)]}' { "log": [ { "commit": "72fa59970f8698023045ab0713d66f3f4f96945c", "tree": "ed9a5eaf8212270d464c6d4396ae5a568352a997", "parents": [ "1d229d54dbc26971142f61c3d271a68db236d178" ], "author": { "name": "Vasiliy Kulikov", "email": "segoon@openwall.com", "time": "Mon Aug 08 19:02:04 2011 +0400" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Aug 11 11:24:42 2011 -0700" }, "message": "move RLIMIT_NPROC check from set_user() to do_execve_common()\n\nThe patch http://lkml.org/lkml/2003/7/13/226 introduced an RLIMIT_NPROC\ncheck in set_user() to check for NPROC exceeding via setuid() and\nsimilar functions.\n\nBefore the check there was a possibility to greatly exceed the allowed\nnumber of processes by an unprivileged user if the program relied on\nrlimit only. But the check created new security threat: many poorly\nwritten programs simply don\u0027t check setuid() return code and believe it\ncannot fail if executed with root privileges. So, the check is removed\nin this patch because of too often privilege escalations related to\nbuggy programs.\n\nThe NPROC can still be enforced in the common code flow of daemons\nspawning user processes. Most of daemons do fork()+setuid()+execve().\nThe check introduced in execve() (1) enforces the same limit as in\nsetuid() and (2) doesn\u0027t create similar security issues.\n\nNeil Brown suggested to track what specific process has exceeded the\nlimit by setting PF_NPROC_EXCEEDED process flag. With the change only\nthis process would fail on execve(), and other processes\u0027 execve()\nbehaviour is not changed.\n\nSolar Designer suggested to re-check whether NPROC limit is still\nexceeded at the moment of execve(). If the process was sleeping for\ndays between set*uid() and execve(), and the NPROC counter step down\nunder the limit, the defered execve() failure because NPROC limit was\nexceeded days ago would be unexpected. If the limit is not exceeded\nanymore, we clear the flag on successful calls to execve() and fork().\n\nThe flag is also cleared on successful calls to set_user() as the limit\nwas exceeded for the previous user, not the current one.\n\nSimilar check was introduced in -ow patches (without the process flag).\n\nv3 - clear PF_NPROC_EXCEEDED on successful calls to set_user().\n\nReviewed-by: James Morris \u003cjmorris@namei.org\u003e\nSigned-off-by: Vasiliy Kulikov \u003csegoon@openwall.com\u003e\nAcked-by: NeilBrown \u003cneilb@suse.de\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "fb0a685cb95a0267a96153af2f72486f27be5847", "tree": "99ffae5ab7733ce8a1819fec51ca137a3af48d37", "parents": [ "293eb1e7772b25a93647c798c7b89bf26c2da2e0" ], "author": { "name": "Daniel Rebelo de Oliveira", "email": "psykon@gmail.com", "time": "Tue Jul 26 16:08:39 2011 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Jul 26 16:49:44 2011 -0700" }, "message": "kernel/fork.c: fix a few coding style issues\n\nSigned-off-by: Daniel Rebelo de Oliveira \u003cpsykon@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": "778d3b0ff0654ad7092bf823fd32010066b12365", "tree": "cd0073d8c513e1c56fd6950c4ec985f16fd004ad", "parents": [ "8521fc50d433507a7cdc96bec280f9e5888a54cc" ], "author": { "name": "Michal Hocko", "email": "mhocko@suse.cz", "time": "Tue Jul 26 16:08:30 2011 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Jul 26 16:49:43 2011 -0700" }, "message": "cpusets: randomize node rotor used in cpuset_mem_spread_node()\n\n[ This patch has already been accepted as commit 0ac0c0d0f837 but later\n reverted (commit 35926ff5fba8) because it itroduced arch specific\n __node_random which was defined only for x86 code so it broke other\n archs. This is a followup without any arch specific code. Other than\n that there are no functional changes.]\n\nSome workloads that create a large number of small files tend to assign\ntoo many pages to node 0 (multi-node systems). Part of the reason is\nthat the rotor (in cpuset_mem_spread_node()) used to assign nodes starts\nat node 0 for newly created tasks.\n\nThis patch changes the rotor to be initialized to a random node number\nof the cpuset.\n\n[akpm@linux-foundation.org: fix layout]\n[Lee.Schermerhorn@hp.com: Define stub numa_random() for !NUMA configuration]\n[mhocko@suse.cz: Make it arch independent]\n[akpm@linux-foundation.org: fix CONFIG_NUMA\u003dy, MAX_NUMNODES\u003e1 build]\nSigned-off-by: Jack Steiner \u003csteiner@sgi.com\u003e\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nSigned-off-by: Michal Hocko \u003cmhocko@suse.cz\u003e\nReviewed-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: Pekka Enberg \u003cpenberg@cs.helsinki.fi\u003e\nCc: Paul Menage \u003cmenage@google.com\u003e\nCc: Jack Steiner \u003csteiner@sgi.com\u003e\nCc: Robin Holt \u003cholt@sgi.com\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nCc: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nCc: Jack Steiner \u003csteiner@sgi.com\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Michal Hocko \u003cmhocko@suse.cz\u003e\nCc: Paul Menage \u003cmenage@google.com\u003e\nCc: Pekka Enberg \u003cpenberg@cs.helsinki.fi\u003e\nCc: Robin Holt \u003cholt@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "096a705bbc080a4041636d07514560da8d78acbe", "tree": "38c3c01225709ffa53419083ea6332f8a72610de", "parents": [ "fea80311a939a746533a6d7e7c3183729d6a3faf", "5757a6d76cdf6dda2a492c09b985c015e86779b1" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Jul 25 10:33:36 2011 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Jul 25 10:33:36 2011 -0700" }, "message": "Merge branch \u0027for-3.1/core\u0027 of git://git.kernel.dk/linux-block\n\n* \u0027for-3.1/core\u0027 of git://git.kernel.dk/linux-block: (24 commits)\n block: strict rq_affinity\n backing-dev: use synchronize_rcu_expedited instead of synchronize_rcu\n block: fix patch import error in max_discard_sectors check\n block: reorder request_queue to remove 64 bit alignment padding\n CFQ: add think time check for group\n CFQ: add think time check for service tree\n CFQ: move think time check variables to a separate struct\n fixlet: Remove fs_excl from struct task.\n cfq: Remove special treatment for metadata rqs.\n block: document blk_plug list access\n block: avoid building too big plug list\n compat_ioctl: fix make headers_check regression\n block: eliminate potential for infinite loop in blkdev_issue_discard\n compat_ioctl: fix warning caused by qemu\n block: flush MEDIA_CHANGE from drivers on close(2)\n blk-throttle: Make total_nr_queued unsigned\n block: Add __attribute__((format(printf...) and fix fallout\n fs/partitions/check.c: make local symbols static\n block:remove some spare spaces in genhd.c\n block:fix the comment error in blkdev.h\n ...\n" }, { "commit": "bbd9d6f7fbb0305c9a592bf05a32e87eb364a4ff", "tree": "12b2bb4202b05f6ae6a43c6ce830a0472043dbe5", "parents": [ "8e204874db000928e37199c2db82b7eb8966cc3c", "5a9a43646cf709312d71eca71cef90ad802f28f9" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Jul 22 19:02:39 2011 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Jul 22 19:02:39 2011 -0700" }, "message": "Merge branch \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6\n\n* \u0027for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs-2.6: (107 commits)\n vfs: use ERR_CAST for err-ptr tossing in lookup_instantiate_filp\n isofs: Remove global fs lock\n jffs2: fix IN_DELETE_SELF on overwriting rename() killing a directory\n fix IN_DELETE_SELF on overwriting rename() on ramfs et.al.\n mm/truncate.c: fix build for CONFIG_BLOCK not enabled\n fs:update the NOTE of the file_operations structure\n Remove dead code in dget_parent()\n AFS: Fix silly characters in a comment\n switch d_add_ci() to d_splice_alias() in \"found negative\" case as well\n simplify gfs2_lookup()\n jfs_lookup(): don\u0027t bother with . or ..\n get rid of useless dget_parent() in btrfs rename() and link()\n get rid of useless dget_parent() in fs/btrfs/ioctl.c\n fs: push i_mutex and filemap_write_and_wait down into -\u003efsync() handlers\n drivers: fix up various -\u003ellseek() implementations\n fs: handle SEEK_HOLE/SEEK_DATA properly in all fs\u0027s that define their own llseek\n Ext4: handle SEEK_HOLE/SEEK_DATA generically\n Btrfs: implement our own -\u003ellseek\n fs: add SEEK_HOLE and SEEK_DATA flags\n reiserfs: make reiserfs default to barrier\u003dflush\n ...\n\nFix up trivial conflicts in fs/xfs/linux-2.6/xfs_super.c due to the new\nshrinker callout for the inode cache, that clashed with the xfs code to\nstart the periodic workers later.\n" }, { "commit": "75b56ec294b074d70f8a676ab02611a3fea76cab", "tree": "d5299adb43ac6fc8dcc50c3e438c7f0cdd452b1c", "parents": [ "6d16d6d9bb6f93e6f8506cfb3e91795d6443d54f", "efbe2eee6dc0f179be84292bf269528b3ec365e9" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Jul 22 16:43:21 2011 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Jul 22 16:43:21 2011 -0700" }, "message": "Merge branch \u0027core-locking-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip\n\n* \u0027core-locking-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:\n lockdep: Fix lockdep_no_validate against IRQ states\n mutex: Make mutex_destroy() an inline function\n plist: Remove the need to supply locks to plist heads\n lockup detector: Fix reference to the non-existent CONFIG_DETECT_SOFTLOCKUP option\n" }, { "commit": "6657719390cd05be45f4e3b501d8bb46889c0a19", "tree": "8d2d97f645b05badd134526659f5d9adc7ab9234", "parents": [ "1ba106818615faddb63ba782f85f3498b9eb61c6" ], "author": { "name": "Al Viro", "email": "viro@zeniv.linux.org.uk", "time": "Tue Jun 28 15:41:10 2011 -0400" }, "committer": { "name": "Al Viro", "email": "viro@zeniv.linux.org.uk", "time": "Wed Jul 20 01:44:07 2011 -0400" }, "message": "make sure that nsproxy_cache is initialized early enough\n\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n" }, { "commit": "dcace06cc29df927a74a6bc0e57b9bef87704377", "tree": "9a04518032869b1ed79933026379ea0d7081e43a", "parents": [ "6634ae1033ceaeca5877dd75723210f8c2648c17" ], "author": { "name": "Oleg Nesterov", "email": "oleg@redhat.com", "time": "Fri Jul 08 19:13:54 2011 +0200" }, "committer": { "name": "Oleg Nesterov", "email": "oleg@redhat.com", "time": "Sun Jul 17 20:23:51 2011 +0200" }, "message": "ptrace: mv send-SIGSTOP from do_fork() to ptrace_init_task()\n\nIf the new child is traced, do_fork() adds the pending SIGSTOP.\nIt assumes that either it is traced because of auto-attach or the\ntracer attached later, in both cases sigaddset/set_thread_flag is\ncorrect even if SIGSTOP is already pending.\n\nNow that we have PTRACE_SEIZE this is no longer right in the latter\ncase. If the tracer does PTRACE_SEIZE after copy_process() makes the\nchild visible the queued SIGSTOP is wrong.\n\nWe could check PT_SEIZED bit and change ptrace_attach() to set both\nPT_PTRACED and PT_SEIZED bits simultaneously but see the next patch,\nwe need to know whether this child was auto-attached or not anyway.\n\nSo this patch simply moves this code to ptrace_init_task(), this\nway we can never race with ptrace_attach().\n\nSigned-off-by: Oleg Nesterov \u003coleg@redhat.com\u003e\nAcked-by: Tejun Heo \u003ctj@kernel.org\u003e\n" }, { "commit": "4aede84b33d6beb401136a3deca0651ae07c5e99", "tree": "831266dbb15227584da5011ae4bb1e5038a69677", "parents": [ "a07405b7802691d29ab3b23bdc76ee6d006aad0b" ], "author": { "name": "Justin TerAvest", "email": "teravest@google.com", "time": "Tue Jul 12 08:31:45 2011 +0200" }, "committer": { "name": "Jens Axboe", "email": "jaxboe@fusionio.com", "time": "Tue Jul 12 08:35:10 2011 +0200" }, "message": "fixlet: Remove fs_excl from struct task.\n\nfs_excl is a poor man\u0027s priority inheritance for filesystems to hint to\nthe block layer that an operation is important. It was never clearly\nspecified, not widely adopted, and will not prevent starvation in many\ncases (like across cgroups).\n\nfs_excl was introduced with the time sliced CFQ IO scheduler, to\nindicate when a process held FS exclusive resources and thus needed\na boost.\n\nIt doesn\u0027t cover all file systems, and it was never fully complete.\nLets kill it.\n\nSigned-off-by: Justin TerAvest \u003cteravest@google.com\u003e\nSigned-off-by: Jens Axboe \u003cjaxboe@fusionio.com\u003e\n" }, { "commit": "732375c6a5a4cc825b676c922d547aba96b8ce15", "tree": "35002255d0e52ad478ffa7134b73c35452c502a0", "parents": [ "8edbb83e5bc3c7d5d76861fc61872105288d2610" ], "author": { "name": "Dima Zavin", "email": "dima@android.com", "time": "Thu Jul 07 17:27:59 2011 -0700" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Jul 08 14:02:53 2011 +0200" }, "message": "plist: Remove the need to supply locks to plist heads\n\nThis was legacy code brought over from the RT tree and\nis no longer necessary.\n\nSigned-off-by: Dima Zavin \u003cdima@android.com\u003e\nAcked-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nCc: Daniel Walker \u003cdwalker@codeaurora.org\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Andi Kleen \u003candi@firstfloor.org\u003e\nCc: Lai Jiangshan \u003claijs@cn.fujitsu.com\u003e\nLink: http://lkml.kernel.org/r/1310084879-10351-2-git-send-email-dima@android.com\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "4b9d33e6d83cc05a8005a8f9a8b9677fa0f53626", "tree": "250b740d22f9604326ecfd769dd2f74d60187a19", "parents": [ "a288eecce5253cc1565d400a52b9b476a157e040" ], "author": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Fri Jun 17 16:50:38 2011 +0200" }, "committer": { "name": "Oleg Nesterov", "email": "oleg@redhat.com", "time": "Wed Jun 22 19:26:29 2011 +0200" }, "message": "ptrace: kill clone/exec tracehooks\n\nAt this point, tracehooks aren\u0027t useful to mainline kernel and mostly\njust add an extra layer of obfuscation. Although they have comments,\nwithout actual in-kernel users, it is difficult to tell what are their\nassumptions and they\u0027re actually trying to achieve. To mainline\nkernel, they just aren\u0027t worth keeping around.\n\nThis patch kills the following clone and exec related tracehooks.\n\n\ttracehook_prepare_clone()\n\ttracehook_finish_clone()\n\ttracehook_report_clone()\n\ttracehook_report_clone_complete()\n\ttracehook_unsafe_exec()\n\nThe changes are mostly trivial - logic is moved to the caller and\ncomments are merged and adjusted appropriately.\n\nThe only exception is in check_unsafe_exec() where LSM_UNSAFE_PTRACE*\nare OR\u0027d to bprm-\u003eunsafe instead of setting it, which produces the\nsame result as the field is always zero on entry. It also tests\np-\u003eptrace instead of (p-\u003eptrace \u0026 PT_PTRACED) for consistency, which\nalso gives the same result.\n\nThis doesn\u0027t introduce any behavior change.\n\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\nCc: Christoph Hellwig \u003chch@infradead.org\u003e\nSigned-off-by: Oleg Nesterov \u003coleg@redhat.com\u003e\n" }, { "commit": "a288eecce5253cc1565d400a52b9b476a157e040", "tree": "a933dd8c9791be83b7a67a33502c79e7b441960e", "parents": [ "f3c04b934d429b1ace21866f011b66de328c0dc9" ], "author": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Fri Jun 17 16:50:37 2011 +0200" }, "committer": { "name": "Oleg Nesterov", "email": "oleg@redhat.com", "time": "Wed Jun 22 19:26:28 2011 +0200" }, "message": "ptrace: kill trivial tracehooks\n\nAt this point, tracehooks aren\u0027t useful to mainline kernel and mostly\njust add an extra layer of obfuscation. Although they have comments,\nwithout actual in-kernel users, it is difficult to tell what are their\nassumptions and they\u0027re actually trying to achieve. To mainline\nkernel, they just aren\u0027t worth keeping around.\n\nThis patch kills the following trivial tracehooks.\n\n* Ones testing whether task is ptraced. Replace with -\u003eptrace test.\n\n\ttracehook_expect_breakpoints()\n\ttracehook_consider_ignored_signal()\n\ttracehook_consider_fatal_signal()\n\n* ptrace_event() wrappers. Call directly.\n\n\ttracehook_report_exec()\n\ttracehook_report_exit()\n\ttracehook_report_vfork_done()\n\n* ptrace_release_task() wrapper. Call directly.\n\n\ttracehook_finish_release_task()\n\n* noop\n\n\ttracehook_prepare_release_task()\n\ttracehook_report_death()\n\nThis doesn\u0027t introduce any behavior change.\n\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\nCc: Christoph Hellwig \u003chch@infradead.org\u003e\nCc: Martin Schwidefsky \u003cschwidefsky@de.ibm.com\u003e\nSigned-off-by: Oleg Nesterov \u003coleg@redhat.com\u003e\n" }, { "commit": "6345d24daf0c1fffe6642081d783cdf653ebaa5c", "tree": "415a253621279111bd481d48cbb86174c70b952a", "parents": [ "cab0d85c8dfcad4d799f9c294571440c6f1db091" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sun May 29 11:32:28 2011 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sun May 29 11:32:28 2011 -0700" }, "message": "mm: Fix boot crash in mm_alloc()\n\nThomas Gleixner reports that we now have a boot crash triggered by\nCONFIG_CPUMASK_OFFSTACK\u003dy:\n\n BUG: unable to handle kernel NULL pointer dereference at (null)\n IP: [\u003cc11ae035\u003e] find_next_bit+0x55/0xb0\n Call Trace:\n [\u003cc11addda\u003e] cpumask_any_but+0x2a/0x70\n [\u003cc102396b\u003e] flush_tlb_mm+0x2b/0x80\n [\u003cc1022705\u003e] pud_populate+0x35/0x50\n [\u003cc10227ba\u003e] pgd_alloc+0x9a/0xf0\n [\u003cc103a3fc\u003e] mm_init+0xec/0x120\n [\u003cc103a7a3\u003e] mm_alloc+0x53/0xd0\n\nwhich was introduced by commit de03c72cfce5 (\"mm: convert\nmm-\u003ecpu_vm_cpumask into cpumask_var_t\"), and is due to wrong ordering of\nmm_init() vs mm_init_cpumask\n\nThomas wrote a patch to just fix the ordering of initialization, but I\nhate the new double allocation in the fork path, so I ended up instead\ndoing some more radical surgery to clean it all up.\n\nReported-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nReported-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "3864601387cf4196371e3c1897fdffa5228296f9", "tree": "1c517a970194f9e49ef98ef434c650771ffa31e1", "parents": [ "63ab25ebbc50f74550bd8d164a34724b498f6fb9" ], "author": { "name": "Jiri Slaby", "email": "jslaby@suse.cz", "time": "Thu May 26 16:25:46 2011 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu May 26 17:12:36 2011 -0700" }, "message": "mm: extract exe_file handling from procfs\n\nSetup and cleanup of mm_struct-\u003eexe_file is currently done in fs/proc/.\nThis was because exe_file was needed only for /proc/\u003cpid\u003e/exe. Since we\nwill need the exe_file functionality also for core dumps (so core name can\ncontain full binary path), built this functionality always into the\nkernel.\n\nTo achieve that move that out of proc FS to the kernel/ where in fact it\nshould belong. By doing that we can make dup_mm_exe_file static. Also we\ncan drop linux/proc_fs.h inclusion in fs/exec.c and kernel/fork.c.\n\nSigned-off-by: Jiri Slaby \u003cjslaby@suse.cz\u003e\nCc: Alexander Viro \u003cviro@zeniv.linux.org.uk\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "a77aea92010acf54ad785047234418d5d68772e2", "tree": "c7cb57b62fd02bee2baceb79251923f7caec6139", "parents": [ "d846687d7f84e45f23ecf3846dbb43312a1206dd" ], "author": { "name": "Daniel Lezcano", "email": "daniel.lezcano@free.fr", "time": "Thu May 26 16:25:23 2011 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu May 26 17:12:34 2011 -0700" }, "message": "cgroup: remove the ns_cgroup\n\nThe ns_cgroup is an annoying cgroup at the namespace / cgroup frontier and\nleads to some problems:\n\n * cgroup creation is out-of-control\n * cgroup name can conflict when pids are looping\n * it is not possible to have a single process handling a lot of\n namespaces without falling in a exponential creation time\n * we may want to create a namespace without creating a cgroup\n\n The ns_cgroup was replaced by a compatibility flag \u0027clone_children\u0027,\n where a newly created cgroup will copy the parent cgroup values.\n The userspace has to manually create a cgroup and add a task to\n the \u0027tasks\u0027 file.\n\nThis patch removes the ns_cgroup as suggested in the following thread:\n\nhttps://lists.linux-foundation.org/pipermail/containers/2009-June/018616.html\n\nThe \u0027cgroup_clone\u0027 function is removed because it is no longer used.\n\nThis is a userspace-visible change. Commit 45531757b45c (\"cgroup: notify\nns_cgroup deprecated\") (merged into 2.6.27) caused the kernel to emit a\nprintk warning users that the feature is planned for removal. Since that\ntime we have heard from XXX users who were affected by this.\n\nSigned-off-by: Daniel Lezcano \u003cdaniel.lezcano@free.fr\u003e\nSigned-off-by: Serge E. Hallyn \u003cserge.hallyn@canonical.com\u003e\nCc: Eric W. Biederman \u003cebiederm@xmission.com\u003e\nCc: Jamal Hadi Salim \u003chadi@cyberus.ca\u003e\nReviewed-by: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nAcked-by: Paul Menage \u003cmenage@google.com\u003e\nAcked-by: Matt Helsley \u003cmatthltc@us.ibm.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "4714d1d32d97239fb5ae3e10521d3f133a899b66", "tree": "fb50707cefc386bf4e87cac9661a38dcfe3192df", "parents": [ "dcb3a08e69629ea65a3e9647da730bfaf670497d" ], "author": { "name": "Ben Blum", "email": "bblum@andrew.cmu.edu", "time": "Thu May 26 16:25:18 2011 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu May 26 17:12:34 2011 -0700" }, "message": "cgroups: read-write lock CLONE_THREAD forking per threadgroup\n\nAdds functionality to read/write lock CLONE_THREAD fork()ing per-threadgroup\n\nAdd an rwsem that lives in a threadgroup\u0027s signal_struct that\u0027s taken for\nreading in the fork path, under CONFIG_CGROUPS. If another part of the\nkernel later wants to use such a locking mechanism, the CONFIG_CGROUPS\nifdefs should be changed to a higher-up flag that CGROUPS and the other\nsystem would both depend on.\n\nThis is a pre-patch for cgroup-procs-write.patch.\n\nSigned-off-by: Ben Blum \u003cbblum@andrew.cmu.edu\u003e\nCc: \"Eric W. Biederman\" \u003cebiederm@xmission.com\u003e\nCc: Li Zefan \u003clizf@cn.fujitsu.com\u003e\nCc: Matt Helsley \u003cmatthltc@us.ibm.com\u003e\nReviewed-by: Paul Menage \u003cmenage@google.com\u003e\nCc: Oleg Nesterov \u003coleg@redhat.com\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nCc: Miao Xie \u003cmiaox@cn.fujitsu.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "de03c72cfce5b263a674d04348b58475ec50163c", "tree": "e2b035234440bcd1aa88078c3f9c8457d461ef9c", "parents": [ "692e0b35427a088bf75d9363788c61c7edbe93a5" ], "author": { "name": "KOSAKI Motohiro", "email": "kosaki.motohiro@jp.fujitsu.com", "time": "Tue May 24 17:12:15 2011 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed May 25 08:39:21 2011 -0700" }, "message": "mm: convert mm-\u003ecpu_vm_cpumask into cpumask_var_t\n\ncpumask_t is very big struct and cpu_vm_mask is placed wrong position.\nIt might lead to reduce cache hit ratio.\n\nThis patch has two change.\n1) Move the place of cpumask into last of mm_struct. Because usually cpumask\n is accessed only front bits when the system has cpu-hotplug capability\n2) Convert cpu_vm_mask into cpumask_var_t. It may help to reduce memory\n footprint if cpumask_size() will use nr_cpumask_bits properly in future.\n\nIn addition, this patch change the name of cpu_vm_mask with cpu_vm_mask_var.\nIt may help to detect out of tree cpu_vm_mask users.\n\nThis patch has no functional change.\n\n[akpm@linux-foundation.org: build fix]\n[akpm@linux-foundation.org: coding-style fixes]\nSigned-off-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: David Howells \u003cdhowells@redhat.com\u003e\nCc: Koichi Yasutake \u003cyasutake.koichi@jp.panasonic.com\u003e\nCc: Hugh Dickins \u003chughd@google.com\u003e\nCc: Chris Metcalf \u003ccmetcalf@tilera.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "3d48ae45e72390ddf8cc5256ac32ed6f7a19cbea", "tree": "1f46db3a8424090dd8e0b58991fa5acc1a73e680", "parents": [ "97a894136f29802da19a15541de3c019e1ca147e" ], "author": { "name": "Peter Zijlstra", "email": "a.p.zijlstra@chello.nl", "time": "Tue May 24 17:12:06 2011 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed May 25 08:39:18 2011 -0700" }, "message": "mm: Convert i_mmap_lock to a mutex\n\nStraightforward conversion of i_mmap_lock to a mutex.\n\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nAcked-by: Hugh Dickins \u003chughd@google.com\u003e\nCc: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nCc: David Miller \u003cdavem@davemloft.net\u003e\nCc: Martin Schwidefsky \u003cschwidefsky@de.ibm.com\u003e\nCc: Russell King \u003crmk@arm.linux.org.uk\u003e\nCc: Paul Mundt \u003clethal@linux-sh.org\u003e\nCc: Jeff Dike \u003cjdike@addtoit.com\u003e\nCc: Richard Weinberger \u003crichard@nod.at\u003e\nCc: Tony Luck \u003ctony.luck@intel.com\u003e\nCc: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Nick Piggin \u003cnpiggin@kernel.dk\u003e\nCc: Namhyung Kim \u003cnamhyung@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": "97a894136f29802da19a15541de3c019e1ca147e", "tree": "1fd3f92ba92a37d5d8527a1f41458091d0a944dc", "parents": [ "e4c70a6629f9c74c4b0de258a3951890e9047c82" ], "author": { "name": "Peter Zijlstra", "email": "a.p.zijlstra@chello.nl", "time": "Tue May 24 17:12:04 2011 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed May 25 08:39:17 2011 -0700" }, "message": "mm: Remove i_mmap_lock lockbreak\n\nHugh says:\n \"The only significant loser, I think, would be page reclaim (when\n concurrent with truncation): could spin for a long time waiting for\n the i_mmap_mutex it expects would soon be dropped? \"\n\nCounter points:\n - cpu contention makes the spin stop (need_resched())\n - zap pages should be freeing pages at a higher rate than reclaim\n ever can\n\nI think the simplification of the truncate code is definitely worth it.\n\nEffectively reverts: 2aa15890f3c (\"mm: prevent concurrent\nunmap_mapping_range() on the same inode\") and takes out the code that\ncaused its problem.\n\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nReviewed-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Hugh Dickins \u003chughd@google.com\u003e\nCc: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nCc: David Miller \u003cdavem@davemloft.net\u003e\nCc: Martin Schwidefsky \u003cschwidefsky@de.ibm.com\u003e\nCc: Russell King \u003crmk@arm.linux.org.uk\u003e\nCc: Paul Mundt \u003clethal@linux-sh.org\u003e\nCc: Jeff Dike \u003cjdike@addtoit.com\u003e\nCc: Richard Weinberger \u003crichard@nod.at\u003e\nCc: Tony Luck \u003ctony.luck@intel.com\u003e\nCc: Mel Gorman \u003cmel@csn.ul.ie\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Nick Piggin \u003cnpiggin@kernel.dk\u003e\nCc: Namhyung Kim \u003cnamhyung@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": "3e51e3edfd81bfd9853ad7de91167e4ce33d0fe7", "tree": "777d871949911f3e79a5b94545a7b6a55bdc2259", "parents": [ "9cb5baba5e3acba0994ad899ee908799104c9965" ], "author": { "name": "Samir Bellabes", "email": "sam@synack.fr", "time": "Wed May 11 18:18:05 2011 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu May 12 09:36:37 2011 +0200" }, "message": "sched: Remove unused parameters from sched_fork() and wake_up_new_task()\n\nsched_fork() and wake_up_new_task() are defined with a parameter\n\u0027unsigned long clone_flags\u0027, which is unused.\n\nThis patch removes the parameters.\n\nSigned-off-by: Samir Bellabes \u003csam@synack.fr\u003e\nAcked-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nLink: http://lkml.kernel.org/r/1305130685-1047-1-git-send-email-sam@synack.fr\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "625f2a378e5a10f45fdc37932fc9f8a21676de9e", "tree": "1bf966a8e65463cdcc313c559533f032657c9dcf", "parents": [ "d3bf52e998056a6002b2aecfe1d25486376382ac" ], "author": { "name": "Jonathan Corbet", "email": "corbet@lwn.net", "time": "Fri Apr 22 11:19:10 2011 -0600" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sun Apr 24 13:18:38 2011 +0200" }, "message": "sched: Get rid of lock_depth\n\nNeil Brown pointed out that lock_depth somehow escaped the BKL\nremoval work. Let\u0027s get rid of it now.\n\nNote that the perf scripting utilities still have a bunch of\ncode for dealing with common_lock_depth in tracepoints; I have\nleft that in place in case anybody wants to use that code with\nolder kernels.\n\nSuggested-by: Neil Brown \u003cneilb@suse.de\u003e\nSigned-off-by: Jonathan Corbet \u003ccorbet@lwn.net\u003e\nCc: Arnd Bergmann \u003carnd@arndb.de\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nCc: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\nCc: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nLink: http://lkml.kernel.org/r/20110422111910.456c0e84@bike.lwn.net\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "6c5103890057b1bb781b26b7aae38d33e4c517d8", "tree": "e6e57961dcddcb5841acb34956e70b9dc696a880", "parents": [ "3dab04e6978e358ad2307bca563fabd6c5d2c58b", "9d2e157d970a73b3f270b631828e03eb452d525e" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Mar 24 10:16:26 2011 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Mar 24 10:16:26 2011 -0700" }, "message": "Merge branch \u0027for-2.6.39/core\u0027 of git://git.kernel.dk/linux-2.6-block\n\n* \u0027for-2.6.39/core\u0027 of git://git.kernel.dk/linux-2.6-block: (65 commits)\n Documentation/iostats.txt: bit-size reference etc.\n cfq-iosched: removing unnecessary think time checking\n cfq-iosched: Don\u0027t clear queue stats when preempt.\n blk-throttle: Reset group slice when limits are changed\n blk-cgroup: Only give unaccounted_time under debug\n cfq-iosched: Don\u0027t set active queue in preempt\n block: fix non-atomic access to genhd inflight structures\n block: attempt to merge with existing requests on plug flush\n block: NULL dereference on error path in __blkdev_get()\n cfq-iosched: Don\u0027t update group weights when on service tree\n fs: assign sb-\u003es_bdi to default_backing_dev_info if the bdi is going away\n block: Require subsystems to explicitly allocate bio_set integrity mempool\n jbd2: finish conversion from WRITE_SYNC_PLUG to WRITE_SYNC and explicit plugging\n jbd: finish conversion from WRITE_SYNC_PLUG to WRITE_SYNC and explicit plugging\n fs: make fsync_buffers_list() plug\n mm: make generic_writepages() use plugging\n blk-cgroup: Add unaccounted time to timeslice_used.\n block: fixup plugging stubs for !CONFIG_BLOCK\n block: remove obsolete comments for blkdev_issue_zeroout.\n blktrace: Use rq-\u003ecmd_flags directly in blk_add_trace_rq.\n ...\n\nFix up conflicts in fs/{aio.c,super.c}\n" }, { "commit": "4308eebbeb2026827d4492ce8c23d99f7f144a82", "tree": "3781e227988b4d986bf98dcc0390df17c6fe8f10", "parents": [ "45a68628d37222e655219febce9e91b6484789b2" ], "author": { "name": "Eric W. Biederman", "email": "ebiederm@xmission.com", "time": "Wed Mar 23 16:43:13 2011 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Mar 23 19:46:58 2011 -0700" }, "message": "pidns: call pid_ns_prepare_proc() from create_pid_namespace()\n\nReorganize proc_get_sb() so it can be called before the struct pid of the\nfirst process is allocated.\n\nSigned-off-by: Eric W. Biederman \u003cebiederm@xmission.com\u003e\nSigned-off-by: Daniel Lezcano \u003cdaniel.lezcano@free.fr\u003e\nCc: Oleg Nesterov \u003coleg@redhat.com\u003e\nCc: Alexey Dobriyan \u003cadobriyan@gmail.com\u003e\nAcked-by: Serge E. Hallyn \u003cserge@hallyn.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "45a68628d37222e655219febce9e91b6484789b2", "tree": "6acb5c45e8b11022358a1c28691c9b2c75a7df91", "parents": [ "bfdc0b497faa82a0ba2f9dddcf109231dd519fcc" ], "author": { "name": "Eric W. Biederman", "email": "ebiederm@xmission.com", "time": "Wed Mar 23 16:43:12 2011 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Mar 23 19:46:57 2011 -0700" }, "message": "pid: remove the child_reaper special case in init/main.c\n\nThis patchset is a cleanup and a preparation to unshare the pid namespace.\nThese prerequisites prepare for Eric\u0027s patchset to give a file descriptor\nto a namespace and join an existing namespace.\n\nThis patch:\n\nIt turns out that the existing assignment in copy_process of the\nchild_reaper can handle the initial assignment of child_reaper we just\nneed to generalize the test in kernel/fork.c\n\nSigned-off-by: Eric W. Biederman \u003cebiederm@xmission.com\u003e\nSigned-off-by: Daniel Lezcano \u003cdaniel.lezcano@free.fr\u003e\nCc: Oleg Nesterov \u003coleg@redhat.com\u003e\nCc: Alexey Dobriyan \u003cadobriyan@gmail.com\u003e\nAcked-by: Serge E. Hallyn \u003cserge@hallyn.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "9bfb23fc4a481650e60d22dbe84c0fd5a9d49bba", "tree": "a88488a871e6b765dede72ff28db00c71848201d", "parents": [ "4d51985e484dd11d9047dfcd1278ec9ccfb435d5" ], "author": { "name": "Oleg Nesterov", "email": "oleg@redhat.com", "time": "Tue Mar 22 16:34:09 2011 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Mar 22 17:44:11 2011 -0700" }, "message": "sys_unshare: remove the dead CLONE_THREAD/SIGHAND/VM code\n\nCleanup: kill the dead code which does nothing but complicates the code\nand confuses the reader.\n\nsys_unshare(CLONE_THREAD/SIGHAND/VM) is not really implemented, and I\ndoubt very much it will ever work. At least, nobody even tried since the\noriginal 99d1419d96d7df9cfa56 (\"unshare system call -v5: system call\nhandler function\") was applied more than 4 years ago.\n\nAnd the code is not consistent. unshare_thread() always fails\nunconditionally, while unshare_sighand() and unshare_vm() pretend to work\nif there is nothing to unshare.\n\nRemove unshare_thread(), unshare_sighand(), unshare_vm() helpers and\nrelated variables and add a simple CLONE_THREAD | CLONE_SIGHAND| CLONE_VM\ncheck into check_unshare_flags().\n\nAlso, move the \"CLONE_NEWNS needs CLONE_FS\" check from\ncheck_unshare_flags() to sys_unshare(). This looks more consistent and\nmatches the similar do_sysvsem check in sys_unshare().\n\nNote: with or without this patch \"atomic_read(mm-\u003emm_users) \u003e 1\" can give\na false positive due to get_task_mm().\n\nSigned-off-by: Oleg Nesterov \u003coleg@redhat.com\u003e\nAcked-by: Roland McGrath \u003croland@redhat.com\u003e\nCc: Janak Desai \u003cjanak@us.ibm.com\u003e\nCc: Daniel Lezcano \u003cdaniel.lezcano@free.fr\u003e\nCc: \"Eric W. Biederman\" \u003cebiederm@xmission.com\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Alexey Dobriyan \u003cadobriyan@gmail.com\u003e\nAcked-by: Serge Hallyn \u003cserge.hallyn@canonical.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "207205a2ba2655652fe46a60b49838af6c16a919", "tree": "4309aa7cd5cf39c805219001e0ed8ec5b71e4d5e", "parents": [ "b6a84016bd2598e35ead635147fa53619982648d" ], "author": { "name": "Eric Dumazet", "email": "eric.dumazet@gmail.com", "time": "Tue Mar 22 16:30:44 2011 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Mar 22 17:44:01 2011 -0700" }, "message": "kthread: NUMA aware kthread_create_on_node()\n\nAll kthreads being created from a single helper task, they all use memory\nfrom a single node for their kernel stack and task struct.\n\nThis patch suite creates kthread_create_on_node(), adding a \u0027cpu\u0027 parameter\nto parameters already used by kthread_create().\n\nThis parameter serves in allocating memory for the new kthread on its\nmemory node if possible.\n\nSigned-off-by: Eric Dumazet \u003ceric.dumazet@gmail.com\u003e\nAcked-by: David S. Miller \u003cdavem@davemloft.net\u003e\nReviewed-by: Andi Kleen \u003cak@linux.intel.com\u003e\nAcked-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\nCc: Tejun Heo \u003ctj@kernel.org\u003e\nCc: Tony Luck \u003ctony.luck@intel.com\u003e\nCc: Fenghua Yu \u003cfenghua.yu@intel.com\u003e\nCc: David Howells \u003cdhowells@redhat.com\u003e\nCc: \u003clinux-arch@vger.kernel.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "b6a84016bd2598e35ead635147fa53619982648d", "tree": "a73dc0ef4e353723bf123898f0fc143e587c16d8", "parents": [ "504f52b5439aaf26d3e2c1d45ec10fce38c8dd27" ], "author": { "name": "Eric Dumazet", "email": "eric.dumazet@gmail.com", "time": "Tue Mar 22 16:30:42 2011 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Mar 22 17:44:01 2011 -0700" }, "message": "mm: NUMA aware alloc_thread_info_node()\n\nAdd a node parameter to alloc_thread_info(), and change its name to\nalloc_thread_info_node()\n\nThis change is needed to allow NUMA aware kthread_create_on_cpu()\n\nSigned-off-by: Eric Dumazet \u003ceric.dumazet@gmail.com\u003e\nAcked-by: David S. Miller \u003cdavem@davemloft.net\u003e\nReviewed-by: Andi Kleen \u003cak@linux.intel.com\u003e\nAcked-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\nCc: Tejun Heo \u003ctj@kernel.org\u003e\nCc: Tony Luck \u003ctony.luck@intel.com\u003e\nCc: Fenghua Yu \u003cfenghua.yu@intel.com\u003e\nCc: David Howells \u003cdhowells@redhat.com\u003e\nCc: \u003clinux-arch@vger.kernel.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "504f52b5439aaf26d3e2c1d45ec10fce38c8dd27", "tree": "cb46d72c50e843c36540c88ef8c9000dff31c1c8", "parents": [ "9d502c1c8d47b337c378c2ac8eaeee7918ad16b1" ], "author": { "name": "Eric Dumazet", "email": "eric.dumazet@gmail.com", "time": "Tue Mar 22 16:30:41 2011 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Mar 22 17:44:01 2011 -0700" }, "message": "mm: NUMA aware alloc_task_struct_node()\n\nAll kthreads being created from a single helper task, they all use memory\nfrom a single node for their kernel stack and task struct.\n\nThis patch suite creates kthread_create_on_cpu(), adding a \u0027cpu\u0027 parameter\nto parameters already used by kthread_create().\n\nThis parameter serves in allocating memory for the new kthread on its\nmemory node if available.\n\nUsers of this new function are : ksoftirqd, kworker, migration, pktgend...\n\nThis patch:\n\nAdd a node parameter to alloc_task_struct(), and change its name to\nalloc_task_struct_node()\n\nThis change is needed to allow NUMA aware kthread_create_on_cpu()\n\nSigned-off-by: Eric Dumazet \u003ceric.dumazet@gmail.com\u003e\nAcked-by: David S. Miller \u003cdavem@davemloft.net\u003e\nReviewed-by: Andi Kleen \u003cak@linux.intel.com\u003e\nAcked-by: Rusty Russell \u003crusty@rustcorp.com.au\u003e\nCc: Tejun Heo \u003ctj@kernel.org\u003e\nCc: Tony Luck \u003ctony.luck@intel.com\u003e\nCc: Fenghua Yu \u003cfenghua.yu@intel.com\u003e\nCc: David Howells \u003cdhowells@redhat.com\u003e\nCc: \u003clinux-arch@vger.kernel.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "77c100c83e84316ced2507c5799f79c2c80bc6b9", "tree": "93bbf41cc6a1a5f38730f241e104816a488a4715", "parents": [ "4005996e428b0d3df10cd0eba389a14b9f5403e4" ], "author": { "name": "Rik van Riel", "email": "riel@redhat.com", "time": "Tue Feb 01 09:51:46 2011 -0500" }, "committer": { "name": "Marcelo Tosatti", "email": "mtosatti@redhat.com", "time": "Thu Mar 17 13:08:28 2011 -0300" }, "message": "export pid symbols needed for kvm_vcpu_on_spin\n\nExport the symbols required for a race-free kvm_vcpu_on_spin.\n\nSigned-off-by: Rik van Riel \u003criel@redhat.com\u003e\nSigned-off-by: Avi Kivity \u003cavi@redhat.com\u003e\n" }, { "commit": "73c101011926c5832e6e141682180c4debe2cf45", "tree": "b8eeb521a7833cb198d6f39d5a931d820e2a663f", "parents": [ "a488e74976bf0a9bccecdd094378394942dacef1" ], "author": { "name": "Jens Axboe", "email": "jaxboe@fusionio.com", "time": "Tue Mar 08 13:19:51 2011 +0100" }, "committer": { "name": "Jens Axboe", "email": "jaxboe@fusionio.com", "time": "Thu Mar 10 08:45:54 2011 +0100" }, "message": "block: initial patch for on-stack per-task plugging\n\nThis patch adds support for creating a queuing context outside\nof the queue itself. This enables us to batch up pieces of IO\nbefore grabbing the block device queue lock and submitting them to\nthe IO scheduler.\n\nThe context is created on the stack of the process and assigned in\nthe task structure, so that we can auto-unplug it if we hit a schedule\nevent.\n\nThe current queue plugging happens implicitly if IO is submitted to\nan empty device, yet callers have to remember to unplug that IO when\nthey are going to wait for it. This is an ugly API and has caused bugs\nin the past. Additionally, it requires hacks in the vm (-\u003esync_page()\ncallback) to handle that logic. By switching to an explicit plugging\nscheme we make the API a lot nicer and can get rid of the -\u003esync_page()\nhack in the vm.\n\nSigned-off-by: Jens Axboe \u003cjaxboe@fusionio.com\u003e\n" }, { "commit": "ba76149f47d8c939efa0acc07a191237af900471", "tree": "162990f51dd24984f114cba14fc7169a3b54f0f1", "parents": [ "79134171df238171daa4c024a42b77b401ccb00b" ], "author": { "name": "Andrea Arcangeli", "email": "aarcange@redhat.com", "time": "Thu Jan 13 15:46:58 2011 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jan 13 17:32:43 2011 -0800" }, "message": "thp: khugepaged\n\nAdd khugepaged to relocate fragmented pages into hugepages if new\nhugepages become available. (this is indipendent of the defrag logic that\nwill have to make new hugepages available)\n\nThe fundamental reason why khugepaged is unavoidable, is that some memory\ncan be fragmented and not everything can be relocated. So when a virtual\nmachine quits and releases gigabytes of hugepages, we want to use those\nfreely available hugepages to create huge-pmd in the other virtual\nmachines that may be running on fragmented memory, to maximize the CPU\nefficiency at all times. The scan is slow, it takes nearly zero cpu time,\nexcept when it copies data (in which case it means we definitely want to\npay for that cpu time) so it seems a good tradeoff.\n\nIn addition to the hugepages being released by other process releasing\nmemory, we have the strong suspicion that the performance impact of\npotentially defragmenting hugepages during or before each page fault could\nlead to more performance inconsistency than allocating small pages at\nfirst and having them collapsed into large pages later... if they prove\nthemselfs to be long lived mappings (khugepaged scan is slow so short\nlived mappings have low probability to run into khugepaged if compared to\nlong lived mappings).\n\nSigned-off-by: Andrea Arcangeli \u003caarcange@redhat.com\u003e\nAcked-by: Rik van Riel \u003criel@redhat.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "e7a00c45f29c0155007aa150bf231a70fa470365", "tree": "3225a79905dede614ed44e98776cdc6285bbd28a", "parents": [ "4e6af67e970a2ac287739a4c526c857b5bda27ec" ], "author": { "name": "Andrea Arcangeli", "email": "aarcange@redhat.com", "time": "Thu Jan 13 15:46:45 2011 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jan 13 17:32:41 2011 -0800" }, "message": "thp: add pmd_huge_pte to mm_struct\n\nThis increase the size of the mm struct a bit but it is needed to\npreallocate one pte for each hugepage so that split_huge_page will not\nrequire a fail path. Guarantee of success is a fundamental property of\nsplit_huge_page to avoid decrasing swapping reliability and to avoid\nadding -ENOMEM fail paths that would otherwise force the hugepage-unaware\nVM code to learn rolling back in the middle of its pte mangling operations\n(if something we need it to learn handling pmd_trans_huge natively rather\nbeing capable of rollback). When split_huge_page runs a pte is needed to\nsucceed the split, to map the newly splitted regular pages with a regular\npte. This way all existing VM code remains backwards compatible by just\nadding a split_huge_page* one liner. The memory waste of those\npreallocated ptes is negligible and so it is worth it.\n\nSigned-off-by: Andrea Arcangeli \u003caarcange@redhat.com\u003e\nAcked-by: Rik van Riel \u003criel@redhat.com\u003e\nAcked-by: Mel Gorman \u003cmel@csn.ul.ie\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "dabb16f639820267b3850d804571c70bd93d4e07", "tree": "7da59e6133cd2f820389574ac9206c56e046f5d4", "parents": [ "d0a21265dfb5fa8ae54e90d0fb6d1c215b10a28a" ], "author": { "name": "Mandeep Singh Baines", "email": "msb@chromium.org", "time": "Thu Jan 13 15:46:05 2011 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jan 13 17:32:35 2011 -0800" }, "message": "oom: allow a non-CAP_SYS_RESOURCE proces to oom_score_adj down\n\nWe\u0027d like to be able to oom_score_adj a process up/down as it\nenters/leaves the foreground. Currently, it is not possible to oom_adj\ndown without CAP_SYS_RESOURCE. This patch allows a task to decrease its\noom_score_adj back to the value that a CAP_SYS_RESOURCE thread set it to\nor its inherited value at fork. Assuming the thread that has forked it\nhas oom_score_adj of 0, each process could decrease it back from 0 upon\nactivation unless a CAP_SYS_RESOURCE thread elevated it to something\nhigher.\n\nAlternative considered:\n\n* a setuid binary\n* a daemon with CAP_SYS_RESOURCE\n\nSince you don\u0027t wan\u0027t all processes to be able to reduce their oom_adj, a\nsetuid or daemon implementation would be complex. The alternatives also\nhave much higher overhead.\n\nThis patch updated from original patch based on feedback from David\nRientjes.\n\nSigned-off-by: Mandeep Singh Baines \u003cmsb@chromium.org\u003e\nAcked-by: David Rientjes \u003crientjes@google.com\u003e\nCc: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Rik van Riel \u003criel@redhat.com\u003e\nCc: Ying Han \u003cyinghan@google.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "43bb40c9e3aa51a3b038c9df2c9afb4d4685614d", "tree": "3b7d37ef585d4a94d7d56f62f02418b0b0d056c1", "parents": [ "5dfbd1d734ef5415bc47b034df7433ba21e40e7b" ], "author": { "name": "Dave Jones", "email": "davej@redhat.com", "time": "Thu Jan 13 15:45:40 2011 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Jan 13 17:32:31 2011 -0800" }, "message": "sched: remove long deprecated CLONE_STOPPED flag\n\nThis warning was added in commit bdff746a3915 (\"clone: prepare to recycle\nCLONE_STOPPED\") three years ago. 2.6.26 came and went. As far as I know,\nno-one is actually using CLONE_STOPPED.\n\nSigned-off-by: Dave Jones \u003cdavej@redhat.com\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Tejun Heo \u003ctj@kernel.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "72eb6a791459c87a0340318840bb3bd9252b627b", "tree": "3bfb8ad99f9c7e511f37f72d57b56a2cea06d753", "parents": [ "23d69b09b78c4876e134f104a3814c30747c53f1", "55ee4ef30241a62b700f79517e6d5ef2ddbefa67" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Jan 07 17:02:58 2011 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Jan 07 17:02:58 2011 -0800" }, "message": "Merge branch \u0027for-2.6.38\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu\n\n* \u0027for-2.6.38\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu: (30 commits)\n gameport: use this_cpu_read instead of lookup\n x86: udelay: Use this_cpu_read to avoid address calculation\n x86: Use this_cpu_inc_return for nmi counter\n x86: Replace uses of current_cpu_data with this_cpu ops\n x86: Use this_cpu_ops to optimize code\n vmstat: User per cpu atomics to avoid interrupt disable / enable\n irq_work: Use per cpu atomics instead of regular atomics\n cpuops: Use cmpxchg for xchg to avoid lock semantics\n x86: this_cpu_cmpxchg and this_cpu_xchg operations\n percpu: Generic this_cpu_cmpxchg() and this_cpu_xchg support\n percpu,x86: relocate this_cpu_add_return() and friends\n connector: Use this_cpu operations\n xen: Use this_cpu_inc_return\n taskstats: Use this_cpu_ops\n random: Use this_cpu_inc_return\n fs: Use this_cpu_inc_return in buffer.c\n highmem: Use this_cpu_xx_return() operations\n vmstat: Use this_cpu_inc_return for vm statistics\n x86: Support for this_cpu_add, sub, dec, inc_return\n percpu: Generic support for this_cpu_add, sub, dec, inc_return\n ...\n\nFixed up conflicts: in arch/x86/kernel/{apic/nmi.c, apic/x2apic_uv_x.c, process.c}\nas per Tejun.\n" }, { "commit": "1c5354de90c900b369e2ebd36c3a065ede29eb93", "tree": "3144205e179f8c4503db06e8da95b604d1640b68", "parents": [ "e9aa1dd19fe49b5aed3ca94aab87576e534d2a39" ], "author": { "name": "Mike Galbraith", "email": "efault@gmx.de", "time": "Wed Jan 05 11:16:04 2011 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Jan 07 15:54:39 2011 +0100" }, "message": "sched: Move sched_autogroup_exit() to free_signal_struct()\n\nPer Oleg\u0027s suggestion, undo fork failure free/put_signal_struct change,\nand move sched_autogroup_exit() to free_signal_struct() instead.\n\nSigned-off-by: Mike Galbraith \u003cefault@gmx.de\u003e\nReviewed-by: Oleg Nesterov \u003coleg@redhat.com\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nLKML-Reference: \u003c1294222564.8369.6.camel@marge.simson.net\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "27066fd484a32c80630136aa2b91c980f3198f9d", "tree": "78ddabdedbfd7525d13ecd62a745525843f1d0e8", "parents": [ "101e5f77bf35679809586e250b6c62193d2ed179", "3c0eee3fe6a3a1c745379547c7e7c904aa64f6d5" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Jan 05 14:14:42 2011 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Jan 05 14:14:46 2011 +0100" }, "message": "Merge commit \u0027v2.6.37\u0027 into sched/core\n\nMerge reason: Merge the final .37 tree.\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "101e5f77bf35679809586e250b6c62193d2ed179", "tree": "7756de0a3d1d859e05a85134dee2d8e70616d287", "parents": [ "4f8219875a0dad2cfad9e93a3fafcd9626db98d2" ], "author": { "name": "Mike Galbraith", "email": "efault@gmx.de", "time": "Fri Dec 31 09:32:30 2010 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Jan 04 15:10:36 2011 +0100" }, "message": "sched, autogroup: Fix reference leak\n\nThe cgroup exit mess also uncovered a struct autogroup reference leak.\ncopy_process() was simply freeing vs putting the signal_struct,\nstranding a reference.\n\nSigned-off-by: Mike Galbraith \u003cefault@gmx.de\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Oleg Nesterov \u003coleg@redhat.com\u003e\nLKML-Reference: \u003c1293784350.6839.2.camel@marge.simson.net\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "909ea96468096b07fbb41aaf69be060d92bd9271", "tree": "a7e015edd96b5f674874fe78cdd889769e130a2a", "parents": [ "780f36d8b3fa9572f731d4fb85067b2e45e6f993" ], "author": { "name": "Christoph Lameter", "email": "cl@linux.com", "time": "Wed Dec 08 16:22:55 2010 +0100" }, "committer": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Fri Dec 17 15:07:19 2010 +0100" }, "message": "core: Replace __get_cpu_var with __this_cpu_read if not used for an address.\n\n__get_cpu_var() can be replaced with this_cpu_read and will then use a\nsingle read instruction with implied address calculation to access the\ncorrect per cpu instance.\n\nHowever, the address of a per cpu variable passed to __this_cpu_read()\ncannot be determined (since it\u0027s an implied address conversion through\nsegment prefixes). Therefore apply this only to uses of __get_cpu_var\nwhere the address of the variable is not used.\n\nCc: Pekka Enberg \u003cpenberg@cs.helsinki.fi\u003e\nCc: Hugh Dickins \u003chughd@google.com\u003e\nCc: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nAcked-by: H. Peter Anvin \u003chpa@zytor.com\u003e\nSigned-off-by: Christoph Lameter \u003ccl@linux.com\u003e\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\n" }, { "commit": "f26f9aff6aaf67e9a430d16c266f91b13a5bff64", "tree": "84e39b539b42655dbae6b80acbe14e10772711fe", "parents": [ "0f004f5a696a9434b7214d0d3cbd0525ee77d428" ], "author": { "name": "Mike Galbraith", "email": "efault@gmx.de", "time": "Wed Dec 08 11:05:42 2010 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Dec 08 20:15:06 2010 +0100" }, "message": "Sched: fix skip_clock_update optimization\n\nidle_balance() drops/retakes rq-\u003elock, leaving the previous task\nvulnerable to set_tsk_need_resched(). Clear it after we return\nfrom balancing instead, and in setup_thread_stack() as well, so\nno successfully descheduled or never scheduled task has it set.\n\nNeed resched confused the skip_clock_update logic, which assumes\nthat the next call to update_rq_clock() will come nearly immediately\nafter being set. Make the optimization robust against the waking\na sleeper before it sucessfully deschedules case by checking that\nthe current task has not been dequeued before setting the flag,\nsince it is that useless clock update we\u0027re trying to save, and\nclear unconditionally in schedule() proper instead of conditionally\nin put_prev_task().\n\nSigned-off-by: Mike Galbraith \u003cefault@gmx.de\u003e\nReported-by: Bjoern B. Brandenburg \u003cbbb.lst@gmail.com\u003e\nTested-by: Yong Zhang \u003cyong.zhang0@gmail.com\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: stable@kernel.org\nLKML-Reference: \u003c1291802742.1417.9.camel@marge.simson.net\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "5091faa449ee0b7d73bc296a93bca9540fc51d0a", "tree": "55f5e96e189af65c85c769fce48627b8a5abb86b", "parents": [ "822bc180a7f7a7bc5fcaaea195f41b487cc8cae8" ], "author": { "name": "Mike Galbraith", "email": "efault@gmx.de", "time": "Tue Nov 30 14:18:03 2010 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Tue Nov 30 16:03:35 2010 +0100" }, "message": "sched: Add \u0027autogroup\u0027 scheduling feature: automated per session task groups\n\nA recurring complaint from CFS users is that parallel kbuild has\na negative impact on desktop interactivity. This patch\nimplements an idea from Linus, to automatically create task\ngroups. Currently, only per session autogroups are implemented,\nbut the patch leaves the way open for enhancement.\n\nImplementation: each task\u0027s signal struct contains an inherited\npointer to a refcounted autogroup struct containing a task group\npointer, the default for all tasks pointing to the\ninit_task_group. When a task calls setsid(), a new task group\nis created, the process is moved into the new task group, and a\nreference to the preveious task group is dropped. Child\nprocesses inherit this task group thereafter, and increase it\u0027s\nrefcount. When the last thread of a process exits, the\nprocess\u0027s reference is dropped, such that when the last process\nreferencing an autogroup exits, the autogroup is destroyed.\n\nAt runqueue selection time, IFF a task has no cgroup assignment,\nits current autogroup is used.\n\nAutogroup bandwidth is controllable via setting it\u0027s nice level\nthrough the proc filesystem:\n\n cat /proc/\u003cpid\u003e/autogroup\n\nDisplays the task\u0027s group and the group\u0027s nice level.\n\n echo \u003cnice level\u003e \u003e /proc/\u003cpid\u003e/autogroup\n\nSets the task group\u0027s shares to the weight of nice \u003clevel\u003e task.\nSetting nice level is rate limited for !admin users due to the\nabuse risk of task group locking.\n\nThe feature is enabled from boot by default if\nCONFIG_SCHED_AUTOGROUP\u003dy is selected, but can be disabled via\nthe boot option noautogroup, and can also be turned on/off on\nthe fly via:\n\n echo [01] \u003e /proc/sys/kernel/sched_autogroup_enabled\n\n... which will automatically move tasks to/from the root task group.\n\nSigned-off-by: Mike Galbraith \u003cefault@gmx.de\u003e\nAcked-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\nAcked-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Markus Trippelsdorf \u003cmarkus@trippelsdorf.de\u003e\nCc: Mathieu Desnoyers \u003cmathieu.desnoyers@efficios.com\u003e\nCc: Paul Turner \u003cpjt@google.com\u003e\nCc: Oleg Nesterov \u003coleg@redhat.com\u003e\n[ Removed the task_group_path() debug code, and fixed !EVENTFD build failure. ]\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\nLKML-Reference: \u003c1290281700.28711.9.camel@maggy.simson.net\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "9b1bf12d5d51bca178dea21b04a0805e29d60cf1", "tree": "902a2c0e5882a2152da59a589958d6426dc84643", "parents": [ "b84011508360d6885a9d95a235ec77d56f133377" ], "author": { "name": "KOSAKI Motohiro", "email": "kosaki.motohiro@jp.fujitsu.com", "time": "Wed Oct 27 15:34:08 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Oct 27 18:03:12 2010 -0700" }, "message": "signals: move cred_guard_mutex from task_struct to signal_struct\n\nOleg Nesterov pointed out we have to prevent multiple-threads-inside-exec\nitself and we can reuse -\u003ecred_guard_mutex for it. Yes, concurrent\nexecve() has no worth.\n\nLet\u0027s move -\u003ecred_guard_mutex from task_struct to signal_struct. It\nnaturally prevent multiple-threads-inside-exec.\n\nSigned-off-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nReviewed-by: Oleg Nesterov \u003coleg@redhat.com\u003e\nAcked-by: Roland McGrath \u003croland@redhat.com\u003e\nAcked-by: David Howells \u003cdhowells@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": "3d5992d2ac7dc09aed8ab537cba074589f0f0a52", "tree": "0fbb51026e8aa13ddd7a6516c04471ceb97bc277", "parents": [ "0f4d208f1975f16f269134cee5f44c1f048581da" ], "author": { "name": "Ying Han", "email": "yinghan@google.com", "time": "Tue Oct 26 14:21:23 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Oct 26 16:52:05 2010 -0700" }, "message": "oom: add per-mm oom disable count\n\nIt\u0027s pointless to kill a task if another thread sharing its mm cannot be\nkilled to allow future memory freeing. A subsequent patch will prevent\nkills in such cases, but first it\u0027s necessary to have a way to flag a task\nthat shares memory with an OOM_DISABLE task that doesn\u0027t incur an\nadditional tasklist scan, which would make select_bad_process() an O(n^2)\nfunction.\n\nThis patch adds an atomic counter to struct mm_struct that follows how\nmany threads attached to it have an oom_score_adj of OOM_SCORE_ADJ_MIN.\nThey cannot be killed by the kernel, so their memory cannot be freed in\noom conditions.\n\nThis only requires task_lock() on the task that we\u0027re operating on, it\ndoes not require mm-\u003emmap_sem since task_lock() pins the mm and the\noperation is atomic.\n\n[rientjes@google.com: changelog and sys_unshare() code]\n[rientjes@google.com: protect oom_disable_count with task_lock in fork]\n[rientjes@google.com: use old_mm for oom_disable_count in exec]\nSigned-off-by: Ying Han \u003cyinghan@google.com\u003e\nSigned-off-by: David Rientjes \u003crientjes@google.com\u003e\nCc: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Rik van Riel \u003criel@redhat.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "a247c3a97a0216b18a46243eda26081f1928ec37", "tree": "ecf6996b252e9cc818d170eba4b8eb25aac3d596", "parents": [ "df08cdc7ef606509debe7677c439be0ca48790e4" ], "author": { "name": "Andrea Arcangeli", "email": "aarcange@redhat.com", "time": "Wed Sep 22 13:05:12 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Sep 22 17:22:39 2010 -0700" }, "message": "rmap: fix walk during fork\n\nThe below bug in fork led to the rmap walk finding the parent huge-pmd\ntwice instead of just once, because the anon_vma_chain objects of the\nchild vma still point to the vma-\u003evm_mm of the parent.\n\nThe patch fixes it by making the rmap walk accurate during fork. It\u0027s not\na big deal normally but it worth being accurate considering the cost is\nthe same.\n\nSigned-off-by: Andrea Arcangeli \u003caarcange@redhat.com\u003e\nAcked-by: Johannes Weiner \u003cjweiner@redhat.com\u003e\nAcked-by: Rik van Riel \u003criel@redhat.com\u003e\nAcked-by: Hugh Dickins \u003chughd@google.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "297c5eee372478fc32fec5fe8eed711eedb13f3d", "tree": "18415eae0833ff4767943f985900524d6b1d73f1", "parents": [ "36423a5ed5e4ea95ceedb68fad52965033e11639" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Aug 20 16:24:55 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sat Aug 21 08:49:21 2010 -0700" }, "message": "mm: make the vma list be doubly linked\n\nIt\u0027s a really simple list, and several of the users want to go backwards\nin it to find the previous vma. So rather than have to look up the\nprevious entry with \u0027find_vma_prev()\u0027 or something similar, just make it\ndoubly linked instead.\n\nTested-by: Ian Campbell \u003cijc@hellion.org.uk\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "2a4419b5b2a77f3f4537c14f7ad7df95770655dd", "tree": "ad66519a92b995920ecada788e4a08e265747545", "parents": [ "44672e4fbd40e2dda8bbce7d0f71d24dbfc7e00e" ], "author": { "name": "Nick Piggin", "email": "npiggin@kernel.dk", "time": "Wed Aug 18 04:37:33 2010 +1000" }, "committer": { "name": "Al Viro", "email": "viro@zeniv.linux.org.uk", "time": "Wed Aug 18 08:35:46 2010 -0400" }, "message": "fs: fs_struct rwlock to spinlock\n\nfs: fs_struct rwlock to spinlock\n\nstruct fs_struct.lock is an rwlock with the read-side used to protect root and\npwd members while taking references to them. Taking a reference to a path\ntypically requires just 2 atomic ops, so the critical section is very small.\nParallel read-side operations would have cacheline contention on the lock, the\ndentry, and the vfsmount cachelines, so the rwlock is unlikely to ever give a\nreal parallelism increase.\n\nReplace it with a spinlock to avoid one or two atomic operations in typical\npath lookup fastpath.\n\nSigned-off-by: Nick Piggin \u003cnpiggin@kernel.dk\u003e\nSigned-off-by: Al Viro \u003cviro@zeniv.linux.org.uk\u003e\n" }, { "commit": "a63d83f427fbce97a6cea0db2e64b0eb8435cd10", "tree": "8ac229cdf6e2289d97e82e35774057106fe7f4a2", "parents": [ "74bcbf40546bb7500f2a7ba4ff3cc056a6bd004a" ], "author": { "name": "David Rientjes", "email": "rientjes@google.com", "time": "Mon Aug 09 17:19:46 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Mon Aug 09 20:45:02 2010 -0700" }, "message": "oom: badness heuristic rewrite\n\nThis a complete rewrite of the oom killer\u0027s badness() heuristic which is\nused to determine which task to kill in oom conditions. The goal is to\nmake it as simple and predictable as possible so the results are better\nunderstood and we end up killing the task which will lead to the most\nmemory freeing while still respecting the fine-tuning from userspace.\n\nInstead of basing the heuristic on mm-\u003etotal_vm for each task, the task\u0027s\nrss and swap space is used instead. This is a better indication of the\namount of memory that will be freeable if the oom killed task is chosen\nand subsequently exits. This helps specifically in cases where KDE or\nGNOME is chosen for oom kill on desktop systems instead of a memory\nhogging task.\n\nThe baseline for the heuristic is a proportion of memory that each task is\ncurrently using in memory plus swap compared to the amount of \"allowable\"\nmemory. \"Allowable,\" in this sense, means the system-wide resources for\nunconstrained oom conditions, the set of mempolicy nodes, the mems\nattached to current\u0027s cpuset, or a memory controller\u0027s limit. The\nproportion is given on a scale of 0 (never kill) to 1000 (always kill),\nroughly meaning that if a task has a badness() score of 500 that the task\nconsumes approximately 50% of allowable memory resident in RAM or in swap\nspace.\n\nThe proportion is always relative to the amount of \"allowable\" memory and\nnot the total amount of RAM systemwide so that mempolicies and cpusets may\noperate in isolation; they shall not need to know the true size of the\nmachine on which they are running if they are bound to a specific set of\nnodes or mems, respectively.\n\nRoot tasks are given 3% extra memory just like __vm_enough_memory()\nprovides in LSMs. In the event of two tasks consuming similar amounts of\nmemory, it is generally better to save root\u0027s task.\n\nBecause of the change in the badness() heuristic\u0027s baseline, it is also\nnecessary to introduce a new user interface to tune it. It\u0027s not possible\nto redefine the meaning of /proc/pid/oom_adj with a new scale since the\nABI cannot be changed for backward compatability. Instead, a new tunable,\n/proc/pid/oom_score_adj, is added that ranges from -1000 to +1000. It may\nbe used to polarize the heuristic such that certain tasks are never\nconsidered for oom kill while others may always be considered. The value\nis added directly into the badness() score so a value of -500, for\nexample, means to discount 50% of its memory consumption in comparison to\nother tasks either on the system, bound to the mempolicy, in the cpuset,\nor sharing the same memory controller.\n\n/proc/pid/oom_adj is changed so that its meaning is rescaled into the\nunits used by /proc/pid/oom_score_adj, and vice versa. Changing one of\nthese per-task tunables will rescale the value of the other to an\nequivalent meaning. Although /proc/pid/oom_adj was originally defined as\na bitshift on the badness score, it now shares the same linear growth as\n/proc/pid/oom_score_adj but with different granularity. This is required\nso the ABI is not broken with userspace applications and allows oom_adj to\nbe deprecated for future removal.\n\nSigned-off-by: David Rientjes \u003crientjes@google.com\u003e\nCc: Nick Piggin \u003cnpiggin@suse.de\u003e\nCc: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Oleg Nesterov \u003coleg@redhat.com\u003e\nCc: Balbir Singh \u003cbalbir@in.ibm.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "21aa9af03d06cb1d19a3738e5cf12acff984e69b", "tree": "e205a742a4a9baf098b4e3d428c04f4d3a065bca", "parents": [ "9ed3811a6c0d6b66e6cd47a5d7b9136386dce743" ], "author": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Tue Jun 08 21:40:37 2010 +0200" }, "committer": { "name": "Tejun Heo", "email": "tj@kernel.org", "time": "Tue Jun 08 21:40:37 2010 +0200" }, "message": "sched: add hooks for workqueue\n\nConcurrency managed workqueue needs to know when workers are going to\nsleep and waking up. Using these two hooks, cmwq keeps track of the\ncurrent concurrency level and throttles execution of new works if it\u0027s\ntoo high and wakes up another worker from the sleep hook if it becomes\ntoo low.\n\nThis patch introduces PF_WQ_WORKER to identify workqueue workers and\nadds the following two hooks.\n\n* wq_worker_waking_up(): called when a worker is woken up.\n\n* wq_worker_sleeping(): called when a worker is going to sleep and may\n return a pointer to a local task which should be woken up. The\n returned task is woken up using try_to_wake_up_local() which is\n simplified ttwu which is called under rq lock and can only wake up\n local tasks.\n\nBoth hooks are currently defined as noop in kernel/workqueue_sched.h.\nLater cmwq implementation will replace them with proper\nimplementation.\n\nThese hooks are hard coded as they\u0027ll always be enabled.\n\nSigned-off-by: Tejun Heo \u003ctj@kernel.org\u003e\nAcked-by: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Mike Galbraith \u003cefault@gmx.de\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "35926ff5fba8245bd1c6ac04155048f6f89232b1", "tree": "9afc520f47e29cb3cd80462fe62858f17b1c6cfb", "parents": [ "b612a0553714c6b9744ad0d03f10cac78f3a84b1" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sun May 30 09:00:03 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sun May 30 09:00:03 2010 -0700" }, "message": "Revert \"cpusets: randomize node rotor used in cpuset_mem_spread_node()\"\n\nThis reverts commit 0ac0c0d0f837c499afd02a802f9cf52d3027fa3b, which\ncaused cross-architecture build problems for all the wrong reasons.\nIA64 already added its own version of __node_random(), but the fact is,\nthere is nothing architectural about the function, and the original\ncommit was just badly done. Revert it, since no fix is forthcoming.\n\nRequested-by: Stephen Rothwell \u003csfr@canb.auug.org.au\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "f106eee10038c2ee5b6056aaf3f6d5229be6dcdd", "tree": "de7ce930b7119a1be00f3c7604065896d31abc9c", "parents": [ "f20011457f41c11edb5ea5038ad0c8ea9f392023" ], "author": { "name": "Oleg Nesterov", "email": "oleg@redhat.com", "time": "Wed May 26 14:44:11 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu May 27 09:12:52 2010 -0700" }, "message": "pids: fix fork_idle() to setup -\u003epids correctly\n\ncopy_process(pid \u003d\u003e \u0026init_struct_pid) doesn\u0027t do attach_pid/etc.\n\nIt shouldn\u0027t, but this means that the idle threads run with the wrong\npids copied from the caller\u0027s task_struct. In x86 case the caller is\neither kernel_init() thread or keventd.\n\nIn particular, this means that after the series of cpu_up/cpu_down an\nidle thread (which never exits) can run with .pid pointing to nowhere.\n\nChange fork_idle() to initialize idle-\u003epids[] correctly. We only set\n.pid \u003d \u0026init_struct_pid but do not add .node to list, INIT_TASK() does\nthe same for the boot-cpu idle thread (swapper).\n\nSigned-off-by: Oleg Nesterov \u003coleg@redhat.com\u003e\nCc: Cedric Le Goater \u003cclg@fr.ibm.com\u003e\nCc: Dave Hansen \u003chaveblue@us.ibm.com\u003e\nCc: Eric Biederman \u003cebiederm@xmission.com\u003e\nCc: Herbert Poetzl \u003cherbert@13thfloor.at\u003e\nCc: Mathias Krause \u003cMathias.Krause@secunet.com\u003e\nAcked-by: Roland McGrath \u003croland@redhat.com\u003e\nAcked-by: Serge Hallyn \u003cserue@us.ibm.com\u003e\nCc: Sukadev Bhattiprolu \u003csukadev@us.ibm.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "b3ac022cb9dc5883505a88b159d1b240ad1ef405", "tree": "bffa035303cbe3c5bde048ac3d3154fb57059e2d", "parents": [ "dd98acf74762764fbc4382a1d9a244f11a2658cc" ], "author": { "name": "Oleg Nesterov", "email": "oleg@redhat.com", "time": "Wed May 26 14:43:24 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu May 27 09:12:47 2010 -0700" }, "message": "proc: turn signal_struct-\u003ecount into \"int nr_threads\"\n\nNo functional changes, just s/atomic_t count/int nr_threads/.\n\nWith the recent changes this counter has a single user, get_nr_threads()\nAnd, none of its callers need the really accurate number of threads, not\nto mention each caller obviously races with fork/exit. It is only used to\nreport this value to the user-space, except first_tid() uses it to avoid\nthe unnecessary while_each_thread() loop in the unlikely case.\n\nIt is a bit sad we need a word in struct signal_struct for this, perhaps\nwe can change get_nr_threads() to approximate the number of threads using\nsignal-\u003elive and kill -\u003enr_threads later.\n\n[akpm@linux-foundation.org: coding-style fixes]\nSigned-off-by: Oleg Nesterov \u003coleg@redhat.com\u003e\nCc: Alexey Dobriyan \u003cadobriyan@gmail.com\u003e\nCc: \"Eric W. Biederman\" \u003cebiederm@xmission.com\u003e\nAcked-by: Roland McGrath \u003croland@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": "6e1be45aa6ba6a36c0312f65ecf311135c73001d", "tree": "3ea540e0ee249259e40e26c38215981b466075ad", "parents": [ "97101eb41d0d3c97543878ce40e0b8a8b2747ed7" ], "author": { "name": "Oleg Nesterov", "email": "oleg@redhat.com", "time": "Wed May 26 14:43:21 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu May 27 09:12:47 2010 -0700" }, "message": "check_unshare_flags: kill the bogus CLONE_SIGHAND/sig-\u003ecount check\n\ncheck_unshare_flags(CLONE_SIGHAND) adds CLONE_THREAD to *flags_ptr if the\ntask is multithreaded to ensure unshare_thread() will fail.\n\nNot only this is a bit strange way to return the error, this is absolutely\nmeaningless. If signal-\u003ecount \u003e 1 then sighand-\u003ecount must be also \u003e 1,\nand unshare_sighand() will fail anyway.\n\nIn fact, all CLONE_THREAD/SIGHAND/VM checks inside sys_unshare() do not\nlook right. Fortunately this code doesn\u0027t really work anyway.\n\nSigned-off-by: Oleg Nesterov \u003coleg@redhat.com\u003e\nCc: Balbir Singh \u003cbalbir@linux.vnet.ibm.com\u003e\nAcked-by: Roland McGrath \u003croland@redhat.com\u003e\nCc: Veaceslav Falico \u003cvfalico@redhat.com\u003e\nCc: Stanislaw Gruszka \u003csgruszka@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": "97101eb41d0d3c97543878ce40e0b8a8b2747ed7", "tree": "d33299c8d4787d3b578ea432fdaceb965a2acd97", "parents": [ "a705be6b5e8b05f2ae51536ec709de921960326c" ], "author": { "name": "Oleg Nesterov", "email": "oleg@redhat.com", "time": "Wed May 26 14:43:20 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu May 27 09:12:46 2010 -0700" }, "message": "exit: move taskstats_tgid_free() from __exit_signal() to free_signal_struct()\n\nMove taskstats_tgid_free() from __exit_signal() to free_signal_struct().\n\nThis way signal-\u003estats never points to nowhere and we can read -\u003estats\nlockless.\n\nSigned-off-by: Oleg Nesterov \u003coleg@redhat.com\u003e\nCc: Balbir Singh \u003cbalbir@linux.vnet.ibm.com\u003e\nCc: Roland McGrath \u003croland@redhat.com\u003e\nCc: Veaceslav Falico \u003cvfalico@redhat.com\u003e\nCc: Stanislaw Gruszka \u003csgruszka@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": "a705be6b5e8b05f2ae51536ec709de921960326c", "tree": "a4d71651807dabe2dc48bd36cf2e954d7ef967a8", "parents": [ "d40e48e02f3785b9342ee4eb3d7cc9f12981b7f5" ], "author": { "name": "Oleg Nesterov", "email": "oleg@redhat.com", "time": "Wed May 26 14:43:19 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu May 27 09:12:46 2010 -0700" }, "message": "kill the obsolete thread_group_cputime_free() helper\n\nKill the empty thread_group_cputime_free() helper. It was needed to free\nthe per-cpu data which we no longer have.\n\nSigned-off-by: Oleg Nesterov \u003coleg@redhat.com\u003e\nCc: Balbir Singh \u003cbalbir@linux.vnet.ibm.com\u003e\nCc: Roland McGrath \u003croland@redhat.com\u003e\nCc: Veaceslav Falico \u003cvfalico@redhat.com\u003e\nCc: Stanislaw Gruszka \u003csgruszka@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": "ea6d290ca34c4fd91b7348338c0cc7bdeff94a35", "tree": "6e9bd367650d9233c5b6cf1059845f17cb1bc460", "parents": [ "4dec2a91fd7e8815d730afbfdcf085cbf53433ac" ], "author": { "name": "Oleg Nesterov", "email": "oleg@redhat.com", "time": "Wed May 26 14:43:16 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu May 27 09:12:46 2010 -0700" }, "message": "signals: make task_struct-\u003esignal immutable/refcountable\n\nWe have a lot of problems with accessing task_struct-\u003esignal, it can\n\"disappear\" at any moment. Even current can\u0027t use its -\u003esignal safely\nafter exit_notify(). -\u003esiglock helps, but it is not convenient, not\nalways possible, and sometimes it makes sense to use task-\u003esignal even\nafter this task has already dead.\n\nThis patch adds the reference counter, sigcnt, into signal_struct. This\nreference is owned by task_struct and it is dropped in\n__put_task_struct(). Perhaps it makes sense to export\nget/put_signal_struct() later, but currently I don\u0027t see the immediate\nreason.\n\nRename __cleanup_signal() to free_signal_struct() and unexport it. With\nthe previous changes it does nothing except kmem_cache_free().\n\nChange __exit_signal() to not clear/free -\u003esignal, it will be freed when\nthe last reference to any thread in the thread group goes away.\n\nNote:\n\t- when the last thead exits signal-\u003etty can point to nowhere, see\n\t the next patch.\n\n\t- with or without this patch signal_struct-\u003ecount should go away,\n\t or at least it should be \"int nr_threads\" for fs/proc. This will\n\t be addressed later.\n\nSigned-off-by: Oleg Nesterov \u003coleg@redhat.com\u003e\nCc: Alan Cox \u003calan@linux.intel.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nAcked-by: Roland McGrath \u003croland@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": "4dec2a91fd7e8815d730afbfdcf085cbf53433ac", "tree": "cd33cc793abf532d4ca212d09c1e8d3154a8b530", "parents": [ "ffdf91856c812646aa276711fa7e3ad80b00764a" ], "author": { "name": "Oleg Nesterov", "email": "oleg@redhat.com", "time": "Wed May 26 14:43:15 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu May 27 09:12:46 2010 -0700" }, "message": "fork/exit: move tty_kref_put() outside of __cleanup_signal()\n\ntty_kref_put() has two callsites in copy_process() paths,\n\n\t1. if copy_process() suceeds it is called before we copy\n\t signal-\u003etty from parent\n\n\t2. otherwise it is called from __cleanup_signal() under\n\t bad_fork_cleanup_signal: label\n\nIn both cases tty_kref_put() is not right and unneeded because we don\u0027t\nhave the balancing tty_kref_get(). Fortunately, this is harmless because\nthis can only happen without CLONE_THREAD, and in this case signal-\u003etty\nmust be NULL.\n\nRemove tty_kref_put() from copy_process() and __cleanup_signal(), and\nchange another caller of __cleanup_signal(), __exit_signal(), to call\ntty_kref_put() by hand.\n\nI hope this change makes sense by itself, but it is also needed to make\n-\u003esignal refcountable.\n\nSigned-off-by: Oleg Nesterov \u003coleg@redhat.com\u003e\nAcked-by: Alan Cox \u003calan@linux.intel.com\u003e\nAcked-by: Roland McGrath \u003croland@redhat.com\u003e\nCc: Greg KH \u003cgreg@kroah.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "0ac0c0d0f837c499afd02a802f9cf52d3027fa3b", "tree": "c20a7306d4b727722556af1aa5565855686aee07", "parents": [ "6adef3ebe570bcde67fd6c16101451ddde5712b5" ], "author": { "name": "Jack Steiner", "email": "steiner@sgi.com", "time": "Wed May 26 14:42:51 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu May 27 09:12:44 2010 -0700" }, "message": "cpusets: randomize node rotor used in cpuset_mem_spread_node()\n\nSome workloads that create a large number of small files tend to assign\ntoo many pages to node 0 (multi-node systems). Part of the reason is that\nthe rotor (in cpuset_mem_spread_node()) used to assign nodes starts at\nnode 0 for newly created tasks.\n\nThis patch changes the rotor to be initialized to a random node number of\nthe cpuset.\n\n[akpm@linux-foundation.org: fix layout]\n[Lee.Schermerhorn@hp.com: Define stub numa_random() for !NUMA configuration]\nSigned-off-by: Jack Steiner \u003csteiner@sgi.com\u003e\nSigned-off-by: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: Pekka Enberg \u003cpenberg@cs.helsinki.fi\u003e\nCc: Paul Menage \u003cmenage@google.com\u003e\nCc: Jack Steiner \u003csteiner@sgi.com\u003e\nCc: Robin Holt \u003cholt@sgi.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "4d7b4ac22fbec1a03206c6cde353f2fd6942f828", "tree": "2d96a9e9c28cf6fa628a278decc00ad55a8b043b", "parents": [ "3aaf51ace5975050ab43c7d4d7e439e0ae7d13d7", "94f3ca95787ada3d64339a4ecb2754236ab563f6" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 18 08:19:03 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 18 08:19:03 2010 -0700" }, "message": "Merge branch \u0027perf-core-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip\n\n* \u0027perf-core-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (311 commits)\n perf tools: Add mode to build without newt support\n perf symbols: symbol inconsistency message should be done only at verbose\u003d1\n perf tui: Add explicit -lslang option\n perf options: Type check all the remaining OPT_ variants\n perf options: Type check OPT_BOOLEAN and fix the offenders\n perf options: Check v type in OPT_U?INTEGER\n perf options: Introduce OPT_UINTEGER\n perf tui: Add workaround for slang \u003c 2.1.4\n perf record: Fix bug mismatch with -c option definition\n perf options: Introduce OPT_U64\n perf tui: Add help window to show key associations\n perf tui: Make \u003c- exit menus too\n perf newt: Add single key shortcuts for zoom into DSO and threads\n perf newt: Exit browser unconditionally when CTRL+C, q or Q is pressed\n perf newt: Fix the \u0027A\u0027/\u0027a\u0027 shortcut for annotate\n perf newt: Make \u003c- exit the ui_browser\n x86, perf: P4 PMU - fix counters management logic\n perf newt: Make \u003c- zoom out filters\n perf report: Report number of events, not samples\n perf hist: Clarify events_stats fields usage\n ...\n\nFix up trivial conflicts in kernel/fork.c and tools/perf/builtin-record.c\n" }, { "commit": "34441427aab4bdb3069a4ffcda69a99357abcb2e", "tree": "3beebde910f25b0945e9105017fd743c9e5241a5", "parents": [ "3c904afd7358e9ef515eb5df36b6f25c2b7fc2da" ], "author": { "name": "Robin Holt", "email": "holt@sgi.com", "time": "Tue May 11 14:06:46 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue May 11 17:33:41 2010 -0700" }, "message": "revert \"procfs: provide stack information for threads\" and its fixup commits\n\nOriginally, commit d899bf7b (\"procfs: provide stack information for\nthreads\") attempted to introduce a new feature for showing where the\nthreadstack was located and how many pages are being utilized by the\nstack.\n\nCommit c44972f1 (\"procfs: disable per-task stack usage on NOMMU\") was\napplied to fix the NO_MMU case.\n\nCommit 89240ba0 (\"x86, fs: Fix x86 procfs stack information for threads on\n64-bit\") was applied to fix a bug in ia32 executables being loaded.\n\nCommit 9ebd4eba7 (\"procfs: fix /proc/\u003cpid\u003e/stat stack pointer for kernel\nthreads\") was applied to fix a bug which had kernel threads printing a\nuserland stack address.\n\nCommit 1306d603f (\u0027proc: partially revert \"procfs: provide stack\ninformation for threads\"\u0027) was then applied to revert the stack pages\nbeing used to solve a significant performance regression.\n\nThis patch nearly undoes the effect of all these patches.\n\nThe reason for reverting these is it provides an unusable value in\nfield 28. For x86_64, a fork will result in the task-\u003estack_start\nvalue being updated to the current user top of stack and not the stack\nstart address. This unpredictability of the stack_start value makes\nit worthless. That includes the intended use of showing how much stack\nspace a thread has.\n\nOther architectures will get different values. As an example, ia64\ngets 0. The do_fork() and copy_process() functions appear to treat the\nstack_start and stack_size parameters as architecture specific.\n\nI only partially reverted c44972f1 (\"procfs: disable per-task stack usage\non NOMMU\") . If I had completely reverted it, I would have had to change\nmm/Makefile only build pagewalk.o when CONFIG_PROC_PAGE_MONITOR is\nconfigured. Since I could not test the builds without significant effort,\nI decided to not change mm/Makefile.\n\nI only partially reverted 89240ba0 (\"x86, fs: Fix x86 procfs stack\ninformation for threads on 64-bit\") . I left the KSTK_ESP() change in\nplace as that seemed worthwhile.\n\nSigned-off-by: Robin Holt \u003cholt@sgi.com\u003e\nCc: Stefani Seibold \u003cstefani@seibold.net\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Michal Simek \u003cmonstr@monstr.eu\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\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": "ca7e0c612005937a4a5a75d3fed90459993de65c", "tree": "b574fc0f0189b52ffc87ba20c418228db556faa1", "parents": [ "8141d0050d76e5695011b5ab577ec66fb51a998c", "f5284e7635787224dda1a2bf82a4c56b1c75671f" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Apr 08 13:36:36 2010 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Apr 08 13:37:18 2010 +0200" }, "message": "Merge branch \u0027linus\u0027 into perf/core\n\nSemantic conflict: arch/x86/kernel/cpu/perf_event_intel_ds.c\n\nMerge reason: pick up latest fixes, fix the conflict\n\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "a3a2e76c77fa22b114e421ac11dec0c56c3503fb", "tree": "cc67bbd8d5d364e55ea7a00d0b5ad68d5eac08ac", "parents": [ "b01d0942c2b7a3026d2b7d38b5773d3d00420e06" ], "author": { "name": "KAMEZAWA Hiroyuki", "email": "kamezawa.hiroyu@jp.fujitsu.com", "time": "Tue Apr 06 14:34:42 2010 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Apr 07 08:38:02 2010 -0700" }, "message": "mm: avoid null-pointer deref in sync_mm_rss()\n\n- We weren\u0027t zeroing p-\u003erss_stat[] at fork()\n\n- Consequently sync_mm_rss() was dereferencing tsk-\u003emm for kernel\n threads and was oopsing.\n\n- Make __sync_task_rss_stat() static, too.\n\nAddresses https://bugzilla.kernel.org/show_bug.cgi?id\u003d15648\n\n[akpm@linux-foundation.org: remove the BUG_ON(!mm-\u003erss)]\nReported-by: Troels Liebe Bentsen \u003ctlb@rapanden.dk\u003e\nSigned-off-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\n\"Michael S. Tsirkin\" \u003cmst@redhat.com\u003e\nCc: Andrea Arcangeli \u003caarcange@redhat.com\u003e\nCc: Rik van Riel \u003criel@redhat.com\u003e\nCc: Minchan Kim \u003cminchan.kim@gmail.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "faa4602e47690fb11221e00f9b9697c8dc0d4b19", "tree": "af667d1cdff7dc63b6893ee3f27a1f2503229ed1", "parents": [ "7c5ecaf7666617889f337296c610815b519abfa9" ], "author": { "name": "Peter Zijlstra", "email": "a.p.zijlstra@chello.nl", "time": "Thu Mar 25 14:51:50 2010 +0100" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Fri Mar 26 11:33:55 2010 +0100" }, "message": "x86, perf, bts, mm: Delete the never used BTS-ptrace code\n\nSupport for the PMU\u0027s BTS features has been upstreamed in\nv2.6.32, but we still have the old and disabled ptrace-BTS,\nas Linus noticed it not so long ago.\n\nIt\u0027s buggy: TIF_DEBUGCTLMSR is trampling all over that MSR without\nregard for other uses (perf) and doesn\u0027t provide the flexibility\nneeded for perf either.\n\nIts users are ptrace-block-step and ptrace-bts, since ptrace-bts\nwas never used and ptrace-block-step can be implemented using a\nmuch simpler approach.\n\nSo axe all 3000 lines of it. That includes the *locked_memory*()\nAPIs in mm/mlock.c as well.\n\nReported-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Roland McGrath \u003croland@redhat.com\u003e\nCc: Oleg Nesterov \u003coleg@redhat.com\u003e\nCc: Markus Metzger \u003cmarkus.t.metzger@intel.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nLKML-Reference: \u003c20100325135413.938004390@chello.nl\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\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": "93c59907c6f247d09239135caecf294a106a2ae0", "tree": "f115d3763f7479ebbb9516c96bce68237edef860", "parents": [ "4dd66e69d472f0ba5355a2529364d0db9a18a02b" ], "author": { "name": "Veaceslav Falico", "email": "vfalico@redhat.com", "time": "Wed Mar 10 15:23:03 2010 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Mar 12 15:52:39 2010 -0800" }, "message": "copy_signal() cleanup: clean thread_group_cputime_init()\n\nRemove unneeded initializations in thread_group_cputime_init() and in\nposix_cpu_timers_init_group(). They are useless after kmem_cache_zalloc()\nwas used in copy_signal().\n\nSigned-off-by: Veaceslav Falico \u003cvfalico@redhat.com\u003e\nAcked-by: Oleg Nesterov \u003coleg@redhat.com\u003e\nCc: Roland McGrath \u003croland@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": "a56704ef6b0c5796c9ff38cc78aa232dfb9644d7", "tree": "7f304a916fbcd22388ed1a66c63c5571f9572bd7", "parents": [ "e34112e3966fc466ced2698e6c196bb50b1ee20e" ], "author": { "name": "Veaceslav Falico", "email": "vfalico@redhat.com", "time": "Wed Mar 10 15:23:01 2010 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Mar 12 15:52:39 2010 -0800" }, "message": "copy_signal() cleanup: use zalloc and remove initializations\n\nUse kmem_cache_zalloc() on signal creation and remove unneeded\ninitialization lines in copy_signal().\n\nSigned-off-by: Veaceslav Falico \u003cvfalico@redhat.com\u003e\nAcked-by: Oleg Nesterov \u003coleg@redhat.com\u003e\nCc: Roland McGrath \u003croland@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": "78d7d407b62a021e6d2e8dc24c0b90e390ab58a1", "tree": "8c1074b84db4b977bad6802a3701e0113c0a7739", "parents": [ "d4bb527438b4181cd3c564ae04dd344c381283a1" ], "author": { "name": "Jiri Slaby", "email": "jslaby@suse.cz", "time": "Fri Mar 05 13:42:54 2010 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sat Mar 06 11:26:33 2010 -0800" }, "message": "kernel core: use helpers for rlimits\n\nMake sure compiler won\u0027t do weird things with limits. E.g. fetching them\ntwice may return 2 different values after writable limits are implemented.\n\nI.e. either use rlimit helpers added in commit 3e10e716abf3 (\"resource:\nadd helpers for fetching rlimits\") or ACCESS_ONCE if not applicable.\n\nSigned-off-by: Jiri Slaby \u003cjslaby@suse.cz\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nCc: john stultz \u003cjohnstul@us.ibm.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "5beb49305251e5669852ed541e8e2f2f7696c53e", "tree": "46457450a22f23938b24904aeba5d4ada2f53b20", "parents": [ "648bcc771145172a14bc35eeb849ed08f6aa4f1e" ], "author": { "name": "Rik van Riel", "email": "riel@redhat.com", "time": "Fri Mar 05 13:42:07 2010 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sat Mar 06 11:26:26 2010 -0800" }, "message": "mm: change anon_vma linking to fix multi-process server scalability issue\n\nThe old anon_vma code can lead to scalability issues with heavily forking\nworkloads. Specifically, each anon_vma will be shared between the parent\nprocess and all its child processes.\n\nIn a workload with 1000 child processes and a VMA with 1000 anonymous\npages per process that get COWed, this leads to a system with a million\nanonymous pages in the same anon_vma, each of which is mapped in just one\nof the 1000 processes. However, the current rmap code needs to walk them\nall, leading to O(N) scanning complexity for each page.\n\nThis can result in systems where one CPU is walking the page tables of\n1000 processes in page_referenced_one, while all other CPUs are stuck on\nthe anon_vma lock. This leads to catastrophic failure for a benchmark\nlike AIM7, where the total number of processes can reach in the tens of\nthousands. Real workloads are still a factor 10 less process intensive\nthan AIM7, but they are catching up.\n\nThis patch changes the way anon_vmas and VMAs are linked, which allows us\nto associate multiple anon_vmas with a VMA. At fork time, each child\nprocess gets its own anon_vmas, in which its COWed pages will be\ninstantiated. The parents\u0027 anon_vma is also linked to the VMA, because\nnon-COWed pages could be present in any of the children.\n\nThis reduces rmap scanning complexity to O(1) for the pages of the 1000\nchild processes, with O(N) complexity for at most 1/N pages in the system.\n This reduces the average scanning cost in heavily forking workloads from\nO(N) to 2.\n\nThe only real complexity in this patch stems from the fact that linking a\nVMA to anon_vmas now involves memory allocations. This means vma_adjust\ncan fail, if it needs to attach a VMA to anon_vma structures. This in\nturn means error handling needs to be added to the calling functions.\n\nA second source of complexity is that, because there can be multiple\nanon_vmas, the anon_vma linking in vma_adjust can no longer be done under\n\"the\" anon_vma lock. To prevent the rmap code from walking up an\nincomplete VMA, this patch introduces the VM_LOCK_RMAP VMA flag. This bit\nflag uses the same slot as the NOMMU VM_MAPPED_COPY, with an ifdef in mm.h\nto make sure it is impossible to compile a kernel that needs both symbolic\nvalues for the same bitflag.\n\nSome test results:\n\nWithout the anon_vma changes, when AIM7 hits around 9.7k users (on a test\nbox with 16GB RAM and not quite enough IO), the system ends up running\n\u003e99% in system time, with every CPU on the same anon_vma lock in the\npageout code.\n\nWith these changes, AIM7 hits the cross-over point around 29.7k users.\nThis happens with ~99% IO wait time, there never seems to be any spike in\nsystem time. The anon_vma lock contention appears to be resolved.\n\n[akpm@linux-foundation.org: cleanups]\nSigned-off-by: Rik van Riel \u003criel@redhat.com\u003e\nCc: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Larry Woodman \u003clwoodman@redhat.com\u003e\nCc: Lee Schermerhorn \u003cLee.Schermerhorn@hp.com\u003e\nCc: Minchan Kim \u003cminchan.kim@gmail.com\u003e\nCc: Andrea Arcangeli \u003caarcange@redhat.com\u003e\nCc: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "d559db086ff5be9bcc259e5aa50bf3d881eaf1d1", "tree": "aa968c8a4093234e4623a34c0415bf9d8683671c", "parents": [ "19b629f581320999ddb9f6597051b79cdb53459c" ], "author": { "name": "KAMEZAWA Hiroyuki", "email": "kamezawa.hiroyu@jp.fujitsu.com", "time": "Fri Mar 05 13:41:39 2010 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Sat Mar 06 11:26:23 2010 -0800" }, "message": "mm: clean up mm_counter\n\nPresently, per-mm statistics counter is defined by macro in sched.h\n\nThis patch modifies it to\n - defined in mm.h as inlinf functions\n - use array instead of macro\u0027s name creation.\n\nThis patch is for reducing patch size in future patch to modify\nimplementation of per-mm counter.\n\nSigned-off-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nReviewed-by: Minchan Kim \u003cminchan.kim@gmail.com\u003e\nCc: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nCc: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "db1466b3e1bd1727375cdbfcbea4bcce2f860f61", "tree": "e56e8d7b82f8851e570d95f531ec62e4d107967a", "parents": [ "0e064caf6402d1d67db4233d26beec88ca212919" ], "author": { "name": "Paul E. McKenney", "email": "paulmck@linux.vnet.ibm.com", "time": "Wed Mar 03 07:46:56 2010 -0800" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Mar 04 11:46:14 2010 +0100" }, "message": "rcu: Use wrapper function instead of exporting tasklist_lock\n\nLockdep-RCU commit d11c563d exported tasklist_lock, which is not\na good thing. This patch instead exports a function that uses\nlockdep to check whether tasklist_lock is held.\n\nSuggested-by: Christoph Hellwig \u003chch@lst.de\u003e\nSigned-off-by: Paul E. McKenney \u003cpaulmck@linux.vnet.ibm.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\nCc: Christoph Hellwig \u003chch@lst.de\u003e\nLKML-Reference: \u003c1267631219-8713-1-git-send-email-paulmck@linux.vnet.ibm.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "d11c563dd20ff35da5652c3e1c989d9e10e1d6d0", "tree": "b189f50de7a01d7603935d4da7e755d764dfe67e", "parents": [ "a898def29e4119bc01ebe7ca97423181f4c0ea2d" ], "author": { "name": "Paul E. McKenney", "email": "paulmck@linux.vnet.ibm.com", "time": "Mon Feb 22 17:04:50 2010 -0800" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Thu Feb 25 10:34:26 2010 +0100" }, "message": "sched: Use lockdep-based checking on rcu_dereference()\n\nUpdate the rcu_dereference() usages to take advantage of the new\nlockdep-based checking.\n\nSigned-off-by: Paul E. McKenney \u003cpaulmck@linux.vnet.ibm.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: \u003c1266887105-1528-6-git-send-email-paulmck@linux.vnet.ibm.com\u003e\n[ -v2: fix allmodconfig missing symbol export build failure on x86 ]\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "fabf318e5e4bda0aca2b0d617b191884fda62703", "tree": "651b2ee4fb8f393d2fe93f133a5ec6129cb7a8e8", "parents": [ "6d558c3ac9b6508d26fd5cadccce51fc9d726b1c" ], "author": { "name": "Peter Zijlstra", "email": "a.p.zijlstra@chello.nl", "time": "Thu Jan 21 21:04:57 2010 +0100" }, "committer": { "name": "Thomas Gleixner", "email": "tglx@linutronix.de", "time": "Thu Jan 21 23:25:31 2010 +0100" }, "message": "sched: Fix fork vs hotplug vs cpuset namespaces\n\nThere are a number of issues:\n\n1) TASK_WAKING vs cgroup_clone (cpusets)\n\ncopy_process():\n\n sched_fork()\n child-\u003estate \u003d TASK_WAKING; /* waiting for wake_up_new_task() */\n if (current-\u003ensproxy !\u003d p-\u003ensproxy)\n ns_cgroup_clone()\n cgroup_clone()\n mutex_lock(inode-\u003ei_mutex)\n mutex_lock(cgroup_mutex)\n cgroup_attach_task()\n\t ss-\u003ecan_attach()\n ss-\u003eattach() [ -\u003e cpuset_attach() ]\n cpuset_attach_task()\n set_cpus_allowed_ptr();\n while (child-\u003estate \u003d\u003d TASK_WAKING)\n cpu_relax();\nwill deadlock the system.\n\n\n2) cgroup_clone (cpusets) vs copy_process\n\nSo even if the above would work we still have:\n\ncopy_process():\n\n if (current-\u003ensproxy !\u003d p-\u003ensproxy)\n ns_cgroup_clone()\n cgroup_clone()\n mutex_lock(inode-\u003ei_mutex)\n mutex_lock(cgroup_mutex)\n cgroup_attach_task()\n\t ss-\u003ecan_attach()\n ss-\u003eattach() [ -\u003e cpuset_attach() ]\n cpuset_attach_task()\n set_cpus_allowed_ptr();\n ...\n\n p-\u003ecpus_allowed \u003d current-\u003ecpus_allowed\n\nover-writing the modified cpus_allowed.\n\n\n3) fork() vs hotplug\n\n if we unplug the child\u0027s cpu after the sanity check when the child\n gets attached to the task_list but before wake_up_new_task() shit\n will meet with fan.\n\nSolve all these issues by moving fork cpu selection into\nwake_up_new_task().\n\nReported-by: Serge E. Hallyn \u003cserue@us.ibm.com\u003e\nTested-by: Serge E. Hallyn \u003cserue@us.ibm.com\u003e\nSigned-off-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nLKML-Reference: \u003c1264106190.4283.1314.camel@laptop\u003e\nSigned-off-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\n" }, { "commit": "9cd80bbb07fcd6d4d037fad4297496d3b132ac6b", "tree": "322216d34b6d5ba2366f53ba0d677950c4cde766", "parents": [ "0f67b0b0392ccca98459bf40b36c0037793b5f71" ], "author": { "name": "Oleg Nesterov", "email": "oleg@redhat.com", "time": "Thu Dec 17 15:27:15 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Dec 17 15:45:31 2009 -0800" }, "message": "do_wait() optimization: do not place sub-threads on task_struct-\u003echildren list\n\nThanks to Roland who pointed out de_thread() issues.\n\nCurrently we add sub-threads to -\u003ereal_parent-\u003echildren list. This buys\nnothing but slows down do_wait().\n\nWith this patch -\u003echildren contains only main threads (group leaders).\nThe only complication is that forget_original_parent() should iterate over\nsub-threads by hand, and de_thread() needs another list_replace() when it\nchanges -\u003egroup_leader.\n\nHenceforth do_wait_thread() can never see task_detached() \u0026\u0026 !EXIT_DEAD\ntasks, we can remove this check (and we can unify do_wait_thread() and\nptrace_do_wait()).\n\nThis change can confuse the optimistic search in mm_update_next_owner(),\nbut this is fixable and minor.\n\nPerhaps badness() and oom_kill_process() should be updated, but they\nshould be fixed in any case.\n\nSigned-off-by: Oleg Nesterov \u003coleg@redhat.com\u003e\nCc: Roland McGrath \u003croland@redhat.com\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Ratan Nalumasu \u003crnalumasu@gmail.com\u003e\nCc: Vitaly Mayatskikh \u003cvmayatsk@redhat.com\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "6580807da14c423f0d0a708108e6df6ebc8bc83d", "tree": "553e2de8f2174f9bbb6ab9a2454b1306bb5eb4fa", "parents": [ "c6a47cc2ccf9649ee09eeddd70a6d061bde69568" ], "author": { "name": "Oleg Nesterov", "email": "oleg@redhat.com", "time": "Tue Dec 15 16:47:16 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Dec 16 07:20:08 2009 -0800" }, "message": "ptrace: copy_process() should disable stepping\n\nIf the tracee calls fork() after PTRACE_SINGLESTEP, the forked child\nstarts with TIF_SINGLESTEP/X86_EFLAGS_TF bits copied from ptraced parent.\nThis is not right, especially when the new child is not auto-attaced: in\nthis case it is killed by SIGTRAP.\n\nChange copy_process() to call user_disable_single_step(). Tested on x86.\n\nTest-case:\n\n\t#include \u003cstdio.h\u003e\n\t#include \u003cunistd.h\u003e\n\t#include \u003csignal.h\u003e\n\t#include \u003csys/ptrace.h\u003e\n\t#include \u003csys/wait.h\u003e\n\t#include \u003cassert.h\u003e\n\n\tint main(void)\n\t{\n\t\tint pid, status;\n\n\t\tif (!(pid \u003d fork())) {\n\t\t\tassert(ptrace(PTRACE_TRACEME) \u003d\u003d 0);\n\t\t\tkill(getpid(), SIGSTOP);\n\n\t\t\tif (!fork()) {\n\t\t\t\t/* kernel bug: this child will be killed by SIGTRAP */\n\t\t\t\tprintf(\"Hello world\\n\");\n\t\t\t\treturn 43;\n\t\t\t}\n\n\t\t\twait(\u0026status);\n\t\t\treturn WEXITSTATUS(status);\n\t\t}\n\n\t\tfor (;;) {\n\t\t\tassert(pid \u003d\u003d wait(\u0026status));\n\t\t\tif (WIFEXITED(status))\n\t\t\t\tbreak;\n\t\t\tassert(ptrace(PTRACE_SINGLESTEP, pid, 0,0) \u003d\u003d 0);\n\t\t}\n\n\t\tassert(WEXITSTATUS(status) \u003d\u003d 43);\n\t\treturn 0;\n\t}\n\nSigned-off-by: Oleg Nesterov \u003coleg@redhat.com\u003e\nAcked-by: Roland McGrath \u003croland@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": "569b846df54ffb2827b83ce3244c5f032394cba4", "tree": "77c5d373a5edf97710fab8777912971b99e84828", "parents": [ "cd9b45b78a61e8df250e69385c74e729e5b66abf" ], "author": { "name": "KAMEZAWA Hiroyuki", "email": "kamezawa.hiroyu@jp.fujitsu.com", "time": "Tue Dec 15 16:47:03 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Dec 16 07:20:07 2009 -0800" }, "message": "memcg: coalesce uncharge during unmap/truncate\n\nIn massive parallel enviroment, res_counter can be a performance\nbottleneck. One strong techinque to reduce lock contention is reducing\ncalls by coalescing some amount of calls into one.\n\nConsidering charge/uncharge chatacteristic,\n\t- charge is done one by one via demand-paging.\n\t- uncharge is done by\n\t\t- in chunk at munmap, truncate, exit, execve...\n\t\t- one by one via vmscan/paging.\n\nIt seems we have a chance to coalesce uncharges for improving scalability\nat unmap/truncation.\n\nThis patch is a for coalescing uncharge. For avoiding scattering memcg\u0027s\nstructure to functions under /mm, this patch adds memcg batch uncharge\ninformation to the task. A reason for per-task batching is for making use\nof caller\u0027s context information. We do batched uncharge (deleyed\nuncharge) when truncation/unmap occurs but do direct uncharge when\nuncharge is called by memory reclaim (vmscan.c).\n\nThe degree of coalescing depends on callers\n - at invalidate/trucate... pagevec size\n - at unmap ....ZAP_BLOCK_SIZE\n(memory itself will be freed in this degree.)\nThen, we\u0027ll not coalescing too much.\n\nOn x86-64 8cpu server, I tested overheads of memcg at page fault by\nrunning a program which does map/fault/unmap in a loop. Running\na task per a cpu by taskset and see sum of the number of page faults\nin 60secs.\n\n[without memcg config]\n 40156968 page-faults # 0.085 M/sec ( +- 0.046% )\n 27.67 cache-miss/faults\n[root cgroup]\n 36659599 page-faults # 0.077 M/sec ( +- 0.247% )\n 31.58 miss/faults\n[in a child cgroup]\n 18444157 page-faults # 0.039 M/sec ( +- 0.133% )\n 69.96 miss/faults\n[child with this patch]\n 27133719 page-faults # 0.057 M/sec ( +- 0.155% )\n 47.16 miss/faults\n\nWe can see some amounts of improvement.\n(root cgroup doesn\u0027t affected by this patch)\nAnother patch for \"charge\" will follow this and above will be improved more.\n\nChangelog(since 2009/10/02):\n - renamed filed of memcg_batch (as pages to bytes, memsw to memsw_bytes)\n - some clean up and commentary/description updates.\n - added initialize code to copy_process(). (possible bug fix)\n\nChangelog(old):\n - fixed !CONFIG_MEM_CGROUP case.\n - rebased onto the latest mmotm + softlimit fix patches.\n - unified patch for callers\n - added commetns.\n - make -\u003edo_batch as bool.\n - removed css_get() at el. We don\u0027t need it.\n\nSigned-off-by: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Balbir Singh \u003cbalbir@in.ibm.com\u003e\nCc: Daisuke Nishimura \u003cnishimura@mxp.nes.nec.co.jp\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "1d615482547584b9a8bb6316a58fed6ce90dd9ff", "tree": "21dae4b70acb3ce0bdaeeaee1dbd970be41d26e2", "parents": [ "fe841226bd954fba4fd79f037a876053fe9c3217" ], "author": { "name": "Thomas Gleixner", "email": "tglx@linutronix.de", "time": "Tue Nov 17 14:54:03 2009 +0100" }, "committer": { "name": "Thomas Gleixner", "email": "tglx@linutronix.de", "time": "Mon Dec 14 23:55:33 2009 +0100" }, "message": "sched: Convert pi_lock to raw_spinlock\n\nConvert locks which cannot be sleeping locks in preempt-rt to\nraw_spinlocks.\n\nSigned-off-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nAcked-by: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nAcked-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "6035ccd8e9e40bb654fbfdef325902ab531679a5", "tree": "c1810d8a4d4ef150cdf14af72e6087dfc3f4b6e0", "parents": [ "23eb3b64b5e44680c867e165fe1cd18e57fba255", "878eaddd05d251cefa9632c2b8046833c5eead66" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 08 08:19:16 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 08 08:19:16 2009 -0800" }, "message": "Merge branch \u0027for-2.6.33\u0027 of git://git.kernel.dk/linux-2.6-block\n\n* \u0027for-2.6.33\u0027 of git://git.kernel.dk/linux-2.6-block: (113 commits)\n cfq-iosched: Do not access cfqq after freeing it\n block: include linux/err.h to use ERR_PTR\n cfq-iosched: use call_rcu() instead of doing grace period stall on queue exit\n blkio: Allow CFQ group IO scheduling even when CFQ is a module\n blkio: Implement dynamic io controlling policy registration\n blkio: Export some symbols from blkio as its user CFQ can be a module\n block: Fix io_context leak after failure of clone with CLONE_IO\n block: Fix io_context leak after clone with CLONE_IO\n cfq-iosched: make nonrot check logic consistent\n io controller: quick fix for blk-cgroup and modular CFQ\n cfq-iosched: move IO controller declerations to a header file\n cfq-iosched: fix compile problem with !CONFIG_CGROUP\n blkio: Documentation\n blkio: Wait on sync-noidle queue even if rq_noidle \u003d 1\n blkio: Implement group_isolation tunable\n blkio: Determine async workload length based on total number of queues\n blkio: Wait for cfq queue to get backlogged if group is empty\n blkio: Propagate cgroup weight updation to cfq groups\n blkio: Drop the reference to queue once the task changes cgroup\n blkio: Provide some isolation between groups\n ...\n" }, { "commit": "ed9216c1717a3f3738a77908aff78995ea69e7ff", "tree": "c6b5ace7c333dabbf1d94074a13a98244bcdfb26", "parents": [ "d7fc02c7bae7b1cf69269992cf880a43a350cdaa", "d5696725b2a4c59503f5e0bc33adeee7f30cd45b" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 08 08:02:38 2009 -0800" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Dec 08 08:02:38 2009 -0800" }, "message": "Merge branch \u0027kvm-updates/2.6.33\u0027 of git://git.kernel.org/pub/scm/virt/kvm/kvm\n\n* \u0027kvm-updates/2.6.33\u0027 of git://git.kernel.org/pub/scm/virt/kvm/kvm: (84 commits)\n KVM: VMX: Fix comparison of guest efer with stale host value\n KVM: s390: Fix prefix register checking in arch/s390/kvm/sigp.c\n KVM: Drop user return notifier when disabling virtualization on a cpu\n KVM: VMX: Disable unrestricted guest when EPT disabled\n KVM: x86 emulator: limit instructions to 15 bytes\n KVM: s390: Make psw available on all exits, not just a subset\n KVM: x86: Add KVM_GET/SET_VCPU_EVENTS\n KVM: VMX: Report unexpected simultaneous exceptions as internal errors\n KVM: Allow internal errors reported to userspace to carry extra data\n KVM: Reorder IOCTLs in main kvm.h\n KVM: x86: Polish exception injection via KVM_SET_GUEST_DEBUG\n KVM: only clear irq_source_id if irqchip is present\n KVM: x86: disallow KVM_{SET,GET}_LAPIC without allocated in-kernel lapic\n KVM: x86: disallow multiple KVM_CREATE_IRQCHIP\n KVM: VMX: Remove vmx-\u003emsr_offset_efer\n KVM: MMU: update invlpg handler comment\n KVM: VMX: move CR3/PDPTR update to vmx_set_cr3\n KVM: remove duplicated task_switch check\n KVM: powerpc: Fix BUILD_BUG_ON condition\n KVM: VMX: Use shared msr infrastructure\n ...\n\nTrivial conflicts due to new Kconfig options in arch/Kconfig and kernel/Makefile\n" }, { "commit": "b69f2292063d2caf37ca9aec7d63ded203701bf3", "tree": "be4acb81ea4ab7014047808ec2b2c908e8334f55", "parents": [ "61cc74fbb87af6aa551a06a370590c9bc07e29d9" ], "author": { "name": "Louis Rilling", "email": "louis.rilling@kerlabs.com", "time": "Fri Dec 04 14:52:42 2009 +0100" }, "committer": { "name": "Jens Axboe", "email": "jens.axboe@oracle.com", "time": "Fri Dec 04 16:36:18 2009 +0100" }, "message": "block: Fix io_context leak after failure of clone with CLONE_IO\n\nWith CLONE_IO, parent\u0027s io_context-\u003enr_tasks is incremented, but never\ndecremented whenever copy_process() fails afterwards, which prevents\nexit_io_context() from calling IO schedulers exit functions.\n\nGive a task_struct to exit_io_context(), and call exit_io_context() instead of\nput_io_context() in copy_process() cleanup path.\n\nSigned-off-by: Louis Rilling \u003clouis.rilling@kerlabs.com\u003e\nSigned-off-by: Jens Axboe \u003cjens.axboe@oracle.com\u003e\n" }, { "commit": "58988b07cfe2ebe9f9b39d973fd8a083390e749f", "tree": "f7a164abe85b8aa768c58a80c1261208372fb4b0", "parents": [ "22763c5cf3690a681551162c15d34d935308c8d7", "8e7cac79808b62f242069a6ac88d364d35621371" ], "author": { "name": "Avi Kivity", "email": "avi@redhat.com", "time": "Thu Dec 03 09:30:06 2009 +0200" }, "committer": { "name": "Avi Kivity", "email": "avi@redhat.com", "time": "Thu Dec 03 09:30:06 2009 +0200" }, "message": "Merge remote branch \u0027tip/x86/entry\u0027 into kvm-updates/2.6.33\n\nSigned-off-by: Avi Kivity \u003cavi@redhat.com\u003e\n" }, { "commit": "0cf55e1ec08bb5a22e068309e2d8ba1180ab4239", "tree": "6102662a9594d51155bee11666fe8517fcbe6039", "parents": [ "d99ca3b977fc5a93141304f571475c2af9e6c1c5" ], "author": { "name": "Hidetoshi Seto", "email": "seto.hidetoshi@jp.fujitsu.com", "time": "Wed Dec 02 17:28:07 2009 +0900" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Dec 02 17:32:40 2009 +0100" }, "message": "sched, cputime: Introduce thread_group_times()\n\nThis is a real fix for problem of utime/stime values decreasing\ndescribed in the thread:\n\n http://lkml.org/lkml/2009/11/3/522\n\nNow cputime is accounted in the following way:\n\n - {u,s}time in task_struct are increased every time when the thread\n is interrupted by a tick (timer interrupt).\n\n - When a thread exits, its {u,s}time are added to signal-\u003e{u,s}time,\n after adjusted by task_times().\n\n - When all threads in a thread_group exits, accumulated {u,s}time\n (and also c{u,s}time) in signal struct are added to c{u,s}time\n in signal struct of the group\u0027s parent.\n\nSo {u,s}time in task struct are \"raw\" tick count, while\n{u,s}time and c{u,s}time in signal struct are \"adjusted\" values.\n\nAnd accounted values are used by:\n\n - task_times(), to get cputime of a thread:\n This function returns adjusted values that originates from raw\n {u,s}time and scaled by sum_exec_runtime that accounted by CFS.\n\n - thread_group_cputime(), to get cputime of a thread group:\n This function returns sum of all {u,s}time of living threads in\n the group, plus {u,s}time in the signal struct that is sum of\n adjusted cputimes of all exited threads belonged to the group.\n\nThe problem is the return value of thread_group_cputime(),\nbecause it is mixed sum of \"raw\" value and \"adjusted\" value:\n\n group\u0027s {u,s}time \u003d foreach(thread){{u,s}time} + exited({u,s}time)\n\nThis misbehavior can break {u,s}time monotonicity.\nAssume that if there is a thread that have raw values greater\nthan adjusted values (e.g. interrupted by 1000Hz ticks 50 times\nbut only runs 45ms) and if it exits, cputime will decrease (e.g.\n-5ms).\n\nTo fix this, we could do:\n\n group\u0027s {u,s}time \u003d foreach(t){task_times(t)} + exited({u,s}time)\n\nBut task_times() contains hard divisions, so applying it for\nevery thread should be avoided.\n\nThis patch fixes the above problem in the following way:\n\n - Modify thread\u0027s exit (\u003d __exit_signal()) not to use task_times().\n It means {u,s}time in signal struct accumulates raw values instead\n of adjusted values. As the result it makes thread_group_cputime()\n to return pure sum of \"raw\" values.\n\n - Introduce a new function thread_group_times(*task, *utime, *stime)\n that converts \"raw\" values of thread_group_cputime() to \"adjusted\"\n values, in same calculation procedure as task_times().\n\n - Modify group\u0027s exit (\u003d wait_task_zombie()) to use this introduced\n thread_group_times(). It make c{u,s}time in signal struct to\n have adjusted values like before this patch.\n\n - Replace some thread_group_cputime() by thread_group_times().\n This replacements are only applied where conveys the \"adjusted\"\n cputime to users, and where already uses task_times() near by it.\n (i.e. sys_times(), getrusage(), and /proc/\u003cPID\u003e/stat.)\n\nThis patch have a positive side effect:\n\n - Before this patch, if a group contains many short-life threads\n (e.g. runs 0.9ms and not interrupted by ticks), the group\u0027s\n cputime could be invisible since thread\u0027s cputime was accumulated\n after adjusted: imagine adjustment function as adj(ticks, runtime),\n {adj(0, 0.9) + adj(0, 0.9) + ....} \u003d {0 + 0 + ....} \u003d 0.\n After this patch it will not happen because the adjustment is\n applied after accumulated.\n\nv2:\n - remove if()s, put new variables into signal_struct.\n\nSigned-off-by: Hidetoshi Seto \u003cseto.hidetoshi@jp.fujitsu.com\u003e\nAcked-by: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Spencer Candland \u003cspencer@bluehost.com\u003e\nCc: Americo Wang \u003cxiyou.wangcong@gmail.com\u003e\nCc: Oleg Nesterov \u003coleg@redhat.com\u003e\nCc: Balbir Singh \u003cbalbir@in.ibm.com\u003e\nCc: Stanislaw Gruszka \u003csgruszka@redhat.com\u003e\nLKML-Reference: \u003c4B162517.8040909@jp.fujitsu.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "d99ca3b977fc5a93141304f571475c2af9e6c1c5", "tree": "7665ebdafcef46c310055021562e6629f59eafd5", "parents": [ "be8147e68625a1adb111acfd6b98a492be4b74d0" ], "author": { "name": "Hidetoshi Seto", "email": "seto.hidetoshi@jp.fujitsu.com", "time": "Wed Dec 02 17:26:47 2009 +0900" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Wed Dec 02 17:32:39 2009 +0100" }, "message": "sched, cputime: Cleanups related to task_times()\n\n- Remove if({u,s}t)s because no one call it with NULL now.\n- Use cputime_{add,sub}().\n- Add ifndef-endif for prev_{u,s}time since they are used\n only when !VIRT_CPU_ACCOUNTING.\n\nSigned-off-by: Hidetoshi Seto \u003cseto.hidetoshi@jp.fujitsu.com\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nCc: Spencer Candland \u003cspencer@bluehost.com\u003e\nCc: Americo Wang \u003cxiyou.wangcong@gmail.com\u003e\nCc: Oleg Nesterov \u003coleg@redhat.com\u003e\nCc: Balbir Singh \u003cbalbir@in.ibm.com\u003e\nCc: Stanislaw Gruszka \u003csgruszka@redhat.com\u003e\nLKML-Reference: \u003c4B1624C7.7040302@jp.fujitsu.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "8e7cac79808b62f242069a6ac88d364d35621371", "tree": "b68dacc4e080ec8c4587d783a8014906e2eb2445", "parents": [ "3c912b6edaac56cb451e7571c95c15cbb6bd0c81" ], "author": { "name": "Avi Kivity", "email": "avi@redhat.com", "time": "Sun Nov 29 16:34:48 2009 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Sun Nov 29 22:03:04 2009 +0100" }, "message": "core: Fix user return notifier on fork()\n\nfork() clones all thread_info flags, including\nTIF_USER_RETURN_NOTIFY; if the new task is first scheduled on a cpu\nwhich doesn\u0027t have user return notifiers set, this causes user\nreturn notifiers to trigger without any way of clearing itself.\n\nThis is easy to trigger with a forky workload on the host in\nparallel with kvm, resulting in a cpu in an endless loop on the\nverge of returning to userspace.\n\nFix by dropping the TIF_USER_RETURN_NOTIFY immediately after fork.\n\nSigned-off-by: Avi Kivity \u003cavi@redhat.com\u003e\nLKML-Reference: \u003c1259505288-16559-1-git-send-email-avi@redhat.com\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "1d510750941a53a1d3049c1d33c75d6dfcd78618", "tree": "03f501224f839aa897cf540e29595aeda8551052", "parents": [ "1c211849d893b14cc923a18708923954fdd2c63e" ], "author": { "name": "Ian Campbell", "email": "Ian.Campbell@citrix.com", "time": "Tue Nov 03 10:11:14 2009 +0000" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Nov 03 07:52:39 2009 -0800" }, "message": "Correct nr_processes() when CPUs have been unplugged\n\nnr_processes() returns the sum of the per cpu counter process_counts for\nall online CPUs. This counter is incremented for the current CPU on\nfork() and decremented for the current CPU on exit(). Since a process\ndoes not necessarily fork and exit on the same CPU the process_count for\nan individual CPU can be either positive or negative and effectively has\nno meaning in isolation.\n\nTherefore calculating the sum of process_counts over only the online\nCPUs omits the processes which were started or stopped on any CPU which\nhas since been unplugged. Only the sum of process_counts across all\npossible CPUs has meaning.\n\nThe only caller of nr_processes() is proc_root_getattr() which\ncalculates the number of links to /proc as\n stat-\u003enlink \u003d proc_root.nlink + nr_processes();\n\nYou don\u0027t have to be all that unlucky for the nr_processes() to return a\nnegative value leading to a negative number of links (or rather, an\napparently enormous number of links). If this happens then you can get\nfailures where things like \"ls /proc\" start to fail because they got an\n-EOVERFLOW from some stat() call.\n\nExample with some debugging inserted to show what goes on:\n # ps haux|wc -l\n nr_processes: CPU0: 90\n nr_processes: CPU1: 1030\n nr_processes: CPU2: -900\n nr_processes: CPU3: -136\n nr_processes: TOTAL: 84\n proc_root_getattr. nlink 12 + nr_processes() 84 \u003d 96\n 84\n # echo 0 \u003e/sys/devices/system/cpu/cpu1/online\n # ps haux|wc -l\n nr_processes: CPU0: 85\n nr_processes: CPU2: -901\n nr_processes: CPU3: -137\n nr_processes: TOTAL: -953\n proc_root_getattr. nlink 12 + nr_processes() -953 \u003d -941\n 75\n # stat /proc/\n nr_processes: CPU0: 84\n nr_processes: CPU2: -901\n nr_processes: CPU3: -137\n nr_processes: TOTAL: -954\n proc_root_getattr. nlink 12 + nr_processes() -954 \u003d -942\n File: `/proc/\u0027\n Size: 0 Blocks: 0 IO Block: 1024 directory\n Device: 3h/3d Inode: 1 Links: 4294966354\n Access: (0555/dr-xr-xr-x) Uid: ( 0/ root) Gid: ( 0/ root)\n Access: 2009-11-03 09:06:55.000000000 +0000\n Modify: 2009-11-03 09:06:55.000000000 +0000\n Change: 2009-11-03 09:06:55.000000000 +0000\n\nI\u0027m not 100% convinced that the per_cpu regions remain valid for offline\nCPUs, although my testing suggests that they do. If not then I think the\ncorrect solution would be to aggregate the process_count for a given CPU\ninto a global base value in cpu_down().\n\nThis bug appears to pre-date the transition to git and it looks like it\nmay even have been present in linux-2.6.0-test7-bk3 since it looks like\nthe code Rusty patched in http://lwn.net/Articles/64773/ was already\nwrong.\n\nSigned-off-by: Ian Campbell \u003cian.campbell@citrix.com\u003e\nCc: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nCc: Rusty Russell \u003crusty@rustcorp.com.au\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "f579bbcd9bb8b688df03191b92c56ab8af4d6322", "tree": "d450f986022aab73f86f794a03c7f21ad0ece8ec", "parents": [ "e80fb7e52fd305b916a671755ca31ecf8f92e94e", "da085681014fb43d67d9bf6d14bc068e9254bd49" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Oct 08 12:16:35 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Oct 08 12:16:35 2009 -0700" }, "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 futex: fix requeue_pi key imbalance\n futex: Fix typo in FUTEX_WAIT/WAKE_BITSET_PRIVATE definitions\n rcu: Place root rcu_node structure in separate lockdep class\n rcu: Make hot-unplugged CPU relinquish its own RCU callbacks\n rcu: Move rcu_barrier() to rcutree\n futex: Move exit_pi_state() call to release_mm()\n futex: Nullify robust lists after cleanup\n futex: Fix locking imbalance\n panic: Fix panic message visibility by calling bust_spinlocks(0) before dying\n rcu: Replace the rcu_barrier enum with pointer to call_rcu*() function\n rcu: Clean up code based on review feedback from Josh Triplett, part 4\n rcu: Clean up code based on review feedback from Josh Triplett, part 3\n rcu: Fix rcu_lock_map build failure on CONFIG_PROVE_LOCKING\u003dy\n rcu: Clean up code to address Ingo\u0027s checkpatch feedback\n rcu: Clean up code based on review feedback from Josh Triplett, part 2\n rcu: Clean up code based on review feedback from Josh Triplett\n" }, { "commit": "322a2c100a8998158445599ea437fb556aa95b11", "tree": "8039af7452e0fac73f3083cb7e9c1e00d3007811", "parents": [ "fc6b177dee33365ccb29fe6d2092223cf8d679f9" ], "author": { "name": "Thomas Gleixner", "email": "tglx@linutronix.de", "time": "Mon Oct 05 18:18:03 2009 +0200" }, "committer": { "name": "Thomas Gleixner", "email": "tglx@linutronix.de", "time": "Tue Oct 06 17:00:01 2009 +0200" }, "message": "futex: Move exit_pi_state() call to release_mm()\n\nexit_pi_state() is called from do_exit() but not from do_execve().\nMove it to release_mm() so it gets called from do_execve() as well.\n\nSigned-off-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nLKML-Reference: \u003cnew-submission\u003e\nCc: stable@kernel.org\nCc: Anirban Sinha \u003cani@anirban.org\u003e\nCc: Peter Zijlstra \u003cpeterz@infradead.org\u003e\n\n" }, { "commit": "fc6b177dee33365ccb29fe6d2092223cf8d679f9", "tree": "849fcb60282bc6c0a01c3113dfc617c7f03f97d3", "parents": [ "eaaea8036d0261d87d7072c5bc88c7ea730c18ac" ], "author": { "name": "Peter Zijlstra", "email": "peterz@infradead.org", "time": "Mon Oct 05 18:17:32 2009 +0200" }, "committer": { "name": "Thomas Gleixner", "email": "tglx@linutronix.de", "time": "Tue Oct 06 17:00:01 2009 +0200" }, "message": "futex: Nullify robust lists after cleanup\n\nThe robust list pointers of user space held futexes are kept intact\nover an exec() call. When the exec\u0027ed task exits exit_robust_list() is\ncalled with the stale pointer. The risk of corruption is minimal, but\nstill it is incorrect to keep the pointers valid. Actually glibc\nshould uninstall the robust list before calling exec() but we have to\ndeal with it anyway.\n\nNullify the pointers after [compat_]exit_robust_list() has been\ncalled.\n\nReported-by: Anirban Sinha \u003cani@anirban.org\u003e\nSigned-off-by: Peter Zijlstra \u003cpeterz@infradead.org\u003e\nSigned-off-by: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nLKML-Reference: \u003cnew-submission\u003e\nCc: stable@kernel.org\n" }, { "commit": "801460d0cf5c5288153b722565773059b0f44348", "tree": "ff2542903572a546ac59e92f295e9a18e718afa0", "parents": [ "2fa4341074cd02fb39aa23410740764948755635" ], "author": { "name": "Hiroshi Shimamoto", "email": "h-shimamoto@ct.jp.nec.com", "time": "Wed Sep 23 15:57:41 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Sep 24 07:21:05 2009 -0700" }, "message": "task_struct cleanup: move binfmt field to mm_struct\n\nBecause the binfmt is not different between threads in the same process,\nit can be moved from task_struct to mm_struct. And binfmt moudle is\nhandled per mm_struct instead of task_struct.\n\nSigned-off-by: Hiroshi Shimamoto \u003ch-shimamoto@ct.jp.nec.com\u003e\nAcked-by: Oleg Nesterov \u003coleg@redhat.com\u003e\nCc: Rusty Russell \u003crusty@rustcorp.com.au\u003e\nAcked-by: Roland McGrath \u003croland@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": "858f09930b32c11b40fd0c5c467982ba09b10894", "tree": "43972de84d69d61904f4f24ff78f99a3a82c2ff3", "parents": [ "b873c2f34ecd4a5a69b41b852cbc365694541c5f" ], "author": { "name": "Alexey Dobriyan", "email": "adobriyan@gmail.com", "time": "Wed Sep 23 15:57:32 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Sep 24 07:21:05 2009 -0700" }, "message": "aio: ifdef fields in mm_struct\n\n-\u003eioctx_lock and -\u003eioctx_list are used only under CONFIG_AIO.\n\nSigned-off-by: Alexey Dobriyan \u003cadobriyan@gmail.com\u003e\nCc: Zach Brown \u003czach.brown@oracle.com\u003e\nCc: Benjamin LaHaise \u003cbcrl@kvack.org\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "123be07b0b399670a7cc3d82fef0cb4f93ef885c", "tree": "b6edc440be85cf312f7c35ad7b01c7ce7d9241a7", "parents": [ "8d65af789f3e2cf4cfbdbf71a0f7a61ebcd41d38" ], "author": { "name": "Sukadev Bhattiprolu", "email": "sukadev@linux.vnet.ibm.com", "time": "Wed Sep 23 15:57:20 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Thu Sep 24 07:21:04 2009 -0700" }, "message": "fork(): disable CLONE_PARENT for init\n\nWhen global or container-init processes use CLONE_PARENT, they create a\nmulti-rooted process tree. Besides siblings of global init remain as\nzombies on exit since they are not reaped by their parent (swapper). So\nprevent global and container-inits from creating siblings.\n\nSigned-off-by: Sukadev Bhattiprolu \u003csukadev@us.ibm.com\u003e\nAcked-by: Eric W. Biederman \u003cebiederm@xmission.com\u003e\nAcked-by: Roland McGrath \u003croland@redhat.com\u003e\nCc: Oren Laadan \u003corenl@cs.columbia.edu\u003e\nCc: Oleg Nesterov \u003coleg@redhat.com\u003e\nCc: Serge Hallyn \u003cserue@us.ibm.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "31bbb9b58d1e8ebcf2b28c95c2250a9f8e31e397", "tree": "6bb0c0490d66d32eca43e73abb28d8b3ab0e7b91", "parents": [ "ff830b8e5f999d1ccbd0282a666520f0b557daa4", "3f0a525ebf4b8ef041a332bbe4a73aee94bb064b" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Sep 23 09:46:15 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Sep 23 09:46:15 2009 -0700" }, "message": "Merge branch \u0027timers-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip\n\n* \u0027timers-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:\n itimers: Add tracepoints for itimer\n hrtimer: Add tracepoint for hrtimers\n timers: Add tracepoints for timer_list timers\n cputime: Optimize jiffies_to_cputime(1)\n itimers: Simplify arm_timer() code a bit\n itimers: Fix periodic tics precision\n itimers: Merge ITIMER_VIRT and ITIMER_PROF\n\nTrivial header file include conflicts in kernel/fork.c\n" }, { "commit": "d899bf7b55f503ba7d3d07ed27c3a37e270fa7db", "tree": "32a5ee7816b2f0cb3261dcca8102b9cafe9251bd", "parents": [ "cba8aafe1e07dfc8bae5ba78be8e02883bd34d31" ], "author": { "name": "Stefani Seibold", "email": "stefani@seibold.net", "time": "Tue Sep 22 16:45:40 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Sep 23 07:39:41 2009 -0700" }, "message": "procfs: provide stack information for threads\n\nA patch to give a better overview of the userland application stack usage,\nespecially for embedded linux.\n\nCurrently you are only able to dump the main process/thread stack usage\nwhich is showed in /proc/pid/status by the \"VmStk\" Value. But you get no\ninformation about the consumed stack memory of the the threads.\n\nThere is an enhancement in the /proc/\u003cpid\u003e/{task/*,}/*maps and which marks\nthe vm mapping where the thread stack pointer reside with \"[thread stack\nxxxxxxxx]\". xxxxxxxx is the maximum size of stack. This is a value\ninformation, because libpthread doesn\u0027t set the start of the stack to the\ntop of the mapped area, depending of the pthread usage.\n\nA sample output of /proc/\u003cpid\u003e/task/\u003ctid\u003e/maps looks like:\n\n08048000-08049000 r-xp 00000000 03:00 8312 /opt/z\n08049000-0804a000 rw-p 00001000 03:00 8312 /opt/z\n0804a000-0806b000 rw-p 00000000 00:00 0 [heap]\na7d12000-a7d13000 ---p 00000000 00:00 0\na7d13000-a7f13000 rw-p 00000000 00:00 0 [thread stack: 001ff4b4]\na7f13000-a7f14000 ---p 00000000 00:00 0\na7f14000-a7f36000 rw-p 00000000 00:00 0\na7f36000-a8069000 r-xp 00000000 03:00 4222 /lib/libc.so.6\na8069000-a806b000 r--p 00133000 03:00 4222 /lib/libc.so.6\na806b000-a806c000 rw-p 00135000 03:00 4222 /lib/libc.so.6\na806c000-a806f000 rw-p 00000000 00:00 0\na806f000-a8083000 r-xp 00000000 03:00 14462 /lib/libpthread.so.0\na8083000-a8084000 r--p 00013000 03:00 14462 /lib/libpthread.so.0\na8084000-a8085000 rw-p 00014000 03:00 14462 /lib/libpthread.so.0\na8085000-a8088000 rw-p 00000000 00:00 0\na8088000-a80a4000 r-xp 00000000 03:00 8317 /lib/ld-linux.so.2\na80a4000-a80a5000 r--p 0001b000 03:00 8317 /lib/ld-linux.so.2\na80a5000-a80a6000 rw-p 0001c000 03:00 8317 /lib/ld-linux.so.2\nafaf5000-afb0a000 rw-p 00000000 00:00 0 [stack]\nffffe000-fffff000 r-xp 00000000 00:00 0 [vdso]\n\nAlso there is a new entry \"stack usage\" in /proc/\u003cpid\u003e/{task/*,}/status\nwhich will you give the current stack usage in kb.\n\nA sample output of /proc/self/status looks like:\n\nName:\tcat\nState:\tR (running)\nTgid:\t507\nPid:\t507\n.\n.\n.\nCapBnd:\tfffffffffffffeff\nvoluntary_ctxt_switches:\t0\nnonvoluntary_ctxt_switches:\t0\nStack usage:\t12 kB\n\nI also fixed stack base address in /proc/\u003cpid\u003e/{task/*,}/stat to the base\naddress of the associated thread stack and not the one of the main\nprocess. This makes more sense.\n\n[akpm@linux-foundation.org: fs/proc/array.c now needs walk_page_range()]\nSigned-off-by: Stefani Seibold \u003cstefani@seibold.net\u003e\nCc: Ingo Molnar \u003cmingo@elte.hu\u003e\nCc: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nCc: Alexey Dobriyan \u003cadobriyan@gmail.com\u003e\nCc: \"Eric W. Biederman\" \u003cebiederm@xmission.com\u003e\nCc: Randy Dunlap \u003crandy.dunlap@oracle.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "1f10206cf8e945220f7220a809d8bfc15c21f9a5", "tree": "4f2c48ccf9cc52dad9610df54e301e631a351288", "parents": [ "b28cfd2c0616e1b42acc6ee3c77ef6cc3873c510" ], "author": { "name": "Jiri Pirko", "email": "jpirko@redhat.com", "time": "Tue Sep 22 16:44:10 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Wed Sep 23 07:39:30 2009 -0700" }, "message": "getrusage: fill ru_maxrss value\n\nMake -\u003eru_maxrss value in struct rusage filled accordingly to rss hiwater\nmark. This struct is filled as a parameter to getrusage syscall.\n-\u003eru_maxrss value is set to KBs which is the way it is done in BSD\nsystems. /usr/bin/time (gnu time) application converts -\u003eru_maxrss to KBs\nwhich seems to be incorrect behavior. Maintainer of this util was\nnotified by me with the patch which corrects it and cc\u0027ed.\n\nTo make this happen we extend struct signal_struct by two fields. The\nfirst one is -\u003emaxrss which we use to store rss hiwater of the task. The\nsecond one is -\u003ecmaxrss which we use to store highest rss hiwater of all\ntask childs. These values are used in k_getrusage() to actually fill\n-\u003eru_maxrss. k_getrusage() uses current rss hiwater value directly if mm\nstruct exists.\n\nNote:\nexec() clear mm-\u003ehiwater_rss, but doesn\u0027t clear sig-\u003emaxrss.\nit is intetionally behavior. *BSD getrusage have exec() inheriting.\n\ntest programs\n\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\n\ngetrusage.c\n\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\n #include \u003cstdio.h\u003e\n #include \u003cstdlib.h\u003e\n #include \u003cstring.h\u003e\n #include \u003csys/types.h\u003e\n #include \u003csys/time.h\u003e\n #include \u003csys/resource.h\u003e\n #include \u003csys/types.h\u003e\n #include \u003csys/wait.h\u003e\n #include \u003cunistd.h\u003e\n #include \u003csignal.h\u003e\n #include \u003csys/mman.h\u003e\n\n #include \"common.h\"\n\n #define err(str) perror(str), exit(1)\n\nint main(int argc, char** argv)\n{\n\tint status;\n\n\tprintf(\"allocate 100MB\\n\");\n\tconsume(100);\n\n\tprintf(\"testcase1: fork inherit? \\n\");\n\tprintf(\" expect: initial.self ~\u003d child.self\\n\");\n\tshow_rusage(\"initial\");\n\tif (__fork()) {\n\t\twait(\u0026status);\n\t} else {\n\t\tshow_rusage(\"fork child\");\n\t\t_exit(0);\n\t}\n\tprintf(\"\\n\");\n\n\tprintf(\"testcase2: fork inherit? (cont.) \\n\");\n\tprintf(\" expect: initial.children ~\u003d 100MB, but child.children \u003d 0\\n\");\n\tshow_rusage(\"initial\");\n\tif (__fork()) {\n\t\twait(\u0026status);\n\t} else {\n\t\tshow_rusage(\"child\");\n\t\t_exit(0);\n\t}\n\tprintf(\"\\n\");\n\n\tprintf(\"testcase3: fork + malloc \\n\");\n\tprintf(\" expect: child.self ~\u003d initial.self + 50MB\\n\");\n\tshow_rusage(\"initial\");\n\tif (__fork()) {\n\t\twait(\u0026status);\n\t} else {\n\t\tprintf(\"allocate +50MB\\n\");\n\t\tconsume(50);\n\t\tshow_rusage(\"fork child\");\n\t\t_exit(0);\n\t}\n\tprintf(\"\\n\");\n\n\tprintf(\"testcase4: grandchild maxrss\\n\");\n\tprintf(\" expect: post_wait.children ~\u003d 300MB\\n\");\n\tshow_rusage(\"initial\");\n\tif (__fork()) {\n\t\twait(\u0026status);\n\t\tshow_rusage(\"post_wait\");\n\t} else {\n\t\tsystem(\"./child -n 0 -g 300\");\n\t\t_exit(0);\n\t}\n\tprintf(\"\\n\");\n\n\tprintf(\"testcase5: zombie\\n\");\n\tprintf(\" expect: pre_wait ~\u003d initial, IOW the zombie process is not accounted.\\n\");\n\tprintf(\" post_wait ~\u003d 400MB, IOW wait() collect child\u0027s max_rss. \\n\");\n\tshow_rusage(\"initial\");\n\tif (__fork()) {\n\t\tsleep(1); /* children become zombie */\n\t\tshow_rusage(\"pre_wait\");\n\t\twait(\u0026status);\n\t\tshow_rusage(\"post_wait\");\n\t} else {\n\t\tsystem(\"./child -n 400\");\n\t\t_exit(0);\n\t}\n\tprintf(\"\\n\");\n\n\tprintf(\"testcase6: SIG_IGN\\n\");\n\tprintf(\" expect: initial ~\u003d after_zombie (child\u0027s 500MB alloc should be ignored).\\n\");\n\tshow_rusage(\"initial\");\n\tsignal(SIGCHLD, SIG_IGN);\n\tif (__fork()) {\n\t\tsleep(1); /* children become zombie */\n\t\tshow_rusage(\"after_zombie\");\n\t} else {\n\t\tsystem(\"./child -n 500\");\n\t\t_exit(0);\n\t}\n\tprintf(\"\\n\");\n\tsignal(SIGCHLD, SIG_DFL);\n\n\tprintf(\"testcase7: exec (without fork) \\n\");\n\tprintf(\" expect: initial ~\u003d exec \\n\");\n\tshow_rusage(\"initial\");\n\texecl(\"./child\", \"child\", \"-v\", NULL);\n\n\treturn 0;\n}\n\nchild.c\n\u003d\u003d\u003d\u003d\u003d\u003d\u003d\n #include \u003csys/types.h\u003e\n #include \u003cunistd.h\u003e\n #include \u003csys/types.h\u003e\n #include \u003csys/wait.h\u003e\n #include \u003cstdio.h\u003e\n #include \u003cstdlib.h\u003e\n #include \u003cstring.h\u003e\n #include \u003csys/types.h\u003e\n #include \u003csys/time.h\u003e\n #include \u003csys/resource.h\u003e\n\n #include \"common.h\"\n\nint main(int argc, char** argv)\n{\n\tint status;\n\tint c;\n\tlong consume_size \u003d 0;\n\tlong grandchild_consume_size \u003d 0;\n\tint show \u003d 0;\n\n\twhile ((c \u003d getopt(argc, argv, \"n:g:v\")) !\u003d -1) {\n\t\tswitch (c) {\n\t\tcase \u0027n\u0027:\n\t\t\tconsume_size \u003d atol(optarg);\n\t\t\tbreak;\n\t\tcase \u0027v\u0027:\n\t\t\tshow \u003d 1;\n\t\t\tbreak;\n\t\tcase \u0027g\u0027:\n\n\t\t\tgrandchild_consume_size \u003d atol(optarg);\n\t\t\tbreak;\n\t\tdefault:\n\t\t\tbreak;\n\t\t}\n\t}\n\n\tif (show)\n\t\tshow_rusage(\"exec\");\n\n\tif (consume_size) {\n\t\tprintf(\"child alloc %ldMB\\n\", consume_size);\n\t\tconsume(consume_size);\n\t}\n\n\tif (grandchild_consume_size) {\n\t\tif (fork()) {\n\t\t\twait(\u0026status);\n\t\t} else {\n\t\t\tprintf(\"grandchild alloc %ldMB\\n\", grandchild_consume_size);\n\t\t\tconsume(grandchild_consume_size);\n\n\t\t\texit(0);\n\t\t}\n\t}\n\n\treturn 0;\n}\n\ncommon.c\n\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\n #include \u003cstdio.h\u003e\n #include \u003cstdlib.h\u003e\n #include \u003cstring.h\u003e\n #include \u003csys/types.h\u003e\n #include \u003csys/time.h\u003e\n #include \u003csys/resource.h\u003e\n #include \u003csys/types.h\u003e\n #include \u003csys/wait.h\u003e\n #include \u003cunistd.h\u003e\n #include \u003csignal.h\u003e\n #include \u003csys/mman.h\u003e\n\n #include \"common.h\"\n #define err(str) perror(str), exit(1)\n\nvoid show_rusage(char *prefix)\n{\n \tint err, err2;\n \tstruct rusage rusage_self;\n \tstruct rusage rusage_children;\n\n \tprintf(\"%s: \", prefix);\n \terr \u003d getrusage(RUSAGE_SELF, \u0026rusage_self);\n \tif (!err)\n \t\tprintf(\"self %ld \", rusage_self.ru_maxrss);\n \terr2 \u003d getrusage(RUSAGE_CHILDREN, \u0026rusage_children);\n \tif (!err2)\n \t\tprintf(\"children %ld \", rusage_children.ru_maxrss);\n\n \tprintf(\"\\n\");\n}\n\n/* Some buggy OS need this worthless CPU waste. */\nvoid make_pagefault(void)\n{\n\tvoid *addr;\n\tint size \u003d getpagesize();\n\tint i;\n\n\tfor (i\u003d0; i\u003c1000; i++) {\n\t\taddr \u003d mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON, -1, 0);\n\t\tif (addr \u003d\u003d MAP_FAILED)\n\t\t\terr(\"make_pagefault\");\n\t\tmemset(addr, 0, size);\n\t\tmunmap(addr, size);\n\t}\n}\n\nvoid consume(int mega)\n{\n \tsize_t sz \u003d mega * 1024 * 1024;\n \tvoid *ptr;\n\n \tptr \u003d malloc(sz);\n \tmemset(ptr, 0, sz);\n\tmake_pagefault();\n}\n\npid_t __fork(void)\n{\n\tpid_t pid;\n\n\tpid \u003d fork();\n\tmake_pagefault();\n\n\treturn pid;\n}\n\ncommon.h\n\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\nvoid show_rusage(char *prefix);\nvoid make_pagefault(void);\nvoid consume(int mega);\npid_t __fork(void);\n\nFreeBSD result (expected result)\n\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\nallocate 100MB\ntestcase1: fork inherit?\n expect: initial.self ~\u003d child.self\ninitial: self 103492 children 0\nfork child: self 103540 children 0\n\ntestcase2: fork inherit? (cont.)\n expect: initial.children ~\u003d 100MB, but child.children \u003d 0\ninitial: self 103540 children 103540\nchild: self 103564 children 0\n\ntestcase3: fork + malloc\n expect: child.self ~\u003d initial.self + 50MB\ninitial: self 103564 children 103564\nallocate +50MB\nfork child: self 154860 children 0\n\ntestcase4: grandchild maxrss\n expect: post_wait.children ~\u003d 300MB\ninitial: self 103564 children 154860\ngrandchild alloc 300MB\npost_wait: self 103564 children 308720\n\ntestcase5: zombie\n expect: pre_wait ~\u003d initial, IOW the zombie process is not accounted.\n post_wait ~\u003d 400MB, IOW wait() collect child\u0027s max_rss.\ninitial: self 103564 children 308720\nchild alloc 400MB\npre_wait: self 103564 children 308720\npost_wait: self 103564 children 411312\n\ntestcase6: SIG_IGN\n expect: initial ~\u003d after_zombie (child\u0027s 500MB alloc should be ignored).\ninitial: self 103564 children 411312\nchild alloc 500MB\nafter_zombie: self 103624 children 411312\n\ntestcase7: exec (without fork)\n expect: initial ~\u003d exec\ninitial: self 103624 children 411312\nexec: self 103624 children 411312\n\nLinux result (actual test result)\n\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\nallocate 100MB\ntestcase1: fork inherit?\n expect: initial.self ~\u003d child.self\ninitial: self 102848 children 0\nfork child: self 102572 children 0\n\ntestcase2: fork inherit? (cont.)\n expect: initial.children ~\u003d 100MB, but child.children \u003d 0\ninitial: self 102876 children 102644\nchild: self 102572 children 0\n\ntestcase3: fork + malloc\n expect: child.self ~\u003d initial.self + 50MB\ninitial: self 102876 children 102644\nallocate +50MB\nfork child: self 153804 children 0\n\ntestcase4: grandchild maxrss\n expect: post_wait.children ~\u003d 300MB\ninitial: self 102876 children 153864\ngrandchild alloc 300MB\npost_wait: self 102876 children 307536\n\ntestcase5: zombie\n expect: pre_wait ~\u003d initial, IOW the zombie process is not accounted.\n post_wait ~\u003d 400MB, IOW wait() collect child\u0027s max_rss.\ninitial: self 102876 children 307536\nchild alloc 400MB\npre_wait: self 102876 children 307536\npost_wait: self 102876 children 410076\n\ntestcase6: SIG_IGN\n expect: initial ~\u003d after_zombie (child\u0027s 500MB alloc should be ignored).\ninitial: self 102876 children 410076\nchild alloc 500MB\nafter_zombie: self 102880 children 410076\n\ntestcase7: exec (without fork)\n expect: initial ~\u003d exec\ninitial: self 102880 children 410076\nexec: self 102880 children 410076\n\nSigned-off-by: Jiri Pirko \u003cjpirko@redhat.com\u003e\nSigned-off-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Oleg Nesterov \u003coleg@redhat.com\u003e\nCc: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nCc: 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": "28b83c5193e7ab951e402252278f2cc79dc4d298", "tree": "10080e8d3957c2a03f8419ab44c9ecb0ffcdaee0", "parents": [ "f168e1b6390e2d79cf57e48e6ae6d9b0a9e2851a" ], "author": { "name": "KOSAKI Motohiro", "email": "kosaki.motohiro@jp.fujitsu.com", "time": "Mon Sep 21 17:03:13 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Sep 22 07:17:39 2009 -0700" }, "message": "oom: move oom_adj value from task_struct to signal_struct\n\nCurrently, OOM logic callflow is here.\n\n __out_of_memory()\n select_bad_process() for each task\n badness() calculate badness of one task\n oom_kill_process() search child\n oom_kill_task() kill target task and mm shared tasks with it\n\nexample, process-A have two thread, thread-A and thread-B and it have very\nfat memory and each thread have following oom_adj and oom_score.\n\n thread-A: oom_adj \u003d OOM_DISABLE, oom_score \u003d 0\n thread-B: oom_adj \u003d 0, oom_score \u003d very-high\n\nThen, select_bad_process() select thread-B, but oom_kill_task() refuse\nkill the task because thread-A have OOM_DISABLE. Thus __out_of_memory()\ncall select_bad_process() again. but select_bad_process() select the same\ntask. It mean kernel fall in livelock.\n\nThe fact is, select_bad_process() must select killable task. otherwise\nOOM logic go into livelock.\n\nAnd root cause is, oom_adj shouldn\u0027t be per-thread value. it should be\nper-process value because OOM-killer kill a process, not thread. Thus\nThis patch moves oomkilladj (now more appropriately named oom_adj) from\nstruct task_struct to struct signal_struct. it naturally prevent\nselect_bad_process() choose wrong task.\n\nSigned-off-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nCc: Paul Menage \u003cmenage@google.com\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nCc: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Rik van Riel \u003criel@redhat.com\u003e\nCc: Oleg Nesterov \u003coleg@redhat.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "1c2fb7a4c2ca7a958b02bc1e615d0254990bba8d", "tree": "489a97bd453b8002f2234f7e736548103315fa38", "parents": [ "9ba6929480088a85c1ff60a4b1f1c9fc80dbd2b7" ], "author": { "name": "Andrea Arcangeli", "email": "aarcange@redhat.com", "time": "Mon Sep 21 17:02:22 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Sep 22 07:17:32 2009 -0700" }, "message": "ksm: fix deadlock with munlock in exit_mmap\n\nRawhide users have reported hang at startup when cryptsetup is run: the\nsame problem can be simply reproduced by running a program int main() {\nmlockall(MCL_CURRENT | MCL_FUTURE); return 0; }\n\nThe problem is that exit_mmap() applies munlock_vma_pages_all() to\nclean up VM_LOCKED areas, and its current implementation (stupidly)\ntries to fault in absent pages, for example where PROT_NONE prevented\nthem being faulted in when mlocking. Whereas the \"ksm: fix oom\ndeadlock\" patch, knowing there\u0027s a race by which KSM might try to fault\nin pages after exit_mmap() had finally zapped the range, backs out of\nsuch faults doing nothing when its ksm_test_exit() notices mm_users 0.\n\nSo revert that part of \"ksm: fix oom deadlock\" which moved the\nksm_exit() call from before exit_mmap() to the middle of exit_mmap();\nand remove those ksm_test_exit() checks from the page fault paths, so\nallowing the munlocking to proceed without interference.\n\nksm_exit, if there are rmap_items still chained on this mm slot, takes\nmmap_sem write side: so preventing KSM from working on an mm while\nexit_mmap runs. And KSM will bail out as soon as it notices that\nmm_users is already zero, thanks to its internal ksm_test_exit checks.\nSo that when a task is killed by OOM killer or the user, KSM will not\nindefinitely prevent it from running exit_mmap to release its memory.\n\nThis does break a part of what \"ksm: fix oom deadlock\" was trying to\nachieve. When unmerging KSM (echo 2 \u003e/sys/kernel/mm/ksm), and even\nwhen ksmd itself has to cancel a KSM page, it is possible that the\nfirst OOM-kill victim would be the KSM process being faulted: then its\nmemory won\u0027t be freed until a second victim has been selected (freeing\nmemory for the unmerging fault to complete).\n\nBut the OOM killer is already liable to kill a second victim once the\nintended victim\u0027s p-\u003emm goes to NULL: so there\u0027s not much point in\nrejecting this KSM patch before fixing that OOM behaviour. It is very\nmuch more important to allow KSM users to boot up, than to haggle over\nan unlikely and poorly supported OOM case.\n\nWe also intend to fix munlocking to not fault pages: at which point\nthis patch _could_ be reverted; though that would be controversial, so\nwe hope to find a better solution.\n\nSigned-off-by: Andrea Arcangeli \u003caarcange@redhat.com\u003e\nAcked-by: Justin M. Forbes \u003cjforbes@redhat.com\u003e\nAcked-for-now-by: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nCc: Izik Eidus \u003cieidus@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": "9ba6929480088a85c1ff60a4b1f1c9fc80dbd2b7", "tree": "39aab8cdffae598b55e35c578f70820712286ab4", "parents": [ "cd551f97519d35855be5a8720a47cc802ee4fd06" ], "author": { "name": "Hugh Dickins", "email": "hugh.dickins@tiscali.co.uk", "time": "Mon Sep 21 17:02:20 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Sep 22 07:17:32 2009 -0700" }, "message": "ksm: fix oom deadlock\n\nThere\u0027s a now-obvious deadlock in KSM\u0027s out-of-memory handling:\nimagine ksmd or KSM_RUN_UNMERGE handling, holding ksm_thread_mutex,\ntrying to allocate a page to break KSM in an mm which becomes the\nOOM victim (quite likely in the unmerge case): it\u0027s killed and goes\nto exit, and hangs there waiting to acquire ksm_thread_mutex.\n\nClearly we must not require ksm_thread_mutex in __ksm_exit, simple\nthough that made everything else: perhaps use mmap_sem somehow?\nAnd part of the answer lies in the comments on unmerge_ksm_pages:\n__ksm_exit should also leave all the rmap_item removal to ksmd.\n\nBut there\u0027s a fundamental problem, that KSM relies upon mmap_sem to\nguarantee the consistency of the mm it\u0027s dealing with, yet exit_mmap\ntears down an mm without taking mmap_sem. And bumping mm_users won\u0027t\nhelp at all, that just ensures that the pages the OOM killer assumes\nare on their way to being freed will not be freed.\n\nThe best answer seems to be, to move the ksm_exit callout from just\nbefore exit_mmap, to the middle of exit_mmap: after the mm\u0027s pages\nhave been freed (if the mmu_gather is flushed), but before its page\ntables and vma structures have been freed; and down_write,up_write\nmmap_sem there to serialize with KSM\u0027s own reliance on mmap_sem.\n\nBut KSM then needs to be careful, whenever it downs mmap_sem, to\ncheck that the mm is not already exiting: there\u0027s a danger of using\nfind_vma on a layout that\u0027s being torn apart, or writing into page\ntables which have been freed for reuse; and even do_anonymous_page\nand __do_fault need to check they\u0027re not being called by break_ksm\nto reinstate a pte after zap_pte_range has zapped that page table.\n\nThough it might be clearer to add an exiting flag, set while holding\nmmap_sem in __ksm_exit, that wouldn\u0027t cover the issue of reinstating\na zapped pte. All we need is to check whether mm_users is 0 - but\nmust remember that ksmd may detect that before __ksm_exit is reached.\nSo, ksm_test_exit(mm) added to comment such checks on mm-\u003emm_users.\n\n__ksm_exit now has to leave clearing up the rmap_items to ksmd,\nthat needs ksm_thread_mutex; but shift the exiting mm just after the\nksm_scan cursor so that it will soon be dealt with. __ksm_enter raise\nmm_count to hold the mm_struct, ksmd\u0027s exit processing (exactly like\nits processing when it finds all VM_MERGEABLEs unmapped) mmdrop it,\nsimilar procedure for KSM_RUN_UNMERGE (which has stopped ksmd).\n\nBut also give __ksm_exit a fast path: when there\u0027s no complication\n(no rmap_items attached to mm and it\u0027s not at the ksm_scan cursor),\nit can safely do all the exiting work itself. This is not just an\noptimization: when ksmd is not running, the raised mm_count would\notherwise leak mm_structs.\n\nSigned-off-by: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nAcked-by: Izik Eidus \u003cieidus@redhat.com\u003e\nCc: Andrea Arcangeli \u003caarcange@redhat.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "f8af4da3b4c14e7267c4ffb952079af3912c51c5", "tree": "17b0cfbd2d3d9abf9008f69e7fee5369cec7afa5", "parents": [ "d19f352484467a5e518639ddff0554669c10ffab" ], "author": { "name": "Hugh Dickins", "email": "hugh.dickins@tiscali.co.uk", "time": "Mon Sep 21 17:01:57 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Sep 22 07:17:31 2009 -0700" }, "message": "ksm: the mm interface to ksm\n\nThis patch presents the mm interface to a dummy version of ksm.c, for\nbetter scrutiny of that interface: the real ksm.c follows later.\n\nWhen CONFIG_KSM is not set, madvise(2) reject MADV_MERGEABLE and\nMADV_UNMERGEABLE with EINVAL, since that seems more helpful than\npretending that they can be serviced. But when CONFIG_KSM\u003dy, accept them\neven if KSM is not currently running, and even on areas which KSM will not\ntouch (e.g. hugetlb or shared file or special driver mappings).\n\nLike other madvices, report ENOMEM despite success if any area in the\nrange is unmapped, and use EAGAIN to report out of memory.\n\nDefine vma flag VM_MERGEABLE to identify an area on which KSM may try\nmerging pages: leave it to ksm_madvise() to decide whether to set it.\nDefine mm flag MMF_VM_MERGEABLE to identify an mm which might contain\nVM_MERGEABLE areas, to minimize callouts when forking or exiting.\n\nBased upon earlier patches by Chris Wright and Izik Eidus.\n\nSigned-off-by: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nSigned-off-by: Chris Wright \u003cchrisw@redhat.com\u003e\nSigned-off-by: Izik Eidus \u003cieidus@redhat.com\u003e\nCc: Michael Kerrisk \u003cmtk.manpages@gmail.com\u003e\nCc: Andrea Arcangeli \u003caarcange@redhat.com\u003e\nCc: Rik van Riel \u003criel@redhat.com\u003e\nCc: Wu Fengguang \u003cfengguang.wu@intel.com\u003e\nCc: Balbir Singh \u003cbalbir@in.ibm.com\u003e\nCc: Hugh Dickins \u003chugh.dickins@tiscali.co.uk\u003e\nCc: KAMEZAWA Hiroyuki \u003ckamezawa.hiroyu@jp.fujitsu.com\u003e\nCc: Lee Schermerhorn \u003clee.schermerhorn@hp.com\u003e\nCc: Avi Kivity \u003cavi@redhat.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": "c6a7f5728a1db45d30df55a01adc130b4ab0327c", "tree": "36649bc6ebb959841a5097c699968722cfd99c4d", "parents": [ "71de1ccbe1fb40203edd3beb473f8580d917d2ca" ], "author": { "name": "KOSAKI Motohiro", "email": "kosaki.motohiro@jp.fujitsu.com", "time": "Mon Sep 21 17:01:32 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Tue Sep 22 07:17:27 2009 -0700" }, "message": "mm: oom analysis: Show kernel stack usage in /proc/meminfo and OOM log output\n\nThe amount of memory allocated to kernel stacks can become significant and\ncause OOM conditions. However, we do not display the amount of memory\nconsumed by stacks.\n\nAdd code to display the amount of memory used for stacks in /proc/meminfo.\n\nSigned-off-by: KOSAKI Motohiro \u003ckosaki.motohiro@jp.fujitsu.com\u003e\nReviewed-by: Christoph Lameter \u003ccl@linux-foundation.org\u003e\nReviewed-by: Minchan Kim \u003cminchan.kim@gmail.com\u003e\nReviewed-by: Rik van Riel \u003criel@redhat.com\u003e\nCc: David Rientjes \u003crientjes@google.com\u003e\nSigned-off-by: Andrew Morton \u003cakpm@linux-foundation.org\u003e\nSigned-off-by: Linus Torvalds \u003ctorvalds@linux-foundation.org\u003e\n" }, { "commit": "cdd6c482c9ff9c55475ee7392ec8f672eddb7be6", "tree": "81f98a3ab46c589792057fe2392c1e10f8ad7893", "parents": [ "dfc65094d0313cc48969fa60bcf33d693aeb05a7" ], "author": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Sep 21 12:02:48 2009 +0200" }, "committer": { "name": "Ingo Molnar", "email": "mingo@elte.hu", "time": "Mon Sep 21 14:28:04 2009 +0200" }, "message": "perf: Do the big rename: Performance Counters -\u003e Performance Events\n\nBye-bye Performance Counters, welcome Performance Events!\n\nIn the past few months the perfcounters subsystem has grown out its\ninitial role of counting hardware events, and has become (and is\nbecoming) a much broader generic event enumeration, reporting, logging,\nmonitoring, analysis facility.\n\nNaming its core object \u0027perf_counter\u0027 and naming the subsystem\n\u0027perfcounters\u0027 has become more and more of a misnomer. With pending\ncode like hw-breakpoints support the \u0027counter\u0027 name is less and\nless appropriate.\n\nAll in one, we\u0027ve decided to rename the subsystem to \u0027performance\nevents\u0027 and to propagate this rename through all fields, variables\nand API names. (in an ABI compatible fashion)\n\nThe word \u0027event\u0027 is also a bit shorter than \u0027counter\u0027 - which makes\nit slightly more convenient to write/handle as well.\n\nThanks goes to Stephane Eranian who first observed this misnomer and\nsuggested a rename.\n\nUser-space tooling and ABI compatibility is not affected - this patch\nshould be function-invariant. (Also, defconfigs were not touched to\nkeep the size down.)\n\nThis patch has been generated via the following script:\n\n FILES\u003d$(find * -type f | grep -vE \u0027oprofile|[^K]config\u0027)\n\n sed -i \\\n -e \u0027s/PERF_EVENT_/PERF_RECORD_/g\u0027 \\\n -e \u0027s/PERF_COUNTER/PERF_EVENT/g\u0027 \\\n -e \u0027s/perf_counter/perf_event/g\u0027 \\\n -e \u0027s/nb_counters/nb_events/g\u0027 \\\n -e \u0027s/swcounter/swevent/g\u0027 \\\n -e \u0027s/tpcounter_event/tp_event/g\u0027 \\\n $FILES\n\n for N in $(find . -name perf_counter.[ch]); do\n M\u003d$(echo $N | sed \u0027s/perf_counter/perf_event/g\u0027)\n mv $N $M\n done\n\n FILES\u003d$(find . -name perf_event.*)\n\n sed -i \\\n -e \u0027s/COUNTER_MASK/REG_MASK/g\u0027 \\\n -e \u0027s/COUNTER/EVENT/g\u0027 \\\n -e \u0027s/\\\u003cevent\\\u003e/event_id/g\u0027 \\\n -e \u0027s/counter/event/g\u0027 \\\n -e \u0027s/Counter/Event/g\u0027 \\\n $FILES\n\n... to keep it as correct as possible. This script can also be\nused by anyone who has pending perfcounters patches - it converts\na Linux kernel tree over to the new naming. We tried to time this\nchange to the point in time where the amount of pending patches\nis the smallest: the end of the merge window.\n\nNamespace clashes were fixed up in a preparatory patch - and some\nstylistic fallout will be fixed up in a subsequent patch.\n\n( NOTE: \u0027counters\u0027 are still the proper terminology when we deal\n with hardware registers - and these sed scripts are a bit\n over-eager in renaming them. I\u0027ve undone some of that, but\n in case there\u0027s something left where \u0027counter\u0027 would be\n better than \u0027event\u0027 we can undo that on an individual basis\n instead of touching an otherwise nicely automated patch. )\n\nSuggested-by: Stephane Eranian \u003ceranian@google.com\u003e\nAcked-by: Peter Zijlstra \u003ca.p.zijlstra@chello.nl\u003e\nAcked-by: Paul Mackerras \u003cpaulus@samba.org\u003e\nReviewed-by: Arjan van de Ven \u003carjan@linux.intel.com\u003e\nCc: Mike Galbraith \u003cefault@gmx.de\u003e\nCc: Arnaldo Carvalho de Melo \u003cacme@redhat.com\u003e\nCc: Frederic Weisbecker \u003cfweisbec@gmail.com\u003e\nCc: Steven Rostedt \u003crostedt@goodmis.org\u003e\nCc: Benjamin Herrenschmidt \u003cbenh@kernel.crashing.org\u003e\nCc: David Howells \u003cdhowells@redhat.com\u003e\nCc: Kyle McMartin \u003ckyle@mcmartin.ca\u003e\nCc: Martin Schwidefsky \u003cschwidefsky@de.ibm.com\u003e\nCc: \"David S. Miller\" \u003cdavem@davemloft.net\u003e\nCc: Thomas Gleixner \u003ctglx@linutronix.de\u003e\nCc: \"H. Peter Anvin\" \u003chpa@zytor.com\u003e\nCc: \u003clinux-arch@vger.kernel.org\u003e\nLKML-Reference: \u003cnew-submission\u003e\nSigned-off-by: Ingo Molnar \u003cmingo@elte.hu\u003e\n" }, { "commit": "eee2775d9924b22643bd89b2e568cc5eed7e8a04", "tree": "095ad7851895c5d39596f3ff7ee1e078235a2501", "parents": [ "53e16fbd30005905168d9b75555fdc7e0a2eac58", "7db905e636f08ea5bc9825c1f73d77802e8ccad5" ], "author": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Sep 11 13:20:18 2009 -0700" }, "committer": { "name": "Linus Torvalds", "email": "torvalds@linux-foundation.org", "time": "Fri Sep 11 13:20:18 2009 -0700" }, "message": "Merge branch \u0027core-rcu-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip\n\n* \u0027core-rcu-for-linus\u0027 of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (28 commits)\n rcu: Move end of special early-boot RCU operation earlier\n rcu: Changes from reviews: avoid casts, fix/add warnings, improve comments\n rcu: Create rcutree plugins to handle hotplug CPU for multi-level trees\n rcu: Remove lockdep annotations from RCU\u0027s _notrace() API members\n rcu: Add #ifdef to suppress __rcu_offline_cpu() warning in !HOTPLUG_CPU builds\n rcu: Add CPU-offline processing for single-node configurations\n rcu: Add \"notrace\" to RCU function headers used by ftrace\n rcu: Remove CONFIG_PREEMPT_RCU\n rcu: Merge preemptable-RCU functionality into hierarchical RCU\n rcu: Simplify rcu_pending()/rcu_check_callbacks() API\n rcu: Use debugfs_remove_recursive() simplify code.\n rcu: Merge per-RCU-flavor initialization into pre-existing macro\n rcu: Fix online/offline indication for rcudata.csv trace file\n rcu: Consolidate sparse and lockdep declarations in include/linux/rcupdate.h\n rcu: Renamings to increase RCU clarity\n rcu: Move private definitions from include/linux/rcutree.h to kernel/rcutree.h\n rcu: Expunge lingering references to CONFIG_CLASSIC_RCU, optimize on !SMP\n rcu: Delay rcu_barrier() wait until beginning of next CPU-hotunplug operation.\n rcu: Fix typo in rcu_irq_exit() comment header\n rcu: Make rcupreempt_trace.c look at offline CPUs\n ...\n" }, { "commit": "a3c8b97396ef42edfb845788ba6f53b2a93ce980", "tree": "530c5bdbc534618311dab3e0af245835af56db0f", "parents": [ "74fca6a42863ffacaf7ba6f1936a9f228950f657", "9f0ab4a3f0fdb1ff404d150618ace2fa069bb2e1" ], "author": { "name": "James Morris", "email": "jmorris@namei.org", "time": "Fri Sep 11 08:04:49 2009 +1000" }, "committer": { "name": "James Morris", "email": "jmorris@namei.org", "time": "Fri Sep 11 08:04:49 2009 +1000" }, "message": "Merge branch \u0027next\u0027 into for-linus\n" } ], "next": "29e2035bddecce3eb584a8304528b50da8370a24" }