mm/madvise: optimize lazyfreeing with mTHP in madvise_free

This patch optimizes lazyfreeing with PTE-mapped mTHP[1] (Inspired by
David Hildenbrand[2]).  We aim to avoid unnecessary folio splitting if the
large folio is fully mapped within the target range.

If a large folio is locked or shared, or if we fail to split it, we just
leave it in place and advance to the next PTE in the range.  But note that
the behavior is changed; previously, any failure of this sort would cause
the entire operation to give up.  As large folios become more common,
sticking to the old way could result in wasted opportunities.

On an Intel I5 CPU, lazyfreeing a 1GiB VMA backed by PTE-mapped folios of
the same size results in the following runtimes for madvise(MADV_FREE) in
seconds (shorter is better):

Folio Size |   Old    |   New    | Change
------------------------------------------
      4KiB | 0.590251 | 0.590259 |    0%
     16KiB | 2.990447 | 0.185655 |  -94%
     32KiB | 2.547831 | 0.104870 |  -95%
     64KiB | 2.457796 | 0.052812 |  -97%
    128KiB | 2.281034 | 0.032777 |  -99%
    256KiB | 2.230387 | 0.017496 |  -99%
    512KiB | 2.189106 | 0.010781 |  -99%
   1024KiB | 2.183949 | 0.007753 |  -99%
   2048KiB | 0.002799 | 0.002804 |    0%

[1] https://lkml.kernel.org/r/20231207161211.2374093-5-ryan.roberts@arm.com
[2] https://lore.kernel.org/linux-mm/20240214204435.167852-1-david@redhat.com

Link: https://lkml.kernel.org/r/20240418134435.6092-5-ioworker0@gmail.com
Signed-off-by: Lance Yang <ioworker0@gmail.com>
Reviewed-by: Ryan Roberts <ryan.roberts@arm.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Barry Song <21cnbao@gmail.com>
Cc: Jeff Xie <xiehuan09@gmail.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Yin Fengwei <fengwei.yin@intel.com>
Cc: Zach O'Keefe <zokeefe@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/mm/madvise.c b/mm/madvise.c
index 5b5ba394992fd9cbc45d9df14a8ffc71351b06a1..56efea02e26c3fb30c6e25db9dcce261c3e7568c 100644 (file)
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -643,6 +643,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
                                unsigned long end, struct mm_walk *walk)
 
 {
+       const cydp_t cydp_flags = CYDP_CLEAR_YOUNG | CYDP_CLEAR_DIRTY;
        struct mmu_gather *tlb = walk->private;
        struct mm_struct *mm = tlb->mm;
        struct vm_area_struct *vma = walk->vma;
@@ -697,44 +698,57 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
                        continue;
 
                /*
-                * If pmd isn't transhuge but the folio is large and
-                * is owned by only this process, split it and
-                * deactivate all pages.
+                * If we encounter a large folio, only split it if it is not
+                * fully mapped within the range we are operating on. Otherwise
+                * leave it as is so that it can be marked as lazyfree. If we
+                * fail to split a folio, leave it in place and advance to the
+                * next pte in the range.
                 */
                if (folio_test_large(folio)) {
-                       int err;
+                       bool any_young, any_dirty;
 
-                       if (folio_likely_mapped_shared(folio))
-                               break;
-                       if (!folio_trylock(folio))
-                               break;
-                       folio_get(folio);
-                       arch_leave_lazy_mmu_mode();
-                       pte_unmap_unlock(start_pte, ptl);
-                       start_pte = NULL;
-                       err = split_folio(folio);
-                       folio_unlock(folio);
-                       folio_put(folio);
-                       if (err)
-                               break;
-                       start_pte = pte =
-                               pte_offset_map_lock(mm, pmd, addr, &ptl);
-                       if (!start_pte)
-                               break;
-                       arch_enter_lazy_mmu_mode();
-                       pte--;
-                       addr -= PAGE_SIZE;
-                       continue;
+                       nr = madvise_folio_pte_batch(addr, end, folio, pte,
+                                                    ptent, &any_young, &any_dirty);
+
+                       if (nr < folio_nr_pages(folio)) {
+                               int err;
+
+                               if (folio_likely_mapped_shared(folio))
+                                       continue;
+                               if (!folio_trylock(folio))
+                                       continue;
+                               folio_get(folio);
+                               arch_leave_lazy_mmu_mode();
+                               pte_unmap_unlock(start_pte, ptl);
+                               start_pte = NULL;
+                               err = split_folio(folio);
+                               folio_unlock(folio);
+                               folio_put(folio);
+                               pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
+                               start_pte = pte;
+                               if (!start_pte)
+                                       break;
+                               arch_enter_lazy_mmu_mode();
+                               if (!err)
+                                       nr = 0;
+                               continue;
+                       }
+
+                       if (any_young)
+                               ptent = pte_mkyoung(ptent);
+                       if (any_dirty)
+                               ptent = pte_mkdirty(ptent);
                }
 
                if (folio_test_swapcache(folio) || folio_test_dirty(folio)) {
                        if (!folio_trylock(folio))
                                continue;
                        /*
-                        * If folio is shared with others, we mustn't clear
-                        * the folio's dirty flag.
+                        * If we have a large folio at this point, we know it is
+                        * fully mapped so if its mapcount is the same as its
+                        * number of pages, it must be exclusive.
                         */
-                       if (folio_mapcount(folio) != 1) {
+                       if (folio_mapcount(folio) != folio_nr_pages(folio)) {
                                folio_unlock(folio);
                                continue;
                        }
@@ -750,19 +764,8 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
                }
 
                if (pte_young(ptent) || pte_dirty(ptent)) {
-                       /*
-                        * Some of architecture(ex, PPC) don't update TLB
-                        * with set_pte_at and tlb_remove_tlb_entry so for
-                        * the portability, remap the pte with old|clean
-                        * after pte clearing.
-                        */
-                       ptent = ptep_get_and_clear_full(mm, addr, pte,
-                                                       tlb->fullmm);
-
-                       ptent = pte_mkold(ptent);
-                       ptent = pte_mkclean(ptent);
-                       set_pte_at(mm, addr, pte, ptent);
-                       tlb_remove_tlb_entry(tlb, pte, addr);
+                       clear_young_dirty_ptes(vma, addr, pte, nr, cydp_flags);
+                       tlb_remove_tlb_entries(tlb, pte, nr, addr);
                }
                folio_mark_lazyfree(folio);
        }