Merge x86-64 update from Andi

9 files changed, 129 insertions, 80 deletions

diff --git a/arch/i386/kernel/acpi/boot.c b/arch/i386/kernel/acpi/boot.c
index b66c13c0cc0f..f36677241ecd 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) (					    \
@@ -459,7 +458,7 @@ 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 +542,7 @@ 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);
 	}
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 c28d26fb5f24..5e2da704f0fa 100644
--- a/arch/i386/kernel/cpu/intel.c
+++ b/arch/i386/kernel/cpu/intel.c
@@ -158,7 +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);
 
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/smpboot.c b/arch/i386/kernel/smpboot.c
index bc5a9d97466b..d16520da4550 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)
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[].