提交 bf664c0a 编写于 作者: M Mike Frysinger

Blackfin: fix sparseirq/kstat_irqs fallout

The sparseirq changes (d7e51e66) played poorly with the Blackfin irqchip
implementation as we're still using the old hardirq method.  Our bad irq
structure had a NULL kstat_irqs field so when all the common code tries
to increment this field, everything goes big bada boom.
Signed-off-by: NMike Frysinger <vapier@gentoo.org>
上级 ce0bf52d
...@@ -59,12 +59,14 @@ static struct irq_chip bad_chip = { ...@@ -59,12 +59,14 @@ static struct irq_chip bad_chip = {
.unmask = dummy_mask_unmask_irq, .unmask = dummy_mask_unmask_irq,
}; };
static int bad_stats;
static struct irq_desc bad_irq_desc = { static struct irq_desc bad_irq_desc = {
.status = IRQ_DISABLED, .status = IRQ_DISABLED,
.chip = &bad_chip, .chip = &bad_chip,
.handle_irq = handle_bad_irq, .handle_irq = handle_bad_irq,
.depth = 1, .depth = 1,
.lock = __SPIN_LOCK_UNLOCKED(irq_desc->lock), .lock = __SPIN_LOCK_UNLOCKED(irq_desc->lock),
.kstat_irqs = &bad_stats,
#ifdef CONFIG_SMP #ifdef CONFIG_SMP
.affinity = CPU_MASK_ALL .affinity = CPU_MASK_ALL
#endif #endif
......
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