Merge branch 'x86/apic' into irq/numa

Conflicts:
	arch/x86/kernel/apic/io_apic.c

Merge reason: non-trivial interaction between ongoing work in io_apic.c
              and the NUMA migration feature in the irq tree.
Signed-off-by: Ingo Molnar <mingo@elte.hu>

Documentation/kernel-parameters.txt

@@ -1565,6 +1565,9 @@ and is between 256 and 4096 characters. It is defined in the file
 	noinitrd	[RAM] Tells the kernel not to load any configured
 			initial RAM disk.
 
+	nointremap	[X86-64, Intel-IOMMU] Do not enable interrupt
+			remapping.
+
 	nointroute	[IA-64]
 
 	nojitter	[IA64] Disables jitter checking for ITC timers.

arch/x86/Kconfig

@@ -349,7 +349,7 @@ config X86_UV
 	depends on X86_64
 	depends on X86_EXTENDED_PLATFORM
 	depends on NUMA
-	select X86_X2APIC
+	depends on X86_X2APIC
 	---help---
 	  This option is needed in order to support SGI Ultraviolet systems.
 	  If you don't have one of these, you should say N here.

arch/x86/include/asm/apic.h

@@ -107,8 +107,7 @@ extern u32 native_safe_apic_wait_icr_idle(void);
 extern void native_apic_icr_write(u32 low, u32 id);
 extern u64 native_apic_icr_read(void);
 
-#define EIM_8BIT_APIC_ID	0
-#define EIM_32BIT_APIC_ID	1
+extern int x2apic_mode;
 
 #ifdef CONFIG_X86_X2APIC
 /*
@@ -166,10 +165,9 @@ static inline u64 native_x2apic_icr_read(void)
 	return val;
 }
 
-extern int x2apic, x2apic_phys;
+extern int x2apic_phys;
 extern void check_x2apic(void);
 extern void enable_x2apic(void);
-extern void enable_IR_x2apic(void);
 extern void x2apic_icr_write(u32 low, u32 id);
 static inline int x2apic_enabled(void)
 {
@@ -183,6 +181,8 @@ static inline int x2apic_enabled(void)
 		return 1;
 	return 0;
 }
+
+#define x2apic_supported()	(cpu_has_x2apic)
 #else
 static inline void check_x2apic(void)
 {
@@ -190,28 +190,20 @@ static inline void check_x2apic(void)
 static inline void enable_x2apic(void)
 {
 }
-static inline void enable_IR_x2apic(void)
-{
-}
 static inline int x2apic_enabled(void)
 {
 	return 0;
 }
 
-#define	x2apic	0
-
+#define	x2apic_preenabled 0
+#define	x2apic_supported()	0
 #endif
 
-extern int get_physical_broadcast(void);
+extern void enable_IR_x2apic(void);
 
-#ifdef CONFIG_X86_X2APIC
-static inline void ack_x2APIC_irq(void)
-{
-	/* Docs say use 0 for future compatibility */
-	native_apic_msr_write(APIC_EOI, 0);
-}
-#endif
+extern int get_physical_broadcast(void);
 
+extern void apic_disable(void);
 extern int lapic_get_maxlvt(void);
 extern void clear_local_APIC(void);
 extern void connect_bsp_APIC(void);
@@ -252,7 +244,7 @@ static inline void lapic_shutdown(void) { }
 #define local_apic_timer_c2_ok		1
 static inline void init_apic_mappings(void) { }
 static inline void disable_local_APIC(void) { }
-
+static inline void apic_disable(void) { }
 #endif /* !CONFIG_X86_LOCAL_APIC */
 
 #ifdef CONFIG_X86_64

arch/x86/include/asm/i8259.h

@@ -60,8 +60,4 @@ extern struct irq_chip i8259A_chip;
 extern void mask_8259A(void);
 extern void unmask_8259A(void);
 
-#ifdef CONFIG_X86_32
-extern void init_ISA_irqs(void);
-#endif
-
 #endif /* _ASM_X86_I8259_H */

arch/x86/include/asm/io_apic.h

@@ -161,15 +161,11 @@ extern int io_apic_set_pci_routing(struct device *dev, int ioapic, int pin,
 extern int (*ioapic_renumber_irq)(int ioapic, int irq);
 extern void ioapic_init_mappings(void);
 
-#ifdef CONFIG_X86_64
 extern struct IO_APIC_route_entry **alloc_ioapic_entries(void);
 extern void free_ioapic_entries(struct IO_APIC_route_entry **ioapic_entries);
 extern int save_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries);
 extern void mask_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries);
 extern int restore_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries);
-extern void reinit_intr_remapped_IO_APIC(int intr_remapping,
-	struct IO_APIC_route_entry **ioapic_entries);
-#endif
 
 extern void probe_nr_irqs_gsi(void);
 

arch/x86/include/asm/irq_remapping.h

 #ifndef _ASM_X86_IRQ_REMAPPING_H
 #define _ASM_X86_IRQ_REMAPPING_H
 
-#define IRTE_DEST(dest) ((x2apic) ? dest : dest << 8)
+#define IRTE_DEST(dest) ((x2apic_mode) ? dest : dest << 8)
 
 #endif	/* _ASM_X86_IRQ_REMAPPING_H */

arch/x86/include/asm/irq_vectors.h

@@ -34,6 +34,7 @@
 
 #ifdef CONFIG_X86_32
 # define SYSCALL_VECTOR			0x80
+# define IA32_SYSCALL_VECTOR		0x80
 #else
 # define IA32_SYSCALL_VECTOR		0x80
 #endif

arch/x86/include/asm/setup.h

@@ -33,7 +33,6 @@ struct x86_quirks {
 	int (*setup_ioapic_ids)(void);
 };
 
-extern void x86_quirk_pre_intr_init(void);
 extern void x86_quirk_intr_init(void);
 
 extern void x86_quirk_trap_init(void);

arch/x86/kernel/Makefile

@@ -28,7 +28,7 @@ CFLAGS_paravirt.o	:= $(nostackp)
 obj-y			:= process_$(BITS).o signal.o entry_$(BITS).o
 obj-y			+= traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
 obj-y			+= time_$(BITS).o ioport.o ldt.o dumpstack.o
-obj-y			+= setup.o i8259.o irqinit_$(BITS).o
+obj-y			+= setup.o i8259.o irqinit.o
 obj-$(CONFIG_X86_VISWS)	+= visws_quirks.o
 obj-$(CONFIG_X86_32)	+= probe_roms_32.o
 obj-$(CONFIG_X86_32)	+= sys_i386_32.o i386_ksyms_32.o

arch/x86/kernel/apic/es7000_32.c

@@ -145,7 +145,7 @@ es7000_rename_gsi(int ioapic, int gsi)
 	return gsi;
 }
 
-static int wakeup_secondary_cpu_via_mip(int cpu, unsigned long eip)
+static int __cpuinit wakeup_secondary_cpu_via_mip(int cpu, unsigned long eip)
 {
 	unsigned long vect = 0, psaival = 0;
 

arch/x86/kernel/apic/io_apic.c

@@ -489,121 +489,6 @@ static void ioapic_mask_entry(int apic, int pin)
 	spin_unlock_irqrestore(&ioapic_lock, flags);
 }
 
-#ifdef CONFIG_SMP
-static void send_cleanup_vector(struct irq_cfg *cfg)
-{
-	cpumask_var_t cleanup_mask;
-
-	if (unlikely(!alloc_cpumask_var(&cleanup_mask, GFP_ATOMIC))) {
-		unsigned int i;
-		cfg->move_cleanup_count = 0;
-		for_each_cpu_and(i, cfg->old_domain, cpu_online_mask)
-			cfg->move_cleanup_count++;
-		for_each_cpu_and(i, cfg->old_domain, cpu_online_mask)
-			apic->send_IPI_mask(cpumask_of(i), IRQ_MOVE_CLEANUP_VECTOR);
-	} else {
-		cpumask_and(cleanup_mask, cfg->old_domain, cpu_online_mask);
-		cfg->move_cleanup_count = cpumask_weight(cleanup_mask);
-		apic->send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR);
-		free_cpumask_var(cleanup_mask);
-	}
-	cfg->move_in_progress = 0;
-}
-
-static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq_cfg *cfg)
-{
-	int apic, pin;
-	struct irq_pin_list *entry;
-	u8 vector = cfg->vector;
-
-	entry = cfg->irq_2_pin;
-	for (;;) {
-		unsigned int reg;
-
-		if (!entry)
-			break;
-
-		apic = entry->apic;
-		pin = entry->pin;
-		/*
-		 * With interrupt-remapping, destination information comes
-		 * from interrupt-remapping table entry.
-		 */
-		if (!irq_remapped(irq))
-			io_apic_write(apic, 0x11 + pin*2, dest);
-		reg = io_apic_read(apic, 0x10 + pin*2);
-		reg &= ~IO_APIC_REDIR_VECTOR_MASK;
-		reg |= vector;
-		io_apic_modify(apic, 0x10 + pin*2, reg);
-		if (!entry->next)
-			break;
-		entry = entry->next;
-	}
-}
-
-static int
-assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask);
-
-/*
- * Either sets desc->affinity to a valid value, and returns
- * ->cpu_mask_to_apicid of that, or returns BAD_APICID and
- * leaves desc->affinity untouched.
- */
-static unsigned int
-set_desc_affinity(struct irq_desc *desc, const struct cpumask *mask)
-{
-	struct irq_cfg *cfg;
-	unsigned int irq;
-
-	if (!cpumask_intersects(mask, cpu_online_mask))
-		return BAD_APICID;
-
-	irq = desc->irq;
-	cfg = desc->chip_data;
-	if (assign_irq_vector(irq, cfg, mask))
-		return BAD_APICID;
-
-	cpumask_copy(desc->affinity, mask);
-
-	return apic->cpu_mask_to_apicid_and(desc->affinity, cfg->domain);
-}
-
-static int
-set_ioapic_affinity_irq_desc(struct irq_desc *desc, const struct cpumask *mask)
-{
-	struct irq_cfg *cfg;
-	unsigned long flags;
-	unsigned int dest;
-	unsigned int irq;
-	int ret = -1;
-
-	irq = desc->irq;
-	cfg = desc->chip_data;
-
-	spin_lock_irqsave(&ioapic_lock, flags);
-	dest = set_desc_affinity(desc, mask);
-	if (dest != BAD_APICID) {
-		/* Only the high 8 bits are valid. */
-		dest = SET_APIC_LOGICAL_ID(dest);
-		__target_IO_APIC_irq(irq, dest, cfg);
-		ret = 0;
-	}
-	spin_unlock_irqrestore(&ioapic_lock, flags);
-
-	return ret;
-}
-
-static int
-set_ioapic_affinity_irq(unsigned int irq, const struct cpumask *mask)
-{
-	struct irq_desc *desc;
-
-	desc = irq_to_desc(irq);
-
-	return set_ioapic_affinity_irq_desc(desc, mask);
-}
-#endif /* CONFIG_SMP */
-
 /*
  * The common case is 1:1 IRQ<->pin mappings. Sometimes there are
  * shared ISA-space IRQs, so we have to support them. We are super
@@ -822,7 +707,6 @@ static int __init ioapic_pirq_setup(char *str)
 __setup("pirq=", ioapic_pirq_setup);
 #endif /* CONFIG_X86_32 */
 
-#ifdef CONFIG_INTR_REMAP
 struct IO_APIC_route_entry **alloc_ioapic_entries(void)
 {
 	int apic;
@@ -920,20 +804,6 @@ int restore_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries)
 	return 0;
 }
 
-void reinit_intr_remapped_IO_APIC(int intr_remapping,
-	struct IO_APIC_route_entry **ioapic_entries)
-
-{
-	/*
-	 * for now plain restore of previous settings.
-	 * TBD: In the case of OS enabling interrupt-remapping,
-	 * IO-APIC RTE's need to be setup to point to interrupt-remapping
-	 * table entries. for now, do a plain restore, and wait for
-	 * the setup_IO_APIC_irqs() to do proper initialization.
-	 */
-	restore_IO_APIC_setup(ioapic_entries);
-}
-
 void free_ioapic_entries(struct IO_APIC_route_entry **ioapic_entries)
 {
 	int apic;
@@ -943,7 +813,6 @@ void free_ioapic_entries(struct IO_APIC_route_entry **ioapic_entries)
 
 	kfree(ioapic_entries);
 }
-#endif
 
 /*
  * Find the IRQ entry number of a certain pin.
@@ -2332,6 +2201,118 @@ static int ioapic_retrigger_irq(unsigned int irq)
  */
 
 #ifdef CONFIG_SMP
+static void send_cleanup_vector(struct irq_cfg *cfg)
+{
+	cpumask_var_t cleanup_mask;
+
+	if (unlikely(!alloc_cpumask_var(&cleanup_mask, GFP_ATOMIC))) {
+		unsigned int i;
+		cfg->move_cleanup_count = 0;
+		for_each_cpu_and(i, cfg->old_domain, cpu_online_mask)
+			cfg->move_cleanup_count++;
+		for_each_cpu_and(i, cfg->old_domain, cpu_online_mask)
+			apic->send_IPI_mask(cpumask_of(i), IRQ_MOVE_CLEANUP_VECTOR);
+	} else {
+		cpumask_and(cleanup_mask, cfg->old_domain, cpu_online_mask);
+		cfg->move_cleanup_count = cpumask_weight(cleanup_mask);
+		apic->send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR);
+		free_cpumask_var(cleanup_mask);
+	}
+	cfg->move_in_progress = 0;
+}
+
+static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq_cfg *cfg)
+{
+	int apic, pin;
+	struct irq_pin_list *entry;
+	u8 vector = cfg->vector;
+
+	entry = cfg->irq_2_pin;
+	for (;;) {
+		unsigned int reg;
+
+		if (!entry)
+			break;
+
+		apic = entry->apic;
+		pin = entry->pin;
+		/*
+		 * With interrupt-remapping, destination information comes
+		 * from interrupt-remapping table entry.
+		 */
+		if (!irq_remapped(irq))
+			io_apic_write(apic, 0x11 + pin*2, dest);
+		reg = io_apic_read(apic, 0x10 + pin*2);
+		reg &= ~IO_APIC_REDIR_VECTOR_MASK;
+		reg |= vector;
+		io_apic_modify(apic, 0x10 + pin*2, reg);
+		if (!entry->next)
+			break;
+		entry = entry->next;
+	}
+}
+
+static int
+assign_irq_vector(int irq, struct irq_cfg *cfg, const struct cpumask *mask);
+
+/*
+ * Either sets desc->affinity to a valid value, and returns
+ * ->cpu_mask_to_apicid of that, or returns BAD_APICID and
+ * leaves desc->affinity untouched.
+ */
+static unsigned int
+set_desc_affinity(struct irq_desc *desc, const struct cpumask *mask)
+{
+	struct irq_cfg *cfg;
+	unsigned int irq;
+
+	if (!cpumask_intersects(mask, cpu_online_mask))
+		return BAD_APICID;
+
+	irq = desc->irq;
+	cfg = desc->chip_data;
+	if (assign_irq_vector(irq, cfg, mask))
+		return BAD_APICID;
+
+	cpumask_copy(desc->affinity, mask);
+
+	return apic->cpu_mask_to_apicid_and(desc->affinity, cfg->domain);
+}
+
+static int
+set_ioapic_affinity_irq_desc(struct irq_desc *desc, const struct cpumask *mask)
+{
+	struct irq_cfg *cfg;
+	unsigned long flags;
+	unsigned int dest;
+	unsigned int irq;
+	int ret = -1;
+
+	irq = desc->irq;
+	cfg = desc->chip_data;
+
+	spin_lock_irqsave(&ioapic_lock, flags);
+	dest = set_desc_affinity(desc, mask);
+	if (dest != BAD_APICID) {
+		/* Only the high 8 bits are valid. */
+		dest = SET_APIC_LOGICAL_ID(dest);
+		__target_IO_APIC_irq(irq, dest, cfg);
+		ret = 0;
+	}
+	spin_unlock_irqrestore(&ioapic_lock, flags);
+
+	return ret;
+}
+
+static int
+set_ioapic_affinity_irq(unsigned int irq, const struct cpumask *mask)
+{
+	struct irq_desc *desc;
+
+	desc = irq_to_desc(irq);
+
+	return set_ioapic_affinity_irq_desc(desc, mask);
+}
 
 #ifdef CONFIG_INTR_REMAP
 
@@ -2478,53 +2459,6 @@ static void irq_complete_move(struct irq_desc **descp)
 static inline void irq_complete_move(struct irq_desc **descp) {}
 #endif
 
-static void __eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg)
-{
-	int apic, pin;
-	struct irq_pin_list *entry;
-
-	entry = cfg->irq_2_pin;
-	for (;;) {
-
-		if (!entry)
-			break;
-
-		apic = entry->apic;
-		pin = entry->pin;
-		io_apic_eoi(apic, pin);
-		entry = entry->next;
-	}
-}
-
-static void
-eoi_ioapic_irq(struct irq_desc *desc)
-{
-	struct irq_cfg *cfg;
-	unsigned long flags;
-	unsigned int irq;
-
-	irq = desc->irq;
-	cfg = desc->chip_data;
-
-	spin_lock_irqsave(&ioapic_lock, flags);
-	__eoi_ioapic_irq(irq, cfg);
-	spin_unlock_irqrestore(&ioapic_lock, flags);
-}
-
-#ifdef CONFIG_X86_X2APIC
-static void ack_x2apic_level(unsigned int irq)
-{
-	struct irq_desc *desc = irq_to_desc(irq);
-	ack_x2APIC_irq();
-	eoi_ioapic_irq(desc);
-}
-
-static void ack_x2apic_edge(unsigned int irq)
-{
-	ack_x2APIC_irq();
-}
-#endif
-
 static void ack_apic_edge(unsigned int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
@@ -2588,9 +2522,6 @@ static void ack_apic_level(unsigned int irq)
 	 */
 	ack_APIC_irq();
 
-	if (irq_remapped(irq))
-		eoi_ioapic_irq(desc);
-
 	/* Now we can move and renable the irq */
 	if (unlikely(do_unmask_irq)) {
 		/* Only migrate the irq if the ack has been received.
@@ -2637,22 +2568,50 @@ static void ack_apic_level(unsigned int irq)
 }
 
 #ifdef CONFIG_INTR_REMAP
+static void __eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg)
+{
+	int apic, pin;
+	struct irq_pin_list *entry;
+
+	entry = cfg->irq_2_pin;
+	for (;;) {
+
+		if (!entry)
+			break;
+
+		apic = entry->apic;
+		pin = entry->pin;
+		io_apic_eoi(apic, pin);
+		entry = entry->next;
+	}
+}
+
+static void
+eoi_ioapic_irq(struct irq_desc *desc)
+{
+	struct irq_cfg *cfg;
+	unsigned long flags;
+	unsigned int irq;
+
+	irq = desc->irq;
+	cfg = desc->chip_data;
+
+	spin_lock_irqsave(&ioapic_lock, flags);
+	__eoi_ioapic_irq(irq, cfg);
+	spin_unlock_irqrestore(&ioapic_lock, flags);
+}
+
 static void ir_ack_apic_edge(unsigned int irq)
 {
-#ifdef CONFIG_X86_X2APIC
-       if (x2apic_enabled())
-               return ack_x2apic_edge(irq);
-#endif
-       return ack_apic_edge(irq);
+	ack_APIC_irq();
 }
 
 static void ir_ack_apic_level(unsigned int irq)
 {
-#ifdef CONFIG_X86_X2APIC
-       if (x2apic_enabled())
-               return ack_x2apic_level(irq);
-#endif
-       return ack_apic_level(irq);
+	struct irq_desc *desc = irq_to_desc(irq);
+
+	ack_APIC_irq();
+	eoi_ioapic_irq(desc);
 }
 #endif /* CONFIG_INTR_REMAP */
 

arch/x86/kernel/apic/probe_64.c

@@ -50,7 +50,7 @@ static struct apic *apic_probe[] __initdata = {
 void __init default_setup_apic_routing(void)
 {
 #ifdef CONFIG_X86_X2APIC
-	if (x2apic && (apic != &apic_x2apic_phys &&
+	if (x2apic_mode && (apic != &apic_x2apic_phys &&
 #ifdef CONFIG_X86_UV
 		       apic != &apic_x2apic_uv_x &&
 #endif

arch/x86/kernel/apic/summit_32.c

@@ -173,13 +173,6 @@ static inline int is_WPEG(struct rio_detail *rio){
 		rio->type == LookOutAWPEG || rio->type == LookOutBWPEG);
 }
 
-
-/* In clustered mode, the high nibble of APIC ID is a cluster number.
- * The low nibble is a 4-bit bitmap. */
-#define XAPIC_DEST_CPUS_SHIFT	4
-#define XAPIC_DEST_CPUS_MASK	((1u << XAPIC_DEST_CPUS_SHIFT) - 1)
-#define XAPIC_DEST_CLUSTER_MASK	(XAPIC_DEST_CPUS_MASK << XAPIC_DEST_CPUS_SHIFT)
-
 #define SUMMIT_APIC_DFR_VALUE	(APIC_DFR_CLUSTER)
 
 static const struct cpumask *summit_target_cpus(void)

arch/x86/kernel/apic/x2apic_uv_x.c

@@ -105,7 +105,7 @@ static void uv_vector_allocation_domain(int cpu, struct cpumask *retmask)
 	cpumask_set_cpu(cpu, retmask);
 }
 
-static int uv_wakeup_secondary(int phys_apicid, unsigned long start_rip)
+static int __cpuinit uv_wakeup_secondary(int phys_apicid, unsigned long start_rip)
 {
 #ifdef CONFIG_SMP
 	unsigned long val;

arch/x86/kernel/irq.c

@@ -24,9 +24,9 @@ void (*generic_interrupt_extension)(void) = NULL;
  */
 void ack_bad_irq(unsigned int irq)
 {
-	printk(KERN_ERR "unexpected IRQ trap at vector %02x\n", irq);
+	if (printk_ratelimit())
+		pr_err("unexpected IRQ trap at vector %02x\n", irq);
 
-#ifdef CONFIG_X86_LOCAL_APIC
 	/*
 	 * Currently unexpected vectors happen only on SMP and APIC.
 	 * We _must_ ack these because every local APIC has only N
@@ -36,9 +36,7 @@ void ack_bad_irq(unsigned int irq)
 	 * completely.
 	 * But only ack when the APIC is enabled -AK
 	 */
-	if (cpu_has_apic)
-		ack_APIC_irq();
-#endif
+	ack_APIC_irq();
 }
 
 #define irq_stats(x)		(&per_cpu(irq_stat, x))
@@ -178,7 +176,7 @@ u64 arch_irq_stat_cpu(unsigned int cpu)
 	sum += irq_stats(cpu)->irq_thermal_count;
 # ifdef CONFIG_X86_64
 	sum += irq_stats(cpu)->irq_threshold_count;
-#endif
+# endif
 #endif
 	return sum;
 }
@@ -213,14 +211,11 @@ unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
 	irq = __get_cpu_var(vector_irq)[vector];
 
 	if (!handle_irq(irq, regs)) {
-#ifdef CONFIG_X86_64
-		if (!disable_apic)
-			ack_APIC_irq();
-#endif
+		ack_APIC_irq();
 
 		if (printk_ratelimit())
-			printk(KERN_EMERG "%s: %d.%d No irq handler for vector (irq %d)\n",
-			       __func__, smp_processor_id(), vector, irq);
+			pr_emerg("%s: %d.%d No irq handler for vector (irq %d)\n",
+				__func__, smp_processor_id(), vector, irq);
 	}
 
 	irq_exit();

arch/x86/kernel/irqinit_32.c → arch/x86/kernel/irqinit.c

+#include <linux/linkage.h>
 #include <linux/errno.h>
 #include <linux/signal.h>
 #include <linux/sched.h>
 #include <linux/ioport.h>
 #include <linux/interrupt.h>
+#include <linux/timex.h>
 #include <linux/slab.h>
 #include <linux/random.h>
+#include <linux/kprobes.h>
 #include <linux/init.h>
 #include <linux/kernel_stat.h>
 #include <linux/sysdev.h>
 #include <linux/bitops.h>
+#include <linux/acpi.h>
 #include <linux/io.h>
 #include <linux/delay.h>
 
 #include <asm/atomic.h>
 #include <asm/system.h>
 #include <asm/timer.h>
+#include <asm/hw_irq.h>
 #include <asm/pgtable.h>
 #include <asm/desc.h>
 #include <asm/apic.h>
@@ -22,7 +27,23 @@
 #include <asm/i8259.h>
 #include <asm/traps.h>
 
+/*
+ * ISA PIC or low IO-APIC triggered (INTA-cycle or APIC) interrupts:
+ * (these are usually mapped to vectors 0x30-0x3f)
+ */
+
+/*
+ * The IO-APIC gives us many more interrupt sources. Most of these
+ * are unused but an SMP system is supposed to have enough memory ...
+ * sometimes (mostly wrt. hw bugs) we get corrupted vectors all
+ * across the spectrum, so we really want to be prepared to get all
+ * of these. Plus, more powerful systems might have more than 64
+ * IO-APIC registers.
+ *
+ * (these are usually mapped into the 0x30-0xff vector range)
+ */
 
+#ifdef CONFIG_X86_32
 /*
  * Note that on a 486, we don't want to do a SIGFPE on an irq13
  * as the irq is unreliable, and exception 16 works correctly
@@ -52,30 +73,7 @@ static struct irqaction fpu_irq = {
 	.handler = math_error_irq,
 	.name = "fpu",
 };
-
-void __init init_ISA_irqs(void)
-{
-	int i;
-
-#ifdef CONFIG_X86_LOCAL_APIC
-	init_bsp_APIC();
 #endif
-	init_8259A(0);
-
-	/*
-	 * 16 old-style INTA-cycle interrupts:
-	 */
-	for (i = 0; i < NR_IRQS_LEGACY; i++) {
-		struct irq_desc *desc = irq_to_desc(i);
-
-		desc->status = IRQ_DISABLED;
-		desc->action = NULL;
-		desc->depth = 1;
-
-		set_irq_chip_and_handler_name(i, &i8259A_chip,
-					      handle_level_irq, "XT");
-	}
-}
 
 /*
  * IRQ2 is cascade interrupt to second interrupt controller
@@ -118,29 +116,37 @@ int vector_used_by_percpu_irq(unsigned int vector)
 	return 0;
 }
 
-/* Overridden in paravirt.c */
-void init_IRQ(void) __attribute__((weak, alias("native_init_IRQ")));
-
-void __init native_init_IRQ(void)
+static void __init init_ISA_irqs(void)
 {
 	int i;
 
-	/* Execute any quirks before the call gates are initialised: */
-	x86_quirk_pre_intr_init();
+#if defined(CONFIG_X86_64) || defined(CONFIG_X86_LOCAL_APIC)
+	init_bsp_APIC();
+#endif
+	init_8259A(0);
 
 	/*
-	 * Cover the whole vector space, no vector can escape
-	 * us. (some of these will be overridden and become
-	 * 'special' SMP interrupts)
+	 * 16 old-style INTA-cycle interrupts:
 	 */
-	for (i =  FIRST_EXTERNAL_VECTOR; i < NR_VECTORS; i++) {
-		/* SYSCALL_VECTOR was reserved in trap_init. */
-		if (i != SYSCALL_VECTOR)
-			set_intr_gate(i, interrupt[i-FIRST_EXTERNAL_VECTOR]);
+	for (i = 0; i < NR_IRQS_LEGACY; i++) {
+		struct irq_desc *desc = irq_to_desc(i);
+
+		desc->status = IRQ_DISABLED;
+		desc->action = NULL;
+		desc->depth = 1;
+
+		set_irq_chip_and_handler_name(i, &i8259A_chip,
+					      handle_level_irq, "XT");
 	}
+}
 
+/* Overridden in paravirt.c */
+void init_IRQ(void) __attribute__((weak, alias("native_init_IRQ")));
 
-#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_SMP)
+static void __init smp_intr_init(void)
+{
+#ifdef CONFIG_SMP
+#if defined(CONFIG_X86_64) || defined(CONFIG_X86_LOCAL_APIC)
 	/*
 	 * The reschedule interrupt is a CPU-to-CPU reschedule-helper
 	 * IPI, driven by wakeup.
@@ -160,16 +166,27 @@ void __init native_init_IRQ(void)
 	/* IPI for generic function call */
 	alloc_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt);
 
-	/* IPI for single call function */
+	/* IPI for generic single function call */
 	alloc_intr_gate(CALL_FUNCTION_SINGLE_VECTOR,
-				 call_function_single_interrupt);
+			call_function_single_interrupt);
 
 	/* Low priority IPI to cleanup after moving an irq */
 	set_intr_gate(IRQ_MOVE_CLEANUP_VECTOR, irq_move_cleanup_interrupt);
 	set_bit(IRQ_MOVE_CLEANUP_VECTOR, used_vectors);
 #endif
+#endif /* CONFIG_SMP */
+}
+
+static void __init apic_intr_init(void)
+{
+	smp_intr_init();
+
+#ifdef CONFIG_X86_64
+	alloc_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt);
+	alloc_intr_gate(THRESHOLD_APIC_VECTOR, threshold_interrupt);
+#endif
 
-#ifdef CONFIG_X86_LOCAL_APIC
+#if defined(CONFIG_X86_64) || defined(CONFIG_X86_LOCAL_APIC)
 	/* self generated IPI for local APIC timer */
 	alloc_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt);
 
@@ -179,16 +196,67 @@ void __init native_init_IRQ(void)
 	/* IPI vectors for APIC spurious and error interrupts */
 	alloc_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt);
 	alloc_intr_gate(ERROR_APIC_VECTOR, error_interrupt);
+
+	/* Performance monitoring interrupts: */
+# ifdef CONFIG_PERF_COUNTERS
+	alloc_intr_gate(LOCAL_PERF_VECTOR, perf_counter_interrupt);
+	alloc_intr_gate(LOCAL_PENDING_VECTOR, perf_pending_interrupt);
+# endif
+
 #endif
 
+#ifdef CONFIG_X86_32
 #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_MCE_P4THERMAL)
 	/* thermal monitor LVT interrupt */
 	alloc_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt);
 #endif
+#endif
+}
+
+/**
+ * x86_quirk_pre_intr_init - initialisation prior to setting up interrupt vectors
+ *
+ * Description:
+ *	Perform any necessary interrupt initialisation prior to setting up
+ *	the "ordinary" interrupt call gates.  For legacy reasons, the ISA
+ *	interrupts should be initialised here if the machine emulates a PC
+ *	in any way.
+ **/
+static void __init x86_quirk_pre_intr_init(void)
+{
+#ifdef CONFIG_X86_32
+	if (x86_quirks->arch_pre_intr_init) {
+		if (x86_quirks->arch_pre_intr_init())
+			return;
+	}
+#endif
+	init_ISA_irqs();
+}
+
+void __init native_init_IRQ(void)
+{
+	int i;
+
+	/* Execute any quirks before the call gates are initialised: */
+	x86_quirk_pre_intr_init();
+
+	apic_intr_init();
+
+	/*
+	 * Cover the whole vector space, no vector can escape
+	 * us. (some of these will be overridden and become
+	 * 'special' SMP interrupts)
+	 */
+	for (i = FIRST_EXTERNAL_VECTOR; i < NR_VECTORS; i++) {
+		/* IA32_SYSCALL_VECTOR could be used in trap_init already. */
+		if (!test_bit(i, used_vectors))
+			set_intr_gate(i, interrupt[i-FIRST_EXTERNAL_VECTOR]);
+	}
 
 	if (!acpi_ioapic)
 		setup_irq(2, &irq2);
 
+#ifdef CONFIG_X86_32
 	/*
 	 * Call quirks after call gates are initialised (usually add in
 	 * the architecture specific gates):
@@ -203,4 +271,5 @@ void __init native_init_IRQ(void)
 		setup_irq(FPU_IRQ, &fpu_irq);
 
 	irq_ctx_init(smp_processor_id());
+#endif
 }

arch/x86/kernel/irqinit_64.c

-#include <linux/linkage.h>
-#include <linux/errno.h>
-#include <linux/signal.h>
-#include <linux/sched.h>
-#include <linux/ioport.h>
-#include <linux/interrupt.h>
-#include <linux/timex.h>
-#include <linux/slab.h>
-#include <linux/random.h>
-#include <linux/init.h>
-#include <linux/kernel_stat.h>
-#include <linux/sysdev.h>
-#include <linux/bitops.h>
-#include <linux/acpi.h>
-#include <linux/io.h>
-#include <linux/delay.h>
-
-#include <asm/atomic.h>
-#include <asm/system.h>
-#include <asm/hw_irq.h>
-#include <asm/pgtable.h>
-#include <asm/desc.h>
-#include <asm/apic.h>
-#include <asm/i8259.h>
-
-/*
- * ISA PIC or low IO-APIC triggered (INTA-cycle or APIC) interrupts:
- * (these are usually mapped to vectors 0x30-0x3f)
- */
-
-/*
- * The IO-APIC gives us many more interrupt sources. Most of these
- * are unused but an SMP system is supposed to have enough memory ...
- * sometimes (mostly wrt. hw bugs) we get corrupted vectors all
- * across the spectrum, so we really want to be prepared to get all
- * of these. Plus, more powerful systems might have more than 64
- * IO-APIC registers.
- *
- * (these are usually mapped into the 0x30-0xff vector range)
- */
-
-/*
- * IRQ2 is cascade interrupt to second interrupt controller
- */
-
-static struct irqaction irq2 = {
-	.handler = no_action,
-	.name = "cascade",
-};
-DEFINE_PER_CPU(vector_irq_t, vector_irq) = {
-	[0 ... IRQ0_VECTOR - 1] = -1,
-	[IRQ0_VECTOR] = 0,
-	[IRQ1_VECTOR] = 1,
-	[IRQ2_VECTOR] = 2,
-	[IRQ3_VECTOR] = 3,
-	[IRQ4_VECTOR] = 4,
-	[IRQ5_VECTOR] = 5,
-	[IRQ6_VECTOR] = 6,
-	[IRQ7_VECTOR] = 7,
-	[IRQ8_VECTOR] = 8,
-	[IRQ9_VECTOR] = 9,
-	[IRQ10_VECTOR] = 10,
-	[IRQ11_VECTOR] = 11,
-	[IRQ12_VECTOR] = 12,
-	[IRQ13_VECTOR] = 13,
-	[IRQ14_VECTOR] = 14,
-	[IRQ15_VECTOR] = 15,
-	[IRQ15_VECTOR + 1 ... NR_VECTORS - 1] = -1
-};
-
-int vector_used_by_percpu_irq(unsigned int vector)
-{
-	int cpu;
-
-	for_each_online_cpu(cpu) {
-		if (per_cpu(vector_irq, cpu)[vector] != -1)
-			return 1;
-	}
-
-	return 0;
-}
-
-static void __init init_ISA_irqs(void)
-{
-	int i;
-
-	init_bsp_APIC();
-	init_8259A(0);
-
-	for (i = 0; i < NR_IRQS_LEGACY; i++) {
-		struct irq_desc *desc = irq_to_desc(i);
-
-		desc->status = IRQ_DISABLED;
-		desc->action = NULL;
-		desc->depth = 1;
-
-		/*
-		 * 16 old-style INTA-cycle interrupts:
-		 */
-		set_irq_chip_and_handler_name(i, &i8259A_chip,
-						      handle_level_irq, "XT");
-	}
-}
-
-void init_IRQ(void) __attribute__((weak, alias("native_init_IRQ")));
-
-static void __init smp_intr_init(void)
-{
-#ifdef CONFIG_SMP
-	/*
-	 * The reschedule interrupt is a CPU-to-CPU reschedule-helper
-	 * IPI, driven by wakeup.
-	 */
-	alloc_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt);
-
-	/* IPIs for invalidation */
-	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 */
-	alloc_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt);
-
-	/* IPI for generic single function call */
-	alloc_intr_gate(CALL_FUNCTION_SINGLE_VECTOR,
-			call_function_single_interrupt);
-
-	/* Low priority IPI to cleanup after moving an irq */
-	set_intr_gate(IRQ_MOVE_CLEANUP_VECTOR, irq_move_cleanup_interrupt);
-	set_bit(IRQ_MOVE_CLEANUP_VECTOR, used_vectors);
-#endif
-}
-
-static void __init apic_intr_init(void)
-{
-	smp_intr_init();
-
-	alloc_intr_gate(THERMAL_APIC_VECTOR, thermal_interrupt);
-	alloc_intr_gate(THRESHOLD_APIC_VECTOR, threshold_interrupt);
-
-	/* self generated IPI for local APIC timer */
-	alloc_intr_gate(LOCAL_TIMER_VECTOR, apic_timer_interrupt);
-
-	/* generic IPI for platform specific use */
-	alloc_intr_gate(GENERIC_INTERRUPT_VECTOR, generic_interrupt);
-
-	/* IPI vectors for APIC spurious and error interrupts */
-	alloc_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt);
-	alloc_intr_gate(ERROR_APIC_VECTOR, error_interrupt);
-}
-
-void __init native_init_IRQ(void)
-{
-	int i;
-
-	init_ISA_irqs();
-	/*
-	 * Cover the whole vector space, no vector can escape
-	 * us. (some of these will be overridden and become
-	 * 'special' SMP interrupts)
-	 */
-	for (i = 0; i < (NR_VECTORS - FIRST_EXTERNAL_VECTOR); i++) {
-		int vector = FIRST_EXTERNAL_VECTOR + i;
-		if (vector != IA32_SYSCALL_VECTOR)
-			set_intr_gate(vector, interrupt[i]);
-	}
-
-	apic_intr_init();
-
-	if (!acpi_ioapic)
-		setup_irq(2, &irq2);
-}

arch/x86/kernel/setup.c

@@ -996,24 +996,6 @@ void __init setup_arch(char **cmdline_p)
 
 #ifdef CONFIG_X86_32
 
-/**
- * x86_quirk_pre_intr_init - initialisation prior to setting up interrupt vectors
- *
- * Description:
- *	Perform any necessary interrupt initialisation prior to setting up
- *	the "ordinary" interrupt call gates.  For legacy reasons, the ISA
- *	interrupts should be initialised here if the machine emulates a PC
- *	in any way.
- **/
-void __init x86_quirk_pre_intr_init(void)
-{
-	if (x86_quirks->arch_pre_intr_init) {
-		if (x86_quirks->arch_pre_intr_init())
-			return;
-	}
-	init_ISA_irqs();
-}
-
 /**
  * x86_quirk_intr_init - post gate setup interrupt initialisation
  *

arch/x86/kernel/smp.c

@@ -193,19 +193,19 @@ void smp_call_function_single_interrupt(struct pt_regs *regs)
 }
 
 struct smp_ops smp_ops = {
-	.smp_prepare_boot_cpu = native_smp_prepare_boot_cpu,
-	.smp_prepare_cpus = native_smp_prepare_cpus,
-	.smp_cpus_done = native_smp_cpus_done,
+	.smp_prepare_boot_cpu	= native_smp_prepare_boot_cpu,
+	.smp_prepare_cpus	= native_smp_prepare_cpus,
+	.smp_cpus_done		= native_smp_cpus_done,
 
-	.smp_send_stop = native_smp_send_stop,
-	.smp_send_reschedule = native_smp_send_reschedule,
+	.smp_send_stop		= native_smp_send_stop,
+	.smp_send_reschedule	= native_smp_send_reschedule,
 
-	.cpu_up = native_cpu_up,
-	.cpu_die = native_cpu_die,
-	.cpu_disable = native_cpu_disable,
-	.play_dead = native_play_dead,
+	.cpu_up			= native_cpu_up,
+	.cpu_die		= native_cpu_die,
+	.cpu_disable		= native_cpu_disable,
+	.play_dead		= native_play_dead,
 
-	.send_call_func_ipi = native_send_call_func_ipi,
+	.send_call_func_ipi	= native_send_call_func_ipi,
 	.send_call_func_single_ipi = native_send_call_func_single_ipi,
 };
 EXPORT_SYMBOL_GPL(smp_ops);

arch/x86/kernel/smpboot.c

@@ -504,7 +504,7 @@ void __inquire_remote_apic(int apicid)
  * INIT, INIT, STARTUP sequence will reset the chip hard for us, and this
  * won't ... remember to clear down the APIC, etc later.
  */
-int __devinit
+int __cpuinit
 wakeup_secondary_cpu_via_nmi(int logical_apicid, unsigned long start_eip)
 {
 	unsigned long send_status, accept_status = 0;
@@ -538,7 +538,7 @@ wakeup_secondary_cpu_via_nmi(int logical_apicid, unsigned long start_eip)
 	return (send_status | accept_status);
 }
 
-int __devinit
+static int __cpuinit
 wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
 {
 	unsigned long send_status, accept_status = 0;
@@ -822,10 +822,12 @@ do_rest:
 	/* mark "stuck" area as not stuck */
 	*((volatile unsigned long *)trampoline_base) = 0;
 
-	/*
-	 * Cleanup possible dangling ends...
-	 */
-	smpboot_restore_warm_reset_vector();
+	if (get_uv_system_type() != UV_NON_UNIQUE_APIC) {
+		/*
+		 * Cleanup possible dangling ends...
+		 */
+		smpboot_restore_warm_reset_vector();
+	}
 
 	return boot_error;
 }

arch/x86/kernel/traps.c

@@ -969,11 +969,8 @@ void __init trap_init(void)
 	for (i = 0; i < FIRST_EXTERNAL_VECTOR; i++)
 		set_bit(i, used_vectors);
 
-#ifdef CONFIG_X86_64
 	set_bit(IA32_SYSCALL_VECTOR, used_vectors);
-#else
-	set_bit(SYSCALL_VECTOR, used_vectors);
-#endif
+
 	/*
 	 * Should be a barrier for any external CPU state:
 	 */

drivers/pci/intel-iommu.c

@@ -1968,15 +1968,6 @@ static int __init init_dmars(void)
 		}
 	}
 
-#ifdef CONFIG_INTR_REMAP
-	if (!intr_remapping_enabled) {
-		ret = enable_intr_remapping(0);
-		if (ret)
-			printk(KERN_ERR
-			       "IOMMU: enable interrupt remapping failed\n");
-	}
-#endif
-
 	/*
 	 * For each rmrr
 	 *   for each dev attached to rmrr

drivers/pci/intr_remapping.c

@@ -15,6 +15,14 @@ static struct ioapic_scope ir_ioapic[MAX_IO_APICS];
 static int ir_ioapic_num;
 int intr_remapping_enabled;
 
+static int disable_intremap;
+static __init int setup_nointremap(char *str)
+{
+	disable_intremap = 1;
+	return 0;
+}
+early_param("nointremap", setup_nointremap);
+
 struct irq_2_iommu {
 	struct intel_iommu *iommu;
 	u16 irte_index;
@@ -420,20 +428,6 @@ static void iommu_set_intr_remapping(struct intel_iommu *iommu, int mode)
 		      readl, (sts & DMA_GSTS_IRTPS), sts);
 	spin_unlock_irqrestore(&iommu->register_lock, flags);
 
-	if (mode == 0) {
-		spin_lock_irqsave(&iommu->register_lock, flags);
-
-		/* enable comaptiblity format interrupt pass through */
-		cmd = iommu->gcmd | DMA_GCMD_CFI;
-		iommu->gcmd |= DMA_GCMD_CFI;
-		writel(cmd, iommu->reg + DMAR_GCMD_REG);
-
-		IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
-			      readl, (sts & DMA_GSTS_CFIS), sts);
-
-		spin_unlock_irqrestore(&iommu->register_lock, flags);
-	}
-
 	/*
 	 * global invalidation of interrupt entry cache before enabling
 	 * interrupt-remapping.
@@ -513,6 +507,23 @@ end:
 	spin_unlock_irqrestore(&iommu->register_lock, flags);
 }
 
+int __init intr_remapping_supported(void)
+{
+	struct dmar_drhd_unit *drhd;
+
+	if (disable_intremap)
+		return 0;
+
+	for_each_drhd_unit(drhd) {
+		struct intel_iommu *iommu = drhd->iommu;
+
+		if (!ecap_ir_support(iommu->ecap))
+			return 0;
+	}
+
+	return 1;
+}
+
 int __init enable_intr_remapping(int eim)
 {
 	struct dmar_drhd_unit *drhd;

include/linux/dmar.h

@@ -108,6 +108,7 @@ struct irte {
 };
 #ifdef CONFIG_INTR_REMAP
 extern int intr_remapping_enabled;
+extern int intr_remapping_supported(void);
 extern int enable_intr_remapping(int);
 extern void disable_intr_remapping(void);
 extern int reenable_intr_remapping(int);
@@ -157,6 +158,8 @@ static inline struct intel_iommu *map_ioapic_to_ir(int apic)
 }
 #define irq_remapped(irq)		(0)
 #define enable_intr_remapping(mode)	(-1)
+#define disable_intr_remapping()	(0)
+#define reenable_intr_remapping(mode)	(0)
 #define intr_remapping_enabled		(0)
 #endif