Christoph Lameter \u003ccl@linux-foundation.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": "b05ca7385a2848abdc72051f832722641daed8b0", "tree": "ce0463be127434f25f23025142f2313d2dae21ab", "parents": [ "ab8a3e14e6f8e567560f664bbd29aefb306a274e" ], "author": { "name": "KOSAKI Motohiro", "email": "kosaki.motohiro@jp.fujitsu.com", "time": "Mon Oct 26 16:49:59 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Oct 29 07:39:29 2009 -0700" }, "message": "do_mbind(): fix memory leak\n\nIf migrate_prep is failed, new variable is leaked. This patch fixes it.\n\nSigned-off-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nAcked-by: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: \u003cstable@kernel.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "ab8a3e14e6f8e567560f664bbd29aefb306a274e", "tree": "72de6b1c5a9130a0503ecc4d9e16db236f6884a0", "parents": [ "47f365eb575735c6b2edf5d08e0d16d26a9c23bd" ], "author": { "name": "KOSAKI Motohiro", "email": "kosaki.motohiro@jp.fujitsu.com", "time": "Mon Oct 26 16:49:58 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Oct 29 07:39:29 2009 -0700" }, "message": "mbind(): fix leak of never putback pages\n\nIf mbind() receives an invalid address, do_mbind leaks a page. The\nfollowing test program detects this leak.\n\nThis patch fixes it.\n\nmigrate_efault.c\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\n #include \u003cnumaif.h\u003e\n #include \u003cnuma.h\u003e\n #include \u003csys/mman.h\u003e\n #include \u003cstdio.h\u003e\n #include \u003cunistd.h\u003e\n #include \u003cstdlib.h\u003e\n #include \u003cstring.h\u003e\n\nstatic unsigned long pagesize;\n\nstatic void* make_hole_mapping(void)\n{\n\n\tvoid* addr;\n\n\taddr \u003d mmap(NULL, pagesize*3, PROT_READ|PROT_WRITE,\n\t\t MAP_ANON|MAP_PRIVATE, 0, 0);\n\tif (addr \u003d\u003d MAP_FAILED)\n\t\treturn NULL;\n\n\t/* make page populate */\n\tmemset(addr, 0, pagesize*3);\n\n\t/* make memory hole */\n\tmunmap(addr+pagesize, pagesize);\n\n\treturn addr;\n}\n\nint main(int argc, char** argv)\n{\n\tvoid* addr;\n\tint ch;\n\tint node;\n\tstruct bitmask *nmask \u003d numa_allocate_nodemask();\n\tint err;\n\tint node_set \u003d 0;\n\n\twhile ((ch \u003d getopt(argc, argv, \"n:\")) !\u003d -1){\n\t\tswitch (ch){\n\t\tcase \u0027n\u0027:\n\t\t\tnode \u003d strtol(optarg, NULL, 0);\n\t\t\tnuma_bitmask_setbit(nmask, node);\n\t\t\tnode_set \u003d 1;\n\t\t\tbreak;\n\t\tdefault:\n\t\t\t;\n\t\t}\n\t}\n\targc -\u003d optind;\n\targv +\u003d optind;\n\n\tif (!node_set)\n\t\tnuma_bitmask_setbit(nmask, 0);\n\n\tpagesize \u003d getpagesize();\n\n\taddr \u003d make_hole_mapping();\n\n\terr \u003d mbind(addr, pagesize*3, MPOL_BIND, nmask-\u003emaskp, nmask-\u003esize, MPOL_MF_MOVE_ALL);\n\tif (err)\n\t\tperror(\"mbind \");\n\n\treturn 0;\n}\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\n\nSigned-off-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nAcked-by: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: \u003cstable@kernel.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "4bfc44958e499af9a73f62201543b3a1f617cfeb", "tree": "01b40f951cd1a5e6dda8e2b21e1e24650c43c95e", "parents": [ "93274e4d4e9416ad1fa47e2f26011e2c483fe5fe" ], "author": { "name": "KAMEZAWA Hiroyuki", "email": "kamezawa.hiroyu@jp.fujitsu.com", "time": "Thu Aug 06 15:07:33 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Aug 07 10:39:55 2009 -0700" }, "message": "mm: make set_mempolicy(MPOL_INTERLEAV) N_HIGH_MEMORY aware\n\nAt first, init_task\u0027s mems_allowed is initialized as this.\n init_task-\u003emems_allowed \u003d\u003d node_state[N_POSSIBLE]\n\nAnd cpuset\u0027s top_cpuset mask is initialized as this\n top_cpuset-\u003emems_allowed \u003d node_state[N_HIGH_MEMORY]\n\nBefore 2.6.29:\npolicy\u0027s mems_allowed is initialized as this.\n\n 1. update tasks-\u003emems_allowed by its cpuset-\u003emems_allowed.\n 2. policy-\u003emems_allowed \u003d nodes_and(tasks-\u003emems_allowed, user\u0027s mask)\n\nUpdating task\u0027s mems_allowed in reference to top_cpuset\u0027s one.\ncpuset\u0027s mems_allowed is aware of N_HIGH_MEMORY, always.\n\nIn 2.6.30: After commit 58568d2a8215cb6f55caf2332017d7bdff954e1c\n(\"cpuset,mm: update tasks\u0027 mems_allowed in time\"), policy\u0027s mems_allowed\nis initialized as this.\n\n 1. policy-\u003emems_allowd \u003d nodes_and(task-\u003emems_allowed, user\u0027s mask)\n\nHere, if task is in top_cpuset, task-\u003emems_allowed is not updated from\ninit\u0027s one. Assume user excutes command as #numactrl --interleave\u003dall\n,....\n\n policy-\u003emems_allowd \u003d nodes_and(N_POSSIBLE, ALL_SET_MASK)\n\nThen, policy\u0027s mems_allowd can includes a possible node, which has no pgdat.\n\nMPOL\u0027s INTERLEAVE just scans nodemask of task-\u003emems_allowd and access this\ndirectly.\n\n NODE_DATA(nid)-\u003ezonelist even if NODE_DATA(nid)\u003d\u003dNULL\n\nThen, what\u0027s we need is making policy-\u003emems_allowed be aware of\nN_HIGH_MEMORY. This patch does that. But to do so, extra nodemask will\nbe on statck. Because I know cpumask has a new interface of\nCPUMASK_ALLOC(), I added it to node.\n\nThis patch stands on old behavior. But I feel this fix itself is just a\nBand-Aid. But to do fundametal fix, we have to take care of memory\nhotplug and it takes time. (task-\u003emems_allowd should be N_HIGH_MEMORY, I\nthink.)\n\nmpol_set_nodemask() should be aware of N_HIGH_MEMORY and policy\u0027s nodemask\nshould be includes only online nodes.\n\nIn old behavior, this is guaranteed by frequent reference to cpuset\u0027s\ncode. Now, most of them are removed and mempolicy has to check it by\nitself.\n\nTo do check, a few nodemask_t will be used for calculating nodemask. But,\nsize of nodemask_t can be big and it\u0027s not good to allocate them on stack.\n\nNow, cpumask_t has CPUMASK_ALLOC/FREE an easy code for get scratch area.\nNODEMASK_ALLOC/FREE shoudl be there.\n\n[akpm@linux-foundation.org: cleanups \u0026 tweaks]\nTested-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nSigned-off-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Miao Xie \u003cmiaox@cn.fujitsu.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: Paul Menage \u003cmenage@google.com\u003e\nCc: Nick Piggin \u003cnickpiggin@yahoo.com.au\u003e\nCc: Yasunori Goto \u003cy-goto@jp.fujitsu.com\u003e\nCc: Pekka Enberg \u003cpenberg@cs.helsinki.fi\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nCc: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "6484eb3e2a81807722c5f28efef94d8338b7b996", "tree": "10ce36f412c2ff0c7eb399af1a189f8e354f56db", "parents": [ "b3c466ce512923298ae8c0121d3e9f397a3f1210" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Tue Jun 16 15:31:54 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Jun 16 19:47:32 2009 -0700" }, "message": "page allocator: do not check NUMA node ID when the caller knows the node is valid\n\nCallers of alloc_pages_node() can optionally specify -1 as a node to mean\n\"allocate from the current node\". However, a number of the callers in\nfast paths know for a fact their node is valid. To avoid a comparison and\nbranch, this patch adds alloc_pages_exact_node() that only checks the nid\nwith VM_BUG_ON(). Callers that know their node is valid are then\nconverted.\n\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nReviewed-by: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nReviewed-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nReviewed-by: Pekka Enberg \u003cpenberg@cs.helsinki.fi\u003e\nAcked-by: Paul Mundt \u003clethal@linux-sh.org\u003e\t[for the SLOB NUMA bits]\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Nick Piggin \u003cnickpiggin@yahoo.com.au\u003e\nCc: Dave Hansen \u003cdave@linux.vnet.ibm.com\u003e\nCc: Lee Schermerhorn \u003cLee.Schermerhorn@hp.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "58568d2a8215cb6f55caf2332017d7bdff954e1c", "tree": "ffcdee457494ac78d6550b0aeac86536ca152e7b", "parents": [ "950592f7b991f267d707d372b90f508bbe72acbc" ], "author": { "name": "Miao Xie", "email": "miaox@cn.fujitsu.com", "time": "Tue Jun 16 15:31:49 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Jun 16 19:47:31 2009 -0700" }, "message": "cpuset,mm: update tasks\u0027 mems_allowed in time\n\nFix allocating page cache/slab object on the unallowed node when memory\nspread is set by updating tasks\u0027 mems_allowed after its cpuset\u0027s mems is\nchanged.\n\nIn order to update tasks\u0027 mems_allowed in time, we must modify the code of\nmemory policy. Because the memory policy is applied in the process\u0027s\ncontext originally. After applying this patch, one task directly\nmanipulates anothers mems_allowed, and we use alloc_lock in the\ntask_struct to protect mems_allowed and memory policy of the task.\n\nBut in the fast path, we didn\u0027t use lock to protect them, because adding a\nlock may lead to performance regression. But if we don\u0027t add a lock,the\ntask might see no nodes when changing cpuset\u0027s mems_allowed to some\nnon-overlapping set. In order to avoid it, we set all new allowed nodes,\nthen clear newly disallowed ones.\n\n[lee.schermerhorn@hp.com:\n The rework of mpol_new() to extract the adjusting of the node mask to\n apply cpuset and mpol flags \"context\" breaks set_mempolicy() and mbind()\n with MPOL_PREFERRED and a NULL nodemask--i.e., explicit local\n allocation. Fix this by adding the check for MPOL_PREFERRED and empty\n node mask to mpol_new_mpolicy().\n\n Remove the now unneeded \u0027nodes \u003d NULL\u0027 from mpol_new().\n\n Note that mpol_new_mempolicy() is always called with a non-NULL\n \u0027nodes\u0027 parameter now that it has been removed from mpol_new().\n Therefore, we don\u0027t need to test nodes for NULL before testing it for\n \u0027empty\u0027. However, just to be extra paranoid, add a VM_BUG_ON() to\n verify this assumption.]\n[lee.schermerhorn@hp.com:\n\n I don\u0027t think the function name \u0027mpol_new_mempolicy\u0027 is descriptive\n enough to differentiate it from mpol_new().\n\n This function applies cpuset set context, usually constraining nodes\n to those allowed by the cpuset. However, when the \u0027RELATIVE_NODES flag\n is set, it also translates the nodes. So I settled on\n \u0027mpol_set_nodemask()\u0027, because the comment block for mpol_new() mentions\n that we need to call this function to \"set nodes\".\n\n Some additional minor line length, whitespace and typo cleanup.]\nSigned-off-by: Miao Xie \u003cmiaox@cn.fujitsu.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: Paul Menage \u003cmenage@google.com\u003e\nCc: Nick Piggin \u003cnickpiggin@yahoo.com.au\u003e\nCc: Yasunori Goto \u003cy-goto@jp.fujitsu.com\u003e\nCc: Pekka Enberg \u003cpenberg@cs.helsinki.fi\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "938bb9f5e840eddbf54e4f62f6c5ba9b3ae12c9d", "tree": "a25324159ed8cc96b97a4d39aaf228bbd07e3824", "parents": [ "1e7bfb2134dfec37ce04fb3a4ca89299e892d10c" ], "author": { "name": "Heiko Carstens", "email": "heiko.carstens@de.ibm.com", "time": "Wed Jan 14 14:14:30 2009 +0100" }, "committer": { "name": "Heiko Carstens", "email": "heiko.carstens@de.ibm.com", "time": "Wed Jan 14 14:15:30 2009 +0100" }, "message": "[CVE-2009-0029] System call wrappers part 28\n\nSigned-off-by: Heiko Carstens \u003cheiko.carstens@de.ibm.com\u003e\n" }, { "commit": "2b828925652340277a889cbc11b2d0637f7cdaf7", "tree": "32fcb3d3e466fc419fad2d3717956a5b5ad3d35a", "parents": [ "3a3b7ce9336952ea7b9564d976d068a238976c9d", "58e20d8d344b0ee083febb18c2b021d2427e56ca" ], "author": { "name": "James Morris", "email": "jmorris@namei.org", "time": "Fri Nov 14 11:29:12 2008 +1100" }, "committer": { "name": "James Morris", "email": "jmorris@namei.org", "time": "Fri Nov 14 11:29:12 2008 +1100" }, "message": "Merge branch \u0027master\u0027 into next\n\nConflicts:\n\tsecurity/keys/internal.h\n\tsecurity/keys/process_keys.c\n\tsecurity/keys/request_key.c\n\nFixed conflicts above by using the non \u0027tsk\u0027 versions.\n\nSigned-off-by: James Morris \u003cjmorris@namei.org\u003e\n" }, { "commit": "c69e8d9c01db2adc503464993c358901c9af9de4", "tree": "bed94aaa9aeb7a7834d1c880f72b62a11a752c78", "parents": [ "86a264abe542cfececb4df129bc45a0338d8cdb9" ], "author": { "name": "David Howells", "email": "dhowells@redhat.com", "time": "Fri Nov 14 10:39:19 2008 +1100" }, "committer": { "name": "James Morris", "email": "jmorris@namei.org", "time": "Fri Nov 14 10:39:19 2008 +1100" }, "message": "CRED: Use RCU to access another task\u0027s creds and to release a task\u0027s own creds\n\nUse RCU to access another task\u0027s creds and to release a task\u0027s own creds.\nThis means that it will be possible for the credentials of a task to be\nreplaced without another task (a) requiring a full lock to read them, and (b)\nseeing deallocated memory.\n\nSigned-off-by: David Howells \u003cdhowells@redhat.com\u003e\nAcked-by: James Morris \u003cjmorris@namei.org\u003e\nAcked-by: Serge Hallyn \u003cserue@us.ibm.com\u003e\nSigned-off-by: James Morris \u003cjmorris@namei.org\u003e\n" }, { "commit": "b6dff3ec5e116e3af6f537d4caedcad6b9e5082a", "tree": "9e76f972eb7ce9b84e0146c8e4126a3f86acb428", "parents": [ "15a2460ed0af7538ca8e6c610fe607a2cd9da142" ], "author": { "name": "David Howells", "email": "dhowells@redhat.com", "time": "Fri Nov 14 10:39:16 2008 +1100" }, "committer": { "name": "James Morris", "email": "jmorris@namei.org", "time": "Fri Nov 14 10:39:16 2008 +1100" }, "message": "CRED: Separate task security context from task_struct\n\nSeparate the task security context from task_struct. At this point, the\nsecurity data is temporarily embedded in the task_struct with two pointers\npointing to it.\n\nNote that the Alpha arch is altered as it refers to (E)UID and (E)GID in\nentry.S via asm-offsets.\n\nWith comment fixes Signed-off-by: Marc Dionne \u003cmarc.c.dionne@gmail.com\u003e\n\nSigned-off-by: David Howells \u003cdhowells@redhat.com\u003e\nAcked-by: James Morris \u003cjmorris@namei.org\u003e\nAcked-by: Serge Hallyn \u003cserue@us.ibm.com\u003e\nSigned-off-by: James Morris \u003cjmorris@namei.org\u003e\n" }, { "commit": "76aac0e9a17742e60d408be1a706e9aaad370891", "tree": "e873a000d9c96209726e0958e311f005c13b2ed5", "parents": [ "b103c59883f1ec6e4d548b25054608cb5724453c" ], "author": { "name": "David Howells", "email": "dhowells@redhat.com", "time": "Fri Nov 14 10:39:12 2008 +1100" }, "committer": { "name": "James Morris", "email": "jmorris@namei.org", "time": "Fri Nov 14 10:39:12 2008 +1100" }, "message": "CRED: Wrap task credential accesses in the core kernel\n\nWrap access to task credentials so that they can be separated more easily from\nthe task_struct during the introduction of COW creds.\n\nChange most current-\u003e(|e|s|fs)[ug]id to current_(|e|s|fs)[ug]id().\n\nChange some task-\u003ee?[ug]id to task_e?[ug]id(). In some places it makes more\nsense to use RCU directly rather than a convenient wrapper; these will be\naddressed by later patches.\n\nSigned-off-by: David Howells \u003cdhowells@redhat.com\u003e\nReviewed-by: James Morris \u003cjmorris@namei.org\u003e\nAcked-by: Serge Hallyn \u003cserue@us.ibm.com\u003e\nCc: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\nCc: linux-audit@redhat.com\nCc: containers@lists.linux-foundation.org\nCc: linux-mm@kvack.org\nSigned-off-by: James Morris \u003cjmorris@namei.org\u003e\n" }, { "commit": "0aedadf91a70a11c4a3e7c7d99b21e5528af8d5d", "tree": "9e2529fa79ff4134f99772b5ed3693316e2221a5", "parents": [ "17a1217e12d8c8434f8a3deef7bf980c724a6ac7" ], "author": { "name": "Christoph Lameter", "email": "cl@linux-foundation.org", "time": "Thu Nov 06 12:53:30 2008 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Nov 06 15:41:18 2008 -0800" }, "message": "mm: move migrate_prep out from under mmap_sem\n\nMove the migrate_prep outside the mmap_sem for the following system calls\n\n1. sys_move_pages\n2. sys_migrate_pages\n3. sys_mbind()\n\nIt really does not matter when we flush the lru. The system is free to\nadd pages onto the lru even during migration which will make the page\nmigration either skip the page (mbind, migrate_pages) or return a busy\nstate (move_pages).\n\nFixes this lockdep warning (and potential deadlock):\n\nSome VM place has\n mmap_sem -\u003e kevent_wq via lru_add_drain_all()\n\nnet/core/dev.c::dev_ioctl() has\n rtnl_lock -\u003e mmap_sem (*) the ioctl has copy_from_user() and it can do page fault.\n\nlinkwatch_event has\n kevent_wq -\u003e rtnl_lock\n\nSigned-off-by: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nReported-by: Heiko Carstens \u003cheiko.carstens@de.ibm.com\u003e\nCc: Nick Piggin \u003cnickpiggin@yahoo.com.au\u003e\nCc: Hugh Dickins \u003chugh@veritas.com\u003e\nCc: Rik van Riel \u003criel@redhat.com\u003e\nCc: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "894bc310419ac95f4fa4142dc364401a7e607f65", "tree": "15d56a7333b41620016b845d2323dd06e822b621", "parents": [ "8a7a8544a4f6554ec2d8048ac9f9672f442db5a2" ], "author": { "name": "Lee Schermerhorn", "email": "Lee.Schermerhorn@hp.com", "time": "Sat Oct 18 20:26:39 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Oct 20 08:50:26 2008 -0700" }, "message": "Unevictable LRU Infrastructure\n\nWhen the system contains lots of mlocked or otherwise unevictable pages,\nthe pageout code (kswapd) can spend lots of time scanning over these\npages. Worse still, the presence of lots of unevictable pages can confuse\nkswapd into thinking that more aggressive pageout modes are required,\nresulting in all kinds of bad behaviour.\n\nInfrastructure to manage pages excluded from reclaim--i.e., hidden from\nvmscan. Based on a patch by Larry Woodman of Red Hat. Reworked to\nmaintain \"unevictable\" pages on a separate per-zone LRU list, to \"hide\"\nthem from vmscan.\n\nKosaki Motohiro added the support for the memory controller unevictable\nlru list.\n\nPages on the unevictable list have both PG_unevictable and PG_lru set.\nThus, PG_unevictable is analogous to and mutually exclusive with\nPG_active--it specifies which LRU list the page is on.\n\nThe unevictable infrastructure is enabled by a new mm Kconfig option\n[CONFIG_]UNEVICTABLE_LRU.\n\nA new function \u0027page_evictable(page, vma)\u0027 in vmscan.c tests whether or\nnot a page may be evictable. Subsequent patches will add the various\n!evictable tests. We\u0027ll want to keep these tests light-weight for use in\nshrink_active_list() and, possibly, the fault path.\n\nTo avoid races between tasks putting pages [back] onto an LRU list and\ntasks that might be moving the page from non-evictable to evictable state,\nthe new function \u0027putback_lru_page()\u0027 -- inverse to \u0027isolate_lru_page()\u0027\n-- tests the \"evictability\" of a page after placing it on the LRU, before\ndropping the reference. If the page has become unevictable,\nputback_lru_page() will redo the \u0027putback\u0027, thus moving the page to the\nunevictable list. This way, we avoid \"stranding\" evictable pages on the\nunevictable list.\n\n[akpm@linux-foundation.org: fix fallout from out-of-order merge]\n[riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build]\n[nishimura@mxp.nes.nec.co.jp: remove redundant mapping check]\n[kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework]\n[kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c]\n[kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure]\n[kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch]\n[kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch]\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nSigned-off-by: Rik van Riel \u003criel@redhat.com\u003e\nSigned-off-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nDebugged-by: Benjamin Kidwell \u003cbenjkidwell@yahoo.com\u003e\nSigned-off-by: Daisuke Nishimura \u003cnishimura@mxp.nes.nec.co.jp\u003e\nSigned-off-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "62695a84eb8f2e718bf4dfb21700afaa7a08e0ea", "tree": "0af7bac599748a7e462bff16d70c702c9e33a2fb", "parents": [ "71088785c6bc68fddb450063d57b1bd1c78e0ea1" ], "author": { "name": "Nick Piggin", "email": "npiggin@suse.de", "time": "Sat Oct 18 20:26:09 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Oct 20 08:50:25 2008 -0700" }, "message": "vmscan: move isolate_lru_page() to vmscan.c\n\nOn large memory systems, the VM can spend way too much time scanning\nthrough pages that it cannot (or should not) evict from memory. Not only\ndoes it use up CPU time, but it also provokes lock contention and can\nleave large systems under memory presure in a catatonic state.\n\nThis patch series improves VM scalability by:\n\n1) putting filesystem backed, swap backed and unevictable pages\n onto their own LRUs, so the system only scans the pages that it\n can/should evict from memory\n\n2) switching to two handed clock replacement for the anonymous LRUs,\n so the number of pages that need to be scanned when the system\n starts swapping is bound to a reasonable number\n\n3) keeping unevictable pages off the LRU completely, so the\n VM does not waste CPU time scanning them. ramfs, ramdisk,\n SHM_LOCKED shared memory segments and mlock()ed VMA pages\n are keept on the unevictable list.\n\nThis patch:\n\nisolate_lru_page logically belongs to be in vmscan.c than migrate.c.\n\nIt is tough, because we don\u0027t need that function without memory migration\nso there is a valid argument to have it in migrate.c. However a\nsubsequent patch needs to make use of it in the core mm, so we can happily\nmove it to vmscan.c.\n\nAlso, make the function a little more generic by not requiring that it\nadds an isolated page to a given list. Callers can do that.\n\n\tNote that we now have \u0027__isolate_lru_page()\u0027, that does\n\tsomething quite different, visible outside of vmscan.c\n\tfor use with memory controller. Methinks we need to\n\trationalize these names/purposes.\t--lts\n\n[akpm@linux-foundation.org: fix mm/memory_hotplug.c build]\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Rik van Riel \u003criel@redhat.com\u003e\nSigned-off-by: Lee Schermerhorn \u003cLee.Schermerhorn@hp.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "d6bf73e4340f52159c1d9f13836b62e20fcd12d3", "tree": "18e3b9e4f126958d7d55758d9a70375a847b5760", "parents": [ "6a4ad39b3de60ad0e75a78098be0f0eb1722b753" ], "author": { "name": "MinChan Kim", "email": "minchan.kim@gmail.com", "time": "Tue Aug 12 15:08:52 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Aug 12 16:07:29 2008 -0700" }, "message": "do_migrate_pages(): remove unused variable\n\nSigned-off-by: MinChan Kim \u003cminchan.kim@gmail.com\u003e\nAcked-by: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "a5516438959d90b071ff0a484ce4f3f523dc3152", "tree": "e356ba9364c76b93c176b4d4a262b7aca3ee8f91", "parents": [ "b7ba30c679ed1eb7ed3ed8f281f6493282042bd4" ], "author": { "name": "Andi Kleen", "email": "ak@suse.de", "time": "Wed Jul 23 21:27:41 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jul 24 10:47:17 2008 -0700" }, "message": "hugetlb: modular state for hugetlb page size\n\nThe goal of this patchset is to support multiple hugetlb page sizes. This\nis achieved by introducing a new struct hstate structure, which\nencapsulates the important hugetlb state and constants (eg. huge page\nsize, number of huge pages currently allocated, etc).\n\nThe hstate structure is then passed around the code which requires these\nfields, they will do the right thing regardless of the exact hstate they\nare operating on.\n\nThis patch adds the hstate structure, with a single global instance of it\n(default_hstate), and does the basic work of converting hugetlb to use the\nhstate.\n\nFuture patches will add more hstate structures to allow for different\nhugetlbfs mounts to have different page sizes.\n\n[akpm@linux-foundation.org: coding-style fixes]\nAcked-by: Adam Litke \u003cagl@us.ibm.com\u003e\nAcked-by: Nishanth Aravamudan \u003cnacc@us.ibm.com\u003e\nSigned-off-by: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Nick Piggin \u003cnpiggin@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "d79df630f622806c4d0e116fbaf6ebf6baf53461", "tree": "d5a1c06209210c84ec60099687e4a87723ae1599", "parents": [ "b8a0b6ccf2ba2519ace65d782b41ee91bf3c3778" ], "author": { "name": "David Rientjes", "email": "rientjes@google.com", "time": "Fri Jul 04 12:24:13 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Jul 04 13:03:05 2008 -0700" }, "message": "mempolicy: mask off internal flags for userspace API\n\nFlags considered internal to the mempolicy kernel code are stored as part\nof the \"flags\" member of struct mempolicy.\n\nBefore exposing a policy type to userspace via get_mempolicy(), these\ninternal flags must be masked. Flags exposed to userspace, however,\nshould still be returned to the user.\n\nSigned-off-by: David Rientjes \u003crientjes@google.com\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "71fe804b6d56d6a7aed680e096901434cef6a2c3", "tree": "3dd437e09fe6ee57644c72c79e08c562d4bb6389", "parents": [ "3f226aa1cbc006f9d90f22084f519ad2a1286cd8" ], "author": { "name": "Lee Schermerhorn", "email": "lee.schermerhorn@hp.com", "time": "Mon Apr 28 02:13:26 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Apr 28 08:58:25 2008 -0700" }, "message": "mempolicy: use struct mempolicy pointer in shmem_sb_info\n\nThis patch replaces the mempolicy mode, mode_flags, and nodemask in the\nshmem_sb_info struct with a struct mempolicy pointer, initialized to NULL.\nThis removes dependency on the details of mempolicy from shmem.c and hugetlbfs\ninode.c and simplifies the interfaces.\n\nmpol_parse_str() in mempolicy.c is changed to return, via a pointer to a\npointer arg, a struct mempolicy pointer on success. For MPOL_DEFAULT, the\nreturned pointer is NULL. Further, mpol_parse_str() now takes a \u0027no_context\u0027\nargument that causes the input nodemask to be stored in the w.user_nodemask of\nthe created mempolicy for use when the mempolicy is installed in a tmpfs inode\nshared policy tree. At that time, any cpuset contextualization is applied to\nthe original input nodemask. This preserves the previous behavior where the\ninput nodemask was stored in the superblock. We can think of the returned\nmempolicy as \"context free\".\n\nBecause mpol_parse_str() is now calling mpol_new(), we can remove from\nmpol_to_str() the semantic checks that mpol_new() already performs.\n\nAdd \u0027no_context\u0027 parameter to mpol_to_str() to specify that it should format\nthe nodemask in w.user_nodemask for \u0027bind\u0027 and \u0027interleave\u0027 policies.\n\nChange mpol_shared_policy_init() to take a pointer to a \"context free\" struct\nmempolicy and to create a new, \"contextualized\" mempolicy using the mode,\nmode_flags and user_nodemask from the input mempolicy.\n\n Note: we know that the mempolicy passed to mpol_to_str() or\n mpol_shared_policy_init() from a tmpfs superblock is \"context free\". This\n is currently the only instance thereof. However, if we found more uses for\n this concept, and introduced any ambiguity as to whether a mempolicy was\n context free or not, we could add another internal mode flag to identify\n context free mempolicies. Then, we could remove the \u0027no_context\u0027 argument\n from mpol_to_str().\n\nAdded shmem_get_sbmpol() to return a reference counted superblock mempolicy,\nif one exists, to pass to mpol_shared_policy_init(). We must add the\nreference under the sb stat_lock to prevent races with replacement of the mpol\nby remount. This reference is removed in mpol_shared_policy_init().\n\n[akpm@linux-foundation.org: build fix]\n[akpm@linux-foundation.org: another build fix]\n[akpm@linux-foundation.org: yet another build fix]\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "3f226aa1cbc006f9d90f22084f519ad2a1286cd8", "tree": "e54a87abb19f9dea184f4c17c4c8532d3d715de8", "parents": [ "095f1fc4ebf36c64fddf9b6db29b1ab5517378e6" ], "author": { "name": "Lee Schermerhorn", "email": "lee.schermerhorn@hp.com", "time": "Mon Apr 28 02:13:24 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Apr 28 08:58:25 2008 -0700" }, "message": "mempolicy: support mpol\u003dlocal tmpfs mount option\n\nFor tmpfs/shmem shared policies, MPOL_DEFAULT is not necessarily equivalent to\n\"local allocation\". Because shared policies are at the same \"scope\" level\n[see Documentation/vm/numa_memory_policy.txt], as vma policies MPOL_DEFAULT\nmeans \"fall back to current task policy\".\n\nThis patch extends the memory policy string parsing function to display\n\"local\" for MPOL_PREFERRED + MPOL_F_LOCAL. This allows one to specify local\nallocation as the default policy for shared memory areas via the tmpfs mpol\nmount option, regardless of the current task\u0027s policy.\n\nAlso, \"local\" is now displayed for this policy. This patch allows us to\naccept the same input format as the display.\n\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "095f1fc4ebf36c64fddf9b6db29b1ab5517378e6", "tree": "39aae9d5b05d8501d1794e92c6115331c0a40848", "parents": [ "2291990ab36b4b2d8a81b1f92e7a046e51632a60" ], "author": { "name": "Lee Schermerhorn", "email": "lee.schermerhorn@hp.com", "time": "Mon Apr 28 02:13:23 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Apr 28 08:58:24 2008 -0700" }, "message": "mempolicy: rework shmem mpol parsing and display\n\nmm/shmem.c currently contains functions to parse and display memory policy\nstrings for the tmpfs \u0027mpol\u0027 mount option. Move this to mm/mempolicy.c with\nthe rest of the mempolicy support. With subsequent patches, we\u0027ll be able to\nremove knowledge of the details [mode, flags, policy, ...] completely from\nshmem.c\n\n1) replace shmem_parse_mpol() in mm/shmem.c with mpol_parse_str() in\n mm/mempolicy.c. Rework to use the policy_types[] array [used by\n mpol_to_str()] to look up mode by name.\n\n2) use mpol_to_str() to format policy for shmem_show_mpol(). mpol_to_str()\n expects a pointer to a struct mempolicy, so temporarily construct one.\n This will be replaced with a reference to a struct mempolicy in the tmpfs\n superblock in a subsequent patch.\n\n NOTE 1: I changed mpol_to_str() to use a colon \u0027:\u0027 rather than an equal\n sign \u0027\u003d\u0027 as the nodemask delimiter to match mpol_parse_str() and the\n tmpfs/shmem mpol mount option formatting that now uses mpol_to_str(). This\n is a user visible change to numa_maps, but then the addition of the mode\n flags already changed the display. It makes sense to me to have the mounts\n and numa_maps display the policy in the same format. However, if anyone\n objects strongly, I can pass the desired nodemask delimeter as an arg to\n mpol_to_str().\n\n Note 2: Like show_numa_map(), I don\u0027t check the return code from\n mpol_to_str(). I do use a longer buffer than the one provided by\n show_numa_map(), which seems to have sufficed so far.\n\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "2291990ab36b4b2d8a81b1f92e7a046e51632a60", "tree": "b5b6b8ca9c92bc3c84cd7e7aefb5010d3793db4d", "parents": [ "fc36b8d3d819047eb4d23ca079fb4d3af20ff076" ], "author": { "name": "Lee Schermerhorn", "email": "lee.schermerhorn@hp.com", "time": "Mon Apr 28 02:13:22 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Apr 28 08:58:24 2008 -0700" }, "message": "mempolicy: clean-up mpol-to-str() mempolicy formatting\n\nmpol-to-str() formats memory policies into printable strings. Currently this\nis only used to display \"numa_maps\". A subsequent patch will use\nmpol_to_str() for formatting tmpfs [shmem] mpol mount options, allowing us to\nremove essentially duplicate code in mm/shmem.c. This patch cleans up\nmpol_to_str() generally and in preparation for that patch.\n\n1) show_numa_maps() is not checking the return code from mpol_to_str().\n There\u0027s not a lot we can do in this context if mpol_to_str() did return the\n error [insufficient space in buffer]. Proposed \"solution\": just check,\n under DEBUG_VM, that callers are providing sufficient buffer space for the\n policy, flags, and a few nodes. This way, we\u0027ll get some display.\n show_numa_maps() is providing a 50-byte buffer, so it won\u0027t trip this\n check. 50-bytes should be sufficient unless one has a large number of\n nodes in a very sparse nodemask.\n\n2) The display of the new mode flags [\"static\" \u0026 \"relative\"] was set up to\n display multiple flags, separated by a \"bar\" \u0027|\u0027. However, this support is\n incomplete--e.g., need_bar was never incremented; and currently, these two\n flags are mutually exclusive. So remove the \"bar\" support, for now, and\n only display one flag.\n\n3) Use snprint() to format flags, so as not to overflow the buffer. Not\n that it\u0027s ever happed, AFAIK.\n\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "fc36b8d3d819047eb4d23ca079fb4d3af20ff076", "tree": "65ee215a6bdca1e8d4ac4b57525445d7d1829c1d", "parents": [ "53f2556b6792ed99fde965f5e061749edd455623" ], "author": { "name": "Lee Schermerhorn", "email": "lee.schermerhorn@hp.com", "time": "Mon Apr 28 02:13:21 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Apr 28 08:58:24 2008 -0700" }, "message": "mempolicy: use MPOL_F_LOCAL to Indicate Preferred Local Policy\n\nNow that we\u0027re using \"preferred local\" policy for system default, we need to\nmake this as fast as possible. Because of the variable size of the mempolicy\nstructure [based on size of nodemasks], the preferred_node may be in a\ndifferent cacheline from the mode. This can result in accessing an extra\ncacheline in the normal case of system default policy. Suspect this is the\ncause of an observed 2-3% slowdown in page fault testing relative to kernel\nwithout this patch series.\n\nTo alleviate this, use an internal mode flag, MPOL_F_LOCAL in the mempolicy\nflags member which is guaranteed [?] to be in the same cacheline as the mode\nitself.\n\nVerified that reworked mempolicy now performs slightly better on 25-rc8-mm1\nfor both anon and shmem segments with system default and vma [preferred local]\npolicy.\n\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "53f2556b6792ed99fde965f5e061749edd455623", "tree": "82a679e33bc8c305297cbe4655be0dac24728907", "parents": [ "bea904d54d6faa92400f10c8ea3d3828b8e1eb93" ], "author": { "name": "Lee Schermerhorn", "email": "lee.schermerhorn@hp.com", "time": "Mon Apr 28 02:13:20 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Apr 28 08:58:24 2008 -0700" }, "message": "mempolicy: mPOL_PREFERRED cleanups for \"local allocation\"\n\nHere are a couple of \"cleanups\" for MPOL_PREFERRED behavior when\nv.preferred_node \u003c 0 -- i.e., \"local allocation\":\n\n1) [do_]get_mempolicy() calls the now renamed get_policy_nodemask()\n to fetch the nodemask associated with a policy. Currently,\n get_policy_nodemask() returns the set of nodes with memory, when\n the policy \u0027mode\u0027 is \u0027PREFERRED, and the preferred_node is \u003c 0.\n Change to return an empty nodemask, as this is what was specified\n to achieve \"local allocation\".\n\n2) When a task is moved into a [new] cpuset, mpol_rebind_policy() is\n called to adjust any task and vma policy nodes to be valid in the\n new cpuset. However, when the policy is MPOL_PREFERRED, and the\n preferred_node is \u003c0, no rebind is necessary. The \"local allocation\"\n indication is valid in any cpuset. Existing code will \"do the right\n thing\" because node_remap() will just return the argument node when\n it is outside of the valid range of node ids. However, I think it is\n clearer and cleaner to skip the remap explicitly in this case.\n\n3) mpol_to_str() produces a printable, \"human readable\" string from a\n struct mempolicy. For MPOL_PREFERRED with preferred_node \u003c0, show\n \"local\", as this indicates local allocation, as the task migrates\n among nodes. Note that this matches the usage of \"local allocation\"\n in libnuma() and numactl. Without this change, I believe that node_set()\n [via set_bit()] will set bit 31, resulting in a misleading display.\n\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "bea904d54d6faa92400f10c8ea3d3828b8e1eb93", "tree": "24966dd4dabadb4bb32aa1e00fae2c2168661229", "parents": [ "52cd3b074050dd664380b5e8cfc85d4a6ed8ad48" ], "author": { "name": "Lee Schermerhorn", "email": "lee.schermerhorn@hp.com", "time": "Mon Apr 28 02:13:18 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Apr 28 08:58:24 2008 -0700" }, "message": "mempolicy: use MPOL_PREFERRED for system-wide default policy\n\nCurrently, when one specifies MPOL_DEFAULT via a NUMA memory policy API\n[set_mempolicy(), mbind() and internal versions], the kernel simply installs a\nNULL struct mempolicy pointer in the appropriate context: task policy, vma\npolicy, or shared policy. This causes any use of that policy to \"fall back\"\nto the next most specific policy scope.\n\nThe only use of MPOL_DEFAULT to mean \"local allocation\" is in the system\ndefault policy. This requires extra checks/cases for MPOL_DEFAULT in many\nmempolicy.c functions.\n\nThere is another, \"preferred\" way to specify local allocation via the APIs.\nThat is using the MPOL_PREFERRED policy mode with an empty nodemask.\nInternally, the empty nodemask gets converted to a preferred_node id of \u0027-1\u0027.\nAll internal usage of MPOL_PREFERRED will convert the \u0027-1\u0027 to the id of the\nnode local to the cpu where the allocation occurs.\n\nSystem default policy, except during boot, is hard-coded to \"local\nallocation\". By using the MPOL_PREFERRED mode with a negative value of\npreferred node for system default policy, MPOL_DEFAULT will never occur in the\n\u0027policy\u0027 member of a struct mempolicy. Thus, we can remove all checks for\nMPOL_DEFAULT when converting policy to a node id/zonelist in the allocation\npaths.\n\nIn slab_node() return local node id when policy pointer is NULL. No need to\nset a pol value to take the switch default. Replace switch default with\nBUG()--i.e., shouldn\u0027t happen.\n\nWith this patch MPOL_DEFAULT is only used in the APIs, including internal\ncalls to do_set_mempolicy() and in the display of policy in\n/proc/\u003cpid\u003e/numa_maps. It always means \"fall back\" to the the next most\nspecific policy scope. This simplifies the description of memory policies\nquite a bit, with no visible change in behavior.\n\nget_mempolicy() continues to return MPOL_DEFAULT and an empty nodemask when\nthe requested policy [task or vma/shared] is NULL. These are the values one\nwould supply via set_mempolicy() or mbind() to achieve that condition--default\nbehavior.\n\nThis patch updates Documentation to reflect this change.\n\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "52cd3b074050dd664380b5e8cfc85d4a6ed8ad48", "tree": "fcfcf55c0e81376ea34919fab26e29bedd7f3b88", "parents": [ "a6020ed759404372e8be2b276e85e51735472cc9" ], "author": { "name": "Lee Schermerhorn", "email": "lee.schermerhorn@hp.com", "time": "Mon Apr 28 02:13:16 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Apr 28 08:58:24 2008 -0700" }, "message": "mempolicy: rework mempolicy Reference Counting [yet again]\n\nAfter further discussion with Christoph Lameter, it has become clear that my\nearlier attempts to clean up the mempolicy reference counting were a bit of\noverkill in some areas, resulting in superflous ref/unref in what are usually\nfast paths. In other areas, further inspection reveals that I botched the\nunref for interleave policies.\n\nA separate patch, suitable for upstream/stable trees, fixes up the known\nerrors in the previous attempt to fix reference counting.\n\nThis patch reworks the memory policy referencing counting and, one hopes,\nsimplifies the code. Maybe I\u0027ll get it right this time.\n\nSee the update to the numa_memory_policy.txt document for a discussion of\nmemory policy reference counting that motivates this patch.\n\nSummary:\n\nLookup of mempolicy, based on (vma, address) need only add a reference for\nshared policy, and we need only unref the policy when finished for shared\npolicies. So, this patch backs out all of the unneeded extra reference\ncounting added by my previous attempt. It then unrefs only shared policies\nwhen we\u0027re finished with them, using the mpol_cond_put() [conditional put]\nhelper function introduced by this patch.\n\nNote that shmem_swapin() calls read_swap_cache_async() with a dummy vma\ncontaining just the policy. read_swap_cache_async() can call alloc_page_vma()\nmultiple times, so we can\u0027t let alloc_page_vma() unref the shared policy in\nthis case. To avoid this, we make a copy of any non-null shared policy and\nremove the MPOL_F_SHARED flag from the copy. This copy occurs before reading\na page [or multiple pages] from swap, so the overhead should not be an issue\nhere.\n\nI introduced a new static inline function \"mpol_cond_copy()\" to copy the\nshared policy to an on-stack policy and remove the flags that would require a\nconditional free. The current implementation of mpol_cond_copy() assumes that\nthe struct mempolicy contains no pointers to dynamically allocated structures\nthat must be duplicated or reference counted during copy.\n\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "aab0b1029f0843756b68e0ed3ca983685bf43ed6", "tree": "95a0546c908a1c7a3bf1353f433ff1464faf68db", "parents": [ "45c4745af381851b0406d8e4db99e62e265691c2" ], "author": { "name": "Lee Schermerhorn", "email": "lee.schermerhorn@hp.com", "time": "Mon Apr 28 02:13:13 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Apr 28 08:58:24 2008 -0700" }, "message": "mempolicy: mark shared policies for unref\n\nAs part of yet another rework of mempolicy reference counting, we want to be\nable to identify shared policies efficiently, because they have an extra ref\ntaken on lookup that needs to be removed when we\u0027re finished using the policy.\n\n Note: the extra ref is required because the policies are\n shared between tasks/processes and can be changed/freed\n by one task while another task is using them--e.g., for\n page allocation.\n\nBuilding on David Rientjes mempolicy \"mode flags\" enhancement, this patch\nindicates a \"shared\" policy by setting a new MPOL_F_SHARED flag in the flags\nmember of the struct mempolicy added by David. MPOL_F_SHARED, and any future\n\"internal mode flags\" are reserved from bit zero up, as they will never be\npassed in the upper bits of the mode argument of a mempolicy API.\n\nI set the MPOL_F_SHARED flag when the policy is installed in the shared policy\nrb-tree. Don\u0027t need/want to clear the flag when removing from the tree as the\nmempolicy is freed [unref\u0027d] internally to the sp_delete() function. However,\na task could hold another reference on this mempolicy from a prior lookup. We\nneed the MPOL_F_SHARED flag to stay put so that any tasks holding a ref will\nunref, eventually freeing, the mempolicy.\n\nA later patch in this series will introduce a function to conditionally unref\n[mpol_free] a policy. The MPOL_F_SHARED flag is one reason [currently the\nonly reason] to unref/free a policy via the conditional free.\n\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "45c4745af381851b0406d8e4db99e62e265691c2", "tree": "d93f6f7b3d7eb3773aaa80444c56baff99e670d6", "parents": [ "ae4d8c16aa22775f5731677abb8a82f03cec877e" ], "author": { "name": "Lee Schermerhorn", "email": "lee.schermerhorn@hp.com", "time": "Mon Apr 28 02:13:12 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Apr 28 08:58:24 2008 -0700" }, "message": "mempolicy: rename struct mempolicy \u0027policy\u0027 member to \u0027mode\u0027\n\nThe terms \u0027policy\u0027 and \u0027mode\u0027 are both used in various places to describe the\nsemantics of the value stored in the \u0027policy\u0027 member of struct mempolicy.\nFurthermore, the term \u0027policy\u0027 is used to refer to that member, to the entire\nstruct mempolicy and to the more abstract concept of the tuple consisting of a\n\"mode\" and an optional node or set of nodes. Recently, we have added \"mode\nflags\" that are passed in the upper bits of the \u0027mode\u0027 [or sometimes,\n\u0027policy\u0027] member of the numa APIs.\n\nI\u0027d like to resolve this confusion, which perhaps only exists in my mind, by\nrenaming the \u0027policy\u0027 member to \u0027mode\u0027 throughout, and fixing up the\nDocumentation. Man pages will be updated separately.\n\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "ae4d8c16aa22775f5731677abb8a82f03cec877e", "tree": "2d34c6fd334b51cc5f3265cd4ec26db758639b5c", "parents": [ "f4e53d910b7dde2685b177f1e7c3e3e0b4a42f7b" ], "author": { "name": "Lee Schermerhorn", "email": "lee.schermerhorn@hp.com", "time": "Mon Apr 28 02:13:11 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Apr 28 08:58:24 2008 -0700" }, "message": "mempolicy: fixup Fallback for Default Shmem Policy\n\nget_vma_policy() is not handling fallback to task policy correctly when the\nget_policy() vm_op returns NULL. The NULL overwrites the \u0027pol\u0027 variable that\nwas holding the fallback task mempolicy. So, it was falling back directly to\nsystem default policy.\n\nFix get_vma_policy() to use only non-NULL policy returned from the vma\nget_policy op.\n\nshm_get_policy() was falling back to current task\u0027s mempolicy if the \"backing\nfile system\" [tmpfs vs hugetlbfs] does not support the get_policy vm_op and\nthe vma policy is null. This is incorrect for show_numa_maps() which is\nlikely querying the numa_maps of some task other than current. Remove this\nfallback.\n\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "f4e53d910b7dde2685b177f1e7c3e3e0b4a42f7b", "tree": "db4db3abbc0b63de88dabd13e9359ca86973935c", "parents": [ "846a16bf0fc80dc95a414ffce465e3cbf9680247" ], "author": { "name": "Lee Schermerhorn", "email": "lee.schermerhorn@hp.com", "time": "Mon Apr 28 02:13:10 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Apr 28 08:58:23 2008 -0700" }, "message": "mempolicy: write lock mmap_sem while changing task mempolicy\n\nA read of /proc/\u003cpid\u003e/numa_maps holds the target task\u0027s mmap_sem for read\nwhile examining each vma\u0027s mempolicy. A vma\u0027s mempolicy can fall back to the\ntask\u0027s policy. However, the task could be changing it\u0027s task policy and free\nthe one that the show_numa_maps() is examining.\n\nTo prevent this, grab the mmap_sem for write when updating task mempolicy.\nPointed out to me by Christoph Lameter and extracted and reworked from\nChristoph\u0027s alternative mempol reference counting patch.\n\nThis is analogous to the way that do_mbind() and do_get_mempolicy() prevent\nraces between task\u0027s sharing an mm_struct [a.k.a. threads] setting and\nquerying a mempolicy for a particular address.\n\nNote: this is necessary, but not sufficient, to allow us to stop taking an\nextra reference on \"other task\u0027s mempolicy\" in get_vma_policy. Subsequent\npatches will complete this update, allowing us to simplify the tests for\nwhether we need to unref a mempolicy at various points in the code.\n\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "846a16bf0fc80dc95a414ffce465e3cbf9680247", "tree": "45e03061c5e3d8242bf470509771926f37177415", "parents": [ "f0be3d32b05d3fea2fcdbbb81a39dac2a7163169" ], "author": { "name": "Lee Schermerhorn", "email": "lee.schermerhorn@hp.com", "time": "Mon Apr 28 02:13:09 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Apr 28 08:58:23 2008 -0700" }, "message": "mempolicy: rename mpol_copy to mpol_dup\n\nThis patch renames mpol_copy() to mpol_dup() because, well, that\u0027s what it\ndoes. Like, e.g., strdup() for strings, mpol_dup() takes a pointer to an\nexisting mempolicy, allocates a new one and copies the contents.\n\nIn a later patch, I want to use the name mpol_copy() to copy the contents from\none mempolicy to another like, e.g., strcpy() does for strings.\n\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "f0be3d32b05d3fea2fcdbbb81a39dac2a7163169", "tree": "5794ce6a8befbce82cd3e44ff15fbf3bb5f2f3bf", "parents": [ "3b1163006332302117b1b2acf226d4014ff46525" ], "author": { "name": "Lee Schermerhorn", "email": "lee.schermerhorn@hp.com", "time": "Mon Apr 28 02:13:08 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Apr 28 08:58:23 2008 -0700" }, "message": "mempolicy: rename mpol_free to mpol_put\n\nThis is a change that was requested some time ago by Mel Gorman. Makes sense\nto me, so here it is.\n\nNote: I retain the name \"mpol_free_shared_policy()\" because it actually does\nfree the shared_policy, which is NOT a reference counted object. However, ...\n\nThe mempolicy object[s] referenced by the shared_policy are reference counted,\nso mpol_put() is used to release the reference held by the shared_policy. The\nmempolicy might not be freed at this time, because some task attached to the\nshared object associated with the shared policy may be in the process of\nallocating a page based on the mempolicy. In that case, the task performing\nthe allocation will hold a reference on the mempolicy, obtained via\nmpol_shared_policy_lookup(). The mempolicy will be freed when all tasks\nholding such a reference have called mpol_put() for the mempolicy.\n\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "3e1f064562fcff7bf3856bc1d00dfa84d4f121cc", "tree": "9ebc17449238ab5284b72f634405044376dc816b", "parents": [ "3842b46de626d1a3c44ad280d67ab0a4dc047d13" ], "author": { "name": "David Rientjes", "email": "rientjes@google.com", "time": "Mon Apr 28 02:12:34 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Apr 28 08:58:20 2008 -0700" }, "message": "mempolicy: disallow static or relative flags for local preferred mode\n\nMPOL_F_STATIC_NODES and MPOL_F_RELATIVE_NODES don\u0027t mean anything for\nMPOL_PREFERRED policies that were created with an empty nodemask (for purely\nlocal allocations). They\u0027ll never be invalidated because the allowed mems of\na task changes or need to be rebound relative to a cpuset\u0027s placement.\n\nAlso fixes a bug identified by Lee Schermerhorn that disallowed empty\nnodemasks to be passed to MPOL_PREFERRED to specify local allocations. [A\ndifferent, somewhat incomplete, patch already existed in 25-rc5-mm1.]\n\nCc: Paul Jackson \u003cpj@sgi.com\u003e\nCc: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: Lee Schermerhorn \u003cLee.Schermerhorn@hp.com\u003e\nCc: Andi Kleen \u003cak@suse.de\u003e\nCc: Randy Dunlap \u003crandy.dunlap@oracle.com\u003e\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.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": "37012946da940521fb997a758a219d2f1ab56e51", "tree": "16553f91325720a53d0314070793700b5926e052", "parents": [ "1d0d2680a01c4f9e292ec6d4714884da939053a1" ], "author": { "name": "David Rientjes", "email": "rientjes@google.com", "time": "Mon Apr 28 02:12:33 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Apr 28 08:58:20 2008 -0700" }, "message": "mempolicy: create mempolicy_operations structure\n\nCreate a mempolicy_operations structure that currently points to two\nfunctions[*] for the various modes:\n\n\tint (*create)(struct mempolicy *, const nodemask_t *);\n\tvoid (*rebind)(struct mempolicy *, const nodemask_t *);\n\nThis splits the implementation for the various modes out of two large\nfunctions, mpol_new() and mpol_rebind_policy(). Eventually it may be\nbeneficial to add additional functions to accomodate the existing switch()\nstatements in mm/mempolicy.c.\n\n [*] The -\u003ecreate() function for MPOL_DEFAULT is currently NULL since no\n struct mempolicy is dynamically allocated.\n\n[Lee.Schermerhorn@hp.com: fix regression in the package mempolicy regression tests]\nSigned-off-by: David Rientjes \u003crientjes@google.com\u003e\nCc: Paul Jackson \u003cpj@sgi.com\u003e\nCc: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Eric Whitney \u003ceric.whitney@hp.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "1d0d2680a01c4f9e292ec6d4714884da939053a1", "tree": "1377ed40ec15ffecc584b308a671be47b5145db3", "parents": [ "65d66fc02ed9433b957588071b60425b12628e25" ], "author": { "name": "David Rientjes", "email": "rientjes@google.com", "time": "Mon Apr 28 02:12:32 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Apr 28 08:58:20 2008 -0700" }, "message": "mempolicy: move rebind functions\n\nMove the mpol_rebind_{policy,task,mm}() functions after mpol_new() to avoid\nhaving to declare function prototypes.\n\nCc: Paul Jackson \u003cpj@sgi.com\u003e\nCc: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: Lee Schermerhorn \u003cLee.Schermerhorn@hp.com\u003e\nCc: Andi Kleen \u003cak@suse.de\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": "4c50bc0116cf3cc35e7152d6a8424b4db65f52d6", "tree": "99c617602cc1946fc86b48e9a35f14f9f354cf67", "parents": [ "7ea931c9fc80c4d0a4306c30ec92eb0f1d922a0b" ], "author": { "name": "David Rientjes", "email": "rientjes@google.com", "time": "Mon Apr 28 02:12:30 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Apr 28 08:58:19 2008 -0700" }, "message": "mempolicy: add MPOL_F_RELATIVE_NODES flag\n\nAdds another optional mode flag, MPOL_F_RELATIVE_NODES, that specifies\nnodemasks passed via set_mempolicy() or mbind() should be considered relative\nto the current task\u0027s mems_allowed.\n\nWhen the mempolicy is created, the passed nodemask is folded and mapped onto\nthe current task\u0027s mems_allowed. For example, consider a task using\nset_mempolicy() to pass MPOL_INTERLEAVE | MPOL_F_RELATIVE_NODES with a\nnodemask of 1-3. If current\u0027s mems_allowed is 4-7, the effected nodemask is\n5-7 (the second, third, and fourth node of mems_allowed).\n\nIf the same task is attached to a cpuset, the mempolicy nodemask is rebound\neach time the mems are changed. Some possible rebinds and results are:\n\n\tmems\t\t\tresult\n\t1-3\t\t\t1-3\n\t1-7\t\t\t2-4\n\t1,5-6\t\t\t1,5-6\n\t1,5-7\t\t\t5-7\n\nLikewise, the zonelist built for MPOL_BIND acts on the set of zones assigned\nto the resultant nodemask from the relative remap.\n\nIn the MPOL_PREFERRED case, the preferred node is remapped from the currently\neffected nodemask to the relative nodemask.\n\nThis mempolicy mode flag was conceived of by Paul Jackson \u003cpj@sgi.com\u003e.\n\nCc: Paul Jackson \u003cpj@sgi.com\u003e\nCc: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: Lee Schermerhorn \u003cLee.Schermerhorn@hp.com\u003e\nCc: Andi Kleen \u003cak@suse.de\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": "f5b087b52f1710eb0bf15a2d2b030c51a6a1ca9e", "tree": "66336235822f59215707dfa501e1d2b66b38a015", "parents": [ "028fec414d803117eb4b2ed12acb4dd5da65b32d" ], "author": { "name": "David Rientjes", "email": "rientjes@google.com", "time": "Mon Apr 28 02:12:27 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Apr 28 08:58:19 2008 -0700" }, "message": "mempolicy: add MPOL_F_STATIC_NODES flag\n\nAdd an optional mempolicy mode flag, MPOL_F_STATIC_NODES, that suppresses the\nnode remap when the policy is rebound.\n\nAdds another member to struct mempolicy, nodemask_t user_nodemask, as part of\na union with cpuset_mems_allowed:\n\n\tstruct mempolicy {\n\t\t...\n\t\tunion {\n\t\t\tnodemask_t cpuset_mems_allowed;\n\t\t\tnodemask_t user_nodemask;\n\t\t} w;\n\t}\n\nthat stores the the nodemask that the user passed when he or she created the\nmempolicy via set_mempolicy() or mbind(). When using MPOL_F_STATIC_NODES,\nwhich is passed with any mempolicy mode, the user\u0027s passed nodemask\nintersected with the VMA or task\u0027s allowed nodes is always used when\ndetermining the preferred node, setting the MPOL_BIND zonelist, or creating\nthe interleave nodemask. This happens whenever the policy is rebound,\nincluding when a task\u0027s cpuset assignment changes or the cpuset\u0027s mems are\nchanged.\n\nThis creates an interesting side-effect in that it allows the mempolicy\n\"intent\" to lie dormant and uneffected until it has access to the node(s) that\nit desires. For example, if you currently ask for an interleaved policy over\na set of nodes that you do not have access to, the mempolicy is not created\nand the task continues to use the previous policy. With this change, however,\nit is possible to create the same mempolicy; it is only effected when access\nto nodes in the nodemask is acquired.\n\nIt is also possible to mount tmpfs with the static nodemask behavior when\nspecifying a node or nodemask. To do this, simply add \"\u003dstatic\" immediately\nfollowing the mempolicy mode at mount time:\n\n\tmount -o remount mpol\u003dinterleave\u003dstatic:1-3\n\nAlso removes mpol_check_policy() and folds its logic into mpol_new() since it\nis now obsoleted. The unused vma_mpol_equal() is also removed.\n\nCc: Paul Jackson \u003cpj@sgi.com\u003e\nCc: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: Lee Schermerhorn \u003cLee.Schermerhorn@hp.com\u003e\nCc: Andi Kleen \u003cak@suse.de\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": "028fec414d803117eb4b2ed12acb4dd5da65b32d", "tree": "427f37ea0331369c1babc55c424c4fd2ac3b39f5", "parents": [ "a3b51e0142d1be156ac697eaadadd6cfbb7ba32b" ], "author": { "name": "David Rientjes", "email": "rientjes@google.com", "time": "Mon Apr 28 02:12:25 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Apr 28 08:58:19 2008 -0700" }, "message": "mempolicy: support optional mode flags\n\nWith the evolution of mempolicies, it is necessary to support mempolicy mode\nflags that specify how the policy shall behave in certain circumstances. The\nmost immediate need for mode flag support is to suppress remapping the\nnodemask of a policy at the time of rebind.\n\nBoth the mempolicy mode and flags are passed by the user in the \u0027int policy\u0027\nformal of either the set_mempolicy() or mbind() syscall. A new constant,\nMPOL_MODE_FLAGS, represents the union of legal optional flags that may be\npassed as part of this int. Mempolicies that include illegal flags as part of\ntheir policy are rejected as invalid.\n\nAn additional member to struct mempolicy is added to support the mode flags:\n\n\tstruct mempolicy {\n\t\t...\n\t\tunsigned short policy;\n\t\tunsigned short flags;\n\t}\n\nThe splitting of the \u0027int\u0027 actual passed by the user is done in\nsys_set_mempolicy() and sys_mbind() for their respective syscalls. This is\ndone by intersecting the actual with MPOL_MODE_FLAGS, rejecting the syscall of\nthere are additional flags, and storing it in the new \u0027flags\u0027 member of struct\nmempolicy. The intersection of the actual with ~MPOL_MODE_FLAGS is stored in\nthe \u0027policy\u0027 member of the struct and all current users of pol-\u003epolicy remain\nunchanged.\n\nThe union of the policy mode and optional mode flags is passed back to the\nuser in get_mempolicy().\n\nThis combination of mode and flags within the same actual does not break\nuserspace code that relies on get_mempolicy(\u0026policy, ...) and either\n\n\tswitch (policy) {\n\tcase MPOL_BIND:\n\t\t...\n\tcase MPOL_INTERLEAVE:\n\t\t...\n\t};\n\nstatements or\n\n\tif (policy \u003d\u003d MPOL_INTERLEAVE) {\n\t\t...\n\t}\n\nstatements. Such applications would need to use optional mode flags when\ncalling set_mempolicy() or mbind() for these previously implemented statements\nto stop working. If an application does start using optional mode flags, it\nwill need to mask the optional flags off the policy in switch and conditional\nstatements that only test mode.\n\nAn additional member is also added to struct shmem_sb_info to store the\noptional mode flags.\n\n[hugh@veritas.com: shmem mpol: fix build warning]\nCc: Paul Jackson \u003cpj@sgi.com\u003e\nCc: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: Lee Schermerhorn \u003cLee.Schermerhorn@hp.com\u003e\nCc: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: David Rientjes \u003crientjes@google.com\u003e\nSigned-off-by: Hugh Dickins \u003chugh@veritas.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "a3b51e0142d1be156ac697eaadadd6cfbb7ba32b", "tree": "da9e527316f112c09f0bc16553c64e3c87125c82", "parents": [ "1b27d05b6e21249d2338be26dfcbe8f8d8ff8a5b" ], "author": { "name": "David Rientjes", "email": "rientjes@google.com", "time": "Mon Apr 28 02:12:23 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Apr 28 08:58:19 2008 -0700" }, "message": "mempolicy: convert MPOL constants to enum\n\nThe mempolicy mode constants, MPOL_DEFAULT, MPOL_PREFERRED, MPOL_BIND, and\nMPOL_INTERLEAVE, are better declared as part of an enum since they are\nsequentially numbered and cannot be combined.\n\nThe policy member of struct mempolicy is also converted from type short to\ntype unsigned short. A negative policy does not have any legitimate meaning,\nso it is possible to change its type in preparation for adding optional mode\nflags later.\n\nThe equivalent member of struct shmem_sb_info is also changed from int to\nunsigned short.\n\nFor compatibility, the policy formal to get_mempolicy() remains as a pointer\nto an int:\n\n\tint get_mempolicy(int *policy, unsigned long *nmask,\n\t\t\t unsigned long maxnode, unsigned long addr,\n\t\t\t unsigned long flags);\n\nalthough the only possible values is the range of type unsigned short.\n\nCc: Paul Jackson \u003cpj@sgi.com\u003e\nCc: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: Lee Schermerhorn \u003cLee.Schermerhorn@hp.com\u003e\nCc: Andi Kleen \u003cak@suse.de\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": "19770b32609b6bf97a3dece2529089494cbfc549", "tree": "3b5922d1b20aabdf929bde9309f323841717747a", "parents": [ "dd1a239f6f2d4d3eedd318583ec319aa145b324c" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Mon Apr 28 02:12:18 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Apr 28 08:58:19 2008 -0700" }, "message": "mm: filter based on a nodemask as well as a gfp_mask\n\nThe MPOL_BIND policy creates a zonelist that is used for allocations\ncontrolled by that mempolicy. As the per-node zonelist is already being\nfiltered based on a zone id, this patch adds a version of __alloc_pages() that\ntakes a nodemask for further filtering. This eliminates the need for\nMPOL_BIND to create a custom zonelist.\n\nA positive benefit of this is that allocations using MPOL_BIND now use the\nlocal node\u0027s distance-ordered zonelist instead of a custom node-id-ordered\nzonelist. I.e., pages will be allocated from the closest allowed node with\navailable memory.\n\n[Lee.Schermerhorn@hp.com: Mempolicy: update stale documentation and comments]\n[Lee.Schermerhorn@hp.com: Mempolicy: make dequeue_huge_page_vma() obey MPOL_BIND nodemask]\n[Lee.Schermerhorn@hp.com: Mempolicy: make dequeue_huge_page_vma() obey MPOL_BIND nodemask rework]\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nAcked-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: Hugh Dickins \u003chugh@veritas.com\u003e\nCc: Nick Piggin \u003cnickpiggin@yahoo.com.au\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "dd1a239f6f2d4d3eedd318583ec319aa145b324c", "tree": "aff4224c96b5e2e67588c3946858a724863eeaf9", "parents": [ "54a6eb5c4765aa573a030ceeba2c14e3d2ea5706" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Mon Apr 28 02:12:17 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Apr 28 08:58:18 2008 -0700" }, "message": "mm: have zonelist contains structs with both a zone pointer and zone_idx\n\nFiltering zonelists requires very frequent use of zone_idx(). This is costly\nas it involves a lookup of another structure and a substraction operation. As\nthe zone_idx is often required, it should be quickly accessible. The node idx\ncould also be stored here if it was found that accessing zone-\u003enode is\nsignificant which may be the case on workloads where nodemasks are heavily\nused.\n\nThis patch introduces a struct zoneref to store a zone pointer and a zone\nindex. The zonelist then consists of an array of these struct zonerefs which\nare looked up as necessary. Helpers are given for accessing the zone index as\nwell as the node index.\n\n[kamezawa.hiroyu@jp.fujitsu.com: Suggested struct zoneref instead of embedding information in pointers]\n[hugh@veritas.com: mm-have-zonelist: fix memcg ooms]\n[hugh@veritas.com: just return do_try_to_free_pages]\n[hugh@veritas.com: do_try_to_free_pages gfp_mask redundant]\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nAcked-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nAcked-by: David Rientjes \u003crientjes@google.com\u003e\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: Nick Piggin \u003cnickpiggin@yahoo.com.au\u003e\nSigned-off-by: Hugh Dickins \u003chugh@veritas.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "0e88460da6ab7bb6a7ef83675412ed5b6315d741", "tree": "1feb4de2362e4998a0deeab66af1efb9c7b8bb34", "parents": [ "dac1d27bc8d5ca636d3014ecfdf94407031d1970" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Mon Apr 28 02:12:14 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Apr 28 08:58:18 2008 -0700" }, "message": "mm: introduce node_zonelist() for accessing the zonelist for a GFP mask\n\nIntroduce a node_zonelist() helper function. It is used to lookup the\nappropriate zonelist given a node and a GFP mask. The patch on its own is a\ncleanup but it helps clarify parts of the two-zonelist-per-node patchset. If\nnecessary, it can be merged with the next patch in this set without problems.\n\nReviewed-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: Hugh Dickins \u003chugh@veritas.com\u003e\nCc: Nick Piggin \u003cnickpiggin@yahoo.com.au\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "69682d852f5c94ee94e21174b3e8b719626c98db", "tree": "ed3c7c0681ef7658132ae32f1cd8a56bb6451621", "parents": [ "9afa802ff568d935dab33dd207dc25d9849f35d4" ], "author": { "name": "Lee Schermerhorn", "email": "Lee.Schermerhorn@hp.com", "time": "Mon Mar 10 11:43:45 2008 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Mon Mar 10 18:01:19 2008 -0700" }, "message": "mempolicy: fix reference counting bugs\n\nAddress 3 known bugs in the current memory policy reference counting method.\nI have a series of patches to rework the reference counting to reduce overhead\nin the allocation path. However, that series will require testing in -mm once\nI repost it.\n\n1) alloc_page_vma() does not release the extra reference taken for\n vma/shared mempolicy when the mode \u003d\u003d MPOL_INTERLEAVE. This can result in\n leaking mempolicy structures. This is probably occurring, but not being\n noticed.\n\n Fix: add the conditional release of the reference.\n\n2) hugezonelist unconditionally releases a reference on the mempolicy when\n mode \u003d\u003d MPOL_INTERLEAVE. This can result in decrementing the reference\n count for system default policy [should have no ill effect] or premature\n freeing of task policy. If this occurred, the next allocation using task\n mempolicy would use the freed structure and probably BUG out.\n\n Fix: add the necessary check to the release.\n\n3) The current reference counting method assumes that vma \u0027get_policy()\u0027\n methods automatically add an extra reference a non-NULL returned mempolicy.\n This is true for shmem_get_policy() used by tmpfs mappings, including\n regular page shm segments. However, SHM_HUGETLB shm\u0027s, backed by\n hugetlbfs, just use the vma policy without the extra reference. This\n results in freeing of the vma policy on the first allocation, with reuse of\n the freed mempolicy structure on subsequent allocations.\n\n Fix: Rather than add another condition to the conditional reference\n release, which occur in the allocation path, just add a reference when\n returning the vma policy in shm_get_policy() to match the assumptions.\n\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Greg KH \u003cgreg@kroah.com\u003e\nCc: Andi Kleen \u003cak@suse.de\u003e\nCc: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nCc: \u003ceric.whitney@hp.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "c32c2f63a9d6c953aaf168c0b2551da9734f76d2", "tree": "14eca3083f3de4a87a95359ab66109c10add1ae7", "parents": [ "e83aece3afad4d56cc01abe069d3519e851cd2de" ], "author": { "name": "Jan Blunck", "email": "jblunck@suse.de", "time": "Thu Feb 14 19:38:43 2008 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Thu Feb 14 21:17:08 2008 -0800" }, "message": "d_path: Make seq_path() use a struct path argument\n\nseq_path() is always called with a dentry and a vfsmount from a struct path.\nMake seq_path() take it directly as an argument.\n\nSigned-off-by: Jan Blunck \u003cjblunck@suse.de\u003e\nCc: Christoph Hellwig \u003chch@lst.de\u003e\nCc: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\nCc: \"J. Bruce Fields\" \u003cbfields@fieldses.org\u003e\nCc: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "31f1de46b90ad360a16e7af3e277d104961df923", "tree": "a54e8698d4e4d088c4008e0ae91b579b13d2c208", "parents": [ "1a510089849ff9f70b654659bf976a6baf3a4833" ], "author": { "name": "KOSAKI Motohiro", "email": "kosaki.motohiro@jp.fujitsu.com", "time": "Tue Feb 12 13:30:22 2008 +0900" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Mon Feb 11 20:48:29 2008 -0800" }, "message": "mempolicy: silently restrict nodemask to allowed nodes\n\nKosaki Motohito noted that \"numactl --interleave\u003dall ...\" failed in the\npresence of memoryless nodes. This patch attempts to fix that problem.\n\nSome background:\n\nnumactl --interleave\u003dall calls set_mempolicy(2) with a fully populated\n[out to MAXNUMNODES] nodemask. set_mempolicy() [in do_set_mempolicy()]\ncalls contextualize_policy() which requires that the nodemask be a\nsubset of the current task\u0027s mems_allowed; else EINVAL will be returned.\n\nA task\u0027s mems_allowed will always be a subset of node_states[N_HIGH_MEMORY]\ni.e., nodes with memory. So, a fully populated nodemask will be\ndeclared invalid if it includes memoryless nodes.\n\n NOTE: the same thing will occur when running in a cpuset\n with restricted mem_allowed--for the same reason:\n node mask contains dis-allowed nodes.\n\nmbind(2), on the other hand, just masks off any nodes in the nodemask\nthat are not included in the caller\u0027s mems_allowed.\n\nIn each case [mbind() and set_mempolicy()], mpol_check_policy() will\ncomplain [again, resulting in EINVAL] if the nodemask contains any\nmemoryless nodes. This is somewhat redundant as mpol_new() will remove\nmemoryless nodes for interleave policy, as will bind_zonelist()--called\nby mpol_new() for BIND policy.\n\nProposed fix:\n\n1) modify contextualize_policy logic to:\n a) remember whether the incoming node mask is empty.\n b) if not, restrict the nodemask to allowed nodes, as is\n currently done in-line for mbind(). This guarantees\n that the resulting mask includes only nodes with memory.\n\n NOTE: this is a [benign, IMO] change in behavior for\n set_mempolicy(). Dis-allowed nodes will be\n silently ignored, rather than returning an error.\n\n c) fold this code into mpol_check_policy(), replace 2 calls to\n contextualize_policy() to call mpol_check_policy() directly\n and remove contextualize_policy().\n\n2) In existing mpol_check_policy() logic, after \"contextualization\":\n a) MPOL_DEFAULT: require that in coming mask \"was_empty\"\n b) MPOL_{BIND|INTERLEAVE}: require that contextualized nodemask\n contains at least one node.\n c) add a case for MPOL_PREFERRED: if in coming was not empty\n and resulting mask IS empty, user specified invalid nodes.\n Return EINVAL.\n c) remove the now redundant check for memoryless nodes\n\n3) remove the now redundant masking of policy nodes for interleave\n policy from mpol_new().\n\n4) Now that mpol_check_policy() contextualizes the nodemask, remove\n the in-line nodes_and() from sys_mbind(). I believe that this\n restores mbind() to the behavior before the memoryless-nodes\n patch series. E.g., we\u0027ll no longer treat an invalid nodemask\n with MPOL_PREFERRED as local allocation.\n\n[ Patch history:\n\n v1 -\u003e v2:\n - Communicate whether or not incoming node mask was empty to\n mpol_check_policy() for better error checking.\n - As suggested by David Rientjes, remove the now unused\n cpuset_nodes_subset_current_mems_allowed() from cpuset.h\n\n v2 -\u003e v3:\n - As suggested by Kosaki Motohito, fold the \"contextualization\"\n of policy nodemask into mpol_check_policy(). Looks a little\n cleaner. ]\n\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nSigned-off-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nTested-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nAcked-by: David Rientjes \u003crientjes@google.com\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "3ad33b2436b545cbe8b28e53f3710432cad457ab", "tree": "581808f90a08838ee27d76cc24812c7093c216a9", "parents": [ "e1a1c997afe907e6ec4799e4be0f38cffd8b418c" ], "author": { "name": "Lee Schermerhorn", "email": "Lee.Schermerhorn@hp.com", "time": "Wed Nov 14 16:59:10 2007 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Wed Nov 14 18:45:38 2007 -0800" }, "message": "Migration: find correct vma in new_vma_page()\n\nWe hit the BUG_ON() in mm/rmap.c:vma_address() when trying to migrate via\nmbind(MPOL_MF_MOVE) a non-anon region that spans multiple vmas. For\nanon-regions, we just fail to migrate any pages beyond the 1st vma in the\nrange.\n\nThis occurs because do_mbind() collects a list of pages to migrate by\ncalling check_range(). check_range() walks the task\u0027s mm, spanning vmas as\nnecessary, to collect the migratable pages into a list. Then, do_mbind()\ncalls migrate_pages() passing the list of pages, a function to allocate new\npages based on vma policy [new_vma_page()], and a pointer to the first vma\nof the range.\n\nFor each page in the list, new_vma_page() calls page_address_in_vma()\npassing the page and the vma [first in range] to obtain the address to get\nfor alloc_page_vma(). The page address is needed to get interleaving\npolicy correct. If the pages in the list come from multiple vmas,\neventually, new_page_address() will pass that page to page_address_in_vma()\nwith the incorrect vma. For !PageAnon pages, this will result in a bug\ncheck in rmap.c:vma_address(). For anon pages, vma_address() will just\nreturn EFAULT and fail the migration.\n\nThis patch modifies new_vma_page() to check the return value from\npage_address_in_vma(). If the return value is EFAULT, new_vma_page()\nsearchs forward via vm_next for the vma that maps the page--i.e., that does\nnot return EFAULT. This assumes that the pages in the list handed to\nmigrate_pages() is in address order. This is currently case. The patch\ndocuments this assumption in a new comment block for new_vma_page().\n\nIf new_vma_page() cannot locate the vma mapping the page in a forward\nsearch in the mm, it will pass a NULL vma to alloc_page_vma(). This will\nresult in the allocation using the task policy, if any, else system default\npolicy. This situation is unlikely, but the patch documents this behavior\nwith a comment.\n\nNote, this patch results in restarting from the first vma in a multi-vma\nrange each time new_vma_page() is called. If this is not acceptable, we\ncan make the vma argument a pointer, both in new_vma_page() and it\u0027s caller\nunmap_and_move() so that the value held by the loop in migrate_pages()\nalways passes down the last vma in which a page was found. This will\nrequire changes to all new_page_t functions passed to migrate_pages(). Is\nthis necessary?\n\nFor this patch to work, we can\u0027t bug check in vma_address() for pages\noutside the argument vma. This patch removes the BUG_ON(). All other\ncallers [besides new_vma_page()] already check the return status.\n\nTested on x86_64, 4 node NUMA platform.\n\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nAcked-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "228ebcbe634a30aec35132ea4375721bcc41bec0", "tree": "a875976fd5bde6e2f931aa235c34c88a2738493f", "parents": [ "b488893a390edfe027bae7a46e9af8083e740668" ], "author": { "name": "Pavel Emelyanov", "email": "xemul@openvz.org", "time": "Thu Oct 18 23:40:16 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Fri Oct 19 11:53:40 2007 -0700" }, "message": "Uninline find_task_by_xxx set of functions\n\nThe find_task_by_something is a set of macros are used to find task by pid\ndepending on what kind of pid is proposed - global or virtual one. All of\nthem are wrappers above the most generic one - find_task_by_pid_type_ns() -\nand just substitute some args for it.\n\nIt turned out, that dereferencing the current-\u003ensproxy-\u003epid_ns construction\nand pushing one more argument on the stack inline cause kernel text size to\ngrow.\n\nThis patch moves all this stuff out-of-line into kernel/pid.c. Together\nwith the next patch it saves a bit less than 400 bytes from the .text\nsection.\n\nSigned-off-by: Pavel Emelyanov \u003cxemul@openvz.org\u003e\nCc: Sukadev Bhattiprolu \u003csukadev@us.ibm.com\u003e\nCc: Oleg Nesterov \u003coleg@tv-sign.ru\u003e\nCc: Paul Menage \u003cmenage@google.com\u003e\nCc: \"Eric W. Biederman\" \u003cebiederm@xmission.com\u003e\nAcked-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "b488893a390edfe027bae7a46e9af8083e740668", "tree": "c469a7f99ad01005a73011c029eb5e5d15454559", "parents": [ "3eb07c8c8adb6f0572baba844ba2d9e501654316" ], "author": { "name": "Pavel Emelyanov", "email": "xemul@openvz.org", "time": "Thu Oct 18 23:40:14 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Fri Oct 19 11:53:40 2007 -0700" }, "message": "pid namespaces: changes to show virtual ids to user\n\nThis is the largest patch in the set. Make all (I hope) the places where\nthe pid is shown to or get from user operate on the virtual pids.\n\nThe idea is:\n - all in-kernel data structures must store either struct pid itself\n or the pid\u0027s global nr, obtained with pid_nr() call;\n - when seeking the task from kernel code with the stored id one\n should use find_task_by_pid() call that works with global pids;\n - when showing pid\u0027s numerical value to the user the virtual one\n should be used, but however when one shows task\u0027s pid outside this\n task\u0027s namespace the global one is to be used;\n - when getting the pid from userspace one need to consider this as\n the virtual one and use appropriate task/pid-searching functions.\n\n[akpm@linux-foundation.org: build fix]\n[akpm@linux-foundation.org: nuther build fix]\n[akpm@linux-foundation.org: yet nuther build fix]\n[akpm@linux-foundation.org: remove unneeded casts]\nSigned-off-by: Pavel Emelyanov \u003cxemul@openvz.org\u003e\nSigned-off-by: Alexey Dobriyan \u003cadobriyan@openvz.org\u003e\nCc: Sukadev Bhattiprolu \u003csukadev@us.ibm.com\u003e\nCc: Oleg Nesterov \u003coleg@tv-sign.ru\u003e\nCc: Paul Menage \u003cmenage@google.com\u003e\nCc: \"Eric W. Biederman\" \u003cebiederm@xmission.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "8793d854edbc2774943a4b0de3304dc73991159a", "tree": "380b3403a0fedfcce61d9af5af1ffbcc71017abf", "parents": [ "81a6a5cdd2c5cd70874b88afe524ab09e9e869af" ], "author": { "name": "Paul Menage", "email": "menage@google.com", "time": "Thu Oct 18 23:39:39 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Fri Oct 19 11:53:36 2007 -0700" }, "message": "Task Control Groups: make cpusets a client of cgroups\n\nRemove the filesystem support logic from the cpusets system and makes cpusets\na cgroup subsystem\n\nThe \"cpuset\" filesystem becomes a dummy filesystem; attempts to mount it get\npassed through to the cgroup filesystem with the appropriate options to\nemulate the old cpuset filesystem behaviour.\n\nSigned-off-by: Paul Menage \u003cmenage@google.com\u003e\nCc: Serge E. Hallyn \u003cserue@us.ibm.com\u003e\nCc: \"Eric W. Biederman\" \u003cebiederm@xmission.com\u003e\nCc: Dave Hansen \u003chaveblue@us.ibm.com\u003e\nCc: Balbir Singh \u003cbalbir@in.ibm.com\u003e\nCc: Paul Jackson \u003cpj@sgi.com\u003e\nCc: Kirill Korotaev \u003cdev@openvz.org\u003e\nCc: Herbert Poetzl \u003cherbert@13thfloor.at\u003e\nCc: Srivatsa Vaddagiri \u003cvatsa@in.ibm.com\u003e\nCc: Cedric Le Goater \u003cclg@fr.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": "dbcb0f19c877df9026b8c1227758d38bd561e9c4", "tree": "f58c85976906f42ff44798f514177392d7c48d0f", "parents": [ "d8dc74f212c38407fc9f4367181f8f969b719485" ], "author": { "name": "Adrian Bunk", "email": "bunk@stusta.de", "time": "Tue Oct 16 01:26:26 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:43:03 2007 -0700" }, "message": "mm/mempolicy.c: cleanups\n\nThis patch contains the following cleanups:\n- every file should include the headers containing the prototypes for\n its global functions\n- make the follosing needlessly global functions static:\n - migrate_to_node()\n - do_mbind()\n - sp_alloc()\n - mpol_rebind_policy()\n\n[akpm@linux-foundation.org: fix uninitialised var warning]\nSigned-off-by: Adrian Bunk \u003cbunk@stusta.de\u003e\nAcked-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "37b07e4163f7306aa735a6e250e8d22293e5b8de", "tree": "5c9c1935253a39aa840a9923bf1c86620cb6f733", "parents": [ "0e1e7c7a739562a321fda07c7cd2a97a7114f8f8" ], "author": { "name": "Lee Schermerhorn", "email": "Lee.Schermerhorn@hp.com", "time": "Tue Oct 16 01:25:39 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:59 2007 -0700" }, "message": "memoryless nodes: fixup uses of node_online_map in generic code\n\nHere\u0027s a cut at fixing up uses of the online node map in generic code.\n\nmm/shmem.c:shmem_parse_mpol()\n\n\tEnsure nodelist is subset of nodes with memory.\n\tUse node_states[N_HIGH_MEMORY] as default for missing\n\tnodelist for interleave policy.\n\nmm/shmem.c:shmem_fill_super()\n\n\tinitialize policy_nodes to node_states[N_HIGH_MEMORY]\n\nmm/page-writeback.c:highmem_dirtyable_memory()\n\n\tsum over nodes with memory\n\nmm/page_alloc.c:zlc_setup()\n\n\tallowednodes - use nodes with memory.\n\nmm/page_alloc.c:default_zonelist_order()\n\n\taverage over nodes with memory.\n\nmm/page_alloc.c:find_next_best_node()\n\n\tskip nodes w/o memory.\n\tN_HIGH_MEMORY state mask may not be initialized at this time,\n\tunless we want to depend on early_calculate_totalpages() [see\n\tbelow]. Will ZONE_MOVABLE ever be configurable?\n\nmm/page_alloc.c:find_zone_movable_pfns_for_nodes()\n\n\tspread kernelcore over nodes with memory.\n\n\tThis required calling early_calculate_totalpages()\n\tunconditionally, and populating N_HIGH_MEMORY node\n\tstate therein from nodes in the early_node_map[].\n\tIf we can depend on this, we can eliminate the\n\tpopulation of N_HIGH_MEMORY mask from __build_all_zonelists()\n\tand use the N_HIGH_MEMORY mask in find_next_best_node().\n\nmm/mempolicy.c:mpol_check_policy()\n\n\tEnsure nodes specified for policy are subset of\n\tnodes with memory.\n\n[akpm@linux-foundation.org: fix warnings]\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nAcked-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: Shaohua Li \u003cshaohua.li@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": "56bbd65df0e92a4a8eb70c5f2b416ae2b6c5fb31", "tree": "714154b7b16d2e08c60d49b925aa0e789f0f0be0", "parents": [ "4199cfa02b982f4c739e8a6a304d6a40e1935d25" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Tue Oct 16 01:25:35 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:58 2007 -0700" }, "message": "Memoryless nodes: Update memory policy and page migration\n\nOnline nodes now may have no memory. The checks and initialization must\ntherefore be changed to no longer use the online functions.\n\nThis will correctly initialize the interleave on bootup to only target nodes\nwith memory and will make sys_move_pages return an error when a page is to be\nmoved to a memoryless node. Similarly we will get an error if MPOL_BIND and\nMPOL_INTERLEAVE is used on a memoryless node.\n\nThese are somewhat new semantics. So far one could specify memoryless nodes\nand we would maybe do the right thing and just ignore the node (or we\u0027d do\nsomething strange like with MPOL_INTERLEAVE). If we want to allow the\nspecification of memoryless nodes via memory policies then we need to keep\nchecking for online nodes.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nAcked-by: Nishanth Aravamudan \u003cnacc@us.ibm.com\u003e\nTested-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nAcked-by: Bob Picco \u003cbob.picco@hp.com\u003e\nCc: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Mel Gorman \u003cmel@skynet.ie\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "6eaf806a223e61dc5f2de4ab591f11beb97a8f3b", "tree": "fd63b422c3cb357792d12f9170c354e25b94daa0", "parents": [ "7ea1530ab3fdfa85441061909cc8040e84776fd4" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Tue Oct 16 01:25:30 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:58 2007 -0700" }, "message": "Memoryless nodes: Fix interleave behavior for memoryless nodes\n\nMPOL_INTERLEAVE currently simply loops over all nodes. Allocations on\nmemoryless nodes will be redirected to nodes with memory. This results in an\nimbalance because the neighboring nodes to memoryless nodes will get\nsignificantly more interleave hits that the rest of the nodes on the system.\n\nWe can avoid this imbalance by clearing the nodes in the interleave node set\nthat have no memory. If we use the node map of the memory nodes instead of\nthe online nodes then we have only the nodes we want.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Nishanth Aravamudan \u003cnacc@us.ibm.com\u003e\nTested-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nAcked-by: Bob Picco \u003cbob.picco@hp.com\u003e\nCc: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Mel Gorman \u003cmel@skynet.ie\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "754af6f5a85fcd1ecb456851d20c65e4c6ce10ab", "tree": "8c985bfd704a8c993d6ca992725969c6fc5c9e5a", "parents": [ "32a4330d4156e55a4888a201f484dbafed9504ed" ], "author": { "name": "Lee Schermerhorn", "email": "Lee.Schermerhorn@hp.com", "time": "Tue Oct 16 01:24:51 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:54 2007 -0700" }, "message": "Mem Policy: add MPOL_F_MEMS_ALLOWED get_mempolicy() flag\n\nAllow an application to query the memories allowed by its context.\n\nUpdated numa_memory_policy.txt to mention that applications can use this to\nobtain allowed memories for constructing valid policies.\n\nTODO: update out-of-tree libnuma wrapper[s], or maybe add a new\nwrapper--e.g., numa_get_mems_allowed() ?\n\nAlso, update numa syscall man pages.\n\nTested with memtoy V\u003e\u003d0.13.\n\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nAcked-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "43fac94dd62667c83dd2daa5b7ac548512af780a", "tree": "68b8cf73959afd24410f3f398bda5953c7dcbadd", "parents": [ "39e91e433169bdfd5a312654e5988986662afd7f" ], "author": { "name": "Jesper Juhl", "email": "jesper.juhl@gmail.com", "time": "Tue Oct 16 01:24:30 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Oct 16 09:42:52 2007 -0700" }, "message": "Clean up duplicate includes in mm/\n\nThis patch cleans up duplicate includes in\n\tmm/\n\nSigned-off-by: Jesper Juhl \u003cjesper.juhl@gmail.com\u003e\nAcked-by: Paul Mundt \u003clethal@linux-sh.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "480eccf9ae1073b87bb4fe118971fbf134a5bc61", "tree": "b66cd85cd6ad9dc7c141d34837a848111d036584", "parents": [ "28f300d23674fa01ae747c66ce861d4ee6aebe8c" ], "author": { "name": "Lee Schermerhorn", "email": "Lee.Schermerhorn@hp.com", "time": "Tue Sep 18 22:46:47 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Wed Sep 19 11:24:18 2007 -0700" }, "message": "Fix NUMA Memory Policy Reference Counting\n\nThis patch proposes fixes to the reference counting of memory policy in the\npage allocation paths and in show_numa_map(). Extracted from my \"Memory\nPolicy Cleanups and Enhancements\" series as stand-alone.\n\nShared policy lookup [shmem] has always added a reference to the policy,\nbut this was never unrefed after page allocation or after formatting the\nnuma map data.\n\nDefault system policy should not require additional ref counting, nor\nshould the current task\u0027s task policy. However, show_numa_map() calls\nget_vma_policy() to examine what may be [likely is] another task\u0027s policy.\nThe latter case needs protection against freeing of the policy.\n\nThis patch adds a reference count to a mempolicy returned by\nget_vma_policy() when the policy is a vma policy or another task\u0027s\nmempolicy. Again, shared policy is already reference counted on lookup. A\nmatching \"unref\" [__mpol_free()] is performed in alloc_page_vma() for\nshared and vma policies, and in show_numa_map() for shared and another\ntask\u0027s mempolicy. We can call __mpol_free() directly, saving an admittedly\ninexpensive inline NULL test, because we know we have a non-NULL policy.\n\nHandling policy ref counts for hugepages is a bit trickier.\nhuge_zonelist() returns a zone list that might come from a shared or vma\n\u0027BIND policy. In this case, we should hold the reference until after the\nhuge page allocation in dequeue_hugepage(). The patch modifies\nhuge_zonelist() to return a pointer to the mempolicy if it needs to be\nunref\u0027d after allocation.\n\nKernel Build [16cpu, 32GB, ia64] - average of 10 runs:\n\n\t\tw/o patch\tw/ refcount patch\n\t Avg\t Std Devn\t Avg\t Std Devn\nReal:\t 100.59\t 0.38\t 100.63\t 0.43\nUser:\t1209.60\t 0.37\t1209.91\t 0.31\nSystem: 81.52\t 0.42\t 81.64\t 0.34\n\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nAcked-by: Andi Kleen \u003cak@suse.de\u003e\nCc: Christoph Lameter \u003cclameter@sgi.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": "3b42d28b2a04b3c9830eb865288239d45eccc402", "tree": "776a297ef8bd8a879da74290543907014abe6198", "parents": [ "dec4ad86c2fbea062e9ef9caa6d6e79f7c5e0b12" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Fri Aug 31 00:12:08 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Fri Aug 31 01:42:23 2007 -0700" }, "message": "Page migration: Do not accept invalid nodes in the target nodeset\n\nPage migration currently does not check if the target of the move contains\nnodes that that are invalid (if root attempts to migrate pages)\nand may try to allocate from invalid nodes if these are specified\nleading to oopses.\n\nReturn -EINVAL if an offline node is specified.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: Shaohua Li \u003cshaohua.li@intel.com\u003e\nCc: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "b377fd3982ad957c796758a90e2988401a884241", "tree": "3d7449ccdf7038bffffa9323873f4095cc1ac6ce", "parents": [ "8e92f21ba3ea3f54e4be062b87ef9fc4af2d33e2" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Wed Aug 22 14:02:05 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Wed Aug 22 19:52:47 2007 -0700" }, "message": "Apply memory policies to top two highest zones when highest zone is ZONE_MOVABLE\n\nThe NUMA layer only supports NUMA policies for the highest zone. When\nZONE_MOVABLE is configured with kernelcore\u003d, the the highest zone becomes\nZONE_MOVABLE. The result is that policies are only applied to allocations\nlike anonymous pages and page cache allocated from ZONE_MOVABLE when the\nzone is used.\n\nThis patch applies policies to the two highest zones when the highest zone\nis ZONE_MOVABLE. As ZONE_MOVABLE consists of pages from the highest \"real\"\nzone, it\u0027s always functionally equivalent.\n\nThe patch has been tested on a variety of machines both NUMA and non-NUMA\ncovering x86, x86_64 and ppc64. No abnormal results were seen in\nkernbench, tbench, dbench or hackbench. It passes regression tests from\nthe numactl package with and without kernelcore\u003d once numactl tests are\npatched to wait for vmstat counters to update.\n\nakpm: this is the nasty hack to fix NUMA mempolicies in the presence of\nZONE_MOVABLE and kernelcore\u003d in 2.6.23. Christoph says \"For .24 either merge\nthe mobility or get the other solution that Mel is working on. That solution\nwould only use a single zonelist per node and filter on the fly. That may\nhelp performance and also help to make memory policies work better.\"\n\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nAcked-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nTested-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nAcked-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: Andi Kleen \u003cak@suse.de\u003e\nCc: Paul Mundt \u003clethal@linux-sh.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "20c2df83d25c6a95affe6157a4c9cac4cf5ffaac", "tree": "415c4453d2b17a50abe7a3e515177e1fa337bd67", "parents": [ "64fb98fc40738ae1a98bcea9ca3145b89fb71524" ], "author": { "name": "Paul Mundt", "email": "lethal@linux-sh.org", "time": "Fri Jul 20 10:11:58 2007 +0900" }, "committer": { "name": "Paul Mundt", "email": "lethal@linux-sh.org", "time": "Fri Jul 20 10:11:58 2007 +0900" }, "message": "mm: Remove slab destructors from kmem_cache_create().\n\nSlab destructors were no longer supported after Christoph\u0027s\nc59def9f222d44bb7e2f0a559f2906191a0862d7 change. They\u0027ve been\nBUGs for both slab and slub, and slob never supported them\neither.\n\nThis rips out support for the dtor pointer from kmem_cache_create()\ncompletely and fixes up every single callsite in the kernel (there were\nabout 224, not including the slab allocator definitions themselves,\nor the documentation references).\n\nSigned-off-by: Paul Mundt \u003clethal@linux-sh.org\u003e\n" }, { "commit": "396faf0303d273219db5d7eb4a2879ad977ed185", "tree": "96cb64fd6713ef7a924f4f878e259aea781f079a", "parents": [ "2a1e274acf0b1c192face19a4be7c12d4503eaaf" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Tue Jul 17 04:03:13 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Jul 17 10:22:59 2007 -0700" }, "message": "Allow huge page allocations to use GFP_HIGH_MOVABLE\n\nHuge pages are not movable so are not allocated from ZONE_MOVABLE. However,\nas ZONE_MOVABLE will always have pages that can be migrated or reclaimed, it\ncan be used to satisfy hugepage allocations even when the system has been\nrunning a long time. This allows an administrator to resize the hugepage pool\nat runtime depending on the size of ZONE_MOVABLE.\n\nThis patch adds a new sysctl called hugepages_treat_as_movable. When a\nnon-zero value is written to it, future allocations for the huge page pool\nwill use ZONE_MOVABLE. Despite huge pages being non-movable, we do not\nintroduce additional external fragmentation of note as huge pages are always\nthe largest contiguous block we care about.\n\n[akpm@linux-foundation.org: various fixes]\nSigned-off-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": "769848c03895b63e5662eb7e4ec8c4866f7d0183", "tree": "8911c7c312c8b8b172795fa2874c8162e1d3d15a", "parents": [ "a32ea1e1f925399e0d81ca3f7394a44a6dafa12c" ], "author": { "name": "Mel Gorman", "email": "mel@csn.ul.ie", "time": "Tue Jul 17 04:03:05 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Jul 17 10:22:59 2007 -0700" }, "message": "Add __GFP_MOVABLE for callers to flag allocations from high memory that may be migrated\n\nIt is often known at allocation time whether a page may be migrated or not.\nThis patch adds a flag called __GFP_MOVABLE and a new mask called\nGFP_HIGH_MOVABLE. Allocations using the __GFP_MOVABLE can be either migrated\nusing the page migration mechanism or reclaimed by syncing with backing\nstorage and discarding.\n\nAn API function very similar to alloc_zeroed_user_highpage() is added for\n__GFP_MOVABLE allocations called alloc_zeroed_user_highpage_movable(). The\nflags used by alloc_zeroed_user_highpage() are not changed because it would\nchange the semantics of an existing API. After this patch is applied there\nare no in-kernel users of alloc_zeroed_user_highpage() so it probably should\nbe marked deprecated if this patch is merged.\n\nNote that this patch includes a minor cleanup to the use of __GFP_ZERO in\nshmem.c to keep all flag modifications to inode-\u003emapping in the\nshmem_dir_alloc() helper function. This clean-up suggestion is courtesy of\nHugh Dickens.\n\nAdditional credit goes to Christoph Lameter and Linus Torvalds for shaping the\nconcept. Credit to Hugh Dickens for catching issues with shmem swap vector\nand ramfs allocations.\n\n[akpm@linux-foundation.org: build fix]\n[hugh@veritas.com: __GFP_ZERO cleanup]\nSigned-off-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: Andy Whitcroft \u003capw@shadowen.org\u003e\nCc: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "140d5a49046b6d73dce4a4229e88c000a99ee126", "tree": "64dcfe28ef6f5ccee5a2722e5c332c66ded29e28", "parents": [ "462e00cc7151ed91fba688594436c453c80efb5d" ], "author": { "name": "Paul Mundt", "email": "lethal@linux-sh.org", "time": "Sun Jul 15 23:38:16 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Mon Jul 16 09:05:36 2007 -0700" }, "message": "numa: mempolicy: trivial debug fixes.\n\nEnabling debugging fails to build due to the nodemask variable in\ndo_mbind() having changed names, and then oopses on boot due to the\nassumption that the nodemask can be dereferenced -- which doesn\u0027t work out\nso well when the policy is changed to MPOL_DEFAULT with a NULL nodemask by\nnuma_default_policy().\n\nThis fixes it up, and switches from PDprintk() to pr_debug() while\nwe\u0027re at it.\n\nSigned-off-by: Paul Mundt \u003clethal@linux-sh.org\u003e\nCc: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "b71636e29823c0602d908a2a62e94c9b57a97491", "tree": "d69a20eec2cc05bcd9b0dac2b9d4ccd9bad39e09", "parents": [ "f0630fff54a239efbbd89faf6a62da071ef1ff78" ], "author": { "name": "Paul Mundt", "email": "lethal@linux-sh.org", "time": "Sun Jul 15 23:38:15 2007 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Mon Jul 16 09:05:36 2007 -0700" }, "message": "numa: mempolicy: dynamic interleave map for system init\n\nThis converts the default system init memory policy to use a dynamically\ncreated node map instead of defaulting to all online nodes. Nodes of a\ncertain size (\u003e\u003d 16MB) are judged to be suitable for interleave, and are added\nto the map. If all nodes are smaller in size, the largest one is\nautomatically selected.\n\nWithout this, tiny nodes find themselves out of memory before we even make it\nto userspace. Systems with large nodes will notice no change.\n\nOnly the system init policy is effected by this change, the regular\nMPOL_DEFAULT policy is still switched to later on in the boot process as\nnormal.\n\nSigned-off-by: Paul Mundt \u003clethal@linux-sh.org\u003e\nCc: Andi Kleen \u003cak@suse.de\u003e\nCc: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: Hugh Dickins \u003chugh@veritas.com\u003e\nCc: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "0dc952dc3e6d96d554a19fa7bee3f3b1d55e3cff", "tree": "1dcf2ff93784716143b7acef816888a71a9504c2", "parents": [ "1f2b69f9bdce8461341e5fb864568a2ee90079c8" ], "author": { "name": "Christoph Lameter", "email": "clameter@engr.sgi.com", "time": "Mon Mar 05 00:30:33 2007 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Mon Mar 05 07:57:51 2007 -0800" }, "message": "[PATCH] Page migration: Fix vma flag checking\n\nCurrently we do not check for vma flags if sys_move_pages is called to move\nindividual pages. If sys_migrate_pages is called to move pages then we\ncheck for vm_flags that indicate a non migratable vma but that still\nincludes VM_LOCKED and we can migrate mlocked pages.\n\nExtract the vma_migratable check from mm/mempolicy.c, fix it and put it\ninto migrate.h so that is can be used from both locations.\n\nProblem was spotted by Lee Schermerhorn\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "8af5e2eb3cc4450ffba9496c875beac41bf4f4f8", "tree": "d15c56e8add1b53d5ed4d5dcb5d1f016d8f2b1c9", "parents": [ "b446b60e4eb5e5457120c4728ada871b1209c1d0" ], "author": { "name": "KAMEZAWA Hiroyuki", "email": "kamezawa.hiroyu@jp.fujitsu.com", "time": "Tue Feb 20 13:57:49 2007 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Feb 20 17:10:13 2007 -0800" }, "message": "[PATCH] fix mempolicy\u0027s check on a system with memory-less-node\n\nbind_zonelist() can create zero-length zonelist if there is a\nmemory-less-node. This patch checks the length of zonelist. If length is\n0, returns -EINVAL.\n\ntested on ia64/NUMA with memory-less-node.\n\nSigned-off-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nAcked-by: Andi Kleen \u003cak@suse.de\u003e\nCc: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "6267276f3fdda9ad0d5ca451bdcbdf42b802d64b", "tree": "fcc92bd645401a2c0f9e6a35b8e215868969db4d", "parents": [ "65e458d43dff872ee560e721fb0fdb367bb5adb0" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Sat Feb 10 01:43:07 2007 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Sun Feb 11 10:51:18 2007 -0800" }, "message": "[PATCH] optional ZONE_DMA: deal with cases of ZONE_DMA meaning the first zone\n\nThis patchset follows up on the earlier work in Andrew\u0027s tree to reduce the\nnumber of zones. The patches allow to go to a minimum of 2 zones. This one\nallows also to make ZONE_DMA optional and therefore the number of zones can be\nreduced to one.\n\nZONE_DMA is usually used for ISA DMA devices. There are a number of reasons\nwhy we would not want to have ZONE_DMA\n\n1. Some arches do not need ZONE_DMA at all.\n\n2. With the advent of IOMMUs DMA zones are no longer needed.\n The necessity of DMA zones may drastically be reduced\n in the future. This patchset allows a compilation of\n a kernel without that overhead.\n\n3. Devices that require ISA DMA get rare these days. All\n my systems do not have any need for ISA DMA.\n\n4. The presence of an additional zone unecessarily complicates\n VM operations because it must be scanned and balancing\n logic must operate on its.\n\n5. With only ZONE_NORMAL one can reach the situation where\n we have only one zone. This will allow the unrolling of many\n loops in the VM and allows the optimization of varous\n code paths in the VM.\n\n6. Having only a single zone in a NUMA system results in a\n 1-1 correspondence between nodes and zones. Various additional\n optimizations to critical VM paths become possible.\n\nMany systems today can operate just fine with a single zone. If you look at\nwhat is in ZONE_DMA then one usually sees that nothing uses it. The DMA slabs\nare empty (Some arches use ZONE_DMA instead of ZONE_NORMAL, then ZONE_NORMAL\nwill be empty instead).\n\nOn all of my systems (i386, x86_64, ia64) ZONE_DMA is completely empty. Why\nconstantly look at an empty zone in /proc/zoneinfo and empty slab in\n/proc/slabinfo? Non i386 also frequently have no need for ZONE_DMA and zones\nstay empty.\n\nThe patchset was tested on i386 (UP / SMP), x86_64 (UP, NUMA) and ia64 (NUMA).\n\nThe RFC posted earlier (see\nhttp://marc.theaimsgroup.com/?l\u003dlinux-kernel\u0026m\u003d115231723513008\u0026w\u003d2) had lots\nof #ifdefs in them. An effort has been made to minize the number of #ifdefs\nand make this as compact as possible. The job was made much easier by the\nongoing efforts of others to extract common arch specific functionality.\n\nI have been running this for awhile now on my desktop and finally Linux is\nusing all my available RAM instead of leaving the 16MB in ZONE_DMA untouched:\n\nchristoph@pentium940:~$ cat /proc/zoneinfo\nNode 0, zone Normal\n pages free 4435\n min 1448\n low 1810\n high 2172\n active 241786\n inactive 210170\n scanned 0 (a: 0 i: 0)\n spanned 524224\n present 524224\n nr_anon_pages 61680\n nr_mapped 14271\n nr_file_pages 390264\n nr_slab_reclaimable 27564\n nr_slab_unreclaimable 1793\n nr_page_table_pages 449\n nr_dirty 39\n nr_writeback 0\n nr_unstable 0\n nr_bounce 0\n cpu: 0 pcp: 0\n count: 156\n high: 186\n batch: 31\n cpu: 0 pcp: 1\n count: 9\n high: 62\n batch: 15\n vm stats threshold: 20\n cpu: 1 pcp: 0\n count: 177\n high: 186\n batch: 31\n cpu: 1 pcp: 1\n count: 12\n high: 62\n batch: 15\n vm stats threshold: 20\n all_unreclaimable: 0\n prev_priority: 12\n temp_priority: 12\n start_pfn: 0\n\nThis patch:\n\nIn two places in the VM we use ZONE_DMA to refer to the first zone. If\nZONE_DMA is optional then other zones may be first. So simply replace\nZONE_DMA with zone 0.\n\nThis also fixes ZONETABLE_PGSHIFT. If we have only a single zone then\nZONES_PGSHIFT may become 0 because there is no need anymore to encode the zone\nnumber related to a pgdat. However, we still need a zonetable to index all\nthe zones for each node if this is a NUMA system. Therefore define\nZONETABLE_SHIFT unconditionally as the offset of the ZONE field in page flags.\n\n[apw@shadowen.org: fix mismerge]\nAcked-by: Christoph Hellwig \u003chch@infradead.org\u003e\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: Andi Kleen \u003cak@suse.de\u003e\nCc: \"Luck, Tony\" \u003ctony.luck@intel.com\u003e\nCc: Kyle McMartin \u003ckyle@mcmartin.ca\u003e\nCc: Matthew Wilcox \u003cwilly@debian.org\u003e\nCc: James Bottomley \u003cJames.Bottomley@steeleye.com\u003e\nCc: Paul Mundt \u003clethal@linux-sh.org\u003e\nSigned-off-by: Andy Whitcroft \u003capw@shadowen.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "30150f8d7b76f25b1127a5079528b7a17307f995", "tree": "3ea69d5dbd7b131fc32bbf416ba9970079bd25c6", "parents": [ "79603a35009ff39562cd5634fa1cf513eb080f27" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Mon Jan 22 20:40:45 2007 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.linux-foundation.org", "time": "Tue Jan 23 07:52:06 2007 -0800" }, "message": "[PATCH] mbind: restrict nodes to the currently allowed cpuset\n\nCurrently one can specify an arbitrary node mask to mbind that includes\nnodes not allowed. If that is done with an interleave policy then we will\ngo around all the nodes. Those outside of the currently allowed cpuset\nwill be redirected to the border nodes. Interleave will then create\nimbalances at the borders of the cpuset.\n\nThis patch restricts the nodes to the currently allowed cpuset.\n\nThe RFC for this patch was discussed at\nhttp://marc.theaimsgroup.com/?t\u003d116793842100004\u0026r\u003d1\u0026w\u003d2\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nCc: Paul Jackson \u003cpj@sgi.com\u003e\nCc: Andi Kleen \u003cak@suse.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "e9536ae7205d255bc94616b72910fc6e16c861fe", "tree": "4c91e2fbe096958ab8f7476306c4a61c30cbe502", "parents": [ "1b04fe9a8ef10774174897b15d753b9de85fe9e9" ], "author": { "name": "Josef Sipek", "email": "jsipek@fsl.cs.sunysb.edu", "time": "Fri Dec 08 02:37:21 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.osdl.org", "time": "Fri Dec 08 08:28:47 2006 -0800" }, "message": "[PATCH] struct path: convert mm\n\nSigned-off-by: Josef Sipek \u003cjsipek@fsl.cs.sunysb.edu\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "15ad7cdcfd76450d4beebc789ec646664238184d", "tree": "279d05a76ae0906c23ee2de8c5684d95d9886ad3", "parents": [ "4a08a9f68168e547c2baf100020e9b96cae5fbd1" ], "author": { "name": "Helge Deller", "email": "deller@gmx.de", "time": "Wed Dec 06 20:40:36 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.osdl.org", "time": "Thu Dec 07 08:39:46 2006 -0800" }, "message": "[PATCH] struct seq_operations and struct file_operations constification\n\n - move some file_operations structs into the .rodata section\n\n - move static strings from policy_types[] array into the .rodata section\n\n - fix generic seq_operations usages, so that those structs may be defined\n as \"const\" as well\n\n[akpm@osdl.org: couple of fixes]\nSigned-off-by: Helge Deller \u003cdeller@gmx.de\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "e94b1766097d53e6f3ccfb36c8baa562ffeda3fc", "tree": "93fa0a8ab84976d4e89c50768ca8b8878d642a0d", "parents": [ "54e6ecb23951b195d02433a741c7f7cb0b796c78" ], "author": { "name": "Christoph Lameter", "email": "clameter@sgi.com", "time": "Wed Dec 06 20:33:17 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.osdl.org", "time": "Thu Dec 07 08:39:24 2006 -0800" }, "message": "[PATCH] slab: remove SLAB_KERNEL\n\nSLAB_KERNEL is an alias of GFP_KERNEL.\n\nSigned-off-by: Christoph Lameter \u003cclameter@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" }, { "commit": "25ba77c141dbcd2602dd0171824d0d72aa023a01", "tree": "153eb9bc567f63d739dcaf8a3caf11c8f48b8379", "parents": [ "bc4ba393c007248f76c05945abb7b7b892cdd1cc" ], "author": { "name": "Andy Whitcroft", "email": "apw@shadowen.org", "time": "Wed Dec 06 20:33:03 2006 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@woody.osdl.org", "time": "Thu Dec 07 08:39:23 2006 -0800" }, "message": "[PATCH] numa node ids are int, page_to_nid and zone_to_nid should return int\n\nNUMA node ids are passed as either int or unsigned int almost exclusivly\npage_to_nid and zone_to_nid both return unsigned long. This is a throw\nback to when page_to_nid was a #define and was thus exposing the real type\nof the page flags field.\n\nIn addition to fixing up the definitions of page_to_nid and zone_to_nid I\naudited the users of these functions identifying the following incorrect\nuses:\n\n1) mm/page_alloc.c show_node() -- printk dumping the node id,\n2) include/asm-ia64/pgalloc.h pgtable_quicklist_free() -- comparison\n against numa_node_id() which returns an int from cpu_to_node(), and\n3) mm/mpolicy.c check_pte_range -- used as an index in node_isset which\n uses bit_set which in generic code takes an int.\n\nSigned-off-by: Andy Whitcroft \u003capw@shadowen.org\u003e\nCc: Christoph Lameter \u003cclameter@engr.sgi.com\u003e\nCc: \"Luck, Tony\" \u003ctony.luck@intel.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@osdl.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@osdl.org\u003e\n" } ], "next": "9276b1bc96a132f4068fdee00983c532f43d3a26" }