提交 c48e0913 编写于 作者: H Heiko Carstens 提交者: Martin Schwidefsky

[S390] Small barrier() and cpu_relax() cleanup.

cpu_relax() has barrier() semantics hence there is no need to use both
of them in conjunction in sclp_sync_wait(). Also change cpu_relax()
so it's more obvious that it has barrier semantics.
Signed-off-by: NHeiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: NMartin Schwidefsky <schwidefsky@de.ibm.com>
上级 1125b464
......@@ -433,7 +433,6 @@ sclp_sync_wait(void)
get_clock() > timeout &&
del_timer(&sclp_request_timer))
sclp_request_timer.function(sclp_request_timer.data);
barrier();
cpu_relax();
}
local_irq_disable();
......
......@@ -201,9 +201,8 @@ unsigned long get_wchan(struct task_struct *p);
static inline void cpu_relax(void)
{
if (MACHINE_HAS_DIAG44)
asm volatile("diag 0,0,68" : : : "memory");
else
barrier();
asm volatile("diag 0,0,68");
barrier();
}
/*
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册