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>

21 files changed, 455 insertions, 598 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 674e21e9f0a..e03485b2828 100644
--- a/arch/x86/Kconfig
+++ b/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.
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 42f2f837742..3738438a91f 100644
--- a/arch/x86/include/asm/apic.h
+++ b/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
diff --git a/arch/x86/include/asm/i8259.h b/arch/x86/include/asm/i8259.h
index 1a99e6c092a..58d7091eeb1 100644
--- a/arch/x86/include/asm/i8259.h
+++ b/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 */
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index 07f2913ba5d..27bd2fdd00a 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/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);
 
diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h
index 0396760fccb..f275e224450 100644
--- a/arch/x86/include/asm/irq_remapping.h
+++ b/arch/x86/include/asm/irq_remapping.h
@@ -1,6 +1,6 @@
 #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 */
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index 3cbd79bbb47..910b5a3d675 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/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
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index bdc2ada05ae..4093d1ed6db 100644
--- a/arch/x86/include/asm/setup.h
+++ b/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);
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 145cce75cda..16e3acfe19e 100644
--- a/arch/x86/kernel/Makefile
+++ b/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
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index f2870920f24..28f747d61d7 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -98,6 +98,29 @@ early_param("lapic", parse_lapic);
 /* Local APIC was disabled by the BIOS and enabled by the kernel */
 static int enabled_via_apicbase;
 
+/*
+ * Handle interrupt mode configuration register (IMCR).
+ * This register controls whether the interrupt signals
+ * that reach the BSP come from the master PIC or from the
+ * local APIC. Before entering Symmetric I/O Mode, either
+ * the BIOS or the operating system must switch out of
+ * PIC Mode by changing the IMCR.
+ */
+static inline void imcr_pic_to_apic(void)
+{
+	/* select IMCR register */
+	outb(0x70, 0x22);
+	/* NMI and 8259 INTR go through APIC */
+	outb(0x01, 0x23);
+}
+
+static inline void imcr_apic_to_pic(void)
+{
+	/* select IMCR register */
+	outb(0x70, 0x22);
+	/* NMI and 8259 INTR go directly to BSP */
+	outb(0x00, 0x23);
+}
 #endif
 
 #ifdef CONFIG_X86_64
@@ -111,13 +134,19 @@ static __init int setup_apicpmtimer(char *s)
 __setup("apicpmtimer", setup_apicpmtimer);
 #endif
 
+int x2apic_mode;
 #ifdef CONFIG_X86_X2APIC
-int x2apic;
 /* x2apic enabled before OS handover */
 static int x2apic_preenabled;
 static int disable_x2apic;
 static __init int setup_nox2apic(char *str)
 {
+	if (x2apic_enabled()) {
+		pr_warning("Bios already enabled x2apic, "
+			   "can't enforce nox2apic");
+		return 0;
+	}
+
 	disable_x2apic = 1;
 	setup_clear_cpu_cap(X86_FEATURE_X2APIC);
 	return 0;
@@ -209,6 +238,24 @@ static int modern_apic(void)
 	return lapic_get_version() >= 0x14;
 }
 
+/*
+ * bare function to substitute write operation
+ * and it's _that_ fast :)
+ */
+void native_apic_write_dummy(u32 reg, u32 v)
+{
+	WARN_ON_ONCE((cpu_has_apic || !disable_apic));
+}
+
+/*
+ * right after this call apic->write doesn't do anything
+ * note that there is no restore operation it works one way
+ */
+void apic_disable(void)
+{
+	apic->write = native_apic_write_dummy;
+}
+
 void native_apic_wait_icr_idle(void)
 {
 	while (apic_read(APIC_ICR) & APIC_ICR_BUSY)
@@ -815,7 +862,7 @@ void clear_local_APIC(void)
 	u32 v;
 
 	/* APIC hasn't been mapped yet */
-	if (!x2apic && !apic_phys)
+	if (!x2apic_mode && !apic_phys)
 		return;
 
 	maxlvt = lapic_get_maxlvt();
@@ -1287,7 +1334,7 @@ void check_x2apic(void)
 {
 	if (x2apic_enabled()) {
 		pr_info("x2apic enabled by BIOS, switching to x2apic ops\n");
-		x2apic_preenabled = x2apic = 1;
+		x2apic_preenabled = x2apic_mode = 1;
 	}
 }
 
@@ -1295,7 +1342,7 @@ void enable_x2apic(void)
 {
 	int msr, msr2;
 
-	if (!x2apic)
+	if (!x2apic_mode)
 		return;
 
 	rdmsr(MSR_IA32_APICBASE, msr, msr2);
@@ -1304,6 +1351,7 @@ void enable_x2apic(void)
 		wrmsr(MSR_IA32_APICBASE, msr | X2APIC_ENABLE, 0);
 	}
 }
+#endif /* CONFIG_X86_X2APIC */
 
 void __init enable_IR_x2apic(void)
 {
@@ -1312,32 +1360,21 @@ void __init enable_IR_x2apic(void)
 	unsigned long flags;
 	struct IO_APIC_route_entry **ioapic_entries = NULL;
 
-	if (!cpu_has_x2apic)
-		return;
-
-	if (!x2apic_preenabled && disable_x2apic) {
-		pr_info("Skipped enabling x2apic and Interrupt-remapping "
-			"because of nox2apic\n");
-		return;
+	ret = dmar_table_init();
+	if (ret) {
+		pr_debug("dmar_table_init() failed with %d:\n", ret);
+		goto ir_failed;
 	}
 
-	if (x2apic_preenabled && disable_x2apic)
-		panic("Bios already enabled x2apic, can't enforce nox2apic");
-
-	if (!x2apic_preenabled && skip_ioapic_setup) {
-		pr_info("Skipped enabling x2apic and Interrupt-remapping "
-			"because of skipping io-apic setup\n");
-		return;
+	if (!intr_remapping_supported()) {
+		pr_debug("intr-remapping not supported\n");
+		goto ir_failed;
 	}
 
-	ret = dmar_table_init();
-	if (ret) {
-		pr_info("dmar_table_init() failed with %d:\n", ret);
 
-		if (x2apic_preenabled)
-			panic("x2apic enabled by bios. But IR enabling failed");
-		else
-			pr_info("Not enabling x2apic,Intr-remapping\n");
+	if (!x2apic_preenabled && skip_ioapic_setup) {
+		pr_info("Skipped enabling intr-remap because of skipping "
+			"io-apic setup\n");
 		return;
 	}
 
@@ -1357,19 +1394,16 @@ void __init enable_IR_x2apic(void)
 	mask_IO_APIC_setup(ioapic_entries);
 	mask_8259A();
 
-	ret = enable_intr_remapping(EIM_32BIT_APIC_ID);
-
-	if (ret && x2apic_preenabled) {
-		local_irq_restore(flags);
-		panic("x2apic enabled by bios. But IR enabling failed");
-	}
-
+	ret = enable_intr_remapping(x2apic_supported());
 	if (ret)
 		goto end_restore;
 
-	if (!x2apic) {
-		x2apic = 1;
+	pr_info("Enabled Interrupt-remapping\n");
+
+	if (x2apic_supported() && !x2apic_mode) {
+		x2apic_mode = 1;
 		enable_x2apic();
+		pr_info("Enabled x2apic\n");
 	}
 
 end_restore:
@@ -1378,37 +1412,34 @@ end_restore:
 		 * IR enabling failed
 		 */
 		restore_IO_APIC_setup(ioapic_entries);
-	else
-		reinit_intr_remapped_IO_APIC(x2apic_preenabled, ioapic_entries);
 
 	unmask_8259A();
 	local_irq_restore(flags);
 
 end:
-	if (!ret) {
-		if (!x2apic_preenabled)
-			pr_info("Enabled x2apic and interrupt-remapping\n");
-		else
-			pr_info("Enabled Interrupt-remapping\n");
-	} else
-		pr_err("Failed to enable Interrupt-remapping and x2apic\n");
 	if (ioapic_entries)
 		free_ioapic_entries(ioapic_entries);
+
+	if (!ret)
+		return;
+
+ir_failed:
+	if (x2apic_preenabled)
+		panic("x2apic enabled by bios. But IR enabling failed");
+	else if (cpu_has_x2apic)
+		pr_info("Not enabling x2apic,Intr-remapping\n");
 #else
 	if (!cpu_has_x2apic)
 		return;
 
 	if (x2apic_preenabled)
 		panic("x2apic enabled prior OS handover,"
-		      " enable CONFIG_INTR_REMAP");
-
-	pr_info("Enable CONFIG_INTR_REMAP for enabling intr-remapping "
-		" and x2apic\n");
+		      " enable CONFIG_X86_X2APIC, CONFIG_INTR_REMAP");
 #endif
 
 	return;
 }
-#endif /* CONFIG_X86_X2APIC */
+
 
 #ifdef CONFIG_X86_64
 /*
@@ -1539,7 +1570,7 @@ void __init early_init_lapic_mapping(void)
  */
 void __init init_apic_mappings(void)
 {
-	if (x2apic) {
+	if (x2apic_mode) {
 		boot_cpu_physical_apicid = read_apic_id();
 		return;
 	}
@@ -1565,6 +1596,12 @@ void __init init_apic_mappings(void)
 	 */
 	if (boot_cpu_physical_apicid == -1U)
 		boot_cpu_physical_apicid = read_apic_id();
+
+	/* lets check if we may to NOP'ify apic operations */
+	if (!cpu_has_apic) {
+		pr_info("APIC: disable apic facility\n");
+		apic_disable();
+	}
 }
 
 /*
@@ -1733,8 +1770,7 @@ void __init connect_bsp_APIC(void)
 		 */
 		apic_printk(APIC_VERBOSE, "leaving PIC mode, "
 				"enabling APIC mode.\n");
-		outb(0x70, 0x22);
-		outb(0x01, 0x23);
+		imcr_pic_to_apic();
 	}
 #endif
 	if (apic->enable_apic_mode)
@@ -1762,8 +1798,7 @@ void disconnect_bsp_APIC(int virt_wire_setup)
 		 */
 		apic_printk(APIC_VERBOSE, "disabling APIC mode, "
 				"entering PIC mode.\n");
-		outb(0x70, 0x22);
-		outb(0x00, 0x23);
+		imcr_apic_to_pic();
 		return;
 	}
 #endif
@@ -1969,10 +2004,10 @@ static int lapic_suspend(struct sys_device *dev, pm_message_t state)
 
 	local_irq_save(flags);
 	disable_local_APIC();
-#ifdef CONFIG_INTR_REMAP
+
 	if (intr_remapping_enabled)
 		disable_intr_remapping();
-#endif
+
 	local_irq_restore(flags);
 	return 0;
 }
@@ -1982,8 +2017,6 @@ static int lapic_resume(struct sys_device *dev)
 	unsigned int l, h;
 	unsigned long flags;
 	int maxlvt;
-
-#ifdef CONFIG_INTR_REMAP
 	int ret;
 	struct IO_APIC_route_entry **ioapic_entries = NULL;
 
@@ -1991,7 +2024,7 @@ static int lapic_resume(struct sys_device *dev)
 		return 0;
 
 	local_irq_save(flags);
-	if (x2apic) {
+	if (intr_remapping_enabled) {
 		ioapic_entries = alloc_ioapic_entries();
 		if (!ioapic_entries) {
 			WARN(1, "Alloc ioapic_entries in lapic resume failed.");
@@ -2007,17 +2040,10 @@ static int lapic_resume(struct sys_device *dev)
 
 		mask_IO_APIC_setup(ioapic_entries);
 		mask_8259A();
-		enable_x2apic();
 	}
-#else
-	if (!apic_pm_state.active)
-		return 0;
 
-	local_irq_save(flags);
-	if (x2apic)
+	if (x2apic_mode)
 		enable_x2apic();
-#endif
-
 	else {
 		/*
 		 * Make sure the APICBASE points to the right address
@@ -2055,20 +2081,15 @@ static int lapic_resume(struct sys_device *dev)
 	apic_write(APIC_ESR, 0);
 	apic_read(APIC_ESR);
 
-#ifdef CONFIG_INTR_REMAP
-	if (intr_remapping_enabled)
-		reenable_intr_remapping(EIM_32BIT_APIC_ID);
-
-	if (x2apic) {
+	if (intr_remapping_enabled) {
+		reenable_intr_remapping(x2apic_mode);
 		unmask_8259A();
 		restore_IO_APIC_setup(ioapic_entries);
 		free_ioapic_entries(ioapic_entries);
 	}
-#endif
 
 	local_irq_restore(flags);
 
-
 	return 0;
 }
 
@@ -2117,31 +2138,14 @@ static void apic_pm_activate(void) { }
 #endif	/* CONFIG_PM */
 
 #ifdef CONFIG_X86_64
-/*
- * apic_is_clustered_box() -- Check if we can expect good TSC
- *
- * Thus far, the major user of this is IBM's Summit2 series:
- *
- * Clustered boxes may have unsynced TSC problems if they are
- * multi-chassis. Use available data to take a good guess.
- * If in doubt, go HPET.
- */
-__cpuinit int apic_is_clustered_box(void)
+
+static int __cpuinit apic_cluster_num(void)
 {
 	int i, clusters, zeros;
 	unsigned id;
 	u16 *bios_cpu_apicid;
 	DECLARE_BITMAP(clustermap, NUM_APIC_CLUSTERS);
 
-	/*
-	 * there is not this kind of box with AMD CPU yet.
-	 * Some AMD box with quadcore cpu and 8 sockets apicid
-	 * will be [4, 0x23] or [8, 0x27] could be thought to
-	 * vsmp box still need checking...
-	 */
-	if ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && !is_vsmp_box())
-		return 0;
-
 	bios_cpu_apicid = early_per_cpu_ptr(x86_bios_cpu_apicid);
 	bitmap_zero(clustermap, NUM_APIC_CLUSTERS);
 
@@ -2177,18 +2181,67 @@ __cpuinit int apic_is_clustered_box(void)
 			++zeros;
 	}
 
-	/* ScaleMP vSMPowered boxes have one cluster per board and TSCs are
-	 * not guaranteed to be synced between boards
-	 */
-	if (is_vsmp_box() && clusters > 1)
+	return clusters;
+}
+
+static int __cpuinitdata multi_checked;
+static int __cpuinitdata multi;
+
+static int __cpuinit set_multi(const struct dmi_system_id *d)
+{
+	if (multi)
+		return 0;
+	printk(KERN_INFO "APIC: %s detected, Multi Chassis\n", d->ident);
+	multi = 1;
+	return 0;
+}
+
+static const __cpuinitconst struct dmi_system_id multi_dmi_table[] = {
+	{
+		.callback = set_multi,
+		.ident = "IBM System Summit2",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "IBM"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Summit2"),
+		},
+	},
+	{}
+};
+
+static void __cpuinit dmi_check_multi(void)
+{
+	if (multi_checked)
+		return;
+
+	dmi_check_system(multi_dmi_table);
+	multi_checked = 1;
+}
+
+/*
+ * apic_is_clustered_box() -- Check if we can expect good TSC
+ *
+ * Thus far, the major user of this is IBM's Summit2 series:
+ * Clustered boxes may have unsynced TSC problems if they are
+ * multi-chassis.
+ * Use DMI to check them
+ */
+__cpuinit int apic_is_clustered_box(void)
+{
+	dmi_check_multi();
+	if (multi)
 		return 1;
 
+	if (!is_vsmp_box())
+		return 0;
+
 	/*
-	 * If clusters > 2, then should be multi-chassis.
-	 * May have to revisit this when multi-core + hyperthreaded CPUs come
-	 * out, but AFAIK this will work even for them.
+	 * ScaleMP vSMPowered boxes have one cluster per board and TSCs are
+	 * not guaranteed to be synced between boards
 	 */
-	return (clusters > 2);
+	if (apic_cluster_num() > 1)
+		return 1;
+
+	return 0;
 }
 #endif
 
diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c
index 1c11b819f24..8e07c141866 100644
--- a/arch/x86/kernel/apic/es7000_32.c
+++ b/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;
 
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index e583291fe6c..21c30e1121e 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/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 */