19 files changed, 279 insertions, 257 deletions

diff --git a/arch/x86_64/kernel/Makefile b/arch/x86_64/kernel/Makefile
index 3c7cbff04d3d..ae399458024b 100644
--- a/arch/x86_64/kernel/Makefile
+++ b/arch/x86_64/kernel/Makefile
@@ -43,6 +43,7 @@ obj-$(CONFIG_PCI)		+= early-quirks.o
 
 obj-y                           += topology.o
 obj-y                           += intel_cacheinfo.o
+obj-y                           += pcspeaker.o
 
 CFLAGS_vsyscall.o               := $(PROFILING) -g0
 
@@ -56,3 +57,4 @@ quirks-y			+= ../../i386/kernel/quirks.o
 i8237-y                         += ../../i386/kernel/i8237.o
 msr-$(subst m,y,$(CONFIG_X86_MSR))  += ../../i386/kernel/msr.o
 alternative-y                   += ../../i386/kernel/alternative.o
+pcspeaker-y                     += ../../i386/kernel/pcspeaker.o
diff --git a/arch/x86_64/kernel/acpi/sleep.c b/arch/x86_64/kernel/acpi/sleep.c
index 5ebf62c7a3d2..23178ce6c783 100644
--- a/arch/x86_64/kernel/acpi/sleep.c
+++ b/arch/x86_64/kernel/acpi/sleep.c
@@ -58,7 +58,7 @@ unsigned long acpi_wakeup_address = 0;
 unsigned long acpi_video_flags;
 extern char wakeup_start, wakeup_end;
 
-extern unsigned long FASTCALL(acpi_copy_wakeup_routine(unsigned long));
+extern unsigned long acpi_copy_wakeup_routine(unsigned long);
 
 static pgd_t low_ptr;
 
diff --git a/arch/x86_64/kernel/e820.c b/arch/x86_64/kernel/e820.c
index 6fe191c58084..4651fd22b213 100644
--- a/arch/x86_64/kernel/e820.c
+++ b/arch/x86_64/kernel/e820.c
@@ -83,6 +83,13 @@ static inline int bad_addr(unsigned long *addrp, unsigned long size)
                 return 1;
         }
 
+#ifdef CONFIG_NUMA
+        /* NUMA memory to node map */
+        if (last >= nodemap_addr && addr < nodemap_addr + nodemap_size) {
+                *addrp = nodemap_addr + nodemap_size;
+                return 1;
+        }
+#endif
         /* XXX ramdisk image here? */ 
         return 0;
 } 
@@ -184,6 +191,37 @@ unsigned long __init e820_end_of_ram(void)
 }
 
 /*
+ * Find the hole size in the range.
+ */
+unsigned long __init e820_hole_size(unsigned long start, unsigned long end)
+{
+        unsigned long ram = 0;
+        int i;
+
+        for (i = 0; i < e820.nr_map; i++) {
+                struct e820entry *ei = &e820.map[i];
+                unsigned long last, addr;
+
+                if (ei->type != E820_RAM ||
+                    ei->addr+ei->size <= start ||
+                    ei->addr >= end)
+                        continue;
+
+                addr = round_up(ei->addr, PAGE_SIZE);
+                if (addr < start)
+                        addr = start;
+
+                last = round_down(ei->addr + ei->size, PAGE_SIZE);
+                if (last >= end)
+                        last = end;
+
+                if (last > addr)
+                        ram += last - addr;
+        }
+        return ((end - start) - ram);
+}
+
+/*
  * Mark e820 reserved areas as busy for the resource manager.
  */
 void __init e820_reserve_resources(void)
diff --git a/arch/x86_64/kernel/head.S b/arch/x86_64/kernel/head.S
index 1e6f80870679..598a4d0351fc 100644
--- a/arch/x86_64/kernel/head.S
+++ b/arch/x86_64/kernel/head.S
@@ -163,6 +163,20 @@ startup_64:
          */
         lgdt    cpu_gdt_descr
 
+        /* set up data segments. actually 0 would do too */
+        movl $__KERNEL_DS,%eax
+        movl %eax,%ds
+        movl %eax,%ss
+        movl %eax,%es
+
+        /*
+         * We don't really need to load %fs or %gs, but load them anyway
+         * to kill any stale realmode selectors.  This allows execution
+         * under VT hardware.
+         */
+        movl %eax,%fs
+        movl %eax,%gs
+
         /* 
          * Setup up a dummy PDA. this is just for some early bootup code
          * that does in_interrupt() 
@@ -173,12 +187,6 @@ startup_64:
         shrq    $32,%rdx
         wrmsr   
 
-        /* set up data segments. actually 0 would do too */
-        movl $__KERNEL_DS,%eax
-        movl %eax,%ds   
-        movl %eax,%ss
-        movl %eax,%es
-                        
         /* esi is pointer to real mode structure with interesting info.
            pass it to C */
         movl    %esi, %edi
diff --git a/arch/x86_64/kernel/io_apic.c b/arch/x86_64/kernel/io_apic.c
index 6be6730acb5c..566e64d966c4 100644
--- a/arch/x86_64/kernel/io_apic.c
+++ b/arch/x86_64/kernel/io_apic.c
@@ -831,7 +831,7 @@ static void __init setup_IO_APIC_irq(int apic, int pin, int idx, int irq)
         entry.delivery_mode = INT_DELIVERY_MODE;
         entry.dest_mode = INT_DEST_MODE;
         entry.mask = 0;                         /* enable IRQ */
-        entry.dest.logical.logical_dest = cpu_mask_to_apicid(TARGET_CPUS);
+        entry.dest = cpu_mask_to_apicid(TARGET_CPUS);
 
         entry.trigger = irq_trigger(idx);
         entry.polarity = irq_polarity(idx);
@@ -839,7 +839,7 @@ static void __init setup_IO_APIC_irq(int apic, int pin, int idx, int irq)
         if (irq_trigger(idx)) {
                 entry.trigger = 1;
                 entry.mask = 1;
-                entry.dest.logical.logical_dest = cpu_mask_to_apicid(TARGET_CPUS);
+                entry.dest = cpu_mask_to_apicid(TARGET_CPUS);
         }
 
         if (!apic && !IO_APIC_IRQ(irq))
@@ -851,7 +851,7 @@ static void __init setup_IO_APIC_irq(int apic, int pin, int idx, int irq)
                 if (vector < 0)
                         return;
 
-                entry.dest.logical.logical_dest = cpu_mask_to_apicid(mask);
+                entry.dest = cpu_mask_to_apicid(mask);
                 entry.vector = vector;
 
                 ioapic_register_intr(irq, vector, IOAPIC_AUTO);
@@ -920,7 +920,7 @@ static void __init setup_ExtINT_IRQ0_pin(unsigned int apic, unsigned int pin, in
          */
         entry.dest_mode = INT_DEST_MODE;
         entry.mask = 0;                                 /* unmask IRQ now */
-        entry.dest.logical.logical_dest = cpu_mask_to_apicid(TARGET_CPUS);
+        entry.dest = cpu_mask_to_apicid(TARGET_CPUS);
         entry.delivery_mode = INT_DELIVERY_MODE;
         entry.polarity = 0;
         entry.trigger = 0;
@@ -1020,18 +1020,17 @@ void __apicdebuginit print_IO_APIC(void)
 
         printk(KERN_DEBUG ".... IRQ redirection table:\n");
 
-        printk(KERN_DEBUG " NR Log Phy Mask Trig IRR Pol"
-                          " Stat Dest Deli Vect:   \n");
+        printk(KERN_DEBUG " NR Dst Mask Trig IRR Pol"
+                          " Stat Dmod Deli Vect:   \n");
 
         for (i = 0; i <= reg_01.bits.entries; i++) {
                 struct IO_APIC_route_entry entry;
 
                 entry = ioapic_read_entry(apic, i);
 
-                printk(KERN_DEBUG " %02x %03X %02X  ",
+                printk(KERN_DEBUG " %02x %03X ",
                         i,
-                        entry.dest.logical.logical_dest,
-                        entry.dest.physical.physical_dest
+                        entry.dest
                 );
 
                 printk("%1d    %1d    %1d   %1d   %1d    %1d    %1d    %02X\n",
@@ -1293,8 +1292,7 @@ void disable_IO_APIC(void)
                 entry.dest_mode       = 0; /* Physical */
                 entry.delivery_mode   = dest_ExtINT; /* ExtInt */
                 entry.vector          = 0;
-                entry.dest.physical.physical_dest =
-                                        GET_APIC_ID(apic_read(APIC_ID));
+                entry.dest          = GET_APIC_ID(apic_read(APIC_ID));
 
                 /*
                  * Add it to the IO-APIC irq-routing table:
@@ -1556,7 +1554,7 @@ static inline void unlock_ExtINT_logic(void)
 
         entry1.dest_mode = 0;                   /* physical delivery */
         entry1.mask = 0;                        /* unmask IRQ now */
-        entry1.dest.physical.physical_dest = hard_smp_processor_id();
+        entry1.dest = hard_smp_processor_id();
         entry1.delivery_mode = dest_ExtINT;
         entry1.polarity = entry0.polarity;
         entry1.trigger = 0;
@@ -2131,7 +2129,7 @@ int io_apic_set_pci_routing (int ioapic, int pin, int irq, int triggering, int p
 
         entry.delivery_mode = INT_DELIVERY_MODE;
         entry.dest_mode = INT_DEST_MODE;
-        entry.dest.logical.logical_dest = cpu_mask_to_apicid(mask);
+        entry.dest = cpu_mask_to_apicid(mask);
         entry.trigger = triggering;
         entry.polarity = polarity;
         entry.mask = 1;                                  /* Disabled (masked) */
diff --git a/arch/x86_64/kernel/ioport.c b/arch/x86_64/kernel/ioport.c
index fe063d3cfe42..745b1f0f494e 100644
--- a/arch/x86_64/kernel/ioport.c
+++ b/arch/x86_64/kernel/ioport.c
@@ -114,6 +114,6 @@ asmlinkage long sys_iopl(unsigned int level, struct pt_regs *regs)
                 if (!capable(CAP_SYS_RAWIO))
                         return -EPERM;
         }
-        regs->eflags = (regs->eflags &~ 0x3000UL) | (level << 12);
+        regs->eflags = (regs->eflags &~ X86_EFLAGS_IOPL) | (level << 12);
         return 0;
 }
diff --git a/arch/x86_64/kernel/irq.c b/arch/x86_64/kernel/irq.c
index 0c06af6c13bc..3bc30d2c13d3 100644
--- a/arch/x86_64/kernel/irq.c
+++ b/arch/x86_64/kernel/irq.c
@@ -18,6 +18,7 @@
 #include <asm/uaccess.h>
 #include <asm/io_apic.h>
 #include <asm/idle.h>
+#include <asm/smp.h>
 
 atomic_t irq_err_count;
 
@@ -120,9 +121,14 @@ asmlinkage unsigned int do_IRQ(struct pt_regs *regs)
 
         if (likely(irq < NR_IRQS))
                 generic_handle_irq(irq);
-        else if (printk_ratelimit())
-                printk(KERN_EMERG "%s: %d.%d No irq handler for vector\n",
-                        __func__, smp_processor_id(), vector);
+        else {
+                if (!disable_apic)
+                        ack_APIC_irq();
+
+                if (printk_ratelimit())
+                        printk(KERN_EMERG "%s: %d.%d No irq handler for vector\n",
+                                __func__, smp_processor_id(), vector);
+        }
 
         irq_exit();
 
diff --git a/arch/x86_64/kernel/mce.c b/arch/x86_64/kernel/mce.c
index bdb54a2c9f18..8011a8e1c7d4 100644
--- a/arch/x86_64/kernel/mce.c
+++ b/arch/x86_64/kernel/mce.c
@@ -19,6 +19,7 @@
 #include <linux/cpu.h>
 #include <linux/percpu.h>
 #include <linux/ctype.h>
+#include <linux/kmod.h>
 #include <asm/processor.h> 
 #include <asm/msr.h>
 #include <asm/mce.h>
@@ -42,6 +43,10 @@ static unsigned long console_logged;
 static int notify_user;
 static int rip_msr;
 static int mce_bootlog = 1;
+static atomic_t mce_events;
+
+static char trigger[128];
+static char *trigger_argv[2] = { trigger, NULL };
 
 /*
  * Lockless MCE logging infrastructure.
@@ -57,6 +62,7 @@ struct mce_log mcelog = {
 void mce_log(struct mce *mce)
 {
         unsigned next, entry;
+        atomic_inc(&mce_events);
         mce->finished = 0;
         wmb();
         for (;;) {
@@ -161,6 +167,17 @@ static inline void mce_get_rip(struct mce *m, struct pt_regs *regs)
         }
 }
 
+static void do_mce_trigger(void)
+{
+        static atomic_t mce_logged;
+        int events = atomic_read(&mce_events);
+        if (events != atomic_read(&mce_logged) && trigger[0]) {
+                /* Small race window, but should be harmless.  */
+                atomic_set(&mce_logged, events);
+                call_usermodehelper(trigger, trigger_argv, NULL, -1);
+        }
+}
+
 /* 
  * The actual machine check handler
  */
@@ -234,8 +251,12 @@ void do_machine_check(struct pt_regs * regs, long error_code)
         }
 
         /* Never do anything final in the polling timer */
-        if (!regs)
+        if (!regs) {
+                /* Normal interrupt context here. Call trigger for any new
+                   events. */
+                do_mce_trigger();
                 goto out;
+        }
 
         /* If we didn't find an uncorrectable error, pick
            the last one (shouldn't happen, just being safe). */
@@ -606,17 +627,42 @@ DEFINE_PER_CPU(struct sys_device, device_mce);
         }                                                                          \
         static SYSDEV_ATTR(name, 0644, show_ ## name, set_ ## name);
 
+/* TBD should generate these dynamically based on number of available banks */
 ACCESSOR(bank0ctl,bank[0],mce_restart())
 ACCESSOR(bank1ctl,bank[1],mce_restart())
 ACCESSOR(bank2ctl,bank[2],mce_restart())
 ACCESSOR(bank3ctl,bank[3],mce_restart())
 ACCESSOR(bank4ctl,bank[4],mce_restart())
 ACCESSOR(bank5ctl,bank[5],mce_restart())
-static struct sysdev_attribute * bank_attributes[NR_BANKS] = {
-        &attr_bank0ctl, &attr_bank1ctl, &attr_bank2ctl,
-        &attr_bank3ctl, &attr_bank4ctl, &attr_bank5ctl};
+
+static ssize_t show_trigger(struct sys_device *s, char *buf)
+{
+        strcpy(buf, trigger);
+        strcat(buf, "\n");
+        return strlen(trigger) + 1;
+}
+
+static ssize_t set_trigger(struct sys_device *s,const char *buf,size_t siz)
+{
+        char *p;
+        int len;
+        strncpy(trigger, buf, sizeof(trigger));
+        trigger[sizeof(trigger)-1] = 0;
+        len = strlen(trigger);
+        p = strchr(trigger, '\n');
+        if (*p) *p = 0;
+        return len;
+}
+
+static SYSDEV_ATTR(trigger, 0644, show_trigger, set_trigger);
 ACCESSOR(tolerant,tolerant,)
 ACCESSOR(check_interval,check_interval,mce_restart())
+static struct sysdev_attribute *mce_attributes[] = {
+        &attr_bank0ctl, &attr_bank1ctl, &attr_bank2ctl,
+        &attr_bank3ctl, &attr_bank4ctl, &attr_bank5ctl,
+        &attr_tolerant, &attr_check_interval, &attr_trigger,
+        NULL
+};
 
 /* Per cpu sysdev init.  All of the cpus still share the same ctl bank */
 static __cpuinit int mce_create_device(unsigned int cpu)
@@ -632,11 +678,9 @@ static __cpuinit int mce_create_device(unsigned int cpu)
         err = sysdev_register(&per_cpu(device_mce,cpu));
 
         if (!err) {
-                for (i = 0; i < banks; i++)
+                for (i = 0; mce_attributes[i]; i++)
                         sysdev_create_file(&per_cpu(device_mce,cpu),
-                                bank_attributes[i]);
-                sysdev_create_file(&per_cpu(device_mce,cpu), &attr_tolerant);
-                sysdev_create_file(&per_cpu(device_mce,cpu), &attr_check_interval);
+                                mce_attributes[i]);
         }
         return err;
 }
@@ -645,11 +689,9 @@ static void mce_remove_device(unsigned int cpu)
 {
         int i;
 
-        for (i = 0; i < banks; i++)
+        for (i = 0; mce_attributes[i]; i++)
                 sysdev_remove_file(&per_cpu(device_mce,cpu),
-                        bank_attributes[i]);
-        sysdev_remove_file(&per_cpu(device_mce,cpu), &attr_tolerant);
-        sysdev_remove_file(&per_cpu(device_mce,cpu), &attr_check_interval);
+                        mce_attributes[i]);
         sysdev_unregister(&per_cpu(device_mce,cpu));
         memset(&per_cpu(device_mce, cpu).kobj, 0, sizeof(struct kobject));
 }
diff --git a/arch/x86_64/kernel/mce_amd.c b/arch/x86_64/kernel/mce_amd.c
index 93c707257637..d0bd5d66e103 100644
--- a/arch/x86_64/kernel/mce_amd.c
+++ b/arch/x86_64/kernel/mce_amd.c
@@ -37,6 +37,8 @@
 #define THRESHOLD_MAX     0xFFF
 #define INT_TYPE_APIC     0x00020000
 #define MASK_VALID_HI     0x80000000
+#define MASK_CNTP_HI      0x40000000
+#define MASK_LOCKED_HI    0x20000000
 #define MASK_LVTOFF_HI    0x00F00000
 #define MASK_COUNT_EN_HI  0x00080000
 #define MASK_INT_TYPE_HI  0x00060000
@@ -122,14 +124,17 @@ void __cpuinit mce_amd_feature_init(struct cpuinfo_x86 *c)
                 for (block = 0; block < NR_BLOCKS; ++block) {
                         if (block == 0)
                                 address = MSR_IA32_MC0_MISC + bank * 4;
-                        else if (block == 1)
-                                address = MCG_XBLK_ADDR
-                                        + ((low & MASK_BLKPTR_LO) >> 21);
+                        else if (block == 1) {
+                                address = (low & MASK_BLKPTR_LO) >> 21;
+                                if (!address)
+                                        break;
+                                address += MCG_XBLK_ADDR;
+                        }
                         else
                                 ++address;
 
                         if (rdmsr_safe(address, &low, &high))
-                                continue;
+                                break;
 
                         if (!(high & MASK_VALID_HI)) {
                                 if (block)
@@ -138,8 +143,8 @@ void __cpuinit mce_amd_feature_init(struct cpuinfo_x86 *c)
                                         break;
                         }
 
-                        if (!(high & MASK_VALID_HI >> 1)  ||
-                             (high & MASK_VALID_HI >> 2))
+                        if (!(high & MASK_CNTP_HI)  ||
+                             (high & MASK_LOCKED_HI))
                                 continue;
 
                         if (!block)
@@ -187,17 +192,22 @@ asmlinkage void mce_threshold_interrupt(void)
 
         /* assume first bank caused it */
         for (bank = 0; bank < NR_BANKS; ++bank) {
+                if (!(per_cpu(bank_map, m.cpu) & (1 << bank)))
+                        continue;
                 for (block = 0; block < NR_BLOCKS; ++block) {
                         if (block == 0)
                                 address = MSR_IA32_MC0_MISC + bank * 4;
-                        else if (block == 1)
-                                address = MCG_XBLK_ADDR
-                                        + ((low & MASK_BLKPTR_LO) >> 21);
+                        else if (block == 1) {
+                                address = (low & MASK_BLKPTR_LO) >> 21;
+                                if (!address)
+                                        break;
+                                address += MCG_XBLK_ADDR;
+                        }
                         else
                                 ++address;
 
                         if (rdmsr_safe(address, &low, &high))
-                                continue;
+                                break;
 
                         if (!(high & MASK_VALID_HI)) {
                                 if (block)
@@ -206,10 +216,14 @@ asmlinkage void mce_threshold_interrupt(void)
                                         break;
                         }
 
-                        if (!(high & MASK_VALID_HI >> 1)  ||
-                             (high & MASK_VALID_HI >> 2))
+                        if (!(high & MASK_CNTP_HI)  ||
+                             (high & MASK_LOCKED_HI))
                                 continue;
 
+                        /* Log the machine check that caused the threshold
+                           event. */
+                        do_machine_check(NULL, 0);
+
                         if (high & MASK_OVERFLOW_HI) {
                                 rdmsrl(address, m.misc);
                                 rdmsrl(MSR_IA32_MC0_STATUS + bank * 4,
@@ -385,7 +399,7 @@ static __cpuinit int allocate_threshold_blocks(unsigned int cpu,
                 return 0;
 
         if (rdmsr_safe(address, &low, &high))
-                goto recurse;
+                return 0;
 
         if (!(high & MASK_VALID_HI)) {
                 if (block)
@@ -394,8 +408,8 @@ static __cpuinit int allocate_threshold_blocks(unsigned int cpu,
                         return 0;
         }
 
-        if (!(high & MASK_VALID_HI >> 1)  ||
-             (high & MASK_VALID_HI >> 2))
+        if (!(high & MASK_CNTP_HI)  ||
+             (high & MASK_LOCKED_HI))
                 goto recurse;
 
         b = kzalloc(sizeof(struct threshold_block), GFP_KERNEL);
diff --git a/arch/x86_64/kernel/nmi.c b/arch/x86_64/kernel/nmi.c
index 9cb42ecb7f89..486f4c61a948 100644
--- a/arch/x86_64/kernel/nmi.c
+++ b/arch/x86_64/kernel/nmi.c
@@ -172,7 +172,7 @@ static __cpuinit inline int nmi_known_cpu(void)
 {
         switch (boot_cpu_data.x86_vendor) {
         case X86_VENDOR_AMD:
-                return boot_cpu_data.x86 == 15;
+                return boot_cpu_data.x86 == 15 || boot_cpu_data.x86 == 16;
         case X86_VENDOR_INTEL:
                 if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON))
                         return 1;
@@ -214,6 +214,23 @@ static __init void nmi_cpu_busy(void *data)
 }
 #endif
 
+static unsigned int adjust_for_32bit_ctr(unsigned int hz)
+{
+        unsigned int retval = hz;
+
+        /*
+         * On Intel CPUs with ARCH_PERFMON only 32 bits in the counter
+         * are writable, with higher bits sign extending from bit 31.
+         * So, we can only program the counter with 31 bit values and
+         * 32nd bit should be 1, for 33.. to be 1.
+         * Find the appropriate nmi_hz
+         */
+        if ((((u64)cpu_khz * 1000) / retval) > 0x7fffffffULL) {
+                retval = ((u64)cpu_khz * 1000) / 0x7fffffffUL + 1;
+        }
+        return retval;
+}
+
 int __init check_nmi_watchdog (void)
 {
         int *counts;
@@ -268,17 +285,8 @@ int __init check_nmi_watchdog (void)
                 struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
 
                 nmi_hz = 1;
-                /*
-                 * On Intel CPUs with ARCH_PERFMON only 32 bits in the counter
-                 * are writable, with higher bits sign extending from bit 31.
-                 * So, we can only program the counter with 31 bit values and
-                 * 32nd bit should be 1, for 33.. to be 1.
-                 * Find the appropriate nmi_hz
-                 */
-                if (wd->perfctr_msr == MSR_ARCH_PERFMON_PERFCTR0 &&
-                        ((u64)cpu_khz * 1000) > 0x7fffffffULL) {
-                        nmi_hz = ((u64)cpu_khz * 1000) / 0x7fffffffUL + 1;
-                }
+                if (wd->perfctr_msr == MSR_ARCH_PERFMON_PERFCTR0)
+                        nmi_hz = adjust_for_32bit_ctr(nmi_hz);
         }
 
         kfree(counts);
@@ -360,6 +368,33 @@ void enable_timer_nmi_watchdog(void)
         }
 }
 
+static void __acpi_nmi_disable(void *__unused)
+{
+        apic_write(APIC_LVT0, APIC_DM_NMI | APIC_LVT_MASKED);
+}
+
+/*
+ * Disable timer based NMIs on all CPUs:
+ */
+void acpi_nmi_disable(void)
+{
+        if (atomic_read(&nmi_active) && nmi_watchdog == NMI_IO_APIC)
+                on_each_cpu(__acpi_nmi_disable, NULL, 0, 1);
+}
+
+static void __acpi_nmi_enable(void *__unused)
+{
+        apic_write(APIC_LVT0, APIC_DM_NMI);
+}
+
+/*
+ * Enable timer based NMIs on all CPUs:
+ */
+void acpi_nmi_enable(void)
+{
+        if (atomic_read(&nmi_active) && nmi_watchdog == NMI_IO_APIC)
+                on_each_cpu(__acpi_nmi_enable, NULL, 0, 1);
+}
 #ifdef CONFIG_PM
 
 static int nmi_pm_active; /* nmi_active before suspend */
@@ -634,7 +669,9 @@ static int setup_intel_arch_watchdog(void)
 
         /* setup the timer */
         wrmsr(evntsel_msr, evntsel, 0);
-        wrmsrl(perfctr_msr, -((u64)cpu_khz * 1000 / nmi_hz));
+
+        nmi_hz = adjust_for_32bit_ctr(nmi_hz);
+        wrmsr(perfctr_msr, (u32)(-((u64)cpu_khz * 1000 / nmi_hz)), 0);
 
         apic_write(APIC_LVTPC, APIC_DM_NMI);
         evntsel |= ARCH_PERFMON_EVENTSEL0_ENABLE;
@@ -855,15 +892,23 @@ int __kprobes nmi_watchdog_tick(struct pt_regs * regs, unsigned reason)
                                 dummy &= ~P4_CCCR_OVF;
                                 wrmsrl(wd->cccr_msr, dummy);
                                 apic_write(APIC_LVTPC, APIC_DM_NMI);
+                                /* start the cycle over again */
+                                wrmsrl(wd->perfctr_msr,
+                                       -((u64)cpu_khz * 1000 / nmi_hz));
                         } else if (wd->perfctr_msr == MSR_ARCH_PERFMON_PERFCTR0) {
                                 /*
                                  * ArchPerfom/Core Duo needs to re-unmask
                                  * the apic vector
                                  */
                                 apic_write(APIC_LVTPC, APIC_DM_NMI);
+                                /* ARCH_PERFMON has 32 bit counter writes */
+                                wrmsr(wd->perfctr_msr,
+                                     (u32)(-((u64)cpu_khz * 1000 / nmi_hz)), 0);
+                        } else {
+                                /* start the cycle over again */
+                                wrmsrl(wd->perfctr_msr,
+                                       -((u64)cpu_khz * 1000 / nmi_hz));
                         }
-                        /* start the cycle over again */
-                        wrmsrl(wd->perfctr_msr, -((u64)cpu_khz * 1000 / nmi_hz));
                         rc = 1;
                 } else  if (nmi_watchdog == NMI_IO_APIC) {
                         /* don't know how to accurately check for this.
diff --git a/arch/x86_64/kernel/pci-calgary.c b/arch/x86_64/kernel/pci-calgary.c
index 3d65b1d4c2b3..04480c3b68f5 100644
--- a/arch/x86_64/kernel/pci-calgary.c
+++ b/arch/x86_64/kernel/pci-calgary.c
@@ -138,6 +138,8 @@ static const unsigned long phb_debug_offsets[] = {
 
 #define PHB_DEBUG_STUFF_OFFSET  0x0020
 
+#define EMERGENCY_PAGES 32 /* = 128KB */
+
 unsigned int specified_table_size = TCE_TABLE_SIZE_UNSPECIFIED;
 static int translate_empty_slots __read_mostly = 0;
 static int calgary_detected __read_mostly = 0;
@@ -296,6 +298,16 @@ static void __iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr,
 {
         unsigned long entry;
         unsigned long badbit;
+        unsigned long badend;
+
+        /* were we called with bad_dma_address? */
+        badend = bad_dma_address + (EMERGENCY_PAGES * PAGE_SIZE);
+        if (unlikely((dma_addr >= bad_dma_address) && (dma_addr < badend))) {
+                printk(KERN_ERR "Calgary: driver tried unmapping bad DMA "
+                       "address 0x%Lx\n", dma_addr);
+                WARN_ON(1);
+                return;
+        }
 
         entry = dma_addr >> PAGE_SHIFT;
 
@@ -656,8 +668,8 @@ static void __init calgary_reserve_regions(struct pci_dev *dev)
         u64 start;
         struct iommu_table *tbl = dev->sysdata;
 
-        /* reserve bad_dma_address in case it's a legal address */
-        iommu_range_reserve(tbl, bad_dma_address, 1);
+        /* reserve EMERGENCY_PAGES from bad_dma_address and up */
+        iommu_range_reserve(tbl, bad_dma_address, EMERGENCY_PAGES);
 
         /* avoid the BIOS/VGA first 640KB-1MB region */
         start = (640 * 1024);
@@ -1176,6 +1188,7 @@ int __init calgary_iommu_init(void)
         }
 
         force_iommu = 1;
+        bad_dma_address = 0x0;
         dma_ops = &calgary_dma_ops;
 
         return 0;
diff --git a/arch/x86_64/kernel/pci-dma.c b/arch/x86_64/kernel/pci-dma.c
index 683b7a5c1ab3..651ccfb06697 100644
--- a/arch/x86_64/kernel/pci-dma.c
+++ b/arch/x86_64/kernel/pci-dma.c
@@ -223,30 +223,10 @@ int dma_set_mask(struct device *dev, u64 mask)
 }
 EXPORT_SYMBOL(dma_set_mask);
 
-/* iommu=[size][,noagp][,off][,force][,noforce][,leak][,memaper[=order]][,merge]
-         [,forcesac][,fullflush][,nomerge][,biomerge]
-   size  set size of iommu (in bytes)
-   noagp don't initialize the AGP driver and use full aperture.
-   off   don't use the IOMMU
-   leak  turn on simple iommu leak tracing (only when CONFIG_IOMMU_LEAK is on)
-   memaper[=order] allocate an own aperture over RAM with size 32MB^order.
-   noforce don't force IOMMU usage. Default.
-   force  Force IOMMU.
-   merge  Do lazy merging. This may improve performance on some block devices.
-          Implies force (experimental)
-   biomerge Do merging at the BIO layer. This is more efficient than merge,
-            but should be only done with very big IOMMUs. Implies merge,force.
-   nomerge Don't do SG merging.
-   forcesac For SAC mode for masks <40bits  (experimental)
-   fullflush Flush IOMMU on each allocation (default)
-   nofullflush Don't use IOMMU fullflush
-   allowed  overwrite iommu off workarounds for specific chipsets.
-   soft  Use software bounce buffering (default for Intel machines)
-   noaperture Don't touch the aperture for AGP.
-   allowdac Allow DMA >4GB
-   nodac    Forbid DMA >4GB
-   panic    Force panic when IOMMU overflows
-*/
+/*
+ * See <Documentation/x86_64/boot-options.txt> for the iommu kernel parameter
+ * documentation.
+ */
 __init int iommu_setup(char *p)
 {
         iommu_merge = 1;
diff --git a/arch/x86_64/kernel/pci-gart.c b/arch/x86_64/kernel/pci-gart.c
index fc1960f1f243..030eb3753358 100644
--- a/arch/x86_64/kernel/pci-gart.c
+++ b/arch/x86_64/kernel/pci-gart.c
@@ -185,7 +185,7 @@ static void iommu_full(struct device *dev, size_t size, int dir)
 static inline int need_iommu(struct device *dev, unsigned long addr, size_t size)
 { 
         u64 mask = *dev->dma_mask;
-        int high = addr + size >= mask;
+        int high = addr + size > mask;
         int mmu = high;
         if (force_iommu) 
                 mmu = 1; 
@@ -195,7 +195,7 @@ static inline int need_iommu(struct device *dev, unsigned long addr, size_t size
 static inline int nonforced_iommu(struct device *dev, unsigned long addr, size_t size)
 { 
         u64 mask = *dev->dma_mask;
-        int high = addr + size >= mask;
+        int high = addr + size > mask;
         int mmu = high;
         return mmu; 
 }
diff --git a/arch/x86_64/kernel/ptrace.c b/arch/x86_64/kernel/ptrace.c
index addc14af0c56..4326a690a509 100644
--- a/arch/x86_64/kernel/ptrace.c
+++ b/arch/x86_64/kernel/ptrace.c
@@ -536,8 +536,12 @@ long arch_ptrace(struct task_struct *child, long request, long addr, long data)
                 }
                 ret = 0;
                 for (ui = 0; ui < sizeof(struct user_regs_struct); ui += sizeof(long)) {
-                        ret |= __get_user(tmp, (unsigned long __user *) data);
-                        putreg(child, ui, tmp);
+                        ret = __get_user(tmp, (unsigned long __user *) data);
+                        if (ret)
+                                break;
+                        ret = putreg(child, ui, tmp);
+                        if (ret)
+                                break;
                         data += sizeof(long);
                 }
                 break;
diff --git a/arch/x86_64/kernel/setup.c b/arch/x86_64/kernel/setup.c
index 60477244d1a3..3d98b696881d 100644
--- a/arch/x86_64/kernel/setup.c
+++ b/arch/x86_64/kernel/setup.c
@@ -138,128 +138,6 @@ struct resource code_resource = {
         .flags = IORESOURCE_RAM,
 };
 
-#define IORESOURCE_ROM (IORESOURCE_BUSY | IORESOURCE_READONLY | IORESOURCE_MEM)
-
-static struct resource system_rom_resource = {
-        .name = "System ROM",
-        .start = 0xf0000,
-        .end = 0xfffff,
-        .flags = IORESOURCE_ROM,
-};
-
-static struct resource extension_rom_resource = {
-        .name = "Extension ROM",
-        .start = 0xe0000,
-        .end = 0xeffff,
-        .flags = IORESOURCE_ROM,
-};
-
-static struct resource adapter_rom_resources[] = {
-        { .name = "Adapter ROM", .start = 0xc8000, .end = 0,
-                .flags = IORESOURCE_ROM },
-        { .name = "Adapter ROM", .start = 0, .end = 0,
-                .flags = IORESOURCE_ROM },
-        { .name = "Adapter ROM", .start = 0, .end = 0,
-                .flags = IORESOURCE_ROM },
-        { .name = "Adapter ROM", .start = 0, .end = 0,
-                .flags = IORESOURCE_ROM },
-        { .name = "Adapter ROM", .start = 0, .end = 0,
-                .flags = IORESOURCE_ROM },
-        { .name = "Adapter ROM", .start = 0, .end = 0,
-                .flags = IORESOURCE_ROM }
-};
-
-static struct resource video_rom_resource = {
-        .name = "Video ROM",
-        .start = 0xc0000,
-        .end = 0xc7fff,
-        .flags = IORESOURCE_ROM,
-};
-
-static struct resource video_ram_resource = {
-        .name = "Video RAM area",
-        .start = 0xa0000,
-        .end = 0xbffff,
-        .flags = IORESOURCE_RAM,
-};
-
-#define romsignature(x) (*(unsigned short *)(x) == 0xaa55)
-
-static int __init romchecksum(unsigned char *rom, unsigned long length)
-{
-        unsigned char *p, sum = 0;
-
-        for (p = rom; p < rom + length; p++)
-                sum += *p;
-        return sum == 0;
-}
-
-static void __init probe_roms(void)
-{
-        unsigned long start, length, upper;
-        unsigned char *rom;
-        int           i;
-
-        /* video rom */
-        upper = adapter_rom_resources[0].start;
-        for (start = video_rom_resource.start; start < upper; start += 2048) {
-                rom = isa_bus_to_virt(start);
-                if (!romsignature(rom))
-                        continue;
-
-                video_rom_resource.start = start;
-
-                /* 0 < length <= 0x7f * 512, historically */
-                length = rom[2] * 512;
-
-                /* if checksum okay, trust length byte */
-                if (length && romchecksum(rom, length))
-                        video_rom_resource.end = start + length - 1;
-
-                request_resource(&iomem_resource, &video_rom_resource);
-                break;
-                        }
-
-        start = (video_rom_resource.end + 1 + 2047) & ~2047UL;
-        if (start < upper)
-                start = upper;
-
-        /* system rom */
-        request_resource(&iomem_resource, &system_rom_resource);
-        upper = system_rom_resource.start;
-
-        /* check for extension rom (ignore length byte!) */
-        rom = isa_bus_to_virt(extension_rom_resource.start);
-        if (romsignature(rom)) {
-                length = extension_rom_resource.end - extension_rom_resource.start + 1;
-                if (romchecksum(rom, length)) {
-                        request_resource(&iomem_resource, &extension_rom_resource);
-                        upper = extension_rom_resource.start;
-                }
-        }
-
-        /* check for adapter roms on 2k boundaries */
-        for (i = 0; i < ARRAY_SIZE(adapter_rom_resources) && start < upper;
-             start += 2048) {
-                rom = isa_bus_to_virt(start);
-                if (!romsignature(rom))
-                        continue;
-
-                /* 0 < length <= 0x7f * 512, historically */
-                length = rom[2] * 512;
-
-                /* but accept any length that fits if checksum okay */
-                if (!length || start + length > upper || !romchecksum(rom, length))
-                        continue;
-
-                adapter_rom_resources[i].start = start;
-                adapter_rom_resources[i].end = start + length - 1;
-                request_resource(&iomem_resource, &adapter_rom_resources[i]);
-
-                start = adapter_rom_resources[i++].end & ~2047UL;
-        }
-}
-
 #ifdef CONFIG_PROC_VMCORE
 /* elfcorehdr= specifies the location of elf core header
  * stored by the crashed kernel. This option will be passed
@@ -444,6 +322,11 @@ void __init setup_arch(char **cmdline_p)
         /* reserve ebda region */
         if (ebda_addr)
                 reserve_bootmem_generic(ebda_addr, ebda_size);
+#ifdef CONFIG_NUMA
+        /* reserve nodemap region */
+        if (nodemap_addr)
+                reserve_bootmem_generic(nodemap_addr, nodemap_size);
+#endif
 
 #ifdef CONFIG_SMP
         /*
@@ -519,15 +402,11 @@ void __init setup_arch(char **cmdline_p)
         init_apic_mappings();
 
         /*
-         * Request address space for all standard RAM and ROM resources
-         * and also for regions reported as reserved by the e820.
-         */
-        probe_roms();
+         * We trust e820 completely. No explicit ROM probing in memory.
+         */
         e820_reserve_resources(); 
         e820_mark_nosave_regions();
 
-        request_resource(&iomem_resource, &video_ram_resource);
-
         {
         unsigned i;
         /* request I/O space for devices used on all i[345]86 PCs */
@@ -1063,7 +942,8 @@ static int show_cpuinfo(struct seq_file *m, void *v)
                 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
                 NULL, NULL, NULL, "syscall", NULL, NULL, NULL, NULL,
                 NULL, NULL, NULL, NULL, "nx", NULL, "mmxext", NULL,
-                NULL, "fxsr_opt", NULL, "rdtscp", NULL, "lm", "3dnowext", "3dnow",
+                NULL, "fxsr_opt", "pdpe1gb", "rdtscp", NULL, "lm",
+                "3dnowext", "3dnow",
 
                 /* Transmeta-defined */
                 "recovery", "longrun", NULL, "lrti", NULL, NULL, NULL, NULL,
@@ -1081,7 +961,7 @@ static int show_cpuinfo(struct seq_file *m, void *v)
                 /* Intel-defined (#2) */
                 "pni", NULL, NULL, "monitor", "ds_cpl", "vmx", "smx", "est",
                 "tm2", "ssse3", "cid", NULL, NULL, "cx16", "xtpr", NULL,
-                NULL, NULL, "dca", NULL, NULL, NULL, NULL, NULL,
+                NULL, NULL, "dca", NULL, NULL, NULL, NULL, "popcnt",
                 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
 
                 /* VIA/Cyrix/Centaur-defined */
@@ -1091,8 +971,10 @@ static int show_cpuinfo(struct seq_file *m, void *v)
                 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
 
                 /* AMD-defined (#2) */
-                "lahf_lm", "cmp_legacy", "svm", NULL, "cr8_legacy", NULL, NULL, NULL,
-                NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+                "lahf_lm", "cmp_legacy", "svm", "extapic", "cr8_legacy",
+                "altmovcr8", "abm", "sse4a",
+                "misalignsse", "3dnowprefetch",
+                "osvw", "ibs", NULL, NULL, NULL, NULL,
                 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
                 NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
         };
@@ -1103,6 +985,9 @@ static int show_cpuinfo(struct seq_file *m, void *v)
                 "ttp",  /* thermal trip */
                 "tm",
                 "stc",
+                "100mhzsteps",
+                "hwpstate",
+                NULL,   /* tsc invariant mapped to constant_tsc */
                 NULL,
                 /* nothing */   /* constant_tsc - moved to flags */
         };
@@ -1219,23 +1104,3 @@ struct seq_operations cpuinfo_op = {
         .stop = c_stop,
         .show = show_cpuinfo,
 };
-
-#if defined(CONFIG_INPUT_PCSPKR) || defined(CONFIG_INPUT_PCSPKR_MODULE)
-#include <linux/platform_device.h>
-static __init int add_pcspkr(void)
-{
-        struct platform_device *pd;
-        int ret;
-
-        pd = platform_device_alloc("pcspkr", -1);
-        if (!pd)
-                return -ENOMEM;
-
-        ret = platform_device_add(pd);
-        if (ret)
-                platform_device_put(pd);
-
-        return ret;
-}
-device_initcall(add_pcspkr);
-#endif
diff --git a/arch/x86_64/kernel/setup64.c b/arch/x86_64/kernel/setup64.c
index 8c4b80fe71a1..6a70b55f719d 100644
--- a/arch/x86_64/kernel/setup64.c
+++ b/arch/x86_64/kernel/setup64.c
@@ -37,7 +37,6 @@ struct desc_ptr idt_descr = { 256 * 16 - 1, (unsigned long) idt_table };
 char boot_cpu_stack[IRQSTACKSIZE] __attribute__((section(".bss.page_aligned")));
 
 unsigned long __supported_pte_mask __read_mostly = ~0UL;
-EXPORT_SYMBOL(__supported_pte_mask);
 static int do_not_nx __cpuinitdata = 0;
 
 /* noexec=on|off
diff --git a/arch/x86_64/kernel/stacktrace.c b/arch/x86_64/kernel/stacktrace.c
index 6026b31d037e..65ac2c6b34a6 100644
--- a/arch/x86_64/kernel/stacktrace.c
+++ b/arch/x86_64/kernel/stacktrace.c
@@ -32,7 +32,7 @@ static void save_stack_address(void *data, unsigned long addr)
                 trace->skip--;
                 return;
         }
-        if (trace->nr_entries < trace->max_entries - 1)
+        if (trace->nr_entries < trace->max_entries)
                 trace->entries[trace->nr_entries++] = addr;
 }
 
@@ -49,7 +49,8 @@ static struct stacktrace_ops save_stack_ops = {
 void save_stack_trace(struct stack_trace *trace, struct task_struct *task)
 {
         dump_trace(task, NULL, NULL, &save_stack_ops, trace);
-        trace->entries[trace->nr_entries++] = ULONG_MAX;
+        if (trace->nr_entries < trace->max_entries)
+                trace->entries[trace->nr_entries++] = ULONG_MAX;
 }
 EXPORT_SYMBOL(save_stack_trace);
 
diff --git a/arch/x86_64/kernel/time.c b/arch/x86_64/kernel/time.c
index 335cc91c49b7..3cc6886f1fb7 100644
--- a/arch/x86_64/kernel/time.c
+++ b/arch/x86_64/kernel/time.c
@@ -657,6 +657,7 @@ core_initcall(cpufreq_tsc);
 
 #define TICK_COUNT 100000000
 #define TICK_MIN   5000
+#define MAX_READ_RETRIES 5
 
 /*
  * Some platforms take periodic SMI interrupts with 5ms duration. Make sure none
@@ -664,13 +665,17 @@ core_initcall(cpufreq_tsc);
  */
 static void __init read_hpet_tsc(int *hpet, int *tsc)
 {
-        int tsc1, tsc2, hpet1;
+        int tsc1, tsc2, hpet1, retries = 0;
+        static int msg;
 
         do {
                 tsc1 = get_cycles_sync();
                 hpet1 = hpet_readl(HPET_COUNTER);
                 tsc2 = get_cycles_sync();
-        } while (tsc2 - tsc1 > TICK_MIN);
+        } while (tsc2 - tsc1 > TICK_MIN && retries++ < MAX_READ_RETRIES);
+        if (retries >= MAX_READ_RETRIES && !msg++)
+                printk(KERN_WARNING
+                       "hpet.c: exceeded max retries to read HPET & TSC\n");
         *hpet = hpet1;
         *tsc = tsc2;
 }
@@ -1221,8 +1226,9 @@ static void hpet_rtc_timer_reinit(void)
                 if (PIE_on)
                         PIE_count += lost_ints;
 
-                printk(KERN_WARNING "rtc: lost some interrupts at %ldHz.\n",
-                       hpet_rtc_int_freq);
+                if (printk_ratelimit())
+                        printk(KERN_WARNING "rtc: lost some interrupts at %ldHz.\n",
+                               hpet_rtc_int_freq);
         }
 }
 
diff --git a/arch/x86_64/kernel/x8664_ksyms.c b/arch/x86_64/kernel/x8664_ksyms.c
index 6d77e4797a47..0dffae69f4ad 100644
--- a/arch/x86_64/kernel/x8664_ksyms.c
+++ b/arch/x86_64/kernel/x8664_ksyms.c
@@ -26,6 +26,7 @@ EXPORT_SYMBOL(__put_user_4);
 EXPORT_SYMBOL(__put_user_8);
 
 EXPORT_SYMBOL(copy_user_generic);
+EXPORT_SYMBOL(__copy_user_nocache);
 EXPORT_SYMBOL(copy_from_user);
 EXPORT_SYMBOL(copy_to_user);
 EXPORT_SYMBOL(__copy_from_user_inatomic);
@@ -34,8 +35,8 @@ EXPORT_SYMBOL(copy_page);
 EXPORT_SYMBOL(clear_page);
 
 #ifdef CONFIG_SMP
-extern void FASTCALL( __write_lock_failed(rwlock_t *rw));
-extern void FASTCALL( __read_lock_failed(rwlock_t *rw));
+extern void  __write_lock_failed(rwlock_t *rw);
+extern void  __read_lock_failed(rwlock_t *rw);
 EXPORT_SYMBOL(__write_lock_failed);
 EXPORT_SYMBOL(__read_lock_failed);
 #endif