20 files changed, 348 insertions, 109 deletions

diff --git a/arch/i386/kernel/acpi/boot.c b/arch/i386/kernel/acpi/boot.c
index 92f79cdd9a48..d12fb97a5337 100644
--- a/arch/i386/kernel/acpi/boot.c
+++ b/arch/i386/kernel/acpi/boot.c
@@ -70,7 +70,7 @@ static inline int acpi_madt_oem_check(char *oem_id, char *oem_table_id) { return
 
 #define PREFIX                  "ACPI: "
 
-int acpi_noirq __initdata;      /* skip ACPI IRQ initialization */
+int acpi_noirq;                         /* skip ACPI IRQ initialization */
 int acpi_pci_disabled __initdata;       /* skip ACPI PCI scan and IRQ initialization */
 int acpi_ht __initdata = 1;     /* enable HT */
 
@@ -82,6 +82,7 @@ EXPORT_SYMBOL(acpi_strict);
 acpi_interrupt_flags acpi_sci_flags __initdata;
 int acpi_sci_override_gsi __initdata;
 int acpi_skip_timer_override __initdata;
+int acpi_use_timer_override __initdata;
 
 #ifdef CONFIG_X86_LOCAL_APIC
 static u64 acpi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE;
@@ -332,7 +333,7 @@ acpi_parse_ioapic(acpi_table_entry_header * header, const unsigned long end)
 /*
  * Parse Interrupt Source Override for the ACPI SCI
  */
-static void acpi_sci_ioapic_setup(u32 gsi, u16 polarity, u16 trigger)
+static void acpi_sci_ioapic_setup(u32 bus_irq, u32 gsi, u16 polarity, u16 trigger)
 {
         if (trigger == 0)       /* compatible SCI trigger is level */
                 trigger = 3;
@@ -352,13 +353,13 @@ static void acpi_sci_ioapic_setup(u32 gsi, u16 polarity, u16 trigger)
          * If GSI is < 16, this will update its flags,
          * else it will create a new mp_irqs[] entry.
          */
-        mp_override_legacy_irq(gsi, polarity, trigger, gsi);
+        mp_override_legacy_irq(bus_irq, polarity, trigger, gsi);
 
         /*
          * stash over-ride to indicate we've been here
          * and for later update of acpi_fadt
          */
-        acpi_sci_override_gsi = gsi;
+        acpi_sci_override_gsi = bus_irq;
         return;
 }
 
@@ -376,7 +377,7 @@ acpi_parse_int_src_ovr(acpi_table_entry_header * header,
         acpi_table_print_madt_entry(header);
 
         if (intsrc->bus_irq == acpi_fadt.sci_int) {
-                acpi_sci_ioapic_setup(intsrc->global_irq,
+                acpi_sci_ioapic_setup(intsrc->bus_irq, intsrc->global_irq,
                                       intsrc->flags.polarity,
                                       intsrc->flags.trigger);
                 return 0;
@@ -879,7 +880,7 @@ static int __init acpi_parse_madt_ioapic_entries(void)
          * pretend we got one so we can set the SCI flags.
          */
         if (!acpi_sci_override_gsi)
-                acpi_sci_ioapic_setup(acpi_fadt.sci_int, 0, 0);
+                acpi_sci_ioapic_setup(acpi_fadt.sci_int, acpi_fadt.sci_int, 0, 0);
 
         /* Fill in identity legacy mapings where no override */
         mp_config_acpi_legacy_irqs();
@@ -1300,6 +1301,13 @@ static int __init parse_acpi_skip_timer_override(char *arg)
         return 0;
 }
 early_param("acpi_skip_timer_override", parse_acpi_skip_timer_override);
+
+static int __init parse_acpi_use_timer_override(char *arg)
+{
+        acpi_use_timer_override = 1;
+        return 0;
+}
+early_param("acpi_use_timer_override", parse_acpi_use_timer_override);
 #endif /* CONFIG_X86_IO_APIC */
 
 static int __init setup_acpi_sci(char *s)
diff --git a/arch/i386/kernel/acpi/cstate.c b/arch/i386/kernel/acpi/cstate.c
index 25db49ef1770..20563e52c622 100644
--- a/arch/i386/kernel/acpi/cstate.c
+++ b/arch/i386/kernel/acpi/cstate.c
@@ -10,6 +10,7 @@
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/acpi.h>
+#include <linux/cpu.h>
 
 #include <acpi/processor.h>
 #include <asm/acpi.h>
@@ -41,5 +42,124 @@ void acpi_processor_power_init_bm_check(struct acpi_processor_flags *flags,
                 flags->bm_check = 1;
         }
 }
-
 EXPORT_SYMBOL(acpi_processor_power_init_bm_check);
+
+/* The code below handles cstate entry with monitor-mwait pair on Intel*/
+
+struct cstate_entry_s {
+        struct {
+                unsigned int eax;
+                unsigned int ecx;
+        } states[ACPI_PROCESSOR_MAX_POWER];
+};
+static struct cstate_entry_s *cpu_cstate_entry; /* per CPU ptr */
+
+static short mwait_supported[ACPI_PROCESSOR_MAX_POWER];
+
+#define MWAIT_SUBSTATE_MASK     (0xf)
+#define MWAIT_SUBSTATE_SIZE     (4)
+
+#define CPUID_MWAIT_LEAF (5)
+#define CPUID5_ECX_EXTENSIONS_SUPPORTED (0x1)
+#define CPUID5_ECX_INTERRUPT_BREAK      (0x2)
+
+#define MWAIT_ECX_INTERRUPT_BREAK       (0x1)
+
+#define NATIVE_CSTATE_BEYOND_HALT       (2)
+
+int acpi_processor_ffh_cstate_probe(unsigned int cpu,
+                struct acpi_processor_cx *cx, struct acpi_power_register *reg)
+{
+        struct cstate_entry_s *percpu_entry;
+        struct cpuinfo_x86 *c = cpu_data + cpu;
+
+        cpumask_t saved_mask;
+        int retval;
+        unsigned int eax, ebx, ecx, edx;
+        unsigned int edx_part;
+        unsigned int cstate_type; /* C-state type and not ACPI C-state type */
+        unsigned int num_cstate_subtype;
+
+        if (!cpu_cstate_entry || c->cpuid_level < CPUID_MWAIT_LEAF )
+                return -1;
+
+        if (reg->bit_offset != NATIVE_CSTATE_BEYOND_HALT)
+                return -1;
+
+        percpu_entry = per_cpu_ptr(cpu_cstate_entry, cpu);
+        percpu_entry->states[cx->index].eax = 0;
+        percpu_entry->states[cx->index].ecx = 0;
+
+        /* Make sure we are running on right CPU */
+        saved_mask = current->cpus_allowed;
+        retval = set_cpus_allowed(current, cpumask_of_cpu(cpu));
+        if (retval)
+                return -1;
+
+        cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &edx);
+
+        /* Check whether this particular cx_type (in CST) is supported or not */
+        cstate_type = (cx->address >> MWAIT_SUBSTATE_SIZE) + 1;
+        edx_part = edx >> (cstate_type * MWAIT_SUBSTATE_SIZE);
+        num_cstate_subtype = edx_part & MWAIT_SUBSTATE_MASK;
+
+        retval = 0;
+        if (num_cstate_subtype < (cx->address & MWAIT_SUBSTATE_MASK)) {
+                retval = -1;
+                goto out;
+        }
+
+        /* mwait ecx extensions INTERRUPT_BREAK should be supported for C2/C3 */
+        if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED) ||
+            !(ecx & CPUID5_ECX_INTERRUPT_BREAK)) {
+                retval = -1;
+                goto out;
+        }
+        percpu_entry->states[cx->index].ecx = MWAIT_ECX_INTERRUPT_BREAK;
+
+        /* Use the hint in CST */
+        percpu_entry->states[cx->index].eax = cx->address;
+
+        if (!mwait_supported[cstate_type]) {
+                mwait_supported[cstate_type] = 1;
+                printk(KERN_DEBUG "Monitor-Mwait will be used to enter C-%d "
+                       "state\n", cx->type);
+        }
+
+out:
+        set_cpus_allowed(current, saved_mask);
+        return retval;
+}
+EXPORT_SYMBOL_GPL(acpi_processor_ffh_cstate_probe);
+
+void acpi_processor_ffh_cstate_enter(struct acpi_processor_cx *cx)
+{
+        unsigned int cpu = smp_processor_id();
+        struct cstate_entry_s *percpu_entry;
+
+        percpu_entry = per_cpu_ptr(cpu_cstate_entry, cpu);
+        mwait_idle_with_hints(percpu_entry->states[cx->index].eax,
+                              percpu_entry->states[cx->index].ecx);
+}
+EXPORT_SYMBOL_GPL(acpi_processor_ffh_cstate_enter);
+
+static int __init ffh_cstate_init(void)
+{
+        struct cpuinfo_x86 *c = &boot_cpu_data;
+        if (c->x86_vendor != X86_VENDOR_INTEL)
+                return -1;
+
+        cpu_cstate_entry = alloc_percpu(struct cstate_entry_s);
+        return 0;
+}
+
+static void __exit ffh_cstate_exit(void)
+{
+        if (cpu_cstate_entry) {
+                free_percpu(cpu_cstate_entry);
+                cpu_cstate_entry = NULL;
+        }
+}
+
+arch_initcall(ffh_cstate_init);
+__exitcall(ffh_cstate_exit);
diff --git a/arch/i386/kernel/acpi/earlyquirk.c b/arch/i386/kernel/acpi/earlyquirk.c
index fe799b11ac0a..c9841692bb7c 100644
--- a/arch/i386/kernel/acpi/earlyquirk.c
+++ b/arch/i386/kernel/acpi/earlyquirk.c
@@ -27,11 +27,17 @@ static int __init check_bridge(int vendor, int device)
 #ifdef CONFIG_ACPI
         /* According to Nvidia all timer overrides are bogus unless HPET
            is enabled. */
-        if (vendor == PCI_VENDOR_ID_NVIDIA) {
+        if (!acpi_use_timer_override && vendor == PCI_VENDOR_ID_NVIDIA) {
                 nvidia_hpet_detected = 0;
                 acpi_table_parse(ACPI_HPET, nvidia_hpet_check);
                 if (nvidia_hpet_detected == 0) {
                         acpi_skip_timer_override = 1;
+                          printk(KERN_INFO "Nvidia board "
+                       "detected. Ignoring ACPI "
+                       "timer override.\n");
+                printk(KERN_INFO "If you got timer trouble "
+                                 "try acpi_use_timer_override\n");
+
                 }
         }
 #endif
diff --git a/arch/i386/kernel/alternative.c b/arch/i386/kernel/alternative.c
index 28ab80649764..583c238e17fb 100644
--- a/arch/i386/kernel/alternative.c
+++ b/arch/i386/kernel/alternative.c
@@ -344,6 +344,7 @@ void alternatives_smp_switch(int smp)
 
 void __init alternative_instructions(void)
 {
+        unsigned long flags;
         if (no_replacement) {
                 printk(KERN_INFO "(SMP-)alternatives turned off\n");
                 free_init_pages("SMP alternatives",
@@ -351,6 +352,8 @@ void __init alternative_instructions(void)
                                 (unsigned long)__smp_alt_end);
                 return;
         }
+
+        local_irq_save(flags);
         apply_alternatives(__alt_instructions, __alt_instructions_end);
 
         /* switch to patch-once-at-boottime-only mode and free the
@@ -386,4 +389,5 @@ void __init alternative_instructions(void)
                 alternatives_smp_switch(0);
         }
 #endif
+        local_irq_restore(flags);
 }
diff --git a/arch/i386/kernel/apm.c b/arch/i386/kernel/apm.c
index b42f2d914af3..a60358fe9a49 100644
--- a/arch/i386/kernel/apm.c
+++ b/arch/i386/kernel/apm.c
@@ -198,7 +198,7 @@
  *   (APM) BIOS Interface Specification, Revision 1.2, February 1996.
  *
  * [This document is available from Microsoft at:
- *    http://www.microsoft.com/hwdev/busbios/amp_12.htm]
+ *    http://www.microsoft.com/whdc/archive/amp_12.mspx]
  */
 
 #include <linux/module.h>
@@ -540,11 +540,30 @@ static inline void apm_restore_cpus(cpumask_t mask)
  * Also, we KNOW that for the non error case of apm_bios_call, there
  * is no useful data returned in the low order 8 bits of eax.
  */
-#define APM_DO_CLI      \
-        if (apm_info.allow_ints) \
-                local_irq_enable(); \
-        else \
+
+static inline unsigned long __apm_irq_save(void)
+{
+        unsigned long flags;
+        local_save_flags(flags);
+        if (apm_info.allow_ints) {
+                if (irqs_disabled_flags(flags))
+                        local_irq_enable();
+        } else
+                local_irq_disable();
+
+        return flags;
+}
+
+#define apm_irq_save(flags) \
+        do { flags = __apm_irq_save(); } while (0)
+
+static inline void apm_irq_restore(unsigned long flags)
+{
+        if (irqs_disabled_flags(flags))
                 local_irq_disable();
+        else if (irqs_disabled())
+                local_irq_enable();
+}
 
 #ifdef APM_ZERO_SEGS
 #       define APM_DECL_SEGS \
@@ -596,12 +615,11 @@ static u8 apm_bios_call(u32 func, u32 ebx_in, u32 ecx_in,
         save_desc_40 = gdt[0x40 / 8];
         gdt[0x40 / 8] = bad_bios_desc;
 
-        local_save_flags(flags);
-        APM_DO_CLI;
+        apm_irq_save(flags);
         APM_DO_SAVE_SEGS;
         apm_bios_call_asm(func, ebx_in, ecx_in, eax, ebx, ecx, edx, esi);
         APM_DO_RESTORE_SEGS;
-        local_irq_restore(flags);
+        apm_irq_restore(flags);
         gdt[0x40 / 8] = save_desc_40;
         put_cpu();
         apm_restore_cpus(cpus);
@@ -640,12 +658,11 @@ static u8 apm_bios_call_simple(u32 func, u32 ebx_in, u32 ecx_in, u32 *eax)
         save_desc_40 = gdt[0x40 / 8];
         gdt[0x40 / 8] = bad_bios_desc;
 
-        local_save_flags(flags);
-        APM_DO_CLI;
+        apm_irq_save(flags);
         APM_DO_SAVE_SEGS;
         error = apm_bios_call_simple_asm(func, ebx_in, ecx_in, eax);
         APM_DO_RESTORE_SEGS;
-        local_irq_restore(flags);
+        apm_irq_restore(flags);
         gdt[0x40 / 8] = save_desc_40;
         put_cpu();
         apm_restore_cpus(cpus);
diff --git a/arch/i386/kernel/cpu/mcheck/therm_throt.c b/arch/i386/kernel/cpu/mcheck/therm_throt.c
index 4f43047de406..2d8703b7ce65 100644
--- a/arch/i386/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/i386/kernel/cpu/mcheck/therm_throt.c
@@ -110,17 +110,15 @@ int therm_throt_process(int curr)
 
 #ifdef CONFIG_SYSFS
 /* Add/Remove thermal_throttle interface for CPU device */
-static __cpuinit int thermal_throttle_add_dev(struct sys_device * sys_dev)
+static __cpuinit int thermal_throttle_add_dev(struct sys_device *sys_dev)
 {
-        sysfs_create_group(&sys_dev->kobj, &thermal_throttle_attr_group);
-        return 0;
+        return sysfs_create_group(&sys_dev->kobj, &thermal_throttle_attr_group);
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-static __cpuinit int thermal_throttle_remove_dev(struct sys_device * sys_dev)
+static __cpuinit void thermal_throttle_remove_dev(struct sys_device *sys_dev)
 {
-        sysfs_remove_group(&sys_dev->kobj, &thermal_throttle_attr_group);
-        return 0;
+        return sysfs_remove_group(&sys_dev->kobj, &thermal_throttle_attr_group);
 }
 
 /* Mutex protecting device creation against CPU hotplug */
@@ -133,12 +131,14 @@ static __cpuinit int thermal_throttle_cpu_callback(struct notifier_block *nfb,
 {
         unsigned int cpu = (unsigned long)hcpu;
         struct sys_device *sys_dev;
+        int err;
 
         sys_dev = get_cpu_sysdev(cpu);
         mutex_lock(&therm_cpu_lock);
         switch (action) {
         case CPU_ONLINE:
-                thermal_throttle_add_dev(sys_dev);
+                err = thermal_throttle_add_dev(sys_dev);
+                WARN_ON(err);
                 break;
         case CPU_DEAD:
                 thermal_throttle_remove_dev(sys_dev);
@@ -157,6 +157,7 @@ static struct notifier_block thermal_throttle_cpu_notifier =
 static __init int thermal_throttle_init_device(void)
 {
         unsigned int cpu = 0;
+        int err;
 
         if (!atomic_read(&therm_throt_en))
                 return 0;
@@ -167,8 +168,10 @@ static __init int thermal_throttle_init_device(void)
         mutex_lock(&therm_cpu_lock);
 #endif
         /* connect live CPUs to sysfs */
-        for_each_online_cpu(cpu)
-                thermal_throttle_add_dev(get_cpu_sysdev(cpu));
+        for_each_online_cpu(cpu) {
+                err = thermal_throttle_add_dev(get_cpu_sysdev(cpu));
+                WARN_ON(err);
+        }
 #ifdef CONFIG_HOTPLUG_CPU
         mutex_unlock(&therm_cpu_lock);
 #endif
diff --git a/arch/i386/kernel/head.S b/arch/i386/kernel/head.S
index be9d883c62ce..ca31f18d277c 100644
--- a/arch/i386/kernel/head.S
+++ b/arch/i386/kernel/head.S
@@ -317,7 +317,7 @@ is386:	movl $2,%ecx		# set MP
         movl %eax,%gs
         lldt %ax
         cld                     # gcc2 wants the direction flag cleared at all times
-        pushl %eax              # fake return address
+        pushl $0                # fake return address for unwinder
 #ifdef CONFIG_SMP
         movb ready, %cl
         movb $1, ready
diff --git a/arch/i386/kernel/i8253.c b/arch/i386/kernel/i8253.c
index 477b24daff53..9a0060b92e32 100644
--- a/arch/i386/kernel/i8253.c
+++ b/arch/i386/kernel/i8253.c
@@ -109,7 +109,7 @@ static struct clocksource clocksource_pit = {
 
 static int __init init_pit_clocksource(void)
 {
-        if (num_possible_cpus() > 4) /* PIT does not scale! */
+        if (num_possible_cpus() > 1) /* PIT does not scale! */
                 return 0;
 
         clocksource_pit.mult = clocksource_hz2mult(CLOCK_TICK_RATE, 20);
diff --git a/arch/i386/kernel/i8259.c b/arch/i386/kernel/i8259.c
index d53eafb6daa7..62996cd17084 100644
--- a/arch/i386/kernel/i8259.c
+++ b/arch/i386/kernel/i8259.c
@@ -113,7 +113,8 @@ void make_8259A_irq(unsigned int irq)
 {
         disable_irq_nosync(irq);
         io_apic_irqs &= ~(1<<irq);
-        set_irq_chip_and_handler(irq, &i8259A_chip, handle_level_irq);
+        set_irq_chip_and_handler_name(irq, &i8259A_chip, handle_level_irq,
+                                      "XT");
         enable_irq(irq);
 }
 
@@ -369,8 +370,8 @@ void __init init_ISA_irqs (void)
                         /*
                          * 16 old-style INTA-cycle interrupts:
                          */
-                        set_irq_chip_and_handler(i, &i8259A_chip,
-                                                 handle_level_irq);
+                        set_irq_chip_and_handler_name(i, &i8259A_chip,
+                                                      handle_level_irq, "XT");
                 } else {
                         /*
                          * 'high' PCI IRQs filled in on demand
diff --git a/arch/i386/kernel/io_apic.c b/arch/i386/kernel/io_apic.c
index cd082c36ca03..3b7a63e0ed1a 100644
--- a/arch/i386/kernel/io_apic.c
+++ b/arch/i386/kernel/io_apic.c
@@ -91,6 +91,46 @@ static struct irq_pin_list {
         int apic, pin, next;
 } irq_2_pin[PIN_MAP_SIZE];
 
+struct io_apic {
+        unsigned int index;
+        unsigned int unused[3];
+        unsigned int data;
+};
+
+static __attribute_const__ struct io_apic __iomem *io_apic_base(int idx)
+{
+        return (void __iomem *) __fix_to_virt(FIX_IO_APIC_BASE_0 + idx)
+                + (mp_ioapics[idx].mpc_apicaddr & ~PAGE_MASK);
+}
+
+static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg)
+{
+        struct io_apic __iomem *io_apic = io_apic_base(apic);
+        writel(reg, &io_apic->index);
+        return readl(&io_apic->data);
+}
+
+static inline void io_apic_write(unsigned int apic, unsigned int reg, unsigned int value)
+{
+        struct io_apic __iomem *io_apic = io_apic_base(apic);
+        writel(reg, &io_apic->index);
+        writel(value, &io_apic->data);
+}
+
+/*
+ * Re-write a value: to be used for read-modify-write
+ * cycles where the read already set up the index register.
+ *
+ * Older SiS APIC requires we rewrite the index register
+ */
+static inline void io_apic_modify(unsigned int apic, unsigned int reg, unsigned int value)
+{
+        volatile struct io_apic *io_apic = io_apic_base(apic);
+        if (sis_apic_bug)
+                writel(reg, &io_apic->index);
+        writel(value, &io_apic->data);
+}
+
 union entry_union {
         struct { u32 w1, w2; };
         struct IO_APIC_route_entry entry;
@@ -107,12 +147,34 @@ static struct IO_APIC_route_entry ioapic_read_entry(int apic, int pin)
         return eu.entry;
 }
 
+/*
+ * When we write a new IO APIC routing entry, we need to write the high
+ * word first! If the mask bit in the low word is clear, we will enable
+ * the interrupt, and we need to make sure the entry is fully populated
+ * before that happens.
+ */
 static void ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e)
 {
         unsigned long flags;
         union entry_union eu;
         eu.entry = e;
         spin_lock_irqsave(&ioapic_lock, flags);
+        io_apic_write(apic, 0x11 + 2*pin, eu.w2);
+        io_apic_write(apic, 0x10 + 2*pin, eu.w1);
+        spin_unlock_irqrestore(&ioapic_lock, flags);
+}
+
+/*
+ * When we mask an IO APIC routing entry, we need to write the low
+ * word first, in order to set the mask bit before we change the
+ * high bits!
+ */
+static void ioapic_mask_entry(int apic, int pin)
+{
+        unsigned long flags;
+        union entry_union eu = { .entry.mask = 1 };
+
+        spin_lock_irqsave(&ioapic_lock, flags);
         io_apic_write(apic, 0x10 + 2*pin, eu.w1);
         io_apic_write(apic, 0x11 + 2*pin, eu.w2);
         spin_unlock_irqrestore(&ioapic_lock, flags);
@@ -234,9 +296,7 @@ static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin)
         /*
          * Disable it in the IO-APIC irq-routing table:
          */
-        memset(&entry, 0, sizeof(entry));
-        entry.mask = 1;
-        ioapic_write_entry(apic, pin, entry);
+        ioapic_mask_entry(apic, pin);
 }
 
 static void clear_IO_APIC (void)
@@ -1225,11 +1285,13 @@ static void ioapic_register_intr(int irq, int vector, unsigned long trigger)
 {
         if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
                         trigger == IOAPIC_LEVEL)
-                set_irq_chip_and_handler(irq, &ioapic_chip,
-                                         handle_fasteoi_irq);
-        else
-                set_irq_chip_and_handler(irq, &ioapic_chip,
-                                         handle_edge_irq);
+                set_irq_chip_and_handler_name(irq, &ioapic_chip,
+                                         handle_fasteoi_irq, "fasteoi");
+        else {
+                irq_desc[irq].status |= IRQ_DELAYED_DISABLE;
+                set_irq_chip_and_handler_name(irq, &ioapic_chip,
+                                         handle_edge_irq, "edge");
+        }
         set_intr_gate(vector, interrupt[irq]);
 }
 
@@ -2235,7 +2297,8 @@ static inline void check_timer(void)
         printk(KERN_INFO "...trying to set up timer as Virtual Wire IRQ...");
 
         disable_8259A_irq(0);
-        set_irq_chip_and_handler(0, &lapic_chip, handle_fasteoi_irq);
+        set_irq_chip_and_handler_name(0, &lapic_chip, handle_fasteoi_irq,
+                                      "fasteio");
         apic_write_around(APIC_LVT0, APIC_DM_FIXED | vector);   /* Fixed mode */
         enable_8259A_irq(0);
 
@@ -2541,7 +2604,8 @@ int arch_setup_msi_irq(unsigned int irq, struct pci_dev *dev)
 
         write_msi_msg(irq, &msg);
 
-        set_irq_chip_and_handler(irq, &msi_chip, handle_edge_irq);
+        set_irq_chip_and_handler_name(irq, &msi_chip, handle_edge_irq,
+                                      "edge");
 
         return 0;
 }
@@ -2562,18 +2626,16 @@ void arch_teardown_msi_irq(unsigned int irq)
 
 static void target_ht_irq(unsigned int irq, unsigned int dest)
 {
-        u32 low, high;
-        low  = read_ht_irq_low(irq);
-        high = read_ht_irq_high(irq);
+        struct ht_irq_msg msg;
+        fetch_ht_irq_msg(irq, &msg);
 
-        low  &= ~(HT_IRQ_LOW_DEST_ID_MASK);
-        high &= ~(HT_IRQ_HIGH_DEST_ID_MASK);
+        msg.address_lo &= ~(HT_IRQ_LOW_DEST_ID_MASK);
+        msg.address_hi &= ~(HT_IRQ_HIGH_DEST_ID_MASK);
 
-        low  |= HT_IRQ_LOW_DEST_ID(dest);
-        high |= HT_IRQ_HIGH_DEST_ID(dest);
+        msg.address_lo |= HT_IRQ_LOW_DEST_ID(dest);
+        msg.address_hi |= HT_IRQ_HIGH_DEST_ID(dest);
 
-        write_ht_irq_low(irq, low);
-        write_ht_irq_high(irq, high);
+        write_ht_irq_msg(irq, &msg);
 }
 
 static void set_ht_irq_affinity(unsigned int irq, cpumask_t mask)
@@ -2594,7 +2656,7 @@ static void set_ht_irq_affinity(unsigned int irq, cpumask_t mask)
 }
 #endif
 
-static struct hw_interrupt_type ht_irq_chip = {
+static struct irq_chip ht_irq_chip = {
         .name           = "PCI-HT",
         .mask           = mask_ht_irq,
         .unmask         = unmask_ht_irq,
@@ -2611,7 +2673,7 @@ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
 
         vector = assign_irq_vector(irq);
         if (vector >= 0) {
-                u32 low, high;
+                struct ht_irq_msg msg;
                 unsigned dest;
                 cpumask_t tmp;
 
@@ -2619,9 +2681,10 @@ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
                 cpu_set(vector >> 8, tmp);
                 dest = cpu_mask_to_apicid(tmp);
 
-                high =  HT_IRQ_HIGH_DEST_ID(dest);
+                msg.address_hi = HT_IRQ_HIGH_DEST_ID(dest);
 
-                low =   HT_IRQ_LOW_BASE |
+                msg.address_lo =
+                        HT_IRQ_LOW_BASE |
                         HT_IRQ_LOW_DEST_ID(dest) |
                         HT_IRQ_LOW_VECTOR(vector) |
                         ((INT_DEST_MODE == 0) ?
@@ -2633,10 +2696,10 @@ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
                                 HT_IRQ_LOW_MT_ARBITRATED) |
                         HT_IRQ_LOW_IRQ_MASKED;
 
-                write_ht_irq_low(irq, low);
-                write_ht_irq_high(irq, high);
+                write_ht_irq_msg(irq, &msg);
 
-                set_irq_chip_and_handler(irq, &ht_irq_chip, handle_edge_irq);
+                set_irq_chip_and_handler_name(irq, &ht_irq_chip,
+                                              handle_edge_irq, "edge");
         }
         return vector;
 }
diff --git a/arch/i386/kernel/irq.c b/arch/i386/kernel/irq.c
index 8cfc7dbec7b9..3201d421090a 100644
--- a/arch/i386/kernel/irq.c
+++ b/arch/i386/kernel/irq.c
@@ -258,7 +258,7 @@ int show_interrupts(struct seq_file *p, void *v)
                         seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
 #endif
                 seq_printf(p, " %8s", irq_desc[i].chip->name);
-                seq_printf(p, "-%s", handle_irq_name(irq_desc[i].handle_irq));
+                seq_printf(p, "-%-8s", irq_desc[i].name);
                 seq_printf(p, "  %s", action->name);
 
                 for (action=action->next; action; action = action->next)
diff --git a/arch/i386/kernel/kprobes.c b/arch/i386/kernel/kprobes.c
index d98e44b16fe2..fc79e1e859c4 100644
--- a/arch/i386/kernel/kprobes.c
+++ b/arch/i386/kernel/kprobes.c
@@ -361,8 +361,11 @@ no_kprobe:
         asm volatile ( ".global kretprobe_trampoline\n"
                         "kretprobe_trampoline: \n"
                         "       pushf\n"
-                        /* skip cs, eip, orig_eax, es, ds */
-                        "       subl $20, %esp\n"
+                        /* skip cs, eip, orig_eax */
+                        "       subl $12, %esp\n"
+                        "       pushl %gs\n"
+                        "       pushl %ds\n"
+                        "       pushl %es\n"
                         "       pushl %eax\n"
                         "       pushl %ebp\n"
                         "       pushl %edi\n"
@@ -373,10 +376,10 @@ no_kprobe:
                         "       movl %esp, %eax\n"
                         "       call trampoline_handler\n"
                         /* move eflags to cs */
-                        "       movl 48(%esp), %edx\n"
-                        "       movl %edx, 44(%esp)\n"
+                        "       movl 52(%esp), %edx\n"
+                        "       movl %edx, 48(%esp)\n"
                         /* save true return address on eflags */
-                        "       movl %eax, 48(%esp)\n"
+                        "       movl %eax, 52(%esp)\n"
                         "       popl %ebx\n"
                         "       popl %ecx\n"
                         "       popl %edx\n"
@@ -384,8 +387,8 @@ no_kprobe:
                         "       popl %edi\n"
                         "       popl %ebp\n"
                         "       popl %eax\n"
-                        /* skip eip, orig_eax, es, ds */
-                        "       addl $16, %esp\n"
+                        /* skip eip, orig_eax, es, ds, gs */
+                        "       addl $20, %esp\n"
                         "       popf\n"
                         "       ret\n");
 }
@@ -404,6 +407,10 @@ fastcall void *__kprobes trampoline_handler(struct pt_regs *regs)
         INIT_HLIST_HEAD(&empty_rp);
         spin_lock_irqsave(&kretprobe_lock, flags);
         head = kretprobe_inst_table_head(current);
+        /* fixup registers */
+        regs->xcs = __KERNEL_CS;
+        regs->eip = trampoline_address;
+        regs->orig_eax = 0xffffffff;
 
         /*
          * It is possible to have multiple instances associated with a given
@@ -425,6 +432,7 @@ fastcall void *__kprobes trampoline_handler(struct pt_regs *regs)
 
                 if (ri->rp && ri->rp->handler){
                         __get_cpu_var(current_kprobe) = &ri->rp->kp;
+                        get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE;
                         ri->rp->handler(ri, regs);
                         __get_cpu_var(current_kprobe) = NULL;
                 }
diff --git a/arch/i386/kernel/microcode.c b/arch/i386/kernel/microcode.c
index 9b9479768d5e..23f5984d0654 100644
--- a/arch/i386/kernel/microcode.c
+++ b/arch/i386/kernel/microcode.c
@@ -577,7 +577,7 @@ static void microcode_init_cpu(int cpu)
         set_cpus_allowed(current, cpumask_of_cpu(cpu));
         mutex_lock(&microcode_mutex);
         collect_cpu_info(cpu);
-        if (uci->valid)
+        if (uci->valid && system_state == SYSTEM_RUNNING)
                 cpu_request_microcode(cpu);
         mutex_unlock(&microcode_mutex);
         set_cpus_allowed(current, old);
@@ -656,14 +656,18 @@ static struct attribute_group mc_attr_group = {
 
 static int mc_sysdev_add(struct sys_device *sys_dev)
 {
-        int cpu = sys_dev->id;
+        int err, cpu = sys_dev->id;
         struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
 
         if (!cpu_online(cpu))
                 return 0;
+
         pr_debug("Microcode:CPU %d added\n", cpu);
         memset(uci, 0, sizeof(*uci));
-        sysfs_create_group(&sys_dev->kobj, &mc_attr_group);
+
+        err = sysfs_create_group(&sys_dev->kobj, &mc_attr_group);
+        if (err)
+                return err;
 
         microcode_init_cpu(cpu);
         return 0;
diff --git a/arch/i386/kernel/nmi.c b/arch/i386/kernel/nmi.c
index 3e8e3adb0489..eaafe233a5da 100644
--- a/arch/i386/kernel/nmi.c
+++ b/arch/i386/kernel/nmi.c
@@ -219,11 +219,11 @@ static int __init check_nmi_watchdog(void)
         int cpu;
 
         /* Enable NMI watchdog for newer systems.
-           Actually it should be safe for most systems before 2004 too except
-           for some IBM systems that corrupt registers when NMI happens
-           during SMM. Unfortunately we don't have more exact information
-           on these and use this coarse check. */
-        if (nmi_watchdog == NMI_DEFAULT && dmi_get_year(DMI_BIOS_DATE) >= 2004)
+           Probably safe on most older systems too, but let's be careful.
+           IBM ThinkPads use INT10 inside SMM and that allows early NMI inside SMM
+           which hangs the system. Disable watchdog for all thinkpads */
+        if (nmi_watchdog == NMI_DEFAULT && dmi_get_year(DMI_BIOS_DATE) >= 2004 &&
+                !dmi_name_in_vendors("ThinkPad"))
                 nmi_watchdog = NMI_LOCAL_APIC;
 
         if ((nmi_watchdog == NMI_NONE) || (nmi_watchdog == NMI_DEFAULT))
diff --git a/arch/i386/kernel/process.c b/arch/i386/kernel/process.c
index b0a07801d9df..dd53c58f64f1 100644
--- a/arch/i386/kernel/process.c
+++ b/arch/i386/kernel/process.c
@@ -205,7 +205,7 @@ void cpu_idle(void)
 void cpu_idle_wait(void)
 {
         unsigned int cpu, this_cpu = get_cpu();
-        cpumask_t map;
+        cpumask_t map, tmp = current->cpus_allowed;
 
         set_cpus_allowed(current, cpumask_of_cpu(this_cpu));
         put_cpu();
@@ -227,6 +227,8 @@ void cpu_idle_wait(void)
                 }
                 cpus_and(map, map, cpu_online_map);
         } while (!cpus_empty(map));
+
+        set_cpus_allowed(current, tmp);
 }
 EXPORT_SYMBOL_GPL(cpu_idle_wait);
 
@@ -236,20 +238,28 @@ EXPORT_SYMBOL_GPL(cpu_idle_wait);
  * We execute MONITOR against need_resched and enter optimized wait state
  * through MWAIT. Whenever someone changes need_resched, we would be woken
  * up from MWAIT (without an IPI).
+ *
+ * New with Core Duo processors, MWAIT can take some hints based on CPU
+ * capability.
  */
-static void mwait_idle(void)
+void mwait_idle_with_hints(unsigned long eax, unsigned long ecx)
 {
-        local_irq_enable();
-
-        while (!need_resched()) {
+        if (!need_resched()) {
                 __monitor((void *)&current_thread_info()->flags, 0, 0);
                 smp_mb();
-                if (need_resched())
-                        break;
-                __mwait(0, 0);
+                if (!need_resched())
+                        __mwait(eax, ecx);
         }
 }
 
+/* Default MONITOR/MWAIT with no hints, used for default C1 state */
+static void mwait_idle(void)
+{
+        local_irq_enable();
+        while (!need_resched())
+                mwait_idle_with_hints(0, 0);
+}
+
 void __devinit select_idle_routine(const struct cpuinfo_x86 *c)
 {
         if (cpu_has(c, X86_FEATURE_MWAIT)) {
@@ -328,7 +338,6 @@ extern void kernel_thread_helper(void);
 int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags)
 {
         struct pt_regs regs;
-        int err;
 
         memset(&regs, 0, sizeof(regs));
 
@@ -343,10 +352,7 @@ int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags)
         regs.eflags = X86_EFLAGS_IF | X86_EFLAGS_SF | X86_EFLAGS_PF | 0x2;
 
         /* Ok, create the new process.. */
-        err = do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0, &regs, 0, NULL, NULL);
-        if (err == 0) /* terminate kernel stack */
-                task_pt_regs(current)->eip = 0;
-        return err;
+        return do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0, &regs, 0, NULL, NULL);
 }
 EXPORT_SYMBOL(kernel_thread);
 
diff --git a/arch/i386/kernel/setup.c b/arch/i386/kernel/setup.c
index 000cf03751fe..141041dde74d 100644
--- a/arch/i386/kernel/setup.c
+++ b/arch/i386/kernel/setup.c
@@ -846,7 +846,7 @@ efi_find_max_pfn(unsigned long start, unsigned long end, void *arg)
 static int __init
 efi_memory_present_wrapper(unsigned long start, unsigned long end, void *arg)
 {
-        memory_present(0, start, end);
+        memory_present(0, PFN_UP(start), PFN_DOWN(end));
         return 0;
 }
 
@@ -1083,16 +1083,15 @@ static unsigned long __init setup_memory(void)
 
 void __init zone_sizes_init(void)
 {
+        unsigned long max_zone_pfns[MAX_NR_ZONES];
+        memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
+        max_zone_pfns[ZONE_DMA] =
+                virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT;
+        max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
 #ifdef CONFIG_HIGHMEM
-        unsigned long max_zone_pfns[MAX_NR_ZONES] = {
-                        virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT,
-                        max_low_pfn,
-                        highend_pfn};
+        max_zone_pfns[ZONE_HIGHMEM] = highend_pfn;
         add_active_range(0, 0, highend_pfn);
 #else
-        unsigned long max_zone_pfns[MAX_NR_ZONES] = {
-                        virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT,
-                        max_low_pfn};
         add_active_range(0, 0, max_low_pfn);
 #endif
 
diff --git a/arch/i386/kernel/syscall_table.S b/arch/i386/kernel/syscall_table.S
index 7e639f78b0b9..2697e9210e92 100644
--- a/arch/i386/kernel/syscall_table.S
+++ b/arch/i386/kernel/syscall_table.S
@@ -318,3 +318,4 @@ ENTRY(sys_call_table)
         .long sys_vmsplice
         .long sys_move_pages
         .long sys_getcpu
+        .long sys_epoll_pwait
diff --git a/arch/i386/kernel/traps.c b/arch/i386/kernel/traps.c
index 00489b706d27..fe9c5e8e7e6f 100644
--- a/arch/i386/kernel/traps.c
+++ b/arch/i386/kernel/traps.c
@@ -129,15 +129,19 @@ static inline unsigned long print_context_stack(struct thread_info *tinfo,
 
 #ifdef  CONFIG_FRAME_POINTER
         while (valid_stack_ptr(tinfo, (void *)ebp)) {
+                unsigned long new_ebp;
                 addr = *(unsigned long *)(ebp + 4);
                 ops->address(data, addr);
                 /*
                  * break out of recursive entries (such as
-                 * end_of_stack_stop_unwind_function):
+                 * end_of_stack_stop_unwind_function). Also,
+                 * we can never allow a frame pointer to
+                 * move downwards!
                  */
-                if (ebp == *(unsigned long *)ebp)
+                new_ebp = *(unsigned long *)ebp;
+                if (new_ebp <= ebp)
                         break;
-                ebp = *(unsigned long *)ebp;
+                ebp = new_ebp;
         }
 #else
         while (valid_stack_ptr(tinfo, stack)) {
diff --git a/arch/i386/kernel/tsc.c b/arch/i386/kernel/tsc.c
index b8fa0a8b2e47..fbc95828cd74 100644
--- a/arch/i386/kernel/tsc.c
+++ b/arch/i386/kernel/tsc.c
@@ -349,8 +349,8 @@ static int tsc_update_callback(void)
         int change = 0;
 
         /* check to see if we should switch to the safe clocksource: */
-        if (clocksource_tsc.rating != 50 && check_tsc_unstable()) {
-                clocksource_tsc.rating = 50;
+        if (clocksource_tsc.rating != 0 && check_tsc_unstable()) {
+                clocksource_tsc.rating = 0;
                 clocksource_reselect();
                 change = 1;
         }
@@ -461,7 +461,7 @@ static int __init init_tsc_clocksource(void)
                                                         clocksource_tsc.shift);
                 /* lower the rating if we already know its unstable: */
                 if (check_tsc_unstable())
-                        clocksource_tsc.rating = 50;
+                        clocksource_tsc.rating = 0;
 
                 init_timer(&verify_tsc_freq_timer);
                 verify_tsc_freq_timer.function = verify_tsc_freq;
diff --git a/arch/i386/kernel/vmlinux.lds.S b/arch/i386/kernel/vmlinux.lds.S
index 1e7ac1c44ddc..c6f84a0322ba 100644
--- a/arch/i386/kernel/vmlinux.lds.S
+++ b/arch/i386/kernel/vmlinux.lds.S
@@ -51,6 +51,7 @@ SECTIONS
   __tracedata_end = .;
 
   /* writeable */
+  . = ALIGN(4096);
   .data : AT(ADDR(.data) - LOAD_OFFSET) {       /* Data */
         *(.data)
         CONSTRUCTORS
@@ -126,13 +127,7 @@ SECTIONS
   __setup_end = .;
   __initcall_start = .;
   .initcall.init : AT(ADDR(.initcall.init) - LOAD_OFFSET) {
-        *(.initcall1.init) 
-        *(.initcall2.init) 
-        *(.initcall3.init) 
-        *(.initcall4.init) 
-        *(.initcall5.init) 
-        *(.initcall6.init) 
-        *(.initcall7.init)
+        INITCALLS
   }
   __initcall_end = .;
   __con_initcall_start = .;