[PATCH 1/2] irq: sparseirq enabling v3

From: Yinghai Lu
Date: Wed Nov 26 2008 - 21:27:20 EST


impact: new feature sparseirq

add some kind of hash table as Ingo suggesting.
remove dyna_array

when sparse_irq is used (CONFIG_SPARSE_IRQ), use kzalloc_node to get irq_desc, irq_cfg
use desc->chip_data for x86 to store irq_cfg

also prepare
need to add struct (irq_desc **descp) to ack_edge/level to make sure desc get updated
try to pass desc cfg as more as possible to avoid list looking up.

seperate move_irq_desc to another patch

v2: use pointer array instead of hash
v3: remove code for passing desc

Signed-off-by: Yinghai Lu <yinghai@xxxxxxxxxx>

---
arch/x86/Kconfig | 10
arch/x86/include/asm/io_apic.h | 2
arch/x86/include/asm/irq_vectors.h | 11
arch/x86/kernel/io_apic.c | 634 ++++++++++++++++++++++---------------
arch/x86/kernel/irq.c | 24 +
arch/x86/kernel/irq_32.c | 2
arch/x86/kernel/irq_64.c | 2
arch/x86/kernel/irqinit_32.c | 3
arch/x86/kernel/irqinit_64.c | 3
arch/x86/kernel/setup.c | 2
drivers/char/random.c | 31 +
drivers/pci/intr_remapping.c | 76 ++++
drivers/pci/msi.c | 55 ++-
drivers/xen/events.c | 9
fs/proc/interrupts.c | 18 +
fs/proc/stat.c | 17
include/linux/interrupt.h | 2
include/linux/irq.h | 67 +++
include/linux/irqnr.h | 15
include/linux/kernel_stat.h | 14
include/linux/msi.h | 3
init/main.c | 11
kernel/irq/autoprobe.c | 10
kernel/irq/chip.c | 3
kernel/irq/handle.c | 187 ++++++++++
kernel/irq/proc.c | 3
kernel/irq/spurious.c | 4
27 files changed, 900 insertions(+), 318 deletions(-)

Index: linux-2.6/arch/x86/Kconfig
===================================================================
--- linux-2.6.orig/arch/x86/Kconfig
+++ linux-2.6/arch/x86/Kconfig
@@ -241,6 +241,16 @@ config X86_HAS_BOOT_CPU_ID
def_bool y
depends on X86_VOYAGER

+config SPARSE_IRQ
+ bool "Support sparse irq numbering"
+ depends on PCI_MSI || HT_IRQ
+ default y
+ help
+ This enables support for sparse irq, esp for msi/msi-x. You may need
+ if you have lots of cards supports msi-x installed.
+
+ If you don't know what to do here, say 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 +108,33 @@ static int __init parse_noapic(char *str
early_param("noapic", parse_noapic);

struct irq_pin_list;
+
+/*
+ * This is performance-critical, we want to do it O(1)
+ *
+ * the indexing order of this array favors 1:1 mappings
+ * between pins and IRQs.
+ */
+
+struct irq_pin_list {
+ int apic, pin;
+ struct irq_pin_list *next;
+};
+
+static struct irq_pin_list *get_one_free_irq_2_pin(int cpu)
+{
+ struct irq_pin_list *pin;
+ int node;
+
+ node = cpu_to_node(cpu);
+
+ pin = kzalloc_node(sizeof(*pin), GFP_ATOMIC, node);
+ printk(KERN_DEBUG " alloc irq_2_pin on cpu %d node %d\n", cpu, node);
+
+ return pin;
+}
+
struct irq_cfg {
- unsigned int irq;
struct irq_pin_list *irq_2_pin;
cpumask_t domain;
cpumask_t old_domain;
@@ -119,81 +144,102 @@ struct irq_cfg {
};

/* irq_cfg is indexed by the sum of all RTEs in all I/O APICs. */
+#ifdef CONFIG_SPARSE_IRQ
+static struct irq_cfg irq_cfgx[] = {
+#else
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, },
+#endif
+ [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++)
-
-static struct irq_cfg *irq_cfg(unsigned int irq)
+void __init arch_early_irq_init(void)
{
- return irq < nr_irqs ? irq_cfgx + irq : NULL;
+ struct irq_cfg *cfg;
+ struct irq_desc *desc;
+ int count;
+ int i;
+#ifdef CONFIG_SPARSE_IRQ
+ int count_desc = NR_IRQS_LEGACY;
+#else
+ int count_desc = NR_IRQS;
+#endif
+
+ cfg = irq_cfgx;
+ count = ARRAY_SIZE(irq_cfgx);
+
+ BUG_ON(count > count_desc);
+
+ for (i = 0; i < count; i++) {
+ desc = irq_to_desc(i);
+ desc->chip_data = &cfg[i];
+ }
}

-static struct irq_cfg *irq_cfg_alloc(unsigned int irq)
+#ifdef CONFIG_SPARSE_IRQ
+static struct irq_cfg *irq_cfg(unsigned int irq)
{
- return irq_cfg(irq);
+ struct irq_cfg *cfg = NULL;
+ struct irq_desc *desc;
+
+ desc = irq_to_desc(irq);
+ if (desc)
+ cfg = desc->chip_data;
+
+ 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)
+static struct irq_cfg *get_one_free_irq_cfg(int cpu)
+{
+ struct irq_cfg *cfg;
+ int node;

-/*
- * This is performance-critical, we want to do it O(1)
- *
- * the indexing order of this array favors 1:1 mappings
- * between pins and IRQs.
- */
+ node = cpu_to_node(cpu);

-struct irq_pin_list {
- int apic, pin;
- struct irq_pin_list *next;
-};
+ cfg = kzalloc_node(sizeof(*cfg), GFP_ATOMIC, node);
+ printk(KERN_DEBUG " alloc irq_cfg on cpu %d node %d\n", cpu, node);

-static struct irq_pin_list irq_2_pin_head[PIN_MAP_SIZE];
-static struct irq_pin_list *irq_2_pin_ptr;
+ return cfg;
+}

-static void __init irq_2_pin_init(void)
+void arch_init_chip_data(struct irq_desc *desc, 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];
+ struct irq_cfg *cfg;

- irq_2_pin_ptr = &pin[0];
+ cfg = desc->chip_data;
+ if (!cfg) {
+ desc->chip_data = get_one_free_irq_cfg(cpu);
+ if (!desc->chip_data) {
+ printk(KERN_ERR "can not alloc irq_cfg\n");
+ BUG_ON(1);
+ }
+ }
}

-static struct irq_pin_list *get_one_free_irq_2_pin(void)
+#else
+static struct irq_cfg *irq_cfg(unsigned int irq)
{
- struct irq_pin_list *pin = irq_2_pin_ptr;
+ return irq < nr_irqs ? irq_cfgx + irq : NULL;
+}

- if (!pin)
- panic("can not get more irq_2_pin\n");
+#endif

- irq_2_pin_ptr = pin->next;
- pin->next = NULL;
- return pin;
+static inline void set_extra_move_desc(struct irq_desc *desc, cpumask_t mask)
+{
}

struct io_apic {
@@ -237,11 +283,10 @@ static inline void io_apic_modify(unsign
writel(value, &io_apic->data);
}

-static bool io_apic_level_ack_pending(unsigned int irq)
+static bool io_apic_level_ack_pending(struct irq_cfg *cfg)
{
struct irq_pin_list *entry;
unsigned long flags;
- struct irq_cfg *cfg = irq_cfg(irq);

spin_lock_irqsave(&ioapic_lock, flags);
entry = cfg->irq_2_pin;
@@ -323,13 +368,12 @@ static void ioapic_mask_entry(int apic,
}

#ifdef CONFIG_SMP
-static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, u8 vector)
+static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq_cfg *cfg)
{
int apic, pin;
- struct irq_cfg *cfg;
struct irq_pin_list *entry;
+ u8 vector = cfg->vector;

- cfg = irq_cfg(irq);
entry = cfg->irq_2_pin;
for (;;) {
unsigned int reg;
@@ -359,24 +403,27 @@ 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)
+static void set_ioapic_affinity_irq_desc(struct irq_desc *desc, cpumask_t mask)
{
struct irq_cfg *cfg;
unsigned long flags;
unsigned int dest;
cpumask_t tmp;
- struct irq_desc *desc;
+ unsigned int irq;

cpus_and(tmp, mask, cpu_online_map);
if (cpus_empty(tmp))
return;

- cfg = irq_cfg(irq);
- if (assign_irq_vector(irq, mask))
+ irq = desc->irq;
+ cfg = desc->chip_data;
+ if (assign_irq_vector(irq, cfg, mask))
return;

+ set_extra_move_desc(desc, mask);
+
cpus_and(tmp, cfg->domain, mask);
dest = cpu_mask_to_apicid(tmp);
/*
@@ -384,12 +431,20 @@ static void set_ioapic_affinity_irq(unsi
*/
dest = SET_APIC_LOGICAL_ID(dest);

- desc = irq_to_desc(irq);
spin_lock_irqsave(&ioapic_lock, flags);
- __target_IO_APIC_irq(irq, dest, cfg->vector);
+ __target_IO_APIC_irq(irq, dest, cfg);
desc->affinity = mask;
spin_unlock_irqrestore(&ioapic_lock, flags);
}
+
+static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t mask)
+{
+ struct irq_desc *desc;
+
+ desc = irq_to_desc(irq);
+
+ set_ioapic_affinity_irq_desc(desc, mask);
+}
#endif /* CONFIG_SMP */

/*
@@ -397,16 +452,18 @@ static void set_ioapic_affinity_irq(unsi
* shared ISA-space IRQs, so we have to support them. We are super
* fast in the common case, and fast for shared ISA-space IRQs.
*/
-static void add_pin_to_irq(unsigned int irq, int apic, int pin)
+static void add_pin_to_irq_cpu(struct irq_cfg *cfg, int cpu, int apic, int pin)
{
- 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();
+ entry = get_one_free_irq_2_pin(cpu);
+ if (!entry) {
+ printk(KERN_ERR "can not alloc irq_2_pin to add %d - %d\n",
+ apic, pin);
+ return;
+ }
cfg->irq_2_pin = entry;
entry->apic = apic;
entry->pin = pin;
@@ -421,7 +478,7 @@ 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;
@@ -430,11 +487,10 @@ static void add_pin_to_irq(unsigned int
/*
* Reroute an IRQ to a different pin.
*/
-static void __init replace_pin_at_irq(unsigned int irq,
+static void __init replace_pin_at_irq_cpu(struct irq_cfg *cfg, int cpu,
int oldapic, int oldpin,
int newapic, int newpin)
{
- struct irq_cfg *cfg = irq_cfg(irq);
struct irq_pin_list *entry = cfg->irq_2_pin;
int replaced = 0;

@@ -451,18 +507,16 @@ static void __init replace_pin_at_irq(un

/* why? call replace before add? */
if (!replaced)
- add_pin_to_irq(irq, newapic, newpin);
+ add_pin_to_irq_cpu(cfg, cpu, newapic, newpin);
}

-static inline void io_apic_modify_irq(unsigned int irq,
+static inline void io_apic_modify_irq(struct irq_cfg *cfg,
int mask_and, int mask_or,
void (*final)(struct irq_pin_list *entry))
{
int pin;
- struct irq_cfg *cfg;
struct irq_pin_list *entry;

- cfg = irq_cfg(irq);
for (entry = cfg->irq_2_pin; entry != NULL; entry = entry->next) {
unsigned int reg;
pin = entry->pin;
@@ -475,9 +529,9 @@ static inline void io_apic_modify_irq(un
}
}

-static void __unmask_IO_APIC_irq(unsigned int irq)
+static void __unmask_IO_APIC_irq(struct irq_cfg *cfg)
{
- io_apic_modify_irq(irq, ~IO_APIC_REDIR_MASKED, 0, NULL);
+ io_apic_modify_irq(cfg, ~IO_APIC_REDIR_MASKED, 0, NULL);
}

#ifdef CONFIG_X86_64
@@ -492,47 +546,64 @@ void io_apic_sync(struct irq_pin_list *e
readl(&io_apic->data);
}

-static void __mask_IO_APIC_irq(unsigned int irq)
+static void __mask_IO_APIC_irq(struct irq_cfg *cfg)
{
- io_apic_modify_irq(irq, ~0, IO_APIC_REDIR_MASKED, &io_apic_sync);
+ io_apic_modify_irq(cfg, ~0, IO_APIC_REDIR_MASKED, &io_apic_sync);
}
#else /* CONFIG_X86_32 */
-static void __mask_IO_APIC_irq(unsigned int irq)
+static void __mask_IO_APIC_irq(struct irq_cfg *cfg)
{
- io_apic_modify_irq(irq, ~0, IO_APIC_REDIR_MASKED, NULL);
+ io_apic_modify_irq(cfg, ~0, IO_APIC_REDIR_MASKED, NULL);
}

-static void __mask_and_edge_IO_APIC_irq(unsigned int irq)
+static void __mask_and_edge_IO_APIC_irq(struct irq_cfg *cfg)
{
- io_apic_modify_irq(irq, ~IO_APIC_REDIR_LEVEL_TRIGGER,
+ io_apic_modify_irq(cfg, ~IO_APIC_REDIR_LEVEL_TRIGGER,
IO_APIC_REDIR_MASKED, NULL);
}

-static void __unmask_and_level_IO_APIC_irq(unsigned int irq)
+static void __unmask_and_level_IO_APIC_irq(struct irq_cfg *cfg)
{
- io_apic_modify_irq(irq, ~IO_APIC_REDIR_MASKED,
+ io_apic_modify_irq(cfg, ~IO_APIC_REDIR_MASKED,
IO_APIC_REDIR_LEVEL_TRIGGER, NULL);
}
#endif /* CONFIG_X86_32 */

-static void mask_IO_APIC_irq (unsigned int irq)
+static void mask_IO_APIC_irq_desc(struct irq_desc *desc)
{
+ struct irq_cfg *cfg = desc->chip_data;
unsigned long flags;

+ BUG_ON(!cfg);
+
spin_lock_irqsave(&ioapic_lock, flags);
- __mask_IO_APIC_irq(irq);
+ __mask_IO_APIC_irq(cfg);
spin_unlock_irqrestore(&ioapic_lock, flags);
}

-static void unmask_IO_APIC_irq (unsigned int irq)
+static void unmask_IO_APIC_irq_desc(struct irq_desc *desc)
{
+ struct irq_cfg *cfg = desc->chip_data;
unsigned long flags;

spin_lock_irqsave(&ioapic_lock, flags);
- __unmask_IO_APIC_irq(irq);
+ __unmask_IO_APIC_irq(cfg);
spin_unlock_irqrestore(&ioapic_lock, flags);
}

+static void mask_IO_APIC_irq(unsigned int irq)
+{
+ struct irq_desc *desc = irq_to_desc(irq);
+
+ mask_IO_APIC_irq_desc(desc);
+}
+static void unmask_IO_APIC_irq(unsigned int irq)
+{
+ struct irq_desc *desc = irq_to_desc(irq);
+
+ unmask_IO_APIC_irq_desc(desc);
+}
+
static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin)
{
struct IO_APIC_route_entry entry;
@@ -809,7 +880,7 @@ 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 +1105,7 @@ 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
@@ -1050,16 +1121,13 @@ 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);
+ if ((cfg->move_in_progress) || cfg->move_cleanup_count)
+ return -EBUSY;

/* Only try and allocate irqs on cpus that are present */
cpus_and(mask, mask, cpu_online_map);

- if ((cfg->move_in_progress) || cfg->move_cleanup_count)
- return -EBUSY;
-
old_vector = cfg->vector;
if (old_vector) {
cpumask_t tmp;
@@ -1113,24 +1181,22 @@ 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;
@@ -1162,14 +1228,16 @@ 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];
@@ -1215,11 +1283,8 @@ static inline int IO_APIC_irq_trigger(in
}
#endif

-static void ioapic_register_intr(int irq, unsigned long trigger)
+static void ioapic_register_intr(int irq, struct irq_desc *desc, unsigned long trigger)
{
- struct irq_desc *desc;
-
- desc = irq_to_desc(irq);

if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
trigger == IOAPIC_LEVEL)
@@ -1311,7 +1376,7 @@ static int setup_ioapic_entry(int apic,
return 0;
}

-static void setup_IO_APIC_irq(int apic, int pin, unsigned int irq,
+static void setup_IO_APIC_irq(int apic, int pin, unsigned int irq, struct irq_desc *desc,
int trigger, int polarity)
{
struct irq_cfg *cfg;
@@ -1321,10 +1386,10 @@ static void setup_IO_APIC_irq(int apic,
if (!IO_APIC_IRQ(irq))
return;

- cfg = irq_cfg(irq);
+ cfg = desc->chip_data;

mask = TARGET_CPUS;
- if (assign_irq_vector(irq, mask))
+ if (assign_irq_vector(irq, cfg, mask))
return;

cpus_and(mask, cfg->domain, mask);
@@ -1341,12 +1406,12 @@ 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)
+ ioapic_register_intr(irq, desc, trigger);
+ if (irq < NR_IRQS_LEGACY)
disable_8259A_irq(irq);

ioapic_write_entry(apic, pin, entry);
@@ -1356,6 +1421,9 @@ static void __init setup_IO_APIC_irqs(vo
{
int apic, pin, idx, irq;
int notcon = 0;
+ struct irq_desc *desc;
+ struct irq_cfg *cfg;
+ int cpu = boot_cpu_id;

apic_printk(APIC_VERBOSE, KERN_DEBUG "init IO_APIC IRQs\n");

@@ -1387,9 +1455,15 @@ static void __init setup_IO_APIC_irqs(vo
if (multi_timer_check(apic, irq))
continue;
#endif
- add_pin_to_irq(irq, apic, pin);
+ desc = irq_to_desc_alloc_cpu(irq, cpu);
+ if (!desc) {
+ printk(KERN_INFO "can not get irq_desc for %d\n", irq);
+ continue;
+ }
+ cfg = desc->chip_data;
+ add_pin_to_irq_cpu(cfg, cpu, apic, pin);

- setup_IO_APIC_irq(apic, pin, irq,
+ setup_IO_APIC_irq(apic, pin, irq, desc,
irq_trigger(idx), irq_polarity(idx));
}
}
@@ -1448,6 +1522,7 @@ __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)
@@ -1537,8 +1612,10 @@ __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);
@@ -1549,7 +1626,7 @@ __apicdebuginit(void) print_IO_APIC(void
entry = entry->next;
}
printk("\n");
- }
+ } end_for_each_irq_desc();

printk(KERN_INFO ".................................... done.\n");

@@ -2022,14 +2099,16 @@ static unsigned int startup_ioapic_irq(u
{
int was_pending = 0;
unsigned long flags;
+ struct irq_cfg *cfg;

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;
}
- __unmask_IO_APIC_irq(irq);
+ cfg = irq_cfg(irq);
+ __unmask_IO_APIC_irq(cfg);
spin_unlock_irqrestore(&ioapic_lock, flags);

return was_pending;
@@ -2092,35 +2171,37 @@ static DECLARE_DELAYED_WORK(ir_migration
* as simple as edge triggered migration and we can do the irq migration
* with a simple atomic update to IO-APIC RTE.
*/
-static void migrate_ioapic_irq(int irq, cpumask_t mask)
+static void migrate_ioapic_irq_desc(struct irq_desc *desc, cpumask_t mask)
{
struct irq_cfg *cfg;
- struct irq_desc *desc;
cpumask_t tmp, cleanup_mask;
struct irte irte;
int modify_ioapic_rte;
unsigned int dest;
unsigned long flags;
+ unsigned int irq;

cpus_and(tmp, mask, cpu_online_map);
if (cpus_empty(tmp))
return;

+ irq = desc->irq;
if (get_irte(irq, &irte))
return;

- if (assign_irq_vector(irq, mask))
+ cfg = desc->chip_data;
+ if (assign_irq_vector(irq, cfg, mask))
return;

- cfg = irq_cfg(irq);
+ set_extra_move_desc(desc, mask);
+
cpus_and(tmp, cfg->domain, mask);
dest = cpu_mask_to_apicid(tmp);

- desc = irq_to_desc(irq);
modify_ioapic_rte = desc->status & IRQ_LEVEL;
if (modify_ioapic_rte) {
spin_lock_irqsave(&ioapic_lock, flags);
- __target_IO_APIC_irq(irq, dest, cfg->vector);
+ __target_IO_APIC_irq(irq, dest, cfg);
spin_unlock_irqrestore(&ioapic_lock, flags);
}

@@ -2142,14 +2223,14 @@ static void migrate_ioapic_irq(int irq,
desc->affinity = mask;
}

-static int migrate_irq_remapped_level(int irq)
+static int migrate_irq_remapped_level_desc(struct irq_desc *desc)
{
int ret = -1;
- struct irq_desc *desc = irq_to_desc(irq);
+ struct irq_cfg *cfg = desc->chip_data;

- mask_IO_APIC_irq(irq);
+ mask_IO_APIC_irq_desc(desc);

- if (io_apic_level_ack_pending(irq)) {
+ if (io_apic_level_ack_pending(cfg)) {
/*
* Interrupt in progress. Migrating irq now will change the
* vector information in the IO-APIC RTE and that will confuse
@@ -2161,14 +2242,15 @@ static int migrate_irq_remapped_level(in
}

/* everthing is clear. we have right of way */
- migrate_ioapic_irq(irq, desc->pending_mask);
+ migrate_ioapic_irq_desc(desc, desc->pending_mask);

ret = 0;
desc->status &= ~IRQ_MOVE_PENDING;
cpus_clear(desc->pending_mask);

unmask:
- unmask_IO_APIC_irq(irq);
+ unmask_IO_APIC_irq_desc(desc);
+
return ret;
}

@@ -2192,24 +2274,28 @@ static void ir_irq_migration(struct work
desc->chip->set_affinity(irq, desc->pending_mask);
spin_unlock_irqrestore(&desc->lock, flags);
}
- }
+ } end_for_each_irq_desc();
}

/*
* Migrates the IRQ destination in the process context.
*/
-static void set_ir_ioapic_affinity_irq(unsigned int irq, cpumask_t mask)
+static void set_ir_ioapic_affinity_irq_desc(struct irq_desc *desc, cpumask_t mask)
{
- struct irq_desc *desc = irq_to_desc(irq);
-
if (desc->status & IRQ_LEVEL) {
desc->status |= IRQ_MOVE_PENDING;
desc->pending_mask = mask;
- migrate_irq_remapped_level(irq);
+ migrate_irq_remapped_level_desc(desc);
return;
}

- migrate_ioapic_irq(irq, mask);
+ migrate_ioapic_irq_desc(desc, mask);
+}
+static void set_ir_ioapic_affinity_irq(unsigned int irq, cpumask_t mask)
+{
+ struct irq_desc *desc = irq_to_desc(irq);
+
+ set_ir_ioapic_affinity_irq_desc(desc, mask);
}
#endif

@@ -2229,6 +2315,9 @@ asmlinkage void smp_irq_move_cleanup_int
struct irq_cfg *cfg;
irq = __get_cpu_var(vector_irq)[vector];

+ if (irq == -1)
+ continue;
+
desc = irq_to_desc(irq);
if (!desc)
continue;
@@ -2250,9 +2339,10 @@ unlock:
irq_exit();
}

-static void irq_complete_move(unsigned int irq)
+static void irq_complete_move(struct irq_desc **descp)
{
- struct irq_cfg *cfg = irq_cfg(irq);
+ struct irq_desc *desc = *descp;
+ struct irq_cfg *cfg = desc->chip_data;
unsigned vector, me;

if (likely(!cfg->move_in_progress))
@@ -2270,8 +2360,9 @@ static void irq_complete_move(unsigned i
}
}
#else
-static inline void irq_complete_move(unsigned int irq) {}
+static inline void irq_complete_move(struct irq_desc **descp) {}
#endif
+
#ifdef CONFIG_INTR_REMAP
static void ack_x2apic_level(unsigned int irq)
{
@@ -2282,11 +2373,14 @@ static void ack_x2apic_edge(unsigned int
{
ack_x2APIC_irq();
}
+
#endif

static void ack_apic_edge(unsigned int irq)
{
- irq_complete_move(irq);
+ struct irq_desc *desc = irq_to_desc(irq);
+
+ irq_complete_move(&desc);
move_native_irq(irq);
ack_APIC_irq();
}
@@ -2295,18 +2389,21 @@ atomic_t irq_mis_count;

static void ack_apic_level(unsigned int irq)
{
+ struct irq_desc *desc = irq_to_desc(irq);
+
#ifdef CONFIG_X86_32
unsigned long v;
int i;
#endif
+ struct irq_cfg *cfg;
int do_unmask_irq = 0;

- irq_complete_move(irq);
+ irq_complete_move(&desc);
#ifdef CONFIG_GENERIC_PENDING_IRQ
/* If we are moving the irq we need to mask it */
- if (unlikely(irq_to_desc(irq)->status & IRQ_MOVE_PENDING)) {
+ if (unlikely(desc->status & IRQ_MOVE_PENDING)) {
do_unmask_irq = 1;
- mask_IO_APIC_irq(irq);
+ mask_IO_APIC_irq_desc(desc);
}
#endif

@@ -2330,7 +2427,8 @@ static void ack_apic_level(unsigned int
* operation to prevent an edge-triggered interrupt escaping meanwhile.
* The idea is from Manfred Spraul. --macro
*/
- i = irq_cfg(irq)->vector;
+ cfg = desc->chip_data;
+ i = cfg->vector;

v = apic_read(APIC_TMR + ((i & ~0x1f) >> 1));
#endif
@@ -2369,17 +2467,18 @@ static void ack_apic_level(unsigned int
* accurate and is causing problems then it is a hardware bug
* and you can go talk to the chipset vendor about it.
*/
- if (!io_apic_level_ack_pending(irq))
+ cfg = desc->chip_data;
+ if (!io_apic_level_ack_pending(cfg))
move_masked_irq(irq);
- unmask_IO_APIC_irq(irq);
+ unmask_IO_APIC_irq_desc(desc);
}

#ifdef CONFIG_X86_32
if (!(v & (1 << (i & 0x1f)))) {
atomic_inc(&irq_mis_count);
spin_lock(&ioapic_lock);
- __mask_and_edge_IO_APIC_irq(irq);
- __unmask_and_level_IO_APIC_irq(irq);
+ __mask_and_edge_IO_APIC_irq(cfg);
+ __unmask_and_level_IO_APIC_irq(cfg);
spin_unlock(&ioapic_lock);
}
#endif
@@ -2430,22 +2529,21 @@ 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();
}

/*
@@ -2468,7 +2566,7 @@ static void unmask_lapic_irq(unsigned in
apic_write(APIC_LVT0, v & ~APIC_LVT_MASKED);
}

-static void ack_lapic_irq (unsigned int irq)
+static void ack_lapic_irq(unsigned int irq)
{
ack_APIC_irq();
}
@@ -2480,11 +2578,8 @@ static struct irq_chip lapic_chip __read
.ack = ack_lapic_irq,
};

-static void lapic_register_intr(int irq)
+static void lapic_register_intr(int irq, struct irq_desc *desc)
{
- 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");
@@ -2588,7 +2683,9 @@ int timer_through_8259 __initdata;
*/
static inline void __init check_timer(void)
{
- struct irq_cfg *cfg = irq_cfg(0);
+ struct irq_desc *desc = irq_to_desc(0);
+ struct irq_cfg *cfg = desc->chip_data;
+ int cpu = boot_cpu_id;
int apic1, pin1, apic2, pin2;
unsigned long flags;
unsigned int ver;
@@ -2603,7 +2700,7 @@ 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
@@ -2654,10 +2751,10 @@ static inline void __init check_timer(vo
* Ok, does IRQ0 through the IOAPIC work?
*/
if (no_pin1) {
- add_pin_to_irq(0, apic1, pin1);
+ add_pin_to_irq_cpu(cfg, cpu, apic1, pin1);
setup_timer_IRQ0_pin(apic1, pin1, cfg->vector);
}
- unmask_IO_APIC_irq(0);
+ unmask_IO_APIC_irq_desc(desc);
if (timer_irq_works()) {
if (nmi_watchdog == NMI_IO_APIC) {
setup_nmi();
@@ -2683,9 +2780,9 @@ static inline void __init check_timer(vo
/*
* legacy devices should be connected to IO APIC #0
*/
- replace_pin_at_irq(0, apic1, pin1, apic2, pin2);
+ replace_pin_at_irq_cpu(cfg, cpu, apic1, pin1, apic2, pin2);
setup_timer_IRQ0_pin(apic2, pin2, cfg->vector);
- unmask_IO_APIC_irq(0);
+ unmask_IO_APIC_irq_desc(desc);
enable_8259A_irq(0);
if (timer_irq_works()) {
apic_printk(APIC_QUIET, KERN_INFO "....... works.\n");
@@ -2717,7 +2814,7 @@ static inline void __init check_timer(vo
apic_printk(APIC_QUIET, KERN_INFO
"...trying to set up timer as Virtual Wire IRQ...\n");

- lapic_register_intr(0);
+ lapic_register_intr(0, desc);
apic_write(APIC_LVT0, APIC_DM_FIXED | cfg->vector); /* Fixed mode */
enable_8259A_irq(0);

@@ -2902,22 +2999,26 @@ 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;
+ int cpu = boot_cpu_id;
+ struct irq_desc *desc_new = NULL;

irq = 0;
spin_lock_irqsave(&vector_lock, flags);
- for (new = irq_want; new > 0; new--) {
+ for (new = irq_want; new < NR_IRQS; new++) {
if (platform_legacy_irq(new))
continue;
- cfg_new = irq_cfg(new);
- if (cfg_new && cfg_new->vector != 0)
+
+ desc_new = irq_to_desc_alloc_cpu(new, cpu);
+ if (!desc_new) {
+ printk(KERN_INFO "can not get irq_desc for %d\n", new);
+ continue;
+ }
+ cfg_new = desc_new->chip_data;
+
+ if (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 (__assign_irq_vector(new, cfg_new, TARGET_CPUS) == 0)
irq = new;
break;
}
@@ -2925,15 +3026,21 @@ 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;
}

+static int nr_irqs_gsi = NR_IRQS_LEGACY;
int create_irq(void)
{
+ unsigned int irq_want;
int irq;

- irq = create_irq_nr(nr_irqs - 1);
+ irq_want = nr_irqs_gsi;
+ irq = create_irq_nr(irq_want);

if (irq == 0)
irq = -1;
@@ -2944,14 +3051,22 @@ 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);
}

@@ -2966,12 +3081,12 @@ 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);

@@ -3029,35 +3144,35 @@ static int msi_compose_msg(struct pci_de
#ifdef CONFIG_SMP
static void set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
{
+ struct irq_desc *desc = irq_to_desc(irq);
struct irq_cfg *cfg;
struct msi_msg msg;
unsigned int dest;
cpumask_t tmp;
- struct irq_desc *desc;

cpus_and(tmp, mask, cpu_online_map);
if (cpus_empty(tmp))
return;

- if (assign_irq_vector(irq, mask))
+ cfg = desc->chip_data;
+ if (assign_irq_vector(irq, cfg, mask))
return;

- cfg = irq_cfg(irq);
+ set_extra_move_desc(desc, mask);
+
cpus_and(tmp, cfg->domain, mask);
dest = cpu_mask_to_apicid(tmp);

- read_msi_msg(irq, &msg);
+ read_msi_msg_desc(desc, &msg);

msg.data &= ~MSI_DATA_VECTOR_MASK;
msg.data |= MSI_DATA_VECTOR(cfg->vector);
msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
msg.address_lo |= MSI_ADDR_DEST_ID(dest);

- write_msi_msg(irq, &msg);
- desc = irq_to_desc(irq);
+ write_msi_msg_desc(desc, &msg);
desc->affinity = mask;
}
-
#ifdef CONFIG_INTR_REMAP
/*
* Migrate the MSI irq to another cpumask. This migration is
@@ -3065,11 +3180,11 @@ static void set_msi_irq_affinity(unsigne
*/
static void ir_set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
{
+ struct irq_desc *desc = irq_to_desc(irq);
struct irq_cfg *cfg;
unsigned int dest;
cpumask_t tmp, cleanup_mask;
struct irte irte;
- struct irq_desc *desc;

cpus_and(tmp, mask, cpu_online_map);
if (cpus_empty(tmp))
@@ -3078,10 +3193,12 @@ static void ir_set_msi_irq_affinity(unsi
if (get_irte(irq, &irte))
return;

- if (assign_irq_vector(irq, mask))
+ cfg = desc->chip_data;
+ if (assign_irq_vector(irq, cfg, mask))
return;

- cfg = irq_cfg(irq);
+ set_extra_move_desc(desc, mask);
+
cpus_and(tmp, cfg->domain, mask);
dest = cpu_mask_to_apicid(tmp);

@@ -3105,9 +3222,9 @@ static void ir_set_msi_irq_affinity(unsi
cfg->move_in_progress = 0;
}

- desc = irq_to_desc(irq);
desc->affinity = mask;
}
+
#endif
#endif /* CONFIG_SMP */

@@ -3166,7 +3283,7 @@ static int msi_alloc_irte(struct pci_dev
}
#endif

-static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc, int irq)
+static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq)
{
int ret;
struct msi_msg msg;
@@ -3175,7 +3292,7 @@ static int setup_msi_irq(struct pci_dev
if (ret < 0)
return ret;

- set_irq_msi(irq, desc);
+ set_irq_msi(irq, msidesc);
write_msi_msg(irq, &msg);

#ifdef CONFIG_INTR_REMAP
@@ -3195,26 +3312,13 @@ static int setup_msi_irq(struct pci_dev
return 0;
}

-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;
-}
-
-int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc)
+int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc)
{
unsigned int irq;
int ret;
unsigned int irq_want;

- irq_want = build_irq_for_pci_dev(dev) + 0x100;
-
+ irq_want = nr_irqs_gsi;
irq = create_irq_nr(irq_want);
if (irq == 0)
return -1;
@@ -3228,7 +3332,7 @@ int arch_setup_msi_irq(struct pci_dev *d
goto error;
no_ir:
#endif
- ret = setup_msi_irq(dev, desc, irq);
+ ret = setup_msi_irq(dev, msidesc, irq);
if (ret < 0) {
destroy_irq(irq);
return ret;
@@ -3246,7 +3350,7 @@ int arch_setup_msi_irqs(struct pci_dev *
{
unsigned int irq;
int ret, sub_handle;
- struct msi_desc *desc;
+ struct msi_desc *msidesc;
unsigned int irq_want;

#ifdef CONFIG_INTR_REMAP
@@ -3254,10 +3358,11 @@ int arch_setup_msi_irqs(struct pci_dev *
int index = 0;
#endif

- irq_want = build_irq_for_pci_dev(dev) + 0x100;
+ irq_want = nr_irqs_gsi;
sub_handle = 0;
- list_for_each_entry(desc, &dev->msi_list, list) {
- irq = create_irq_nr(irq_want--);
+ list_for_each_entry(msidesc, &dev->msi_list, list) {
+ irq = create_irq_nr(irq_want);
+ irq_want++;
if (irq == 0)
return -1;
#ifdef CONFIG_INTR_REMAP
@@ -3289,7 +3394,7 @@ int arch_setup_msi_irqs(struct pci_dev *
}
no_ir:
#endif
- ret = setup_msi_irq(dev, desc, irq);
+ ret = setup_msi_irq(dev, msidesc, irq);
if (ret < 0)
goto error;
sub_handle++;
@@ -3310,20 +3415,22 @@ void arch_teardown_msi_irq(unsigned int
#ifdef CONFIG_SMP
static void dmar_msi_set_affinity(unsigned int irq, cpumask_t mask)
{
+ struct irq_desc *desc = irq_to_desc(irq);
struct irq_cfg *cfg;
struct msi_msg msg;
unsigned int dest;
cpumask_t tmp;
- struct irq_desc *desc;

cpus_and(tmp, mask, cpu_online_map);
if (cpus_empty(tmp))
return;

- if (assign_irq_vector(irq, mask))
+ cfg = desc->chip_data;
+ if (assign_irq_vector(irq, cfg, mask))
return;

- cfg = irq_cfg(irq);
+ set_extra_move_desc(desc, mask);
+
cpus_and(tmp, cfg->domain, mask);
dest = cpu_mask_to_apicid(tmp);

@@ -3335,9 +3442,9 @@ static void dmar_msi_set_affinity(unsign
msg.address_lo |= MSI_ADDR_DEST_ID(dest);

dmar_msi_write(irq, &msg);
- desc = irq_to_desc(irq);
desc->affinity = mask;
}
+
#endif /* CONFIG_SMP */

struct irq_chip dmar_msi_type = {
@@ -3371,8 +3478,8 @@ int arch_setup_dmar_msi(unsigned int irq
#ifdef CONFIG_SMP
static void hpet_msi_set_affinity(unsigned int irq, cpumask_t mask)
{
+ struct irq_desc *desc = irq_to_desc(irq);
struct irq_cfg *cfg;
- struct irq_desc *desc;
struct msi_msg msg;
unsigned int dest;
cpumask_t tmp;
@@ -3381,10 +3488,12 @@ static void hpet_msi_set_affinity(unsign
if (cpus_empty(tmp))
return;

- if (assign_irq_vector(irq, mask))
+ cfg = desc->chip_data;
+ if (assign_irq_vector(irq, cfg, mask))
return;

- cfg = irq_cfg(irq);
+ set_extra_move_desc(desc, mask);
+
cpus_and(tmp, cfg->domain, mask);
dest = cpu_mask_to_apicid(tmp);

@@ -3396,9 +3505,9 @@ static void hpet_msi_set_affinity(unsign
msg.address_lo |= MSI_ADDR_DEST_ID(dest);

hpet_msi_write(irq, &msg);
- desc = irq_to_desc(irq);
desc->affinity = mask;
}
+
#endif /* CONFIG_SMP */

struct irq_chip hpet_msi_type = {
@@ -3453,26 +3562,28 @@ static void target_ht_irq(unsigned int i

static void set_ht_irq_affinity(unsigned int irq, cpumask_t mask)
{
+ struct irq_desc *desc = irq_to_desc(irq);
struct irq_cfg *cfg;
unsigned int dest;
cpumask_t tmp;
- struct irq_desc *desc;

cpus_and(tmp, mask, cpu_online_map);
if (cpus_empty(tmp))
return;

- if (assign_irq_vector(irq, mask))
+ cfg = desc->chip_data;
+ if (assign_irq_vector(irq, cfg, mask))
return;

- cfg = irq_cfg(irq);
+ set_extra_move_desc(desc, mask);
+
cpus_and(tmp, cfg->domain, mask);
dest = cpu_mask_to_apicid(tmp);

target_ht_irq(irq, dest, cfg->vector);
- desc = irq_to_desc(irq);
desc->affinity = mask;
}
+
#endif

static struct irq_chip ht_irq_chip = {
@@ -3492,13 +3603,13 @@ 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);

@@ -3544,7 +3655,9 @@ 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;

@@ -3553,8 +3666,6 @@ 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));
@@ -3606,9 +3717,16 @@ int __init io_apic_get_redir_entries (in
return reg_01.bits.entries;
}

-int __init probe_nr_irqs(void)
+void __init probe_nr_irqs_gsi(void)
{
- return NR_IRQS;
+ int idx;
+ int nr = 0;
+
+ for (idx = 0; idx < nr_ioapics; idx++)
+ nr += io_apic_get_redir_entries(idx) + 1;
+
+ if (nr > nr_irqs_gsi)
+ nr_irqs_gsi = nr;
}

/* --------------------------------------------------------------------------
@@ -3707,19 +3825,31 @@ int __init io_apic_get_version(int ioapi

int io_apic_set_pci_routing (int ioapic, int pin, int irq, int triggering, int polarity)
{
+ struct irq_desc *desc;
+ struct irq_cfg *cfg;
+ int cpu = boot_cpu_id;
+
if (!IO_APIC_IRQ(irq)) {
apic_printk(APIC_QUIET,KERN_ERR "IOAPIC[%d]: Invalid reference to IRQ 0\n",
ioapic);
return -EINVAL;
}

+ desc = irq_to_desc_alloc_cpu(irq, cpu);
+ if (!desc) {
+ printk(KERN_INFO "can not get irq_desc %d\n", irq);
+ return 0;
+ }
+
/*
* IRQs < 16 are already in the irq_2_pin[] map
*/
- if (irq >= 16)
- add_pin_to_irq(irq, ioapic, pin);
+ if (irq >= NR_IRQS_LEGACY) {
+ cfg = desc->chip_data;
+ add_pin_to_irq_cpu(cfg, cpu, ioapic, pin);
+ }

- setup_IO_APIC_irq(ioapic, pin, irq, triggering, polarity);
+ setup_IO_APIC_irq(ioapic, pin, irq, desc, triggering, polarity);

return 0;
}
@@ -3773,9 +3903,10 @@ void __init setup_ioapic_dest(void)
* when you have too many devices, because at that time only boot
* cpu is online.
*/
- cfg = irq_cfg(irq);
+ desc = irq_to_desc(irq);
+ cfg = desc->chip_data;
if (!cfg->vector) {
- setup_IO_APIC_irq(ioapic, pin, irq,
+ setup_IO_APIC_irq(ioapic, pin, irq, desc,
irq_trigger(irq_entry),
irq_polarity(irq_entry));
continue;
@@ -3785,7 +3916,6 @@ void __init setup_ioapic_dest(void)
/*
* Honour affinities which have been set in early boot
*/
- desc = irq_to_desc(irq);
if (desc->status &
(IRQ_NO_BALANCING | IRQ_AFFINITY_SET))
mask = desc->affinity;
@@ -3794,10 +3924,10 @@ void __init setup_ioapic_dest(void)

#ifdef CONFIG_INTR_REMAP
if (intr_remapping_enabled)
- set_ir_ioapic_affinity_irq(irq, mask);
+ set_ir_ioapic_affinity_irq_desc(desc, mask);
else
#endif
- set_ioapic_affinity_irq(irq, mask);
+ set_ioapic_affinity_irq_desc(desc, mask);
}

}
@@ -3846,7 +3976,6 @@ 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
@@ -76,8 +76,7 @@ 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/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_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_SPARSE_IRQ
if (irq >= nr_irqs)
return;
+#endif

state = get_timer_rand_state(irq);

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 +19,75 @@ struct irq_2_iommu {
u8 irte_mask;
};

-static struct irq_2_iommu irq_2_iommuX[NR_IRQS];
+#ifdef CONFIG_SPARSE_IRQ
+static struct irq_2_iommu *get_one_free_irq_2_iommu(int cpu)
+{
+ struct irq_2_iommu *iommu;
+ int node;
+
+ node = cpu_to_node(cpu);
+
+ iommu = kzalloc_node(sizeof(*iommu), GFP_ATOMIC, 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);
+
+ if (WARN_ON_ONCE(!desc))
+ return NULL;
+
+ 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);
+ if (!desc) {
+ printk(KERN_INFO "can not get irq_desc for %d\n", irq);
+ return NULL;
+ }
+
+ 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, boot_cpu_id);
}

+#else /* !CONFIG_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(unsigned int irq)
{
return irq_2_iommu(irq);
}
+#endif

static DEFINE_SPINLOCK(irq_2_ir_lock);

@@ -86,9 +144,11 @@ int alloc_irte(struct intel_iommu *iommu
if (!count)
return -1;

+#ifndef CONFIG_SPARSE_IRQ
/* protect irq_2_iommu_alloc later */
if (irq >= nr_irqs)
return -1;
+#endif

/*
* start the IRTE search from index 0.
@@ -130,6 +190,12 @@ int alloc_irte(struct intel_iommu *iommu
table->base[i].present = 1;

irq_iommu = irq_2_iommu_alloc(irq);
+ if (!irq_iommu) {
+ spin_unlock(&irq_2_ir_lock);
+ printk(KERN_ERR "can't allocate irq_2_iommu\n");
+ return -1;
+ }
+
irq_iommu->iommu = iommu;
irq_iommu->irte_index = index;
irq_iommu->sub_handle = 0;
@@ -177,6 +243,12 @@ int set_irte_irq(int irq, struct intel_i

irq_iommu = irq_2_iommu_alloc(irq);

+ if (!irq_iommu) {
+ spin_unlock(&irq_2_ir_lock);
+ printk(KERN_ERR "can't allocate irq_2_iommu\n");
+ return -1;
+ }
+
irq_iommu->iommu = iommu;
irq_iommu->irte_index = index;
irq_iommu->sub_handle = subhandle;
Index: linux-2.6/drivers/xen/events.c
===================================================================
--- linux-2.6.orig/drivers/xen/events.c
+++ linux-2.6/drivers/xen/events.c
@@ -141,8 +141,9 @@ static void init_evtchn_cpu_bindings(voi
int i;

/* By default all event channels notify CPU#0. */
- for_each_irq_desc(i, desc)
+ 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 +92,17 @@ 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_SPARSE_IRQ
+ seq_printf(p, " %d:%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
@@ -8,6 +8,23 @@
/*
* /proc/interrupts
*/
+#ifdef CONFIG_SPARSE_IRQ
+static void *int_seq_start(struct seq_file *f, loff_t *pos)
+{
+ rcu_read_lock();
+ return seq_list_start(&sparse_irqs_head, *pos);
+}
+
+static void *int_seq_next(struct seq_file *f, void *v, loff_t *pos)
+{
+ return seq_list_next(v, &sparse_irqs_head, pos);
+}
+
+static void int_seq_stop(struct seq_file *f, void *v)
+{
+ rcu_read_unlock();
+}
+#else
static void *int_seq_start(struct seq_file *f, loff_t *pos)
{
return (*pos <= nr_irqs) ? pos : NULL;
@@ -25,6 +42,7 @@ static void int_seq_stop(struct seq_file
{
/* Nothing to do */
}
+#endif

static const struct seq_operations int_seq_ops = {
.start = int_seq_start,
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
@@ -129,6 +129,8 @@ struct irq_chip {
const char *typename;
};

+struct timer_rand_state;
+struct irq_2_iommu;
/**
* struct irq_desc - interrupt descriptor
* @irq: interrupt number for this descriptor
@@ -154,6 +156,14 @@ struct irq_chip {
*/
struct irq_desc {
unsigned int irq;
+#ifdef CONFIG_SPARSE_IRQ
+ struct list_head list;
+ 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 +191,64 @@ struct irq_desc {
const char *name;
} ____cacheline_internodealigned_in_smp;

+extern void early_irq_init(void);
+extern void arch_early_irq_init(void);
+extern void arch_init_chip_data(struct irq_desc *desc, int cpu);
+extern void arch_init_copy_chip_data(struct irq_desc *old_desc,
+ struct irq_desc *desc, int cpu);
+extern void arch_free_chip_data(struct irq_desc *old_desc, struct irq_desc *desc);
+
+#ifndef CONFIG_SPARSE_IRQ

extern struct irq_desc irq_desc[NR_IRQS];

static inline struct irq_desc *irq_to_desc(unsigned int irq)
{
- return (irq < nr_irqs) ? irq_desc + irq : NULL;
+ return (irq < NR_IRQS) ? irq_desc + irq : NULL;
+}
+static inline struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu)
+{
+ return irq_to_desc(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
+
+#else
+
+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 *move_irq_desc(struct irq_desc *old_desc, int cpu);
+
+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:
*/
@@ -380,6 +440,11 @@ extern int set_irq_msi(unsigned int irq,
#define get_irq_data(irq) (irq_to_desc(irq)->handler_data)
#define get_irq_msi(irq) (irq_to_desc(irq)->msi_desc)

+#define get_irq_desc_chip(desc) ((desc)->chip)
+#define get_irq_desc_chip_data(desc) ((desc)->chip_data)
+#define get_irq_desc_data(desc) ((desc)->handler_data)
+#define get_irq_desc_msi(desc) ((desc)->msi_desc)
+
#endif /* CONFIG_GENERIC_HARDIRQS */

#endif /* !CONFIG_S390 */
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_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_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_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
@@ -57,7 +57,7 @@ unsigned long probe_irq_on(void)
desc->chip->startup(i);
}
spin_unlock_irq(&desc->lock);
- }
+ } end_for_each_irq_desc();

/* Wait for longstanding interrupts to trigger. */
msleep(20);
@@ -75,7 +75,7 @@ unsigned long probe_irq_on(void)
desc->status |= IRQ_PENDING;
}
spin_unlock_irq(&desc->lock);
- }
+ } end_for_each_irq_desc();

/*
* Wait for spurious interrupts to trigger
@@ -99,7 +99,7 @@ unsigned long probe_irq_on(void)
mask |= 1 << i;
}
spin_unlock_irq(&desc->lock);
- }
+ } end_for_each_irq_desc();

return mask;
}
@@ -135,7 +135,7 @@ unsigned int probe_irq_mask(unsigned lon
desc->chip->shutdown(i);
}
spin_unlock_irq(&desc->lock);
- }
+ } end_for_each_irq_desc();
mutex_unlock(&probing_active);

return mask & val;
@@ -179,7 +179,7 @@ int probe_irq_off(unsigned long val)
desc->chip->shutdown(i);
}
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 +24,10 @@
*/
void dynamic_irq_init(unsigned int irq)
{
- struct irq_desc *desc = irq_to_desc(irq);
+ struct irq_desc *desc;
unsigned long flags;

+ desc = irq_to_desc(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 +56,164 @@ void handle_bad_irq(unsigned int irq, st
int nr_irqs = NR_IRQS;
EXPORT_SYMBOL_GPL(nr_irqs);

+void __init __attribute__((weak)) arch_early_irq_init(void)
+{
+}
+
+#ifdef CONFIG_SPARSE_IRQ
+static struct irq_desc irq_desc_init = {
+ .irq = -1,
+ .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;
+
+ /* Compute how many bytes we need per irq and allocate them */
+ bytes = nr * sizeof(unsigned int);
+
+ node = cpu_to_node(cpu);
+ ptr = kzalloc_node(bytes, GFP_ATOMIC, node);
+ printk(KERN_DEBUG " alloc kstat_irqs on cpu %d node %d\n", cpu, node);
+
+ if (ptr)
+ desc->kstat_irqs = (unsigned int *)ptr;
+}
+
+void __attribute__((weak)) arch_init_chip_data(struct irq_desc *desc, int cpu)
+{
+}
+
+static void init_one_irq_desc(int irq, struct irq_desc *desc, int cpu)
+{
+ memcpy(desc, &irq_desc_init, sizeof(struct irq_desc));
+ desc->irq = irq;
+#ifdef CONFIG_SMP
+ desc->cpu = cpu;
+#endif
+ lockdep_set_class(&desc->lock, &irq_desc_lock_class);
+ init_kstat_irqs(desc, cpu, nr_cpu_ids);
+ if (!desc->kstat_irqs) {
+ printk(KERN_ERR "can not alloc kstat_irqs\n");
+ BUG_ON(1);
+ }
+ arch_init_chip_data(desc, cpu);
+}
+
+/*
+ * Protect the sparse_irqs:
+ */
+static DEFINE_SPINLOCK(sparse_irq_lock);
+LIST_HEAD(sparse_irqs_head);
+
+struct irq_desc *irq_desc_ptrs[NR_IRQS] __read_mostly;
+
+static struct irq_desc irq_desc_legacy[NR_IRQS_LEGACY] __cacheline_aligned_in_smp = {
+ [0 ... NR_IRQS_LEGACY-1] = {
+ .irq = -1,
+ .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_irq_init(void)
+{
+ struct irq_desc *desc;
+ int legacy_count;
+ int i;
+
+ desc = irq_desc_legacy;
+ legacy_count = ARRAY_SIZE(irq_desc_legacy);
+
+ for (i = 0; i < legacy_count; i++) {
+ desc[i].irq = i;
+ desc[i].kstat_irqs = kstat_irqs_legacy[i];
+
+ irq_desc_ptrs[i] = desc + i;
+ list_add_tail(&desc[i].list, &sparse_irqs_head);
+ }
+
+ for (i = legacy_count; i < NR_IRQS; i++)
+ irq_desc_ptrs[i] = NULL;
+
+ arch_early_irq_init();
+}
+
+struct irq_desc *irq_to_desc(unsigned int irq)
+{
+ if (irq >= NR_IRQS) {
+ printk(KERN_WARNING "irq >= NR_IRQS in irq_to_desc: %d %d\n",
+ irq, NR_IRQS);
+ WARN_ON(1);
+ return NULL;
+ }
+ return irq_desc_ptrs[irq];
+}
+
+struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu)
+{
+ struct irq_desc *desc;
+ unsigned long flags;
+ int node;
+
+ if (irq >= NR_IRQS) {
+ printk(KERN_WARNING "irq >= NR_IRQS in irq_to_desc_alloc: %d %d\n",
+ irq, NR_IRQS);
+ WARN_ON(1);
+ return NULL;
+ }
+
+ desc = irq_desc_ptrs[irq];
+ if (desc)
+ return desc;
+
+ spin_lock_irqsave(&sparse_irq_lock, flags);
+
+ /* We have to check it to avoid races with another CPU */
+ desc = irq_desc_ptrs[irq];
+ if (desc)
+ goto out_unlock;
+
+ node = cpu_to_node(cpu);
+ desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node);
+ printk(KERN_DEBUG " alloc irq_desc for %d on cpu %d node %d\n",
+ irq, cpu, node);
+ if (!desc) {
+ printk(KERN_ERR "can not alloc irq_desc\n");
+ BUG_ON(1);
+ }
+ init_one_irq_desc(irq, desc, cpu);
+
+ irq_desc_ptrs[irq] = desc;
+ list_add_tail_rcu(&desc->list, &sparse_irqs_head);
+
+out_unlock:
+ spin_unlock_irqrestore(&sparse_irq_lock, flags);
+
+ return desc;
+}
+
+#else
+
struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
[0 ... NR_IRQS-1] = {
.status = IRQ_DISABLED,
@@ -62,6 +227,8 @@ struct irq_desc irq_desc[NR_IRQS] __cach
}
};

+#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 +428,25 @@ 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_SPARSE_IRQ
struct irq_desc *desc;
int i;

- for_each_irq_desc(i, desc)
+ for_each_irq_desc(i, desc) {
lockdep_set_class(&desc->lock, &irq_desc_lock_class);
+ } end_for_each_irq_desc();
+#endif
}
#endif
+
+#ifdef CONFIG_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 +99,37 @@ 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;
+ int head = 0;

+#ifdef CONFIG_SPARSE_IRQ
+ desc = list_entry(v, struct irq_desc, list);
+ i = desc->irq;
+ if (&desc->list == sparse_irqs_head.next)
+ head = 1;
+#else
+ i = *(loff_t *) v;
if (i > nr_irqs)
return 0;

if (i == nr_irqs)
return show_other_interrupts(p);
+ if (i == 0)
+ head = 1;
+
+ desc = irq_to_desc(i);
+#endif

/* print header */
- if (i == 0) {
+ if (head) {
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 +160,12 @@ int show_interrupts(struct seq_file *p,
seq_putc(p, '\n');
out:
spin_unlock_irqrestore(&desc->lock, flags);
+
+#ifdef CONFIG_SPARSE_IRQ
+ if (&desc->list == sparse_irqs_head.prev)
+ show_other_interrupts(p);
+#endif
+
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(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
@@ -254,7 +254,7 @@ void fixup_irqs(cpumask_t map)
desc->chip->set_affinity(irq, mask);
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
@@ -125,7 +125,7 @@ void fixup_irqs(cpumask_t map)
printk("Broke affinity for irq %i\n", irq);
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
@@ -243,7 +243,8 @@ void init_irq_proc(void)
/*
* Create entries for all existing IRQs.
*/
- for_each_irq_desc(irq, desc)
+ 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
@@ -99,7 +99,7 @@ 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;
}
@@ -122,7 +122,7 @@ static void poll_spurious_irqs(unsigned
continue;

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/init/main.c
===================================================================
--- linux-2.6.orig/init/main.c
+++ linux-2.6/init/main.c
@@ -542,6 +542,15 @@ void __init __weak thread_info_cache_ini
{
}

+void __init __weak arch_early_irq_init(void)
+{
+}
+
+void __init __weak early_irq_init(void)
+{
+ arch_early_irq_init();
+}
+
asmlinkage void __init start_kernel(void)
{
char * command_line;
@@ -612,6 +621,8 @@ asmlinkage void __init start_kernel(void
sort_main_extable();
trap_init();
rcu_init();
+ /* init some links before init_ISA_irqs() */
+ early_irq_init();
init_IRQ();
pidhash_init();
init_timers();
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
@@ -101,12 +101,23 @@
#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)
+
+#ifndef CONFIG_SPARSE_IRQ
# if NR_CPUS < MAX_IO_APICS
# define NR_IRQS (NR_VECTORS + (32 * NR_CPUS))
# else
# define NR_IRQS (NR_VECTORS + (32 * MAX_IO_APICS))
# endif
+#else
+# if (8 * NR_CPUS) > (32 * MAX_IO_APICS)
+# define NR_IRQS (NR_VECTORS + (8 * NR_CPUS))
+# else
+# define NR_IRQS (NR_VECTORS + (32 * MAX_IO_APICS))
+# endif
+#endif

#elif defined(CONFIG_X86_VOYAGER)

Index: linux-2.6/drivers/pci/msi.c
===================================================================
--- linux-2.6.orig/drivers/pci/msi.c
+++ linux-2.6/drivers/pci/msi.c
@@ -103,11 +103,11 @@ static void msix_set_enable(struct pci_d
}
}

-static void msix_flush_writes(unsigned int irq)
+static void msix_flush_writes(struct irq_desc *desc)
{
struct msi_desc *entry;

- entry = get_irq_msi(irq);
+ entry = get_irq_desc_msi(desc);
BUG_ON(!entry || !entry->dev);
switch (entry->msi_attrib.type) {
case PCI_CAP_ID_MSI:
@@ -135,11 +135,11 @@ static void msix_flush_writes(unsigned i
* Returns 1 if it succeeded in masking the interrupt and 0 if the device
* doesn't support MSI masking.
*/
-static int msi_set_mask_bits(unsigned int irq, u32 mask, u32 flag)
+static int msi_set_mask_bits(struct irq_desc *desc, u32 mask, u32 flag)
{
struct msi_desc *entry;

- entry = get_irq_msi(irq);
+ entry = get_irq_desc_msi(desc);
BUG_ON(!entry || !entry->dev);
switch (entry->msi_attrib.type) {
case PCI_CAP_ID_MSI:
@@ -172,9 +172,9 @@ static int msi_set_mask_bits(unsigned in
return 1;
}

-void read_msi_msg(unsigned int irq, struct msi_msg *msg)
+void read_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg)
{
- struct msi_desc *entry = get_irq_msi(irq);
+ struct msi_desc *entry = get_irq_desc_msi(desc);
switch(entry->msi_attrib.type) {
case PCI_CAP_ID_MSI:
{
@@ -211,9 +211,16 @@ void read_msi_msg(unsigned int irq, stru
}
}

-void write_msi_msg(unsigned int irq, struct msi_msg *msg)
+void read_msi_msg(unsigned int irq, struct msi_msg *msg)
{
- struct msi_desc *entry = get_irq_msi(irq);
+ struct irq_desc *desc = irq_to_desc(irq);
+
+ read_msi_msg_desc(desc, msg);
+}
+
+void write_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg)
+{
+ struct msi_desc *entry = get_irq_desc_msi(desc);
switch (entry->msi_attrib.type) {
case PCI_CAP_ID_MSI:
{
@@ -252,21 +259,31 @@ void write_msi_msg(unsigned int irq, str
entry->msg = *msg;
}

+void write_msi_msg(unsigned int irq, struct msi_msg *msg)
+{
+ struct irq_desc *desc = irq_to_desc(irq);
+
+ write_msi_msg_desc(desc, msg);
+}
+
void mask_msi_irq(unsigned int irq)
{
- msi_set_mask_bits(irq, 1, 1);
- msix_flush_writes(irq);
+ struct irq_desc *desc = irq_to_desc(irq);
+
+ msi_set_mask_bits(desc, 1, 1);
+ msix_flush_writes(desc);
}

void unmask_msi_irq(unsigned int irq)
{
- msi_set_mask_bits(irq, 1, 0);
- msix_flush_writes(irq);
+ struct irq_desc *desc = irq_to_desc(irq);
+
+ msi_set_mask_bits(desc, 1, 0);
+ msix_flush_writes(desc);
}

static int msi_free_irqs(struct pci_dev* dev);

-
static struct msi_desc* alloc_msi_entry(void)
{
struct msi_desc *entry;
@@ -303,9 +320,11 @@ static void __pci_restore_msi_state(stru
pci_intx_for_msi(dev, 0);
msi_set_enable(dev, 0);
write_msi_msg(dev->irq, &entry->msg);
- if (entry->msi_attrib.maskbit)
- msi_set_mask_bits(dev->irq, entry->msi_attrib.maskbits_mask,
+ if (entry->msi_attrib.maskbit) {
+ struct irq_desc *desc = irq_to_desc(dev->irq);
+ msi_set_mask_bits(desc, entry->msi_attrib.maskbits_mask,
entry->msi_attrib.masked);
+ }

pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &control);
control &= ~PCI_MSI_FLAGS_QSIZE;
@@ -327,8 +346,9 @@ static void __pci_restore_msix_state(str
msix_set_enable(dev, 0);

list_for_each_entry(entry, &dev->msi_list, list) {
+ struct irq_desc *desc = irq_to_desc(entry->irq);
write_msi_msg(entry->irq, &entry->msg);
- msi_set_mask_bits(entry->irq, 1, entry->msi_attrib.masked);
+ msi_set_mask_bits(desc, 1, entry->msi_attrib.masked);
}

BUG_ON(list_empty(&dev->msi_list));
@@ -596,7 +616,8 @@ void pci_msi_shutdown(struct pci_dev* de
/* Return the the pci reset with msi irqs unmasked */
if (entry->msi_attrib.maskbit) {
u32 mask = entry->msi_attrib.maskbits_mask;
- msi_set_mask_bits(dev->irq, mask, ~mask);
+ struct irq_desc *desc = irq_to_desc(dev->irq);
+ msi_set_mask_bits(desc, mask, ~mask);
}
if (!entry->dev || entry->msi_attrib.type != PCI_CAP_ID_MSI)
return;
Index: linux-2.6/include/linux/msi.h
===================================================================
--- linux-2.6.orig/include/linux/msi.h
+++ linux-2.6/include/linux/msi.h
@@ -10,8 +10,11 @@ struct msi_msg {
};

/* Helper functions */
+struct irq_desc;
extern void mask_msi_irq(unsigned int irq);
extern void unmask_msi_irq(unsigned int irq);
+extern void read_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg);
+extern void write_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg);
extern void read_msi_msg(unsigned int irq, struct msi_msg *msg);
extern void write_msi_msg(unsigned int irq, struct msi_msg *msg);

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
@@ -198,7 +198,7 @@ extern void restore_IO_APIC_setup(void);
extern void reinit_intr_remapped_IO_APIC(int);
#endif

-extern int probe_nr_irqs(void);
+extern void probe_nr_irqs_gsi(void);

#else /* !CONFIG_X86_IO_APIC */
#define io_apic_assign_pci_irqs 0
Index: linux-2.6/arch/x86/kernel/setup.c
===================================================================
--- linux-2.6.orig/arch/x86/kernel/setup.c
+++ linux-2.6/arch/x86/kernel/setup.c
@@ -953,7 +953,7 @@ void __init setup_arch(char **cmdline_p)
ioapic_init_mappings();

/* need to wait for io_apic is mapped */
- nr_irqs = probe_nr_irqs();
+ probe_nr_irqs_gsi();

kvm_guest_init();


--
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/