From 2e3468778dbe3ec389a10c21a703bb8e5be5cfbc Mon Sep 17 00:00:00 2001 From: Peter Xu Date: Thu, 11 Aug 2022 12:13:29 -0400 Subject: mm: remember young/dirty bit for page migrations When page migration happens, we always ignore the young/dirty bit settings in the old pgtable, and marking the page as old in the new page table using either pte_mkold() or pmd_mkold(), and keeping the pte clean. That's fine from functional-wise, but that's not friendly to page reclaim because the moving page can be actively accessed within the procedure. Not to mention hardware setting the young bit can bring quite some overhead on some systems, e.g. x86_64 needs a few hundreds nanoseconds to set the bit. The same slowdown problem to dirty bits when the memory is first written after page migration happened. Actually we can easily remember the A/D bit configuration and recover the information after the page is migrated. To achieve it, define a new set of bits in the migration swap offset field to cache the A/D bits for old pte. Then when removing/recovering the migration entry, we can recover the A/D bits even if the page changed. One thing to mention is that here we used max_swapfile_size() to detect how many swp offset bits we have, and we'll only enable this feature if we know the swp offset is big enough to store both the PFN value and the A/D bits. Otherwise the A/D bits are dropped like before. Link: https://lkml.kernel.org/r/20220811161331.37055-6-peterx@redhat.com Signed-off-by: Peter Xu Reviewed-by: "Huang, Ying" Cc: Alistair Popple Cc: Andi Kleen Cc: Andrea Arcangeli Cc: David Hildenbrand Cc: Hugh Dickins Cc: "Kirill A . Shutemov" Cc: Minchan Kim Cc: Nadav Amit Cc: Vlastimil Babka Cc: Dave Hansen Signed-off-by: Andrew Morton --- mm/huge_memory.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) (limited to 'mm/huge_memory.c') diff --git a/mm/huge_memory.c b/mm/huge_memory.c index b4666774abf0..f4a656b279b1 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2121,7 +2121,8 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, write = is_writable_migration_entry(entry); if (PageAnon(page)) anon_exclusive = is_readable_exclusive_migration_entry(entry); - young = false; + young = is_migration_entry_young(entry); + dirty = is_migration_entry_dirty(entry); soft_dirty = pmd_swp_soft_dirty(old_pmd); uffd_wp = pmd_swp_uffd_wp(old_pmd); } else { @@ -2183,6 +2184,10 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, else swp_entry = make_readable_migration_entry( page_to_pfn(page + i)); + if (young) + swp_entry = make_migration_entry_young(swp_entry); + if (dirty) + swp_entry = make_migration_entry_dirty(swp_entry); entry = swp_entry_to_pte(swp_entry); if (soft_dirty) entry = pte_swp_mksoft_dirty(entry); @@ -3201,6 +3206,10 @@ int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, entry = make_readable_exclusive_migration_entry(page_to_pfn(page)); else entry = make_readable_migration_entry(page_to_pfn(page)); + if (pmd_young(pmdval)) + entry = make_migration_entry_young(entry); + if (pmd_dirty(pmdval)) + entry = make_migration_entry_dirty(entry); pmdswp = swp_entry_to_pmd(entry); if (pmd_soft_dirty(pmdval)) pmdswp = pmd_swp_mksoft_dirty(pmdswp); @@ -3226,13 +3235,18 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) entry = pmd_to_swp_entry(*pvmw->pmd); get_page(new); - pmde = pmd_mkold(mk_huge_pmd(new, READ_ONCE(vma->vm_page_prot))); + pmde = mk_huge_pmd(new, READ_ONCE(vma->vm_page_prot)); if (pmd_swp_soft_dirty(*pvmw->pmd)) pmde = pmd_mksoft_dirty(pmde); if (is_writable_migration_entry(entry)) pmde = maybe_pmd_mkwrite(pmde, vma); if (pmd_swp_uffd_wp(*pvmw->pmd)) pmde = pmd_wrprotect(pmd_mkuffd_wp(pmde)); + if (!is_migration_entry_young(entry)) + pmde = pmd_mkold(pmde); + /* NOTE: this may contain setting soft-dirty on some archs */ + if (PageDirty(new) && is_migration_entry_dirty(entry)) + pmde = pmd_mkdirty(pmde); if (PageAnon(new)) { rmap_t rmap_flags = RMAP_COMPOUND; -- cgit v1.2.3