Merge branch 'linus' into x86/x2apic

44 files changed, 1034 insertions, 288 deletions

diff --git a/include/asm-x86/amd_iommu_types.h b/include/asm-x86/amd_iommu_types.h
index 7bfcb47cc45..22aa58ca199 100644
--- a/include/asm-x86/amd_iommu_types.h
+++ b/include/asm-x86/amd_iommu_types.h
@@ -27,13 +27,12 @@
 /*
  * some size calculation constants
  */
-#define DEV_TABLE_ENTRY_SIZE		256
+#define DEV_TABLE_ENTRY_SIZE		32
 #define ALIAS_TABLE_ENTRY_SIZE		2
 #define RLOOKUP_TABLE_ENTRY_SIZE	(sizeof(void *))
 
 /* helper macros */
 #define LOW_U32(x) ((x) & ((1ULL << 32)-1))
-#define HIGH_U32(x) (LOW_U32((x) >> 32))
 
 /* Length of the MMIO region for the AMD IOMMU */
 #define MMIO_REGION_LENGTH       0x4000
@@ -158,78 +157,170 @@
 
 #define MAX_DOMAIN_ID 65536
 
+/*
+ * This structure contains generic data for  IOMMU protection domains
+ * independent of their use.
+ */
 struct protection_domain {
-	spinlock_t lock;
-	u16 id;
-	int mode;
-	u64 *pt_root;
-	void *priv;
+	spinlock_t lock; /* mostly used to lock the page table*/
+	u16 id;		 /* the domain id written to the device table */
+	int mode;	 /* paging mode (0-6 levels) */
+	u64 *pt_root;	 /* page table root pointer */
+	void *priv;	 /* private data */
 };
 
+/*
+ * Data container for a dma_ops specific protection domain
+ */
 struct dma_ops_domain {
 	struct list_head list;
+
+	/* generic protection domain information */
 	struct protection_domain domain;
+
+	/* size of the aperture for the mappings */
 	unsigned long aperture_size;
+
+	/* address we start to search for free addresses */
 	unsigned long next_bit;
+
+	/* address allocation bitmap */
 	unsigned long *bitmap;
+
+	/*
+	 * Array of PTE pages for the aperture. In this array we save all the
+	 * leaf pages of the domain page table used for the aperture. This way
+	 * we don't need to walk the page table to find a specific PTE. We can
+	 * just calculate its address in constant time.
+	 */
 	u64 **pte_pages;
 };
 
+/*
+ * Structure where we save information about one hardware AMD IOMMU in the
+ * system.
+ */
 struct amd_iommu {
 	struct list_head list;
+
+	/* locks the accesses to the hardware */
 	spinlock_t lock;
 
+	/* device id of this IOMMU */
 	u16 devid;
+	/*
+	 * Capability pointer. There could be more than one IOMMU per PCI
+	 * device function if there are more than one AMD IOMMU capability
+	 * pointers.
+	 */
 	u16 cap_ptr;
 
+	/* physical address of MMIO space */
 	u64 mmio_phys;
+	/* virtual address of MMIO space */
 	u8 *mmio_base;
+
+	/* capabilities of that IOMMU read from ACPI */
 	u32 cap;
+
+	/* first device this IOMMU handles. read from PCI */
 	u16 first_device;
+	/* last device this IOMMU handles. read from PCI */
 	u16 last_device;
+
+	/* start of exclusion range of that IOMMU */
 	u64 exclusion_start;
+	/* length of exclusion range of that IOMMU */
 	u64 exclusion_length;
 
+	/* command buffer virtual address */
 	u8 *cmd_buf;
+	/* size of command buffer */
 	u32 cmd_buf_size;
 
+	/* if one, we need to send a completion wait command */
 	int need_sync;
 
+	/* default dma_ops domain for that IOMMU */
 	struct dma_ops_domain *default_dom;
 };
 
+/*
+ * List with all IOMMUs in the system. This list is not locked because it is
+ * only written and read at driver initialization or suspend time
+ */
 extern struct list_head amd_iommu_list;
 
+/*
+ * Structure defining one entry in the device table
+ */
 struct dev_table_entry {
 	u32 data[8];
 };
 
+/*
+ * One entry for unity mappings parsed out of the ACPI table.
+ */
 struct unity_map_entry {
 	struct list_head list;
+
+	/* starting device id this entry is used for (including) */
 	u16 devid_start;
+	/* end device id this entry is used for (including) */
 	u16 devid_end;
+
+	/* start address to unity map (including) */
 	u64 address_start;
+	/* end address to unity map (including) */
 	u64 address_end;
+
+	/* required protection */
 	int prot;
 };
 
+/*
+ * List of all unity mappings. It is not locked because as runtime it is only
+ * read. It is created at ACPI table parsing time.
+ */
 extern struct list_head amd_iommu_unity_map;
 
-/* data structures for device handling */
+/*
+ * Data structures for device handling
+ */
+
+/*
+ * Device table used by hardware. Read and write accesses by software are
+ * locked with the amd_iommu_pd_table lock.
+ */
 extern struct dev_table_entry *amd_iommu_dev_table;
+
+/*
+ * Alias table to find requestor ids to device ids. Not locked because only
+ * read on runtime.
+ */
 extern u16 *amd_iommu_alias_table;
+
+/*
+ * Reverse lookup table to find the IOMMU which translates a specific device.
+ */
 extern struct amd_iommu **amd_iommu_rlookup_table;
 
+/* size of the dma_ops aperture as power of 2 */
 extern unsigned amd_iommu_aperture_order;
 
+/* largest PCI device id we expect translation requests for */
 extern u16 amd_iommu_last_bdf;
 
 /* data structures for protection domain handling */
 extern struct protection_domain **amd_iommu_pd_table;
+
+/* allocation bitmap for domain ids */
 extern unsigned long *amd_iommu_pd_alloc_bitmap;
 
+/* will be 1 if device isolation is enabled */
 extern int amd_iommu_isolate;
 
+/* takes a PCI device id and prints it out in a readable form */
 static inline void print_devid(u16 devid, int nl)
 {
 	int bus = devid >> 8;
@@ -241,4 +332,11 @@ static inline void print_devid(u16 devid, int nl)
 		printk("\n");
 }
 
+/* takes bus and device/function and returns the device id
+ * FIXME: should that be in generic PCI code? */
+static inline u16 calc_devid(u8 bus, u8 devfn)
+{
+	return (((u16)bus) << 8) | devfn;
+}
+
 #endif
diff --git a/include/asm-x86/apic.h b/include/asm-x86/apic.h
index 300b65e5724..51339910fdc 100644
--- a/include/asm-x86/apic.h
+++ b/include/asm-x86/apic.h
@@ -14,8 +14,6 @@
 
 #define ARCH_APICTIMER_STOPS_ON_C3	1
 
-#define Dprintk printk
-
 /*
  * Debugging macros
  */
diff --git a/include/asm-x86/arch_hooks.h b/include/asm-x86/arch_hooks.h
index 768aee8a04e..8411750ceb6 100644
--- a/include/asm-x86/arch_hooks.h
+++ b/include/asm-x86/arch_hooks.h
@@ -21,6 +21,7 @@ extern void intr_init_hook(void);
 extern void pre_intr_init_hook(void);
 extern void pre_setup_arch_hook(void);
 extern void trap_init_hook(void);
+extern void pre_time_init_hook(void);
 extern void time_init_hook(void);
 extern void mca_nmi_hook(void);
 
diff --git a/include/asm-x86/bitops.h b/include/asm-x86/bitops.h
index 96b1829cea1..cfb2b64f76e 100644
--- a/include/asm-x86/bitops.h
+++ b/include/asm-x86/bitops.h
@@ -356,7 +356,7 @@ static inline unsigned long ffz(unsigned long word)
  * __fls: find last set bit in word
  * @word: The word to search
  *
- * Undefined if no zero exists, so code should check against ~0UL first.
+ * Undefined if no set bit exists, so code should check against 0 first.
  */
 static inline unsigned long __fls(unsigned long word)
 {
diff --git a/include/asm-x86/calling.h b/include/asm-x86/calling.h
index f13e62e2cb3..2bc162e0ec6 100644
--- a/include/asm-x86/calling.h
+++ b/include/asm-x86/calling.h
@@ -104,7 +104,7 @@
 	.endif
 	.endm
 
-	.macro LOAD_ARGS offset
+	.macro LOAD_ARGS offset, skiprax=0
 	movq \offset(%rsp),    %r11
 	movq \offset+8(%rsp),  %r10
 	movq \offset+16(%rsp), %r9
@@ -113,7 +113,10 @@
 	movq \offset+48(%rsp), %rdx
 	movq \offset+56(%rsp), %rsi
 	movq \offset+64(%rsp), %rdi
+	.if \skiprax
+	.else
 	movq \offset+72(%rsp), %rax
+	.endif
 	.endm
 
 #define REST_SKIP	6*8
@@ -165,4 +168,3 @@
 	.macro icebp
 	.byte 0xf1
 	.endm
-
diff --git a/include/asm-x86/dma-mapping.h b/include/asm-x86/dma-mapping.h
index a1a4dc7fe6e..c2ddd3d1b88 100644
--- a/include/asm-x86/dma-mapping.h
+++ b/include/asm-x86/dma-mapping.h
@@ -14,7 +14,6 @@ extern dma_addr_t bad_dma_address;
 extern int iommu_merge;
 extern struct device fallback_dev;
 extern int panic_on_overflow;
-extern int forbid_dac;
 extern int force_iommu;
 
 struct dma_mapping_ops {
diff --git a/include/asm-x86/e820.h b/include/asm-x86/e820.h
index 06633b01dd5..16a31e2c7c5 100644
--- a/include/asm-x86/e820.h
+++ b/include/asm-x86/e820.h
@@ -90,6 +90,14 @@ static inline void e820_mark_nosave_regions(unsigned long limit_pfn)
 }
 #endif
 
+#ifdef CONFIG_MEMTEST
+extern void early_memtest(unsigned long start, unsigned long end);
+#else
+static inline void early_memtest(unsigned long start, unsigned long end)
+{
+}
+#endif
+
 extern unsigned long end_user_pfn;
 
 extern u64 find_e820_area(u64 start, u64 end, u64 size, u64 align);
diff --git a/include/asm-x86/fixmap_32.h b/include/asm-x86/fixmap_32.h
index aae2f0501a4..f1ac2b2167d 100644
--- a/include/asm-x86/fixmap_32.h
+++ b/include/asm-x86/fixmap_32.h
@@ -90,13 +90,13 @@ enum fixed_addresses {
 	 * 256 temporary boot-time mappings, used by early_ioremap(),
 	 * before ioremap() is functional.
 	 *
-	 * We round it up to the next 512 pages boundary so that we
+	 * We round it up to the next 256 pages boundary so that we
 	 * can have a single pgd entry and a single pte table:
 	 */
 #define NR_FIX_BTMAPS		64
 #define FIX_BTMAPS_NESTING	4
-	FIX_BTMAP_END = __end_of_permanent_fixed_addresses + 512 -
-			(__end_of_permanent_fixed_addresses & 511),
+	FIX_BTMAP_END = __end_of_permanent_fixed_addresses + 256 -
+			(__end_of_permanent_fixed_addresses & 255),
 	FIX_BTMAP_BEGIN = FIX_BTMAP_END + NR_FIX_BTMAPS*FIX_BTMAPS_NESTING - 1,
 	FIX_WP_TEST,
 #ifdef CONFIG_ACPI
diff --git a/include/asm-x86/ftrace.h b/include/asm-x86/ftrace.h
index c184441133f..5c68b32ee1c 100644
--- a/include/asm-x86/ftrace.h
+++ b/include/asm-x86/ftrace.h
@@ -1,5 +1,5 @@
 #ifndef _ASM_X86_FTRACE
-#define _ASM_SPARC64_FTRACE
+#define _ASM_X86_FTRACE
 
 #ifdef CONFIG_FTRACE
 #define MCOUNT_ADDR		((long)(mcount))
diff --git a/include/asm-x86/gart.h b/include/asm-x86/gart.h
index 33b9aeeb35a..3f62a83887f 100644
--- a/include/asm-x86/gart.h
+++ b/include/asm-x86/gart.h
@@ -2,7 +2,6 @@
 #define _ASM_X8664_GART_H 1
 
 #include <asm/e820.h>
-#include <asm/iommu.h>
 
 extern void set_up_gart_resume(u32, u32);
 
diff --git a/include/asm-x86/iommu.h b/include/asm-x86/iommu.h
index 068c9a40aa5..d63166fb3ab 100644
--- a/include/asm-x86/iommu.h
+++ b/include/asm-x86/iommu.h
@@ -25,10 +25,18 @@ extern void gart_iommu_hole_init(void);
 static inline void early_gart_iommu_check(void)
 {
 }
-
+static inline void gart_iommu_init(void)
+{
+}
 static inline void gart_iommu_shutdown(void)
 {
 }
+static inline void gart_parse_options(char *options)
+{
+}
+static inline void gart_iommu_hole_init(void)
+{
+}
 #endif
 
 #endif
diff --git a/include/asm-x86/kvm.h b/include/asm-x86/kvm.h
index 80eefef2cc7..6f1840812e5 100644
--- a/include/asm-x86/kvm.h
+++ b/include/asm-x86/kvm.h
@@ -228,5 +228,6 @@ struct kvm_pit_state {
 #define KVM_TRC_CLTS             (KVM_TRC_HANDLER + 0x12)
 #define KVM_TRC_LMSW             (KVM_TRC_HANDLER + 0x13)
 #define KVM_TRC_APIC_ACCESS      (KVM_TRC_HANDLER + 0x14)
+#define KVM_TRC_TDP_FAULT        (KVM_TRC_HANDLER + 0x15)
 
 #endif
diff --git a/include/asm-x86/kvm_host.h b/include/asm-x86/kvm_host.h
index 844f2a89afb..fdde0bedaa9 100644
--- a/include/asm-x86/kvm_host.h
+++ b/include/asm-x86/kvm_host.h
@@ -27,6 +27,7 @@
 #define KVM_PRIVATE_MEM_SLOTS 4
 
 #define KVM_PIO_PAGE_OFFSET 1
+#define KVM_COALESCED_MMIO_PAGE_OFFSET 2
 
 #define CR3_PAE_RESERVED_BITS ((X86_CR3_PWT | X86_CR3_PCD) - 1)
 #define CR3_NONPAE_RESERVED_BITS ((PAGE_SIZE-1) & ~(X86_CR3_PWT | X86_CR3_PCD))
@@ -79,6 +80,7 @@
 #define KVM_MIN_FREE_MMU_PAGES 5
 #define KVM_REFILL_PAGES 25
 #define KVM_MAX_CPUID_ENTRIES 40
+#define KVM_NR_VAR_MTRR 8
 
 extern spinlock_t kvm_lock;
 extern struct list_head vm_list;
@@ -109,12 +111,12 @@ enum {
 };
 
 enum {
+	VCPU_SREG_ES,
 	VCPU_SREG_CS,
+	VCPU_SREG_SS,
 	VCPU_SREG_DS,
-	VCPU_SREG_ES,
 	VCPU_SREG_FS,
 	VCPU_SREG_GS,
-	VCPU_SREG_SS,
 	VCPU_SREG_TR,
 	VCPU_SREG_LDTR,
 };
@@ -243,6 +245,7 @@ struct kvm_vcpu_arch {
 	gfn_t last_pt_write_gfn;
 	int   last_pt_write_count;
 	u64  *last_pte_updated;
+	gfn_t last_pte_gfn;
 
 	struct {
 		gfn_t gfn;	/* presumed gfn during guest pte update */
@@ -287,6 +290,10 @@ struct kvm_vcpu_arch {
 	unsigned int hv_clock_tsc_khz;
 	unsigned int time_offset;
 	struct page *time_page;
+
+	bool nmi_pending;
+
+	u64 mtrr[0x100];
 };
 
 struct kvm_mem_alias {
@@ -344,6 +351,7 @@ struct kvm_vcpu_stat {
 	u32 mmio_exits;
 	u32 signal_exits;
 	u32 irq_window_exits;
+	u32 nmi_window_exits;
 	u32 halt_exits;
 	u32 halt_wakeup;
 	u32 request_irq_exits;
@@ -379,7 +387,6 @@ struct kvm_x86_ops {
 	void (*prepare_guest_switch)(struct kvm_vcpu *vcpu);
 	void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu);
 	void (*vcpu_put)(struct kvm_vcpu *vcpu);
-	void (*vcpu_decache)(struct kvm_vcpu *vcpu);
 
 	int (*set_guest_debug)(struct kvm_vcpu *vcpu,
 			       struct kvm_debug_guest *dbg);
@@ -497,6 +504,10 @@ int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr,
 int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr,
 		    unsigned long value);
 
+void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
+int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector,
+				int type_bits, int seg);
+
 int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason);
 
 void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
@@ -515,6 +526,8 @@ void kvm_queue_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_nmi(struct kvm_vcpu *vcpu);
+
 void fx_init(struct kvm_vcpu *vcpu);
 
 int emulator_read_std(unsigned long addr,
@@ -554,55 +567,53 @@ static inline struct kvm_mmu_page *page_header(hpa_t shadow_page)
 	return (struct kvm_mmu_page *)page_private(page);
 }
 
-static inline u16 read_fs(void)
+static inline u16 kvm_read_fs(void)
 {
 	u16 seg;
 	asm("mov %%fs, %0" : "=g"(seg));
 	return seg;
 }
 
-static inline u16 read_gs(void)
+static inline u16 kvm_read_gs(void)
 {
 	u16 seg;
 	asm("mov %%gs, %0" : "=g"(seg));
 	return seg;
 }
 
-static inline u16 read_ldt(void)
+static inline u16 kvm_read_ldt(void)
 {
 	u16 ldt;
 	asm("sldt %0" : "=g"(ldt));
 	return ldt;
 }
 
-static inline void load_fs(u16 sel)
+static inline void kvm_load_fs(u16 sel)
 {
 	asm("mov %0, %%fs" : : "rm"(sel));
 }
 
-static inline void load_gs(u16 sel)
+static inline void kvm_load_gs(u16 sel)
 {
 	asm("mov %0, %%gs" : : "rm"(sel));
 }
 
-#ifndef load_ldt
-static inline void load_ldt(u16 sel)
+static inline void kvm_load_ldt(u16 sel)
 {
 	asm("lldt %0" : : "rm"(sel));
 }
-#endif
 
-static inline void get_idt(struct descriptor_table *table)
+static inline void kvm_get_idt(struct descriptor_table *table)
 {
 	asm("sidt %0" : "=m"(*table));
 }
 
-static inline void get_gdt(struct descriptor_table *table)
+static inline void kvm_get_gdt(struct descriptor_table *table)
 {
 	asm("sgdt %0" : "=m"(*table));
 }
 
-static inline unsigned long read_tr_base(void)
+static inline unsigned long kvm_read_tr_base(void)
 {
 	u16 tr;
 	asm("str %0" : "=g"(tr));
@@ -619,17 +630,17 @@ static inline unsigned long read_msr(unsigned long msr)
 }
 #endif
 
-static inline void fx_save(struct i387_fxsave_struct *image)
+static inline void kvm_fx_save(struct i387_fxsave_struct *image)
 {
 	asm("fxsave (%0)":: "r" (image));
 }
 
-static inline void fx_restore(struct i387_fxsave_struct *image)
+static inline void kvm_fx_restore(struct i387_fxsave_struct *image)
 {
 	asm("fxrstor (%0)":: "r" (image));
 }
 
-static inline void fx_finit(void)
+static inline void kvm_fx_finit(void)
 {
 	asm("finit");
 }
@@ -691,4 +702,30 @@ enum {
 	trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \
 						vcpu, 0, 0, 0, 0, 0, 0)
 
+#ifdef CONFIG_64BIT
+# define KVM_EX_ENTRY ".quad"
+# define KVM_EX_PUSH "pushq"
+#else
+# define KVM_EX_ENTRY ".long"
+# define KVM_EX_PUSH "pushl"
+#endif
+
+/*
+ * Hardware virtualization extension instructions may fault if a
+ * reboot turns off virtualization while processes are running.
+ * Trap the fault and ignore the instruction if that happens.
+ */
+asmlinkage void kvm_handle_fault_on_reboot(void);
+
+#define __kvm_handle_fault_on_reboot(insn) \
+	"666: " insn "\n\t" \
+	".pushsection .text.fixup, \"ax\" \n" \
+	"667: \n\t" \
+	KVM_EX_PUSH " $666b \n\t" \
+	"jmp kvm_handle_fault_on_reboot \n\t" \
+	".popsection \n\t" \
+	".pushsection __ex_table, \"a\" \n\t" \
+	KVM_EX_ENTRY " 666b, 667b \n\t" \
+	".popsection"
+
 #endif
diff --git a/include/asm-x86/kvm_x86_emulate.h b/include/asm-x86/kvm_x86_emulate.h
index b877bbd2d3a..4e8c1e48d91 100644
--- a/include/asm-x86/kvm_x86_emulate.h
+++ b/include/asm-x86/kvm_x86_emulate.h
@@ -124,7 +124,8 @@ struct decode_cache {
 	u8 rex_prefix;
 	struct operand src;
 	struct operand dst;
-	unsigned long *override_base;
+	bool has_seg_override;
+	u8 seg_override;
 	unsigned int d;
 	unsigned long regs[NR_VCPU_REGS];
 	unsigned long eip;
@@ -134,6 +135,7 @@ struct decode_cache {
 	u8 modrm_reg;
 	u8 modrm_rm;
 	u8 use_modrm_ea;
+	bool rip_relative;
 	unsigned long modrm_ea;
 	void *modrm_ptr;
 	unsigned long modrm_val;
@@ -150,12 +152,7 @@ struct x86_emulate_ctxt {
 	/* Emulated execution mode, represented by an X86EMUL_MODE value. */
 	int mode;
 
-	unsigned long cs_base;
-	unsigned long ds_base;
-	unsigned long es_base;
-	unsigned long ss_base;
-	unsigned long gs_base;
-	unsigned long fs_base;
+	u32 cs_base;
 
 	/* decode cache */
 
diff --git a/include/asm-x86/mach-default/smpboot_hooks.h b/include/asm-x86/mach-default/smpboot_hooks.h
index 56d001b9dce..dbab36d64d4 100644
--- a/include/asm-x86/mach-default/smpboot_hooks.h
+++ b/include/asm-x86/mach-default/smpboot_hooks.h
@@ -12,11 +12,11 @@ static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip)
 {
 	CMOS_WRITE(0xa, 0xf);
 	local_flush_tlb();
-	Dprintk("1.\n");
+	pr_debug("1.\n");
 	*((volatile unsigned short *) TRAMPOLINE_HIGH) = start_eip >> 4;
-	Dprintk("2.\n");
+	pr_debug("2.\n");
 	*((volatile unsigned short *) TRAMPOLINE_LOW) = start_eip & 0xf;
-	Dprintk("3.\n");
+	pr_debug("3.\n");
 }
 
 static inline void smpboot_restore_warm_reset_vector(void)
diff --git a/include/asm-x86/mach-generic/mach_mpspec.h b/include/asm-x86/mach-generic/mach_mpspec.h
index 9ef0b941bb2..c83c120be53 100644
--- a/include/asm-x86/mach-generic/mach_mpspec.h
+++ b/include/asm-x86/mach-generic/mach_mpspec.h
@@ -7,4 +7,6 @@
 /* Maximum 256 PCI busses, plus 1 ISA bus in each of 4 cabinets. */
 #define MAX_MP_BUSSES 260
 
+extern void numaq_mps_oem_check(struct mp_config_table *mpc, char *oem,
+				char *productid);
 #endif /* __ASM_MACH_MPSPEC_H */
diff --git a/include/asm-x86/mach-visws/entry_arch.h b/include/asm-x86/mach-visws/entry_arch.h
deleted file mode 100644
index 86be554342d..00000000000
--- a/include/asm-x86/mach-visws/entry_arch.h
+++ /dev/null
@@ -1,5 +0,0 @@
-/*
- * VISWS uses the standard Linux entry points:
- */
-
-#include "../mach-default/entry_arch.h"
diff --git a/include/asm-x86/mach-visws/mach_apic.h b/include/asm-x86/mach-visws/mach_apic.h
deleted file mode 100644
index 6943e7a1d0e..00000000000
--- a/include/asm-x86/mach-visws/mach_apic.h
+++ /dev/null
@@ -1 +0,0 @@
-#include "../mach-default/mach_apic.h"
diff --git a/include/asm-x86/mach-visws/mach_apicdef.h b/include/asm-x86/mach-visws/mach_apicdef.h
deleted file mode 100644
index 42711d152a9..00000000000
--- a/include/asm-x86/mach-visws/mach_apicdef.h
+++ /dev/null
@@ -1 +0,0 @@
-#include "../mach-default/mach_apicdef.h"
diff --git a/include/asm-x86/mach-visws/setup_arch.h b/include/asm-x86/mach-visws/setup_arch.h
deleted file mode 100644
index fa4766ca2d1..00000000000
--- a/include/asm-x86/mach-visws/setup_arch.h
+++ /dev/null
@@ -1 +0,0 @@
-#include "../mach-default/setup_arch.h"
diff --git a/include/asm-x86/mach-visws/smpboot_hooks.h b/include/asm-x86/mach-visws/smpboot_hooks.h
deleted file mode 100644
index e4433ca8871..00000000000
--- a/include/asm-x86/mach-visws/smpboot_hooks.h
+++ /dev/null
@@ -1 +0,0 @@
-#include "../mach-default/smpboot_hooks.h"
diff --git a/include/asm-x86/paravirt.h b/include/asm-x86/paravirt.h
index 08f89e385a9..a8b19ec04ac 100644
--- a/include/asm-x86/paravirt.h
+++ b/include/asm-x86/paravirt.h
@@ -319,6 +319,15 @@ struct pv_mmu_ops {
 			   unsigned long phys, pgprot_t flags);
 };
 
+struct raw_spinlock;
+struct pv_lock_ops {
+	int (*spin_is_locked)(struct raw_spinlock *lock);
+	int (*spin_is_contended)(struct raw_spinlock *lock);
+	void (*spin_lock)(struct raw_spinlock *lock);
+	int (*spin_trylock)(struct raw_spinlock *lock);
+	void (*spin_unlock)(struct raw_spinlock *lock);
+};
+
 /* This contains all the paravirt structures: we get a convenient
  * number for each function using the offset which we use to indicate
  * what to patch. */
@@ -329,6 +338,7 @@ struct paravirt_patch_template {
 	struct pv_irq_ops pv_irq_ops;
 	struct pv_apic_ops pv_apic_ops;
 	struct pv_mmu_ops pv_mmu_ops;
+	struct pv_lock_ops pv_lock_ops;
 };
 
 extern struct pv_info pv_info;
@@ -338,6 +348,7 @@ extern struct pv_cpu_ops pv_cpu_ops;
 extern struct pv_irq_ops pv_irq_ops;
 extern struct pv_apic_ops pv_apic_ops;
 extern struct pv_mmu_ops pv_mmu_ops;
+extern struct pv_lock_ops pv_lock_ops;
 
 #define PARAVIRT_PATCH(x)					\
 	(offsetof(struct paravirt_patch_template, x) / sizeof(void *))
@@ -1349,6 +1360,37 @@ static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx,
 void _paravirt_nop(void);
 #define paravirt_nop	((void *)_paravirt_nop)
 
+void paravirt_use_bytelocks(void);
+
+#ifdef CONFIG_SMP
+
+static inline int __raw_spin_is_locked(struct raw_spinlock *lock)
+{
+	return PVOP_CALL1(int, pv_lock_ops.spin_is_locked, lock);
+}
+
+static inline int __raw_spin_is_contended(struct raw_spinlock *lock)
+{
+	return PVOP_CALL1(int, pv_lock_ops.spin_is_contended, lock);
+}
+
+static __always_inline void __raw_spin_lock(struct raw_spinlock *lock)
+{
+	PVOP_VCALL1(pv_lock_ops.spin_lock, lock);
+}
+
+static __always_inline int __raw_spin_trylock(struct raw_spinlock *lock)
+{
+	return PVOP_CALL1(int, pv_lock_ops.spin_trylock, lock);
+}
+
+static __always_inline void __raw_spin_unlock(struct raw_spinlock *lock)
+{
+	PVOP_VCALL1(pv_lock_ops.spin_unlock, lock);
+}
+
+#endif
+
 /* These all sit in the .parainstructions section to tell us what to patch. */
 struct paravirt_patch_site {
 	u8 *instr; 		/* original instructions */
@@ -1371,8 +1413,8 @@ extern struct paravirt_patch_site __parainstructions[],
  * caller saved registers but the argument parameter */
 #define PV_SAVE_REGS "pushq %%rdi;"
 #define PV_RESTORE_REGS "popq %%rdi;"
-#define PV_EXTRA_CLOBBERS EXTRA_CLOBBERS, "rcx" , "rdx"
-#define PV_VEXTRA_CLOBBERS EXTRA_CLOBBERS, "rdi", "rcx" , "rdx"
+#define PV_EXTRA_CLOBBERS EXTRA_CLOBBERS, "rcx" , "rdx", "rsi"
+#define PV_VEXTRA_CLOBBERS EXTRA_CLOBBERS, "rdi", "rcx" , "rdx", "rsi"
 #define PV_FLAGS_ARG "D"
 #endif
 
@@ -1433,6 +1475,7 @@ static inline unsigned long __raw_local_irq_save(void)
 	return f;
 }
 
+
 /* Make sure as little as possible of this mess escapes. */
 #undef PARAVIRT_CALL
 #undef __PVOP_CALL
@@ -1464,8 +1507,26 @@ static inline unsigned long __raw_local_irq_save(void)
 
 
 #ifdef CONFIG_X86_64
-#define PV_SAVE_REGS   pushq %rax; pushq %rdi; pushq %rcx; pushq %rdx
-#define PV_RESTORE_REGS popq %rdx; popq %rcx; popq %rdi; popq %rax
+#define PV_SAVE_REGS				\
+	push %rax;				\
+	push %rcx;				\
+	push %rdx;				\
+	push %rsi;				\
+	push %rdi;				\
+	push %r8;				\
+	push %r9;				\
+	push %r10;				\
+	push %r11
+#define PV_RESTORE_REGS				\
+	pop %r11;				\
+	pop %r10;				\
+	pop %r9;				\
+	pop %r8;				\
+	pop %rdi;				\
+	pop %rsi;				\
+	pop %rdx;				\
+	pop %rcx;				\
+	pop %rax
 #define PARA_PATCH(struct, off)        ((PARAVIRT_PATCH_##struct + (off)) / 8)
 #define PARA_SITE(ptype, clobbers, ops) _PVSITE(ptype, clobbers, ops, .quad, 8)
 #define PARA_INDIRECT(addr)	*addr(%rip)
diff --git a/include/asm-x86/percpu.h b/include/asm-x86/percpu.h
index 912a3a17b9d..4e91ee1e37a 100644
--- a/include/asm-x86/percpu.h
+++ b/include/asm-x86/percpu.h
@@ -22,6 +22,32 @@
 
 DECLARE_PER_CPU(struct x8664_pda, pda);
 
+/*
+ * These are supposed to be implemented as a single instruction which
+ * operates on the per-cpu data base segment.  x86-64 doesn't have
+ * that yet, so this is a fairly inefficient workaround for the
+ * meantime.  The single instruction is atomic with respect to
+ * preemption and interrupts, so we need to explicitly disable
+ * interrupts here to achieve the same effect.  However, because it
+ * can be used from within interrupt-disable/enable, we can't actually
+ * disable interrupts; disabling preemption is enough.
+ */
+#define x86_read_percpu(var)						\
+	({								\
+		typeof(per_cpu_var(var)) __tmp;				\
+		preempt_disable();					\
+		__tmp = __get_cpu_var(var);				\
+		preempt_enable();					\
+		__tmp;							\
+	})
+
+#define x86_write_percpu(var, val)					\
+	do {								\
+		preempt_disable();					\
+		__get_cpu_var(var) = (val);				\
+		preempt_enable();					\
+	} while(0)
+
 #else /* CONFIG_X86_64 */
 
 #ifdef __ASSEMBLY__
diff --git a/include/asm-x86/pgtable.h b/include/asm-x86/pgtable.h
index 49cbd76b954..96aa76e691d 100644
--- a/include/asm-x86/pgtable.h
+++ b/include/asm-x86/pgtable.h
@@ -302,6 +302,14 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 /* Install a pte for a particular vaddr in kernel space. */
 void set_pte_vaddr(unsigned long vaddr, pte_t pte);
 
+#ifdef CONFIG_X86_32
+extern void native_pagetable_setup_start(pgd_t *base);
+extern void native_pagetable_setup_done(pgd_t *base);
+#else
+static inline void native_pagetable_setup_start(pgd_t *base) {}
+static inline void native_pagetable_setup_done(pgd_t *base) {}
+#endif
+
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
 #else  /* !CONFIG_PARAVIRT */
@@ -333,6 +341,16 @@ void set_pte_vaddr(unsigned long vaddr, pte_t pte);
 
 #define pte_update(mm, addr, ptep)              do { } while (0)
 #define pte_update_defer(mm, addr, ptep)        do { } while (0)
+
+static inline void __init paravirt_pagetable_setup_start(pgd_t *base)
+{
+	native_pagetable_setup_start(base);
+}
+
+static inline void __init paravirt_pagetable_setup_done(pgd_t *base)
+{
+	native_pagetable_setup_done(base);
+}
 #endif	/* CONFIG_PARAVIRT */
 
 #endif	/* __ASSEMBLY__ */
diff --git a/include/asm-x86/pgtable_32.h b/include/asm-x86/pgtable_32.h
index ec871c420d7..0611abf96a5 100644
--- a/include/asm-x86/pgtable_32.h
+++ b/include/asm-x86/pgtable_32.h
@@ -171,21 +171,6 @@ do {						\
  */
 #define update_mmu_cache(vma, address, pte) do { } while (0)
 
-extern void native_pagetable_setup_start(pgd_t *base);
-extern void native_pagetable_setup_done(pgd_t *base);
-
-#ifndef CONFIG_PARAVIRT
-static inline void __init paravirt_pagetable_setup_start(pgd_t *base)
-{
-	native_pagetable_setup_start(base);
-}
-
-static inline void __init paravirt_pagetable_setup_done(pgd_t *base)
-{
-	native_pagetable_setup_done(base);
-}
-#endif	/* !CONFIG_PARAVIRT */
-
 #endif /* !__ASSEMBLY__ */
 
 /*
diff --git a/include/asm-x86/pgtable_64.h b/include/asm-x86/pgtable_64.h
index fa7208b483c..805d3128bfc 100644
--- a/include/asm-x86/pgtable_64.h
+++ b/include/asm-x86/pgtable_64.h
@@ -16,6 +16,8 @@
 extern pud_t level3_kernel_pgt[512];
 extern pud_t level3_ident_pgt[512];
 extern pmd_t level2_kernel_pgt[512];
+extern pmd_t level2_fixmap_pgt[512];
+extern pmd_t level2_ident_pgt[512];
 extern pgd_t init_level4_pgt[];
 
 #define swapper_pg_dir init_level4_pgt
diff --git a/include/asm-x86/processor.h b/include/asm-x86/processor.h
index 55402d2ab93..15cb82a44e8 100644
--- a/include/asm-x86/processor.h
+++ b/include/asm-x86/processor.h
@@ -722,8 +722,6 @@ static inline void __sti_mwait(unsigned long eax, unsigned long ecx)
 
 extern void mwait_idle_with_hints(unsigned long eax, unsigned long ecx);
 
-extern int			force_mwait;
-
 extern void select_idle_routine(const struct cpuinfo_x86 *c);
 
 extern unsigned long		boot_option_idle_override;
diff --git a/include/asm-x86/ptrace-abi.h b/include/asm-x86/ptrace-abi.h
index f224eb3c315..72e7b9db29b 100644
--- a/include/asm-x86/ptrace-abi.h
+++ b/include/asm-x86/ptrace-abi.h
@@ -73,11 +73,11 @@
 
 #ifdef __x86_64__
 # define PTRACE_ARCH_PRCTL	  30
-#else
-# define PTRACE_SYSEMU		  31
-# define PTRACE_SYSEMU_SINGLESTEP 32
 #endif
 
+#define PTRACE_SYSEMU		  31
+#define PTRACE_SYSEMU_SINGLESTEP  32
+
 #define PTRACE_SINGLEBLOCK	33	/* resume execution until next branch */
 
 #ifndef __ASSEMBLY__
diff --git a/include/asm-x86/segment.h b/include/asm-x86/segment.h
index dfc8601c089..646452ea9ea 100644
--- a/include/asm-x86/segment.h
+++ b/include/asm-x86/segment.h
@@ -1,6 +1,15 @@
 #ifndef _ASM_X86_SEGMENT_H_
 #define _ASM_X86_SEGMENT_H_
 
+/* Constructor for a conventional segment GDT (or LDT) entry */
+/* This is a macro so it can be used in initializers */
+#define GDT_ENTRY(flags, base, limit)			\
+	((((base)  & 0xff000000ULL) << (56-24)) |	\
+	 (((flags) & 0x0000f0ffULL) << 40) |		\
+	 (((limit) & 0x000f0000ULL) << (48-16)) |	\
+	 (((base)  & 0x00ffffffULL) << 16) |		\
+	 (((limit) & 0x0000ffffULL)))
+
 /* Simple and small GDT entries for booting only */
 
 #define GDT_ENTRY_BOOT_CS	2
diff --git a/include/asm-x86/setup.h b/include/asm-x86/setup.h
index 90ab2225e71..a07c6f1c01e 100644
--- a/include/asm-x86/setup.h
+++ b/include/asm-x86/setup.h
@@ -19,13 +19,28 @@ static inline int is_visws_box(void) { return 0; }
 /*
  * Any setup quirks to be performed?
  */
-extern int (*arch_time_init_quirk)(void);
-extern int (*arch_pre_intr_init_quirk)(void);
-extern int (*arch_intr_init_quirk)(void);
-extern int (*arch_trap_init_quirk)(void);
-extern char * (*arch_memory_setup_quirk)(void);
-extern int (*mach_get_smp_config_quirk)(unsigned int early);
-extern int (*mach_find_smp_config_quirk)(unsigned int reserve);
+struct mpc_config_processor;
+struct mpc_config_bus;
+struct mp_config_oemtable;
+struct x86_quirks {
+	int (*arch_pre_time_init)(void);
+	int (*arch_time_init)(void);
+	int (*arch_pre_intr_init)(void);
+	int (*arch_intr_init)(void);
+	int (*arch_trap_init)(void);
+	char * (*arch_memory_setup)(void);
+	int (*mach_get_smp_config)(unsigned int early);
+	int (*mach_find_smp_config)(unsigned int reserve);
+
+	int *mpc_record;
+	int (*mpc_apic_id)(struct mpc_config_processor *m);
+	void (*mpc_oem_bus_info)(struct mpc_config_bus *m, char *name);
+	void (*mpc_oem_pci_bus)(struct mpc_config_bus *m);
+	void (*smp_read_mpc_oem)(struct mp_config_oemtable *oemtable,
+                                    unsigned short oemsize);
+};
+
+extern struct x86_quirks *x86_quirks;
 
 #ifndef CONFIG_PARAVIRT
 #define paravirt_post_allocator_init()	do {} while (0)
@@ -76,6 +91,7 @@ extern unsigned long init_pg_tables_start;
 extern unsigned long init_pg_tables_end;
 
 #else
+void __init x86_64_init_pda(void);
 void __init x86_64_start_kernel(char *real_mode);
 void __init x86_64_start_reservations(char *real_mode_data);
 
diff --git a/include/asm-x86/signal.h b/include/asm-x86/signal.h
index f15186d39c6..6dac49364e9 100644
--- a/include/asm-x86/signal.h
+++ b/include/asm-x86/signal.h
@@ -181,12 +181,12 @@ typedef struct sigaltstack {
 #ifdef __KERNEL__
 #include <asm/sigcontext.h>
 
-#ifdef __386__
+#ifdef __i386__
 
 #define __HAVE_ARCH_SIG_BITOPS
 
 #define sigaddset(set,sig)		    \
-	(__builtin_constantp(sig)	    \
+	(__builtin_constant_p(sig)	    \
 	 ? __const_sigaddset((set), (sig))  \
 	 : __gen_sigaddset((set), (sig)))
 
diff --git a/include/asm-x86/smp.h b/include/asm-x86/smp.h
index 1896cdb0076..59d6cfcc404 100644
--- a/include/asm-x86/smp.h
+++ b/include/asm-x86/smp.h
@@ -25,6 +25,8 @@ extern cpumask_t cpu_callin_map;
 extern void (*mtrr_hook)(void);
 extern void zap_low_mappings(void);
 
+extern int __cpuinit get_local_pda(int cpu);
+
 extern int smp_num_siblings;
 extern unsigned int num_processors;
 extern cpumask_t cpu_initialized;
diff --git a/include/asm-x86/spinlock.h b/include/asm-x86/spinlock.h
index 21e89bf92f1..4f9a9861799 100644
--- a/include/asm-x86/spinlock.h
+++ b/include/asm-x86/spinlock.h
@@ -6,7 +6,7 @@
 #include <asm/page.h>
 #include <asm/processor.h>
 #include <linux/compiler.h>
-
+#include <asm/paravirt.h>
 /*
  * Your basic SMP spinlocks, allowing only a single CPU anywhere
  *
@@ -54,21 +54,21 @@
  * much between them in performance though, especially as locks are out of line.
  */
 #if (NR_CPUS < 256)
-static inline int __raw_spin_is_locked(raw_spinlock_t *lock)
+static inline int __ticket_spin_is_locked(raw_spinlock_t *lock)
 {
 	int tmp = ACCESS_ONCE(lock->slock);
 
 	return (((tmp >> 8) & 0xff) != (tmp & 0xff));
 }
 
-static inline int __raw_spin_is_contended(raw_spinlock_t *lock)
+static inline int __ticket_spin_is_contended(raw_spinlock_t *lock)
 {
 	int tmp = ACCESS_ONCE(lock->slock);
 
 	return (((tmp >> 8) & 0xff) - (tmp & 0xff)) > 1;
 }
 
-static __always_inline void __raw_spin_lock(raw_spinlock_t *lock)
+static __always_inline void __ticket_spin_lock(raw_spinlock_t *lock)
 {
 	short inc = 0x0100;
 
@@ -87,9 +87,7 @@ static __always_inline void __raw_spin_lock(raw_spinlock_t *lock)
 		: "memory", "cc");
 }
 
-#define __raw_spin_lock_flags(lock, flags) __raw_spin_lock(lock)
-
-static __always_inline int __raw_spin_trylock(raw_spinlock_t *lock)
+static __always_inline int __ticket_spin_trylock(raw_spinlock_t *lock)
 {
 	int tmp;
 	short new;
@@ -110,7 +108,7 @@ static __always_inline int __raw_spin_trylock(raw_spinlock_t *lock)
 	return tmp;
 }
 
-static __always_inline void __raw_spin_unlock(raw_spinlock_t *lock)
+static __always_inline void __ticket_spin_unlock(raw_spinlock_t *lock)
 {
 	asm volatile(UNLOCK_LOCK_PREFIX "incb %0"
 		     : "+m" (lock->slock)
@@ -118,21 +116,21 @@ static __always_inline void __raw_spin_unlock(raw_spinlock_t *lock)
 		     : "memory", "cc");
 }
 #else
-static inline int __raw_spin_is_locked(raw_spinlock_t *lock)
+static inline int __ticket_spin_is_locked(raw_spinlock_t *lock)
 {
 	int tmp = ACCESS_ONCE(lock->slock);
 
 	return (((tmp >> 16) & 0xffff) != (tmp & 0xffff));
 }
 
-static inline int __raw_spin_is_contended(raw_spinlock_t *lock)
+static inline int __ticket_spin_is_contended(raw_spinlock_t *lock)
 {
 	int tmp = ACCESS_ONCE(lock->slock);
 
 	return (((tmp >> 16) & 0xffff) - (tmp & 0xffff)) > 1;
 }
 
-static __always_inline void __raw_spin_lock(raw_spinlock_t *lock)
+static __always_inline void __ticket_spin_lock(raw_spinlock_t *lock)
 {
 	int inc = 0x00010000;
 	int tmp;
@@ -153,9 +151,7 @@ static __always_inline void __raw_spin_lock(raw_spinlock_t *lock)
 		     : "memory", "cc");
 }
 
-#define __raw_spin_lock_flags(lock, flags) __raw_spin_lock(lock)
-
-static __always_inline int __raw_spin_trylock(raw_spinlock_t *lock)
+static __always_inline int __ticket_spin_trylock(raw_spinlock_t *lock)
 {
 	int tmp;
 	int new;
@@ -177,7 +173,7 @@ static __always_inline int __raw_spin_trylock(raw_spinlock_t *lock)
 	return tmp;
 }
 
-static __always_inline void __raw_spin_unlock(raw_spinlock_t *lock)
+static __always_inline void __ticket_spin_unlock(raw_spinlock_t *lock)
 {
 	asm volatile(UNLOCK_LOCK_PREFIX "incw %0"
 		     : "+m" (lock->slock)
@@ -186,6 +182,98 @@ static __always_inline void __raw_spin_unlock(raw_spinlock_t *lock)
 }
 #endif
 
+#define __raw_spin_lock_flags(lock, flags) __raw_spin_lock(lock)
+
+#ifdef CONFIG_PARAVIRT
+/*
+ * Define virtualization-friendly old-style lock byte lock, for use in
+ * pv_lock_ops if desired.
+ *
+ * This differs from the pre-2.6.24 spinlock by always using xchgb
+ * rather than decb to take the lock; this allows it to use a
+ * zero-initialized lock structure.  It also maintains a 1-byte
+ * contention counter, so that we can implement
+ * __byte_spin_is_contended.
+ */
+struct __byte_spinlock {
+	s8 lock;
+	s8 spinners;
+};
+
+static inline int __byte_spin_is_locked(raw_spinlock_t *lock)
+{
+	struct __byte_spinlock *bl = (struct __byte_spinlock *)lock;
+	return bl->lock != 0;
+}
+
+static inline int __byte_spin_is_contended(raw_spinlock_t *lock)
+{
+	struct __byte_spinlock *bl = (struct __byte_spinlock *)lock;
+	return bl->spinners != 0;
+}
+
+static inline void __byte_spin_lock(raw_spinlock_t *lock)
+{
+	struct __byte_spinlock *bl = (struct __byte_spinlock *)lock;
+	s8 val = 1;
+
+	asm("1: xchgb %1, %0\n"
+	    "   test %1,%1\n"
+	    "   jz 3f\n"
+	    "   " LOCK_PREFIX "incb %2\n"
+	    "2: rep;nop\n"
+	    "   cmpb $1, %0\n"
+	    "   je 2b\n"
+	    "   " LOCK_PREFIX "decb %2\n"
+	    "   jmp 1b\n"
+	    "3:"
+	    : "+m" (bl->lock), "+q" (val), "+m" (bl->spinners): : "memory");
+}
+
+static inline int __byte_spin_trylock(raw_spinlock_t *lock)
+{
+	struct __byte_spinlock *bl = (struct __byte_spinlock *)lock;
+	u8 old = 1;
+
+	asm("xchgb %1,%0"
+	    : "+m" (bl->lock), "+q" (old) : : "memory");
+
+	return old == 0;
+}
+
+static inline void __byte_spin_unlock(raw_spinlock_t *lock)
+{
+	struct __byte_spinlock *bl = (struct __byte_spinlock *)lock;
+	smp_wmb();
+	bl->lock = 0;
+}
+#else  /* !CONFIG_PARAVIRT */
+static inline int __raw_spin_is_locked(raw_spinlock_t *lock)
+{
+	return __ticket_spin_is_locked(lock);
+}
+
+static inline int __raw_spin_is_contended(raw_spinlock_t *lock)
+{
+	return __ticket_spin_is_contended(lock);
+}
+
+static __always_inline void __raw_spin_lock(raw_spinlock_t *lock)
+{
+	__ticket_spin_lock(lock);
+}
+
+static __always_inline int __raw_spin_trylock(raw_spinlock_t *lock)
+{
+	return __ticket_spin_trylock(lock);
+}
+
+static __always_inline void __raw_spin_unlock(raw_spinlock_t *lock)
+{
+	__ticket_spin_unlock(lock);
+}
+#endif	/* CONFIG_PARAVIRT */
+
 static inline void __raw_spin_unlock_wait(raw_spinlock_t *lock)
 {
 	while (__raw_spin_is_locked(lock))
diff --git a/include/asm-x86/spinlock_types.h b/include/asm-x86/spinlock_types.h
index 9029cf78cf5..06c071c9eee 100644
--- a/include/asm-x86/spinlock_types.h
+++ b/include/asm-x86/spinlock_types.h
@@ -5,7 +5,7 @@
 # error "please don't include this file directly"
 #endif
 
-typedef struct {
+typedef struct raw_spinlock {
 	unsigned int slock;
 } raw_spinlock_t;
 
diff --git a/include/asm-x86/swiotlb.h b/include/asm-x86/swiotlb.h
index f5d9e74b1e4..c706a744263 100644
--- a/include/asm-x86/swiotlb.h
+++ b/include/asm-x86/swiotlb.h
@@ -45,12 +45,14 @@ extern int swiotlb_force;
 
 #ifdef CONFIG_SWIOTLB
 extern int swiotlb;
+extern void pci_swiotlb_init(void);
 #else
 #define swiotlb 0
+static inline void pci_swiotlb_init(void)
+{
+}
 #endif
 
-extern void pci_swiotlb_init(void);
-
 static inline void dma_mark_clean(void *addr, size_t size) {}
 
 #endif /* _ASM_SWIOTLB_H */
diff --git a/include/asm-x86/thread_info.h b/include/asm-x86/thread_info.h
index 895339d2bc0..0a8f27d31d0 100644
--- a/include/asm-x86/thread_info.h
+++ b/include/asm-x86/thread_info.h
@@ -75,9 +75,7 @@ struct thread_info {
 #define TIF_NEED_RESCHED	3	/* rescheduling necessary */
 #define TIF_SINGLESTEP		4	/* reenable singlestep on user return*/
 #define TIF_IRET		5	/* force IRET */
-#ifdef CONFIG_X86_32
 #define TIF_SYSCALL_EMU		6	/* syscall emulation active */
-#endif
 #define TIF_SYSCALL_AUDIT	7	/* syscall auditing active */
 #define TIF_SECCOMP		8	/* secure computing */
 #define TIF_MCE_NOTIFY		10	/* notify userspace of an MCE */
@@ -100,11 +98,7 @@ struct thread_info {
 #define _TIF_SINGLESTEP		(1 << TIF_SINGLESTEP)
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
 #define _TIF_IRET		(1 << TIF_IRET)
-#ifdef CONFIG_X86_32
 #define _TIF_SYSCALL_EMU	(1 << TIF_SYSCALL_EMU)
-#else
-#define _TIF_SYSCALL_EMU	0
-#endif
 #define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
 #define _TIF_SECCOMP		(1 << TIF_SECCOMP)
 #define _TIF_MCE_NOTIFY		(1 << TIF_MCE_NOTIFY)
@@ -121,18 +115,27 @@ struct thread_info {
 #define _TIF_DS_AREA_MSR	(1 << TIF_DS_AREA_MSR)
 #define _TIF_BTS_TRACE_TS	(1 << TIF_BTS_TRACE_TS)
 
+/* work to do in syscall_trace_enter() */
+#define _TIF_WORK_SYSCALL_ENTRY	\
+	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU | \
+	 _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | _TIF_SINGLESTEP)
+
+/* work to do in syscall_trace_leave() */
+#define _TIF_WORK_SYSCALL_EXIT	\
+	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SINGLESTEP)
+
 /* work to do on interrupt/exception return */
 #define _TIF_WORK_MASK							\
 	(0x0000FFFF &							\
-	 ~(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SINGLESTEP|	\
-	 _TIF_SECCOMP|_TIF_SYSCALL_EMU))
+	 ~(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|			\
+	   _TIF_SINGLESTEP|_TIF_SECCOMP|_TIF_SYSCALL_EMU))
 
 /* work to do on any return to user space */
 #define _TIF_ALLWORK_MASK (0x0000FFFF & ~_TIF_SECCOMP)
 
 /* Only used for 64 bit */
 #define _TIF_DO_NOTIFY_MASK						\
-	(_TIF_SIGPENDING|_TIF_SINGLESTEP|_TIF_MCE_NOTIFY|_TIF_HRTICK_RESCHED)
+	(_TIF_SIGPENDING|_TIF_MCE_NOTIFY|_TIF_HRTICK_RESCHED)
 
 /* flags to check in __switch_to() */
 #define _TIF_WORK_CTXSW							\
diff --git a/include/asm-x86/traps.h b/include/asm-x86/traps.h
new file mode 100644
index 00000000000..a4b65a71bd6
--- /dev/null
+++ b/include/asm-x86/traps.h
@@ -0,0 +1,66 @@
+#ifndef _ASM_X86_TRAPS_H
+#define _ASM_X86_TRAPS_H
+
+/* Common in X86_32 and X86_64 */
+asmlinkage void divide_error(void);
+asmlinkage void debug(void);
+asmlinkage void nmi(void);
+asmlinkage void int3(void);
+asmlinkage void overflow(void);
+asmlinkage void bounds(void);
+asmlinkage void invalid_op(void);
+asmlinkage void device_not_available(void);
+asmlinkage void coprocessor_segment_overrun(void);
+asmlinkage void invalid_TSS(void);
+asmlinkage void segment_not_present(void);
+asmlinkage void stack_segment(void);
+asmlinkage void general_protection(void);
+asmlinkage void page_fault(void);
+asmlinkage void coprocessor_error(void);
+asmlinkage void simd_coprocessor_error(void);
+asmlinkage void alignment_check(void);
+asmlinkage void spurious_interrupt_bug(void);
+#ifdef CONFIG_X86_MCE
+asmlinkage void machine_check(void);
+#endif /* CONFIG_X86_MCE */
+
+void do_divide_error(struct pt_regs *, long);
+void do_overflow(struct pt_regs *, long);
+void do_bounds(struct pt_regs *, long);
+void do_coprocessor_segment_overrun(struct pt_regs *, long);
+void do_invalid_TSS(struct pt_regs *, long);
+void do_segment_not_present(struct pt_regs *, long);
+void do_stack_segment(struct pt_regs *, long);
+void do_alignment_check(struct pt_regs *, long);
+void do_invalid_op(struct pt_regs *, long);
+void do_general_protection(struct pt_regs *, long);
+void do_nmi(struct pt_regs *, long);
+
+extern int panic_on_unrecovered_nmi;
+extern int kstack_depth_to_print;
+
+#ifdef CONFIG_X86_32
+
+void do_iret_error(struct pt_regs *, long);
+void do_int3(struct pt_regs *, long);
+void do_debug(struct pt_regs *, long);
+void math_error(void __user *);
+void do_coprocessor_error(struct pt_regs *, long);
+void do_simd_coprocessor_error(struct pt_regs *, long);
+void do_spurious_interrupt_bug(struct pt_regs *, long);
+unsigned long patch_espfix_desc(unsigned long, unsigned long);
+asmlinkage void math_emulate(long);
+
+#else /* CONFIG_X86_32 */
+
+asmlinkage void double_fault(void);
+
+asmlinkage void do_int3(struct pt_regs *, long);
+asmlinkage void do_stack_segment(struct pt_regs *, long);
+asmlinkage void do_debug(struct pt_regs *, unsigned long);
+asmlinkage void do_coprocessor_error(struct pt_regs *);
+asmlinkage void do_simd_coprocessor_error(struct pt_regs *);
+asmlinkage void do_spurious_interrupt_bug(struct pt_regs *);
+
+#endif /* CONFIG_X86_32 */
+#endif /* _ASM_X86_TRAPS_H */
diff --git a/include/asm-x86/vdso.h b/include/asm-x86/vdso.h
index 86e085e003d..8e18fb80f5e 100644
--- a/include/asm-x86/vdso.h
+++ b/include/asm-x86/vdso.h
@@ -36,4 +36,12 @@ extern const char VDSO32_PRELINK[];
 extern void __user __kernel_sigreturn;
 extern void __user __kernel_rt_sigreturn;
 
+/*
+ * These symbols are defined by vdso32.S to mark the bounds
+ * of the ELF DSO images included therein.
+ */
+extern const char vdso32_int80_start, vdso32_int80_end;
+extern const char vdso32_syscall_start, vdso32_syscall_end;
+extern const char vdso32_sysenter_start, vdso32_sysenter_end;
+
 #endif	/* asm-x86/vdso.h */
diff --git a/include/asm-x86/xen/events.h b/include/asm-x86/xen/events.h
index f8d57ea1f05..8ded7472002 100644
--- a/include/asm-x86/xen/events.h
+++ b/include/asm-x86/xen/events.h
@@ -5,6 +5,7 @@ enum ipi_vector {
 	XEN_RESCHEDULE_VECTOR,
 	XEN_CALL_FUNCTION_VECTOR,
 	XEN_CALL_FUNCTION_SINGLE_VECTOR,
+	XEN_SPIN_UNLOCK_VECTOR,
 
 	XEN_NR_IPIS,
 };
diff --git a/include/asm-x86/xen/hypercall.h b/include/asm-x86/xen/hypercall.h
index 2a4f9b41d68..91cb7fd5c12 100644
--- a/include/asm-x86/xen/hypercall.h
+++ b/include/asm-x86/xen/hypercall.h
@@ -40,83 +40,157 @@
 #include <xen/interface/sched.h>
 #include <xen/interface/physdev.h>
 
+/*
+ * The hypercall asms have to meet several constraints:
+ * - Work on 32- and 64-bit.
+ *    The two architectures put their arguments in different sets of
+ *    registers.
+ *
+ * - Work around asm syntax quirks
+ *    It isn't possible to specify one of the rNN registers in a
+ *    constraint, so we use explicit register variables to get the
+ *    args into the right place.
+ *
+ * - Mark all registers as potentially clobbered
+ *    Even unused parameters can be clobbered by the hypervisor, so we
+ *    need to make sure gcc knows it.
+ *
+ * - Avoid compiler bugs.
+ *    This is the tricky part.  Because x86_32 has such a constrained
+ *    register set, gcc versions below 4.3 have trouble generating
+ *    code when all the arg registers and memory are trashed by the
+ *    asm.  There are syntactically simpler ways of achieving the
+ *    semantics below, but they cause the compiler to crash.
+ *
+ *    The only combination I found which works is:
+ *     - assign the __argX variables first
+ *     - list all actually used parameters as "+r" (__argX)
+ *     - clobber the rest
+ *
+ * The result certainly isn't pretty, and it really shows up cpp's
+ * weakness as as macro language.  Sorry.  (But let's just give thanks
+ * there aren't more than 5 arguments...)
+ */
+
 extern struct { char _entry[32]; } hypercall_page[];
 
+#define __HYPERCALL		"call hypercall_page+%c[offset]"
+#define __HYPERCALL_ENTRY(x)						\
+	[offset] "i" (__HYPERVISOR_##x * sizeof(hypercall_page[0]))
+
+#ifdef CONFIG_X86_32
+#define __HYPERCALL_RETREG	"eax"
+#define __HYPERCALL_ARG1REG	"ebx"
+#define __HYPERCALL_ARG2REG	"ecx"
+#define __HYPERCALL_ARG3REG	"edx"
+#define __HYPERCALL_ARG4REG	"esi"
+#define __HYPERCALL_ARG5REG	"edi"
+#else
+#define __HYPERCALL_RETREG	"rax"
+#define __HYPERCALL_ARG1REG	"rdi"
+#define __HYPERCALL_ARG2REG	"rsi"
+#define __HYPERCALL_ARG3REG	"rdx"
+#define __HYPERCALL_ARG4REG	"r10"
+#define __HYPERCALL_ARG5REG	"r8"
+#endif
+
+#define __HYPERCALL_DECLS						\
+	register unsigned long __res  asm(__HYPERCALL_RETREG);		\
+	register unsigned long __arg1 asm(__HYPERCALL_ARG1REG) = __arg1; \
+	register unsigned long __arg2 asm(__HYPERCALL_ARG2REG) = __arg2; \
+	register unsigned long __arg3 asm(__HYPERCALL_ARG3REG) = __arg3; \
+	register unsigned long __arg4 asm(__HYPERCALL_ARG4REG) = __arg4; \
+	register unsigned long __arg5 asm(__HYPERCALL_ARG5REG) = __arg5;
+
+#define __HYPERCALL_0PARAM	"=r" (__res)
+#define __HYPERCALL_1PARAM	__HYPERCALL_0PARAM, "+r" (__arg1)
+#define __HYPERCALL_2PARAM	__HYPERCALL_1PARAM, "+r" (__arg2)
+#define __HYPERCALL_3PARAM	__HYPERCALL_2PARAM, "+r" (__arg3)
+#define __HYPERCALL_4PARAM	__HYPERCALL_3PARAM, "+r" (__arg4)
+#define __HYPERCALL_5PARAM	__HYPERCALL_4PARAM, "+r" (__arg5)
+
+#define __HYPERCALL_0ARG()
+#define __HYPERCALL_1ARG(a1)						\
+	__HYPERCALL_0ARG()		__arg1 = (unsigned long)(a1);
+#define __HYPERCALL_2ARG(a1,a2)						\
+	__HYPERCALL_1ARG(a1)		__arg2 = (unsigned long)(a2);
+#define __HYPERCALL_3ARG(a1,a2,a3)					\
+	__HYPERCALL_2ARG(a1,a2)		__arg3 = (unsigned long)(a3);
+#define __HYPERCALL_4ARG(a1,a2,a3,a4)					\
+	__HYPERCALL_3ARG(a1,a2,a3)	__arg4 = (unsigned long)(a4);
+#define __HYPERCALL_5ARG(a1,a2,a3,a4,a5)				\
+	__HYPERCALL_4ARG(a1,a2,a3,a4)	__arg5 = (unsigned long)(a5);
+
+#define __HYPERCALL_CLOBBER5	"memory"
+#define __HYPERCALL_CLOBBER4	__HYPERCALL_CLOBBER5, __HYPERCALL_ARG5REG
+#define __HYPERCALL_CLOBBER3	__HYPERCALL_CLOBBER4, __HYPERCALL_ARG4REG
+#define __HYPERCALL_CLOBBER2	__HYPERCALL_CLOBBER3, __HYPERCALL_ARG3REG
+#define __HYPERCALL_CLOBBER1	__HYPERCALL_CLOBBER2, __HYPERCALL_ARG2REG
+#define __HYPERCALL_CLOBBER0	__HYPERCALL_CLOBBER1, __HYPERCALL_ARG1REG
+
 #define _hypercall0(type, name)						\
 ({									\
-	long __res;							\
-	asm volatile (							\
-		"call %[call]"						\
-		: "=a" (__res)						\
-		: [call] "m" (hypercall_page[__HYPERVISOR_##name])	\
-		: "memory" );						\
+	__HYPERCALL_DECLS;						\
+	__HYPERCALL_0ARG();						\
+	asm volatile (__HYPERCALL					\
+		      : __HYPERCALL_0PARAM				\
+		      : __HYPERCALL_ENTRY(name)				\
+		      : __HYPERCALL_CLOBBER0);				\
 	(type)__res;							\
 })
 
 #define _hypercall1(type, name, a1)					\
 ({									\
-	long __res, __ign1;						\
-	asm volatile (							\
-		"call %[call]"						\
-		: "=a" (__res), "=b" (__ign1)				\
-		: "1" ((long)(a1)),					\
-		  [call] "m" (hypercall_page[__HYPERVISOR_##name])	\
-		: "memory" );						\
+	__HYPERCALL_DECLS;						\
+	__HYPERCALL_1ARG(a1);						\
+	asm volatile (__HYPERCALL					\
+		      : __HYPERCALL_1PARAM				\
+		      : __HYPERCALL_ENTRY(name)				\
+		      : __HYPERCALL_CLOBBER1);				\
 	(type)__res;							\
 })
 
 #define _hypercall2(type, name, a1, a2)					\
 ({									\
-	long __res, __ign1, __ign2;					\
-	asm volatile (							\
-		"call %[call]"						\
-		: "=a" (__res), "=b" (__ign1), "=c" (__ign2)		\
-		: "1" ((long)(a1)), "2" ((long)(a2)),			\
-		  [call] "m" (hypercall_page[__HYPERVISOR_##name])	\
-		: "memory" );						\
+	__HYPERCALL_DECLS;						\
+	__HYPERCALL_2ARG(a1, a2);					\
+	asm volatile (__HYPERCALL					\
+		      : __HYPERCALL_2PARAM				\
+		      : __HYPERCALL_ENTRY(name)				\
+		      : __HYPERCALL_CLOBBER2);				\
 	(type)__res;							\
 })
 
 #define _hypercall3(type, name, a1, a2, a3)				\
 ({									\
-	long __res, __ign1, __ign2, __ign3;				\
-	asm volatile (							\
-		"call %[call]"						\
-		: "=a" (__res), "=b" (__ign1), "=c" (__ign2),		\
-		"=d" (__ign3)						\
-		: "1" ((long)(a1)), "2" ((long)(a2)),			\
-		  "3" ((long)(a3)),					\
-		  [call] "m" (hypercall_page[__HYPERVISOR_##name])	\
-		: "memory" );						\
+	__HYPERCALL_DECLS;						\
+	__HYPERCALL_3ARG(a1, a2, a3);					\
+	asm volatile (__HYPERCALL					\
+		      : __HYPERCALL_3PARAM				\
+		      : __HYPERCALL_ENTRY(name)				\
+		      : __HYPERCALL_CLOBBER3);				\
 	(type)__res;							\
 })
 
 #define _hypercall4(type, name, a1, a2, a3, a4)				\
 ({									\
-	long __res, __ign1, __ign2, __ign3, __ign4;			\
-	asm volatile (							\
-		"call %[call]"						\
-		: "=a" (__res), "=b" (__ign1), "=c" (__ign2),		\
-		"=d" (__ign3), "=S" (__ign4)				\
-		: "1" ((long)(a1)), "2" ((long)(a2)),			\
-		  "3" ((long)(a3)), "4" ((long)(a4)),			\
-		  [call] "m" (hypercall_page[__HYPERVISOR_##name])	\
-		: "memory" );						\
+	__HYPERCALL_DECLS;						\
+	__HYPERCALL_4ARG(a1, a2, a3, a4);				\
+	asm volatile (__HYPERCALL					\
+		      : __HYPERCALL_4PARAM				\
+		      : __HYPERCALL_ENTRY(name)				\
+		      : __HYPERCALL_CLOBBER4);				\
 	(type)__res;							\
 })
 
 #define _hypercall5(type, name, a1, a2, a3, a4, a5)			\
 ({									\
-	long __res, __ign1, __ign2, __ign3, __ign4, __ign5;		\
-	asm volatile (							\
-		"call %[call]"						\
-		: "=a" (__res), "=b" (__ign1), "=c" (__ign2),		\
-		"=d" (__ign3), "=S" (__ign4), "=D" (__ign5)		\
-		: "1" ((long)(a1)), "2" ((long)(a2)),			\
-		  "3" ((long)(a3)), "4" ((long)(a4)),			\
-		  "5" ((long)(a5)),					\
-		  [call] "m" (hypercall_page[__HYPERVISOR_##name])	\
-		: "memory" );						\
+	__HYPERCALL_DECLS;						\
+	__HYPERCALL_5ARG(a1, a2, a3, a4, a5);				\
+	asm volatile (__HYPERCALL					\
+		      : __HYPERCALL_5PARAM				\
+		      : __HYPERCALL_ENTRY(name)				\
+		      : __HYPERCALL_CLOBBER5);				\
 	(type)__res;							\
 })
 
@@ -152,6 +226,7 @@ HYPERVISOR_stack_switch(unsigned long ss, unsigned long esp)
 	return _hypercall2(int, stack_switch, ss, esp);
 }
 
+#ifdef CONFIG_X86_32
 static inline int
 HYPERVISOR_set_callbacks(unsigned long event_selector,
 			 unsigned long event_address,
@@ -162,6 +237,17 @@ HYPERVISOR_set_callbacks(unsigned long event_selector,
 			   event_selector, event_address,
 			   failsafe_selector, failsafe_address);
 }
+#else  /* CONFIG_X86_64 */
+static inline int
+HYPERVISOR_set_callbacks(unsigned long event_address,
+			unsigned long failsafe_address,
+			unsigned long syscall_address)
+{
+	return _hypercall3(int, set_callbacks,
+			   event_address, failsafe_address,
+			   syscall_address);
+}
+#endif  /* CONFIG_X86_{32,64} */
 
 static inline int
 HYPERVISOR_callback_op(int cmd, void *arg)
@@ -223,12 +309,12 @@ static inline int
 HYPERVISOR_update_va_mapping(unsigned long va, pte_t new_val,
 			     unsigned long flags)
 {
-	unsigned long pte_hi = 0;
-#ifdef CONFIG_X86_PAE
-	pte_hi = new_val.pte_high;
-#endif
-	return _hypercall4(int, update_va_mapping, va,
-			   new_val.pte_low, pte_hi, flags);
+	if (sizeof(new_val) == sizeof(long))
+		return _hypercall3(int, update_va_mapping, va,
+				   new_val.pte, flags);
+	else
+		return _hypercall4(int, update_va_mapping, va,
+				   new_val.pte, new_val.pte >> 32, flags);
 }
 
 static inline int
@@ -281,12 +367,13 @@ static inline int
 HYPERVISOR_update_va_mapping_otherdomain(unsigned long va, pte_t new_val,
 					 unsigned long flags, domid_t domid)
 {
-	unsigned long pte_hi = 0;
-#ifdef CONFIG_X86_PAE
-	pte_hi = new_val.pte_high;
-#endif
-	return _hypercall5(int, update_va_mapping_otherdomain, va,
-			   new_val.pte_low, pte_hi, flags, domid);
+	if (sizeof(new_val) == sizeof(long))
+		return _hypercall4(int, update_va_mapping_otherdomain, va,
+				   new_val.pte, flags, domid);
+	else
+		return _hypercall5(int, update_va_mapping_otherdomain, va,
+				   new_val.pte, new_val.pte >> 32,
+				   flags, domid);
 }
 
 static inline int
@@ -301,6 +388,14 @@ HYPERVISOR_vcpu_op(int cmd, int vcpuid, void *extra_args)
 	return _hypercall3(int, vcpu_op, cmd, vcpuid, extra_args);
 }
 
+#ifdef CONFIG_X86_64
+static inline int
+HYPERVISOR_set_segment_base(int reg, unsigned long value)
+{
+	return _hypercall2(int, set_segment_base, reg, value);
+}
+#endif
+
 static inline int
 HYPERVISOR_suspend(unsigned long srec)
 {
@@ -327,14 +422,14 @@ MULTI_update_va_mapping(struct multicall_entry *mcl, unsigned long va,
 {
 	mcl->op = __HYPERVISOR_update_va_mapping;
 	mcl->args[0] = va;
-#ifdef CONFIG_X86_PAE
-	mcl->args[1] = new_val.pte_low;
-	mcl->args[2] = new_val.pte_high;
-#else
-	mcl->args[1] = new_val.pte_low;
-	mcl->args[2] = 0;
-#endif
-	mcl->args[3] = flags;
+	if (sizeof(new_val) == sizeof(long)) {
+		mcl->args[1] = new_val.pte;
+		mcl->args[2] = flags;
+	} else {
+		mcl->args[1] = new_val.pte;
+		mcl->args[2] = new_val.pte >> 32;
+		mcl->args[3] = flags;
+	}
 }
 
 static inline void
@@ -354,15 +449,16 @@ MULTI_update_va_mapping_otherdomain(struct multicall_entry *mcl, unsigned long v
 {
 	mcl->op = __HYPERVISOR_update_va_mapping_otherdomain;
 	mcl->args[0] = va;
-#ifdef CONFIG_X86_PAE
-	mcl->args[1] = new_val.pte_low;
-	mcl->args[2] = new_val.pte_high;
-#else
-	mcl->args[1] = new_val.pte_low;
-	mcl->args[2] = 0;
-#endif
-	mcl->args[3] = flags;
-	mcl->args[4] = domid;
+	if (sizeof(new_val) == sizeof(long)) {
+		mcl->args[1] = new_val.pte;
+		mcl->args[2] = flags;
+		mcl->args[3] = domid;
+	} else {
+		mcl->args[1] = new_val.pte;
+		mcl->args[2] = new_val.pte >> 32;
+		mcl->args[3] = flags;
+		mcl->args[4] = domid;
+	}
 }
 
 static inline void
@@ -370,10 +466,15 @@ MULTI_update_descriptor(struct multicall_entry *mcl, u64 maddr,
 			struct desc_struct desc)
 {
 	mcl->op = __HYPERVISOR_update_descriptor;
-	mcl->args[0] = maddr;
-	mcl->args[1] = maddr >> 32;
-	mcl->args[2] = desc.a;
-	mcl->args[3] = desc.b;
+	if (sizeof(maddr) == sizeof(long)) {
+		mcl->args[0] = maddr;
+		mcl->args[1] = *(unsigned long *)&desc;
+	} else {
+		mcl->args[0] = maddr;
+		mcl->args[1] = maddr >> 32;
+		mcl->args[2] = desc.a;
+		mcl->args[3] = desc.b;
+	}
 }
 
 static inline void
diff --git a/include/asm-x86/xen/interface.h b/include/asm-x86/xen/interface.h
index 6227000a1e8..9d810f2538a 100644
--- a/include/asm-x86/xen/interface.h
+++ b/include/asm-x86/xen/interface.h
@@ -1,13 +1,13 @@
 /******************************************************************************
  * arch-x86_32.h
  *
- * Guest OS interface to x86 32-bit Xen.
+ * Guest OS interface to x86 Xen.
  *
  * Copyright (c) 2004, K A Fraser
  */
 
-#ifndef __XEN_PUBLIC_ARCH_X86_32_H__
-#define __XEN_PUBLIC_ARCH_X86_32_H__
+#ifndef __ASM_X86_XEN_INTERFACE_H
+#define __ASM_X86_XEN_INTERFACE_H
 
 #ifdef __XEN__
 #define __DEFINE_GUEST_HANDLE(name, type) \
@@ -57,6 +57,17 @@ DEFINE_GUEST_HANDLE(long);
 DEFINE_GUEST_HANDLE(void);
 #endif
 
+#ifndef HYPERVISOR_VIRT_START
+#define HYPERVISOR_VIRT_START mk_unsigned_long(__HYPERVISOR_VIRT_START)
+#endif
+
+#ifndef machine_to_phys_mapping
+#define machine_to_phys_mapping ((unsigned long *)HYPERVISOR_VIRT_START)
+#endif
+
+/* Maximum number of virtual CPUs in multi-processor guests. */
+#define MAX_VIRT_CPUS 32
+
 /*
  * SEGMENT DESCRIPTOR TABLES
  */
@@ -71,58 +82,21 @@ DEFINE_GUEST_HANDLE(void);
 #define FIRST_RESERVED_GDT_ENTRY (FIRST_RESERVED_GDT_BYTE / 8)
 
 /*
- * These flat segments are in the Xen-private section of every GDT. Since these
- * are also present in the initial GDT, many OSes will be able to avoid
- * installing their own GDT.
- */
-#define FLAT_RING1_CS 0xe019    /* GDT index 259 */
-#define FLAT_RING1_DS 0xe021    /* GDT index 260 */
-#define FLAT_RING1_SS 0xe021    /* GDT index 260 */
-#define FLAT_RING3_CS 0xe02b    /* GDT index 261 */
-#define FLAT_RING3_DS 0xe033    /* GDT index 262 */
-#define FLAT_RING3_SS 0xe033    /* GDT index 262 */
-
-#define FLAT_KERNEL_CS FLAT_RING1_CS
-#define FLAT_KERNEL_DS FLAT_RING1_DS
-#define FLAT_KERNEL_SS FLAT_RING1_SS
-#define FLAT_USER_CS    FLAT_RING3_CS
-#define FLAT_USER_DS    FLAT_RING3_DS
-#define FLAT_USER_SS    FLAT_RING3_SS
-
-/* And the trap vector is... */
-#define TRAP_INSTR "int $0x82"
-
-/*
- * Virtual addresses beyond this are not modifiable by guest OSes. The
- * machine->physical mapping table starts at this address, read-only.
- */
-#ifdef CONFIG_X86_PAE
-#define __HYPERVISOR_VIRT_START 0xF5800000
-#else
-#define __HYPERVISOR_VIRT_START 0xFC000000
-#endif
-
-#ifndef HYPERVISOR_VIRT_START
-#define HYPERVISOR_VIRT_START mk_unsigned_long(__HYPERVISOR_VIRT_START)
-#endif
-
-#ifndef machine_to_phys_mapping
-#define machine_to_phys_mapping ((unsigned long *)HYPERVISOR_VIRT_START)
-#endif
-
-/* Maximum number of virtual CPUs in multi-processor guests. */
-#define MAX_VIRT_CPUS 32
-
-#ifndef __ASSEMBLY__
-
-/*
  * Send an array of these to HYPERVISOR_set_trap_table()
+ * The privilege level specifies which modes may enter a trap via a software
+ * interrupt. On x86/64, since rings 1 and 2 are unavailable, we allocate
+ * privilege levels as follows:
+ *  Level == 0: Noone may enter
+ *  Level == 1: Kernel may enter
+ *  Level == 2: Kernel may enter
+ *  Level == 3: Everyone may enter
  */
 #define TI_GET_DPL(_ti)		((_ti)->flags & 3)
 #define TI_GET_IF(_ti)		((_ti)->flags & 4)
 #define TI_SET_DPL(_ti, _dpl)	((_ti)->flags |= (_dpl))
 #define TI_SET_IF(_ti, _if)	((_ti)->flags |= ((!!(_if))<<2))
 
+#ifndef __ASSEMBLY__
 struct trap_info {
     uint8_t       vector;  /* exception vector                              */
     uint8_t       flags;   /* 0-3: privilege level; 4: clear event enable?  */
@@ -131,32 +105,21 @@ struct trap_info {
 };
 DEFINE_GUEST_HANDLE_STRUCT(trap_info);
 
-struct cpu_user_regs {
-    uint32_t ebx;
-    uint32_t ecx;
-    uint32_t edx;
-    uint32_t esi;
-    uint32_t edi;
-    uint32_t ebp;
-    uint32_t eax;
-    uint16_t error_code;    /* private */
-    uint16_t entry_vector;  /* private */
-    uint32_t eip;
-    uint16_t cs;
-    uint8_t  saved_upcall_mask;
-    uint8_t  _pad0;
-    uint32_t eflags;        /* eflags.IF == !saved_upcall_mask */
-    uint32_t esp;
-    uint16_t ss, _pad1;
-    uint16_t es, _pad2;
-    uint16_t ds, _pad3;
-    uint16_t fs, _pad4;
-    uint16_t gs, _pad5;
+struct arch_shared_info {
+    unsigned long max_pfn;                  /* max pfn that appears in table */
+    /* Frame containing list of mfns containing list of mfns containing p2m. */
+    unsigned long pfn_to_mfn_frame_list_list;
+    unsigned long nmi_reason;
 };
-DEFINE_GUEST_HANDLE_STRUCT(cpu_user_regs);
+#endif	/* !__ASSEMBLY__ */
 
-typedef uint64_t tsc_timestamp_t; /* RDTSC timestamp */
+#ifdef CONFIG_X86_32
+#include "interface_32.h"
+#else
+#include "interface_64.h"
+#endif
 
+#ifndef __ASSEMBLY__
 /*
  * The following is all CPU context. Note that the fpu_ctxt block is filled
  * in by FXSAVE if the CPU has feature FXSR; otherwise FSAVE is used.
@@ -173,33 +136,29 @@ struct vcpu_guest_context {
     unsigned long ldt_base, ldt_ents;       /* LDT (linear address, # ents) */
     unsigned long gdt_frames[16], gdt_ents; /* GDT (machine frames, # ents) */
     unsigned long kernel_ss, kernel_sp;     /* Virtual TSS (only SS1/SP1)   */
+    /* NB. User pagetable on x86/64 is placed in ctrlreg[1]. */
     unsigned long ctrlreg[8];               /* CR0-CR7 (control registers)  */
     unsigned long debugreg[8];              /* DB0-DB7 (debug registers)    */
+#ifdef __i386__
     unsigned long event_callback_cs;        /* CS:EIP of event callback     */
     unsigned long event_callback_eip;
     unsigned long failsafe_callback_cs;     /* CS:EIP of failsafe callback  */
     unsigned long failsafe_callback_eip;
+#else
+    unsigned long event_callback_eip;
+    unsigned long failsafe_callback_eip;
+    unsigned long syscall_callback_eip;
+#endif
     unsigned long vm_assist;                /* VMASST_TYPE_* bitmap */
+#ifdef __x86_64__
+    /* Segment base addresses. */
+    uint64_t      fs_base;
+    uint64_t      gs_base_kernel;
+    uint64_t      gs_base_user;
+#endif
 };
 DEFINE_GUEST_HANDLE_STRUCT(vcpu_guest_context);
-
-struct arch_shared_info {
-    unsigned long max_pfn;                  /* max pfn that appears in table */
-    /* Frame containing list of mfns containing list of mfns containing p2m. */
-    unsigned long pfn_to_mfn_frame_list_list;
-    unsigned long nmi_reason;
-};
-
-struct arch_vcpu_info {
-    unsigned long cr2;
-    unsigned long pad[5]; /* sizeof(struct vcpu_info) == 64 */
-};
-
-struct xen_callback {
-	unsigned long cs;
-	unsigned long eip;
-};
-#endif /* !__ASSEMBLY__ */
+#endif	/* !__ASSEMBLY__ */
 
 /*
  * Prefix forces emulation of some non-trapping instructions.
@@ -213,4 +172,4 @@ struct xen_callback {
 #define XEN_CPUID          XEN_EMULATE_PREFIX "cpuid"
 #endif
 
-#endif
+#endif	/* __ASM_X86_XEN_INTERFACE_H */
diff --git a/include/asm-x86/xen/interface_32.h b/include/asm-x86/xen/interface_32.h
new file mode 100644
index 00000000000..d8ac41d5db8
--- /dev/null
+++ b/include/asm-x86/xen/interface_32.h
@@ -0,0 +1,97 @@
+/******************************************************************************
+ * arch-x86_32.h
+ *
+ * Guest OS interface to x86 32-bit Xen.
+ *
+ * Copyright (c) 2004, K A Fraser
+ */
+
+#ifndef __ASM_X86_XEN_INTERFACE_32_H
+#define __ASM_X86_XEN_INTERFACE_32_H
+
+
+/*
+ * These flat segments are in the Xen-private section of every GDT. Since these
+ * are also present in the initial GDT, many OSes will be able to avoid
+ * installing their own GDT.
+ */
+#define FLAT_RING1_CS 0xe019    /* GDT index 259 */
+#define FLAT_RING1_DS 0xe021    /* GDT index 260 */
+#define FLAT_RING1_SS 0xe021    /* GDT index 260 */
+#define FLAT_RING3_CS 0xe02b    /* GDT index 261 */
+#define FLAT_RING3_DS 0xe033    /* GDT index 262 */
+#define FLAT_RING3_SS 0xe033    /* GDT index 262 */
+
+#define FLAT_KERNEL_CS FLAT_RING1_CS
+#define FLAT_KERNEL_DS FLAT_RING1_DS
+#define FLAT_KERNEL_SS FLAT_RING1_SS
+#define FLAT_USER_CS    FLAT_RING3_CS
+#define FLAT_USER_DS    FLAT_RING3_DS
+#define FLAT_USER_SS    FLAT_RING3_SS
+
+/* And the trap vector is... */
+#define TRAP_INSTR "int $0x82"
+
+/*
+ * Virtual addresses beyond this are not modifiable by guest OSes. The
+ * machine->physical mapping table starts at this address, read-only.
+ */
+#define __HYPERVISOR_VIRT_START 0xF5800000
+
+#ifndef __ASSEMBLY__
+
+struct cpu_user_regs {
+    uint32_t ebx;
+    uint32_t ecx;
+    uint32_t edx;
+    uint32_t esi;
+    uint32_t edi;
+    uint32_t ebp;
+    uint32_t eax;
+    uint16_t error_code;    /* private */
+    uint16_t entry_vector;  /* private */
+    uint32_t eip;
+    uint16_t cs;
+    uint8_t  saved_upcall_mask;
+    uint8_t  _pad0;
+    uint32_t eflags;        /* eflags.IF == !saved_upcall_mask */
+    uint32_t esp;
+    uint16_t ss, _pad1;
+    uint16_t es, _pad2;
+    uint16_t ds, _pad3;
+    uint16_t fs, _pad4;
+    uint16_t gs, _pad5;
+};
+DEFINE_GUEST_HANDLE_STRUCT(cpu_user_regs);
+
+typedef uint64_t tsc_timestamp_t; /* RDTSC timestamp */
+
+struct arch_vcpu_info {
+    unsigned long cr2;
+    unsigned long pad[5]; /* sizeof(struct vcpu_info) == 64 */
+};
+
+struct xen_callback {
+	unsigned long cs;
+	unsigned long eip;
+};
+typedef struct xen_callback xen_callback_t;
+
+#define XEN_CALLBACK(__cs, __eip)				\
+	((struct xen_callback){ .cs = (__cs), .eip = (unsigned long)(__eip) })
+#endif /* !__ASSEMBLY__ */
+
+
+/*
+ * Page-directory addresses above 4GB do not fit into architectural %cr3.
+ * When accessing %cr3, or equivalent field in vcpu_guest_context, guests
+ * must use the following accessor macros to pack/unpack valid MFNs.
+ *
+ * Note that Xen is using the fact that the pagetable base is always
+ * page-aligned, and putting the 12 MSB of the address into the 12 LSB
+ * of cr3.
+ */
+#define xen_pfn_to_cr3(pfn) (((unsigned)(pfn) << 12) | ((unsigned)(pfn) >> 20))
+#define xen_cr3_to_pfn(cr3) (((unsigned)(cr3) >> 12) | ((unsigned)(cr3) << 20))
+
+#endif	/* __ASM_X86_XEN_INTERFACE_32_H */
diff --git a/include/asm-x86/xen/interface_64.h b/include/asm-x86/xen/interface_64.h
new file mode 100644
index 00000000000..842266ce96e
--- /dev/null
+++ b/include/asm-x86/xen/interface_64.h
@@ -0,0 +1,159 @@
+#ifndef __ASM_X86_XEN_INTERFACE_64_H
+#define __ASM_X86_XEN_INTERFACE_64_H
+
+/*
+ * 64-bit segment selectors
+ * These flat segments are in the Xen-private section of every GDT. Since these
+ * are also present in the initial GDT, many OSes will be able to avoid
+ * installing their own GDT.
+ */
+
+#define FLAT_RING3_CS32 0xe023  /* GDT index 260 */
+#define FLAT_RING3_CS64 0xe033  /* GDT index 261 */
+#define FLAT_RING3_DS32 0xe02b  /* GDT index 262 */
+#define FLAT_RING3_DS64 0x0000  /* NULL selector */
+#define FLAT_RING3_SS32 0xe02b  /* GDT index 262 */
+#define FLAT_RING3_SS64 0xe02b  /* GDT index 262 */
+
+#define FLAT_KERNEL_DS64 FLAT_RING3_DS64
+#define FLAT_KERNEL_DS32 FLAT_RING3_DS32
+#define FLAT_KERNEL_DS   FLAT_KERNEL_DS64
+#define FLAT_KERNEL_CS64 FLAT_RING3_CS64
+#define FLAT_KERNEL_CS32 FLAT_RING3_CS32
+#define FLAT_KERNEL_CS   FLAT_KERNEL_CS64
+#define FLAT_KERNEL_SS64 FLAT_RING3_SS64
+#define FLAT_KERNEL_SS32 FLAT_RING3_SS32
+#define FLAT_KERNEL_SS   FLAT_KERNEL_SS64
+
+#define FLAT_USER_DS64 FLAT_RING3_DS64
+#define FLAT_USER_DS32 FLAT_RING3_DS32
+#define FLAT_USER_DS   FLAT_USER_DS64
+#define FLAT_USER_CS64 FLAT_RING3_CS64
+#define FLAT_USER_CS32 FLAT_RING3_CS32
+#define FLAT_USER_CS   FLAT_USER_CS64
+#define FLAT_USER_SS64 FLAT_RING3_SS64
+#define FLAT_USER_SS32 FLAT_RING3_SS32
+#define FLAT_USER_SS   FLAT_USER_SS64
+
+#define __HYPERVISOR_VIRT_START 0xFFFF800000000000
+#define __HYPERVISOR_VIRT_END   0xFFFF880000000000
+#define __MACH2PHYS_VIRT_START  0xFFFF800000000000
+#define __MACH2PHYS_VIRT_END    0xFFFF804000000000
+
+#ifndef HYPERVISOR_VIRT_START
+#define HYPERVISOR_VIRT_START mk_unsigned_long(__HYPERVISOR_VIRT_START)
+#define HYPERVISOR_VIRT_END   mk_unsigned_long(__HYPERVISOR_VIRT_END)
+#endif
+
+#define MACH2PHYS_VIRT_START  mk_unsigned_long(__MACH2PHYS_VIRT_START)
+#define MACH2PHYS_VIRT_END    mk_unsigned_long(__MACH2PHYS_VIRT_END)
+#define MACH2PHYS_NR_ENTRIES  ((MACH2PHYS_VIRT_END-MACH2PHYS_VIRT_START)>>3)
+#ifndef machine_to_phys_mapping
+#define machine_to_phys_mapping ((unsigned long *)HYPERVISOR_VIRT_START)
+#endif
+
+/*
+ * int HYPERVISOR_set_segment_base(unsigned int which, unsigned long base)
+ *  @which == SEGBASE_*  ;  @base == 64-bit base address
+ * Returns 0 on success.
+ */
+#define SEGBASE_FS          0
+#define SEGBASE_GS_USER     1
+#define SEGBASE_GS_KERNEL   2
+#define SEGBASE_GS_USER_SEL 3 /* Set user %gs specified in base[15:0] */
+
+/*
+ * int HYPERVISOR_iret(void)
+ * All arguments are on the kernel stack, in the following format.
+ * Never returns if successful. Current kernel context is lost.
+ * The saved CS is mapped as follows:
+ *   RING0 -> RING3 kernel mode.
+ *   RING1 -> RING3 kernel mode.
+ *   RING2 -> RING3 kernel mode.
+ *   RING3 -> RING3 user mode.
+ * However RING0 indicates that the guest kernel should return to iteself
+ * directly with
+ *      orb   $3,1*8(%rsp)
+ *      iretq
+ * If flags contains VGCF_in_syscall:
+ *   Restore RAX, RIP, RFLAGS, RSP.
+ *   Discard R11, RCX, CS, SS.
+ * Otherwise:
+ *   Restore RAX, R11, RCX, CS:RIP, RFLAGS, SS:RSP.
+ * All other registers are saved on hypercall entry and restored to user.
+ */
+/* Guest exited in SYSCALL context? Return to guest with SYSRET? */
+#define _VGCF_in_syscall 8
+#define VGCF_in_syscall  (1<<_VGCF_in_syscall)
+#define VGCF_IN_SYSCALL  VGCF_in_syscall
+
+#ifndef __ASSEMBLY__
+
+struct iret_context {
+    /* Top of stack (%rsp at point of hypercall). */
+    uint64_t rax, r11, rcx, flags, rip, cs, rflags, rsp, ss;
+    /* Bottom of iret stack frame. */
+};
+
+#if defined(__GNUC__) && !defined(__STRICT_ANSI__)
+/* Anonymous union includes both 32- and 64-bit names (e.g., eax/rax). */
+#define __DECL_REG(name) union { \
+    uint64_t r ## name, e ## name; \
+    uint32_t _e ## name; \
+}
+#else
+/* Non-gcc sources must always use the proper 64-bit name (e.g., rax). */
+#define __DECL_REG(name) uint64_t r ## name
+#endif
+
+struct cpu_user_regs {
+    uint64_t r15;
+    uint64_t r14;
+    uint64_t r13;
+    uint64_t r12;
+    __DECL_REG(bp);
+    __DECL_REG(bx);
+    uint64_t r11;
+    uint64_t r10;
+    uint64_t r9;
+    uint64_t r8;
+    __DECL_REG(ax);
+    __DECL_REG(cx);
+    __DECL_REG(dx);
+    __DECL_REG(si);
+    __DECL_REG(di);
+    uint32_t error_code;    /* private */
+    uint32_t entry_vector;  /* private */
+    __DECL_REG(ip);
+    uint16_t cs, _pad0[1];
+    uint8_t  saved_upcall_mask;
+    uint8_t  _pad1[3];
+    __DECL_REG(flags);      /* rflags.IF == !saved_upcall_mask */
+    __DECL_REG(sp);
+    uint16_t ss, _pad2[3];
+    uint16_t es, _pad3[3];
+    uint16_t ds, _pad4[3];
+    uint16_t fs, _pad5[3]; /* Non-zero => takes precedence over fs_base.     */
+    uint16_t gs, _pad6[3]; /* Non-zero => takes precedence over gs_base_usr. */
+};
+DEFINE_GUEST_HANDLE_STRUCT(cpu_user_regs);
+
+#undef __DECL_REG
+
+#define xen_pfn_to_cr3(pfn) ((unsigned long)(pfn) << 12)
+#define xen_cr3_to_pfn(cr3) ((unsigned long)(cr3) >> 12)
+
+struct arch_vcpu_info {
+    unsigned long cr2;
+    unsigned long pad; /* sizeof(vcpu_info_t) == 64 */
+};
+
+typedef unsigned long xen_callback_t;
+
+#define XEN_CALLBACK(__cs, __rip)				\
+	((unsigned long)(__rip))
+
+#endif /* !__ASSEMBLY__ */
+
+
+#endif	/* __ASM_X86_XEN_INTERFACE_64_H */
diff --git a/include/asm-x86/xen/page.h b/include/asm-x86/xen/page.h
index 377c04591c1..05e678a8662 100644
--- a/include/asm-x86/xen/page.h
+++ b/include/asm-x86/xen/page.h
@@ -148,13 +148,17 @@ static inline pte_t __pte_ma(pteval_t x)
 }
 
 #define pmd_val_ma(v) ((v).pmd)
+#ifdef __PAGETABLE_PUD_FOLDED
 #define pud_val_ma(v) ((v).pgd.pgd)
+#else
+#define pud_val_ma(v) ((v).pud)
+#endif
 #define __pmd_ma(x)	((pmd_t) { (x) } )
 
 #define pgd_val_ma(x)	((x).pgd)
 
 
-xmaddr_t arbitrary_virt_to_machine(unsigned long address);
+xmaddr_t arbitrary_virt_to_machine(void *address);
 void make_lowmem_page_readonly(void *vaddr);
 void make_lowmem_page_readwrite(void *vaddr);