diff options
Diffstat (limited to 'arch/x86/mm/tlb.c')
| -rw-r--r-- | arch/x86/mm/tlb.c | 24 |
1 files changed, 22 insertions, 2 deletions
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 39f80111e6f1..5d221709353e 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -911,11 +911,31 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next, * CR3 and cpu_tlbstate.loaded_mm are not all in sync. */ this_cpu_write(cpu_tlbstate.loaded_mm, LOADED_MM_SWITCHING); - barrier(); - /* Start receiving IPIs and then read tlb_gen (and LAM below) */ + /* + * Make sure this CPU is set in mm_cpumask() such that we'll + * receive invalidation IPIs. + * + * Rely on the smp_mb() implied by cpumask_set_cpu()'s atomic + * operation, or explicitly provide one. Such that: + * + * switch_mm_irqs_off() flush_tlb_mm_range() + * smp_store_release(loaded_mm, SWITCHING); atomic64_inc_return(tlb_gen) + * smp_mb(); // here // smp_mb() implied + * atomic64_read(tlb_gen); this_cpu_read(loaded_mm); + * + * we properly order against flush_tlb_mm_range(), where the + * loaded_mm load can happen in mative_flush_tlb_multi() -> + * should_flush_tlb(). + * + * This way switch_mm() must see the new tlb_gen or + * flush_tlb_mm_range() must see the new loaded_mm, or both. + */ if (next != &init_mm && !cpumask_test_cpu(cpu, mm_cpumask(next))) cpumask_set_cpu(cpu, mm_cpumask(next)); + else + smp_mb(); + next_tlb_gen = atomic64_read(&next->context.tlb_gen); ns = choose_new_asid(next, next_tlb_gen); |