x86: move kstat_irqs from kstat to irq_desc

based on Eric's patch ...

together mold it with dyn_array for irq_desc, will allcate kstat_irqs for
nr_irq_desc alltogether if needed. -- at that point nr_cpus is known already.

v2: make sure system without generic_hardirqs works they don't have irq_desc
v3: fix merging
v4: [mingo@elte.hu] fix typo

[ mingo@elte.hu ] irq: build fix

fix:

 arch/x86/xen/spinlock.c: In function 'xen_spin_lock_slow':
 arch/x86/xen/spinlock.c:90: error: 'struct kernel_stat' has no member named 'irqs'

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

3 files changed, 76 insertions, 41 deletions

diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 76c225c..2aa3d4b2 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -312,14 +312,13 @@ handle_simple_irq(unsigned int irq, struct irq_desc *desc)
 {
 	struct irqaction *action;
 	irqreturn_t action_ret;
-	const unsigned int cpu = smp_processor_id();
 
 	spin_lock(&desc->lock);
 
 	if (unlikely(desc->status & IRQ_INPROGRESS))
 		goto out_unlock;
 	desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
-	kstat_cpu(cpu).irqs[irq]++;
+	kstat_irqs_this_cpu(desc)++;
 
 	action = desc->action;
 	if (unlikely(!action || (desc->status & IRQ_DISABLED)))
@@ -351,7 +350,6 @@ out_unlock:
 void
 handle_level_irq(unsigned int irq, struct irq_desc *desc)
 {
-	unsigned int cpu = smp_processor_id();
 	struct irqaction *action;
 	irqreturn_t action_ret;
 
@@ -361,7 +359,7 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc)
 	if (unlikely(desc->status & IRQ_INPROGRESS))
 		goto out_unlock;
 	desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
-	kstat_cpu(cpu).irqs[irq]++;
+	kstat_irqs_this_cpu(desc)++;
 
 	/*
 	 * If its disabled or no action available
@@ -399,7 +397,6 @@ out_unlock:
 void
 handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
 {
-	unsigned int cpu = smp_processor_id();
 	struct irqaction *action;
 	irqreturn_t action_ret;
 
@@ -409,7 +406,7 @@ handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
 		goto out;
 
 	desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
-	kstat_cpu(cpu).irqs[irq]++;
+	kstat_irqs_this_cpu(desc)++;
 
 	/*
 	 * If its disabled or no action available
@@ -458,8 +455,6 @@ out:
 void
 handle_edge_irq(unsigned int irq, struct irq_desc *desc)
 {
-	const unsigned int cpu = smp_processor_id();
-
 	spin_lock(&desc->lock);
 
 	desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
@@ -476,7 +471,7 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
 		goto out_unlock;
 	}
 
-	kstat_cpu(cpu).irqs[irq]++;
+	kstat_irqs_this_cpu(desc)++;
 
 	/* Start handling the irq */
 	desc->chip->ack(irq);
@@ -531,7 +526,7 @@ handle_percpu_irq(unsigned int irq, struct irq_desc *desc)
 {
 	irqreturn_t action_ret;
 
-	kstat_this_cpu.irqs[irq]++;
+	kstat_irqs_this_cpu(desc)++;
 
 	if (desc->chip->ack)
 		desc->chip->ack(irq);
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 9fc33b3..1f34699 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -37,7 +37,7 @@ void
 handle_bad_irq(unsigned int irq, struct irq_desc *desc)
 {
 	print_irq_desc(irq, desc);
-	kstat_this_cpu.irqs[irq]++;
+	kstat_irqs_this_cpu(desc)++;
 	ack_bad_irq(irq);
 }
 
@@ -80,17 +80,38 @@ static void init_one_irq_desc(struct irq_desc *desc)
 #endif
 }
 
-#ifdef CONFIG_HAVE_SPARSE_IRQ
-static int nr_irq_desc = 32;
+extern int after_bootmem;
+extern void *__alloc_bootmem_nopanic(unsigned long size,
+			     unsigned long align,
+			     unsigned long goal);
 
-static int __init parse_nr_irq_desc(char *arg)
+static void init_kstat_irqs(struct irq_desc *desc, int nr_desc, int nr)
 {
-	if (arg)
-		nr_irq_desc = simple_strtoul(arg, NULL, 0);
-	return 0;
+	unsigned long bytes, total_bytes;
+	char *ptr;
+	int i;
+	unsigned long phys;
+
+	/* Compute how many bytes we need per irq and allocate them */
+	bytes = nr * sizeof(unsigned int);
+	total_bytes = bytes * nr_desc;
+	if (after_bootmem)
+		ptr = kzalloc(total_bytes, GFP_ATOMIC);
+	else
+		ptr = __alloc_bootmem_nopanic(total_bytes, PAGE_SIZE, 0);
+
+	if (!ptr)
+		panic(" can not allocate kstat_irqs\n");
+
+	phys = __pa(ptr);
+	printk(KERN_DEBUG "kstat_irqs ==> [%#lx - %#lx]\n", phys, phys + total_bytes);
+
+	for (i = 0; i < nr_desc; i++) {
+		desc[i].kstat_irqs = (unsigned int *)ptr;
+		ptr += bytes;
+	}
 }
 
-early_param("nr_irq_desc", parse_nr_irq_desc);
 
 static void __init init_work(void *data)
 {
@@ -100,25 +121,44 @@ static void __init init_work(void *data)
 
 	desc = *da->name;
 
-	for (i = 0; i < *da->nr; i++)
+	for (i = 0; i < *da->nr; i++) {
 		init_one_irq_desc(&desc[i]);
+#ifndef CONFIG_HAVE_SPARSE_IRQ
+		desc[i].irq = i;
+#endif
+	}
 
+#ifdef CONFIG_HAVE_SPARSE_IRQ
 	for (i = 1; i < *da->nr; i++)
 		desc[i-1].next = &desc[i];
+#endif
+
+	/* init kstat_irqs, nr_cpu_ids is ready already */
+	init_kstat_irqs(desc, *da->nr, nr_cpu_ids);
 }
 
+#ifdef CONFIG_HAVE_SPARSE_IRQ
+static int nr_irq_desc = 32;
+
+static int __init parse_nr_irq_desc(char *arg)
+{
+	if (arg)
+		nr_irq_desc = simple_strtoul(arg, NULL, 0);
+	return 0;
+}
+
+early_param("nr_irq_desc", parse_nr_irq_desc);
+
 static struct irq_desc *sparse_irqs;
 DEFINE_DYN_ARRAY(sparse_irqs, sizeof(struct irq_desc), nr_irq_desc, PAGE_SIZE, init_work);
 
-extern int after_bootmem;
-extern void *__alloc_bootmem_nopanic(unsigned long size,
-			     unsigned long align,
-			     unsigned long goal);
 struct irq_desc *irq_to_desc(unsigned int irq)
 {
 	struct irq_desc *desc, *desc_pri;
 	int i;
 	int count = 0;
+	unsigned long phys;
+	unsigned long total_bytes;
 
 	BUG_ON(irq == -1U);
 
@@ -141,38 +181,34 @@ struct irq_desc *irq_to_desc(unsigned int irq)
 	 */
 	printk(KERN_DEBUG "try to get more irq_desc %d\n", nr_irq_desc);
 
+	total_bytes = sizeof(struct irq_desc) * nr_irq_desc;
 	if (after_bootmem)
-		desc = kzalloc(sizeof(struct irq_desc)*nr_irq_desc, GFP_ATOMIC);
+		desc = kzalloc(total_bytes, GFP_ATOMIC);
 	else
-		desc = __alloc_bootmem_nopanic(sizeof(struct irq_desc)*nr_irq_desc, PAGE_SIZE, 0);
+		desc = __alloc_bootmem_nopanic(total_bytes, PAGE_SIZE, 0);
 
 	if (!desc)
 		panic("please boot with nr_irq_desc= %d\n", count * 2);
 
+	phys = __pa(desc);
+	printk(KERN_DEBUG "irq_desc ==> [%#lx - %#lx]\n", phys, phys + total_bytes);
+
 	for (i = 0; i < nr_irq_desc; i++)
 		init_one_irq_desc(&desc[i]);
 
 	for (i = 1; i < nr_irq_desc; i++)
 		desc[i-1].next = &desc[i];
 
+	/* init kstat_irqs, nr_cpu_ids is ready already */
+	init_kstat_irqs(desc, nr_irq_desc, nr_cpu_ids);
+
 	desc->irq = irq;
 	desc_pri->next = desc;
 
 	return desc;
 }
 #else
-static void __init init_work(void *data)
-{
-	struct dyn_array *da = data;
-	int i;
-	struct  irq_desc *desc;
-
-	desc = *da->name;
 
-	for (i = 0; i < *da->nr; i++)
-		init_one_irq_desc(&desc[i]);
-
-}
 static struct irq_desc *irq_desc;
 DEFINE_DYN_ARRAY(irq_desc, sizeof(struct irq_desc), nr_irqs, PAGE_SIZE, init_work);
 
@@ -315,7 +351,7 @@ unsigned int __do_IRQ(unsigned int irq)
 	struct irqaction *action;
 	unsigned int status;
 
-	kstat_this_cpu.irqs[irq]++;
+	kstat_irqs_this_cpu(desc)++;
 	if (CHECK_IRQ_PER_CPU(desc->status)) {
 		irqreturn_t action_ret;
 
@@ -415,3 +451,10 @@ void early_init_irq_lock_class(void)
 }
 #endif
 
+unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+	return desc->kstat_irqs[cpu];
+}
+EXPORT_SYMBOL(kstat_irqs_cpu);
+
diff --git a/kernel/sched.c b/kernel/sched.c
index b9d7137..6f23059 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4048,11 +4048,8 @@ static inline void idle_balance(int cpu, struct rq *rq)
 #endif
 
 DEFINE_PER_CPU(struct kernel_stat, kstat);
-EXPORT_PER_CPU_SYMBOL(kstat);
 
-#ifdef CONFIG_HAVE_DYN_ARRAY
-DEFINE_PER_CPU_DYN_ARRAY_ADDR(per_cpu__kstat_irqs, per_cpu__kstat.irqs, sizeof(unsigned int), nr_irqs, sizeof(unsigned long), NULL);
-#endif
+EXPORT_PER_CPU_SYMBOL(kstat);
 
 /*
  * Return p->sum_exec_runtime plus any more ns on the sched_clock