Merge branch 'master' into for-next

Sync with Linus' tree to be able to apply pending patches that
are based on newer code already present upstream.

28 files changed, 200 insertions, 66 deletions

diff --git a/arch/x86/include/asm/apb_timer.h b/arch/x86/include/asm/apb_timer.h
index 2fefa50..af60d8a 100644
--- a/arch/x86/include/asm/apb_timer.h
+++ b/arch/x86/include/asm/apb_timer.h
@@ -62,7 +62,7 @@ extern int sfi_mtimer_num;
 #else /* CONFIG_APB_TIMER */
 
 static inline unsigned long apbt_quick_calibrate(void) {return 0; }
-static inline void apbt_time_init(void) {return 0; }
+static inline void apbt_time_init(void) { }
 
 #endif
 #endif /* ASM_X86_APBT_H */
diff --git a/arch/x86/include/asm/memblock.h b/arch/x86/include/asm/memblock.h
index 19ae14b..0cd3800 100644
--- a/arch/x86/include/asm/memblock.h
+++ b/arch/x86/include/asm/memblock.h
@@ -4,7 +4,6 @@
 #define ARCH_DISCARD_MEMBLOCK
 
 u64 memblock_x86_find_in_range_size(u64 start, u64 *sizep, u64 align);
-void memblock_x86_to_bootmem(u64 start, u64 end);
 
 void memblock_x86_reserve_range(u64 start, u64 end, char *name);
 void memblock_x86_free_range(u64 start, u64 end);
@@ -19,5 +18,6 @@ u64 memblock_x86_hole_size(u64 start, u64 end);
 u64 memblock_x86_find_in_range_node(int nid, u64 start, u64 end, u64 size, u64 align);
 u64 memblock_x86_free_memory_in_range(u64 addr, u64 limit);
 u64 memblock_x86_memory_in_range(u64 addr, u64 limit);
+bool memblock_x86_check_reserved_size(u64 *addrp, u64 *sizep, u64 align);
 
 #endif
diff --git a/arch/x86/include/asm/mmzone_32.h b/arch/x86/include/asm/mmzone_32.h
index 5e83a41..ffa037f 100644
--- a/arch/x86/include/asm/mmzone_32.h
+++ b/arch/x86/include/asm/mmzone_32.h
@@ -48,17 +48,6 @@ static inline int pfn_to_nid(unsigned long pfn)
 #endif
 }
 
-/*
- * Following are macros that each numa implmentation must define.
- */
-
-#define node_start_pfn(nid)	(NODE_DATA(nid)->node_start_pfn)
-#define node_end_pfn(nid)						\
-({									\
-	pg_data_t *__pgdat = NODE_DATA(nid);				\
-	__pgdat->node_start_pfn + __pgdat->node_spanned_pages;		\
-})
-
 static inline int pfn_valid(int pfn)
 {
 	int nid = pfn_to_nid(pfn);
@@ -68,6 +57,8 @@ static inline int pfn_valid(int pfn)
 	return 0;
 }
 
+#define early_pfn_valid(pfn)	pfn_valid((pfn))
+
 #endif /* CONFIG_DISCONTIGMEM */
 
 #ifdef CONFIG_NEED_MULTIPLE_NODES
diff --git a/arch/x86/include/asm/mmzone_64.h b/arch/x86/include/asm/mmzone_64.h
index b3f88d7..129d9aa 100644
--- a/arch/x86/include/asm/mmzone_64.h
+++ b/arch/x86/include/asm/mmzone_64.h
@@ -13,8 +13,5 @@ extern struct pglist_data *node_data[];
 
 #define NODE_DATA(nid)		(node_data[nid])
 
-#define node_start_pfn(nid)	(NODE_DATA(nid)->node_start_pfn)
-#define node_end_pfn(nid)       (NODE_DATA(nid)->node_start_pfn +	\
-				 NODE_DATA(nid)->node_spanned_pages)
 #endif
 #endif /* _ASM_X86_MMZONE_64_H */
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index 31d84ac..a518c0a 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -22,6 +22,8 @@ static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift)
 	u64 product;
 #ifdef __i386__
 	u32 tmp1, tmp2;
+#else
+	ulong tmp;
 #endif
 
 	if (shift < 0)
@@ -42,8 +44,11 @@ static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift)
 		: "a" ((u32)delta), "1" ((u32)(delta >> 32)), "2" (mul_frac) );
 #elif defined(__x86_64__)
 	__asm__ (
-		"mul %%rdx ; shrd $32,%%rdx,%%rax"
-		: "=a" (product) : "0" (delta), "d" ((u64)mul_frac) );
+		"mul %[mul_frac] ; shrd $32, %[hi], %[lo]"
+		: [lo]"=a"(product),
+		  [hi]"=d"(tmp)
+		: "0"(delta),
+		  [mul_frac]"rm"((u64)mul_frac));
 #else
 #error implement me!
 #endif
diff --git a/arch/x86/kernel/acpi/realmode/wakeup.S b/arch/x86/kernel/acpi/realmode/wakeup.S
index ead21b6..b4fd836 100644
--- a/arch/x86/kernel/acpi/realmode/wakeup.S
+++ b/arch/x86/kernel/acpi/realmode/wakeup.S
@@ -28,6 +28,8 @@ pmode_cr3:	.long	0	/* Saved %cr3 */
 pmode_cr4:	.long	0	/* Saved %cr4 */
 pmode_efer:	.quad	0	/* Saved EFER */
 pmode_gdt:	.quad	0
+pmode_misc_en:	.quad	0	/* Saved MISC_ENABLE MSR */
+pmode_behavior:	.long	0	/* Wakeup behavior flags */
 realmode_flags:	.long	0
 real_magic:	.long	0
 trampoline_segment:	.word 0
@@ -91,6 +93,18 @@ wakeup_code:
 	/* Call the C code */
 	calll	main
 
+	/* Restore MISC_ENABLE before entering protected mode, in case
+	   BIOS decided to clear XD_DISABLE during S3. */
+	movl	pmode_behavior, %eax
+	btl	$WAKEUP_BEHAVIOR_RESTORE_MISC_ENABLE, %eax
+	jnc	1f
+
+	movl	pmode_misc_en, %eax
+	movl	pmode_misc_en + 4, %edx
+	movl	$MSR_IA32_MISC_ENABLE, %ecx
+	wrmsr
+1:
+
 	/* Do any other stuff... */
 
 #ifndef CONFIG_64BIT
diff --git a/arch/x86/kernel/acpi/realmode/wakeup.h b/arch/x86/kernel/acpi/realmode/wakeup.h
index e1828c0..97a29e1 100644
--- a/arch/x86/kernel/acpi/realmode/wakeup.h
+++ b/arch/x86/kernel/acpi/realmode/wakeup.h
@@ -21,6 +21,9 @@ struct wakeup_header {
 	u32 pmode_efer_low;	/* Protected mode EFER */
 	u32 pmode_efer_high;
 	u64 pmode_gdt;
+	u32 pmode_misc_en_low;	/* Protected mode MISC_ENABLE */
+	u32 pmode_misc_en_high;
+	u32 pmode_behavior;	/* Wakeup routine behavior flags */
 	u32 realmode_flags;
 	u32 real_magic;
 	u16 trampoline_segment;	/* segment with trampoline code, 64-bit only */
@@ -39,4 +42,7 @@ extern struct wakeup_header wakeup_header;
 #define WAKEUP_HEADER_SIGNATURE 0x51ee1111
 #define WAKEUP_END_SIGNATURE	0x65a22c82
 
+/* Wakeup behavior bits */
+#define WAKEUP_BEHAVIOR_RESTORE_MISC_ENABLE     0
+
 #endif /* ARCH_X86_KERNEL_ACPI_RM_WAKEUP_H */
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 18a857b..103b6ab 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -77,6 +77,12 @@ int acpi_suspend_lowlevel(void)
 
 	header->pmode_cr0 = read_cr0();
 	header->pmode_cr4 = read_cr4_safe();
+	header->pmode_behavior = 0;
+	if (!rdmsr_safe(MSR_IA32_MISC_ENABLE,
+			&header->pmode_misc_en_low,
+			&header->pmode_misc_en_high))
+		header->pmode_behavior |=
+			(1 << WAKEUP_BEHAVIOR_RESTORE_MISC_ENABLE);
 	header->realmode_flags = acpi_realmode_flags;
 	header->real_magic = 0x12345678;
 
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index b961af8..b9338b8 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -390,7 +390,8 @@ static unsigned int reserve_eilvt_offset(int offset, unsigned int new)
 
 /*
  * If mask=1, the LVT entry does not generate interrupts while mask=0
- * enables the vector. See also the BKDGs.
+ * enables the vector. See also the BKDGs. Must be called with
+ * preemption disabled.
  */
 
 int setup_APIC_eilvt(u8 offset, u8 vector, u8 msg_type, u8 mask)
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index b511a01..adc66c3 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -632,14 +632,14 @@ late_initcall(uv_init_heartbeat);
 
 /* Direct Legacy VGA I/O traffic to designated IOH */
 int uv_set_vga_state(struct pci_dev *pdev, bool decode,
-		      unsigned int command_bits, bool change_bridge)
+		      unsigned int command_bits, u32 flags)
 {
 	int domain, bus, rc;
 
-	PR_DEVEL("devfn %x decode %d cmd %x chg_brdg %d\n",
-			pdev->devfn, decode, command_bits, change_bridge);
+	PR_DEVEL("devfn %x decode %d cmd %x flags %d\n",
+			pdev->devfn, decode, command_bits, flags);
 
-	if (!change_bridge)
+	if (!(flags & PCI_VGA_STATE_CHANGE_BRIDGE))
 		return 0;
 
 	if ((command_bits & PCI_COMMAND_IO) == 0)
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index 690bc84..9aeb78a 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -13,6 +13,7 @@
 #include <linux/slab.h>
 #include <linux/pci.h>
 #include <linux/of_pci.h>
+#include <linux/initrd.h>
 
 #include <asm/hpet.h>
 #include <asm/irq_controller.h>
@@ -98,6 +99,16 @@ void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
 	return __alloc_bootmem(size, align, __pa(MAX_DMA_ADDRESS));
 }
 
+#ifdef CONFIG_BLK_DEV_INITRD
+void __init early_init_dt_setup_initrd_arch(unsigned long start,
+					    unsigned long end)
+{
+	initrd_start = (unsigned long)__va(start);
+	initrd_end = (unsigned long)__va(end);
+	initrd_below_start_ok = 1;
+}
+#endif
+
 void __init add_dtb(u64 data)
 {
 	initial_dtb = data + offsetof(struct setup_data, data);
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 2e4928d..e1ba8cb2 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -337,7 +337,7 @@ EXPORT_SYMBOL(boot_option_idle_override);
  * Powermanagement idle function, if any..
  */
 void (*pm_idle)(void);
-#if defined(CONFIG_APM_MODULE) && defined(CONFIG_APM_CPU_IDLE)
+#ifdef CONFIG_APM_MODULE
 EXPORT_SYMBOL(pm_idle);
 #endif
 
@@ -399,7 +399,7 @@ void default_idle(void)
 		cpu_relax();
 	}
 }
-#if defined(CONFIG_APM_MODULE) && defined(CONFIG_APM_CPU_IDLE)
+#ifdef CONFIG_APM_MODULE
 EXPORT_SYMBOL(default_idle);
 #endif
 
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 0c016f7..4f0d46f 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -294,6 +294,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
 			DMI_MATCH(DMI_BOARD_NAME, "VersaLogic Menlow board"),
 		},
 	},
+	{ /* Handle reboot issue on Acer Aspire one */
+		.callback = set_bios_reboot,
+		.ident = "Acer Aspire One A110",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Acer"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "AOA110"),
+		},
+	},
 	{ }
 };
 
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 33a0c11..9fd3137 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -285,6 +285,19 @@ notrace static void __cpuinit start_secondary(void *unused)
 	per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE;
 	x86_platform.nmi_init();
 
+	/*
+	 * Wait until the cpu which brought this one up marked it
+	 * online before enabling interrupts. If we don't do that then
+	 * we can end up waking up the softirq thread before this cpu
+	 * reached the active state, which makes the scheduler unhappy
+	 * and schedule the softirq thread on the wrong cpu. This is
+	 * only observable with forced threaded interrupts, but in
+	 * theory it could also happen w/o them. It's just way harder
+	 * to achieve.
+	 */
+	while (!cpumask_test_cpu(smp_processor_id(), cpu_active_mask))
+		cpu_relax();
+
 	/* enable local interrupts */
 	local_irq_enable();
 
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 6df88c7..adc9867 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -3372,7 +3372,7 @@ x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len)
 	int def_op_bytes, def_ad_bytes, goffset, simd_prefix;
 	bool op_prefix = false;
 	struct opcode opcode;
-	struct operand memop = { .type = OP_NONE };
+	struct operand memop = { .type = OP_NONE }, *memopp = NULL;
 
 	c->eip = ctxt->eip;
 	c->fetch.start = c->eip;
@@ -3547,9 +3547,6 @@ done_prefixes:
 	if (memop.type == OP_MEM && c->ad_bytes != 8)
 		memop.addr.mem.ea = (u32)memop.addr.mem.ea;
 
-	if (memop.type == OP_MEM && c->rip_relative)
-		memop.addr.mem.ea += c->eip;
-
 	/*
 	 * Decode and fetch the source operand: register, memory
 	 * or immediate.
@@ -3571,6 +3568,7 @@ done_prefixes:
 							   c->op_bytes;
 	srcmem_common:
 		c->src = memop;
+		memopp = &c->src;
 		break;
 	case SrcImmU16:
 		rc = decode_imm(ctxt, &c->src, 2, false);
@@ -3667,6 +3665,7 @@ done_prefixes:
 	case DstMem:
 	case DstMem64:
 		c->dst = memop;
+		memopp = &c->dst;
 		if ((c->d & DstMask) == DstMem64)
 			c->dst.bytes = 8;
 		else
@@ -3700,10 +3699,13 @@ done_prefixes:
 		/* Special instructions do their own operand decoding. */
 	default:
 		c->dst.type = OP_NONE; /* Disable writeback. */
-		return 0;
+		break;
 	}
 
 done:
+	if (memopp && memopp->type == OP_MEM && c->rip_relative)
+		memopp->addr.mem.ea += c->eip;
+
 	return (rc == X86EMUL_UNHANDLEABLE) ? EMULATION_FAILED : EMULATION_OK;
 }
 
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 9b9f012..c7af6a7 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -564,7 +564,7 @@ gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t gfn,
 
 static bool mapping_level_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t large_gfn)
 {
-	return gfn_to_memslot_dirty_bitmap(vcpu, large_gfn, true);
+	return !gfn_to_memslot_dirty_bitmap(vcpu, large_gfn, true);
 }
 
 static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn)
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 6c4dc010..9d03ad4 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -121,7 +121,7 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker,
 				    gva_t addr, u32 access)
 {
 	pt_element_t pte;
-	pt_element_t __user *ptep_user;
+	pt_element_t __user *uninitialized_var(ptep_user);
 	gfn_t table_gfn;
 	unsigned index, pt_access, uninitialized_var(pte_access);
 	gpa_t pte_gpa;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 4c3fa0f..d48ec60 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2047,7 +2047,8 @@ static void ept_update_paging_mode_cr0(unsigned long *hw_cr0,
 					unsigned long cr0,
 					struct kvm_vcpu *vcpu)
 {
-	vmx_decache_cr3(vcpu);
+	if (!test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail))
+		vmx_decache_cr3(vcpu);
 	if (!(cr0 & X86_CR0_PG)) {
 		/* From paging/starting to nonpaging */
 		vmcs_write32(CPU_BASED_VM_EXEC_CONTROL,
diff --git a/arch/x86/mm/memblock.c b/arch/x86/mm/memblock.c
index aa11693..992da5e 100644
--- a/arch/x86/mm/memblock.c
+++ b/arch/x86/mm/memblock.c
@@ -8,7 +8,7 @@
 #include <linux/range.h>
 
 /* Check for already reserved areas */
-static bool __init check_with_memblock_reserved_size(u64 *addrp, u64 *sizep, u64 align)
+bool __init memblock_x86_check_reserved_size(u64 *addrp, u64 *sizep, u64 align)
 {
 	struct memblock_region *r;
 	u64 addr = *addrp, last;
@@ -59,7 +59,7 @@ u64 __init memblock_x86_find_in_range_size(u64 start, u64 *sizep, u64 align)
 		if (addr >= ei_last)
 			continue;
 		*sizep = ei_last - addr;
-		while (check_with_memblock_reserved_size(&addr, sizep, align))
+		while (memblock_x86_check_reserved_size(&addr, sizep, align))
 			;
 
 		if (*sizep)
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index cf97500..68894fd 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -112,8 +112,10 @@ static void nmi_cpu_start(void *dummy)
 static int nmi_start(void)
 {
 	get_online_cpus();
-	on_each_cpu(nmi_cpu_start, NULL, 1);
 	ctr_running = 1;
+	/* make ctr_running visible to the nmi handler: */
+	smp_mb();
+	on_each_cpu(nmi_cpu_start, NULL, 1);
 	put_online_cpus();
 	return 0;
 }
@@ -504,15 +506,18 @@ static int nmi_setup(void)
 
 	nmi_enabled = 0;
 	ctr_running = 0;
-	barrier();
+	/* make variables visible to the nmi handler: */
+	smp_mb();
 	err = register_die_notifier(&profile_exceptions_nb);
 	if (err)
 		goto fail;
 
 	get_online_cpus();
 	register_cpu_notifier(&oprofile_cpu_nb);
-	on_each_cpu(nmi_cpu_setup, NULL, 1);
 	nmi_enabled = 1;
+	/* make nmi_enabled visible to the nmi handler: */
+	smp_mb();
+	on_each_cpu(nmi_cpu_setup, NULL, 1);
 	put_online_cpus();
 
 	return 0;
@@ -531,7 +536,8 @@ static void nmi_shutdown(void)
 	nmi_enabled = 0;
 	ctr_running = 0;
 	put_online_cpus();
-	barrier();
+	/* make variables visible to the nmi handler: */
+	smp_mb();
 	unregister_die_notifier(&profile_exceptions_nb);
 	msrs = &get_cpu_var(cpu_msrs);
 	model->shutdown(msrs);
diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c
index 9fd8a56..9cbb710 100644
--- a/arch/x86/oprofile/op_model_amd.c
+++ b/arch/x86/oprofile/op_model_amd.c
@@ -609,16 +609,21 @@ static int setup_ibs_ctl(int ibs_eilvt_off)
 	return 0;
 }
 
+/*
+ * This runs only on the current cpu. We try to find an LVT offset and
+ * setup the local APIC. For this we must disable preemption. On
+ * success we initialize all nodes with this offset. This updates then
+ * the offset in the IBS_CTL per-node msr. The per-core APIC setup of
+ * the IBS interrupt vector is called from op_amd_setup_ctrs()/op_-
+ * amd_cpu_shutdown() using the new offset.
+ */
 static int force_ibs_eilvt_setup(void)
 {
 	int offset;
 	int ret;
 
-	/*
-	 * find the next free available EILVT entry, skip offset 0,
-	 * pin search to this cpu
-	 */
 	preempt_disable();
+	/* find the next free available EILVT entry, skip offset 0 */
 	for (offset = 1; offset < APIC_EILVT_NR_MAX; offset++) {
 		if (get_eilvt(offset))
 			break;
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index 0972315..68c3c13 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -188,7 +188,7 @@ static bool resource_contains(struct resource *res, resource_size_t point)
 	return false;
 }
 
-static void coalesce_windows(struct pci_root_info *info, int type)
+static void coalesce_windows(struct pci_root_info *info, unsigned long type)
 {
 	int i, j;
 	struct resource *res1, *res2;
diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index 8214724..f567965 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -327,7 +327,7 @@ int __init pci_xen_hvm_init(void)
 }
 
 #ifdef CONFIG_XEN_DOM0
-static int xen_register_pirq(u32 gsi, int triggering)
+static int xen_register_pirq(u32 gsi, int gsi_override, int triggering)
 {
 	int rc, pirq, irq = -1;
 	struct physdev_map_pirq map_irq;
@@ -344,16 +344,18 @@ static int xen_register_pirq(u32 gsi, int triggering)
 		shareable = 1;
 		name = "ioapic-level";
 	}
-
 	pirq = xen_allocate_pirq_gsi(gsi);
 	if (pirq < 0)
 		goto out;
 
-	irq = xen_bind_pirq_gsi_to_irq(gsi, pirq, shareable, name);
+	if (gsi_override >= 0)
+		irq = xen_bind_pirq_gsi_to_irq(gsi_override, pirq, shareable, name);
+	else
+		irq = xen_bind_pirq_gsi_to_irq(gsi, pirq, shareable, name);
 	if (irq < 0)
 		goto out;
 
-	printk(KERN_DEBUG "xen: --> pirq=%d -> irq=%d\n", pirq, irq);
+	printk(KERN_DEBUG "xen: --> pirq=%d -> irq=%d (gsi=%d)\n", pirq, irq, gsi);
 
 	map_irq.domid = DOMID_SELF;
 	map_irq.type = MAP_PIRQ_TYPE_GSI;
@@ -370,7 +372,7 @@ out:
 	return irq;
 }
 
-static int xen_register_gsi(u32 gsi, int triggering, int polarity)
+static int xen_register_gsi(u32 gsi, int gsi_override, int triggering, int polarity)
 {
 	int rc, irq;
 	struct physdev_setup_gsi setup_gsi;
@@ -381,7 +383,7 @@ static int xen_register_gsi(u32 gsi, int triggering, int polarity)
 	printk(KERN_DEBUG "xen: registering gsi %u triggering %d polarity %d\n",
 			gsi, triggering, polarity);
 
-	irq = xen_register_pirq(gsi, triggering);
+	irq = xen_register_pirq(gsi, gsi_override, triggering);
 
 	setup_gsi.gsi = gsi;
 	setup_gsi.triggering = (triggering == ACPI_EDGE_SENSITIVE ? 0 : 1);
@@ -403,6 +405,8 @@ static __init void xen_setup_acpi_sci(void)
 	int rc;
 	int trigger, polarity;
 	int gsi = acpi_sci_override_gsi;
+	int irq = -1;
+	int gsi_override = -1;
 
 	if (!gsi)
 		return;
@@ -419,7 +423,25 @@ static __init void xen_setup_acpi_sci(void)
 	printk(KERN_INFO "xen: sci override: global_irq=%d trigger=%d "
 			"polarity=%d\n", gsi, trigger, polarity);
 
-	gsi = xen_register_gsi(gsi, trigger, polarity);
+	/* Before we bind the GSI to a Linux IRQ, check whether
+	 * we need to override it with bus_irq (IRQ) value. Usually for
+	 * IRQs below IRQ_LEGACY_IRQ this holds IRQ == GSI, as so:
+	 *  ACPI: INT_SRC_OVR (bus 0 bus_irq 9 global_irq 9 low level)
+	 * but there are oddballs where the IRQ != GSI:
+	 *  ACPI: INT_SRC_OVR (bus 0 bus_irq 9 global_irq 20 low level)
+	 * which ends up being: gsi_to_irq[9] == 20
+	 * (which is what acpi_gsi_to_irq ends up calling when starting the
+	 * the ACPI interpreter and keels over since IRQ 9 has not been
+	 * setup as we had setup IRQ 20 for it).
+	 */
+	/* Check whether the GSI != IRQ */
+	if (acpi_gsi_to_irq(gsi, &irq) == 0) {
+		if (irq >= 0 && irq != gsi)
+			/* Bugger, we MUST have that IRQ. */
+			gsi_override = irq;
+	}
+
+	gsi = xen_register_gsi(gsi, gsi_override, trigger, polarity);
 	printk(KERN_INFO "xen: acpi sci %d\n", gsi);
 
 	return;
@@ -428,7 +450,7 @@ static __init void xen_setup_acpi_sci(void)
 static int acpi_register_gsi_xen(struct device *dev, u32 gsi,
 				 int trigger, int polarity)
 {
-	return xen_register_gsi(gsi, trigger, polarity);
+	return xen_register_gsi(gsi, -1 /* no GSI override */, trigger, polarity);
 }
 
 static int __init pci_xen_initial_domain(void)
@@ -467,7 +489,7 @@ void __init xen_setup_pirqs(void)
 		if (acpi_get_override_irq(irq, &trigger, &polarity) == -1)
 			continue;
 
-		xen_register_pirq(irq,
+		xen_register_pirq(irq, -1 /* no GSI override */,
 			trigger ? ACPI_LEVEL_SENSITIVE : ACPI_EDGE_SENSITIVE);
 	}
 }
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 0d3a4fa..899e393 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -310,14 +310,31 @@ void __init efi_reserve_boot_services(void)
 
 	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
 		efi_memory_desc_t *md = p;
-		unsigned long long start = md->phys_addr;
-		unsigned long long size = md->num_pages << EFI_PAGE_SHIFT;
+		u64 start = md->phys_addr;
+		u64 size = md->num_pages << EFI_PAGE_SHIFT;
 
 		if (md->type != EFI_BOOT_SERVICES_CODE &&
 		    md->type != EFI_BOOT_SERVICES_DATA)
 			continue;
-
-		memblock_x86_reserve_range(start, start + size, "EFI Boot");
+		/* Only reserve where possible:
+		 * - Not within any already allocated areas
+		 * - Not over any memory area (really needed, if above?)
+		 * - Not within any part of the kernel
+		 * - Not the bios reserved area
+		*/
+		if ((start+size >= virt_to_phys(_text)
+				&& start <= virt_to_phys(_end)) ||
+			!e820_all_mapped(start, start+size, E820_RAM) ||
+			memblock_x86_check_reserved_size(&start, &size,
+							1<<EFI_PAGE_SHIFT)) {
+			/* Could not reserve, skip it */
+			md->num_pages = 0;
+			memblock_dbg(PFX "Could not reserve boot range "
+					"[0x%010llx-0x%010llx]\n",
+						start, start+size-1);
+		} else
+			memblock_x86_reserve_range(start, start+size,
+							"EFI Boot");
 	}
 }
 
@@ -334,6 +351,10 @@ static void __init efi_free_boot_services(void)
 		    md->type != EFI_BOOT_SERVICES_DATA)
 			continue;
 
+		/* Could not reserve boot area */
+		if (!size)
+			continue;
+
 		free_bootmem_late(start, size);
 	}
 }
@@ -483,9 +504,6 @@ void __init efi_init(void)
 	x86_platform.set_wallclock = efi_set_rtc_mmss;
 #endif
 
-	/* Setup for EFI runtime service */
-	reboot_type = BOOT_EFI;
-
 #if EFI_DEBUG
 	print_efi_memmap();
 #endif
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index dd7b88f..5525163 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1033,6 +1033,13 @@ static void xen_machine_halt(void)
 	xen_reboot(SHUTDOWN_poweroff);
 }
 
+static void xen_machine_power_off(void)
+{
+	if (pm_power_off)
+		pm_power_off();
+	xen_reboot(SHUTDOWN_poweroff);
+}
+
 static void xen_crash_shutdown(struct pt_regs *regs)
 {
 	xen_reboot(SHUTDOWN_crash);
@@ -1058,7 +1065,7 @@ int xen_panic_handler_init(void)
 static const struct machine_ops xen_machine_ops __initconst = {
 	.restart = xen_restart,
 	.halt = xen_machine_halt,
-	.power_off = xen_machine_halt,
+	.power_off = xen_machine_power_off,
 	.shutdown = xen_machine_halt,
 	.crash_shutdown = xen_crash_shutdown,
 	.emergency_restart = xen_emergency_restart,
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index dc708dc..0ccccb6 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -59,6 +59,7 @@
 #include <asm/page.h>
 #include <asm/init.h>
 #include <asm/pat.h>
+#include <asm/smp.h>
 
 #include <asm/xen/hypercall.h>
 #include <asm/xen/hypervisor.h>
@@ -1231,7 +1232,11 @@ static void xen_flush_tlb_others(const struct cpumask *cpus,
 {
 	struct {
 		struct mmuext_op op;
+#ifdef CONFIG_SMP
+		DECLARE_BITMAP(mask, num_processors);
+#else
 		DECLARE_BITMAP(mask, NR_CPUS);
+#endif
 	} *args;
 	struct multicall_space mcs;
 
@@ -1599,6 +1604,11 @@ static void __init xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn)
 		for (pteidx = 0; pteidx < PTRS_PER_PTE; pteidx++, pfn++) {
 			pte_t pte;
 
+#ifdef CONFIG_X86_32
+			if (pfn > max_pfn_mapped)
+				max_pfn_mapped = pfn;
+#endif
+
 			if (!pte_none(pte_page[pteidx]))
 				continue;
 
@@ -1766,7 +1776,9 @@ pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd,
 	initial_kernel_pmd =
 		extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE);
 
-	max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->mfn_list));
+	max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->pt_base) +
+				  xen_start_info->nr_pt_frames * PAGE_SIZE +
+				  512*1024);
 
 	kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd);
 	memcpy(initial_kernel_pmd, kernel_pmd, sizeof(pmd_t) * PTRS_PER_PMD);
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index be1a464..60aeeb5 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -227,11 +227,7 @@ char * __init xen_memory_setup(void)
 
 	memcpy(map_raw, map, sizeof(map));
 	e820.nr_map = 0;
-#ifdef CONFIG_X86_32
 	xen_extra_mem_start = mem_end;
-#else
-	xen_extra_mem_start = max((1ULL << 32), mem_end);
-#endif
 	for (i = 0; i < memmap.nr_entries; i++) {
 		unsigned long long end;
 
@@ -266,6 +262,12 @@ char * __init xen_memory_setup(void)
 		if (map[i].size > 0)
 			e820_add_region(map[i].addr, map[i].size, map[i].type);
 	}
+	/* Align the balloon area so that max_low_pfn does not get set
+	 * to be at the _end_ of the PCI gap at the far end (fee01000).
+	 * Note that xen_extra_mem_start gets set in the loop above to be
+	 * past the last E820 region. */
+	if (xen_initial_domain() && (xen_extra_mem_start < (1ULL<<32)))
+		xen_extra_mem_start = (1ULL<<32);
 
 	/*
 	 * In domU, the ISA region is normal, usable memory, but we
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 41038c0..b4533a8 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -205,11 +205,18 @@ static void __init xen_smp_prepare_boot_cpu(void)
 static void __init xen_smp_prepare_cpus(unsigned int max_cpus)
 {
 	unsigned cpu;
+	unsigned int i;
 
 	xen_init_lock_cpu(0);
 
 	smp_store_cpu_info(0);
 	cpu_data(0).x86_max_cores = 1;
+
+	for_each_possible_cpu(i) {
+		zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL);
+		zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
+		zalloc_cpumask_var(&per_cpu(cpu_llc_shared_map, i), GFP_KERNEL);
+	}
 	set_cpu_sibling_map(0);
 
 	if (xen_smp_intr_init(0))