x86: Unify cpu/apicid <-> NUMA node mapping between 32 and 64bit

The mapping between cpu/apicid and node is done via
apicid_to_node[] on 64bit and apicid_2_node[] +
apic->x86_32_numa_cpu_node() on 32bit. This difference makes it
difficult to further unify 32 and 64bit NUMA handling.

This patch unifies it by replacing both apicid_to_node[] and
apicid_2_node[] with __apicid_to_node[] array, which is accessed
by two accessors - set_apicid_to_node() and numa_cpu_node().  On
64bit, numa_cpu_node() always consults __apicid_to_node[]
directly while 32bit goes through apic->numa_cpu_node() method
to allow apic implementations to override it.

srat_detect_node() for amd cpus contains workaround for broken
NUMA configuration which assumes relationship between APIC ID,
HT node ID and NUMA topology.  Leave it to access
__apicid_to_node[] directly as mapping through CPU might result
in undesirable behavior change.  The comment is reformatted and
updated to note the ugliness.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Pekka Enberg <penberg@kernel.org>
Cc: eric.dumazet@gmail.com
Cc: yinghai@kernel.org
Cc: brgerst@gmail.com
Cc: gorcunov@gmail.com
Cc: shaohui.zheng@intel.com
Cc: rientjes@google.com
LKML-Reference: <1295789862-25482-14-git-send-email-tj@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Cc: David Rientjes <rientjes@google.com>

6 files changed, 31 insertions, 25 deletions

diff --git a/arch/x86/mm/amdtopology_64.c b/arch/x86/mm/amdtopology_64.c
index f21962c435e..c7fae38c408 100644
--- a/arch/x86/mm/amdtopology_64.c
+++ b/arch/x86/mm/amdtopology_64.c
@@ -247,7 +247,7 @@ void __init amd_fake_nodes(const struct bootnode *nodes, int nr_nodes)
 		__acpi_map_pxm_to_node(nid, i);
 #endif
 	}
-	memcpy(apicid_to_node, fake_apicid_to_node, sizeof(apicid_to_node));
+	memcpy(__apicid_to_node, fake_apicid_to_node, sizeof(__apicid_to_node));
 }
 #endif /* CONFIG_NUMA_EMU */
 
@@ -285,7 +285,7 @@ int __init amd_scan_nodes(void)
 				nodes[i].start >> PAGE_SHIFT,
 				nodes[i].end >> PAGE_SHIFT);
 		for (j = apicid_base; j < cores + apicid_base; j++)
-			apicid_to_node[(i << bits) + j] = i;
+			set_apicid_to_node((i << bits) + j, i);
 		setup_node_bootmem(i, nodes[i].start, nodes[i].end);
 	}
 
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index ebf6d7887a3..480b3571c8b 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -26,8 +26,12 @@ static __init int numa_setup(char *opt)
 early_param("numa", numa_setup);
 
 /*
- * Which logical CPUs are on which nodes
+ * apicid, cpu, node mappings
  */
+s16 __apicid_to_node[MAX_LOCAL_APIC] __cpuinitdata = {
+	[0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE
+};
+
 cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
 EXPORT_SYMBOL(node_to_cpumask_map);
 
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index 84a3e4c9f27..8d91d227be0 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -110,6 +110,12 @@ void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags);
 
 static unsigned long kva_start_pfn;
 static unsigned long kva_pages;
+
+int __cpuinit numa_cpu_node(int cpu)
+{
+	return apic->x86_32_numa_cpu_node(cpu);
+}
+
 /*
  * FLAT - support for basic PC memory model with discontig enabled, essentially
  *        a single node with all available processors in it with a flat
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 95ea1551eeb..1e1026f61a5 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -26,10 +26,6 @@ EXPORT_SYMBOL(node_data);
 
 struct memnode memnode;
 
-s16 apicid_to_node[MAX_LOCAL_APIC] __cpuinitdata = {
-	[0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE
-};
-
 static unsigned long __initdata nodemap_addr;
 static unsigned long __initdata nodemap_size;
 
@@ -716,12 +712,8 @@ void __init init_cpu_to_node(void)
 	BUG_ON(cpu_to_apicid == NULL);
 
 	for_each_possible_cpu(cpu) {
-		int node;
-		u16 apicid = cpu_to_apicid[cpu];
+		int node = numa_cpu_node(cpu);
 
-		if (apicid == BAD_APICID)
-			continue;
-		node = apicid_to_node[apicid];
 		if (node == NUMA_NO_NODE)
 			continue;
 		if (!node_online(node))
@@ -731,6 +723,14 @@ void __init init_cpu_to_node(void)
 }
 #endif
 
+int __cpuinit numa_cpu_node(int cpu)
+{
+	int apicid = early_per_cpu(x86_cpu_to_apicid, cpu);
+
+	if (apicid != BAD_APICID)
+		return __apicid_to_node[apicid];
+	return NUMA_NO_NODE;
+}
 
 void __cpuinit numa_set_node(int cpu, int node)
 {
@@ -776,13 +776,9 @@ void __cpuinit numa_remove_cpu(int cpu)
 void __cpuinit numa_add_cpu(int cpu)
 {
 	unsigned long addr;
-	u16 apicid;
-	int physnid;
-	int nid = NUMA_NO_NODE;
+	int physnid, nid;
 
-	apicid = early_per_cpu(x86_cpu_to_apicid, cpu);
-	if (apicid != BAD_APICID)
-		nid = apicid_to_node[apicid];
+	nid = numa_cpu_node(cpu);
 	if (nid == NUMA_NO_NODE)
 		nid = early_cpu_to_node(cpu);
 	BUG_ON(nid == NUMA_NO_NODE || !node_online(nid));
diff --git a/arch/x86/mm/srat_32.c b/arch/x86/mm/srat_32.c
index 6027a481000..48651c6f657 100644
--- a/arch/x86/mm/srat_32.c
+++ b/arch/x86/mm/srat_32.c
@@ -255,7 +255,7 @@ int __init get_memcfg_from_srat(void)
 			 num_memory_chunks);
 
 	for (i = 0; i < MAX_LOCAL_APIC; i++)
-		apicid_2_node[i] = pxm_to_node(apicid_to_pxm[i]);
+		set_apicid_to_node(i, pxm_to_node(apicid_to_pxm[i]));
 
 	for (j = 0; j < num_memory_chunks; j++){
 		struct node_memory_chunk_s * chunk = &node_memory_chunk[j];
diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c
index 603d285d1da..9a97261a241 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -79,7 +79,7 @@ static __init void bad_srat(void)
 	printk(KERN_ERR "SRAT: SRAT not used.\n");
 	acpi_numa = -1;
 	for (i = 0; i < MAX_LOCAL_APIC; i++)
-		apicid_to_node[i] = NUMA_NO_NODE;
+		set_apicid_to_node(i, NUMA_NO_NODE);
 	for (i = 0; i < MAX_NUMNODES; i++) {
 		nodes[i].start = nodes[i].end = 0;
 		nodes_add[i].start = nodes_add[i].end = 0;
@@ -138,7 +138,7 @@ acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa)
 		printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%04x -> Node %u skipped apicid that is too big\n", pxm, apic_id, node);
 		return;
 	}
-	apicid_to_node[apic_id] = node;
+	set_apicid_to_node(apic_id, node);
 	node_set(node, cpu_nodes_parsed);
 	acpi_numa = 1;
 	printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%04x -> Node %u\n",
@@ -178,7 +178,7 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa)
 		return;
 	}
 
-	apicid_to_node[apic_id] = node;
+	set_apicid_to_node(apic_id, node);
 	node_set(node, cpu_nodes_parsed);
 	acpi_numa = 1;
 	printk(KERN_INFO "SRAT: PXM %u -> APIC 0x%02x -> Node %u\n",
@@ -521,7 +521,7 @@ void __init acpi_fake_nodes(const struct bootnode *fake_nodes, int num_nodes)
 		 * node, it must now point to the fake node ID.
 		 */
 		for (j = 0; j < MAX_LOCAL_APIC; j++)
-			if (apicid_to_node[j] == nid &&
+			if (__apicid_to_node[j] == nid &&
 			    fake_apicid_to_node[j] == NUMA_NO_NODE)
 				fake_apicid_to_node[j] = i;
 	}
@@ -532,13 +532,13 @@ void __init acpi_fake_nodes(const struct bootnode *fake_nodes, int num_nodes)
 	 * value.
 	 */
 	for (i = 0; i < MAX_LOCAL_APIC; i++)
-		if (apicid_to_node[i] != NUMA_NO_NODE &&
+		if (__apicid_to_node[i] != NUMA_NO_NODE &&
 		    fake_apicid_to_node[i] == NUMA_NO_NODE)
 			fake_apicid_to_node[i] = 0;
 
 	for (i = 0; i < num_nodes; i++)
 		__acpi_map_pxm_to_node(fake_node_to_pxm_map[i], i);
-	memcpy(apicid_to_node, fake_apicid_to_node, sizeof(apicid_to_node));
+	memcpy(__apicid_to_node, fake_apicid_to_node, sizeof(__apicid_to_node));
 
 	nodes_clear(nodes_parsed);
 	for (i = 0; i < num_nodes; i++)