From: Ashok Raj <ashok.raj@intel.com>
irq affinity setting via /proc was forcing iosapic rte programming by force.
The correct way to do this is to perform this when a interrupt is pending.
---
25-akpm/arch/ia64/kernel/iosapic.c | 19 +++++++++++++++++++
25-akpm/arch/ia64/kernel/irq.c | 12 +++++++++---
2 files changed, 28 insertions(+), 3 deletions(-)
diff -puN arch/ia64/kernel/iosapic.c~ia64-cpuhotplug-irq_affinity_fix arch/ia64/kernel/iosapic.c
--- 25/arch/ia64/kernel/iosapic.c~ia64-cpuhotplug-irq_affinity_fix Wed Apr 28 14:50:01 2004
+++ 25-akpm/arch/ia64/kernel/iosapic.c Wed Apr 28 14:50:01 2004
@@ -98,6 +98,7 @@
#endif
static spinlock_t iosapic_lock = SPIN_LOCK_UNLOCKED;
+cpumask_t __cacheline_aligned pending_irq_cpumask[NR_IRQS];
/* These tables map IA-64 vectors to the IOSAPIC pin that generates this vector. */
@@ -331,6 +332,21 @@ iosapic_set_affinity (unsigned int irq,
#endif
}
+static inline void move_irq(int irq)
+{
+ /* note - we hold desc->lock */
+ cpumask_t tmp;
+ irq_desc_t *desc = irq_descp(irq);
+
+ if (!cpus_empty(pending_irq_cpumask[irq])) {
+ cpus_and(tmp, pending_irq_cpumask[irq], cpu_online_map);
+ if (unlikely(!cpus_empty(tmp))) {
+ desc->handler->set_affinity(irq, pending_irq_cpumask[irq]);
+ }
+ cpus_clear(pending_irq_cpumask[irq]);
+ }
+}
+
/*
* Handlers for level-triggered interrupts.
*/
@@ -347,6 +363,7 @@ iosapic_end_level_irq (unsigned int irq)
{
ia64_vector vec = irq_to_vector(irq);
+ move_irq(irq);
writel(vec, iosapic_intr_info[vec].addr + IOSAPIC_EOI);
}
@@ -386,6 +403,8 @@ static void
iosapic_ack_edge_irq (unsigned int irq)
{
irq_desc_t *idesc = irq_descp(irq);
+
+ move_irq(irq);
/*
* Once we have recorded IRQ_PENDING already, we can mask the
* interrupt for real. This prevents IRQ storms from unhandled
diff -puN arch/ia64/kernel/irq.c~ia64-cpuhotplug-irq_affinity_fix arch/ia64/kernel/irq.c
--- 25/arch/ia64/kernel/irq.c~ia64-cpuhotplug-irq_affinity_fix Wed Apr 28 14:50:01 2004
+++ 25-akpm/arch/ia64/kernel/irq.c Wed Apr 28 14:50:01 2004
@@ -46,7 +46,7 @@
#include <asm/delay.h>
#include <asm/irq.h>
-
+extern cpumask_t __cacheline_aligned pending_irq_cpumask[NR_IRQS];
/*
* Linux has a controller-independent x86 interrupt architecture.
@@ -938,7 +938,9 @@ void set_irq_affinity_info (unsigned int
static int irq_affinity_read_proc (char *page, char **start, off_t off,
int count, int *eof, void *data)
{
- int len = cpumask_scnprintf(page, count, irq_affinity[(long)data]);
+ int len = sprintf(page, "%s", irq_redir[(long)data] ? "r " : "");
+
+ len += cpumask_scnprintf(page+len, count, irq_affinity[(long)data]);
if (count - len < 2)
return -EINVAL;
len += sprintf(page + len, "\n");
@@ -956,6 +958,7 @@ static int irq_affinity_write_proc (stru
int rlen;
int prelen;
irq_desc_t *desc = irq_descp(irq);
+ unsigned long flags;
if (!desc->handler->set_affinity)
return -EIO;
@@ -994,7 +997,10 @@ static int irq_affinity_write_proc (stru
if (cpus_empty(tmp))
return -EINVAL;
- desc->handler->set_affinity(irq, new_value);
+ spin_lock_irqsave(&desc->lock, flags);
+ pending_irq_cpumask[irq] = new_value;
+ spin_unlock_irqrestore(&desc->lock, flags);
+
return full_count;
}
_