x86: Fix CPU llc_shared_map information for AMD Magny-Cours

Construct entire NodeID and use it as cpu_llc_id. Thus internal node
siblings are stored in llc_shared_map.
Signed-off-by: NAndreas Herrmann <andreas.herrmann3@amd.com>
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>

arch/x86/include/asm/cpufeature.h

@@ -95,6 +95,7 @@
 #define X86_FEATURE_NONSTOP_TSC	(3*32+24) /* TSC does not stop in C states */
 #define X86_FEATURE_CLFLUSH_MONITOR (3*32+25) /* "" clflush reqd with monitor */
 #define X86_FEATURE_EXTD_APICID	(3*32+26) /* has extended APICID (8 bits) */
+#define X86_FEATURE_AMD_DCM     (3*32+27) /* multi-node processor */
 
 /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
 #define X86_FEATURE_XMM3	(4*32+ 0) /* "pni" SSE-3 */

arch/x86/kernel/cpu/amd.c

@@ -250,6 +250,64 @@ 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.
@@ -267,6 +325,9 @@ 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
 }
 
@@ -277,7 +338,8 @@ static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c)
 	int node;
 	unsigned apicid = cpu_has_apic ? hard_smp_processor_id() : c->apicid;
 
-	node = c->phys_proc_id;
+	node = per_cpu(cpu_llc_id, cpu);
+
 	if (apicid_to_node[apicid] != NUMA_NO_NODE)
 		node = apicid_to_node[apicid];
 	if (!node_online(node)) {