On Tue, Nov 10, 2020 at 10:16 AM Matthew Wilcox <willy@xxxxxxxxxxxxx> wrote: > > On Tue, Nov 10, 2020 at 10:12:48AM -0800, Yang Shi wrote: > > @@ -2142,6 +2151,10 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, > > int page_lru = page_is_file_lru(page); > > unsigned long start = address & HPAGE_PMD_MASK; > > > > + if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && > > + is_shared_exec_page(vma, page)) > > + goto out; > > Why include the IS_ENABLED() check? Once the ~50 patches I have pending > go in, shared executable THPs can exist without this option. And can't > we have executables on tmpfs today without this option too? Aha, yes, thanks for reminding. I had the patches baked in my tree before your patches were posted. We could have executables on tmpfs w/o that config. Will remove it. Thanks.
