23 files changed, 249 insertions, 127 deletions

diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index bafd80defa43..903683b07e42 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -440,6 +440,8 @@ static inline int fls(int x)
 
 #ifdef __KERNEL__
 
+#include <asm-generic/bitops/find.h>
+
 #include <asm-generic/bitops/sched.h>
 
 #define ARCH_HAS_FAST_MULTIPLIER 1
diff --git a/arch/x86/include/asm/calling.h b/arch/x86/include/asm/calling.h
index 0e63c9a2a8d0..30af5a832163 100644
--- a/arch/x86/include/asm/calling.h
+++ b/arch/x86/include/asm/calling.h
@@ -48,36 +48,38 @@ For 32-bit we have the following conventions - kernel is built with
 
 
 /*
- * 64-bit system call stack frame layout defines and helpers,
- * for assembly code:
+ * 64-bit system call stack frame layout defines and helpers, for
+ * assembly code (note that the seemingly unnecessary parentheses
+ * are to prevent cpp from inserting spaces in expressions that get
+ * passed to macros):
  */
 
-#define R15		  0
-#define R14		  8
-#define R13		 16
-#define R12		 24
-#define RBP		 32
-#define RBX		 40
+#define R15		  (0)
+#define R14		  (8)
+#define R13		 (16)
+#define R12		 (24)
+#define RBP		 (32)
+#define RBX		 (40)
 
 /* arguments: interrupts/non tracing syscalls only save up to here: */
-#define R11		 48
-#define R10		 56
-#define R9		 64
-#define R8		 72
-#define RAX		 80
-#define RCX		 88
-#define RDX		 96
-#define RSI		104
-#define RDI		112
-#define ORIG_RAX	120       /* + error_code */
+#define R11		 (48)
+#define R10		 (56)
+#define R9		 (64)
+#define R8		 (72)
+#define RAX		 (80)
+#define RCX		 (88)
+#define RDX		 (96)
+#define RSI		(104)
+#define RDI		(112)
+#define ORIG_RAX	(120)       /* + error_code */
 /* end of arguments */
 
 /* cpu exception frame or undefined in case of fast syscall: */
-#define RIP		128
-#define CS		136
-#define EFLAGS		144
-#define RSP		152
-#define SS		160
+#define RIP		(128)
+#define CS		(136)
+#define EFLAGS		(144)
+#define RSP		(152)
+#define SS		(160)
 
 #define ARGOFFSET	R11
 #define SWFRAME		ORIG_RAX
@@ -111,7 +113,7 @@ For 32-bit we have the following conventions - kernel is built with
 	.endif
 	.endm
 
-#define ARG_SKIP	9*8
+#define ARG_SKIP	(9*8)
 
 	.macro RESTORE_ARGS skiprax=0, addskip=0, skiprcx=0, skipr11=0, \
 			    skipr8910=0, skiprdx=0
@@ -169,7 +171,7 @@ For 32-bit we have the following conventions - kernel is built with
 	.endif
 	.endm
 
-#define REST_SKIP	6*8
+#define REST_SKIP	(6*8)
 
 	.macro SAVE_REST
 	subq $REST_SKIP, %rsp
diff --git a/arch/x86/include/asm/entry_arch.h b/arch/x86/include/asm/entry_arch.h
index b8e96a18676b..57650ab4a5f5 100644
--- a/arch/x86/include/asm/entry_arch.h
+++ b/arch/x86/include/asm/entry_arch.h
@@ -16,22 +16,11 @@ BUILD_INTERRUPT(call_function_single_interrupt,CALL_FUNCTION_SINGLE_VECTOR)
 BUILD_INTERRUPT(irq_move_cleanup_interrupt,IRQ_MOVE_CLEANUP_VECTOR)
 BUILD_INTERRUPT(reboot_interrupt,REBOOT_VECTOR)
 
-BUILD_INTERRUPT3(invalidate_interrupt0,INVALIDATE_TLB_VECTOR_START+0,
-		 smp_invalidate_interrupt)
-BUILD_INTERRUPT3(invalidate_interrupt1,INVALIDATE_TLB_VECTOR_START+1,
-		 smp_invalidate_interrupt)
-BUILD_INTERRUPT3(invalidate_interrupt2,INVALIDATE_TLB_VECTOR_START+2,
-		 smp_invalidate_interrupt)
-BUILD_INTERRUPT3(invalidate_interrupt3,INVALIDATE_TLB_VECTOR_START+3,
-		 smp_invalidate_interrupt)
-BUILD_INTERRUPT3(invalidate_interrupt4,INVALIDATE_TLB_VECTOR_START+4,
-		 smp_invalidate_interrupt)
-BUILD_INTERRUPT3(invalidate_interrupt5,INVALIDATE_TLB_VECTOR_START+5,
-		 smp_invalidate_interrupt)
-BUILD_INTERRUPT3(invalidate_interrupt6,INVALIDATE_TLB_VECTOR_START+6,
-		 smp_invalidate_interrupt)
-BUILD_INTERRUPT3(invalidate_interrupt7,INVALIDATE_TLB_VECTOR_START+7,
+.irpc idx, "01234567"
+BUILD_INTERRUPT3(invalidate_interrupt\idx,
+		 (INVALIDATE_TLB_VECTOR_START)+\idx,
 		 smp_invalidate_interrupt)
+.endr
 #endif
 
 BUILD_INTERRUPT(x86_platform_ipi, X86_PLATFORM_IPI_VECTOR)
diff --git a/arch/x86/include/asm/highmem.h b/arch/x86/include/asm/highmem.h
index 8caac76ac324..3bd04022fd0c 100644
--- a/arch/x86/include/asm/highmem.h
+++ b/arch/x86/include/asm/highmem.h
@@ -59,11 +59,12 @@ extern void kunmap_high(struct page *page);
 
 void *kmap(struct page *page);
 void kunmap(struct page *page);
-void *kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot);
-void *kmap_atomic(struct page *page, enum km_type type);
-void kunmap_atomic_notypecheck(void *kvaddr, enum km_type type);
-void *kmap_atomic_pfn(unsigned long pfn, enum km_type type);
-void *kmap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot);
+
+void *kmap_atomic_prot(struct page *page, pgprot_t prot);
+void *__kmap_atomic(struct page *page);
+void __kunmap_atomic(void *kvaddr);
+void *kmap_atomic_pfn(unsigned long pfn);
+void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot);
 struct page *kmap_atomic_to_page(void *ptr);
 
 #define flush_cache_kmaps()	do { } while (0)
diff --git a/arch/x86/include/asm/iomap.h b/arch/x86/include/asm/iomap.h
index c4191b3b7056..363e33eb6ec1 100644
--- a/arch/x86/include/asm/iomap.h
+++ b/arch/x86/include/asm/iomap.h
@@ -27,10 +27,10 @@
 #include <asm/tlbflush.h>
 
 void __iomem *
-iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot);
+iomap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot);
 
 void
-iounmap_atomic(void __iomem *kvaddr, enum km_type type);
+iounmap_atomic(void __iomem *kvaddr);
 
 int
 iomap_create_wc(resource_size_t base, unsigned long size, pgprot_t *prot);
diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h
index 5458380b6ef8..13b0ebaa512f 100644
--- a/arch/x86/include/asm/irq.h
+++ b/arch/x86/include/asm/irq.h
@@ -19,18 +19,14 @@ static inline int irq_canonicalize(int irq)
 # 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
+#ifdef CONFIG_X86_32
+extern void irq_ctx_init(int cpu);
 #else
 # 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
 
+#define __ARCH_HAS_DO_SOFTIRQ
+
 #ifdef CONFIG_HOTPLUG_CPU
 #include <linux/cpumask.h>
 extern void fixup_irqs(void);
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 1f99ecfc48e1..b36c6b3fe144 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -139,6 +139,7 @@ struct x86_emulate_ops {
 	void (*set_segment_selector)(u16 sel, int seg, struct kvm_vcpu *vcpu);
 	unsigned long (*get_cached_segment_base)(int seg, struct kvm_vcpu *vcpu);
 	void (*get_gdt)(struct desc_ptr *dt, struct kvm_vcpu *vcpu);
+	void (*get_idt)(struct desc_ptr *dt, struct kvm_vcpu *vcpu);
 	ulong (*get_cr)(int cr, struct kvm_vcpu *vcpu);
 	int (*set_cr)(int cr, ulong val, struct kvm_vcpu *vcpu);
 	int (*cpl)(struct kvm_vcpu *vcpu);
@@ -156,7 +157,10 @@ struct operand {
 		unsigned long orig_val;
 		u64 orig_val64;
 	};
-	unsigned long *ptr;
+	union {
+		unsigned long *reg;
+		unsigned long mem;
+	} addr;
 	union {
 		unsigned long val;
 		u64 val64;
@@ -190,6 +194,7 @@ struct decode_cache {
 	bool has_seg_override;
 	u8 seg_override;
 	unsigned int d;
+	int (*execute)(struct x86_emulate_ctxt *ctxt);
 	unsigned long regs[NR_VCPU_REGS];
 	unsigned long eip;
 	/* modrm */
@@ -197,17 +202,16 @@ struct decode_cache {
 	u8 modrm_mod;
 	u8 modrm_reg;
 	u8 modrm_rm;
-	u8 use_modrm_ea;
+	u8 modrm_seg;
 	bool rip_relative;
-	unsigned long modrm_ea;
-	void *modrm_ptr;
-	unsigned long modrm_val;
 	struct fetch_cache fetch;
 	struct read_cache io_read;
 	struct read_cache mem_read;
 };
 
 struct x86_emulate_ctxt {
+	struct x86_emulate_ops *ops;
+
 	/* Register state before/after emulation. */
 	struct kvm_vcpu *vcpu;
 
@@ -220,12 +224,11 @@ struct x86_emulate_ctxt {
 	/* interruptibility state, as a result of execution of STI or MOV SS */
 	int interruptibility;
 
-	bool restart; /* restart string instruction after writeback */
+	bool perm_ok; /* do not check permissions if true */
 
 	int exception; /* exception that happens during emulation or -1 */
 	u32 error_code; /* error code for exception */
 	bool error_code_valid;
-	unsigned long cr2; /* faulted address in case of #PF */
 
 	/* decode cache */
 	struct decode_cache decode;
@@ -249,13 +252,14 @@ struct x86_emulate_ctxt {
 #define X86EMUL_MODE_HOST X86EMUL_MODE_PROT64
 #endif
 
-int x86_decode_insn(struct x86_emulate_ctxt *ctxt,
-		    struct x86_emulate_ops *ops);
-int x86_emulate_insn(struct x86_emulate_ctxt *ctxt,
-		     struct x86_emulate_ops *ops);
+int x86_decode_insn(struct x86_emulate_ctxt *ctxt);
+#define EMULATION_FAILED -1
+#define EMULATION_OK 0
+#define EMULATION_RESTART 1
+int x86_emulate_insn(struct x86_emulate_ctxt *ctxt);
 int emulator_task_switch(struct x86_emulate_ctxt *ctxt,
-			 struct x86_emulate_ops *ops,
 			 u16 tss_selector, int reason,
 			 bool has_error_code, u32 error_code);
-
+int emulate_int_real(struct x86_emulate_ctxt *ctxt,
+		     struct x86_emulate_ops *ops, int irq);
 #endif /* _ASM_X86_KVM_X86_EMULATE_H */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index c52e2eb40a1e..9e6fe391094e 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -236,10 +236,14 @@ struct kvm_pio_request {
  */
 struct kvm_mmu {
 	void (*new_cr3)(struct kvm_vcpu *vcpu);
+	void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long root);
+	unsigned long (*get_cr3)(struct kvm_vcpu *vcpu);
 	int (*page_fault)(struct kvm_vcpu *vcpu, gva_t gva, u32 err);
+	void (*inject_page_fault)(struct kvm_vcpu *vcpu);
 	void (*free)(struct kvm_vcpu *vcpu);
 	gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t gva, u32 access,
 			    u32 *error);
+	gpa_t (*translate_gpa)(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access);
 	void (*prefetch_page)(struct kvm_vcpu *vcpu,
 			      struct kvm_mmu_page *page);
 	int (*sync_page)(struct kvm_vcpu *vcpu,
@@ -249,13 +253,18 @@ struct kvm_mmu {
 	int root_level;
 	int shadow_root_level;
 	union kvm_mmu_page_role base_role;
+	bool direct_map;
 
 	u64 *pae_root;
+	u64 *lm_root;
 	u64 rsvd_bits_mask[2][4];
+
+	bool nx;
+
+	u64 pdptrs[4]; /* pae */
 };
 
 struct kvm_vcpu_arch {
-	u64 host_tsc;
 	/*
 	 * rip and regs accesses must go through
 	 * kvm_{register,rip}_{read,write} functions.
@@ -272,7 +281,6 @@ struct kvm_vcpu_arch {
 	unsigned long cr4_guest_owned_bits;
 	unsigned long cr8;
 	u32 hflags;
-	u64 pdptrs[4]; /* pae */
 	u64 efer;
 	u64 apic_base;
 	struct kvm_lapic *apic;    /* kernel irqchip context */
@@ -282,7 +290,41 @@ struct kvm_vcpu_arch {
 	u64 ia32_misc_enable_msr;
 	bool tpr_access_reporting;
 
+	/*
+	 * Paging state of the vcpu
+	 *
+	 * If the vcpu runs in guest mode with two level paging this still saves
+	 * the paging mode of the l1 guest. This context is always used to
+	 * handle faults.
+	 */
 	struct kvm_mmu mmu;
+
+	/*
+	 * Paging state of an L2 guest (used for nested npt)
+	 *
+	 * This context will save all necessary information to walk page tables
+	 * of the an L2 guest. This context is only initialized for page table
+	 * walking and not for faulting since we never handle l2 page faults on
+	 * the host.
+	 */
+	struct kvm_mmu nested_mmu;
+
+	/*
+	 * Pointer to the mmu context currently used for
+	 * gva_to_gpa translations.
+	 */
+	struct kvm_mmu *walk_mmu;
+
+	/*
+	 * This struct is filled with the necessary information to propagate a
+	 * page fault into the guest
+	 */
+	struct {
+		u64      address;
+		unsigned error_code;
+		bool     nested;
+	} fault;
+
 	/* only needed in kvm_pv_mmu_op() path, but it's hot so
 	 * put it here to avoid allocation */
 	struct kvm_pv_mmu_op_buffer mmu_op_buffer;
@@ -336,9 +378,15 @@ struct kvm_vcpu_arch {
 
 	gpa_t time;
 	struct pvclock_vcpu_time_info hv_clock;
-	unsigned int hv_clock_tsc_khz;
+	unsigned int hw_tsc_khz;
 	unsigned int time_offset;
 	struct page *time_page;
+	u64 last_host_tsc;
+	u64 last_guest_tsc;
+	u64 last_kernel_ns;
+	u64 last_tsc_nsec;
+	u64 last_tsc_write;
+	bool tsc_catchup;
 
 	bool nmi_pending;
 	bool nmi_injected;
@@ -367,9 +415,9 @@ struct kvm_vcpu_arch {
 };
 
 struct kvm_arch {
-	unsigned int n_free_mmu_pages;
+	unsigned int n_used_mmu_pages;
 	unsigned int n_requested_mmu_pages;
-	unsigned int n_alloc_mmu_pages;
+	unsigned int n_max_mmu_pages;
 	atomic_t invlpg_counter;
 	struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES];
 	/*
@@ -394,8 +442,14 @@ struct kvm_arch {
 	gpa_t ept_identity_map_addr;
 
 	unsigned long irq_sources_bitmap;
-	u64 vm_init_tsc;
 	s64 kvmclock_offset;
+	spinlock_t tsc_write_lock;
+	u64 last_tsc_nsec;
+	u64 last_tsc_offset;
+	u64 last_tsc_write;
+	u32 virtual_tsc_khz;
+	u32 virtual_tsc_mult;
+	s8 virtual_tsc_shift;
 
 	struct kvm_xen_hvm_config xen_hvm_config;
 
@@ -505,6 +559,7 @@ struct kvm_x86_ops {
 	void (*queue_exception)(struct kvm_vcpu *vcpu, unsigned nr,
 				bool has_error_code, u32 error_code,
 				bool reinject);
+	void (*cancel_injection)(struct kvm_vcpu *vcpu);
 	int (*interrupt_allowed)(struct kvm_vcpu *vcpu);
 	int (*nmi_allowed)(struct kvm_vcpu *vcpu);
 	bool (*get_nmi_mask)(struct kvm_vcpu *vcpu);
@@ -517,11 +572,16 @@ struct kvm_x86_ops {
 	u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio);
 	int (*get_lpage_level)(void);
 	bool (*rdtscp_supported)(void);
+	void (*adjust_tsc_offset)(struct kvm_vcpu *vcpu, s64 adjustment);
+
+	void (*set_tdp_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3);
 
 	void (*set_supported_cpuid)(u32 func, struct kvm_cpuid_entry2 *entry);
 
 	bool (*has_wbinvd_exit)(void);
 
+	void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset);
+
 	const struct trace_print_flags *exit_reasons_str;
 };
 
@@ -544,7 +604,7 @@ void kvm_mmu_zap_all(struct kvm *kvm);
 unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm);
 void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages);
 
-int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3);
+int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3);
 
 int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
 			  const void *val, int bytes);
@@ -608,8 +668,11 @@ void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr);
 void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code);
 void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr);
 void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code);
-void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long cr2,
-			   u32 error_code);
+void kvm_inject_page_fault(struct kvm_vcpu *vcpu);
+int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
+			    gfn_t gfn, void *data, int offset, int len,
+			    u32 access);
+void kvm_propagate_fault(struct kvm_vcpu *vcpu);
 bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl);
 
 int kvm_pic_set_irq(void *opaque, int irq, int level);
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index 05eba5e9a8e8..7b562b6184bc 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -158,6 +158,12 @@ static inline unsigned int kvm_arch_para_features(void)
 	return cpuid_eax(KVM_CPUID_FEATURES);
 }
 
+#ifdef CONFIG_KVM_GUEST
+void __init kvm_guest_init(void);
+#else
+#define kvm_guest_init() do { } while (0)
 #endif
 
+#endif /* __KERNEL__ */
+
 #endif /* _ASM_X86_KVM_PARA_H */
diff --git a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h
index 3e2ce58a31a3..67763c5d8b4e 100644
--- a/arch/x86/include/asm/module.h
+++ b/arch/x86/include/asm/module.h
@@ -60,12 +60,7 @@
 #endif
 
 #ifdef CONFIG_X86_32
-# ifdef CONFIG_4KSTACKS
-#  define MODULE_STACKSIZE "4KSTACKS "
-# else
-#  define MODULE_STACKSIZE ""
-# endif
-# define MODULE_ARCH_VERMAGIC MODULE_PROC_FAMILY MODULE_STACKSIZE
+# define MODULE_ARCH_VERMAGIC MODULE_PROC_FAMILY
 #endif
 
 #endif /* _ASM_X86_MODULE_H */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 91ba8e6b630a..3ea3dc487047 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -199,6 +199,7 @@
 #define MSR_IA32_TSC			0x00000010
 #define MSR_IA32_PLATFORM_ID		0x00000017
 #define MSR_IA32_EBL_CR_POWERON		0x0000002a
+#define MSR_EBC_FREQUENCY_ID		0x0000002c
 #define MSR_IA32_FEATURE_CONTROL        0x0000003a
 
 #define FEATURE_CONTROL_LOCKED				(1<<0)
diff --git a/arch/x86/include/asm/olpc.h b/arch/x86/include/asm/olpc.h
index 101229b0d8ed..42a978c0c1b3 100644
--- a/arch/x86/include/asm/olpc.h
+++ b/arch/x86/include/asm/olpc.h
@@ -89,6 +89,8 @@ extern int olpc_ec_mask_unset(uint8_t bits);
 /* EC commands */
 
 #define EC_FIRMWARE_REV		0x08
+#define EC_WLAN_ENTER_RESET	0x35
+#define EC_WLAN_LEAVE_RESET	0x25
 
 /* SCI source values */
 
diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h
index 6f1b7331313f..ade619ff9e2a 100644
--- a/arch/x86/include/asm/page_32_types.h
+++ b/arch/x86/include/asm/page_32_types.h
@@ -15,11 +15,7 @@
  */
 #define __PAGE_OFFSET		_AC(CONFIG_PAGE_OFFSET, UL)
 
-#ifdef CONFIG_4KSTACKS
-#define THREAD_ORDER	0
-#else
 #define THREAD_ORDER	1
-#endif
 #define THREAD_SIZE 	(PAGE_SIZE << THREAD_ORDER)
 
 #define STACKFAULT_STACK 0
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index cd28f9ad910d..f899e01a8ac9 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -47,6 +47,20 @@
 #ifdef CONFIG_SMP
 #define __percpu_arg(x)		"%%"__stringify(__percpu_seg)":%P" #x
 #define __my_cpu_offset		percpu_read(this_cpu_off)
+
+/*
+ * Compared to the generic __my_cpu_offset version, the following
+ * saves one instruction and avoids clobbering a temp register.
+ */
+#define __this_cpu_ptr(ptr)				\
+({							\
+	unsigned long tcp_ptr__;			\
+	__verify_pcpu_ptr(ptr);				\
+	asm volatile("add " __percpu_arg(1) ", %0"	\
+		     : "=r" (tcp_ptr__)			\
+		     : "m" (this_cpu_off), "0" (ptr));	\
+	(typeof(*(ptr)) __kernel __force *)tcp_ptr__;	\
+})
 #else
 #define __percpu_arg(x)		"%P" #x
 #endif
diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h
index f686f49e8b7b..0c92113c4cb6 100644
--- a/arch/x86/include/asm/pgtable_32.h
+++ b/arch/x86/include/asm/pgtable_32.h
@@ -26,7 +26,7 @@ struct mm_struct;
 struct vm_area_struct;
 
 extern pgd_t swapper_pg_dir[1024];
-extern pgd_t trampoline_pg_dir[1024];
+extern pgd_t initial_page_table[1024];
 
 static inline void pgtable_cache_init(void) { }
 static inline void check_pgt_cache(void) { }
@@ -49,24 +49,14 @@ extern void set_pmd_pfn(unsigned long, unsigned long, pgprot_t);
 #endif
 
 #if defined(CONFIG_HIGHPTE)
-#define __KM_PTE			\
-	(in_nmi() ? KM_NMI_PTE : 	\
-	 in_irq() ? KM_IRQ_PTE :	\
-	 KM_PTE0)
 #define pte_offset_map(dir, address)					\
-	((pte_t *)kmap_atomic(pmd_page(*(dir)), __KM_PTE) +		\
+	((pte_t *)kmap_atomic(pmd_page(*(dir))) +		\
 	 pte_index((address)))
-#define pte_offset_map_nested(dir, address)				\
-	((pte_t *)kmap_atomic(pmd_page(*(dir)), KM_PTE1) +		\
-	 pte_index((address)))
-#define pte_unmap(pte) kunmap_atomic((pte), __KM_PTE)
-#define pte_unmap_nested(pte) kunmap_atomic((pte), KM_PTE1)
+#define pte_unmap(pte) kunmap_atomic((pte))
 #else
 #define pte_offset_map(dir, address)					\
 	((pte_t *)page_address(pmd_page(*(dir))) + pte_index((address)))
-#define pte_offset_map_nested(dir, address) pte_offset_map((dir), (address))
 #define pte_unmap(pte) do { } while (0)
-#define pte_unmap_nested(pte) do { } while (0)
 #endif
 
 /* Clear a kernel PTE and flush it from the TLB */
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index f96ac9bedf75..f86da20347f2 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -127,9 +127,7 @@ static inline int pgd_large(pgd_t pgd) { return 0; }
 
 /* x86-64 always has all page tables mapped. */
 #define pte_offset_map(dir, address) pte_offset_kernel((dir), (address))
-#define pte_offset_map_nested(dir, address) pte_offset_kernel((dir), (address))
 #define pte_unmap(pte) ((void)(pte))/* NOP */
-#define pte_unmap_nested(pte) ((void)(pte)) /* NOP */
 
 #define update_mmu_cache(vma, address, ptep) do { } while (0)
 
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index cd02f324aa6b..7f7e577a0e39 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -12,4 +12,42 @@ void pvclock_read_wallclock(struct pvclock_wall_clock *wall,
 			    struct pvclock_vcpu_time_info *vcpu,
 			    struct timespec *ts);
 
+/*
+ * Scale a 64-bit delta by scaling and multiplying by a 32-bit fraction,
+ * yielding a 64-bit result.
+ */
+static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift)
+{
+	u64 product;
+#ifdef __i386__
+	u32 tmp1, tmp2;
+#endif
+
+	if (shift < 0)
+		delta >>= -shift;
+	else
+		delta <<= shift;
+
+#ifdef __i386__
+	__asm__ (
+		"mul  %5       ; "
+		"mov  %4,%%eax ; "
+		"mov  %%edx,%4 ; "
+		"mul  %5       ; "
+		"xor  %5,%5    ; "
+		"add  %4,%%eax ; "
+		"adc  %5,%%edx ; "
+		: "=A" (product), "=r" (tmp1), "=r" (tmp2)
+		: "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) );
+#else
+#error implement me!
+#endif
+
+	return product;
+}
+
 #endif /* _ASM_X86_PVCLOCK_H */
diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h
index 14e0ed86a6f9..231f1c1d6607 100644
--- a/arch/x86/include/asm/segment.h
+++ b/arch/x86/include/asm/segment.h
@@ -73,31 +73,31 @@
 
 #define GDT_ENTRY_DEFAULT_USER_DS	15
 
-#define GDT_ENTRY_KERNEL_BASE	12
+#define GDT_ENTRY_KERNEL_BASE		(12)
 
-#define GDT_ENTRY_KERNEL_CS		(GDT_ENTRY_KERNEL_BASE + 0)
+#define GDT_ENTRY_KERNEL_CS		(GDT_ENTRY_KERNEL_BASE+0)
 
-#define GDT_ENTRY_KERNEL_DS		(GDT_ENTRY_KERNEL_BASE + 1)
+#define GDT_ENTRY_KERNEL_DS		(GDT_ENTRY_KERNEL_BASE+1)
 
-#define GDT_ENTRY_TSS			(GDT_ENTRY_KERNEL_BASE + 4)
-#define GDT_ENTRY_LDT			(GDT_ENTRY_KERNEL_BASE + 5)
+#define GDT_ENTRY_TSS			(GDT_ENTRY_KERNEL_BASE+4)
+#define GDT_ENTRY_LDT			(GDT_ENTRY_KERNEL_BASE+5)
 
-#define GDT_ENTRY_PNPBIOS_BASE		(GDT_ENTRY_KERNEL_BASE + 6)
-#define GDT_ENTRY_APMBIOS_BASE		(GDT_ENTRY_KERNEL_BASE + 11)
+#define GDT_ENTRY_PNPBIOS_BASE		(GDT_ENTRY_KERNEL_BASE+6)
+#define GDT_ENTRY_APMBIOS_BASE		(GDT_ENTRY_KERNEL_BASE+11)
 
-#define GDT_ENTRY_ESPFIX_SS		(GDT_ENTRY_KERNEL_BASE + 14)
-#define __ESPFIX_SS (GDT_ENTRY_ESPFIX_SS * 8)
+#define GDT_ENTRY_ESPFIX_SS		(GDT_ENTRY_KERNEL_BASE+14)
+#define __ESPFIX_SS			(GDT_ENTRY_ESPFIX_SS*8)
 
-#define GDT_ENTRY_PERCPU			(GDT_ENTRY_KERNEL_BASE + 15)
+#define GDT_ENTRY_PERCPU		(GDT_ENTRY_KERNEL_BASE+15)
 #ifdef CONFIG_SMP
 #define __KERNEL_PERCPU (GDT_ENTRY_PERCPU * 8)
 #else
 #define __KERNEL_PERCPU 0
 #endif
 
-#define GDT_ENTRY_STACK_CANARY		(GDT_ENTRY_KERNEL_BASE + 16)
+#define GDT_ENTRY_STACK_CANARY		(GDT_ENTRY_KERNEL_BASE+16)
 #ifdef CONFIG_CC_STACKPROTECTOR
-#define __KERNEL_STACK_CANARY		(GDT_ENTRY_STACK_CANARY * 8)
+#define __KERNEL_STACK_CANARY		(GDT_ENTRY_STACK_CANARY*8)
 #else
 #define __KERNEL_STACK_CANARY		0
 #endif
@@ -182,10 +182,10 @@
 
 #endif
 
-#define __KERNEL_CS	(GDT_ENTRY_KERNEL_CS * 8)
-#define __KERNEL_DS	(GDT_ENTRY_KERNEL_DS * 8)
-#define __USER_DS     (GDT_ENTRY_DEFAULT_USER_DS* 8 + 3)
-#define __USER_CS     (GDT_ENTRY_DEFAULT_USER_CS* 8 + 3)
+#define __KERNEL_CS	(GDT_ENTRY_KERNEL_CS*8)
+#define __KERNEL_DS	(GDT_ENTRY_KERNEL_DS*8)
+#define __USER_DS	(GDT_ENTRY_DEFAULT_USER_DS*8+3)
+#define __USER_CS	(GDT_ENTRY_DEFAULT_USER_CS*8+3)
 #ifndef CONFIG_PARAVIRT
 #define get_kernel_rpl()  0
 #endif
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 4cfc90824068..4c2f63c7fc1b 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -50,7 +50,7 @@ struct smp_ops {
 	void (*smp_prepare_cpus)(unsigned max_cpus);
 	void (*smp_cpus_done)(unsigned max_cpus);
 
-	void (*smp_send_stop)(void);
+	void (*stop_other_cpus)(int wait);
 	void (*smp_send_reschedule)(int cpu);
 
 	int (*cpu_up)(unsigned cpu);
@@ -73,7 +73,12 @@ extern struct smp_ops smp_ops;
 
 static inline void smp_send_stop(void)
 {
-	smp_ops.smp_send_stop();
+	smp_ops.stop_other_cpus(0);
+}
+
+static inline void stop_other_cpus(void)
+{
+	smp_ops.stop_other_cpus(1);
 }
 
 static inline void smp_prepare_boot_cpu(void)
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 7f3eba08e7de..169be8938b96 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -172,6 +172,4 @@ static inline void flush_tlb_kernel_range(unsigned long start,
 	flush_tlb_all();
 }
 
-extern void zap_low_mappings(bool early);
-
 #endif /* _ASM_X86_TLBFLUSH_H */
diff --git a/arch/x86/include/asm/trampoline.h b/arch/x86/include/asm/trampoline.h
index 4dde797c0578..f4500fb3b485 100644
--- a/arch/x86/include/asm/trampoline.h
+++ b/arch/x86/include/asm/trampoline.h
@@ -13,16 +13,13 @@ extern unsigned char *trampoline_base;
 
 extern unsigned long init_rsp;
 extern unsigned long initial_code;
-extern unsigned long initial_page_table;
 extern unsigned long initial_gs;
 
 #define TRAMPOLINE_SIZE roundup(trampoline_end - trampoline_data, PAGE_SIZE)
 
 extern unsigned long setup_trampoline(void);
-extern void __init setup_trampoline_page_table(void);
 extern void __init reserve_trampoline_memory(void);
 #else
-static inline void setup_trampoline_page_table(void) {}
 static inline void reserve_trampoline_memory(void) {}
 #endif /* CONFIG_X86_TRAMPOLINE */
 
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index 7fda040a76cd..a3c28ae4025b 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -200,6 +200,23 @@ extern struct { char _entry[32]; } hypercall_page[];
 	(type)__res;							\
 })
 
+static inline long
+privcmd_call(unsigned call,
+	     unsigned long a1, unsigned long a2,
+	     unsigned long a3, unsigned long a4,
+	     unsigned long a5)
+{
+	__HYPERCALL_DECLS;
+	__HYPERCALL_5ARG(a1, a2, a3, a4, a5);
+
+	asm volatile("call *%[call]"
+		     : __HYPERCALL_5PARAM
+		     : [call] "a" (&hypercall_page[call])
+		     : __HYPERCALL_CLOBBER5);
+
+	return (long)__res;
+}
+
 static inline int
 HYPERVISOR_set_trap_table(struct trap_info *table)
 {
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index bf5f7d32bd08..dd8c1414b3d5 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -37,14 +37,21 @@ typedef struct xpaddr {
 
 
 extern unsigned long get_phys_to_machine(unsigned long pfn);
-extern void set_phys_to_machine(unsigned long pfn, unsigned long mfn);
+extern bool set_phys_to_machine(unsigned long pfn, unsigned long mfn);
 
 static inline unsigned long pfn_to_mfn(unsigned long pfn)
 {
+	unsigned long mfn;
+
 	if (xen_feature(XENFEAT_auto_translated_physmap))
 		return pfn;
 
-	return get_phys_to_machine(pfn) & ~FOREIGN_FRAME_BIT;
+	mfn = get_phys_to_machine(pfn);
+
+	if (mfn != INVALID_P2M_ENTRY)
+		mfn &= ~FOREIGN_FRAME_BIT;
+
+	return mfn;
 }
 
 static inline int phys_to_machine_mapping_valid(unsigned long pfn)
@@ -159,6 +166,7 @@ static inline pte_t __pte_ma(pteval_t x)
 
 #define pgd_val_ma(x)	((x).pgd)
 
+void xen_set_domain_pte(pte_t *ptep, pte_t pteval, unsigned domid);
 
 xmaddr_t arbitrary_virt_to_machine(void *address);
 unsigned long arbitrary_virt_to_mfn(void *vaddr);