X-Git-Url: http://pilppa.org/gitweb/gitweb.cgi?a=blobdiff_plain;f=arch%2Fx86%2Fkernel%2Fio_apic_32.c;h=59d2e8a273e31ac8452a3e5df25659f71bf8d54b;hb=0f978f4505e96227a89b3c9447552aca983c6b57;hp=e710289f673e86503d1ba9d77e1770e3559c1ccd;hpb=446d27338d3b422dd3dfe496d0f362230994d059;p=linux-2.6-omap-h63xx.git

diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index e710289f673..59d2e8a273e 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -70,6 +70,7 @@ int timer_through_8259 __initdata;
  */
 int sis_apic_bug = -1;
 
+int first_free_entry;
 /*
  * # of IRQ routing registers
  */
@@ -93,12 +94,180 @@ DECLARE_BITMAP(mp_bus_not_pci, MAX_MP_BUSSES);
 
 static int disable_timer_pin_1 __initdata;
 
+struct irq_cfg;
+struct irq_pin_list;
+struct irq_cfg {
+	unsigned int irq;
+	struct irq_cfg *next;
+	struct irq_pin_list *irq_2_pin;
+	u8 vector;
+};
+
+
+/* irq_cfg is indexed by the sum of all RTEs in all I/O APICs. */
+static struct irq_cfg irq_cfg_legacy[] __initdata = {
+	[0]  = { .irq =  0, .vector = IRQ0_VECTOR,  },
+	[1]  = { .irq =  1, .vector = IRQ1_VECTOR,  },
+	[2]  = { .irq =  2, .vector = IRQ2_VECTOR,  },
+	[3]  = { .irq =  3, .vector = IRQ3_VECTOR,  },
+	[4]  = { .irq =  4, .vector = IRQ4_VECTOR,  },
+	[5]  = { .irq =  5, .vector = IRQ5_VECTOR,  },
+	[6]  = { .irq =  6, .vector = IRQ6_VECTOR,  },
+	[7]  = { .irq =  7, .vector = IRQ7_VECTOR,  },
+	[8]  = { .irq =  8, .vector = IRQ8_VECTOR,  },
+	[9]  = { .irq =  9, .vector = IRQ9_VECTOR,  },
+	[10] = { .irq = 10, .vector = IRQ10_VECTOR, },
+	[11] = { .irq = 11, .vector = IRQ11_VECTOR, },
+	[12] = { .irq = 12, .vector = IRQ12_VECTOR, },
+	[13] = { .irq = 13, .vector = IRQ13_VECTOR, },
+	[14] = { .irq = 14, .vector = IRQ14_VECTOR, },
+	[15] = { .irq = 15, .vector = IRQ15_VECTOR, },
+};
+
+static struct irq_cfg irq_cfg_init = { .irq =  -1U, };
+/* need to be biger than size of irq_cfg_legacy */
+static int nr_irq_cfg = 32;
+
+static int __init parse_nr_irq_cfg(char *arg)
+{
+	if (arg) {
+		nr_irq_cfg = simple_strtoul(arg, NULL, 0);
+		if (nr_irq_cfg < 32)
+			nr_irq_cfg = 32;
+	}
+	return 0;
+}
+
+early_param("nr_irq_cfg", parse_nr_irq_cfg);
+
+static void init_one_irq_cfg(struct irq_cfg *cfg)
+{
+	memcpy(cfg, &irq_cfg_init, sizeof(struct irq_cfg));
+}
+
+static struct irq_cfg *irq_cfgx;
+static struct irq_cfg *irq_cfgx_free;
+static void __init init_work(void *data)
+{
+	struct dyn_array *da = data;
+	struct irq_cfg *cfg;
+	int legacy_count;
+	int i;
+
+	cfg = *da->name;
+
+	memcpy(cfg, irq_cfg_legacy, sizeof(irq_cfg_legacy));
+
+	legacy_count = sizeof(irq_cfg_legacy)/sizeof(irq_cfg_legacy[0]);
+	for (i = legacy_count; i < *da->nr; i++)
+		init_one_irq_cfg(&cfg[i]);
+
+	for (i = 1; i < *da->nr; i++)
+		cfg[i-1].next = &cfg[i];
+
+	irq_cfgx_free = &irq_cfgx[legacy_count];
+	irq_cfgx[legacy_count - 1].next = NULL;
+}
+
+#define for_each_irq_cfg(cfg)           \
+	for (cfg = irq_cfgx; cfg; cfg = cfg->next)
+
+DEFINE_DYN_ARRAY(irq_cfgx, sizeof(struct irq_cfg), nr_irq_cfg, PAGE_SIZE, init_work);
+
+static struct irq_cfg *irq_cfg(unsigned int irq)
+{
+	struct irq_cfg *cfg;
+
+	cfg = irq_cfgx;
+	while (cfg) {
+		if (cfg->irq == irq)
+			return cfg;
+
+		cfg = cfg->next;
+	}
+
+	return NULL;
+}
+
+static struct irq_cfg *irq_cfg_alloc(unsigned int irq)
+{
+	struct irq_cfg *cfg, *cfg_pri;
+	int i;
+	int count = 0;
+
+	cfg_pri = cfg = irq_cfgx;
+	while (cfg) {
+		if (cfg->irq == irq)
+			return cfg;
+
+		cfg_pri = cfg;
+		cfg = cfg->next;
+		count++;
+	}
+
+	if (!irq_cfgx_free) {
+		unsigned long phys;
+		unsigned long total_bytes;
+		/*
+		 *  we run out of pre-allocate ones, allocate more
+		 */
+		printk(KERN_DEBUG "try to get more irq_cfg %d\n", nr_irq_cfg);
+
+		total_bytes = sizeof(struct irq_cfg) * nr_irq_cfg;
+		if (after_bootmem)
+			cfg = kzalloc(total_bytes, GFP_ATOMIC);
+		else
+			cfg = __alloc_bootmem_nopanic(total_bytes, PAGE_SIZE, 0);
+
+		if (!cfg)
+			panic("please boot with nr_irq_cfg= %d\n", count * 2);
+
+		phys = __pa(cfg);
+		printk(KERN_DEBUG "irq_irq ==> [%#lx - %#lx]\n", phys, phys + total_bytes);
+
+		for (i = 0; i < nr_irq_cfg; i++)
+			init_one_irq_cfg(&cfg[i]);
+
+		for (i = 1; i < nr_irq_cfg; i++)
+			cfg[i-1].next = &cfg[i];
+
+		irq_cfgx_free = cfg;
+	}
+
+	cfg = irq_cfgx_free;
+	irq_cfgx_free = irq_cfgx_free->next;
+	cfg->next = NULL;
+	if (cfg_pri)
+		cfg_pri->next = cfg;
+	else
+		irq_cfgx = cfg;
+	cfg->irq = irq;
+	printk(KERN_DEBUG "found new irq_cfg for irq %d\n", cfg->irq);
+
+#ifdef CONFIG_HAVE_SPARSE_IRQ_DEBUG
+	{
+		/* dump the results */
+		struct irq_cfg *cfg;
+		unsigned long phys;
+		unsigned long bytes = sizeof(struct irq_cfg);
+
+		printk(KERN_DEBUG "=========================== %d\n", irq);
+		printk(KERN_DEBUG "irq_cfg dump after get that for %d\n", irq);
+		for_each_irq_cfg(cfg) {
+			phys = __pa(cfg);
+			printk(KERN_DEBUG "irq_cfg %d ==> [%#lx - %#lx]\n", cfg->irq, phys, phys + bytes);
+		}
+		printk(KERN_DEBUG "===========================\n");
+	}
+#endif
+	return cfg;
+}
+
 /*
  * Rough estimation of how many shared IRQs there are, can
  * be changed anytime.
  */
-#define MAX_PLUS_SHARED_IRQS NR_IRQS
-#define PIN_MAP_SIZE (MAX_PLUS_SHARED_IRQS + NR_IRQS)
+int pin_map_size;
 
 /*
  * This is performance-critical, we want to do it O(1)
@@ -107,9 +276,66 @@ static int disable_timer_pin_1 __initdata;
  * between pins and IRQs.
  */
 
-static struct irq_pin_list {
-	int apic, pin, next;
-} irq_2_pin[PIN_MAP_SIZE];
+struct irq_pin_list {
+	int apic, pin;
+	struct irq_pin_list *next;
+};
+
+static struct irq_pin_list *irq_2_pin_head;
+/* fill one page ? */
+static int nr_irq_2_pin = 0x100;
+static struct irq_pin_list *irq_2_pin_ptr;
+static void __init irq_2_pin_init_work(void *data)
+{
+	struct dyn_array *da = data;
+	struct irq_pin_list *pin;
+	int i;
+
+	pin = *da->name;
+
+	for (i = 1; i < *da->nr; i++)
+		pin[i-1].next = &pin[i];
+
+	irq_2_pin_ptr = &pin[0];
+}
+DEFINE_DYN_ARRAY(irq_2_pin_head, sizeof(struct irq_pin_list), nr_irq_2_pin, PAGE_SIZE, irq_2_pin_init_work);
+
+static struct irq_pin_list *get_one_free_irq_2_pin(void)
+{
+	struct irq_pin_list *pin;
+	int i;
+
+	pin = irq_2_pin_ptr;
+
+	if (pin) {
+		irq_2_pin_ptr = pin->next;
+		pin->next = NULL;
+		return pin;
+	}
+
+	/*
+	 *  we run out of pre-allocate ones, allocate more
+	 */
+	printk(KERN_DEBUG "try to get more irq_2_pin %d\n", nr_irq_2_pin);
+
+	if (after_bootmem)
+		pin = kzalloc(sizeof(struct irq_pin_list)*nr_irq_2_pin,
+				 GFP_ATOMIC);
+	else
+		pin = __alloc_bootmem_nopanic(sizeof(struct irq_pin_list) *
+				nr_irq_2_pin, PAGE_SIZE, 0);
+
+	if (!pin)
+		panic("can not get more irq_2_pin\n");
+
+	for (i = 1; i < nr_irq_2_pin; i++)
+		pin[i-1].next = &pin[i];
+
+	irq_2_pin_ptr = pin->next;
+	pin->next = NULL;
+
+	return pin;
+}
 
 struct io_apic {
 	unsigned int index;
@@ -213,20 +439,34 @@ static void ioapic_mask_entry(int apic, int pin)
  */
 static void add_pin_to_irq(unsigned int irq, int apic, int pin)
 {
-	static int first_free_entry = NR_IRQS;
-	struct irq_pin_list *entry = irq_2_pin + irq;
+	struct irq_cfg *cfg;
+	struct irq_pin_list *entry;
+
+	/* first time to refer irq_cfg, so with new */
+	cfg = irq_cfg_alloc(irq);
+	entry = cfg->irq_2_pin;
+	if (!entry) {
+		entry = get_one_free_irq_2_pin();
+		cfg->irq_2_pin = entry;
+		entry->apic = apic;
+		entry->pin = pin;
+		printk(KERN_DEBUG " 0 add_pin_to_irq: irq %d --> apic %d pin %d\n", irq, apic, pin);
+		return;
+	}
 
-	while (entry->next)
-		entry = irq_2_pin + entry->next;
+	while (entry->next) {
+		/* not again, please */
+		if (entry->apic == apic && entry->pin == pin)
+			return;
 
-	if (entry->pin != -1) {
-		entry->next = first_free_entry;
-		entry = irq_2_pin + entry->next;
-		if (++first_free_entry >= PIN_MAP_SIZE)
-			panic("io_apic.c: whoops");
+		entry = entry->next;
 	}
+
+	entry->next = get_one_free_irq_2_pin();
+	entry = entry->next;
 	entry->apic = apic;
 	entry->pin = pin;
+	printk(KERN_DEBUG " x add_pin_to_irq: irq %d --> apic %d pin %d\n", irq, apic, pin);
 }
 
 /*
@@ -236,35 +476,45 @@ static void __init replace_pin_at_irq(unsigned int irq,
 				      int oldapic, int oldpin,
 				      int newapic, int newpin)
 {
-	struct irq_pin_list *entry = irq_2_pin + irq;
+	struct irq_cfg *cfg = irq_cfg(irq);
+	struct irq_pin_list *entry = cfg->irq_2_pin;
+	int replaced = 0;
 
-	while (1) {
+	while (entry) {
 		if (entry->apic == oldapic && entry->pin == oldpin) {
 			entry->apic = newapic;
 			entry->pin = newpin;
-		}
-		if (!entry->next)
+			replaced = 1;
+			/* every one is different, right? */
 			break;
-		entry = irq_2_pin + entry->next;
+		}
+		entry = entry->next;
 	}
+
+	/* why? call replace before add? */
+	if (!replaced)
+		add_pin_to_irq(irq, newapic, newpin);
 }
 
 static void __modify_IO_APIC_irq(unsigned int irq, unsigned long enable, unsigned long disable)
 {
-	struct irq_pin_list *entry = irq_2_pin + irq;
+	struct irq_cfg *cfg;
+	struct irq_pin_list *entry;
 	unsigned int pin, reg;
 
+	cfg = irq_cfg(irq);
+	entry = cfg->irq_2_pin;
 	for (;;) {
-		pin = entry->pin;
-		if (pin == -1)
+		if (!entry)
 			break;
+		pin = entry->pin;
 		reg = io_apic_read(entry->apic, 0x10 + pin*2);
 		reg &= ~disable;
 		reg |= enable;
 		io_apic_modify(entry->apic, 0x10 + pin*2, reg);
 		if (!entry->next)
 			break;
-		entry = irq_2_pin + entry->next;
+		entry = entry->next;
 	}
 }
 
@@ -339,11 +589,17 @@ static void clear_IO_APIC(void)
 #ifdef CONFIG_SMP
 static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t cpumask)
 {
+	struct irq_cfg *cfg;
 	unsigned long flags;
 	int pin;
-	struct irq_pin_list *entry = irq_2_pin + irq;
+	struct irq_pin_list *entry;
 	unsigned int apicid_value;
 	cpumask_t tmp;
+	struct irq_desc *desc;
+
+
+	cfg = irq_cfg(irq);
+	entry = cfg->irq_2_pin;
 
 	cpus_and(tmp, cpumask, cpu_online_map);
 	if (cpus_empty(tmp))
@@ -356,394 +612,19 @@ static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t cpumask)
 	apicid_value = apicid_value << 24;
 	spin_lock_irqsave(&ioapic_lock, flags);
 	for (;;) {
-		pin = entry->pin;
-		if (pin == -1)
+		if (!entry)
 			break;
+		pin = entry->pin;
 		io_apic_write(entry->apic, 0x10 + 1 + pin*2, apicid_value);
 		if (!entry->next)
 			break;
-		entry = irq_2_pin + entry->next;
+		entry = entry->next;
 	}
-	irq_desc[irq].affinity = cpumask;
+	desc = irq_to_desc(irq);
+	desc->affinity = cpumask;
 	spin_unlock_irqrestore(&ioapic_lock, flags);
 }
 
-#if defined(CONFIG_IRQBALANCE)
-# include <asm/processor.h>	/* kernel_thread() */
-# include <linux/kernel_stat.h>	/* kstat */
-# include <linux/slab.h>		/* kmalloc() */
-# include <linux/timer.h>
-
-#define IRQBALANCE_CHECK_ARCH -999
-#define MAX_BALANCED_IRQ_INTERVAL	(5*HZ)
-#define MIN_BALANCED_IRQ_INTERVAL	(HZ/2)
-#define BALANCED_IRQ_MORE_DELTA		(HZ/10)
-#define BALANCED_IRQ_LESS_DELTA		(HZ)
-
-static int irqbalance_disabled __read_mostly = IRQBALANCE_CHECK_ARCH;
-static int physical_balance __read_mostly;
-static long balanced_irq_interval __read_mostly = MAX_BALANCED_IRQ_INTERVAL;
-
-static struct irq_cpu_info {
-	unsigned long *last_irq;
-	unsigned long *irq_delta;
-	unsigned long irq;
-} irq_cpu_data[NR_CPUS];
-
-#define CPU_IRQ(cpu)		(irq_cpu_data[cpu].irq)
-#define LAST_CPU_IRQ(cpu, irq)   (irq_cpu_data[cpu].last_irq[irq])
-#define IRQ_DELTA(cpu, irq) 	(irq_cpu_data[cpu].irq_delta[irq])
-
-#define IDLE_ENOUGH(cpu,now) \
-	(idle_cpu(cpu) && ((now) - per_cpu(irq_stat, (cpu)).idle_timestamp > 1))
-
-#define IRQ_ALLOWED(cpu, allowed_mask)	cpu_isset(cpu, allowed_mask)
-
-#define CPU_TO_PACKAGEINDEX(i) (first_cpu(per_cpu(cpu_sibling_map, i)))
-
-static cpumask_t balance_irq_affinity[NR_IRQS] = {
-	[0 ... NR_IRQS-1] = CPU_MASK_ALL
-};
-
-void set_balance_irq_affinity(unsigned int irq, cpumask_t mask)
-{
-	balance_irq_affinity[irq] = mask;
-}
-
-static unsigned long move(int curr_cpu, cpumask_t allowed_mask,
-			unsigned long now, int direction)
-{
-	int search_idle = 1;
-	int cpu = curr_cpu;
-
-	goto inside;
-
-	do {
-		if (unlikely(cpu == curr_cpu))
-			search_idle = 0;
-inside:
-		if (direction == 1) {
-			cpu++;
-			if (cpu >= NR_CPUS)
-				cpu = 0;
-		} else {
-			cpu--;
-			if (cpu == -1)
-				cpu = NR_CPUS-1;
-		}
-	} while (!cpu_online(cpu) || !IRQ_ALLOWED(cpu, allowed_mask) ||
-			(search_idle && !IDLE_ENOUGH(cpu, now)));
-
-	return cpu;
-}
-
-static inline void balance_irq(int cpu, int irq)
-{
-	unsigned long now = jiffies;
-	cpumask_t allowed_mask;
-	unsigned int new_cpu;
-
-	if (irqbalance_disabled)
-		return;
-
-	cpus_and(allowed_mask, cpu_online_map, balance_irq_affinity[irq]);
-	new_cpu = move(cpu, allowed_mask, now, 1);
-	if (cpu != new_cpu)
-		set_pending_irq(irq, cpumask_of_cpu(new_cpu));
-}
-
-static inline void rotate_irqs_among_cpus(unsigned long useful_load_threshold)
-{
-	int i, j;
-
-	for_each_online_cpu(i) {
-		for (j = 0; j < NR_IRQS; j++) {
-			if (!irq_desc[j].action)
-				continue;
-			/* Is it a significant load ?  */
-			if (IRQ_DELTA(CPU_TO_PACKAGEINDEX(i), j) <
-						useful_load_threshold)
-				continue;
-			balance_irq(i, j);
-		}
-	}
-	balanced_irq_interval = max((long)MIN_BALANCED_IRQ_INTERVAL,
-		balanced_irq_interval - BALANCED_IRQ_LESS_DELTA);
-	return;
-}
-
-static void do_irq_balance(void)
-{
-	int i, j;
-	unsigned long max_cpu_irq = 0, min_cpu_irq = (~0);
-	unsigned long move_this_load = 0;
-	int max_loaded = 0, min_loaded = 0;
-	int load;
-	unsigned long useful_load_threshold = balanced_irq_interval + 10;
-	int selected_irq;
-	int tmp_loaded, first_attempt = 1;
-	unsigned long tmp_cpu_irq;
-	unsigned long imbalance = 0;
-	cpumask_t allowed_mask, target_cpu_mask, tmp;
-
-	for_each_possible_cpu(i) {
-		int package_index;
-		CPU_IRQ(i) = 0;
-		if (!cpu_online(i))
-			continue;
-		package_index = CPU_TO_PACKAGEINDEX(i);
-		for (j = 0; j < NR_IRQS; j++) {
-			unsigned long value_now, delta;
-			/* Is this an active IRQ or balancing disabled ? */
-			if (!irq_desc[j].action || irq_balancing_disabled(j))
-				continue;
-			if (package_index == i)
-				IRQ_DELTA(package_index, j) = 0;
-			/* Determine the total count per processor per IRQ */
-			value_now = (unsigned long) kstat_cpu(i).irqs[j];
-
-			/* Determine the activity per processor per IRQ */
-			delta = value_now - LAST_CPU_IRQ(i, j);
-
-			/* Update last_cpu_irq[][] for the next time */
-			LAST_CPU_IRQ(i, j) = value_now;
-
-			/* Ignore IRQs whose rate is less than the clock */
-			if (delta < useful_load_threshold)
-				continue;
-			/* update the load for the processor or package total */
-			IRQ_DELTA(package_index, j) += delta;
-
-			/* Keep track of the higher numbered sibling as well */
-			if (i != package_index)
-				CPU_IRQ(i) += delta;
-			/*
-			 * We have sibling A and sibling B in the package
-			 *
-			 * cpu_irq[A] = load for cpu A + load for cpu B
-			 * cpu_irq[B] = load for cpu B
-			 */
-			CPU_IRQ(package_index) += delta;
-		}
-	}
-	/* Find the least loaded processor package */
-	for_each_online_cpu(i) {
-		if (i != CPU_TO_PACKAGEINDEX(i))
-			continue;
-		if (min_cpu_irq > CPU_IRQ(i)) {
-			min_cpu_irq = CPU_IRQ(i);
-			min_loaded = i;
-		}
-	}
-	max_cpu_irq = ULONG_MAX;
-
-tryanothercpu:
-	/*
-	 * Look for heaviest loaded processor.
-	 * We may come back to get the next heaviest loaded processor.
-	 * Skip processors with trivial loads.
-	 */
-	tmp_cpu_irq = 0;
-	tmp_loaded = -1;
-	for_each_online_cpu(i) {
-		if (i != CPU_TO_PACKAGEINDEX(i))
-			continue;
-		if (max_cpu_irq <= CPU_IRQ(i))
-			continue;
-		if (tmp_cpu_irq < CPU_IRQ(i)) {
-			tmp_cpu_irq = CPU_IRQ(i);
-			tmp_loaded = i;
-		}
-	}
-
-	if (tmp_loaded == -1) {
-	 /*
-	  * In the case of small number of heavy interrupt sources,
-	  * loading some of the cpus too much. We use Ingo's original
-	  * approach to rotate them around.
-	  */
-		if (!first_attempt && imbalance >= useful_load_threshold) {
-			rotate_irqs_among_cpus(useful_load_threshold);
-			return;
-		}
-		goto not_worth_the_effort;
-	}
-
-	first_attempt = 0;		/* heaviest search */
-	max_cpu_irq = tmp_cpu_irq;	/* load */
-	max_loaded = tmp_loaded;	/* processor */
-	imbalance = (max_cpu_irq - min_cpu_irq) / 2;
-
-	/*
-	 * if imbalance is less than approx 10% of max load, then
-	 * observe diminishing returns action. - quit
-	 */
-	if (imbalance < (max_cpu_irq >> 3))
-		goto not_worth_the_effort;
-
-tryanotherirq:
-	/* if we select an IRQ to move that can't go where we want, then
-	 * see if there is another one to try.
-	 */
-	move_this_load = 0;
-	selected_irq = -1;
-	for (j = 0; j < NR_IRQS; j++) {
-		/* Is this an active IRQ? */
-		if (!irq_desc[j].action)
-			continue;
-		if (imbalance <= IRQ_DELTA(max_loaded, j))
-			continue;
-		/* Try to find the IRQ that is closest to the imbalance
-		 * without going over.
-		 */
-		if (move_this_load < IRQ_DELTA(max_loaded, j)) {
-			move_this_load = IRQ_DELTA(max_loaded, j);
-			selected_irq = j;
-		}
-	}
-	if (selected_irq == -1)
-		goto tryanothercpu;
-
-	imbalance = move_this_load;
-
-	/* For physical_balance case, we accumulated both load
-	 * values in the one of the siblings cpu_irq[],
-	 * to use the same code for physical and logical processors
-	 * as much as possible.
-	 *
-	 * NOTE: the cpu_irq[] array holds the sum of the load for
-	 * sibling A and sibling B in the slot for the lowest numbered
-	 * sibling (A), _AND_ the load for sibling B in the slot for
-	 * the higher numbered sibling.
-	 *
-	 * We seek the least loaded sibling by making the comparison
-	 * (A+B)/2 vs B
-	 */
-	load = CPU_IRQ(min_loaded) >> 1;
-	for_each_cpu_mask(j, per_cpu(cpu_sibling_map, min_loaded)) {
-		if (load > CPU_IRQ(j)) {
-			/* This won't change cpu_sibling_map[min_loaded] */
-			load = CPU_IRQ(j);
-			min_loaded = j;
-		}
-	}
-
-	cpus_and(allowed_mask,
-		cpu_online_map,
-		balance_irq_affinity[selected_irq]);
-	target_cpu_mask = cpumask_of_cpu(min_loaded);
-	cpus_and(tmp, target_cpu_mask, allowed_mask);
-
-	if (!cpus_empty(tmp)) {
-		/* mark for change destination */
-		set_pending_irq(selected_irq, cpumask_of_cpu(min_loaded));
-
-		/* Since we made a change, come back sooner to
-		 * check for more variation.
-		 */
-		balanced_irq_interval = max((long)MIN_BALANCED_IRQ_INTERVAL,
-			balanced_irq_interval - BALANCED_IRQ_LESS_DELTA);
-		return;
-	}
-	goto tryanotherirq;
-
-not_worth_the_effort:
-	/*
-	 * if we did not find an IRQ to move, then adjust the time interval
-	 * upward
-	 */
-	balanced_irq_interval = min((long)MAX_BALANCED_IRQ_INTERVAL,
-		balanced_irq_interval + BALANCED_IRQ_MORE_DELTA);
-	return;
-}
-
-static int balanced_irq(void *unused)
-{
-	int i;
-	unsigned long prev_balance_time = jiffies;
-	long time_remaining = balanced_irq_interval;
-
-	/* push everything to CPU 0 to give us a starting point.  */
-	for (i = 0 ; i < NR_IRQS ; i++) {
-		irq_desc[i].pending_mask = cpumask_of_cpu(0);
-		set_pending_irq(i, cpumask_of_cpu(0));
-	}
-
-	set_freezable();
-	for ( ; ; ) {
-		time_remaining = schedule_timeout_interruptible(time_remaining);
-		try_to_freeze();
-		if (time_after(jiffies,
-				prev_balance_time+balanced_irq_interval)) {
-			preempt_disable();
-			do_irq_balance();
-			prev_balance_time = jiffies;
-			time_remaining = balanced_irq_interval;
-			preempt_enable();
-		}
-	}
-	return 0;
-}
-
-static int __init balanced_irq_init(void)
-{
-	int i;
-	struct cpuinfo_x86 *c;
-	cpumask_t tmp;
-
-	cpus_shift_right(tmp, cpu_online_map, 2);
-	c = &boot_cpu_data;
-	/* When not overwritten by the command line ask subarchitecture. */
-	if (irqbalance_disabled == IRQBALANCE_CHECK_ARCH)
-		irqbalance_disabled = NO_BALANCE_IRQ;
-	if (irqbalance_disabled)
-		return 0;
-
-	 /* disable irqbalance completely if there is only one processor online */
-	if (num_online_cpus() < 2) {
-		irqbalance_disabled = 1;
-		return 0;
-	}
-	/*
-	 * Enable physical balance only if more than 1 physical processor
-	 * is present
-	 */
-	if (smp_num_siblings > 1 && !cpus_empty(tmp))
-		physical_balance = 1;
-
-	for_each_online_cpu(i) {
-		irq_cpu_data[i].irq_delta = kzalloc(sizeof(unsigned long) * NR_IRQS, GFP_KERNEL);
-		irq_cpu_data[i].last_irq = kzalloc(sizeof(unsigned long) * NR_IRQS, GFP_KERNEL);
-		if (irq_cpu_data[i].irq_delta == NULL || irq_cpu_data[i].last_irq == NULL) {
-			printk(KERN_ERR "balanced_irq_init: out of memory");
-			goto failed;
-		}
-	}
-
-	printk(KERN_INFO "Starting balanced_irq\n");
-	if (!IS_ERR(kthread_run(balanced_irq, NULL, "kirqd")))
-		return 0;
-	printk(KERN_ERR "balanced_irq_init: failed to spawn balanced_irq");
-failed:
-	for_each_possible_cpu(i) {
-		kfree(irq_cpu_data[i].irq_delta);
-		irq_cpu_data[i].irq_delta = NULL;
-		kfree(irq_cpu_data[i].last_irq);
-		irq_cpu_data[i].last_irq = NULL;
-	}
-	return 0;
-}
-
-int __devinit irqbalance_disable(char *str)
-{
-	irqbalance_disabled = 1;
-	return 1;
-}
-
-__setup("noirqbalance", irqbalance_disable);
-
-late_initcall(balanced_irq_init);
-#endif /* CONFIG_IRQBALANCE */
 #endif /* CONFIG_SMP */
 
 #ifndef CONFIG_SMP
@@ -1167,18 +1048,18 @@ static inline int IO_APIC_irq_trigger(int irq)
 	return 0;
 }
 
-/* irq_vectors is indexed by the sum of all RTEs in all I/O APICs. */
-static u8 irq_vector[NR_IRQ_VECTORS] __read_mostly = { FIRST_DEVICE_VECTOR , 0 };
 
 static int __assign_irq_vector(int irq)
 {
 	static int current_vector = FIRST_DEVICE_VECTOR, current_offset;
 	int vector, offset;
+	struct irq_cfg *cfg;
 
-	BUG_ON((unsigned)irq >= NR_IRQ_VECTORS);
+	BUG_ON((unsigned)irq >= nr_irqs);
 
-	if (irq_vector[irq] > 0)
-		return irq_vector[irq];
+	cfg = irq_cfg(irq);
+	if (cfg->vector > 0)
+		return cfg->vector;
 
 	vector = current_vector;
 	offset = current_offset;
@@ -1195,7 +1076,7 @@ next:
 
 	current_vector = vector;
 	current_offset = offset;
-	irq_vector[irq] = vector;
+	cfg->vector = vector;
 
 	return vector;
 }
@@ -1220,13 +1101,16 @@ static struct irq_chip ioapic_chip;
 
 static void ioapic_register_intr(int irq, int vector, unsigned long trigger)
 {
+	struct irq_desc *desc;
+
+	desc = irq_to_desc(irq);
 	if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
 	    trigger == IOAPIC_LEVEL) {
-		irq_desc[irq].status |= IRQ_LEVEL;
+		desc->status |= IRQ_LEVEL;
 		set_irq_chip_and_handler_name(irq, &ioapic_chip,
 					 handle_fasteoi_irq, "fasteoi");
 	} else {
-		irq_desc[irq].status &= ~IRQ_LEVEL;
+		desc->status &= ~IRQ_LEVEL;
 		set_irq_chip_and_handler_name(irq, &ioapic_chip,
 					 handle_edge_irq, "edge");
 	}
@@ -1353,6 +1237,7 @@ __apicdebuginit(void) print_IO_APIC(void)
 	union IO_APIC_reg_02 reg_02;
 	union IO_APIC_reg_03 reg_03;
 	unsigned long flags;
+	struct irq_cfg *cfg;
 
 	if (apic_verbosity == APIC_QUIET)
 		return;
@@ -1441,16 +1326,16 @@ __apicdebuginit(void) print_IO_APIC(void)
 	}
 	}
 	printk(KERN_DEBUG "IRQ to pin mappings:\n");
-	for (i = 0; i < NR_IRQS; i++) {
-		struct irq_pin_list *entry = irq_2_pin + i;
-		if (entry->pin < 0)
+	for_each_irq_cfg(cfg) {
+		struct irq_pin_list *entry = cfg->irq_2_pin;
+		if (!entry)
 			continue;
 		printk(KERN_DEBUG "IRQ%d ", i);
 		for (;;) {
 			printk("-> %d:%d", entry->apic, entry->pin);
 			if (!entry->next)
 				break;
-			entry = irq_2_pin + entry->next;
+			entry = entry->next;
 		}
 		printk("\n");
 	}
@@ -1621,10 +1506,6 @@ static void __init enable_IO_APIC(void)
 	int i, apic;
 	unsigned long flags;
 
-	for (i = 0; i < PIN_MAP_SIZE; i++) {
-		irq_2_pin[i].pin = -1;
-		irq_2_pin[i].next = 0;
-	}
 	if (!pirqs_enabled)
 		for (i = 0; i < MAX_PIRQS; i++)
 			pirq_entries[i] = -1;
@@ -1954,7 +1835,7 @@ static void ack_ioapic_quirk_irq(unsigned int irq)
  * operation to prevent an edge-triggered interrupt escaping meanwhile.
  * The idea is from Manfred Spraul.  --macro
  */
-	i = irq_vector[irq];
+	i = irq_cfg(irq)->vector;
 
 	v = apic_read(APIC_TMR + ((i & ~0x1f) >> 1));
 
@@ -1971,7 +1852,7 @@ static void ack_ioapic_quirk_irq(unsigned int irq)
 
 static int ioapic_retrigger_irq(unsigned int irq)
 {
-	send_IPI_self(irq_vector[irq]);
+	send_IPI_self(irq_cfg(irq)->vector);
 
 	return 1;
 }
@@ -1993,6 +1874,8 @@ static struct irq_chip ioapic_chip __read_mostly = {
 static inline void init_IO_APIC_traps(void)
 {
 	int irq;
+	struct irq_desc *desc;
+	struct irq_cfg *cfg;
 
 	/*
 	 * NOTE! The local APIC isn't very good at handling
@@ -2005,8 +1888,9 @@ static inline void init_IO_APIC_traps(void)
 	 * Also, we've got to be careful not to trash gate
 	 * 0x80, because int 0x80 is hm, kind of importantish. ;)
 	 */
-	for (irq = 0; irq < NR_IRQS ; irq++) {
-		if (IO_APIC_IRQ(irq) && !irq_vector[irq]) {
+	for_each_irq_cfg(cfg) {
+		irq = cfg->irq;
+		if (IO_APIC_IRQ(irq) && !cfg->vector) {
 			/*
 			 * Hmm.. We don't have an entry for this,
 			 * so default to an old-fashioned 8259
@@ -2014,9 +1898,11 @@ static inline void init_IO_APIC_traps(void)
 			 */
 			if (irq < 16)
 				make_8259A_irq(irq);
-			else
+			else {
+				desc = irq_to_desc(irq);
 				/* Strange. Oh, well.. */
-				irq_desc[irq].chip = &no_irq_chip;
+				desc->chip = &no_irq_chip;
+			}
 		}
 	}
 }
@@ -2055,7 +1941,10 @@ static struct irq_chip lapic_chip __read_mostly = {
 
 static void lapic_register_intr(int irq, int vector)
 {
-	irq_desc[irq].status &= ~IRQ_LEVEL;
+	struct irq_desc *desc;
+
+	desc = irq_to_desc(irq);
+	desc->status &= ~IRQ_LEVEL;
 	set_irq_chip_and_handler_name(irq, &lapic_chip, handle_edge_irq,
 				      "edge");
 	set_intr_gate(vector, interrupt[irq]);
@@ -2446,14 +2335,18 @@ int create_irq(void)
 	/* Allocate an unused irq */
 	int irq, new, vector = 0;
 	unsigned long flags;
+	struct irq_cfg *cfg_new;
 
 	irq = -ENOSPC;
 	spin_lock_irqsave(&vector_lock, flags);
-	for (new = (NR_IRQS - 1); new >= 0; new--) {
+	for (new = (nr_irqs - 1); new >= 0; new--) {
 		if (platform_legacy_irq(new))
 			continue;
-		if (irq_vector[new] != 0)
+		cfg_new = irq_cfg(new);
+		if (cfg_new && cfg_new->vector != 0)
 			continue;
+		if (!cfg_new)
+			cfg_new = irq_cfg_alloc(new);
 		vector = __assign_irq_vector(new);
 		if (likely(vector > 0))
 			irq = new;
@@ -2475,8 +2368,8 @@ void destroy_irq(unsigned int irq)
 	dynamic_irq_cleanup(irq);
 
 	spin_lock_irqsave(&vector_lock, flags);
-	clear_bit(irq_vector[irq], used_vectors);
-	irq_vector[irq] = 0;
+	clear_bit(irq_cfg(irq)->vector, used_vectors);
+	irq_cfg(irq)->vector = 0;
 	spin_unlock_irqrestore(&vector_lock, flags);
 }
 
@@ -2522,6 +2415,7 @@ static void set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
 	unsigned int dest;
 	cpumask_t tmp;
 	int vector;
+	struct irq_desc *desc;
 
 	cpus_and(tmp, mask, cpu_online_map);
 	if (cpus_empty(tmp))
@@ -2541,7 +2435,8 @@ static void set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
 	msg.address_lo |= MSI_ADDR_DEST_ID(dest);
 
 	write_msi_msg(irq, &msg);
-	irq_desc[irq].affinity = mask;
+	desc = irq_to_desc(irq);
+	desc->affinity = mask;
 }
 #endif /* CONFIG_SMP */
 
@@ -2615,6 +2510,7 @@ static void set_ht_irq_affinity(unsigned int irq, cpumask_t mask)
 {
 	unsigned int dest;
 	cpumask_t tmp;
+	struct irq_desc *desc;
 
 	cpus_and(tmp, mask, cpu_online_map);
 	if (cpus_empty(tmp))
@@ -2625,7 +2521,8 @@ static void set_ht_irq_affinity(unsigned int irq, cpumask_t mask)
 	dest = cpu_mask_to_apicid(mask);
 
 	target_ht_irq(irq, dest);
-	irq_desc[irq].affinity = mask;
+	desc = irq_to_desc(irq);
+	desc->affinity = mask;
 }
 #endif