From 9f498cc5be7e013d8d6e4c616980ed0ffc8680d2 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 23 Jul 2009 14:46:33 +0200 Subject: perf_counter: Full task tracing In order to be able to distinguish between no samples due to inactivity and no samples due to task ended, Arjan asked for PERF_EVENT_EXIT events. This is useful to the boot delay instrumentation (bootchart) app. This patch changes the PERF_EVENT_FORK to be emitted on every clone, and adds PERF_EVENT_EXIT to be emitted on task exit, after the task's counters have been closed. This task tracing is controlled through: attr.comm || attr.mmap and through the new attr.task field. Suggested-by: Arjan van de Ven Cc: Paul Mackerras Cc: Anton Blanchard Signed-off-by: Peter Zijlstra [ cleaned up perf_counter.h a bit ] Signed-off-by: Ingo Molnar --- kernel/fork.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 29b532e718f..466531eb92c 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1269,6 +1269,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, write_unlock_irq(&tasklist_lock); proc_fork_connector(p); cgroup_post_fork(p); + perf_counter_fork(p); return p; bad_fork_free_pid: @@ -1410,9 +1411,6 @@ long do_fork(unsigned long clone_flags, init_completion(&vfork); } - if (!(clone_flags & CLONE_THREAD)) - perf_counter_fork(p); - audit_finish_fork(p); tracehook_report_clone(regs, clone_flags, nr, p); -- cgit v1.2.3 From 9c8a8228d0827e0d91d28527209988f672f97d28 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 6 Aug 2009 15:09:28 -0700 Subject: execve: must clear current->clear_child_tid While looking at Jens Rosenboom bug report (http://lkml.org/lkml/2009/7/27/35) about strange sys_futex call done from a dying "ps" program, we found following problem. clone() syscall has special support for TID of created threads. This support includes two features. One (CLONE_CHILD_SETTID) is to set an integer into user memory with the TID value. One (CLONE_CHILD_CLEARTID) is to clear this same integer once the created thread dies. The integer location is a user provided pointer, provided at clone() time. kernel keeps this pointer value into current->clear_child_tid. At execve() time, we should make sure kernel doesnt keep this user provided pointer, as full user memory is replaced by a new one. As glibc fork() actually uses clone() syscall with CLONE_CHILD_SETTID and CLONE_CHILD_CLEARTID set, chances are high that we might corrupt user memory in forked processes. Following sequence could happen: 1) bash (or any program) starts a new process, by a fork() call that glibc maps to a clone( ... CLONE_CHILD_SETTID | CLONE_CHILD_CLEARTID ...) syscall 2) When new process starts, its current->clear_child_tid is set to a location that has a meaning only in bash (or initial program) context (&THREAD_SELF->tid) 3) This new process does the execve() syscall to start a new program. current->clear_child_tid is left unchanged (a non NULL value) 4) If this new program creates some threads, and initial thread exits, kernel will attempt to clear the integer pointed by current->clear_child_tid from mm_release() : if (tsk->clear_child_tid && !(tsk->flags & PF_SIGNALED) && atomic_read(&mm->mm_users) > 1) { u32 __user * tidptr = tsk->clear_child_tid; tsk->clear_child_tid = NULL; /* * We don't check the error code - if userspace has * not set up a proper pointer then tough luck. */ << here >> put_user(0, tidptr); sys_futex(tidptr, FUTEX_WAKE, 1, NULL, NULL, 0); } 5) OR : if new program is not multi-threaded, but spied by /proc/pid users (ps command for example), mm_users > 1, and the exiting program could corrupt 4 bytes in a persistent memory area (shm or memory mapped file) If current->clear_child_tid points to a writeable portion of memory of the new program, kernel happily and silently corrupts 4 bytes of memory, with unexpected effects. Fix is straightforward and should not break any sane program. Reported-by: Jens Rosenboom Acked-by: Linus Torvalds Signed-off-by: Eric Dumazet Signed-off-by: Oleg Nesterov Cc: Peter Zijlstra Cc: Sonny Rao Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Ulrich Drepper Cc: Oleg Nesterov Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 466531eb92c..021e1138556 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -568,18 +568,18 @@ void mm_release(struct task_struct *tsk, struct mm_struct *mm) * the value intact in a core dump, and to save the unnecessary * trouble otherwise. Userland only wants this done for a sys_exit. */ - if (tsk->clear_child_tid - && !(tsk->flags & PF_SIGNALED) - && atomic_read(&mm->mm_users) > 1) { - u32 __user * tidptr = tsk->clear_child_tid; + if (tsk->clear_child_tid) { + if (!(tsk->flags & PF_SIGNALED) && + atomic_read(&mm->mm_users) > 1) { + /* + * We don't check the error code - if userspace has + * not set up a proper pointer then tough luck. + */ + put_user(0, tsk->clear_child_tid); + sys_futex(tsk->clear_child_tid, FUTEX_WAKE, + 1, NULL, NULL, 0); + } tsk->clear_child_tid = NULL; - - /* - * We don't check the error code - if userspace has - * not set up a proper pointer then tough luck. - */ - put_user(0, tidptr); - sys_futex(tidptr, FUTEX_WAKE, 1, NULL, NULL, 0); } } -- cgit v1.2.3 From 0753ba01e126020bf0f8150934903b48935b697d Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Tue, 18 Aug 2009 14:11:10 -0700 Subject: mm: revert "oom: move oom_adj value" The commit 2ff05b2b (oom: move oom_adj value) moveed the oom_adj value to the mm_struct. It was a very good first step for sanitize OOM. However Paul Menage reported the commit makes regression to his job scheduler. Current OOM logic can kill OOM_DISABLED process. Why? His program has the code of similar to the following. ... set_oom_adj(OOM_DISABLE); /* The job scheduler never killed by oom */ ... if (vfork() == 0) { set_oom_adj(0); /* Invoked child can be killed */ execve("foo-bar-cmd"); } .... vfork() parent and child are shared the same mm_struct. then above set_oom_adj(0) doesn't only change oom_adj for vfork() child, it's also change oom_adj for vfork() parent. Then, vfork() parent (job scheduler) lost OOM immune and it was killed. Actually, fork-setting-exec idiom is very frequently used in userland program. We must not break this assumption. Then, this patch revert commit 2ff05b2b and related commit. Reverted commit list --------------------- - commit 2ff05b2b4e (oom: move oom_adj value from task_struct to mm_struct) - commit 4d8b9135c3 (oom: avoid unnecessary mm locking and scanning for OOM_DISABLE) - commit 8123681022 (oom: only oom kill exiting tasks with attached memory) - commit 933b787b57 (mm: copy over oom_adj value at fork time) Signed-off-by: KOSAKI Motohiro Cc: Paul Menage Cc: David Rientjes Cc: KAMEZAWA Hiroyuki Cc: Rik van Riel Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Nick Piggin Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 1 - 1 file changed, 1 deletion(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 021e1138556..144326b7af5 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -426,7 +426,6 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p) init_rwsem(&mm->mmap_sem); INIT_LIST_HEAD(&mm->mmlist); mm->flags = (current->mm) ? current->mm->flags : default_dump_filter; - mm->oom_adj = (current->mm) ? current->mm->oom_adj : 0; mm->core_state = NULL; mm->nr_ptes = 0; set_mm_counter(mm, file_rss, 0); -- cgit v1.2.3 From 4ab6c08336535f8c8e42cf45d7adeda882eff06e Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 26 Aug 2009 14:29:24 -0700 Subject: clone(): fix race between copy_process() and de_thread() Spotted by Hiroshi Shimamoto who also provided the test-case below. copy_process() uses signal->count as a reference counter, but it is not. This test case #include #include #include #include #include #include void *null_thread(void *p) { for (;;) sleep(1); return NULL; } void *exec_thread(void *p) { execl("/bin/true", "/bin/true", NULL); return null_thread(p); } int main(int argc, char **argv) { for (;;) { pid_t pid; int ret, status; pid = fork(); if (pid < 0) break; if (!pid) { pthread_t tid; pthread_create(&tid, NULL, exec_thread, NULL); for (;;) pthread_create(&tid, NULL, null_thread, NULL); } do { ret = waitpid(pid, &status, 0); } while (ret == -1 && errno == EINTR); } return 0; } quickly creates an unkillable task. If copy_process(CLONE_THREAD) races with de_thread() copy_signal()->atomic(signal->count) breaks the signal->notify_count logic, and the execing thread can hang forever in kernel space. Change copy_process() to increment count/live only when we know for sure we can't fail. In this case the forked thread will take care of its reference to signal correctly. If copy_process() fails, check CLONE_THREAD flag. If it it set - do nothing, the counters were not changed and current belongs to the same thread group. If it is not set, ->signal must be released in any case (and ->count must be == 1), the forked child is the only thread in the thread group. We need more cleanups here, in particular signal->count should not be used by de_thread/__exit_signal at all. This patch only fixes the bug. Reported-by: Hiroshi Shimamoto Tested-by: Hiroshi Shimamoto Signed-off-by: Oleg Nesterov Acked-by: Roland McGrath Cc: KAMEZAWA Hiroyuki Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 20 +++++--------------- 1 file changed, 5 insertions(+), 15 deletions(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 144326b7af5..e6c04d462ab 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -815,11 +815,8 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) { struct signal_struct *sig; - if (clone_flags & CLONE_THREAD) { - atomic_inc(¤t->signal->count); - atomic_inc(¤t->signal->live); + if (clone_flags & CLONE_THREAD) return 0; - } sig = kmem_cache_alloc(signal_cachep, GFP_KERNEL); tsk->signal = sig; @@ -877,16 +874,6 @@ void __cleanup_signal(struct signal_struct *sig) kmem_cache_free(signal_cachep, sig); } -static void cleanup_signal(struct task_struct *tsk) -{ - struct signal_struct *sig = tsk->signal; - - atomic_dec(&sig->live); - - if (atomic_dec_and_test(&sig->count)) - __cleanup_signal(sig); -} - static void copy_flags(unsigned long clone_flags, struct task_struct *p) { unsigned long new_flags = p->flags; @@ -1239,6 +1226,8 @@ static struct task_struct *copy_process(unsigned long clone_flags, } if (clone_flags & CLONE_THREAD) { + atomic_inc(¤t->signal->count); + atomic_inc(¤t->signal->live); p->group_leader = current->group_leader; list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group); } @@ -1282,7 +1271,8 @@ bad_fork_cleanup_mm: if (p->mm) mmput(p->mm); bad_fork_cleanup_signal: - cleanup_signal(p); + if (!(clone_flags & CLONE_THREAD)) + __cleanup_signal(p->signal); bad_fork_cleanup_sighand: __cleanup_sighand(p->sighand); bad_fork_cleanup_fs: -- cgit v1.2.3