17 files changed, 114 insertions, 67 deletions

diff --git a/include/asm-i386/bugs.h b/include/asm-i386/bugs.h
index 2a9e4ee..592ffee 100644
--- a/include/asm-i386/bugs.h
+++ b/include/asm-i386/bugs.h
@@ -189,6 +189,6 @@ static void __init check_bugs(void)
 	check_fpu();
 	check_hlt();
 	check_popad();
-	system_utsname.machine[1] = '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86);
+	init_utsname()->machine[1] = '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86);
 	alternative_instructions(); 
 }
diff --git a/include/asm-i386/dma-mapping.h b/include/asm-i386/dma-mapping.h
index 576ae01..81999a3 100644
--- a/include/asm-i386/dma-mapping.h
+++ b/include/asm-i386/dma-mapping.h
@@ -21,7 +21,7 @@ static inline dma_addr_t
 dma_map_single(struct device *dev, void *ptr, size_t size,
 	       enum dma_data_direction direction)
 {
-	BUG_ON(direction == DMA_NONE);
+	BUG_ON(!valid_dma_direction(direction));
 	WARN_ON(size == 0);
 	flush_write_buffers();
 	return virt_to_phys(ptr);
@@ -31,7 +31,7 @@ static inline void
 dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
 		 enum dma_data_direction direction)
 {
-	BUG_ON(direction == DMA_NONE);
+	BUG_ON(!valid_dma_direction(direction));
 }
 
 static inline int
@@ -40,7 +40,7 @@ dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
 {
 	int i;
 
-	BUG_ON(direction == DMA_NONE);
+	BUG_ON(!valid_dma_direction(direction));
 	WARN_ON(nents == 0 || sg[0].length == 0);
 
 	for (i = 0; i < nents; i++ ) {
@@ -57,7 +57,7 @@ static inline dma_addr_t
 dma_map_page(struct device *dev, struct page *page, unsigned long offset,
 	     size_t size, enum dma_data_direction direction)
 {
-	BUG_ON(direction == DMA_NONE);
+	BUG_ON(!valid_dma_direction(direction));
 	return page_to_phys(page) + offset;
 }
 
@@ -65,7 +65,7 @@ static inline void
 dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size,
 	       enum dma_data_direction direction)
 {
-	BUG_ON(direction == DMA_NONE);
+	BUG_ON(!valid_dma_direction(direction));
 }
 
 
@@ -73,7 +73,7 @@ static inline void
 dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nhwentries,
 	     enum dma_data_direction direction)
 {
-	BUG_ON(direction == DMA_NONE);
+	BUG_ON(!valid_dma_direction(direction));
 }
 
 static inline void
diff --git a/include/asm-i386/elf.h b/include/asm-i386/elf.h
index db4344d..3a05436 100644
--- a/include/asm-i386/elf.h
+++ b/include/asm-i386/elf.h
@@ -112,7 +112,7 @@ typedef struct user_fxsr_struct elf_fpxregset_t;
    For the moment, we have only optimizations for the Intel generations,
    but that could change... */
 
-#define ELF_PLATFORM  (system_utsname.machine)
+#define ELF_PLATFORM  (utsname()->machine)
 
 #define SET_PERSONALITY(ex, ibcs2) do { } while (0)
 
diff --git a/include/asm-i386/mach-default/do_timer.h b/include/asm-i386/mach-default/do_timer.h
index 6312c3e..4182c34 100644
--- a/include/asm-i386/mach-default/do_timer.h
+++ b/include/asm-i386/mach-default/do_timer.h
@@ -16,7 +16,7 @@
 
 static inline void do_timer_interrupt_hook(struct pt_regs *regs)
 {
-	do_timer(regs);
+	do_timer(1);
 #ifndef CONFIG_SMP
 	update_process_times(user_mode_vm(regs));
 #endif
diff --git a/include/asm-i386/mach-summit/mach_apic.h b/include/asm-i386/mach-summit/mach_apic.h
index a81b059..254a0fe 100644
--- a/include/asm-i386/mach-summit/mach_apic.h
+++ b/include/asm-i386/mach-summit/mach_apic.h
@@ -88,7 +88,7 @@ static inline void clustered_apic_check(void)
 
 static inline int apicid_to_node(int logical_apicid)
 {
-	return logical_apicid >> 5;          /* 2 clusterids per CEC */
+	return apicid_2_node[logical_apicid];
 }
 
 /* Mapping from cpu number to logical apicid */
diff --git a/include/asm-i386/mach-visws/do_timer.h b/include/asm-i386/mach-visws/do_timer.h
index 95568e6..8db618c5 100644
--- a/include/asm-i386/mach-visws/do_timer.h
+++ b/include/asm-i386/mach-visws/do_timer.h
@@ -9,7 +9,7 @@ static inline void do_timer_interrupt_hook(struct pt_regs *regs)
 	/* Clear the interrupt */
 	co_cpu_write(CO_CPU_STAT,co_cpu_read(CO_CPU_STAT) & ~CO_STAT_TIMEINTR);
 
-	do_timer(regs);
+	do_timer(1);
 #ifndef CONFIG_SMP
 	update_process_times(user_mode_vm(regs));
 #endif
diff --git a/include/asm-i386/mach-voyager/do_timer.h b/include/asm-i386/mach-voyager/do_timer.h
index eaf5180..099fe9f 100644
--- a/include/asm-i386/mach-voyager/do_timer.h
+++ b/include/asm-i386/mach-voyager/do_timer.h
@@ -3,7 +3,7 @@
 
 static inline void do_timer_interrupt_hook(struct pt_regs *regs)
 {
-	do_timer(regs);
+	do_timer(1);
 #ifndef CONFIG_SMP
 	update_process_times(user_mode_vm(regs));
 #endif
diff --git a/include/asm-i386/mca_dma.h b/include/asm-i386/mca_dma.h
index 4b3b526..fbb1f3b 100644
--- a/include/asm-i386/mca_dma.h
+++ b/include/asm-i386/mca_dma.h
@@ -181,7 +181,7 @@ static __inline__ void mca_set_dma_io(unsigned int dmanr, unsigned int io_addr)
  *	@mode: mode to set
  *
  *	The DMA controller supports several modes. The mode values you can
- *	set are :
+ *	set are-
  *
  *	%MCA_DMA_MODE_READ when reading from the DMA device.
  *
@@ -190,7 +190,6 @@ static __inline__ void mca_set_dma_io(unsigned int dmanr, unsigned int io_addr)
  *	%MCA_DMA_MODE_IO to do DMA to or from an I/O port.
  *
  *	%MCA_DMA_MODE_16 to do 16bit transfers.
- *
  */
 
 static __inline__ void mca_set_dma_mode(unsigned int dmanr, unsigned int mode)
diff --git a/include/asm-i386/nmi.h b/include/asm-i386/nmi.h
index 303bcd4..269d315 100644
--- a/include/asm-i386/nmi.h
+++ b/include/asm-i386/nmi.h
@@ -36,4 +36,10 @@ extern unsigned int nmi_watchdog;
 #define NMI_LOCAL_APIC	2
 #define NMI_INVALID	3
 
+struct ctl_table;
+struct file;
+extern int proc_nmi_enabled(struct ctl_table *, int , struct file *,
+			void __user *, size_t *, loff_t *);
+extern int unknown_nmi_panic;
+
 #endif /* ASM_NMI_H */
diff --git a/include/asm-i386/pgtable-2level.h b/include/asm-i386/pgtable-2level.h
index 201c86a..8d8d3b9 100644
--- a/include/asm-i386/pgtable-2level.h
+++ b/include/asm-i386/pgtable-2level.h
@@ -16,6 +16,7 @@
 #define set_pte(pteptr, pteval) (*(pteptr) = pteval)
 #define set_pte_at(mm,addr,ptep,pteval) set_pte(ptep,pteval)
 #define set_pte_atomic(pteptr, pteval) set_pte(pteptr,pteval)
+#define set_pte_present(mm,addr,ptep,pteval) set_pte_at(mm,addr,ptep,pteval)
 #define set_pmd(pmdptr, pmdval) (*(pmdptr) = (pmdval))
 
 #define pte_clear(mm,addr,xp)	do { set_pte_at(mm, addr, xp, __pte(0)); } while (0)
diff --git a/include/asm-i386/pgtable-3level.h b/include/asm-i386/pgtable-3level.h
index 0d89917..c2d701e 100644
--- a/include/asm-i386/pgtable-3level.h
+++ b/include/asm-i386/pgtable-3level.h
@@ -58,7 +58,21 @@ static inline void set_pte(pte_t *ptep, pte_t pte)
 }
 #define set_pte_at(mm,addr,ptep,pteval) set_pte(ptep,pteval)
 
-#define __HAVE_ARCH_SET_PTE_ATOMIC
+/*
+ * Since this is only called on user PTEs, and the page fault handler
+ * must handle the already racy situation of simultaneous page faults,
+ * we are justified in merely clearing the PTE present bit, followed
+ * by a set.  The ordering here is important.
+ */
+static inline void set_pte_present(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte)
+{
+	ptep->pte_low = 0;
+	smp_wmb();
+	ptep->pte_high = pte.pte_high;
+	smp_wmb();
+	ptep->pte_low = pte.pte_low;
+}
+
 #define set_pte_atomic(pteptr,pteval) \
 		set_64bit((unsigned long long *)(pteptr),pte_val(pteval))
 #define set_pmd(pmdptr,pmdval) \
diff --git a/include/asm-i386/pgtable.h b/include/asm-i386/pgtable.h
index 541b3e2..7d398f4 100644
--- a/include/asm-i386/pgtable.h
+++ b/include/asm-i386/pgtable.h
@@ -247,6 +247,23 @@ static inline pte_t pte_mkhuge(pte_t pte)	{ (pte).pte_low |= _PAGE_PSE; return p
 #endif
 
 /*
+ * Rules for using pte_update - it must be called after any PTE update which
+ * has not been done using the set_pte / clear_pte interfaces.  It is used by
+ * shadow mode hypervisors to resynchronize the shadow page tables.  Kernel PTE
+ * updates should either be sets, clears, or set_pte_atomic for P->P
+ * transitions, which means this hook should only be called for user PTEs.
+ * This hook implies a P->P protection or access change has taken place, which
+ * requires a subsequent TLB flush.  The notification can optionally be delayed
+ * until the TLB flush event by using the pte_update_defer form of the
+ * interface, but care must be taken to assure that the flush happens while
+ * still holding the same page table lock so that the shadow and primary pages
+ * do not become out of sync on SMP.
+ */
+#define pte_update(mm, addr, ptep)		do { } while (0)
+#define pte_update_defer(mm, addr, ptep)	do { } while (0)
+
+
+/*
  * We only update the dirty/accessed state if we set
  * the dirty bit by hand in the kernel, since the hardware
  * will do the accessed bit for us, and we don't want to
@@ -258,25 +275,54 @@ static inline pte_t pte_mkhuge(pte_t pte)	{ (pte).pte_low |= _PAGE_PSE; return p
 do {									\
 	if (dirty) {							\
 		(ptep)->pte_low = (entry).pte_low;			\
+		pte_update_defer((vma)->vm_mm, (addr), (ptep));		\
 		flush_tlb_page(vma, address);				\
 	}								\
 } while (0)
 
+/*
+ * We don't actually have these, but we want to advertise them so that
+ * we can encompass the flush here.
+ */
 #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_DIRTY
-static inline int ptep_test_and_clear_dirty(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
-{
-	if (!pte_dirty(*ptep))
-		return 0;
-	return test_and_clear_bit(_PAGE_BIT_DIRTY, &ptep->pte_low);
-}
-
 #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
-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->pte_low);
-}
+
+/*
+ * Rules for using ptep_establish: the pte MUST be a user pte, and
+ * must be a present->present transition.
+ */
+#define __HAVE_ARCH_PTEP_ESTABLISH
+#define ptep_establish(vma, address, ptep, pteval)			\
+do {									\
+	set_pte_present((vma)->vm_mm, address, ptep, pteval);		\
+	flush_tlb_page(vma, address);					\
+} while (0)
+
+#define __HAVE_ARCH_PTEP_CLEAR_DIRTY_FLUSH
+#define ptep_clear_flush_dirty(vma, address, ptep)			\
+({									\
+	int __dirty;							\
+	__dirty = pte_dirty(*(ptep));					\
+	if (__dirty) {							\
+		clear_bit(_PAGE_BIT_DIRTY, &(ptep)->pte_low);		\
+		pte_update_defer((vma)->vm_mm, (addr), (ptep));		\
+		flush_tlb_page(vma, address);				\
+	}								\
+	__dirty;							\
+})
+
+#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
+#define ptep_clear_flush_young(vma, address, ptep)			\
+({									\
+	int __young;							\
+	__young = pte_young(*(ptep));					\
+	if (__young) {							\
+		clear_bit(_PAGE_BIT_ACCESSED, &(ptep)->pte_low);	\
+		pte_update_defer((vma)->vm_mm, (addr), (ptep));		\
+		flush_tlb_page(vma, address);				\
+	}								\
+	__young;							\
+})
 
 #define __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL
 static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, unsigned long addr, pte_t *ptep, int full)
@@ -295,6 +341,7 @@ static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, unsigned long
 static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
 	clear_bit(_PAGE_BIT_RW, &ptep->pte_low);
+	pte_update(mm, addr, ptep);
 }
 
 /*
@@ -426,6 +473,13 @@ extern pte_t *lookup_address(unsigned long address);
 #define pte_unmap_nested(pte) do { } while (0)
 #endif
 
+/* Clear a kernel PTE and flush it from the TLB */
+#define kpte_clear_flush(ptep, vaddr)					\
+do {									\
+	pte_clear(&init_mm, vaddr, ptep);				\
+	__flush_tlb_one(vaddr);						\
+} while (0)
+
 /*
  * The i386 doesn't have any external MMU info: the kernel page
  * tables contain all the necessary information.
diff --git a/include/asm-i386/ptrace.h b/include/asm-i386/ptrace.h
index a4a0e52..d505f50 100644
--- a/include/asm-i386/ptrace.h
+++ b/include/asm-i386/ptrace.h
@@ -47,7 +47,10 @@ static inline int user_mode_vm(struct pt_regs *regs)
 {
 	return ((regs->xcs & SEGMENT_RPL_MASK) | (regs->eflags & VM_MASK)) >= USER_RPL;
 }
+
 #define instruction_pointer(regs) ((regs)->eip)
+#define regs_return_value(regs) ((regs)->eax)
+
 extern unsigned long profile_pc(struct pt_regs *regs);
 #endif /* __KERNEL__ */
 
diff --git a/include/asm-i386/smp.h b/include/asm-i386/smp.h
index 32ac8c9..6aa1206 100644
--- a/include/asm-i386/smp.h
+++ b/include/asm-i386/smp.h
@@ -46,6 +46,8 @@ extern u8 x86_cpu_to_apicid[];
 
 #define cpu_physical_id(cpu)	x86_cpu_to_apicid[cpu]
 
+extern u8 apicid_2_node[];
+
 #ifdef CONFIG_HOTPLUG_CPU
 extern void cpu_exit_clear(void);
 extern void cpu_uninit(void);
@@ -82,6 +84,7 @@ static inline int hard_smp_processor_id(void)
 #endif
 #endif
 
+extern int safe_smp_processor_id(void);
 extern int __cpu_disable(void);
 extern void __cpu_die(unsigned int cpu);
 extern unsigned int num_processors;
@@ -90,6 +93,7 @@ extern unsigned int num_processors;
 
 #else /* CONFIG_SMP */
 
+#define safe_smp_processor_id()		0
 #define cpu_physical_id(cpu)		boot_cpu_physical_apicid
 
 #define NO_PROC_ID		0xFF		/* No processor magic marker */
diff --git a/include/asm-i386/spinlock.h b/include/asm-i386/spinlock.h
index b0b3043..c18b71f 100644
--- a/include/asm-i386/spinlock.h
+++ b/include/asm-i386/spinlock.h
@@ -205,4 +205,8 @@ static inline void __raw_write_unlock(raw_rwlock_t *rw)
 				 : "+m" (rw->lock) : : "memory");
 }
 
+#define _raw_spin_relax(lock)	cpu_relax()
+#define _raw_read_relax(lock)	cpu_relax()
+#define _raw_write_relax(lock)	cpu_relax()
+
 #endif /* __ASM_SPINLOCK_H */
diff --git a/include/asm-i386/topology.h b/include/asm-i386/topology.h
index 6adbd9b..978d095 100644
--- a/include/asm-i386/topology.h
+++ b/include/asm-i386/topology.h
@@ -74,6 +74,7 @@ static inline int node_to_first_cpu(int node)
 #define SD_NODE_INIT (struct sched_domain) {		\
 	.span			= CPU_MASK_NONE,	\
 	.parent			= NULL,			\
+	.child			= NULL,			\
 	.groups			= NULL,			\
 	.min_interval		= 8,			\
 	.max_interval		= 32,			\
diff --git a/include/asm-i386/unistd.h b/include/asm-i386/unistd.h
index bd99870..3ca7ab9 100644
--- a/include/asm-i386/unistd.h
+++ b/include/asm-i386/unistd.h
@@ -451,45 +451,6 @@ __syscall_return(type,__res); \
 #define __ARCH_WANT_SYS_RT_SIGACTION
 #define __ARCH_WANT_SYS_RT_SIGSUSPEND
 
-#ifdef __KERNEL_SYSCALLS__
-
-#include <linux/compiler.h>
-#include <linux/types.h>
-#include <linux/linkage.h>
-#include <asm/ptrace.h>
-
-/*
- * we need this inline - forking from kernel space will result
- * in NO COPY ON WRITE (!!!), until an execve is executed. This
- * is no problem, but for the stack. This is handled by not letting
- * main() use the stack at all after fork(). Thus, no function
- * calls - which means inline code for fork too, as otherwise we
- * would use the stack upon exit from 'fork()'.
- *
- * Actually only pause and fork are needed inline, so that there
- * won't be any messing with the stack from main(), but we define
- * some others too.
- */
-static inline _syscall3(int,execve,const char *,file,char **,argv,char **,envp)
-
-asmlinkage int sys_modify_ldt(int func, void __user *ptr, unsigned long bytecount);
-asmlinkage long sys_mmap2(unsigned long addr, unsigned long len,
-			unsigned long prot, unsigned long flags,
-			unsigned long fd, unsigned long pgoff);
-asmlinkage int sys_execve(struct pt_regs regs);
-asmlinkage int sys_clone(struct pt_regs regs);
-asmlinkage int sys_fork(struct pt_regs regs);
-asmlinkage int sys_vfork(struct pt_regs regs);
-asmlinkage int sys_pipe(unsigned long __user *fildes);
-asmlinkage long sys_iopl(unsigned long unused);
-struct sigaction;
-asmlinkage long sys_rt_sigaction(int sig,
-				const struct sigaction __user *act,
-				struct sigaction __user *oact,
-				size_t sigsetsize);
-
-#endif /* __KERNEL_SYSCALLS__ */
-
 /*
  * "Conditional" syscalls
  *