In the page reclaim code, we only track the CPU(s) where the TLB needs
to be flushed, rather than all the individual mappings that may be getting
invalidated.
Use broadcast TLB flushing when that is available.
Signed-off-by: Rik van Riel <riel@xxxxxxxxxxx>
---
arch/x86/mm/tlb.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 49b3e90503a3..746a89924f02 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -1321,7 +1321,9 @@ void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
* a local TLB flush is needed. Optimize this use-case by calling
* flush_tlb_func_local() directly in this case.
*/
- if (cpumask_any_but(&batch->cpumask, cpu) < nr_cpu_ids) {
+ if (cpu_feature_enabled(X86_FEATURE_INVLPGB)) {
+ invlpgb_flush_all_nonglobals();
+ } else if (cpumask_any_but(&batch->cpumask, cpu) < nr_cpu_ids) {
flush_tlb_multi(&batch->cpumask, info);
} else if (cpumask_test_cpu(cpu, &batch->cpumask)) {
lockdep_assert_irqs_enabled();
--
2.47.1
