x86 transition to 4k stacks (3/3)

diff -Nru a/arch/i386/kernel/init_task.c b/arch/i386/kernel/init_task.c
@@ -13,6 +13,9 @@
 static struct signal_struct init_signals = INIT_SIGNALS(init_signals);
 struct mm_struct init_mm = INIT_MM(init_mm);
 
+union thread_union init_irq_union
+	__attribute__((__section__(".data.init_task")));
+
 #ifdef CONFIG_X86_STACK_CHECK
 union thread_union stack_overflow_stack
 	__attribute__((__section__(".data.init_task")));

diff -Nru a/arch/i386/kernel/irq.c b/arch/i386/kernel/irq.c
@@ -311,7 +311,8 @@
  * SMP cross-CPU interrupts have their own specific
  * handlers).
  */
-asmlinkage unsigned int do_IRQ(struct pt_regs regs)
+struct pt_regs *do_IRQ(struct pt_regs *regs) __attribute__((regparm(1)));
+struct pt_regs *do_IRQ(struct pt_regs *regs)
 {	
 	/* 
 	 * We ack quickly, we don't want the irq controller

@@ -323,12 +324,19 @@
 	 * 0 return value means that this irq is already being
 	 * handled by some other CPU. (or is disabled)
 	 */
-	int irq = regs.orig_eax & 0xff; /* high bits used in ret_from_ code  */
+	int irq = regs->orig_eax & 0xff; /* high bits used in ret_from_ code  */
 	int cpu = smp_processor_id();
 	irq_desc_t *desc = irq_desc + irq;
 	struct irqaction * action;
 	unsigned int status;
 
+	/* 
+	 * get the preempt count from the thread that was interrupted 
+	 * preempt_count() is the interrupt stack's thread_info 
+	 * current->thread_info is the interrupted task
+	 */
+	preempt_count() += current->thread_info->preempt_count; 
+
 	irq_enter();
 	kstat.irqs[cpu][irq]++;
 	spin_lock(&desc->lock);

@@ -373,7 +381,7 @@
 	 */
 	for (;;) {
 		spin_unlock(&desc->lock);
-		handle_IRQ_event(irq, &regs, action);
+		handle_IRQ_event(irq, regs, action);
 		spin_lock(&desc->lock);
 		
 		if (likely(!(desc->status & IRQ_PENDING)))

@@ -391,8 +399,9 @@
 	spin_unlock(&desc->lock);
 
 	irq_exit();
+	preempt_count() += current->thread_info->preempt_count; 
 
-	return 1;
+	return regs;
 }
 
 /**

diff -Nru a/arch/i386/kernel/process.c b/arch/i386/kernel/process.c
@@ -427,6 +427,7 @@
 
 	/* never put a printk in __switch_to... printk() calls wake_up*() indirectly */
 
+	next_p->thread_info->irq_stack = prev_p->thread_info->irq_stack;
 	unlazy_fpu(prev_p);
 
 	/*

diff -Nru a/arch/i386/kernel/smpboot.c b/arch/i386/kernel/smpboot.c
@@ -69,6 +69,11 @@
 /* Per CPU bogomips and other parameters */
 struct cpuinfo_x86 cpu_data[NR_CPUS] __cacheline_aligned;
 
+/* Per CPU interrupt stacks */
+extern union thread_union init_irq_union;
+union thread_union *irq_stacks[NR_CPUS] __cacheline_aligned =
+	{ &init_irq_union, };
+
 /* Set when the idlers are all forked */
 int smp_threads_ready;
 

@@ -763,6 +768,28 @@
 	return (send_status | accept_status);
 }
 
+static void __init setup_irq_stack(struct task_struct *p, int cpu)
+{
+	unsigned long stk;
+
+	stk = __get_free_pages(GFP_KERNEL, THREAD_ORDER+1);
+	if (!stk)
+		panic("I can't seem to allocate my irq stack.  Oh well, giving up.");
+
+	irq_stacks[cpu] = (void *)stk;
+	memset(irq_stacks[cpu], 0, THREAD_SIZE);
+	irq_stacks[cpu]->thread_info.cpu = cpu;
+	irq_stacks[cpu]->thread_info.preempt_count = 1;
+					/* interrupts are not preemptable */
+	p->thread_info->irq_stack = irq_stacks[cpu];
+
+	/* If we want to make the irq stack more than one unit
+	 * deep, we can chain then off of the irq_stack pointer
+	 * here.
+	 */
+}
+
+
 extern unsigned long cpu_initialized;
 
 static void __init do_boot_cpu (int apicid) 

@@ -786,6 +813,8 @@
 	if (IS_ERR(idle))
 		panic("failed fork for CPU %d", cpu);
 
+	setup_irq_stack(idle, cpu);
+
 	/*
 	 * We remove it from the pidhash and the runqueue
 	 * once we got the process:

@@ -803,7 +832,13 @@
 
 	/* So we see what's up   */
 	printk("Booting processor %d/%d eip %lx\n", cpu, apicid, start_eip);
-	stack_start.esp = (void *) (1024 + PAGE_SIZE + (char *)idle->thread_info);
+
+	/* The -4 is to correct for the fact that the stack pointer
+	 * is used to find the location of the thread_info structure
+	 * by masking off several of the LSBs.  Without the -4, esp
+	 * is pointing to the page after the one the stack is on.
+	 */
+	stack_start.esp = (void *)(THREAD_SIZE - 4 + (char *)idle->thread_info);
 
 	/*
 	 * This grunge runs the startup process for

diff -Nru a/include/asm-i386/thread_info.h b/include/asm-i386/thread_info.h
@@ -29,9 +29,11 @@
 	__s32			preempt_count; /* 0 => preemptable, <0 => BUG */
 
 	mm_segment_t		addr_limit;	/* thread address space:
+						   0 for interrupts: illegal
 					 	   0-0xBFFFFFFF for user-thead
 						   0-0xFFFFFFFF for kernel-thread
 						*/
+	struct thread_info	*irq_stack;	/* pointer to cpu irq stack */
 
 	__u8			supervisor_stack[0];
 };

@@ -45,6 +47,7 @@
 #define TI_CPU		0x0000000C
 #define TI_PRE_COUNT	0x00000010
 #define TI_ADDR_LIMIT	0x00000014
+#define TI_IRQ_STACK	0x00000018
 
 #endif
 

@@ -59,6 +62,7 @@
 #define INIT_THREAD_SIZE       THREAD_SIZE
 
 #ifndef __ASSEMBLY__
+
 #define INIT_THREAD_INFO(tsk)			\
 {						\
 	.task		= &tsk,         	\

@@ -67,8 +71,9 @@
 	.cpu		= 0,			\
 	.preempt_count	= 1,			\
 	.addr_limit	= KERNEL_DS,		\
+	.irq_stack	= &init_irq_union	\
 }
-
+			
 #define init_thread_info	(init_thread_union.thread_info)
 #define init_stack		(init_thread_union.stack)
 

diff -Nru a/arch/i386/kernel/init_task.c b/arch/i386/kernel/init_task.c
@@ -13,6 +13,9 @@
 static struct signal_struct init_signals = INIT_SIGNALS(init_signals);
 struct mm_struct init_mm = INIT_MM(init_mm);
 
+union thread_union init_irq_union
+	__attribute__((__section__(".data.init_task")));
+
 #ifdef CONFIG_X86_STACK_CHECK
 union thread_union stack_overflow_stack
 	__attribute__((__section__(".data.init_task")));

diff -Nru a/arch/i386/kernel/irq.c b/arch/i386/kernel/irq.c
@@ -311,7 +311,8 @@
  * SMP cross-CPU interrupts have their own specific
  * handlers).
  */
-asmlinkage unsigned int do_IRQ(struct pt_regs regs)
+struct pt_regs *do_IRQ(struct pt_regs *regs) __attribute__((regparm(1)));
+struct pt_regs *do_IRQ(struct pt_regs *regs)
 {	
 	/* 
 	 * We ack quickly, we don't want the irq controller

@@ -323,7 +324,7 @@
 	 * 0 return value means that this irq is already being
 	 * handled by some other CPU. (or is disabled)
 	 */
-	int irq = regs.orig_eax & 0xff; /* high bits used in ret_from_ code  */
+	int irq = regs->orig_eax & 0xff; /* high bits used in ret_from_ code  */
 	int cpu = smp_processor_id();
 	irq_desc_t *desc = irq_desc + irq;
 	struct irqaction * action;

@@ -373,7 +374,7 @@
 	 */
 	for (;;) {
 		spin_unlock(&desc->lock);
-		handle_IRQ_event(irq, &regs, action);
+		handle_IRQ_event(irq, regs, action);
 		spin_lock(&desc->lock);
 		
 		if (likely(!(desc->status & IRQ_PENDING)))

@@ -392,7 +393,7 @@
 
 	irq_exit();
 
-	return 1;
+	return regs;
 }
 
 /**

diff -Nru a/arch/i386/kernel/process.c b/arch/i386/kernel/process.c
@@ -427,6 +427,7 @@
 
 	/* never put a printk in __switch_to... printk() calls wake_up*() indirectly */
 
+	next_p->thread_info->irq_stack = prev_p->thread_info->irq_stack;
 	unlazy_fpu(prev_p);
 
 	/*

diff -Nru a/arch/i386/kernel/smpboot.c b/arch/i386/kernel/smpboot.c
@@ -69,6 +69,11 @@
 /* Per CPU bogomips and other parameters */
 struct cpuinfo_x86 cpu_data[NR_CPUS] __cacheline_aligned;
 
+/* Per CPU interrupt stacks */
+extern union thread_union init_irq_union;
+union thread_union *irq_stacks[NR_CPUS] __cacheline_aligned =
+	{ &init_irq_union, };
+
 /* Set when the idlers are all forked */
 int smp_threads_ready;
 

@@ -763,6 +768,28 @@
 	return (send_status | accept_status);
 }
 
+static void __init setup_irq_stack(struct task_struct *p, int cpu)
+{
+	unsigned long stk;
+
+	stk = __get_free_pages(GFP_KERNEL, THREAD_ORDER+1);
+	if (!stk)
+		panic("I can't seem to allocate my irq stack.  Oh well, giving up.");
+
+	irq_stacks[cpu] = (void *)stk;
+	memset(irq_stacks[cpu], 0, THREAD_SIZE);
+	irq_stacks[cpu]->thread_info.cpu = cpu;
+	irq_stacks[cpu]->thread_info.preempt_count = 1;
+					/* interrupts are not preemptable */
+	p->thread_info->irq_stack = irq_stacks[cpu];
+
+	/* If we want to make the irq stack more than one unit
+	 * deep, we can chain then off of the irq_stack pointer
+	 * here.
+	 */
+}
+
+
 extern unsigned long cpu_initialized;
 
 static void __init do_boot_cpu (int apicid) 

@@ -786,6 +813,8 @@
 	if (IS_ERR(idle))
 		panic("failed fork for CPU %d", cpu);
 
+	setup_irq_stack(idle, cpu);
+
 	/*
 	 * We remove it from the pidhash and the runqueue
 	 * once we got the process:

@@ -803,7 +832,13 @@
 
 	/* So we see what's up   */
 	printk("Booting processor %d/%d eip %lx\n", cpu, apicid, start_eip);
-	stack_start.esp = (void *) (1024 + PAGE_SIZE + (char *)idle->thread_info);
+
+	/* The -4 is to correct for the fact that the stack pointer
+	 * is used to find the location of the thread_info structure
+	 * by masking off several of the LSBs.  Without the -4, esp
+	 * is pointing to the page after the one the stack is on.
+	 */
+	stack_start.esp = (void *)(THREAD_SIZE - 4 + (char *)idle->thread_info);
 
 	/*
 	 * This grunge runs the startup process for

diff -Nru a/include/asm-i386/thread_info.h b/include/asm-i386/thread_info.h
@@ -29,9 +29,11 @@
 	__s32			preempt_count; /* 0 => preemptable, <0 => BUG */
 
 	mm_segment_t		addr_limit;	/* thread address space:
+						   0 for interrupts: illegal
 					 	   0-0xBFFFFFFF for user-thead
 						   0-0xFFFFFFFF for kernel-thread
 						*/
+	struct thread_info	*irq_stack;	/* pointer to cpu irq stack */
 
 	__u8			supervisor_stack[0];
 };

@@ -45,6 +47,7 @@
 #define TI_CPU		0x0000000C
 #define TI_PRE_COUNT	0x00000010
 #define TI_ADDR_LIMIT	0x00000014
+#define TI_IRQ_STACK	0x00000018
 
 #endif
 

@@ -59,6 +62,7 @@
 #define INIT_THREAD_SIZE       THREAD_SIZE
 
 #ifndef __ASSEMBLY__
+
 #define INIT_THREAD_INFO(tsk)			\
 {						\
 	.task		= &tsk,         	\

@@ -67,8 +71,9 @@
 	.cpu		= 0,			\
 	.preempt_count	= 1,			\
 	.addr_limit	= KERNEL_DS,		\
+	.irq_stack	= &init_irq_union	\
 }
-
+			
 #define init_thread_info	(init_thread_union.thread_info)
 #define init_stack		(init_thread_union.stack)