Pull release into acpica branch

47 files changed, 681 insertions, 337 deletions

diff --git a/include/asm-x86_64/apic.h b/include/asm-x86_64/apic.h
index 5647b7de174..4f6a4dc455b 100644
--- a/include/asm-x86_64/apic.h
+++ b/include/asm-x86_64/apic.h
@@ -42,11 +42,6 @@ static __inline void apic_write(unsigned long reg, unsigned int v)
 	*((volatile unsigned int *)(APIC_BASE+reg)) = v;
 }
 
-static __inline void apic_write_atomic(unsigned long reg, unsigned int v)
-{
-	xchg((volatile unsigned int *)(APIC_BASE+reg), v);
-}
-
 static __inline unsigned int apic_read(unsigned long reg)
 {
 	return *((volatile unsigned int *)(APIC_BASE+reg));
@@ -57,10 +52,6 @@ static __inline__ void apic_wait_icr_idle(void)
 	while ( apic_read( APIC_ICR ) & APIC_ICR_BUSY );
 }
 
-#define FORCE_READ_AROUND_WRITE 0
-#define apic_read_around(x)
-#define apic_write_around(x,y) apic_write((x),(y))
-
 static inline void ack_APIC_irq(void)
 {
 	/*
@@ -71,7 +62,7 @@ static inline void ack_APIC_irq(void)
 	 */
 
 	/* Docs say use 0 for future compatibility */
-	apic_write_around(APIC_EOI, 0);
+	apic_write(APIC_EOI, 0);
 }
 
 extern int get_maxlvt (void);
@@ -113,6 +104,12 @@ extern int disable_timer_pin_1;
 
 extern void setup_threshold_lvt(unsigned long lvt_off);
 
+void smp_send_timer_broadcast_ipi(void);
+void switch_APIC_timer_to_ipi(void *cpumask);
+void switch_ipi_to_APIC_timer(void *cpumask);
+
+#define ARCH_APICTIMER_STOPS_ON_C3	1
+
 #endif /* CONFIG_X86_LOCAL_APIC */
 
 extern unsigned boot_cpu_id;
diff --git a/include/asm-x86_64/apicdef.h b/include/asm-x86_64/apicdef.h
index fb1c99ac669..decaa2d540e 100644
--- a/include/asm-x86_64/apicdef.h
+++ b/include/asm-x86_64/apicdef.h
@@ -13,6 +13,7 @@
 #define		APIC_ID		0x20
 #define			APIC_ID_MASK		(0xFFu<<24)
 #define			GET_APIC_ID(x)		(((x)>>24)&0xFFu)
+#define			SET_APIC_ID(x)		(((x)<<24))
 #define		APIC_LVR	0x30
 #define			APIC_LVR_MASK		0xFF00FF
 #define			GET_APIC_VERSION(x)	((x)&0xFFu)
diff --git a/include/asm-x86_64/atomic.h b/include/asm-x86_64/atomic.h
index 72eb071488c..4b5cd553e77 100644
--- a/include/asm-x86_64/atomic.h
+++ b/include/asm-x86_64/atomic.h
@@ -2,6 +2,7 @@
 #define __ARCH_X86_64_ATOMIC__
 
 #include <linux/config.h>
+#include <asm/types.h>
 
 /* atomic_t should be 32 bit signed type */
 
@@ -389,6 +390,7 @@ static __inline__ long atomic64_sub_return(long i, atomic64_t *v)
 #define atomic64_dec_return(v)  (atomic64_sub_return(1,v))
 
 #define atomic_cmpxchg(v, old, new) ((int)cmpxchg(&((v)->counter), old, new))
+#define atomic_xchg(v, new) (xchg(&((v)->counter), new))
 
 /**
  * atomic_add_unless - add unless the number is a given value
diff --git a/include/asm-x86_64/bitops.h b/include/asm-x86_64/bitops.h
index a4d5d090945..eb4df23e1e4 100644
--- a/include/asm-x86_64/bitops.h
+++ b/include/asm-x86_64/bitops.h
@@ -29,7 +29,7 @@ static __inline__ void set_bit(int nr, volatile void * addr)
 {
 	__asm__ __volatile__( LOCK_PREFIX
 		"btsl %1,%0"
-		:"=m" (ADDR)
+		:"+m" (ADDR)
 		:"dIr" (nr) : "memory");
 }
 
@@ -46,7 +46,7 @@ static __inline__ void __set_bit(int nr, volatile void * addr)
 {
 	__asm__ volatile(
 		"btsl %1,%0"
-		:"=m" (ADDR)
+		:"+m" (ADDR)
 		:"dIr" (nr) : "memory");
 }
 
@@ -64,7 +64,7 @@ static __inline__ void clear_bit(int nr, volatile void * addr)
 {
 	__asm__ __volatile__( LOCK_PREFIX
 		"btrl %1,%0"
-		:"=m" (ADDR)
+		:"+m" (ADDR)
 		:"dIr" (nr));
 }
 
@@ -72,7 +72,7 @@ static __inline__ void __clear_bit(int nr, volatile void * addr)
 {
 	__asm__ __volatile__(
 		"btrl %1,%0"
-		:"=m" (ADDR)
+		:"+m" (ADDR)
 		:"dIr" (nr));
 }
 
@@ -92,7 +92,7 @@ static __inline__ void __change_bit(int nr, volatile void * addr)
 {
 	__asm__ __volatile__(
 		"btcl %1,%0"
-		:"=m" (ADDR)
+		:"+m" (ADDR)
 		:"dIr" (nr));
 }
 
@@ -109,7 +109,7 @@ static __inline__ void change_bit(int nr, volatile void * addr)
 {
 	__asm__ __volatile__( LOCK_PREFIX
 		"btcl %1,%0"
-		:"=m" (ADDR)
+		:"+m" (ADDR)
 		:"dIr" (nr));
 }
 
@@ -127,7 +127,7 @@ static __inline__ int test_and_set_bit(int nr, volatile void * addr)
 
 	__asm__ __volatile__( LOCK_PREFIX
 		"btsl %2,%1\n\tsbbl %0,%0"
-		:"=r" (oldbit),"=m" (ADDR)
+		:"=r" (oldbit),"+m" (ADDR)
 		:"dIr" (nr) : "memory");
 	return oldbit;
 }
@@ -147,7 +147,7 @@ static __inline__ int __test_and_set_bit(int nr, volatile void * addr)
 
 	__asm__(
 		"btsl %2,%1\n\tsbbl %0,%0"
-		:"=r" (oldbit),"=m" (ADDR)
+		:"=r" (oldbit),"+m" (ADDR)
 		:"dIr" (nr));
 	return oldbit;
 }
@@ -166,7 +166,7 @@ static __inline__ int test_and_clear_bit(int nr, volatile void * addr)
 
 	__asm__ __volatile__( LOCK_PREFIX
 		"btrl %2,%1\n\tsbbl %0,%0"
-		:"=r" (oldbit),"=m" (ADDR)
+		:"=r" (oldbit),"+m" (ADDR)
 		:"dIr" (nr) : "memory");
 	return oldbit;
 }
@@ -186,7 +186,7 @@ static __inline__ int __test_and_clear_bit(int nr, volatile void * addr)
 
 	__asm__(
 		"btrl %2,%1\n\tsbbl %0,%0"
-		:"=r" (oldbit),"=m" (ADDR)
+		:"=r" (oldbit),"+m" (ADDR)
 		:"dIr" (nr));
 	return oldbit;
 }
@@ -198,7 +198,7 @@ static __inline__ int __test_and_change_bit(int nr, volatile void * addr)
 
 	__asm__ __volatile__(
 		"btcl %2,%1\n\tsbbl %0,%0"
-		:"=r" (oldbit),"=m" (ADDR)
+		:"=r" (oldbit),"+m" (ADDR)
 		:"dIr" (nr) : "memory");
 	return oldbit;
 }
@@ -217,7 +217,7 @@ static __inline__ int test_and_change_bit(int nr, volatile void * addr)
 
 	__asm__ __volatile__( LOCK_PREFIX
 		"btcl %2,%1\n\tsbbl %0,%0"
-		:"=r" (oldbit),"=m" (ADDR)
+		:"=r" (oldbit),"+m" (ADDR)
 		:"dIr" (nr) : "memory");
 	return oldbit;
 }
@@ -397,6 +397,22 @@ static __inline__ int fls64(__u64 x)
 }
 
 /**
+ * fls - find last bit set
+ * @x: the word to search
+ *
+ * This is defined the same way as ffs.
+ */
+static __inline__ int fls(int x)
+{
+	int r;
+
+	__asm__("bsrl %1,%0\n\t"
+		"cmovzl %2,%0"
+		: "=&r" (r) : "rm" (x), "rm" (-1));
+	return r+1;
+}
+
+/**
  * hweightN - returns the hamming weight of a N-bit word
  * @x: the word to weigh
  *
@@ -434,9 +450,6 @@ static __inline__ int fls64(__u64 x)
 #define minix_find_first_zero_bit(addr,size) \
 	find_first_zero_bit((void*)addr,size)
 
-/* find last set bit */
-#define fls(x) generic_fls(x)
-
 #endif /* __KERNEL__ */
 
 #endif /* _X86_64_BITOPS_H */
diff --git a/include/asm-x86_64/cache.h b/include/asm-x86_64/cache.h
index 33e53424128..263f0a211ed 100644
--- a/include/asm-x86_64/cache.h
+++ b/include/asm-x86_64/cache.h
@@ -9,6 +9,17 @@
 /* L1 cache line size */
 #define L1_CACHE_SHIFT	(CONFIG_X86_L1_CACHE_SHIFT)
 #define L1_CACHE_BYTES	(1 << L1_CACHE_SHIFT)
-#define L1_CACHE_SHIFT_MAX 7	/* largest L1 which this arch supports */
+
+#ifdef CONFIG_X86_VSMP
+
+/* vSMP Internode cacheline shift */
+#define INTERNODE_CACHE_SHIFT (12)
+#ifdef CONFIG_SMP
+#define __cacheline_aligned_in_smp					\
+       __attribute__((__aligned__(1 << (INTERNODE_CACHE_SHIFT))))         \
+       __attribute__((__section__(".data.page_aligned")))
+#endif
+
+#endif
 
 #endif
diff --git a/include/asm-x86_64/compat.h b/include/asm-x86_64/compat.h
index f0155c38f63..b37ab8218ef 100644
--- a/include/asm-x86_64/compat.h
+++ b/include/asm-x86_64/compat.h
@@ -198,8 +198,13 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr)
 
 static __inline__ void __user *compat_alloc_user_space(long len)
 {
-	struct pt_regs *regs = (void *)current->thread.rsp0 - sizeof(struct pt_regs); 
+	struct pt_regs *regs = task_pt_regs(current);
 	return (void __user *)regs->rsp - len; 
 }
 
+static inline int is_compat_task(void)
+{
+	return current_thread_info()->status & TS_COMPAT;
+}
+
 #endif /* _ASM_X86_64_COMPAT_H */
diff --git a/include/asm-x86_64/cpufeature.h b/include/asm-x86_64/cpufeature.h
index aea308c6570..41c0ac8559b 100644
--- a/include/asm-x86_64/cpufeature.h
+++ b/include/asm-x86_64/cpufeature.h
@@ -61,8 +61,9 @@
 #define X86_FEATURE_K6_MTRR	(3*32+ 1) /* AMD K6 nonstandard MTRRs */
 #define X86_FEATURE_CYRIX_ARR	(3*32+ 2) /* Cyrix ARRs (= MTRRs) */
 #define X86_FEATURE_CENTAUR_MCR	(3*32+ 3) /* Centaur MCRs (= MTRRs) */
-#define X86_FEATURE_K8_C	(3*32+ 4) /* C stepping K8 */
+/* 4 free */
 #define X86_FEATURE_CONSTANT_TSC (3*32+5) /* TSC runs at constant rate */
+#define X86_FEATURE_SYNC_RDTSC  (3*32+6)  /* RDTSC syncs CPU core */
 
 /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
 #define X86_FEATURE_XMM3	(4*32+ 0) /* Streaming SIMD Extensions-3 */
diff --git a/include/asm-x86_64/desc.h b/include/asm-x86_64/desc.h
index 33764869387..eb7723a4679 100644
--- a/include/asm-x86_64/desc.h
+++ b/include/asm-x86_64/desc.h
@@ -25,7 +25,7 @@ struct n_desc_struct {
 	unsigned int a,b;
 }; 	
 
-extern struct desc_struct cpu_gdt_table[NR_CPUS][GDT_ENTRIES];
+extern struct desc_struct cpu_gdt_table[GDT_ENTRIES];
 
 enum { 
 	GATE_INTERRUPT = 0xE, 
@@ -79,6 +79,9 @@ extern struct desc_struct default_ldt[];
 extern struct gate_struct idt_table[]; 
 extern struct desc_ptr cpu_gdt_descr[];
 
+/* the cpu gdt accessor */
+#define cpu_gdt(_cpu) ((struct desc_struct *)cpu_gdt_descr[_cpu].address)
+
 static inline void _set_gate(void *adr, unsigned type, unsigned long func, unsigned dpl, unsigned ist)  
 {
 	struct gate_struct s; 	
@@ -114,6 +117,11 @@ static inline void set_system_gate(int nr, void *func)
 	_set_gate(&idt_table[nr], GATE_INTERRUPT, (unsigned long) func, 3, 0); 
 } 
 
+static inline void set_system_gate_ist(int nr, void *func, unsigned ist)
+{
+	_set_gate(&idt_table[nr], GATE_INTERRUPT, (unsigned long) func, 3, ist);
+}
+
 static inline void set_tssldt_descriptor(void *ptr, unsigned long tss, unsigned type, 
 					 unsigned size) 
 { 
@@ -139,20 +147,20 @@ static inline void set_tss_desc(unsigned cpu, void *addr)
 	 * -1? seg base+limit should be pointing to the address of the
 	 * last valid byte
 	 */
-	set_tssldt_descriptor(&cpu_gdt_table[cpu][GDT_ENTRY_TSS],
+	set_tssldt_descriptor(&cpu_gdt(cpu)[GDT_ENTRY_TSS],
 		(unsigned long)addr, DESC_TSS,
 		IO_BITMAP_OFFSET + IO_BITMAP_BYTES + sizeof(unsigned long) - 1);
 } 
 
 static inline void set_ldt_desc(unsigned cpu, void *addr, int size)
 { 
-	set_tssldt_descriptor(&cpu_gdt_table[cpu][GDT_ENTRY_LDT], (unsigned long)addr, 
+	set_tssldt_descriptor(&cpu_gdt(cpu)[GDT_ENTRY_LDT], (unsigned long)addr,
 			      DESC_LDT, size * 8 - 1);
 }
 
 static inline void set_seg_base(unsigned cpu, int entry, void *base)
 { 
-	struct desc_struct *d = &cpu_gdt_table[cpu][entry];
+	struct desc_struct *d = &cpu_gdt(cpu)[entry];
 	u32 addr = (u32)(u64)base;
 	BUG_ON((u64)base >> 32); 
 	d->base0 = addr & 0xffff;
@@ -194,7 +202,7 @@ static inline void set_seg_base(unsigned cpu, int entry, void *base)
 
 static inline void load_TLS(struct thread_struct *t, unsigned int cpu)
 {
-	u64 *gdt = (u64 *)(cpu_gdt_table[cpu] + GDT_ENTRY_TLS_MIN);
+	u64 *gdt = (u64 *)(cpu_gdt(cpu) + GDT_ENTRY_TLS_MIN);
 	gdt[0] = t->tls_array[0];
 	gdt[1] = t->tls_array[1];
 	gdt[2] = t->tls_array[2];
diff --git a/include/asm-x86_64/dma-mapping.h b/include/asm-x86_64/dma-mapping.h
index 36d16dfbac8..49a81a66516 100644
--- a/include/asm-x86_64/dma-mapping.h
+++ b/include/asm-x86_64/dma-mapping.h
@@ -12,155 +12,176 @@
 #include <asm/io.h>
 #include <asm/swiotlb.h>
 
-extern dma_addr_t bad_dma_address;
-#define dma_mapping_error(x) \
-	(swiotlb ? swiotlb_dma_mapping_error(x) : ((x) == bad_dma_address))
-
-void *dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
-			 gfp_t gfp);
-void dma_free_coherent(struct device *dev, size_t size, void *vaddr,
-			 dma_addr_t dma_handle);
+struct dma_mapping_ops {
+	int             (*mapping_error)(dma_addr_t dma_addr);
+	void*           (*alloc_coherent)(struct device *dev, size_t size,
+                                dma_addr_t *dma_handle, gfp_t gfp);
+	void            (*free_coherent)(struct device *dev, size_t size,
+                                void *vaddr, dma_addr_t dma_handle);
+	dma_addr_t      (*map_single)(struct device *hwdev, void *ptr,
+                                size_t size, int direction);
+	/* like map_single, but doesn't check the device mask */
+	dma_addr_t      (*map_simple)(struct device *hwdev, char *ptr,
+                                size_t size, int direction);
+	void            (*unmap_single)(struct device *dev, dma_addr_t addr,
+		                size_t size, int direction);
+	void            (*sync_single_for_cpu)(struct device *hwdev,
+		                dma_addr_t dma_handle, size_t size,
+				int direction);
+	void            (*sync_single_for_device)(struct device *hwdev,
+                                dma_addr_t dma_handle, size_t size,
+				int direction);
+	void            (*sync_single_range_for_cpu)(struct device *hwdev,
+                                dma_addr_t dma_handle, unsigned long offset,
+		                size_t size, int direction);
+	void            (*sync_single_range_for_device)(struct device *hwdev,
+				dma_addr_t dma_handle, unsigned long offset,
+		                size_t size, int direction);
+	void            (*sync_sg_for_cpu)(struct device *hwdev,
+                                struct scatterlist *sg, int nelems,
+				int direction);
+	void            (*sync_sg_for_device)(struct device *hwdev,
+				struct scatterlist *sg, int nelems,
+				int direction);
+	int             (*map_sg)(struct device *hwdev, struct scatterlist *sg,
+		                int nents, int direction);
+	void            (*unmap_sg)(struct device *hwdev,
+				struct scatterlist *sg, int nents,
+				int direction);
+	int             (*dma_supported)(struct device *hwdev, u64 mask);
+	int		is_phys;
+};
 
-#ifdef CONFIG_GART_IOMMU
+extern dma_addr_t bad_dma_address;
+extern struct dma_mapping_ops* dma_ops;
+extern int iommu_merge;
 
-extern dma_addr_t dma_map_single(struct device *hwdev, void *ptr, size_t size,
-				 int direction);
-extern void dma_unmap_single(struct device *dev, dma_addr_t addr,size_t size,
-			     int direction);
+static inline int dma_mapping_error(dma_addr_t dma_addr)
+{
+	if (dma_ops->mapping_error)
+		return dma_ops->mapping_error(dma_addr);
 
-#else
+	return (dma_addr == bad_dma_address);
+}
 
-/* No IOMMU */
+extern void *dma_alloc_coherent(struct device *dev, size_t size,
+				dma_addr_t *dma_handle, gfp_t gfp);
+extern void dma_free_coherent(struct device *dev, size_t size, void *vaddr,
+			      dma_addr_t dma_handle);
 
-static inline dma_addr_t dma_map_single(struct device *hwdev, void *ptr,
-					size_t size, int direction)
+static inline dma_addr_t
+dma_map_single(struct device *hwdev, void *ptr, size_t size,
+	       int direction)
 {
-	dma_addr_t addr;
-
-	if (direction == DMA_NONE)
-		out_of_line_bug();
-	addr = virt_to_bus(ptr);
-
-	if ((addr+size) & ~*hwdev->dma_mask)
-		out_of_line_bug();
-	return addr;
+	return dma_ops->map_single(hwdev, ptr, size, direction);
 }
 
-static inline void dma_unmap_single(struct device *hwdev, dma_addr_t dma_addr,
-				    size_t size, int direction)
+static inline void
+dma_unmap_single(struct device *dev, dma_addr_t addr,size_t size,
+		 int direction)
 {
-	if (direction == DMA_NONE)
-		out_of_line_bug();
-	/* Nothing to do */
+	dma_ops->unmap_single(dev, addr, size, direction);
 }
 
-#endif
-
 #define dma_map_page(dev,page,offset,size,dir) \
 	dma_map_single((dev), page_address(page)+(offset), (size), (dir))
 
-static inline void dma_sync_single_for_cpu(struct device *hwdev,
-					       dma_addr_t dma_handle,
-					       size_t size, int direction)
-{
-	if (direction == DMA_NONE)
-		out_of_line_bug();
-
-	if (swiotlb)
-		return swiotlb_sync_single_for_cpu(hwdev,dma_handle,size,direction);
+#define dma_unmap_page dma_unmap_single
 
+static inline void
+dma_sync_single_for_cpu(struct device *hwdev, dma_addr_t dma_handle,
+			size_t size, int direction)
+{
+	if (dma_ops->sync_single_for_cpu)
+		dma_ops->sync_single_for_cpu(hwdev, dma_handle, size,
+					     direction);
 	flush_write_buffers();
 }
 
-static inline void dma_sync_single_for_device(struct device *hwdev,
-						  dma_addr_t dma_handle,
-						  size_t size, int direction)
+static inline void
+dma_sync_single_for_device(struct device *hwdev, dma_addr_t dma_handle,
+			   size_t size, int direction)
 {
-        if (direction == DMA_NONE)
-		out_of_line_bug();
-
-	if (swiotlb)
-		return swiotlb_sync_single_for_device(hwdev,dma_handle,size,direction);
-
+	if (dma_ops->sync_single_for_device)
+		dma_ops->sync_single_for_device(hwdev, dma_handle, size,
+						direction);
 	flush_write_buffers();
 }
 
-static inline void dma_sync_single_range_for_cpu(struct device *hwdev,
-						 dma_addr_t dma_handle,
-						 unsigned long offset,
-						 size_t size, int direction)
+static inline void
+dma_sync_single_range_for_cpu(struct device *hwdev, dma_addr_t dma_handle,
+			      unsigned long offset, size_t size, int direction)
 {
-	if (direction == DMA_NONE)
-		out_of_line_bug();
-
-	if (swiotlb)
-		return swiotlb_sync_single_range_for_cpu(hwdev,dma_handle,offset,size,direction);
+	if (dma_ops->sync_single_range_for_cpu) {
+		dma_ops->sync_single_range_for_cpu(hwdev, dma_handle, offset, size, direction);
+	}
 
 	flush_write_buffers();
 }
 
-static inline void dma_sync_single_range_for_device(struct device *hwdev,
-						    dma_addr_t dma_handle,
-						    unsigned long offset,
-						    size_t size, int direction)
+static inline void
+dma_sync_single_range_for_device(struct device *hwdev, dma_addr_t dma_handle,
+				 unsigned long offset, size_t size, int direction)
 {
-        if (direction == DMA_NONE)
-		out_of_line_bug();
-
-	if (swiotlb)
-		return swiotlb_sync_single_range_for_device(hwdev,dma_handle,offset,size,direction);
+	if (dma_ops->sync_single_range_for_device)
+		dma_ops->sync_single_range_for_device(hwdev, dma_handle,
+						      offset, size, direction);
 
 	flush_write_buffers();
 }
 
-static inline void dma_sync_sg_for_cpu(struct device *hwdev,
-				       struct scatterlist *sg,
-				       int nelems, int direction)
+static inline void
+dma_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg,
+		    int nelems, int direction)
 {
-	if (direction == DMA_NONE)
-		out_of_line_bug();
-
-	if (swiotlb)
-		return swiotlb_sync_sg_for_cpu(hwdev,sg,nelems,direction);
-
+	if (dma_ops->sync_sg_for_cpu)
+		dma_ops->sync_sg_for_cpu(hwdev, sg, nelems, direction);
 	flush_write_buffers();
 }
 
-static inline void dma_sync_sg_for_device(struct device *hwdev,
-					  struct scatterlist *sg,
-					  int nelems, int direction)
+static inline void
+dma_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
+		       int nelems, int direction)
 {
-	if (direction == DMA_NONE)
-		out_of_line_bug();
-
-	if (swiotlb)
-		return swiotlb_sync_sg_for_device(hwdev,sg,nelems,direction);
+	if (dma_ops->sync_sg_for_device) {
+		dma_ops->sync_sg_for_device(hwdev, sg, nelems, direction);
+	}
 
 	flush_write_buffers();
 }
 
-extern int dma_map_sg(struct device *hwdev, struct scatterlist *sg,
-		      int nents, int direction);
-extern void dma_unmap_sg(struct device *hwdev, struct scatterlist *sg,
-			 int nents, int direction);
+static inline int
+dma_map_sg(struct device *hwdev, struct scatterlist *sg, int nents, int direction)
+{
+	return dma_ops->map_sg(hwdev, sg, nents, direction);
+}
 
-#define dma_unmap_page dma_unmap_single
+static inline void
+dma_unmap_sg(struct device *hwdev, struct scatterlist *sg, int nents,
+	     int direction)
+{
+	dma_ops->unmap_sg(hwdev, sg, nents, direction);
+}
 
 extern int dma_supported(struct device *hwdev, u64 mask);
-extern int dma_get_cache_alignment(void);
-#define dma_is_consistent(h) 1
 
-static inline int dma_set_mask(struct device *dev, u64 mask)
+/* same for gart, swiotlb, and nommu */
+static inline int dma_get_cache_alignment(void)
 {
-	if (!dev->dma_mask || !dma_supported(dev, mask))
-		return -EIO;
-	*dev->dma_mask = mask;
-	return 0;
+	return boot_cpu_data.x86_clflush_size;
 }
 
-static inline void dma_cache_sync(void *vaddr, size_t size, enum dma_data_direction dir)
+#define dma_is_consistent(h) 1
+
+extern int dma_set_mask(struct device *dev, u64 mask);
+
+static inline void
+dma_cache_sync(void *vaddr, size_t size, enum dma_data_direction dir)
 {
 	flush_write_buffers();
 }
 
-#endif
+extern struct device fallback_dev;
+extern int panic_on_overflow;
+
+#endif /* _X8664_DMA_MAPPING_H */
diff --git a/include/asm-x86_64/dwarf2.h b/include/asm-x86_64/dwarf2.h
index 582757fc036..07654bd155b 100644
--- a/include/asm-x86_64/dwarf2.h
+++ b/include/asm-x86_64/dwarf2.h
@@ -14,7 +14,7 @@
    away for older version. 
  */
 
-#ifdef CONFIG_DEBUG_INFO
+#ifdef CONFIG_UNWIND_INFO
 
 #define CFI_STARTPROC .cfi_startproc
 #define CFI_ENDPROC .cfi_endproc
@@ -28,6 +28,7 @@
 #define CFI_RESTORE .cfi_restore
 #define CFI_REMEMBER_STATE .cfi_remember_state
 #define CFI_RESTORE_STATE .cfi_restore_state
+#define CFI_UNDEFINED .cfi_undefined
 
 #else
 
@@ -44,6 +45,7 @@
 #define CFI_RESTORE	#
 #define CFI_REMEMBER_STATE	#
 #define CFI_RESTORE_STATE	#
+#define CFI_UNDEFINED	#
 
 #endif
 
diff --git a/include/asm-x86_64/e820.h b/include/asm-x86_64/e820.h
index e682edc24a6..8dcc3266524 100644
--- a/include/asm-x86_64/e820.h
+++ b/include/asm-x86_64/e820.h
@@ -55,6 +55,7 @@ extern unsigned long e820_hole_size(unsigned long start_pfn,
 				    unsigned long end_pfn);
 
 extern void __init parse_memopt(char *p, char **end);
+extern void __init parse_memmapopt(char *p, char **end);
 
 extern struct e820map e820;
 #endif/*!__ASSEMBLY__*/
diff --git a/include/asm-x86_64/edac.h b/include/asm-x86_64/edac.h
new file mode 100644
index 00000000000..cad1cd42b4e
--- /dev/null
+++ b/include/asm-x86_64/edac.h
@@ -0,0 +1,18 @@
+#ifndef ASM_EDAC_H
+#define ASM_EDAC_H
+
+/* ECC atomic, DMA, SMP and interrupt safe scrub function */
+
+static __inline__ void atomic_scrub(void *va, u32 size)
+{
+	unsigned int *virt_addr = va;
+	u32 i;
+
+	for (i = 0; i < size / 4; i++, virt_addr++)
+		/* Very carefully read and write to memory atomically
+		 * so we are interrupt, DMA and SMP safe.
+		 */
+		__asm__ __volatile__("lock; addl $0, %0"::"m"(*virt_addr));
+}
+
+#endif
diff --git a/include/asm-x86_64/fixmap.h b/include/asm-x86_64/fixmap.h
index a582cfcf223..7b286bd21d1 100644
--- a/include/asm-x86_64/fixmap.h
+++ b/include/asm-x86_64/fixmap.h
@@ -76,7 +76,7 @@ extern void __this_fixmap_does_not_exist(void);
  * directly without translation, we catch the bug with a NULL-deference
  * kernel oops. Illegal ranges of incoming indices are caught too.
  */
-static inline unsigned long fix_to_virt(const unsigned int idx)
+static __always_inline unsigned long fix_to_virt(const unsigned int idx)
 {
 	/*
 	 * this branch gets completely eliminated after inlining,
diff --git a/include/asm-x86_64/gart-mapping.h b/include/asm-x86_64/gart-mapping.h
new file mode 100644
index 00000000000..ada497b0b55
--- /dev/null
+++ b/include/asm-x86_64/gart-mapping.h
@@ -0,0 +1,16 @@
+#ifndef _X8664_GART_MAPPING_H
+#define _X8664_GART_MAPPING_H 1
+
+#include <linux/types.h>
+#include <asm/types.h>
+
+struct device;
+
+extern void*
+gart_alloc_coherent(struct device *dev, size_t size,
+        dma_addr_t *dma_handle, gfp_t gfp);
+
+extern int
+gart_dma_supported(struct device *hwdev, u64 mask);
+
+#endif /* _X8664_GART_MAPPING_H */
diff --git a/include/asm-x86_64/hw_irq.h b/include/asm-x86_64/hw_irq.h
index c14a8c7267a..0df1715dee7 100644
--- a/include/asm-x86_64/hw_irq.h
+++ b/include/asm-x86_64/hw_irq.h
@@ -46,18 +46,18 @@ struct hw_interrupt_type;
  *  some of the following vectors are 'rare', they are merged
  *  into a single vector (CALL_FUNCTION_VECTOR) to save vector space.
  *  TLB, reschedule and local APIC vectors are performance-critical.
- *
- *  Vectors 0xf0-0xf9 are free (reserved for future Linux use).
  */
 #define SPURIOUS_APIC_VECTOR	0xff
 #define ERROR_APIC_VECTOR	0xfe
 #define RESCHEDULE_VECTOR	0xfd
 #define CALL_FUNCTION_VECTOR	0xfc
-#define KDB_VECTOR		0xfb	/* reserved for KDB */
+/* fb free - please don't readd KDB here because it's useless
+   (hint - think what a NMI bit does to a vector) */
 #define THERMAL_APIC_VECTOR	0xfa
 #define THRESHOLD_APIC_VECTOR   0xf9
-#define INVALIDATE_TLB_VECTOR_END	0xf8
-#define INVALIDATE_TLB_VECTOR_START	0xf0	/* f0-f8 used for TLB flush */
+/* f8 free */
+#define INVALIDATE_TLB_VECTOR_END	0xf7
+#define INVALIDATE_TLB_VECTOR_START	0xf0	/* f0-f7 used for TLB flush */
 
 #define NUM_INVALIDATE_TLB_VECTORS	8
 
diff --git a/include/asm-x86_64/i387.h b/include/asm-x86_64/i387.h
index aa39cfd0e00..876eb9a2fe7 100644
--- a/include/asm-x86_64/i387.h
+++ b/include/asm-x86_64/i387.h
@@ -30,7 +30,7 @@ extern int save_i387(struct _fpstate __user *buf);
  */
 
 #define unlazy_fpu(tsk) do { \
-	if ((tsk)->thread_info->status & TS_USEDFPU) \
+	if (task_thread_info(tsk)->status & TS_USEDFPU) \
 		save_init_fpu(tsk); \
 } while (0)
 
@@ -46,9 +46,9 @@ static inline void tolerant_fwait(void)
 }
 
 #define clear_fpu(tsk) do { \
-	if ((tsk)->thread_info->status & TS_USEDFPU) {		\
+	if (task_thread_info(tsk)->status & TS_USEDFPU) {	\
 		tolerant_fwait();				\
-		(tsk)->thread_info->status &= ~TS_USEDFPU;	\
+		task_thread_info(tsk)->status &= ~TS_USEDFPU;	\
 		stts();						\
 	}							\
 } while (0)
@@ -75,7 +75,8 @@ extern int set_fpregs(struct task_struct *tsk,
 static inline int restore_fpu_checking(struct i387_fxsave_struct *fx) 
 { 
 	int err;
-	asm volatile("1:  rex64 ; fxrstor (%[fx])\n\t"
+
+	asm volatile("1:  rex64/fxrstor (%[fx])\n\t"
 		     "2:\n"
 		     ".section .fixup,\"ax\"\n"
 		     "3:  movl $-1,%[err]\n"
@@ -86,7 +87,11 @@ static inline int restore_fpu_checking(struct i387_fxsave_struct *fx)
 		     "   .quad  1b,3b\n"
 		     ".previous"
 		     : [err] "=r" (err)
-		     : [fx] "r" (fx), "0" (0)); 
+#if 0 /* See comment in __fxsave_clear() below. */
+		     : [fx] "r" (fx), "m" (*fx), "0" (0));
+#else
+		     : [fx] "cdaSDb" (fx), "m" (*fx), "0" (0));
+#endif
 	if (unlikely(err))
 		init_fpu(current);
 	return err;
@@ -95,7 +100,8 @@ static inline int restore_fpu_checking(struct i387_fxsave_struct *fx)
 static inline int save_i387_checking(struct i387_fxsave_struct __user *fx) 
 { 
 	int err;
-	asm volatile("1:  rex64 ; fxsave (%[fx])\n\t"
+
+	asm volatile("1:  rex64/fxsave (%[fx])\n\t"
 		     "2:\n"
 		     ".section .fixup,\"ax\"\n"
 		     "3:  movl $-1,%[err]\n"
@@ -105,20 +111,53 @@ static inline int save_i387_checking(struct i387_fxsave_struct __user *fx)
 		     "   .align 8\n"
 		     "   .quad  1b,3b\n"
 		     ".previous"
-		     : [err] "=r" (err)
-		     : [fx] "r" (fx), "0" (0)); 
+		     : [err] "=r" (err), "=m" (*fx)
+#if 0 /* See comment in __fxsave_clear() below. */
+		     : [fx] "r" (fx), "0" (0));
+#else
+		     : [fx] "cdaSDb" (fx), "0" (0));
+#endif
 	if (unlikely(err))
 		__clear_user(fx, sizeof(struct i387_fxsave_struct));
 	return err;
 } 
 
+static inline void __fxsave_clear(struct task_struct *tsk)
+{
+	/* Using "rex64; fxsave %0" is broken because, if the memory operand
+	   uses any extended registers for addressing, a second REX prefix
+	   will be generated (to the assembler, rex64 followed by semicolon
+	   is a separate instruction), and hence the 64-bitness is lost. */
+#if 0
+	/* Using "fxsaveq %0" would be the ideal choice, but is only supported
+	   starting with gas 2.16. */
+	__asm__ __volatile__("fxsaveq %0"
+			     : "=m" (tsk->thread.i387.fxsave));
+#elif 0
+	/* Using, as a workaround, the properly prefixed form below isn't
+	   accepted by any binutils version so far released, complaining that
+	   the same type of prefix is used twice if an extended register is
+	   needed for addressing (fix submitted to mainline 2005-11-21). */
+	__asm__ __volatile__("rex64/fxsave %0"
+			     : "=m" (tsk->thread.i387.fxsave));
+#else
+	/* This, however, we can work around by forcing the compiler to select
+	   an addressing mode that doesn't require extended registers. */
+	__asm__ __volatile__("rex64/fxsave %P2(%1)"
+			     : "=m" (tsk->thread.i387.fxsave)
+			     : "cdaSDb" (tsk),
+				"i" (offsetof(__typeof__(*tsk),
+					      thread.i387.fxsave)));
+#endif
+	__asm__ __volatile__("fnclex");
+}
+
 static inline void kernel_fpu_begin(void)
 {
 	struct thread_info *me = current_thread_info();
 	preempt_disable();
-	if (me->status & TS_USEDFPU) { 
-		asm volatile("rex64 ; fxsave %0 ; fnclex"
-			      : "=m" (me->task->thread.i387.fxsave));
+	if (me->status & TS_USEDFPU) {
+		__fxsave_clear(me->task);
 		me->status &= ~TS_USEDFPU;
 		return;
 	}
@@ -131,11 +170,10 @@ static inline void kernel_fpu_end(void)
 	preempt_enable();
 }
 
-static inline void save_init_fpu( struct task_struct *tsk )
+static inline void save_init_fpu(struct task_struct *tsk)
 {
-	asm volatile( "rex64 ; fxsave %0 ; fnclex"
-		      : "=m" (tsk->thread.i387.fxsave));
-	tsk->thread_info->status &= ~TS_USEDFPU;
+ 	__fxsave_clear(tsk);
+	task_thread_info(tsk)->status &= ~TS_USEDFPU;
 	stts();
 }
 
diff --git a/include/asm-x86_64/ia32.h b/include/asm-x86_64/ia32.h
index c7bc9c0525b..e6b7f2234e4 100644
--- a/include/asm-x86_64/ia32.h
+++ b/include/asm-x86_64/ia32.h
@@ -169,6 +169,8 @@ int ia32_child_tls(struct task_struct *p, struct pt_regs *childregs);
 struct linux_binprm;
 extern int ia32_setup_arg_pages(struct linux_binprm *bprm,
 				unsigned long stack_top, int exec_stack);
+struct mm_struct;
+extern void ia32_pick_mmap_layout(struct mm_struct *mm);
 
 #endif
 
diff --git a/include/asm-x86_64/ia32_unistd.h b/include/asm-x86_64/ia32_unistd.h
index d5166ec3868..e87cd83a0e8 100644
--- a/include/asm-x86_64/ia32_unistd.h
+++ b/include/asm-x86_64/ia32_unistd.h
@@ -299,7 +299,21 @@
 #define __NR_ia32_inotify_init		291
 #define __NR_ia32_inotify_add_watch	292
 #define __NR_ia32_inotify_rm_watch	293
+#define __NR_ia32_migrate_pages		294
+#define __NR_ia32_opanat		295
+#define __NR_ia32_mkdirat		296
+#define __NR_ia32_mknodat		297
+#define __NR_ia32_fchownat		298
+#define __NR_ia32_futimesat		299
+#define __NR_ia32_newfstatat		300
+#define __NR_ia32_unlinkat		301
+#define __NR_ia32_renameat		302
+#define __NR_ia32_linkat		303
+#define __NR_ia32_symlinkat		304
+#define __NR_ia32_readlinkat		305
+#define __NR_ia32_fchmodat		306
+#define __NR_ia32_faccessat		307
 
-#define IA32_NR_syscalls 294	/* must be > than biggest syscall! */
+#define IA32_NR_syscalls 308	/* must be > than biggest syscall! */
 
 #endif /* _ASM_X86_64_IA32_UNISTD_H_ */
diff --git a/include/asm-x86_64/idle.h b/include/asm-x86_64/idle.h
new file mode 100644
index 00000000000..6bd47dcf206
--- /dev/null
+++ b/include/asm-x86_64/idle.h
@@ -0,0 +1,14 @@
+#ifndef _ASM_X86_64_IDLE_H
+#define _ASM_X86_64_IDLE_H 1
+
+#define IDLE_START 1
+#define IDLE_END 2
+
+struct notifier_block;
+void idle_notifier_register(struct notifier_block *n);
+void idle_notifier_unregister(struct notifier_block *n);
+
+void enter_idle(void);
+void exit_idle(void);
+
+#endif
diff --git a/include/asm-x86_64/io.h b/include/asm-x86_64/io.h
index 52ff269fe05..9dac18db829 100644
--- a/include/asm-x86_64/io.h
+++ b/include/asm-x86_64/io.h
@@ -143,6 +143,11 @@ static inline void __iomem * ioremap (unsigned long offset, unsigned long size)
 extern void __iomem * ioremap_nocache (unsigned long offset, unsigned long size);
 extern void iounmap(volatile void __iomem *addr);
 
+/* Use normal IO mappings for DMI */
+#define dmi_ioremap ioremap
+#define dmi_iounmap(x,l) iounmap(x)
+#define dmi_alloc(l) kmalloc(l, GFP_ATOMIC)
+
 /*
  * ISA I/O bus memory addresses are 1:1 with the physical address.
  */
diff --git a/include/asm-x86_64/ioctl.h b/include/asm-x86_64/ioctl.h
index 609b663b6bf..b279fe06dfe 100644
--- a/include/asm-x86_64/ioctl.h
+++ b/include/asm-x86_64/ioctl.h
@@ -1,75 +1 @@
-/* $Id: ioctl.h,v 1.2 2001/07/04 09:08:13 ak Exp $
- *
- * linux/ioctl.h for Linux by H.H. Bergman.
- */
-
-#ifndef _ASMX8664_IOCTL_H
-#define _ASMX8664_IOCTL_H
-
-/* ioctl command encoding: 32 bits total, command in lower 16 bits,
- * size of the parameter structure in the lower 14 bits of the
- * upper 16 bits.
- * Encoding the size of the parameter structure in the ioctl request
- * is useful for catching programs compiled with old versions
- * and to avoid overwriting user space outside the user buffer area.
- * The highest 2 bits are reserved for indicating the ``access mode''.
- * NOTE: This limits the max parameter size to 16kB -1 !
- */
-
-/*
- * The following is for compatibility across the various Linux
- * platforms.  The i386 ioctl numbering scheme doesn't really enforce
- * a type field.  De facto, however, the top 8 bits of the lower 16
- * bits are indeed used as a type field, so we might just as well make
- * this explicit here.  Please be sure to use the decoding macros
- * below from now on.
- */
-#define _IOC_NRBITS	8
-#define _IOC_TYPEBITS	8
-#define _IOC_SIZEBITS	14
-#define _IOC_DIRBITS	2
-
-#define _IOC_NRMASK	((1 << _IOC_NRBITS)-1)
-#define _IOC_TYPEMASK	((1 << _IOC_TYPEBITS)-1)
-#define _IOC_SIZEMASK	((1 << _IOC_SIZEBITS)-1)
-#define _IOC_DIRMASK	((1 << _IOC_DIRBITS)-1)
-
-#define _IOC_NRSHIFT	0
-#define _IOC_TYPESHIFT	(_IOC_NRSHIFT+_IOC_NRBITS)
-#define _IOC_SIZESHIFT	(_IOC_TYPESHIFT+_IOC_TYPEBITS)
-#define _IOC_DIRSHIFT	(_IOC_SIZESHIFT+_IOC_SIZEBITS)
-
-/*
- * Direction bits.
- */
-#define _IOC_NONE	0U
-#define _IOC_WRITE	1U
-#define _IOC_READ	2U
-
-#define _IOC(dir,type,nr,size) \
-	(((dir)  << _IOC_DIRSHIFT) | \
-	 ((type) << _IOC_TYPESHIFT) | \
-	 ((nr)   << _IOC_NRSHIFT) | \
-	 ((size) << _IOC_SIZESHIFT))
-
-/* used to create numbers */
-#define _IO(type,nr)		_IOC(_IOC_NONE,(type),(nr),0)
-#define _IOR(type,nr,size)	_IOC(_IOC_READ,(type),(nr),sizeof(size))
-#define _IOW(type,nr,size)	_IOC(_IOC_WRITE,(type),(nr),sizeof(size))
-#define _IOWR(type,nr,size)	_IOC(_IOC_READ|_IOC_WRITE,(type),(nr),sizeof(size))
-
-/* used to decode ioctl numbers.. */
-#define _IOC_DIR(nr)		(((nr) >> _IOC_DIRSHIFT) & _IOC_DIRMASK)
-#define _IOC_TYPE(nr)		(((nr) >> _IOC_TYPESHIFT) & _IOC_TYPEMASK)
-#define _IOC_NR(nr)		(((nr) >> _IOC_NRSHIFT) & _IOC_NRMASK)
-#define _IOC_SIZE(nr)		(((nr) >> _IOC_SIZESHIFT) & _IOC_SIZEMASK)
-
-/* ...and for the drivers/sound files... */
-
-#define IOC_IN		(_IOC_WRITE << _IOC_DIRSHIFT)
-#define IOC_OUT		(_IOC_READ << _IOC_DIRSHIFT)
-#define IOC_INOUT	((_IOC_WRITE|_IOC_READ) << _IOC_DIRSHIFT)
-#define IOCSIZE_MASK	(_IOC_SIZEMASK << _IOC_SIZESHIFT)
-#define IOCSIZE_SHIFT	(_IOC_SIZESHIFT)
-
-#endif /* _ASMX8664_IOCTL_H */
+#include <asm-generic/ioctl.h>
diff --git a/include/asm-x86_64/ipi.h b/include/asm-x86_64/ipi.h
index 022e9d340ad..2a5c162b7d9 100644
--- a/include/asm-x86_64/ipi.h
+++ b/include/asm-x86_64/ipi.h
@@ -38,10 +38,6 @@ static inline unsigned int __prepare_ICR (unsigned int shortcut, int vector, uns
 		icr |= APIC_DM_FIXED | vector;
 		break;
 	case NMI_VECTOR:
-		/*
-		 * Setup KDB IPI to be delivered as an NMI
-		 */
-	case KDB_VECTOR:
 		icr |= APIC_DM_NMI;
 		break;
 	}
diff --git a/include/asm-x86_64/irq.h b/include/asm-x86_64/irq.h
index fb724ba37ae..9db5a1b4f7b 100644
--- a/include/asm-x86_64/irq.h
+++ b/include/asm-x86_64/irq.h
@@ -36,7 +36,7 @@
 #define NR_IRQ_VECTORS NR_IRQS
 #else
 #define NR_IRQS 224
-#define NR_IRQ_VECTORS 1024
+#define NR_IRQ_VECTORS (32 * NR_CPUS)
 #endif
 
 static __inline__ int irq_canonicalize(int irq)
diff --git a/include/asm-x86_64/kdebug.h b/include/asm-x86_64/kdebug.h
index f604e84c530..b9ed4c0c878 100644
--- a/include/asm-x86_64/kdebug.h
+++ b/include/asm-x86_64/kdebug.h
@@ -35,9 +35,16 @@ enum die_val {
 	DIE_PAGE_FAULT,
 }; 
 	
-static inline int notify_die(enum die_val val,char *str,struct pt_regs *regs,long err,int trap, int sig)
-{ 
-	struct die_args args = { .regs=regs, .str=str, .err=err, .trapnr=trap,.signr=sig }; 
+static inline int notify_die(enum die_val val, const char *str,
+			struct pt_regs *regs, long err, int trap, int sig)
+{
+	struct die_args args = {
+		.regs = regs,
+		.str = str,
+		.err = err,
+		.trapnr = trap,
+		.signr = sig
+	};
 	return notifier_call_chain(&die_chain, val, &args); 
 } 
 
diff --git a/include/asm-x86_64/kexec.h b/include/asm-x86_64/kexec.h
index 42d2ff15c59..ae28cd44bcd 100644
--- a/include/asm-x86_64/kexec.h
+++ b/include/asm-x86_64/kexec.h
@@ -3,6 +3,7 @@
 
 #include <asm/page.h>
 #include <asm/proto.h>
+#include <asm/ptrace.h>
 
 /*
  * KEXEC_SOURCE_MEMORY_LIMIT maximum page get_free_page can return.
@@ -26,8 +27,40 @@
 #define KEXEC_ARCH KEXEC_ARCH_X86_64
 
 #define MAX_NOTE_BYTES 1024
-typedef u32 note_buf_t[MAX_NOTE_BYTES/4];
 
-extern note_buf_t crash_notes[];
+/*
+ * Saving the registers of the cpu on which panic occured in
+ * crash_kexec to save a valid sp. The registers of other cpus
+ * will be saved in machine_crash_shutdown while shooting down them.
+ */
+
+static inline void crash_setup_regs(struct pt_regs *newregs,
+						struct pt_regs *oldregs)
+{
+	if (oldregs)
+		memcpy(newregs, oldregs, sizeof(*newregs));
+	else {
+		__asm__ __volatile__("movq %%rbx,%0" : "=m"(newregs->rbx));
+		__asm__ __volatile__("movq %%rcx,%0" : "=m"(newregs->rcx));
+		__asm__ __volatile__("movq %%rdx,%0" : "=m"(newregs->rdx));
+		__asm__ __volatile__("movq %%rsi,%0" : "=m"(newregs->rsi));
+		__asm__ __volatile__("movq %%rdi,%0" : "=m"(newregs->rdi));
+		__asm__ __volatile__("movq %%rbp,%0" : "=m"(newregs->rbp));
+		__asm__ __volatile__("movq %%rax,%0" : "=m"(newregs->rax));
+		__asm__ __volatile__("movq %%rsp,%0" : "=m"(newregs->rsp));
+		__asm__ __volatile__("movq %%r8,%0" : "=m"(newregs->r8));
+		__asm__ __volatile__("movq %%r9,%0" : "=m"(newregs->r9));
+		__asm__ __volatile__("movq %%r10,%0" : "=m"(newregs->r10));
+		__asm__ __volatile__("movq %%r11,%0" : "=m"(newregs->r11));
+		__asm__ __volatile__("movq %%r12,%0" : "=m"(newregs->r12));
+		__asm__ __volatile__("movq %%r13,%0" : "=m"(newregs->r13));
+		__asm__ __volatile__("movq %%r14,%0" : "=m"(newregs->r14));
+		__asm__ __volatile__("movq %%r15,%0" : "=m"(newregs->r15));
+		__asm__ __volatile__("movl %%ss, %%eax;" :"=a"(newregs->ss));
+		__asm__ __volatile__("movl %%cs, %%eax;" :"=a"(newregs->cs));
+		__asm__ __volatile__("pushfq; popq %0" :"=m"(newregs->eflags));
 
+		newregs->rip = (unsigned long)current_text_addr();
+	}
+}
 #endif /* _X86_64_KEXEC_H */
diff --git a/include/asm-x86_64/kprobes.h b/include/asm-x86_64/kprobes.h
index 4dd7a7e148d..98a1e95ddb9 100644
--- a/include/asm-x86_64/kprobes.h
+++ b/include/asm-x86_64/kprobes.h
@@ -27,7 +27,10 @@
 #include <linux/ptrace.h>
 #include <linux/percpu.h>
 
+#define  __ARCH_WANT_KPROBES_INSN_SLOT
+
 struct pt_regs;
+struct kprobe;
 
 typedef u8 kprobe_opcode_t;
 #define BREAKPOINT_INSTRUCTION	0xcc
@@ -42,6 +45,7 @@ typedef u8 kprobe_opcode_t;
 #define ARCH_SUPPORTS_KRETPROBES
 
 void kretprobe_trampoline(void);
+extern void arch_remove_kprobe(struct kprobe *p);
 
 /* Architecture specific copy of original instruction*/
 struct arch_specific_insn {
diff --git a/include/asm-x86_64/mmu_context.h b/include/asm-x86_64/mmu_context.h
index b630d52bdfb..16e4be4de0c 100644
--- a/include/asm-x86_64/mmu_context.h
+++ b/include/asm-x86_64/mmu_context.h
@@ -15,18 +15,13 @@
 int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
 void destroy_context(struct mm_struct *mm);
 
-#ifdef CONFIG_SMP
-
 static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 {
+#ifdef CONFIG_SMP
 	if (read_pda(mmu_state) == TLBSTATE_OK) 
 		write_pda(mmu_state, TLBSTATE_LAZY);
-}
-#else
-static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
-{
-}
 #endif
+}
 
 static inline void load_cr3(pgd_t *pgd)
 {
diff --git a/include/asm-x86_64/mmzone.h b/include/asm-x86_64/mmzone.h
index 69baaa8a3ce..972c9359f7d 100644
--- a/include/asm-x86_64/mmzone.h
+++ b/include/asm-x86_64/mmzone.h
@@ -36,22 +36,12 @@ static inline __attribute__((pure)) int phys_to_nid(unsigned long addr)
 				 NODE_DATA(nid)->node_spanned_pages)
 
 #ifdef CONFIG_DISCONTIGMEM
-
 #define pfn_to_nid(pfn) phys_to_nid((unsigned long)(pfn) << PAGE_SHIFT)
 #define kvaddr_to_nid(kaddr)	phys_to_nid(__pa(kaddr))
 
-/* Requires pfn_valid(pfn) to be true */
-#define pfn_to_page(pfn) ({ \
-	int nid = phys_to_nid(((unsigned long)(pfn)) << PAGE_SHIFT); 	\
-	((pfn) - node_start_pfn(nid)) + NODE_DATA(nid)->node_mem_map;	\
-})
-
-#define page_to_pfn(page) \
-	(long)(((page) - page_zone(page)->zone_mem_map) + page_zone(page)->zone_start_pfn)
-
-#define pfn_valid(pfn) ((pfn) >= num_physpages ? 0 : \
-			({ u8 nid__ = pfn_to_nid(pfn); \
-			   nid__ != 0xff && (pfn) >= node_start_pfn(nid__) && (pfn) < node_end_pfn(nid__); }))
+extern struct page *pfn_to_page(unsigned long pfn);
+extern unsigned long page_to_pfn(struct page *page);
+extern int pfn_valid(unsigned long pfn);
 #endif
 
 #define local_mapnr(kvaddr) \
diff --git a/include/asm-x86_64/mutex.h b/include/asm-x86_64/mutex.h
new file mode 100644
index 00000000000..11fbee2bd6c
--- /dev/null
+++ b/include/asm-x86_64/mutex.h
@@ -0,0 +1,113 @@
+/*
+ * Assembly implementation of the mutex fastpath, based on atomic
+ * decrement/increment.
+ *
+ * started by Ingo Molnar:
+ *
+ *  Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
+ */
+#ifndef _ASM_MUTEX_H
+#define _ASM_MUTEX_H
+
+/**
+ * __mutex_fastpath_lock - decrement and call function if negative
+ * @v: pointer of type atomic_t
+ * @fail_fn: function to call if the result is negative
+ *
+ * Atomically decrements @v and calls <fail_fn> if the result is negative.
+ */
+#define __mutex_fastpath_lock(v, fail_fn)				\
+do {									\
+	unsigned long dummy;						\
+									\
+	typecheck(atomic_t *, v);					\
+	typecheck_fn(fastcall void (*)(atomic_t *), fail_fn);		\
+									\
+	__asm__ __volatile__(						\
+		LOCK	"   decl (%%rdi)	\n"			\
+			"   js 2f		\n"			\
+			"1:			\n"			\
+									\
+		LOCK_SECTION_START("")					\
+			"2: call "#fail_fn"	\n"			\
+			"   jmp 1b		\n"			\
+		LOCK_SECTION_END					\
+									\
+		:"=D" (dummy)						\
+		: "D" (v)						\
+		: "rax", "rsi", "rdx", "rcx",				\
+		  "r8", "r9", "r10", "r11", "memory");			\
+} while (0)
+
+/**
+ *  __mutex_fastpath_lock_retval - try to take the lock by moving the count
+ *                                 from 1 to a 0 value
+ *  @count: pointer of type atomic_t
+ *  @fail_fn: function to call if the original value was not 1
+ *
+ * Change the count from 1 to a value lower than 1, and call <fail_fn> if
+ * it wasn't 1 originally. This function returns 0 if the fastpath succeeds,
+ * or anything the slow path function returns
+ */
+static inline int
+__mutex_fastpath_lock_retval(atomic_t *count,
+			     int fastcall (*fail_fn)(atomic_t *))
+{
+	if (unlikely(atomic_dec_return(count) < 0))
+		return fail_fn(count);
+	else
+		return 0;
+}
+
+/**
+ * __mutex_fastpath_unlock - increment and call function if nonpositive
+ * @v: pointer of type atomic_t
+ * @fail_fn: function to call if the result is nonpositive
+ *
+ * Atomically increments @v and calls <fail_fn> if the result is nonpositive.
+ */
+#define __mutex_fastpath_unlock(v, fail_fn)				\
+do {									\
+	unsigned long dummy;						\
+									\
+	typecheck(atomic_t *, v);					\
+	typecheck_fn(fastcall void (*)(atomic_t *), fail_fn);		\
+									\
+	__asm__ __volatile__(						\
+		LOCK	"   incl (%%rdi)	\n"			\
+			"   jle 2f		\n"			\
+			"1:			\n"			\
+									\
+		LOCK_SECTION_START("")					\
+			"2: call "#fail_fn"	\n"			\
+			"   jmp 1b		\n"			\
+		LOCK_SECTION_END					\
+									\
+		:"=D" (dummy)						\
+		: "D" (v)						\
+		: "rax", "rsi", "rdx", "rcx",				\
+		  "r8", "r9", "r10", "r11", "memory");			\
+} while (0)
+
+#define __mutex_slowpath_needs_to_unlock()	1
+
+/**
+ * __mutex_fastpath_trylock - try to acquire the mutex, without waiting
+ *
+ *  @count: pointer of type atomic_t
+ *  @fail_fn: fallback function
+ *
+ * Change the count from 1 to 0 and return 1 (success), or return 0 (failure)
+ * if it wasn't 1 originally. [the fallback function is never used on
+ * x86_64, because all x86_64 CPUs have a CMPXCHG instruction.]
+ */
+static inline int
+__mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *))
+{
+	if (likely(atomic_cmpxchg(count, 1, 0) == 1))
+		return 1;
+	else
+		return 0;
+}
+
+#endif
diff --git a/include/asm-x86_64/numa.h b/include/asm-x86_64/numa.h
index d51e56fdc3d..34e434ce326 100644
--- a/include/asm-x86_64/numa.h
+++ b/include/asm-x86_64/numa.h
@@ -20,6 +20,11 @@ extern int numa_off;
 extern void numa_set_node(int cpu, int node);
 
 extern unsigned char apicid_to_node[256];
+#ifdef CONFIG_NUMA
+extern void __init init_cpu_to_node(void);
+#else
+#define init_cpu_to_node() do {} while (0)
+#endif
 
 #define NUMA_NO_NODE 0xff
 
diff --git a/include/asm-x86_64/page.h b/include/asm-x86_64/page.h
index 06e489f3247..615e3e49492 100644
--- a/include/asm-x86_64/page.h
+++ b/include/asm-x86_64/page.h
@@ -14,13 +14,25 @@
 #define PHYSICAL_PAGE_MASK	(~(PAGE_SIZE-1) & __PHYSICAL_MASK)
 
 #define THREAD_ORDER 1 
-#ifdef __ASSEMBLY__
-#define THREAD_SIZE  (1 << (PAGE_SHIFT + THREAD_ORDER))
-#else
-#define THREAD_SIZE  (1UL << (PAGE_SHIFT + THREAD_ORDER))
-#endif
+#define THREAD_SIZE  (PAGE_SIZE << THREAD_ORDER)
 #define CURRENT_MASK (~(THREAD_SIZE-1))
 
+#define EXCEPTION_STACK_ORDER 0
+#define EXCEPTION_STKSZ (PAGE_SIZE << EXCEPTION_STACK_ORDER)
+
+#define DEBUG_STACK_ORDER EXCEPTION_STACK_ORDER
+#define DEBUG_STKSZ (PAGE_SIZE << DEBUG_STACK_ORDER)
+
+#define IRQSTACK_ORDER 2
+#define IRQSTACKSIZE (PAGE_SIZE << IRQSTACK_ORDER)
+
+#define STACKFAULT_STACK 1
+#define DOUBLEFAULT_STACK 2
+#define NMI_STACK 3
+#define DEBUG_STACK 4
+#define MCE_STACK 5
+#define N_EXCEPTION_STACKS 5  /* hw limit: 7 */
+
 #define LARGE_PAGE_MASK (~(LARGE_PAGE_SIZE-1))
 #define LARGE_PAGE_SIZE (1UL << PMD_SHIFT)
 
diff --git a/include/asm-x86_64/pci.h b/include/asm-x86_64/pci.h
index eeb3088a1c9..fd03e15d7ea 100644
--- a/include/asm-x86_64/pci.h
+++ b/include/asm-x86_64/pci.h
@@ -42,18 +42,20 @@ int pcibios_set_irq_routing(struct pci_dev *dev, int pin, int irq);
 #include <asm/scatterlist.h>
 #include <linux/string.h>
 #include <asm/page.h>
+#include <linux/dma-mapping.h> /* for have_iommu */
 
 extern int iommu_setup(char *opt);
 
-#ifdef CONFIG_GART_IOMMU
 /* The PCI address space does equal the physical memory
  * address space.  The networking and block device layers use
  * this boolean for bounce buffer decisions
  *
- * On AMD64 it mostly equals, but we set it to zero to tell some subsystems
- * that an IOMMU is available.
+ * On AMD64 it mostly equals, but we set it to zero if a hardware
+ * IOMMU (gart) of sotware IOMMU (swiotlb) is available.
  */
-#define PCI_DMA_BUS_IS_PHYS	(no_iommu ? 1 : 0)
+#define PCI_DMA_BUS_IS_PHYS (dma_ops->is_phys)
+
+#ifdef CONFIG_GART_IOMMU
 
 /*
  * x86-64 always supports DAC, but sometimes it is useful to force
@@ -79,7 +81,6 @@ extern int iommu_sac_force;
 #else
 /* No IOMMU */
 
-#define PCI_DMA_BUS_IS_PHYS	1
 #define pci_dac_dma_supported(pci_dev, mask)    1
 
 #define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)
diff --git a/include/asm-x86_64/pda.h b/include/asm-x86_64/pda.h
index 8733ccfa442..c7ab38a601a 100644
--- a/include/asm-x86_64/pda.h
+++ b/include/asm-x86_64/pda.h
@@ -5,6 +5,7 @@
 #include <linux/stddef.h>
 #include <linux/types.h>
 #include <linux/cache.h>
+#include <asm/page.h>
 
 /* Per processor datastructure. %gs points to it while the kernel runs */ 
 struct x8664_pda {
@@ -12,6 +13,9 @@ struct x8664_pda {
 	unsigned long data_offset;	/* Per cpu data offset from linker address */
 	unsigned long kernelstack;  /* top of kernel stack for current */ 
 	unsigned long oldrsp; 	    /* user rsp for system call */
+#if DEBUG_STKSZ > EXCEPTION_STKSZ
+	unsigned long debugstack;   /* #DB/#BP stack. */
+#endif
         int irqcount;		    /* Irq nesting counter. Starts with -1 */  	
 	int cpunumber;		    /* Logical CPU number */
 	char *irqstackptr;	/* top of irqstack */
@@ -23,11 +27,10 @@ struct x8664_pda {
 	unsigned apic_timer_irqs;
 } ____cacheline_aligned_in_smp;
 
+extern struct x8664_pda *_cpu_pda[];
+extern struct x8664_pda boot_cpu_pda[];
 
-#define IRQSTACK_ORDER 2
-#define IRQSTACKSIZE (PAGE_SIZE << IRQSTACK_ORDER) 
-
-extern struct x8664_pda cpu_pda[];
+#define cpu_pda(i) (_cpu_pda[i])
 
 /* 
  * There is no fast way to get the base address of the PDA, all the accesses
diff --git a/include/asm-x86_64/percpu.h b/include/asm-x86_64/percpu.h
index 9c71855736f..29a6b0408f7 100644
--- a/include/asm-x86_64/percpu.h
+++ b/include/asm-x86_64/percpu.h
@@ -11,7 +11,7 @@
 
 #include <asm/pda.h>
 
-#define __per_cpu_offset(cpu) (cpu_pda[cpu].data_offset)
+#define __per_cpu_offset(cpu) (cpu_pda(cpu)->data_offset)
 #define __my_cpu_offset() read_pda(data_offset)
 
 /* Separate out the type, so (int[3], foo) works. */
diff --git a/include/asm-x86_64/pgtable.h b/include/asm-x86_64/pgtable.h
index 02888d7a496..8fbf4dd7211 100644
--- a/include/asm-x86_64/pgtable.h
+++ b/include/asm-x86_64/pgtable.h
@@ -267,25 +267,25 @@ static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot)
  */
 #define __LARGE_PTE (_PAGE_PSE|_PAGE_PRESENT)
 static inline int pte_user(pte_t pte)		{ return pte_val(pte) & _PAGE_USER; }
-extern inline int pte_read(pte_t pte)		{ return pte_val(pte) & _PAGE_USER; }
-extern inline int pte_exec(pte_t pte)		{ return pte_val(pte) & _PAGE_USER; }
-extern inline int pte_dirty(pte_t pte)		{ return pte_val(pte) & _PAGE_DIRTY; }
-extern inline int pte_young(pte_t pte)		{ return pte_val(pte) & _PAGE_ACCESSED; }
-extern inline int pte_write(pte_t pte)		{ return pte_val(pte) & _PAGE_RW; }
+static inline int pte_read(pte_t pte)		{ return pte_val(pte) & _PAGE_USER; }
+static inline int pte_exec(pte_t pte)		{ return pte_val(pte) & _PAGE_USER; }
+static inline int pte_dirty(pte_t pte)		{ return pte_val(pte) & _PAGE_DIRTY; }
+static inline int pte_young(pte_t pte)		{ return pte_val(pte) & _PAGE_ACCESSED; }
+static inline int pte_write(pte_t pte)		{ return pte_val(pte) & _PAGE_RW; }
 static inline int pte_file(pte_t pte)		{ return pte_val(pte) & _PAGE_FILE; }
 static inline int pte_huge(pte_t pte)		{ return (pte_val(pte) & __LARGE_PTE) == __LARGE_PTE; }
 
-extern inline pte_t pte_rdprotect(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_USER)); return pte; }
-extern inline pte_t pte_exprotect(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_USER)); return pte; }
-extern inline pte_t pte_mkclean(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_DIRTY)); return pte; }
-extern inline pte_t pte_mkold(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_ACCESSED)); return pte; }
-extern inline pte_t pte_wrprotect(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_RW)); return pte; }
-extern inline pte_t pte_mkread(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _PAGE_USER)); return pte; }
-extern inline pte_t pte_mkexec(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _PAGE_USER)); return pte; }
-extern inline pte_t pte_mkdirty(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _PAGE_DIRTY)); return pte; }
-extern inline pte_t pte_mkyoung(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _PAGE_ACCESSED)); return pte; }
-extern inline pte_t pte_mkwrite(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _PAGE_RW)); return pte; }
-extern inline pte_t pte_mkhuge(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | __LARGE_PTE)); return pte; }
+static inline pte_t pte_rdprotect(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_USER)); return pte; }
+static inline pte_t pte_exprotect(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_USER)); return pte; }
+static inline pte_t pte_mkclean(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_DIRTY)); return pte; }
+static inline pte_t pte_mkold(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_ACCESSED)); return pte; }
+static inline pte_t pte_wrprotect(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_RW)); return pte; }
+static inline pte_t pte_mkread(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _PAGE_USER)); return pte; }
+static inline pte_t pte_mkexec(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _PAGE_USER)); return pte; }
+static inline pte_t pte_mkdirty(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _PAGE_DIRTY)); return pte; }
+static inline pte_t pte_mkyoung(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _PAGE_ACCESSED)); return pte; }
+static inline pte_t pte_mkwrite(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _PAGE_RW)); return pte; }
+static inline pte_t pte_mkhuge(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | __LARGE_PTE)); return pte; }
 
 struct vm_area_struct;
 
diff --git a/include/asm-x86_64/processor.h b/include/asm-x86_64/processor.h
index 4861246548f..8c8d88c036e 100644
--- a/include/asm-x86_64/processor.h
+++ b/include/asm-x86_64/processor.h
@@ -227,7 +227,13 @@ struct tss_struct {
 extern struct cpuinfo_x86 boot_cpu_data;
 DECLARE_PER_CPU(struct tss_struct,init_tss);
 
+#ifdef CONFIG_X86_VSMP
+#define ARCH_MIN_TASKALIGN	(1 << INTERNODE_CACHE_SHIFT)
+#define ARCH_MIN_MMSTRUCT_ALIGN	(1 << INTERNODE_CACHE_SHIFT)
+#else
 #define ARCH_MIN_TASKALIGN	16
+#define ARCH_MIN_MMSTRUCT_ALIGN	0
+#endif
 
 struct thread_struct {
 	unsigned long	rsp0;
@@ -267,15 +273,6 @@ struct thread_struct {
 #define INIT_MMAP \
 { &init_mm, 0, 0, NULL, PAGE_SHARED, VM_READ | VM_WRITE | VM_EXEC, 1, NULL, NULL }
 
-#define STACKFAULT_STACK 1
-#define DOUBLEFAULT_STACK 2 
-#define NMI_STACK 3 
-#define DEBUG_STACK 4 
-#define MCE_STACK 5
-#define N_EXCEPTION_STACKS 5  /* hw limit: 7 */
-#define EXCEPTION_STKSZ (PAGE_SIZE << EXCEPTION_STACK_ORDER)
-#define EXCEPTION_STACK_ORDER 0 
-
 #define start_thread(regs,new_rip,new_rsp) do { \
 	asm volatile("movl %0,%%fs; movl %0,%%es; movl %0,%%ds": :"r" (0));	 \
 	load_gs_index(0);							\
@@ -317,8 +314,8 @@ extern long kernel_thread(int (*fn)(void *), void * arg, unsigned long flags);
 #define thread_saved_pc(t) (*(unsigned long *)((t)->thread.rsp - 8))
 
 extern unsigned long get_wchan(struct task_struct *p);
-#define KSTK_EIP(tsk) \
-	(((struct pt_regs *)(tsk->thread.rsp0 - sizeof(struct pt_regs)))->rip)
+#define task_pt_regs(tsk) ((struct pt_regs *)(tsk)->thread.rsp0 - 1)
+#define KSTK_EIP(tsk) (task_pt_regs(tsk)->rip)
 #define KSTK_ESP(tsk) -1 /* sorry. doesn't work for syscall. */
 
 
@@ -480,4 +477,6 @@ extern unsigned long boot_option_idle_override;
 /* Boot loader type from the setup header */
 extern int bootloader_type;
 
+#define HAVE_ARCH_PICK_MMAP_LAYOUT 1
+
 #endif /* __ASM_X86_64_PROCESSOR_H */
diff --git a/include/asm-x86_64/proto.h b/include/asm-x86_64/proto.h
index 34501086afe..115e496c613 100644
--- a/include/asm-x86_64/proto.h
+++ b/include/asm-x86_64/proto.h
@@ -67,8 +67,6 @@ extern void load_gs_index(unsigned gs);
 
 extern unsigned long end_pfn_map; 
 
-extern cpumask_t cpu_initialized;
-
 extern void show_trace(unsigned long * rsp);
 extern void show_registers(struct pt_regs *regs);
 
@@ -91,8 +89,12 @@ extern void check_efer(void);
 
 extern int unhandled_signal(struct task_struct *tsk, int sig);
 
+extern int unsynchronized_tsc(void);
+
 extern void select_idle_routine(const struct cpuinfo_x86 *c);
-extern void swiotlb_init(void);
+
+extern void gart_parse_options(char *);
+extern void __init no_iommu_init(void);
 
 extern unsigned long table_start, table_end;
 
@@ -106,12 +108,17 @@ extern int skip_ioapic_setup;
 extern int acpi_ht;
 extern int acpi_disabled;
 
+#ifdef CONFIG_GART_IOMMU
 extern int fallback_aper_order;
 extern int fallback_aper_force;
 extern int iommu_aperture;
-extern int iommu_aperture_disabled;
 extern int iommu_aperture_allowed;
+extern int iommu_aperture_disabled;
 extern int fix_aperture;
+#else
+#define iommu_aperture 0
+#define iommu_aperture_allowed 0
+#endif
 extern int force_iommu;
 
 extern int reboot_force;
diff --git a/include/asm-x86_64/segment.h b/include/asm-x86_64/segment.h
index 44adaf18c11..d4bed33fb32 100644
--- a/include/asm-x86_64/segment.h
+++ b/include/asm-x86_64/segment.h
@@ -19,15 +19,13 @@
 #define __USER_DS     0x2b   /* 5*8+3 */ 
 #define __USER_CS     0x33   /* 6*8+3 */ 
 #define __USER32_DS	__USER_DS 
-#define __KERNEL16_CS	(GDT_ENTRY_KERNELCS16 * 8)
-#define __KERNEL_COMPAT32_CS   0x8
 
 #define GDT_ENTRY_TLS 1
 #define GDT_ENTRY_TSS 8	/* needs two entries */
 #define GDT_ENTRY_LDT 10 /* needs two entries */
 #define GDT_ENTRY_TLS_MIN 12
 #define GDT_ENTRY_TLS_MAX 14
-#define GDT_ENTRY_KERNELCS16 15
+/* 15 free */
 
 #define GDT_ENTRY_TLS_ENTRIES 3
 
diff --git a/include/asm-x86_64/smp.h b/include/asm-x86_64/smp.h
index d030409a8fb..9ccbb2cfd5c 100644
--- a/include/asm-x86_64/smp.h
+++ b/include/asm-x86_64/smp.h
@@ -35,6 +35,7 @@ extern cpumask_t cpu_present_mask;
 extern cpumask_t cpu_possible_map;
 extern cpumask_t cpu_online_map;
 extern cpumask_t cpu_callout_map;
+extern cpumask_t cpu_initialized;
 
 /*
  * Private routines/data
diff --git a/include/asm-x86_64/swiotlb.h b/include/asm-x86_64/swiotlb.h
index dddf1b21868..60757efd135 100644
--- a/include/asm-x86_64/swiotlb.h
+++ b/include/asm-x86_64/swiotlb.h
@@ -3,10 +3,14 @@
 
 #include <linux/config.h>
 
+#include <asm/dma-mapping.h>
+
 /* SWIOTLB interface */
 
-extern dma_addr_t swiotlb_map_single(struct device *hwdev, void *ptr, size_t size,
-				      int dir);
+extern dma_addr_t swiotlb_map_single(struct device *hwdev, void *ptr,
+				     size_t size, int dir);
+extern void *swiotlb_alloc_coherent(struct device *hwdev, size_t size,
+                       dma_addr_t *dma_handle, gfp_t flags);
 extern void swiotlb_unmap_single(struct device *hwdev, dma_addr_t dev_addr,
 				  size_t size, int dir);
 extern void swiotlb_sync_single_for_cpu(struct device *hwdev,
@@ -34,10 +38,10 @@ extern int swiotlb_map_sg(struct device *hwdev, struct scatterlist *sg,
 extern void swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sg,
 			 int nents, int direction);
 extern int swiotlb_dma_mapping_error(dma_addr_t dma_addr);
-extern void *swiotlb_alloc_coherent (struct device *hwdev, size_t size,
-				     dma_addr_t *dma_handle, gfp_t flags);
 extern void swiotlb_free_coherent (struct device *hwdev, size_t size,
 				   void *vaddr, dma_addr_t dma_handle);
+extern int swiotlb_dma_supported(struct device *hwdev, u64 mask);
+extern void swiotlb_init(void);
 
 #ifdef CONFIG_SWIOTLB
 extern int swiotlb;
@@ -45,4 +49,6 @@ extern int swiotlb;
 #define swiotlb 0
 #endif
 
-#endif
+extern void pci_swiotlb_init(void);
+
+#endif /* _ASM_SWTIOLB_H */
diff --git a/include/asm-x86_64/system.h b/include/asm-x86_64/system.h
index b34cc2ee222..a73f0c789d8 100644
--- a/include/asm-x86_64/system.h
+++ b/include/asm-x86_64/system.h
@@ -20,8 +20,8 @@
 #define __RESTORE(reg,offset) "movq (14-" #offset ")*8(%%rsp),%%" #reg "\n\t"
 
 /* frame pointer must be last for get_wchan */
-#define SAVE_CONTEXT    "pushfq ; pushq %%rbp ; movq %%rsi,%%rbp\n\t"
-#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp ; popfq\n\t" 
+#define SAVE_CONTEXT    "pushq %%rbp ; movq %%rsi,%%rbp\n\t"
+#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp\n\t"
 
 #define __EXTRA_CLOBBER  \
 	,"rcx","rbx","rdx","r8","r9","r10","r11","r12","r13","r14","r15"
@@ -137,6 +137,21 @@ struct alt_instr {
 		      "663:\n\t" newinstr "\n664:\n"   /* replacement */ \
 		      ".previous" :: "i" (feature), ##input)
 
+/* Like alternative_input, but with a single output argument */
+#define alternative_io(oldinstr, newinstr, feature, output, input...) \
+	asm volatile ("661:\n\t" oldinstr "\n662:\n"			\
+		      ".section .altinstructions,\"a\"\n"		\
+		      "  .align 8\n"					\
+		      "  .quad 661b\n"            /* label */		\
+		      "  .quad 663f\n"		  /* new instruction */	\
+		      "  .byte %c[feat]\n"        /* feature bit */	\
+		      "  .byte 662b-661b\n"       /* sourcelen */	\
+		      "  .byte 664f-663f\n"       /* replacementlen */	\
+		      ".previous\n"					\
+		      ".section .altinstr_replacement,\"ax\"\n"		\
+		      "663:\n\t" newinstr "\n664:\n"   /* replacement */ \
+		      ".previous" : output : [feat] "i" (feature), ##input)
+
 /*
  * Clear and set 'TS' bit respectively
  */
@@ -178,6 +193,15 @@ static inline void write_cr4(unsigned long val)
 #define wbinvd() \
 	__asm__ __volatile__ ("wbinvd": : :"memory");
 
+/*
+ * On SMP systems, when the scheduler does migration-cost autodetection,
+ * it needs a way to flush as much of the CPU's caches as possible.
+ */
+static inline void sched_cacheflush(void)
+{
+	wbinvd();
+}
+
 #endif	/* __KERNEL__ */
 
 #define nop() __asm__ __volatile__ ("nop")
@@ -311,12 +335,24 @@ static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
 /* interrupt control.. */
 #define local_save_flags(x)	do { warn_if_not_ulong(x); __asm__ __volatile__("# save_flags \n\t pushfq ; popq %q0":"=g" (x): /* no input */ :"memory"); } while (0)
 #define local_irq_restore(x) 	__asm__ __volatile__("# restore_flags \n\t pushq %0 ; popfq": /* no output */ :"g" (x):"memory", "cc")
+
+#ifdef CONFIG_X86_VSMP
+/* Interrupt control for VSMP  architecture */
+#define local_irq_disable()	do { unsigned long flags; local_save_flags(flags); local_irq_restore((flags & ~(1 << 9)) | (1 << 18)); } while (0)
+#define local_irq_enable()	do { unsigned long flags; local_save_flags(flags); local_irq_restore((flags | (1 << 9)) & ~(1 << 18)); } while (0)
+
+#define irqs_disabled()					\
+({							\
+	unsigned long flags;				\
+	local_save_flags(flags);			\
+	(flags & (1<<18)) || !(flags & (1<<9));		\
+})
+
+/* For spinlocks etc */
+#define local_irq_save(x)	do { local_save_flags(x); local_irq_restore((x & ~(1 << 9)) | (1 << 18)); } while (0)
+#else  /* CONFIG_X86_VSMP */
 #define local_irq_disable() 	__asm__ __volatile__("cli": : :"memory")
 #define local_irq_enable()	__asm__ __volatile__("sti": : :"memory")
-/* used in the idle loop; sti takes one instruction cycle to complete */
-#define safe_halt()		__asm__ __volatile__("sti; hlt": : :"memory")
-/* used when interrupts are already enabled or to shutdown the processor */
-#define halt()			__asm__ __volatile__("hlt": : :"memory")
 
 #define irqs_disabled()			\
 ({					\
@@ -327,15 +363,14 @@ static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
 
 /* For spinlocks etc */
 #define local_irq_save(x) 	do { warn_if_not_ulong(x); __asm__ __volatile__("# local_irq_save \n\t pushfq ; popq %0 ; cli":"=g" (x): /* no input */ :"memory"); } while (0)
+#endif
 
-void cpu_idle_wait(void);
+/* used in the idle loop; sti takes one instruction cycle to complete */
+#define safe_halt()		__asm__ __volatile__("sti; hlt": : :"memory")
+/* used when interrupts are already enabled or to shutdown the processor */
+#define halt()			__asm__ __volatile__("hlt": : :"memory")
 
-/*
- * disable hlt during certain critical i/o operations
- */
-#define HAVE_DISABLE_HLT
-void disable_hlt(void);
-void enable_hlt(void);
+void cpu_idle_wait(void);
 
 extern unsigned long arch_align_stack(unsigned long sp);
 
diff --git a/include/asm-x86_64/thread_info.h b/include/asm-x86_64/thread_info.h
index 08eb6e4f373..4ac0e0a3693 100644
--- a/include/asm-x86_64/thread_info.h
+++ b/include/asm-x86_64/thread_info.h
@@ -76,8 +76,6 @@ static inline struct thread_info *stack_thread_info(void)
 #define alloc_thread_info(tsk) \
 	((struct thread_info *) __get_free_pages(GFP_KERNEL,THREAD_ORDER))
 #define free_thread_info(ti) free_pages((unsigned long) (ti), THREAD_ORDER)
-#define get_thread_info(ti) get_task_struct((ti)->task)
-#define put_thread_info(ti) put_task_struct((ti)->task)
 
 #else /* !__ASSEMBLY__ */
 
@@ -138,6 +136,7 @@ static inline struct thread_info *stack_thread_info(void)
  * have to worry about atomic accesses.
  */
 #define TS_USEDFPU		0x0001	/* FPU was used by this task this quantum (SMP) */
+#define TS_COMPAT		0x0002	/* 32bit syscall active */
 
 #endif /* __KERNEL__ */
 
diff --git a/include/asm-x86_64/timex.h b/include/asm-x86_64/timex.h
index f971f45d6d7..f18443fcdf0 100644
--- a/include/asm-x86_64/timex.h
+++ b/include/asm-x86_64/timex.h
@@ -10,6 +10,9 @@
 #include <asm/msr.h>
 #include <asm/vsyscall.h>
 #include <asm/hpet.h>
+#include <asm/system.h>
+#include <asm/processor.h>
+#include <linux/compiler.h>
 
 #define CLOCK_TICK_RATE	PIT_TICK_RATE	/* Underlying HZ */
 
@@ -23,6 +26,19 @@ static inline cycles_t get_cycles (void)
 	return ret;
 }
 
+/* Like get_cycles, but make sure the CPU is synchronized. */
+static __always_inline cycles_t get_cycles_sync(void)
+{
+	unsigned long long ret;
+	unsigned eax;
+	/* Don't do an additional sync on CPUs where we know
+	   RDTSC is already synchronous. */
+	alternative_io(ASM_NOP2, "cpuid", X86_FEATURE_SYNC_RDTSC,
+			  "=a" (eax), "0" (1) : "ebx","ecx","edx","memory");
+	rdtscll(ret);
+	return ret;
+}
+
 extern unsigned int cpu_khz;
 
 extern int read_current_timer(unsigned long *timer_value);
diff --git a/include/asm-x86_64/topology.h b/include/asm-x86_64/topology.h
index 7d82bc56b9f..2fa7f27381b 100644
--- a/include/asm-x86_64/topology.h
+++ b/include/asm-x86_64/topology.h
@@ -39,7 +39,6 @@ extern int __node_distance(int, int);
 	.max_interval		= 32,			\
 	.busy_factor		= 32,			\
 	.imbalance_pct		= 125,			\
-	.cache_hot_time		= (10*1000000),		\
 	.cache_nice_tries	= 2,			\
 	.busy_idx		= 3,			\
 	.idle_idx		= 2,			\
diff --git a/include/asm-x86_64/uaccess.h b/include/asm-x86_64/uaccess.h
index 1bb8b8a2443..bddffcb591b 100644
--- a/include/asm-x86_64/uaccess.h
+++ b/include/asm-x86_64/uaccess.h
@@ -244,7 +244,7 @@ extern unsigned long copy_to_user(void __user *to, const void *from, unsigned le
 extern unsigned long copy_from_user(void *to, const void __user *from, unsigned len); 
 extern unsigned long copy_in_user(void __user *to, const void __user *from, unsigned len); 
 
-static inline int __copy_from_user(void *dst, const void __user *src, unsigned size) 
+static __always_inline int __copy_from_user(void *dst, const void __user *src, unsigned size)
 { 
        int ret = 0;
 	if (!__builtin_constant_p(size))
@@ -273,7 +273,7 @@ static inline int __copy_from_user(void *dst, const void __user *src, unsigned s
 	}
 }	
 
-static inline int __copy_to_user(void __user *dst, const void *src, unsigned size) 
+static __always_inline int __copy_to_user(void __user *dst, const void *src, unsigned size)
 { 
        int ret = 0;
 	if (!__builtin_constant_p(size))
@@ -305,7 +305,7 @@ static inline int __copy_to_user(void __user *dst, const void *src, unsigned siz
 }	
 
 
-static inline int __copy_in_user(void __user *dst, const void __user *src, unsigned size) 
+static __always_inline int __copy_in_user(void __user *dst, const void __user *src, unsigned size)
 { 
        int ret = 0;
 	if (!__builtin_constant_p(size))
@@ -348,6 +348,7 @@ static inline int __copy_in_user(void __user *dst, const void __user *src, unsig
 long strncpy_from_user(char *dst, const char __user *src, long count);
 long __strncpy_from_user(char *dst, const char __user *src, long count);
 long strnlen_user(const char __user *str, long n);
+long __strnlen_user(const char __user *str, long n);
 long strlen_user(const char __user *str);
 unsigned long clear_user(void __user *mem, unsigned long len);
 unsigned long __clear_user(void __user *mem, unsigned long len);
diff --git a/include/asm-x86_64/unistd.h b/include/asm-x86_64/unistd.h
index 2c42150bce0..436d099b5b6 100644
--- a/include/asm-x86_64/unistd.h
+++ b/include/asm-x86_64/unistd.h
@@ -571,8 +571,37 @@ __SYSCALL(__NR_inotify_init, sys_inotify_init)
 __SYSCALL(__NR_inotify_add_watch, sys_inotify_add_watch)
 #define __NR_inotify_rm_watch	255
 __SYSCALL(__NR_inotify_rm_watch, sys_inotify_rm_watch)
+#define __NR_migrate_pages	256
+__SYSCALL(__NR_migrate_pages, sys_migrate_pages)
+#define __NR_openat		257
+__SYSCALL(__NR_openat, sys_openat)
+#define __NR_mkdirat		258
+__SYSCALL(__NR_mkdirat, sys_mkdirat)
+#define __NR_mknodat		259
+__SYSCALL(__NR_mknodat, sys_mknodat)
+#define __NR_fchownat		260
+__SYSCALL(__NR_fchownat, sys_fchownat)
+#define __NR_futimesat		261
+__SYSCALL(__NR_futimesat, sys_futimesat)
+#define __NR_newfstatat		262
+__SYSCALL(__NR_newfstatat, sys_newfstatat)
+#define __NR_unlinkat		263
+__SYSCALL(__NR_unlinkat, sys_unlinkat)
+#define __NR_renameat		264
+__SYSCALL(__NR_renameat, sys_renameat)
+#define __NR_linkat		265
+__SYSCALL(__NR_linkat, sys_linkat)
+#define __NR_symlinkat		266
+__SYSCALL(__NR_symlinkat, sys_symlinkat)
+#define __NR_readlinkat		267
+__SYSCALL(__NR_readlinkat, sys_readlinkat)
+#define __NR_fchmodat		268
+__SYSCALL(__NR_fchmodat, sys_fchmodat)
+#define __NR_faccessat		269
+__SYSCALL(__NR_faccessat, sys_faccessat)
+
+#define __NR_syscall_max __NR_faccessat
 
-#define __NR_syscall_max __NR_inotify_rm_watch
 #ifndef __NO_STUBS
 
 /* user-visible error numbers are in the range -1 - -4095 */
diff --git a/include/asm-x86_64/vsyscall.h b/include/asm-x86_64/vsyscall.h
index 438a3f52f83..a85e16f56d7 100644
--- a/include/asm-x86_64/vsyscall.h
+++ b/include/asm-x86_64/vsyscall.h
@@ -36,8 +36,8 @@ struct vxtime_data {
 	int mode;
 };
 
-#define hpet_readl(a)           readl((void *)fix_to_virt(FIX_HPET_BASE) + a)
-#define hpet_writel(d,a)        writel(d, (void *)fix_to_virt(FIX_HPET_BASE) + a)
+#define hpet_readl(a)           readl((const void __iomem *)fix_to_virt(FIX_HPET_BASE) + a)
+#define hpet_writel(d,a)        writel(d, (void __iomem *)fix_to_virt(FIX_HPET_BASE) + a)
 
 /* vsyscall space (readonly) */
 extern struct vxtime_data __vxtime;