Merge branch 'x86/irq' into x86/devel

Conflicts:

	arch/x86/kernel/i8259.c
	arch/x86/kernel/irqinit_64.c
Signed-off-by: NIngo Molnar <mingo@elte.hu>

arch/x86/kernel/acpi/boot.c

@@ -514,8 +514,6 @@ int acpi_register_gsi(u32 gsi, int triggering, int polarity)
 	 * Make sure all (legacy) PCI IRQs are set as level-triggered.
 	 */
 	if (acpi_irq_model == ACPI_IRQ_MODEL_PIC) {
-		extern void eisa_set_level_irq(unsigned int irq);
-
 		if (triggering == ACPI_LEVEL_SENSITIVE)
 			eisa_set_level_irq(gsi);
 	}

arch/x86/kernel/apic_32.c

@@ -70,6 +70,10 @@ static int local_apic_timer_disabled;
 int local_apic_timer_c2_ok;
 EXPORT_SYMBOL_GPL(local_apic_timer_c2_ok);
 
+int first_system_vector = 0xfe;
+
+char system_vectors[NR_VECTORS] = { [0 ... NR_VECTORS-1] = SYS_VECTOR_FREE};
+
 /*
  * Debug level, exported for io_apic.c
  */
@@ -1351,13 +1355,13 @@ void __init smp_intr_init(void)
 	 * The reschedule interrupt is a CPU-to-CPU reschedule-helper
 	 * IPI, driven by wakeup.
 	 */
-	set_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt);
+	alloc_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt);
 
 	/* IPI for invalidation */
-	set_intr_gate(INVALIDATE_TLB_VECTOR, invalidate_interrupt);
+	alloc_intr_gate(INVALIDATE_TLB_VECTOR, invalidate_interrupt);
 
 	/* IPI for generic function call */
-	set_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt);
+	alloc_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt);
 }
 #endif
 
@@ -1370,15 +1374,15 @@ void __init apic_intr_init(void)
 	smp_intr_init();
 #endif
 	/* self generated IPI for local APIC timer */
-	set_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt);
+	alloc_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt);
 
 	/* IPI vectors for APIC spurious and error interrupts */
-	set_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt);
-	set_intr_gate(ERROR_APIC_VECTOR, error_interrupt);
+	alloc_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt);
+	alloc_intr_gate(ERROR_APIC_VECTOR, error_interrupt);
 
 	/* thermal monitor LVT interrupt */
 #ifdef CONFIG_X86_MCE_P4THERMAL
-	set_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt);
+	alloc_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt);
 #endif
 }
 

arch/x86/kernel/entry_32.S

@@ -51,7 +51,7 @@
 #include <asm/percpu.h>
 #include <asm/dwarf2.h>
 #include <asm/processor-flags.h>
-#include "irq_vectors.h"
+#include <asm/irq_vectors.h>
 
 /*
  * We use macros for low-level operations which need to be overridden

arch/x86/kernel/genx2apic_uv_x.c

@@ -5,7 +5,7 @@
  *
  * SGI UV APIC functions (note: not an Intel compatible APIC)
  *
- * Copyright (C) 2007 Silicon Graphics, Inc. All rights reserved.
+ * Copyright (C) 2007-2008 Silicon Graphics, Inc. All rights reserved.
  */
 
 #include <linux/threads.h>
@@ -55,37 +55,37 @@ static cpumask_t uv_vector_allocation_domain(int cpu)
 int uv_wakeup_secondary(int phys_apicid, unsigned int start_rip)
 {
 	unsigned long val;
-	int nasid;
+	int pnode;
 
-	nasid = uv_apicid_to_nasid(phys_apicid);
+	pnode = uv_apicid_to_pnode(phys_apicid);
 	val = (1UL << UVH_IPI_INT_SEND_SHFT) |
 	    (phys_apicid << UVH_IPI_INT_APIC_ID_SHFT) |
 	    (((long)start_rip << UVH_IPI_INT_VECTOR_SHFT) >> 12) |
 	    APIC_DM_INIT;
-	uv_write_global_mmr64(nasid, UVH_IPI_INT, val);
+	uv_write_global_mmr64(pnode, UVH_IPI_INT, val);
 	mdelay(10);
 
 	val = (1UL << UVH_IPI_INT_SEND_SHFT) |
 	    (phys_apicid << UVH_IPI_INT_APIC_ID_SHFT) |
 	    (((long)start_rip << UVH_IPI_INT_VECTOR_SHFT) >> 12) |
 	    APIC_DM_STARTUP;
-	uv_write_global_mmr64(nasid, UVH_IPI_INT, val);
+	uv_write_global_mmr64(pnode, UVH_IPI_INT, val);
 	return 0;
 }
 
 static void uv_send_IPI_one(int cpu, int vector)
 {
 	unsigned long val, apicid, lapicid;
-	int nasid;
+	int pnode;
 
 	apicid = per_cpu(x86_cpu_to_apicid, cpu); /* ZZZ - cache node-local ? */
 	lapicid = apicid & 0x3f;		/* ZZZ macro needed */
-	nasid = uv_apicid_to_nasid(apicid);
+	pnode = uv_apicid_to_pnode(apicid);
 	val =
 	    (1UL << UVH_IPI_INT_SEND_SHFT) | (lapicid <<
 					      UVH_IPI_INT_APIC_ID_SHFT) |
 	    (vector << UVH_IPI_INT_VECTOR_SHFT);
-	uv_write_global_mmr64(nasid, UVH_IPI_INT, val);
+	uv_write_global_mmr64(pnode, UVH_IPI_INT, val);
 }
 
 static void uv_send_IPI_mask(cpumask_t mask, int vector)
@@ -159,39 +159,81 @@ struct genapic apic_x2apic_uv_x = {
 	.phys_pkg_id = phys_pkg_id,	/* Fixme ZZZ */
 };
 
-static __cpuinit void set_x2apic_extra_bits(int nasid)
+static __cpuinit void set_x2apic_extra_bits(int pnode)
 {
-	__get_cpu_var(x2apic_extra_bits) = ((nasid >> 1) << 6);
+	__get_cpu_var(x2apic_extra_bits) = (pnode << 6);
 }
 
 /*
  * Called on boot cpu.
  */
+static __init int boot_pnode_to_blade(int pnode)
+{
+	int blade;
+
+	for (blade = 0; blade < uv_num_possible_blades(); blade++)
+		if (pnode == uv_blade_info[blade].pnode)
+			return blade;
+	BUG();
+}
+
+struct redir_addr {
+	unsigned long redirect;
+	unsigned long alias;
+};
+
+#define DEST_SHIFT UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_SHFT
+
+static __initdata struct redir_addr redir_addrs[] = {
+	{UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR, UVH_SI_ALIAS0_OVERLAY_CONFIG},
+	{UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR, UVH_SI_ALIAS1_OVERLAY_CONFIG},
+	{UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR, UVH_SI_ALIAS2_OVERLAY_CONFIG},
+};
+
+static __init void get_lowmem_redirect(unsigned long *base, unsigned long *size)
+{
+	union uvh_si_alias0_overlay_config_u alias;
+	union uvh_rh_gam_alias210_redirect_config_2_mmr_u redirect;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(redir_addrs); i++) {
+		alias.v = uv_read_local_mmr(redir_addrs[i].alias);
+		if (alias.s.base == 0) {
+			*size = (1UL << alias.s.m_alias);
+			redirect.v = uv_read_local_mmr(redir_addrs[i].redirect);
+			*base = (unsigned long)redirect.s.dest_base << DEST_SHIFT;
+			return;
+		}
+	}
+	BUG();
+}
+
 static __init void uv_system_init(void)
 {
 	union uvh_si_addr_map_config_u m_n_config;
-	int bytes, nid, cpu, lcpu, nasid, last_nasid, blade;
-	unsigned long mmr_base;
+	union uvh_node_id_u node_id;
+	unsigned long gnode_upper, lowmem_redir_base, lowmem_redir_size;
+	int bytes, nid, cpu, lcpu, pnode, blade, i, j, m_val, n_val;
+	unsigned long mmr_base, present;
 
 	m_n_config.v = uv_read_local_mmr(UVH_SI_ADDR_MAP_CONFIG);
+	m_val = m_n_config.s.m_skt;
+	n_val = m_n_config.s.n_skt;
 	mmr_base =
 	    uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR) &
 	    ~UV_MMR_ENABLE;
 	printk(KERN_DEBUG "UV: global MMR base 0x%lx\n", mmr_base);
 
-	last_nasid = -1;
-	for_each_possible_cpu(cpu) {
-		nid = cpu_to_node(cpu);
-		nasid = uv_apicid_to_nasid(per_cpu(x86_cpu_to_apicid, cpu));
-		if (nasid != last_nasid)
-			uv_possible_blades++;
-		last_nasid = nasid;
-	}
+	for(i = 0; i < UVH_NODE_PRESENT_TABLE_DEPTH; i++)
+		uv_possible_blades +=
+		  hweight64(uv_read_local_mmr( UVH_NODE_PRESENT_TABLE + i * 8));
 	printk(KERN_DEBUG "UV: Found %d blades\n", uv_num_possible_blades());
 
 	bytes = sizeof(struct uv_blade_info) * uv_num_possible_blades();
 	uv_blade_info = alloc_bootmem_pages(bytes);
 
+	get_lowmem_redirect(&lowmem_redir_base, &lowmem_redir_size);
+
 	bytes = sizeof(uv_node_to_blade[0]) * num_possible_nodes();
 	uv_node_to_blade = alloc_bootmem_pages(bytes);
 	memset(uv_node_to_blade, 255, bytes);
@@ -200,43 +242,56 @@ static __init void uv_system_init(void)
 	uv_cpu_to_blade = alloc_bootmem_pages(bytes);
 	memset(uv_cpu_to_blade, 255, bytes);
 
-	last_nasid = -1;
-	blade = -1;
-	lcpu = -1;
-	for_each_possible_cpu(cpu) {
-		nid = cpu_to_node(cpu);
-		nasid = uv_apicid_to_nasid(per_cpu(x86_cpu_to_apicid, cpu));
-		if (nasid != last_nasid) {
-			blade++;
-			lcpu = -1;
-			uv_blade_info[blade].nr_posible_cpus = 0;
+	blade = 0;
+	for (i = 0; i < UVH_NODE_PRESENT_TABLE_DEPTH; i++) {
+		present = uv_read_local_mmr(UVH_NODE_PRESENT_TABLE + i * 8);
+		for (j = 0; j < 64; j++) {
+			if (!test_bit(j, &present))
+				continue;
+			uv_blade_info[blade].pnode = (i * 64 + j);
+			uv_blade_info[blade].nr_possible_cpus = 0;
 			uv_blade_info[blade].nr_online_cpus = 0;
+			blade++;
 		}
-		last_nasid = nasid;
-		lcpu++;
+	}
 
-		uv_cpu_hub_info(cpu)->m_val = m_n_config.s.m_skt;
-		uv_cpu_hub_info(cpu)->n_val = m_n_config.s.n_skt;
+	node_id.v = uv_read_local_mmr(UVH_NODE_ID);
+	gnode_upper = (((unsigned long)node_id.s.node_id) &
+		       ~((1 << n_val) - 1)) << m_val;
+
+	for_each_present_cpu(cpu) {
+		nid = cpu_to_node(cpu);
+		pnode = uv_apicid_to_pnode(per_cpu(x86_cpu_to_apicid, cpu));
+		blade = boot_pnode_to_blade(pnode);
+		lcpu = uv_blade_info[blade].nr_possible_cpus;
+		uv_blade_info[blade].nr_possible_cpus++;
+
+		uv_cpu_hub_info(cpu)->lowmem_remap_base = lowmem_redir_base;
+		uv_cpu_hub_info(cpu)->lowmem_remap_top =
+					lowmem_redir_base + lowmem_redir_size;
+		uv_cpu_hub_info(cpu)->m_val = m_val;
+		uv_cpu_hub_info(cpu)->n_val = m_val;
 		uv_cpu_hub_info(cpu)->numa_blade_id = blade;
 		uv_cpu_hub_info(cpu)->blade_processor_id = lcpu;
-		uv_cpu_hub_info(cpu)->local_nasid = nasid;
-		uv_cpu_hub_info(cpu)->gnode_upper =
-		    nasid & ~((1 << uv_hub_info->n_val) - 1);
+		uv_cpu_hub_info(cpu)->pnode = pnode;
+		uv_cpu_hub_info(cpu)->pnode_mask = (1 << n_val) - 1;
+		uv_cpu_hub_info(cpu)->gpa_mask = (1 << (m_val + n_val)) - 1;
+		uv_cpu_hub_info(cpu)->gnode_upper = gnode_upper;
 		uv_cpu_hub_info(cpu)->global_mmr_base = mmr_base;
 		uv_cpu_hub_info(cpu)->coherency_domain_number = 0;/* ZZZ */
-		uv_blade_info[blade].nasid = nasid;
-		uv_blade_info[blade].nr_posible_cpus++;
 		uv_node_to_blade[nid] = blade;
 		uv_cpu_to_blade[cpu] = blade;
 
-		printk(KERN_DEBUG "UV cpu %d, apicid 0x%x, nasid %d, nid %d\n",
-		       cpu, per_cpu(x86_cpu_to_apicid, cpu), nasid, nid);
-		printk(KERN_DEBUG "UV   lcpu %d, blade %d\n", lcpu, blade);
+		printk(KERN_DEBUG "UV cpu %d, apicid 0x%x, pnode %d, nid %d, "
+			"lcpu %d, blade %d\n",
+			cpu, per_cpu(x86_cpu_to_apicid, cpu), pnode, nid,
+			lcpu, blade);
 	}
 }
 
 /*
  * Called on each cpu to initialize the per_cpu UV data area.
+ * 	ZZZ hotplug not supported yet
  */
 void __cpuinit uv_cpu_init(void)
 {
@@ -246,5 +301,5 @@ void __cpuinit uv_cpu_init(void)
 	uv_blade_info[uv_numa_blade_id()].nr_online_cpus++;
 
 	if (get_uv_system_type() == UV_NON_UNIQUE_APIC)
-		set_x2apic_extra_bits(uv_hub_info->local_nasid);
+		set_x2apic_extra_bits(uv_hub_info->pnode);
 }

arch/x86/kernel/i8259.c

@@ -297,34 +297,28 @@ void init_8259A(int auto_eoi)
 	 * outb_pic - this has to work on a wide range of PC hardware.
 	 */
 	outb_pic(0x11, PIC_MASTER_CMD);	/* ICW1: select 8259A-1 init */
-#ifndef CONFIG_X86_64
-	outb_pic(0x20 + 0, PIC_MASTER_IMR);	/* ICW2: 8259A-1 IR0-7 mapped to 0x20-0x27 */
-	outb_pic(1U << PIC_CASCADE_IR, PIC_MASTER_IMR);	/* 8259A-1 (the master) has a slave on IR2 */
-#else /* CONFIG_X86_64 */
-	/* ICW2: 8259A-1 IR0-7 mapped to 0x30-0x37 */
+
+	/* ICW2: 8259A-1 IR0-7 mapped to 0x30-0x37 on x86-64,
+	                       to 0x20-0x27 on i386 */
 	outb_pic(IRQ0_VECTOR, PIC_MASTER_IMR);
+
 	/* 8259A-1 (the master) has a slave on IR2 */
-	outb_pic(0x04, PIC_MASTER_IMR);
-#endif /* CONFIG_X86_64 */
+	outb_pic(1U << PIC_CASCADE_IR, PIC_MASTER_IMR);
+
 	if (auto_eoi)	/* master does Auto EOI */
 		outb_pic(MASTER_ICW4_DEFAULT | PIC_ICW4_AEOI, PIC_MASTER_IMR);
 	else		/* master expects normal EOI */
 		outb_pic(MASTER_ICW4_DEFAULT, PIC_MASTER_IMR);
 
 	outb_pic(0x11, PIC_SLAVE_CMD);	/* ICW1: select 8259A-2 init */
-#ifndef CONFIG_X86_64
-	outb_pic(0x20 + 8, PIC_SLAVE_IMR);	/* ICW2: 8259A-2 IR0-7 mapped to 0x28-0x2f */
-	outb_pic(PIC_CASCADE_IR, PIC_SLAVE_IMR);	/* 8259A-2 is a slave on master's IR2 */
-	outb_pic(SLAVE_ICW4_DEFAULT, PIC_SLAVE_IMR); /* (slave's support for AEOI in flat mode is to be investigated) */
-#else /* CONFIG_X86_64 */
-	/* ICW2: 8259A-2 IR0-7 mapped to 0x38-0x3f */
+
+	/* ICW2: 8259A-2 IR0-7 mapped to IRQ8_VECTOR */
 	outb_pic(IRQ8_VECTOR, PIC_SLAVE_IMR);
 	/* 8259A-2 is a slave on master's IR2 */
 	outb_pic(PIC_CASCADE_IR, PIC_SLAVE_IMR);
 	/* (slave's support for AEOI in flat mode is to be investigated) */
 	outb_pic(SLAVE_ICW4_DEFAULT, PIC_SLAVE_IMR);
 
-#endif /* CONFIG_X86_64 */
 	if (auto_eoi)
 		/*
 		 * In AEOI mode we just have to mask the interrupt

arch/x86/kernel/io_apic_32.c

@@ -1174,7 +1174,7 @@ static int __assign_irq_vector(int irq)
 	offset = current_offset;
 next:
 	vector += 8;
-	if (vector >= FIRST_SYSTEM_VECTOR) {
+	if (vector >= first_system_vector) {
 		offset = (offset + 1) % 8;
 		vector = FIRST_DEVICE_VECTOR + offset;
 	}
@@ -2280,7 +2280,7 @@ void __init setup_IO_APIC(void)
 	int i;
 
 	/* Reserve all the system vectors. */
-	for (i = FIRST_SYSTEM_VECTOR; i < NR_VECTORS; i++)
+	for (i = first_system_vector; i < NR_VECTORS; i++)
 		set_bit(i, used_vectors);
 
 	enable_IO_APIC();

arch/x86/kernel/io_apic_64.c

@@ -82,6 +82,10 @@ static struct irq_cfg irq_cfg[NR_IRQS] __read_mostly = {
 
 static int assign_irq_vector(int irq, cpumask_t mask);
 
+int first_system_vector = 0xfe;
+
+char system_vectors[NR_VECTORS] = { [0 ... NR_VECTORS-1] = SYS_VECTOR_FREE};
+
 #define __apicdebuginit  __init
 
 int sis_apic_bug; /* not actually supported, dummy for compile */
@@ -737,7 +741,7 @@ static int __assign_irq_vector(int irq, cpumask_t mask)
 		offset = current_offset;
 next:
 		vector += 8;
-		if (vector >= FIRST_SYSTEM_VECTOR) {
+		if (vector >= first_system_vector) {
 			/* If we run out of vectors on large boxen, must share them. */
 			offset = (offset + 1) % 8;
 			vector = FIRST_DEVICE_VECTOR + offset;

arch/x86/kernel/irq_32.c

@@ -48,6 +48,29 @@ void ack_bad_irq(unsigned int irq)
 #endif
 }
 
+#ifdef CONFIG_DEBUG_STACKOVERFLOW
+/* Debugging check for stack overflow: is there less than 1KB free? */
+static int check_stack_overflow(void)
+{
+	long sp;
+
+	__asm__ __volatile__("andl %%esp,%0" :
+			     "=r" (sp) : "0" (THREAD_SIZE - 1));
+
+	return sp < (sizeof(struct thread_info) + STACK_WARN);
+}
+
+static void print_stack_overflow(void)
+{
+	printk(KERN_WARNING "low stack detected by irq handler\n");
+	dump_stack();
+}
+
+#else
+static inline int check_stack_overflow(void) { return 0; }
+static inline void print_stack_overflow(void) { }
+#endif
+
 #ifdef CONFIG_4KSTACKS
 /*
  * per-CPU IRQ handling contexts (thread information and stack)
@@ -59,48 +82,29 @@ union irq_ctx {
 
 static union irq_ctx *hardirq_ctx[NR_CPUS] __read_mostly;
 static union irq_ctx *softirq_ctx[NR_CPUS] __read_mostly;
-#endif
 
-/*
- * do_IRQ handles all normal device IRQ's (the special
- * SMP cross-CPU interrupts have their own specific
- * handlers).
- */
-unsigned int do_IRQ(struct pt_regs *regs)
-{	
-	struct pt_regs *old_regs;
-	/* high bit used in ret_from_ code */
-	int irq = ~regs->orig_ax;
-	struct irq_desc *desc = irq_desc + irq;
-#ifdef CONFIG_4KSTACKS
-	union irq_ctx *curctx, *irqctx;
-	u32 *isp;
-#endif
+static char softirq_stack[NR_CPUS * THREAD_SIZE]
+		__attribute__((__section__(".bss.page_aligned")));
 
-	if (unlikely((unsigned)irq >= NR_IRQS)) {
-		printk(KERN_EMERG "%s: cannot handle IRQ %d\n",
-					__func__, irq);
-		BUG();
-	}
+static char hardirq_stack[NR_CPUS * THREAD_SIZE]
+		__attribute__((__section__(".bss.page_aligned")));
 
-	old_regs = set_irq_regs(regs);
-	irq_enter();
-#ifdef CONFIG_DEBUG_STACKOVERFLOW
-	/* Debugging check for stack overflow: is there less than 1KB free? */
-	{
-		long sp;
-
-		__asm__ __volatile__("andl %%esp,%0" :
-					"=r" (sp) : "0" (THREAD_SIZE - 1));
-		if (unlikely(sp < (sizeof(struct thread_info) + STACK_WARN))) {
-			printk("do_IRQ: stack overflow: %ld\n",
-				sp - sizeof(struct thread_info));
-			dump_stack();
-		}
-	}
-#endif
+static void call_on_stack(void *func, void *stack)
+{
+	asm volatile("xchgl	%%ebx,%%esp	\n"
+		     "call	*%%edi		\n"
+		     "movl	%%ebx,%%esp	\n"
+		     : "=b" (stack)
+		     : "0" (stack),
+		       "D"(func)
+		     : "memory", "cc", "edx", "ecx", "eax");
+}
 
-#ifdef CONFIG_4KSTACKS
+static inline int
+execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq)
+{
+	union irq_ctx *curctx, *irqctx;
+	u32 *isp, arg1, arg2;
 
 	curctx = (union irq_ctx *) current_thread_info();
 	irqctx = hardirq_ctx[smp_processor_id()];
@@ -111,52 +115,39 @@ unsigned int do_IRQ(struct pt_regs *regs)
 	 * handler) we can't do that and just have to keep using the
 	 * current stack (which is the irq stack already after all)
 	 */
-	if (curctx != irqctx) {
-		int arg1, arg2, bx;
+	if (unlikely(curctx == irqctx))
+		return 0;
 
-		/* build the stack frame on the IRQ stack */
-		isp = (u32*) ((char*)irqctx + sizeof(*irqctx));
-		irqctx->tinfo.task = curctx->tinfo.task;
-		irqctx->tinfo.previous_esp = current_stack_pointer;
+	/* build the stack frame on the IRQ stack */
+	isp = (u32 *) ((char*)irqctx + sizeof(*irqctx));
+	irqctx->tinfo.task = curctx->tinfo.task;
+	irqctx->tinfo.previous_esp = current_stack_pointer;
 
-		/*
-		 * Copy the softirq bits in preempt_count so that the
-		 * softirq checks work in the hardirq context.
-		 */
-		irqctx->tinfo.preempt_count =
-			(irqctx->tinfo.preempt_count & ~SOFTIRQ_MASK) |
-			(curctx->tinfo.preempt_count & SOFTIRQ_MASK);
-
-		asm volatile(
-			"       xchgl  %%ebx,%%esp    \n"
-			"       call   *%%edi         \n"
-			"       movl   %%ebx,%%esp    \n"
-			: "=a" (arg1), "=d" (arg2), "=b" (bx)
-			:  "0" (irq),   "1" (desc),  "2" (isp),
-			   "D" (desc->handle_irq)
-			: "memory", "cc", "ecx"
-		);
-	} else
-#endif
-		desc->handle_irq(irq, desc);
-
-	irq_exit();
-	set_irq_regs(old_regs);
+	/*
+	 * Copy the softirq bits in preempt_count so that the
+	 * softirq checks work in the hardirq context.
+	 */
+	irqctx->tinfo.preempt_count =
+		(irqctx->tinfo.preempt_count & ~SOFTIRQ_MASK) |
+		(curctx->tinfo.preempt_count & SOFTIRQ_MASK);
+
+	if (unlikely(overflow))
+		call_on_stack(print_stack_overflow, isp);
+
+	asm volatile("xchgl	%%ebx,%%esp	\n"
+		     "call	*%%edi		\n"
+		     "movl	%%ebx,%%esp	\n"
+		     : "=a" (arg1), "=d" (arg2), "=b" (isp)
+		     :  "0" (irq),   "1" (desc),  "2" (isp),
+			"D" (desc->handle_irq)
+		     : "memory", "cc", "ecx");
 	return 1;
 }
 
-#ifdef CONFIG_4KSTACKS
-
-static char softirq_stack[NR_CPUS * THREAD_SIZE]
-		__attribute__((__section__(".bss.page_aligned")));
-
-static char hardirq_stack[NR_CPUS * THREAD_SIZE]
-		__attribute__((__section__(".bss.page_aligned")));
-
 /*
  * allocate per-cpu stacks for hardirq and for softirq processing
  */
-void irq_ctx_init(int cpu)
+void __cpuinit irq_ctx_init(int cpu)
 {
 	union irq_ctx *irqctx;
 
@@ -164,25 +155,25 @@ void irq_ctx_init(int cpu)
 		return;
 
 	irqctx = (union irq_ctx*) &hardirq_stack[cpu*THREAD_SIZE];
-	irqctx->tinfo.task              = NULL;
-	irqctx->tinfo.exec_domain       = NULL;
-	irqctx->tinfo.cpu               = cpu;
-	irqctx->tinfo.preempt_count     = HARDIRQ_OFFSET;
-	irqctx->tinfo.addr_limit        = MAKE_MM_SEG(0);
+	irqctx->tinfo.task		= NULL;
+	irqctx->tinfo.exec_domain	= NULL;
+	irqctx->tinfo.cpu		= cpu;
+	irqctx->tinfo.preempt_count	= HARDIRQ_OFFSET;
+	irqctx->tinfo.addr_limit	= MAKE_MM_SEG(0);
 
 	hardirq_ctx[cpu] = irqctx;
 
 	irqctx = (union irq_ctx*) &softirq_stack[cpu*THREAD_SIZE];
-	irqctx->tinfo.task              = NULL;
-	irqctx->tinfo.exec_domain       = NULL;
-	irqctx->tinfo.cpu               = cpu;
-	irqctx->tinfo.preempt_count     = 0;
-	irqctx->tinfo.addr_limit        = MAKE_MM_SEG(0);
+	irqctx->tinfo.task		= NULL;
+	irqctx->tinfo.exec_domain	= NULL;
+	irqctx->tinfo.cpu		= cpu;
+	irqctx->tinfo.preempt_count	= 0;
+	irqctx->tinfo.addr_limit	= MAKE_MM_SEG(0);
 
 	softirq_ctx[cpu] = irqctx;
 
-	printk("CPU %u irqstacks, hard=%p soft=%p\n",
-		cpu,hardirq_ctx[cpu],softirq_ctx[cpu]);
+	printk(KERN_DEBUG "CPU %u irqstacks, hard=%p soft=%p\n",
+	       cpu,hardirq_ctx[cpu],softirq_ctx[cpu]);
 }
 
 void irq_ctx_exit(int cpu)
@@ -211,24 +202,55 @@ asmlinkage void do_softirq(void)
 		/* build the stack frame on the softirq stack */
 		isp = (u32*) ((char*)irqctx + sizeof(*irqctx));
 
-		asm volatile(
-			"       xchgl   %%ebx,%%esp     \n"
-			"       call    __do_softirq    \n"
-			"       movl    %%ebx,%%esp     \n"
-			: "=b"(isp)
-			: "0"(isp)
-			: "memory", "cc", "edx", "ecx", "eax"
-		);
+		call_on_stack(__do_softirq, isp);
 		/*
 		 * Shouldnt happen, we returned above if in_interrupt():
-	 	 */
+		 */
 		WARN_ON_ONCE(softirq_count());
 	}
 
 	local_irq_restore(flags);
 }
+
+#else
+static inline int
+execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq) { return 0; }
 #endif
 
+/*
+ * do_IRQ handles all normal device IRQ's (the special
+ * SMP cross-CPU interrupts have their own specific
+ * handlers).
+ */
+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;
+
+	if (unlikely((unsigned)irq >= NR_IRQS)) {
+		printk(KERN_EMERG "%s: cannot handle IRQ %d\n",
+					__func__, irq);
+		BUG();
+	}
+
+	old_regs = set_irq_regs(regs);
+	irq_enter();
+
+	overflow = check_stack_overflow();
+
+	if (!execute_on_irq_stack(overflow, desc, irq)) {
+		if (unlikely(overflow))
+			print_stack_overflow();
+		desc->handle_irq(irq, desc);
+	}
+
+	irq_exit();
+	set_irq_regs(old_regs);
+	return 1;
+}
+
 /*
  * Interrupt statistics:
  */

arch/x86/kernel/irqinit_64.c

@@ -34,6 +34,20 @@
  * interrupt-controller happy.
  */
 
+#define IRQ_NAME2(nr) nr##_interrupt(void)
+#define IRQ_NAME(nr) IRQ_NAME2(IRQ##nr)
+
+/*
+ *	SMP has a few special interrupts for IPI messages
+ */
+
+#define BUILD_IRQ(nr)				\
+	asmlinkage void IRQ_NAME(nr);		\
+	asm("\n.p2align\n"			\
+	    "IRQ" #nr "_interrupt:\n\t"		\
+	    "push $~(" #nr ") ; "		\
+	    "jmp common_interrupt");
+
 #define BI(x,y) \
 	BUILD_IRQ(x##y)
 
@@ -170,33 +184,33 @@ void __init native_init_IRQ(void)
 	 * The reschedule interrupt is a CPU-to-CPU reschedule-helper
 	 * IPI, driven by wakeup.
 	 */
-	set_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt);
+	alloc_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt);
 
 	/* IPIs for invalidation */
-	set_intr_gate(INVALIDATE_TLB_VECTOR_START+0, invalidate_interrupt0);
-	set_intr_gate(INVALIDATE_TLB_VECTOR_START+1, invalidate_interrupt1);
-	set_intr_gate(INVALIDATE_TLB_VECTOR_START+2, invalidate_interrupt2);
-	set_intr_gate(INVALIDATE_TLB_VECTOR_START+3, invalidate_interrupt3);
-	set_intr_gate(INVALIDATE_TLB_VECTOR_START+4, invalidate_interrupt4);
-	set_intr_gate(INVALIDATE_TLB_VECTOR_START+5, invalidate_interrupt5);
-	set_intr_gate(INVALIDATE_TLB_VECTOR_START+6, invalidate_interrupt6);
-	set_intr_gate(INVALIDATE_TLB_VECTOR_START+7, invalidate_interrupt7);
+	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+0, invalidate_interrupt0);
+	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+1, invalidate_interrupt1);
+	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+2, invalidate_interrupt2);
+	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+3, invalidate_interrupt3);
+	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+4, invalidate_interrupt4);
+	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+5, invalidate_interrupt5);
+	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+6, invalidate_interrupt6);
+	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+7, invalidate_interrupt7);
 
 	/* IPI for generic function call */
-	set_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt);
+	alloc_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt);
 
 	/* Low priority IPI to cleanup after moving an irq */
 	set_intr_gate(IRQ_MOVE_CLEANUP_VECTOR, irq_move_cleanup_interrupt);
 #endif
-	set_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt);
-	set_intr_gate(THRESHOLD_APIC_VECTOR, threshold_interrupt);
+	alloc_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt);
+	alloc_intr_gate(THRESHOLD_APIC_VECTOR, threshold_interrupt);
 
 	/* self generated IPI for local APIC timer */
-	set_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt);
+	alloc_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt);
 
 	/* IPI vectors for APIC spurious and error interrupts */
-	set_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt);
-	set_intr_gate(ERROR_APIC_VECTOR, error_interrupt);
+	alloc_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt);
+	alloc_intr_gate(ERROR_APIC_VECTOR, error_interrupt);
 
 	if (!acpi_ioapic)
 		setup_irq(2, &irq2);

arch/x86/kernel/vmiclock_32.c

@@ -33,8 +33,7 @@
 #include <asm/apic.h>
 #include <asm/timer.h>
 #include <asm/i8253.h>
-
-#include <irq_vectors.h>
+#include <asm/irq_vectors.h>
 
 #define VMI_ONESHOT  (VMI_ALARM_IS_ONESHOT  | VMI_CYCLES_REAL | vmi_get_alarm_wiring())
 #define VMI_PERIODIC (VMI_ALARM_IS_PERIODIC | VMI_CYCLES_REAL | vmi_get_alarm_wiring())

arch/x86/mach-visws/visws_apic.c

@@ -21,10 +21,9 @@
 #include <asm/io.h>
 #include <asm/apic.h>
 #include <asm/i8259.h>
+#include <asm/irq_vectors.h>
 
 #include "cobalt.h"
-#include "irq_vectors.h"
-
 
 static DEFINE_SPINLOCK(cobalt_lock);
 

include/asm-x86/desc.h

@@ -311,6 +311,28 @@ static inline void set_intr_gate(unsigned int n, void *addr)
 	_set_gate(n, GATE_INTERRUPT, addr, 0, 0, __KERNEL_CS);
 }
 
+#define SYS_VECTOR_FREE		0
+#define SYS_VECTOR_ALLOCED	1
+
+extern int first_system_vector;
+extern char system_vectors[];
+
+static inline void alloc_system_vector(int vector)
+{
+	if (system_vectors[vector] == SYS_VECTOR_FREE) {
+		system_vectors[vector] = SYS_VECTOR_ALLOCED;
+		if (first_system_vector > vector)
+			first_system_vector = vector;
+	} else
+		BUG();
+}
+
+static inline void alloc_intr_gate(unsigned int n, void *addr)
+{
+	alloc_system_vector(n);
+	set_intr_gate(n, addr);
+}
+
 /*
  * This routine sets up an interrupt gate at directory privilege level 3.
  */

include/asm-x86/genapic_64.h

@@ -44,4 +44,6 @@ DECLARE_PER_CPU(int, x2apic_extra_bits);
 extern void uv_cpu_init(void);
 extern int uv_wakeup_secondary(int phys_apicid, unsigned int start_rip);
 
+extern void setup_apic_routing(void);
+
 #endif

include/asm-x86/hw_irq.h

+#ifndef _ASM_HW_IRQ_H
+#define _ASM_HW_IRQ_H
+
+/*
+ * (C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar
+ *
+ * moved some of the old arch/i386/kernel/irq.h to here. VY
+ *
+ * IRQ/IPI changes taken from work by Thomas Radke
+ * <tomsoft@informatik.tu-chemnitz.de>
+ *
+ * hacked by Andi Kleen for x86-64.
+ * unified by tglx
+ */
+
+#include <asm/irq_vectors.h>
+
+#ifndef __ASSEMBLY__
+
+#include <linux/percpu.h>
+#include <linux/profile.h>
+#include <linux/smp.h>
+
+#include <asm/atomic.h>
+#include <asm/irq.h>
+#include <asm/sections.h>
+
+#define platform_legacy_irq(irq)	((irq) < 16)
+
+/* Interrupt handlers registered during init_IRQ */
+extern void apic_timer_interrupt(void);
+extern void error_interrupt(void);
+extern void spurious_interrupt(void);
+extern void thermal_interrupt(void);
+extern void reschedule_interrupt(void);
+
+extern void invalidate_interrupt(void);
+extern void invalidate_interrupt0(void);
+extern void invalidate_interrupt1(void);
+extern void invalidate_interrupt2(void);
+extern void invalidate_interrupt3(void);
+extern void invalidate_interrupt4(void);
+extern void invalidate_interrupt5(void);
+extern void invalidate_interrupt6(void);
+extern void invalidate_interrupt7(void);
+
+extern void irq_move_cleanup_interrupt(void);
+extern void threshold_interrupt(void);
+
+extern void call_function_interrupt(void);
+
+/* PIC specific functions */
+extern void disable_8259A_irq(unsigned int irq);
+extern void enable_8259A_irq(unsigned int irq);
+extern int i8259A_irq_pending(unsigned int irq);
+extern void make_8259A_irq(unsigned int irq);
+extern void init_8259A(int aeoi);
+
+/* IOAPIC */
+#define IO_APIC_IRQ(x) (((x) >= 16) || ((1<<(x)) & io_apic_irqs))
+extern unsigned long io_apic_irqs;
+
+extern void init_VISWS_APIC_irqs(void);
+extern void setup_IO_APIC(void);
+extern void disable_IO_APIC(void);
+extern void print_IO_APIC(void);
+extern int IO_APIC_get_PCI_irq_vector(int bus, int slot, int fn);
+extern void setup_ioapic_dest(void);
+
+#ifdef CONFIG_X86_64
+extern void enable_IO_APIC(void);
+#endif
+
+/* IPI functions */
+extern void send_IPI_self(int vector);
+extern void send_IPI(int dest, int vector);
+
+/* Statistics */
+extern atomic_t irq_err_count;
+extern atomic_t irq_mis_count;
+
+/* EISA */
+extern void eisa_set_level_irq(unsigned int irq);
+
+/* Voyager functions */
+extern asmlinkage void vic_cpi_interrupt(void);
+extern asmlinkage void vic_sys_interrupt(void);
+extern asmlinkage void vic_cmn_interrupt(void);
+extern asmlinkage void qic_timer_interrupt(void);
+extern asmlinkage void qic_invalidate_interrupt(void);
+extern asmlinkage void qic_reschedule_interrupt(void);
+extern asmlinkage void qic_enable_irq_interrupt(void);
+extern asmlinkage void qic_call_function_interrupt(void);
+
 #ifdef CONFIG_X86_32
-# include "hw_irq_32.h"
+extern void (*const interrupt[NR_IRQS])(void);
 #else
-# include "hw_irq_64.h"
+typedef int vector_irq_t[NR_VECTORS];
+DECLARE_PER_CPU(vector_irq_t, vector_irq);
+extern void __setup_vector_irq(int cpu);
+extern spinlock_t vector_lock;
+#endif
+
+#endif /* !ASSEMBLY_ */
+
 #endif

include/asm-x86/hw_irq_32.h

-#ifndef _ASM_HW_IRQ_H
-#define _ASM_HW_IRQ_H
-
-/*
- *	linux/include/asm/hw_irq.h
- *
- *	(C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar
- *
- *	moved some of the old arch/i386/kernel/irq.h to here. VY
- *
- *	IRQ/IPI changes taken from work by Thomas Radke
- *	<tomsoft@informatik.tu-chemnitz.de>
- */
-
-#include <linux/profile.h>
-#include <asm/atomic.h>
-#include <asm/irq.h>
-#include <asm/sections.h>
-
-#define NMI_VECTOR		0x02
-
-/*
- * Various low-level irq details needed by irq.c, process.c,
- * time.c, io_apic.c and smp.c
- *
- * Interrupt entry/exit code at both C and assembly level
- */
-
-extern void (*const interrupt[NR_IRQS])(void);
-
-#ifdef CONFIG_SMP
-void reschedule_interrupt(void);
-void invalidate_interrupt(void);
-void call_function_interrupt(void);
-#endif
-
-#ifdef CONFIG_X86_LOCAL_APIC
-void apic_timer_interrupt(void);
-void error_interrupt(void);
-void spurious_interrupt(void);
-void thermal_interrupt(void);
-#define platform_legacy_irq(irq)	((irq) < 16)
-#endif
-
-void disable_8259A_irq(unsigned int irq);
-void enable_8259A_irq(unsigned int irq);
-int i8259A_irq_pending(unsigned int irq);
-void make_8259A_irq(unsigned int irq);
-void init_8259A(int aeoi);
-void send_IPI_self(int vector);
-void init_VISWS_APIC_irqs(void);
-void setup_IO_APIC(void);
-void disable_IO_APIC(void);
-void print_IO_APIC(void);
-int IO_APIC_get_PCI_irq_vector(int bus, int slot, int fn);
-void send_IPI(int dest, int vector);
-void setup_ioapic_dest(void);
-
-extern unsigned long io_apic_irqs;
-
-extern atomic_t irq_err_count;
-extern atomic_t irq_mis_count;
-
-#define IO_APIC_IRQ(x) (((x) >= 16) || ((1<<(x)) & io_apic_irqs))
-
-#endif /* _ASM_HW_IRQ_H */

include/asm-x86/hw_irq_64.h

-#ifndef _ASM_HW_IRQ_H
-#define _ASM_HW_IRQ_H
-
-/*
- *	linux/include/asm/hw_irq.h
- *
- *	(C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar
- *
- *	moved some of the old arch/i386/kernel/irq.h to here. VY
- *
- *	IRQ/IPI changes taken from work by Thomas Radke
- *	<tomsoft@informatik.tu-chemnitz.de>
- *
- *	hacked by Andi Kleen for x86-64.
- */
-
-#ifndef __ASSEMBLY__
-#include <asm/atomic.h>
-#include <asm/irq.h>
-#include <linux/profile.h>
-#include <linux/smp.h>
-#include <linux/percpu.h>
-#endif
-
-#define NMI_VECTOR		0x02
-/*
- * IDT vectors usable for external interrupt sources start
- * at 0x20:
- */
-#define FIRST_EXTERNAL_VECTOR	0x20
-
-#define IA32_SYSCALL_VECTOR	0x80
-
-
-/* Reserve the lowest usable priority level 0x20 - 0x2f for triggering
- * cleanup after irq migration.
- */
-#define IRQ_MOVE_CLEANUP_VECTOR	FIRST_EXTERNAL_VECTOR
-
-/*
- * Vectors 0x30-0x3f are used for ISA interrupts.
- */
-#define IRQ0_VECTOR		(FIRST_EXTERNAL_VECTOR + 0x10)
-#define IRQ1_VECTOR		(IRQ0_VECTOR + 1)
-#define IRQ2_VECTOR		(IRQ0_VECTOR + 2)
-#define IRQ3_VECTOR		(IRQ0_VECTOR + 3)
-#define IRQ4_VECTOR		(IRQ0_VECTOR + 4)
-#define IRQ5_VECTOR		(IRQ0_VECTOR + 5)
-#define IRQ6_VECTOR		(IRQ0_VECTOR + 6)
-#define IRQ7_VECTOR		(IRQ0_VECTOR + 7)
-#define IRQ8_VECTOR		(IRQ0_VECTOR + 8)
-#define IRQ9_VECTOR		(IRQ0_VECTOR + 9)
-#define IRQ10_VECTOR		(IRQ0_VECTOR + 10)
-#define IRQ11_VECTOR		(IRQ0_VECTOR + 11)
-#define IRQ12_VECTOR		(IRQ0_VECTOR + 12)
-#define IRQ13_VECTOR		(IRQ0_VECTOR + 13)
-#define IRQ14_VECTOR		(IRQ0_VECTOR + 14)
-#define IRQ15_VECTOR		(IRQ0_VECTOR + 15)
-
-/*
- * Special IRQ vectors used by the SMP architecture, 0xf0-0xff
- *
- *  some of the following vectors are 'rare', they are merged
- *  into a single vector (CALL_FUNCTION_VECTOR) to save vector space.
- *  TLB, reschedule and local APIC vectors are performance-critical.
- */
-#define SPURIOUS_APIC_VECTOR	0xff
-#define ERROR_APIC_VECTOR	0xfe
-#define RESCHEDULE_VECTOR	0xfd
-#define CALL_FUNCTION_VECTOR	0xfc
-/* fb free - please don't readd KDB here because it's useless
-   (hint - think what a NMI bit does to a vector) */
-#define THERMAL_APIC_VECTOR	0xfa
-#define THRESHOLD_APIC_VECTOR   0xf9
-/* f8 free */
-#define INVALIDATE_TLB_VECTOR_END	0xf7
-#define INVALIDATE_TLB_VECTOR_START	0xf0	/* f0-f7 used for TLB flush */
-
-#define NUM_INVALIDATE_TLB_VECTORS	8
-
-/*
- * Local APIC timer IRQ vector is on a different priority level,
- * to work around the 'lost local interrupt if more than 2 IRQ
- * sources per level' errata.
- */
-#define LOCAL_TIMER_VECTOR	0xef
-
-/*
- * First APIC vector available to drivers: (vectors 0x30-0xee)
- * we start at 0x41 to spread out vectors evenly between priority
- * levels. (0x80 is the syscall vector)
- */
-#define FIRST_DEVICE_VECTOR	(IRQ15_VECTOR + 2)
-#define FIRST_SYSTEM_VECTOR	0xef   /* duplicated in irq.h */
-
-
-#ifndef __ASSEMBLY__
-
-/* Interrupt handlers registered during init_IRQ */
-void apic_timer_interrupt(void);
-void spurious_interrupt(void);
-void error_interrupt(void);
-void reschedule_interrupt(void);
-void call_function_interrupt(void);
-void irq_move_cleanup_interrupt(void);
-void invalidate_interrupt0(void);
-void invalidate_interrupt1(void);
-void invalidate_interrupt2(void);
-void invalidate_interrupt3(void);
-void invalidate_interrupt4(void);
-void invalidate_interrupt5(void);
-void invalidate_interrupt6(void);
-void invalidate_interrupt7(void);
-void thermal_interrupt(void);
-void threshold_interrupt(void);
-void i8254_timer_resume(void);
-
-typedef int vector_irq_t[NR_VECTORS];
-DECLARE_PER_CPU(vector_irq_t, vector_irq);
-extern void __setup_vector_irq(int cpu);
-extern spinlock_t vector_lock;
-
-/*
- * Various low-level irq details needed by irq.c, process.c,
- * time.c, io_apic.c and smp.c
- *
- * Interrupt entry/exit code at both C and assembly level
- */
-
-extern void disable_8259A_irq(unsigned int irq);
-extern void enable_8259A_irq(unsigned int irq);
-extern int i8259A_irq_pending(unsigned int irq);
-extern void make_8259A_irq(unsigned int irq);
-extern void init_8259A(int aeoi);
-extern void send_IPI_self(int vector);
-extern void init_VISWS_APIC_irqs(void);
-extern void setup_IO_APIC(void);
-extern void enable_IO_APIC(void);
-extern void disable_IO_APIC(void);
-extern void print_IO_APIC(void);
-extern int IO_APIC_get_PCI_irq_vector(int bus, int slot, int fn);
-extern void send_IPI(int dest, int vector);
-extern void setup_ioapic_dest(void);
-extern void native_init_IRQ(void);
-
-extern unsigned long io_apic_irqs;
-
-extern atomic_t irq_err_count;
-extern atomic_t irq_mis_count;
-
-#define IO_APIC_IRQ(x) (((x) >= 16) || ((1<<(x)) & io_apic_irqs))
-
-#include <asm/ptrace.h>
-
-#define IRQ_NAME2(nr) nr##_interrupt(void)
-#define IRQ_NAME(nr) IRQ_NAME2(IRQ##nr)
-
-/*
- *	SMP has a few special interrupts for IPI messages
- */
-
-#define BUILD_IRQ(nr)				\
-	asmlinkage void IRQ_NAME(nr);		\
-	asm("\n.p2align\n"			\
-	    "IRQ" #nr "_interrupt:\n\t"		\
-	    "push $~(" #nr ") ; "		\
-	    "jmp common_interrupt");
-
-#define platform_legacy_irq(irq)	((irq) < 16)
-
-#endif
-
-#endif /* _ASM_HW_IRQ_H */

include/asm-x86/irq.h

-#ifdef CONFIG_X86_32
-# include "irq_32.h"
+#ifndef _ASM_IRQ_H
+#define _ASM_IRQ_H
+/*
+ *	(C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar
+ *
+ *	IRQ/IPI changes taken from work by Thomas Radke
+ *	<tomsoft@informatik.tu-chemnitz.de>
+ */
+
+#include <asm/apicdef.h>
+#include <asm/irq_vectors.h>
+
+static inline int irq_canonicalize(int irq)
+{
+	return ((irq == 2) ? 9 : irq);
+}
+
+#ifdef CONFIG_X86_LOCAL_APIC
+# define ARCH_HAS_NMI_WATCHDOG
+#endif
+
+#ifdef CONFIG_4KSTACKS
+  extern void irq_ctx_init(int cpu);
+  extern void irq_ctx_exit(int cpu);
+# define __ARCH_HAS_DO_SOFTIRQ
 #else
-# include "irq_64.h"
+# define irq_ctx_init(cpu) do { } while (0)
+# define irq_ctx_exit(cpu) do { } while (0)
+# ifdef CONFIG_X86_64
+#  define __ARCH_HAS_DO_SOFTIRQ
+# endif
+#endif
+
+#ifdef CONFIG_IRQBALANCE
+extern int irqbalance_disable(char *str);
+#endif
+
+#ifdef CONFIG_HOTPLUG_CPU
+#include <linux/cpumask.h>
+extern void fixup_irqs(cpumask_t map);
 #endif
+
+extern unsigned int do_IRQ(struct pt_regs *regs);
+extern void init_IRQ(void);
+extern void native_init_IRQ(void);
+
+/* Interrupt vector management */
+extern DECLARE_BITMAP(used_vectors, NR_VECTORS);
+
+#endif /* _ASM_IRQ_H */

include/asm-x86/irq_32.h

-#ifndef _ASM_IRQ_H
-#define _ASM_IRQ_H
-
-/*
- *	linux/include/asm/irq.h
- *
- *	(C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar
- *
- *	IRQ/IPI changes taken from work by Thomas Radke
- *	<tomsoft@informatik.tu-chemnitz.de>
- */
-
-#include <linux/sched.h>
-/* include comes from machine specific directory */
-#include "irq_vectors.h"
-#include <asm/thread_info.h>
-
-static inline int irq_canonicalize(int irq)
-{
-	return ((irq == 2) ? 9 : irq);
-}
-
-#ifdef CONFIG_X86_LOCAL_APIC
-# define ARCH_HAS_NMI_WATCHDOG		/* See include/linux/nmi.h */
-#endif
-
-#ifdef CONFIG_4KSTACKS
-  extern void irq_ctx_init(int cpu);
-  extern void irq_ctx_exit(int cpu);
-# define __ARCH_HAS_DO_SOFTIRQ
-#else
-# define irq_ctx_init(cpu) do { } while (0)
-# define irq_ctx_exit(cpu) do { } while (0)
-#endif
-
-#ifdef CONFIG_IRQBALANCE
-extern int irqbalance_disable(char *str);
-#endif
-
-#ifdef CONFIG_HOTPLUG_CPU
-extern void fixup_irqs(cpumask_t map);
-#endif
-
-unsigned int do_IRQ(struct pt_regs *regs);
-void init_IRQ(void);
-void __init native_init_IRQ(void);
-
-/* Interrupt vector management */
-extern DECLARE_BITMAP(used_vectors, NR_VECTORS);
-
-#endif /* _ASM_IRQ_H */

include/asm-x86/irq_64.h

-#ifndef _ASM_IRQ_H
-#define _ASM_IRQ_H
-
-/*
- *	linux/include/asm/irq.h
- *
- *	(C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar
- *
- *	IRQ/IPI changes taken from work by Thomas Radke
- *	<tomsoft@informatik.tu-chemnitz.de>
- */
-
-#define TIMER_IRQ 0
-
-/*
- * 16 8259A IRQ's, 208 potential APIC interrupt sources.
- * Right now the APIC is mostly only used for SMP.
- * 256 vectors is an architectural limit. (we can have
- * more than 256 devices theoretically, but they will
- * have to use shared interrupts)
- * Since vectors 0x00-0x1f are used/reserved for the CPU,
- * the usable vector space is 0x20-0xff (224 vectors)
- */
-
-/*
- * The maximum number of vectors supported by x86_64 processors
- * is limited to 256. For processors other than x86_64, NR_VECTORS
- * should be changed accordingly.
- */
-#define NR_VECTORS 256
-
-#define FIRST_SYSTEM_VECTOR	0xef   /* duplicated in hw_irq.h */
-
-#define NR_IRQS (NR_VECTORS + (32 * NR_CPUS))
-#define NR_IRQ_VECTORS NR_IRQS
-
-static inline int irq_canonicalize(int irq)
-{
-	return ((irq == 2) ? 9 : irq);
-}
-
-#define ARCH_HAS_NMI_WATCHDOG		/* See include/linux/nmi.h */
-
-#ifdef CONFIG_HOTPLUG_CPU
-#include <linux/cpumask.h>
-extern void fixup_irqs(cpumask_t map);
-#endif
-
-#define __ARCH_HAS_DO_SOFTIRQ 1
-
-#endif /* _ASM_IRQ_H */

include/asm-x86/mach-voyager/irq_vectors.h → include/asm-x86/irq_vectors.h

-/* -*- mode: c; c-basic-offset: 8 -*- */
-
-/* Copyright (C) 2002
- *
- * Author: James.Bottomley@HansenPartnership.com
- *
- * linux/arch/i386/voyager/irq_vectors.h
- *
- * This file provides definitions for the VIC and QIC CPIs
- */
-
 #ifndef _ASM_IRQ_VECTORS_H
 #define _ASM_IRQ_VECTORS_H
 
+#include <linux/threads.h>
+
+#define NMI_VECTOR		0x02
+
 /*
  * IDT vectors usable for external interrupt sources start
  * at 0x20:
  */
 #define FIRST_EXTERNAL_VECTOR	0x20
 
-#define SYSCALL_VECTOR		0x80
+#ifdef CONFIG_X86_32
+# define SYSCALL_VECTOR		0x80
+#else
+# define IA32_SYSCALL_VECTOR	0x80
+#endif
+
+/*
+ * Reserve the lowest usable priority level 0x20 - 0x2f for triggering
+ * cleanup after irq migration on 64 bit.
+ */
+#define IRQ_MOVE_CLEANUP_VECTOR	FIRST_EXTERNAL_VECTOR
 
 /*
- * Vectors 0x20-0x2f are used for ISA interrupts.
+ * Vectors 0x20-0x2f are used for ISA interrupts on 32 bit.
+ * Vectors 0x30-0x3f are used for ISA interrupts on 64 bit.
  */
+#ifdef CONFIG_X86_32
+#define IRQ0_VECTOR		(FIRST_EXTERNAL_VECTOR)
+#else
+#define IRQ0_VECTOR		(FIRST_EXTERNAL_VECTOR + 0x10)
+#endif
+#define IRQ1_VECTOR		(IRQ0_VECTOR + 1)
+#define IRQ2_VECTOR		(IRQ0_VECTOR + 2)
+#define IRQ3_VECTOR		(IRQ0_VECTOR + 3)
+#define IRQ4_VECTOR		(IRQ0_VECTOR + 4)
+#define IRQ5_VECTOR		(IRQ0_VECTOR + 5)
+#define IRQ6_VECTOR		(IRQ0_VECTOR + 6)
+#define IRQ7_VECTOR		(IRQ0_VECTOR + 7)
+#define IRQ8_VECTOR		(IRQ0_VECTOR + 8)
+#define IRQ9_VECTOR		(IRQ0_VECTOR + 9)
+#define IRQ10_VECTOR		(IRQ0_VECTOR + 10)
+#define IRQ11_VECTOR		(IRQ0_VECTOR + 11)
+#define IRQ12_VECTOR		(IRQ0_VECTOR + 12)
+#define IRQ13_VECTOR		(IRQ0_VECTOR + 13)
+#define IRQ14_VECTOR		(IRQ0_VECTOR + 14)
+#define IRQ15_VECTOR		(IRQ0_VECTOR + 15)
 
+/*
+ * Special IRQ vectors used by the SMP architecture, 0xf0-0xff
+ *
+ *  some of the following vectors are 'rare', they are merged
+ *  into a single vector (CALL_FUNCTION_VECTOR) to save vector space.
+ *  TLB, reschedule and local APIC vectors are performance-critical.
+ *
+ *  Vectors 0xf0-0xfa are free (reserved for future Linux use).
+ */
+#ifdef CONFIG_X86_32
+
+# define SPURIOUS_APIC_VECTOR		0xff
+# define ERROR_APIC_VECTOR		0xfe
+# define INVALIDATE_TLB_VECTOR		0xfd
+# define RESCHEDULE_VECTOR		0xfc
+# define CALL_FUNCTION_VECTOR		0xfb
+# define THERMAL_APIC_VECTOR		0xf0
+
+#else
+
+#define SPURIOUS_APIC_VECTOR		0xff
+#define ERROR_APIC_VECTOR		0xfe
+#define RESCHEDULE_VECTOR		0xfd
+#define CALL_FUNCTION_VECTOR		0xfc
+#define THERMAL_APIC_VECTOR		0xfa
+#define THRESHOLD_APIC_VECTOR		0xf9
+#define INVALIDATE_TLB_VECTOR_END	0xf7
+#define INVALIDATE_TLB_VECTOR_START	0xf0	/* f0-f7 used for TLB flush */
+
+#define NUM_INVALIDATE_TLB_VECTORS	8
+
+#endif
+
+/*
+ * Local APIC timer IRQ vector is on a different priority level,
+ * to work around the 'lost local interrupt if more than 2 IRQ
+ * sources per level' errata.
+ */
+#define LOCAL_TIMER_VECTOR	0xef
+
+/*
+ * First APIC vector available to drivers: (vectors 0x30-0xee) we
+ * start at 0x31(0x41) to spread out vectors evenly between priority
+ * levels. (0x80 is the syscall vector)
+ */
+#ifdef CONFIG_X86_32
+# define FIRST_DEVICE_VECTOR	0x31
+#else
+# define FIRST_DEVICE_VECTOR	(IRQ15_VECTOR + 2)
+#endif
+
+#define NR_VECTORS		256
+
+#define FPU_IRQ			13
+
+#define	FIRST_VM86_IRQ		3
+#define LAST_VM86_IRQ		15
+#define invalid_vm86_irq(irq)	((irq) < 3 || (irq) > 15)
+
+#if !defined(CONFIG_X86_VISWS) && !defined(CONFIG_X86_VOYAGER)
+
+# if defined(CONFIG_X86_IO_APIC) || defined(CONFIG_PARAVIRT)
+
+#  define NR_IRQS		224
+
+#  if (224 >= 32 * NR_CPUS)
+#   define NR_IRQ_VECTORS	NR_IRQS
+#  else
+#   define NR_IRQ_VECTORS	(32 * NR_CPUS)
+#  endif
+
+# else /* IO_APIC || PARAVIRT */
+
+#  define NR_IRQS		16
+#  define NR_IRQ_VECTORS	NR_IRQS
+
+# endif
+
+#else /* !VISWS && !VOYAGER */
+
+# define NR_IRQS		224
+# define NR_IRQ_VECTORS		NR_IRQS
+
+#endif /* VISWS */
+
+/* Voyager specific defines */
 /* These define the CPIs we use in linux */
 #define VIC_CPI_LEVEL0			0
 #define VIC_CPI_LEVEL1			1
@@ -55,25 +165,5 @@
 #define VIC_CPU_BOOT_CPI		VIC_CPI_LEVEL0
 #define VIC_CPU_BOOT_ERRATA_CPI		(VIC_CPI_LEVEL0 + 8)
 
-#define NR_VECTORS 256
-#define NR_IRQS 224
-#define NR_IRQ_VECTORS NR_IRQS
-
-#define FPU_IRQ				13
-
-#define	FIRST_VM86_IRQ		3
-#define LAST_VM86_IRQ		15
-#define invalid_vm86_irq(irq)	((irq) < 3 || (irq) > 15)
-
-#ifndef __ASSEMBLY__
-extern asmlinkage void vic_cpi_interrupt(void);
-extern asmlinkage void vic_sys_interrupt(void);
-extern asmlinkage void vic_cmn_interrupt(void);
-extern asmlinkage void qic_timer_interrupt(void);
-extern asmlinkage void qic_invalidate_interrupt(void);
-extern asmlinkage void qic_reschedule_interrupt(void);
-extern asmlinkage void qic_enable_irq_interrupt(void);
-extern asmlinkage void qic_call_function_interrupt(void);
-#endif /* !__ASSEMBLY__ */
 
 #endif /* _ASM_IRQ_VECTORS_H */

include/asm-x86/mach-default/irq_vectors.h

-/*
- * This file should contain #defines for all of the interrupt vector
- * numbers used by this architecture.
- *
- * In addition, there are some standard defines:
- *
- *	FIRST_EXTERNAL_VECTOR:
- *		The first free place for external interrupts
- *
- *	SYSCALL_VECTOR:
- *		The IRQ vector a syscall makes the user to kernel transition
- *		under.
- *
- *	TIMER_IRQ:
- *		The IRQ number the timer interrupt comes in at.
- *
- *	NR_IRQS:
- *		The total number of interrupt vectors (including all the
- *		architecture specific interrupts) needed.
- *
- */			
-#ifndef _ASM_IRQ_VECTORS_H
-#define _ASM_IRQ_VECTORS_H
-
-/*
- * IDT vectors usable for external interrupt sources start
- * at 0x20:
- */
-#define FIRST_EXTERNAL_VECTOR	0x20
-
-#define SYSCALL_VECTOR		0x80
-
-/*
- * Vectors 0x20-0x2f are used for ISA interrupts.
- */
-
-/*
- * Special IRQ vectors used by the SMP architecture, 0xf0-0xff
- *
- *  some of the following vectors are 'rare', they are merged
- *  into a single vector (CALL_FUNCTION_VECTOR) to save vector space.
- *  TLB, reschedule and local APIC vectors are performance-critical.
- *
- *  Vectors 0xf0-0xfa are free (reserved for future Linux use).
- */
-#define SPURIOUS_APIC_VECTOR	0xff
-#define ERROR_APIC_VECTOR	0xfe
-#define INVALIDATE_TLB_VECTOR	0xfd
-#define RESCHEDULE_VECTOR	0xfc
-#define CALL_FUNCTION_VECTOR	0xfb
-
-#define THERMAL_APIC_VECTOR	0xf0
-/*
- * Local APIC timer IRQ vector is on a different priority level,
- * to work around the 'lost local interrupt if more than 2 IRQ
- * sources per level' errata.
- */
-#define LOCAL_TIMER_VECTOR	0xef
-
-/*
- * First APIC vector available to drivers: (vectors 0x30-0xee)
- * we start at 0x31 to spread out vectors evenly between priority
- * levels. (0x80 is the syscall vector)
- */
-#define FIRST_DEVICE_VECTOR	0x31
-#define FIRST_SYSTEM_VECTOR	0xef
-
-#define TIMER_IRQ 0
-
-/*
- * 16 8259A IRQ's, 208 potential APIC interrupt sources.
- * Right now the APIC is mostly only used for SMP.
- * 256 vectors is an architectural limit. (we can have
- * more than 256 devices theoretically, but they will
- * have to use shared interrupts)
- * Since vectors 0x00-0x1f are used/reserved for the CPU,
- * the usable vector space is 0x20-0xff (224 vectors)
- */
-
-/*
- * The maximum number of vectors supported by i386 processors
- * is limited to 256. For processors other than i386, NR_VECTORS
- * should be changed accordingly.
- */
-#define NR_VECTORS 256
-
-#include "irq_vectors_limits.h"
-
-#define FPU_IRQ			13
-
-#define	FIRST_VM86_IRQ		3
-#define LAST_VM86_IRQ		15
-#define invalid_vm86_irq(irq)	((irq) < 3 || (irq) > 15)
-
-
-#endif /* _ASM_IRQ_VECTORS_H */

include/asm-x86/mach-default/irq_vectors_limits.h

-#ifndef _ASM_IRQ_VECTORS_LIMITS_H
-#define _ASM_IRQ_VECTORS_LIMITS_H
-
-#if defined(CONFIG_X86_IO_APIC) || defined(CONFIG_PARAVIRT)
-#define NR_IRQS 224
-# if (224 >= 32 * NR_CPUS)
-# define NR_IRQ_VECTORS NR_IRQS
-# else
-# define NR_IRQ_VECTORS (32 * NR_CPUS)
-# endif
-#else
-#define NR_IRQS 16
-#define NR_IRQ_VECTORS NR_IRQS
-#endif
-
-#endif /* _ASM_IRQ_VECTORS_LIMITS_H */

include/asm-x86/mach-visws/irq_vectors.h

-#ifndef _ASM_IRQ_VECTORS_H
-#define _ASM_IRQ_VECTORS_H
-
-/*
- * IDT vectors usable for external interrupt sources start
- * at 0x20:
- */
-#define FIRST_EXTERNAL_VECTOR	0x20
-
-#define SYSCALL_VECTOR		0x80
-
-/*
- * Vectors 0x20-0x2f are used for ISA interrupts.
- */
-
-/*
- * Special IRQ vectors used by the SMP architecture, 0xf0-0xff
- *
- *  some of the following vectors are 'rare', they are merged
- *  into a single vector (CALL_FUNCTION_VECTOR) to save vector space.
- *  TLB, reschedule and local APIC vectors are performance-critical.
- *
- *  Vectors 0xf0-0xfa are free (reserved for future Linux use).
- */
-#define SPURIOUS_APIC_VECTOR	0xff
-#define ERROR_APIC_VECTOR	0xfe
-#define INVALIDATE_TLB_VECTOR	0xfd
-#define RESCHEDULE_VECTOR	0xfc
-#define CALL_FUNCTION_VECTOR	0xfb
-
-#define THERMAL_APIC_VECTOR	0xf0
-/*
- * Local APIC timer IRQ vector is on a different priority level,
- * to work around the 'lost local interrupt if more than 2 IRQ
- * sources per level' errata.
- */
-#define LOCAL_TIMER_VECTOR	0xef
-
-/*
- * First APIC vector available to drivers: (vectors 0x30-0xee)
- * we start at 0x31 to spread out vectors evenly between priority
- * levels. (0x80 is the syscall vector)
- */
-#define FIRST_DEVICE_VECTOR	0x31
-#define FIRST_SYSTEM_VECTOR	0xef
-
-#define TIMER_IRQ 0
-
-/*
- * IRQ definitions
- */
-#define NR_VECTORS 256
-#define NR_IRQS 224
-#define NR_IRQ_VECTORS NR_IRQS
-
-#define FPU_IRQ			13
-
-#define	FIRST_VM86_IRQ		3
-#define LAST_VM86_IRQ		15
-#define invalid_vm86_irq(irq)	((irq) < 3 || (irq) > 15)
-
-#endif /* _ASM_IRQ_VECTORS_H */

include/asm-x86/uv/uv_hub.h

@@ -5,7 +5,7 @@
  *
  * SGI UV architectural definitions
  *
- * Copyright (C) 2007 Silicon Graphics, Inc. All rights reserved.
+ * Copyright (C) 2007-2008 Silicon Graphics, Inc. All rights reserved.
  */
 
 #ifndef __ASM_X86_UV_HUB_H__
@@ -20,26 +20,49 @@
 /*
  * Addressing Terminology
  *
- * 	NASID - network ID of a router, Mbrick or Cbrick. Nasid values of
- * 		routers always have low bit of 1, C/MBricks have low bit
- * 		equal to 0. Most addressing macros that target UV hub chips
- * 		right shift the NASID by 1 to exclude the always-zero bit.
+ *	M       - The low M bits of a physical address represent the offset
+ *		  into the blade local memory. RAM memory on a blade is physically
+ *		  contiguous (although various IO spaces may punch holes in
+ *		  it)..
  *
- *	SNASID - NASID right shifted by 1 bit.
+ * 	N	- Number of bits in the node portion of a socket physical
+ * 		  address.
+ *
+ * 	NASID   - network ID of a router, Mbrick or Cbrick. Nasid values of
+ * 	 	  routers always have low bit of 1, C/MBricks have low bit
+ * 		  equal to 0. Most addressing macros that target UV hub chips
+ * 		  right shift the NASID by 1 to exclude the always-zero bit.
+ * 		  NASIDs contain up to 15 bits.
+ *
+ *	GNODE   - NASID right shifted by 1 bit. Most mmrs contain gnodes instead
+ *		  of nasids.
+ *
+ * 	PNODE   - the low N bits of the GNODE. The PNODE is the most useful variant
+ * 		  of the nasid for socket usage.
+ *
+ *
+ *  NumaLink Global Physical Address Format:
+ *  +--------------------------------+---------------------+
+ *  |00..000|      GNODE             |      NodeOffset     |
+ *  +--------------------------------+---------------------+
+ *          |<-------53 - M bits --->|<--------M bits ----->
+ *
+ *	M - number of node offset bits (35 .. 40)
  *
  *
  *  Memory/UV-HUB Processor Socket Address Format:
- *  +--------+---------------+---------------------+
- *  |00..0000|    SNASID     |      NodeOffset     |
- *  +--------+---------------+---------------------+
- *           <--- N bits --->|<--------M bits ----->
+ *  +----------------+---------------+---------------------+
+ *  |00..000000000000|   PNODE       |      NodeOffset     |
+ *  +----------------+---------------+---------------------+
+ *                   <--- N bits --->|<--------M bits ----->
  *
- *	M number of node offset bits (35 .. 40)
- *	N number of SNASID bits (0 .. 10)
+ *	M - number of node offset bits (35 .. 40)
+ *	N - number of PNODE bits (0 .. 10)
  *
  *		Note: M + N cannot currently exceed 44 (x86_64) or 46 (IA64).
  *		The actual values are configuration dependent and are set at
- *		boot time
+ *		boot time. M & N values are set by the hardware/BIOS at boot.
+ *
  *
  * APICID format
  * 	NOTE!!!!!! This is the current format of the APICID. However, code
@@ -48,14 +71,14 @@
  *
  * 		1111110000000000
  * 		5432109876543210
- *		nnnnnnnnnnlc0cch
+ *		pppppppppplc0cch
  *		sssssssssss
  *
- *			n  = snasid bits
+ *			p  = pnode bits
  *			l =  socket number on board
  *			c  = core
  *			h  = hyperthread
- *			s  = bits that are in the socket CSR
+ *			s  = bits that are in the SOCKET_ID CSR
  *
  *	Note: Processor only supports 12 bits in the APICID register. The ACPI
  *	      tables hold all 16 bits. Software needs to be aware of this.
@@ -74,7 +97,7 @@
  * This value is also the value of the maximum number of non-router NASIDs
  * in the numalink fabric.
  *
- * NOTE: a brick may be 1 or 2 OS nodes. Don't get these confused.
+ * NOTE: a brick may contain 1 or 2 OS nodes. Don't get these confused.
  */
 #define UV_MAX_NUMALINK_BLADES	16384
 
@@ -96,8 +119,12 @@
  */
 struct uv_hub_info_s {
 	unsigned long	global_mmr_base;
-	unsigned short	local_nasid;
-	unsigned short	gnode_upper;
+	unsigned long	gpa_mask;
+	unsigned long	gnode_upper;
+	unsigned long	lowmem_remap_top;
+	unsigned long	lowmem_remap_base;
+	unsigned short	pnode;
+	unsigned short	pnode_mask;
 	unsigned short	coherency_domain_number;
 	unsigned short	numa_blade_id;
 	unsigned char	blade_processor_id;
@@ -112,83 +139,124 @@ DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
  * Local & Global MMR space macros.
  * 	Note: macros are intended to be used ONLY by inline functions
  * 	in this file - not by other kernel code.
+ * 		n -  NASID (full 15-bit global nasid)
+ * 		g -  GNODE (full 15-bit global nasid, right shifted 1)
+ * 		p -  PNODE (local part of nsids, right shifted 1)
  */
-#define UV_SNASID(n)			((n) >> 1)
-#define UV_NASID(n)			((n) << 1)
+#define UV_NASID_TO_PNODE(n)		(((n) >> 1) & uv_hub_info->pnode_mask)
+#define UV_PNODE_TO_NASID(p)		(((p) << 1) | uv_hub_info->gnode_upper)
 
 #define UV_LOCAL_MMR_BASE		0xf4000000UL
 #define UV_GLOBAL_MMR32_BASE		0xf8000000UL
 #define UV_GLOBAL_MMR64_BASE		(uv_hub_info->global_mmr_base)
 
-#define UV_GLOBAL_MMR32_SNASID_MASK	0x3ff
-#define UV_GLOBAL_MMR32_SNASID_SHIFT	15
-#define UV_GLOBAL_MMR64_SNASID_SHIFT	26
+#define UV_GLOBAL_MMR32_PNODE_SHIFT	15
+#define UV_GLOBAL_MMR64_PNODE_SHIFT	26
 
-#define UV_GLOBAL_MMR32_NASID_BITS(n)					\
-		(((UV_SNASID(n) & UV_GLOBAL_MMR32_SNASID_MASK)) <<	\
-		(UV_GLOBAL_MMR32_SNASID_SHIFT))
+#define UV_GLOBAL_MMR32_PNODE_BITS(p)	((p) << (UV_GLOBAL_MMR32_PNODE_SHIFT))
 
-#define UV_GLOBAL_MMR64_NASID_BITS(n)					\
-	((unsigned long)UV_SNASID(n) << UV_GLOBAL_MMR64_SNASID_SHIFT)
+#define UV_GLOBAL_MMR64_PNODE_BITS(p)					\
+	((unsigned long)(p) << UV_GLOBAL_MMR64_PNODE_SHIFT)
+
+#define UV_APIC_PNODE_SHIFT	6
+
+/*
+ * Macros for converting between kernel virtual addresses, socket local physical
+ * addresses, and UV global physical addresses.
+ * 	Note: use the standard __pa() & __va() macros for converting
+ * 	      between socket virtual and socket physical addresses.
+ */
+
+/* socket phys RAM --> UV global physical address */
+static inline unsigned long uv_soc_phys_ram_to_gpa(unsigned long paddr)
+{
+	if (paddr < uv_hub_info->lowmem_remap_top)
+		paddr += uv_hub_info->lowmem_remap_base;
+	return paddr | uv_hub_info->gnode_upper;
+}
+
+
+/* socket virtual --> UV global physical address */
+static inline unsigned long uv_gpa(void *v)
+{
+	return __pa(v) | uv_hub_info->gnode_upper;
+}
+
+/* socket virtual --> UV global physical address */
+static inline void *uv_vgpa(void *v)
+{
+	return (void *)uv_gpa(v);
+}
+
+/* UV global physical address --> socket virtual */
+static inline void *uv_va(unsigned long gpa)
+{
+	return __va(gpa & uv_hub_info->gpa_mask);
+}
+
+/* pnode, offset --> socket virtual */
+static inline void *uv_pnode_offset_to_vaddr(int pnode, unsigned long offset)
+{
+	return __va(((unsigned long)pnode << uv_hub_info->m_val) | offset);
+}
 
-#define UV_APIC_NASID_SHIFT	6
 
 /*
- * Extract a NASID from an APICID (full apicid, not processor subset)
+ * Extract a PNODE from an APICID (full apicid, not processor subset)
  */
-static inline int uv_apicid_to_nasid(int apicid)
+static inline int uv_apicid_to_pnode(int apicid)
 {
-	return (UV_NASID(apicid >> UV_APIC_NASID_SHIFT));
+	return (apicid >> UV_APIC_PNODE_SHIFT);
 }
 
 /*
  * Access global MMRs using the low memory MMR32 space. This region supports
  * faster MMR access but not all MMRs are accessible in this space.
  */
-static inline unsigned long *uv_global_mmr32_address(int nasid,
+static inline unsigned long *uv_global_mmr32_address(int pnode,
 				unsigned long offset)
 {
 	return __va(UV_GLOBAL_MMR32_BASE |
-		       UV_GLOBAL_MMR32_NASID_BITS(nasid) | offset);
+		       UV_GLOBAL_MMR32_PNODE_BITS(pnode) | offset);
 }
 
-static inline void uv_write_global_mmr32(int nasid, unsigned long offset,
+static inline void uv_write_global_mmr32(int pnode, unsigned long offset,
 				 unsigned long val)
 {
-	*uv_global_mmr32_address(nasid, offset) = val;
+	*uv_global_mmr32_address(pnode, offset) = val;
 }
 
-static inline unsigned long uv_read_global_mmr32(int nasid,
+static inline unsigned long uv_read_global_mmr32(int pnode,
 						 unsigned long offset)
 {
-	return *uv_global_mmr32_address(nasid, offset);
+	return *uv_global_mmr32_address(pnode, offset);
 }
 
 /*
  * Access Global MMR space using the MMR space located at the top of physical
  * memory.
  */
-static inline unsigned long *uv_global_mmr64_address(int nasid,
+static inline unsigned long *uv_global_mmr64_address(int pnode,
 				unsigned long offset)
 {
 	return __va(UV_GLOBAL_MMR64_BASE |
-		       UV_GLOBAL_MMR64_NASID_BITS(nasid) | offset);
+		    UV_GLOBAL_MMR64_PNODE_BITS(pnode) | offset);
 }
 
-static inline void uv_write_global_mmr64(int nasid, unsigned long offset,
+static inline void uv_write_global_mmr64(int pnode, unsigned long offset,
 				unsigned long val)
 {
-	*uv_global_mmr64_address(nasid, offset) = val;
+	*uv_global_mmr64_address(pnode, offset) = val;
 }
 
-static inline unsigned long uv_read_global_mmr64(int nasid,
+static inline unsigned long uv_read_global_mmr64(int pnode,
 						 unsigned long offset)
 {
-	return *uv_global_mmr64_address(nasid, offset);
+	return *uv_global_mmr64_address(pnode, offset);
 }
 
 /*
- * Access node local MMRs. Faster than using global space but only local MMRs
+ * Access hub local MMRs. Faster than using global space but only local MMRs
  * are accessible.
  */
 static inline unsigned long *uv_local_mmr_address(unsigned long offset)
@@ -207,15 +275,15 @@ static inline void uv_write_local_mmr(unsigned long offset, unsigned long val)
 }
 
 /*
- * Structures and definitions for converting between cpu, node, and blade
+ * Structures and definitions for converting between cpu, node, pnode, and blade
  * numbers.
  */
 struct uv_blade_info {
-	unsigned short	nr_posible_cpus;
+	unsigned short	nr_possible_cpus;
 	unsigned short	nr_online_cpus;
-	unsigned short	nasid;
+	unsigned short	pnode;
 };
-struct uv_blade_info *uv_blade_info;
+extern struct uv_blade_info *uv_blade_info;
 extern short *uv_node_to_blade;
 extern short *uv_cpu_to_blade;
 extern short uv_possible_blades;
@@ -244,16 +312,16 @@ static inline int uv_node_to_blade_id(int nid)
 	return uv_node_to_blade[nid];
 }
 
-/* Convert a blade id to the NASID of the blade */
-static inline int uv_blade_to_nasid(int bid)
+/* Convert a blade id to the PNODE of the blade */
+static inline int uv_blade_to_pnode(int bid)
 {
-	return uv_blade_info[bid].nasid;
+	return uv_blade_info[bid].pnode;
 }
 
 /* Determine the number of possible cpus on a blade */
 static inline int uv_blade_nr_possible_cpus(int bid)
 {
-	return uv_blade_info[bid].nr_posible_cpus;
+	return uv_blade_info[bid].nr_possible_cpus;
 }
 
 /* Determine the number of online cpus on a blade */
@@ -262,16 +330,16 @@ static inline int uv_blade_nr_online_cpus(int bid)
 	return uv_blade_info[bid].nr_online_cpus;
 }
 
-/* Convert a cpu id to the NASID of the blade containing the cpu */
-static inline int uv_cpu_to_nasid(int cpu)
+/* Convert a cpu id to the PNODE of the blade containing the cpu */
+static inline int uv_cpu_to_pnode(int cpu)
 {
-	return uv_blade_info[uv_cpu_to_blade_id(cpu)].nasid;
+	return uv_blade_info[uv_cpu_to_blade_id(cpu)].pnode;
 }
 
-/* Convert a node number to the NASID of the blade */
-static inline int uv_node_to_nasid(int nid)
+/* Convert a linux node number to the PNODE of the blade */
+static inline int uv_node_to_pnode(int nid)
 {
-	return uv_blade_info[uv_node_to_blade_id(nid)].nasid;
+	return uv_blade_info[uv_node_to_blade_id(nid)].pnode;
 }
 
 /* Maximum possible number of blades */

include/linux/kernel_stat.h

 #ifndef _LINUX_KERNEL_STAT_H
 #define _LINUX_KERNEL_STAT_H
 
-#include <asm/irq.h>
 #include <linux/smp.h>
 #include <linux/threads.h>
 #include <linux/percpu.h>
 #include <linux/cpumask.h>
+#include <asm/irq.h>
 #include <asm/cputime.h>
 
 /*