x86: cleanup early per cpu variables/accesses v4

  * Introduce a new PER_CPU macro called "EARLY_PER_CPU".  This is
    used by some per_cpu variables that are initialized and accessed
    before there are per_cpu areas allocated.

    ["Early" in respect to per_cpu variables is "earlier than the per_cpu
    areas have been setup".]

    This patchset adds these new macros:

	DEFINE_EARLY_PER_CPU(_type, _name, _initvalue)
	EXPORT_EARLY_PER_CPU_SYMBOL(_name)
	DECLARE_EARLY_PER_CPU(_type, _name)

	early_per_cpu_ptr(_name)
	early_per_cpu_map(_name, _idx)
	early_per_cpu(_name, _cpu)

    The DEFINE macro defines the per_cpu variable as well as the early
    map and pointer.  It also initializes the per_cpu variable and map
    elements to "_initvalue".  The early_* macros provide access to
    the initial map (usually setup during system init) and the early
    pointer.  This pointer is initialized to point to the early map
    but is then NULL'ed when the actual per_cpu areas are setup.  After
    that the per_cpu variable is the correct access to the variable.

    The early_per_cpu() macro is not very efficient but does show how to
    access the variable if you have a function that can be called both
    "early" and "late".  It tests the early ptr to be NULL, and if not
    then it's still valid.  Otherwise, the per_cpu variable is used
    instead:

	#define early_per_cpu(_name, _cpu) 			\
		(early_per_cpu_ptr(_name) ?			\
			early_per_cpu_ptr(_name)[_cpu] :	\
			per_cpu(_name, _cpu))

    A better method is to actually check the pointer manually.  In the
    case below, numa_set_node can be called both "early" and "late":

	void __cpuinit numa_set_node(int cpu, int node)
	{
	    int *cpu_to_node_map = early_per_cpu_ptr(x86_cpu_to_node_map);

	    if (cpu_to_node_map)
		    cpu_to_node_map[cpu] = node;
	    else
		    per_cpu(x86_cpu_to_node_map, cpu) = node;
	}

  * Add a flag "arch_provides_topology_pointers" that indicates pointers
    to topology cpumask_t maps are available.  Otherwise, use the function
    returning the cpumask_t value.  This is useful if cpumask_t set size
    is very large to avoid copying data on to/off of the stack.

  * The coverage of CONFIG_DEBUG_PER_CPU_MAPS has been increased while
    the non-debug case has been optimized a bit.

  * Remove an unreferenced compiler warning in drivers/base/topology.c

  * Clean up #ifdef in setup.c

For inclusion into sched-devel/latest tree.

Based on:
	git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6.git
    +   sched-devel/latest  .../mingo/linux-2.6-sched-devel.git

Signed-off-by: Mike Travis <travis@sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

1 files changed, 82 insertions, 61 deletions

diff --git a/include/asm-x86/topology.h b/include/asm-x86/topology.h
index dcf3f8131d6..dac09cb66dc 100644
--- a/include/asm-x86/topology.h
+++ b/include/asm-x86/topology.h
@@ -35,87 +35,67 @@
 # 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)
-{
-	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;
-}
-#else
-#define	early_cpu_to_node(cpu)	cpu_to_node(cpu)
-#endif
+/* 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()	(per_cpu(x86_cpu_to_node_map, raw_smp_processor_id()))
+
+#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
-
-/* Returns a pointer to the cpumask of CPUs on Node 'node'. */
-#define node_to_cpumask_ptr(v, node)		\
-		cpumask_t *v = &(node_to_cpumask_map[node])
-
-#define node_to_cpumask_ptr_next(v, node)	\
-			   v = &(node_to_cpumask_map[node])
-#endif
+/* 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];
 
-#endif /* CONFIG_X86_64 */
+	return per_cpu(x86_cpu_to_node_map, cpu);
+}
 
-/*
- * Returns the number of the node containing Node 'node'. This
- * architecture is flat, so it is a pretty simple function!
- */
-#define parent_node(node) (node)
+/* 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)
@@ -123,14 +103,29 @@ static inline cpumask_t node_to_cpumask(int node)
 	return node_to_cpumask_map[node];
 }
 
+#endif /* !CONFIG_DEBUG_PER_CPU_MAPS */
+#endif /* CONFIG_X86_64 */
+
+/* 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)
+
 /* 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);
+	node_to_cpumask_ptr(mask, node);
+	return first_cpu(*mask);
 }
 
+/*
+ * Returns the number of the node containing Node 'node'. This
+ * architecture is flat, so it is a pretty simple function!
+ */
+#define parent_node(node) (node)
+
 #define pcibus_to_node(bus) __pcibus_to_node(bus)
 #define pcibus_to_cpumask(bus) __pcibus_to_cpumask(bus)
 
@@ -180,8 +175,31 @@ 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>
@@ -193,6 +211,9 @@ 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 +241,4 @@ static inline void set_mp_bus_to_node(int busnum, int node)
 }
 #endif
 
-#endif
+#endif /* _ASM_X86_TOPOLOGY_H */