summaryrefslogtreecommitdiffstats
path: root/kernel/cpuset.c
diff options
context:
space:
mode:
authorOleg Nesterov <oleg@redhat.com>2010-03-15 10:10:03 +0100
committerIngo Molnar <mingo@elte.hu>2010-04-02 20:12:01 +0200
commit897f0b3c3ff40b443c84e271bef19bd6ae885195 (patch)
tree6b969149bb59591a1c9485de405639db6c4208d6 /kernel/cpuset.c
parent25c2d55c00c6097e6792ebf21e31342f23b9b768 (diff)
downloadlinux-897f0b3c3ff40b443c84e271bef19bd6ae885195.tar.gz
linux-897f0b3c3ff40b443c84e271bef19bd6ae885195.tar.bz2
linux-897f0b3c3ff40b443c84e271bef19bd6ae885195.zip
sched: Kill the broken and deadlockable cpuset_lock/cpuset_cpus_allowed_locked code
This patch just states the fact the cpusets/cpuhotplug interaction is broken and removes the deadlockable code which only pretends to work. - cpuset_lock() doesn't really work. It is needed for cpuset_cpus_allowed_locked() but we can't take this lock in try_to_wake_up()->select_fallback_rq() path. - cpuset_lock() is deadlockable. Suppose that a task T bound to CPU takes callback_mutex. If cpu_down(CPU) happens before T drops callback_mutex stop_machine() preempts T, then migration_call(CPU_DEAD) tries to take cpuset_lock() and hangs forever because CPU is already dead and thus T can't be scheduled. - cpuset_cpus_allowed_locked() is deadlockable too. It takes task_lock() which is not irq-safe, but try_to_wake_up() can be called from irq. Kill them, and change select_fallback_rq() to use cpu_possible_mask, like we currently do without CONFIG_CPUSETS. Also, with or without this patch, with or without CONFIG_CPUSETS, the callers of select_fallback_rq() can race with each other or with set_cpus_allowed() pathes. The subsequent patches try to to fix these problems. Signed-off-by: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20100315091003.GA9123@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Diffstat (limited to 'kernel/cpuset.c')
-rw-r--r--kernel/cpuset.c27
1 files changed, 1 insertions, 26 deletions
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index d10946748ec2..9a747f56d58c 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -2182,19 +2182,10 @@ void __init cpuset_init_smp(void)
void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
{
mutex_lock(&callback_mutex);
- cpuset_cpus_allowed_locked(tsk, pmask);
- mutex_unlock(&callback_mutex);
-}
-
-/**
- * cpuset_cpus_allowed_locked - return cpus_allowed mask from a tasks cpuset.
- * Must be called with callback_mutex held.
- **/
-void cpuset_cpus_allowed_locked(struct task_struct *tsk, struct cpumask *pmask)
-{
task_lock(tsk);
guarantee_online_cpus(task_cs(tsk), pmask);
task_unlock(tsk);
+ mutex_unlock(&callback_mutex);
}
void cpuset_init_current_mems_allowed(void)
@@ -2383,22 +2374,6 @@ int __cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask)
}
/**
- * cpuset_lock - lock out any changes to cpuset structures
- *
- * The out of memory (oom) code needs to mutex_lock cpusets
- * from being changed while it scans the tasklist looking for a
- * task in an overlapping cpuset. Expose callback_mutex via this
- * cpuset_lock() routine, so the oom code can lock it, before
- * locking the task list. The tasklist_lock is a spinlock, so
- * must be taken inside callback_mutex.
- */
-
-void cpuset_lock(void)
-{
- mutex_lock(&callback_mutex);
-}
-
-/**
* cpuset_unlock - release lock on cpuset changes
*
* Undo the lock taken in a previous cpuset_lock() call.