From 3c90e6e99b08f01d5684a3a07cceae6a543e4fa8 Mon Sep 17 00:00:00 2001 From: Srivatsa Vaddagiri Date: Fri, 9 Nov 2007 22:39:39 +0100 Subject: [PATCH] sched: fix copy_namespace() <-> sched_fork() dependency in do_fork Sukadev Bhattiprolu reported a kernel crash with control groups. There are couple of problems discovered by Suka's test: - The test requires the cgroup filesystem to be mounted with atleast the cpu and ns options (i.e both namespace and cpu controllers are active in the same hierarchy). # mkdir /dev/cpuctl # mount -t cgroup -ocpu,ns none cpuctl (or simply) # mount -t cgroup none cpuctl -> Will activate all controllers in same hierarchy. - The test invokes clone() with CLONE_NEWNS set. This causes a a new child to be created, also a new group (do_fork->copy_namespaces->ns_cgroup_clone-> cgroup_clone) and the child is attached to the new group (cgroup_clone-> attach_task->sched_move_task). At this point in time, the child's scheduler related fields are uninitialized (including its on_rq field, which it has inherited from parent). As a result sched_move_task thinks its on runqueue, when it isn't. As a solution to this problem, I moved sched_fork() call, which initializes scheduler related fields on a new task, before copy_namespaces(). I am not sure though whether moving up will cause other side-effects. Do you see any issue? - The second problem exposed by this test is that task_new_fair() assumes that parent and child will be part of the same group (which needn't be as this test shows). As a result, cfs_rq->curr can be NULL for the child. The solution is to test for curr pointer being NULL in task_new_fair(). With the patch below, I could run ns_exec() fine w/o a crash. Reported-by: Sukadev Bhattiprolu Signed-off-by: Srivatsa Vaddagiri Signed-off-by: Ingo Molnar --- kernel/fork.c | 6 +++--- kernel/sched_fair.c | 3 ++- 2 files changed, 5 insertions(+), 4 deletions(-) diff --git a/kernel/fork.c b/kernel/fork.c index 28a74015198..8ca1a14cdc8 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1123,6 +1123,9 @@ static struct task_struct *copy_process(unsigned long clone_flags, p->blocked_on = NULL; /* not blocked yet */ #endif + /* Perform scheduler related setup. Assign this task to a CPU. */ + sched_fork(p, clone_flags); + if ((retval = security_task_alloc(p))) goto bad_fork_cleanup_policy; if ((retval = audit_alloc(p))) @@ -1212,9 +1215,6 @@ static struct task_struct *copy_process(unsigned long clone_flags, INIT_LIST_HEAD(&p->ptrace_children); INIT_LIST_HEAD(&p->ptrace_list); - /* Perform scheduler related setup. Assign this task to a CPU. */ - sched_fork(p, clone_flags); - /* Now that the task is set up, run cgroup callbacks if * necessary. We need to run them before the task is visible * on the tasklist. */ diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 6c361472cc7..d3c03070872 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -1067,8 +1067,9 @@ static void task_new_fair(struct rq *rq, struct task_struct *p) update_curr(cfs_rq); place_entity(cfs_rq, se, 1); + /* 'curr' will be NULL if the child belongs to a different group */ if (sysctl_sched_child_runs_first && this_cpu == task_cpu(p) && - curr->vruntime < se->vruntime) { + curr && curr->vruntime < se->vruntime) { /* * Upon rescheduling, sched_class::put_prev_task() will place * 'current' within the tree based on its new key value.