3 files changed, 277 insertions, 289 deletions

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 9c9ce75e3ae4..0a1987b4acc4 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -22,7 +22,7 @@ obj-y			+= setup_$(BITS).o i8259.o irqinit_$(BITS).o setup.o
 obj-$(CONFIG_X86_32)    += probe_roms_32.o
 obj-$(CONFIG_X86_32)    += sys_i386_32.o i386_ksyms_32.o
 obj-$(CONFIG_X86_64)    += sys_x86_64.o x8664_ksyms_64.o
-obj-$(CONFIG_X86_64)    += syscall_64.o vsyscall_64.o setup64.o
+obj-$(CONFIG_X86_64)    += syscall_64.o vsyscall_64.o
 obj-y                   += bootflag.o e820.o
 obj-y                   += pci-dma.o quirks.o i8237.o topology.o kdebugfs.o
 obj-y                   += alternative.o i8253.o pci-nommu.o
diff --git a/arch/x86/kernel/cpu/common_64.c b/arch/x86/kernel/cpu/common_64.c
index 48ba79961583..9fb5b7caaa89 100644
--- a/arch/x86/kernel/cpu/common_64.c
+++ b/arch/x86/kernel/cpu/common_64.c
@@ -1,10 +1,17 @@
 #include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/string.h>
+#include <linux/bootmem.h>
+#include <linux/bitops.h>
+#include <linux/module.h>
+#include <linux/kgdb.h>
+#include <linux/topology.h>
 #include <linux/string.h>
 #include <linux/delay.h>
 #include <linux/smp.h>
 #include <linux/module.h>
 #include <linux/percpu.h>
-#include <linux/bootmem.h>
 #include <asm/processor.h>
 #include <asm/i387.h>
 #include <asm/msr.h>
@@ -19,6 +26,15 @@
 #include <asm/apic.h>
 #include <mach_apic.h>
 #endif
+#include <asm/pda.h>
+#include <asm/pgtable.h>
+#include <asm/processor.h>
+#include <asm/desc.h>
+#include <asm/atomic.h>
+#include <asm/proto.h>
+#include <asm/sections.h>
+#include <asm/setup.h>
+#include <asm/genapic.h>
 
 #include "cpu.h"
 
@@ -404,3 +420,262 @@ static __init int setup_disablecpuid(char *arg)
         return 1;
 }
 __setup("clearcpuid=", setup_disablecpuid);
+
+#ifndef CONFIG_DEBUG_BOOT_PARAMS
+struct boot_params __initdata boot_params;
+#else
+struct boot_params boot_params;
+#endif
+
+cpumask_t cpu_initialized __cpuinitdata = CPU_MASK_NONE;
+
+struct x8664_pda **_cpu_pda __read_mostly;
+EXPORT_SYMBOL(_cpu_pda);
+
+struct desc_ptr idt_descr = { 256 * 16 - 1, (unsigned long) idt_table };
+
+char boot_cpu_stack[IRQSTACKSIZE] __page_aligned_bss;
+
+unsigned long __supported_pte_mask __read_mostly = ~0UL;
+EXPORT_SYMBOL_GPL(__supported_pte_mask);
+
+static int do_not_nx __cpuinitdata;
+
+/* noexec=on|off
+Control non executable mappings for 64bit processes.
+
+on      Enable(default)
+off     Disable
+*/
+static int __init nonx_setup(char *str)
+{
+        if (!str)
+                return -EINVAL;
+        if (!strncmp(str, "on", 2)) {
+                __supported_pte_mask |= _PAGE_NX;
+                do_not_nx = 0;
+        } else if (!strncmp(str, "off", 3)) {
+                do_not_nx = 1;
+                __supported_pte_mask &= ~_PAGE_NX;
+        }
+        return 0;
+}
+early_param("noexec", nonx_setup);
+
+int force_personality32;
+
+/* noexec32=on|off
+Control non executable heap for 32bit processes.
+To control the stack too use noexec=off
+
+on      PROT_READ does not imply PROT_EXEC for 32bit processes (default)
+off     PROT_READ implies PROT_EXEC
+*/
+static int __init nonx32_setup(char *str)
+{
+        if (!strcmp(str, "on"))
+                force_personality32 &= ~READ_IMPLIES_EXEC;
+        else if (!strcmp(str, "off"))
+                force_personality32 |= READ_IMPLIES_EXEC;
+        return 1;
+}
+__setup("noexec32=", nonx32_setup);
+
+void pda_init(int cpu)
+{
+        struct x8664_pda *pda = cpu_pda(cpu);
+
+        /* Setup up data that may be needed in __get_free_pages early */
+        asm volatile("movl %0,%%fs ; movl %0,%%gs" :: "r" (0));
+        /* Memory clobbers used to order PDA accessed */
+        mb();
+        wrmsrl(MSR_GS_BASE, pda);
+        mb();
+
+        pda->cpunumber = cpu;
+        pda->irqcount = -1;
+        pda->kernelstack = (unsigned long)stack_thread_info() -
+                                 PDA_STACKOFFSET + THREAD_SIZE;
+        pda->active_mm = &init_mm;
+        pda->mmu_state = 0;
+
+        if (cpu == 0) {
+                /* others are initialized in smpboot.c */
+                pda->pcurrent = &init_task;
+                pda->irqstackptr = boot_cpu_stack;
+        } else {
+                pda->irqstackptr = (char *)
+                        __get_free_pages(GFP_ATOMIC, IRQSTACK_ORDER);
+                if (!pda->irqstackptr)
+                        panic("cannot allocate irqstack for cpu %d", cpu);
+
+                if (pda->nodenumber == 0 && cpu_to_node(cpu) != NUMA_NO_NODE)
+                        pda->nodenumber = cpu_to_node(cpu);
+        }
+
+        pda->irqstackptr += IRQSTACKSIZE-64;
+}
+
+char boot_exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ +
+                           DEBUG_STKSZ]
+__attribute__((section(".bss.page_aligned")));
+
+extern asmlinkage void ignore_sysret(void);
+
+/* May not be marked __init: used by software suspend */
+void syscall_init(void)
+{
+        /*
+         * LSTAR and STAR live in a bit strange symbiosis.
+         * They both write to the same internal register. STAR allows to
+         * set CS/DS but only a 32bit target. LSTAR sets the 64bit rip.
+         */
+        wrmsrl(MSR_STAR,  ((u64)__USER32_CS)<<48  | ((u64)__KERNEL_CS)<<32);
+        wrmsrl(MSR_LSTAR, system_call);
+        wrmsrl(MSR_CSTAR, ignore_sysret);
+
+#ifdef CONFIG_IA32_EMULATION
+        syscall32_cpu_init();
+#endif
+
+        /* Flags to clear on syscall */
+        wrmsrl(MSR_SYSCALL_MASK,
+               X86_EFLAGS_TF|X86_EFLAGS_DF|X86_EFLAGS_IF|X86_EFLAGS_IOPL);
+}
+
+void __cpuinit check_efer(void)
+{
+        unsigned long efer;
+
+        rdmsrl(MSR_EFER, efer);
+        if (!(efer & EFER_NX) || do_not_nx)
+                __supported_pte_mask &= ~_PAGE_NX;
+}
+
+unsigned long kernel_eflags;
+
+/*
+ * Copies of the original ist values from the tss are only accessed during
+ * debugging, no special alignment required.
+ */
+DEFINE_PER_CPU(struct orig_ist, orig_ist);
+
+/*
+ * cpu_init() initializes state that is per-CPU. Some data is already
+ * initialized (naturally) in the bootstrap process, such as the GDT
+ * and IDT. We reload them nevertheless, this function acts as a
+ * 'CPU state barrier', nothing should get across.
+ * A lot of state is already set up in PDA init.
+ */
+void __cpuinit cpu_init(void)
+{
+        int cpu = stack_smp_processor_id();
+        struct tss_struct *t = &per_cpu(init_tss, cpu);
+        struct orig_ist *orig_ist = &per_cpu(orig_ist, cpu);
+        unsigned long v;
+        char *estacks = NULL;
+        struct task_struct *me;
+        int i;
+
+        /* CPU 0 is initialised in head64.c */
+        if (cpu != 0)
+                pda_init(cpu);
+        else
+                estacks = boot_exception_stacks;
+
+        me = current;
+
+        if (cpu_test_and_set(cpu, cpu_initialized))
+                panic("CPU#%d already initialized!\n", cpu);
+
+        printk(KERN_INFO "Initializing CPU#%d\n", cpu);
+
+        clear_in_cr4(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE);
+
+        /*
+         * Initialize the per-CPU GDT with the boot GDT,
+         * and set up the GDT descriptor:
+         */
+
+        switch_to_new_gdt();
+        load_idt((const struct desc_ptr *)&idt_descr);
+
+        memset(me->thread.tls_array, 0, GDT_ENTRY_TLS_ENTRIES * 8);
+        syscall_init();
+
+        wrmsrl(MSR_FS_BASE, 0);
+        wrmsrl(MSR_KERNEL_GS_BASE, 0);
+        barrier();
+
+        check_efer();
+
+        /*
+         * set up and load the per-CPU TSS
+         */
+        for (v = 0; v < N_EXCEPTION_STACKS; v++) {
+                static const unsigned int order[N_EXCEPTION_STACKS] = {
+                        [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STACK_ORDER,
+                        [DEBUG_STACK - 1] = DEBUG_STACK_ORDER
+                };
+                if (cpu) {
+                        estacks = (char *)__get_free_pages(GFP_ATOMIC, order[v]);
+                        if (!estacks)
+                                panic("Cannot allocate exception stack %ld %d\n",
+                                      v, cpu);
+                }
+                estacks += PAGE_SIZE << order[v];
+                orig_ist->ist[v] = t->x86_tss.ist[v] = (unsigned long)estacks;
+        }
+
+        t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap);
+        /*
+         * <= is required because the CPU will access up to
+         * 8 bits beyond the end of the IO permission bitmap.
+         */
+        for (i = 0; i <= IO_BITMAP_LONGS; i++)
+                t->io_bitmap[i] = ~0UL;
+
+        atomic_inc(&init_mm.mm_count);
+        me->active_mm = &init_mm;
+        if (me->mm)
+                BUG();
+        enter_lazy_tlb(&init_mm, me);
+
+        load_sp0(t, &current->thread);
+        set_tss_desc(cpu, t);
+        load_TR_desc();
+        load_LDT(&init_mm.context);
+
+#ifdef CONFIG_KGDB
+        /*
+         * If the kgdb is connected no debug regs should be altered.  This
+         * is only applicable when KGDB and a KGDB I/O module are built
+         * into the kernel and you are using early debugging with
+         * kgdbwait. KGDB will control the kernel HW breakpoint registers.
+         */
+        if (kgdb_connected && arch_kgdb_ops.correct_hw_break)
+                arch_kgdb_ops.correct_hw_break();
+        else {
+#endif
+        /*
+         * Clear all 6 debug registers:
+         */
+
+        set_debugreg(0UL, 0);
+        set_debugreg(0UL, 1);
+        set_debugreg(0UL, 2);
+        set_debugreg(0UL, 3);
+        set_debugreg(0UL, 6);
+        set_debugreg(0UL, 7);
+#ifdef CONFIG_KGDB
+        /* If the kgdb is connected no debug regs should be altered. */
+        }
+#endif
+
+        fpu_init();
+
+        raw_local_save_flags(kernel_eflags);
+
+        if (is_uv_system())
+                uv_cpu_init();
+}
diff --git a/arch/x86/kernel/setup64.c b/arch/x86/kernel/setup64.c
deleted file mode 100644
index 151d3155ddf6..000000000000
--- a/arch/x86/kernel/setup64.c
+++ /dev/null
@@ -1,287 +0,0 @@
-/* 
- * X86-64 specific CPU setup.
- * Copyright (C) 1995  Linus Torvalds
- * Copyright 2001, 2002, 2003 SuSE Labs / Andi Kleen.
- * See setup.c for older changelog.
- */ 
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/sched.h>
-#include <linux/string.h>
-#include <linux/bootmem.h>
-#include <linux/bitops.h>
-#include <linux/module.h>
-#include <linux/kgdb.h>
-#include <linux/topology.h>
-#include <asm/pda.h>
-#include <asm/pgtable.h>
-#include <asm/processor.h>
-#include <asm/desc.h>
-#include <asm/atomic.h>
-#include <asm/mmu_context.h>
-#include <asm/smp.h>
-#include <asm/i387.h>
-#include <asm/percpu.h>
-#include <asm/proto.h>
-#include <asm/sections.h>
-#include <asm/setup.h>
-#include <asm/genapic.h>
-
-#ifndef CONFIG_DEBUG_BOOT_PARAMS
-struct boot_params __initdata boot_params;
-#else
-struct boot_params boot_params;
-#endif
-
-cpumask_t cpu_initialized __cpuinitdata = CPU_MASK_NONE;
-
-struct x8664_pda **_cpu_pda __read_mostly;
-EXPORT_SYMBOL(_cpu_pda);
-
-struct desc_ptr idt_descr = { 256 * 16 - 1, (unsigned long) idt_table };
-
-char boot_cpu_stack[IRQSTACKSIZE] __page_aligned_bss;
-
-unsigned long __supported_pte_mask __read_mostly = ~0UL;
-EXPORT_SYMBOL_GPL(__supported_pte_mask);
-
-static int do_not_nx __cpuinitdata = 0;
-
-/* noexec=on|off
-Control non executable mappings for 64bit processes.
-
-on      Enable(default)
-off     Disable
-*/ 
-static int __init nonx_setup(char *str)
-{
-        if (!str)
-                return -EINVAL;
-        if (!strncmp(str, "on", 2)) {
-                __supported_pte_mask |= _PAGE_NX; 
-                do_not_nx = 0; 
-        } else if (!strncmp(str, "off", 3)) {
-                do_not_nx = 1;
-                __supported_pte_mask &= ~_PAGE_NX;
-        }
-        return 0;
-} 
-early_param("noexec", nonx_setup);
-
-int force_personality32 = 0; 
-
-/* noexec32=on|off
-Control non executable heap for 32bit processes.
-To control the stack too use noexec=off
-
-on      PROT_READ does not imply PROT_EXEC for 32bit processes (default)
-off     PROT_READ implies PROT_EXEC
-*/
-static int __init nonx32_setup(char *str)
-{
-        if (!strcmp(str, "on"))
-                force_personality32 &= ~READ_IMPLIES_EXEC;
-        else if (!strcmp(str, "off"))
-                force_personality32 |= READ_IMPLIES_EXEC;
-        return 1;
-}
-__setup("noexec32=", nonx32_setup);
-
-void pda_init(int cpu)
-{ 
-        struct x8664_pda *pda = cpu_pda(cpu);
-
-        /* Setup up data that may be needed in __get_free_pages early */
-        asm volatile("movl %0,%%fs ; movl %0,%%gs" :: "r" (0)); 
-        /* Memory clobbers used to order PDA accessed */
-        mb();
-        wrmsrl(MSR_GS_BASE, pda);
-        mb();
-
-        pda->cpunumber = cpu; 
-        pda->irqcount = -1;
-        pda->kernelstack = 
-                (unsigned long)stack_thread_info() - PDA_STACKOFFSET + THREAD_SIZE; 
-        pda->active_mm = &init_mm;
-        pda->mmu_state = 0;
-
-        if (cpu == 0) {
-                /* others are initialized in smpboot.c */
-                pda->pcurrent = &init_task;
-                pda->irqstackptr = boot_cpu_stack; 
-        } else {
-                pda->irqstackptr = (char *)
-                        __get_free_pages(GFP_ATOMIC, IRQSTACK_ORDER);
-                if (!pda->irqstackptr)
-                        panic("cannot allocate irqstack for cpu %d", cpu); 
-
-                if (pda->nodenumber == 0 && cpu_to_node(cpu) != NUMA_NO_NODE)
-                        pda->nodenumber = cpu_to_node(cpu);
-        }
-
-        pda->irqstackptr += IRQSTACKSIZE-64;
-} 
-
-char boot_exception_stacks[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]
-__attribute__((section(".bss.page_aligned")));
-
-extern asmlinkage void ignore_sysret(void);
-
-/* May not be marked __init: used by software suspend */
-void syscall_init(void)
-{
-        /* 
-         * LSTAR and STAR live in a bit strange symbiosis.
-         * They both write to the same internal register. STAR allows to set CS/DS
-         * but only a 32bit target. LSTAR sets the 64bit rip.    
-         */ 
-        wrmsrl(MSR_STAR,  ((u64)__USER32_CS)<<48  | ((u64)__KERNEL_CS)<<32); 
-        wrmsrl(MSR_LSTAR, system_call); 
-        wrmsrl(MSR_CSTAR, ignore_sysret);
-
-#ifdef CONFIG_IA32_EMULATION            
-        syscall32_cpu_init ();
-#endif
-
-        /* Flags to clear on syscall */
-        wrmsrl(MSR_SYSCALL_MASK,
-               X86_EFLAGS_TF|X86_EFLAGS_DF|X86_EFLAGS_IF|X86_EFLAGS_IOPL);
-}
-
-void __cpuinit check_efer(void)
-{
-        unsigned long efer;
-
-        rdmsrl(MSR_EFER, efer); 
-        if (!(efer & EFER_NX) || do_not_nx) { 
-                __supported_pte_mask &= ~_PAGE_NX; 
-        }       
-}
-
-unsigned long kernel_eflags;
-
-/*
- * Copies of the original ist values from the tss are only accessed during
- * debugging, no special alignment required.
- */
-DEFINE_PER_CPU(struct orig_ist, orig_ist);
-
-/*
- * cpu_init() initializes state that is per-CPU. Some data is already
- * initialized (naturally) in the bootstrap process, such as the GDT
- * and IDT. We reload them nevertheless, this function acts as a
- * 'CPU state barrier', nothing should get across.
- * A lot of state is already set up in PDA init.
- */
-void __cpuinit cpu_init (void)
-{
-        int cpu = stack_smp_processor_id();
-        struct tss_struct *t = &per_cpu(init_tss, cpu);
-        struct orig_ist *orig_ist = &per_cpu(orig_ist, cpu);
-        unsigned long v; 
-        char *estacks = NULL; 
-        struct task_struct *me;
-        int i;
-
-        /* CPU 0 is initialised in head64.c */
-        if (cpu != 0) {
-                pda_init(cpu);
-        } else 
-                estacks = boot_exception_stacks; 
-
-        me = current;
-
-        if (cpu_test_and_set(cpu, cpu_initialized))
-                panic("CPU#%d already initialized!\n", cpu);
-
-        printk("Initializing CPU#%d\n", cpu);
-
-        clear_in_cr4(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE);
-
-        /*
-         * Initialize the per-CPU GDT with the boot GDT,
-         * and set up the GDT descriptor:
-         */
-
-        switch_to_new_gdt();
-        load_idt((const struct desc_ptr *)&idt_descr);
-
-        memset(me->thread.tls_array, 0, GDT_ENTRY_TLS_ENTRIES * 8);
-        syscall_init();
-
-        wrmsrl(MSR_FS_BASE, 0);
-        wrmsrl(MSR_KERNEL_GS_BASE, 0);
-        barrier(); 
-
-        check_efer();
-
-        /*
-         * set up and load the per-CPU TSS
-         */
-        for (v = 0; v < N_EXCEPTION_STACKS; v++) {
-                static const unsigned int order[N_EXCEPTION_STACKS] = {
-                        [0 ... N_EXCEPTION_STACKS - 1] = EXCEPTION_STACK_ORDER,
-                        [DEBUG_STACK - 1] = DEBUG_STACK_ORDER
-                };
-                if (cpu) {
-                        estacks = (char *)__get_free_pages(GFP_ATOMIC, order[v]);
-                        if (!estacks)
-                                panic("Cannot allocate exception stack %ld %d\n",
-                                      v, cpu); 
-                }
-                estacks += PAGE_SIZE << order[v];
-                orig_ist->ist[v] = t->x86_tss.ist[v] = (unsigned long)estacks;
-        }
-
-        t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap);
-        /*
-         * <= is required because the CPU will access up to
-         * 8 bits beyond the end of the IO permission bitmap.
-         */
-        for (i = 0; i <= IO_BITMAP_LONGS; i++)
-                t->io_bitmap[i] = ~0UL;
-
-        atomic_inc(&init_mm.mm_count);
-        me->active_mm = &init_mm;
-        if (me->mm)
-                BUG();
-        enter_lazy_tlb(&init_mm, me);
-
-        load_sp0(t, &current->thread);
-        set_tss_desc(cpu, t);
-        load_TR_desc();
-        load_LDT(&init_mm.context);
-
-#ifdef CONFIG_KGDB
-        /*
-         * If the kgdb is connected no debug regs should be altered.  This
-         * is only applicable when KGDB and a KGDB I/O module are built
-         * into the kernel and you are using early debugging with
-         * kgdbwait. KGDB will control the kernel HW breakpoint registers.
-         */
-        if (kgdb_connected && arch_kgdb_ops.correct_hw_break)
-                arch_kgdb_ops.correct_hw_break();
-        else {
-#endif
-        /*
-         * Clear all 6 debug registers:
-         */
-
-        set_debugreg(0UL, 0);
-        set_debugreg(0UL, 1);
-        set_debugreg(0UL, 2);
-        set_debugreg(0UL, 3);
-        set_debugreg(0UL, 6);
-        set_debugreg(0UL, 7);
-#ifdef CONFIG_KGDB
-        /* If the kgdb is connected no debug regs should be altered. */
-        }
-#endif
-
-        fpu_init(); 
-
-        raw_local_save_flags(kernel_eflags);
-
-        if (is_uv_system())
-                uv_cpu_init();
-}