X-Git-Url: http://pilppa.org/gitweb/gitweb.cgi?a=blobdiff_plain;f=kernel%2Fcpuset.c;h=12815d3f1a05ee25efc0eb489ff9c6abc4e4cb98;hb=b2e977ca364764dabb091c360f329868b7e3f29b;hp=2a75e44e1a41355bc55cc4819f167e4bc63f0cab;hpb=977127174a7dff52d17faeeb4c4949a54221881f;p=linux-2.6-omap-h63xx.git

diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 2a75e44e1a4..12815d3f1a0 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -641,7 +641,7 @@ static void guarantee_online_mems(const struct cpuset *cs, nodemask_t *pmask)
  * task has been modifying its cpuset.
  */
 
-void cpuset_update_task_memory_state()
+void cpuset_update_task_memory_state(void)
 {
 	int my_cpusets_mem_gen;
 	struct task_struct *tsk = current;
@@ -1554,7 +1554,7 @@ struct ctr_struct {
  * when reading out p->cpuset, as we don't really care if it changes
  * on the next cycle, and we are not going to try to dereference it.
  */
-static inline int pid_array_load(pid_t *pidarray, int npids, struct cpuset *cs)
+static int pid_array_load(pid_t *pidarray, int npids, struct cpuset *cs)
 {
 	int n = 0;
 	struct task_struct *g, *p;
@@ -1977,6 +1977,39 @@ void cpuset_fork(struct task_struct *child)
  * We don't need to task_lock() this reference to tsk->cpuset,
  * because tsk is already marked PF_EXITING, so attach_task() won't
  * mess with it, or task is a failed fork, never visible to attach_task.
+ *
+ * Hack:
+ *
+ *    Set the exiting tasks cpuset to the root cpuset (top_cpuset).
+ *
+ *    Don't leave a task unable to allocate memory, as that is an
+ *    accident waiting to happen should someone add a callout in
+ *    do_exit() after the cpuset_exit() call that might allocate.
+ *    If a task tries to allocate memory with an invalid cpuset,
+ *    it will oops in cpuset_update_task_memory_state().
+ *
+ *    We call cpuset_exit() while the task is still competent to
+ *    handle notify_on_release(), then leave the task attached to
+ *    the root cpuset (top_cpuset) for the remainder of its exit.
+ *
+ *    To do this properly, we would increment the reference count on
+ *    top_cpuset, and near the very end of the kernel/exit.c do_exit()
+ *    code we would add a second cpuset function call, to drop that
+ *    reference.  This would just create an unnecessary hot spot on
+ *    the top_cpuset reference count, to no avail.
+ *
+ *    Normally, holding a reference to a cpuset without bumping its
+ *    count is unsafe.   The cpuset could go away, or someone could
+ *    attach us to a different cpuset, decrementing the count on
+ *    the first cpuset that we never incremented.  But in this case,
+ *    top_cpuset isn't going away, and either task has PF_EXITING set,
+ *    which wards off any attach_task() attempts, or task is a failed
+ *    fork, never visible to attach_task.
+ *
+ *    Another way to do this would be to set the cpuset pointer
+ *    to NULL here, and check in cpuset_update_task_memory_state()
+ *    for a NULL pointer.  This hack avoids that NULL check, for no
+ *    cost (other than this way too long comment ;).
  **/
 
 void cpuset_exit(struct task_struct *tsk)
@@ -1984,7 +2017,7 @@ void cpuset_exit(struct task_struct *tsk)
 	struct cpuset *cs;
 
 	cs = tsk->cpuset;
-	tsk->cpuset = NULL;
+	tsk->cpuset = &top_cpuset;	/* Hack - see comment above */
 
 	if (notify_on_release(cs)) {
 		char *pathbuf = NULL;
@@ -2149,6 +2182,33 @@ int __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask)
 	return allowed;
 }
 
+/**
+ * cpuset_lock - lock out any changes to cpuset structures
+ *
+ * The out of memory (oom) code needs to lock down cpusets
+ * from being changed while it scans the tasklist looking for a
+ * task in an overlapping cpuset.  Expose callback_sem 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_sem.
+ */
+
+void cpuset_lock(void)
+{
+	down(&callback_sem);
+}
+
+/**
+ * cpuset_unlock - release lock on cpuset changes
+ *
+ * Undo the lock taken in a previous cpuset_lock() call.
+ */
+
+void cpuset_unlock(void)
+{
+	up(&callback_sem);
+}
+
 /**
  * cpuset_excl_nodes_overlap - Do we overlap @p's mem_exclusive ancestors?
  * @p: pointer to task_struct of some other task.
@@ -2158,7 +2218,7 @@ int __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask)
  * determine if task @p's memory usage might impact the memory
  * available to the current task.
  *
- * Acquires callback_sem - not suitable for calling from a fast path.
+ * Call while holding callback_sem.
  **/
 
 int cpuset_excl_nodes_overlap(const struct task_struct *p)
@@ -2166,8 +2226,6 @@ int cpuset_excl_nodes_overlap(const struct task_struct *p)
 	const struct cpuset *cs1, *cs2;	/* my and p's cpuset ancestors */
 	int overlap = 0;		/* do cpusets overlap? */
 
-	down(&callback_sem);
-
 	task_lock(current);
 	if (current->flags & PF_EXITING) {
 		task_unlock(current);
@@ -2186,8 +2244,6 @@ int cpuset_excl_nodes_overlap(const struct task_struct *p)
 
 	overlap = nodes_intersects(cs1->mems_allowed, cs2->mems_allowed);
 done:
-	up(&callback_sem);
-
 	return overlap;
 }