diff --git a/arch/mips/include/asm/smp.h b/arch/mips/include/asm/smp.h index 2b25d1ba1ea0..16f1ea9ab191 100644 --- a/arch/mips/include/asm/smp.h +++ b/arch/mips/include/asm/smp.h @@ -23,6 +23,7 @@ extern int smp_num_siblings; extern cpumask_t cpu_sibling_map[]; extern cpumask_t cpu_core_map[]; +extern cpumask_t cpu_foreign_map; #define raw_smp_processor_id() (current_thread_info()->cpu) diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c index faa46ebd9dda..d0744cc77ea7 100644 --- a/arch/mips/kernel/smp.c +++ b/arch/mips/kernel/smp.c @@ -63,6 +63,13 @@ EXPORT_SYMBOL(cpu_sibling_map); cpumask_t cpu_core_map[NR_CPUS] __read_mostly; EXPORT_SYMBOL(cpu_core_map); +/* + * A logcal cpu mask containing only one VPE per core to + * reduce the number of IPIs on large MT systems. + */ +cpumask_t cpu_foreign_map __read_mostly; +EXPORT_SYMBOL(cpu_foreign_map); + /* representing cpus for which sibling maps can be computed */ static cpumask_t cpu_sibling_setup_map; @@ -103,6 +110,29 @@ static inline void set_cpu_core_map(int cpu) } } +/* + * Calculate a new cpu_foreign_map mask whenever a + * new cpu appears or disappears. + */ +static inline void calculate_cpu_foreign_map(void) +{ + int i, k, core_present; + cpumask_t temp_foreign_map; + + /* Re-calculate the mask */ + for_each_online_cpu(i) { + core_present = 0; + for_each_cpu(k, &temp_foreign_map) + if (cpu_data[i].package == cpu_data[k].package && + cpu_data[i].core == cpu_data[k].core) + core_present = 1; + if (!core_present) + cpumask_set_cpu(i, &temp_foreign_map); + } + + cpumask_copy(&cpu_foreign_map, &temp_foreign_map); +} + struct plat_smp_ops *mp_ops; EXPORT_SYMBOL(mp_ops); @@ -146,6 +176,8 @@ asmlinkage void start_secondary(void) set_cpu_sibling_map(cpu); set_cpu_core_map(cpu); + calculate_cpu_foreign_map(); + cpumask_set_cpu(cpu, &cpu_callin_map); synchronise_count_slave(cpu); @@ -173,9 +205,18 @@ void __irq_entry smp_call_function_interrupt(void) static void stop_this_cpu(void *dummy) { /* - * Remove this CPU: + * Remove this CPU. Be a bit slow here and + * set the bits for every online CPU so we don't miss + * any IPI whilst taking this VPE down. */ + + cpumask_copy(&cpu_foreign_map, cpu_online_mask); + + /* Make it visible to every other CPU */ + smp_mb(); + set_cpu_online(smp_processor_id(), false); + calculate_cpu_foreign_map(); local_irq_disable(); while (1); } @@ -197,6 +238,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus) mp_ops->prepare_cpus(max_cpus); set_cpu_sibling_map(0); set_cpu_core_map(0); + calculate_cpu_foreign_map(); #ifndef CONFIG_HOTPLUG_CPU init_cpu_present(cpu_possible_mask); #endif diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c index 7f660dc67596..a5974ddba44b 100644 --- a/arch/mips/mm/c-r4k.c +++ b/arch/mips/mm/c-r4k.c @@ -37,6 +37,7 @@ #include /* for run_uncached() */ #include #include +#include /* * Special Variant of smp_call_function for use by cache functions: @@ -51,9 +52,16 @@ static inline void r4k_on_each_cpu(void (*func) (void *info), void *info) { preempt_disable(); -#ifndef CONFIG_MIPS_MT_SMP - smp_call_function(func, info, 1); -#endif + /* + * The Coherent Manager propagates address-based cache ops to other + * cores but not index-based ops. However, r4k_on_each_cpu is used + * in both cases so there is no easy way to tell what kind of op is + * executed to the other cores. The best we can probably do is + * to restrict that call when a CM is not present because both + * CM-based SMP protocols (CMP & CPS) restrict index-based cache ops. + */ + if (!mips_cm_present()) + smp_call_function_many(&cpu_foreign_map, func, info, 1); func(info); preempt_enable(); }