22 files changed, 120 insertions, 42 deletions

diff --git a/arch/i386/Kconfig b/arch/i386/Kconfig
index 0afec8566e7b..5b1a7d46d1d9 100644
--- a/arch/i386/Kconfig
+++ b/arch/i386/Kconfig
@@ -733,7 +733,7 @@ config PHYSICAL_START
 
 config HOTPLUG_CPU
         bool "Support for hot-pluggable CPUs (EXPERIMENTAL)"
-        depends on SMP && HOTPLUG && EXPERIMENTAL
+        depends on SMP && HOTPLUG && EXPERIMENTAL && !X86_VOYAGER
         ---help---
           Say Y here to experiment with turning CPUs off and on.  CPUs
           can be controlled through /sys/devices/system/cpu.
@@ -1060,6 +1060,7 @@ source "arch/i386/oprofile/Kconfig"
 
 config KPROBES
         bool "Kprobes (EXPERIMENTAL)"
+        depends on EXPERIMENTAL && MODULES
         help
           Kprobes allows you to trap at almost any kernel address and
           execute a callback function.  register_kprobe() establishes
diff --git a/arch/i386/boot/.gitignore b/arch/i386/boot/.gitignore
new file mode 100644
index 000000000000..495f20c085de
--- /dev/null
+++ b/arch/i386/boot/.gitignore
@@ -0,0 +1,3 @@
+bootsect
+bzImage
+setup
diff --git a/arch/i386/boot/tools/.gitignore b/arch/i386/boot/tools/.gitignore
new file mode 100644
index 000000000000..378eac25d311
--- /dev/null
+++ b/arch/i386/boot/tools/.gitignore
@@ -0,0 +1 @@
+build
diff --git a/arch/i386/kernel/.gitignore b/arch/i386/kernel/.gitignore
new file mode 100644
index 000000000000..40836ad9079c
--- /dev/null
+++ b/arch/i386/kernel/.gitignore
@@ -0,0 +1 @@
+vsyscall.lds
diff --git a/arch/i386/kernel/Makefile b/arch/i386/kernel/Makefile
index 60c3f76dfca4..53bb9a79e274 100644
--- a/arch/i386/kernel/Makefile
+++ b/arch/i386/kernel/Makefile
@@ -7,7 +7,7 @@ extra-y := head.o init_task.o vmlinux.lds
 obj-y   := process.o semaphore.o signal.o entry.o traps.o irq.o \
                 ptrace.o time.o ioport.o ldt.o setup.o i8259.o sys_i386.o \
                 pci-dma.o i386_ksyms.o i387.o dmi_scan.o bootflag.o \
-                quirks.o i8237.o
+                quirks.o i8237.o topology.o
 
 obj-y                           += cpu/
 obj-y                           += timers/
diff --git a/arch/i386/kernel/cpu/common.c b/arch/i386/kernel/cpu/common.c
index 7eb9213734a3..4ecd4b326ded 100644
--- a/arch/i386/kernel/cpu/common.c
+++ b/arch/i386/kernel/cpu/common.c
@@ -4,6 +4,7 @@
 #include <linux/smp.h>
 #include <linux/module.h>
 #include <linux/percpu.h>
+#include <linux/bootmem.h>
 #include <asm/semaphore.h>
 #include <asm/processor.h>
 #include <asm/i387.h>
@@ -18,6 +19,9 @@
 
 #include "cpu.h"
 
+DEFINE_PER_CPU(struct Xgt_desc_struct, cpu_gdt_descr);
+EXPORT_PER_CPU_SYMBOL(cpu_gdt_descr);
+
 DEFINE_PER_CPU(unsigned char, cpu_16bit_stack[CPU_16BIT_STACK_SIZE]);
 EXPORT_PER_CPU_SYMBOL(cpu_16bit_stack);
 
@@ -571,8 +575,9 @@ void __devinit cpu_init(void)
         int cpu = smp_processor_id();
         struct tss_struct * t = &per_cpu(init_tss, cpu);
         struct thread_struct *thread = &current->thread;
-        struct desc_struct *gdt = get_cpu_gdt_table(cpu);
+        struct desc_struct *gdt;
         __u32 stk16_off = (__u32)&per_cpu(cpu_16bit_stack, cpu);
+        struct Xgt_desc_struct *cpu_gdt_descr = &per_cpu(cpu_gdt_descr, cpu);
 
         if (cpu_test_and_set(cpu, cpu_initialized)) {
                 printk(KERN_WARNING "CPU#%d already initialized!\n", cpu);
@@ -590,6 +595,25 @@ void __devinit cpu_init(void)
         }
 
         /*
+         * This is a horrible hack to allocate the GDT.  The problem
+         * is that cpu_init() is called really early for the boot CPU
+         * (and hence needs bootmem) but much later for the secondary
+         * CPUs, when bootmem will have gone away
+         */
+        if (NODE_DATA(0)->bdata->node_bootmem_map) {
+                gdt = (struct desc_struct *)alloc_bootmem_pages(PAGE_SIZE);
+                /* alloc_bootmem_pages panics on failure, so no check */
+                memset(gdt, 0, PAGE_SIZE);
+        } else {
+                gdt = (struct desc_struct *)get_zeroed_page(GFP_KERNEL);
+                if (unlikely(!gdt)) {
+                        printk(KERN_CRIT "CPU%d failed to allocate GDT\n", cpu);
+                        for (;;)
+                                local_irq_enable();
+                }
+        }
+
+        /*
          * Initialize the per-CPU GDT with the boot GDT,
          * and set up the GDT descriptor:
          */
@@ -601,10 +625,10 @@ void __devinit cpu_init(void)
                 ((((__u64)stk16_off) << 32) & 0xff00000000000000ULL) |
                 (CPU_16BIT_STACK_SIZE - 1);
 
-        cpu_gdt_descr[cpu].size = GDT_SIZE - 1;
-        cpu_gdt_descr[cpu].address = (unsigned long)gdt;
+        cpu_gdt_descr->size = GDT_SIZE - 1;
+        cpu_gdt_descr->address = (unsigned long)gdt;
 
-        load_gdt(&cpu_gdt_descr[cpu]);
+        load_gdt(cpu_gdt_descr);
         load_idt(&idt_descr);
 
         /*
diff --git a/arch/i386/kernel/cpu/transmeta.c b/arch/i386/kernel/cpu/transmeta.c
index bdbeb77f4e22..7214c9b577ab 100644
--- a/arch/i386/kernel/cpu/transmeta.c
+++ b/arch/i386/kernel/cpu/transmeta.c
@@ -1,4 +1,5 @@
 #include <linux/kernel.h>
+#include <linux/mm.h>
 #include <linux/init.h>
 #include <asm/processor.h>
 #include <asm/msr.h>
diff --git a/arch/i386/kernel/efi.c b/arch/i386/kernel/efi.c
index ecad519fd395..e3e42fd62401 100644
--- a/arch/i386/kernel/efi.c
+++ b/arch/i386/kernel/efi.c
@@ -103,17 +103,19 @@ static void efi_call_phys_prelog(void)
          */
         local_flush_tlb();
 
-        cpu_gdt_descr[0].address = __pa(cpu_gdt_descr[0].address);
-        load_gdt((struct Xgt_desc_struct *) __pa(&cpu_gdt_descr[0]));
+        per_cpu(cpu_gdt_descr, 0).address =
+                                 __pa(per_cpu(cpu_gdt_descr, 0).address);
+        load_gdt((struct Xgt_desc_struct *)__pa(&per_cpu(cpu_gdt_descr, 0)));
 }
 
 static void efi_call_phys_epilog(void)
 {
         unsigned long cr4;
 
-        cpu_gdt_descr[0].address =
-                (unsigned long) __va(cpu_gdt_descr[0].address);
-        load_gdt(&cpu_gdt_descr[0]);
+        per_cpu(cpu_gdt_descr, 0).address =
+                        (unsigned long)__va(per_cpu(cpu_gdt_descr, 0).address);
+        load_gdt((struct Xgt_desc_struct *)__va(&per_cpu(cpu_gdt_descr, 0)));
+
         cr4 = read_cr4();
 
         if (cr4 & X86_CR4_PSE) {
diff --git a/arch/i386/kernel/head.S b/arch/i386/kernel/head.S
index 5884469f6bfe..e0b7c632efbc 100644
--- a/arch/i386/kernel/head.S
+++ b/arch/i386/kernel/head.S
@@ -398,7 +398,11 @@ ignore_int:
         pushl 32(%esp)
         pushl 40(%esp)
         pushl $int_msg
+#ifdef CONFIG_EARLY_PRINTK
+        call early_printk
+#else
         call printk
+#endif
         addl $(5*4),%esp
         popl %ds
         popl %es
@@ -530,5 +534,3 @@ ENTRY(cpu_gdt_table)
         .quad 0x0000000000000000        /* 0xf0 - unused */
         .quad 0x0000000000000000        /* 0xf8 - GDT entry 31: double-fault TSS */
 
-        /* Be sure this is zeroed to avoid false validations in Xen */
-        .fill PAGE_SIZE_asm / 8 - GDT_ENTRIES,8,0
diff --git a/arch/i386/kernel/i386_ksyms.c b/arch/i386/kernel/i386_ksyms.c
index 3999bec50c33..055325056a74 100644
--- a/arch/i386/kernel/i386_ksyms.c
+++ b/arch/i386/kernel/i386_ksyms.c
@@ -3,8 +3,6 @@
 #include <asm/checksum.h>
 #include <asm/desc.h>
 
-EXPORT_SYMBOL_GPL(cpu_gdt_descr);
-
 EXPORT_SYMBOL(__down_failed);
 EXPORT_SYMBOL(__down_failed_interruptible);
 EXPORT_SYMBOL(__down_failed_trylock);
diff --git a/arch/i386/kernel/io_apic.c b/arch/i386/kernel/io_apic.c
index f2dd218d88cb..235822b3f41b 100644
--- a/arch/i386/kernel/io_apic.c
+++ b/arch/i386/kernel/io_apic.c
@@ -2566,8 +2566,10 @@ int __init io_apic_get_unique_id (int ioapic, int apic_id)
                 spin_unlock_irqrestore(&ioapic_lock, flags);
 
                 /* Sanity check */
-                if (reg_00.bits.ID != apic_id)
-                        panic("IOAPIC[%d]: Unable change apic_id!\n", ioapic);
+                if (reg_00.bits.ID != apic_id) {
+                        printk("IOAPIC[%d]: Unable to change apic_id!\n", ioapic);
+                        return -1;
+                }
         }
 
         apic_printk(APIC_VERBOSE, KERN_INFO
diff --git a/arch/i386/kernel/kprobes.c b/arch/i386/kernel/kprobes.c
index 6483eeb1a4e8..694a13997637 100644
--- a/arch/i386/kernel/kprobes.c
+++ b/arch/i386/kernel/kprobes.c
@@ -58,6 +58,11 @@ static inline int is_IF_modifier(kprobe_opcode_t opcode)
 
 int __kprobes arch_prepare_kprobe(struct kprobe *p)
 {
+        /* insn: must be on special executable page on i386. */
+        p->ainsn.insn = get_insn_slot();
+        if (!p->ainsn.insn)
+                return -ENOMEM;
+
         memcpy(p->ainsn.insn, p->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
         p->opcode = *p->addr;
         return 0;
@@ -77,6 +82,13 @@ void __kprobes arch_disarm_kprobe(struct kprobe *p)
                            (unsigned long) p->addr + sizeof(kprobe_opcode_t));
 }
 
+void __kprobes arch_remove_kprobe(struct kprobe *p)
+{
+        down(&kprobe_mutex);
+        free_insn_slot(p->ainsn.insn);
+        up(&kprobe_mutex);
+}
+
 static inline void save_previous_kprobe(struct kprobe_ctlblk *kcb)
 {
         kcb->prev_kprobe.kp = kprobe_running();
@@ -111,7 +123,7 @@ static inline void prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
         if (p->opcode == BREAKPOINT_INSTRUCTION)
                 regs->eip = (unsigned long)p->addr;
         else
-                regs->eip = (unsigned long)&p->ainsn.insn;
+                regs->eip = (unsigned long)p->ainsn.insn;
 }
 
 /* Called with kretprobe_lock held */
@@ -351,7 +363,7 @@ static void __kprobes resume_execution(struct kprobe *p,
 {
         unsigned long *tos = (unsigned long *)&regs->esp;
         unsigned long next_eip = 0;
-        unsigned long copy_eip = (unsigned long)&p->ainsn.insn;
+        unsigned long copy_eip = (unsigned long)p->ainsn.insn;
         unsigned long orig_eip = (unsigned long)p->addr;
 
         switch (p->ainsn.insn[0]) {
diff --git a/arch/i386/kernel/mpparse.c b/arch/i386/kernel/mpparse.c
index 0102f3d50e57..e6e2f43db85e 100644
--- a/arch/i386/kernel/mpparse.c
+++ b/arch/i386/kernel/mpparse.c
@@ -710,7 +710,7 @@ void __init get_smp_config (void)
                  * Read the physical hardware table.  Anything here will
                  * override the defaults.
                  */
-                if (!smp_read_mpc((void *)mpf->mpf_physptr)) {
+                if (!smp_read_mpc(phys_to_virt(mpf->mpf_physptr))) {
                         smp_found_config = 0;
                         printk(KERN_ERR "BIOS bug, MP table errors detected!...\n");
                         printk(KERN_ERR "... disabling SMP support. (tell your hw vendor)\n");
@@ -915,6 +915,7 @@ void __init mp_register_ioapic (
         u32                     gsi_base)
 {
         int                     idx = 0;
+        int                     tmpid;
 
         if (nr_ioapics >= MAX_IO_APICS) {
                 printk(KERN_ERR "ERROR: Max # of I/O APICs (%d) exceeded "
@@ -935,9 +936,14 @@ void __init mp_register_ioapic (
 
         set_fixmap_nocache(FIX_IO_APIC_BASE_0 + idx, address);
         if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && (boot_cpu_data.x86 < 15))
-                mp_ioapics[idx].mpc_apicid = io_apic_get_unique_id(idx, id);
+                tmpid = io_apic_get_unique_id(idx, id);
         else
-                mp_ioapics[idx].mpc_apicid = id;
+                tmpid = id;
+        if (tmpid == -1) {
+                nr_ioapics--;
+                return;
+        }
+        mp_ioapics[idx].mpc_apicid = tmpid;
         mp_ioapics[idx].mpc_apicver = io_apic_get_version(idx);
         
         /* 
diff --git a/arch/i386/kernel/smpboot.c b/arch/i386/kernel/smpboot.c
index 255adb498268..eba7f53f8b4a 100644
--- a/arch/i386/kernel/smpboot.c
+++ b/arch/i386/kernel/smpboot.c
@@ -87,11 +87,7 @@ EXPORT_SYMBOL(cpu_online_map);
 cpumask_t cpu_callin_map;
 cpumask_t cpu_callout_map;
 EXPORT_SYMBOL(cpu_callout_map);
-#ifdef CONFIG_HOTPLUG_CPU
-cpumask_t cpu_possible_map = CPU_MASK_ALL;
-#else
 cpumask_t cpu_possible_map;
-#endif
 EXPORT_SYMBOL(cpu_possible_map);
 static cpumask_t smp_commenced_mask;
 
@@ -902,12 +898,6 @@ static int __devinit do_boot_cpu(int apicid, int cpu)
         unsigned long start_eip;
         unsigned short nmi_high = 0, nmi_low = 0;
 
-        if (!cpu_gdt_descr[cpu].address &&
-            !(cpu_gdt_descr[cpu].address = get_zeroed_page(GFP_KERNEL))) {
-                printk("Failed to allocate GDT for CPU %d\n", cpu);
-                return 1;
-        }
-
         ++cpucount;
 
         /*
diff --git a/arch/i386/kernel/syscall_table.S b/arch/i386/kernel/syscall_table.S
index 5a8b3fb6d27b..ac687d00a1ce 100644
--- a/arch/i386/kernel/syscall_table.S
+++ b/arch/i386/kernel/syscall_table.S
@@ -299,7 +299,7 @@ ENTRY(sys_call_table)
         .long sys_mknodat
         .long sys_fchownat
         .long sys_futimesat
-        .long sys_newfstatat            /* 300 */
+        .long sys_fstatat64             /* 300 */
         .long sys_unlinkat
         .long sys_renameat
         .long sys_linkat
diff --git a/arch/i386/kernel/timers/timer_tsc.c b/arch/i386/kernel/timers/timer_tsc.c
index 7c86e3c5f1c1..a7f5a2aceba2 100644
--- a/arch/i386/kernel/timers/timer_tsc.c
+++ b/arch/i386/kernel/timers/timer_tsc.c
@@ -282,6 +282,10 @@ time_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
         if (val != CPUFREQ_RESUMECHANGE)
                 write_seqlock_irq(&xtime_lock);
         if (!ref_freq) {
+                if (!freq->old){
+                        ref_freq = freq->new;
+                        goto end;
+                }
                 ref_freq = freq->old;
                 loops_per_jiffy_ref = cpu_data[freq->cpu].loops_per_jiffy;
 #ifndef CONFIG_SMP
@@ -307,6 +311,7 @@ time_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
 #endif
         }
 
+end:
         if (val != CPUFREQ_RESUMECHANGE)
                 write_sequnlock_irq(&xtime_lock);
 
diff --git a/arch/i386/mach-default/topology.c b/arch/i386/kernel/topology.c
index b64314069e78..67a0e1baa28b 100644
--- a/arch/i386/mach-default/topology.c
+++ b/arch/i386/kernel/topology.c
@@ -1,12 +1,12 @@
 /*
- * arch/i386/mach-generic/topology.c - Populate driverfs with topology information
+ * arch/i386/kernel/topology.c - Populate driverfs with topology information
  *
  * Written by: Matthew Dobson, IBM Corporation
  * Original Code: Paul Dorwin, IBM Corporation, Patrick Mochel, OSDL
  *
  * Copyright (C) 2002, IBM Corp.
  *
- * All rights reserved.          
+ * All rights reserved.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -34,7 +34,7 @@ static struct i386_cpu cpu_devices[NR_CPUS];
 
 int arch_register_cpu(int num){
         struct node *parent = NULL;
-        
+
 #ifdef CONFIG_NUMA
         int node = cpu_to_node(num);
         if (node_online(node))
diff --git a/arch/i386/kernel/vsyscall-sysenter.S b/arch/i386/kernel/vsyscall-sysenter.S
index 4daefb2ec1b2..76b728159403 100644
--- a/arch/i386/kernel/vsyscall-sysenter.S
+++ b/arch/i386/kernel/vsyscall-sysenter.S
@@ -7,6 +7,21 @@
  *    for details.
  */
 
+/*
+ * The caller puts arg2 in %ecx, which gets pushed. The kernel will use
+ * %ecx itself for arg2. The pushing is because the sysexit instruction
+ * (found in entry.S) requires that we clobber %ecx with the desired %esp.
+ * User code might expect that %ecx is unclobbered though, as it would be
+ * for returning via the iret instruction, so we must push and pop.
+ *
+ * The caller puts arg3 in %edx, which the sysexit instruction requires
+ * for %eip. Thus, exactly as for arg2, we must push and pop.
+ *
+ * Arg6 is different. The caller puts arg6 in %ebp. Since the sysenter
+ * instruction clobbers %esp, the user's %esp won't even survive entry
+ * into the kernel. We store %esp in %ebp. Code in entry.S must fetch
+ * arg6 from the stack.
+ */
         .text
         .globl __kernel_vsyscall
         .type __kernel_vsyscall,@function
diff --git a/arch/i386/mach-default/Makefile b/arch/i386/mach-default/Makefile
index e95bb0237921..012fe34459e6 100644
--- a/arch/i386/mach-default/Makefile
+++ b/arch/i386/mach-default/Makefile
@@ -2,4 +2,4 @@
 # Makefile for the linux kernel.
 #
 
-obj-y                           := setup.o topology.o
+obj-y                           := setup.o
diff --git a/arch/i386/mach-voyager/voyager_basic.c b/arch/i386/mach-voyager/voyager_basic.c
index aa49a33a572c..b584060ec004 100644
--- a/arch/i386/mach-voyager/voyager_basic.c
+++ b/arch/i386/mach-voyager/voyager_basic.c
@@ -23,6 +23,8 @@
 #include <linux/delay.h>
 #include <linux/reboot.h>
 #include <linux/sysrq.h>
+#include <linux/smp.h>
+#include <linux/nodemask.h>
 #include <asm/io.h>
 #include <asm/voyager.h>
 #include <asm/vic.h>
@@ -328,4 +330,3 @@ void machine_power_off(void)
         if (pm_power_off)
                 pm_power_off();
 }
-
diff --git a/arch/i386/mach-voyager/voyager_smp.c b/arch/i386/mach-voyager/voyager_smp.c
index 72a1b9cae2e4..8165626a5c30 100644
--- a/arch/i386/mach-voyager/voyager_smp.c
+++ b/arch/i386/mach-voyager/voyager_smp.c
@@ -240,7 +240,7 @@ static cpumask_t smp_commenced_mask = CPU_MASK_NONE;
 cpumask_t cpu_callin_map = CPU_MASK_NONE;
 cpumask_t cpu_callout_map = CPU_MASK_NONE;
 EXPORT_SYMBOL(cpu_callout_map);
-cpumask_t cpu_possible_map = CPU_MASK_ALL;
+cpumask_t cpu_possible_map = CPU_MASK_NONE;
 EXPORT_SYMBOL(cpu_possible_map);
 
 /* The per processor IRQ masks (these are usually kept in sync) */
@@ -402,6 +402,7 @@ find_smp_config(void)
         cpus_addr(phys_cpu_present_map)[0] |= voyager_extended_cmos_read(VOYAGER_PROCESSOR_PRESENT_MASK + 1) << 8;
         cpus_addr(phys_cpu_present_map)[0] |= voyager_extended_cmos_read(VOYAGER_PROCESSOR_PRESENT_MASK + 2) << 16;
         cpus_addr(phys_cpu_present_map)[0] |= voyager_extended_cmos_read(VOYAGER_PROCESSOR_PRESENT_MASK + 3) << 24;
+        cpu_possible_map = phys_cpu_present_map;
         printk("VOYAGER SMP: phys_cpu_present_map = 0x%lx\n", cpus_addr(phys_cpu_present_map)[0]);
         /* Here we set up the VIC to enable SMP */
         /* enable the CPIs by writing the base vector to their register */
diff --git a/arch/i386/oprofile/backtrace.c b/arch/i386/oprofile/backtrace.c
index acc18138fb22..c049ce414f01 100644
--- a/arch/i386/oprofile/backtrace.c
+++ b/arch/i386/oprofile/backtrace.c
@@ -20,7 +20,20 @@ struct frame_head {
 } __attribute__((packed));
 
 static struct frame_head *
-dump_backtrace(struct frame_head * head)
+dump_kernel_backtrace(struct frame_head * head)
+{
+        oprofile_add_trace(head->ret);
+
+        /* frame pointers should strictly progress back up the stack
+         * (towards higher addresses) */
+        if (head >= head->ebp)
+                return NULL;
+
+        return head->ebp;
+}
+
+static struct frame_head *
+dump_user_backtrace(struct frame_head * head)
 {
         struct frame_head bufhead[2];
 
@@ -105,10 +118,10 @@ x86_backtrace(struct pt_regs * const regs, unsigned int depth)
 
         if (!user_mode_vm(regs)) {
                 while (depth-- && valid_kernel_stack(head, regs))
-                        head = dump_backtrace(head);
+                        head = dump_kernel_backtrace(head);
                 return;
         }
 
         while (depth-- && head)
-                head = dump_backtrace(head);
+                head = dump_user_backtrace(head);
 }