drm: merge in Linus mainline

29 files changed, 324 insertions, 140 deletions

diff --git a/arch/i386/Kconfig b/arch/i386/Kconfig
index dbf90ad6eac3..6004bb0795e0 100644
--- a/arch/i386/Kconfig
+++ b/arch/i386/Kconfig
@@ -699,7 +699,7 @@ depends on PM && !X86_VISWS
 
 config APM
 	tristate "APM (Advanced Power Management) BIOS support"
-	depends on PM
+	depends on PM && PM_LEGACY
 	---help---
 	  APM is a BIOS specification for saving power using several different
 	  techniques. This is mostly useful for battery powered laptops with
diff --git a/arch/i386/kernel/acpi/boot.c b/arch/i386/kernel/acpi/boot.c
index b66c13c0cc0f..447fa9e33ffb 100644
--- a/arch/i386/kernel/acpi/boot.c
+++ b/arch/i386/kernel/acpi/boot.c
@@ -39,17 +39,14 @@
 
 #ifdef	CONFIG_X86_64
 
-static inline void acpi_madt_oem_check(char *oem_id, char *oem_table_id)
-{
-}
 extern void __init clustered_apic_check(void);
-static inline int ioapic_setup_disabled(void)
-{
-	return 0;
-}
 
+extern int gsi_irq_sharing(int gsi);
 #include <asm/proto.h>
 
+static inline int acpi_madt_oem_check(char *oem_id, char *oem_table_id) { return 0; }
+
+
 #else				/* X86 */
 
 #ifdef	CONFIG_X86_LOCAL_APIC
@@ -57,6 +54,8 @@ static inline int ioapic_setup_disabled(void)
 #include <mach_mpparse.h>
 #endif				/* CONFIG_X86_LOCAL_APIC */
 
+static inline int gsi_irq_sharing(int gsi) { return gsi; }
+
 #endif				/* X86 */
 
 #define BAD_MADT_ENTRY(entry, end) (					    \
@@ -249,9 +248,7 @@ acpi_parse_lapic(acpi_table_entry_header * header, const unsigned long end)
 
 	acpi_table_print_madt_entry(header);
 
-	/* no utility in registering a disabled processor */
-	if (processor->flags.enabled == 0)
-		return 0;
+	/* Register even disabled CPUs for cpu hotplug */
 
 	x86_acpiid_to_apicid[processor->acpi_id] = processor->id;
 
@@ -459,7 +456,7 @@ int acpi_gsi_to_irq(u32 gsi, unsigned int *irq)
 		*irq = IO_APIC_VECTOR(gsi);
 	else
 #endif
-		*irq = gsi;
+		*irq = gsi_irq_sharing(gsi);
 	return 0;
 }
 
@@ -543,7 +540,7 @@ acpi_scan_rsdp(unsigned long start, unsigned long length)
 	 * RSDP signature.
 	 */
 	for (offset = 0; offset < length; offset += 16) {
-		if (strncmp((char *)(start + offset), "RSD PTR ", sig_len))
+		if (strncmp((char *)(phys_to_virt(start) + offset), "RSD PTR ", sig_len))
 			continue;
 		return (start + offset);
 	}
@@ -641,6 +638,13 @@ static int __init acpi_parse_fadt(unsigned long phys, unsigned long size)
 			return 0;
 
 		pmtmr_ioport = fadt->xpm_tmr_blk.address;
+		/*
+		 * "X" fields are optional extensions to the original V1.0
+		 * fields, so we must selectively expand V1.0 fields if the
+		 * corresponding X field is zero.
+	 	 */
+		if (!pmtmr_ioport)
+			pmtmr_ioport = fadt->V1_pm_tmr_blk;
 	} else {
 		/* FADT rev. 1 */
 		pmtmr_ioport = fadt->V1_pm_tmr_blk;
diff --git a/arch/i386/kernel/apm.c b/arch/i386/kernel/apm.c
index 003548b8735f..1e60acbed3c1 100644
--- a/arch/i386/kernel/apm.c
+++ b/arch/i386/kernel/apm.c
@@ -218,6 +218,7 @@
 #include <linux/time.h>
 #include <linux/sched.h>
 #include <linux/pm.h>
+#include <linux/pm_legacy.h>
 #include <linux/device.h>
 #include <linux/kernel.h>
 #include <linux/smp.h>
diff --git a/arch/i386/kernel/cpu/amd.c b/arch/i386/kernel/cpu/amd.c
index 53a1681cd964..e344ef88cfcd 100644
--- a/arch/i386/kernel/cpu/amd.c
+++ b/arch/i386/kernel/cpu/amd.c
@@ -206,9 +206,9 @@ static void __init init_amd(struct cpuinfo_x86 *c)
 	display_cacheinfo(c);
 
 	if (cpuid_eax(0x80000000) >= 0x80000008) {
-		c->x86_num_cores = (cpuid_ecx(0x80000008) & 0xff) + 1;
-		if (c->x86_num_cores & (c->x86_num_cores - 1))
-			c->x86_num_cores = 1;
+		c->x86_max_cores = (cpuid_ecx(0x80000008) & 0xff) + 1;
+		if (c->x86_max_cores & (c->x86_max_cores - 1))
+			c->x86_max_cores = 1;
 	}
 
 #ifdef CONFIG_X86_HT
@@ -217,15 +217,15 @@ static void __init init_amd(struct cpuinfo_x86 *c)
 	 * distingush the cores.  Assumes number of cores is a power
 	 * of two.
 	 */
-	if (c->x86_num_cores > 1) {
+	if (c->x86_max_cores > 1) {
 		int cpu = smp_processor_id();
 		unsigned bits = 0;
-		while ((1 << bits) < c->x86_num_cores)
+		while ((1 << bits) < c->x86_max_cores)
 			bits++;
 		cpu_core_id[cpu] = phys_proc_id[cpu] & ((1<<bits)-1);
 		phys_proc_id[cpu] >>= bits;
 		printk(KERN_INFO "CPU %d(%d) -> Core %d\n",
-		       cpu, c->x86_num_cores, cpu_core_id[cpu]);
+		       cpu, c->x86_max_cores, cpu_core_id[cpu]);
 	}
 #endif
 }
diff --git a/arch/i386/kernel/cpu/common.c b/arch/i386/kernel/cpu/common.c
index c145fb30002e..31e344b26bae 100644
--- a/arch/i386/kernel/cpu/common.c
+++ b/arch/i386/kernel/cpu/common.c
@@ -231,10 +231,10 @@ static void __init early_cpu_detect(void)
 		cpuid(0x00000001, &tfms, &misc, &junk, &cap0);
 		c->x86 = (tfms >> 8) & 15;
 		c->x86_model = (tfms >> 4) & 15;
-		if (c->x86 == 0xf) {
+		if (c->x86 == 0xf)
 			c->x86 += (tfms >> 20) & 0xff;
+		if (c->x86 >= 0x6)
 			c->x86_model += ((tfms >> 16) & 0xF) << 4;
-		}
 		c->x86_mask = tfms & 15;
 		if (cap0 & (1<<19))
 			c->x86_cache_alignment = ((misc >> 8) & 0xff) * 8;
@@ -333,7 +333,7 @@ void __devinit identify_cpu(struct cpuinfo_x86 *c)
 	c->x86_model = c->x86_mask = 0;	/* So far unknown... */
 	c->x86_vendor_id[0] = '\0'; /* Unset */
 	c->x86_model_id[0] = '\0';  /* Unset */
-	c->x86_num_cores = 1;
+	c->x86_max_cores = 1;
 	memset(&c->x86_capability, 0, sizeof c->x86_capability);
 
 	if (!have_cpuid_p()) {
@@ -443,52 +443,44 @@ void __devinit identify_cpu(struct cpuinfo_x86 *c)
 void __devinit detect_ht(struct cpuinfo_x86 *c)
 {
 	u32 	eax, ebx, ecx, edx;
-	int 	index_msb, tmp;
+	int 	index_msb, core_bits;
 	int 	cpu = smp_processor_id();
 
+	cpuid(1, &eax, &ebx, &ecx, &edx);
+
+	c->apicid = phys_pkg_id((ebx >> 24) & 0xFF, 0);
+
 	if (!cpu_has(c, X86_FEATURE_HT) || cpu_has(c, X86_FEATURE_CMP_LEGACY))
 		return;
 
-	cpuid(1, &eax, &ebx, &ecx, &edx);
 	smp_num_siblings = (ebx & 0xff0000) >> 16;
 
 	if (smp_num_siblings == 1) {
 		printk(KERN_INFO  "CPU: Hyper-Threading is disabled\n");
 	} else if (smp_num_siblings > 1 ) {
-		index_msb = 31;
 
 		if (smp_num_siblings > NR_CPUS) {
 			printk(KERN_WARNING "CPU: Unsupported number of the siblings %d", smp_num_siblings);
 			smp_num_siblings = 1;
 			return;
 		}
-		tmp = smp_num_siblings;
-		while ((tmp & 0x80000000 ) == 0) {
-			tmp <<=1 ;
-			index_msb--;
-		}
-		if (smp_num_siblings & (smp_num_siblings - 1))
-			index_msb++;
+
+		index_msb = get_count_order(smp_num_siblings);
 		phys_proc_id[cpu] = phys_pkg_id((ebx >> 24) & 0xFF, index_msb);
 
 		printk(KERN_INFO  "CPU: Physical Processor ID: %d\n",
 		       phys_proc_id[cpu]);
 
-		smp_num_siblings = smp_num_siblings / c->x86_num_cores;
+		smp_num_siblings = smp_num_siblings / c->x86_max_cores;
 
-		tmp = smp_num_siblings;
-		index_msb = 31;
-		while ((tmp & 0x80000000) == 0) {
-			tmp <<=1 ;
-			index_msb--;
-		}
+		index_msb = get_count_order(smp_num_siblings) ;
 
-		if (smp_num_siblings & (smp_num_siblings - 1))
-			index_msb++;
+		core_bits = get_count_order(c->x86_max_cores);
 
-		cpu_core_id[cpu] = phys_pkg_id((ebx >> 24) & 0xFF, index_msb);
+		cpu_core_id[cpu] = phys_pkg_id((ebx >> 24) & 0xFF, index_msb) &
+					       ((1 << core_bits) - 1);
 
-		if (c->x86_num_cores > 1)
+		if (c->x86_max_cores > 1)
 			printk(KERN_INFO  "CPU: Processor Core ID: %d\n",
 			       cpu_core_id[cpu]);
 	}
diff --git a/arch/i386/kernel/cpu/intel.c b/arch/i386/kernel/cpu/intel.c
index 43601de0f633..5e2da704f0fa 100644
--- a/arch/i386/kernel/cpu/intel.c
+++ b/arch/i386/kernel/cpu/intel.c
@@ -6,6 +6,7 @@
 #include <linux/bitops.h>
 #include <linux/smp.h>
 #include <linux/thread_info.h>
+#include <linux/module.h>
 
 #include <asm/processor.h>
 #include <asm/msr.h>
@@ -157,7 +158,7 @@ static void __devinit init_intel(struct cpuinfo_x86 *c)
 	if ( p )
 		strcpy(c->x86_model_id, p);
 	
-	c->x86_num_cores = num_cpu_cores(c);
+	c->x86_max_cores = num_cpu_cores(c);
 
 	detect_ht(c);
 
@@ -264,5 +265,52 @@ __init int intel_cpu_init(void)
 	return 0;
 }
 
+#ifndef CONFIG_X86_CMPXCHG
+unsigned long cmpxchg_386_u8(volatile void *ptr, u8 old, u8 new)
+{
+	u8 prev;
+	unsigned long flags;
+
+	/* Poor man's cmpxchg for 386. Unsuitable for SMP */
+	local_irq_save(flags);
+	prev = *(u8 *)ptr;
+	if (prev == old)
+		*(u8 *)ptr = new;
+	local_irq_restore(flags);
+	return prev;
+}
+EXPORT_SYMBOL(cmpxchg_386_u8);
+
+unsigned long cmpxchg_386_u16(volatile void *ptr, u16 old, u16 new)
+{
+	u16 prev;
+	unsigned long flags;
+
+	/* Poor man's cmpxchg for 386. Unsuitable for SMP */
+	local_irq_save(flags);
+	prev = *(u16 *)ptr;
+	if (prev == old)
+		*(u16 *)ptr = new;
+	local_irq_restore(flags);
+	return prev;
+}
+EXPORT_SYMBOL(cmpxchg_386_u16);
+
+unsigned long cmpxchg_386_u32(volatile void *ptr, u32 old, u32 new)
+{
+	u32 prev;
+	unsigned long flags;
+
+	/* Poor man's cmpxchg for 386. Unsuitable for SMP */
+	local_irq_save(flags);
+	prev = *(u32 *)ptr;
+	if (prev == old)
+		*(u32 *)ptr = new;
+	local_irq_restore(flags);
+	return prev;
+}
+EXPORT_SYMBOL(cmpxchg_386_u32);
+#endif
+
 // arch_initcall(intel_cpu_init);
 
diff --git a/arch/i386/kernel/cpu/intel_cacheinfo.c b/arch/i386/kernel/cpu/intel_cacheinfo.c
index 4dc42a189ae5..fbfd374aa336 100644
--- a/arch/i386/kernel/cpu/intel_cacheinfo.c
+++ b/arch/i386/kernel/cpu/intel_cacheinfo.c
@@ -293,29 +293,45 @@ static struct _cpuid4_info *cpuid4_info[NR_CPUS];
 #ifdef CONFIG_SMP
 static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index)
 {
-	struct _cpuid4_info	*this_leaf;
+	struct _cpuid4_info	*this_leaf, *sibling_leaf;
 	unsigned long num_threads_sharing;
-#ifdef CONFIG_X86_HT
-	struct cpuinfo_x86 *c = cpu_data + cpu;
-#endif
+	int index_msb, i;
+	struct cpuinfo_x86 *c = cpu_data;
 
 	this_leaf = CPUID4_INFO_IDX(cpu, index);
 	num_threads_sharing = 1 + this_leaf->eax.split.num_threads_sharing;
 
 	if (num_threads_sharing == 1)
 		cpu_set(cpu, this_leaf->shared_cpu_map);
-#ifdef CONFIG_X86_HT
-	else if (num_threads_sharing == smp_num_siblings)
-		this_leaf->shared_cpu_map = cpu_sibling_map[cpu];
-	else if (num_threads_sharing == (c->x86_num_cores * smp_num_siblings))
-		this_leaf->shared_cpu_map = cpu_core_map[cpu];
-	else
-		printk(KERN_DEBUG "Number of CPUs sharing cache didn't match "
-				"any known set of CPUs\n");
-#endif
+	else {
+		index_msb = get_count_order(num_threads_sharing);
+
+		for_each_online_cpu(i) {
+			if (c[i].apicid >> index_msb ==
+			    c[cpu].apicid >> index_msb) {
+				cpu_set(i, this_leaf->shared_cpu_map);
+				if (i != cpu && cpuid4_info[i])  {
+					sibling_leaf = CPUID4_INFO_IDX(i, index);
+					cpu_set(cpu, sibling_leaf->shared_cpu_map);
+				}
+			}
+		}
+	}
+}
+static void __devinit cache_remove_shared_cpu_map(unsigned int cpu, int index)
+{
+	struct _cpuid4_info	*this_leaf, *sibling_leaf;
+	int sibling;
+
+	this_leaf = CPUID4_INFO_IDX(cpu, index);
+	for_each_cpu_mask(sibling, this_leaf->shared_cpu_map) {
+		sibling_leaf = CPUID4_INFO_IDX(sibling, index);	
+		cpu_clear(cpu, sibling_leaf->shared_cpu_map);
+	}
 }
 #else
 static void __init cache_shared_cpu_map_setup(unsigned int cpu, int index) {}
+static void __init cache_remove_shared_cpu_map(unsigned int cpu, int index) {}
 #endif
 
 static void free_cache_attributes(unsigned int cpu)
@@ -574,8 +590,10 @@ static void __cpuexit cache_remove_dev(struct sys_device * sys_dev)
 	unsigned int cpu = sys_dev->id;
 	unsigned long i;
 
-	for (i = 0; i < num_cache_leaves; i++)
+	for (i = 0; i < num_cache_leaves; i++) {
+		cache_remove_shared_cpu_map(cpu, i);
 		kobject_unregister(&(INDEX_KOBJECT_PTR(cpu,i)->kobj));
+	}
 	kobject_unregister(cache_kobject[cpu]);
 	cpuid4_cache_sysfs_exit(cpu);
 	return;
diff --git a/arch/i386/kernel/cpu/mtrr/main.c b/arch/i386/kernel/cpu/mtrr/main.c
index dd4ebd6af7e4..1e9db198c440 100644
--- a/arch/i386/kernel/cpu/mtrr/main.c
+++ b/arch/i386/kernel/cpu/mtrr/main.c
@@ -626,6 +626,14 @@ void __init mtrr_bp_init(void)
 		if (cpuid_eax(0x80000000) >= 0x80000008) {
 			u32 phys_addr;
 			phys_addr = cpuid_eax(0x80000008) & 0xff;
+			/* CPUID workaround for Intel 0F33/0F34 CPU */
+			if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
+			    boot_cpu_data.x86 == 0xF &&
+			    boot_cpu_data.x86_model == 0x3 &&
+			    (boot_cpu_data.x86_mask == 0x3 ||
+			     boot_cpu_data.x86_mask == 0x4))
+				phys_addr = 36;
+
 			size_or_mask = ~((1 << (phys_addr - PAGE_SHIFT)) - 1);
 			size_and_mask = ~size_or_mask & 0xfff00000;
 		} else if (boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR &&
diff --git a/arch/i386/kernel/cpu/proc.c b/arch/i386/kernel/cpu/proc.c
index 41b871ecf4b3..e7921315ae9d 100644
--- a/arch/i386/kernel/cpu/proc.c
+++ b/arch/i386/kernel/cpu/proc.c
@@ -94,12 +94,11 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 	if (c->x86_cache_size >= 0)
 		seq_printf(m, "cache size\t: %d KB\n", c->x86_cache_size);
 #ifdef CONFIG_X86_HT
-	if (c->x86_num_cores * smp_num_siblings > 1) {
+	if (c->x86_max_cores * smp_num_siblings > 1) {
 		seq_printf(m, "physical id\t: %d\n", phys_proc_id[n]);
-		seq_printf(m, "siblings\t: %d\n",
-				c->x86_num_cores * smp_num_siblings);
+		seq_printf(m, "siblings\t: %d\n", cpus_weight(cpu_core_map[n]));
 		seq_printf(m, "core id\t\t: %d\n", cpu_core_id[n]);
-		seq_printf(m, "cpu cores\t: %d\n", c->x86_num_cores);
+		seq_printf(m, "cpu cores\t: %d\n", c->booted_cores);
 	}
 #endif
 	
diff --git a/arch/i386/kernel/crash.c b/arch/i386/kernel/crash.c
index af809ccf5fbe..0248e084017c 100644
--- a/arch/i386/kernel/crash.c
+++ b/arch/i386/kernel/crash.c
@@ -21,6 +21,7 @@
 #include <asm/hardirq.h>
 #include <asm/nmi.h>
 #include <asm/hw_irq.h>
+#include <asm/apic.h>
 #include <mach_ipi.h>
 
 
@@ -147,6 +148,7 @@ static int crash_nmi_callback(struct pt_regs *regs, int cpu)
 		regs = &fixed_regs;
 	}
 	crash_save_this_cpu(regs, cpu);
+	disable_local_APIC();
 	atomic_dec(&waiting_for_crash_ipi);
 	/* Assume hlt works */
 	halt();
@@ -186,6 +188,7 @@ static void nmi_shootdown_cpus(void)
 	}
 
 	/* Leave the nmi callback set */
+	disable_local_APIC();
 }
 #else
 static void nmi_shootdown_cpus(void)
@@ -210,5 +213,9 @@ void machine_crash_shutdown(struct pt_regs *regs)
 	/* Make a note of crashing cpu. Will be used in NMI callback.*/
 	crashing_cpu = smp_processor_id();
 	nmi_shootdown_cpus();
+	lapic_shutdown();
+#if defined(CONFIG_X86_IO_APIC)
+	disable_IO_APIC();
+#endif
 	crash_save_self(regs);
 }
diff --git a/arch/i386/kernel/entry.S b/arch/i386/kernel/entry.S
index 9e24f7b207ee..e50b93155249 100644
--- a/arch/i386/kernel/entry.S
+++ b/arch/i386/kernel/entry.S
@@ -560,11 +560,10 @@ nmi_stack_fixup:
 nmi_debug_stack_check:
 	cmpw $__KERNEL_CS,16(%esp)
 	jne nmi_stack_correct
-	cmpl $debug - 1,(%esp)
-	jle nmi_stack_correct
+	cmpl $debug,(%esp)
+	jb nmi_stack_correct
 	cmpl $debug_esp_fix_insn,(%esp)
-	jle nmi_debug_stack_fixup
-nmi_debug_stack_fixup:
+	ja nmi_stack_correct
 	FIX_STACK(24,nmi_stack_correct, 1)
 	jmp nmi_stack_correct
 
diff --git a/arch/i386/kernel/io_apic.c b/arch/i386/kernel/io_apic.c
index cc5d7ac5b2e7..22c8675c79f4 100644
--- a/arch/i386/kernel/io_apic.c
+++ b/arch/i386/kernel/io_apic.c
@@ -2009,7 +2009,7 @@ static void ack_edge_ioapic_vector(unsigned int vector)
 {
 	int irq = vector_to_irq(vector);
 
-	move_irq(vector);
+	move_native_irq(vector);
 	ack_edge_ioapic_irq(irq);
 }
 
@@ -2024,7 +2024,7 @@ static void end_level_ioapic_vector (unsigned int vector)
 {
 	int irq = vector_to_irq(vector);
 
-	move_irq(vector);
+	move_native_irq(vector);
 	end_level_ioapic_irq(irq);
 }
 
diff --git a/arch/i386/kernel/kprobes.c b/arch/i386/kernel/kprobes.c
index 32b0c24ab9a6..19edcd526ba4 100644
--- a/arch/i386/kernel/kprobes.c
+++ b/arch/i386/kernel/kprobes.c
@@ -191,7 +191,7 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 			 */
 			save_previous_kprobe(kcb);
 			set_current_kprobe(p, regs, kcb);
-			p->nmissed++;
+			kprobes_inc_nmissed_count(p);
 			prepare_singlestep(p, regs);
 			kcb->kprobe_status = KPROBE_REENTER;
 			return 1;
diff --git a/arch/i386/kernel/mpparse.c b/arch/i386/kernel/mpparse.c
index 8f767d9aa45d..1ca5269b1e86 100644
--- a/arch/i386/kernel/mpparse.c
+++ b/arch/i386/kernel/mpparse.c
@@ -220,8 +220,9 @@ static void __devinit MP_processor_info (struct mpc_config_processor *m)
 	num_processors++;
 
 	if ((num_processors > 8) &&
-	    APIC_XAPIC(ver) &&
-	    (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL))
+	    ((APIC_XAPIC(ver) &&
+	     (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)) ||
+	     (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)))
 		def_to_bigsmp = 1;
 	else
 		def_to_bigsmp = 0;
diff --git a/arch/i386/kernel/process.c b/arch/i386/kernel/process.c
index 1cb261f225d5..2333aead0563 100644
--- a/arch/i386/kernel/process.c
+++ b/arch/i386/kernel/process.c
@@ -393,13 +393,6 @@ void flush_thread(void)
 {
 	struct task_struct *tsk = current;
 
-	/*
-	 * Remove function-return probe instances associated with this task
-	 * and put them back on the free list. Do not insert an exit probe for
-	 * this function, it will be disabled by kprobe_flush_task if you do.
-	 */
-	kprobe_flush_task(tsk);
-
 	memset(tsk->thread.debugreg, 0, sizeof(unsigned long)*8);
 	memset(tsk->thread.tls_array, 0, sizeof(tsk->thread.tls_array));	
 	/*
@@ -561,7 +554,9 @@ int dump_task_regs(struct task_struct *tsk, elf_gregset_t *regs)
 	struct pt_regs ptregs;
 	
 	ptregs = *(struct pt_regs *)
-		((unsigned long)tsk->thread_info+THREAD_SIZE - sizeof(ptregs));
+		((unsigned long)tsk->thread_info +
+		/* see comments in copy_thread() about -8 */
+		THREAD_SIZE - sizeof(ptregs) - 8);
 	ptregs.xcs &= 0xffff;
 	ptregs.xds &= 0xffff;
 	ptregs.xes &= 0xffff;
diff --git a/arch/i386/kernel/reboot.c b/arch/i386/kernel/reboot.c
index 350ea6680f63..2afe0f8d555a 100644
--- a/arch/i386/kernel/reboot.c
+++ b/arch/i386/kernel/reboot.c
@@ -111,6 +111,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "PowerEdge 2400"),
 		},
 	},
+	{	/* Handle problems with rebooting on HP nc6120 */
+		.callback = set_bios_reboot,
+		.ident = "HP Compaq nc6120",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Hewlett-Packard"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "HP Compaq nc6120"),
+		},
+	},
 	{ }
 };
 
diff --git a/arch/i386/kernel/smpboot.c b/arch/i386/kernel/smpboot.c
index bc5a9d97466b..9ed449af8e9f 100644
--- a/arch/i386/kernel/smpboot.c
+++ b/arch/i386/kernel/smpboot.c
@@ -72,9 +72,11 @@ int phys_proc_id[NR_CPUS] __read_mostly = {[0 ... NR_CPUS-1] = BAD_APICID};
 /* Core ID of each logical CPU */
 int cpu_core_id[NR_CPUS] __read_mostly = {[0 ... NR_CPUS-1] = BAD_APICID};
 
+/* representing HT siblings of each logical CPU */
 cpumask_t cpu_sibling_map[NR_CPUS] __read_mostly;
 EXPORT_SYMBOL(cpu_sibling_map);
 
+/* representing HT and core siblings of each logical CPU */
 cpumask_t cpu_core_map[NR_CPUS] __read_mostly;
 EXPORT_SYMBOL(cpu_core_map);
 
@@ -442,35 +444,60 @@ static void __devinit smp_callin(void)
 
 static int cpucount;
 
+/* representing cpus for which sibling maps can be computed */
+static cpumask_t cpu_sibling_setup_map;
+
 static inline void
 set_cpu_sibling_map(int cpu)
 {
 	int i;
+	struct cpuinfo_x86 *c = cpu_data;
+
+	cpu_set(cpu, cpu_sibling_setup_map);
 
 	if (smp_num_siblings > 1) {
-		for (i = 0; i < NR_CPUS; i++) {
-			if (!cpu_isset(i, cpu_callout_map))
-				continue;
-			if (cpu_core_id[cpu] == cpu_core_id[i]) {
+		for_each_cpu_mask(i, cpu_sibling_setup_map) {
+			if (phys_proc_id[cpu] == phys_proc_id[i] &&
+			    cpu_core_id[cpu] == cpu_core_id[i]) {
 				cpu_set(i, cpu_sibling_map[cpu]);
 				cpu_set(cpu, cpu_sibling_map[i]);
+				cpu_set(i, cpu_core_map[cpu]);
+				cpu_set(cpu, cpu_core_map[i]);
 			}
 		}
 	} else {
 		cpu_set(cpu, cpu_sibling_map[cpu]);
 	}
 
-	if (current_cpu_data.x86_num_cores > 1) {
-		for (i = 0; i < NR_CPUS; i++) {
-			if (!cpu_isset(i, cpu_callout_map))
-				continue;
-			if (phys_proc_id[cpu] == phys_proc_id[i]) {
-				cpu_set(i, cpu_core_map[cpu]);
-				cpu_set(cpu, cpu_core_map[i]);
-			}
-		}
-	} else {
+	if (current_cpu_data.x86_max_cores == 1) {
 		cpu_core_map[cpu] = cpu_sibling_map[cpu];
+		c[cpu].booted_cores = 1;
+		return;
+	}
+
+	for_each_cpu_mask(i, cpu_sibling_setup_map) {
+		if (phys_proc_id[cpu] == phys_proc_id[i]) {
+			cpu_set(i, cpu_core_map[cpu]);
+			cpu_set(cpu, cpu_core_map[i]);
+			/*
+			 *  Does this new cpu bringup a new core?
+			 */
+			if (cpus_weight(cpu_sibling_map[cpu]) == 1) {
+				/*
+				 * for each core in package, increment
+				 * the booted_cores for this new cpu
+				 */
+				if (first_cpu(cpu_sibling_map[i]) == i)
+					c[cpu].booted_cores++;
+				/*
+				 * increment the core count for all
+				 * the other cpus in this package
+				 */
+				if (i != cpu)
+					c[i].booted_cores++;
+			} else if (i != cpu && !c[cpu].booted_cores)
+				c[cpu].booted_cores = c[i].booted_cores;
+		}
 	}
 }
 
@@ -1095,11 +1122,8 @@ static void __init smp_boot_cpus(unsigned int max_cpus)
 
 	current_thread_info()->cpu = 0;
 	smp_tune_scheduling();
-	cpus_clear(cpu_sibling_map[0]);
-	cpu_set(0, cpu_sibling_map[0]);
 
-	cpus_clear(cpu_core_map[0]);
-	cpu_set(0, cpu_core_map[0]);
+	set_cpu_sibling_map(0);
 
 	/*
 	 * If we couldn't find an SMP configuration at boot time,
@@ -1278,15 +1302,24 @@ static void
 remove_siblinginfo(int cpu)
 {
 	int sibling;
+	struct cpuinfo_x86 *c = cpu_data;
 
+	for_each_cpu_mask(sibling, cpu_core_map[cpu]) {
+		cpu_clear(cpu, cpu_core_map[sibling]);
+		/*
+		 * last thread sibling in this cpu core going down
+		 */
+		if (cpus_weight(cpu_sibling_map[cpu]) == 1)
+			c[sibling].booted_cores--;
+	}
+			
 	for_each_cpu_mask(sibling, cpu_sibling_map[cpu])
 		cpu_clear(cpu, cpu_sibling_map[sibling]);
-	for_each_cpu_mask(sibling, cpu_core_map[cpu])
-		cpu_clear(cpu, cpu_core_map[sibling]);
 	cpus_clear(cpu_sibling_map[cpu]);
 	cpus_clear(cpu_core_map[cpu]);
 	phys_proc_id[cpu] = BAD_APICID;
 	cpu_core_id[cpu] = BAD_APICID;
+	cpu_clear(cpu, cpu_sibling_setup_map);
 }
 
 int __cpu_disable(void)
@@ -1305,8 +1338,7 @@ int __cpu_disable(void)
 	if (cpu == 0)
 		return -EBUSY;
 
-	/* We enable the timer again on the exit path of the death loop */
-	disable_APIC_timer();
+	clear_local_APIC();
 	/* Allow any queued timer interrupts to get serviced */
 	local_irq_enable();
 	mdelay(1);
diff --git a/arch/i386/kernel/srat.c b/arch/i386/kernel/srat.c
index 8de658db8146..52b3ed5d2cb5 100644
--- a/arch/i386/kernel/srat.c
+++ b/arch/i386/kernel/srat.c
@@ -137,8 +137,8 @@ static void __init parse_memory_affinity_structure (char *sratp)
 		 "enabled and removable" : "enabled" ) );
 }
 
-#if MAX_NR_ZONES != 3
-#error "MAX_NR_ZONES != 3, chunk_to_zone requires review"
+#if MAX_NR_ZONES != 4
+#error "MAX_NR_ZONES != 4, chunk_to_zone requires review"
 #endif
 /* Take a chunk of pages from page frame cstart to cend and count the number
  * of pages in each zone, returned via zones[].
diff --git a/arch/i386/kernel/timers/timer_pit.c b/arch/i386/kernel/timers/timer_pit.c
index e42e46d35159..b9b6bd56b9ba 100644
--- a/arch/i386/kernel/timers/timer_pit.c
+++ b/arch/i386/kernel/timers/timer_pit.c
@@ -25,8 +25,9 @@ static int __init init_pit(char* override)
 {
  	/* check clock override */
  	if (override[0] && strncmp(override,"pit",3))
- 		printk(KERN_ERR "Warning: clock= override failed. Defaulting to PIT\n");
- 
+ 		printk(KERN_ERR "Warning: clock= override failed. Defaulting "
+				"to PIT\n");
+ 	init_cpu_khz();
 	count_p = LATCH;
 	return 0;
 }
diff --git a/arch/i386/kernel/traps.c b/arch/i386/kernel/traps.c
index c34d1bfc5161..f0dffa03fbba 100644
--- a/arch/i386/kernel/traps.c
+++ b/arch/i386/kernel/traps.c
@@ -650,13 +650,6 @@ fastcall void do_nmi(struct pt_regs * regs, long error_code)
 
 	cpu = smp_processor_id();
 
-#ifdef CONFIG_HOTPLUG_CPU
-	if (!cpu_online(cpu)) {
-		nmi_exit();
-		return;
-	}
-#endif
-
 	++nmi_count(cpu);
 
 	if (!rcu_dereference(nmi_callback)(regs, cpu))
diff --git a/arch/i386/mm/init.c b/arch/i386/mm/init.c
index 542d9298da5e..06e26f006238 100644
--- a/arch/i386/mm/init.c
+++ b/arch/i386/mm/init.c
@@ -28,6 +28,7 @@
 #include <linux/proc_fs.h>
 #include <linux/efi.h>
 #include <linux/memory_hotplug.h>
+#include <linux/initrd.h>
 
 #include <asm/processor.h>
 #include <asm/system.h>
@@ -267,7 +268,7 @@ static void __init permanent_kmaps_init(pgd_t *pgd_base)
 	pkmap_page_table = pte;	
 }
 
-void __devinit free_new_highpage(struct page *page)
+static void __devinit free_new_highpage(struct page *page)
 {
 	set_page_count(page, 1);
 	__free_page(page);
diff --git a/arch/i386/mm/ioremap.c b/arch/i386/mm/ioremap.c
index 5d09de8d1c6b..247fde76aaed 100644
--- a/arch/i386/mm/ioremap.c
+++ b/arch/i386/mm/ioremap.c
@@ -223,9 +223,15 @@ void __iomem *ioremap_nocache (unsigned long phys_addr, unsigned long size)
 }
 EXPORT_SYMBOL(ioremap_nocache);
 
+/**
+ * iounmap - Free a IO remapping
+ * @addr: virtual address from ioremap_*
+ *
+ * Caller must ensure there is only one unmapping for the same pointer.
+ */
 void iounmap(volatile void __iomem *addr)
 {
-	struct vm_struct *p;
+	struct vm_struct *p, *o;
 
 	if ((void __force *)addr <= high_memory)
 		return;
@@ -239,22 +245,37 @@ void iounmap(volatile void __iomem *addr)
 			addr < phys_to_virt(ISA_END_ADDRESS))
 		return;
 
-	write_lock(&vmlist_lock);
-	p = __remove_vm_area((void *)(PAGE_MASK & (unsigned long __force)addr));
-	if (!p) { 
-		printk(KERN_WARNING "iounmap: bad address %p\n", addr);
+	addr = (volatile void __iomem *)(PAGE_MASK & (unsigned long __force)addr);
+
+	/* Use the vm area unlocked, assuming the caller
+	   ensures there isn't another iounmap for the same address
+	   in parallel. Reuse of the virtual address is prevented by
+	   leaving it in the global lists until we're done with it.
+	   cpa takes care of the direct mappings. */
+	read_lock(&vmlist_lock);
+	for (p = vmlist; p; p = p->next) {
+		if (p->addr == addr)
+			break;
+	}
+	read_unlock(&vmlist_lock);
+
+	if (!p) {
+		printk("iounmap: bad address %p\n", addr);
 		dump_stack();
-		goto out_unlock;
+		return;
 	}
 
+	/* Reset the direct mapping. Can block */
 	if ((p->flags >> 20) && p->phys_addr < virt_to_phys(high_memory) - 1) {
 		change_page_attr(virt_to_page(__va(p->phys_addr)),
 				 p->size >> PAGE_SHIFT,
 				 PAGE_KERNEL);
 		global_flush_tlb();
 	} 
-out_unlock:
-	write_unlock(&vmlist_lock);
+
+	/* Finally remove it */
+	o = remove_vm_area((void *)addr);
+	BUG_ON(p != o || o == NULL);
 	kfree(p); 
 }
 EXPORT_SYMBOL(iounmap);
diff --git a/arch/i386/pci/Makefile b/arch/i386/pci/Makefile
index ead6122dd06d..5461d4d5ea1e 100644
--- a/arch/i386/pci/Makefile
+++ b/arch/i386/pci/Makefile
@@ -1,7 +1,7 @@
 obj-y				:= i386.o
 
 obj-$(CONFIG_PCI_BIOS)		+= pcbios.o
-obj-$(CONFIG_PCI_MMCONFIG)	+= mmconfig.o
+obj-$(CONFIG_PCI_MMCONFIG)	+= mmconfig.o direct.o
 obj-$(CONFIG_PCI_DIRECT)	+= direct.o
 
 pci-y				:= fixup.o
diff --git a/arch/i386/pci/common.c b/arch/i386/pci/common.c
index c96bea14b98f..f6bc48da4d2a 100644
--- a/arch/i386/pci/common.c
+++ b/arch/i386/pci/common.c
@@ -132,7 +132,7 @@ struct pci_bus * __devinit pcibios_scan_root(int busnum)
 		}
 	}
 
-	printk("PCI: Probing PCI hardware (bus %02x)\n", busnum);
+	printk(KERN_DEBUG "PCI: Probing PCI hardware (bus %02x)\n", busnum);
 
 	return pci_scan_bus_parented(NULL, busnum, &pci_root_ops, NULL);
 }
@@ -144,7 +144,7 @@ static int __init pcibios_init(void)
 	struct cpuinfo_x86 *c = &boot_cpu_data;
 
 	if (!raw_pci_ops) {
-		printk("PCI: System does not support PCI\n");
+		printk(KERN_WARNING "PCI: System does not support PCI\n");
 		return 0;
 	}
 
diff --git a/arch/i386/pci/direct.c b/arch/i386/pci/direct.c
index 30b7e9b4f6a2..e3ac502bf2fb 100644
--- a/arch/i386/pci/direct.c
+++ b/arch/i386/pci/direct.c
@@ -13,7 +13,7 @@
 #define PCI_CONF1_ADDRESS(bus, devfn, reg) \
 	(0x80000000 | (bus << 16) | (devfn << 8) | (reg & ~3))
 
-static int pci_conf1_read(unsigned int seg, unsigned int bus,
+int pci_conf1_read(unsigned int seg, unsigned int bus,
 			  unsigned int devfn, int reg, int len, u32 *value)
 {
 	unsigned long flags;
@@ -42,7 +42,7 @@ static int pci_conf1_read(unsigned int seg, unsigned int bus,
 	return 0;
 }
 
-static int pci_conf1_write(unsigned int seg, unsigned int bus,
+int pci_conf1_write(unsigned int seg, unsigned int bus,
 			   unsigned int devfn, int reg, int len, u32 value)
 {
 	unsigned long flags;
@@ -201,7 +201,7 @@ static int __init pci_sanity_check(struct pci_raw_ops *o)
 			return 1;
 	}
 
-	DBG("PCI: Sanity check failed\n");
+	DBG(KERN_WARNING "PCI: Sanity check failed\n");
 	return 0;
 }
 
diff --git a/arch/i386/pci/fixup.c b/arch/i386/pci/fixup.c
index 3984226a8b98..eeb1b1f2d548 100644
--- a/arch/i386/pci/fixup.c
+++ b/arch/i386/pci/fixup.c
@@ -433,9 +433,8 @@ static void __devinit pci_post_fixup_toshiba_ohci1394(struct pci_dev *dev)
 		return; /* only applies to certain Toshibas (so far) */
 
 	/* Restore config space on Toshiba laptops */
-	mdelay(10);
 	pci_write_config_word(dev, PCI_CACHE_LINE_SIZE, toshiba_line_size);
-	pci_write_config_word(dev, PCI_INTERRUPT_LINE, dev->irq);
+	pci_read_config_byte(dev, PCI_INTERRUPT_LINE, (u8 *)&dev->irq);
 	pci_write_config_dword(dev, PCI_BASE_ADDRESS_0,
 			       pci_resource_start(dev, 0));
 	pci_write_config_dword(dev, PCI_BASE_ADDRESS_1,
diff --git a/arch/i386/pci/i386.c b/arch/i386/pci/i386.c
index 6d6338500c3c..ed2c8c899bd3 100644
--- a/arch/i386/pci/i386.c
+++ b/arch/i386/pci/i386.c
@@ -221,6 +221,11 @@ int pcibios_enable_resources(struct pci_dev *dev, int mask)
 			continue;
 
 		r = &dev->resource[idx];
+		if (!(r->flags & (IORESOURCE_IO | IORESOURCE_MEM)))
+			continue;
+		if ((idx == PCI_ROM_RESOURCE) &&
+				(!(r->flags & IORESOURCE_ROM_ENABLE)))
+			continue;
 		if (!r->start && r->end) {
 			printk(KERN_ERR "PCI: Device %s not available because of resource collisions\n", pci_name(dev));
 			return -EINVAL;
@@ -230,8 +235,6 @@ int pcibios_enable_resources(struct pci_dev *dev, int mask)
 		if (r->flags & IORESOURCE_MEM)
 			cmd |= PCI_COMMAND_MEMORY;
 	}
-	if (dev->resource[PCI_ROM_RESOURCE].start)
-		cmd |= PCI_COMMAND_MEMORY;
 	if (cmd != old_cmd) {
 		printk("PCI: Enabling device %s (%04x -> %04x)\n", pci_name(dev), old_cmd, cmd);
 		pci_write_config_word(dev, PCI_COMMAND, cmd);
diff --git a/arch/i386/pci/mmconfig.c b/arch/i386/pci/mmconfig.c
index dfbf80cff834..4bb4d4b0f73a 100644
--- a/arch/i386/pci/mmconfig.c
+++ b/arch/i386/pci/mmconfig.c
@@ -19,21 +19,25 @@
 /* The base address of the last MMCONFIG device accessed */
 static u32 mmcfg_last_accessed_device;
 
+static DECLARE_BITMAP(fallback_slots, 32);
+
 /*
  * Functions for accessing PCI configuration space with MMCONFIG accesses
  */
-static u32 get_base_addr(unsigned int seg, int bus)
+static u32 get_base_addr(unsigned int seg, int bus, unsigned devfn)
 {
 	int cfg_num = -1;
 	struct acpi_table_mcfg_config *cfg;
 
+	if (seg == 0 && bus == 0 &&
+	    test_bit(PCI_SLOT(devfn), fallback_slots))
+		return 0;
+
 	while (1) {
 		++cfg_num;
 		if (cfg_num >= pci_mmcfg_config_num) {
-			/* something bad is going on, no cfg table is found. */
-			/* so we fall back to the old way we used to do this */
-			/* and just rely on the first entry to be correct. */
-			return pci_mmcfg_config[0].base_address;
+			/* Not found - fallback to type 1 */
+			return 0;
 		}
 		cfg = &pci_mmcfg_config[cfg_num];
 		if (cfg->pci_segment_group_number != seg)
@@ -44,9 +48,9 @@ static u32 get_base_addr(unsigned int seg, int bus)
 	}
 }
 
-static inline void pci_exp_set_dev_base(unsigned int seg, int bus, int devfn)
+static inline void pci_exp_set_dev_base(unsigned int base, int bus, int devfn)
 {
-	u32 dev_base = get_base_addr(seg, bus) | (bus << 20) | (devfn << 12);
+	u32 dev_base = base | (bus << 20) | (devfn << 12);
 	if (dev_base != mmcfg_last_accessed_device) {
 		mmcfg_last_accessed_device = dev_base;
 		set_fixmap_nocache(FIX_PCIE_MCFG, dev_base);
@@ -57,13 +61,18 @@ static int pci_mmcfg_read(unsigned int seg, unsigned int bus,
 			  unsigned int devfn, int reg, int len, u32 *value)
 {
 	unsigned long flags;
+	u32 base;
 
 	if (!value || (bus > 255) || (devfn > 255) || (reg > 4095))
 		return -EINVAL;
 
+	base = get_base_addr(seg, bus, devfn);
+	if (!base)
+		return pci_conf1_read(seg,bus,devfn,reg,len,value);
+
 	spin_lock_irqsave(&pci_config_lock, flags);
 
-	pci_exp_set_dev_base(seg, bus, devfn);
+	pci_exp_set_dev_base(base, bus, devfn);
 
 	switch (len) {
 	case 1:
@@ -86,13 +95,18 @@ static int pci_mmcfg_write(unsigned int seg, unsigned int bus,
 			   unsigned int devfn, int reg, int len, u32 value)
 {
 	unsigned long flags;
+	u32 base;
 
 	if ((bus > 255) || (devfn > 255) || (reg > 4095)) 
 		return -EINVAL;
 
+	base = get_base_addr(seg, bus, devfn);
+	if (!base)
+		return pci_conf1_write(seg,bus,devfn,reg,len,value);
+
 	spin_lock_irqsave(&pci_config_lock, flags);
 
-	pci_exp_set_dev_base(seg, bus, devfn);
+	pci_exp_set_dev_base(base, bus, devfn);
 
 	switch (len) {
 	case 1:
@@ -116,6 +130,37 @@ static struct pci_raw_ops pci_mmcfg = {
 	.write =	pci_mmcfg_write,
 };
 
+/* K8 systems have some devices (typically in the builtin northbridge)
+   that are only accessible using type1
+   Normally this can be expressed in the MCFG by not listing them
+   and assigning suitable _SEGs, but this isn't implemented in some BIOS.
+   Instead try to discover all devices on bus 0 that are unreachable using MM
+   and fallback for them.
+   We only do this for bus 0/seg 0 */
+static __init void unreachable_devices(void)
+{
+	int i;
+	unsigned long flags;
+
+	for (i = 0; i < 32; i++) {
+		u32 val1;
+		u32 addr;
+
+		pci_conf1_read(0, 0, PCI_DEVFN(i, 0), 0, 4, &val1);
+		if (val1 == 0xffffffff)
+			continue;
+
+		/* Locking probably not needed, but safer */
+		spin_lock_irqsave(&pci_config_lock, flags);
+		addr = get_base_addr(0, 0, PCI_DEVFN(i, 0));
+		if (addr != 0)
+			pci_exp_set_dev_base(addr, 0, PCI_DEVFN(i, 0));
+		if (addr == 0 || readl((u32 __iomem *)mmcfg_virt_addr) != val1)
+			set_bit(i, fallback_slots);
+		spin_unlock_irqrestore(&pci_config_lock, flags);
+	}
+}
+
 static int __init pci_mmcfg_init(void)
 {
 	if ((pci_probe & PCI_PROBE_MMCONF) == 0)
@@ -131,6 +176,8 @@ static int __init pci_mmcfg_init(void)
 	raw_pci_ops = &pci_mmcfg;
 	pci_probe = (pci_probe & ~PCI_PROBE_MASK) | PCI_PROBE_MMCONF;
 
+	unreachable_devices();
+
  out:
 	return 0;
 }
diff --git a/arch/i386/pci/pci.h b/arch/i386/pci/pci.h
index 127d53ad16be..f550781ec310 100644
--- a/arch/i386/pci/pci.h
+++ b/arch/i386/pci/pci.h
@@ -74,3 +74,10 @@ extern spinlock_t pci_config_lock;
 
 extern int (*pcibios_enable_irq)(struct pci_dev *dev);
 extern void (*pcibios_disable_irq)(struct pci_dev *dev);
+
+extern int pci_conf1_write(unsigned int seg, unsigned int bus,
+			   unsigned int devfn, int reg, int len, u32 value);
+extern int pci_conf1_read(unsigned int seg, unsigned int bus,
+			  unsigned int devfn, int reg, int len, u32 *value);
+
+