20 files changed, 108 insertions, 85 deletions

diff --git a/include/asm-x86_64/apicdef.h b/include/asm-x86_64/apicdef.h
index decaa2d540e..5a48e9bcf21 100644
--- a/include/asm-x86_64/apicdef.h
+++ b/include/asm-x86_64/apicdef.h
@@ -39,6 +39,7 @@
 #define			APIC_SPIV_FOCUS_DISABLED	(1<<9)
 #define			APIC_SPIV_APIC_ENABLED		(1<<8)
 #define		APIC_ISR	0x100
+#define		APIC_ISR_NR	0x8	/* Number of 32 bit ISR registers. */
 #define		APIC_TMR	0x180
 #define 	APIC_IRR	0x200
 #define 	APIC_ESR	0x280
diff --git a/include/asm-x86_64/atomic.h b/include/asm-x86_64/atomic.h
index 4b5cd553e77..cecbf7baa6a 100644
--- a/include/asm-x86_64/atomic.h
+++ b/include/asm-x86_64/atomic.h
@@ -405,8 +405,14 @@ static __inline__ long atomic64_sub_return(long i, atomic64_t *v)
 ({								\
 	int c, old;						\
 	c = atomic_read(v);					\
-	while (c != (u) && (old = atomic_cmpxchg((v), c, c + (a))) != c) \
+	for (;;) {						\
+		if (unlikely(c == (u)))				\
+			break;					\
+		old = atomic_cmpxchg((v), c, c + (a));		\
+		if (likely(old == c))				\
+			break;					\
 		c = old;					\
+	}							\
 	c != (u);						\
 })
 #define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
diff --git a/include/asm-x86_64/cache.h b/include/asm-x86_64/cache.h
index 263f0a211ed..c8043a16152 100644
--- a/include/asm-x86_64/cache.h
+++ b/include/asm-x86_64/cache.h
@@ -20,6 +20,8 @@
        __attribute__((__section__(".data.page_aligned")))
 #endif
 
+#define __read_mostly __attribute__((__section__(".data.read_mostly")))
+
 #endif
 
 #endif
diff --git a/include/asm-x86_64/dmi.h b/include/asm-x86_64/dmi.h
new file mode 100644
index 00000000000..93b2b15d432
--- /dev/null
+++ b/include/asm-x86_64/dmi.h
@@ -0,0 +1,27 @@
+#ifndef _ASM_DMI_H
+#define _ASM_DMI_H 1
+
+#include <asm/io.h>
+
+extern void *dmi_ioremap(unsigned long addr, unsigned long size);
+extern void dmi_iounmap(void *addr, unsigned long size);
+
+#define DMI_MAX_DATA 2048
+
+extern int dmi_alloc_index;
+extern char dmi_alloc_data[DMI_MAX_DATA];
+
+/* This is so early that there is no good way to allocate dynamic memory. 
+   Allocate data in an BSS array. */
+static inline void *dmi_alloc(unsigned len)
+{
+	int idx = dmi_alloc_index;
+	if ((dmi_alloc_index += len) > DMI_MAX_DATA)
+		return NULL;
+	return dmi_alloc_data + idx;
+}
+
+#define dmi_ioremap early_ioremap
+#define dmi_iounmap early_iounmap
+
+#endif
diff --git a/include/asm-x86_64/elf.h b/include/asm-x86_64/elf.h
index 43862cd6a56..c98633af07d 100644
--- a/include/asm-x86_64/elf.h
+++ b/include/asm-x86_64/elf.h
@@ -8,6 +8,7 @@
 #include <asm/ptrace.h>
 #include <asm/user.h>
 #include <asm/processor.h>
+#include <asm/compat.h>
 
 /* x86-64 relocation types */
 #define R_X86_64_NONE		0	/* No reloc */
@@ -157,6 +158,9 @@ extern int dump_task_fpu (struct task_struct *, elf_fpregset_t *);
 #define ELF_CORE_COPY_TASK_REGS(tsk, elf_regs) dump_task_regs(tsk, elf_regs)
 #define ELF_CORE_COPY_FPREGS(tsk, elf_fpregs) dump_task_fpu(tsk, elf_fpregs)
 
+/* 1GB for 64bit, 8MB for 32bit */
+#define STACK_RND_MASK (is_compat_task() ? 0x7ff : 0x3fffff)
+
 #endif
 
 #endif
diff --git a/include/asm-x86_64/floppy.h b/include/asm-x86_64/floppy.h
index af7ded63b51..52825ce689f 100644
--- a/include/asm-x86_64/floppy.h
+++ b/include/asm-x86_64/floppy.h
@@ -155,7 +155,7 @@ static int fd_request_irq(void)
 
 static unsigned long dma_mem_alloc(unsigned long size)
 {
-	return __get_dma_pages(GFP_KERNEL,get_order(size));
+	return __get_dma_pages(GFP_KERNEL|__GFP_NORETRY,get_order(size));
 }
 
 
diff --git a/include/asm-x86_64/io.h b/include/asm-x86_64/io.h
index 9dac18db829..cafdfb37f0d 100644
--- a/include/asm-x86_64/io.h
+++ b/include/asm-x86_64/io.h
@@ -135,6 +135,9 @@ static inline void __iomem * ioremap (unsigned long offset, unsigned long size)
 	return __ioremap(offset, size, 0);
 }
 
+extern void *early_ioremap(unsigned long addr, unsigned long size);
+extern void early_iounmap(void *addr, unsigned long size);
+
 /*
  * This one maps high address device memory and turns off caching for that area.
  * it's useful if some control registers are in such an area and write combining
@@ -143,11 +146,6 @@ 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.
  */
@@ -202,23 +200,6 @@ static inline __u64 __readq(const volatile void __iomem *addr)
 
 #define mmiowb()
 
-#ifdef CONFIG_UNORDERED_IO
-static inline void __writel(__u32 val, volatile void __iomem *addr)
-{
-	volatile __u32 __iomem *target = addr;
-	asm volatile("movnti %1,%0"
-		     : "=m" (*target)
-		     : "r" (val) : "memory");
-}
-
-static inline void __writeq(__u64 val, volatile void __iomem *addr)
-{
-	volatile __u64 __iomem *target = addr;
-	asm volatile("movnti %1,%0"
-		     : "=m" (*target)
-		     : "r" (val) : "memory");
-}
-#else
 static inline void __writel(__u32 b, volatile void __iomem *addr)
 {
 	*(__force volatile __u32 *)addr = b;
@@ -227,7 +208,6 @@ static inline void __writeq(__u64 b, volatile void __iomem *addr)
 {
 	*(__force volatile __u64 *)addr = b;
 }
-#endif
 static inline void __writeb(__u8 b, volatile void __iomem *addr)
 {
 	*(__force volatile __u8 *)addr = b;
@@ -269,23 +249,11 @@ void memset_io(volatile void __iomem *a, int b, size_t c);
  */
 #define __ISA_IO_base ((char __iomem *)(PAGE_OFFSET))
 
-#define isa_readb(a) readb(__ISA_IO_base + (a))
-#define isa_readw(a) readw(__ISA_IO_base + (a))
-#define isa_readl(a) readl(__ISA_IO_base + (a))
-#define isa_writeb(b,a) writeb(b,__ISA_IO_base + (a))
-#define isa_writew(w,a) writew(w,__ISA_IO_base + (a))
-#define isa_writel(l,a) writel(l,__ISA_IO_base + (a))
-#define isa_memset_io(a,b,c)		memset_io(__ISA_IO_base + (a),(b),(c))
-#define isa_memcpy_fromio(a,b,c)	memcpy_fromio((a),__ISA_IO_base + (b),(c))
-#define isa_memcpy_toio(a,b,c)		memcpy_toio(__ISA_IO_base + (a),(b),(c))
-
-
 /*
  * Again, x86-64 does not require mem IO specific function.
  */
 
 #define eth_io_copy_and_sum(a,b,c,d)		eth_copy_and_sum((a),(void *)(b),(c),(d))
-#define isa_eth_io_copy_and_sum(a,b,c,d)	eth_copy_and_sum((a),(void *)(__ISA_IO_base + (b)),(c),(d))
 
 /**
  *	check_signature		-	find BIOS signatures
diff --git a/include/asm-x86_64/local.h b/include/asm-x86_64/local.h
index 3e72c41727c..bf148037d4e 100644
--- a/include/asm-x86_64/local.h
+++ b/include/asm-x86_64/local.h
@@ -5,7 +5,7 @@
 
 typedef struct
 {
-	volatile unsigned int counter;
+	volatile unsigned long counter;
 } local_t;
 
 #define LOCAL_INIT(i)	{ (i) }
@@ -16,7 +16,7 @@ typedef struct
 static __inline__ void local_inc(local_t *v)
 {
 	__asm__ __volatile__(
-		"incl %0"
+		"incq %0"
 		:"=m" (v->counter)
 		:"m" (v->counter));
 }
@@ -24,7 +24,7 @@ static __inline__ void local_inc(local_t *v)
 static __inline__ void local_dec(local_t *v)
 {
 	__asm__ __volatile__(
-		"decl %0"
+		"decq %0"
 		:"=m" (v->counter)
 		:"m" (v->counter));
 }
@@ -32,7 +32,7 @@ static __inline__ void local_dec(local_t *v)
 static __inline__ void local_add(unsigned int i, local_t *v)
 {
 	__asm__ __volatile__(
-		"addl %1,%0"
+		"addq %1,%0"
 		:"=m" (v->counter)
 		:"ir" (i), "m" (v->counter));
 }
@@ -40,7 +40,7 @@ static __inline__ void local_add(unsigned int i, local_t *v)
 static __inline__ void local_sub(unsigned int i, local_t *v)
 {
 	__asm__ __volatile__(
-		"subl %1,%0"
+		"subq %1,%0"
 		:"=m" (v->counter)
 		:"ir" (i), "m" (v->counter));
 }
diff --git a/include/asm-x86_64/mmu_context.h b/include/asm-x86_64/mmu_context.h
index 16e4be4de0c..19f0c83d079 100644
--- a/include/asm-x86_64/mmu_context.h
+++ b/include/asm-x86_64/mmu_context.h
@@ -34,12 +34,12 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 	unsigned cpu = smp_processor_id();
 	if (likely(prev != next)) {
 		/* stop flush ipis for the previous mm */
-		clear_bit(cpu, &prev->cpu_vm_mask);
+		cpu_clear(cpu, prev->cpu_vm_mask);
 #ifdef CONFIG_SMP
 		write_pda(mmu_state, TLBSTATE_OK);
 		write_pda(active_mm, next);
 #endif
-		set_bit(cpu, &next->cpu_vm_mask);
+		cpu_set(cpu, next->cpu_vm_mask);
 		load_cr3(next->pgd);
 
 		if (unlikely(next->context.ldt != prev->context.ldt)) 
@@ -50,7 +50,7 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 		write_pda(mmu_state, TLBSTATE_OK);
 		if (read_pda(active_mm) != next)
 			out_of_line_bug();
-		if(!test_and_set_bit(cpu, &next->cpu_vm_mask)) {
+		if (!cpu_test_and_set(cpu, next->cpu_vm_mask)) {
 			/* We were in lazy tlb mode and leave_mm disabled 
 			 * tlb flush IPI delivery. We must reload CR3
 			 * to make sure to use no freed page tables.
diff --git a/include/asm-x86_64/mmzone.h b/include/asm-x86_64/mmzone.h
index 972c9359f7d..937f99b2688 100644
--- a/include/asm-x86_64/mmzone.h
+++ b/include/asm-x86_64/mmzone.h
@@ -15,8 +15,13 @@
 #define NODEMAPSIZE 0xfff
 
 /* Simple perfect hash to map physical addresses to node numbers */
-extern int memnode_shift; 
-extern u8  memnodemap[NODEMAPSIZE]; 
+struct memnode {
+	int shift;
+	u8 map[NODEMAPSIZE];
+} ____cacheline_aligned;
+extern struct memnode memnode;
+#define memnode_shift memnode.shift
+#define memnodemap memnode.map
 
 extern struct pglist_data *node_data[];
 
diff --git a/include/asm-x86_64/numa.h b/include/asm-x86_64/numa.h
index dffe276ca2d..f6cbb4cbb5a 100644
--- a/include/asm-x86_64/numa.h
+++ b/include/asm-x86_64/numa.h
@@ -4,11 +4,11 @@
 #include <linux/nodemask.h>
 #include <asm/numnodes.h>
 
-struct node { 
+struct bootnode {
 	u64 start,end; 
 };
 
-extern int compute_hash_shift(struct node *nodes, int numnodes);
+extern int compute_hash_shift(struct bootnode *nodes, int numnodes);
 extern int pxm_to_node(int nid);
 
 #define ZONE_ALIGN (1UL << (MAX_ORDER+PAGE_SHIFT))
diff --git a/include/asm-x86_64/pda.h b/include/asm-x86_64/pda.h
index c7ab38a601a..b47c3df9ed1 100644
--- a/include/asm-x86_64/pda.h
+++ b/include/asm-x86_64/pda.h
@@ -22,8 +22,8 @@ struct x8664_pda {
 	int nodenumber;		    /* number of current node */
 	unsigned int __softirq_pending;
 	unsigned int __nmi_count;	/* number of NMI on this CPUs */
-	struct mm_struct *active_mm;
 	int mmu_state;     
+	struct mm_struct *active_mm;
 	unsigned apic_timer_irqs;
 } ____cacheline_aligned_in_smp;
 
diff --git a/include/asm-x86_64/percpu.h b/include/asm-x86_64/percpu.h
index 29a6b0408f7..4405b4adeab 100644
--- a/include/asm-x86_64/percpu.h
+++ b/include/asm-x86_64/percpu.h
@@ -26,10 +26,9 @@
 #define percpu_modcopy(pcpudst, src, size)			\
 do {								\
 	unsigned int __i;					\
-	for (__i = 0; __i < NR_CPUS; __i++)			\
-		if (cpu_possible(__i))				\
-			memcpy((pcpudst)+__per_cpu_offset(__i),	\
-			       (src), (size));			\
+	for_each_cpu(__i)					\
+		memcpy((pcpudst)+__per_cpu_offset(__i),		\
+		       (src), (size));				\
 } while (0)
 
 extern void setup_per_cpu_areas(void);
diff --git a/include/asm-x86_64/pgalloc.h b/include/asm-x86_64/pgalloc.h
index 08cad2482bc..43d4c333a8b 100644
--- a/include/asm-x86_64/pgalloc.h
+++ b/include/asm-x86_64/pgalloc.h
@@ -45,12 +45,39 @@ static inline void pud_free (pud_t *pud)
 	free_page((unsigned long)pud);
 }
 
+static inline void pgd_list_add(pgd_t *pgd)
+{
+	struct page *page = virt_to_page(pgd);
+
+	spin_lock(&pgd_lock);
+	page->index = (pgoff_t)pgd_list;
+	if (pgd_list)
+		pgd_list->private = (unsigned long)&page->index;
+	pgd_list = page;
+	page->private = (unsigned long)&pgd_list;
+	spin_unlock(&pgd_lock);
+}
+
+static inline void pgd_list_del(pgd_t *pgd)
+{
+	struct page *next, **pprev, *page = virt_to_page(pgd);
+
+	spin_lock(&pgd_lock);
+	next = (struct page *)page->index;
+	pprev = (struct page **)page->private;
+	*pprev = next;
+	if (next)
+		next->private = (unsigned long)pprev;
+	spin_unlock(&pgd_lock);
+}
+
 static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 {
 	unsigned boundary;
 	pgd_t *pgd = (pgd_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT);
 	if (!pgd)
 		return NULL;
+	pgd_list_add(pgd);
 	/*
 	 * Copy kernel pointers in from init.
 	 * Could keep a freelist or slab cache of those because the kernel
@@ -67,6 +94,7 @@ static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 static inline void pgd_free(pgd_t *pgd)
 {
 	BUG_ON((unsigned long)pgd & (PAGE_SIZE-1));
+	pgd_list_del(pgd);
 	free_page((unsigned long)pgd);
 }
 
diff --git a/include/asm-x86_64/pgtable.h b/include/asm-x86_64/pgtable.h
index 715fd94cf57..31e83c3bd02 100644
--- a/include/asm-x86_64/pgtable.h
+++ b/include/asm-x86_64/pgtable.h
@@ -273,7 +273,7 @@ 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; }
+static inline int pte_huge(pte_t pte)		{ return pte_val(pte) & _PAGE_PSE; }
 
 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; }
@@ -285,7 +285,7 @@ static inline pte_t pte_mkexec(pte_t pte)	{ set_pte(&pte, __pte(pte_val(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; }
+static inline pte_t pte_mkhuge(pte_t pte)	{ set_pte(&pte, __pte(pte_val(pte) | _PAGE_PSE)); return pte; }
 
 struct vm_area_struct;
 
@@ -293,19 +293,19 @@ static inline int ptep_test_and_clear_dirty(struct vm_area_struct *vma, unsigned
 {
 	if (!pte_dirty(*ptep))
 		return 0;
-	return test_and_clear_bit(_PAGE_BIT_DIRTY, ptep);
+	return test_and_clear_bit(_PAGE_BIT_DIRTY, &ptep->pte);
 }
 
 static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
 {
 	if (!pte_young(*ptep))
 		return 0;
-	return test_and_clear_bit(_PAGE_BIT_ACCESSED, ptep);
+	return test_and_clear_bit(_PAGE_BIT_ACCESSED, &ptep->pte);
 }
 
 static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
-	clear_bit(_PAGE_BIT_RW, ptep);
+	clear_bit(_PAGE_BIT_RW, &ptep->pte);
 }
 
 /*
@@ -420,6 +420,10 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 #define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val(pte) })
 #define __swp_entry_to_pte(x)		((pte_t) { (x).val })
 
+extern spinlock_t pgd_lock;
+extern struct page *pgd_list;
+void vmalloc_sync_all(void);
+
 #endif /* !__ASSEMBLY__ */
 
 extern int kern_addr_valid(unsigned long addr); 
diff --git a/include/asm-x86_64/poll.h b/include/asm-x86_64/poll.h
index c43cbba3191..c0475a9d8bb 100644
--- a/include/asm-x86_64/poll.h
+++ b/include/asm-x86_64/poll.h
@@ -16,6 +16,7 @@
 #define POLLWRBAND	0x0200
 #define POLLMSG		0x0400
 #define POLLREMOVE	0x1000
+#define POLLRDHUP       0x2000
 
 struct pollfd {
 	int fd;
diff --git a/include/asm-x86_64/proto.h b/include/asm-x86_64/proto.h
index 3ba8fd45fcb..8abf2a43c94 100644
--- a/include/asm-x86_64/proto.h
+++ b/include/asm-x86_64/proto.h
@@ -53,8 +53,6 @@ extern int sysctl_vsyscall;
 extern int nohpet;
 extern unsigned long vxtime_hz;
 
-extern void do_softirq_thunk(void);
-
 extern int numa_setup(char *opt);
 
 extern int setup_early_printk(char *); 
@@ -129,7 +127,6 @@ extern int fix_aperture;
 #define iommu_aperture 0
 #define iommu_aperture_allowed 0
 #endif
-extern int force_iommu;
 
 extern int reboot_force;
 extern int notsc_setup(char *);
diff --git a/include/asm-x86_64/string.h b/include/asm-x86_64/string.h
index a3493ee282b..ee6bf275349 100644
--- a/include/asm-x86_64/string.h
+++ b/include/asm-x86_64/string.h
@@ -40,26 +40,15 @@ extern void *__memcpy(void *to, const void *from, size_t len);
 
 
 #define __HAVE_ARCH_MEMSET
-#define memset __builtin_memset
+void *memset(void *s, int c, size_t n);
 
 #define __HAVE_ARCH_MEMMOVE
 void * memmove(void * dest,const void *src,size_t count);
 
-/* Use C out of line version for memcmp */ 
-#define memcmp __builtin_memcmp
 int memcmp(const void * cs,const void * ct,size_t count);
-
-/* out of line string functions use always C versions */ 
-#define strlen __builtin_strlen
 size_t strlen(const char * s);
-
-#define strcpy __builtin_strcpy
-char * strcpy(char * dest,const char *src);
-
-#define strcat __builtin_strcat
-char * strcat(char * dest, const char * src);
-
-#define strcmp __builtin_strcmp
+char *strcpy(char * dest,const char *src);
+char *strcat(char * dest, const char * src);
 int strcmp(const char * cs,const char * ct);
 
 #endif /* __KERNEL__ */
diff --git a/include/asm-x86_64/suspend.h b/include/asm-x86_64/suspend.h
index bb9f40597d0..bc7f81715e5 100644
--- a/include/asm-x86_64/suspend.h
+++ b/include/asm-x86_64/suspend.h
@@ -39,9 +39,7 @@ extern unsigned long saved_context_r12, saved_context_r13, saved_context_r14, sa
 extern unsigned long saved_context_eflags;
 
 #define loaddebug(thread,register) \
-               __asm__("movq %0,%%db" #register  \
-                       : /* no output */ \
-                       :"r" ((thread)->debugreg##register))
+	set_debugreg((thread)->debugreg##register, register)
 
 extern void fix_processor_context(void);
 
diff --git a/include/asm-x86_64/system.h b/include/asm-x86_64/system.h
index b7f66034ae7..39759898022 100644
--- a/include/asm-x86_64/system.h
+++ b/include/asm-x86_64/system.h
@@ -70,12 +70,6 @@ extern void load_gs_index(unsigned);
 		".previous"			\
 		: :"r" (value), "r" (0))
 
-#define set_debug(value,register) \
-                __asm__("movq %0,%%db" #register  \
-		: /* no output */ \
-		:"r" ((unsigned long) value))
-
-
 #ifdef __KERNEL__
 struct alt_instr { 
 	__u8 *instr; 		/* original instruction */