[PATCH 01/33] x86: add after_bootmem for 32bit

[PATCH 01/33] x86: add after_bootmem for 32bit

[Yinghai Lu]

to prepare to use dyn_array support etc.

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
---
 arch/x86/mm/init_32.c |    3 +++
 1 files changed, 3 insertions(+), 0 deletions(-)

diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 4974e97..b5c1751 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -65,6 +65,7 @@ static unsigned long __meminitdata table_end;
 static unsigned long __meminitdata table_top;
 
 static int __initdata after_init_bootmem;
+int after_bootmem;
 
 static __init void *alloc_low_page(unsigned long *phys)
 {
@@ -924,6 +925,8 @@ 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;
-- 
1.5.4.5

[PATCH 00/33] dyn_array and nr_irqs support v4

[Yinghai Lu]

Please check dyn_array support for x86
v3: split changing to nr_irqs to small patches
    fix checkpatch error
    reorder the patch sequence to make dyn_array support go at first
        so could use that with arrays other than NR_IRQS
v4: add CONFIG_HAVE_SPARSE_IRQ with list to use condensed irq_desc array
    so could use 32 init, and init more if needed.

now: x86 32bit: have CONFIG_HAVE_DYN_ARRAY
     x86 64bit: have CONFIG_HAVE_DYN_ARRAY and CONFIG_HAVE_SPARSE_IRQ

left:
a. hook irq_2_iommu to irq_desc ?
b. expand /proc/interrupts to process > nr_irqs
c. expand to use irq > nr_irqs for msi

notes: may break some arch compling...

Thanks

Yinghai Lu

[PATCH 01/33] x86: add after_bootmem for 32bit

[Yinghai Lu]

to prepare to use dyn_array support etc.

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
---
 arch/x86/mm/init_32.c |    3 +++
 1 files changed, 3 insertions(+), 0 deletions(-)

diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 4974e97..b5c1751 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -65,6 +65,7 @@ static unsigned long __meminitdata table_end;
 static unsigned long __meminitdata table_top;
 
 static int __initdata after_init_bootmem;
+int after_bootmem;
 
 static __init void *alloc_low_page(unsigned long *phys)
 {
@@ -924,6 +925,8 @@ 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;
-- 
1.5.4.5

[PATCH 02/33] x86: remove irq_vectors_limits

[Yinghai Lu]

no user

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
---
 include/asm-x86/mach-generic/irq_vectors_limits.h |   14 --------------
 include/asm-x86/summit/irq_vectors_limits.h       |   14 --------------
 2 files changed, 0 insertions(+), 28 deletions(-)
 delete mode 100644 include/asm-x86/mach-generic/irq_vectors_limits.h
 delete mode 100644 include/asm-x86/summit/irq_vectors_limits.h

diff --git a/include/asm-x86/mach-generic/irq_vectors_limits.h b/include/asm-x86/mach-generic/irq_vectors_limits.h
deleted file mode 100644
index f7870e1..0000000
--- a/include/asm-x86/mach-generic/irq_vectors_limits.h
+++ /dev/null
@@ -1,14 +0,0 @@
-#ifndef ASM_X86__MACH_GENERIC__IRQ_VECTORS_LIMITS_H
-#define ASM_X86__MACH_GENERIC__IRQ_VECTORS_LIMITS_H
-
-/*
- * For Summit or generic (i.e. installer) kernels, we have lots of I/O APICs,
- * even with uni-proc kernels, so use a big array.
- *
- * This value should be the same in both the generic and summit subarches.
- * Change one, change 'em both.
- */
-#define NR_IRQS	224
-#define NR_IRQ_VECTORS	1024
-
-#endif /* ASM_X86__MACH_GENERIC__IRQ_VECTORS_LIMITS_H */
diff --git a/include/asm-x86/summit/irq_vectors_limits.h b/include/asm-x86/summit/irq_vectors_limits.h
deleted file mode 100644
index 890ce3f..0000000
--- a/include/asm-x86/summit/irq_vectors_limits.h
+++ /dev/null
@@ -1,14 +0,0 @@
-#ifndef _ASM_IRQ_VECTORS_LIMITS_H
-#define _ASM_IRQ_VECTORS_LIMITS_H
-
-/*
- * For Summit or generic (i.e. installer) kernels, we have lots of I/O APICs,
- * even with uni-proc kernels, so use a big array.
- *
- * This value should be the same in both the generic and summit subarches.
- * Change one, change 'em both.
- */
-#define NR_IRQS	224
-#define NR_IRQ_VECTORS	1024
-
-#endif /* _ASM_IRQ_VECTORS_LIMITS_H */
-- 
1.5.4.5

[PATCH 03/33] add dyn_array support

[Yinghai Lu]

could have crazy big arrays and allocate them in bootmem at init stage.
also also to allocate array according to size we need to use to avoid wasting
memory
use CONFIG_HAVE_DYN_ARRAY to enable it or not

usage:

|static struct irq_desc irq_desc_init __initdata = {
|       .status = IRQ_DISABLED,
|       .chip = &no_irq_chip,
|       .handle_irq = handle_bad_irq,
|       .depth = 1,
|       .lock = __SPIN_LOCK_UNLOCKED(irq_desc->lock),
|#ifdef CONFIG_SMP
|       .affinity = CPU_MASK_ALL
|#endif
|};
|
|static void __init init_work(void *data)
|{
|       struct dyn_array *da = data;
|       struct  irq_desc *desc;
|       int i;
|
|       desc = *da->name;
|
|       for (i = 0; i < *da->nr; i++)
|               memcpy(&desc[i], &irq_desc_init, sizeof(struct irq_desc));
|}
|
|struct irq_desc *irq_desc;
|DEFINE_DYN_ARRAY(irq_desc, sizeof(struct irq_desc), nr_irqs, PAGE_SIZE, init_work);

after pre_alloc_dyn_array() after setup_arch(), that array is ready to use
in this way could replace irq_desc[NR_IRQS] array with dyn_array irq_desc[nr_irqs]

v2: remove _nopanic in pre_alloc_dyn_array()

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
---
 include/asm-generic/vmlinux.lds.h |    7 +++++++
 include/linux/init.h              |   23 +++++++++++++++++++++++
 init/main.c                       |   24 ++++++++++++++++++++++++
 3 files changed, 54 insertions(+), 0 deletions(-)

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index a44ec7a..1c3daac 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -214,6 +214,13 @@
  * All archs are supposed to use RO_DATA() */
 #define RODATA RO_DATA(4096)
 
+#define DYN_ARRAY_INIT(align)							\
+	. = ALIGN((align));						\
+	.dyn_array.init : AT(ADDR(.dyn_array.init) - LOAD_OFFSET) {	\
+		VMLINUX_SYMBOL(__dyn_array_start) = .;			\
+		*(.dyn_array.init)					\
+		VMLINUX_SYMBOL(__dyn_array_end) = .;			\
+	}
 #define SECURITY_INIT							\
 	.security_initcall.init : AT(ADDR(.security_initcall.init) - LOAD_OFFSET) { \
 		VMLINUX_SYMBOL(__security_initcall_start) = .;		\
diff --git a/include/linux/init.h b/include/linux/init.h
index 915c5b9..c31cd94 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -249,6 +249,29 @@ struct obs_kernel_param {
 
 /* Relies on boot_command_line being set */
 void __init parse_early_param(void);
+
+struct dyn_array {
+	void **name;
+	unsigned long size;
+	unsigned int *nr;
+	unsigned long align;
+	void (*init_work)(void *);
+};
+extern struct dyn_array *__dyn_array_start[], *__dyn_array_end[];
+
+#define DEFINE_DYN_ARRAY(nameX, sizeX, nrX, alignX, init_workX) \
+		static struct dyn_array __dyn_array_##nameX __initdata = \
+		{	.name = (void **)&nameX,\
+			.size = sizeX,\
+			.nr   = &nrX,\
+			.align = alignX,\
+			.init_work = init_workX,\
+		}; \
+		static struct dyn_array *__dyn_array_ptr_##nameX __used \
+		__attribute__((__section__(".dyn_array.init"))) = \
+			&__dyn_array_##nameX
+
+extern void pre_alloc_dyn_array(void);
 #endif /* __ASSEMBLY__ */
 
 /**
diff --git a/init/main.c b/init/main.c
index 3f8fa37..a53f1cf 100644
--- a/init/main.c
+++ b/init/main.c
@@ -539,6 +539,29 @@ void __init __weak thread_info_cache_init(void)
 {
 }
 
+void pre_alloc_dyn_array(void)
+{
+#ifdef CONFIG_HAVE_DYN_ARRAY
+	unsigned long size, phys = 0;
+	struct dyn_array **daa;
+
+	for (daa = __dyn_array_start ; daa < __dyn_array_end; daa++) {
+		struct dyn_array *da = *daa;
+
+		size = da->size * (*da->nr);
+		print_fn_descriptor_symbol("dyna_array %s ", da->name);
+		printk(KERN_CONT "size:%#lx nr:%d align:%#lx",
+			da->size, *da->nr, da->align);
+		*da->name = __alloc_bootmem(size, da->align, phys);
+		phys = virt_to_phys(*da->name);
+		printk(KERN_CONT " ==> [%#lx - %#lx]\n", phys, phys + size);
+
+		if (da->init_work)
+			da->init_work(da);
+	}
+#endif
+}
+
 asmlinkage void __init start_kernel(void)
 {
 	char * command_line;
@@ -576,6 +599,7 @@ asmlinkage void __init start_kernel(void)
 	printk(KERN_NOTICE);
 	printk(linux_banner);
 	setup_arch(&command_line);
+	pre_alloc_dyn_array();
 	mm_init_owner(&init_mm, &init_task);
 	setup_command_line(command_line);
 	unwind_setup();
-- 
1.5.4.5

[PATCH 04/33] add per_cpu_dyn_array support

[Yinghai Lu]

could make array in per_cpu is allocated dynamically too

usage:
| /* in .h */
|struct kernel_stat {
|       struct cpu_usage_stat   cpustat;
|       unsigned int *irqs;
|};
|
| /* in .c */
|DEFINE_PER_CPU(struct kernel_stat, kstat);
|
|DEFINE_PER_CPU_DYN_ARRAY_ADDR(per_cpu__kstat_irqs, per_cpu__kstat.irqs, sizeof(unsigned int), nr_irqs, sizeof(unsigned long), NULL);

after setup_percpu()/per_cpu_alloc_dyn_array(), that dyn_array in per_cpu area is ready to use

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
---
 arch/x86/kernel/setup_percpu.c    |    7 +++-
 include/asm-generic/vmlinux.lds.h |    6 +++
 include/linux/init.h              |   27 ++++++++++++++--
 init/main.c                       |   63 +++++++++++++++++++++++++++++++++++-
 4 files changed, 96 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 0e67f72..13ba7a8 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -140,7 +140,7 @@ static void __init setup_cpu_pda_map(void)
  */
 void __init setup_per_cpu_areas(void)
 {
-	ssize_t size = PERCPU_ENOUGH_ROOM;
+	ssize_t size, old_size;
 	char *ptr;
 	int cpu;
 
@@ -148,7 +148,8 @@ void __init setup_per_cpu_areas(void)
 	setup_cpu_pda_map();
 
 	/* Copy section for each CPU (we discard the original) */
-	size = PERCPU_ENOUGH_ROOM;
+	old_size = PERCPU_ENOUGH_ROOM;
+	size = old_size + per_cpu_dyn_array_size();
 	printk(KERN_INFO "PERCPU: Allocating %zd bytes of per cpu data\n",
 			  size);
 
@@ -176,6 +177,8 @@ void __init setup_per_cpu_areas(void)
 		per_cpu_offset(cpu) = ptr - __per_cpu_start;
 		memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
 
+		per_cpu_alloc_dyn_array(cpu, ptr + old_size);
+
 	}
 
 	printk(KERN_DEBUG "NR_CPUS: %d, nr_cpu_ids: %d, nr_node_ids %d\n",
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 1c3daac..e76244a 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -220,6 +220,12 @@
 		VMLINUX_SYMBOL(__dyn_array_start) = .;			\
 		*(.dyn_array.init)					\
 		VMLINUX_SYMBOL(__dyn_array_end) = .;			\
+	}								\
+	. = ALIGN((align));						\
+	.per_cpu_dyn_array.init : AT(ADDR(.per_cpu_dyn_array.init) - LOAD_OFFSET) {	\
+		VMLINUX_SYMBOL(__per_cpu_dyn_array_start) = .;		\
+		*(.per_cpu_dyn_array.init)				\
+		VMLINUX_SYMBOL(__per_cpu_dyn_array_end) = .;		\
 	}
 #define SECURITY_INIT							\
 	.security_initcall.init : AT(ADDR(.security_initcall.init) - LOAD_OFFSET) { \
diff --git a/include/linux/init.h b/include/linux/init.h
index c31cd94..9fbe61b 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -258,12 +258,13 @@ struct dyn_array {
 	void (*init_work)(void *);
 };
 extern struct dyn_array *__dyn_array_start[], *__dyn_array_end[];
+extern struct dyn_array *__per_cpu_dyn_array_start[], *__per_cpu_dyn_array_end[];
 
-#define DEFINE_DYN_ARRAY(nameX, sizeX, nrX, alignX, init_workX) \
+#define DEFINE_DYN_ARRAY_ADDR(nameX, addrX, sizeX, nrX, alignX, init_workX) \
 		static struct dyn_array __dyn_array_##nameX __initdata = \
-		{	.name = (void **)&nameX,\
+		{	.name = (void **)&(nameX),\
 			.size = sizeX,\
-			.nr   = &nrX,\
+			.nr   = &(nrX),\
 			.align = alignX,\
 			.init_work = init_workX,\
 		}; \
@@ -271,7 +272,27 @@ extern struct dyn_array *__dyn_array_start[], *__dyn_array_end[];
 		__attribute__((__section__(".dyn_array.init"))) = \
 			&__dyn_array_##nameX
 
+#define DEFINE_DYN_ARRAY(nameX, sizeX, nrX, alignX, init_workX) \
+	DEFINE_DYN_ARRAY_ADDR(nameX, nameX, sizeX, nrX, alignX, init_workX)
+
+#define DEFINE_PER_CPU_DYN_ARRAY_ADDR(nameX, addrX, sizeX, nrX, alignX, init_workX) \
+		static struct dyn_array __per_cpu_dyn_array_##nameX __initdata = \
+		{	.name = (void **)&(addrX),\
+			.size = sizeX,\
+			.nr   = &(nrX),\
+			.align = alignX,\
+			.init_work = init_workX,\
+		}; \
+		static struct dyn_array *__per_cpu_dyn_array_ptr_##nameX __used \
+		__attribute__((__section__(".per_cpu_dyn_array.init"))) = \
+			&__per_cpu_dyn_array_##nameX
+
+#define DEFINE_PER_CPU_DYN_ARRAY(nameX, sizeX, nrX, alignX, init_workX) \
+	DEFINE_PER_CPU_DYN_ARRAY_ADDR(nameX, nameX, nrX, alignX, init_workX)
+
 extern void pre_alloc_dyn_array(void);
+extern unsigned long per_cpu_dyn_array_size(void);
+extern void per_cpu_alloc_dyn_array(int cpu, char *ptr);
 #endif /* __ASSEMBLY__ */
 
 /**
diff --git a/init/main.c b/init/main.c
index a53f1cf..18478d3 100644
--- a/init/main.c
+++ b/init/main.c
@@ -394,17 +394,19 @@ EXPORT_SYMBOL(__per_cpu_offset);
 
 static void __init setup_per_cpu_areas(void)
 {
-	unsigned long size, i;
+	unsigned long size, i, old_size;
 	char *ptr;
 	unsigned long nr_possible_cpus = num_possible_cpus();
 
 	/* Copy section for each CPU (we discard the original) */
-	size = ALIGN(PERCPU_ENOUGH_ROOM, PAGE_SIZE);
+	old_size = PERCPU_ENOUGH_ROOM;
+	size = ALIGN(old_size + per_cpu_dyn_array_size(), PAGE_SIZE);
 	ptr = alloc_bootmem_pages(size * nr_possible_cpus);
 
 	for_each_possible_cpu(i) {
 		__per_cpu_offset[i] = ptr - __per_cpu_start;
 		memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
+		per_cpu_alloc_dyn_array(cpu, ptr + old_size);
 		ptr += size;
 	}
 }
@@ -562,6 +564,63 @@ void pre_alloc_dyn_array(void)
 #endif
 }
 
+unsigned long per_cpu_dyn_array_size(void)
+{
+	unsigned long total_size = 0;
+#ifdef CONFIG_HAVE_DYN_ARRAY
+	unsigned long size;
+	struct dyn_array **daa;
+
+	for (daa = __per_cpu_dyn_array_start ; daa < __per_cpu_dyn_array_end; daa++) {
+		struct dyn_array *da = *daa;
+
+		size = da->size * (*da->nr);
+		print_fn_descriptor_symbol("per_cpu_dyna_array %s ", da->name);
+		printk(KERN_CONT "size:%#lx nr:%d align:%#lx\n",
+			da->size, *da->nr, da->align);
+		total_size += roundup(size, da->align);
+	}
+	if (total_size)
+		printk(KERN_DEBUG "per_cpu_dyna_array total_size: %#lx\n",
+			 total_size);
+#endif
+	return total_size;
+}
+
+void per_cpu_alloc_dyn_array(int cpu, char *ptr)
+{
+#ifdef CONFIG_HAVE_DYN_ARRAY
+	unsigned long size, phys;
+	struct dyn_array **daa;
+	unsigned long addr;
+	void **array;
+
+	phys = virt_to_phys(ptr);
+
+	for (daa = __per_cpu_dyn_array_start ; daa < __per_cpu_dyn_array_end; daa++) {
+		struct dyn_array *da = *daa;
+
+		size = da->size * (*da->nr);
+		print_fn_descriptor_symbol("per_cpu_dyna_array %s ", da->name);
+		printk(KERN_CONT "size:%#lx nr:%d align:%#lx",
+			da->size, *da->nr, da->align);
+
+		phys = roundup(phys, da->align);
+		addr = (unsigned long)da->name;
+		addr += per_cpu_offset(cpu);
+		array = (void **)addr;
+		*array = phys_to_virt(phys);
+		*da->name = *array; /* so init_work could use it directly */
+		printk(KERN_CONT " %p ==> [%#lx - %#lx]\n", array, phys, phys + size);
+		phys += size;
+
+		if (da->init_work) {
+			da->init_work(da);
+		}
+	}
+#endif
+}
+
 asmlinkage void __init start_kernel(void)
 {
 	char * command_line;
-- 
1.5.4.5

[PATCH 05/33] x86: alloc dyn_array all alltogether

[Yinghai Lu]

so could spare some memory with small alignment in bootmem

also tighten the alignment checking..., and make print out less debug info

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
---
 arch/x86/kernel/setup_percpu.c |   16 +++++++---
 include/linux/init.h           |    2 +-
 init/main.c                    |   65 ++++++++++++++++++++++++++++++---------
 3 files changed, 62 insertions(+), 21 deletions(-)

diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 13ba7a8..2b7dab6 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -140,26 +140,31 @@ static void __init setup_cpu_pda_map(void)
  */
 void __init setup_per_cpu_areas(void)
 {
-	ssize_t size, old_size;
+	ssize_t size, old_size, da_size;
 	char *ptr;
 	int cpu;
+	unsigned long align = 1;
 
 	/* Setup cpu_pda map */
 	setup_cpu_pda_map();
 
 	/* Copy section for each CPU (we discard the original) */
 	old_size = PERCPU_ENOUGH_ROOM;
-	size = old_size + per_cpu_dyn_array_size();
+	da_size = per_cpu_dyn_array_size(&align);
+	align = max_t(unsigned long, PAGE_SIZE, align);
+	size = roundup(old_size + da_size, align);
 	printk(KERN_INFO "PERCPU: Allocating %zd bytes of per cpu data\n",
 			  size);
 
 	for_each_possible_cpu(cpu) {
 #ifndef CONFIG_NEED_MULTIPLE_NODES
-		ptr = alloc_bootmem_pages(size);
+		ptr = __alloc_bootmem(size, align,
+				 __pa(MAX_DMA_ADDRESS));
 #else
 		int node = early_cpu_to_node(cpu);
 		if (!node_online(node) || !NODE_DATA(node)) {
-			ptr = alloc_bootmem_pages(size);
+			ptr = __alloc_bootmem(size, align,
+					 __pa(MAX_DMA_ADDRESS));
 			printk(KERN_INFO
 			       "cpu %d has no node %d or node-local memory\n",
 				cpu, node);
@@ -168,7 +173,8 @@ void __init setup_per_cpu_areas(void)
 					 cpu, __pa(ptr));
 		}
 		else {
-			ptr = alloc_bootmem_pages_node(NODE_DATA(node), size);
+			ptr = __alloc_bootmem_node(NODE_DATA(node), size, align,
+							__pa(MAX_DMA_ADDRESS));
 			if (ptr)
 				printk(KERN_DEBUG "per cpu data for cpu%d on node%d at %016lx\n",
 					 cpu, node, __pa(ptr));
diff --git a/include/linux/init.h b/include/linux/init.h
index 9fbe61b..2e42af8 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -291,7 +291,7 @@ extern struct dyn_array *__per_cpu_dyn_array_start[], *__per_cpu_dyn_array_end[]
 	DEFINE_PER_CPU_DYN_ARRAY_ADDR(nameX, nameX, nrX, alignX, init_workX)
 
 extern void pre_alloc_dyn_array(void);
-extern unsigned long per_cpu_dyn_array_size(void);
+extern unsigned long per_cpu_dyn_array_size(unsigned long *align);
 extern void per_cpu_alloc_dyn_array(int cpu, char *ptr);
 #endif /* __ASSEMBLY__ */
 
diff --git a/init/main.c b/init/main.c
index 18478d3..3454b4a 100644
--- a/init/main.c
+++ b/init/main.c
@@ -397,10 +397,14 @@ static void __init setup_per_cpu_areas(void)
 	unsigned long size, i, old_size;
 	char *ptr;
 	unsigned long nr_possible_cpus = num_possible_cpus();
+	unsigned long align = 1;
+	unsigned da_size;
 
 	/* Copy section for each CPU (we discard the original) */
 	old_size = PERCPU_ENOUGH_ROOM;
-	size = ALIGN(old_size + per_cpu_dyn_array_size(), PAGE_SIZE);
+	da_size = per_cpu_dyn_array_size(&align);
+	align = max_t(unsigned long, PAGE_SIZE, align);
+	size = ALIGN(old_size + da_size, align);
 	ptr = alloc_bootmem_pages(size * nr_possible_cpus);
 
 	for_each_possible_cpu(i) {
@@ -544,45 +548,78 @@ void __init __weak thread_info_cache_init(void)
 void pre_alloc_dyn_array(void)
 {
 #ifdef CONFIG_HAVE_DYN_ARRAY
-	unsigned long size, phys = 0;
+	unsigned long total_size = 0, size, phys;
+	unsigned long max_align = 1;
 	struct dyn_array **daa;
+	char *ptr;
 
+	/* get the total size at first */
 	for (daa = __dyn_array_start ; daa < __dyn_array_end; daa++) {
 		struct dyn_array *da = *daa;
 
 		size = da->size * (*da->nr);
-		print_fn_descriptor_symbol("dyna_array %s ", da->name);
-		printk(KERN_CONT "size:%#lx nr:%d align:%#lx",
+		print_fn_descriptor_symbol("dyn_array %s ", da->name);
+		printk(KERN_CONT "size:%#lx nr:%d align:%#lx\n",
 			da->size, *da->nr, da->align);
-		*da->name = __alloc_bootmem(size, da->align, phys);
-		phys = virt_to_phys(*da->name);
+		total_size += roundup(size, da->align);
+		if (da->align > max_align)
+			max_align = da->align;
+	}
+	if (total_size)
+		printk(KERN_DEBUG "dyn_array total_size: %#lx\n",
+			 total_size);
+	else
+		return;
+
+	/* allocate them all together */
+	max_align = max_t(unsigned long, max_align, PAGE_SIZE);
+	ptr = __alloc_bootmem_nopanic(total_size, max_align, 0);
+	if (!ptr)
+		panic("Can not alloc dyn_alloc\n");
+
+	phys = virt_to_phys(ptr);
+	for (daa = __dyn_array_start ; daa < __dyn_array_end; daa++) {
+		struct dyn_array *da = *daa;
+
+		size = da->size * (*da->nr);
+		print_fn_descriptor_symbol("dyn_array %s ", da->name);
+
+		phys = roundup(phys, da->align);
+		*da->name = phys_to_virt(phys);
 		printk(KERN_CONT " ==> [%#lx - %#lx]\n", phys, phys + size);
 
+		phys += size;
+
 		if (da->init_work)
 			da->init_work(da);
 	}
 #endif
 }
 
-unsigned long per_cpu_dyn_array_size(void)
+unsigned long per_cpu_dyn_array_size(unsigned long *align)
 {
 	unsigned long total_size = 0;
 #ifdef CONFIG_HAVE_DYN_ARRAY
 	unsigned long size;
 	struct dyn_array **daa;
+	unsigned max_align = 1;
 
 	for (daa = __per_cpu_dyn_array_start ; daa < __per_cpu_dyn_array_end; daa++) {
 		struct dyn_array *da = *daa;
 
 		size = da->size * (*da->nr);
-		print_fn_descriptor_symbol("per_cpu_dyna_array %s ", da->name);
+		print_fn_descriptor_symbol("per_cpu_dyn_array %s ", da->name);
 		printk(KERN_CONT "size:%#lx nr:%d align:%#lx\n",
 			da->size, *da->nr, da->align);
 		total_size += roundup(size, da->align);
+		if (da->align > max_align)
+			max_align = da->align;
 	}
-	if (total_size)
-		printk(KERN_DEBUG "per_cpu_dyna_array total_size: %#lx\n",
+	if (total_size) {
+		printk(KERN_DEBUG "per_cpu_dyn_array total_size: %#lx\n",
 			 total_size);
+		*align = max_align;
+	}
 #endif
 	return total_size;
 }
@@ -596,14 +633,11 @@ void per_cpu_alloc_dyn_array(int cpu, char *ptr)
 	void **array;
 
 	phys = virt_to_phys(ptr);
-
 	for (daa = __per_cpu_dyn_array_start ; daa < __per_cpu_dyn_array_end; daa++) {
 		struct dyn_array *da = *daa;
 
 		size = da->size * (*da->nr);
-		print_fn_descriptor_symbol("per_cpu_dyna_array %s ", da->name);
-		printk(KERN_CONT "size:%#lx nr:%d align:%#lx",
-			da->size, *da->nr, da->align);
+		print_fn_descriptor_symbol("per_cpu_dyn_array %s ", da->name);
 
 		phys = roundup(phys, da->align);
 		addr = (unsigned long)da->name;
@@ -611,7 +645,8 @@ void per_cpu_alloc_dyn_array(int cpu, char *ptr)
 		array = (void **)addr;
 		*array = phys_to_virt(phys);
 		*da->name = *array; /* so init_work could use it directly */
-		printk(KERN_CONT " %p ==> [%#lx - %#lx]\n", array, phys, phys + size);
+		printk(KERN_CONT " ==> [%#lx - %#lx]\n", phys, phys + size);
+
 		phys += size;
 
 		if (da->init_work) {
-- 
1.5.4.5

[PATCH 06/33] x86: enable dyn_array support

[Yinghai Lu]

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
---
 arch/Kconfig                     |    2 ++
 arch/x86/Kconfig                 |    1 +
 arch/x86/kernel/vmlinux_32.lds.S |    1 +
 arch/x86/kernel/vmlinux_64.lds.S |    3 +++
 4 files changed, 7 insertions(+), 0 deletions(-)

diff --git a/arch/Kconfig b/arch/Kconfig
index 0267bab..c1f9feb 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -103,3 +103,5 @@ config HAVE_CLK
 	  The <linux/clk.h> calls support software clock gating and
 	  thus are a key power management tool on many systems.
 
+config HAVE_DYN_ARRAY
+	def_bool n
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index bd30e8b..d30b101 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -33,6 +33,7 @@ config X86
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_GENERIC_DMA_COHERENT if X86_32
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
+	select HAVE_DYN_ARRAY
 
 config ARCH_DEFCONFIG
 	string
diff --git a/arch/x86/kernel/vmlinux_32.lds.S b/arch/x86/kernel/vmlinux_32.lds.S
index 248a575..20b835a 100644
--- a/arch/x86/kernel/vmlinux_32.lds.S
+++ b/arch/x86/kernel/vmlinux_32.lds.S
@@ -145,6 +145,7 @@ SECTIONS
 	*(.x86cpuvendor.init)
 	__x86cpuvendor_end = .;
   }
+  DYN_ARRAY_INIT(8)
   SECURITY_INIT
   . = ALIGN(4);
   .altinstructions : AT(ADDR(.altinstructions) - LOAD_OFFSET) {
diff --git a/arch/x86/kernel/vmlinux_64.lds.S b/arch/x86/kernel/vmlinux_64.lds.S
index 63e5c1a..5b9cc10 100644
--- a/arch/x86/kernel/vmlinux_64.lds.S
+++ b/arch/x86/kernel/vmlinux_64.lds.S
@@ -174,6 +174,9 @@ SECTIONS
 	*(.x86cpuvendor.init)
   }
   __x86cpuvendor_end = .;
+
+  DYN_ARRAY_INIT(8)
+
   SECURITY_INIT
 
   . = ALIGN(8);
-- 
1.5.4.5

[PATCH 07/33] introduce nr_irqs

[Yinghai Lu]

and at this point it is equal NR_IRQS

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
---
 include/linux/irq.h    |    2 ++
 kernel/irq/autoprobe.c |   10 +++++-----
 kernel/irq/chip.c      |   20 ++++++++++----------
 kernel/irq/handle.c    |    3 ++-
 kernel/irq/manage.c    |   16 ++++++++--------
 kernel/irq/proc.c      |    2 +-
 kernel/irq/resend.c    |    4 ++--
 kernel/irq/spurious.c  |    4 ++--
 8 files changed, 32 insertions(+), 29 deletions(-)

diff --git a/include/linux/irq.h b/include/linux/irq.h
index 1d73d1a..bd69d90 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -24,6 +24,8 @@
 #include <asm/ptrace.h>
 #include <asm/irq_regs.h>
 
+extern int nr_irqs;
+
 struct irq_desc;
 typedef	void (*irq_flow_handler_t)(unsigned int irq,
 					    struct irq_desc *desc);
diff --git a/kernel/irq/autoprobe.c b/kernel/irq/autoprobe.c
index 533068c..c689e98 100644
--- a/kernel/irq/autoprobe.c
+++ b/kernel/irq/autoprobe.c
@@ -38,7 +38,7 @@ unsigned long probe_irq_on(void)
 	 * something may have generated an irq long ago and we want to
 	 * flush such a longstanding irq before considering it as spurious.
 	 */
-	for (i = NR_IRQS-1; i > 0; i--) {
+	for (i = nr_irqs-1; i > 0; i--) {
 		desc = irq_desc + i;
 
 		spin_lock_irq(&desc->lock);
@@ -68,7 +68,7 @@ unsigned long probe_irq_on(void)
 	 * (we must startup again here because if a longstanding irq
 	 * happened in the previous stage, it may have masked itself)
 	 */
-	for (i = NR_IRQS-1; i > 0; i--) {
+	for (i = nr_irqs-1; i > 0; i--) {
 		desc = irq_desc + i;
 
 		spin_lock_irq(&desc->lock);
@@ -89,7 +89,7 @@ unsigned long probe_irq_on(void)
 	 * Now filter out any obviously spurious interrupts
 	 */
 	mask = 0;
-	for (i = 0; i < NR_IRQS; i++) {
+	for (i = 0; i < nr_irqs; i++) {
 		unsigned int status;
 
 		desc = irq_desc + i;
@@ -130,7 +130,7 @@ unsigned int probe_irq_mask(unsigned long val)
 	int i;
 
 	mask = 0;
-	for (i = 0; i < NR_IRQS; i++) {
+	for (i = 0; i < nr_irqs; i++) {
 		struct irq_desc *desc = irq_desc + i;
 		unsigned int status;
 
@@ -173,7 +173,7 @@ int probe_irq_off(unsigned long val)
 {
 	int i, irq_found = 0, nr_irqs = 0;
 
-	for (i = 0; i < NR_IRQS; i++) {
+	for (i = 0; i < nr_irqs; i++) {
 		struct irq_desc *desc = irq_desc + i;
 		unsigned int status;
 
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 3cd441e..20a9307 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -27,7 +27,7 @@ void dynamic_irq_init(unsigned int irq)
 	struct irq_desc *desc;
 	unsigned long flags;
 
-	if (irq >= NR_IRQS) {
+	if (irq >= nr_irqs) {
 		WARN(1, KERN_ERR "Trying to initialize invalid IRQ%d\n", irq);
 		return;
 	}
@@ -60,7 +60,7 @@ void dynamic_irq_cleanup(unsigned int irq)
 	struct irq_desc *desc;
 	unsigned long flags;
 
-	if (irq >= NR_IRQS) {
+	if (irq >= nr_irqs) {
 		WARN(1, KERN_ERR "Trying to cleanup invalid IRQ%d\n", irq);
 		return;
 	}
@@ -92,7 +92,7 @@ int set_irq_chip(unsigned int irq, struct irq_chip *chip)
 	struct irq_desc *desc;
 	unsigned long flags;
 
-	if (irq >= NR_IRQS) {
+	if (irq >= nr_irqs) {
 		WARN(1, KERN_ERR "Trying to install chip for IRQ%d\n", irq);
 		return -EINVAL;
 	}
@@ -121,7 +121,7 @@ int set_irq_type(unsigned int irq, unsigned int type)
 	unsigned long flags;
 	int ret = -ENXIO;
 
-	if (irq >= NR_IRQS) {
+	if (irq >= nr_irqs) {
 		printk(KERN_ERR "Trying to set irq type for IRQ%d\n", irq);
 		return -ENODEV;
 	}
@@ -148,7 +148,7 @@ int set_irq_data(unsigned int irq, void *data)
 	struct irq_desc *desc;
 	unsigned long flags;
 
-	if (irq >= NR_IRQS) {
+	if (irq >= nr_irqs) {
 		printk(KERN_ERR
 		       "Trying to install controller data for IRQ%d\n", irq);
 		return -EINVAL;
@@ -174,7 +174,7 @@ int set_irq_msi(unsigned int irq, struct msi_desc *entry)
 	struct irq_desc *desc;
 	unsigned long flags;
 
-	if (irq >= NR_IRQS) {
+	if (irq >= nr_irqs) {
 		printk(KERN_ERR
 		       "Trying to install msi data for IRQ%d\n", irq);
 		return -EINVAL;
@@ -200,7 +200,7 @@ int set_irq_chip_data(unsigned int irq, void *data)
 	struct irq_desc *desc = irq_desc + irq;
 	unsigned long flags;
 
-	if (irq >= NR_IRQS || !desc->chip) {
+	if (irq >= nr_irqs || !desc->chip) {
 		printk(KERN_ERR "BUG: bad set_irq_chip_data(IRQ#%d)\n", irq);
 		return -EINVAL;
 	}
@@ -544,7 +544,7 @@ __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 	struct irq_desc *desc;
 	unsigned long flags;
 
-	if (irq >= NR_IRQS) {
+	if (irq >= nr_irqs) {
 		printk(KERN_ERR
 		       "Trying to install type control for IRQ%d\n", irq);
 		return;
@@ -609,7 +609,7 @@ void __init set_irq_noprobe(unsigned int irq)
 	struct irq_desc *desc;
 	unsigned long flags;
 
-	if (irq >= NR_IRQS) {
+	if (irq >= nr_irqs) {
 		printk(KERN_ERR "Trying to mark IRQ%d non-probeable\n", irq);
 
 		return;
@@ -627,7 +627,7 @@ void __init set_irq_probe(unsigned int irq)
 	struct irq_desc *desc;
 	unsigned long flags;
 
-	if (irq >= NR_IRQS) {
+	if (irq >= nr_irqs) {
 		printk(KERN_ERR "Trying to mark IRQ%d probeable\n", irq);
 
 		return;
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index f4c8a03..e9d022c 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -47,6 +47,7 @@ handle_bad_irq(unsigned int irq, struct irq_desc *desc)
  *
  * Controller mappings for all interrupt sources:
  */
+int nr_irqs = NR_IRQS;
 struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
 	[0 ... NR_IRQS-1] = {
 		.status = IRQ_DISABLED,
@@ -265,7 +266,7 @@ void early_init_irq_lock_class(void)
 {
 	int i;
 
-	for (i = 0; i < NR_IRQS; i++)
+	for (i = 0; i < nr_irqs; i++)
 		lockdep_set_class(&irq_desc[i].lock, &irq_desc_lock_class);
 }
 
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 22d10d3..3bd67c8 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -34,7 +34,7 @@ void synchronize_irq(unsigned int irq)
 	struct irq_desc *desc = irq_desc + irq;
 	unsigned int status;
 
-	if (irq >= NR_IRQS)
+	if (irq >= nr_irqs)
 		return;
 
 	do {
@@ -143,7 +143,7 @@ void disable_irq_nosync(unsigned int irq)
 	struct irq_desc *desc = irq_desc + irq;
 	unsigned long flags;
 
-	if (irq >= NR_IRQS)
+	if (irq >= nr_irqs)
 		return;
 
 	spin_lock_irqsave(&desc->lock, flags);
@@ -171,7 +171,7 @@ void disable_irq(unsigned int irq)
 {
 	struct irq_desc *desc = irq_desc + irq;
 
-	if (irq >= NR_IRQS)
+	if (irq >= nr_irqs)
 		return;
 
 	disable_irq_nosync(irq);
@@ -214,7 +214,7 @@ void enable_irq(unsigned int irq)
 	struct irq_desc *desc = irq_desc + irq;
 	unsigned long flags;
 
-	if (irq >= NR_IRQS)
+	if (irq >= nr_irqs)
 		return;
 
 	spin_lock_irqsave(&desc->lock, flags);
@@ -290,7 +290,7 @@ int can_request_irq(unsigned int irq, unsigned long irqflags)
 {
 	struct irqaction *action;
 
-	if (irq >= NR_IRQS || irq_desc[irq].status & IRQ_NOREQUEST)
+	if (irq >= nr_irqs || irq_desc[irq].status & IRQ_NOREQUEST)
 		return 0;
 
 	action = irq_desc[irq].action;
@@ -349,7 +349,7 @@ int setup_irq(unsigned int irq, struct irqaction *new)
 	int shared = 0;
 	int ret;
 
-	if (irq >= NR_IRQS)
+	if (irq >= nr_irqs)
 		return -EINVAL;
 
 	if (desc->chip == &no_irq_chip)
@@ -503,7 +503,7 @@ void free_irq(unsigned int irq, void *dev_id)
 	unsigned long flags;
 
 	WARN_ON(in_interrupt());
-	if (irq >= NR_IRQS)
+	if (irq >= nr_irqs)
 		return;
 
 	desc = irq_desc + irq;
@@ -617,7 +617,7 @@ int request_irq(unsigned int irq, irq_handler_t handler,
 	 */
 	if ((irqflags & IRQF_SHARED) && !dev_id)
 		return -EINVAL;
-	if (irq >= NR_IRQS)
+	if (irq >= nr_irqs)
 		return -EINVAL;
 	if (irq_desc[irq].status & IRQ_NOREQUEST)
 		return -EINVAL;
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 6c6d35d..74d7922 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -234,7 +234,7 @@ void init_irq_proc(void)
 	/*
 	 * Create entries for all existing IRQs.
 	 */
-	for (i = 0; i < NR_IRQS; i++)
+	for (i = 0; i < nr_irqs; i++)
 		register_irq_proc(i);
 }
 
diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c
index a804679..cba8aa5 100644
--- a/kernel/irq/resend.c
+++ b/kernel/irq/resend.c
@@ -33,8 +33,8 @@ static void resend_irqs(unsigned long arg)
 	struct irq_desc *desc;
 	int irq;
 
-	while (!bitmap_empty(irqs_resend, NR_IRQS)) {
-		irq = find_first_bit(irqs_resend, NR_IRQS);
+	while (!bitmap_empty(irqs_resend, nr_irqs)) {
+		irq = find_first_bit(irqs_resend, nr_irqs);
 		clear_bit(irq, irqs_resend);
 		desc = irq_desc + irq;
 		local_irq_disable();
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index 19fe9d6..e26ca1e 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -91,7 +91,7 @@ static int misrouted_irq(int irq)
 	int i;
 	int ok = 0;
 
-	for (i = 1; i < NR_IRQS; i++) {
+	for (i = 1; i < nr_irqs; i++) {
 		struct irq_desc *desc = irq_desc + i;
 
 		if (i == irq)	/* Already tried */
@@ -107,7 +107,7 @@ static int misrouted_irq(int irq)
 static void poll_spurious_irqs(unsigned long dummy)
 {
 	int i;
-	for (i = 1; i < NR_IRQS; i++) {
+	for (i = 1; i < nr_irqs; i++) {
 		struct irq_desc *desc = irq_desc + i;
 		unsigned int status;
 
-- 
1.5.4.5

[PATCH 08/33] x86: using nr_irqs

[Yinghai Lu]

also add first_free_entry and pin_map_size

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
---
 arch/x86/kernel/io_apic_32.c |   26 ++++++++++++++------------
 arch/x86/kernel/io_apic_64.c |   33 +++++++++++++++++----------------
 arch/x86/kernel/irq_32.c     |    8 ++++----
 arch/x86/kernel/irq_64.c     |    8 ++++----
 arch/x86/kernel/irqinit_32.c |    2 +-
 arch/x86/kernel/irqinit_64.c |    2 +-
 include/asm-x86/irq.h        |    3 +++
 7 files changed, 44 insertions(+), 38 deletions(-)

diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index 7f0d88c..d5953ff 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -70,6 +70,7 @@ int timer_through_8259 __initdata;
  */
 int sis_apic_bug = -1;
 
+int first_free_entry = NR_IRQS;
 /*
  * # of IRQ routing registers
  */
@@ -100,6 +101,8 @@ static int disable_timer_pin_1 __initdata;
 #define MAX_PLUS_SHARED_IRQS NR_IRQS
 #define PIN_MAP_SIZE (MAX_PLUS_SHARED_IRQS + NR_IRQS)
 
+int pin_map_size = PIN_MAP_SIZE;
+
 /*
  * This is performance-critical, we want to do it O(1)
  *
@@ -213,7 +216,6 @@ static void ioapic_mask_entry(int apic, int pin)
  */
 static void add_pin_to_irq(unsigned int irq, int apic, int pin)
 {
-	static int first_free_entry = NR_IRQS;
 	struct irq_pin_list *entry = irq_2_pin + irq;
 
 	while (entry->next)
@@ -222,7 +224,7 @@ static void add_pin_to_irq(unsigned int irq, int apic, int pin)
 	if (entry->pin != -1) {
 		entry->next = first_free_entry;
 		entry = irq_2_pin + entry->next;
-		if (++first_free_entry >= PIN_MAP_SIZE)
+		if (++first_free_entry >= pin_map_size)
 			panic("io_apic.c: whoops");
 	}
 	entry->apic = apic;
@@ -457,7 +459,7 @@ static inline void rotate_irqs_among_cpus(unsigned long useful_load_threshold)
 	int i, j;
 
 	for_each_online_cpu(i) {
-		for (j = 0; j < NR_IRQS; j++) {
+		for (j = 0; j < nr_irqs; j++) {
 			if (!irq_desc[j].action)
 				continue;
 			/* Is it a significant load ?  */
@@ -492,7 +494,7 @@ static void do_irq_balance(void)
 		if (!cpu_online(i))
 			continue;
 		package_index = CPU_TO_PACKAGEINDEX(i);
-		for (j = 0; j < NR_IRQS; j++) {
+		for (j = 0; j < nr_irqs; j++) {
 			unsigned long value_now, delta;
 			/* Is this an active IRQ or balancing disabled ? */
 			if (!irq_desc[j].action || irq_balancing_disabled(j))
@@ -587,7 +589,7 @@ tryanotherirq:
 	 */
 	move_this_load = 0;
 	selected_irq = -1;
-	for (j = 0; j < NR_IRQS; j++) {
+	for (j = 0; j < nr_irqs; j++) {
 		/* Is this an active IRQ? */
 		if (!irq_desc[j].action)
 			continue;
@@ -664,7 +666,7 @@ static int balanced_irq(void *unused)
 	long time_remaining = balanced_irq_interval;
 
 	/* push everything to CPU 0 to give us a starting point.  */
-	for (i = 0 ; i < NR_IRQS ; i++) {
+	for (i = 0 ; i < nr_irqs ; i++) {
 		irq_desc[i].pending_mask = cpumask_of_cpu(0);
 		set_pending_irq(i, cpumask_of_cpu(0));
 	}
@@ -712,8 +714,8 @@ static int __init balanced_irq_init(void)
 		physical_balance = 1;
 
 	for_each_online_cpu(i) {
-		irq_cpu_data[i].irq_delta = kzalloc(sizeof(unsigned long) * NR_IRQS, GFP_KERNEL);
-		irq_cpu_data[i].last_irq = kzalloc(sizeof(unsigned long) * NR_IRQS, GFP_KERNEL);
+		irq_cpu_data[i].irq_delta = kzalloc(sizeof(unsigned long) * nr_irqs, GFP_KERNEL);
+		irq_cpu_data[i].last_irq = kzalloc(sizeof(unsigned long) * nr_irqs, GFP_KERNEL);
 		if (irq_cpu_data[i].irq_delta == NULL || irq_cpu_data[i].last_irq == NULL) {
 			printk(KERN_ERR "balanced_irq_init: out of memory");
 			goto failed;
@@ -1445,7 +1447,7 @@ __apicdebuginit(void) print_IO_APIC(void)
 	}
 	}
 	printk(KERN_DEBUG "IRQ to pin mappings:\n");
-	for (i = 0; i < NR_IRQS; i++) {
+	for (i = 0; i < nr_irqs; i++) {
 		struct irq_pin_list *entry = irq_2_pin + i;
 		if (entry->pin < 0)
 			continue;
@@ -1625,7 +1627,7 @@ static void __init enable_IO_APIC(void)
 	int i, apic;
 	unsigned long flags;
 
-	for (i = 0; i < PIN_MAP_SIZE; i++) {
+	for (i = 0; i < pin_map_size; i++) {
 		irq_2_pin[i].pin = -1;
 		irq_2_pin[i].next = 0;
 	}
@@ -2009,7 +2011,7 @@ static inline void init_IO_APIC_traps(void)
 	 * Also, we've got to be careful not to trash gate
 	 * 0x80, because int 0x80 is hm, kind of importantish. ;)
 	 */
-	for (irq = 0; irq < NR_IRQS ; irq++) {
+	for (irq = 0; irq < nr_irqs ; irq++) {
 		if (IO_APIC_IRQ(irq) && !irq_vector[irq]) {
 			/*
 			 * Hmm.. We don't have an entry for this,
@@ -2453,7 +2455,7 @@ int create_irq(void)
 
 	irq = -ENOSPC;
 	spin_lock_irqsave(&vector_lock, flags);
-	for (new = (NR_IRQS - 1); new >= 0; new--) {
+	for (new = (nr_irqs - 1); new >= 0; new--) {
 		if (platform_legacy_irq(new))
 			continue;
 		if (irq_vector[new] != 0)
diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
index 8800743..456f2e7 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -132,6 +132,7 @@ DECLARE_BITMAP(mp_bus_not_pci, MAX_MP_BUSSES);
 #define MAX_PLUS_SHARED_IRQS NR_IRQS
 #define PIN_MAP_SIZE (MAX_PLUS_SHARED_IRQS + NR_IRQS)
 
+int pin_map_size = PIN_MAP_SIZE;
 /*
  * This is performance-critical, we want to do it O(1)
  *
@@ -224,7 +225,7 @@ static inline void io_apic_sync(unsigned int apic)
 	int pin;							\
 	struct irq_pin_list *entry = irq_2_pin + irq;			\
 									\
-	BUG_ON(irq >= NR_IRQS);						\
+	BUG_ON(irq >= nr_irqs);						\
 	for (;;) {							\
 		unsigned int reg;					\
 		pin = entry->pin;					\
@@ -301,7 +302,7 @@ static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, u8 vector)
 	int apic, pin;
 	struct irq_pin_list *entry = irq_2_pin + irq;
 
-	BUG_ON(irq >= NR_IRQS);
+	BUG_ON(irq >= nr_irqs);
 	for (;;) {
 		unsigned int reg;
 		apic = entry->apic;
@@ -358,19 +359,19 @@ static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t mask)
  * 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.
  */
+int first_free_entry = NR_IRQS;
 static void add_pin_to_irq(unsigned int irq, int apic, int pin)
 {
-	static int first_free_entry = NR_IRQS;
 	struct irq_pin_list *entry = irq_2_pin + irq;
 
-	BUG_ON(irq >= NR_IRQS);
+	BUG_ON(irq >= nr_irqs);
 	while (entry->next)
 		entry = irq_2_pin + entry->next;
 
 	if (entry->pin != -1) {
 		entry->next = first_free_entry;
 		entry = irq_2_pin + entry->next;
-		if (++first_free_entry >= PIN_MAP_SIZE)
+		if (++first_free_entry >= pin_map_size)
 			panic("io_apic.c: ran out of irq_2_pin entries!");
 	}
 	entry->apic = apic;
@@ -634,7 +635,7 @@ int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin)
 				best_guess = irq;
 		}
 	}
-	BUG_ON(best_guess >= NR_IRQS);
+	BUG_ON(best_guess >= nr_irqs);
 	return best_guess;
 }
 
@@ -766,7 +767,7 @@ static int pin_2_irq(int idx, int apic, int pin)
 			irq += nr_ioapic_registers[i++];
 		irq += pin;
 	}
-	BUG_ON(irq >= NR_IRQS);
+	BUG_ON(irq >= nr_irqs);
 	return irq;
 }
 
@@ -788,7 +789,7 @@ static int __assign_irq_vector(int irq, cpumask_t mask)
 	int cpu;
 	struct irq_cfg *cfg;
 
-	BUG_ON((unsigned)irq >= NR_IRQS);
+	BUG_ON((unsigned)irq >= nr_irqs);
 	cfg = &irq_cfg[irq];
 
 	/* Only try and allocate irqs on cpus that are present */
@@ -862,7 +863,7 @@ static void __clear_irq_vector(int irq)
 	cpumask_t mask;
 	int cpu, vector;
 
-	BUG_ON((unsigned)irq >= NR_IRQS);
+	BUG_ON((unsigned)irq >= nr_irqs);
 	cfg = &irq_cfg[irq];
 	BUG_ON(!cfg->vector);
 
@@ -882,7 +883,7 @@ static void __setup_vector_irq(int cpu)
 	int irq, vector;
 
 	/* Mark the inuse vectors */
-	for (irq = 0; irq < NR_IRQS; ++irq) {
+	for (irq = 0; irq < nr_irqs; ++irq) {
 		if (!cpu_isset(cpu, irq_cfg[irq].domain))
 			continue;
 		vector = irq_cfg[irq].vector;
@@ -1188,7 +1189,7 @@ __apicdebuginit(void) print_IO_APIC(void)
 	}
 	}
 	printk(KERN_DEBUG "IRQ to pin mappings:\n");
-	for (i = 0; i < NR_IRQS; i++) {
+	for (i = 0; i < nr_irqs; i++) {
 		struct irq_pin_list *entry = irq_2_pin + i;
 		if (entry->pin < 0)
 			continue;
@@ -1361,7 +1362,7 @@ void __init enable_IO_APIC(void)
 	int i, apic;
 	unsigned long flags;
 
-	for (i = 0; i < PIN_MAP_SIZE; i++) {
+	for (i = 0; i < pin_map_size; i++) {
 		irq_2_pin[i].pin = -1;
 		irq_2_pin[i].next = 0;
 	}
@@ -1655,7 +1656,7 @@ static void ir_irq_migration(struct work_struct *work)
 {
 	int irq;
 
-	for (irq = 0; irq < NR_IRQS; irq++) {
+	for (irq = 0; irq < nr_irqs; irq++) {
 		struct irq_desc *desc = irq_desc + irq;
 		if (desc->status & IRQ_MOVE_PENDING) {
 			unsigned long flags;
@@ -1704,7 +1705,7 @@ asmlinkage void smp_irq_move_cleanup_interrupt(void)
 		struct irq_desc *desc;
 		struct irq_cfg *cfg;
 		irq = __get_cpu_var(vector_irq)[vector];
-		if (irq >= NR_IRQS)
+		if (irq >= nr_irqs)
 			continue;
 
 		desc = irq_desc + irq;
@@ -1862,7 +1863,7 @@ static inline void init_IO_APIC_traps(void)
 	 * Also, we've got to be careful not to trash gate
 	 * 0x80, because int 0x80 is hm, kind of importantish. ;)
 	 */
-	for (irq = 0; irq < NR_IRQS ; irq++) {
+	for (irq = 0; irq < nr_irqs ; irq++) {
 		if (IO_APIC_IRQ(irq) && !irq_cfg[irq].vector) {
 			/*
 			 * Hmm.. We don't have an entry for this,
@@ -2276,7 +2277,7 @@ int create_irq(void)
 
 	irq = -ENOSPC;
 	spin_lock_irqsave(&vector_lock, flags);
-	for (new = (NR_IRQS - 1); new >= 0; new--) {
+	for (new = (nr_irqs - 1); new >= 0; new--) {
 		if (platform_legacy_irq(new))
 			continue;
 		if (irq_cfg[new].vector != 0)
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 1cf8c1f..0cff2f4 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -226,7 +226,7 @@ unsigned int do_IRQ(struct pt_regs *regs)
 	int overflow, irq = ~regs->orig_ax;
 	struct irq_desc *desc = irq_desc + irq;
 
-	if (unlikely((unsigned)irq >= NR_IRQS)) {
+	if (unlikely((unsigned)irq >= nr_irqs)) {
 		printk(KERN_EMERG "%s: cannot handle IRQ %d\n",
 					__func__, irq);
 		BUG();
@@ -271,7 +271,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_putc(p, '\n');
 	}
 
-	if (i < NR_IRQS) {
+	if (i < nr_irqs) {
 		unsigned any_count = 0;
 
 		spin_lock_irqsave(&irq_desc[i].lock, flags);
@@ -303,7 +303,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_putc(p, '\n');
 skip:
 		spin_unlock_irqrestore(&irq_desc[i].lock, flags);
-	} else if (i == NR_IRQS) {
+	} else if (i == nr_irqs) {
 		seq_printf(p, "NMI: ");
 		for_each_online_cpu(j)
 			seq_printf(p, "%10u ", nmi_count(j));
@@ -396,7 +396,7 @@ void fixup_irqs(cpumask_t map)
 	unsigned int irq;
 	static int warned;
 
-	for (irq = 0; irq < NR_IRQS; irq++) {
+	for (irq = 0; irq < nr_irqs; irq++) {
 		cpumask_t mask;
 		if (irq == 2)
 			continue;
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 1f78b23..de94c60 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -81,7 +81,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_putc(p, '\n');
 	}
 
-	if (i < NR_IRQS) {
+	if (i < nr_irqs) {
 		unsigned any_count = 0;
 
 		spin_lock_irqsave(&irq_desc[i].lock, flags);
@@ -112,7 +112,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_putc(p, '\n');
 skip:
 		spin_unlock_irqrestore(&irq_desc[i].lock, flags);
-	} else if (i == NR_IRQS) {
+	} else if (i == nr_irqs) {
 		seq_printf(p, "NMI: ");
 		for_each_online_cpu(j)
 			seq_printf(p, "%10u ", cpu_pda(j)->__nmi_count);
@@ -201,7 +201,7 @@ asmlinkage unsigned int do_IRQ(struct pt_regs *regs)
 	stack_overflow_check(regs);
 #endif
 
-	if (likely(irq < NR_IRQS))
+	if (likely(irq < nr_irqs))
 		generic_handle_irq(irq);
 	else {
 		if (!disable_apic)
@@ -224,7 +224,7 @@ void fixup_irqs(cpumask_t map)
 	unsigned int irq;
 	static int warned;
 
-	for (irq = 0; irq < NR_IRQS; irq++) {
+	for (irq = 0; irq < nr_irqs; irq++) {
 		cpumask_t mask;
 		int break_affinity = 0;
 		int set_affinity = 1;
diff --git a/arch/x86/kernel/irqinit_32.c b/arch/x86/kernel/irqinit_32.c
index d669142..b13d932 100644
--- a/arch/x86/kernel/irqinit_32.c
+++ b/arch/x86/kernel/irqinit_32.c
@@ -91,7 +91,7 @@ void __init native_init_IRQ(void)
 	 */
 	for (i = 0; i < (NR_VECTORS - FIRST_EXTERNAL_VECTOR); i++) {
 		int vector = FIRST_EXTERNAL_VECTOR + i;
-		if (i >= NR_IRQS)
+		if (i >= nr_irqs)
 			break;
 		/* SYSCALL_VECTOR was reserved in trap_init. */
 		if (!test_bit(vector, used_vectors))
diff --git a/arch/x86/kernel/irqinit_64.c b/arch/x86/kernel/irqinit_64.c
index 1f26fd9..48674e6 100644
--- a/arch/x86/kernel/irqinit_64.c
+++ b/arch/x86/kernel/irqinit_64.c
@@ -142,7 +142,7 @@ static void __init init_ISA_irqs (void)
 	init_bsp_APIC();
 	init_8259A(0);
 
-	for (i = 0; i < NR_IRQS; i++) {
+	for (i = 0; i < nr_irqs; i++) {
 		irq_desc[i].status = IRQ_DISABLED;
 		irq_desc[i].action = NULL;
 		irq_desc[i].depth = 1;
diff --git a/include/asm-x86/irq.h b/include/asm-x86/irq.h
index 1e5f290..2a130c4 100644
--- a/include/asm-x86/irq.h
+++ b/include/asm-x86/irq.h
@@ -10,6 +10,9 @@
 #include <asm/apicdef.h>
 #include <asm/irq_vectors.h>
 
+extern int pin_map_size;
+extern int first_free_entry;
+
 static inline int irq_canonicalize(int irq)
 {
 	return ((irq == 2) ? 9 : irq);
-- 
1.5.4.5

[PATCH 09/33] drivers/char to use nr_irqs

[Yinghai Lu]

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
---
 drivers/char/hpet.c       |    2 +-
 drivers/char/random.c     |    4 ++--
 drivers/char/vr41xx_giu.c |    2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c
index 2908a0e..8d562ae 100644
--- a/drivers/char/hpet.c
+++ b/drivers/char/hpet.c
@@ -219,7 +219,7 @@ static void hpet_timer_set_irq(struct hpet_dev *devp)
 	for (irq = find_first_bit(&v, HPET_MAX_IRQ); irq < HPET_MAX_IRQ;
 		irq = find_next_bit(&v, HPET_MAX_IRQ, 1 + irq)) {
 
-		if (irq >= NR_IRQS) {
+		if (irq >= nr_irqs) {
 			irq = HPET_MAX_IRQ;
 			break;
 		}
diff --git a/drivers/char/random.c b/drivers/char/random.c
index e0d0e37..fdbdcfc 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -647,7 +647,7 @@ EXPORT_SYMBOL_GPL(add_input_randomness);
 
 void add_interrupt_randomness(int irq)
 {
-	if (irq >= NR_IRQS || irq_timer_state[irq] == NULL)
+	if (irq >= nr_irqs || irq_timer_state[irq] == NULL)
 		return;
 
 	DEBUG_ENT("irq event %d\n", irq);
@@ -911,7 +911,7 @@ void rand_initialize_irq(int irq)
 {
 	struct timer_rand_state *state;
 
-	if (irq >= NR_IRQS || irq_timer_state[irq])
+	if (irq >= nr_irqs || irq_timer_state[irq])
 		return;
 
 	/*
diff --git a/drivers/char/vr41xx_giu.c b/drivers/char/vr41xx_giu.c
index ffe9b4e..54c8372 100644
--- a/drivers/char/vr41xx_giu.c
+++ b/drivers/char/vr41xx_giu.c
@@ -641,7 +641,7 @@ static int __devinit giu_probe(struct platform_device *dev)
 	}
 
 	irq = platform_get_irq(dev, 0);
-	if (irq < 0 || irq >= NR_IRQS)
+	if (irq < 0 || irq >= nr_irqs)
 		return -EBUSY;
 
 	return cascade_irq(irq, giu_get_irq);
-- 
1.5.4.5

[PATCH 10/33] drivers/net to use nr_irqs

[Yinghai Lu]

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
---
 drivers/net/3c59x.c                   |    4 ++--
 drivers/net/hamradio/baycom_ser_fdx.c |    4 ++--
 drivers/net/hamradio/scc.c            |    6 +++---
 drivers/net/wan/sbni.c                |    2 +-
 4 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/net/3c59x.c b/drivers/net/3c59x.c
index 8db4e6b..7449a1c 100644
--- a/drivers/net/3c59x.c
+++ b/drivers/net/3c59x.c
@@ -90,7 +90,7 @@ static int vortex_debug = 1;
 #include <linux/eisa.h>
 #include <linux/bitops.h>
 #include <linux/jiffies.h>
-#include <asm/irq.h>			/* For NR_IRQS only. */
+#include <asm/irq.h>			/* For nr_irqs only. */
 #include <asm/io.h>
 #include <asm/uaccess.h>
 
@@ -1221,7 +1221,7 @@ static int __devinit vortex_probe1(struct device *gendev,
 	if (print_info)
 		printk(", IRQ %d\n", dev->irq);
 	/* Tell them about an invalid IRQ. */
-	if (dev->irq <= 0 || dev->irq >= NR_IRQS)
+	if (dev->irq <= 0 || dev->irq >= nr_irqs)
 		printk(KERN_WARNING " *** Warning: IRQ %d is unlikely to work! ***\n",
 			   dev->irq);
 
diff --git a/drivers/net/hamradio/baycom_ser_fdx.c b/drivers/net/hamradio/baycom_ser_fdx.c
index 17ac697..b6a816e 100644
--- a/drivers/net/hamradio/baycom_ser_fdx.c
+++ b/drivers/net/hamradio/baycom_ser_fdx.c
@@ -416,10 +416,10 @@ static int ser12_open(struct net_device *dev)
 	if (!dev || !bc)
 		return -ENXIO;
 	if (!dev->base_addr || dev->base_addr > 0xffff-SER12_EXTENT ||
-	    dev->irq < 2 || dev->irq > NR_IRQS) {
+	    dev->irq < 2 || dev->irq > nr_irqs) {
 		printk(KERN_INFO "baycom_ser_fdx: invalid portnumber (max %u) "
 				"or irq (2 <= irq <= %d)\n",
-				0xffff-SER12_EXTENT, NR_IRQS);
+				0xffff-SER12_EXTENT, nr_irqs);
 		return -ENXIO;
 	}
 	if (bc->baud < 300 || bc->baud > 4800) {
diff --git a/drivers/net/hamradio/scc.c b/drivers/net/hamradio/scc.c
index 45ae9d1..c17e39b 100644
--- a/drivers/net/hamradio/scc.c
+++ b/drivers/net/hamradio/scc.c
@@ -1465,7 +1465,7 @@ static void z8530_init(void)
 	printk(KERN_INFO "Init Z8530 driver: %u channels, IRQ", Nchips*2);
 	
 	flag=" ";
-	for (k = 0; k < NR_IRQS; k++)
+	for (k = 0; k < nr_irqs; k++)
 		if (Ivec[k].used) 
 		{
 			printk("%s%d", flag, k);
@@ -1728,7 +1728,7 @@ static int scc_net_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 
 			if (hwcfg.irq == 2) hwcfg.irq = 9;
 
-			if (hwcfg.irq < 0 || hwcfg.irq >= NR_IRQS)
+			if (hwcfg.irq < 0 || hwcfg.irq >= nr_irqs)
 				return -EINVAL;
 				
 			if (!Ivec[hwcfg.irq].used && hwcfg.irq)
@@ -2148,7 +2148,7 @@ static void __exit scc_cleanup_driver(void)
 		}
 		
 	/* To unload the port must be closed so no real IRQ pending */
-	for (k=0; k < NR_IRQS ; k++)
+	for (k = 0; k < nr_irqs ; k++)
 		if (Ivec[k].used) free_irq(k, NULL);
 		
 	local_irq_enable();
diff --git a/drivers/net/wan/sbni.c b/drivers/net/wan/sbni.c
index e59255a..8bd13b8 100644
--- a/drivers/net/wan/sbni.c
+++ b/drivers/net/wan/sbni.c
@@ -318,7 +318,7 @@ sbni_pci_probe( struct net_device  *dev )
 				continue;
 		}
 
-		if( pci_irq_line <= 0  ||  pci_irq_line >= NR_IRQS )
+		if (pci_irq_line <= 0 || pci_irq_line >= nr_irqs)
 			printk( KERN_WARNING "  WARNING: The PCI BIOS assigned "
 				"this PCI card to IRQ %d, which is unlikely "
 				"to work!.\n"
-- 
1.5.4.5

[PATCH 11/33] drivers intr remapping to use nr_irqs

[Yinghai Lu]

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
---
 drivers/pci/intr_remapping.c |   16 ++++++++--------
 1 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/pci/intr_remapping.c b/drivers/pci/intr_remapping.c
index bb642cc..980566e 100644
--- a/drivers/pci/intr_remapping.c
+++ b/drivers/pci/intr_remapping.c
@@ -22,7 +22,7 @@ static DEFINE_SPINLOCK(irq_2_ir_lock);
 
 int irq_remapped(int irq)
 {
-	if (irq > NR_IRQS)
+	if (irq > nr_irqs)
 		return 0;
 
 	if (!irq_2_iommu[irq].iommu)
@@ -35,7 +35,7 @@ int get_irte(int irq, struct irte *entry)
 {
 	int index;
 
-	if (!entry || irq > NR_IRQS)
+	if (!entry || irq > nr_irqs)
 		return -1;
 
 	spin_lock(&irq_2_ir_lock);
@@ -126,7 +126,7 @@ int map_irq_to_irte_handle(int irq, u16 *sub_handle)
 	int index;
 
 	spin_lock(&irq_2_ir_lock);
-	if (irq >= NR_IRQS || !irq_2_iommu[irq].iommu) {
+	if (irq >= nr_irqs || !irq_2_iommu[irq].iommu) {
 		spin_unlock(&irq_2_ir_lock);
 		return -1;
 	}
@@ -140,7 +140,7 @@ int map_irq_to_irte_handle(int irq, u16 *sub_handle)
 int set_irte_irq(int irq, struct intel_iommu *iommu, u16 index, u16 subhandle)
 {
 	spin_lock(&irq_2_ir_lock);
-	if (irq >= NR_IRQS || irq_2_iommu[irq].iommu) {
+	if (irq >= nr_irqs || irq_2_iommu[irq].iommu) {
 		spin_unlock(&irq_2_ir_lock);
 		return -1;
 	}
@@ -158,7 +158,7 @@ int set_irte_irq(int irq, struct intel_iommu *iommu, u16 index, u16 subhandle)
 int clear_irte_irq(int irq, struct intel_iommu *iommu, u16 index)
 {
 	spin_lock(&irq_2_ir_lock);
-	if (irq >= NR_IRQS || !irq_2_iommu[irq].iommu) {
+	if (irq >= nr_irqs || !irq_2_iommu[irq].iommu) {
 		spin_unlock(&irq_2_ir_lock);
 		return -1;
 	}
@@ -180,7 +180,7 @@ int modify_irte(int irq, struct irte *irte_modified)
 	struct intel_iommu *iommu;
 
 	spin_lock(&irq_2_ir_lock);
-	if (irq >= NR_IRQS || !irq_2_iommu[irq].iommu) {
+	if (irq >= nr_irqs || !irq_2_iommu[irq].iommu) {
 		spin_unlock(&irq_2_ir_lock);
 		return -1;
 	}
@@ -205,7 +205,7 @@ int flush_irte(int irq)
 	struct intel_iommu *iommu;
 
 	spin_lock(&irq_2_ir_lock);
-	if (irq >= NR_IRQS || !irq_2_iommu[irq].iommu) {
+	if (irq >= nr_irqs || !irq_2_iommu[irq].iommu) {
 		spin_unlock(&irq_2_ir_lock);
 		return -1;
 	}
@@ -248,7 +248,7 @@ int free_irte(int irq)
 	struct intel_iommu *iommu;
 
 	spin_lock(&irq_2_ir_lock);
-	if (irq >= NR_IRQS || !irq_2_iommu[irq].iommu) {
+	if (irq >= nr_irqs || !irq_2_iommu[irq].iommu) {
 		spin_unlock(&irq_2_ir_lock);
 		return -1;
 	}
-- 
1.5.4.5

[PATCH 12/33] drivers/pcmcia to use nr_irqs

[Yinghai Lu]

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
---
 drivers/pcmcia/at91_cf.c      |    2 +-
 drivers/pcmcia/vrc4171_card.c |    2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/pcmcia/at91_cf.c b/drivers/pcmcia/at91_cf.c
index 6849685..194c8ba 100644
--- a/drivers/pcmcia/at91_cf.c
+++ b/drivers/pcmcia/at91_cf.c
@@ -273,7 +273,7 @@ static int __init at91_cf_probe(struct platform_device *pdev)
 			goto fail0d;
 		cf->socket.pci_irq = board->irq_pin;
 	} else
-		cf->socket.pci_irq = NR_IRQS + 1;
+		cf->socket.pci_irq = nr_irqs + 1;
 
 	/* pcmcia layer only remaps "real" memory not iospace */
 	cf->socket.io_offset = (unsigned long)
diff --git a/drivers/pcmcia/vrc4171_card.c b/drivers/pcmcia/vrc4171_card.c
index eee2f1c..b2c4124 100644
--- a/drivers/pcmcia/vrc4171_card.c
+++ b/drivers/pcmcia/vrc4171_card.c
@@ -639,7 +639,7 @@ static int __devinit vrc4171_card_setup(char *options)
 		int irq;
 		options += 4;
 		irq = simple_strtoul(options, &options, 0);
-		if (irq >= 0 && irq < NR_IRQS)
+		if (irq >= 0 && irq < nr_irqs)
 			vrc4171_irq = irq;
 
 		if (*options != ',')
-- 
1.5.4.5

[PATCH 13/33] drivers/rtc to use nr_irqs

[Yinghai Lu]

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
---
 drivers/rtc/rtc-vr41xx.c |    4 ++--
 1 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/rtc/rtc-vr41xx.c b/drivers/rtc/rtc-vr41xx.c
index 884b635..834dcc6 100644
--- a/drivers/rtc/rtc-vr41xx.c
+++ b/drivers/rtc/rtc-vr41xx.c
@@ -360,7 +360,7 @@ static int __devinit rtc_probe(struct platform_device *pdev)
 	spin_unlock_irq(&rtc_lock);
 
 	aie_irq = platform_get_irq(pdev, 0);
-	if (aie_irq < 0 || aie_irq >= NR_IRQS) {
+	if (aie_irq < 0 || aie_irq >= nr_irqs) {
 		retval = -EBUSY;
 		goto err_device_unregister;
 	}
@@ -371,7 +371,7 @@ static int __devinit rtc_probe(struct platform_device *pdev)
 		goto err_device_unregister;
 
 	pie_irq = platform_get_irq(pdev, 1);
-	if (pie_irq < 0 || pie_irq >= NR_IRQS)
+	if (pie_irq < 0 || pie_irq >= nr_irqs)
 		goto err_free_irq;
 
 	retval = request_irq(pie_irq, rtclong1_interrupt, IRQF_DISABLED,
-- 
1.5.4.5

[PATCH 14/33] drivers/scsi to use nr_irqs

[Yinghai Lu]

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
---
 drivers/scsi/aha152x.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

diff --git a/drivers/scsi/aha152x.c b/drivers/scsi/aha152x.c
index b5a868d..1e5478a 100644
--- a/drivers/scsi/aha152x.c
+++ b/drivers/scsi/aha152x.c
@@ -337,7 +337,7 @@ CMD_INC_RESID(struct scsi_cmnd *cmd, int inc)
 #else
 #define IRQ_MIN 9
 #if defined(__PPC)
-#define IRQ_MAX (NR_IRQS-1)
+#define IRQ_MAX (nr_irqs-1)
 #else
 #define IRQ_MAX 12
 #endif
-- 
1.5.4.5

[PATCH 15/33] drivers/serial to use nr_irqs

[Yinghai Lu]

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
---
 drivers/serial/8250.c                   |    4 ++--
 drivers/serial/amba-pl010.c             |    2 +-
 drivers/serial/amba-pl011.c             |    2 +-
 drivers/serial/cpm_uart/cpm_uart_core.c |    2 +-
 drivers/serial/m32r_sio.c               |    4 ++--
 drivers/serial/serial_core.c            |    2 +-
 drivers/serial/serial_lh7a40x.c         |    2 +-
 drivers/serial/sh-sci.c                 |    2 +-
 drivers/serial/ucc_uart.c               |    2 +-
 9 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/drivers/serial/8250.c b/drivers/serial/8250.c
index 3a4d677..3920324 100644
--- a/drivers/serial/8250.c
+++ b/drivers/serial/8250.c
@@ -2433,7 +2433,7 @@ static void serial8250_config_port(struct uart_port *port, int flags)
 static int
 serial8250_verify_port(struct uart_port *port, struct serial_struct *ser)
 {
-	if (ser->irq >= NR_IRQS || ser->irq < 0 ||
+	if (ser->irq >= nr_irqs || ser->irq < 0 ||
 	    ser->baud_base < 9600 || ser->type < PORT_UNKNOWN ||
 	    ser->type >= ARRAY_SIZE(uart_config) || ser->type == PORT_CIRRUS ||
 	    ser->type == PORT_STARTECH)
@@ -2964,7 +2964,7 @@ static int __init serial8250_init(void)
 		"%d ports, IRQ sharing %sabled\n", nr_uarts,
 		share_irqs ? "en" : "dis");
 
-	for (i = 0; i < NR_IRQS; i++)
+	for (i = 0; i < nr_irqs; i++)
 		spin_lock_init(&irq_lists[i].lock);
 
 	ret = uart_register_driver(&serial8250_reg);
diff --git a/drivers/serial/amba-pl010.c b/drivers/serial/amba-pl010.c
index 90b56c2..7156268 100644
--- a/drivers/serial/amba-pl010.c
+++ b/drivers/serial/amba-pl010.c
@@ -512,7 +512,7 @@ static int pl010_verify_port(struct uart_port *port, struct serial_struct *ser)
 	int ret = 0;
 	if (ser->type != PORT_UNKNOWN && ser->type != PORT_AMBA)
 		ret = -EINVAL;
-	if (ser->irq < 0 || ser->irq >= NR_IRQS)
+	if (ser->irq < 0 || ser->irq >= nr_irqs)
 		ret = -EINVAL;
 	if (ser->baud_base < 9600)
 		ret = -EINVAL;
diff --git a/drivers/serial/amba-pl011.c b/drivers/serial/amba-pl011.c
index 9d08f27..b718004 100644
--- a/drivers/serial/amba-pl011.c
+++ b/drivers/serial/amba-pl011.c
@@ -572,7 +572,7 @@ static int pl010_verify_port(struct uart_port *port, struct serial_struct *ser)
 	int ret = 0;
 	if (ser->type != PORT_UNKNOWN && ser->type != PORT_AMBA)
 		ret = -EINVAL;
-	if (ser->irq < 0 || ser->irq >= NR_IRQS)
+	if (ser->irq < 0 || ser->irq >= nr_irqs)
 		ret = -EINVAL;
 	if (ser->baud_base < 9600)
 		ret = -EINVAL;
diff --git a/drivers/serial/cpm_uart/cpm_uart_core.c b/drivers/serial/cpm_uart/cpm_uart_core.c
index a4f8692..b09fdc2 100644
--- a/drivers/serial/cpm_uart/cpm_uart_core.c
+++ b/drivers/serial/cpm_uart/cpm_uart_core.c
@@ -589,7 +589,7 @@ static int cpm_uart_verify_port(struct uart_port *port,
 
 	if (ser->type != PORT_UNKNOWN && ser->type != PORT_CPM)
 		ret = -EINVAL;
-	if (ser->irq < 0 || ser->irq >= NR_IRQS)
+	if (ser->irq < 0 || ser->irq >= nr_irqs)
 		ret = -EINVAL;
 	if (ser->baud_base < 9600)
 		ret = -EINVAL;
diff --git a/drivers/serial/m32r_sio.c b/drivers/serial/m32r_sio.c
index 23d0305..611c97a 100644
--- a/drivers/serial/m32r_sio.c
+++ b/drivers/serial/m32r_sio.c
@@ -922,7 +922,7 @@ static void m32r_sio_config_port(struct uart_port *port, int flags)
 static int
 m32r_sio_verify_port(struct uart_port *port, struct serial_struct *ser)
 {
-	if (ser->irq >= NR_IRQS || ser->irq < 0 ||
+	if (ser->irq >= nr_irqs || ser->irq < 0 ||
 	    ser->baud_base < 9600 || ser->type < PORT_UNKNOWN ||
 	    ser->type >= ARRAY_SIZE(uart_config))
 		return -EINVAL;
@@ -1162,7 +1162,7 @@ static int __init m32r_sio_init(void)
 
 	printk(KERN_INFO "Serial: M32R SIO driver\n");
 
-	for (i = 0; i < NR_IRQS; i++)
+	for (i = 0; i < nr_irqs; i++)
 		spin_lock_init(&irq_lists[i].lock);
 
 	ret = uart_register_driver(&m32r_sio_reg);
diff --git a/drivers/serial/serial_core.c b/drivers/serial/serial_core.c
index f977c98..effd0bd 100644
--- a/drivers/serial/serial_core.c
+++ b/drivers/serial/serial_core.c
@@ -741,7 +741,7 @@ static int uart_set_info(struct uart_state *state,
 	if (port->ops->verify_port)
 		retval = port->ops->verify_port(port, &new_serial);
 
-	if ((new_serial.irq >= NR_IRQS) || (new_serial.irq < 0) ||
+	if ((new_serial.irq >= nr_irqs) || (new_serial.irq < 0) ||
 	    (new_serial.baud_base < 9600))
 		retval = -EINVAL;
 
diff --git a/drivers/serial/serial_lh7a40x.c b/drivers/serial/serial_lh7a40x.c
index cb49a5a..61dc8b3 100644
--- a/drivers/serial/serial_lh7a40x.c
+++ b/drivers/serial/serial_lh7a40x.c
@@ -460,7 +460,7 @@ static int lh7a40xuart_verify_port (struct uart_port* port,
 
 	if (ser->type != PORT_UNKNOWN && ser->type != PORT_LH7A40X)
 		ret = -EINVAL;
-	if (ser->irq < 0 || ser->irq >= NR_IRQS)
+	if (ser->irq < 0 || ser->irq >= nr_irqs)
 		ret = -EINVAL;
 	if (ser->baud_base < 9600) /* *** FIXME: is this true? */
 		ret = -EINVAL;
diff --git a/drivers/serial/sh-sci.c b/drivers/serial/sh-sci.c
index 3df2aae..667b4b8 100644
--- a/drivers/serial/sh-sci.c
+++ b/drivers/serial/sh-sci.c
@@ -1157,7 +1157,7 @@ static int sci_verify_port(struct uart_port *port, struct serial_struct *ser)
 {
 	struct sci_port *s = &sci_ports[port->line];
 
-	if (ser->irq != s->irqs[SCIx_TXI_IRQ] || ser->irq > NR_IRQS)
+	if (ser->irq != s->irqs[SCIx_TXI_IRQ] || ser->irq > nr_irqs)
 		return -EINVAL;
 	if (ser->baud_base < 2400)
 		/* No paper tape reader for Mitch.. */
diff --git a/drivers/serial/ucc_uart.c b/drivers/serial/ucc_uart.c
index 5c5d18d..503f0b9 100644
--- a/drivers/serial/ucc_uart.c
+++ b/drivers/serial/ucc_uart.c
@@ -1066,7 +1066,7 @@ static int qe_uart_verify_port(struct uart_port *port,
 	if (ser->type != PORT_UNKNOWN && ser->type != PORT_CPM)
 		return -EINVAL;
 
-	if (ser->irq < 0 || ser->irq >= NR_IRQS)
+	if (ser->irq < 0 || ser->irq >= nr_irqs)
 		return -EINVAL;
 
 	if (ser->baud_base < 9600)
-- 
1.5.4.5

[PATCH 16/33] drivers proc to use nr_irqs

[Yinghai Lu]

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
---
 fs/proc/proc_misc.c |   10 +++++-----
 1 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
index ded9698..1968251 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -503,7 +503,7 @@ static int show_stat(struct seq_file *p, void *v)
 	struct timespec boottime;
 	unsigned int *per_irq_sum;
 
-	per_irq_sum = kzalloc(sizeof(unsigned int)*NR_IRQS, GFP_KERNEL);
+	per_irq_sum = kzalloc(sizeof(unsigned int)*nr_irqs, GFP_KERNEL);
 	if (!per_irq_sum)
 		return -ENOMEM;
 
@@ -525,7 +525,7 @@ static int show_stat(struct seq_file *p, void *v)
 		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 (j = 0; j < NR_IRQS; j++) {
+		for (j = 0; j < nr_irqs; j++) {
 			unsigned int temp = kstat_cpu(i).irqs[j];
 			sum += temp;
 			per_irq_sum[j] += temp;
@@ -571,7 +571,7 @@ static int show_stat(struct seq_file *p, void *v)
 	}
 	seq_printf(p, "intr %llu", (unsigned long long)sum);
 
-	for (i = 0; i < NR_IRQS; i++)
+	for (i = 0; i < nr_irqs; i++)
 		seq_printf(p, " %u", per_irq_sum[i]);
 
 	seq_printf(p,
@@ -625,13 +625,13 @@ static const struct file_operations proc_stat_operations = {
  */
 static void *int_seq_start(struct seq_file *f, loff_t *pos)
 {
-	return (*pos <= NR_IRQS) ? pos : NULL;
+	return (*pos <= nr_irqs) ? pos : NULL;
 }
 
 static void *int_seq_next(struct seq_file *f, void *v, loff_t *pos)
 {
 	(*pos)++;
-	if (*pos > NR_IRQS)
+	if (*pos > nr_irqs)
 		return NULL;
 	return pos;
 }
-- 
1.5.4.5

[PATCH 17/33] drivers xen events to use nr_irqs

[Yinghai Lu]

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
---
 drivers/xen/events.c |   12 ++++++------
 1 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index a083703..8e329c2 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -139,7 +139,7 @@ static void init_evtchn_cpu_bindings(void)
 #ifdef CONFIG_SMP
 	int i;
 	/* By default all event channels notify CPU#0. */
-	for (i = 0; i < NR_IRQS; i++)
+	for (i = 0; i < nr_irqs; i++)
 		irq_desc[i].affinity = cpumask_of_cpu(0);
 #endif
 
@@ -223,12 +223,12 @@ static int find_unbound_irq(void)
 	int irq;
 
 	/* Only allocate from dynirq range */
-	for (irq = 0; irq < NR_IRQS; irq++)
+	for (irq = 0; irq < nr_irqs; irq++)
 		if (irq_bindcount[irq] == 0)
 			break;
 
-	if (irq == NR_IRQS)
-		panic("No available IRQ to bind to: increase NR_IRQS!\n");
+	if (irq == nr_irqs)
+		panic("No available IRQ to bind to: increase nr_irqs!\n");
 
 	return irq;
 }
@@ -761,7 +761,7 @@ void xen_irq_resume(void)
 		mask_evtchn(evtchn);
 
 	/* No IRQ <-> event-channel mappings. */
-	for (irq = 0; irq < NR_IRQS; 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++)
@@ -793,7 +793,7 @@ void __init xen_init_IRQ(void)
 		mask_evtchn(i);
 
 	/* Dynamic IRQ space is currently unbound. Zero the refcnts. */
-	for (i = 0; i < NR_IRQS; i++)
+	for (i = 0; i < nr_irqs; i++)
 		irq_bindcount[i] = 0;
 
 	irq_ctx_init(smp_processor_id());
-- 
1.5.4.5

[PATCH 18/33] make irq_timer_state to use dyn_array

[Yinghai Lu]

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
---
 drivers/char/random.c |    6 ++++++
 1 files changed, 6 insertions(+), 0 deletions(-)

diff --git a/drivers/char/random.c b/drivers/char/random.c
index fdbdcfc..872669e 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -558,7 +558,13 @@ struct timer_rand_state {
 };
 
 static struct timer_rand_state input_timer_state;
+
+#ifdef CONFIG_HAVE_DYN_ARRAY
+static struct timer_rand_state **irq_timer_state;
+DEFINE_DYN_ARRAY(irq_timer_state, sizeof(struct timer_rand_state *), nr_irqs, PAGE_SIZE, NULL);
+#else
 static struct timer_rand_state *irq_timer_state[NR_IRQS];
+#endif
 
 /*
  * This function adds entropy to the entropy "pool" by using timing
-- 
1.5.4.5

[PATCH 19/33] make irq2_iommu to use dyn_array

[Yinghai Lu]

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
---
 drivers/pci/intr_remapping.c |    6 ++++--
 1 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/intr_remapping.c b/drivers/pci/intr_remapping.c
index 980566e..ced5ebc 100644
--- a/drivers/pci/intr_remapping.c
+++ b/drivers/pci/intr_remapping.c
@@ -11,12 +11,14 @@ static struct ioapic_scope ir_ioapic[MAX_IO_APICS];
 static int ir_ioapic_num;
 int intr_remapping_enabled;
 
-static struct {
+static struct irq_2_iommu {
 	struct intel_iommu *iommu;
 	u16 irte_index;
 	u16 sub_handle;
 	u8  irte_mask;
-} irq_2_iommu[NR_IRQS];
+} *irq_2_iommu;
+
+DEFINE_DYN_ARRAY(irq_2_iommu, sizeof(struct irq_2_iommu), nr_irqs, PAGE_SIZE, NULL);
 
 static DEFINE_SPINLOCK(irq_2_ir_lock);
 
-- 
1.5.4.5

[PATCH 20/33] make irq_desc to use dyn_array

[Yinghai Lu]

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
---
 include/linux/irq.h |    4 ++++
 kernel/irq/handle.c |   31 +++++++++++++++++++++++++++++++
 2 files changed, 35 insertions(+), 0 deletions(-)

diff --git a/include/linux/irq.h b/include/linux/irq.h
index bd69d90..c22e870 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -181,7 +181,11 @@ struct irq_desc {
 	const char		*name;
 } ____cacheline_internodealigned_in_smp;
 
+#ifdef CONFIG_HAVE_DYN_ARRAY
+extern struct irq_desc *irq_desc;
+#else
 extern struct irq_desc irq_desc[NR_IRQS];
+#endif
 
 /*
  * Migration helpers for obsolete names, they will go away:
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index e9d022c..e94eeca 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -48,6 +48,36 @@ handle_bad_irq(unsigned int irq, struct irq_desc *desc)
  * Controller mappings for all interrupt sources:
  */
 int nr_irqs = NR_IRQS;
+
+#ifdef CONFIG_HAVE_DYN_ARRAY
+static struct irq_desc irq_desc_init __initdata = {
+	.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 init_work(void *data)
+{
+	struct dyn_array *da = data;
+	int i;
+	struct  irq_desc *desc;
+
+	desc = *da->name;
+
+	for (i = 0; i < *da->nr; i++)
+		memcpy(&desc[i], &irq_desc_init, sizeof(struct irq_desc));
+}
+
+struct irq_desc *irq_desc;
+DEFINE_DYN_ARRAY(irq_desc, sizeof(struct irq_desc), nr_irqs, PAGE_SIZE, init_work);
+
+#else
+
 struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
 	[0 ... NR_IRQS-1] = {
 		.status = IRQ_DISABLED,
@@ -60,6 +90,7 @@ struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
 #endif
 	}
 };
+#endif
 
 /*
  * What should we do if we get a hw irq event on an illegal vector?
-- 
1.5.4.5

[PATCH 21/33] serial: change remove NR_IRQS in 8250.c v2

[Yinghai Lu]

use small array with index to handle irq locking for serial port
hope 32 slot is enough

v2: according to Eric, move irq_no into irq_info, and not clean irq_no

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Cc: Alan Cox <alan@lxorguk.ukuu.org.uk>
---
 drivers/serial/8250.c |   45 +++++++++++++++++++++++++++++++++++++++++----
 1 files changed, 41 insertions(+), 4 deletions(-)

diff --git a/drivers/serial/8250.c b/drivers/serial/8250.c
index 3920324..595b956 100644
--- a/drivers/serial/8250.c
+++ b/drivers/serial/8250.c
@@ -147,9 +147,39 @@ struct uart_8250_port {
 struct irq_info {
 	spinlock_t		lock;
 	struct list_head	*head;
+	int irq_no;
 };
 
-static struct irq_info irq_lists[NR_IRQS];
+#define NR_IRQ_INFO	32
+
+static struct irq_info irq_lists[NR_IRQ_INFO] = {
+	[0 ... NR_IRQ_INFO-1] = {
+		.irq_no = -1,
+	}
+};
+
+static struct irq_info *get_irq_info(int irq, int with_free)
+{
+	int i, first_free = -1;
+
+	for (i = 0; i < NR_IRQ_INFO; i++) {
+		if (irq_lists[i].irq_no == irq)
+			return &irq_lists[i];
+		if (irq_lists[i].irq_no == -1 && first_free == -1)
+			first_free = i;
+	}
+	if (!with_free)
+		return NULL;
+
+	if (first_free != -1) {
+		irq_lists[first_free].irq_no = irq;
+		return &irq_lists[first_free];
+	}
+
+	WARN_ON("NR_IRQ_INFO too small");
+
+	return NULL;
+}
 
 /*
  * Here we define the default xmit fifo size used for each type of UART.
@@ -1554,9 +1584,12 @@ static void serial_do_unlink(struct irq_info *i, struct uart_8250_port *up)
 
 static int serial_link_irq_chain(struct uart_8250_port *up)
 {
-	struct irq_info *i = irq_lists + up->port.irq;
+	struct irq_info *i = get_irq_info(up->port.irq, 1);
 	int ret, irq_flags = up->port.flags & UPF_SHARE_IRQ ? IRQF_SHARED : 0;
 
+	if (!i)
+		return -1;
+
 	spin_lock_irq(&i->lock);
 
 	if (i->head) {
@@ -1580,7 +1613,11 @@ static int serial_link_irq_chain(struct uart_8250_port *up)
 
 static void serial_unlink_irq_chain(struct uart_8250_port *up)
 {
-	struct irq_info *i = irq_lists + up->port.irq;
+	int irq_no = up->port.irq;
+	struct irq_info *i = get_irq_info(irq_no, 0);
+
+	if (!i)
+		return;
 
 	BUG_ON(i->head == NULL);
 
@@ -2964,7 +3001,7 @@ static int __init serial8250_init(void)
 		"%d ports, IRQ sharing %sabled\n", nr_uarts,
 		share_irqs ? "en" : "dis");
 
-	for (i = 0; i < nr_irqs; i++)
+	for (i = 0; i < NR_IRQ_INFO; i++)
 		spin_lock_init(&irq_lists[i].lock);
 
 	ret = uart_register_driver(&serial8250_reg);
-- 
1.5.4.5

[PATCH 22/33] irq: make irqs in kernel stat use per_cpu_dyn_array

[Yinghai Lu]

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
---
 include/linux/kernel_stat.h |    4 ++++
 kernel/sched.c              |    5 ++++-
 2 files changed, 8 insertions(+), 1 deletions(-)

diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index cf9f40a..fe1f7fe 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -28,7 +28,11 @@ struct cpu_usage_stat {
 
 struct kernel_stat {
 	struct cpu_usage_stat	cpustat;
+#ifdef CONFIG_HAVE_DYN_ARRAY
+	unsigned int *irqs;
+#else
 	unsigned int irqs[NR_IRQS];
+#endif
 };
 
 DECLARE_PER_CPU(struct kernel_stat, kstat);
diff --git a/kernel/sched.c b/kernel/sched.c
index 55cb4ce..21c0839 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4021,9 +4021,12 @@ static inline void idle_balance(int cpu, struct rq *rq)
 #endif
 
 DEFINE_PER_CPU(struct kernel_stat, kstat);
-
 EXPORT_PER_CPU_SYMBOL(kstat);
 
+#ifdef CONFIG_HAVE_DYN_ARRAY
+DEFINE_PER_CPU_DYN_ARRAY_ADDR(per_cpu__kstat_irqs, per_cpu__kstat.irqs, sizeof(unsigned int), nr_irqs, sizeof(unsigned long), NULL);
+#endif
+
 /*
  * Return p->sum_exec_runtime plus any more ns on the sched_clock
  * that have not yet been banked in case the task is currently running.
-- 
1.5.4.5

[PATCH 23/33] x86: use dyn_array in io_apic_xx.c

[Yinghai Lu]

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
---
 arch/x86/kernel/io_apic_32.c |   54 +++++++++++++++++++++++++++++++++--------
 arch/x86/kernel/io_apic_64.c |   28 ++++++++++++++++-----
 arch/x86/kernel/setup.c      |    6 ++++
 3 files changed, 70 insertions(+), 18 deletions(-)

diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index d5953ff..a0ce64c 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -70,7 +70,7 @@ int timer_through_8259 __initdata;
  */
 int sis_apic_bug = -1;
 
-int first_free_entry = NR_IRQS;
+int first_free_entry;
 /*
  * # of IRQ routing registers
  */
@@ -98,10 +98,7 @@ static int disable_timer_pin_1 __initdata;
  * Rough estimation of how many shared IRQs there are, can
  * be changed anytime.
  */
-#define MAX_PLUS_SHARED_IRQS NR_IRQS
-#define PIN_MAP_SIZE (MAX_PLUS_SHARED_IRQS + NR_IRQS)
-
-int pin_map_size = PIN_MAP_SIZE;
+int pin_map_size;
 
 /*
  * This is performance-critical, we want to do it O(1)
@@ -112,7 +109,9 @@ int pin_map_size = PIN_MAP_SIZE;
 
 static struct irq_pin_list {
 	int apic, pin, next;
-} irq_2_pin[PIN_MAP_SIZE];
+} *irq_2_pin;
+
+DEFINE_DYN_ARRAY(irq_2_pin, sizeof(struct irq_pin_list), pin_map_size, 16, NULL);
 
 struct io_apic {
 	unsigned int index;
@@ -403,9 +402,28 @@ static struct irq_cpu_info {
 
 #define CPU_TO_PACKAGEINDEX(i) (first_cpu(per_cpu(cpu_sibling_map, i)))
 
-static cpumask_t balance_irq_affinity[NR_IRQS] = {
-	[0 ... NR_IRQS-1] = CPU_MASK_ALL
-};
+static cpumask_t balance_irq_affinity_init __initdata = CPU_MASK_ALL;
+
+static cpumask_t *balance_irq_affinity;
+
+
+static void __init irq_affinity_init_work(void *data)
+{
+	struct dyn_array *da = data;
+
+	int i;
+	struct  balance_irq_affinity *affinity;
+
+	affinity = *da->name;
+
+	for (i = 0; i < *da->nr; i++)
+		memcpy(&affinity[i], &balance_irq_affinity_init,
+			 sizeof(struct balance_irq_affinity));
+
+}
+
+DEFINE_DYN_ARRAY(balance_irq_affinity, sizeof(struct balance_irq_affinity), nr_irqs, PAGE_SIZE, irq_affinity_init_work);
+
 
 void set_balance_irq_affinity(unsigned int irq, cpumask_t mask)
 {
@@ -1170,14 +1188,28 @@ static inline int IO_APIC_irq_trigger(int irq)
 }
 
 /* irq_vectors is indexed by the sum of all RTEs in all I/O APICs. */
-static u8 irq_vector[NR_IRQ_VECTORS] __read_mostly = { FIRST_DEVICE_VECTOR , 0 };
+static u8 irq_vector_init_first __initdata = FIRST_DEVICE_VECTOR;
+static u8 *irq_vector;
+
+static void __init irq_vector_init_work(void *data)
+{
+	struct dyn_array *da = data;
+
+	u8 *irq_vec;
+
+	irq_vec = *da->name;
+
+	irq_vec[0] = irq_vector_init_first;
+}
+
+DEFINE_DYN_ARRAY(irq_vector, sizeof(u8), nr_irqs, PAGE_SIZE, irq_vector_init_work);
 
 static int __assign_irq_vector(int irq)
 {
 	static int current_vector = FIRST_DEVICE_VECTOR, current_offset;
 	int vector, offset;
 
-	BUG_ON((unsigned)irq >= NR_IRQ_VECTORS);
+	BUG_ON((unsigned)irq >= nr_irqs);
 
 	if (irq_vector[irq] > 0)
 		return irq_vector[irq];
diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
index 456f2e7..9bcb6c2 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -66,7 +66,7 @@ struct irq_cfg {
 };
 
 /* irq_cfg is indexed by the sum of all RTEs in all I/O APICs. */
-static struct irq_cfg irq_cfg[NR_IRQS] __read_mostly = {
+static struct irq_cfg irq_cfg_legacy[] __initdata = {
 	[0]  = { .domain = CPU_MASK_ALL, .vector = IRQ0_VECTOR,  },
 	[1]  = { .domain = CPU_MASK_ALL, .vector = IRQ1_VECTOR,  },
 	[2]  = { .domain = CPU_MASK_ALL, .vector = IRQ2_VECTOR,  },
@@ -85,6 +85,17 @@ static struct irq_cfg irq_cfg[NR_IRQS] __read_mostly = {
 	[15] = { .domain = CPU_MASK_ALL, .vector = IRQ15_VECTOR, },
 };
 
+static struct irq_cfg *irq_cfg;
+
+static void __init init_work(void *data)
+{
+	struct dyn_array *da = data;
+
+	memcpy(*da->name, irq_cfg_legacy, sizeof(irq_cfg_legacy));
+}
+
+DEFINE_DYN_ARRAY(irq_cfg, sizeof(struct irq_cfg), nr_irqs, PAGE_SIZE, init_work);
+
 static int assign_irq_vector(int irq, cpumask_t mask);
 
 int first_system_vector = 0xfe;
@@ -129,10 +140,9 @@ DECLARE_BITMAP(mp_bus_not_pci, MAX_MP_BUSSES);
  * Rough estimation of how many shared IRQs there are, can
  * be changed anytime.
  */
-#define MAX_PLUS_SHARED_IRQS NR_IRQS
-#define PIN_MAP_SIZE (MAX_PLUS_SHARED_IRQS + NR_IRQS)
 
-int pin_map_size = PIN_MAP_SIZE;
+int pin_map_size;
+
 /*
  * This is performance-critical, we want to do it O(1)
  *
@@ -141,8 +151,12 @@ int pin_map_size = PIN_MAP_SIZE;
  */
 
 static struct irq_pin_list {
-	short apic, pin, next;
-} irq_2_pin[PIN_MAP_SIZE];
+	short apic, pin;
+	int next;
+} *irq_2_pin;
+
+DEFINE_DYN_ARRAY(irq_2_pin, sizeof(struct irq_pin_list), pin_map_size, sizeof(struct irq_pin_list), NULL);
+
 
 struct io_apic {
 	unsigned int index;
@@ -359,7 +373,7 @@ static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t mask)
  * 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.
  */
-int first_free_entry = NR_IRQS;
+int first_free_entry;
 static void add_pin_to_irq(unsigned int irq, int apic, int pin)
 {
 	struct irq_pin_list *entry = irq_2_pin + irq;
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 60e8de1..39c5106 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -856,9 +856,15 @@ void __init setup_arch(char **cmdline_p)
 #endif
 
 	prefill_possible_map();
+
 #ifdef CONFIG_X86_64
+	/* need to wait for nr_cpu_ids settle down */
+	if (nr_irqs == NR_IRQS)
+		nr_irqs = 32 * nr_cpu_ids + 224;
 	init_cpu_to_node();
 #endif
+	pin_map_size = nr_irqs * 2;
+	first_free_entry = nr_irqs;
 
 	init_apic_mappings();
 	ioapic_init_mappings();
-- 
1.5.4.5

[PATCH 24/33] x86: get mp_irqs from madt

[Yinghai Lu]

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
---
 arch/x86/kernel/acpi/boot.c |   30 ++++++++++++++++++++++++++++--
 include/asm-x86/mpspec.h    |    1 +
 2 files changed, 29 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 27ef365..443cb30 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -962,6 +962,29 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base)
 	nr_ioapics++;
 }
 
+int get_nr_irqs_via_madt(void)
+{
+	int idx;
+	int nr = 0;
+
+	for (idx = 0; idx < nr_ioapics; idx++) {
+		if (mp_ioapic_routing[idx].gsi_end > nr)
+			nr = mp_ioapic_routing[idx].gsi_end;
+	}
+
+	nr++;
+
+	/* double it for hotplug and msi and nmi */
+	nr <<= 1;
+
+	/* something wrong ? */
+	if (nr < 32)
+		nr = 32;
+
+	return nr;
+
+}
+
 static void assign_to_mp_irq(struct mp_config_intsrc *m,
 				    struct mp_config_intsrc *mp_irq)
 {
@@ -1259,9 +1282,12 @@ static int __init acpi_parse_madt_ioapic_entries(void)
 		return count;
 	}
 
+
+	nr_irqs = get_nr_irqs_via_madt();
+
 	count =
 	    acpi_table_parse_madt(ACPI_MADT_TYPE_INTERRUPT_OVERRIDE, acpi_parse_int_src_ovr,
-				  NR_IRQ_VECTORS);
+				  nr_irqs);
 	if (count < 0) {
 		printk(KERN_ERR PREFIX
 		       "Error parsing interrupt source overrides entry\n");
@@ -1281,7 +1307,7 @@ static int __init acpi_parse_madt_ioapic_entries(void)
 
 	count =
 	    acpi_table_parse_madt(ACPI_MADT_TYPE_NMI_SOURCE, acpi_parse_nmi_src,
-				  NR_IRQ_VECTORS);
+				  nr_irqs);
 	if (count < 0) {
 		printk(KERN_ERR PREFIX "Error parsing NMI SRC entry\n");
 		/* TBD: Cleanup to allow fallback to MPS */
diff --git a/include/asm-x86/mpspec.h b/include/asm-x86/mpspec.h
index 118da36..5daa0f4 100644
--- a/include/asm-x86/mpspec.h
+++ b/include/asm-x86/mpspec.h
@@ -59,6 +59,7 @@ extern void mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger,
 				   u32 gsi);
 extern void mp_config_acpi_legacy_irqs(void);
 extern int mp_register_gsi(u32 gsi, int edge_level, int active_high_low);
+extern int get_nr_irqs_via_madt(void);
 #ifdef CONFIG_X86_IO_APIC
 extern int mp_config_acpi_gsi(unsigned char number, unsigned int devfn, u8 pin,
 				u32 gsi, int triggering, int polarity);
-- 
1.5.4.5

[PATCH 25/33] x86: remove nr_irq_vectors

[Yinghai Lu]

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
---
 include/asm-x86/irq_vectors.h |    2 --
 1 files changed, 0 insertions(+), 2 deletions(-)

diff --git a/include/asm-x86/irq_vectors.h b/include/asm-x86/irq_vectors.h
index 0817a19..821ff99 100644
--- a/include/asm-x86/irq_vectors.h
+++ b/include/asm-x86/irq_vectors.h
@@ -127,8 +127,6 @@
 
 #endif /* VISWS */
 
-#define NR_IRQ_VECTORS		NR_IRQS
-
 /* Voyager specific defines */
 /* These define the CPIs we use in linux */
 #define VIC_CPI_LEVEL0			0
-- 
1.5.4.5

[PATCH 26/33] x86_64: use get_irq_desc together with dyn_array

[Yinghai Lu]

add CONFIG_HAVE_SPARSE_IRQ to for use condensed array
preallocate 32 irq_desc, and get_irq_desc will try to get more.


Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
---
 arch/Kconfig                        |    4 +
 arch/x86/Kconfig                    |    1 +
 arch/x86/kernel/io_apic_32.c        |   46 +++++++++---
 arch/x86/kernel/io_apic_64.c        |   75 +++++++++++++-------
 arch/x86/kernel/irq_32.c            |   24 ++++---
 arch/x86/kernel/irq_64.c            |   35 +++++----
 arch/x86/kernel/irqinit_64.c        |   10 ++-
 arch/x86/kernel/visws_quirks.c      |   30 +++++----
 arch/x86/mach-voyager/voyager_smp.c |    4 +-
 drivers/gpio/gpiolib.c              |    2 +-
 drivers/mfd/asic3.c                 |    4 +-
 drivers/mfd/htc-egpio.c             |    2 +-
 drivers/parisc/dino.c               |    6 +-
 drivers/parisc/eisa.c               |    4 +-
 drivers/parisc/gsc.c                |   12 ++-
 drivers/parisc/iosapic.c            |    4 +-
 drivers/parisc/superio.c            |    4 +-
 drivers/pcmcia/hd64465_ss.c         |   12 +++-
 drivers/xen/events.c                |    8 ++-
 include/linux/irq.h                 |   32 ++++++---
 kernel/irq/autoprobe.c              |   10 ++--
 kernel/irq/chip.c                   |   32 +++++----
 kernel/irq/handle.c                 |  136 +++++++++++++++++++++++++++++++---
 kernel/irq/manage.c                 |   35 +++++----
 kernel/irq/migration.c              |   14 ++--
 kernel/irq/proc.c                   |   36 +++++----
 kernel/irq/resend.c                 |    2 +-
 kernel/irq/spurious.c               |    5 +-
 28 files changed, 404 insertions(+), 185 deletions(-)

diff --git a/arch/Kconfig b/arch/Kconfig
index c1f9feb..b367622 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -105,3 +105,7 @@ config HAVE_CLK
 
 config HAVE_DYN_ARRAY
 	def_bool n
+
+config HAVE_SPARSE_IRQ
+	def_bool n
+
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index d30b101..0d3fb7d 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -34,6 +34,7 @@ config X86
 	select HAVE_GENERIC_DMA_COHERENT if X86_32
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
 	select HAVE_DYN_ARRAY
+	select HAVE_SPARSE_IRQ if X86_64
 
 config ARCH_DEFCONFIG
 	string
diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index a0ce64c..57a0f61 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -345,6 +345,7 @@ static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t cpumask)
 	struct irq_pin_list *entry = irq_2_pin + irq;
 	unsigned int apicid_value;
 	cpumask_t tmp;
+	struct irq_desc *desc;
 
 	cpus_and(tmp, cpumask, cpu_online_map);
 	if (cpus_empty(tmp))
@@ -365,7 +366,8 @@ static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t cpumask)
 			break;
 		entry = irq_2_pin + entry->next;
 	}
-	irq_desc[irq].affinity = cpumask;
+	desc = get_irq_desc(irq);
+	desc->affinity = cpumask;
 	spin_unlock_irqrestore(&ioapic_lock, flags);
 }
 
@@ -475,10 +477,12 @@ static inline void balance_irq(int cpu, int irq)
 static inline void rotate_irqs_among_cpus(unsigned long useful_load_threshold)
 {
 	int i, j;
+	struct irq_desc *desc;
 
 	for_each_online_cpu(i) {
 		for (j = 0; j < nr_irqs; j++) {
-			if (!irq_desc[j].action)
+			desc = get_irq_desc[j];
+			if (!desc->action)
 				continue;
 			/* Is it a significant load ?  */
 			if (IRQ_DELTA(CPU_TO_PACKAGEINDEX(i), j) <
@@ -505,6 +509,7 @@ static void do_irq_balance(void)
 	unsigned long tmp_cpu_irq;
 	unsigned long imbalance = 0;
 	cpumask_t allowed_mask, target_cpu_mask, tmp;
+	struct irq_desc *desc;
 
 	for_each_possible_cpu(i) {
 		int package_index;
@@ -515,7 +520,8 @@ static void do_irq_balance(void)
 		for (j = 0; j < nr_irqs; j++) {
 			unsigned long value_now, delta;
 			/* Is this an active IRQ or balancing disabled ? */
-			if (!irq_desc[j].action || irq_balancing_disabled(j))
+			desc = get_irq_desc[j];
+			if (!desc->action || irq_balancing_disabled(j))
 				continue;
 			if (package_index == i)
 				IRQ_DELTA(package_index, j) = 0;
@@ -609,7 +615,8 @@ tryanotherirq:
 	selected_irq = -1;
 	for (j = 0; j < nr_irqs; j++) {
 		/* Is this an active IRQ? */
-		if (!irq_desc[j].action)
+		desc = get_irq_desc[j];
+		if (!desc->action)
 			continue;
 		if (imbalance <= IRQ_DELTA(max_loaded, j))
 			continue;
@@ -682,10 +689,12 @@ static int balanced_irq(void *unused)
 	int i;
 	unsigned long prev_balance_time = jiffies;
 	long time_remaining = balanced_irq_interval;
+	struct irq_desc *desc;
 
 	/* push everything to CPU 0 to give us a starting point.  */
 	for (i = 0 ; i < nr_irqs ; i++) {
-		irq_desc[i].pending_mask = cpumask_of_cpu(0);
+		desc = get_irq_desc(i);
+		desc->pending_mask = cpumask_of_cpu(0);
 		set_pending_irq(i, cpumask_of_cpu(0));
 	}
 
@@ -1258,13 +1267,16 @@ static struct irq_chip ioapic_chip;
 
 static void ioapic_register_intr(int irq, int vector, unsigned long trigger)
 {
+	struct irq_desc *desc;
+
+	desc = get_irq_desc(irq);
 	if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
 	    trigger == IOAPIC_LEVEL) {
-		irq_desc[irq].status |= IRQ_LEVEL;
+		desc->status |= IRQ_LEVEL;
 		set_irq_chip_and_handler_name(irq, &ioapic_chip,
 					 handle_fasteoi_irq, "fasteoi");
 	} else {
-		irq_desc[irq].status &= ~IRQ_LEVEL;
+		desc->status &= ~IRQ_LEVEL;
 		set_irq_chip_and_handler_name(irq, &ioapic_chip,
 					 handle_edge_irq, "edge");
 	}
@@ -2031,6 +2043,7 @@ static struct irq_chip ioapic_chip __read_mostly = {
 static inline void init_IO_APIC_traps(void)
 {
 	int irq;
+	struct irq_desc *desc;
 
 	/*
 	 * NOTE! The local APIC isn't very good at handling
@@ -2052,9 +2065,11 @@ static inline void init_IO_APIC_traps(void)
 			 */
 			if (irq < 16)
 				make_8259A_irq(irq);
-			else
+			else {
+				desc = get_irq_desc(irq);
 				/* Strange. Oh, well.. */
-				irq_desc[irq].chip = &no_irq_chip;
+				desc->chip = &no_irq_chip;
+			}
 		}
 	}
 }
@@ -2093,7 +2108,10 @@ static struct irq_chip lapic_chip __read_mostly = {
 
 static void lapic_register_intr(int irq, int vector)
 {
-	irq_desc[irq].status &= ~IRQ_LEVEL;
+	struct irq_desc *desc;
+
+	desc = get_irq_desc(irq);
+	desc->status &= ~IRQ_LEVEL;
 	set_irq_chip_and_handler_name(irq, &lapic_chip, handle_edge_irq,
 				      "edge");
 	set_intr_gate(vector, interrupt[irq]);
@@ -2560,6 +2578,7 @@ static void set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
 	unsigned int dest;
 	cpumask_t tmp;
 	int vector;
+	struct irq_desc *desc;
 
 	cpus_and(tmp, mask, cpu_online_map);
 	if (cpus_empty(tmp))
@@ -2579,7 +2598,8 @@ static void set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
 	msg.address_lo |= MSI_ADDR_DEST_ID(dest);
 
 	write_msi_msg(irq, &msg);
-	irq_desc[irq].affinity = mask;
+	desc = get_irq_desc(irq);
+	desc->affinity = mask;
 }
 #endif /* CONFIG_SMP */
 
@@ -2653,6 +2673,7 @@ static void set_ht_irq_affinity(unsigned int irq, cpumask_t mask)
 {
 	unsigned int dest;
 	cpumask_t tmp;
+	struct irq_desc *desc;
 
 	cpus_and(tmp, mask, cpu_online_map);
 	if (cpus_empty(tmp))
@@ -2663,7 +2684,8 @@ static void set_ht_irq_affinity(unsigned int irq, cpumask_t mask)
 	dest = cpu_mask_to_apicid(mask);
 
 	target_ht_irq(irq, dest);
-	irq_desc[irq].affinity = mask;
+	desc = get_irq_desc(irq);
+	desc->affinity = mask;
 }
 #endif
 
diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
index 9bcb6c2..3734216 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -345,6 +345,7 @@ static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t mask)
 	unsigned long flags;
 	unsigned int dest;
 	cpumask_t tmp;
+	struct irq_desc *desc;
 
 	cpus_and(tmp, mask, cpu_online_map);
 	if (cpus_empty(tmp))
@@ -361,9 +362,10 @@ static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t mask)
 	 */
 	dest = SET_APIC_LOGICAL_ID(dest);
 
+	desc = get_irq_desc(irq);
 	spin_lock_irqsave(&ioapic_lock, flags);
 	__target_IO_APIC_irq(irq, dest, cfg->vector);
-	irq_desc[irq].affinity = mask;
+	desc->affinity = mask;
 	spin_unlock_irqrestore(&ioapic_lock, flags);
 }
 #endif
@@ -928,14 +930,17 @@ static struct irq_chip ir_ioapic_chip;
 
 static void ioapic_register_intr(int irq, unsigned long trigger)
 {
+	struct irq_desc *desc;
+
+	desc = get_irq_desc(irq);
 	if (trigger)
-		irq_desc[irq].status |= IRQ_LEVEL;
+		desc->status |= IRQ_LEVEL;
 	else
-		irq_desc[irq].status &= ~IRQ_LEVEL;
+		desc->status &= ~IRQ_LEVEL;
 
 #ifdef CONFIG_INTR_REMAP
 	if (irq_remapped(irq)) {
-		irq_desc[irq].status |= IRQ_MOVE_PCNTXT;
+		desc->status |= IRQ_MOVE_PCNTXT;
 		if (trigger)
 			set_irq_chip_and_handler_name(irq, &ir_ioapic_chip,
 						      handle_fasteoi_irq,
@@ -1593,10 +1598,10 @@ static DECLARE_DELAYED_WORK(ir_migration_work, ir_irq_migration);
 static void migrate_ioapic_irq(int irq, cpumask_t mask)
 {
 	struct irq_cfg *cfg = irq_cfg + irq;
-	struct irq_desc *desc = irq_desc + irq;
+	struct irq_desc *desc;
 	cpumask_t tmp, cleanup_mask;
 	struct irte irte;
-	int modify_ioapic_rte = desc->status & IRQ_LEVEL;
+	int modify_ioapic_rte;
 	unsigned int dest;
 	unsigned long flags;
 
@@ -1613,6 +1618,8 @@ static void migrate_ioapic_irq(int irq, cpumask_t mask)
 	cpus_and(tmp, cfg->domain, mask);
 	dest = cpu_mask_to_apicid(tmp);
 
+	desc = get_irq_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);
@@ -1634,12 +1641,13 @@ static void migrate_ioapic_irq(int irq, cpumask_t mask)
 		cfg->move_in_progress = 0;
 	}
 
-	irq_desc[irq].affinity = mask;
+	desc->affinity = mask;
 }
 
 static int migrate_irq_remapped_level(int irq)
 {
 	int ret = -1;
+	struct irq_desc *desc = get_irq_desc(irq);
 
 	mask_IO_APIC_irq(irq);
 
@@ -1655,11 +1663,11 @@ static int migrate_irq_remapped_level(int irq)
 	}
 
 	/* everthing is clear. we have right of way */
-	migrate_ioapic_irq(irq, irq_desc[irq].pending_mask);
+	migrate_ioapic_irq(irq, desc->pending_mask);
 
 	ret = 0;
-	irq_desc[irq].status &= ~IRQ_MOVE_PENDING;
-	cpus_clear(irq_desc[irq].pending_mask);
+	desc->status &= ~IRQ_MOVE_PENDING;
+	cpus_clear(desc->pending_mask);
 
 unmask:
 	unmask_IO_APIC_irq(irq);
@@ -1671,7 +1679,7 @@ static void ir_irq_migration(struct work_struct *work)
 	int irq;
 
 	for (irq = 0; irq < nr_irqs; irq++) {
-		struct irq_desc *desc = irq_desc + irq;
+		struct irq_desc *desc = get_irq_desc(irq);
 		if (desc->status & IRQ_MOVE_PENDING) {
 			unsigned long flags;
 
@@ -1683,8 +1691,7 @@ static void ir_irq_migration(struct work_struct *work)
 				continue;
 			}
 
-			desc->chip->set_affinity(irq,
-					         irq_desc[irq].pending_mask);
+			desc->chip->set_affinity(irq, desc->pending_mask);
 			spin_unlock_irqrestore(&desc->lock, flags);
 		}
 	}
@@ -1695,9 +1702,11 @@ static void ir_irq_migration(struct work_struct *work)
  */
 static void set_ir_ioapic_affinity_irq(unsigned int irq, cpumask_t mask)
 {
-	if (irq_desc[irq].status & IRQ_LEVEL) {
-		irq_desc[irq].status |= IRQ_MOVE_PENDING;
-		irq_desc[irq].pending_mask = mask;
+	struct irq_desc *desc = get_irq_desc(irq);
+
+	if (desc->status & IRQ_LEVEL) {
+		desc->status |= IRQ_MOVE_PENDING;
+		desc->pending_mask = mask;
 		migrate_irq_remapped_level(irq);
 		return;
 	}
@@ -1722,7 +1731,7 @@ asmlinkage void smp_irq_move_cleanup_interrupt(void)
 		if (irq >= nr_irqs)
 			continue;
 
-		desc = irq_desc + irq;
+		desc = get_irq_desc(irq);
 		cfg = irq_cfg + irq;
 		spin_lock(&desc->lock);
 		if (!cfg->move_cleanup_count)
@@ -1788,7 +1797,7 @@ static void ack_apic_level(unsigned int irq)
 	irq_complete_move(irq);
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	/* If we are moving the irq we need to mask it */
-	if (unlikely(irq_desc[irq].status & IRQ_MOVE_PENDING)) {
+	if (unlikely(get_irq_desc(irq)->status & IRQ_MOVE_PENDING)) {
 		do_unmask_irq = 1;
 		mask_IO_APIC_irq(irq);
 	}
@@ -1865,6 +1874,7 @@ static struct irq_chip ir_ioapic_chip __read_mostly = {
 static inline void init_IO_APIC_traps(void)
 {
 	int irq;
+	struct irq_desc *desc;
 
 	/*
 	 * NOTE! The local APIC isn't very good at handling
@@ -1886,9 +1896,11 @@ static inline void init_IO_APIC_traps(void)
 			 */
 			if (irq < 16)
 				make_8259A_irq(irq);
-			else
+			else {
+				desc = get_irq_desc(irq);
 				/* Strange. Oh, well.. */
-				irq_desc[irq].chip = &no_irq_chip;
+				desc->chip = &no_irq_chip;
+			}
 		}
 	}
 }
@@ -1923,7 +1935,10 @@ static struct irq_chip lapic_chip __read_mostly = {
 
 static void lapic_register_intr(int irq)
 {
-	irq_desc[irq].status &= ~IRQ_LEVEL;
+	struct irq_desc *desc;
+
+	desc = get_irq_desc(irq);
+	desc->status &= ~IRQ_LEVEL;
 	set_irq_chip_and_handler_name(irq, &lapic_chip, handle_edge_irq,
 				      "edge");
 }
@@ -2399,6 +2414,7 @@ static void set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
 	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))
@@ -2418,7 +2434,8 @@ static void set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
 	msg.address_lo |= MSI_ADDR_DEST_ID(dest);
 
 	write_msi_msg(irq, &msg);
-	irq_desc[irq].affinity = mask;
+	desc = get_irq_desc(irq);
+	desc->affinity = mask;
 }
 
 #ifdef CONFIG_INTR_REMAP
@@ -2432,6 +2449,7 @@ static void ir_set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
 	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))
@@ -2466,7 +2484,8 @@ static void ir_set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
 		cfg->move_in_progress = 0;
 	}
 
-	irq_desc[irq].affinity = mask;
+	desc = get_irq_desc(irq);
+	desc->affinity = mask;
 }
 #endif
 #endif /* CONFIG_SMP */
@@ -2540,7 +2559,7 @@ static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc, int irq)
 
 #ifdef CONFIG_INTR_REMAP
 	if (irq_remapped(irq)) {
-		struct irq_desc *desc = irq_desc + irq;
+		struct irq_desc *desc = get_irq_desc(irq);
 		/*
 		 * irq migration in process context
 		 */
@@ -2652,6 +2671,7 @@ static void dmar_msi_set_affinity(unsigned int irq, cpumask_t mask)
 	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))
@@ -2671,7 +2691,8 @@ static void dmar_msi_set_affinity(unsigned int irq, cpumask_t mask)
 	msg.address_lo |= MSI_ADDR_DEST_ID(dest);
 
 	dmar_msi_write(irq, &msg);
-	irq_desc[irq].affinity = mask;
+	desc = get_irq_desc(irq);
+	desc->affinity = mask;
 }
 #endif /* CONFIG_SMP */
 
@@ -2728,6 +2749,7 @@ static void set_ht_irq_affinity(unsigned int irq, cpumask_t mask)
 	struct irq_cfg *cfg = irq_cfg + irq;
 	unsigned int dest;
 	cpumask_t tmp;
+	struct irq_desc *desc;
 
 	cpus_and(tmp, mask, cpu_online_map);
 	if (cpus_empty(tmp))
@@ -2740,7 +2762,8 @@ static void set_ht_irq_affinity(unsigned int irq, cpumask_t mask)
 	dest = cpu_mask_to_apicid(tmp);
 
 	target_ht_irq(irq, dest, cfg->vector);
-	irq_desc[irq].affinity = mask;
+	desc = get_irq_desc(irq);
+	desc->affinity = mask;
 }
 #endif
 
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 0cff2f4..6bad8a2 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -224,7 +224,7 @@ unsigned int do_IRQ(struct pt_regs *regs)
 	struct pt_regs *old_regs;
 	/* high bit used in ret_from_ code */
 	int overflow, irq = ~regs->orig_ax;
-	struct irq_desc *desc = irq_desc + irq;
+	struct irq_desc *desc = get_irq_desc(irq);
 
 	if (unlikely((unsigned)irq >= nr_irqs)) {
 		printk(KERN_EMERG "%s: cannot handle IRQ %d\n",
@@ -273,15 +273,16 @@ int show_interrupts(struct seq_file *p, void *v)
 
 	if (i < nr_irqs) {
 		unsigned any_count = 0;
+		struct irq_desc *desc = get_irq_desc(i);
 
-		spin_lock_irqsave(&irq_desc[i].lock, flags);
+		spin_lock_irqsave(&desc->lock, flags);
 #ifndef CONFIG_SMP
 		any_count = kstat_irqs(i);
 #else
 		for_each_online_cpu(j)
 			any_count |= kstat_cpu(j).irqs[i];
 #endif
-		action = irq_desc[i].action;
+		action = desc->action;
 		if (!action && !any_count)
 			goto skip;
 		seq_printf(p, "%3d: ",i);
@@ -291,8 +292,8 @@ int show_interrupts(struct seq_file *p, void *v)
 		for_each_online_cpu(j)
 			seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
 #endif
-		seq_printf(p, " %8s", irq_desc[i].chip->name);
-		seq_printf(p, "-%-8s", irq_desc[i].name);
+		seq_printf(p, " %8s", desc->chip->name);
+		seq_printf(p, "-%-8s", desc->name);
 
 		if (action) {
 			seq_printf(p, "  %s", action->name);
@@ -302,7 +303,7 @@ int show_interrupts(struct seq_file *p, void *v)
 
 		seq_putc(p, '\n');
 skip:
-		spin_unlock_irqrestore(&irq_desc[i].lock, flags);
+		spin_unlock_irqrestore(&desc->lock, flags);
 	} else if (i == nr_irqs) {
 		seq_printf(p, "NMI: ");
 		for_each_online_cpu(j)
@@ -398,17 +399,20 @@ void fixup_irqs(cpumask_t map)
 
 	for (irq = 0; irq < nr_irqs; irq++) {
 		cpumask_t mask;
+		struct irq_desc *desc;
+
 		if (irq == 2)
 			continue;
 
-		cpus_and(mask, irq_desc[irq].affinity, map);
+		desc = get_irq_desc(irq);
+		cpus_and(mask, desc->affinity, map);
 		if (any_online_cpu(mask) == NR_CPUS) {
 			printk("Breaking affinity for irq %i\n", irq);
 			mask = map;
 		}
-		if (irq_desc[irq].chip->set_affinity)
-			irq_desc[irq].chip->set_affinity(irq, mask);
-		else if (irq_desc[irq].action && !(warned++))
+		if (desc->chip->set_affinity)
+			desc->chip->set_affinity(irq, mask);
+		else if (desc->action && !(warned++))
 			printk("Cannot set affinity for irq %i\n", irq);
 	}
 
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index de94c60..cf5524b 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -83,15 +83,16 @@ int show_interrupts(struct seq_file *p, void *v)
 
 	if (i < nr_irqs) {
 		unsigned any_count = 0;
+		struct irq_desc *desc = get_irq_desc(i);
 
-		spin_lock_irqsave(&irq_desc[i].lock, flags);
+		spin_lock_irqsave(&desc->lock, flags);
 #ifndef CONFIG_SMP
 		any_count = kstat_irqs(i);
 #else
 		for_each_online_cpu(j)
 			any_count |= kstat_cpu(j).irqs[i];
 #endif
-		action = irq_desc[i].action;
+		action = desc->action;
 		if (!action && !any_count)
 			goto skip;
 		seq_printf(p, "%3d: ",i);
@@ -101,8 +102,8 @@ int show_interrupts(struct seq_file *p, void *v)
 		for_each_online_cpu(j)
 			seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
 #endif
-		seq_printf(p, " %8s", irq_desc[i].chip->name);
-		seq_printf(p, "-%-8s", irq_desc[i].name);
+		seq_printf(p, " %8s", desc->chip->name);
+		seq_printf(p, "-%-8s", desc->name);
 
 		if (action) {
 			seq_printf(p, "  %s", action->name);
@@ -111,7 +112,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		}
 		seq_putc(p, '\n');
 skip:
-		spin_unlock_irqrestore(&irq_desc[i].lock, flags);
+		spin_unlock_irqrestore(&desc->lock, flags);
 	} else if (i == nr_irqs) {
 		seq_printf(p, "NMI: ");
 		for_each_online_cpu(j)
@@ -228,37 +229,39 @@ void fixup_irqs(cpumask_t map)
 		cpumask_t mask;
 		int break_affinity = 0;
 		int set_affinity = 1;
+		struct irq_desc *desc;
 
 		if (irq == 2)
 			continue;
 
+		desc = get_irq_desc(irq);
 		/* interrupt's are disabled at this point */
-		spin_lock(&irq_desc[irq].lock);
+		spin_lock(&desc->lock);
 
 		if (!irq_has_action(irq) ||
-		    cpus_equal(irq_desc[irq].affinity, map)) {
-			spin_unlock(&irq_desc[irq].lock);
+		    cpus_equal(desc->affinity, map)) {
+			spin_unlock(&desc->lock);
 			continue;
 		}
 
-		cpus_and(mask, irq_desc[irq].affinity, map);
+		cpus_and(mask, desc->affinity, map);
 		if (cpus_empty(mask)) {
 			break_affinity = 1;
 			mask = map;
 		}
 
-		if (irq_desc[irq].chip->mask)
-			irq_desc[irq].chip->mask(irq);
+		if (desc->chip->mask)
+			desc->chip->mask(irq);
 
-		if (irq_desc[irq].chip->set_affinity)
-			irq_desc[irq].chip->set_affinity(irq, mask);
+		if (desc->chip->set_affinity)
+			desc->chip->set_affinity(irq, mask);
 		else if (!(warned++))
 			set_affinity = 0;
 
-		if (irq_desc[irq].chip->unmask)
-			irq_desc[irq].chip->unmask(irq);
+		if (desc->chip->unmask)
+			desc->chip->unmask(irq);
 
-		spin_unlock(&irq_desc[irq].lock);
+		spin_unlock(&desc->lock);
 
 		if (break_affinity && set_affinity)
 			printk("Broke affinity for irq %i\n", irq);
diff --git a/arch/x86/kernel/irqinit_64.c b/arch/x86/kernel/irqinit_64.c
index 48674e6..8a7a5a8 100644
--- a/arch/x86/kernel/irqinit_64.c
+++ b/arch/x86/kernel/irqinit_64.c
@@ -143,9 +143,11 @@ static void __init init_ISA_irqs (void)
 	init_8259A(0);
 
 	for (i = 0; i < nr_irqs; i++) {
-		irq_desc[i].status = IRQ_DISABLED;
-		irq_desc[i].action = NULL;
-		irq_desc[i].depth = 1;
+		struct irq_desc *desc = get_irq_desc(i);
+
+		desc->status = IRQ_DISABLED;
+		desc->action = NULL;
+		desc->depth = 1;
 
 		if (i < 16) {
 			/*
@@ -157,7 +159,7 @@ static void __init init_ISA_irqs (void)
 			/*
 			 * 'high' PCI IRQs filled in on demand
 			 */
-			irq_desc[i].chip = &no_irq_chip;
+			desc->chip = &no_irq_chip;
 		}
 	}
 }
diff --git a/arch/x86/kernel/visws_quirks.c b/arch/x86/kernel/visws_quirks.c
index 3059eb4..cd6f273 100644
--- a/arch/x86/kernel/visws_quirks.c
+++ b/arch/x86/kernel/visws_quirks.c
@@ -486,10 +486,11 @@ static void disable_cobalt_irq(unsigned int irq)
 static unsigned int startup_cobalt_irq(unsigned int irq)
 {
 	unsigned long flags;
+	struct irq_desc *desc = get_irq_desc(irq);
 
 	spin_lock_irqsave(&cobalt_lock, flags);
-	if ((irq_desc[irq].status & (IRQ_DISABLED | IRQ_INPROGRESS | IRQ_WAITING)))
-		irq_desc[irq].status &= ~(IRQ_DISABLED | IRQ_INPROGRESS | IRQ_WAITING);
+	if ((desc->status & (IRQ_DISABLED | IRQ_INPROGRESS | IRQ_WAITING)))
+		desc->status &= ~(IRQ_DISABLED | IRQ_INPROGRESS | IRQ_WAITING);
 	enable_cobalt_irq(irq);
 	spin_unlock_irqrestore(&cobalt_lock, flags);
 	return 0;
@@ -508,9 +509,10 @@ static void ack_cobalt_irq(unsigned int irq)
 static void end_cobalt_irq(unsigned int irq)
 {
 	unsigned long flags;
+	struct irq_desc *desc = get_irq_desc(irq);
 
 	spin_lock_irqsave(&cobalt_lock, flags);
-	if (!(irq_desc[irq].status & (IRQ_DISABLED | IRQ_INPROGRESS)))
+	if (!(desc->status & (IRQ_DISABLED | IRQ_INPROGRESS)))
 		enable_cobalt_irq(irq);
 	spin_unlock_irqrestore(&cobalt_lock, flags);
 }
@@ -628,7 +630,7 @@ static irqreturn_t piix4_master_intr(int irq, void *dev_id)
 
 	spin_unlock_irqrestore(&i8259A_lock, flags);
 
-	desc = irq_desc + realirq;
+	desc = get_irq_desc(realirq);
 
 	/*
 	 * handle this 'virtual interrupt' as a Cobalt one now.
@@ -664,27 +666,29 @@ void init_VISWS_APIC_irqs(void)
 	int i;
 
 	for (i = 0; i < CO_IRQ_APIC0 + CO_APIC_LAST + 1; i++) {
-		irq_desc[i].status = IRQ_DISABLED;
-		irq_desc[i].action = 0;
-		irq_desc[i].depth = 1;
+		struct irq_desc *desc = get_irq_desc(i);
+
+		desc->status = IRQ_DISABLED;
+		desc->action = 0;
+		desc->depth = 1;
 
 		if (i == 0) {
-			irq_desc[i].chip = &cobalt_irq_type;
+			desc->chip = &cobalt_irq_type;
 		}
 		else if (i == CO_IRQ_IDE0) {
-			irq_desc[i].chip = &cobalt_irq_type;
+			desc->chip = &cobalt_irq_type;
 		}
 		else if (i == CO_IRQ_IDE1) {
-			irq_desc[i].chip = &cobalt_irq_type;
+			desc->chip = &cobalt_irq_type;
 		}
 		else if (i == CO_IRQ_8259) {
-			irq_desc[i].chip = &piix4_master_irq_type;
+			desc->chip = &piix4_master_irq_type;
 		}
 		else if (i < CO_IRQ_APIC0) {
-			irq_desc[i].chip = &piix4_virtual_irq_type;
+			desc->chip = &piix4_virtual_irq_type;
 		}
 		else if (IS_CO_APIC(i)) {
-			irq_desc[i].chip = &cobalt_irq_type;
+			desc->chip = &cobalt_irq_type;
 		}
 	}
 
diff --git a/arch/x86/mach-voyager/voyager_smp.c b/arch/x86/mach-voyager/voyager_smp.c
index ee0fba0..cdf9092 100644
--- a/arch/x86/mach-voyager/voyager_smp.c
+++ b/arch/x86/mach-voyager/voyager_smp.c
@@ -1481,7 +1481,7 @@ static void disable_local_vic_irq(unsigned int irq)
  * the interrupt off to another CPU */
 static void before_handle_vic_irq(unsigned int irq)
 {
-	irq_desc_t *desc = irq_desc + irq;
+	irq_desc_t *desc = get_irq_desc(irq);
 	__u8 cpu = smp_processor_id();
 
 	_raw_spin_lock(&vic_irq_lock);
@@ -1516,7 +1516,7 @@ static void before_handle_vic_irq(unsigned int irq)
 /* Finish the VIC interrupt: basically mask */
 static void after_handle_vic_irq(unsigned int irq)
 {
-	irq_desc_t *desc = irq_desc + irq;
+	irq_desc_t *desc = get_irq_desc(irq);
 
 	_raw_spin_lock(&vic_irq_lock);
 	{
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 8d29405..8af2a4d 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -1058,7 +1058,7 @@ static void gpiolib_dbg_show(struct seq_file *s, struct gpio_chip *chip)
 
 		if (!is_out) {
 			int		irq = gpio_to_irq(gpio);
-			struct irq_desc	*desc = irq_desc + irq;
+			struct irq_desc	*desc = get_irq_desc(irq);
 
 			/* This races with request_irq(), set_irq_type(),
 			 * and set_irq_wake() ... but those are "rare".
diff --git a/drivers/mfd/asic3.c b/drivers/mfd/asic3.c
index c6408a6..f3b5f24 100644
--- a/drivers/mfd/asic3.c
+++ b/drivers/mfd/asic3.c
@@ -124,7 +124,7 @@ static void asic3_irq_demux(unsigned int irq, struct irq_desc *desc)
 					irqnr = asic->irq_base +
 						(ASIC3_GPIOS_PER_BANK * bank)
 						+ i;
-					desc = irq_desc + irqnr;
+					desc = get_irq_desc(irqnr);
 					desc->handle_irq(irqnr, desc);
 					if (asic->irq_bothedge[bank] & bit)
 						asic3_irq_flip_edge(asic, base,
@@ -137,7 +137,7 @@ static void asic3_irq_demux(unsigned int irq, struct irq_desc *desc)
 		for (i = ASIC3_NUM_GPIOS; i < ASIC3_NR_IRQS; i++) {
 			/* They start at bit 4 and go up */
 			if (status & (1 << (i - ASIC3_NUM_GPIOS + 4))) {
-				desc = irq_desc + asic->irq_base + i;
+				desc = get_irq_desc(asic->irq_base + i);
 				desc->handle_irq(asic->irq_base + i,
 						 desc);
 			}
diff --git a/drivers/mfd/htc-egpio.c b/drivers/mfd/htc-egpio.c
index 6be4317..1991fea 100644
--- a/drivers/mfd/htc-egpio.c
+++ b/drivers/mfd/htc-egpio.c
@@ -112,7 +112,7 @@ static void egpio_handler(unsigned int irq, struct irq_desc *desc)
 		/* Run irq handler */
 		pr_debug("got IRQ %d\n", irqpin);
 		irq = ei->irq_start + irqpin;
-		desc = &irq_desc[irq];
+		desc = get_irq_desc(irq);
 		desc->handle_irq(irq, desc);
 	}
 }
diff --git a/drivers/parisc/dino.c b/drivers/parisc/dino.c
index fd56128..224567f 100644
--- a/drivers/parisc/dino.c
+++ b/drivers/parisc/dino.c
@@ -298,7 +298,8 @@ struct pci_port_ops dino_port_ops = {
 
 static void dino_disable_irq(unsigned int irq)
 {
-	struct dino_device *dino_dev = irq_desc[irq].chip_data;
+	struct irq_desc *desc = get_irq_desc(irq);
+	struct dino_device *dino_dev = desc->chip_data;
 	int local_irq = gsc_find_local_irq(irq, dino_dev->global_irq, DINO_LOCAL_IRQS);
 
 	DBG(KERN_WARNING "%s(0x%p, %d)\n", __func__, dino_dev, irq);
@@ -310,7 +311,8 @@ static void dino_disable_irq(unsigned int irq)
 
 static void dino_enable_irq(unsigned int irq)
 {
-	struct dino_device *dino_dev = irq_desc[irq].chip_data;
+	struct irq_desc *desc = get_irq_desc(irq);
+	struct dino_device *dino_dev = desc->chip_data;
 	int local_irq = gsc_find_local_irq(irq, dino_dev->global_irq, DINO_LOCAL_IRQS);
 	u32 tmp;
 
diff --git a/drivers/parisc/eisa.c b/drivers/parisc/eisa.c
index 771cef5..cee63d8 100644
--- a/drivers/parisc/eisa.c
+++ b/drivers/parisc/eisa.c
@@ -346,10 +346,10 @@ static int __init eisa_probe(struct parisc_device *dev)
 	}
 	
 	/* Reserve IRQ2 */
-	irq_desc[2].action = &irq2_action;
+	get_irq_desc(2)->action = &irq2_action;
 	
 	for (i = 0; i < 16; i++) {
-		irq_desc[i].chip = &eisa_interrupt_type;
+		get_irq_desc(i)->chip = &eisa_interrupt_type;
 	}
 	
 	EISA_bus = 1;
diff --git a/drivers/parisc/gsc.c b/drivers/parisc/gsc.c
index f7d088b..e1dfea8 100644
--- a/drivers/parisc/gsc.c
+++ b/drivers/parisc/gsc.c
@@ -108,7 +108,8 @@ int gsc_find_local_irq(unsigned int irq, int *global_irqs, int limit)
 
 static void gsc_asic_disable_irq(unsigned int irq)
 {
-	struct gsc_asic *irq_dev = irq_desc[irq].chip_data;
+	struct irq_desc *desc = get_irq_desc(irq);
+	struct gsc_asic *irq_dev = desc->chip_data;
 	int local_irq = gsc_find_local_irq(irq, irq_dev->global_irq, 32);
 	u32 imr;
 
@@ -123,7 +124,8 @@ static void gsc_asic_disable_irq(unsigned int irq)
 
 static void gsc_asic_enable_irq(unsigned int irq)
 {
-	struct gsc_asic *irq_dev = irq_desc[irq].chip_data;
+	struct irq_desc *desc = get_irq_desc(irq);
+	struct gsc_asic *irq_dev = desc->chip_data;
 	int local_irq = gsc_find_local_irq(irq, irq_dev->global_irq, 32);
 	u32 imr;
 
@@ -159,12 +161,14 @@ static struct hw_interrupt_type gsc_asic_interrupt_type = {
 int gsc_assign_irq(struct hw_interrupt_type *type, void *data)
 {
 	static int irq = GSC_IRQ_BASE;
+	struct irq_desc *desc;
 
 	if (irq > GSC_IRQ_MAX)
 		return NO_IRQ;
 
-	irq_desc[irq].chip = type;
-	irq_desc[irq].chip_data = data;
+	desc = get_irq_desc(irq);
+	desc->chip = type;
+	desc->chip_data = data;
 	return irq++;
 }
 
diff --git a/drivers/parisc/iosapic.c b/drivers/parisc/iosapic.c
index 6fb3f79..cb50d6b 100644
--- a/drivers/parisc/iosapic.c
+++ b/drivers/parisc/iosapic.c
@@ -619,7 +619,9 @@ iosapic_set_irt_data( struct vector_info *vi, u32 *dp0, u32 *dp1)
 
 static struct vector_info *iosapic_get_vector(unsigned int irq)
 {
-	return irq_desc[irq].chip_data;
+	struct irq_desc *desc = get_irq_desc(irq);
+
+	return desc->chip_data;
 }
 
 static void iosapic_disable_irq(unsigned int irq)
diff --git a/drivers/parisc/superio.c b/drivers/parisc/superio.c
index 1e8d2d1..1463728 100644
--- a/drivers/parisc/superio.c
+++ b/drivers/parisc/superio.c
@@ -363,7 +363,9 @@ int superio_fixup_irq(struct pci_dev *pcidev)
 #endif
 
 	for (i = 0; i < 16; i++) {
-		irq_desc[i].chip = &superio_interrupt_type;
+		struct irq_desc *desc = get_irq_desc(i);
+
+		desc->chip = &superio_interrupt_type;
 	}
 
 	/*
diff --git a/drivers/pcmcia/hd64465_ss.c b/drivers/pcmcia/hd64465_ss.c
index fb2bc1f..a02378e 100644
--- a/drivers/pcmcia/hd64465_ss.c
+++ b/drivers/pcmcia/hd64465_ss.c
@@ -234,15 +234,18 @@ static struct hw_interrupt_type hd64465_ss_irq_type = {
  */
 static void hs_map_irq(hs_socket_t *sp, unsigned int irq)
 {
+	struct irq_desc *desc;
+
     	DPRINTK("hs_map_irq(sock=%d irq=%d)\n", sp->number, irq);
 	
 	if (irq >= HS_NUM_MAPPED_IRQS)
 	    return;
 
+	desc = get_irq_desc(irq);
     	hs_mapped_irq[irq].sock = sp;
 	/* insert ourselves as the irq controller */
-	hs_mapped_irq[irq].old_handler = irq_desc[irq].chip;
-	irq_desc[irq].chip = &hd64465_ss_irq_type;
+	hs_mapped_irq[irq].old_handler = desc->chip;
+	desc->chip = &hd64465_ss_irq_type;
 }
 
 
@@ -251,13 +254,16 @@ static void hs_map_irq(hs_socket_t *sp, unsigned int irq)
  */
 static void hs_unmap_irq(hs_socket_t *sp, unsigned int irq)
 {
+	struct irq_desc *desc;
+
     	DPRINTK("hs_unmap_irq(sock=%d irq=%d)\n", sp->number, irq);
 	
 	if (irq >= HS_NUM_MAPPED_IRQS)
 	    return;
 		
+	desc = get_irq_desc(irq);
 	/* restore the original irq controller */
-	irq_desc[irq].chip = hs_mapped_irq[irq].old_handler;
+	desc->chip = hs_mapped_irq[irq].old_handler;
 }
 
 /*============================================================*/
diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index 8e329c2..faf1235 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -125,7 +125,7 @@ static void bind_evtchn_to_cpu(unsigned int chn, unsigned int cpu)
 
 	BUG_ON(irq == -1);
 #ifdef CONFIG_SMP
-	irq_desc[irq].affinity = cpumask_of_cpu(cpu);
+	get_irq_desc(irq)->affinity = cpumask_of_cpu(cpu);
 #endif
 
 	__clear_bit(chn, cpu_evtchn_mask[cpu_evtchn[chn]]);
@@ -139,8 +139,10 @@ static void init_evtchn_cpu_bindings(void)
 #ifdef CONFIG_SMP
 	int i;
 	/* By default all event channels notify CPU#0. */
-	for (i = 0; i < nr_irqs; i++)
-		irq_desc[i].affinity = cpumask_of_cpu(0);
+	for (i = 0; i < nr_irqs; i++) {
+		struct irq_desc *desc = get_irq_desc(i);
+		desc->affinity = cpumask_of_cpu(0);
+	}
 #endif
 
 	memset(cpu_evtchn, 0, sizeof(cpu_evtchn));
diff --git a/include/linux/irq.h b/include/linux/irq.h
index c22e870..aaf2029 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -154,6 +154,10 @@ struct irq_chip {
  * @name:		flow handler name for /proc/interrupts output
  */
 struct irq_desc {
+	unsigned int		irq;
+#ifdef CONFIG_HAVE_SPARSE_IRQ
+	struct irq_desc		*next;
+#endif
 	irq_flow_handler_t	handle_irq;
 	struct irq_chip		*chip;
 	struct msi_desc		*msi_desc;
@@ -181,9 +185,9 @@ struct irq_desc {
 	const char		*name;
 } ____cacheline_internodealigned_in_smp;
 
-#ifdef CONFIG_HAVE_DYN_ARRAY
-extern struct irq_desc *irq_desc;
-#else
+extern struct irq_desc *get_irq_desc(unsigned int irq);
+#ifndef CONFIG_HAVE_DYN_ARRAY
+/* could be removed if we get rid of all irq_desc reference */
 extern struct irq_desc irq_desc[NR_IRQS];
 #endif
 
@@ -251,7 +255,10 @@ extern int no_irq_affinity;
 
 static inline int irq_balancing_disabled(unsigned int irq)
 {
-	return irq_desc[irq].status & IRQ_NO_BALANCING_MASK;
+	struct irq_desc *desc;
+
+	desc = get_irq_desc(irq);
+	return desc->status & IRQ_NO_BALANCING_MASK;
 }
 
 /* Handle irq action chains: */
@@ -283,7 +290,7 @@ extern unsigned int __do_IRQ(unsigned int irq);
  */
 static inline void generic_handle_irq(unsigned int irq)
 {
-	struct irq_desc *desc = irq_desc + irq;
+	struct irq_desc *desc = get_irq_desc(irq);
 
 #ifdef CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ
 	desc->handle_irq(irq, desc);
@@ -327,7 +334,10 @@ __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 static inline void __set_irq_handler_unlocked(int irq,
 					      irq_flow_handler_t handler)
 {
-	irq_desc[irq].handle_irq = handler;
+	struct irq_desc *desc;
+
+	desc = get_irq_desc(irq);
+	desc->handle_irq = handler;
 }
 
 /*
@@ -361,7 +371,7 @@ extern void destroy_irq(unsigned int irq);
 /* Test to see if a driver has successfully requested an irq */
 static inline int irq_has_action(unsigned int irq)
 {
-	struct irq_desc *desc = irq_desc + irq;
+	struct irq_desc *desc = get_irq_desc(irq);
 	return desc->action != NULL;
 }
 
@@ -376,10 +386,10 @@ extern int set_irq_chip_data(unsigned int irq, void *data);
 extern int set_irq_type(unsigned int irq, unsigned int type);
 extern int set_irq_msi(unsigned int irq, struct msi_desc *entry);
 
-#define get_irq_chip(irq)	(irq_desc[irq].chip)
-#define get_irq_chip_data(irq)	(irq_desc[irq].chip_data)
-#define get_irq_data(irq)	(irq_desc[irq].handler_data)
-#define get_irq_msi(irq)	(irq_desc[irq].msi_desc)
+#define get_irq_chip(irq)	(get_irq_desc(irq)->chip)
+#define get_irq_chip_data(irq)	(get_irq_desc(irq)->chip_data)
+#define get_irq_data(irq)	(get_irq_desc(irq)->handler_data)
+#define get_irq_msi(irq)	(get_irq_desc(irq)->msi_desc)
 
 #endif /* CONFIG_GENERIC_HARDIRQS */
 
diff --git a/kernel/irq/autoprobe.c b/kernel/irq/autoprobe.c
index c689e98..6d15cad 100644
--- a/kernel/irq/autoprobe.c
+++ b/kernel/irq/autoprobe.c
@@ -39,7 +39,7 @@ unsigned long probe_irq_on(void)
 	 * flush such a longstanding irq before considering it as spurious.
 	 */
 	for (i = nr_irqs-1; i > 0; i--) {
-		desc = irq_desc + i;
+		desc = get_irq_desc(i);
 
 		spin_lock_irq(&desc->lock);
 		if (!desc->action && !(desc->status & IRQ_NOPROBE)) {
@@ -69,7 +69,7 @@ unsigned long probe_irq_on(void)
 	 * happened in the previous stage, it may have masked itself)
 	 */
 	for (i = nr_irqs-1; i > 0; i--) {
-		desc = irq_desc + i;
+		desc = get_irq_desc(i);
 
 		spin_lock_irq(&desc->lock);
 		if (!desc->action && !(desc->status & IRQ_NOPROBE)) {
@@ -92,7 +92,7 @@ unsigned long probe_irq_on(void)
 	for (i = 0; i < nr_irqs; i++) {
 		unsigned int status;
 
-		desc = irq_desc + i;
+		desc = get_irq_desc(i);
 		spin_lock_irq(&desc->lock);
 		status = desc->status;
 
@@ -131,7 +131,7 @@ unsigned int probe_irq_mask(unsigned long val)
 
 	mask = 0;
 	for (i = 0; i < nr_irqs; i++) {
-		struct irq_desc *desc = irq_desc + i;
+		struct irq_desc *desc = get_irq_desc(i);
 		unsigned int status;
 
 		spin_lock_irq(&desc->lock);
@@ -174,7 +174,7 @@ int probe_irq_off(unsigned long val)
 	int i, irq_found = 0, nr_irqs = 0;
 
 	for (i = 0; i < nr_irqs; i++) {
-		struct irq_desc *desc = irq_desc + i;
+		struct irq_desc *desc = get_irq_desc(i);
 		unsigned int status;
 
 		spin_lock_irq(&desc->lock);
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 20a9307..df1222f 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -33,7 +33,7 @@ void dynamic_irq_init(unsigned int irq)
 	}
 
 	/* Ensure we don't have left over values from a previous use of this irq */
-	desc = irq_desc + irq;
+	desc = get_irq_desc(irq);
 	spin_lock_irqsave(&desc->lock, flags);
 	desc->status = IRQ_DISABLED;
 	desc->chip = &no_irq_chip;
@@ -65,7 +65,7 @@ void dynamic_irq_cleanup(unsigned int irq)
 		return;
 	}
 
-	desc = irq_desc + irq;
+	desc = get_irq_desc(irq);
 	spin_lock_irqsave(&desc->lock, flags);
 	if (desc->action) {
 		spin_unlock_irqrestore(&desc->lock, flags);
@@ -100,7 +100,7 @@ int set_irq_chip(unsigned int irq, struct irq_chip *chip)
 	if (!chip)
 		chip = &no_irq_chip;
 
-	desc = irq_desc + irq;
+	desc = get_irq_desc(irq);
 	spin_lock_irqsave(&desc->lock, flags);
 	irq_chip_set_defaults(chip);
 	desc->chip = chip;
@@ -126,7 +126,7 @@ int set_irq_type(unsigned int irq, unsigned int type)
 		return -ENODEV;
 	}
 
-	desc = irq_desc + irq;
+	desc = get_irq_desc(irq);
 	if (desc->chip->set_type) {
 		spin_lock_irqsave(&desc->lock, flags);
 		ret = desc->chip->set_type(irq, type);
@@ -154,7 +154,7 @@ int set_irq_data(unsigned int irq, void *data)
 		return -EINVAL;
 	}
 
-	desc = irq_desc + irq;
+	desc = get_irq_desc(irq);
 	spin_lock_irqsave(&desc->lock, flags);
 	desc->handler_data = data;
 	spin_unlock_irqrestore(&desc->lock, flags);
@@ -179,7 +179,7 @@ int set_irq_msi(unsigned int irq, struct msi_desc *entry)
 		       "Trying to install msi data for IRQ%d\n", irq);
 		return -EINVAL;
 	}
-	desc = irq_desc + irq;
+	desc = get_irq_desc(irq);
 	spin_lock_irqsave(&desc->lock, flags);
 	desc->msi_desc = entry;
 	if (entry)
@@ -197,9 +197,10 @@ int set_irq_msi(unsigned int irq, struct msi_desc *entry)
  */
 int set_irq_chip_data(unsigned int irq, void *data)
 {
-	struct irq_desc *desc = irq_desc + irq;
+	struct irq_desc *desc;
 	unsigned long flags;
 
+	desc = get_irq_desc(irq);
 	if (irq >= nr_irqs || !desc->chip) {
 		printk(KERN_ERR "BUG: bad set_irq_chip_data(IRQ#%d)\n", irq);
 		return -EINVAL;
@@ -218,8 +219,9 @@ EXPORT_SYMBOL(set_irq_chip_data);
  */
 static void default_enable(unsigned int irq)
 {
-	struct irq_desc *desc = irq_desc + irq;
+	struct irq_desc *desc;
 
+	desc = get_irq_desc(irq);
 	desc->chip->unmask(irq);
 	desc->status &= ~IRQ_MASKED;
 }
@@ -236,7 +238,10 @@ static void default_disable(unsigned int irq)
  */
 static unsigned int default_startup(unsigned int irq)
 {
-	irq_desc[irq].chip->enable(irq);
+	struct irq_desc *desc;
+
+	desc = get_irq_desc(irq);
+	desc->chip->enable(irq);
 
 	return 0;
 }
@@ -246,8 +251,9 @@ static unsigned int default_startup(unsigned int irq)
  */
 static void default_shutdown(unsigned int irq)
 {
-	struct irq_desc *desc = irq_desc + irq;
+	struct irq_desc *desc;
 
+	desc = get_irq_desc(irq);
 	desc->chip->mask(irq);
 	desc->status |= IRQ_MASKED;
 }
@@ -550,7 +556,7 @@ __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 		return;
 	}
 
-	desc = irq_desc + irq;
+	desc = get_irq_desc(irq);
 
 	if (!handle)
 		handle = handle_bad_irq;
@@ -615,7 +621,7 @@ void __init set_irq_noprobe(unsigned int irq)
 		return;
 	}
 
-	desc = irq_desc + irq;
+	desc = get_irq_desc(irq);
 
 	spin_lock_irqsave(&desc->lock, flags);
 	desc->status |= IRQ_NOPROBE;
@@ -633,7 +639,7 @@ void __init set_irq_probe(unsigned int irq)
 		return;
 	}
 
-	desc = irq_desc + irq;
+	desc = get_irq_desc(irq);
 
 	spin_lock_irqsave(&desc->lock, flags);
 	desc->status &= ~IRQ_NOPROBE;
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index e94eeca..6bc8502 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -18,6 +18,14 @@
 
 #include "internals.h"
 
+#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;
+#endif
+
 /**
  * handle_bad_irq - handle spurious and unhandled irqs
  * @irq:       the interrupt number
@@ -50,7 +58,8 @@ handle_bad_irq(unsigned int irq, struct irq_desc *desc)
 int nr_irqs = NR_IRQS;
 
 #ifdef CONFIG_HAVE_DYN_ARRAY
-static struct irq_desc irq_desc_init __initdata = {
+static struct irq_desc irq_desc_init = {
+	.irq = -1U,
 	.status = IRQ_DISABLED,
 	.chip = &no_irq_chip,
 	.handle_irq = handle_bad_irq,
@@ -61,6 +70,27 @@ static struct irq_desc irq_desc_init __initdata = {
 #endif
 };
 
+
+static void init_one_irq_desc(struct irq_desc *desc)
+{
+	memcpy(desc, &irq_desc_init, sizeof(struct irq_desc));
+#ifdef CONFIG_TRACE_IRQFLAGS
+	lockdep_set_class(&desc->lock, &irq_desc_lock_class);
+#endif
+}
+
+#ifdef CONFIG_HAVE_SPARSE_IRQ
+static int nr_irq_desc = 32;
+
+static int __init parse_nr_irq_desc(char *arg)
+{
+	if (arg)
+		nr_irq_desc = simple_strtoul(arg, NULL, 0);
+	return 0;
+}
+
+early_param("nr_irq_desc", parse_nr_irq_desc);
+
 static void __init init_work(void *data)
 {
 	struct dyn_array *da = data;
@@ -70,12 +100,83 @@ static void __init init_work(void *data)
 	desc = *da->name;
 
 	for (i = 0; i < *da->nr; i++)
-		memcpy(&desc[i], &irq_desc_init, sizeof(struct irq_desc));
+		init_one_irq_desc(&desc[i]);
+
+	for (i = 1; i < *da->nr; i++)
+		desc[i-1].next = &desc[i];
 }
 
-struct irq_desc *irq_desc;
+static struct irq_desc *irq_desc;
+DEFINE_DYN_ARRAY(irq_desc, sizeof(struct irq_desc), nr_irq_desc, PAGE_SIZE, init_work);
+
+extern int after_bootmem;
+extern void *__alloc_bootmem_nopanic(unsigned long size,
+			     unsigned long align,
+			     unsigned long goal);
+struct irq_desc *get_irq_desc(unsigned int irq)
+{
+	struct irq_desc *desc, *desc_pri;
+	int i;
+	int count = 0;
+
+	BUG_ON(irq == -1U);
+
+	desc_pri = desc = &irq_desc[0];
+	while (desc) {
+		if (desc->irq == irq)
+			return desc;
+
+		if (desc->irq == -1U) {
+			desc->irq = irq;
+			return desc;
+		}
+		desc_pri = desc;
+		desc = desc->next;
+		count++;
+	}
+
+	/*
+	 *  we run out of pre-allocate ones, allocate more
+	 */
+	printk(KERN_DEBUG "try to get more irq_desc %d\n", nr_irq_desc);
+
+	if (after_bootmem)
+		desc = kzalloc(sizeof(struct irq_desc)*nr_irq_desc, GFP_ATOMIC);
+	else
+		desc = __alloc_bootmem_nopanic(sizeof(struct irq_desc)*nr_irq_desc, PAGE_SIZE, 0);
+
+        if (!desc)
+		panic("please boot with nr_irq_desc= %d\n", count * 2);
+
+	for (i = 0; i < nr_irq_desc; i++)
+		init_one_irq_desc(&desc[i]);
+
+	for (i = 1; i < nr_irq_desc; i++)
+		desc[i-1].next = &desc[i];
+
+	desc->irq = irq;
+	desc_pri->next = desc;
+
+	return desc;
+}
+#else
+static void __init init_work(void *data)
+{
+	struct dyn_array *da = data;
+	int i;
+	struct  irq_desc *desc;
+
+	desc = *da->name;
+
+	for (i = 0; i < *da->nr; i++)
+		init_one_irq_desc(&desc[i]);
+
+}
+static struct irq_desc *irq_desc;
 DEFINE_DYN_ARRAY(irq_desc, sizeof(struct irq_desc), nr_irqs, PAGE_SIZE, init_work);
 
+#endif
+
 #else
 
 struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
@@ -90,6 +191,17 @@ struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
 #endif
 	}
 };
+
+#endif
+
+#ifndef CONFIG_HAVE_SPARSE_IRQ
+struct irq_desc *get_irq_desc(unsigned int irq)
+{
+	if (irq < nr_irqs)
+		return &irq_desc[irq];
+
+	return NULL;
+}
 #endif
 
 /*
@@ -98,7 +210,10 @@ struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
  */
 static void ack_bad(unsigned int irq)
 {
-	print_irq_desc(irq, irq_desc + irq);
+	struct irq_desc *desc;
+
+	desc = get_irq_desc(irq);
+	print_irq_desc(irq, desc);
 	ack_bad_irq(irq);
 }
 
@@ -195,7 +310,7 @@ irqreturn_t handle_IRQ_event(unsigned int irq, struct irqaction *action)
  */
 unsigned int __do_IRQ(unsigned int irq)
 {
-	struct irq_desc *desc = irq_desc + irq;
+	struct irq_desc *desc = get_irq_desc(irq);
 	struct irqaction *action;
 	unsigned int status;
 
@@ -286,19 +401,16 @@ out:
 }
 #endif
 
-#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;
 
+#ifdef CONFIG_TRACE_IRQFLAGS
 void early_init_irq_lock_class(void)
 {
+#ifndef CONFIG_HAVE_DYN_ARRAY
 	int i;
 
 	for (i = 0; i < nr_irqs; i++)
 		lockdep_set_class(&irq_desc[i].lock, &irq_desc_lock_class);
+#endif
 }
-
 #endif
+
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 3bd67c8..f199122 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -31,7 +31,7 @@ cpumask_t irq_default_affinity = CPU_MASK_ALL;
  */
 void synchronize_irq(unsigned int irq)
 {
-	struct irq_desc *desc = irq_desc + irq;
+	struct irq_desc *desc = get_irq_desc(irq);
 	unsigned int status;
 
 	if (irq >= nr_irqs)
@@ -64,7 +64,7 @@ EXPORT_SYMBOL(synchronize_irq);
  */
 int irq_can_set_affinity(unsigned int irq)
 {
-	struct irq_desc *desc = irq_desc + irq;
+	struct irq_desc *desc = get_irq_desc(irq);
 
 	if (CHECK_IRQ_PER_CPU(desc->status) || !desc->chip ||
 	    !desc->chip->set_affinity)
@@ -81,7 +81,7 @@ int irq_can_set_affinity(unsigned int irq)
  */
 int irq_set_affinity(unsigned int irq, cpumask_t cpumask)
 {
-	struct irq_desc *desc = irq_desc + irq;
+	struct irq_desc *desc = get_irq_desc(irq);
 
 	if (!desc->chip->set_affinity)
 		return -EINVAL;
@@ -111,14 +111,16 @@ int irq_set_affinity(unsigned int irq, cpumask_t cpumask)
 int irq_select_affinity(unsigned int irq)
 {
 	cpumask_t mask;
+	struct irq_desc *desc;
 
 	if (!irq_can_set_affinity(irq))
 		return 0;
 
 	cpus_and(mask, cpu_online_map, irq_default_affinity);
 
-	irq_desc[irq].affinity = mask;
-	irq_desc[irq].chip->set_affinity(irq, mask);
+	desc = get_irq_desc(irq);
+	desc->affinity = mask;
+	desc->chip->set_affinity(irq, mask);
 
 	set_balance_irq_affinity(irq, mask);
 	return 0;
@@ -140,7 +142,7 @@ int irq_select_affinity(unsigned int irq)
  */
 void disable_irq_nosync(unsigned int irq)
 {
-	struct irq_desc *desc = irq_desc + irq;
+	struct irq_desc *desc = get_irq_desc(irq);
 	unsigned long flags;
 
 	if (irq >= nr_irqs)
@@ -169,7 +171,7 @@ EXPORT_SYMBOL(disable_irq_nosync);
  */
 void disable_irq(unsigned int irq)
 {
-	struct irq_desc *desc = irq_desc + irq;
+	struct irq_desc *desc = get_irq_desc(irq);
 
 	if (irq >= nr_irqs)
 		return;
@@ -211,7 +213,7 @@ static void __enable_irq(struct irq_desc *desc, unsigned int irq)
  */
 void enable_irq(unsigned int irq)
 {
-	struct irq_desc *desc = irq_desc + irq;
+	struct irq_desc *desc = get_irq_desc(irq);
 	unsigned long flags;
 
 	if (irq >= nr_irqs)
@@ -225,7 +227,7 @@ EXPORT_SYMBOL(enable_irq);
 
 int set_irq_wake_real(unsigned int irq, unsigned int on)
 {
-	struct irq_desc *desc = irq_desc + irq;
+	struct irq_desc *desc = get_irq_desc(irq);
 	int ret = -ENXIO;
 
 	if (desc->chip->set_wake)
@@ -248,7 +250,7 @@ int set_irq_wake_real(unsigned int irq, unsigned int on)
  */
 int set_irq_wake(unsigned int irq, unsigned int on)
 {
-	struct irq_desc *desc = irq_desc + irq;
+	struct irq_desc *desc = get_irq_desc(irq);
 	unsigned long flags;
 	int ret = 0;
 
@@ -288,12 +290,13 @@ EXPORT_SYMBOL(set_irq_wake);
  */
 int can_request_irq(unsigned int irq, unsigned long irqflags)
 {
+	struct irq_desc *desc = get_irq_desc(irq);
 	struct irqaction *action;
 
-	if (irq >= nr_irqs || irq_desc[irq].status & IRQ_NOREQUEST)
+	if (irq >= nr_irqs || desc->status & IRQ_NOREQUEST)
 		return 0;
 
-	action = irq_desc[irq].action;
+	action =desc->action;
 	if (action)
 		if (irqflags & action->flags & IRQF_SHARED)
 			action = NULL;
@@ -342,7 +345,7 @@ static int __irq_set_trigger(struct irq_chip *chip, unsigned int irq,
  */
 int setup_irq(unsigned int irq, struct irqaction *new)
 {
-	struct irq_desc *desc = irq_desc + irq;
+	struct irq_desc *desc = get_irq_desc(irq);
 	struct irqaction *old, **p;
 	const char *old_name = NULL;
 	unsigned long flags;
@@ -506,7 +509,7 @@ void free_irq(unsigned int irq, void *dev_id)
 	if (irq >= nr_irqs)
 		return;
 
-	desc = irq_desc + irq;
+	desc = get_irq_desc(irq);
 	spin_lock_irqsave(&desc->lock, flags);
 	p = &desc->action;
 	for (;;) {
@@ -602,6 +605,7 @@ int request_irq(unsigned int irq, irq_handler_t handler,
 {
 	struct irqaction *action;
 	int retval;
+	struct irq_desc *desc;
 
 #ifdef CONFIG_LOCKDEP
 	/*
@@ -619,7 +623,8 @@ int request_irq(unsigned int irq, irq_handler_t handler,
 		return -EINVAL;
 	if (irq >= nr_irqs)
 		return -EINVAL;
-	if (irq_desc[irq].status & IRQ_NOREQUEST)
+	desc = get_irq_desc(irq);
+	if (desc->status & IRQ_NOREQUEST)
 		return -EINVAL;
 	if (!handler)
 		return -EINVAL;
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index 77b7acc..4df637c 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -3,18 +3,18 @@
 
 void set_pending_irq(unsigned int irq, cpumask_t mask)
 {
-	struct irq_desc *desc = irq_desc + irq;
+	struct irq_desc *desc = get_irq_desc(irq);
 	unsigned long flags;
 
 	spin_lock_irqsave(&desc->lock, flags);
 	desc->status |= IRQ_MOVE_PENDING;
-	irq_desc[irq].pending_mask = mask;
+	desc->pending_mask = mask;
 	spin_unlock_irqrestore(&desc->lock, flags);
 }
 
 void move_masked_irq(int irq)
 {
-	struct irq_desc *desc = irq_desc + irq;
+	struct irq_desc *desc = get_irq_desc(irq);
 	cpumask_t tmp;
 
 	if (likely(!(desc->status & IRQ_MOVE_PENDING)))
@@ -30,7 +30,7 @@ void move_masked_irq(int irq)
 
 	desc->status &= ~IRQ_MOVE_PENDING;
 
-	if (unlikely(cpus_empty(irq_desc[irq].pending_mask)))
+	if (unlikely(cpus_empty(desc->pending_mask)))
 		return;
 
 	if (!desc->chip->set_affinity)
@@ -38,7 +38,7 @@ void move_masked_irq(int irq)
 
 	assert_spin_locked(&desc->lock);
 
-	cpus_and(tmp, irq_desc[irq].pending_mask, cpu_online_map);
+	cpus_and(tmp, desc->pending_mask, cpu_online_map);
 
 	/*
 	 * If there was a valid mask to work with, please
@@ -55,12 +55,12 @@ void move_masked_irq(int irq)
 	if (likely(!cpus_empty(tmp))) {
 		desc->chip->set_affinity(irq,tmp);
 	}
-	cpus_clear(irq_desc[irq].pending_mask);
+	cpus_clear(desc->pending_mask);
 }
 
 void move_native_irq(int irq)
 {
-	struct irq_desc *desc = irq_desc + irq;
+	struct irq_desc *desc = get_irq_desc(irq);
 
 	if (likely(!(desc->status & IRQ_MOVE_PENDING)))
 		return;
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 74d7922..2d8b936 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -19,7 +19,7 @@ static struct proc_dir_entry *root_irq_dir;
 static int irq_affinity_read_proc(char *page, char **start, off_t off,
 				  int count, int *eof, void *data)
 {
-	struct irq_desc *desc = irq_desc + (long)data;
+	struct irq_desc *desc = get_irq_desc((long)data);
 	cpumask_t *mask = &desc->affinity;
 	int len;
 
@@ -45,8 +45,9 @@ static int irq_affinity_write_proc(struct file *file, const char __user *buffer,
 {
 	unsigned int irq = (int)(long)data, full_count = count, err;
 	cpumask_t new_value;
+	struct irq_desc *desc = get_irq_desc(irq);
 
-	if (!irq_desc[irq].chip->set_affinity || no_irq_affinity ||
+	if (!desc->chip->set_affinity || no_irq_affinity ||
 	    irq_balancing_disabled(irq))
 		return -EIO;
 
@@ -112,20 +113,20 @@ static int default_affinity_write(struct file *file, const char __user *buffer,
 static int irq_spurious_read(char *page, char **start, off_t off,
 				  int count, int *eof, void *data)
 {
-	struct irq_desc *d = &irq_desc[(long) data];
+	struct irq_desc *desc = get_irq_desc((long) data);
 	return sprintf(page, "count %u\n"
 			     "unhandled %u\n"
 			     "last_unhandled %u ms\n",
-			d->irq_count,
-			d->irqs_unhandled,
-			jiffies_to_msecs(d->last_unhandled));
+			desc->irq_count,
+			desc->irqs_unhandled,
+			jiffies_to_msecs(desc->last_unhandled));
 }
 
 #define MAX_NAMELEN 128
 
 static int name_unique(unsigned int irq, struct irqaction *new_action)
 {
-	struct irq_desc *desc = irq_desc + irq;
+	struct irq_desc *desc = get_irq_desc(irq);
 	struct irqaction *action;
 	unsigned long flags;
 	int ret = 1;
@@ -145,8 +146,9 @@ static int name_unique(unsigned int irq, struct irqaction *new_action)
 void register_handler_proc(unsigned int irq, struct irqaction *action)
 {
 	char name [MAX_NAMELEN];
+	struct irq_desc *desc = get_irq_desc(irq);
 
-	if (!irq_desc[irq].dir || action->dir || !action->name ||
+	if (!desc->dir || action->dir || !action->name ||
 					!name_unique(irq, action))
 		return;
 
@@ -154,7 +156,7 @@ void register_handler_proc(unsigned int irq, struct irqaction *action)
 	snprintf(name, MAX_NAMELEN, "%s", action->name);
 
 	/* create /proc/irq/1234/handler/ */
-	action->dir = proc_mkdir(name, irq_desc[irq].dir);
+	action->dir = proc_mkdir(name, desc->dir);
 }
 
 #undef MAX_NAMELEN
@@ -165,22 +167,22 @@ void register_irq_proc(unsigned int irq)
 {
 	char name [MAX_NAMELEN];
 	struct proc_dir_entry *entry;
+	struct irq_desc *desc = get_irq_desc(irq);
 
 	if (!root_irq_dir ||
-		(irq_desc[irq].chip == &no_irq_chip) ||
-			irq_desc[irq].dir)
+		(desc->chip == &no_irq_chip) || desc->dir)
 		return;
 
 	memset(name, 0, MAX_NAMELEN);
 	sprintf(name, "%d", irq);
 
 	/* create /proc/irq/1234 */
-	irq_desc[irq].dir = proc_mkdir(name, root_irq_dir);
+	desc->dir = proc_mkdir(name, root_irq_dir);
 
 #ifdef CONFIG_SMP
 	{
 		/* create /proc/irq/<irq>/smp_affinity */
-		entry = create_proc_entry("smp_affinity", 0600, irq_desc[irq].dir);
+		entry = create_proc_entry("smp_affinity", 0600, desc->dir);
 
 		if (entry) {
 			entry->data = (void *)(long)irq;
@@ -190,7 +192,7 @@ void register_irq_proc(unsigned int irq)
 	}
 #endif
 
-	entry = create_proc_entry("spurious", 0444, irq_desc[irq].dir);
+	entry = create_proc_entry("spurious", 0444, desc->dir);
 	if (entry) {
 		entry->data = (void *)(long)irq;
 		entry->read_proc = irq_spurious_read;
@@ -201,8 +203,10 @@ void register_irq_proc(unsigned int irq)
 
 void unregister_handler_proc(unsigned int irq, struct irqaction *action)
 {
-	if (action->dir)
-		remove_proc_entry(action->dir->name, irq_desc[irq].dir);
+	if (action->dir) {
+		struct irq_desc *desc = get_irq_desc(irq);
+		remove_proc_entry(action->dir->name, desc->dir);
+	}
 }
 
 void register_default_affinity_proc(void)
diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c
index cba8aa5..8e4b78a 100644
--- a/kernel/irq/resend.c
+++ b/kernel/irq/resend.c
@@ -36,7 +36,7 @@ static void resend_irqs(unsigned long arg)
 	while (!bitmap_empty(irqs_resend, nr_irqs)) {
 		irq = find_first_bit(irqs_resend, nr_irqs);
 		clear_bit(irq, irqs_resend);
-		desc = irq_desc + irq;
+		desc = get_irq_desc(irq);
 		local_irq_disable();
 		desc->handle_irq(irq, desc);
 		local_irq_enable();
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index e26ca1e..b2a481c 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -92,11 +92,12 @@ static int misrouted_irq(int irq)
 	int ok = 0;
 
 	for (i = 1; i < nr_irqs; i++) {
-		struct irq_desc *desc = irq_desc + i;
+		struct irq_desc *desc;
 
 		if (i == irq)	/* Already tried */
 			continue;
 
+		desc = get_irq_desc(i);
 		if (try_one_irq(i, desc))
 			ok = 1;
 	}
@@ -108,7 +109,7 @@ static void poll_spurious_irqs(unsigned long dummy)
 {
 	int i;
 	for (i = 1; i < nr_irqs; i++) {
-		struct irq_desc *desc = irq_desc + i;
+		struct irq_desc *desc = get_irq_desc(i);
 		unsigned int status;
 
 		/* Racy but it doesn't matter */
-- 
1.5.4.5

[PATCH 27/33] x86: add get_irq_cfg in io_apic_64.c

[Yinghai Lu]

preallocate size is 32, and if is not enough, get_irq_cfg will more with alloc_bootmem or kzalloc

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
---
 arch/x86/kernel/io_apic_64.c |  182 ++++++++++++++++++++++++++++++++---------
 1 files changed, 142 insertions(+), 40 deletions(-)

diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
index 3734216..8908555 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -57,7 +57,11 @@
 
 #define __apicdebuginit(type) static type __init
 
+struct irq_cfg;
+
 struct irq_cfg {
+	unsigned int irq;
+	struct irq_cfg *next;
 	cpumask_t domain;
 	cpumask_t old_domain;
 	unsigned move_cleanup_count;
@@ -67,34 +71,112 @@ struct irq_cfg {
 
 /* irq_cfg is indexed by the sum of all RTEs in all I/O APICs. */
 static struct irq_cfg irq_cfg_legacy[] __initdata = {
-	[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, },
+	[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;
+static struct irq_cfg irq_cfg_init = { .irq =  -1U, };
+/* need to be biger than size of irq_cfg_legacy */
+static int nr_irq_cfg = 32;
+
+static int __init parse_nr_irq_cfg(char *arg)
+{
+	if (arg) {
+		nr_irq_cfg = simple_strtoul(arg, NULL, 0);
+		if (nr_irq_cfg < 32)
+			nr_irq_cfg = 32;
+	}
+	return 0;
+}
+
+early_param("nr_irq_cfg", parse_nr_irq_cfg);
+
+static void init_one_irq_cfg(struct irq_cfg *cfg)
+{
+        memcpy(cfg, &irq_cfg_init, sizeof(struct irq_desc));
+}
 
 static void __init init_work(void *data)
 {
 	struct dyn_array *da = data;
+	struct irq_cfg *cfg;
+	int i;
 
-	memcpy(*da->name, irq_cfg_legacy, sizeof(irq_cfg_legacy));
+	cfg = *da->name;
+
+	memcpy(cfg, irq_cfg_legacy, sizeof(irq_cfg_legacy));
+
+	i = sizeof(irq_cfg_legacy)/sizeof(irq_cfg_legacy[0]);
+	for (; i < *da->nr; i++)
+		init_one_irq_cfg(&cfg[i]);
+
+	for (i = 1; i < *da->nr; i++)
+		cfg[i-1].next = &cfg[i];
 }
 
-DEFINE_DYN_ARRAY(irq_cfg, sizeof(struct irq_cfg), nr_irqs, PAGE_SIZE, init_work);
+static struct irq_cfg *irq_cfgx;
+DEFINE_DYN_ARRAY(irq_cfgx, sizeof(struct irq_cfg), nr_irq_cfg, PAGE_SIZE, init_work);
+
+static struct irq_cfg *get_irq_cfg(unsigned int irq)
+{
+	struct irq_cfg *cfg, *cfg_pri;
+	int i;
+	int count = 0;
+
+	BUG_ON(irq == -1U);
+
+	cfg_pri = cfg = &irq_cfgx[0];
+	while (cfg) {
+		if (cfg->irq == irq)
+			return cfg;
+
+		if (cfg->irq == -1U) {
+			cfg->irq = irq;
+			return cfg;
+		}
+		cfg_pri = cfg;
+		cfg = cfg->next;
+		count++;
+	}
+
+	/*
+	 *  we run out of pre-allocate ones, allocate more
+	 */
+	printk(KERN_DEBUG "try to get more irq_cfg %d\n", nr_irq_cfg);
+
+	if (after_bootmem)
+		cfg = kzalloc(sizeof(struct irq_cfg)*nr_irq_cfg, GFP_ATOMIC);
+	else
+		cfg = __alloc_bootmem_nopanic(sizeof(struct irq_cfg)*nr_irq_cfg, PAGE_SIZE, 0);
+
+	if (!cfg)
+		panic("please boot with nr_irq_cfg= %d\n", count * 2);
+
+	for (i = 0; i < nr_irq_cfg; i++)
+		init_one_irq_cfg(&cfg[i]);
+
+	for (i = 1; i < nr_irq_cfg; i++)
+		cfg[i-1].next = &cfg[i];
+
+	cfg->irq = irq;
+	cfg_pri->next = cfg;
+
+	return cfg;
+}
 
 static int assign_irq_vector(int irq, cpumask_t mask);
 
@@ -341,7 +423,7 @@ static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, u8 vector)
 
 static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t mask)
 {
-	struct irq_cfg *cfg = irq_cfg + irq;
+	struct irq_cfg *cfg = get_irq_cfg(irq);
 	unsigned long flags;
 	unsigned int dest;
 	cpumask_t tmp;
@@ -806,7 +888,7 @@ static int __assign_irq_vector(int irq, cpumask_t mask)
 	struct irq_cfg *cfg;
 
 	BUG_ON((unsigned)irq >= nr_irqs);
-	cfg = &irq_cfg[irq];
+	cfg = get_irq_cfg(irq);
 
 	/* Only try and allocate irqs on cpus that are present */
 	cpus_and(mask, mask, cpu_online_map);
@@ -880,7 +962,7 @@ static void __clear_irq_vector(int irq)
 	int cpu, vector;
 
 	BUG_ON((unsigned)irq >= nr_irqs);
-	cfg = &irq_cfg[irq];
+	cfg = get_irq_cfg(irq);
 	BUG_ON(!cfg->vector);
 
 	vector = cfg->vector;
@@ -900,17 +982,23 @@ static void __setup_vector_irq(int cpu)
 
 	/* Mark the inuse vectors */
 	for (irq = 0; irq < nr_irqs; ++irq) {
-		if (!cpu_isset(cpu, irq_cfg[irq].domain))
+		struct irq_cfg *cfg = get_irq_cfg(irq);
+
+		if (!cpu_isset(cpu, cfg->domain))
 			continue;
-		vector = irq_cfg[irq].vector;
+		vector = cfg->vector;
 		per_cpu(vector_irq, cpu)[vector] = irq;
 	}
 	/* Mark the free vectors */
 	for (vector = 0; vector < NR_VECTORS; ++vector) {
+		struct irq_cfg *cfg;
+
 		irq = per_cpu(vector_irq, cpu)[vector];
 		if (irq < 0)
 			continue;
-		if (!cpu_isset(cpu, irq_cfg[irq].domain))
+
+		cfg = get_irq_cfg(irq);
+		if (!cpu_isset(cpu, cfg->domain))
 			per_cpu(vector_irq, cpu)[vector] = -1;
 	}
 }
@@ -1024,7 +1112,7 @@ static int setup_ioapic_entry(int apic, int irq,
 static void setup_IO_APIC_irq(int apic, int pin, unsigned int irq,
 			      int trigger, int polarity)
 {
-	struct irq_cfg *cfg = irq_cfg + irq;
+	struct irq_cfg *cfg = get_irq_cfg(irq);
 	struct IO_APIC_route_entry entry;
 	cpumask_t mask;
 
@@ -1550,7 +1638,7 @@ static unsigned int startup_ioapic_irq(unsigned int irq)
 
 static int ioapic_retrigger_irq(unsigned int irq)
 {
-	struct irq_cfg *cfg = &irq_cfg[irq];
+	struct irq_cfg *cfg = get_irq_cfg(irq);
 	unsigned long flags;
 
 	spin_lock_irqsave(&vector_lock, flags);
@@ -1597,7 +1685,7 @@ static DECLARE_DELAYED_WORK(ir_migration_work, ir_irq_migration);
  */
 static void migrate_ioapic_irq(int irq, cpumask_t mask)
 {
-	struct irq_cfg *cfg = irq_cfg + irq;
+	struct irq_cfg *cfg;
 	struct irq_desc *desc;
 	cpumask_t tmp, cleanup_mask;
 	struct irte irte;
@@ -1615,6 +1703,7 @@ static void migrate_ioapic_irq(int irq, cpumask_t mask)
 	if (assign_irq_vector(irq, mask))
 		return;
 
+	cfg = get_irq_cfg(irq);
 	cpus_and(tmp, cfg->domain, mask);
 	dest = cpu_mask_to_apicid(tmp);
 
@@ -1732,7 +1821,7 @@ asmlinkage void smp_irq_move_cleanup_interrupt(void)
 			continue;
 
 		desc = get_irq_desc(irq);
-		cfg = irq_cfg + irq;
+		cfg = get_irq_cfg(irq);
 		spin_lock(&desc->lock);
 		if (!cfg->move_cleanup_count)
 			goto unlock;
@@ -1751,7 +1840,7 @@ unlock:
 
 static void irq_complete_move(unsigned int irq)
 {
-	struct irq_cfg *cfg = irq_cfg + irq;
+	struct irq_cfg *cfg = get_irq_cfg(irq);
 	unsigned vector, me;
 
 	if (likely(!cfg->move_in_progress))
@@ -1888,7 +1977,10 @@ static inline void init_IO_APIC_traps(void)
 	 * 0x80, because int 0x80 is hm, kind of importantish. ;)
 	 */
 	for (irq = 0; irq < nr_irqs ; irq++) {
-		if (IO_APIC_IRQ(irq) && !irq_cfg[irq].vector) {
+		struct irq_cfg *cfg;
+
+		cfg = get_irq_cfg(irq);
+		if (IO_APIC_IRQ(irq) && !cfg->vector) {
 			/*
 			 * Hmm.. We don't have an entry for this,
 			 * so default to an old-fashioned 8259
@@ -2025,7 +2117,7 @@ static inline void __init unlock_ExtINT_logic(void)
  */
 static inline void __init check_timer(void)
 {
-	struct irq_cfg *cfg = irq_cfg + 0;
+	struct irq_cfg *cfg = get_irq_cfg(0);
 	int apic1, pin1, apic2, pin2;
 	unsigned long flags;
 	int no_pin1 = 0;
@@ -2303,13 +2395,15 @@ int create_irq(void)
 	int irq;
 	int new;
 	unsigned long flags;
+	struct irq_cfg *cfg_new;
 
 	irq = -ENOSPC;
 	spin_lock_irqsave(&vector_lock, flags);
 	for (new = (nr_irqs - 1); new >= 0; new--) {
 		if (platform_legacy_irq(new))
 			continue;
-		if (irq_cfg[new].vector != 0)
+		cfg_new = get_irq_cfg(new);
+		if (cfg_new->vector != 0)
 			continue;
 		if (__assign_irq_vector(new, TARGET_CPUS) == 0)
 			irq = new;
@@ -2343,7 +2437,7 @@ void destroy_irq(unsigned int irq)
 #ifdef CONFIG_PCI_MSI
 static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_msg *msg)
 {
-	struct irq_cfg *cfg = irq_cfg + irq;
+	struct irq_cfg *cfg;
 	int err;
 	unsigned dest;
 	cpumask_t tmp;
@@ -2353,6 +2447,7 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_ms
 	if (err)
 		return err;
 
+	cfg = get_irq_cfg(irq);
 	cpus_and(tmp, cfg->domain, tmp);
 	dest = cpu_mask_to_apicid(tmp);
 
@@ -2410,7 +2505,7 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_ms
 #ifdef CONFIG_SMP
 static void set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
 {
-	struct irq_cfg *cfg = irq_cfg + irq;
+	struct irq_cfg *cfg;
 	struct msi_msg msg;
 	unsigned int dest;
 	cpumask_t tmp;
@@ -2423,6 +2518,7 @@ static void set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
 	if (assign_irq_vector(irq, mask))
 		return;
 
+	cfg = get_irq_cfg(irq);
 	cpus_and(tmp, cfg->domain, mask);
 	dest = cpu_mask_to_apicid(tmp);
 
@@ -2445,7 +2541,7 @@ static void set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
  */
 static void ir_set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
 {
-	struct irq_cfg *cfg = irq_cfg + irq;
+	struct irq_cfg *cfg;
 	unsigned int dest;
 	cpumask_t tmp, cleanup_mask;
 	struct irte irte;
@@ -2461,6 +2557,7 @@ static void ir_set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
 	if (assign_irq_vector(irq, mask))
 		return;
 
+	cfg = get_irq_cfg(irq);
 	cpus_and(tmp, cfg->domain, mask);
 	dest = cpu_mask_to_apicid(tmp);
 
@@ -2667,7 +2764,7 @@ void arch_teardown_msi_irq(unsigned int irq)
 #ifdef CONFIG_SMP
 static void dmar_msi_set_affinity(unsigned int irq, cpumask_t mask)
 {
-	struct irq_cfg *cfg = irq_cfg + irq;
+	struct irq_cfg *cfg;
 	struct msi_msg msg;
 	unsigned int dest;
 	cpumask_t tmp;
@@ -2680,6 +2777,7 @@ static void dmar_msi_set_affinity(unsigned int irq, cpumask_t mask)
 	if (assign_irq_vector(irq, mask))
 		return;
 
+	cfg = get_irq_cfg(irq);
 	cpus_and(tmp, cfg->domain, mask);
 	dest = cpu_mask_to_apicid(tmp);
 
@@ -2746,7 +2844,7 @@ static void target_ht_irq(unsigned int irq, unsigned int dest, u8 vector)
 
 static void set_ht_irq_affinity(unsigned int irq, cpumask_t mask)
 {
-	struct irq_cfg *cfg = irq_cfg + irq;
+	struct irq_cfg *cfg;
 	unsigned int dest;
 	cpumask_t tmp;
 	struct irq_desc *desc;
@@ -2758,6 +2856,7 @@ static void set_ht_irq_affinity(unsigned int irq, cpumask_t mask)
 	if (assign_irq_vector(irq, mask))
 		return;
 
+	cfg = get_irq_cfg(irq);
 	cpus_and(tmp, cfg->domain, mask);
 	dest = cpu_mask_to_apicid(tmp);
 
@@ -2780,7 +2879,7 @@ static struct irq_chip ht_irq_chip = {
 
 int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
 {
-	struct irq_cfg *cfg = irq_cfg + irq;
+	struct irq_cfg *cfg;
 	int err;
 	cpumask_t tmp;
 
@@ -2790,6 +2889,7 @@ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
 		struct ht_irq_msg msg;
 		unsigned dest;
 
+		cfg = get_irq_cfg(irq);
 		cpus_and(tmp, cfg->domain, tmp);
 		dest = cpu_mask_to_apicid(tmp);
 
@@ -2888,6 +2988,7 @@ int acpi_get_override_irq(int bus_irq, int *trigger, int *polarity)
 void __init setup_ioapic_dest(void)
 {
 	int pin, ioapic, irq, irq_entry;
+	struct irq_cfg *cfg;
 
 	if (skip_ioapic_setup == 1)
 		return;
@@ -2903,7 +3004,8 @@ void __init setup_ioapic_dest(void)
 			 * when you have too many devices, because at that time only boot
 			 * cpu is online.
 			 */
-			if (!irq_cfg[irq].vector)
+			cfg = get_irq_cfg(irq);
+			if (!cfg->vector)
 				setup_IO_APIC_irq(ioapic, pin, irq,
 						  irq_trigger(irq_entry),
 						  irq_polarity(irq_entry));
-- 
1.5.4.5

[PATCH 28/33] x86: put irq_2_pin pointer into irq_cfg

[Yinghai Lu]

preallocate 32 irq_2_pin, and use get_one_free_irq_2_pin to get one
and link to irq_cfg if needed.
so don't waste one for no irq is enabled.

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
---
 arch/x86/kernel/io_apic_64.c |  162 +++++++++++++++++++++++++++++++-----------
 1 files changed, 121 insertions(+), 41 deletions(-)

diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
index 8908555..c8e4613 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -58,10 +58,11 @@
 #define __apicdebuginit(type) static type __init
 
 struct irq_cfg;
-
+struct irq_pin_list;
 struct irq_cfg {
 	unsigned int irq;
 	struct irq_cfg *next;
+	struct irq_pin_list *irq_2_pin;
 	cpumask_t domain;
 	cpumask_t old_domain;
 	unsigned move_cleanup_count;
@@ -232,13 +233,66 @@ int pin_map_size;
  * between pins and IRQs.
  */
 
-static struct irq_pin_list {
-	short apic, pin;
-	int next;
-} *irq_2_pin;
+struct irq_pin_list {
+	int apic, pin;
+	struct irq_pin_list *next;
+};
+
+static struct irq_pin_list *irq_2_pin_head;
+/* fill one page ? */
+static int nr_irq_2_pin = 0x100;
+static struct irq_pin_list *irq_2_pin_ptr;
+static void __init irq_2_pin_init_work(void *data)
+{
+	struct dyn_array *da = data;
+	struct irq_pin_list *pin;
+	int i;
+
+	pin = *da->name;
+
+	for (i = 1; i < *da->nr; i++)
+		pin[i-1].next = &pin[i];
+
+	irq_2_pin_ptr = &pin[0];
+}
+DEFINE_DYN_ARRAY(irq_2_pin_head, sizeof(struct irq_pin_list), nr_irq_2_pin, PAGE_SIZE, irq_2_pin_init_work);
+
+static struct irq_pin_list *get_one_free_irq_2_pin(void)
+{
+	struct irq_pin_list *pin;
+	int i;
+
+	pin = irq_2_pin_ptr;
+
+	if (pin) {
+		irq_2_pin_ptr = pin->next;
+		pin->next = NULL;
+		return pin;
+	}
+
+	/*
+	 *  we run out of pre-allocate ones, allocate more
+	 */
+	printk(KERN_DEBUG "try to get more irq_2_pin %d\n", nr_irq_2_pin);
+
+	if (after_bootmem)
+		pin = kzalloc(sizeof(struct irq_pin_list)*nr_irq_2_pin,
+				 GFP_ATOMIC);
+	else
+		pin = __alloc_bootmem_nopanic(sizeof(struct irq_pin_list) *
+				nr_irq_2_pin, PAGE_SIZE, 0);
+
+	if (!pin)
+		panic("can not get more irq_2_pin\n");
+
+	for (i = 1; i < nr_irq_2_pin; i++)
+		pin[i-1].next = &pin[i];
 
-DEFINE_DYN_ARRAY(irq_2_pin, sizeof(struct irq_pin_list), pin_map_size, sizeof(struct irq_pin_list), NULL);
+	irq_2_pin_ptr = pin->next;
+	pin->next = NULL;
 
+	return pin;
+}
 
 struct io_apic {
 	unsigned int index;
@@ -280,16 +334,17 @@ static bool io_apic_level_ack_pending(unsigned int irq)
 {
 	struct irq_pin_list *entry;
 	unsigned long flags;
+	struct irq_cfg *cfg = get_irq_cfg(irq);
 
 	spin_lock_irqsave(&ioapic_lock, flags);
-	entry = irq_2_pin + irq;
+	entry = cfg->irq_2_pin;
 	for (;;) {
 		unsigned int reg;
 		int pin;
 
-		pin = entry->pin;
-		if (pin == -1)
+		if (!entry)
 			break;
+		pin = entry->pin;
 		reg = io_apic_read(entry->apic, 0x10 + pin*2);
 		/* Is the remote IRR bit set? */
 		if (reg & IO_APIC_REDIR_REMOTE_IRR) {
@@ -298,7 +353,7 @@ static bool io_apic_level_ack_pending(unsigned int irq)
 		}
 		if (!entry->next)
 			break;
-		entry = irq_2_pin + entry->next;
+		entry = entry->next;
 	}
 	spin_unlock_irqrestore(&ioapic_lock, flags);
 
@@ -319,21 +374,24 @@ static inline void io_apic_sync(unsigned int apic)
 									\
 {									\
 	int pin;							\
-	struct irq_pin_list *entry = irq_2_pin + irq;			\
+	struct irq_cfg *cfg;						\
+	struct irq_pin_list *entry;					\
 									\
 	BUG_ON(irq >= nr_irqs);						\
+	cfg = get_irq_cfg(irq);						\
+	entry = cfg->irq_2_pin;						\
 	for (;;) {							\
 		unsigned int reg;					\
-		pin = entry->pin;					\
-		if (pin == -1)						\
+		if (!entry)						\
 			break;						\
+		pin = entry->pin;					\
 		reg = io_apic_read(entry->apic, 0x10 + R + pin*2);	\
 		reg ACTION;						\
 		io_apic_modify(entry->apic, reg);			\
 		FINAL;							\
 		if (!entry->next)					\
 			break;						\
-		entry = irq_2_pin + entry->next;			\
+		entry = entry->next;					\
 	}								\
 }
 
@@ -396,15 +454,20 @@ static void ioapic_mask_entry(int apic, int pin)
 static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, u8 vector)
 {
 	int apic, pin;
-	struct irq_pin_list *entry = irq_2_pin + irq;
+	struct irq_cfg *cfg;
+	struct irq_pin_list *entry;
 
 	BUG_ON(irq >= nr_irqs);
+	cfg = get_irq_cfg(irq);
+	entry = cfg->irq_2_pin;
 	for (;;) {
 		unsigned int reg;
+
+		if (!entry)
+			break;
+
 		apic = entry->apic;
 		pin = entry->pin;
-		if (pin == -1)
-			break;
 		/*
 		 * With interrupt-remapping, destination information comes
 		 * from interrupt-remapping table entry.
@@ -417,7 +480,7 @@ static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, u8 vector)
 		io_apic_modify(apic, reg);
 		if (!entry->next)
 			break;
-		entry = irq_2_pin + entry->next;
+		entry = entry->next;
 	}
 }
 
@@ -460,20 +523,34 @@ static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t mask)
 int first_free_entry;
 static void add_pin_to_irq(unsigned int irq, int apic, int pin)
 {
-	struct irq_pin_list *entry = irq_2_pin + irq;
+	struct irq_cfg *cfg;
+	struct irq_pin_list *entry;
 
 	BUG_ON(irq >= nr_irqs);
-	while (entry->next)
-		entry = irq_2_pin + entry->next;
+	cfg = get_irq_cfg(irq);
+	entry = cfg->irq_2_pin;
+	if (!entry) {
+		entry = get_one_free_irq_2_pin();
+		cfg->irq_2_pin = entry;
+		entry->apic = apic;
+		entry->pin = pin;
+		printk(KERN_DEBUG " 0 add_pin_to_irq: irq %d --> apic %d pin %d\n", irq, apic, pin);
+		return;
+	}
 
-	if (entry->pin != -1) {
-		entry->next = first_free_entry;
-		entry = irq_2_pin + entry->next;
-		if (++first_free_entry >= pin_map_size)
-			panic("io_apic.c: ran out of irq_2_pin entries!");
+	while (entry->next) {
+		/* not again, please */
+		if (entry->apic == apic && entry->pin == pin)
+			return;
+
+		entry = entry->next;
 	}
+
+	entry->next = get_one_free_irq_2_pin();
+	entry = entry->next;
 	entry->apic = apic;
 	entry->pin = pin;
+	printk(KERN_DEBUG " x add_pin_to_irq: irq %d --> apic %d pin %d\n", irq, apic, pin);
 }
 
 /*
@@ -483,17 +560,24 @@ static void __init replace_pin_at_irq(unsigned int irq,
 				      int oldapic, int oldpin,
 				      int newapic, int newpin)
 {
-	struct irq_pin_list *entry = irq_2_pin + irq;
+	struct irq_cfg *cfg = get_irq_cfg(irq);
+	struct irq_pin_list *entry = cfg->irq_2_pin;
+	int replaced = 0;
 
-	while (1) {
+	while (entry) {
 		if (entry->apic == oldapic && entry->pin == oldpin) {
 			entry->apic = newapic;
 			entry->pin = newpin;
-		}
-		if (!entry->next)
+			replaced = 1;
+			/* every one is different, right? */
 			break;
-		entry = irq_2_pin + entry->next;
+		}
+		entry = entry->next;
 	}
+
+	/* why? call replace before add? */
+	if (!replaced)
+		add_pin_to_irq(irq, newapic, newpin);
 }
 
 
@@ -1297,15 +1381,16 @@ __apicdebuginit(void) print_IO_APIC(void)
 	}
 	printk(KERN_DEBUG "IRQ to pin mappings:\n");
 	for (i = 0; i < nr_irqs; i++) {
-		struct irq_pin_list *entry = irq_2_pin + i;
-		if (entry->pin < 0)
+		struct irq_cfg *cfg = get_irq_cfg(i);
+		struct irq_pin_list *entry = cfg->irq_2_pin;
+		if (!entry)
 			continue;
 		printk(KERN_DEBUG "IRQ%d ", i);
 		for (;;) {
 			printk("-> %d:%d", entry->apic, entry->pin);
 			if (!entry->next)
 				break;
-			entry = irq_2_pin + entry->next;
+			entry = entry->next;
 		}
 		printk("\n");
 	}
@@ -1466,14 +1551,9 @@ void __init enable_IO_APIC(void)
 {
 	union IO_APIC_reg_01 reg_01;
 	int i8259_apic, i8259_pin;
-	int i, apic;
+	int apic;
 	unsigned long flags;
 
-	for (i = 0; i < pin_map_size; i++) {
-		irq_2_pin[i].pin = -1;
-		irq_2_pin[i].next = 0;
-	}
-
 	/*
 	 * The number of IO-APIC IRQ registers (== #pins):
 	 */
-- 
1.5.4.5

[PATCH 29/33] x86: put timer_rand_state pointer into irq_desc

[Yinghai Lu]

so could remove timer_rand_state pointer array

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
---
 drivers/char/random.c |   31 ++++++++++++++++++++-----------
 include/linux/irq.h   |    2 ++
 2 files changed, 22 insertions(+), 11 deletions(-)

diff --git a/drivers/char/random.c b/drivers/char/random.c
index 872669e..d9e7a08 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -559,13 +559,6 @@ struct timer_rand_state {
 
 static struct timer_rand_state input_timer_state;
 
-#ifdef CONFIG_HAVE_DYN_ARRAY
-static struct timer_rand_state **irq_timer_state;
-DEFINE_DYN_ARRAY(irq_timer_state, sizeof(struct timer_rand_state *), nr_irqs, PAGE_SIZE, NULL);
-#else
-static struct timer_rand_state *irq_timer_state[NR_IRQS];
-#endif
-
 /*
  * This function adds entropy to the entropy "pool" by using timing
  * delays.  It uses the timer_rand_state structure to make an estimate
@@ -653,11 +646,20 @@ EXPORT_SYMBOL_GPL(add_input_randomness);
 
 void add_interrupt_randomness(int irq)
 {
-	if (irq >= nr_irqs || irq_timer_state[irq] == NULL)
+	struct timer_rand_state *state;
+	struct irq_desc *desc;
+
+	if (irq >= nr_irqs)
+		return;
+
+	desc = get_irq_desc(irq);
+	state = desc->timer_rand_state;
+
+	if (state == NULL)
 		return;
 
 	DEBUG_ENT("irq event %d\n", irq);
-	add_timer_randomness(irq_timer_state[irq], 0x100 + irq);
+	add_timer_randomness(state, 0x100 + irq);
 }
 
 #ifdef CONFIG_BLOCK
@@ -916,8 +918,15 @@ module_init(rand_initialize);
 void rand_initialize_irq(int irq)
 {
 	struct timer_rand_state *state;
+	struct irq_desc *desc;
+
+	if (irq >= nr_irqs)
+		return;
+
+	desc = get_irq_desc(irq);
+	state = desc->timer_rand_state;
 
-	if (irq >= nr_irqs || irq_timer_state[irq])
+	if (state)
 		return;
 
 	/*
@@ -926,7 +935,7 @@ void rand_initialize_irq(int irq)
 	 */
 	state = kzalloc(sizeof(struct timer_rand_state), GFP_KERNEL);
 	if (state)
-		irq_timer_state[irq] = state;
+		desc->timer_rand_state = state;
 }
 
 #ifdef CONFIG_BLOCK
diff --git a/include/linux/irq.h b/include/linux/irq.h
index aaf2029..3abdf48 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -129,6 +129,7 @@ struct irq_chip {
 	const char	*typename;
 };
 
+struct timer_rand_state;
 /**
  * struct irq_desc - interrupt descriptor
  *
@@ -158,6 +159,7 @@ struct irq_desc {
 #ifdef CONFIG_HAVE_SPARSE_IRQ
 	struct irq_desc		*next;
 #endif
+	struct timer_rand_state *timer_rand_state;
 	irq_flow_handler_t	handle_irq;
 	struct irq_chip		*chip;
 	struct msi_desc		*msi_desc;
-- 
1.5.4.5

[PATCH 30/33] x86: move kstat_irqs from kstat to irq_desc

[Yinghai Lu]

based Eric's patch ...

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


Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
---
 arch/alpha/kernel/irq.c        |    2 +-
 arch/alpha/kernel/irq_alpha.c  |    2 +-
 arch/arm/kernel/irq.c          |    2 +-
 arch/avr32/kernel/irq.c        |    2 +-
 arch/cris/kernel/irq.c         |    2 +-
 arch/frv/kernel/irq.c          |    2 +-
 arch/ia64/kernel/irq.c         |    2 +-
 arch/ia64/kernel/irq_ia64.c    |    8 ++--
 arch/m32r/kernel/irq.c         |    2 +-
 arch/mips/sgi-ip22/ip22-int.c  |    2 +-
 arch/mips/sgi-ip22/ip22-time.c |    2 +-
 arch/mips/sibyte/bcm1480/smp.c |    2 +-
 arch/mips/sibyte/sb1250/irq.c  |    2 +-
 arch/mips/sibyte/sb1250/smp.c  |    2 +-
 arch/parisc/kernel/irq.c       |    2 +-
 arch/powerpc/kernel/irq.c      |    2 +-
 arch/sh/kernel/irq.c           |    2 +-
 arch/sparc64/kernel/irq.c      |    2 +-
 arch/sparc64/kernel/time.c     |    2 +-
 arch/um/kernel/irq.c           |    2 +-
 arch/x86/kernel/io_apic_32.c   |    2 +-
 arch/x86/kernel/irq_32.c       |    4 +-
 arch/x86/kernel/irq_64.c       |    4 +-
 arch/x86/kernel/visws_quirks.c |    2 +-
 arch/xtensa/kernel/irq.c       |    2 +-
 fs/proc/proc_misc.c            |    2 +-
 include/linux/irq.h            |    7 +++
 include/linux/kernel_stat.h    |   14 +++---
 kernel/irq/chip.c              |   15 ++----
 kernel/irq/handle.c            |   97 +++++++++++++++++++++++++++++-----------
 kernel/sched.c                 |    5 +--
 31 files changed, 120 insertions(+), 80 deletions(-)

diff --git a/arch/alpha/kernel/irq.c b/arch/alpha/kernel/irq.c
index c626a82..6728331 100644
--- a/arch/alpha/kernel/irq.c
+++ b/arch/alpha/kernel/irq.c
@@ -89,7 +89,7 @@ show_interrupts(struct seq_file *p, void *v)
 		seq_printf(p, "%10u ", kstat_irqs(irq));
 #else
 		for_each_online_cpu(j)
-			seq_printf(p, "%10u ", kstat_cpu(j).irqs[irq]);
+			seq_printf(p, "%10u ", kstat_irqs_cpu(irq, j));
 #endif
 		seq_printf(p, " %14s", irq_desc[irq].chip->typename);
 		seq_printf(p, "  %c%s",
diff --git a/arch/alpha/kernel/irq_alpha.c b/arch/alpha/kernel/irq_alpha.c
index e16aeb6..5f98d99 100644
--- a/arch/alpha/kernel/irq_alpha.c
+++ b/arch/alpha/kernel/irq_alpha.c
@@ -64,7 +64,7 @@ do_entInt(unsigned long type, unsigned long vector,
 		smp_percpu_timer_interrupt(regs);
 		cpu = smp_processor_id();
 		if (cpu != boot_cpuid) {
-		        kstat_cpu(cpu).irqs[RTC_IRQ]++;
+		        irq_desc[RTC_IRQ].kstat_irqs[cpu]++;
 		} else {
 			handle_irq(RTC_IRQ);
 		}
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index 11dcd52..3da3252 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -75,7 +75,7 @@ int show_interrupts(struct seq_file *p, void *v)
 
 		seq_printf(p, "%3d: ", i);
 		for_each_present_cpu(cpu)
-			seq_printf(p, "%10u ", kstat_cpu(cpu).irqs[i]);
+			seq_printf(p, "%10u ", kstat_irqs_cpu(i, cpu));
 		seq_printf(p, " %10s", irq_desc[i].chip->name ? : "-");
 		seq_printf(p, "  %s", action->name);
 		for (action = action->next; action; action = action->next)
diff --git a/arch/avr32/kernel/irq.c b/arch/avr32/kernel/irq.c
index a8e767d..9f57222 100644
--- a/arch/avr32/kernel/irq.c
+++ b/arch/avr32/kernel/irq.c
@@ -58,7 +58,7 @@ int show_interrupts(struct seq_file *p, void *v)
 
 		seq_printf(p, "%3d: ", i);
 		for_each_online_cpu(cpu)
-			seq_printf(p, "%10u ", kstat_cpu(cpu).irqs[i]);
+			seq_printf(p, "%10u ", kstat_irqs_cpu(i, cpu));
 		seq_printf(p, " %8s", irq_desc[i].chip->name ? : "-");
 		seq_printf(p, "  %s", action->name);
 		for (action = action->next; action; action = action->next)
diff --git a/arch/cris/kernel/irq.c b/arch/cris/kernel/irq.c
index 2dfac8c..86b9113 100644
--- a/arch/cris/kernel/irq.c
+++ b/arch/cris/kernel/irq.c
@@ -66,7 +66,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_printf(p, "%10u ", kstat_irqs(i));
 #else
 		for_each_online_cpu(j)
-			seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
+			seq_printf(p, "%10u ", kstat_irqs_cpu(i,j));
 #endif
 		seq_printf(p, " %14s", irq_desc[i].chip->typename);
 		seq_printf(p, "  %s", action->name);
diff --git a/arch/frv/kernel/irq.c b/arch/frv/kernel/irq.c
index 73abae7..af3e824 100644
--- a/arch/frv/kernel/irq.c
+++ b/arch/frv/kernel/irq.c
@@ -74,7 +74,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		if (action) {
 			seq_printf(p, "%3d: ", i);
 			for_each_present_cpu(cpu)
-				seq_printf(p, "%10u ", kstat_cpu(cpu).irqs[i]);
+				seq_printf(p, "%10u ", kstat_irqs_cpu(i, cpu));
 			seq_printf(p, " %10s", irq_desc[i].chip->name ? : "-");
 			seq_printf(p, "  %s", action->name);
 			for (action = action->next;
diff --git a/arch/ia64/kernel/irq.c b/arch/ia64/kernel/irq.c
index 7fd18f5..4140d51 100644
--- a/arch/ia64/kernel/irq.c
+++ b/arch/ia64/kernel/irq.c
@@ -80,7 +80,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_printf(p, "%10u ", kstat_irqs(i));
 #else
 		for_each_online_cpu(j) {
-			seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
+			seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
 		}
 #endif
 		seq_printf(p, " %14s", irq_desc[i].chip->name);
diff --git a/arch/ia64/kernel/irq_ia64.c b/arch/ia64/kernel/irq_ia64.c
index 28d3d48..fa0fe39 100644
--- a/arch/ia64/kernel/irq_ia64.c
+++ b/arch/ia64/kernel/irq_ia64.c
@@ -495,9 +495,9 @@ ia64_handle_irq (ia64_vector vector, struct pt_regs *regs)
 	while (vector != IA64_SPURIOUS_INT_VECTOR) {
 		if (unlikely(IS_LOCAL_TLB_FLUSH(vector))) {
 			smp_local_flush_tlb();
-			kstat_this_cpu.irqs[vector]++;
+			kstat_irqs_this_cpu(&irq_desc[vector])++;
 		} else if (unlikely(IS_RESCHEDULE(vector)))
-			kstat_this_cpu.irqs[vector]++;
+			kstat_irqs_this_cpu(&irq_desc[vector])++;
 		else {
 			int irq = local_vector_to_irq(vector);
 
@@ -553,9 +553,9 @@ void ia64_process_pending_intr(void)
 	while (vector != IA64_SPURIOUS_INT_VECTOR) {
 		if (unlikely(IS_LOCAL_TLB_FLUSH(vector))) {
 			smp_local_flush_tlb();
-			kstat_this_cpu.irqs[vector]++;
+			kstat_irqs_this_cpu(&irq_desc[vector])++;
 		} else if (unlikely(IS_RESCHEDULE(vector)))
-			kstat_this_cpu.irqs[vector]++;
+			kstat_irqs_this_cpu(&irq_desc[vector])++;
 		else {
 			struct pt_regs *old_regs = set_irq_regs(NULL);
 			int irq = local_vector_to_irq(vector);
diff --git a/arch/m32r/kernel/irq.c b/arch/m32r/kernel/irq.c
index d0c5b0b..63684e8 100644
--- a/arch/m32r/kernel/irq.c
+++ b/arch/m32r/kernel/irq.c
@@ -52,7 +52,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_printf(p, "%10u ", kstat_irqs(i));
 #else
 		for_each_online_cpu(j)
-			seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
+			seq_printf(p, "%10u ", kstat_irqs_cpu(i,j));
 #endif
 		seq_printf(p, " %14s", irq_desc[i].chip->typename);
 		seq_printf(p, "  %s", action->name);
diff --git a/arch/mips/sgi-ip22/ip22-int.c b/arch/mips/sgi-ip22/ip22-int.c
index f6d9bf4..6794c76 100644
--- a/arch/mips/sgi-ip22/ip22-int.c
+++ b/arch/mips/sgi-ip22/ip22-int.c
@@ -164,7 +164,7 @@ static void indy_buserror_irq(void)
 	int irq = SGI_BUSERR_IRQ;
 
 	irq_enter();
-	kstat_this_cpu.irqs[irq]++;
+	kstat_irqs_this_cpu(&irq_desc[irq])++;
 	ip22_be_interrupt(irq);
 	irq_exit();
 }
diff --git a/arch/mips/sgi-ip22/ip22-time.c b/arch/mips/sgi-ip22/ip22-time.c
index 10e5054..f744b2e 100644
--- a/arch/mips/sgi-ip22/ip22-time.c
+++ b/arch/mips/sgi-ip22/ip22-time.c
@@ -186,7 +186,7 @@ void indy_8254timer_irq(void)
 	char c;
 
 	irq_enter();
-	kstat_this_cpu.irqs[irq]++;
+	kstat_irqs_this_cpu(&irq_desc[irq])++;
 	printk(KERN_ALERT "Oops, got 8254 interrupt.\n");
 	ArcRead(0, &c, 1, &cnt);
 	ArcEnterInteractiveMode();
diff --git a/arch/mips/sibyte/bcm1480/smp.c b/arch/mips/sibyte/bcm1480/smp.c
index bd9eeb4..6f09896 100644
--- a/arch/mips/sibyte/bcm1480/smp.c
+++ b/arch/mips/sibyte/bcm1480/smp.c
@@ -180,7 +180,7 @@ void bcm1480_mailbox_interrupt(void)
 	int cpu = smp_processor_id();
 	unsigned int action;
 
-	kstat_this_cpu.irqs[K_BCM1480_INT_MBOX_0_0]++;
+	irq_desc[K_BCM1480_INT_MBOX_0_0].kstat_irqs[cpu]++;
 	/* Load the mailbox register to figure out what we're supposed to do */
 	action = (__raw_readq(mailbox_0_regs[cpu]) >> 48) & 0xffff;
 
diff --git a/arch/mips/sibyte/sb1250/irq.c b/arch/mips/sibyte/sb1250/irq.c
index eac9065..7e388e6 100644
--- a/arch/mips/sibyte/sb1250/irq.c
+++ b/arch/mips/sibyte/sb1250/irq.c
@@ -353,7 +353,7 @@ static void sb1250_kgdb_interrupt(void)
 	 * host to stop the break, since we would see another
 	 * interrupt on the end-of-break too)
 	 */
-	kstat_this_cpu.irqs[kgdb_irq]++;
+	kstat_irqs_this_cpu(&irq_desc[kgdb_irq])++;
 	mdelay(500);
 	duart_out(R_DUART_CMD, V_DUART_MISC_CMD_RESET_BREAK_INT |
 				M_DUART_RX_EN | M_DUART_TX_EN);
diff --git a/arch/mips/sibyte/sb1250/smp.c b/arch/mips/sibyte/sb1250/smp.c
index 0734b93..dd0e55e 100644
--- a/arch/mips/sibyte/sb1250/smp.c
+++ b/arch/mips/sibyte/sb1250/smp.c
@@ -168,7 +168,7 @@ void sb1250_mailbox_interrupt(void)
 	int cpu = smp_processor_id();
 	unsigned int action;
 
-	kstat_this_cpu.irqs[K_INT_MBOX_0]++;
+	irq_desc[K_INT_MBOX_0].kstat_irqs[cpu]++;
 	/* Load the mailbox register to figure out what we're supposed to do */
 	action = (____raw_readq(mailbox_regs[cpu]) >> 48) & 0xffff;
 
diff --git a/arch/parisc/kernel/irq.c b/arch/parisc/kernel/irq.c
index 23ef950..09336cc 100644
--- a/arch/parisc/kernel/irq.c
+++ b/arch/parisc/kernel/irq.c
@@ -183,7 +183,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_printf(p, "%3d: ", i);
 #ifdef CONFIG_SMP
 		for_each_online_cpu(j)
-			seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
+			seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
 #else
 		seq_printf(p, "%10u ", kstat_irqs(i));
 #endif
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 6ac8612..17e5f78 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -200,7 +200,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_printf(p, "%3d: ", i);
 #ifdef CONFIG_SMP
 		for_each_online_cpu(j)
-			seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
+			seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
 #else
 		seq_printf(p, "%10u ", kstat_irqs(i));
 #endif /* CONFIG_SMP */
diff --git a/arch/sh/kernel/irq.c b/arch/sh/kernel/irq.c
index a2a99e4..1e75217 100644
--- a/arch/sh/kernel/irq.c
+++ b/arch/sh/kernel/irq.c
@@ -51,7 +51,7 @@ int show_interrupts(struct seq_file *p, void *v)
 			goto unlock;
 		seq_printf(p, "%3d: ",i);
 		for_each_online_cpu(j)
-			seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
+			seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
 		seq_printf(p, " %14s", irq_desc[i].chip->name);
 		seq_printf(p, "-%-8s", irq_desc[i].name);
 		seq_printf(p, "  %s", action->name);
diff --git a/arch/sparc64/kernel/irq.c b/arch/sparc64/kernel/irq.c
index c481673..4128f01 100644
--- a/arch/sparc64/kernel/irq.c
+++ b/arch/sparc64/kernel/irq.c
@@ -185,7 +185,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_printf(p, "%10u ", kstat_irqs(i));
 #else
 		for_each_online_cpu(j)
-			seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
+			seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
 #endif
 		seq_printf(p, " %9s", irq_desc[i].chip->typename);
 		seq_printf(p, "  %s", action->name);
diff --git a/arch/sparc64/kernel/time.c b/arch/sparc64/kernel/time.c
index a0c6a97..cba800d 100644
--- a/arch/sparc64/kernel/time.c
+++ b/arch/sparc64/kernel/time.c
@@ -942,7 +942,7 @@ void timer_interrupt(int irq, struct pt_regs *regs)
 
 	irq_enter();
 
-	kstat_this_cpu.irqs[0]++;
+	irq_desc[0].kstat_irqs[0]++;
 
 	if (unlikely(!evt->event_handler)) {
 		printk(KERN_WARNING
diff --git a/arch/um/kernel/irq.c b/arch/um/kernel/irq.c
index 3d7aad0..336b615 100644
--- a/arch/um/kernel/irq.c
+++ b/arch/um/kernel/irq.c
@@ -42,7 +42,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_printf(p, "%10u ", kstat_irqs(i));
 #else
 		for_each_online_cpu(j)
-			seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
+			seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
 #endif
 		seq_printf(p, " %14s", irq_desc[i].chip->typename);
 		seq_printf(p, "  %s", action->name);
diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index 57a0f61..ac5413e 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -526,7 +526,7 @@ static void do_irq_balance(void)
 			if (package_index == i)
 				IRQ_DELTA(package_index, j) = 0;
 			/* Determine the total count per processor per IRQ */
-			value_now = (unsigned long) kstat_cpu(i).irqs[j];
+			value_now = (unsigned long) kstat_irqs_cpu(j,i);
 
 			/* Determine the activity per processor per IRQ */
 			delta = value_now - LAST_CPU_IRQ(i, j);
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 6bad8a2..4f2f16d 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -280,7 +280,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		any_count = kstat_irqs(i);
 #else
 		for_each_online_cpu(j)
-			any_count |= kstat_cpu(j).irqs[i];
+			any_count |= kstat_irqs_cpu(i, j);
 #endif
 		action = desc->action;
 		if (!action && !any_count)
@@ -290,7 +290,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_printf(p, "%10u ", kstat_irqs(i));
 #else
 		for_each_online_cpu(j)
-			seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
+			seq_printf(p, "%10u ", kstat_irqs_cpu(i,j));
 #endif
 		seq_printf(p, " %8s", desc->chip->name);
 		seq_printf(p, "-%-8s", desc->name);
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index cf5524b..dde7191 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -90,7 +90,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		any_count = kstat_irqs(i);
 #else
 		for_each_online_cpu(j)
-			any_count |= kstat_cpu(j).irqs[i];
+			any_count |= kstat_irqs_cpu(i, j);
 #endif
 		action = desc->action;
 		if (!action && !any_count)
@@ -100,7 +100,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_printf(p, "%10u ", kstat_irqs(i));
 #else
 		for_each_online_cpu(j)
-			seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
+			seq_printf(p, "%10u ", kstat_irqs_cpu(i,j));
 #endif
 		seq_printf(p, " %8s", desc->chip->name);
 		seq_printf(p, "-%-8s", desc->name);
diff --git a/arch/x86/kernel/visws_quirks.c b/arch/x86/kernel/visws_quirks.c
index cd6f273..c0a8326 100644
--- a/arch/x86/kernel/visws_quirks.c
+++ b/arch/x86/kernel/visws_quirks.c
@@ -635,7 +635,7 @@ static irqreturn_t piix4_master_intr(int irq, void *dev_id)
 	/*
 	 * handle this 'virtual interrupt' as a Cobalt one now.
 	 */
-	kstat_cpu(smp_processor_id()).irqs[realirq]++;
+	kstat_irqs_this_cpu(desc)++;
 
 	if (likely(desc->action != NULL))
 		handle_IRQ_event(realirq, desc->action);
diff --git a/arch/xtensa/kernel/irq.c b/arch/xtensa/kernel/irq.c
index c9ea73b..c35e271 100644
--- a/arch/xtensa/kernel/irq.c
+++ b/arch/xtensa/kernel/irq.c
@@ -99,7 +99,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_printf(p, "%10u ", kstat_irqs(i));
 #else
 		for_each_online_cpu(j)
-			seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
+			seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
 #endif
 		seq_printf(p, " %14s", irq_desc[i].chip->typename);
 		seq_printf(p, "  %s", action->name);
diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
index 1968251..aeb0a40 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -526,7 +526,7 @@ static int show_stat(struct seq_file *p, void *v)
 		steal = cputime64_add(steal, kstat_cpu(i).cpustat.steal);
 		guest = cputime64_add(guest, kstat_cpu(i).cpustat.guest);
 		for (j = 0; j < nr_irqs; j++) {
-			unsigned int temp = kstat_cpu(i).irqs[j];
+			unsigned int temp = kstat_irqs_cpu(j, i);
 			sum += temp;
 			per_irq_sum[j] += temp;
 		}
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 3abdf48..7fbc9c2 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -159,6 +159,11 @@ struct irq_desc {
 #ifdef CONFIG_HAVE_SPARSE_IRQ
 	struct irq_desc		*next;
 #endif
+#ifdef CONFIG_HAVE_DYN_ARRAY
+	unsigned int		*kstat_irqs;
+#else
+	unsigned int		kstat_irqs[NR_CPUS];
+#endif
 	struct timer_rand_state *timer_rand_state;
 	irq_flow_handler_t	handle_irq;
 	struct irq_chip		*chip;
@@ -192,6 +197,8 @@ extern struct irq_desc *get_irq_desc(unsigned int irq);
 /* could be removed if we get rid of all irq_desc reference */
 extern struct irq_desc irq_desc[NR_IRQS];
 #endif
+#define kstat_irqs_this_cpu(DESC) \
+	((DESC)->kstat_irqs[smp_processor_id()])
 
 /*
  * Migration helpers for obsolete names, they will go away:
diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index fe1f7fe..8d8e84b 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -28,11 +28,6 @@ struct cpu_usage_stat {
 
 struct kernel_stat {
 	struct cpu_usage_stat	cpustat;
-#ifdef CONFIG_HAVE_DYN_ARRAY
-	unsigned int *irqs;
-#else
-	unsigned int irqs[NR_IRQS];
-#endif
 };
 
 DECLARE_PER_CPU(struct kernel_stat, kstat);
@@ -43,15 +38,18 @@ DECLARE_PER_CPU(struct kernel_stat, kstat);
 
 extern unsigned long long nr_context_switches(void);
 
+extern unsigned int kstat_irqs_cpu(unsigned int irq, int cpu);
+
 /*
  * Number of interrupts per specific IRQ source, since bootup
  */
-static inline int kstat_irqs(int irq)
+static inline unsigned int kstat_irqs(unsigned int irq)
 {
-	int cpu, sum = 0;
+	unsigned int sum = 0;
+	int cpu;
 
 	for_each_possible_cpu(cpu)
-		sum += kstat_cpu(cpu).irqs[irq];
+		sum += kstat_irqs_cpu(irq, cpu);
 
 	return sum;
 }
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index df1222f..d09800a 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -311,14 +311,13 @@ handle_simple_irq(unsigned int irq, struct irq_desc *desc)
 {
 	struct irqaction *action;
 	irqreturn_t action_ret;
-	const unsigned int cpu = smp_processor_id();
 
 	spin_lock(&desc->lock);
 
 	if (unlikely(desc->status & IRQ_INPROGRESS))
 		goto out_unlock;
 	desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
-	kstat_cpu(cpu).irqs[irq]++;
+	kstat_irqs_this_cpu(desc)++;
 
 	action = desc->action;
 	if (unlikely(!action || (desc->status & IRQ_DISABLED)))
@@ -350,7 +349,6 @@ out_unlock:
 void
 handle_level_irq(unsigned int irq, struct irq_desc *desc)
 {
-	unsigned int cpu = smp_processor_id();
 	struct irqaction *action;
 	irqreturn_t action_ret;
 
@@ -360,7 +358,7 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc)
 	if (unlikely(desc->status & IRQ_INPROGRESS))
 		goto out_unlock;
 	desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
-	kstat_cpu(cpu).irqs[irq]++;
+	kstat_irqs_this_cpu(desc)++;
 
 	/*
 	 * If its disabled or no action available
@@ -398,7 +396,6 @@ out_unlock:
 void
 handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
 {
-	unsigned int cpu = smp_processor_id();
 	struct irqaction *action;
 	irqreturn_t action_ret;
 
@@ -408,7 +405,7 @@ handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
 		goto out;
 
 	desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
-	kstat_cpu(cpu).irqs[irq]++;
+	kstat_irqs_this_cpu(desc)++;
 
 	/*
 	 * If its disabled or no action available
@@ -457,8 +454,6 @@ out:
 void
 handle_edge_irq(unsigned int irq, struct irq_desc *desc)
 {
-	const unsigned int cpu = smp_processor_id();
-
 	spin_lock(&desc->lock);
 
 	desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
@@ -475,7 +470,7 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
 		goto out_unlock;
 	}
 
-	kstat_cpu(cpu).irqs[irq]++;
+	kstat_irqs_this_cpu(desc)++;
 
 	/* Start handling the irq */
 	desc->chip->ack(irq);
@@ -530,7 +525,7 @@ handle_percpu_irq(unsigned int irq, struct irq_desc *desc)
 {
 	irqreturn_t action_ret;
 
-	kstat_this_cpu.irqs[irq]++;
+	kstat_irqs_this_cpu(desc)++;
 
 	if (desc->chip->ack)
 		desc->chip->ack(irq);
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 6bc8502..67f8d9d 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -37,7 +37,7 @@ void
 handle_bad_irq(unsigned int irq, struct irq_desc *desc)
 {
 	print_irq_desc(irq, desc);
-	kstat_this_cpu.irqs[irq]++;
+	kstat_irqs_this_cpu(desc)++;
 	ack_bad_irq(irq);
 }
 
@@ -79,17 +79,38 @@ static void init_one_irq_desc(struct irq_desc *desc)
 #endif
 }
 
-#ifdef CONFIG_HAVE_SPARSE_IRQ
-static int nr_irq_desc = 32;
+extern int after_bootmem;
+extern void *__alloc_bootmem_nopanic(unsigned long size,
+			     unsigned long align,
+			     unsigned long goal);
 
-static int __init parse_nr_irq_desc(char *arg)
+static void init_kstat_irqs(struct irq_desc *desc, int nr_desc, int nr)
 {
-	if (arg)
-		nr_irq_desc = simple_strtoul(arg, NULL, 0);
-	return 0;
+	unsigned long bytes, total_bytes;
+	char *ptr;
+	int i;
+	unsigned long phys;
+
+	/* Compute how many bytes we need per irq and allocate them */
+	bytes = nr * sizeof(unsigned int);
+	total_bytes = bytes * nr_desc;
+	if (after_bootmem)
+		ptr = kzalloc(total_bytes, GFP_ATOMIC);
+	else
+		ptr = __alloc_bootmem_nopanic(total_bytes, PAGE_SIZE, 0);
+
+	if (!ptr)
+		panic(" can not allocate kstat_irqs\n");
+
+	phys = __pa(ptr);
+	printk(KERN_DEBUG "kstat_irqs ==> [%#lx - %#lx]\n", phys, phys + total_bytes);
+
+	for (i = 0; i < nr_desc; i++) {
+		desc[i].kstat_irqs = (unsigned int *)ptr;
+		ptr += bytes;
+	}
 }
 
-early_param("nr_irq_desc", parse_nr_irq_desc);
 
 static void __init init_work(void *data)
 {
@@ -99,25 +120,44 @@ static void __init init_work(void *data)
 
 	desc = *da->name;
 
-	for (i = 0; i < *da->nr; i++)
+	for (i = 0; i < *da->nr; i++) {
 		init_one_irq_desc(&desc[i]);
+#ifdef CONFIG_HAVE_SPARSE_IRQ
+		desc[i].irq = i;
+#endif
+	}
 
+#ifdef CONFIG_HAVE_SPARSE_IRQ
 	for (i = 1; i < *da->nr; i++)
 		desc[i-1].next = &desc[i];
+#endif
+
+	/* init kstat_irqs, nr_cpu_ids is ready already */
+	init_kstat_irqs(desc, *da->nr, nr_cpu_ids);
 }
 
+#ifdef CONFIG_HAVE_SPARSE_IRQ
+static int nr_irq_desc = 32;
+
+static int __init parse_nr_irq_desc(char *arg)
+{
+	if (arg)
+		nr_irq_desc = simple_strtoul(arg, NULL, 0);
+	return 0;
+}
+
+early_param("nr_irq_desc", parse_nr_irq_desc);
+
 static struct irq_desc *irq_desc;
 DEFINE_DYN_ARRAY(irq_desc, sizeof(struct irq_desc), nr_irq_desc, PAGE_SIZE, init_work);
 
-extern int after_bootmem;
-extern void *__alloc_bootmem_nopanic(unsigned long size,
-			     unsigned long align,
-			     unsigned long goal);
 struct irq_desc *get_irq_desc(unsigned int irq)
 {
 	struct irq_desc *desc, *desc_pri;
 	int i;
 	int count = 0;
+	unsigned long phys;
+	unsigned long total_bytes;
 
 	BUG_ON(irq == -1U);
 
@@ -140,38 +180,34 @@ struct irq_desc *get_irq_desc(unsigned int irq)
 	 */
 	printk(KERN_DEBUG "try to get more irq_desc %d\n", nr_irq_desc);
 
+	total_bytes = sizeof(struct irq_desc) * nr_irq_desc;
 	if (after_bootmem)
-		desc = kzalloc(sizeof(struct irq_desc)*nr_irq_desc, GFP_ATOMIC);
+		desc = kzalloc(total_bytes, GFP_ATOMIC);
 	else
-		desc = __alloc_bootmem_nopanic(sizeof(struct irq_desc)*nr_irq_desc, PAGE_SIZE, 0);
+		desc = __alloc_bootmem_nopanic(total_bytes, PAGE_SIZE, 0);
 
         if (!desc)
 		panic("please boot with nr_irq_desc= %d\n", count * 2);
 
+	phys = __pa(desc);
+	printk(KERN_DEBUG "irq_desc ==> [%#lx - %#lx]\n", phys, phys + total_bytes);
+
 	for (i = 0; i < nr_irq_desc; i++)
 		init_one_irq_desc(&desc[i]);
 
 	for (i = 1; i < nr_irq_desc; i++)
 		desc[i-1].next = &desc[i];
 
+	/* init kstat_irqs, nr_cpu_ids is ready already */
+	init_kstat_irqs(desc, nr_irq_desc, nr_cpu_ids);
+
 	desc->irq = irq;
 	desc_pri->next = desc;
 
 	return desc;
 }
 #else
-static void __init init_work(void *data)
-{
-	struct dyn_array *da = data;
-	int i;
-	struct  irq_desc *desc;
-
-	desc = *da->name;
 
-	for (i = 0; i < *da->nr; i++)
-		init_one_irq_desc(&desc[i]);
-
-}
 static struct irq_desc *irq_desc;
 DEFINE_DYN_ARRAY(irq_desc, sizeof(struct irq_desc), nr_irqs, PAGE_SIZE, init_work);
 
@@ -314,7 +350,7 @@ unsigned int __do_IRQ(unsigned int irq)
 	struct irqaction *action;
 	unsigned int status;
 
-	kstat_this_cpu.irqs[irq]++;
+	kstat_irqs_this_cpu(desc)++;
 	if (CHECK_IRQ_PER_CPU(desc->status)) {
 		irqreturn_t action_ret;
 
@@ -414,3 +450,10 @@ void early_init_irq_lock_class(void)
 }
 #endif
 
+unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
+{
+	struct irq_desc *desc = get_irq_desc(irq);
+	return desc->kstat_irqs[cpu];
+}
+EXPORT_SYMBOL(kstat_irqs_cpu);
+
diff --git a/kernel/sched.c b/kernel/sched.c
index 21c0839..55cb4ce 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4021,11 +4021,8 @@ static inline void idle_balance(int cpu, struct rq *rq)
 #endif
 
 DEFINE_PER_CPU(struct kernel_stat, kstat);
-EXPORT_PER_CPU_SYMBOL(kstat);
 
-#ifdef CONFIG_HAVE_DYN_ARRAY
-DEFINE_PER_CPU_DYN_ARRAY_ADDR(per_cpu__kstat_irqs, per_cpu__kstat.irqs, sizeof(unsigned int), nr_irqs, sizeof(unsigned long), NULL);
-#endif
+EXPORT_PER_CPU_SYMBOL(kstat);
 
 /*
  * Return p->sum_exec_runtime plus any more ns on the sched_clock
-- 
1.5.4.5

[PATCH 31/33] replace loop with nr_irqs with for_each_irq_desc

[Yinghai Lu]

so don't all get_irq_desc at begining to allocate all.
and only call that when needed

/proc/interrupts related still use old ways... for compatablilty reason.

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
---
 arch/x86/kernel/io_apic_64.c |   30 +++++++++++++++---------------
 arch/x86/kernel/irq_64.c     |    5 ++---
 arch/x86/kernel/irqinit_64.c |   17 +++++------------
 fs/proc/proc_misc.c          |    7 +++++--
 include/linux/irq.h          |   18 ++++++++++++++++++
 kernel/irq/handle.c          |   31 ++++++++++++++++++++++++++-----
 kernel/irq/internals.h       |    4 ++--
 kernel/irq/manage.c          |    2 +-
 kernel/irq/proc.c            |   10 +++++-----
 9 files changed, 79 insertions(+), 45 deletions(-)

diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
index c8e4613..8bb6565 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -129,6 +129,9 @@ static void __init init_work(void *data)
 		cfg[i-1].next = &cfg[i];
 }
 
+#define for_each_irq_cfg(cfg)		\
+	for(cfg = irq_cfgx; cfg && cfg->irq != -1U; cfg = cfg->next)
+
 static struct irq_cfg *irq_cfgx;
 DEFINE_DYN_ARRAY(irq_cfgx, sizeof(struct irq_cfg), nr_irq_cfg, PAGE_SIZE, init_work);
 
@@ -1063,20 +1066,18 @@ static void __setup_vector_irq(int cpu)
 	/* Initialize vector_irq on a new cpu */
 	/* This function must be called with vector_lock held */
 	int irq, vector;
+	struct irq_cfg *cfg;
 
 	/* Mark the inuse vectors */
-	for (irq = 0; irq < nr_irqs; ++irq) {
-		struct irq_cfg *cfg = get_irq_cfg(irq);
-
+	for_each_irq_cfg(cfg) {
 		if (!cpu_isset(cpu, cfg->domain))
 			continue;
 		vector = cfg->vector;
+		irq = cfg->irq;
 		per_cpu(vector_irq, cpu)[vector] = irq;
 	}
 	/* Mark the free vectors */
 	for (vector = 0; vector < NR_VECTORS; ++vector) {
-		struct irq_cfg *cfg;
-
 		irq = per_cpu(vector_irq, cpu)[vector];
 		if (irq < 0)
 			continue;
@@ -1312,6 +1313,7 @@ __apicdebuginit(void) print_IO_APIC(void)
 	union IO_APIC_reg_01 reg_01;
 	union IO_APIC_reg_02 reg_02;
 	unsigned long flags;
+	struct irq_cfg *cfg;
 
 	if (apic_verbosity == APIC_QUIET)
 		return;
@@ -1380,12 +1382,11 @@ __apicdebuginit(void) print_IO_APIC(void)
 	}
 	}
 	printk(KERN_DEBUG "IRQ to pin mappings:\n");
-	for (i = 0; i < nr_irqs; i++) {
-		struct irq_cfg *cfg = get_irq_cfg(i);
+	for_each_irq_cfg(cfg) {
 		struct irq_pin_list *entry = cfg->irq_2_pin;
 		if (!entry)
 			continue;
-		printk(KERN_DEBUG "IRQ%d ", i);
+		printk(KERN_DEBUG "IRQ%d ", cfg->irq);
 		for (;;) {
 			printk("-> %d:%d", entry->apic, entry->pin);
 			if (!entry->next)
@@ -1845,10 +1846,10 @@ unmask:
 
 static void ir_irq_migration(struct work_struct *work)
 {
-	int irq;
+	unsigned int irq;
+	struct irq_desc *desc;
 
-	for (irq = 0; irq < nr_irqs; irq++) {
-		struct irq_desc *desc = get_irq_desc(irq);
+	for_each_irq_desc(irq, desc) {
 		if (desc->status & IRQ_MOVE_PENDING) {
 			unsigned long flags;
 
@@ -2044,6 +2045,7 @@ static inline void init_IO_APIC_traps(void)
 {
 	int irq;
 	struct irq_desc *desc;
+	struct irq_cfg *cfg;
 
 	/*
 	 * NOTE! The local APIC isn't very good at handling
@@ -2056,10 +2058,8 @@ static inline void init_IO_APIC_traps(void)
 	 * Also, we've got to be careful not to trash gate
 	 * 0x80, because int 0x80 is hm, kind of importantish. ;)
 	 */
-	for (irq = 0; irq < nr_irqs ; irq++) {
-		struct irq_cfg *cfg;
-
-		cfg = get_irq_cfg(irq);
+	for_each_irq_cfg(cfg) {
+		irq = cfg->irq;
 		if (IO_APIC_IRQ(irq) && !cfg->vector) {
 			/*
 			 * Hmm.. We don't have an entry for this,
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index dde7191..c2fe49f 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -224,17 +224,16 @@ void fixup_irqs(cpumask_t map)
 {
 	unsigned int irq;
 	static int warned;
+	struct irq_desc *desc;
 
-	for (irq = 0; irq < nr_irqs; irq++) {
+	for_each_irq_desc(irq, desc) {
 		cpumask_t mask;
 		int break_affinity = 0;
 		int set_affinity = 1;
-		struct irq_desc *desc;
 
 		if (irq == 2)
 			continue;
 
-		desc = get_irq_desc(irq);
 		/* interrupt's are disabled at this point */
 		spin_lock(&desc->lock);
 
diff --git a/arch/x86/kernel/irqinit_64.c b/arch/x86/kernel/irqinit_64.c
index 8a7a5a8..daed12a 100644
--- a/arch/x86/kernel/irqinit_64.c
+++ b/arch/x86/kernel/irqinit_64.c
@@ -142,25 +142,18 @@ static void __init init_ISA_irqs (void)
 	init_bsp_APIC();
 	init_8259A(0);
 
-	for (i = 0; i < nr_irqs; i++) {
+	for (i = 0; i < 16; i++) {
 		struct irq_desc *desc = get_irq_desc(i);
 
 		desc->status = IRQ_DISABLED;
 		desc->action = NULL;
 		desc->depth = 1;
 
-		if (i < 16) {
-			/*
-			 * 16 old-style INTA-cycle interrupts:
-			 */
-			set_irq_chip_and_handler_name(i, &i8259A_chip,
+		/*
+		 * 16 old-style INTA-cycle interrupts:
+		 */
+		set_irq_chip_and_handler_name(i, &i8259A_chip,
 						      handle_level_irq, "XT");
-		} else {
-			/*
-			 * 'high' PCI IRQs filled in on demand
-			 */
-			desc->chip = &no_irq_chip;
-		}
 	}
 }
 
diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
index aeb0a40..32de344 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -502,6 +502,7 @@ static int show_stat(struct seq_file *p, void *v)
 	u64 sum = 0;
 	struct timespec boottime;
 	unsigned int *per_irq_sum;
+	struct irq_desc *desc;
 
 	per_irq_sum = kzalloc(sizeof(unsigned int)*nr_irqs, GFP_KERNEL);
 	if (!per_irq_sum)
@@ -525,8 +526,10 @@ static int show_stat(struct seq_file *p, void *v)
 		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 (j = 0; j < nr_irqs; j++) {
-			unsigned int temp = kstat_irqs_cpu(j, i);
+		for_each_irq_desc(j, desc) {
+			unsigned int temp;
+
+			temp = kstat_irqs_cpu(j, i);
 			sum += temp;
 			per_irq_sum[j] += temp;
 		}
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 7fbc9c2..621abf4 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -193,10 +193,28 @@ struct irq_desc {
 } ____cacheline_internodealigned_in_smp;
 
 extern struct irq_desc *get_irq_desc(unsigned int irq);
+extern struct irq_desc *get_irq_desc_without_new(unsigned int irq);
+
+#ifndef CONFIG_HAVE_SPARSE_IRQ
+
 #ifndef CONFIG_HAVE_DYN_ARRAY
 /* could be removed if we get rid of all irq_desc reference */
 extern struct irq_desc irq_desc[NR_IRQS];
+#else
+extern struct irq_desc *irq_desc;
+#endif
+
+#define for_each_irq_desc(irq, desc)		\
+	for (irq = 0, desc = irq_desc; irq < nr_irqs; irq++, desc = &irq_desc[irq])
+
+#else
+
+extern struct irq_desc *irq_descX;
+#define for_each_irq_desc(irqX, desc)		\
+	for (desc = irq_descX, irqX = desc->irq; desc && irqX != -1U; desc = desc->next, irqX = desc ? desc->irq: -1U)
+
 #endif
+
 #define kstat_irqs_this_cpu(DESC) \
 	((DESC)->kstat_irqs[smp_processor_id()])
 
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 67f8d9d..a2750b8 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -111,7 +111,6 @@ static void init_kstat_irqs(struct irq_desc *desc, int nr_desc, int nr)
 	}
 }
 
-
 static void __init init_work(void *data)
 {
 	struct dyn_array *da = data;
@@ -148,9 +147,27 @@ static int __init parse_nr_irq_desc(char *arg)
 
 early_param("nr_irq_desc", parse_nr_irq_desc);
 
-static struct irq_desc *irq_desc;
-DEFINE_DYN_ARRAY(irq_desc, sizeof(struct irq_desc), nr_irq_desc, PAGE_SIZE, init_work);
+struct irq_desc *irq_descX;
+DEFINE_DYN_ARRAY(irq_descX, sizeof(struct irq_desc), nr_irq_desc, PAGE_SIZE, init_work);
 
+struct irq_desc *get_irq_desc_without_new(unsigned int irq)
+{
+	struct irq_desc *desc;
+
+	BUG_ON(irq == -1U);
+
+	desc = &irq_descX[0];
+	while (desc) {
+		if (desc->irq == irq)
+			return desc;
+
+		if (desc->irq == -1U)
+			return NULL;
+
+		desc = desc->next;
+	}
+	return NULL;
+}
 struct irq_desc *get_irq_desc(unsigned int irq)
 {
 	struct irq_desc *desc, *desc_pri;
@@ -161,7 +178,7 @@ struct irq_desc *get_irq_desc(unsigned int irq)
 
 	BUG_ON(irq == -1U);
 
-	desc_pri = desc = &irq_desc[0];
+	desc_pri = desc = &irq_descX[0];
 	while (desc) {
 		if (desc->irq == irq)
 			return desc;
@@ -208,7 +225,7 @@ struct irq_desc *get_irq_desc(unsigned int irq)
 }
 #else
 
-static struct irq_desc *irq_desc;
+struct irq_desc *irq_desc;
 DEFINE_DYN_ARRAY(irq_desc, sizeof(struct irq_desc), nr_irqs, PAGE_SIZE, init_work);
 
 #endif
@@ -238,6 +255,10 @@ struct irq_desc *get_irq_desc(unsigned int irq)
 
 	return NULL;
 }
+struct irq_desc *get_irq_desc_without_new(unsigned int irq)
+{
+	return get_irq_desc(irq);
+}
 #endif
 
 /*
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 08a849a..605e88c 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -11,11 +11,11 @@ extern void irq_chip_set_defaults(struct irq_chip *chip);
 extern void compat_irq_chip_set_default_handler(struct irq_desc *desc);
 
 #ifdef CONFIG_PROC_FS
-extern void register_irq_proc(unsigned int irq);
+extern void register_irq_proc(unsigned int irq, struct irq_desc *desc);
 extern void register_handler_proc(unsigned int irq, struct irqaction *action);
 extern void unregister_handler_proc(unsigned int irq, struct irqaction *action);
 #else
-static inline void register_irq_proc(unsigned int irq) { }
+static inline void register_irq_proc(unsigned int irq, struct irq_desc *desc) { }
 static inline void register_handler_proc(unsigned int irq,
 					 struct irqaction *action) { }
 static inline void unregister_handler_proc(unsigned int irq,
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index f199122..13db003 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -466,7 +466,7 @@ int setup_irq(unsigned int irq, struct irqaction *new)
 	spin_unlock_irqrestore(&desc->lock, flags);
 
 	new->irq = irq;
-	register_irq_proc(irq);
+	register_irq_proc(irq, desc);
 	new->dir = NULL;
 	register_handler_proc(irq, new);
 
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 2d8b936..43c6c05 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -163,11 +163,10 @@ void register_handler_proc(unsigned int irq, struct irqaction *action)
 
 #define MAX_NAMELEN 10
 
-void register_irq_proc(unsigned int irq)
+void register_irq_proc(unsigned int irq, struct irq_desc *desc)
 {
 	char name [MAX_NAMELEN];
 	struct proc_dir_entry *entry;
-	struct irq_desc *desc = get_irq_desc(irq);
 
 	if (!root_irq_dir ||
 		(desc->chip == &no_irq_chip) || desc->dir)
@@ -226,7 +225,8 @@ void register_default_affinity_proc(void)
 
 void init_irq_proc(void)
 {
-	int i;
+	unsigned irq;
+	struct irq_desc *desc;
 
 	/* create /proc/irq */
 	root_irq_dir = proc_mkdir("irq", NULL);
@@ -238,7 +238,7 @@ void init_irq_proc(void)
 	/*
 	 * Create entries for all existing IRQs.
 	 */
-	for (i = 0; i < nr_irqs; i++)
-		register_irq_proc(i);
+	for_each_irq_desc(irq, desc)
+		register_irq_proc(irq, desc);
 }
 
-- 
1.5.4.5

[PATCH 32/33] remove >= nr_irqs checking with config_have_sparse_irq

[Yinghai Lu]

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
---
 arch/x86/kernel/io_apic_64.c |   36 ++++++++++++++++++++++++------------
 arch/x86/kernel/irq_64.c     |    2 +-
 drivers/char/random.c        |    4 ++++
 fs/proc/proc_misc.c          |   29 +++++++++++++++++------------
 kernel/irq/chip.c            |   28 +++++++++++++++++++++++++++-
 kernel/irq/manage.c          |   37 +++++++++++++++++++++++++++++++------
 6 files changed, 104 insertions(+), 32 deletions(-)

diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
index 8bb6565..1416925 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -135,6 +135,26 @@ static void __init init_work(void *data)
 static struct irq_cfg *irq_cfgx;
 DEFINE_DYN_ARRAY(irq_cfgx, sizeof(struct irq_cfg), nr_irq_cfg, PAGE_SIZE, init_work);
 
+static struct irq_cfg *get_irq_cfg_without_new(unsigned int irq)
+{
+	struct irq_cfg *cfg;
+
+	BUG_ON(irq == -1U);
+
+	cfg = &irq_cfgx[0];
+	while (cfg) {
+		if (cfg->irq == irq)
+			return cfg;
+
+		if (cfg->irq == -1U) {
+			return NULL;
+		}
+		cfg = cfg->next;
+	}
+
+	return NULL;
+}
+
 static struct irq_cfg *get_irq_cfg(unsigned int irq)
 {
 	struct irq_cfg *cfg, *cfg_pri;
@@ -380,7 +400,6 @@ static inline void io_apic_sync(unsigned int apic)
 	struct irq_cfg *cfg;						\
 	struct irq_pin_list *entry;					\
 									\
-	BUG_ON(irq >= nr_irqs);						\
 	cfg = get_irq_cfg(irq);						\
 	entry = cfg->irq_2_pin;						\
 	for (;;) {							\
@@ -460,7 +479,6 @@ static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, u8 vector)
 	struct irq_cfg *cfg;
 	struct irq_pin_list *entry;
 
-	BUG_ON(irq >= nr_irqs);
 	cfg = get_irq_cfg(irq);
 	entry = cfg->irq_2_pin;
 	for (;;) {
@@ -529,7 +547,6 @@ static void add_pin_to_irq(unsigned int irq, int apic, int pin)
 	struct irq_cfg *cfg;
 	struct irq_pin_list *entry;
 
-	BUG_ON(irq >= nr_irqs);
 	cfg = get_irq_cfg(irq);
 	entry = cfg->irq_2_pin;
 	if (!entry) {
@@ -820,7 +837,6 @@ int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin)
 				best_guess = irq;
 		}
 	}
-	BUG_ON(best_guess >= nr_irqs);
 	return best_guess;
 }
 
@@ -952,7 +968,6 @@ static int pin_2_irq(int idx, int apic, int pin)
 			irq += nr_ioapic_registers[i++];
 		irq += pin;
 	}
-	BUG_ON(irq >= nr_irqs);
 	return irq;
 }
 
@@ -974,7 +989,6 @@ static int __assign_irq_vector(int irq, cpumask_t mask)
 	int cpu;
 	struct irq_cfg *cfg;
 
-	BUG_ON((unsigned)irq >= nr_irqs);
 	cfg = get_irq_cfg(irq);
 
 	/* Only try and allocate irqs on cpus that are present */
@@ -1048,7 +1062,6 @@ static void __clear_irq_vector(int irq)
 	cpumask_t mask;
 	int cpu, vector;
 
-	BUG_ON((unsigned)irq >= nr_irqs);
 	cfg = get_irq_cfg(irq);
 	BUG_ON(!cfg->vector);
 
@@ -1898,8 +1911,6 @@ asmlinkage void smp_irq_move_cleanup_interrupt(void)
 		struct irq_desc *desc;
 		struct irq_cfg *cfg;
 		irq = __get_cpu_var(vector_irq)[vector];
-		if (irq >= nr_irqs)
-			continue;
 
 		desc = get_irq_desc(irq);
 		cfg = get_irq_cfg(irq);
@@ -2475,16 +2486,17 @@ int create_irq(void)
 	int irq;
 	int new;
 	unsigned long flags;
-	struct irq_cfg *cfg_new;
+	struct irq_cfg *cfg_new, *cfg;
 
 	irq = -ENOSPC;
 	spin_lock_irqsave(&vector_lock, flags);
 	for (new = (nr_irqs - 1); new >= 0; new--) {
 		if (platform_legacy_irq(new))
 			continue;
-		cfg_new = get_irq_cfg(new);
-		if (cfg_new->vector != 0)
+		cfg = get_irq_cfg_without_new(new);
+		if (!cfg || cfg->vector != 0)
 			continue;
+		cfg_new = get_irq_cfg(new);
 		if (__assign_irq_vector(new, TARGET_CPUS) == 0)
 			irq = new;
 		break;
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index c2fe49f..118f24f 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -202,7 +202,7 @@ asmlinkage unsigned int do_IRQ(struct pt_regs *regs)
 	stack_overflow_check(regs);
 #endif
 
-	if (likely(irq < nr_irqs))
+	if (likely(get_irq_desc_without_new(irq)))
 		generic_handle_irq(irq);
 	else {
 		if (!disable_apic)
diff --git a/drivers/char/random.c b/drivers/char/random.c
index d9e7a08..02c4f13 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -649,8 +649,10 @@ void add_interrupt_randomness(int irq)
 	struct timer_rand_state *state;
 	struct irq_desc *desc;
 
+#ifndef CONFIG_HAVE_SPARSE_IRQ
 	if (irq >= nr_irqs)
 		return;
+#endif
 
 	desc = get_irq_desc(irq);
 	state = desc->timer_rand_state;
@@ -920,8 +922,10 @@ void rand_initialize_irq(int irq)
 	struct timer_rand_state *state;
 	struct irq_desc *desc;
 
+#ifndef CONFIG_HAVE_SPARSE_IRQ
 	if (irq >= nr_irqs)
 		return;
+#endif
 
 	desc = get_irq_desc(irq);
 	state = desc->timer_rand_state;
diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
index 32de344..2a50625 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -495,19 +495,15 @@ static const struct file_operations proc_vmalloc_operations = {
 
 static int show_stat(struct seq_file *p, void *v)
 {
-	int i;
+	int i, j;
 	unsigned long jif;
 	cputime64_t user, nice, system, idle, iowait, irq, softirq, steal;
 	cputime64_t guest;
 	u64 sum = 0;
 	struct timespec boottime;
-	unsigned int *per_irq_sum;
+	unsigned int per_irq_sum;
 	struct irq_desc *desc;
 
-	per_irq_sum = kzalloc(sizeof(unsigned int)*nr_irqs, GFP_KERNEL);
-	if (!per_irq_sum)
-		return -ENOMEM;
-
 	user = nice = system = idle = iowait =
 		irq = softirq = steal = cputime64_zero;
 	guest = cputime64_zero;
@@ -515,8 +511,6 @@ static int show_stat(struct seq_file *p, void *v)
 	jif = boottime.tv_sec;
 
 	for_each_possible_cpu(i) {
-		int j;
-
 		user = cputime64_add(user, kstat_cpu(i).cpustat.user);
 		nice = cputime64_add(nice, kstat_cpu(i).cpustat.nice);
 		system = cputime64_add(system, kstat_cpu(i).cpustat.system);
@@ -531,7 +525,6 @@ static int show_stat(struct seq_file *p, void *v)
 
 			temp = kstat_irqs_cpu(j, i);
 			sum += temp;
-			per_irq_sum[j] += temp;
 		}
 		sum += arch_irq_stat_cpu(i);
 	}
@@ -574,8 +567,21 @@ static int show_stat(struct seq_file *p, void *v)
 	}
 	seq_printf(p, "intr %llu", (unsigned long long)sum);
 
-	for (i = 0; i < nr_irqs; i++)
-		seq_printf(p, " %u", per_irq_sum[i]);
+	/* sum again ? it could be updated? have another field in irq_desc?*/
+	for (j = 0; j < nr_irqs; j++) {
+		per_irq_sum = 0;
+		desc = get_irq_desc_without_new(j);
+
+		if (desc)
+			for_each_possible_cpu(i) {
+				unsigned int temp;
+
+				temp = kstat_irqs_cpu(j, i);
+				per_irq_sum += temp;
+			}
+
+		seq_printf(p, " %u", per_irq_sum);
+	}
 
 	seq_printf(p,
 		"\nctxt %llu\n"
@@ -589,7 +595,6 @@ static int show_stat(struct seq_file *p, void *v)
 		nr_running(),
 		nr_iowait());
 
-	kfree(per_irq_sum);
 	return 0;
 }
 
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index d09800a..2476e96 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -27,10 +27,12 @@ void dynamic_irq_init(unsigned int irq)
 	struct irq_desc *desc;
 	unsigned long flags;
 
+#ifndef CONFIG_HAVE_SPARSE_IRQ
 	if (irq >= nr_irqs) {
 		WARN(1, KERN_ERR "Trying to initialize invalid IRQ%d\n", irq);
 		return;
 	}
+#endif
 
 	/* Ensure we don't have left over values from a previous use of this irq */
 	desc = get_irq_desc(irq);
@@ -60,10 +62,12 @@ void dynamic_irq_cleanup(unsigned int irq)
 	struct irq_desc *desc;
 	unsigned long flags;
 
+#ifndef CONFIG_HAVE_SPARSE_IRQ
 	if (irq >= nr_irqs) {
 		WARN(1, KERN_ERR "Trying to cleanup invalid IRQ%d\n", irq);
 		return;
 	}
+#endif
 
 	desc = get_irq_desc(irq);
 	spin_lock_irqsave(&desc->lock, flags);
@@ -92,10 +96,12 @@ int set_irq_chip(unsigned int irq, struct irq_chip *chip)
 	struct irq_desc *desc;
 	unsigned long flags;
 
+#ifndef CONFIG_HAVE_SPARSE_IRQ
 	if (irq >= nr_irqs) {
 		WARN(1, KERN_ERR "Trying to install chip for IRQ%d\n", irq);
 		return -EINVAL;
 	}
+#endif
 
 	if (!chip)
 		chip = &no_irq_chip;
@@ -121,10 +127,12 @@ int set_irq_type(unsigned int irq, unsigned int type)
 	unsigned long flags;
 	int ret = -ENXIO;
 
+#ifndef CONFIG_HAVE_SPARSE_IRQ
 	if (irq >= nr_irqs) {
 		printk(KERN_ERR "Trying to set irq type for IRQ%d\n", irq);
 		return -ENODEV;
 	}
+#endif
 
 	desc = get_irq_desc(irq);
 	if (desc->chip->set_type) {
@@ -148,11 +156,13 @@ int set_irq_data(unsigned int irq, void *data)
 	struct irq_desc *desc;
 	unsigned long flags;
 
+#ifndef CONFIG_HAVE_SPARSE_IRQ
 	if (irq >= nr_irqs) {
 		printk(KERN_ERR
 		       "Trying to install controller data for IRQ%d\n", irq);
 		return -EINVAL;
 	}
+#endif
 
 	desc = get_irq_desc(irq);
 	spin_lock_irqsave(&desc->lock, flags);
@@ -174,11 +184,13 @@ int set_irq_msi(unsigned int irq, struct msi_desc *entry)
 	struct irq_desc *desc;
 	unsigned long flags;
 
+#ifndef CONFIG_HAVE_SPARSE_IRQ
 	if (irq >= nr_irqs) {
 		printk(KERN_ERR
 		       "Trying to install msi data for IRQ%d\n", irq);
 		return -EINVAL;
 	}
+#endif
 	desc = get_irq_desc(irq);
 	spin_lock_irqsave(&desc->lock, flags);
 	desc->msi_desc = entry;
@@ -200,8 +212,16 @@ int set_irq_chip_data(unsigned int irq, void *data)
 	struct irq_desc *desc;
 	unsigned long flags;
 
+#ifndef CONFIG_HAVE_SPARSE_IRQ
+	if (irq >= nr_irqs) {
+		printk(KERN_ERR
+		       "Trying to install chip data for IRQ%d\n", irq);
+		return -EINVAL;
+	}
+#endif
+
 	desc = get_irq_desc(irq);
-	if (irq >= nr_irqs || !desc->chip) {
+	if (!desc->chip) {
 		printk(KERN_ERR "BUG: bad set_irq_chip_data(IRQ#%d)\n", irq);
 		return -EINVAL;
 	}
@@ -545,11 +565,13 @@ __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 	struct irq_desc *desc;
 	unsigned long flags;
 
+#ifndef CONFIG_HAVE_SPARSE_IRQ
 	if (irq >= nr_irqs) {
 		printk(KERN_ERR
 		       "Trying to install type control for IRQ%d\n", irq);
 		return;
 	}
+#endif
 
 	desc = get_irq_desc(irq);
 
@@ -610,11 +632,13 @@ void __init set_irq_noprobe(unsigned int irq)
 	struct irq_desc *desc;
 	unsigned long flags;
 
+#ifndef CONFIG_HAVE_SPARSE_IRQ
 	if (irq >= nr_irqs) {
 		printk(KERN_ERR "Trying to mark IRQ%d non-probeable\n", irq);
 
 		return;
 	}
+#endif
 
 	desc = get_irq_desc(irq);
 
@@ -628,11 +652,13 @@ void __init set_irq_probe(unsigned int irq)
 	struct irq_desc *desc;
 	unsigned long flags;
 
+#ifndef CONFIG_HAVE_SPARSE_IRQ
 	if (irq >= nr_irqs) {
 		printk(KERN_ERR "Trying to mark IRQ%d probeable\n", irq);
 
 		return;
 	}
+#endif
 
 	desc = get_irq_desc(irq);
 
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 13db003..f6735a2 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -34,8 +34,10 @@ void synchronize_irq(unsigned int irq)
 	struct irq_desc *desc = get_irq_desc(irq);
 	unsigned int status;
 
+#ifndef CONFIG_HAVE_SPARSE_IRQ
 	if (irq >= nr_irqs)
 		return;
+#endif
 
 	do {
 		unsigned long flags;
@@ -142,12 +144,15 @@ int irq_select_affinity(unsigned int irq)
  */
 void disable_irq_nosync(unsigned int irq)
 {
-	struct irq_desc *desc = get_irq_desc(irq);
+	struct irq_desc *desc;
 	unsigned long flags;
 
+#ifndef CONFIG_HAVE_SPARSE_IRQ
 	if (irq >= nr_irqs)
 		return;
+#endif
 
+	desc = get_irq_desc(irq);
 	spin_lock_irqsave(&desc->lock, flags);
 	if (!desc->depth++) {
 		desc->status |= IRQ_DISABLED;
@@ -171,11 +176,14 @@ EXPORT_SYMBOL(disable_irq_nosync);
  */
 void disable_irq(unsigned int irq)
 {
-	struct irq_desc *desc = get_irq_desc(irq);
+	struct irq_desc *desc;
 
+#ifndef CONFIG_HAVE_SPARSE_IRQ
 	if (irq >= nr_irqs)
 		return;
+#endif
 
+	desc = get_irq_desc(irq);
 	disable_irq_nosync(irq);
 	if (desc->action)
 		synchronize_irq(irq);
@@ -213,12 +221,15 @@ static void __enable_irq(struct irq_desc *desc, unsigned int irq)
  */
 void enable_irq(unsigned int irq)
 {
-	struct irq_desc *desc = get_irq_desc(irq);
+	struct irq_desc *desc;
 	unsigned long flags;
 
+#ifndef CONFIG_HAVE_SPARSE_IRQ
 	if (irq >= nr_irqs)
 		return;
+#endif
 
+	desc = get_irq_desc(irq);
 	spin_lock_irqsave(&desc->lock, flags);
 	__enable_irq(desc, irq);
 	spin_unlock_irqrestore(&desc->lock, flags);
@@ -290,10 +301,16 @@ EXPORT_SYMBOL(set_irq_wake);
  */
 int can_request_irq(unsigned int irq, unsigned long irqflags)
 {
-	struct irq_desc *desc = get_irq_desc(irq);
+	struct irq_desc *desc;
 	struct irqaction *action;
 
-	if (irq >= nr_irqs || desc->status & IRQ_NOREQUEST)
+#ifndef CONFIG_HAVE_SPARSE_IRQ
+	if (irq >= nr_irqs)
+		return 0;
+#endif
+
+	desc = get_irq_desc(irq);
+	if (desc->status & IRQ_NOREQUEST)
 		return 0;
 
 	action =desc->action;
@@ -345,16 +362,19 @@ static int __irq_set_trigger(struct irq_chip *chip, unsigned int irq,
  */
 int setup_irq(unsigned int irq, struct irqaction *new)
 {
-	struct irq_desc *desc = get_irq_desc(irq);
+	struct irq_desc *desc;
 	struct irqaction *old, **p;
 	const char *old_name = NULL;
 	unsigned long flags;
 	int shared = 0;
 	int ret;
 
+#ifndef CONFIG_HAVE_SPARSE_IRQ
 	if (irq >= nr_irqs)
 		return -EINVAL;
+#endif
 
+	desc = get_irq_desc(irq);
 	if (desc->chip == &no_irq_chip)
 		return -ENOSYS;
 	/*
@@ -506,8 +526,11 @@ void free_irq(unsigned int irq, void *dev_id)
 	unsigned long flags;
 
 	WARN_ON(in_interrupt());
+
+#ifndef CONFIG_HAVE_SPARSE_IRQ
 	if (irq >= nr_irqs)
 		return;
+#endif
 
 	desc = get_irq_desc(irq);
 	spin_lock_irqsave(&desc->lock, flags);
@@ -621,8 +644,10 @@ int request_irq(unsigned int irq, irq_handler_t handler,
 	 */
 	if ((irqflags & IRQF_SHARED) && !dev_id)
 		return -EINVAL;
+#ifndef CONFIG_HAVE_SPARSE_IRQ
 	if (irq >= nr_irqs)
 		return -EINVAL;
+#endif
 	desc = get_irq_desc(irq);
 	if (desc->status & IRQ_NOREQUEST)
 		return -EINVAL;
-- 
1.5.4.5

[PATCH 33/33] x86_64: add irq_desc in function in paramater

[Yinghai Lu]

So could remove some duplicated calling to get_irq_desc

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
---
 arch/x86/kernel/io_apic_32.c |    6 +++-
 arch/x86/kernel/io_apic_64.c |   45 +++++++++++++++++------------------------
 arch/x86/kernel/irq_32.c     |    3 +-
 arch/x86/kernel/irq_64.c     |    8 ++++--
 drivers/mfd/tc6393xb.c       |    7 ++++-
 drivers/parisc/dino.c        |    3 +-
 drivers/parisc/eisa.c        |    4 ++-
 drivers/parisc/gsc.c         |    3 +-
 drivers/parisc/superio.c     |    4 ++-
 include/linux/irq.h          |   30 ++++++++++++++++++---------
 init/main.c                  |    5 ++++
 kernel/irq/chip.c            |   26 ++++++++++++++++++++++-
 kernel/irq/handle.c          |   35 ++++++++++++++++++++++++++++---
 kernel/irq/manage.c          |    8 +++++++
 kernel/irq/migration.c       |   15 +++++++------
 15 files changed, 141 insertions(+), 61 deletions(-)

diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index ac5413e..c470cd7 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -1975,7 +1975,8 @@ static unsigned int startup_ioapic_irq(unsigned int irq)
 
 static void ack_ioapic_irq(unsigned int irq)
 {
-	move_native_irq(irq);
+	struct irq_desc *desc = get_irq_desc(irq);
+	move_native_irq(irq, desc);
 	ack_APIC_irq();
 }
 
@@ -1983,8 +1984,9 @@ static void ack_ioapic_quirk_irq(unsigned int irq)
 {
 	unsigned long v;
 	int i;
+	struct irq_desc *desc = get_irq_desc(irq);
 
-	move_native_irq(irq);
+	move_native_irq(irq, desc);
 /*
  * It appears there is an erratum which affects at least version 0x11
  * of I/O APIC (that's the 82093AA and cores integrated into various
diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
index 1416925..3a03a70 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -505,13 +505,12 @@ static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, u8 vector)
 	}
 }
 
-static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t mask)
+static void set_ioapic_affinity_irq(unsigned int irq, struct irq_desc *desc, cpumask_t mask)
 {
 	struct irq_cfg *cfg = get_irq_cfg(irq);
 	unsigned long flags;
 	unsigned int dest;
 	cpumask_t tmp;
-	struct irq_desc *desc;
 
 	cpus_and(tmp, mask, cpu_online_map);
 	if (cpus_empty(tmp))
@@ -528,7 +527,6 @@ static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t mask)
 	 */
 	dest = SET_APIC_LOGICAL_ID(dest);
 
-	desc = get_irq_desc(irq);
 	spin_lock_irqsave(&ioapic_lock, flags);
 	__target_IO_APIC_irq(irq, dest, cfg->vector);
 	desc->affinity = mask;
@@ -1874,7 +1872,7 @@ static void ir_irq_migration(struct work_struct *work)
 				continue;
 			}
 
-			desc->chip->set_affinity(irq, desc->pending_mask);
+			desc->chip->set_affinity(irq, desc, desc->pending_mask);
 			spin_unlock_irqrestore(&desc->lock, flags);
 		}
 	}
@@ -1883,10 +1881,8 @@ static void ir_irq_migration(struct work_struct *work)
 /*
  * 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(unsigned int irq, struct irq_desc *desc, cpumask_t mask)
 {
-	struct irq_desc *desc = get_irq_desc(irq);
-
 	if (desc->status & IRQ_LEVEL) {
 		desc->status |= IRQ_MOVE_PENDING;
 		desc->pending_mask = mask;
@@ -1953,32 +1949,32 @@ static void irq_complete_move(unsigned int irq)
 static inline void irq_complete_move(unsigned int irq) {}
 #endif
 #ifdef CONFIG_INTR_REMAP
-static void ack_x2apic_level(unsigned int irq)
+static void ack_x2apic_level(unsigned int irq, struct irq_desc *desc)
 {
 	ack_x2APIC_irq();
 }
 
-static void ack_x2apic_edge(unsigned int irq)
+static void ack_x2apic_edge(unsigned int irq, struct irq_desc *desc)
 {
 	ack_x2APIC_irq();
 }
 #endif
 
-static void ack_apic_edge(unsigned int irq)
+static void ack_apic_edge(unsigned int irq, struct irq_desc *desc)
 {
 	irq_complete_move(irq);
-	move_native_irq(irq);
+	move_native_irq(irq, desc);
 	ack_APIC_irq();
 }
 
-static void ack_apic_level(unsigned int irq)
+static void ack_apic_level(unsigned int irq, struct irq_desc *desc)
 {
 	int do_unmask_irq = 0;
 
 	irq_complete_move(irq);
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	/* If we are moving the irq we need to mask it */
-	if (unlikely(get_irq_desc(irq)->status & IRQ_MOVE_PENDING)) {
+	if (unlikely(desc->status & IRQ_MOVE_PENDING)) {
 		do_unmask_irq = 1;
 		mask_IO_APIC_irq(irq);
 	}
@@ -2019,7 +2015,7 @@ static void ack_apic_level(unsigned int irq)
 		 * and you can go talk to the chipset vendor about it.
 		 */
 		if (!io_apic_level_ack_pending(irq))
-			move_masked_irq(irq);
+			move_masked_irq(irq, desc);
 		unmask_IO_APIC_irq(irq);
 	}
 }
@@ -2104,7 +2100,7 @@ static void mask_lapic_irq(unsigned int irq)
 	apic_write(APIC_LVT0, v | APIC_LVT_MASKED);
 }
 
-static void ack_lapic_irq (unsigned int irq)
+static void ack_lapic_irq (unsigned int irq, struct irq_desc *desc)
 {
 	ack_APIC_irq();
 }
@@ -2595,13 +2591,12 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_ms
 }
 
 #ifdef CONFIG_SMP
-static void set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
+static void set_msi_irq_affinity(unsigned int irq, struct irq_desc *desc, cpumask_t mask)
 {
 	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))
@@ -2622,7 +2617,6 @@ static void set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
 	msg.address_lo |= MSI_ADDR_DEST_ID(dest);
 
 	write_msi_msg(irq, &msg);
-	desc = get_irq_desc(irq);
 	desc->affinity = mask;
 }
 
@@ -2631,13 +2625,12 @@ static void set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
  * Migrate the MSI irq to another cpumask. This migration is
  * done in the process context using interrupt-remapping hardware.
  */
-static void ir_set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
+static void ir_set_msi_irq_affinity(unsigned int irq, struct irq_desc *desc, cpumask_t mask)
 {
 	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))
@@ -2673,7 +2666,6 @@ static void ir_set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
 		cfg->move_in_progress = 0;
 	}
 
-	desc = get_irq_desc(irq);
 	desc->affinity = mask;
 }
 #endif
@@ -2934,12 +2926,11 @@ static void target_ht_irq(unsigned int irq, unsigned int dest, u8 vector)
 	write_ht_irq_msg(irq, &msg);
 }
 
-static void set_ht_irq_affinity(unsigned int irq, cpumask_t mask)
+static void set_ht_irq_affinity(unsigned int irq, struct irq_desc *desc, cpumask_t mask)
 {
 	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))
@@ -2953,7 +2944,6 @@ static void set_ht_irq_affinity(unsigned int irq, cpumask_t mask)
 	dest = cpu_mask_to_apicid(tmp);
 
 	target_ht_irq(irq, dest, cfg->vector);
-	desc = get_irq_desc(irq);
 	desc->affinity = mask;
 }
 #endif
@@ -3081,6 +3071,7 @@ void __init setup_ioapic_dest(void)
 {
 	int pin, ioapic, irq, irq_entry;
 	struct irq_cfg *cfg;
+	struct irq_desc *desc;
 
 	if (skip_ioapic_setup == 1)
 		return;
@@ -3092,6 +3083,8 @@ void __init setup_ioapic_dest(void)
 				continue;
 			irq = pin_2_irq(irq_entry, ioapic, pin);
 
+			desc = get_irq_desc(irq);
+
 			/* setup_IO_APIC_irqs could fail to get vector for some device
 			 * when you have too many devices, because at that time only boot
 			 * cpu is online.
@@ -3103,10 +3096,10 @@ void __init setup_ioapic_dest(void)
 						  irq_polarity(irq_entry));
 #ifdef CONFIG_INTR_REMAP
 			else if (intr_remapping_enabled)
-				set_ir_ioapic_affinity_irq(irq, TARGET_CPUS);
+				set_ir_ioapic_affinity_irq(irq, desc, TARGET_CPUS);
 #endif
 			else
-				set_ioapic_affinity_irq(irq, TARGET_CPUS);
+				set_ioapic_affinity_irq(irq, desc, TARGET_CPUS);
 		}
 
 	}
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 4f2f16d..9bc710a 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -224,7 +224,7 @@ unsigned int do_IRQ(struct pt_regs *regs)
 	struct pt_regs *old_regs;
 	/* high bit used in ret_from_ code */
 	int overflow, irq = ~regs->orig_ax;
-	struct irq_desc *desc = get_irq_desc(irq);
+	struct irq_desc *desc;
 
 	if (unlikely((unsigned)irq >= nr_irqs)) {
 		printk(KERN_EMERG "%s: cannot handle IRQ %d\n",
@@ -232,6 +232,7 @@ unsigned int do_IRQ(struct pt_regs *regs)
 		BUG();
 	}
 
+	desc = get_irq_desc(irq);
 	old_regs = set_irq_regs(regs);
 	irq_enter();
 
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 118f24f..3c7412d 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -189,6 +189,7 @@ u64 arch_irq_stat(void)
 asmlinkage unsigned int do_IRQ(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
+	struct irq_desc *desc;
 
 	/* high bit used in ret_from_ code  */
 	unsigned vector = ~regs->orig_ax;
@@ -202,8 +203,9 @@ asmlinkage unsigned int do_IRQ(struct pt_regs *regs)
 	stack_overflow_check(regs);
 #endif
 
-	if (likely(get_irq_desc_without_new(irq)))
-		generic_handle_irq(irq);
+	desc = get_irq_desc_without_new(irq);
+	if (likely(desc))
+		generic_handle_irq(irq, desc);
 	else {
 		if (!disable_apic)
 			ack_APIC_irq();
@@ -253,7 +255,7 @@ void fixup_irqs(cpumask_t map)
 			desc->chip->mask(irq);
 
 		if (desc->chip->set_affinity)
-			desc->chip->set_affinity(irq, mask);
+			desc->chip->set_affinity(irq, desc, mask);
 		else if (!(warned++))
 			set_affinity = 0;
 
diff --git a/drivers/mfd/tc6393xb.c b/drivers/mfd/tc6393xb.c
index f4fd797..b5ec6ee 100644
--- a/drivers/mfd/tc6393xb.c
+++ b/drivers/mfd/tc6393xb.c
@@ -262,14 +262,17 @@ tc6393xb_irq(unsigned int irq, struct irq_desc *desc)
 	struct tc6393xb *tc6393xb = get_irq_data(irq);
 	unsigned int isr;
 	unsigned int i, irq_base;
+	struct irq_desc *descx;
 
 	irq_base = tc6393xb->irq_base;
 
 	while ((isr = ioread8(tc6393xb->scr + SCR_ISR) &
 				~ioread8(tc6393xb->scr + SCR_IMR)))
 		for (i = 0; i < TC6393XB_NR_IRQS; i++) {
-			if (isr & (1 << i))
-				generic_handle_irq(irq_base + i);
+			if (isr & (1 << i)) {
+				descx = get_irq_desc(irq_base + i);
+				generic_handle_irq(irq_base + i, descx);
+			}
 		}
 }
 
diff --git a/drivers/parisc/dino.c b/drivers/parisc/dino.c
index 224567f..8aac431 100644
--- a/drivers/parisc/dino.c
+++ b/drivers/parisc/dino.c
@@ -389,9 +389,10 @@ ilr_again:
 	do {
 		int local_irq = __ffs(mask);
 		int irq = dino_dev->global_irq[local_irq];
+		struct irq_desc *desc = get_irq_desc(irq);
 		DBG(KERN_DEBUG "%s(%d, %p) mask 0x%x\n",
 			__func__, irq, intr_dev, mask);
-		__do_IRQ(irq);
+		__do_IRQ(irq, desc);
 		mask &= ~(1 << local_irq);
 	} while (mask);
 
diff --git a/drivers/parisc/eisa.c b/drivers/parisc/eisa.c
index cee63d8..1555d17 100644
--- a/drivers/parisc/eisa.c
+++ b/drivers/parisc/eisa.c
@@ -202,6 +202,7 @@ static irqreturn_t eisa_irq(int wax_irq, void *intr_dev)
 {
 	int irq = gsc_readb(0xfc01f000); /* EISA supports 16 irqs */
 	unsigned long flags;
+	struct irq_desc *desc;
         
 	spin_lock_irqsave(&eisa_irq_lock, flags);
 	/* read IRR command */
@@ -233,7 +234,8 @@ static irqreturn_t eisa_irq(int wax_irq, void *intr_dev)
 	}
 	spin_unlock_irqrestore(&eisa_irq_lock, flags);
 
-	__do_IRQ(irq);
+	desc = get_irq_desc(irq);
+	__do_IRQ(irq, desc);
    
 	spin_lock_irqsave(&eisa_irq_lock, flags);
 	/* unmask */
diff --git a/drivers/parisc/gsc.c b/drivers/parisc/gsc.c
index e1dfea8..83000cc 100644
--- a/drivers/parisc/gsc.c
+++ b/drivers/parisc/gsc.c
@@ -87,7 +87,8 @@ irqreturn_t gsc_asic_intr(int gsc_asic_irq, void *dev)
 	do {
 		int local_irq = __ffs(irr);
 		unsigned int irq = gsc_asic->global_irq[local_irq];
-		__do_IRQ(irq);
+		struct irq_desc *desc = get_irq_desc(irq);
+		__do_IRQ(irq, desc);
 		irr &= ~(1 << local_irq);
 	} while (irr);
 
diff --git a/drivers/parisc/superio.c b/drivers/parisc/superio.c
index 1463728..553de09 100644
--- a/drivers/parisc/superio.c
+++ b/drivers/parisc/superio.c
@@ -99,6 +99,7 @@ superio_interrupt(int parent_irq, void *devp)
 {
 	u8 results;
 	u8 local_irq;
+	struct irq_desc *desc;
 
 	/* Poll the 8259 to see if there's an interrupt. */
 	outb (OCW3_POLL,IC_PIC1+0);
@@ -139,7 +140,8 @@ superio_interrupt(int parent_irq, void *devp)
 	}
 
 	/* Call the appropriate device's interrupt */
-	__do_IRQ(local_irq);
+	desc = get_irq_desc(local_irq);
+	__do_IRQ(local_irq, desc);
 
 	/* set EOI - forces a new interrupt if a lower priority device
 	 * still needs service.
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 621abf4..cc2d961 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -106,14 +106,26 @@ struct irq_chip {
 	void		(*enable)(unsigned int irq);
 	void		(*disable)(unsigned int irq);
 
+#ifdef CONFIG_HAVE_SPARSE_IRQ
+	void		(*ack)(unsigned int irq, struct irq_desc *desc);
+#else
 	void		(*ack)(unsigned int irq);
+#endif
 	void		(*mask)(unsigned int irq);
 	void		(*mask_ack)(unsigned int irq);
 	void		(*unmask)(unsigned int irq);
+#ifdef CONFIG_HAVE_SPARSE_IRQ
+	void		(*eoi)(unsigned int irq, struct irq_desc *desc);
+#else
 	void		(*eoi)(unsigned int irq);
+#endif
 
 	void		(*end)(unsigned int irq);
+#ifdef CONFIG_HAVE_SPARSE_IRQ
+	void		(*set_affinity)(unsigned int irq, struct irq_desc *desc, cpumask_t dest);
+#else
 	void		(*set_affinity)(unsigned int irq, cpumask_t dest);
+#endif
 	int		(*retrigger)(unsigned int irq);
 	int		(*set_type)(unsigned int irq, unsigned int flow_type);
 	int		(*set_wake)(unsigned int irq, unsigned int on);
@@ -240,8 +252,8 @@ extern int setup_irq(unsigned int irq, struct irqaction *new);
 #if defined(CONFIG_GENERIC_PENDING_IRQ) || defined(CONFIG_IRQBALANCE)
 
 void set_pending_irq(unsigned int irq, cpumask_t mask);
-void move_native_irq(int irq);
-void move_masked_irq(int irq);
+void move_native_irq(int irq, struct irq_desc *desc);
+void move_masked_irq(int irq, struct irq_desc *desc);
 
 #else /* CONFIG_GENERIC_PENDING_IRQ || CONFIG_IRQBALANCE */
 
@@ -249,11 +261,11 @@ static inline void move_irq(int irq)
 {
 }
 
-static inline void move_native_irq(int irq)
+static inline void move_native_irq(int irq, struct irq_desc *desc)
 {
 }
 
-static inline void move_masked_irq(int irq)
+static inline void move_masked_irq(int irq, struct irq_desc *desc)
 {
 }
 
@@ -265,7 +277,7 @@ static inline void set_pending_irq(unsigned int irq, cpumask_t mask)
 
 #else /* CONFIG_SMP */
 
-#define move_native_irq(x)
+#define move_native_irq(x, y)
 #define move_masked_irq(x)
 
 #endif /* CONFIG_SMP */
@@ -306,7 +318,7 @@ extern void handle_bad_irq(unsigned int irq, struct irq_desc *desc);
  * Monolithic do_IRQ implementation.
  */
 #ifndef CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ
-extern unsigned int __do_IRQ(unsigned int irq);
+extern unsigned int __do_IRQ(unsigned int irq, struct irq_desc *desc);
 #endif
 
 /*
@@ -315,17 +327,15 @@ extern unsigned int __do_IRQ(unsigned int irq);
  * irqchip-style controller then we call the ->handle_irq() handler,
  * and it calls __do_IRQ() if it's attached to an irqtype-style controller.
  */
-static inline void generic_handle_irq(unsigned int irq)
+static inline void generic_handle_irq(unsigned int irq, struct irq_desc *desc)
 {
-	struct irq_desc *desc = get_irq_desc(irq);
-
 #ifdef CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ
 	desc->handle_irq(irq, desc);
 #else
 	if (likely(desc->handle_irq))
 		desc->handle_irq(irq, desc);
 	else
-		__do_IRQ(irq);
+		__do_IRQ(irq, desc);
 #endif
 }
 
diff --git a/init/main.c b/init/main.c
index 3454b4a..a0ecfdf 100644
--- a/init/main.c
+++ b/init/main.c
@@ -593,6 +593,11 @@ void pre_alloc_dyn_array(void)
 		if (da->init_work)
 			da->init_work(da);
 	}
+#else
+	unsigned int i;
+
+	for (i = 0; i < NR_IRQS; i++)
+		irq_desc[i].irq = i;
 #endif
 }
 
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 2476e96..49cf429 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -310,7 +310,11 @@ static inline void mask_ack_irq(struct irq_desc *desc, int irq)
 		desc->chip->mask_ack(irq);
 	else {
 		desc->chip->mask(irq);
+#ifdef CONFIG_HAVE_SPARSE_IRQ
+		desc->chip->ack(irq, desc);
+#else
 		desc->chip->ack(irq);
+#endif
 	}
 }
 
@@ -450,7 +454,11 @@ handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
 	spin_lock(&desc->lock);
 	desc->status &= ~IRQ_INPROGRESS;
 out:
+#ifdef CONFIG_HAVE_SPARSE_IRQ
+	desc->chip->eoi(irq, desc);
+#else
 	desc->chip->eoi(irq);
+#endif
 
 	spin_unlock(&desc->lock);
 }
@@ -493,7 +501,11 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
 	kstat_irqs_this_cpu(desc)++;
 
 	/* Start handling the irq */
+#ifdef CONFIG_HAVE_SPARSE_IRQ
+	desc->chip->ack(irq, desc);
+#else
 	desc->chip->ack(irq);
+#endif
 
 	/* Mark the IRQ currently in progress.*/
 	desc->status |= IRQ_INPROGRESS;
@@ -547,15 +559,25 @@ handle_percpu_irq(unsigned int irq, struct irq_desc *desc)
 
 	kstat_irqs_this_cpu(desc)++;
 
-	if (desc->chip->ack)
+	if (desc->chip->ack) {
+#ifdef CONFIG_HAVE_SPARSE_IRQ
+		desc->chip->ack(irq, desc);
+#else
 		desc->chip->ack(irq);
+#endif
+	}
 
 	action_ret = handle_IRQ_event(irq, desc->action);
 	if (!noirqdebug)
 		note_interrupt(irq, desc, action_ret);
 
-	if (desc->chip->eoi)
+	if (desc->chip->eoi) {
+#ifdef CONFIG_HAVE_SPARSE_IRQ
+		desc->chip->eoi(irq, desc);
+#else
 		desc->chip->eoi(irq);
+#endif
+	}
 }
 
 void
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index a2750b8..c603ac4 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -265,6 +265,13 @@ struct irq_desc *get_irq_desc_without_new(unsigned int irq)
  * What should we do if we get a hw irq event on an illegal vector?
  * Each architecture has to answer this themself.
  */
+#ifdef CONFIG_HAVE_SPARSE_IRQ
+static void ack_bad(unsigned int irq, struct irq_desc *desc)
+{
+	print_irq_desc(irq, desc);
+	ack_bad_irq(irq);
+}
+#else
 static void ack_bad(unsigned int irq)
 {
 	struct irq_desc *desc;
@@ -273,6 +280,7 @@ static void ack_bad(unsigned int irq)
 	print_irq_desc(irq, desc);
 	ack_bad_irq(irq);
 }
+#endif
 
 /*
  * NOP functions
@@ -281,6 +289,12 @@ static void noop(unsigned int irq)
 {
 }
 
+#ifdef CONFIG_HAVE_SPARSE_IRQ
+static void noop_desc(unsigned int irq, struct irq_desc *desc)
+{
+}
+#endif
+
 static unsigned int noop_ret(unsigned int irq)
 {
 	return 0;
@@ -309,7 +323,11 @@ struct irq_chip dummy_irq_chip = {
 	.shutdown	= noop,
 	.enable		= noop,
 	.disable	= noop,
+#ifdef CONFIG_HAVE_SPARSE_IRQ
+	.ack		= noop_desc,
+#else
 	.ack		= noop,
+#endif
 	.mask		= noop,
 	.unmask		= noop,
 	.end		= noop,
@@ -365,9 +383,8 @@ irqreturn_t handle_IRQ_event(unsigned int irq, struct irqaction *action)
  * This is the original x86 implementation which is used for every
  * interrupt type.
  */
-unsigned int __do_IRQ(unsigned int irq)
+unsigned int __do_IRQ(unsigned int irq, struct irq_desc *desc)
 {
-	struct irq_desc *desc = get_irq_desc(irq);
 	struct irqaction *action;
 	unsigned int status;
 
@@ -378,8 +395,13 @@ unsigned int __do_IRQ(unsigned int irq)
 		/*
 		 * No locking required for CPU-local interrupts:
 		 */
-		if (desc->chip->ack)
+		if (desc->chip->ack) {
+#ifdef CONFIG_HAVE_SPARSE_IRQ
+			desc->chip->ack(irq, desc);
+#else
 			desc->chip->ack(irq);
+#endif
+		}
 		if (likely(!(desc->status & IRQ_DISABLED))) {
 			action_ret = handle_IRQ_event(irq, desc->action);
 			if (!noirqdebug)
@@ -390,8 +412,13 @@ unsigned int __do_IRQ(unsigned int irq)
 	}
 
 	spin_lock(&desc->lock);
-	if (desc->chip->ack)
+	if (desc->chip->ack) {
+#ifdef CONFIG_HAVE_SPARSE_IRQ
+		desc->chip->ack(irq, desc);
+#else
 		desc->chip->ack(irq);
+#endif
+	}
 	/*
 	 * REPLAY is when Linux resends an IRQ that was dropped earlier
 	 * WAITING is used by probe to mark irqs that are being tested
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index f6735a2..8539e6e 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -95,7 +95,11 @@ int irq_set_affinity(unsigned int irq, cpumask_t cpumask)
 		unsigned long flags;
 
 		spin_lock_irqsave(&desc->lock, flags);
+#ifdef CONFIG_HAVE_SPARSE_IRQ
+		desc->chip->set_affinity(irq, desc, cpumask);
+#else
 		desc->chip->set_affinity(irq, cpumask);
+#endif
 		spin_unlock_irqrestore(&desc->lock, flags);
 	} else
 		set_pending_irq(irq, cpumask);
@@ -122,7 +126,11 @@ int irq_select_affinity(unsigned int irq)
 
 	desc = get_irq_desc(irq);
 	desc->affinity = mask;
+#ifdef CONFIG_HAVE_SPARSE_IRQ
+	desc->chip->set_affinity(irq, desc, mask);
+#else
 	desc->chip->set_affinity(irq, mask);
+#endif
 
 	set_balance_irq_affinity(irq, mask);
 	return 0;
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index 4df637c..24cf2e0 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -12,9 +12,8 @@ void set_pending_irq(unsigned int irq, cpumask_t mask)
 	spin_unlock_irqrestore(&desc->lock, flags);
 }
 
-void move_masked_irq(int irq)
+void move_masked_irq(int irq, struct irq_desc *desc)
 {
-	struct irq_desc *desc = get_irq_desc(irq);
 	cpumask_t tmp;
 
 	if (likely(!(desc->status & IRQ_MOVE_PENDING)))
@@ -53,15 +52,17 @@ void move_masked_irq(int irq)
 	 * masking the irqs.
 	 */
 	if (likely(!cpus_empty(tmp))) {
-		desc->chip->set_affinity(irq,tmp);
+#ifdef CONFIG_HAVE_SPARSE_IRQ
+		desc->chip->set_affinity(irq, desc, tmp);
+#else
+		desc->chip->set_affinity(irq, tmp);
+#endif
 	}
 	cpus_clear(desc->pending_mask);
 }
 
-void move_native_irq(int irq)
+void move_native_irq(int irq, struct irq_desc *desc)
 {
-	struct irq_desc *desc = get_irq_desc(irq);
-
 	if (likely(!(desc->status & IRQ_MOVE_PENDING)))
 		return;
 
@@ -69,7 +70,7 @@ void move_native_irq(int irq)
 		return;
 
 	desc->chip->mask(irq);
-	move_masked_irq(irq);
+	move_masked_irq(irq, desc);
 	desc->chip->unmask(irq);
 }
 
-- 
1.5.4.5

Re: [PATCH 32/33] remove >= nr_irqs checking with config_have_sparse_irq

[Yinghai Lu]

On Wed, Aug 6, 2008 at 1:43 AM, Yinghai Lu <yhlu.kernel@gmail.com> wrote:
> Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
> ---
>  arch/x86/kernel/io_apic_64.c |   36 ++++++++++++++++++++++++------------
>  arch/x86/kernel/irq_64.c     |    2 +-
>  drivers/char/random.c        |    4 ++++
>  fs/proc/proc_misc.c          |   29 +++++++++++++++++------------
>  kernel/irq/chip.c            |   28 +++++++++++++++++++++++++++-
>  kernel/irq/manage.c          |   37 +++++++++++++++++++++++++++++++------
>  6 files changed, 104 insertions(+), 32 deletions(-)
>
> diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
> index 8bb6565..1416925 100644
> --- a/arch/x86/kernel/io_apic_64.c
> +++ b/arch/x86/kernel/io_apic_64.c

========================================================
> @@ -2475,16 +2486,17 @@ int create_irq(void)
>        int irq;
>        int new;
>        unsigned long flags;
> -       struct irq_cfg *cfg_new;
> +       struct irq_cfg *cfg_new, *cfg;
>
>        irq = -ENOSPC;
>        spin_lock_irqsave(&vector_lock, flags);
>        for (new = (nr_irqs - 1); new >= 0; new--) {
>                if (platform_legacy_irq(new))
>                        continue;
> -               cfg_new = get_irq_cfg(new);
> -               if (cfg_new->vector != 0)
> +               cfg = get_irq_cfg_without_new(new);
> +               if (!cfg || cfg->vector != 0)
>                        continue;
> +               cfg_new = get_irq_cfg(new);
>                if (__assign_irq_vector(new, TARGET_CPUS) == 0)
>                        irq = new;
>                break;
======================================
change to create_irq is not needed, it will disabled msi

YH