Messages in this thread | | | Date | Mon, 22 Jul 2002 16:58:55 +0200 (CEST) | From | Ingo Molnar <> | Subject | [patch] big IRQ lock removal, 2.5.27-D9 |
| |
On Mon, 22 Jul 2002, Oleg Nesterov wrote:
> Note that smp_xxx_interrupt() functions must be carefull > with preemt_{disable,enable} brackets. > > For example, smp_invalidate_interrupt() may be preempted > after put_cpu(). Probably not big deal (it is return path), > but it is better to use preempt_enable_no_resched() here - > let ret_from_intr: do its job.
i solved it slightly differently: added a new put_cpu_no_resched() macro.
> smp_{error,spurious,thermal}_interrupt() - all of them > use printk() without bumping preemt_count and have problem > after spin_unlock_irqrestore(&logbuf_lock, flags).
fixed this - all these IRQ vector paths must use irq_enter()/irq_exit() pairs.
> If these problems worth fixing, then preempt_stop (cli) can be killed in > entry.S:ret_from_intr(), yes? If i understand correctly none of the irq > handlers should return to low level code with irq enabled.
yes, it can be removed, and i did this.
> May I suggest somebody with good english fix > Documentation/preempt-locking.txt? > It states, that disabled interrupts prevents preemption. > Yes, but only in a sense, that the delivery of reschedule > interrupt is suppressed. > > Process with irqs disabled and current->preempt_count == 0 can > be preempted (with interrupts enabled) after spin_lock/unlock etc. > Even in UP case preemption can happen while calling wake_up_...().
added such a section to preempt-locking.txt.
this and the other changes can be found at:
http://redhat.com/~mingo/remove-irqlock-patches/remove-irqlock-2.5.27-D9
is anything else missing?
Ingo
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |