ipc/sem: Rework semaphore wakeups
Current sysv sems have a weird ass wakeup scheme that involves keeping
preemption disabled over a potential O(n^2) loop and busy waiting on
that on other CPUs.
Kill this and simply wake the task directly from under the sem_lock.
This was discovered by a migrate_disable() debug feature that
disallows:
spin_lock();
preempt_disable();
spin_unlock()
preempt_enable();
Cc: Manfred Spraul <manfred@colorfullife.com>
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Reported-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Manfred Spraul <manfred@colorfullife.com>
Link: http://lkml.kernel.org/r/1315994224.5040.1.camel@twins
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
diff --git a/ipc/sem.c b/ipc/sem.c
index 8c4f59b..9f6326d 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -607,7 +607,7 @@
curr = sma->sem_base + sop->sem_num;
sem_op = sop->sem_op;
result = curr->semval;
-
+
if (!sem_op && result)
goto would_block;
@@ -634,7 +634,7 @@
un->semadj[sop->sem_num] -= sop->sem_op;
sop--;
}
-
+
return 0;
out_of_range:
@@ -666,6 +666,13 @@
static void wake_up_sem_queue_prepare(struct list_head *pt,
struct sem_queue *q, int error)
{
+#ifdef CONFIG_PREEMPT_RT_BASE
+ struct task_struct *p = q->sleeper;
+ get_task_struct(p);
+ q->status = error;
+ wake_up_process(p);
+ put_task_struct(p);
+#else
if (list_empty(pt)) {
/*
* Hold preempt off so that we don't get preempted and have the
@@ -677,6 +684,7 @@
q->pid = error;
list_add_tail(&q->list, pt);
+#endif
}
/**
@@ -690,6 +698,7 @@
*/
static void wake_up_sem_queue_do(struct list_head *pt)
{
+#ifndef CONFIG_PREEMPT_RT_BASE
struct sem_queue *q, *t;
int did_something;
@@ -702,6 +711,7 @@
}
if (did_something)
preempt_enable();
+#endif
}
static void unlink_queue(struct sem_array *sma, struct sem_queue *q)
@@ -1161,7 +1171,7 @@
err = security_sem_semctl(NULL, cmd);
if (err)
return err;
-
+
memset(&seminfo,0,sizeof(seminfo));
seminfo.semmni = ns->sc_semmni;
seminfo.semmns = ns->sc_semmns;
@@ -1865,7 +1875,7 @@
/* We need to sleep on this operation, so we put the current
* task into the pending queue and go to sleep.
*/
-
+
queue.sops = sops;
queue.nsops = nsops;
queue.undo = un;
@@ -2000,7 +2010,7 @@
return error;
atomic_inc(&undo_list->refcnt);
tsk->sysvsem.undo_list = undo_list;
- } else
+ } else
tsk->sysvsem.undo_list = NULL;
return 0;