Merge branch 'x86-cpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'x86-cpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (22 commits)
  x86: Fix code patching for paravirt-alternatives on 486
  x86, msr: change msr-reg.o to obj-y, and export its symbols
  x86: Use hard_smp_processor_id() to get apic id for AMD K8 cpus
  x86, sched: Workaround broken sched domain creation for AMD Magny-Cours
  x86, mcheck: Use correct cpumask for shared bank4
  x86, cacheinfo: Fixup L3 cache information for AMD multi-node processors
  x86: Fix CPU llc_shared_map information for AMD Magny-Cours
  x86, msr: Fix msr-reg.S compilation with gas 2.16.1, on 32-bit too
  x86: Move kernel_fpu_using to irq_fpu_usable in asm/i387.h
  x86, msr: fix msr-reg.S compilation with gas 2.16.1
  x86, msr: Export the register-setting MSR functions via /dev/*/msr
  x86, msr: Create _on_cpu helpers for {rw,wr}msr_safe_regs()
  x86, msr: Have the _safe MSR functions return -EIO, not -EFAULT
  x86, msr: CFI annotations, cleanups for msr-reg.S
  x86, asm: Make _ASM_EXTABLE() usable from assembly code
  x86, asm: Add 32-bit versions of the combined CFI macros
  x86, AMD: Disable wrongly set X86_FEATURE_LAHF_LM CPUID bit
  x86, msr: Rewrite AMD rd/wrmsr variants
  x86, msr: Add rd/wrmsr interfaces with preset registers
  x86: add specific support for Intel Atom architecture
  ...

4 files changed, 104 insertions, 18 deletions

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 83b217c..22a47c8 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -253,6 +253,64 @@ static int __cpuinit nearby_node(int apicid)
 #endif
 
 /*
+ * Fixup core topology information for AMD multi-node processors.
+ * Assumption 1: Number of cores in each internal node is the same.
+ * Assumption 2: Mixed systems with both single-node and dual-node
+ *               processors are not supported.
+ */
+#ifdef CONFIG_X86_HT
+static void __cpuinit amd_fixup_dcm(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_PCI
+	u32 t, cpn;
+	u8 n, n_id;
+	int cpu = smp_processor_id();
+
+	/* fixup topology information only once for a core */
+	if (cpu_has(c, X86_FEATURE_AMD_DCM))
+		return;
+
+	/* check for multi-node processor on boot cpu */
+	t = read_pci_config(0, 24, 3, 0xe8);
+	if (!(t & (1 << 29)))
+		return;
+
+	set_cpu_cap(c, X86_FEATURE_AMD_DCM);
+
+	/* cores per node: each internal node has half the number of cores */
+	cpn = c->x86_max_cores >> 1;
+
+	/* even-numbered NB_id of this dual-node processor */
+	n = c->phys_proc_id << 1;
+
+	/*
+	 * determine internal node id and assign cores fifty-fifty to
+	 * each node of the dual-node processor
+	 */
+	t = read_pci_config(0, 24 + n, 3, 0xe8);
+	n = (t>>30) & 0x3;
+	if (n == 0) {
+		if (c->cpu_core_id < cpn)
+			n_id = 0;
+		else
+			n_id = 1;
+	} else {
+		if (c->cpu_core_id < cpn)
+			n_id = 1;
+		else
+			n_id = 0;
+	}
+
+	/* compute entire NodeID, use llc_shared_map to store sibling info */
+	per_cpu(cpu_llc_id, cpu) = (c->phys_proc_id << 1) + n_id;
+
+	/* fixup core id to be in range from 0 to cpn */
+	c->cpu_core_id = c->cpu_core_id % cpn;
+#endif
+}
+#endif
+
+/*
  * On a AMD dual core setup the lower bits of the APIC id distingush the cores.
  * Assumes number of cores is a power of two.
  */
@@ -269,6 +327,9 @@ static void __cpuinit amd_detect_cmp(struct cpuinfo_x86 *c)
 	c->phys_proc_id = c->initial_apicid >> bits;
 	/* use socket ID also for last level cache */
 	per_cpu(cpu_llc_id, cpu) = c->phys_proc_id;
+	/* fixup topology information on multi-node processors */
+	if ((c->x86 == 0x10) && (c->x86_model == 9))
+		amd_fixup_dcm(c);
 #endif
 }
 
@@ -277,9 +338,10 @@ static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c)
 #if defined(CONFIG_NUMA) && defined(CONFIG_X86_64)
 	int cpu = smp_processor_id();
 	int node;
-	unsigned apicid = cpu_has_apic ? hard_smp_processor_id() : c->apicid;
+	unsigned apicid = c->apicid;
+
+	node = per_cpu(cpu_llc_id, cpu);
 
-	node = c->phys_proc_id;
 	if (apicid_to_node[apicid] != NUMA_NO_NODE)
 		node = apicid_to_node[apicid];
 	if (!node_online(node)) {
@@ -406,12 +468,24 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 		/*
 		 * Some BIOSes incorrectly force this feature, but only K8
 		 * revision D (model = 0x14) and later actually support it.
+		 * (AMD Erratum #110, docId: 25759).
 		 */
-		if (c->x86_model < 0x14)
+		if (c->x86_model < 0x14 && cpu_has(c, X86_FEATURE_LAHF_LM)) {
+			u64 val;
+
 			clear_cpu_cap(c, X86_FEATURE_LAHF_LM);
+			if (!rdmsrl_amd_safe(0xc001100d, &val)) {
+				val &= ~(1ULL << 32);
+				wrmsrl_amd_safe(0xc001100d, val);
+			}
+		}
+
 	}
 	if (c->x86 == 0x10 || c->x86 == 0x11)
 		set_cpu_cap(c, X86_FEATURE_REP_GOOD);
+
+	/* get apicid instead of initial apic id from cpuid */
+	c->apicid = hard_smp_processor_id();
 #else
 
 	/*
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 306bf0d..804c40e 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -241,7 +241,7 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
 	case 0:
 		if (!l1->val)
 			return;
-		assoc = l1->assoc;
+		assoc = assocs[l1->assoc];
 		line_size = l1->line_size;
 		lines_per_tag = l1->lines_per_tag;
 		size_in_kb = l1->size_in_kb;
@@ -249,7 +249,7 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
 	case 2:
 		if (!l2.val)
 			return;
-		assoc = l2.assoc;
+		assoc = assocs[l2.assoc];
 		line_size = l2.line_size;
 		lines_per_tag = l2.lines_per_tag;
 		/* cpu_data has errata corrections for K7 applied */
@@ -258,10 +258,14 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
 	case 3:
 		if (!l3.val)
 			return;
-		assoc = l3.assoc;
+		assoc = assocs[l3.assoc];
 		line_size = l3.line_size;
 		lines_per_tag = l3.lines_per_tag;
 		size_in_kb = l3.size_encoded * 512;
+		if (boot_cpu_has(X86_FEATURE_AMD_DCM)) {
+			size_in_kb = size_in_kb >> 1;
+			assoc = assoc >> 1;
+		}
 		break;
 	default:
 		return;
@@ -270,18 +274,14 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
 	eax->split.is_self_initializing = 1;
 	eax->split.type = types[leaf];
 	eax->split.level = levels[leaf];
-	if (leaf == 3)
-		eax->split.num_threads_sharing =
-			current_cpu_data.x86_max_cores - 1;
-	else
-		eax->split.num_threads_sharing = 0;
+	eax->split.num_threads_sharing = 0;
 	eax->split.num_cores_on_die = current_cpu_data.x86_max_cores - 1;
 
 
-	if (assoc == 0xf)
+	if (assoc == 0xffff)
 		eax->split.is_fully_associative = 1;
 	ebx->split.coherency_line_size = line_size - 1;
-	ebx->split.ways_of_associativity = assocs[assoc] - 1;
+	ebx->split.ways_of_associativity = assoc - 1;
 	ebx->split.physical_line_partition = lines_per_tag - 1;
 	ecx->split.number_of_sets = (size_in_kb * 1024) / line_size /
 		(ebx->split.ways_of_associativity + 1) - 1;
@@ -523,6 +523,18 @@ static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index)
 	int index_msb, i;
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 
+	if ((index == 3) && (c->x86_vendor == X86_VENDOR_AMD)) {
+		struct cpuinfo_x86 *d;
+		for_each_online_cpu(i) {
+			if (!per_cpu(cpuid4_info, i))
+				continue;
+			d = &cpu_data(i);
+			this_leaf = CPUID4_INFO_IDX(i, index);
+			cpumask_copy(to_cpumask(this_leaf->shared_cpu_map),
+				     d->llc_shared_map);
+		}
+		return;
+	}
 	this_leaf = CPUID4_INFO_IDX(cpu, index);
 	num_threads_sharing = 1 + this_leaf->eax.split.num_threads_sharing;
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index ddae216..1fecba4 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -489,12 +489,14 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 	int i, err = 0;
 	struct threshold_bank *b = NULL;
 	char name[32];
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
+
 
 	sprintf(name, "threshold_bank%i", bank);
 
 #ifdef CONFIG_SMP
 	if (cpu_data(cpu).cpu_core_id && shared_bank[bank]) {	/* symlink */
-		i = cpumask_first(cpu_core_mask(cpu));
+		i = cpumask_first(c->llc_shared_map);
 
 		/* first core not up yet */
 		if (cpu_data(i).cpu_core_id)
@@ -514,7 +516,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 		if (err)
 			goto out;
 
-		cpumask_copy(b->cpus, cpu_core_mask(cpu));
+		cpumask_copy(b->cpus, c->llc_shared_map);
 		per_cpu(threshold_banks, cpu)[bank] = b;
 
 		goto out;
@@ -539,7 +541,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 #ifndef CONFIG_SMP
 	cpumask_setall(b->cpus);
 #else
-	cpumask_copy(b->cpus, cpu_core_mask(cpu));
+	cpumask_copy(b->cpus, c->llc_shared_map);
 #endif
 
 	per_cpu(threshold_banks, cpu)[bank] = b;
diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c
index 1e90434..62ac8cb 100644
--- a/arch/x86/kernel/cpu/proc.c
+++ b/arch/x86/kernel/cpu/proc.c
@@ -116,11 +116,9 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 		seq_printf(m, "TLB size\t: %d 4K pages\n", c->x86_tlbsize);
 #endif
 	seq_printf(m, "clflush size\t: %u\n", c->x86_clflush_size);
-#ifdef CONFIG_X86_64
 	seq_printf(m, "cache_alignment\t: %d\n", c->x86_cache_alignment);
 	seq_printf(m, "address sizes\t: %u bits physical, %u bits virtual\n",
 		   c->x86_phys_bits, c->x86_virt_bits);
-#endif
 
 	seq_printf(m, "power management:");
 	for (i = 0; i < 32; i++) {