Merge branch 'x86/numa' into x86/devel

Conflicts:

	arch/x86/Kconfig
	arch/x86/kernel/e820.c
	arch/x86/kernel/efi_64.c
	arch/x86/kernel/mpparse.c
	arch/x86/kernel/setup.c
	arch/x86/kernel/setup_32.c
	arch/x86/mm/init_64.c
	include/asm-x86/proto.h

Signed-off-by: Ingo Molnar <mingo@elte.hu>

6 files changed, 153 insertions, 85 deletions

diff --git a/include/asm-x86/numa_64.h b/include/asm-x86/numa_64.h
index 22e87c9f6a8..b510daf4f4d 100644
--- a/include/asm-x86/numa_64.h
+++ b/include/asm-x86/numa_64.h
@@ -14,11 +14,9 @@ extern int compute_hash_shift(struct bootnode *nodes, int numblks,
 
 #define ZONE_ALIGN (1UL << (MAX_ORDER+PAGE_SHIFT))
 
-extern void numa_add_cpu(int cpu);
 extern void numa_init_array(void);
 extern int numa_off;
 
-extern void numa_set_node(int cpu, int node);
 extern void srat_reserve_add_area(int nodeid);
 extern int hotadd_percent;
 
@@ -31,15 +29,16 @@ extern void setup_node_bootmem(int nodeid, unsigned long start,
 
 #ifdef CONFIG_NUMA
 extern void __init init_cpu_to_node(void);
-
-static inline void clear_node_cpumask(int cpu)
-{
-        clear_bit(cpu, (unsigned long *)&node_to_cpumask_map[cpu_to_node(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);
+extern void __cpuinit numa_remove_cpu(int cpu);
 #else
-#define init_cpu_to_node() do {} while (0)
-#define clear_node_cpumask(cpu) do {} while (0)
+static inline void init_cpu_to_node(void)               { }
+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)      { }
+static inline void numa_remove_cpu(int cpu)             { }
 #endif
 
 #endif
diff --git a/include/asm-x86/pda.h b/include/asm-x86/pda.h
index 101fb9e1195..b34e9a7cc80 100644
--- a/include/asm-x86/pda.h
+++ b/include/asm-x86/pda.h
@@ -22,6 +22,8 @@ struct x8664_pda {
                                            offset 40!!! */
 #endif
         char *irqstackptr;
+        short nodenumber;               /* number of current node (32k max) */
+        short in_bootmem;               /* pda lives in bootmem */
         unsigned int __softirq_pending;
         unsigned int __nmi_count;       /* number of NMI on this CPUs */
         short mmu_state;
@@ -37,8 +39,7 @@ struct x8664_pda {
         unsigned irq_spurious_count;
 } ____cacheline_aligned_in_smp;
 
-extern struct x8664_pda *_cpu_pda[];
-extern struct x8664_pda boot_cpu_pda[];
+extern struct x8664_pda **_cpu_pda;
 extern void pda_init(int);
 
 #define cpu_pda(i) (_cpu_pda[i])
diff --git a/include/asm-x86/percpu.h b/include/asm-x86/percpu.h
index 736fc3bb8e1..912a3a17b9d 100644
--- a/include/asm-x86/percpu.h
+++ b/include/asm-x86/percpu.h
@@ -143,4 +143,50 @@ do {							\
 #define x86_or_percpu(var, val) percpu_to_op("or", per_cpu__##var, val)
 #endif /* !__ASSEMBLY__ */
 #endif /* !CONFIG_X86_64 */
+
+#ifdef CONFIG_SMP
+
+/*
+ * Define the "EARLY_PER_CPU" macros.  These are used for some per_cpu
+ * variables that are initialized and accessed before there are per_cpu
+ * areas allocated.
+ */
+
+#define DEFINE_EARLY_PER_CPU(_type, _name, _initvalue)                  \
+        DEFINE_PER_CPU(_type, _name) = _initvalue;                      \
+        __typeof__(_type) _name##_early_map[NR_CPUS] __initdata =       \
+                                { [0 ... NR_CPUS-1] = _initvalue };     \
+        __typeof__(_type) *_name##_early_ptr = _name##_early_map
+
+#define EXPORT_EARLY_PER_CPU_SYMBOL(_name)                      \
+        EXPORT_PER_CPU_SYMBOL(_name)
+
+#define DECLARE_EARLY_PER_CPU(_type, _name)                     \
+        DECLARE_PER_CPU(_type, _name);                          \
+        extern __typeof__(_type) *_name##_early_ptr;            \
+        extern __typeof__(_type)  _name##_early_map[]
+
+#define early_per_cpu_ptr(_name) (_name##_early_ptr)
+#define early_per_cpu_map(_name, _idx) (_name##_early_map[_idx])
+#define early_per_cpu(_name, _cpu)                              \
+        (early_per_cpu_ptr(_name) ?                             \
+                early_per_cpu_ptr(_name)[_cpu] :                \
+                per_cpu(_name, _cpu))
+
+#else   /* !CONFIG_SMP */
+#define DEFINE_EARLY_PER_CPU(_type, _name, _initvalue)          \
+        DEFINE_PER_CPU(_type, _name) = _initvalue
+
+#define EXPORT_EARLY_PER_CPU_SYMBOL(_name)                      \
+        EXPORT_PER_CPU_SYMBOL(_name)
+
+#define DECLARE_EARLY_PER_CPU(_type, _name)                     \
+        DECLARE_PER_CPU(_type, _name)
+
+#define early_per_cpu(_name, _cpu) per_cpu(_name, _cpu)
+#define early_per_cpu_ptr(_name) NULL
+/* no early_per_cpu_map() */
+
+#endif  /* !CONFIG_SMP */
+
 #endif /* _ASM_X86_PERCPU_H_ */
diff --git a/include/asm-x86/smp.h b/include/asm-x86/smp.h
index 514e52b95ce..fc1007321ef 100644
--- a/include/asm-x86/smp.h
+++ b/include/asm-x86/smp.h
@@ -29,21 +29,12 @@ extern int smp_num_siblings;
 extern unsigned int num_processors;
 extern cpumask_t cpu_initialized;
 
-#ifdef CONFIG_SMP
-extern u16 x86_cpu_to_apicid_init[];
-extern u16 x86_bios_cpu_apicid_init[];
-extern void *x86_cpu_to_apicid_early_ptr;
-extern void *x86_bios_cpu_apicid_early_ptr;
-#else
-#define x86_cpu_to_apicid_early_ptr NULL
-#define x86_bios_cpu_apicid_early_ptr NULL
-#endif
-
 DECLARE_PER_CPU(cpumask_t, cpu_sibling_map);
 DECLARE_PER_CPU(cpumask_t, cpu_core_map);
 DECLARE_PER_CPU(u16, cpu_llc_id);
-DECLARE_PER_CPU(u16, x86_cpu_to_apicid);
-DECLARE_PER_CPU(u16, x86_bios_cpu_apicid);
+
+DECLARE_EARLY_PER_CPU(u16, x86_cpu_to_apicid);
+DECLARE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid);
 
 /* Static state in head.S used to set up a CPU */
 extern struct {
diff --git a/include/asm-x86/topology.h b/include/asm-x86/topology.h
index dcf3f8131d6..1f97758de4a 100644
--- a/include/asm-x86/topology.h
+++ b/include/asm-x86/topology.h
@@ -35,79 +35,88 @@
 # endif
 #endif
 
+/* Node not present */
+#define NUMA_NO_NODE    (-1)
+
 #ifdef CONFIG_NUMA
 #include <linux/cpumask.h>
 #include <asm/mpspec.h>
 
-/* Mappings between logical cpu number and node number */
 #ifdef CONFIG_X86_32
-extern int cpu_to_node_map[];
-#else
-/* Returns the number of the current Node. */
-#define numa_node_id()          (early_cpu_to_node(raw_smp_processor_id()))
-#endif
-
-DECLARE_PER_CPU(int, x86_cpu_to_node_map);
-
-#ifdef CONFIG_SMP
-extern int x86_cpu_to_node_map_init[];
-extern void *x86_cpu_to_node_map_early_ptr;
-#else
-#define x86_cpu_to_node_map_early_ptr NULL
-#endif
 
+/* Mappings between node number and cpus on that node. */
 extern cpumask_t node_to_cpumask_map[];
 
-#define NUMA_NO_NODE    (-1)
+/* Mappings between logical cpu number and node number */
+extern int cpu_to_node_map[];
 
 /* Returns the number of the node containing CPU 'cpu' */
-#ifdef CONFIG_X86_32
-#define early_cpu_to_node(cpu)  cpu_to_node(cpu)
 static inline int cpu_to_node(int cpu)
 {
         return cpu_to_node_map[cpu];
 }
+#define early_cpu_to_node(cpu)  cpu_to_node(cpu)
 
-#else /* CONFIG_X86_64 */
-
-#ifdef CONFIG_SMP
-static inline int early_cpu_to_node(int cpu)
+/* Returns a bitmask of CPUs on Node 'node'. */
+static inline cpumask_t node_to_cpumask(int node)
 {
-        int *cpu_to_node_map = x86_cpu_to_node_map_early_ptr;
-
-        if (cpu_to_node_map)
-                return cpu_to_node_map[cpu];
-        else if (per_cpu_offset(cpu))
-                return per_cpu(x86_cpu_to_node_map, cpu);
-        else
-                return NUMA_NO_NODE;
+        return node_to_cpumask_map[node];
 }
-#else
-#define early_cpu_to_node(cpu)  cpu_to_node(cpu)
-#endif
 
+#else /* CONFIG_X86_64 */
+
+/* Mappings between node number and cpus on that node. */
+extern cpumask_t *node_to_cpumask_map;
+
+/* Mappings between logical cpu number and node number */
+DECLARE_EARLY_PER_CPU(int, x86_cpu_to_node_map);
+
+/* Returns the number of the current Node. */
+#define numa_node_id()          read_pda(nodenumber)
+
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+extern int cpu_to_node(int cpu);
+extern int early_cpu_to_node(int cpu);
+extern cpumask_t *_node_to_cpumask_ptr(int node);
+extern cpumask_t node_to_cpumask(int node);
+
+#else   /* !CONFIG_DEBUG_PER_CPU_MAPS */
+
+/* Returns the number of the node containing CPU 'cpu' */
 static inline int cpu_to_node(int cpu)
 {
-#ifdef CONFIG_DEBUG_PER_CPU_MAPS
-        if (x86_cpu_to_node_map_early_ptr) {
-                printk("KERN_NOTICE cpu_to_node(%d): usage too early!\n",
-                       (int)cpu);
-                dump_stack();
-                return ((int *)x86_cpu_to_node_map_early_ptr)[cpu];
-        }
-#endif
         return per_cpu(x86_cpu_to_node_map, cpu);
 }
 
-#ifdef  CONFIG_NUMA
+/* Same function but used if called before per_cpu areas are setup */
+static inline int early_cpu_to_node(int cpu)
+{
+        if (early_per_cpu_ptr(x86_cpu_to_node_map))
+                return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu];
+
+        return per_cpu(x86_cpu_to_node_map, cpu);
+}
 
 /* Returns a pointer to the cpumask of CPUs on Node 'node'. */
+static inline cpumask_t *_node_to_cpumask_ptr(int node)
+{
+        return &node_to_cpumask_map[node];
+}
+
+/* Returns a bitmask of CPUs on Node 'node'. */
+static inline cpumask_t node_to_cpumask(int node)
+{
+        return node_to_cpumask_map[node];
+}
+
+#endif /* !CONFIG_DEBUG_PER_CPU_MAPS */
+
+/* Replace default node_to_cpumask_ptr with optimized version */
 #define node_to_cpumask_ptr(v, node)            \
-                cpumask_t *v = &(node_to_cpumask_map[node])
+                cpumask_t *v = _node_to_cpumask_ptr(node)
 
 #define node_to_cpumask_ptr_next(v, node)       \
-                           v = &(node_to_cpumask_map[node])
-#endif
+                           v = _node_to_cpumask_ptr(node)
 
 #endif /* CONFIG_X86_64 */
 
@@ -117,20 +126,6 @@ static inline int cpu_to_node(int cpu)
  */
 #define parent_node(node) (node)
 
-/* Returns a bitmask of CPUs on Node 'node'. */
-static inline cpumask_t node_to_cpumask(int node)
-{
-        return node_to_cpumask_map[node];
-}
-
-/* Returns the number of the first CPU on Node 'node'. */
-static inline int node_to_first_cpu(int node)
-{
-        cpumask_t mask = node_to_cpumask(node);
-
-        return first_cpu(mask);
-}
-
 #define pcibus_to_node(bus) __pcibus_to_node(bus)
 #define pcibus_to_cpumask(bus) __pcibus_to_cpumask(bus)
 
@@ -180,12 +175,44 @@ extern int __node_distance(int, int);
 #define node_distance(a, b) __node_distance(a, b)
 #endif
 
-#else /* CONFIG_NUMA */
+#else /* !CONFIG_NUMA */
 
+#define numa_node_id()          0
+#define cpu_to_node(cpu)        0
+#define early_cpu_to_node(cpu)  0
+
+static inline cpumask_t *_node_to_cpumask_ptr(int node)
+{
+        return &cpu_online_map;
+}
+static inline cpumask_t node_to_cpumask(int node)
+{
+        return cpu_online_map;
+}
+static inline int node_to_first_cpu(int node)
+{
+        return first_cpu(cpu_online_map);
+}
+
+/* Replace default node_to_cpumask_ptr with optimized version */
+#define node_to_cpumask_ptr(v, node)            \
+                cpumask_t *v = _node_to_cpumask_ptr(node)
+
+#define node_to_cpumask_ptr_next(v, node)       \
+                           v = _node_to_cpumask_ptr(node)
 #endif
 
 #include <asm-generic/topology.h>
 
+#ifdef CONFIG_NUMA
+/* Returns the number of the first CPU on Node 'node'. */
+static inline int node_to_first_cpu(int node)
+{
+        node_to_cpumask_ptr(mask, node);
+        return first_cpu(*mask);
+}
+#endif
+
 extern cpumask_t cpu_coregroup_map(int cpu);
 
 #ifdef ENABLE_TOPO_DEFINES
@@ -193,6 +220,9 @@ extern cpumask_t cpu_coregroup_map(int cpu);
 #define topology_core_id(cpu)                   (cpu_data(cpu).cpu_core_id)
 #define topology_core_siblings(cpu)             (per_cpu(cpu_core_map, cpu))
 #define topology_thread_siblings(cpu)           (per_cpu(cpu_sibling_map, cpu))
+
+/* indicates that pointers to the topology cpumask_t maps are valid */
+#define arch_provides_topology_pointers         yes
 #endif
 
 static inline void arch_fix_phys_package_id(int num, u32 slot)
@@ -220,4 +250,4 @@ static inline void set_mp_bus_to_node(int busnum, int node)
 }
 #endif
 
-#endif
+#endif /* _ASM_X86_TOPOLOGY_H */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index e4de460907c..3d647b24041 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1026,6 +1026,7 @@ extern void mem_init(void);
 extern void show_mem(void);
 extern void si_meminfo(struct sysinfo * val);
 extern void si_meminfo_node(struct sysinfo *val, int nid);
+extern int after_bootmem;
 
 #ifdef CONFIG_NUMA
 extern void setup_per_cpu_pageset(void);