20 files changed, 166 insertions, 123 deletions

diff --git a/arch/i386/kernel/apic.c b/arch/i386/kernel/apic.c
index 496a2c9909fe..d8f94e78de8a 100644
--- a/arch/i386/kernel/apic.c
+++ b/arch/i386/kernel/apic.c
@@ -721,7 +721,7 @@ static int __init apic_set_verbosity(char *str)
                 apic_verbosity = APIC_VERBOSE;
         else
                 printk(KERN_WARNING "APIC Verbosity level %s not recognised"
-                                " use apic=verbose or apic=debug", str);
+                                " use apic=verbose or apic=debug\n", str);
 
         return 0;
 }
diff --git a/arch/i386/kernel/apm.c b/arch/i386/kernel/apm.c
index 1e60acbed3c1..2d793d4aef1a 100644
--- a/arch/i386/kernel/apm.c
+++ b/arch/i386/kernel/apm.c
@@ -303,17 +303,6 @@ extern int (*console_blank_hook)(int);
 #include "apm.h"
 
 /*
- * Define to make all _set_limit calls use 64k limits.  The APM 1.1 BIOS is
- * supposed to provide limit information that it recognizes.  Many machines
- * do this correctly, but many others do not restrict themselves to their
- * claimed limit.  When this happens, they will cause a segmentation
- * violation in the kernel at boot time.  Most BIOS's, however, will
- * respect a 64k limit, so we use that.  If you want to be pedantic and
- * hold your BIOS to its claims, then undefine this.
- */
-#define APM_RELAX_SEGMENTS
-
-/*
  * Define to re-initialize the interrupt 0 timer to 100 Hz after a suspend.
  * This patched by Chad Miller <cmiller@surfsouth.com>, original code by
  * David Chen <chen@ctpa04.mit.edu>
@@ -1075,22 +1064,23 @@ static int apm_engage_power_management(u_short device, int enable)
  
 static int apm_console_blank(int blank)
 {
-        int     error;
-        u_short state;
+        int error, i;
+        u_short state;
+        static const u_short dev[3] = { 0x100, 0x1FF, 0x101 };
 
         state = blank ? APM_STATE_STANDBY : APM_STATE_READY;
-        /* Blank the first display device */
-        error = set_power_state(0x100, state);
-        if ((error != APM_SUCCESS) && (error != APM_NO_ERROR)) {
-                /* try to blank them all instead */
-                error = set_power_state(0x1ff, state);
-                if ((error != APM_SUCCESS) && (error != APM_NO_ERROR))
-                        /* try to blank device one instead */
-                        error = set_power_state(0x101, state);
+
+        for (i = 0; i < ARRAY_SIZE(dev); i++) {
+                error = set_power_state(dev[i], state);
+
+                if ((error == APM_SUCCESS) || (error == APM_NO_ERROR))
+                        return 1;
+
+                if (error == APM_NOT_ENGAGED)
+                        break;
         }
-        if ((error == APM_SUCCESS) || (error == APM_NO_ERROR))
-                return 1;
-        if (error == APM_NOT_ENGAGED) {
+
+        if (error == APM_NOT_ENGAGED && state != APM_STATE_READY) {
                 static int tried;
                 int eng_error;
                 if (tried++ == 0) {
@@ -2233,8 +2223,8 @@ static struct dmi_system_id __initdata apm_dmi_table[] = {
 static int __init apm_init(void)
 {
         struct proc_dir_entry *apm_proc;
+        struct desc_struct *gdt;
         int ret;
-        int i;
 
         dmi_check_system(apm_dmi_table);
 
@@ -2312,45 +2302,30 @@ static int __init apm_init(void)
         set_base(bad_bios_desc, __va((unsigned long)0x40 << 4));
         _set_limit((char *)&bad_bios_desc, 4095 - (0x40 << 4));
 
+        /*
+         * Set up the long jump entry point to the APM BIOS, which is called
+         * from inline assembly.
+         */
         apm_bios_entry.offset = apm_info.bios.offset;
         apm_bios_entry.segment = APM_CS;
 
-        for (i = 0; i < NR_CPUS; i++) {
-                struct desc_struct *gdt = get_cpu_gdt_table(i);
-                set_base(gdt[APM_CS >> 3],
-                         __va((unsigned long)apm_info.bios.cseg << 4));
-                set_base(gdt[APM_CS_16 >> 3],
-                         __va((unsigned long)apm_info.bios.cseg_16 << 4));
-                set_base(gdt[APM_DS >> 3],
-                         __va((unsigned long)apm_info.bios.dseg << 4));
-#ifndef APM_RELAX_SEGMENTS
-                if (apm_info.bios.version == 0x100) {
-#endif
-                        /* For ASUS motherboard, Award BIOS rev 110 (and others?) */
-                        _set_limit((char *)&gdt[APM_CS >> 3], 64 * 1024 - 1);
-                        /* For some unknown machine. */
-                        _set_limit((char *)&gdt[APM_CS_16 >> 3], 64 * 1024 - 1);
-                        /* For the DEC Hinote Ultra CT475 (and others?) */
-                        _set_limit((char *)&gdt[APM_DS >> 3], 64 * 1024 - 1);
-#ifndef APM_RELAX_SEGMENTS
-                } else {
-                        _set_limit((char *)&gdt[APM_CS >> 3],
-                                (apm_info.bios.cseg_len - 1) & 0xffff);
-                        _set_limit((char *)&gdt[APM_CS_16 >> 3],
-                                (apm_info.bios.cseg_16_len - 1) & 0xffff);
-                        _set_limit((char *)&gdt[APM_DS >> 3],
-                                (apm_info.bios.dseg_len - 1) & 0xffff);
-                      /* workaround for broken BIOSes */
-                        if (apm_info.bios.cseg_len <= apm_info.bios.offset)
-                                _set_limit((char *)&gdt[APM_CS >> 3], 64 * 1024 -1);
-                       if (apm_info.bios.dseg_len <= 0x40) { /* 0x40 * 4kB == 64kB */
-                                /* for the BIOS that assumes granularity = 1 */
-                                gdt[APM_DS >> 3].b |= 0x800000;
-                                printk(KERN_NOTICE "apm: we set the granularity of dseg.\n");
-                        }
-                }
-#endif
-        }
+        /*
+         * The APM 1.1 BIOS is supposed to provide limit information that it
+         * recognizes.  Many machines do this correctly, but many others do
+         * not restrict themselves to their claimed limit.  When this happens,
+         * they will cause a segmentation violation in the kernel at boot time.
+         * Most BIOS's, however, will respect a 64k limit, so we use that.
+         *
+         * Note we only set APM segments on CPU zero, since we pin the APM
+         * code to that CPU.
+         */
+        gdt = get_cpu_gdt_table(0);
+        set_base(gdt[APM_CS >> 3],
+                 __va((unsigned long)apm_info.bios.cseg << 4));
+        set_base(gdt[APM_CS_16 >> 3],
+                 __va((unsigned long)apm_info.bios.cseg_16 << 4));
+        set_base(gdt[APM_DS >> 3],
+                 __va((unsigned long)apm_info.bios.dseg << 4));
 
         apm_proc = create_proc_info_entry("apm", 0, NULL, apm_get_info);
         if (apm_proc)
diff --git a/arch/i386/kernel/cpu/amd.c b/arch/i386/kernel/cpu/amd.c
index e344ef88cfcd..e7697e077f6b 100644
--- a/arch/i386/kernel/cpu/amd.c
+++ b/arch/i386/kernel/cpu/amd.c
@@ -161,8 +161,13 @@ static void __init init_amd(struct cpuinfo_x86 *c)
                                         set_bit(X86_FEATURE_K6_MTRR, c->x86_capability);
                                 break;
                         }
-                        break;
 
+                        if (c->x86_model == 10) {
+                                /* AMD Geode LX is model 10 */
+                                /* placeholder for any needed mods */
+                                break;
+                        }
+                        break;
                 case 6: /* An Athlon/Duron */
  
                         /* Bit 15 of Athlon specific MSR 15, needs to be 0
diff --git a/arch/i386/kernel/cpu/common.c b/arch/i386/kernel/cpu/common.c
index 31e344b26bae..cca655688ffc 100644
--- a/arch/i386/kernel/cpu/common.c
+++ b/arch/i386/kernel/cpu/common.c
@@ -18,9 +18,6 @@
 
 #include "cpu.h"
 
-DEFINE_PER_CPU(struct desc_struct, cpu_gdt_table[GDT_ENTRIES]);
-EXPORT_PER_CPU_SYMBOL(cpu_gdt_table);
-
 DEFINE_PER_CPU(unsigned char, cpu_16bit_stack[CPU_16BIT_STACK_SIZE]);
 EXPORT_PER_CPU_SYMBOL(cpu_16bit_stack);
 
@@ -599,11 +596,6 @@ void __devinit cpu_init(void)
         load_idt(&idt_descr);
 
         /*
-         * Delete NT
-         */
-        __asm__("pushfl ; andl $0xffffbfff,(%esp) ; popfl");
-
-        /*
          * Set up and load the per-CPU TSS and LDT
          */
         atomic_inc(&init_mm.mm_count);
diff --git a/arch/i386/kernel/cpu/cyrix.c b/arch/i386/kernel/cpu/cyrix.c
index ff87cc22b323..75015975d038 100644
--- a/arch/i386/kernel/cpu/cyrix.c
+++ b/arch/i386/kernel/cpu/cyrix.c
@@ -343,6 +343,31 @@ static void __init init_cyrix(struct cpuinfo_x86 *c)
 }
 
 /*
+ * Handle National Semiconductor branded processors
+ */
+static void __devinit init_nsc(struct cpuinfo_x86 *c)
+{
+        /* There may be GX1 processors in the wild that are branded
+         * NSC and not Cyrix.
+         *
+         * This function only handles the GX processor, and kicks every
+         * thing else to the Cyrix init function above - that should
+         * cover any processors that might have been branded differently
+         * after NSC aquired Cyrix.
+         *
+         * If this breaks your GX1 horribly, please e-mail
+         * info-linux@ldcmail.amd.com to tell us.
+         */
+
+        /* Handle the GX (Formally known as the GX2) */
+
+        if (c->x86 == 5 && c->x86_model == 5)
+                display_cacheinfo(c);
+        else
+                init_cyrix(c);
+}
+
+/*
  * Cyrix CPUs without cpuid or with cpuid not yet enabled can be detected
  * by the fact that they preserve the flags across the division of 5/2.
  * PII and PPro exhibit this behavior too, but they have cpuid available.
@@ -422,7 +447,7 @@ int __init cyrix_init_cpu(void)
 static struct cpu_dev nsc_cpu_dev __initdata = {
         .c_vendor       = "NSC",
         .c_ident        = { "Geode by NSC" },
-        .c_init         = init_cyrix,
+        .c_init         = init_nsc,
         .c_identify     = generic_identify,
 };
 
diff --git a/arch/i386/kernel/cpuid.c b/arch/i386/kernel/cpuid.c
index 13bae799e626..006141d1c12a 100644
--- a/arch/i386/kernel/cpuid.c
+++ b/arch/i386/kernel/cpuid.c
@@ -117,14 +117,13 @@ static ssize_t cpuid_read(struct file *file, char __user *buf,
 {
         char __user *tmp = buf;
         u32 data[4];
-        size_t rv;
         u32 reg = *ppos;
         int cpu = iminor(file->f_dentry->d_inode);
 
         if (count % 16)
                 return -EINVAL; /* Invalid chunk size */
 
-        for (rv = 0; count; count -= 16) {
+        for (; count; count -= 16) {
                 do_cpuid(cpu, reg, data);
                 if (copy_to_user(tmp, &data, 16))
                         return -EFAULT;
diff --git a/arch/i386/kernel/entry.S b/arch/i386/kernel/entry.S
index e50b93155249..607c06007508 100644
--- a/arch/i386/kernel/entry.S
+++ b/arch/i386/kernel/entry.S
@@ -657,6 +657,7 @@ ENTRY(spurious_interrupt_bug)
         pushl $do_spurious_interrupt_bug
         jmp error_code
 
+.section .rodata,"a"
 #include "syscall_table.S"
 
 syscall_table_size=(.-sys_call_table)
diff --git a/arch/i386/kernel/head.S b/arch/i386/kernel/head.S
index e437fb367498..5884469f6bfe 100644
--- a/arch/i386/kernel/head.S
+++ b/arch/i386/kernel/head.S
@@ -504,19 +504,24 @@ ENTRY(cpu_gdt_table)
         .quad 0x0000000000000000        /* 0x80 TSS descriptor */
         .quad 0x0000000000000000        /* 0x88 LDT descriptor */
 
-        /* Segments used for calling PnP BIOS */
-        .quad 0x00c09a0000000000        /* 0x90 32-bit code */
-        .quad 0x00809a0000000000        /* 0x98 16-bit code */
-        .quad 0x0080920000000000        /* 0xa0 16-bit data */
-        .quad 0x0080920000000000        /* 0xa8 16-bit data */
-        .quad 0x0080920000000000        /* 0xb0 16-bit data */
+        /*
+         * Segments used for calling PnP BIOS have byte granularity.
+         * They code segments and data segments have fixed 64k limits,
+         * the transfer segment sizes are set at run time.
+         */
+        .quad 0x00409a000000ffff        /* 0x90 32-bit code */
+        .quad 0x00009a000000ffff        /* 0x98 16-bit code */
+        .quad 0x000092000000ffff        /* 0xa0 16-bit data */
+        .quad 0x0000920000000000        /* 0xa8 16-bit data */
+        .quad 0x0000920000000000        /* 0xb0 16-bit data */
+
         /*
          * The APM segments have byte granularity and their bases
-         * and limits are set at run time.
+         * are set at run time.  All have 64k limits.
          */
-        .quad 0x00409a0000000000        /* 0xb8 APM CS    code */
-        .quad 0x00009a0000000000        /* 0xc0 APM CS 16 code (16 bit) */
-        .quad 0x0040920000000000        /* 0xc8 APM DS    data */
+        .quad 0x00409a000000ffff        /* 0xb8 APM CS    code */
+        .quad 0x00009a000000ffff        /* 0xc0 APM CS 16 code (16 bit) */
+        .quad 0x004092000000ffff        /* 0xc8 APM DS    data */
 
         .quad 0x0000920000000000        /* 0xd0 - ESPFIX 16-bit SS */
         .quad 0x0000000000000000        /* 0xd8 - unused */
@@ -525,3 +530,5 @@ 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 180f070d03cb..3999bec50c33 100644
--- a/arch/i386/kernel/i386_ksyms.c
+++ b/arch/i386/kernel/i386_ksyms.c
@@ -3,8 +3,7 @@
 #include <asm/checksum.h>
 #include <asm/desc.h>
 
-/* This is definitely a GPL-only symbol */
-EXPORT_SYMBOL_GPL(cpu_gdt_table);
+EXPORT_SYMBOL_GPL(cpu_gdt_descr);
 
 EXPORT_SYMBOL(__down_failed);
 EXPORT_SYMBOL(__down_failed_interruptible);
diff --git a/arch/i386/kernel/io_apic.c b/arch/i386/kernel/io_apic.c
index 22c8675c79f4..7554f8fd874a 100644
--- a/arch/i386/kernel/io_apic.c
+++ b/arch/i386/kernel/io_apic.c
@@ -1722,8 +1722,8 @@ void disable_IO_APIC(void)
                 entry.dest_mode       = 0; /* Physical */
                 entry.delivery_mode   = dest_ExtINT; /* ExtInt */
                 entry.vector          = 0;
-                entry.dest.physical.physical_dest = 0;
-
+                entry.dest.physical.physical_dest =
+                                        GET_APIC_ID(apic_read(APIC_ID));
 
                 /*
                  * Add it to the IO-APIC irq-routing table:
diff --git a/arch/i386/kernel/mpparse.c b/arch/i386/kernel/mpparse.c
index 1ca5269b1e86..91a64016956e 100644
--- a/arch/i386/kernel/mpparse.c
+++ b/arch/i386/kernel/mpparse.c
@@ -38,6 +38,12 @@
 int smp_found_config;
 unsigned int __initdata maxcpus = NR_CPUS;
 
+#ifdef CONFIG_HOTPLUG_CPU
+#define CPU_HOTPLUG_ENABLED     (1)
+#else
+#define CPU_HOTPLUG_ENABLED     (0)
+#endif
+
 /*
  * Various Linux-internal data structures created from the
  * MP-table.
@@ -219,14 +225,18 @@ static void __devinit MP_processor_info (struct mpc_config_processor *m)
         cpu_set(num_processors, cpu_possible_map);
         num_processors++;
 
-        if ((num_processors > 8) &&
-            ((APIC_XAPIC(ver) &&
-             (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)) ||
-             (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)))
-                def_to_bigsmp = 1;
-        else
-                def_to_bigsmp = 0;
-
+        if (CPU_HOTPLUG_ENABLED || (num_processors > 8)) {
+                switch (boot_cpu_data.x86_vendor) {
+                case X86_VENDOR_INTEL:
+                        if (!APIC_XAPIC(ver)) {
+                                def_to_bigsmp = 0;
+                                break;
+                        }
+                        /* If P4 and above fall through */
+                case X86_VENDOR_AMD:
+                        def_to_bigsmp = 1;
+                }
+        }
         bios_cpu_apicid[num_processors - 1] = m->mpc_apicid;
 }
 
diff --git a/arch/i386/kernel/msr.c b/arch/i386/kernel/msr.c
index 44470fea4309..1d0a55e68760 100644
--- a/arch/i386/kernel/msr.c
+++ b/arch/i386/kernel/msr.c
@@ -172,7 +172,6 @@ static ssize_t msr_read(struct file *file, char __user * buf,
 {
         u32 __user *tmp = (u32 __user *) buf;
         u32 data[2];
-        size_t rv;
         u32 reg = *ppos;
         int cpu = iminor(file->f_dentry->d_inode);
         int err;
@@ -180,7 +179,7 @@ static ssize_t msr_read(struct file *file, char __user * buf,
         if (count % 8)
                 return -EINVAL; /* Invalid chunk size */
 
-        for (rv = 0; count; count -= 8) {
+        for (; count; count -= 8) {
                 err = do_rdmsr(cpu, reg, &data[0], &data[1]);
                 if (err)
                         return err;
diff --git a/arch/i386/kernel/process.c b/arch/i386/kernel/process.c
index 2333aead0563..45e7f0ac4b04 100644
--- a/arch/i386/kernel/process.c
+++ b/arch/i386/kernel/process.c
@@ -308,9 +308,7 @@ void show_regs(struct pt_regs * regs)
         cr0 = read_cr0();
         cr2 = read_cr2();
         cr3 = read_cr3();
-        if (current_cpu_data.x86 > 4) {
-                cr4 = read_cr4();
-        }
+        cr4 = read_cr4_safe();
         printk("CR0: %08lx CR2: %08lx CR3: %08lx CR4: %08lx\n", cr0, cr2, cr3, cr4);
         show_trace(NULL, &regs->esp);
 }
@@ -404,17 +402,7 @@ void flush_thread(void)
 
 void release_thread(struct task_struct *dead_task)
 {
-        if (dead_task->mm) {
-                // temporary debugging check
-                if (dead_task->mm->context.size) {
-                        printk("WARNING: dead process %8s still has LDT? <%p/%d>\n",
-                                        dead_task->comm,
-                                        dead_task->mm->context.ldt,
-                                        dead_task->mm->context.size);
-                        BUG();
-                }
-        }
-
+        BUG_ON(dead_task->mm);
         release_vm86_irqs(dead_task);
 }
 
diff --git a/arch/i386/kernel/ptrace.c b/arch/i386/kernel/ptrace.c
index 5ffbb4b7ad05..5c1fb6aada5b 100644
--- a/arch/i386/kernel/ptrace.c
+++ b/arch/i386/kernel/ptrace.c
@@ -32,9 +32,12 @@
  * in exit.c or in signal.c.
  */
 
-/* determines which flags the user has access to. */
-/* 1 = access 0 = no access */
-#define FLAG_MASK 0x00044dd5
+/*
+ * Determines which flags the user has access to [1 = access, 0 = no access].
+ * Prohibits changing ID(21), VIP(20), VIF(19), VM(17), IOPL(12-13), IF(9).
+ * Also masks reserved bits (31-22, 15, 5, 3, 1).
+ */
+#define FLAG_MASK 0x00054dd5
 
 /* set's the trap flag. */
 #define TRAP_FLAG 0x100
diff --git a/arch/i386/kernel/reboot.c b/arch/i386/kernel/reboot.c
index 2afe0f8d555a..2fa5803a759d 100644
--- a/arch/i386/kernel/reboot.c
+++ b/arch/i386/kernel/reboot.c
@@ -111,12 +111,12 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
                         DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge 2400"),
                 },
         },
-        {       /* Handle problems with rebooting on HP nc6120 */
+        {       /* Handle problems with rebooting on HP laptops */
                 .callback = set_bios_reboot,
-                .ident = "HP Compaq nc6120",
+                .ident = "HP Compaq Laptop",
                 .matches = {
                         DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
-                        DMI_MATCH(DMI_PRODUCT_NAME, "HP Compaq nc6120"),
+                        DMI_MATCH(DMI_PRODUCT_NAME, "HP Compaq"),
                 },
         },
         { }
diff --git a/arch/i386/kernel/setup.c b/arch/i386/kernel/setup.c
index fdfcb0cba9b4..27c956db0461 100644
--- a/arch/i386/kernel/setup.c
+++ b/arch/i386/kernel/setup.c
@@ -954,6 +954,12 @@ efi_find_max_pfn(unsigned long start, unsigned long end, void *arg)
         return 0;
 }
 
+static int __init
+efi_memory_present_wrapper(unsigned long start, unsigned long end, void *arg)
+{
+        memory_present(0, start, end);
+        return 0;
+}
 
 /*
  * Find the highest page frame number we have available
@@ -965,6 +971,7 @@ void __init find_max_pfn(void)
         max_pfn = 0;
         if (efi_enabled) {
                 efi_memmap_walk(efi_find_max_pfn, &max_pfn);
+                efi_memmap_walk(efi_memory_present_wrapper, NULL);
                 return;
         }
 
@@ -979,6 +986,7 @@ void __init find_max_pfn(void)
                         continue;
                 if (end > max_pfn)
                         max_pfn = end;
+                memory_present(0, start, end);
         }
 }
 
diff --git a/arch/i386/kernel/smpboot.c b/arch/i386/kernel/smpboot.c
index 9ed449af8e9f..b3c2e2c26743 100644
--- a/arch/i386/kernel/smpboot.c
+++ b/arch/i386/kernel/smpboot.c
@@ -903,6 +903,12 @@ 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 9b21a31d4f4e..f7ba4acc20ec 100644
--- a/arch/i386/kernel/syscall_table.S
+++ b/arch/i386/kernel/syscall_table.S
@@ -1,4 +1,3 @@
-.data
 ENTRY(sys_call_table)
         .long sys_restart_syscall       /* 0 - old "setup()" system call, used for restarting */
         .long sys_exit
diff --git a/arch/i386/kernel/timers/timer_tsc.c b/arch/i386/kernel/timers/timer_tsc.c
index d395e3b42485..47675bbbb316 100644
--- a/arch/i386/kernel/timers/timer_tsc.c
+++ b/arch/i386/kernel/timers/timer_tsc.c
@@ -330,7 +330,9 @@ int recalibrate_cpu_khz(void)
         unsigned int cpu_khz_old = cpu_khz;
 
         if (cpu_has_tsc) {
+                local_irq_disable();
                 init_cpu_khz();
+                local_irq_enable();
                 cpu_data[0].loops_per_jiffy =
                     cpufreq_scale(cpu_data[0].loops_per_jiffy,
                                   cpu_khz_old,
diff --git a/arch/i386/kernel/traps.c b/arch/i386/kernel/traps.c
index ab0e9430f775..53ad954e3ba4 100644
--- a/arch/i386/kernel/traps.c
+++ b/arch/i386/kernel/traps.c
@@ -306,14 +306,17 @@ void die(const char * str, struct pt_regs * regs, long err)
                 .lock_owner_depth =     0
         };
         static int die_counter;
+        unsigned long flags;
 
         if (die.lock_owner != raw_smp_processor_id()) {
                 console_verbose();
-                spin_lock_irq(&die.lock);
+                spin_lock_irqsave(&die.lock, flags);
                 die.lock_owner = smp_processor_id();
                 die.lock_owner_depth = 0;
                 bust_spinlocks(1);
         }
+        else
+                local_save_flags(flags);
 
         if (++die.lock_owner_depth < 3) {
                 int nl = 0;
@@ -340,7 +343,7 @@ void die(const char * str, struct pt_regs * regs, long err)
 
         bust_spinlocks(0);
         die.lock_owner = -1;
-        spin_unlock_irq(&die.lock);
+        spin_unlock_irqrestore(&die.lock, flags);
 
         if (kexec_should_crash(current))
                 crash_kexec(regs);
@@ -1075,9 +1078,9 @@ void __init trap_init(void)
         set_trap_gate(0,&divide_error);
         set_intr_gate(1,&debug);
         set_intr_gate(2,&nmi);
-        set_system_intr_gate(3, &int3); /* int3-5 can be called from all */
+        set_system_intr_gate(3, &int3); /* int3/4 can be called from all */
         set_system_gate(4,&overflow);
-        set_system_gate(5,&bounds);
+        set_trap_gate(5,&bounds);
         set_trap_gate(6,&invalid_op);
         set_trap_gate(7,&device_not_available);
         set_task_gate(8,GDT_ENTRY_DOUBLEFAULT_TSS);
@@ -1095,6 +1098,28 @@ void __init trap_init(void)
 #endif
         set_trap_gate(19,&simd_coprocessor_error);
 
+        if (cpu_has_fxsr) {
+                /*
+                 * Verify that the FXSAVE/FXRSTOR data will be 16-byte aligned.
+                 * Generates a compile-time "error: zero width for bit-field" if
+                 * the alignment is wrong.
+                 */
+                struct fxsrAlignAssert {
+                        int _:!(offsetof(struct task_struct,
+                                        thread.i387.fxsave) & 15);
+                };
+
+                printk(KERN_INFO "Enabling fast FPU save and restore... ");
+                set_in_cr4(X86_CR4_OSFXSR);
+                printk("done.\n");
+        }
+        if (cpu_has_xmm) {
+                printk(KERN_INFO "Enabling unmasked SIMD FPU exception "
+                                "support... ");
+                set_in_cr4(X86_CR4_OSXMMEXCPT);
+                printk("done.\n");
+        }
+
         set_system_gate(SYSCALL_VECTOR,&system_call);
 
         /*