diff options
Diffstat (limited to 'arch/x86/mm/tlb.c')
| -rw-r--r-- | arch/x86/mm/tlb.c | 102 |
1 files changed, 95 insertions, 7 deletions
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 14f4f8f66aa8..4e5a5ddb9e4d 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -105,6 +105,8 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, } this_cpu_write(cpu_tlbstate.loaded_mm, next); + this_cpu_write(cpu_tlbstate.ctxs[0].ctx_id, next->context.ctx_id); + this_cpu_write(cpu_tlbstate.ctxs[0].tlb_gen, atomic64_read(&next->context.tlb_gen)); WARN_ON_ONCE(cpumask_test_cpu(cpu, mm_cpumask(next))); cpumask_set_cpu(cpu, mm_cpumask(next)); @@ -155,25 +157,102 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, switch_ldt(real_prev, next); } +/* + * flush_tlb_func_common()'s memory ordering requirement is that any + * TLB fills that happen after we flush the TLB are ordered after we + * read active_mm's tlb_gen. We don't need any explicit barriers + * because all x86 flush operations are serializing and the + * atomic64_read operation won't be reordered by the compiler. + */ static void flush_tlb_func_common(const struct flush_tlb_info *f, bool local, enum tlb_flush_reason reason) { + /* + * We have three different tlb_gen values in here. They are: + * + * - mm_tlb_gen: the latest generation. + * - local_tlb_gen: the generation that this CPU has already caught + * up to. + * - f->new_tlb_gen: the generation that the requester of the flush + * wants us to catch up to. + */ + struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm); + u64 mm_tlb_gen = atomic64_read(&loaded_mm->context.tlb_gen); + u64 local_tlb_gen = this_cpu_read(cpu_tlbstate.ctxs[0].tlb_gen); + /* This code cannot presently handle being reentered. */ VM_WARN_ON(!irqs_disabled()); + VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[0].ctx_id) != + loaded_mm->context.ctx_id); + if (this_cpu_read(cpu_tlbstate.state) != TLBSTATE_OK) { + /* + * leave_mm() is adequate to handle any type of flush, and + * we would prefer not to receive further IPIs. leave_mm() + * clears this CPU's bit in mm_cpumask(). + */ leave_mm(smp_processor_id()); return; } - if (f->end == TLB_FLUSH_ALL) { - local_flush_tlb(); - if (local) - count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); - trace_tlb_flush(reason, TLB_FLUSH_ALL); - } else { + if (unlikely(local_tlb_gen == mm_tlb_gen)) { + /* + * There's nothing to do: we're already up to date. This can + * happen if two concurrent flushes happen -- the first flush to + * be handled can catch us all the way up, leaving no work for + * the second flush. + */ + return; + } + + WARN_ON_ONCE(local_tlb_gen > mm_tlb_gen); + WARN_ON_ONCE(f->new_tlb_gen > mm_tlb_gen); + + /* + * If we get to this point, we know that our TLB is out of date. + * This does not strictly imply that we need to flush (it's + * possible that f->new_tlb_gen <= local_tlb_gen), but we're + * going to need to flush in the very near future, so we might + * as well get it over with. + * + * The only question is whether to do a full or partial flush. + * + * We do a partial flush if requested and two extra conditions + * are met: + * + * 1. f->new_tlb_gen == local_tlb_gen + 1. We have an invariant that + * we've always done all needed flushes to catch up to + * local_tlb_gen. If, for example, local_tlb_gen == 2 and + * f->new_tlb_gen == 3, then we know that the flush needed to bring + * us up to date for tlb_gen 3 is the partial flush we're + * processing. + * + * As an example of why this check is needed, suppose that there + * are two concurrent flushes. The first is a full flush that + * changes context.tlb_gen from 1 to 2. The second is a partial + * flush that changes context.tlb_gen from 2 to 3. If they get + * processed on this CPU in reverse order, we'll see + * local_tlb_gen == 1, mm_tlb_gen == 3, and end != TLB_FLUSH_ALL. + * If we were to use __flush_tlb_single() and set local_tlb_gen to + * 3, we'd be break the invariant: we'd update local_tlb_gen above + * 1 without the full flush that's needed for tlb_gen 2. + * + * 2. f->new_tlb_gen == mm_tlb_gen. This is purely an optimiation. + * Partial TLB flushes are not all that much cheaper than full TLB + * flushes, so it seems unlikely that it would be a performance win + * to do a partial flush if that won't bring our TLB fully up to + * date. By doing a full flush instead, we can increase + * local_tlb_gen all the way to mm_tlb_gen and we can probably + * avoid another flush in the very near future. + */ + if (f->end != TLB_FLUSH_ALL && + f->new_tlb_gen == local_tlb_gen + 1 && + f->new_tlb_gen == mm_tlb_gen) { + /* Partial flush */ unsigned long addr; unsigned long nr_pages = (f->end - f->start) >> PAGE_SHIFT; + addr = f->start; while (addr < f->end) { __flush_tlb_single(addr); @@ -182,7 +261,16 @@ static void flush_tlb_func_common(const struct flush_tlb_info *f, if (local) count_vm_tlb_events(NR_TLB_LOCAL_FLUSH_ONE, nr_pages); trace_tlb_flush(reason, nr_pages); + } else { + /* Full flush. */ + local_flush_tlb(); + if (local) + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); + trace_tlb_flush(reason, TLB_FLUSH_ALL); } + + /* Both paths above update our state to mm_tlb_gen. */ + this_cpu_write(cpu_tlbstate.ctxs[0].tlb_gen, mm_tlb_gen); } static void flush_tlb_func_local(void *info, enum tlb_flush_reason reason) @@ -253,7 +341,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, cpu = get_cpu(); /* This is also a barrier that synchronizes with switch_mm(). */ - inc_mm_tlb_gen(mm); + info.new_tlb_gen = inc_mm_tlb_gen(mm); /* Should we flush just the requested range? */ if ((end != TLB_FLUSH_ALL) && |