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>

4 files changed, 36 insertions, 4 deletions

diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h
index edc2a455b726..9c7d95f6174b 100644
--- a/arch/x86/include/asm/mpspec.h
+++ b/arch/x86/include/asm/mpspec.h
@@ -25,7 +25,6 @@ extern int pic_mode;
 #define MAX_IRQ_SOURCES		256
 
 extern unsigned int def_to_bigsmp;
-extern u8 apicid_2_node[];
 
 #ifdef CONFIG_X86_NUMAQ
 extern int mp_bus_id_to_node[MAX_MP_BUSSES];
diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h
index 27da400d3138..5e01c768a575 100644
--- a/arch/x86/include/asm/numa.h
+++ b/arch/x86/include/asm/numa.h
@@ -1,5 +1,33 @@
+#ifndef _ASM_X86_NUMA_H
+#define _ASM_X86_NUMA_H
+
+#include <asm/apicdef.h>
+
+#ifdef CONFIG_NUMA
+/*
+ * __apicid_to_node[] stores the raw mapping between physical apicid and
+ * node and is used to initialize cpu_to_node mapping.
+ *
+ * The mapping may be overridden by apic->numa_cpu_node() on 32bit and thus
+ * should be accessed by the accessors - set_apicid_to_node() and
+ * numa_cpu_node().
+ */
+extern s16 __apicid_to_node[MAX_LOCAL_APIC];
+
+static inline void set_apicid_to_node(int apicid, s16 node)
+{
+	__apicid_to_node[apicid] = node;
+}
+#else	/* CONFIG_NUMA */
+static inline void set_apicid_to_node(int apicid, s16 node)
+{
+}
+#endif	/* CONFIG_NUMA */
+
 #ifdef CONFIG_X86_32
 # include "numa_32.h"
 #else
 # include "numa_64.h"
 #endif
+
+#endif	/* _ASM_X86_NUMA_H */
diff --git a/arch/x86/include/asm/numa_32.h b/arch/x86/include/asm/numa_32.h
index b0ef2b449a9d..cdf8043d7a1a 100644
--- a/arch/x86/include/asm/numa_32.h
+++ b/arch/x86/include/asm/numa_32.h
@@ -6,6 +6,12 @@ extern int numa_off;
 extern int pxm_to_nid(int pxm);
 extern void numa_remove_cpu(int cpu);
 
+#ifdef CONFIG_NUMA
+extern int __cpuinit numa_cpu_node(int apicid);
+#else	/* CONFIG_NUMA */
+static inline int numa_cpu_node(int cpu)		{ return NUMA_NO_NODE; }
+#endif	/* CONFIG_NUMA */
+
 #ifdef CONFIG_HIGHMEM
 extern void set_highmem_pages_init(void);
 #else
diff --git a/arch/x86/include/asm/numa_64.h b/arch/x86/include/asm/numa_64.h
index 0493be39607c..4982a9c08c2f 100644
--- a/arch/x86/include/asm/numa_64.h
+++ b/arch/x86/include/asm/numa_64.h
@@ -2,7 +2,6 @@
 #define _ASM_X86_NUMA_64_H
 
 #include <linux/nodemask.h>
-#include <asm/apicdef.h>
 
 struct bootnode {
 	u64 start;
@@ -17,8 +16,6 @@ extern int compute_hash_shift(struct bootnode *nodes, int numblks,
 extern void numa_init_array(void);
 extern int numa_off;
 
-extern s16 apicid_to_node[MAX_LOCAL_APIC];
-
 extern unsigned long numa_free_all_bootmem(void);
 extern void setup_node_bootmem(int nodeid, unsigned long start,
 			       unsigned long end);
@@ -32,6 +29,7 @@ extern void setup_node_bootmem(int nodeid, unsigned long start,
 #define NODE_MIN_SIZE (4*1024*1024)
 
 extern void __init init_cpu_to_node(void);
+extern int __cpuinit numa_cpu_node(int cpu);
 extern void __cpuinit numa_set_node(int cpu, int node);
 extern void __cpuinit numa_clear_node(int cpu);
 extern void __cpuinit numa_add_cpu(int cpu);
@@ -44,6 +42,7 @@ void numa_emu_cmdline(char *);
 #endif /* CONFIG_NUMA_EMU */
 #else
 static inline void init_cpu_to_node(void)		{ }
+static inline int numa_cpu_node(int cpu)		{ return NUMA_NO_NODE; }
 static inline void numa_set_node(int cpu, int node)	{ }
 static inline void numa_clear_node(int cpu)		{ }
 static inline void numa_add_cpu(int cpu, int node)	{ }