[PATCH] x86: kernel irq balance doesn't work
On i386, kernel irq balance doesn't work.
1) In function do_irq_balance, after kernel finds the min_loaded cpu but
before calling set_pending_irq to really pin the selected_irq to the
target cpu, kernel does a cpus_and with irq_affinity[selected_irq].
Later on, when the irq is acked, kernel would calls
move_native_irq=>desc->handler->set_affinity to change the irq affinity.
However, every function pointed by
hw_interrupt_type->set_affinity(unsigned int irq, cpumask_t cpumask)
always changes irq_affinity[irq] to cpumask. Next time when recalling
do_irq_balance, it has to do cpu_ands again with
irq_affinity[selected_irq], but irq_affinity[selected_irq] already
becomes one cpu selected by the first irq balance.
2) Function balance_irq in file arch/i386/kernel/io_apic.c has the same
issue.
[akpm@osdl.org: cleanups]
Signed-off-by: Zhang Yanmin <yanmin.zhang@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 42c9cd5..e8a07e7 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -164,6 +164,14 @@
#endif // CONFIG_SMP
+#ifdef CONFIG_IRQBALANCE
+extern void set_balance_irq_affinity(unsigned int irq, cpumask_t mask);
+#else
+static inline void set_balance_irq_affinity(unsigned int irq, cpumask_t mask)
+{
+}
+#endif
+
extern int no_irq_affinity;
extern int noirqdebug_setup(char *str);