x86: cleanup remaining cpumask_t ops in smpboot code

Impact: use new cpumask API to reduce memory and stack usage

Allocate the following local cpumasks based on the number of cpus that
are present.  References will use new cpumask API.  (Currently only
modified for x86_64, x86_32 continues to use the *_map variants.)

    cpu_callin_mask
    cpu_callout_mask
    cpu_initialized_mask
    cpu_sibling_setup_mask

Provide the following accessor functions:

    struct cpumask *cpu_sibling_mask(int cpu)
    struct cpumask *cpu_core_mask(int cpu)

Other changes are when setting or clearing the cpu online, possible
or present maps, use the accessor functions.

Signed-off-by: Mike Travis <travis@sgi.com>
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

arch/x86/include/asm/smp.h

@@ -18,9 +18,26 @@
 #include <asm/pda.h>
 #include <asm/thread_info.h>
 
+#ifdef CONFIG_X86_64
+
+extern cpumask_var_t cpu_callin_mask;
+extern cpumask_var_t cpu_callout_mask;
+extern cpumask_var_t cpu_initialized_mask;
+extern cpumask_var_t cpu_sibling_setup_mask;
+
+#else /* CONFIG_X86_32 */
+
+extern cpumask_t cpu_callin_map;
 extern cpumask_t cpu_callout_map;
 extern cpumask_t cpu_initialized;
-extern cpumask_t cpu_callin_map;
+extern cpumask_t cpu_sibling_setup_map;
+
+#define cpu_callin_mask		((struct cpumask *)&cpu_callin_map)
+#define cpu_callout_mask	((struct cpumask *)&cpu_callout_map)
+#define cpu_initialized_mask	((struct cpumask *)&cpu_initialized)
+#define cpu_sibling_setup_mask	((struct cpumask *)&cpu_sibling_setup_map)
+
+#endif /* CONFIG_X86_32 */
 
 extern void (*mtrr_hook)(void);
 extern void zap_low_mappings(void);
@@ -29,7 +46,6 @@ extern int __cpuinit get_local_pda(int cpu);
 
 extern int smp_num_siblings;
 extern unsigned int num_processors;
-extern cpumask_t cpu_initialized;
 
 DECLARE_PER_CPU(cpumask_t, cpu_sibling_map);
 DECLARE_PER_CPU(cpumask_t, cpu_core_map);
@@ -38,6 +54,16 @@ DECLARE_PER_CPU(u16, cpu_llc_id);
 DECLARE_PER_CPU(int, cpu_number);
 #endif
 
+static inline struct cpumask *cpu_sibling_mask(int cpu)
+{
+	return &per_cpu(cpu_sibling_map, cpu);
+}
+
+static inline struct cpumask *cpu_core_mask(int cpu)
+{
+	return &per_cpu(cpu_core_map, cpu);
+}
+
 DECLARE_EARLY_PER_CPU(u16, x86_cpu_to_apicid);
 DECLARE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid);
 
@@ -149,7 +175,7 @@ void smp_store_cpu_info(int id);
 /* We don't mark CPUs online until __cpu_up(), so we need another measure */
 static inline int num_booting_cpus(void)
 {
-	return cpus_weight(cpu_callout_map);
+	return cpumask_weight(cpu_callout_mask);
 }
 #else
 static inline void prefill_possible_map(void)

arch/x86/kernel/cpu/common.c

@@ -40,6 +40,26 @@
 
 #include "cpu.h"
 
+#ifdef CONFIG_X86_64
+
+/* all of these masks are initialized in setup_cpu_local_masks() */
+cpumask_var_t cpu_callin_mask;
+cpumask_var_t cpu_callout_mask;
+cpumask_var_t cpu_initialized_mask;
+
+/* representing cpus for which sibling maps can be computed */
+cpumask_var_t cpu_sibling_setup_mask;
+
+#else /* CONFIG_X86_32 */
+
+cpumask_t cpu_callin_map;
+cpumask_t cpu_callout_map;
+cpumask_t cpu_initialized;
+cpumask_t cpu_sibling_setup_map;
+
+#endif /* CONFIG_X86_32 */
+
+
 static struct cpu_dev *this_cpu __cpuinitdata;
 
 #ifdef CONFIG_X86_64
@@ -856,8 +876,6 @@ static __init int setup_disablecpuid(char *arg)
 }
 __setup("clearcpuid=", setup_disablecpuid);
 
-cpumask_t cpu_initialized __cpuinitdata = CPU_MASK_NONE;
-
 #ifdef CONFIG_X86_64
 struct x8664_pda **_cpu_pda __read_mostly;
 EXPORT_SYMBOL(_cpu_pda);
@@ -976,7 +994,7 @@ void __cpuinit cpu_init(void)
 
 	me = current;
 
-	if (cpu_test_and_set(cpu, cpu_initialized))
+	if (cpumask_test_and_set_cpu(cpu, cpu_initialized_mask))
 		panic("CPU#%d already initialized!\n", cpu);
 
 	printk(KERN_INFO "Initializing CPU#%d\n", cpu);
@@ -1085,7 +1103,7 @@ void __cpuinit cpu_init(void)
 	struct tss_struct *t = &per_cpu(init_tss, cpu);
 	struct thread_struct *thread = &curr->thread;
 
-	if (cpu_test_and_set(cpu, cpu_initialized)) {
+	if (cpumask_test_and_set_cpu(cpu, cpu_initialized_mask)) {
 		printk(KERN_WARNING "CPU#%d already initialized!\n", cpu);
 		for (;;) local_irq_enable();
 	}

arch/x86/kernel/setup_percpu.c

@@ -131,7 +131,27 @@ static void __init setup_cpu_pda_map(void)
 	/* point to new pointer table */
 	_cpu_pda = new_cpu_pda;
 }
-#endif
+
+#endif /* CONFIG_SMP && CONFIG_X86_64 */
+
+#ifdef CONFIG_X86_64
+
+/* correctly size the local cpu masks */
+static void setup_cpu_local_masks(void)
+{
+	alloc_bootmem_cpumask_var(&cpu_initialized_mask);
+	alloc_bootmem_cpumask_var(&cpu_callin_mask);
+	alloc_bootmem_cpumask_var(&cpu_callout_mask);
+	alloc_bootmem_cpumask_var(&cpu_sibling_setup_mask);
+}
+
+#else /* CONFIG_X86_32 */
+
+static inline void setup_cpu_local_masks(void)
+{
+}
+
+#endif /* CONFIG_X86_32 */
 
 /*
  * Great future plan:
@@ -187,6 +207,9 @@ void __init setup_per_cpu_areas(void)
 
 	/* Setup node to cpumask map */
 	setup_node_to_cpumask_map();
+
+	/* Setup cpu initialized, callin, callout masks */
+	setup_cpu_local_masks();
 }
 
 #endif

arch/x86/kernel/smp.c

@@ -128,16 +128,23 @@ void native_send_call_func_single_ipi(int cpu)
 
 void native_send_call_func_ipi(const struct cpumask *mask)
 {
-	cpumask_t allbutself;
+	cpumask_var_t allbutself;
 
-	allbutself = cpu_online_map;
-	cpu_clear(smp_processor_id(), allbutself);
+	if (!alloc_cpumask_var(&allbutself, GFP_ATOMIC)) {
+		send_IPI_mask(mask, CALL_FUNCTION_VECTOR);
+		return;
+	}
 
-	if (cpus_equal(*mask, allbutself) &&
-	    cpus_equal(cpu_online_map, cpu_callout_map))
+	cpumask_copy(allbutself, cpu_online_mask);
+	cpumask_clear_cpu(smp_processor_id(), allbutself);
+
+	if (cpumask_equal(mask, allbutself) &&
+	    cpumask_equal(cpu_online_mask, cpu_callout_mask))
 		send_IPI_allbutself(CALL_FUNCTION_VECTOR);
 	else
 		send_IPI_mask(mask, CALL_FUNCTION_VECTOR);
+
+	free_cpumask_var(allbutself);
 }
 
 /*