x86, amd: Normalize compute unit IDs on multi-node processors

On multi-node CPUs we don't need the socket wide compute unit ID
but the node-wide compute unit ID. Thus we need to normalize the
value. This is similar to what we do with cpu_core_id.

A compute unit is then identified by physical_package_id,
node_id, and compute_unit_id.
Signed-off-by: NAndreas Herrmann <andreas.herrmann3@amd.com>
LKML-Reference: <1295881543-572552-2-git-send-email-hans.rosenfeld@amd.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

arch/x86/kernel/cpu/amd.c

@@ -261,7 +261,7 @@ static int __cpuinit nearby_node(int apicid)
 #ifdef CONFIG_X86_HT
 static void __cpuinit amd_get_topology(struct cpuinfo_x86 *c)
 {
-	u32 nodes;
+	u32 nodes, cores_per_cu;
 	u8 node_id;
 	int cpu = smp_processor_id();
 
@@ -276,6 +276,7 @@ static void __cpuinit amd_get_topology(struct cpuinfo_x86 *c)
 		/* get compute unit information */
 		smp_num_siblings = ((ebx >> 8) & 3) + 1;
 		c->compute_unit_id = ebx & 0xff;
+		cores_per_cu = ((ebx >> 8) & 3) + 1;
 	} else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) {
 		u64 value;
 
@@ -288,15 +289,18 @@ static void __cpuinit amd_get_topology(struct cpuinfo_x86 *c)
 	/* fixup multi-node processor information */
 	if (nodes > 1) {
 		u32 cores_per_node;
+		u32 cus_per_node;
 
 		set_cpu_cap(c, X86_FEATURE_AMD_DCM);
 		cores_per_node = c->x86_max_cores / nodes;
+		cus_per_node = cores_per_node / cores_per_cu;
 
 		/* store NodeID, use llc_shared_map to store sibling info */
 		per_cpu(cpu_llc_id, cpu) = node_id;
 
 		/* core id to be in range from 0 to (cores_per_node - 1) */
-		c->cpu_core_id = c->cpu_core_id % cores_per_node;
+		c->cpu_core_id %= cores_per_node;
+		c->compute_unit_id %= cus_per_node;
 	}
 }
 #endif

arch/x86/kernel/smpboot.c

@@ -414,6 +414,7 @@ void __cpuinit set_cpu_sibling_map(int cpu)
 
 			if (cpu_has(c, X86_FEATURE_TOPOEXT)) {
 				if (c->phys_proc_id == o->phys_proc_id &&
+				    per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i) &&
 				    c->compute_unit_id == o->compute_unit_id)
 					link_thread_siblings(cpu, i);
 			} else if (c->phys_proc_id == o->phys_proc_id &&