- else
- on_each_cpu_cond_mask(tlb_is_not_lazy, flush_tlb_func,
- (void *)info, 1, cpumask);
+ } else {
+ /*
+ * Although we could have used on_each_cpu_cond_mask(),
+ * open-coding it has performance advantages, as it eliminates
+ * the need for indirect calls or retpolines. In addition, it
+ * allows to use a designated cpumask for evaluating the
+ * condition, instead of allocating one.
+ *
+ * This code works under the assumption that there are no nested
+ * TLB flushes, an assumption that is already made in
+ * flush_tlb_mm_range().
+ *
+ * cond_cpumask is logically a stack-local variable, but it is
+ * more efficient to have it off the stack and not to allocate
+ * it on demand. Preemption is disabled and this code is
+ * non-reentrant.
+ */
+ struct cpumask *cond_cpumask = this_cpu_ptr(&flush_tlb_mask);
+ int cpu;
+
+ cpumask_clear(cond_cpumask);
+
+ for_each_cpu(cpu, cpumask) {
+ if (tlb_is_not_lazy(cpu))
+ __cpumask_set_cpu(cpu, cond_cpumask);
+ }
+ smp_call_function_many(cond_cpumask, flush_tlb_func, (void *)info, 1);
+ }