Re: add back sparseirq v5
From: Yinghai Lu
Date: Fri Dec 05 2008 - 22:02:37 EST
this one is outdated...
YH
On Fri, Dec 5, 2008 at 6:58 PM, Yinghai Lu <yinghai@xxxxxxxxxx> wrote:
> impact: new feature sparseirq
>
> for sparse_irq, irq_desc, and irq_cfg is not using list_head to chain up
> also not add per_cpu_dyn_array... no user now
>
> v2: add some kind of hash table as Ingo suggesting.
> v3: default to use dyna_array only, aka SPARSE_IRQ = N
> and remove check nr_irqs with NR_IRQS in probe_nr_irqs
> v4: remove dyna_array, and enable sparse_irq by default
> use kzalloc_node to get it
> v5: use desc->chip_data for x86 to store irq_cfg
>
> to do: make irq_desc and go with affinity aka irq_desc moving etc
>
> Signed-off-by: Yinghai Lu <yinghai@xxxxxxxxxx>
>
> ---
> arch/x86/Kconfig | 4
> arch/x86/include/asm/io_apic.h | 4
> arch/x86/include/asm/irq_vectors.h | 2
> arch/x86/kernel/io_apic.c | 275 +++++++++++++++++++++----------------
> arch/x86/kernel/irq.c | 19 +-
> arch/x86/kernel/irq_32.c | 1
> arch/x86/kernel/irq_64.c | 1
> arch/x86/kernel/irqinit_32.c | 3
> arch/x86/kernel/irqinit_64.c | 3
> arch/x86/kernel/setup_percpu.c | 4
> arch/x86/mm/init_32.c | 3
> drivers/char/random.c | 31 ++++
> drivers/pci/htirq.c | 18 ++
> drivers/pci/intr_remapping.c | 65 ++++++++
> drivers/xen/events.c | 7
> fs/proc/interrupts.c | 13 +
> fs/proc/stat.c | 16 +-
> include/linux/interrupt.h | 2
> include/linux/irq.h | 54 ++++++-
> include/linux/irqnr.h | 15 --
> include/linux/kernel_stat.h | 14 +
> init/main.c | 7
> kernel/irq/autoprobe.c | 5
> kernel/irq/chip.c | 4
> kernel/irq/handle.c | 214 ++++++++++++++++++++++++++++
> kernel/irq/proc.c | 1
> kernel/irq/spurious.c | 2
> 27 files changed, 627 insertions(+), 160 deletions(-)
>
> Index: linux-2.6/arch/x86/Kconfig
> ===================================================================
> --- linux-2.6.orig/arch/x86/Kconfig
> +++ linux-2.6/arch/x86/Kconfig
> @@ -236,6 +236,10 @@ config X86_HAS_BOOT_CPU_ID
> def_bool y
> depends on X86_VOYAGER
>
> +config HAVE_SPARSE_IRQ
> + bool
> + default y
> +
> config X86_FIND_SMP_CONFIG
> def_bool y
> depends on X86_MPPARSE || X86_VOYAGER
> Index: linux-2.6/arch/x86/kernel/io_apic.c
> ===================================================================
> --- linux-2.6.orig/arch/x86/kernel/io_apic.c
> +++ linux-2.6/arch/x86/kernel/io_apic.c
> @@ -108,8 +108,8 @@ static int __init parse_noapic(char *str
> early_param("noapic", parse_noapic);
>
> struct irq_pin_list;
> +
> struct irq_cfg {
> - unsigned int irq;
> struct irq_pin_list *irq_2_pin;
> cpumask_t domain;
> cpumask_t old_domain;
> @@ -119,44 +119,72 @@ struct irq_cfg {
> };
>
> /* irq_cfg is indexed by the sum of all RTEs in all I/O APICs. */
> -static struct irq_cfg irq_cfgx[NR_IRQS] = {
> - [0] = { .irq = 0, .domain = CPU_MASK_ALL, .vector = IRQ0_VECTOR, },
> - [1] = { .irq = 1, .domain = CPU_MASK_ALL, .vector = IRQ1_VECTOR, },
> - [2] = { .irq = 2, .domain = CPU_MASK_ALL, .vector = IRQ2_VECTOR, },
> - [3] = { .irq = 3, .domain = CPU_MASK_ALL, .vector = IRQ3_VECTOR, },
> - [4] = { .irq = 4, .domain = CPU_MASK_ALL, .vector = IRQ4_VECTOR, },
> - [5] = { .irq = 5, .domain = CPU_MASK_ALL, .vector = IRQ5_VECTOR, },
> - [6] = { .irq = 6, .domain = CPU_MASK_ALL, .vector = IRQ6_VECTOR, },
> - [7] = { .irq = 7, .domain = CPU_MASK_ALL, .vector = IRQ7_VECTOR, },
> - [8] = { .irq = 8, .domain = CPU_MASK_ALL, .vector = IRQ8_VECTOR, },
> - [9] = { .irq = 9, .domain = CPU_MASK_ALL, .vector = IRQ9_VECTOR, },
> - [10] = { .irq = 10, .domain = CPU_MASK_ALL, .vector = IRQ10_VECTOR, },
> - [11] = { .irq = 11, .domain = CPU_MASK_ALL, .vector = IRQ11_VECTOR, },
> - [12] = { .irq = 12, .domain = CPU_MASK_ALL, .vector = IRQ12_VECTOR, },
> - [13] = { .irq = 13, .domain = CPU_MASK_ALL, .vector = IRQ13_VECTOR, },
> - [14] = { .irq = 14, .domain = CPU_MASK_ALL, .vector = IRQ14_VECTOR, },
> - [15] = { .irq = 15, .domain = CPU_MASK_ALL, .vector = IRQ15_VECTOR, },
> +static struct irq_cfg irq_cfg_legacy[] = {
> + [0] = { .domain = CPU_MASK_ALL, .vector = IRQ0_VECTOR, },
> + [1] = { .domain = CPU_MASK_ALL, .vector = IRQ1_VECTOR, },
> + [2] = { .domain = CPU_MASK_ALL, .vector = IRQ2_VECTOR, },
> + [3] = { .domain = CPU_MASK_ALL, .vector = IRQ3_VECTOR, },
> + [4] = { .domain = CPU_MASK_ALL, .vector = IRQ4_VECTOR, },
> + [5] = { .domain = CPU_MASK_ALL, .vector = IRQ5_VECTOR, },
> + [6] = { .domain = CPU_MASK_ALL, .vector = IRQ6_VECTOR, },
> + [7] = { .domain = CPU_MASK_ALL, .vector = IRQ7_VECTOR, },
> + [8] = { .domain = CPU_MASK_ALL, .vector = IRQ8_VECTOR, },
> + [9] = { .domain = CPU_MASK_ALL, .vector = IRQ9_VECTOR, },
> + [10] = { .domain = CPU_MASK_ALL, .vector = IRQ10_VECTOR, },
> + [11] = { .domain = CPU_MASK_ALL, .vector = IRQ11_VECTOR, },
> + [12] = { .domain = CPU_MASK_ALL, .vector = IRQ12_VECTOR, },
> + [13] = { .domain = CPU_MASK_ALL, .vector = IRQ13_VECTOR, },
> + [14] = { .domain = CPU_MASK_ALL, .vector = IRQ14_VECTOR, },
> + [15] = { .domain = CPU_MASK_ALL, .vector = IRQ15_VECTOR, },
> };
>
> -#define for_each_irq_cfg(irq, cfg) \
> - for (irq = 0, cfg = irq_cfgx; irq < nr_irqs; irq++, cfg++)
> +/*
> + * Protect the irq_cfgx_free freelist:
> + */
> +void __init early_irq_cfg_init_work(void)
> +{
> + struct irq_cfg *cfg;
> + struct irq_desc *desc;
> + int legacy_count;
> + int i;
> +
> + cfg = irq_cfg_legacy;
> + legacy_count = ARRAY_SIZE(irq_cfg_legacy);
> +
> + BUG_ON(legacy_count > NR_IRQS_LEGACY);
> +
> + for (i = 0; i < legacy_count; i++) {
> + desc = irq_to_desc(i);
> + desc->chip_data = &cfg[i];
> + }
> +}
>
> static struct irq_cfg *irq_cfg(unsigned int irq)
> {
> - return irq < nr_irqs ? irq_cfgx + irq : NULL;
> + struct irq_cfg *cfg = NULL;
> + struct irq_desc *desc;
> +
> + desc = irq_to_desc(irq);
> + if (desc)
> + cfg = desc->chip_data;
> +
> + return cfg;
> }
>
> -static struct irq_cfg *irq_cfg_alloc(unsigned int irq)
> +static struct irq_cfg *get_one_free_irq_cfg(int cpu)
> {
> - return irq_cfg(irq);
> -}
> + struct irq_cfg *cfg;
> + int node;
>
> -/*
> - * 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)
> + if (cpu < 0)
> + cpu = smp_processor_id();
> + node = cpu_to_node(cpu);
> +
> + cfg = kzalloc_node(sizeof(*cfg), GFP_KERNEL, node);
> + printk(KERN_DEBUG " alloc irq_cfg on cpu %d node %d\n", cpu, node);
> +
> + return cfg;
> +}
>
> /*
> * This is performance-critical, we want to do it O(1)
> @@ -170,29 +198,18 @@ struct irq_pin_list {
> struct irq_pin_list *next;
> };
>
> -static struct irq_pin_list irq_2_pin_head[PIN_MAP_SIZE];
> -static struct irq_pin_list *irq_2_pin_ptr;
> -
> -static void __init irq_2_pin_init(void)
> +static struct irq_pin_list *get_one_free_irq_2_pin(int cpu)
> {
> - struct irq_pin_list *pin = irq_2_pin_head;
> - int i;
> -
> - for (i = 1; i < PIN_MAP_SIZE; i++)
> - pin[i-1].next = &pin[i];
> -
> - irq_2_pin_ptr = &pin[0];
> -}
> + struct irq_pin_list *pin;
> + int node;
>
> -static struct irq_pin_list *get_one_free_irq_2_pin(void)
> -{
> - struct irq_pin_list *pin = irq_2_pin_ptr;
> + if (cpu < 0)
> + cpu = smp_processor_id();
> + node = cpu_to_node(cpu);
>
> - if (!pin)
> - panic("can not get more irq_2_pin\n");
> + pin = kzalloc_node(sizeof(*pin), GFP_KERNEL, node);
> + printk(KERN_DEBUG " alloc irq_2_pin on cpu %d node %d\n", cpu, node);
>
> - irq_2_pin_ptr = pin->next;
> - pin->next = NULL;
> return pin;
> }
>
> @@ -359,7 +376,7 @@ static void __target_IO_APIC_irq(unsigne
> }
> }
>
> -static int assign_irq_vector(int irq, cpumask_t mask);
> +static int assign_irq_vector(int irq, struct irq_cfg *cfg, cpumask_t mask);
>
> static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t mask)
> {
> @@ -374,7 +391,7 @@ static void set_ioapic_affinity_irq(unsi
> return;
>
> cfg = irq_cfg(irq);
> - if (assign_irq_vector(irq, mask))
> + if (assign_irq_vector(irq, cfg, mask))
> return;
>
> cpus_and(tmp, cfg->domain, mask);
> @@ -399,14 +416,21 @@ static void set_ioapic_affinity_irq(unsi
> */
> static void add_pin_to_irq(unsigned int irq, int apic, int pin)
> {
> + struct irq_desc *desc;
> struct irq_cfg *cfg;
> struct irq_pin_list *entry;
> + int cpu = smp_processor_id();
>
> /* first time to refer irq_cfg, so with new */
> - cfg = irq_cfg_alloc(irq);
> + desc = irq_to_desc_alloc_cpu(irq, cpu);
> + cfg = desc->chip_data;
> + if (!cfg) {
> + cfg = get_one_free_irq_cfg(cpu);
> + desc->chip_data = cfg;
> + }
> entry = cfg->irq_2_pin;
> if (!entry) {
> - entry = get_one_free_irq_2_pin();
> + entry = get_one_free_irq_2_pin(cpu);
> cfg->irq_2_pin = entry;
> entry->apic = apic;
> entry->pin = pin;
> @@ -421,7 +445,7 @@ static void add_pin_to_irq(unsigned int
> entry = entry->next;
> }
>
> - entry->next = get_one_free_irq_2_pin();
> + entry->next = get_one_free_irq_2_pin(cpu);
> entry = entry->next;
> entry->apic = apic;
> entry->pin = pin;
> @@ -809,7 +833,7 @@ EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector
> */
> static int EISA_ELCR(unsigned int irq)
> {
> - if (irq < 16) {
> + if (irq < NR_IRQS_LEGACY) {
> unsigned int port = 0x4d0 + (irq >> 3);
> return (inb(port) >> (irq & 7)) & 1;
> }
> @@ -1034,7 +1058,7 @@ void unlock_vector_lock(void)
> spin_unlock(&vector_lock);
> }
>
> -static int __assign_irq_vector(int irq, cpumask_t mask)
> +static int __assign_irq_vector(int irq, struct irq_cfg *cfg, cpumask_t mask)
> {
> /*
> * NOTE! The local APIC isn't very good at handling
> @@ -1050,9 +1074,6 @@ static int __assign_irq_vector(int irq,
> static int current_vector = FIRST_DEVICE_VECTOR, current_offset = 0;
> unsigned int old_vector;
> int cpu;
> - struct irq_cfg *cfg;
> -
> - cfg = irq_cfg(irq);
>
> /* Only try and allocate irqs on cpus that are present */
> cpus_and(mask, mask, cpu_online_map);
> @@ -1113,24 +1134,22 @@ next:
> return -ENOSPC;
> }
>
> -static int assign_irq_vector(int irq, cpumask_t mask)
> +static int assign_irq_vector(int irq, struct irq_cfg *cfg, cpumask_t mask)
> {
> int err;
> unsigned long flags;
>
> spin_lock_irqsave(&vector_lock, flags);
> - err = __assign_irq_vector(irq, mask);
> + err = __assign_irq_vector(irq, cfg, mask);
> spin_unlock_irqrestore(&vector_lock, flags);
> return err;
> }
>
> -static void __clear_irq_vector(int irq)
> +static void __clear_irq_vector(int irq, struct irq_cfg *cfg)
> {
> - struct irq_cfg *cfg;
> cpumask_t mask;
> int cpu, vector;
>
> - cfg = irq_cfg(irq);
> BUG_ON(!cfg->vector);
>
> vector = cfg->vector;
> @@ -1148,14 +1167,17 @@ void __setup_vector_irq(int cpu)
> /* This function must be called with vector_lock held */
> int irq, vector;
> struct irq_cfg *cfg;
> + struct irq_desc *desc;
>
> /* Mark the inuse vectors */
> - for_each_irq_cfg(irq, cfg) {
> + for_each_irq_desc(irq, desc) {
> + cfg = desc->chip_data;
> if (!cpu_isset(cpu, cfg->domain))
> continue;
> vector = cfg->vector;
> per_cpu(vector_irq, cpu)[vector] = irq;
> }
> + end_for_each_irq_desc();
> /* Mark the free vectors */
> for (vector = 0; vector < NR_VECTORS; ++vector) {
> irq = per_cpu(vector_irq, cpu)[vector];
> @@ -1205,7 +1227,8 @@ static void ioapic_register_intr(int irq
> {
> struct irq_desc *desc;
>
> - desc = irq_to_desc(irq);
> + /* could be first time to use this irq_desc */
> + desc = irq_to_desc_alloc(irq);
>
> if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
> trigger == IOAPIC_LEVEL)
> @@ -1310,7 +1333,7 @@ static void setup_IO_APIC_irq(int apic,
> cfg = irq_cfg(irq);
>
> mask = TARGET_CPUS;
> - if (assign_irq_vector(irq, mask))
> + if (assign_irq_vector(irq, cfg, mask))
> return;
>
> cpus_and(mask, cfg->domain, mask);
> @@ -1327,12 +1350,12 @@ static void setup_IO_APIC_irq(int apic,
> cfg->vector)) {
> printk("Failed to setup ioapic entry for ioapic %d, pin %d\n",
> mp_ioapics[apic].mp_apicid, pin);
> - __clear_irq_vector(irq);
> + __clear_irq_vector(irq, cfg);
> return;
> }
>
> ioapic_register_intr(irq, trigger);
> - if (irq < 16)
> + if (irq < NR_IRQS_LEGACY)
> disable_8259A_irq(irq);
>
> ioapic_write_entry(apic, pin, entry);
> @@ -1434,6 +1457,7 @@ __apicdebuginit(void) print_IO_APIC(void
> union IO_APIC_reg_03 reg_03;
> unsigned long flags;
> struct irq_cfg *cfg;
> + struct irq_desc *desc;
> unsigned int irq;
>
> if (apic_verbosity == APIC_QUIET)
> @@ -1523,8 +1547,11 @@ __apicdebuginit(void) print_IO_APIC(void
> }
> }
> printk(KERN_DEBUG "IRQ to pin mappings:\n");
> - for_each_irq_cfg(irq, cfg) {
> - struct irq_pin_list *entry = cfg->irq_2_pin;
> + for_each_irq_desc(irq, desc) {
> + struct irq_pin_list *entry;
> +
> + cfg = desc->chip_data;
> + entry = cfg->irq_2_pin;
> if (!entry)
> continue;
> printk(KERN_DEBUG "IRQ%d ", irq);
> @@ -1536,6 +1563,7 @@ __apicdebuginit(void) print_IO_APIC(void
> }
> printk("\n");
> }
> + end_for_each_irq_desc();
>
> printk(KERN_INFO ".................................... done.\n");
>
> @@ -2010,7 +2038,7 @@ static unsigned int startup_ioapic_irq(u
> unsigned long flags;
>
> spin_lock_irqsave(&ioapic_lock, flags);
> - if (irq < 16) {
> + if (irq < NR_IRQS_LEGACY) {
> disable_8259A_irq(irq);
> if (i8259A_irq_pending(irq))
> was_pending = 1;
> @@ -2095,10 +2123,10 @@ static void migrate_ioapic_irq(int irq,
> if (get_irte(irq, &irte))
> return;
>
> - if (assign_irq_vector(irq, mask))
> + cfg = irq_cfg(irq);
> + if (assign_irq_vector(irq, cfg, mask))
> return;
>
> - cfg = irq_cfg(irq);
> cpus_and(tmp, cfg->domain, mask);
> dest = cpu_mask_to_apicid(tmp);
>
> @@ -2179,6 +2207,7 @@ static void ir_irq_migration(struct work
> spin_unlock_irqrestore(&desc->lock, flags);
> }
> }
> + end_for_each_irq_desc();
> }
>
> /*
> @@ -2416,22 +2445,22 @@ static inline void init_IO_APIC_traps(vo
> * Also, we've got to be careful not to trash gate
> * 0x80, because int 0x80 is hm, kind of importantish. ;)
> */
> - for_each_irq_cfg(irq, cfg) {
> - if (IO_APIC_IRQ(irq) && !cfg->vector) {
> + for_each_irq_desc(irq, desc) {
> + cfg = desc->chip_data;
> + if (IO_APIC_IRQ(irq) && cfg && !cfg->vector) {
> /*
> * Hmm.. We don't have an entry for this,
> * so default to an old-fashioned 8259
> * interrupt if we can..
> */
> - if (irq < 16)
> + if (irq < NR_IRQS_LEGACY)
> make_8259A_irq(irq);
> - else {
> - desc = irq_to_desc(irq);
> + else
> /* Strange. Oh, well.. */
> desc->chip = &no_irq_chip;
> - }
> }
> }
> + end_for_each_irq_desc();
> }
>
> /*
> @@ -2589,7 +2618,7 @@ static inline void __init check_timer(vo
> * get/set the timer IRQ vector:
> */
> disable_8259A_irq(0);
> - assign_irq_vector(0, TARGET_CPUS);
> + assign_irq_vector(0, cfg, TARGET_CPUS);
>
> /*
> * As IRQ0 is to be enabled in the 8259A, the virtual
> @@ -2888,22 +2917,31 @@ unsigned int create_irq_nr(unsigned int
> unsigned int irq;
> unsigned int new;
> unsigned long flags;
> - struct irq_cfg *cfg_new;
> -
> - irq_want = nr_irqs - 1;
> + struct irq_cfg *cfg_new = NULL;
> + struct irq_desc *desc_new = NULL;
> + int cpu;
>
> irq = 0;
> spin_lock_irqsave(&vector_lock, flags);
> + cpu = smp_processor_id();
> for (new = irq_want; new > 0; new--) {
> if (platform_legacy_irq(new))
> continue;
> - cfg_new = irq_cfg(new);
> +
> + cfg_new = NULL;
> + desc_new = irq_to_desc(new);
> + if (desc_new)
> + cfg_new = desc_new->chip_data;
> if (cfg_new && cfg_new->vector != 0)
> continue;
> /* check if need to create one */
> - if (!cfg_new)
> - cfg_new = irq_cfg_alloc(new);
> - if (__assign_irq_vector(new, TARGET_CPUS) == 0)
> + if (!cfg_new) {
> + cfg_new = get_one_free_irq_cfg(cpu);
> + if (!desc_new)
> + desc_new = irq_to_desc_alloc_cpu(new, cpu);
> + desc_new->chip_data = cfg_new;
> + }
> + if (__assign_irq_vector(new, cfg_new, TARGET_CPUS) == 0)
> irq = new;
> break;
> }
> @@ -2911,6 +2949,9 @@ unsigned int create_irq_nr(unsigned int
>
> if (irq > 0) {
> dynamic_irq_init(irq);
> + /* restore it, in case dynamic_irq_init clear it */
> + if (desc_new)
> + desc_new->chip_data = cfg_new;
> }
> return irq;
> }
> @@ -2930,14 +2971,22 @@ int create_irq(void)
> void destroy_irq(unsigned int irq)
> {
> unsigned long flags;
> + struct irq_cfg *cfg;
> + struct irq_desc *desc;
>
> + /* store it, in case dynamic_irq_cleanup clear it */
> + desc = irq_to_desc(irq);
> + cfg = desc->chip_data;
> dynamic_irq_cleanup(irq);
> + /* connect back irq_cfg */
> + if (desc)
> + desc->chip_data = cfg;
>
> #ifdef CONFIG_INTR_REMAP
> free_irte(irq);
> #endif
> spin_lock_irqsave(&vector_lock, flags);
> - __clear_irq_vector(irq);
> + __clear_irq_vector(irq, cfg);
> spin_unlock_irqrestore(&vector_lock, flags);
> }
>
> @@ -2952,12 +3001,12 @@ static int msi_compose_msg(struct pci_de
> unsigned dest;
> cpumask_t tmp;
>
> + cfg = irq_cfg(irq);
> tmp = TARGET_CPUS;
> - err = assign_irq_vector(irq, tmp);
> + err = assign_irq_vector(irq, cfg, tmp);
> if (err)
> return err;
>
> - cfg = irq_cfg(irq);
> cpus_and(tmp, cfg->domain, tmp);
> dest = cpu_mask_to_apicid(tmp);
>
> @@ -3025,10 +3074,10 @@ static void set_msi_irq_affinity(unsigne
> if (cpus_empty(tmp))
> return;
>
> - if (assign_irq_vector(irq, mask))
> + cfg = irq_cfg(irq);
> + if (assign_irq_vector(irq, cfg, mask))
> return;
>
> - cfg = irq_cfg(irq);
> cpus_and(tmp, cfg->domain, mask);
> dest = cpu_mask_to_apicid(tmp);
>
> @@ -3064,10 +3113,10 @@ static void ir_set_msi_irq_affinity(unsi
> if (get_irte(irq, &irte))
> return;
>
> - if (assign_irq_vector(irq, mask))
> + cfg = irq_cfg(irq);
> + if (assign_irq_vector(irq, cfg, mask))
> return;
>
> - cfg = irq_cfg(irq);
> cpus_and(tmp, cfg->domain, mask);
> dest = cpu_mask_to_apicid(tmp);
>
> @@ -3176,7 +3225,7 @@ static int setup_msi_irq(struct pci_dev
> #endif
> set_irq_chip_and_handler_name(irq, &msi_chip, handle_edge_irq, "edge");
>
> - dev_printk(KERN_DEBUG, &dev->dev, "irq %d for MSI/MSI-X\n", irq);
> + dev_printk(KERN_DEBUG, &dev->dev, "irq %d aka 0x%08x for MSI/MSI-X\n", irq, irq);
>
> return 0;
> }
> @@ -3199,7 +3248,7 @@ int arch_setup_msi_irq(struct pci_dev *d
> int ret;
> unsigned int irq_want;
>
> - irq_want = build_irq_for_pci_dev(dev) + 0x100;
> + irq_want = build_irq_for_pci_dev(dev) + 0xfff;
>
> irq = create_irq_nr(irq_want);
> if (irq == 0)
> @@ -3240,7 +3289,7 @@ int arch_setup_msi_irqs(struct pci_dev *
> int index = 0;
> #endif
>
> - irq_want = build_irq_for_pci_dev(dev) + 0x100;
> + irq_want = build_irq_for_pci_dev(dev) + 0xfff;
> sub_handle = 0;
> list_for_each_entry(desc, &dev->msi_list, list) {
> irq = create_irq_nr(irq_want--);
> @@ -3306,10 +3355,10 @@ static void dmar_msi_set_affinity(unsign
> if (cpus_empty(tmp))
> return;
>
> - if (assign_irq_vector(irq, mask))
> + cfg = irq_cfg(irq);
> + if (assign_irq_vector(irq, cfg, mask))
> return;
>
> - cfg = irq_cfg(irq);
> cpus_and(tmp, cfg->domain, mask);
> dest = cpu_mask_to_apicid(tmp);
>
> @@ -3367,10 +3416,10 @@ static void hpet_msi_set_affinity(unsign
> if (cpus_empty(tmp))
> return;
>
> - if (assign_irq_vector(irq, mask))
> + cfg = irq_cfg(irq);
> + if (assign_irq_vector(irq, cfg, mask))
> return;
>
> - cfg = irq_cfg(irq);
> cpus_and(tmp, cfg->domain, mask);
> dest = cpu_mask_to_apicid(tmp);
>
> @@ -3448,10 +3497,10 @@ static void set_ht_irq_affinity(unsigned
> if (cpus_empty(tmp))
> return;
>
> - if (assign_irq_vector(irq, mask))
> + cfg = irq_cfg(irq);
> + if (assign_irq_vector(irq, cfg, mask))
> return;
>
> - cfg = irq_cfg(irq);
> cpus_and(tmp, cfg->domain, mask);
> dest = cpu_mask_to_apicid(tmp);
>
> @@ -3478,13 +3527,13 @@ int arch_setup_ht_irq(unsigned int irq,
> int err;
> cpumask_t tmp;
>
> + cfg = irq_cfg(irq);
> tmp = TARGET_CPUS;
> - err = assign_irq_vector(irq, tmp);
> + err = assign_irq_vector(irq, cfg, tmp);
> if (!err) {
> struct ht_irq_msg msg;
> unsigned dest;
>
> - cfg = irq_cfg(irq);
> cpus_and(tmp, cfg->domain, tmp);
> dest = cpu_mask_to_apicid(tmp);
>
> @@ -3508,7 +3557,8 @@ int arch_setup_ht_irq(unsigned int irq,
> set_irq_chip_and_handler_name(irq, &ht_irq_chip,
> handle_edge_irq, "edge");
>
> - dev_printk(KERN_DEBUG, &dev->dev, "irq %d for HT\n", irq);
> + dev_printk(KERN_DEBUG, &dev->dev, "irq %d aka 0x%08x for HT\n",
> + irq, irq);
> }
> return err;
> }
> @@ -3530,7 +3580,9 @@ int arch_enable_uv_irq(char *irq_name, u
> unsigned long flags;
> int err;
>
> - err = assign_irq_vector(irq, *eligible_cpu);
> + cfg = irq_cfg(irq);
> +
> + err = assign_irq_vector(irq, cfg, *eligible_cpu);
> if (err != 0)
> return err;
>
> @@ -3539,8 +3591,6 @@ int arch_enable_uv_irq(char *irq_name, u
> irq_name);
> spin_unlock_irqrestore(&vector_lock, flags);
>
> - cfg = irq_cfg(irq);
> -
> mmr_value = 0;
> entry = (struct uv_IO_APIC_route_entry *)&mmr_value;
> BUG_ON(sizeof(struct uv_IO_APIC_route_entry) != sizeof(unsigned long));
> @@ -3611,8 +3661,6 @@ int __init probe_nr_irqs(void)
> /* something wrong ? */
> if (nr < nr_min)
> nr = nr_min;
> - if (WARN_ON(nr > NR_IRQS))
> - nr = NR_IRQS;
>
> return nr;
> }
> @@ -3722,7 +3770,7 @@ int io_apic_set_pci_routing (int ioapic,
> /*
> * IRQs < 16 are already in the irq_2_pin[] map
> */
> - if (irq >= 16)
> + if (irq >= NR_IRQS_LEGACY)
> add_pin_to_irq(irq, ioapic, pin);
>
> setup_IO_APIC_irq(ioapic, pin, irq, triggering, polarity);
> @@ -3836,7 +3884,6 @@ void __init ioapic_init_mappings(void)
> struct resource *ioapic_res;
> int i;
>
> - irq_2_pin_init();
> ioapic_res = ioapic_setup_resources();
> for (i = 0; i < nr_ioapics; i++) {
> if (smp_found_config) {
> Index: linux-2.6/arch/x86/kernel/irqinit_32.c
> ===================================================================
> --- linux-2.6.orig/arch/x86/kernel/irqinit_32.c
> +++ linux-2.6/arch/x86/kernel/irqinit_32.c
> @@ -68,8 +68,7 @@ void __init init_ISA_irqs (void)
> /*
> * 16 old-style INTA-cycle interrupts:
> */
> - for (i = 0; i < 16; i++) {
> - /* first time call this irq_desc */
> + for (i = 0; i < NR_IRQS_LEGACY; i++) {
> struct irq_desc *desc = irq_to_desc(i);
>
> desc->status = IRQ_DISABLED;
> Index: linux-2.6/arch/x86/kernel/irqinit_64.c
> ===================================================================
> --- linux-2.6.orig/arch/x86/kernel/irqinit_64.c
> +++ linux-2.6/arch/x86/kernel/irqinit_64.c
> @@ -142,8 +142,7 @@ void __init init_ISA_irqs(void)
> init_bsp_APIC();
> init_8259A(0);
>
> - for (i = 0; i < 16; i++) {
> - /* first time call this irq_desc */
> + for (i = 0; i < NR_IRQS_LEGACY; i++) {
> struct irq_desc *desc = irq_to_desc(i);
>
> desc->status = IRQ_DISABLED;
> Index: linux-2.6/arch/x86/mm/init_32.c
> ===================================================================
> --- linux-2.6.orig/arch/x86/mm/init_32.c
> +++ linux-2.6/arch/x86/mm/init_32.c
> @@ -66,6 +66,7 @@ static unsigned long __meminitdata table
> static unsigned long __meminitdata table_top;
>
> static int __initdata after_init_bootmem;
> +int after_bootmem;
>
> static __init void *alloc_low_page(unsigned long *phys)
> {
> @@ -987,6 +988,8 @@ void __init mem_init(void)
>
> set_highmem_pages_init();
>
> + after_bootmem = 1;
> +
> codesize = (unsigned long) &_etext - (unsigned long) &_text;
> datasize = (unsigned long) &_edata - (unsigned long) &_etext;
> initsize = (unsigned long) &__init_end - (unsigned long) &__init_begin;
> Index: linux-2.6/drivers/char/random.c
> ===================================================================
> --- linux-2.6.orig/drivers/char/random.c
> +++ linux-2.6/drivers/char/random.c
> @@ -558,6 +558,8 @@ struct timer_rand_state {
> unsigned dont_count_entropy:1;
> };
>
> +#ifndef CONFIG_HAVE_SPARSE_IRQ
> +
> static struct timer_rand_state *irq_timer_state[NR_IRQS];
>
> static struct timer_rand_state *get_timer_rand_state(unsigned int irq)
> @@ -576,6 +578,33 @@ static void set_timer_rand_state(unsigne
> irq_timer_state[irq] = state;
> }
>
> +#else
> +
> +static struct timer_rand_state *get_timer_rand_state(unsigned int irq)
> +{
> + struct irq_desc *desc;
> +
> + desc = irq_to_desc(irq);
> +
> + if (!desc)
> + return NULL;
> +
> + return desc->timer_rand_state;
> +}
> +
> +static void set_timer_rand_state(unsigned int irq, struct timer_rand_state *state)
> +{
> + struct irq_desc *desc;
> +
> + desc = irq_to_desc(irq);
> +
> + if (!desc)
> + return;
> +
> + desc->timer_rand_state = state;
> +}
> +#endif
> +
> static struct timer_rand_state input_timer_state;
>
> /*
> @@ -933,8 +962,10 @@ void rand_initialize_irq(int irq)
> {
> struct timer_rand_state *state;
>
> +#ifndef CONFIG_HAVE_SPARSE_IRQ
> if (irq >= nr_irqs)
> return;
> +#endif
>
> state = get_timer_rand_state(irq);
>
> Index: linux-2.6/drivers/pci/htirq.c
> ===================================================================
> --- linux-2.6.orig/drivers/pci/htirq.c
> +++ linux-2.6/drivers/pci/htirq.c
> @@ -82,6 +82,18 @@ void unmask_ht_irq(unsigned int irq)
> write_ht_irq_msg(irq, &msg);
> }
>
> +static unsigned int build_irq_for_pci_dev(struct pci_dev *dev)
> +{
> + unsigned int irq;
> +
> + irq = dev->bus->number;
> + irq <<= 8;
> + irq |= dev->devfn;
> + irq <<= 12;
> +
> + return irq;
> +}
> +
> /**
> * __ht_create_irq - create an irq and attach it to a device.
> * @dev: The hypertransport device to find the irq capability on.
> @@ -98,6 +110,7 @@ int __ht_create_irq(struct pci_dev *dev,
> int max_irq;
> int pos;
> int irq;
> + unsigned int irq_want;
>
> pos = pci_find_ht_capability(dev, HT_CAPTYPE_IRQ);
> if (!pos)
> @@ -125,7 +138,12 @@ int __ht_create_irq(struct pci_dev *dev,
> cfg->msg.address_lo = 0xffffffff;
> cfg->msg.address_hi = 0xffffffff;
>
> + irq_want = build_irq_for_pci_dev(dev);
> +#ifdef CONFIG_HAVE_SPARSE_IRQ
> + irq = create_irq_nr(irq_want + idx);
> +#else
> irq = create_irq();
> +#endif
>
> if (irq <= 0) {
> kfree(cfg);
> Index: linux-2.6/drivers/pci/intr_remapping.c
> ===================================================================
> --- linux-2.6.orig/drivers/pci/intr_remapping.c
> +++ linux-2.6/drivers/pci/intr_remapping.c
> @@ -19,17 +19,76 @@ struct irq_2_iommu {
> u8 irte_mask;
> };
>
> -static struct irq_2_iommu irq_2_iommuX[NR_IRQS];
> +#ifdef CONFIG_HAVE_SPARSE_IRQ
> +static struct irq_2_iommu *get_one_free_irq_2_iommu(int cpu)
> +{
> + struct irq_2_iommu *iommu;
> + int node;
> +
> + if (cpu < 0)
> + cpu = smp_processor_id();
> + node = cpu_to_node(cpu);
> +
> + iommu = kzalloc_node(sizeof(*iommu), GFP_KERNEL, node);
> + printk(KERN_DEBUG "alloc irq_2_iommu on cpu %d node %d\n", cpu, node);
> +
> + return iommu;
> +}
>
> static struct irq_2_iommu *irq_2_iommu(unsigned int irq)
> {
> - return (irq < nr_irqs) ? irq_2_iommuX + irq : NULL;
> + struct irq_desc *desc;
> +
> + desc = irq_to_desc(irq);
> +
> + BUG_ON(!desc);
> +
> + return desc->irq_2_iommu;
> }
>
> +static struct irq_2_iommu *irq_2_iommu_alloc_cpu(unsigned int irq, int cpu)
> +{
> + struct irq_desc *desc;
> + struct irq_2_iommu *irq_iommu;
> +
> + /*
> + * alloc irq desc if not allocated already.
> + */
> + desc = irq_to_desc_alloc_cpu(irq, cpu);
> +
> + irq_iommu = desc->irq_2_iommu;
> +
> + if (!irq_iommu)
> + desc->irq_2_iommu = get_one_free_irq_2_iommu(cpu);
> +
> + return desc->irq_2_iommu;
> +}
> +
> +static struct irq_2_iommu *irq_2_iommu_alloc(unsigned int irq)
> +{
> + return irq_2_iommu_alloc_cpu(irq, -1);
> +}
> +
> +#else /* !CONFIG_HAVE_SPARSE_IRQ */
> +
> +static struct irq_2_iommu irq_2_iommuX[NR_IRQS];
> +
> +static struct irq_2_iommu *irq_2_iommu(unsigned int irq)
> +{
> + if (irq < nr_irqs)
> + return &irq_2_iommuX[irq];
> +
> + return NULL;
> +}
> +static struct irq_2_iommu *irq_2_iommu_alloc_cpu(unsigned int irq, int cpu)
> +{
> + return irq_2_iommu(irq);
> +}
> static struct irq_2_iommu *irq_2_iommu_alloc(unsigned int irq)
> {
> return irq_2_iommu(irq);
> }
> +#endif
>
> static DEFINE_SPINLOCK(irq_2_ir_lock);
>
> @@ -86,9 +145,11 @@ int alloc_irte(struct intel_iommu *iommu
> if (!count)
> return -1;
>
> +#ifndef CONFIG_HAVE_SPARSE_IRQ
> /* protect irq_2_iommu_alloc later */
> if (irq >= nr_irqs)
> return -1;
> +#endif
>
> /*
> * start the IRTE search from index 0.
> Index: linux-2.6/drivers/xen/events.c
> ===================================================================
> --- linux-2.6.orig/drivers/xen/events.c
> +++ linux-2.6/drivers/xen/events.c
> @@ -143,6 +143,7 @@ static void init_evtchn_cpu_bindings(voi
> /* By default all event channels notify CPU#0. */
> for_each_irq_desc(i, desc)
> desc->affinity = cpumask_of_cpu(0);
> + end_for_each_irq_desc();
> #endif
>
> memset(cpu_evtchn, 0, sizeof(cpu_evtchn));
> @@ -231,7 +232,7 @@ static int find_unbound_irq(void)
> int irq;
>
> /* Only allocate from dynirq range */
> - for_each_irq_nr(irq)
> + for (irq = 0; irq < nr_irqs; irq++)
> if (irq_bindcount[irq] == 0)
> break;
>
> @@ -792,7 +793,7 @@ void xen_irq_resume(void)
> mask_evtchn(evtchn);
>
> /* No IRQ <-> event-channel mappings. */
> - for_each_irq_nr(irq)
> + for (irq = 0; irq < nr_irqs; irq++)
> irq_info[irq].evtchn = 0; /* zap event-channel binding */
>
> for (evtchn = 0; evtchn < NR_EVENT_CHANNELS; evtchn++)
> @@ -824,7 +825,7 @@ void __init xen_init_IRQ(void)
> mask_evtchn(i);
>
> /* Dynamic IRQ space is currently unbound. Zero the refcnts. */
> - for_each_irq_nr(i)
> + for (i = 0; i < nr_irqs; i++)
> irq_bindcount[i] = 0;
>
> irq_ctx_init(smp_processor_id());
> Index: linux-2.6/fs/proc/stat.c
> ===================================================================
> --- linux-2.6.orig/fs/proc/stat.c
> +++ linux-2.6/fs/proc/stat.c
> @@ -27,6 +27,9 @@ static int show_stat(struct seq_file *p,
> u64 sum = 0;
> struct timespec boottime;
> unsigned int per_irq_sum;
> +#ifdef CONFIG_GENERIC_HARDIRQS
> + struct irq_desc *desc;
> +#endif
>
> user = nice = system = idle = iowait =
> irq = softirq = steal = cputime64_zero;
> @@ -44,10 +47,9 @@ static int show_stat(struct seq_file *p,
> softirq = cputime64_add(softirq, kstat_cpu(i).cpustat.softirq);
> steal = cputime64_add(steal, kstat_cpu(i).cpustat.steal);
> guest = cputime64_add(guest, kstat_cpu(i).cpustat.guest);
> -
> - for_each_irq_nr(j)
> + for_each_irq_desc(j, desc)
> sum += kstat_irqs_cpu(j, i);
> -
> + end_for_each_irq_desc();
> sum += arch_irq_stat_cpu(i);
> }
> sum += arch_irq_stat();
> @@ -90,14 +92,18 @@ static int show_stat(struct seq_file *p,
> seq_printf(p, "intr %llu", (unsigned long long)sum);
>
> /* sum again ? it could be updated? */
> - for_each_irq_nr(j) {
> + for_each_irq_desc(j, desc) {
> per_irq_sum = 0;
> -
> for_each_possible_cpu(i)
> per_irq_sum += kstat_irqs_cpu(j, i);
>
> +#ifdef CONFIG_HAVE_SPARSE_IRQ
> + seq_printf(p, " %#x:%u", j, per_irq_sum);
> +#else
> seq_printf(p, " %u", per_irq_sum);
> +#endif
> }
> + end_for_each_irq_desc();
>
> seq_printf(p,
> "\nctxt %llu\n"
> Index: linux-2.6/fs/proc/interrupts.c
> ===================================================================
> --- linux-2.6.orig/fs/proc/interrupts.c
> +++ linux-2.6/fs/proc/interrupts.c
> @@ -10,20 +10,31 @@
> */
> static void *int_seq_start(struct seq_file *f, loff_t *pos)
> {
> +#ifdef CONFIG_HAVE_SPARSE_IRQ
> + rcu_read_lock();
> + return seq_list_start(&sparse_irqs_head, *pos);
> +#else
> return (*pos <= nr_irqs) ? pos : NULL;
> +#endif
> }
>
> static void *int_seq_next(struct seq_file *f, void *v, loff_t *pos)
> {
> +#ifdef CONFIG_HAVE_SPARSE_IRQ
> + return seq_list_next(v, &sparse_irqs_head, pos);
> +#else
> (*pos)++;
> if (*pos > nr_irqs)
> return NULL;
> return pos;
> +#endif
> }
>
> static void int_seq_stop(struct seq_file *f, void *v)
> {
> - /* Nothing to do */
> +#ifdef CONFIG_HAVE_SPARSE_IRQ
> + rcu_read_unlock();
> +#endif
> }
>
> static const struct seq_operations int_seq_ops = {
> Index: linux-2.6/include/linux/interrupt.h
> ===================================================================
> --- linux-2.6.orig/include/linux/interrupt.h
> +++ linux-2.6/include/linux/interrupt.h
> @@ -18,6 +18,8 @@
> #include <asm/ptrace.h>
> #include <asm/system.h>
>
> +extern int nr_irqs;
> +
> /*
> * These correspond to the IORESOURCE_IRQ_* defines in
> * linux/ioport.h to select the interrupt line behaviour. When
> Index: linux-2.6/include/linux/irq.h
> ===================================================================
> --- linux-2.6.orig/include/linux/irq.h
> +++ linux-2.6/include/linux/irq.h
> @@ -128,6 +128,8 @@ struct irq_chip {
> const char *typename;
> };
>
> +struct timer_rand_state;
> +struct irq_2_iommu;
> /**
> * struct irq_desc - interrupt descriptor
> *
> @@ -154,6 +156,15 @@ struct irq_chip {
> */
> struct irq_desc {
> unsigned int irq;
> +#ifdef CONFIG_HAVE_SPARSE_IRQ
> + struct list_head list;
> + struct list_head hash_entry;
> + struct timer_rand_state *timer_rand_state;
> + unsigned int *kstat_irqs;
> +# ifdef CONFIG_INTR_REMAP
> + struct irq_2_iommu *irq_2_iommu;
> +# endif
> +#endif
> irq_flow_handler_t handle_irq;
> struct irq_chip *chip;
> struct msi_desc *msi_desc;
> @@ -181,14 +192,53 @@ struct irq_desc {
> const char *name;
> } ____cacheline_internodealigned_in_smp;
>
> +extern struct irq_desc *irq_to_desc(unsigned int irq);
> +extern struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu);
> +extern struct irq_desc *irq_to_desc_alloc(unsigned int irq);
> +
> +#ifndef CONFIG_HAVE_SPARSE_IRQ
>
> +/* could be removed if we get rid of all irq_desc reference */
> extern struct irq_desc irq_desc[NR_IRQS];
>
> -static inline struct irq_desc *irq_to_desc(unsigned int irq)
> +#ifdef CONFIG_GENERIC_HARDIRQS
> +# define for_each_irq_desc(irq, desc) \
> + for (irq = 0, desc = irq_desc; irq < nr_irqs; irq++, desc++)
> +# define for_each_irq_desc_reverse(irq, desc) \
> + for (irq = nr_irqs - 1, desc = irq_desc + (nr_irqs - 1); \
> + irq >= 0; irq--, desc--)
> +
> +#define end_for_each_irq_desc()
> +#endif
> +
> +static inline early_sparse_irq_init_work(void)
> {
> - return (irq < nr_irqs) ? irq_desc + irq : NULL;
> }
>
> +#else
> +
> +void early_sparse_irq_init_work(void);
> +extern struct list_head sparse_irqs_head;
> +#define for_each_irq_desc(irqX, desc) \
> + rcu_read_lock(); \
> + for (desc = list_entry(rcu_dereference(sparse_irqs_head.next), typeof(*desc), list), irqX = desc->irq; \
> + prefetch(desc->list.next), &desc->list != &sparse_irqs_head; \
> + desc = list_entry(rcu_dereference(desc->list.next), typeof(*desc), list), irqX = desc ? desc->irq : -1U)
> +
> +#define for_each_irq_desc_reverse(irqX, desc) \
> + rcu_read_lock(); \
> + for (desc = list_entry(rcu_dereference(sparse_irqs_head.prev), typeof(*desc), list), irqX = desc->irq; \
> + prefetch(desc->list.prev), &desc->list != &sparse_irqs_head; \
> + desc = list_entry(rcu_dereference(desc->list.prev), typeof(*desc), list), irqX = desc ? desc->irq : -1U)
> +
> +#define end_for_each_irq_desc() rcu_read_unlock()
> +
> +#define kstat_irqs_this_cpu(DESC) \
> + ((DESC)->kstat_irqs[smp_processor_id()])
> +#define kstat_incr_irqs_this_cpu(irqno, DESC) \
> + ((DESC)->kstat_irqs[smp_processor_id()]++)
> +#endif
> +
> /*
> * Migration helpers for obsolete names, they will go away:
> */
> Index: linux-2.6/include/linux/kernel_stat.h
> ===================================================================
> --- linux-2.6.orig/include/linux/kernel_stat.h
> +++ linux-2.6/include/linux/kernel_stat.h
> @@ -28,7 +28,9 @@ struct cpu_usage_stat {
>
> struct kernel_stat {
> struct cpu_usage_stat cpustat;
> - unsigned int irqs[NR_IRQS];
> +#ifndef CONFIG_HAVE_SPARSE_IRQ
> + unsigned int irqs[NR_IRQS];
> +#endif
> };
>
> DECLARE_PER_CPU(struct kernel_stat, kstat);
> @@ -39,6 +41,10 @@ DECLARE_PER_CPU(struct kernel_stat, ksta
>
> extern unsigned long long nr_context_switches(void);
>
> +#ifndef CONFIG_HAVE_SPARSE_IRQ
> +#define kstat_irqs_this_cpu(irq) \
> + (kstat_this_cpu.irqs[irq])
> +
> struct irq_desc;
>
> static inline void kstat_incr_irqs_this_cpu(unsigned int irq,
> @@ -46,11 +52,17 @@ static inline void kstat_incr_irqs_this_
> {
> kstat_this_cpu.irqs[irq]++;
> }
> +#endif
> +
>
> +#ifndef CONFIG_HAVE_SPARSE_IRQ
> static inline unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
> {
> return kstat_cpu(cpu).irqs[irq];
> }
> +#else
> +extern unsigned int kstat_irqs_cpu(unsigned int irq, int cpu);
> +#endif
>
> /*
> * Number of interrupts per specific IRQ source, since bootup
> Index: linux-2.6/kernel/irq/autoprobe.c
> ===================================================================
> --- linux-2.6.orig/kernel/irq/autoprobe.c
> +++ linux-2.6/kernel/irq/autoprobe.c
> @@ -58,6 +58,7 @@ unsigned long probe_irq_on(void)
> }
> spin_unlock_irq(&desc->lock);
> }
> + end_for_each_irq_desc();
>
> /* Wait for longstanding interrupts to trigger. */
> msleep(20);
> @@ -76,6 +77,7 @@ unsigned long probe_irq_on(void)
> }
> spin_unlock_irq(&desc->lock);
> }
> + end_for_each_irq_desc();
>
> /*
> * Wait for spurious interrupts to trigger
> @@ -100,6 +102,7 @@ unsigned long probe_irq_on(void)
> }
> spin_unlock_irq(&desc->lock);
> }
> + end_for_each_irq_desc();
>
> return mask;
> }
> @@ -136,6 +139,7 @@ unsigned int probe_irq_mask(unsigned lon
> }
> spin_unlock_irq(&desc->lock);
> }
> + end_for_each_irq_desc();
> mutex_unlock(&probing_active);
>
> return mask & val;
> @@ -180,6 +184,7 @@ int probe_irq_off(unsigned long val)
> }
> spin_unlock_irq(&desc->lock);
> }
> + end_for_each_irq_desc();
> mutex_unlock(&probing_active);
>
> if (nr_of_irqs > 1)
> Index: linux-2.6/kernel/irq/chip.c
> ===================================================================
> --- linux-2.6.orig/kernel/irq/chip.c
> +++ linux-2.6/kernel/irq/chip.c
> @@ -24,9 +24,11 @@
> */
> void dynamic_irq_init(unsigned int irq)
> {
> - struct irq_desc *desc = irq_to_desc(irq);
> + struct irq_desc *desc;
> unsigned long flags;
>
> + /* first time to use this irq_desc */
> + desc = irq_to_desc_alloc(irq);
> if (!desc) {
> WARN(1, KERN_ERR "Trying to initialize invalid IRQ%d\n", irq);
> return;
> Index: linux-2.6/kernel/irq/handle.c
> ===================================================================
> --- linux-2.6.orig/kernel/irq/handle.c
> +++ linux-2.6/kernel/irq/handle.c
> @@ -15,9 +15,16 @@
> #include <linux/random.h>
> #include <linux/interrupt.h>
> #include <linux/kernel_stat.h>
> +#include <linux/rculist.h>
> +#include <linux/hash.h>
>
> #include "internals.h"
>
> +/*
> + * lockdep: we want to handle all irq_desc locks as a single lock-class:
> + */
> +static struct lock_class_key irq_desc_lock_class;
> +
> /**
> * handle_bad_irq - handle spurious and unhandled irqs
> * @irq: the interrupt number
> @@ -49,6 +56,179 @@ void handle_bad_irq(unsigned int irq, st
> int nr_irqs = NR_IRQS;
> EXPORT_SYMBOL_GPL(nr_irqs);
>
> +#ifdef CONFIG_HAVE_SPARSE_IRQ
> +static struct irq_desc irq_desc_init = {
> + .irq = -1U,
> + .status = IRQ_DISABLED,
> + .chip = &no_irq_chip,
> + .handle_irq = handle_bad_irq,
> + .depth = 1,
> + .lock = __SPIN_LOCK_UNLOCKED(irq_desc_init.lock),
> +#ifdef CONFIG_SMP
> + .affinity = CPU_MASK_ALL
> +#endif
> +};
> +
> +static void init_kstat_irqs(struct irq_desc *desc, int cpu, int nr)
> +{
> + unsigned long bytes;
> + char *ptr;
> + int node;
> + unsigned int irq;
> +
> + /* Compute how many bytes we need per irq and allocate them */
> + bytes = nr * sizeof(unsigned int);
> + irq = desc->irq;
> +
> + if (cpu < 0)
> + cpu = smp_processor_id();
> +
> + node = cpu_to_node(cpu);
> + ptr = kzalloc_node(bytes, GFP_KERNEL, node);
> + printk(KERN_DEBUG " alloc kstat_irqs for %d aka %#x on cpu %d node %d\n",
> + irq, irq, cpu, node);
> +
> + desc->kstat_irqs = (unsigned int *)ptr;
> +}
> +
> +static void init_one_irq_desc(struct irq_desc *desc)
> +{
> + memcpy(desc, &irq_desc_init, sizeof(struct irq_desc));
> + lockdep_set_class(&desc->lock, &irq_desc_lock_class);
> +}
> +
> +/*
> + * Protect the sparse_irqs_free freelist:
> + */
> +static DEFINE_SPINLOCK(sparse_irq_lock);
> +LIST_HEAD(sparse_irqs_head);
> +
> +/*
> + * The sparse irqs are in a hash-table as well, for fast lookup:
> + */
> +#define SPARSEIRQHASH_BITS (13 - 1)
> +#define SPARSEIRQHASH_SIZE (1UL << SPARSEIRQHASH_BITS)
> +#define __sparseirqhashfn(key) hash_long((unsigned long)key, SPARSEIRQHASH_BITS)
> +#define sparseirqhashentry(key) (sparseirqhash_table + __sparseirqhashfn((key)))
> +
> +static struct list_head sparseirqhash_table[SPARSEIRQHASH_SIZE];
> +
> +static struct irq_desc irq_desc_legacy[NR_IRQS_LEGACY] __cacheline_aligned_in_smp = {
> + [0 ... NR_IRQS_LEGACY-1] = {
> + .irq = -1U,
> + .status = IRQ_DISABLED,
> + .chip = &no_irq_chip,
> + .handle_irq = handle_bad_irq,
> + .depth = 1,
> + .lock = __SPIN_LOCK_UNLOCKED(irq_desc_init.lock),
> +#ifdef CONFIG_SMP
> + .affinity = CPU_MASK_ALL
> +#endif
> + }
> +};
> +
> +/* FIXME: use bootmem alloc ...*/
> +static unsigned int kstat_irqs_legacy[NR_IRQS_LEGACY][NR_CPUS];
> +
> +void __init early_sparse_irq_init_work(void)
> +{
> + struct irq_desc *desc;
> + int legacy_count;
> + int i;
> +
> + for (i = 0; i < SPARSEIRQHASH_SIZE; i++)
> + INIT_LIST_HEAD(sparseirqhash_table + i);
> +
> + desc = irq_desc_legacy;
> + legacy_count = ARRAY_SIZE(irq_desc_legacy);
> +
> + for (i = 0; i < legacy_count; i++) {
> + struct list_head *hash_head;
> +
> + hash_head = sparseirqhashentry(i);
> + desc[i].irq = i;
> + desc[i].kstat_irqs = kstat_irqs_legacy[i];
> + list_add_tail(&desc[i].hash_entry, hash_head);
> + list_add_tail(&desc[i].list, &sparse_irqs_head);
> + }
> +}
> +
> +struct irq_desc *irq_to_desc(unsigned int irq)
> +{
> + struct irq_desc *desc;
> + struct list_head *hash_head;
> +
> + hash_head = sparseirqhashentry(irq);
> +
> + /*
> + * We can walk the hash lockfree, because the hash only
> + * grows, and we are careful when adding entries to the end:
> + */
> + list_for_each_entry(desc, hash_head, hash_entry) {
> + if (desc->irq == irq)
> + return desc;
> + }
> +
> + return NULL;
> +}
> +
> +struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu)
> +{
> + struct irq_desc *desc;
> + struct list_head *hash_head;
> + unsigned long flags;
> + int node;
> +
> + desc = irq_to_desc(irq);
> + if (desc)
> + return desc;
> +
> + hash_head = sparseirqhashentry(irq);
> +
> + spin_lock_irqsave(&sparse_irq_lock, flags);
> +
> + /*
> + * We have to do the hash-walk again, to avoid races
> + * with another CPU:
> + */
> + list_for_each_entry(desc, hash_head, hash_entry)
> + if (desc->irq == irq)
> + goto out_unlock;
> +
> + if (cpu < 0)
> + cpu = smp_processor_id();
> +
> + node = cpu_to_node(cpu);
> + desc = kzalloc_node(sizeof(*desc), GFP_KERNEL, node);
> + init_one_irq_desc(desc);
> + desc->irq = irq;
> + init_kstat_irqs(desc, cpu, nr_cpu_ids);
> + printk(KERN_DEBUG " alloc irq_desc for %d aka %#x on cpu %d node %d\n",
> + irq, irq, cpu, node);
> +
> + /*
> + * We use RCU's safe list-add method to make
> + * parallel walking of the hash-list safe:
> + */
> + list_add_tail_rcu(&desc->hash_entry, hash_head);
> + /*
> + * Add it to the global list:
> + */
> + list_add_tail_rcu(&desc->list, &sparse_irqs_head);
> +
> +out_unlock:
> + spin_unlock_irqrestore(&sparse_irq_lock, flags);
> +
> + return desc;
> +}
> +
> +struct irq_desc *irq_to_desc_alloc(unsigned int irq)
> +{
> + return irq_to_desc_alloc_cpu(irq, -1);
> +}
> +
> +#else
> +
> struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
> [0 ... NR_IRQS-1] = {
> .status = IRQ_DISABLED,
> @@ -62,6 +242,23 @@ struct irq_desc irq_desc[NR_IRQS] __cach
> }
> };
>
> +struct irq_desc *irq_to_desc(unsigned int irq)
> +{
> + if (irq < nr_irqs)
> + return &irq_desc[irq];
> +
> + return NULL;
> +}
> +struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu)
> +{
> + return irq_to_desc(irq);
> +}
> +struct irq_desc *irq_to_desc_alloc(unsigned int irq)
> +{
> + return irq_to_desc(irq);
> +}
> +#endif
> +
> /*
> * What should we do if we get a hw irq event on an illegal vector?
> * Each architecture has to answer this themself.
> @@ -261,17 +458,24 @@ out:
>
>
> #ifdef CONFIG_TRACE_IRQFLAGS
> -/*
> - * lockdep: we want to handle all irq_desc locks as a single lock-class:
> - */
> -static struct lock_class_key irq_desc_lock_class;
> -
> void early_init_irq_lock_class(void)
> {
> +#ifndef CONFIG_HAVE_SPARSE_IRQ
> struct irq_desc *desc;
> int i;
>
> for_each_irq_desc(i, desc)
> lockdep_set_class(&desc->lock, &irq_desc_lock_class);
> +#endif
> }
> #endif
> +
> +#ifdef CONFIG_HAVE_SPARSE_IRQ
> +unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
> +{
> + struct irq_desc *desc = irq_to_desc(irq);
> + return desc->kstat_irqs[cpu];
> +}
> +#endif
> +EXPORT_SYMBOL(kstat_irqs_cpu);
> +
> Index: linux-2.6/arch/x86/kernel/irq.c
> ===================================================================
> --- linux-2.6.orig/arch/x86/kernel/irq.c
> +++ linux-2.6/arch/x86/kernel/irq.c
> @@ -99,25 +99,20 @@ static int show_other_interrupts(struct
> int show_interrupts(struct seq_file *p, void *v)
> {
> unsigned long flags, any_count = 0;
> - int i = *(loff_t *) v, j;
> + int i, j;
> struct irqaction *action;
> struct irq_desc *desc;
>
> - if (i > nr_irqs)
> - return 0;
> -
> - if (i == nr_irqs)
> - return show_other_interrupts(p);
> -
> - /* print header */
> - if (i == 0) {
> + desc = list_entry(v, struct irq_desc, list);
> + i = desc->irq;
> + if (&desc->list == sparse_irqs_head.next) {
> + /* print header */
> seq_printf(p, " ");
> for_each_online_cpu(j)
> seq_printf(p, "CPU%-8d", j);
> seq_putc(p, '\n');
> }
>
> - desc = irq_to_desc(i);
> spin_lock_irqsave(&desc->lock, flags);
> #ifndef CONFIG_SMP
> any_count = kstat_irqs(i);
> @@ -148,6 +143,10 @@ int show_interrupts(struct seq_file *p,
> seq_putc(p, '\n');
> out:
> spin_unlock_irqrestore(&desc->lock, flags);
> +
> + if (&desc->list == sparse_irqs_head.prev)
> + show_other_interrupts(p);
> +
> return 0;
> }
>
> Index: linux-2.6/include/linux/irqnr.h
> ===================================================================
> --- linux-2.6.orig/include/linux/irqnr.h
> +++ linux-2.6/include/linux/irqnr.h
> @@ -7,18 +7,11 @@
>
> # define for_each_irq_desc(irq, desc) \
> for (irq = 0; irq < nr_irqs; irq++)
> -#else
> -extern int nr_irqs;
> +# define end_for_each_irq_desc()
>
> -# define for_each_irq_desc(irq, desc) \
> - for (irq = 0, desc = irq_desc; irq < nr_irqs; irq++, desc++)
> -
> -# define for_each_irq_desc_reverse(irq, desc) \
> - for (irq = nr_irqs - 1, desc = irq_desc + (nr_irqs - 1); \
> - irq >= 0; irq--, desc--)
> +static inline early_sparse_irq_init_work(void)
> +{
> +}
> #endif
>
> -#define for_each_irq_nr(irq) \
> - for (irq = 0; irq < nr_irqs; irq++)
> -
> #endif
> Index: linux-2.6/arch/x86/kernel/irq_32.c
> ===================================================================
> --- linux-2.6.orig/arch/x86/kernel/irq_32.c
> +++ linux-2.6/arch/x86/kernel/irq_32.c
> @@ -255,6 +255,7 @@ void fixup_irqs(cpumask_t map)
> else if (desc->action && !(warned++))
> printk("Cannot set affinity for irq %i\n", irq);
> }
> + end_for_each_irq_desc();
>
> #if 0
> barrier();
> Index: linux-2.6/arch/x86/kernel/irq_64.c
> ===================================================================
> --- linux-2.6.orig/arch/x86/kernel/irq_64.c
> +++ linux-2.6/arch/x86/kernel/irq_64.c
> @@ -130,6 +130,7 @@ void fixup_irqs(cpumask_t map)
> else if (!set_affinity)
> printk("Cannot set affinity for irq %i\n", irq);
> }
> + end_for_each_irq_desc();
>
> /* That doesn't seem sufficient. Give it 1ms. */
> local_irq_enable();
> Index: linux-2.6/kernel/irq/proc.c
> ===================================================================
> --- linux-2.6.orig/kernel/irq/proc.c
> +++ linux-2.6/kernel/irq/proc.c
> @@ -245,5 +245,6 @@ void init_irq_proc(void)
> */
> for_each_irq_desc(irq, desc)
> register_irq_proc(irq, desc);
> + end_for_each_irq_desc();
> }
>
> Index: linux-2.6/kernel/irq/spurious.c
> ===================================================================
> --- linux-2.6.orig/kernel/irq/spurious.c
> +++ linux-2.6/kernel/irq/spurious.c
> @@ -100,6 +100,7 @@ static int misrouted_irq(int irq)
> if (try_one_irq(i, desc))
> ok = 1;
> }
> + end_for_each_irq_desc();
> /* So the caller can adjust the irq error counts */
> return ok;
> }
> @@ -124,6 +125,7 @@ static void poll_spurious_irqs(unsigned
> try_one_irq(i, desc);
> }
>
> + end_for_each_irq_desc();
> mod_timer(&poll_spurious_irq_timer,
> jiffies + POLL_SPURIOUS_IRQ_INTERVAL);
> }
> Index: linux-2.6/arch/x86/kernel/setup_percpu.c
> ===================================================================
> --- linux-2.6.orig/arch/x86/kernel/setup_percpu.c
> +++ linux-2.6/arch/x86/kernel/setup_percpu.c
> @@ -191,6 +191,10 @@ void __init setup_per_cpu_areas(void)
>
> /* Setup node to cpumask map */
> setup_node_to_cpumask_map();
> +
> + /* init_work to init list for sparseirq */
> + early_sparse_irq_init_work();
> + early_irq_cfg_init_work();
> }
>
> #endif
> Index: linux-2.6/init/main.c
> ===================================================================
> --- linux-2.6.orig/init/main.c
> +++ linux-2.6/init/main.c
> @@ -363,7 +363,10 @@ static void __init smp_init(void)
> #define smp_init() do { } while (0)
> #endif
>
> -static inline void setup_per_cpu_areas(void) { }
> +static inline void setup_per_cpu_areas(void)
> +{
> + early_sparse_irq_init_work();
> +}
> static inline void setup_nr_cpu_ids(void) { }
> static inline void smp_prepare_cpus(unsigned int maxcpus) { }
>
> @@ -409,6 +412,8 @@ static void __init setup_per_cpu_areas(v
> memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
> ptr += size;
> }
> +
> + early_sparse_irq_init_work();
> }
> #endif /* CONFIG_HAVE_SETUP_PER_CPU_AREA */
>
> Index: linux-2.6/arch/x86/include/asm/io_apic.h
> ===================================================================
> --- linux-2.6.orig/arch/x86/include/asm/io_apic.h
> +++ linux-2.6/arch/x86/include/asm/io_apic.h
> @@ -199,6 +199,7 @@ extern void reinit_intr_remapped_IO_APIC
> #endif
>
> extern int probe_nr_irqs(void);
> +void early_irq_cfg_init_work(void);
>
> #else /* !CONFIG_X86_IO_APIC */
> #define io_apic_assign_pci_irqs 0
> @@ -209,6 +210,9 @@ static inline int probe_nr_irqs(void)
> {
> return NR_IRQS;
> }
> +static inline void early_irq_cfg_init_work(void)
> +{
> +}
> #endif
>
> #endif /* _ASM_X86_IO_APIC_H */
> Index: linux-2.6/arch/x86/include/asm/irq_vectors.h
> ===================================================================
> --- linux-2.6.orig/arch/x86/include/asm/irq_vectors.h
> +++ linux-2.6/arch/x86/include/asm/irq_vectors.h
> @@ -101,6 +101,8 @@
> #define LAST_VM86_IRQ 15
> #define invalid_vm86_irq(irq) ((irq) < 3 || (irq) > 15)
>
> +#define NR_IRQS_LEGACY 16
> +
> #if defined(CONFIG_X86_IO_APIC) && !defined(CONFIG_X86_VOYAGER)
> # if NR_CPUS < MAX_IO_APICS
> # define NR_IRQS (NR_VECTORS + (32 * NR_CPUS))
>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/