Merge branch 'for-linus' of git://one.firstfloor.org/home/andi/git/linux-2.6

* 'for-linus' of git://one.firstfloor.org/home/andi/git/linux-2.6: (225 commits)
  [PATCH] Don't set calgary iommu as default y
  [PATCH] i386/x86-64: New Intel feature flags
  [PATCH] x86: Add a cumulative thermal throttle event counter.
  [PATCH] i386: Make the jiffies compares use the 64bit safe macros.
  [PATCH] x86: Refactor thermal throttle processing
  [PATCH] Add 64bit jiffies compares (for use with get_jiffies_64)
  [PATCH] Fix unwinder warning in traps.c
  [PATCH] x86: Allow disabling early pci scans with pci=noearly or disallowing conf1
  [PATCH] x86: Move direct PCI scanning functions out of line
  [PATCH] i386/x86-64: Make all early PCI scans dependent on CONFIG_PCI
  [PATCH] Don't leak NT bit into next task
  [PATCH] i386/x86-64: Work around gcc bug with noreturn functions in unwinder
  [PATCH] Fix some broken white space in ia32_signal.c
  [PATCH] Initialize argument registers for 32bit signal handlers.
  [PATCH] Remove all traces of signal number conversion
  [PATCH] Don't synchronize time reading on single core AMD systems
  [PATCH] Remove outdated comment in x86-64 mmconfig code
  [PATCH] Use string instructions for Core2 copy/clear
  [PATCH] x86: - restore i8259A eoi status on resume
  [PATCH] i386: Split multi-line printk in oops output.
  ...

29 files changed, 406 insertions, 352 deletions

diff --git a/include/asm-i386/acpi.h b/include/asm-i386/acpi.h
index 20f52395421..6016632d032 100644
--- a/include/asm-i386/acpi.h
+++ b/include/asm-i386/acpi.h
@@ -131,21 +131,7 @@ static inline void disable_acpi(void)
 extern int acpi_gsi_to_irq(u32 gsi, unsigned int *irq);
 
 #ifdef CONFIG_X86_IO_APIC
-extern int skip_ioapic_setup;
 extern int acpi_skip_timer_override;
-
-static inline void disable_ioapic_setup(void)
-{
-	skip_ioapic_setup = 1;
-}
-
-static inline int ioapic_setup_disabled(void)
-{
-	return skip_ioapic_setup;
-}
-
-#else
-static inline void disable_ioapic_setup(void) { }
 #endif
 
 static inline void acpi_noirq_set(void) { acpi_noirq = 1; }
diff --git a/include/asm-i386/alternative-asm.i b/include/asm-i386/alternative-asm.i
new file mode 100644
index 00000000000..6c47e3b9484
--- /dev/null
+++ b/include/asm-i386/alternative-asm.i
@@ -0,0 +1,14 @@
+#include <linux/config.h>
+
+#ifdef CONFIG_SMP
+	.macro LOCK_PREFIX
+1:	lock
+	.section .smp_locks,"a"
+	.align 4
+	.long 1b
+	.previous
+	.endm
+#else
+	.macro LOCK_PREFIX
+	.endm
+#endif
diff --git a/include/asm-i386/apic.h b/include/asm-i386/apic.h
index 2c1e371cebb..3a42b7d6fc9 100644
--- a/include/asm-i386/apic.h
+++ b/include/asm-i386/apic.h
@@ -16,20 +16,8 @@
 #define APIC_VERBOSE 1
 #define APIC_DEBUG   2
 
-extern int enable_local_apic;
 extern int apic_verbosity;
 
-static inline void lapic_disable(void)
-{
-	enable_local_apic = -1;
-	clear_bit(X86_FEATURE_APIC, boot_cpu_data.x86_capability);
-}
-
-static inline void lapic_enable(void)
-{
-	enable_local_apic = 1;
-}
-
 /*
  * Define the default level of output to be very little
  * This can be turned up by using apic=verbose for more
@@ -42,6 +30,8 @@ static inline void lapic_enable(void)
 	} while (0)
 
 
+extern void generic_apic_probe(void);
+
 #ifdef CONFIG_X86_LOCAL_APIC
 
 /*
@@ -117,8 +107,6 @@ extern void enable_APIC_timer(void);
 
 extern void enable_NMI_through_LVT0 (void * dummy);
 
-extern int disable_timer_pin_1;
-
 void smp_send_timer_broadcast_ipi(struct pt_regs *regs);
 void switch_APIC_timer_to_ipi(void *cpumask);
 void switch_ipi_to_APIC_timer(void *cpumask);
diff --git a/include/asm-i386/desc.h b/include/asm-i386/desc.h
index 89b8b82c82b..5874ef119ff 100644
--- a/include/asm-i386/desc.h
+++ b/include/asm-i386/desc.h
@@ -33,50 +33,99 @@ static inline struct desc_struct *get_cpu_gdt_table(unsigned int cpu)
 	return (struct desc_struct *)per_cpu(cpu_gdt_descr, cpu).address;
 }
 
+/*
+ * This is the ldt that every process will get unless we need
+ * something other than this.
+ */
+extern struct desc_struct default_ldt[];
+extern struct desc_struct idt_table[];
+extern void set_intr_gate(unsigned int irq, void * addr);
+
+static inline void pack_descriptor(__u32 *a, __u32 *b,
+	unsigned long base, unsigned long limit, unsigned char type, unsigned char flags)
+{
+	*a = ((base & 0xffff) << 16) | (limit & 0xffff);
+	*b = (base & 0xff000000) | ((base & 0xff0000) >> 16) |
+		(limit & 0x000f0000) | ((type & 0xff) << 8) | ((flags & 0xf) << 20);
+}
+
+static inline void pack_gate(__u32 *a, __u32 *b,
+	unsigned long base, unsigned short seg, unsigned char type, unsigned char flags)
+{
+	*a = (seg << 16) | (base & 0xffff);
+	*b = (base & 0xffff0000) | ((type & 0xff) << 8) | (flags & 0xff);
+}
+
+#define DESCTYPE_LDT 	0x82	/* present, system, DPL-0, LDT */
+#define DESCTYPE_TSS 	0x89	/* present, system, DPL-0, 32-bit TSS */
+#define DESCTYPE_TASK	0x85	/* present, system, DPL-0, task gate */
+#define DESCTYPE_INT	0x8e	/* present, system, DPL-0, interrupt gate */
+#define DESCTYPE_TRAP	0x8f	/* present, system, DPL-0, trap gate */
+#define DESCTYPE_DPL3	0x60	/* DPL-3 */
+#define DESCTYPE_S	0x10	/* !system */
+
 #define load_TR_desc() __asm__ __volatile__("ltr %w0"::"q" (GDT_ENTRY_TSS*8))
 #define load_LDT_desc() __asm__ __volatile__("lldt %w0"::"q" (GDT_ENTRY_LDT*8))
 
 #define load_gdt(dtr) __asm__ __volatile("lgdt %0"::"m" (*dtr))
 #define load_idt(dtr) __asm__ __volatile("lidt %0"::"m" (*dtr))
-#define load_tr(tr) __asm__ __volatile("ltr %0"::"mr" (tr))
-#define load_ldt(ldt) __asm__ __volatile("lldt %0"::"mr" (ldt))
+#define load_tr(tr) __asm__ __volatile("ltr %0"::"m" (tr))
+#define load_ldt(ldt) __asm__ __volatile("lldt %0"::"m" (ldt))
 
 #define store_gdt(dtr) __asm__ ("sgdt %0":"=m" (*dtr))
 #define store_idt(dtr) __asm__ ("sidt %0":"=m" (*dtr))
-#define store_tr(tr) __asm__ ("str %0":"=mr" (tr))
-#define store_ldt(ldt) __asm__ ("sldt %0":"=mr" (ldt))
+#define store_tr(tr) __asm__ ("str %0":"=m" (tr))
+#define store_ldt(ldt) __asm__ ("sldt %0":"=m" (ldt))
 
-/*
- * This is the ldt that every process will get unless we need
- * something other than this.
- */
-extern struct desc_struct default_ldt[];
-extern void set_intr_gate(unsigned int irq, void * addr);
+#if TLS_SIZE != 24
+# error update this code.
+#endif
 
-#define _set_tssldt_desc(n,addr,limit,type) \
-__asm__ __volatile__ ("movw %w3,0(%2)\n\t" \
-	"movw %w1,2(%2)\n\t" \
-	"rorl $16,%1\n\t" \
-	"movb %b1,4(%2)\n\t" \
-	"movb %4,5(%2)\n\t" \
-	"movb $0,6(%2)\n\t" \
-	"movb %h1,7(%2)\n\t" \
-	"rorl $16,%1" \
-	: "=m"(*(n)) : "q" (addr), "r"(n), "ir"(limit), "i"(type))
-
-static inline void __set_tss_desc(unsigned int cpu, unsigned int entry, void *addr)
+static inline void load_TLS(struct thread_struct *t, unsigned int cpu)
 {
-	_set_tssldt_desc(&get_cpu_gdt_table(cpu)[entry], (int)addr,
-		offsetof(struct tss_struct, __cacheline_filler) - 1, 0x89);
+#define C(i) get_cpu_gdt_table(cpu)[GDT_ENTRY_TLS_MIN + i] = t->tls_array[i]
+	C(0); C(1); C(2);
+#undef C
 }
 
-#define set_tss_desc(cpu,addr) __set_tss_desc(cpu, GDT_ENTRY_TSS, addr)
+static inline void write_dt_entry(void *dt, int entry, __u32 entry_a, __u32 entry_b)
+{
+	__u32 *lp = (__u32 *)((char *)dt + entry*8);
+	*lp = entry_a;
+	*(lp+1) = entry_b;
+}
+
+#define write_ldt_entry(dt, entry, a, b) write_dt_entry(dt, entry, a, b)
+#define write_gdt_entry(dt, entry, a, b) write_dt_entry(dt, entry, a, b)
+#define write_idt_entry(dt, entry, a, b) write_dt_entry(dt, entry, a, b)
+
+static inline void _set_gate(int gate, unsigned int type, void *addr, unsigned short seg)
+{
+	__u32 a, b;
+	pack_gate(&a, &b, (unsigned long)addr, seg, type, 0);
+	write_idt_entry(idt_table, gate, a, b);
+}
 
-static inline void set_ldt_desc(unsigned int cpu, void *addr, unsigned int size)
+static inline void __set_tss_desc(unsigned int cpu, unsigned int entry, const void *addr)
 {
-	_set_tssldt_desc(&get_cpu_gdt_table(cpu)[GDT_ENTRY_LDT], (int)addr, ((size << 3)-1), 0x82);
+	__u32 a, b;
+	pack_descriptor(&a, &b, (unsigned long)addr,
+			offsetof(struct tss_struct, __cacheline_filler) - 1,
+			DESCTYPE_TSS, 0);
+	write_gdt_entry(get_cpu_gdt_table(cpu), entry, a, b);
 }
 
+static inline void set_ldt_desc(unsigned int cpu, void *addr, unsigned int entries)
+{
+	__u32 a, b;
+	pack_descriptor(&a, &b, (unsigned long)addr,
+			entries * sizeof(struct desc_struct) - 1,
+			DESCTYPE_LDT, 0);
+	write_gdt_entry(get_cpu_gdt_table(cpu), GDT_ENTRY_LDT, a, b);
+}
+
+#define set_tss_desc(cpu,addr) __set_tss_desc(cpu, GDT_ENTRY_TSS, addr)
+
 #define LDT_entry_a(info) \
 	((((info)->base_addr & 0x0000ffff) << 16) | ((info)->limit & 0x0ffff))
 
@@ -102,24 +151,6 @@ static inline void set_ldt_desc(unsigned int cpu, void *addr, unsigned int size)
 	(info)->seg_not_present	== 1	&& \
 	(info)->useable		== 0	)
 
-static inline void write_ldt_entry(void *ldt, int entry, __u32 entry_a, __u32 entry_b)
-{
-	__u32 *lp = (__u32 *)((char *)ldt + entry*8);
-	*lp = entry_a;
-	*(lp+1) = entry_b;
-}
-
-#if TLS_SIZE != 24
-# error update this code.
-#endif
-
-static inline void load_TLS(struct thread_struct *t, unsigned int cpu)
-{
-#define C(i) get_cpu_gdt_table(cpu)[GDT_ENTRY_TLS_MIN + i] = t->tls_array[i]
-	C(0); C(1); C(2);
-#undef C
-}
-
 static inline void clear_LDT(void)
 {
 	int cpu = get_cpu();
diff --git a/include/asm-i386/dwarf2.h b/include/asm-i386/dwarf2.h
index 2280f6272f8..6d66398a307 100644
--- a/include/asm-i386/dwarf2.h
+++ b/include/asm-i386/dwarf2.h
@@ -1,8 +1,6 @@
 #ifndef _DWARF2_H
 #define _DWARF2_H
 
-#include <linux/config.h>
-
 #ifndef __ASSEMBLY__
 #warning "asm/dwarf2.h should be only included in pure assembly files"
 #endif
@@ -28,6 +26,13 @@
 #define CFI_RESTORE .cfi_restore
 #define CFI_REMEMBER_STATE .cfi_remember_state
 #define CFI_RESTORE_STATE .cfi_restore_state
+#define CFI_UNDEFINED .cfi_undefined
+
+#ifdef CONFIG_AS_CFI_SIGNAL_FRAME
+#define CFI_SIGNAL_FRAME .cfi_signal_frame
+#else
+#define CFI_SIGNAL_FRAME
+#endif
 
 #else
 
@@ -48,6 +53,8 @@
 #define CFI_RESTORE	ignore
 #define CFI_REMEMBER_STATE ignore
 #define CFI_RESTORE_STATE ignore
+#define CFI_UNDEFINED ignore
+#define CFI_SIGNAL_FRAME ignore
 
 #endif
 
diff --git a/include/asm-i386/e820.h b/include/asm-i386/e820.h
index ca82acb8cb1..f7514fb6e8e 100644
--- a/include/asm-i386/e820.h
+++ b/include/asm-i386/e820.h
@@ -18,7 +18,7 @@
 
 #define E820_RAM	1
 #define E820_RESERVED	2
-#define E820_ACPI	3 /* usable as RAM once ACPI tables have been read */
+#define E820_ACPI	3
 #define E820_NVS	4
 
 #define HIGH_MEMORY	(1024*1024)
diff --git a/include/asm-i386/frame.i b/include/asm-i386/frame.i
new file mode 100644
index 00000000000..4d68ddce18b
--- /dev/null
+++ b/include/asm-i386/frame.i
@@ -0,0 +1,24 @@
+#include <linux/config.h>
+#include <asm/dwarf2.h>
+
+/* The annotation hides the frame from the unwinder and makes it look
+   like a ordinary ebp save/restore. This avoids some special cases for
+   frame pointer later */
+#ifdef CONFIG_FRAME_POINTER
+	.macro FRAME
+	pushl %ebp
+	CFI_ADJUST_CFA_OFFSET 4
+	CFI_REL_OFFSET ebp,0
+	movl %esp,%ebp
+	.endm
+	.macro ENDFRAME
+	popl %ebp
+	CFI_ADJUST_CFA_OFFSET -4
+	CFI_RESTORE ebp
+	.endm
+#else
+	.macro FRAME
+	.endm
+	.macro ENDFRAME
+	.endm
+#endif
diff --git a/include/asm-i386/genapic.h b/include/asm-i386/genapic.h
index b3783a32abe..8ffbb0f0745 100644
--- a/include/asm-i386/genapic.h
+++ b/include/asm-i386/genapic.h
@@ -1,6 +1,8 @@
 #ifndef _ASM_GENAPIC_H
 #define _ASM_GENAPIC_H 1
 
+#include <asm/mpspec.h>
+
 /*
  * Generic APIC driver interface.
  *
@@ -63,14 +65,25 @@ struct genapic {
 	unsigned (*get_apic_id)(unsigned long x);
 	unsigned long apic_id_mask;
 	unsigned int (*cpu_mask_to_apicid)(cpumask_t cpumask);
-	
+
+#ifdef CONFIG_SMP
 	/* ipi */
 	void (*send_IPI_mask)(cpumask_t mask, int vector);
 	void (*send_IPI_allbutself)(int vector);
 	void (*send_IPI_all)(int vector);
+#endif
 }; 
 
-#define APICFUNC(x) .x = x
+#define APICFUNC(x) .x = x,
+
+/* More functions could be probably marked IPIFUNC and save some space
+   in UP GENERICARCH kernels, but I don't have the nerve right now
+   to untangle this mess. -AK  */
+#ifdef CONFIG_SMP
+#define IPIFUNC(x) APICFUNC(x)
+#else
+#define IPIFUNC(x)
+#endif
 
 #define APIC_INIT(aname, aprobe) { \
 	.name = aname, \
@@ -80,33 +93,33 @@ struct genapic {
 	.no_balance_irq = NO_BALANCE_IRQ, \
 	.ESR_DISABLE = esr_disable, \
 	.apic_destination_logical = APIC_DEST_LOGICAL, \
-	APICFUNC(apic_id_registered), \
-	APICFUNC(target_cpus), \
-	APICFUNC(check_apicid_used), \
-	APICFUNC(check_apicid_present), \
-	APICFUNC(init_apic_ldr), \
-	APICFUNC(ioapic_phys_id_map), \
-	APICFUNC(clustered_apic_check), \
-	APICFUNC(multi_timer_check), \
-	APICFUNC(apicid_to_node), \
-	APICFUNC(cpu_to_logical_apicid), \
-	APICFUNC(cpu_present_to_apicid), \
-	APICFUNC(apicid_to_cpu_present), \
-	APICFUNC(mpc_apic_id), \
-	APICFUNC(setup_portio_remap), \
-	APICFUNC(check_phys_apicid_present), \
-	APICFUNC(mpc_oem_bus_info), \
-	APICFUNC(mpc_oem_pci_bus), \
-	APICFUNC(mps_oem_check), \
-	APICFUNC(get_apic_id), \
+	APICFUNC(apic_id_registered) \
+	APICFUNC(target_cpus) \
+	APICFUNC(check_apicid_used) \
+	APICFUNC(check_apicid_present) \
+	APICFUNC(init_apic_ldr) \
+	APICFUNC(ioapic_phys_id_map) \
+	APICFUNC(clustered_apic_check) \
+	APICFUNC(multi_timer_check) \
+	APICFUNC(apicid_to_node) \
+	APICFUNC(cpu_to_logical_apicid) \
+	APICFUNC(cpu_present_to_apicid) \
+	APICFUNC(apicid_to_cpu_present) \
+	APICFUNC(mpc_apic_id) \
+	APICFUNC(setup_portio_remap) \
+	APICFUNC(check_phys_apicid_present) \
+	APICFUNC(mpc_oem_bus_info) \
+	APICFUNC(mpc_oem_pci_bus) \
+	APICFUNC(mps_oem_check) \
+	APICFUNC(get_apic_id) \
 	.apic_id_mask = APIC_ID_MASK, \
-	APICFUNC(cpu_mask_to_apicid), \
-	APICFUNC(acpi_madt_oem_check), \
-	APICFUNC(send_IPI_mask), \
-	APICFUNC(send_IPI_allbutself), \
-	APICFUNC(send_IPI_all), \
-	APICFUNC(enable_apic_mode), \
-	APICFUNC(phys_pkg_id), \
+	APICFUNC(cpu_mask_to_apicid) \
+	APICFUNC(acpi_madt_oem_check) \
+	IPIFUNC(send_IPI_mask) \
+	IPIFUNC(send_IPI_allbutself) \
+	IPIFUNC(send_IPI_all) \
+	APICFUNC(enable_apic_mode) \
+	APICFUNC(phys_pkg_id) \
 	}
 
 extern struct genapic *genapic;
diff --git a/include/asm-i386/intel_arch_perfmon.h b/include/asm-i386/intel_arch_perfmon.h
index 134ea9cc528..b52cd60a075 100644
--- a/include/asm-i386/intel_arch_perfmon.h
+++ b/include/asm-i386/intel_arch_perfmon.h
@@ -14,6 +14,18 @@
 
 #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL	(0x3c)
 #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK	(0x00 << 8)
-#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT (1 << 0)
+#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX (0)
+#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT \
+				(1 << (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX))
+
+union cpuid10_eax {
+	struct {
+		unsigned int version_id:8;
+		unsigned int num_counters:8;
+		unsigned int bit_width:8;
+		unsigned int mask_length:8;
+	} split;
+	unsigned int full;
+};
 
 #endif	/* X86_INTEL_ARCH_PERFMON_H */
diff --git a/include/asm-i386/io_apic.h b/include/asm-i386/io_apic.h
index 5092e819b8a..5d309275a1d 100644
--- a/include/asm-i386/io_apic.h
+++ b/include/asm-i386/io_apic.h
@@ -188,6 +188,16 @@ static inline void io_apic_modify(unsigned int apic, unsigned int reg, unsigned
 /* 1 if "noapic" boot option passed */
 extern int skip_ioapic_setup;
 
+static inline void disable_ioapic_setup(void)
+{
+	skip_ioapic_setup = 1;
+}
+
+static inline int ioapic_setup_disabled(void)
+{
+	return skip_ioapic_setup;
+}
+
 /*
  * If we use the IO-APIC for IRQ routing, disable automatic
  * assignment of PCI IRQ's.
@@ -206,6 +216,7 @@ extern int (*ioapic_renumber_irq)(int ioapic, int irq);
 
 #else  /* !CONFIG_X86_IO_APIC */
 #define io_apic_assign_pci_irqs 0
+static inline void disable_ioapic_setup(void) { }
 #endif
 
 extern int assign_irq_vector(int irq);
diff --git a/include/asm-i386/kexec.h b/include/asm-i386/kexec.h
index 53f0e06672d..4dfc9f5ed03 100644
--- a/include/asm-i386/kexec.h
+++ b/include/asm-i386/kexec.h
@@ -1,6 +1,26 @@
 #ifndef _I386_KEXEC_H
 #define _I386_KEXEC_H
 
+#define PA_CONTROL_PAGE  0
+#define VA_CONTROL_PAGE  1
+#define PA_PGD           2
+#define VA_PGD           3
+#define PA_PTE_0         4
+#define VA_PTE_0         5
+#define PA_PTE_1         6
+#define VA_PTE_1         7
+#ifdef CONFIG_X86_PAE
+#define PA_PMD_0         8
+#define VA_PMD_0         9
+#define PA_PMD_1         10
+#define VA_PMD_1         11
+#define PAGES_NR         12
+#else
+#define PAGES_NR         8
+#endif
+
+#ifndef __ASSEMBLY__
+
 #include <asm/fixmap.h>
 #include <asm/ptrace.h>
 #include <asm/string.h>
@@ -72,5 +92,12 @@ static inline void crash_setup_regs(struct pt_regs *newregs,
                newregs->eip = (unsigned long)current_text_addr();
        }
 }
+asmlinkage NORET_TYPE void
+relocate_kernel(unsigned long indirection_page,
+		unsigned long control_page,
+		unsigned long start_address,
+		unsigned int has_pae) ATTRIB_NORET;
+
+#endif /* __ASSEMBLY__ */
 
 #endif /* _I386_KEXEC_H */
diff --git a/include/asm-i386/mach-es7000/mach_apic.h b/include/asm-i386/mach-es7000/mach_apic.h
index b5f3f0d0b2b..26333685a7f 100644
--- a/include/asm-i386/mach-es7000/mach_apic.h
+++ b/include/asm-i386/mach-es7000/mach_apic.h
@@ -123,9 +123,13 @@ extern u8 cpu_2_logical_apicid[];
 /* Mapping from cpu number to logical apicid */
 static inline int cpu_to_logical_apicid(int cpu)
 {
+#ifdef CONFIG_SMP
        if (cpu >= NR_CPUS)
 	       return BAD_APICID;
        return (int)cpu_2_logical_apicid[cpu];
+#else
+	return logical_smp_processor_id();
+#endif
 }
 
 static inline int mpc_apic_id(struct mpc_config_processor *m, struct mpc_config_translation *unused)
diff --git a/include/asm-i386/mach-summit/mach_apic.h b/include/asm-i386/mach-summit/mach_apic.h
index 9fd07328628..a81b0596159 100644
--- a/include/asm-i386/mach-summit/mach_apic.h
+++ b/include/asm-i386/mach-summit/mach_apic.h
@@ -46,10 +46,12 @@ extern u8 cpu_2_logical_apicid[];
 static inline void init_apic_ldr(void)
 {
 	unsigned long val, id;
-	int i, count;
-	u8 lid;
+	int count = 0;
 	u8 my_id = (u8)hard_smp_processor_id();
 	u8 my_cluster = (u8)apicid_cluster(my_id);
+#ifdef CONFIG_SMP
+	u8 lid;
+	int i;
 
 	/* Create logical APIC IDs by counting CPUs already in cluster. */
 	for (count = 0, i = NR_CPUS; --i >= 0; ) {
@@ -57,6 +59,7 @@ static inline void init_apic_ldr(void)
 		if (lid != BAD_APICID && apicid_cluster(lid) == my_cluster)
 			++count;
 	}
+#endif
 	/* We only have a 4 wide bitmap in cluster mode.  If a deranged
 	 * BIOS puts 5 CPUs in one APIC cluster, we're hosed. */
 	BUG_ON(count >= XAPIC_DEST_CPUS_SHIFT);
@@ -91,9 +94,13 @@ static inline int apicid_to_node(int logical_apicid)
 /* Mapping from cpu number to logical apicid */
 static inline int cpu_to_logical_apicid(int cpu)
 {
+#ifdef CONFIG_SMP
        if (cpu >= NR_CPUS)
 	       return BAD_APICID;
 	return (int)cpu_2_logical_apicid[cpu];
+#else
+	return logical_smp_processor_id();
+#endif
 }
 
 static inline int cpu_present_to_apicid(int mps_cpu)
diff --git a/include/asm-i386/mutex.h b/include/asm-i386/mutex.h
index 05a53853122..7a17d9e58ad 100644
--- a/include/asm-i386/mutex.h
+++ b/include/asm-i386/mutex.h
@@ -30,14 +30,10 @@ do {									\
 									\
 	__asm__ __volatile__(						\
 		LOCK_PREFIX "   decl (%%eax)	\n"			\
-			"   js 2f		\n"			\
+			"   jns 1f		\n"			\
+			"   call "#fail_fn"	\n"			\
 			"1:			\n"			\
 									\
-		LOCK_SECTION_START("")					\
-			"2: call "#fail_fn"	\n"			\
-			"   jmp 1b		\n"			\
-		LOCK_SECTION_END					\
-									\
 		:"=a" (dummy)						\
 		: "a" (count)						\
 		: "memory", "ecx", "edx");				\
@@ -86,14 +82,10 @@ do {									\
 									\
 	__asm__ __volatile__(						\
 		LOCK_PREFIX "   incl (%%eax)	\n"			\
-			"   jle 2f		\n"			\
+			"   jg	1f		\n"			\
+			"   call "#fail_fn"	\n"			\
 			"1:			\n"			\
 									\
-		LOCK_SECTION_START("")					\
-			"2: call "#fail_fn"	\n"			\
-			"   jmp 1b		\n"			\
-		LOCK_SECTION_END					\
-									\
 		:"=a" (dummy)						\
 		: "a" (count)						\
 		: "memory", "ecx", "edx");				\
diff --git a/include/asm-i386/nmi.h b/include/asm-i386/nmi.h
index 67d99479999..303bcd4592b 100644
--- a/include/asm-i386/nmi.h
+++ b/include/asm-i386/nmi.h
@@ -6,32 +6,29 @@
 
 #include <linux/pm.h>
 
-struct pt_regs;
-
-typedef int (*nmi_callback_t)(struct pt_regs * regs, int cpu);
-
 /**
- * set_nmi_callback
+ * do_nmi_callback
  *
- * Set a handler for an NMI. Only one handler may be
- * set. Return 1 if the NMI was handled.
+ * Check to see if a callback exists and execute it.  Return 1
+ * if the handler exists and was handled successfully.
  */
-void set_nmi_callback(nmi_callback_t callback);
-
-/**
- * unset_nmi_callback
- *
- * Remove the handler previously set.
- */
-void unset_nmi_callback(void);
-
-extern void setup_apic_nmi_watchdog (void);
-extern int reserve_lapic_nmi(void);
-extern void release_lapic_nmi(void);
+int do_nmi_callback(struct pt_regs *regs, int cpu);
+
+extern int nmi_watchdog_enabled;
+extern int avail_to_resrv_perfctr_nmi_bit(unsigned int);
+extern int avail_to_resrv_perfctr_nmi(unsigned int);
+extern int reserve_perfctr_nmi(unsigned int);
+extern void release_perfctr_nmi(unsigned int);
+extern int reserve_evntsel_nmi(unsigned int);
+extern void release_evntsel_nmi(unsigned int);
+
+extern void setup_apic_nmi_watchdog (void *);
+extern void stop_apic_nmi_watchdog (void *);
 extern void disable_timer_nmi_watchdog(void);
 extern void enable_timer_nmi_watchdog(void);
-extern void nmi_watchdog_tick (struct pt_regs * regs);
+extern int nmi_watchdog_tick (struct pt_regs * regs, unsigned reason);
 
+extern atomic_t nmi_active;
 extern unsigned int nmi_watchdog;
 #define NMI_DEFAULT     -1
 #define NMI_NONE	0
diff --git a/include/asm-i386/pgtable.h b/include/asm-i386/pgtable.h
index 0dc051a8078..541b3e23433 100644
--- a/include/asm-i386/pgtable.h
+++ b/include/asm-i386/pgtable.h
@@ -411,8 +411,6 @@ extern pte_t *lookup_address(unsigned long address);
  static inline int set_kernel_exec(unsigned long vaddr, int enable) { return 0;}
 #endif
 
-extern void noexec_setup(const char *str);
-
 #if defined(CONFIG_HIGHPTE)
 #define pte_offset_map(dir, address) \
 	((pte_t *)kmap_atomic(pmd_page(*(dir)),KM_PTE0) + pte_index(address))
diff --git a/include/asm-i386/ptrace.h b/include/asm-i386/ptrace.h
index 1910880fcd4..a4a0e5207db 100644
--- a/include/asm-i386/ptrace.h
+++ b/include/asm-i386/ptrace.h
@@ -27,6 +27,7 @@ struct pt_regs {
 #ifdef __KERNEL__
 
 #include <asm/vm86.h>
+#include <asm/segment.h>
 
 struct task_struct;
 extern void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, int error_code);
@@ -40,18 +41,14 @@ extern void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs, int erro
  */
 static inline int user_mode(struct pt_regs *regs)
 {
-	return (regs->xcs & 3) != 0;
+	return (regs->xcs & SEGMENT_RPL_MASK) == USER_RPL;
 }
 static inline int user_mode_vm(struct pt_regs *regs)
 {
-	return ((regs->xcs & 3) | (regs->eflags & VM_MASK)) != 0;
+	return ((regs->xcs & SEGMENT_RPL_MASK) | (regs->eflags & VM_MASK)) >= USER_RPL;
 }
 #define instruction_pointer(regs) ((regs)->eip)
-#if defined(CONFIG_SMP) && defined(CONFIG_FRAME_POINTER)
 extern unsigned long profile_pc(struct pt_regs *regs);
-#else
-#define profile_pc(regs) instruction_pointer(regs)
-#endif
 #endif /* __KERNEL__ */
 
 #endif
diff --git a/include/asm-i386/rwlock.h b/include/asm-i386/rwlock.h
index 87c069ccba0..c3e5db32fa4 100644
--- a/include/asm-i386/rwlock.h
+++ b/include/asm-i386/rwlock.h
@@ -20,52 +20,6 @@
 #define RW_LOCK_BIAS		 0x01000000
 #define RW_LOCK_BIAS_STR	"0x01000000"
 
-#define __build_read_lock_ptr(rw, helper)   \
-	asm volatile(LOCK_PREFIX " subl $1,(%0)\n\t" \
-			"jns 1f\n" \
-			"call " helper "\n\t" \
-			"1:\n" \
-			::"a" (rw) : "memory")
-
-#define __build_read_lock_const(rw, helper)   \
-	asm volatile(LOCK_PREFIX " subl $1,%0\n\t" \
-			"jns 1f\n" \
-			"pushl %%eax\n\t" \
-			"leal %0,%%eax\n\t" \
-			"call " helper "\n\t" \
-			"popl %%eax\n\t" \
-			"1:\n" \
-			:"+m" (*(volatile int *)rw) : : "memory")
-
-#define __build_read_lock(rw, helper)	do { \
-						if (__builtin_constant_p(rw)) \
-							__build_read_lock_const(rw, helper); \
-						else \
-							__build_read_lock_ptr(rw, helper); \
-					} while (0)
-
-#define __build_write_lock_ptr(rw, helper) \
-	asm volatile(LOCK_PREFIX " subl $" RW_LOCK_BIAS_STR ",(%0)\n\t" \
-			"jz 1f\n" \
-			"call " helper "\n\t" \
-			"1:\n" \
-			::"a" (rw) : "memory")
-
-#define __build_write_lock_const(rw, helper) \
-	asm volatile(LOCK_PREFIX " subl $" RW_LOCK_BIAS_STR ",%0\n\t" \
-			"jz 1f\n" \
-			"pushl %%eax\n\t" \
-			"leal %0,%%eax\n\t" \
-			"call " helper "\n\t" \
-			"popl %%eax\n\t" \
-			"1:\n" \
-			:"+m" (*(volatile int *)rw) : : "memory")
-
-#define __build_write_lock(rw, helper)	do { \
-						if (__builtin_constant_p(rw)) \
-							__build_write_lock_const(rw, helper); \
-						else \
-							__build_write_lock_ptr(rw, helper); \
-					} while (0)
+/* Code is in asm-i386/spinlock.h */
 
 #endif
diff --git a/include/asm-i386/rwsem.h b/include/asm-i386/rwsem.h
index 43113f5608e..bc598d6388e 100644
--- a/include/asm-i386/rwsem.h
+++ b/include/asm-i386/rwsem.h
@@ -99,17 +99,9 @@ static inline void __down_read(struct rw_semaphore *sem)
 	__asm__ __volatile__(
 		"# beginning down_read\n\t"
 LOCK_PREFIX	"  incl      (%%eax)\n\t" /* adds 0x00000001, returns the old value */
-		"  js        2f\n\t" /* jump if we weren't granted the lock */
+		"  jns        1f\n"
+		"  call call_rwsem_down_read_failed\n"
 		"1:\n\t"
-		LOCK_SECTION_START("")
-		"2:\n\t"
-		"  pushl     %%ecx\n\t"
-		"  pushl     %%edx\n\t"
-		"  call      rwsem_down_read_failed\n\t"
-		"  popl      %%edx\n\t"
-		"  popl      %%ecx\n\t"
-		"  jmp       1b\n"
-		LOCK_SECTION_END
 		"# ending down_read\n\t"
 		: "+m" (sem->count)
 		: "a" (sem)
@@ -151,15 +143,9 @@ static inline void __down_write_nested(struct rw_semaphore *sem, int subclass)
 		"# beginning down_write\n\t"
 LOCK_PREFIX	"  xadd      %%edx,(%%eax)\n\t" /* subtract 0x0000ffff, returns the old value */
 		"  testl     %%edx,%%edx\n\t" /* was the count 0 before? */
-		"  jnz       2f\n\t" /* jump if we weren't granted the lock */
-		"1:\n\t"
-		LOCK_SECTION_START("")
-		"2:\n\t"
-		"  pushl     %%ecx\n\t"
-		"  call      rwsem_down_write_failed\n\t"
-		"  popl      %%ecx\n\t"
-		"  jmp       1b\n"
-		LOCK_SECTION_END
+		"  jz        1f\n"
+		"  call call_rwsem_down_write_failed\n"
+		"1:\n"
 		"# ending down_write"
 		: "+m" (sem->count), "=d" (tmp)
 		: "a" (sem), "1" (tmp)
@@ -193,17 +179,9 @@ static inline void __up_read(struct rw_semaphore *sem)
 	__asm__ __volatile__(
 		"# beginning __up_read\n\t"
 LOCK_PREFIX	"  xadd      %%edx,(%%eax)\n\t" /* subtracts 1, returns the old value */
-		"  js        2f\n\t" /* jump if the lock is being waited upon */
-		"1:\n\t"
-		LOCK_SECTION_START("")
-		"2:\n\t"
-		"  decw      %%dx\n\t" /* do nothing if still outstanding active readers */
-		"  jnz       1b\n\t"
-		"  pushl     %%ecx\n\t"
-		"  call      rwsem_wake\n\t"
-		"  popl      %%ecx\n\t"
-		"  jmp       1b\n"
-		LOCK_SECTION_END
+		"  jns        1f\n\t"
+		"  call call_rwsem_wake\n"
+		"1:\n"
 		"# ending __up_read\n"
 		: "+m" (sem->count), "=d" (tmp)
 		: "a" (sem), "1" (tmp)
@@ -219,17 +197,9 @@ static inline void __up_write(struct rw_semaphore *sem)
 		"# beginning __up_write\n\t"
 		"  movl      %2,%%edx\n\t"
 LOCK_PREFIX	"  xaddl     %%edx,(%%eax)\n\t" /* tries to transition 0xffff0001 -> 0x00000000 */
-		"  jnz       2f\n\t" /* jump if the lock is being waited upon */
+		"  jz       1f\n"
+		"  call call_rwsem_wake\n"
 		"1:\n\t"
-		LOCK_SECTION_START("")
-		"2:\n\t"
-		"  decw      %%dx\n\t" /* did the active count reduce to 0? */
-		"  jnz       1b\n\t" /* jump back if not */
-		"  pushl     %%ecx\n\t"
-		"  call      rwsem_wake\n\t"
-		"  popl      %%ecx\n\t"
-		"  jmp       1b\n"
-		LOCK_SECTION_END
 		"# ending __up_write\n"
 		: "+m" (sem->count)
 		: "a" (sem), "i" (-RWSEM_ACTIVE_WRITE_BIAS)
@@ -244,17 +214,9 @@ static inline void __downgrade_write(struct rw_semaphore *sem)
 	__asm__ __volatile__(
 		"# beginning __downgrade_write\n\t"
 LOCK_PREFIX	"  addl      %2,(%%eax)\n\t" /* transitions 0xZZZZ0001 -> 0xYYYY0001 */
-		"  js        2f\n\t" /* jump if the lock is being waited upon */
+		"  jns       1f\n\t"
+		"  call call_rwsem_downgrade_wake\n"
 		"1:\n\t"
-		LOCK_SECTION_START("")
-		"2:\n\t"
-		"  pushl     %%ecx\n\t"
-		"  pushl     %%edx\n\t"
-		"  call      rwsem_downgrade_wake\n\t"
-		"  popl      %%edx\n\t"
-		"  popl      %%ecx\n\t"
-		"  jmp       1b\n"
-		LOCK_SECTION_END
 		"# ending __downgrade_write\n"
 		: "+m" (sem->count)
 		: "a" (sem), "i" (-RWSEM_WAITING_BIAS)
diff --git a/include/asm-i386/segment.h b/include/asm-i386/segment.h
index faf995307b9..b7ab59685ba 100644
--- a/include/asm-i386/segment.h
+++ b/include/asm-i386/segment.h
@@ -83,6 +83,11 @@
 
 #define GDT_SIZE (GDT_ENTRIES * 8)
 
+/* Matches __KERNEL_CS and __USER_CS (they must be 2 entries apart) */
+#define SEGMENT_IS_FLAT_CODE(x)  (((x) & 0xec) == GDT_ENTRY_KERNEL_CS * 8)
+/* Matches PNP_CS32 and PNP_CS16 (they must be consecutive) */
+#define SEGMENT_IS_PNP_CODE(x)   (((x) & 0xf4) == GDT_ENTRY_PNPBIOS_BASE * 8)
+
 /* Simple and small GDT entries for booting only */
 
 #define GDT_ENTRY_BOOT_CS		2
@@ -112,4 +117,16 @@
  */
 #define IDT_ENTRIES 256
 
+/* Bottom two bits of selector give the ring privilege level */
+#define SEGMENT_RPL_MASK	0x3
+/* Bit 2 is table indicator (LDT/GDT) */
+#define SEGMENT_TI_MASK		0x4
+
+/* User mode is privilege level 3 */
+#define USER_RPL		0x3
+/* LDT segment has TI set, GDT has it cleared */
+#define SEGMENT_LDT		0x4
+#define SEGMENT_GDT		0x0
+
+#define get_kernel_rpl()  0
 #endif
diff --git a/include/asm-i386/semaphore.h b/include/asm-i386/semaphore.h
index d51e800acf2..e63b6a68f04 100644
--- a/include/asm-i386/semaphore.h
+++ b/include/asm-i386/semaphore.h
@@ -100,13 +100,10 @@ static inline void down(struct semaphore * sem)
 	__asm__ __volatile__(
 		"# atomic down operation\n\t"
 		LOCK_PREFIX "decl %0\n\t"     /* --sem->count */
-		"js 2f\n"
-		"1:\n"
-		LOCK_SECTION_START("")
-		"2:\tlea %0,%%eax\n\t"
-		"call __down_failed\n\t"
-		"jmp 1b\n"
-		LOCK_SECTION_END
+		"jns 2f\n"
+		"\tlea %0,%%eax\n\t"
+		"call __down_failed\n"
+		"2:"
 		:"+m" (sem->count)
 		:
 		:"memory","ax");
@@ -123,15 +120,12 @@ static inline int down_interruptible(struct semaphore * sem)
 	might_sleep();
 	__asm__ __volatile__(
 		"# atomic interruptible down operation\n\t"
+		"xorl %0,%0\n\t"
 		LOCK_PREFIX "decl %1\n\t"     /* --sem->count */
-		"js 2f\n\t"
-		"xorl %0,%0\n"
-		"1:\n"
-		LOCK_SECTION_START("")
-		"2:\tlea %1,%%eax\n\t"
-		"call __down_failed_interruptible\n\t"
-		"jmp 1b\n"
-		LOCK_SECTION_END
+		"jns 2f\n\t"
+		"lea %1,%%eax\n\t"
+		"call __down_failed_interruptible\n"
+		"2:"
 		:"=a" (result), "+m" (sem->count)
 		:
 		:"memory");
@@ -148,15 +142,12 @@ static inline int down_trylock(struct semaphore * sem)
 
 	__asm__ __volatile__(
 		"# atomic interruptible down operation\n\t"
+		"xorl %0,%0\n\t"
 		LOCK_PREFIX "decl %1\n\t"     /* --sem->count */
-		"js 2f\n\t"
-		"xorl %0,%0\n"
-		"1:\n"
-		LOCK_SECTION_START("")
-		"2:\tlea %1,%%eax\n\t"
+		"jns 2f\n\t"
+		"lea %1,%%eax\n\t"
 		"call __down_failed_trylock\n\t"
-		"jmp 1b\n"
-		LOCK_SECTION_END
+		"2:\n"
 		:"=a" (result), "+m" (sem->count)
 		:
 		:"memory");
@@ -166,22 +157,16 @@ static inline int down_trylock(struct semaphore * sem)
 /*
  * Note! This is subtle. We jump to wake people up only if
  * the semaphore was negative (== somebody was waiting on it).
- * The default case (no contention) will result in NO
- * jumps for both down() and up().
  */
 static inline void up(struct semaphore * sem)
 {
 	__asm__ __volatile__(
 		"# atomic up operation\n\t"
 		LOCK_PREFIX "incl %0\n\t"     /* ++sem->count */
-		"jle 2f\n"
-		"1:\n"
-		LOCK_SECTION_START("")
-		"2:\tlea %0,%%eax\n\t"
-		"call __up_wakeup\n\t"
-		"jmp 1b\n"
-		LOCK_SECTION_END
-		".subsection 0\n"
+		"jg 1f\n\t"
+		"lea %0,%%eax\n\t"
+		"call __up_wakeup\n"
+		"1:"
 		:"+m" (sem->count)
 		:
 		:"memory","ax");
diff --git a/include/asm-i386/smp.h b/include/asm-i386/smp.h
index 142d10e34ad..32ac8c91d5c 100644
--- a/include/asm-i386/smp.h
+++ b/include/asm-i386/smp.h
@@ -80,17 +80,12 @@ static inline int hard_smp_processor_id(void)
 	return GET_APIC_ID(*(unsigned long *)(APIC_BASE+APIC_ID));
 }
 #endif
-
-static __inline int logical_smp_processor_id(void)
-{
-	/* we don't want to mark this access volatile - bad code generation */
-	return GET_APIC_LOGICAL_ID(*(unsigned long *)(APIC_BASE+APIC_LDR));
-}
-
 #endif
 
 extern int __cpu_disable(void);
 extern void __cpu_die(unsigned int cpu);
+extern unsigned int num_processors;
+
 #endif /* !__ASSEMBLY__ */
 
 #else /* CONFIG_SMP */
@@ -100,4 +95,15 @@ extern void __cpu_die(unsigned int cpu);
 #define NO_PROC_ID		0xFF		/* No processor magic marker */
 
 #endif
+
+#ifndef __ASSEMBLY__
+#ifdef CONFIG_X86_LOCAL_APIC
+static __inline int logical_smp_processor_id(void)
+{
+	/* we don't want to mark this access volatile - bad code generation */
+	return GET_APIC_LOGICAL_ID(*(unsigned long *)(APIC_BASE+APIC_LDR));
+}
+#endif
+#endif
+
 #endif
diff --git a/include/asm-i386/spinlock.h b/include/asm-i386/spinlock.h
index d1020363c41..b0b3043f05e 100644
--- a/include/asm-i386/spinlock.h
+++ b/include/asm-i386/spinlock.h
@@ -4,8 +4,12 @@
 #include <asm/atomic.h>
 #include <asm/rwlock.h>
 #include <asm/page.h>
+#include <asm/processor.h>
 #include <linux/compiler.h>
 
+#define CLI_STRING	"cli"
+#define STI_STRING	"sti"
+
 /*
  * Your basic SMP spinlocks, allowing only a single CPU anywhere
  *
@@ -17,67 +21,64 @@
  * (the type definitions are in asm/spinlock_types.h)
  */
 
-#define __raw_spin_is_locked(x) \
-		(*(volatile signed char *)(&(x)->slock) <= 0)
-
-#define __raw_spin_lock_string \
-	"\n1:\t" \
-	LOCK_PREFIX " ; decb %0\n\t" \
-	"jns 3f\n" \
-	"2:\t" \
-	"rep;nop\n\t" \
-	"cmpb $0,%0\n\t" \
-	"jle 2b\n\t" \
-	"jmp 1b\n" \
-	"3:\n\t"
-
-/*
- * NOTE: there's an irqs-on section here, which normally would have to be
- * irq-traced, but on CONFIG_TRACE_IRQFLAGS we never use
- * __raw_spin_lock_string_flags().
- */
-#define __raw_spin_lock_string_flags \
-	"\n1:\t" \
-	LOCK_PREFIX " ; decb %0\n\t" \
-	"jns 5f\n" \
-	"2:\t" \
-	"testl $0x200, %1\n\t" \
-	"jz 4f\n\t" \
-	"sti\n" \
-	"3:\t" \
-	"rep;nop\n\t" \
-	"cmpb $0, %0\n\t" \
-	"jle 3b\n\t" \
-	"cli\n\t" \
-	"jmp 1b\n" \
-	"4:\t" \
-	"rep;nop\n\t" \
-	"cmpb $0, %0\n\t" \
-	"jg 1b\n\t" \
-	"jmp 4b\n" \
-	"5:\n\t"
+static inline int __raw_spin_is_locked(raw_spinlock_t *x)
+{
+	return *(volatile signed char *)(&(x)->slock) <= 0;
+}
 
 static inline void __raw_spin_lock(raw_spinlock_t *lock)
 {
-	asm(__raw_spin_lock_string : "+m" (lock->slock) : : "memory");
+	asm volatile("\n1:\t"
+		     LOCK_PREFIX " ; decb %0\n\t"
+		     "jns 3f\n"
+		     "2:\t"
+		     "rep;nop\n\t"
+		     "cmpb $0,%0\n\t"
+		     "jle 2b\n\t"
+		     "jmp 1b\n"
+		     "3:\n\t"
+		     : "+m" (lock->slock) : : "memory");
 }
 
 /*
  * It is easier for the lock validator if interrupts are not re-enabled
  * in the middle of a lock-acquire. This is a performance feature anyway
  * so we turn it off:
+ *
+ * NOTE: there's an irqs-on section here, which normally would have to be
+ * irq-traced, but on CONFIG_TRACE_IRQFLAGS we never use this variant.
  */
 #ifndef CONFIG_PROVE_LOCKING
 static inline void __raw_spin_lock_flags(raw_spinlock_t *lock, unsigned long flags)
 {
-	asm(__raw_spin_lock_string_flags : "+m" (lock->slock) : "r" (flags) : "memory");
+	asm volatile(
+		"\n1:\t"
+		LOCK_PREFIX " ; decb %0\n\t"
+		"jns 5f\n"
+		"2:\t"
+		"testl $0x200, %1\n\t"
+		"jz 4f\n\t"
+		STI_STRING "\n"
+		"3:\t"
+		"rep;nop\n\t"
+		"cmpb $0, %0\n\t"
+		"jle 3b\n\t"
+		CLI_STRING "\n\t"
+		"jmp 1b\n"
+		"4:\t"
+		"rep;nop\n\t"
+		"cmpb $0, %0\n\t"
+		"jg 1b\n\t"
+		"jmp 4b\n"
+		"5:\n\t"
+		: "+m" (lock->slock) : "r" (flags) : "memory");
 }
 #endif
 
 static inline int __raw_spin_trylock(raw_spinlock_t *lock)
 {
 	char oldval;
-	__asm__ __volatile__(
+	asm volatile(
 		"xchgb %b0,%1"
 		:"=q" (oldval), "+m" (lock->slock)
 		:"0" (0) : "memory");
@@ -93,38 +94,29 @@ static inline int __raw_spin_trylock(raw_spinlock_t *lock)
 
 #if !defined(CONFIG_X86_OOSTORE) && !defined(CONFIG_X86_PPRO_FENCE)
 
-#define __raw_spin_unlock_string \
-	"movb $1,%0" \
-		:"+m" (lock->slock) : : "memory"
-
-
 static inline void __raw_spin_unlock(raw_spinlock_t *lock)
 {
-	__asm__ __volatile__(
-		__raw_spin_unlock_string
-	);
+	asm volatile("movb $1,%0" : "+m" (lock->slock) :: "memory");
 }
 
 #else
 
-#define __raw_spin_unlock_string \
-	"xchgb %b0, %1" \
-		:"=q" (oldval), "+m" (lock->slock) \
-		:"0" (oldval) : "memory"
-
 static inline void __raw_spin_unlock(raw_spinlock_t *lock)
 {
 	char oldval = 1;
 
-	__asm__ __volatile__(
-		__raw_spin_unlock_string
-	);
+	asm volatile("xchgb %b0, %1"
+		     : "=q" (oldval), "+m" (lock->slock)
+		     : "0" (oldval) : "memory");
 }
 
 #endif
 
-#define __raw_spin_unlock_wait(lock) \
-	do { while (__raw_spin_is_locked(lock)) cpu_relax(); } while (0)
+static inline void __raw_spin_unlock_wait(raw_spinlock_t *lock)
+{
+	while (__raw_spin_is_locked(lock))
+		cpu_relax();
+}
 
 /*
  * Read-write spinlocks, allowing multiple readers
@@ -151,22 +143,36 @@ static inline void __raw_spin_unlock(raw_spinlock_t *lock)
  * read_can_lock - would read_trylock() succeed?
  * @lock: the rwlock in question.
  */
-#define __raw_read_can_lock(x)		((int)(x)->lock > 0)
+static inline int __raw_read_can_lock(raw_rwlock_t *x)
+{
+	return (int)(x)->lock > 0;
+}
 
 /**
  * write_can_lock - would write_trylock() succeed?
  * @lock: the rwlock in question.
  */
-#define __raw_write_can_lock(x)		((x)->lock == RW_LOCK_BIAS)
+static inline int __raw_write_can_lock(raw_rwlock_t *x)
+{
+	return (x)->lock == RW_LOCK_BIAS;
+}
 
 static inline void __raw_read_lock(raw_rwlock_t *rw)
 {
-	__build_read_lock(rw, "__read_lock_failed");
+	asm volatile(LOCK_PREFIX " subl $1,(%0)\n\t"
+		     "jns 1f\n"
+		     "call __read_lock_failed\n\t"
+		     "1:\n"
+		     ::"a" (rw) : "memory");
 }
 
 static inline void __raw_write_lock(raw_rwlock_t *rw)
 {
-	__build_write_lock(rw, "__write_lock_failed");
+	asm volatile(LOCK_PREFIX " subl $" RW_LOCK_BIAS_STR ",(%0)\n\t"
+		     "jz 1f\n"
+		     "call __write_lock_failed\n\t"
+		     "1:\n"
+		     ::"a" (rw) : "memory");
 }
 
 static inline int __raw_read_trylock(raw_rwlock_t *lock)
diff --git a/include/asm-i386/stacktrace.h b/include/asm-i386/stacktrace.h
new file mode 100644
index 00000000000..7d1f6a5cbfc
--- /dev/null
+++ b/include/asm-i386/stacktrace.h
@@ -0,0 +1 @@
+#include <asm-x86_64/stacktrace.h>
diff --git a/include/asm-i386/therm_throt.h b/include/asm-i386/therm_throt.h
new file mode 100644
index 00000000000..399bf6026b1
--- /dev/null
+++ b/include/asm-i386/therm_throt.h
@@ -0,0 +1,9 @@
+#ifndef __ASM_I386_THERM_THROT_H__
+#define __ASM_I386_THERM_THROT_H__ 1
+
+#include <asm/atomic.h>
+
+extern atomic_t therm_throt_en;
+int therm_throt_process(int curr);
+
+#endif /* __ASM_I386_THERM_THROT_H__ */
diff --git a/include/asm-i386/tlbflush.h b/include/asm-i386/tlbflush.h
index d57ca5c540b..360648b0f2b 100644
--- a/include/asm-i386/tlbflush.h
+++ b/include/asm-i386/tlbflush.h
@@ -36,8 +36,6 @@
 			: "memory");					\
 	} while (0)
 
-extern unsigned long pgkern_mask;
-
 # define __flush_tlb_all()						\
 	do {								\
 		if (cpu_has_pge)					\
@@ -49,7 +47,7 @@ extern unsigned long pgkern_mask;
 #define cpu_has_invlpg	(boot_cpu_data.x86 > 3)
 
 #define __flush_tlb_single(addr) \
-	__asm__ __volatile__("invlpg %0": :"m" (*(char *) addr))
+	__asm__ __volatile__("invlpg (%0)" ::"r" (addr) : "memory")
 
 #ifdef CONFIG_X86_INVLPG
 # define __flush_tlb_one(addr) __flush_tlb_single(addr)
diff --git a/include/asm-i386/tsc.h b/include/asm-i386/tsc.h
index 97b828ce31e..c13933185c1 100644
--- a/include/asm-i386/tsc.h
+++ b/include/asm-i386/tsc.h
@@ -6,7 +6,6 @@
 #ifndef _ASM_i386_TSC_H
 #define _ASM_i386_TSC_H
 
-#include <linux/config.h>
 #include <asm/processor.h>
 
 /*
diff --git a/include/asm-i386/unistd.h b/include/asm-i386/unistd.h
index fc1c8ddae14..565d0897b20 100644
--- a/include/asm-i386/unistd.h
+++ b/include/asm-i386/unistd.h
@@ -323,10 +323,11 @@
 #define __NR_tee		315
 #define __NR_vmsplice		316
 #define __NR_move_pages		317
+#define __NR_getcpu		318
 
 #ifdef __KERNEL__
 
-#define NR_syscalls 318
+#define NR_syscalls 319
 
 /*
  * user-visible error numbers are in the range -1 - -128: see
diff --git a/include/asm-i386/unwind.h b/include/asm-i386/unwind.h
index 4c1a0b96856..5031d693b89 100644
--- a/include/asm-i386/unwind.h
+++ b/include/asm-i386/unwind.h
@@ -18,6 +18,7 @@ struct unwind_frame_info
 {
 	struct pt_regs regs;
 	struct task_struct *task;
+	unsigned call_frame:1;
 };
 
 #define UNW_PC(frame)        (frame)->regs.eip
@@ -28,6 +29,8 @@ struct unwind_frame_info
 #define FRAME_LINK_OFFSET    0
 #define STACK_BOTTOM(tsk)    STACK_LIMIT((tsk)->thread.esp0)
 #define STACK_TOP(tsk)       ((tsk)->thread.esp0)
+#else
+#define UNW_FP(frame) ((void)(frame), 0)
 #endif
 #define STACK_LIMIT(ptr)     (((ptr) - 1) & ~(THREAD_SIZE - 1))
 
@@ -42,6 +45,10 @@ struct unwind_frame_info
 	PTREGS_INFO(edi), \
 	PTREGS_INFO(eip)
 
+#define UNW_DEFAULT_RA(raItem, dataAlign) \
+	((raItem).where == Memory && \
+	 !((raItem).value * (dataAlign) + 4))
+
 static inline void arch_unw_init_frame_info(struct unwind_frame_info *info,
                                             /*const*/ struct pt_regs *regs)
 {
@@ -88,6 +95,7 @@ static inline int arch_unw_user_mode(const struct unwind_frame_info *info)
 
 #define UNW_PC(frame) ((void)(frame), 0)
 #define UNW_SP(frame) ((void)(frame), 0)
+#define UNW_FP(frame) ((void)(frame), 0)
 
 static inline int arch_unw_user_mode(const void *info)
 {