From: Ryan Roberts ryan.roberts@arm.com
next inclusion from next-20240510 commit 3931b871c4936c00c4e27c469056d8da47a3493f category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I9OCYO CVE: NA
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...
--------------------------------
Rework madvise_cold_or_pageout_pte_range() to avoid splitting any large folio that is fully and contiguously mapped in the pageout/cold vm range. This change means that large folios will be maintained all the way to swap storage. This both improves performance during swap-out, by eliding the cost of splitting the folio, and sets us up nicely for maintaining the large folio when it is swapped back in (to be covered in a separate series).
Folios that are not fully mapped in the target range are still split, but note that behavior is changed so that if the split fails for any reason (folio locked, shared, etc) we now leave it as is and move to the next pte in the range and continue work on the proceeding folios. Previously any failure of this sort would cause the entire operation to give up and no folios mapped at higher addresses were paged out or made cold. Given large folios are becoming more common, this old behavior would have likely lead to wasted opportunities.
While we are at it, change the code that clears young from the ptes to use ptep_test_and_clear_young(), via the new mkold_ptes() batch helper function. This is more efficent than get_and_clear/modify/set, especially for contpte mappings on arm64, where the old approach would require unfolding/refolding and the new approach can be done in place.
Link: https://lkml.kernel.org/r/20240408183946.2991168-8-ryan.roberts@arm.com Signed-off-by: Ryan Roberts ryan.roberts@arm.com Reviewed-by: Barry Song v-songbaohua@oppo.com Acked-by: David Hildenbrand david@redhat.com Cc: Barry Song 21cnbao@gmail.com Cc: Chris Li chrisl@kernel.org Cc: Gao Xiang xiang@kernel.org Cc: "Huang, Ying" ying.huang@intel.com Cc: Kefeng Wang wangkefeng.wang@huawei.com Cc: Lance Yang ioworker0@gmail.com Cc: Matthew Wilcox (Oracle) willy@infradead.org Cc: Michal Hocko mhocko@suse.com Cc: Yang Shi shy828301@gmail.com Cc: Yu Zhao yuzhao@google.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Liu Shixin liushixin2@huawei.com --- include/linux/pgtable.h | 30 ++++++++++++++ mm/internal.h | 12 +++++- mm/madvise.c | 87 +++++++++++++++++++++++------------------ mm/memory.c | 4 +- 4 files changed, 92 insertions(+), 41 deletions(-)
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index 218921a74c0a..ecc561d49d5b 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -333,6 +333,36 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, } #endif
+#ifndef mkold_ptes +/** + * mkold_ptes - Mark PTEs that map consecutive pages of the same folio as old. + * @vma: VMA the pages are mapped into. + * @addr: Address the first page is mapped at. + * @ptep: Page table pointer for the first entry. + * @nr: Number of entries to mark old. + * + * May be overridden by the architecture; otherwise, implemented as a simple + * loop over ptep_test_and_clear_young(). + * + * Note that PTE bits in the PTE range besides the PFN can differ. For example, + * some PTEs might be write-protected. + * + * Context: The caller holds the page table lock. The PTEs map consecutive + * pages that belong to the same folio. The PTEs are all in the same PMD. + */ +static inline void mkold_ptes(struct vm_area_struct *vma, unsigned long addr, + pte_t *ptep, unsigned int nr) +{ + for (;;) { + ptep_test_and_clear_young(vma, addr, ptep); + if (--nr == 0) + break; + ptep++; + addr += PAGE_SIZE; + } +} +#endif + #ifndef __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_ARCH_HAS_NONLEAF_PMD_YOUNG) static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, diff --git a/mm/internal.h b/mm/internal.h index 2012f237616f..780d1d92020a 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -129,6 +129,8 @@ static inline pte_t __pte_batch_clear_ignored(pte_t pte, fpb_t flags) * @flags: Flags to modify the PTE batch semantics. * @any_writable: Optional pointer to indicate whether any entry except the * first one is writable. + * @any_young: Optional pointer to indicate whether any entry except the + * first one is young. * * Detect a PTE batch: consecutive (present) PTEs that map consecutive * pages of the same large folio. @@ -144,16 +146,18 @@ static inline pte_t __pte_batch_clear_ignored(pte_t pte, fpb_t flags) */ static inline int folio_pte_batch(struct folio *folio, unsigned long addr, pte_t *start_ptep, pte_t pte, int max_nr, fpb_t flags, - bool *any_writable) + bool *any_writable, bool *any_young) { unsigned long folio_end_pfn = folio_pfn(folio) + folio_nr_pages(folio); const pte_t *end_ptep = start_ptep + max_nr; pte_t expected_pte, *ptep; - bool writable; + bool writable, young; int nr;
if (any_writable) *any_writable = false; + if (any_young) + *any_young = false;
VM_WARN_ON_FOLIO(!pte_present(pte), folio); VM_WARN_ON_FOLIO(!folio_test_large(folio) || max_nr < 1, folio); @@ -167,6 +171,8 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr, pte = ptep_get(ptep); if (any_writable) writable = !!pte_write(pte); + if (any_young) + young = !!pte_young(pte); pte = __pte_batch_clear_ignored(pte, flags);
if (!pte_same(pte, expected_pte)) @@ -182,6 +188,8 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr,
if (any_writable) *any_writable |= writable; + if (any_young) + *any_young |= young;
nr = pte_batch_hint(ptep, pte); expected_pte = pte_advance_pfn(expected_pte, nr); diff --git a/mm/madvise.c b/mm/madvise.c index ce491a4f6f87..57ad2c766aa6 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -380,6 +380,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, LIST_HEAD(folio_list); bool pageout_anon_only_filter; unsigned int batch_count = 0; + int nr;
if (fatal_signal_pending(current)) return -EINTR; @@ -467,7 +468,8 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, return 0; flush_tlb_batched_pending(mm); arch_enter_lazy_mmu_mode(); - for (; addr < end; pte++, addr += PAGE_SIZE) { + for (; addr < end; pte += nr, addr += nr * PAGE_SIZE) { + nr = 1; ptent = ptep_get(pte);
if (++batch_count == SWAP_CLUSTER_MAX) { @@ -491,55 +493,66 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, continue;
/* - * Creating a THP page is expensive so split it only if we - * are sure it's worth. Split it if we are only owner. + * 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 swapped out whole. 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; - - if (folio_likely_mapped_shared(folio)) - break; - if (pageout_anon_only_filter && !folio_test_anon(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; + const fpb_t fpb_flags = FPB_IGNORE_DIRTY | + FPB_IGNORE_SOFT_DIRTY; + int max_nr = (end - addr) / PAGE_SIZE; + bool any_young; + + nr = folio_pte_batch(folio, addr, pte, ptent, max_nr, + fpb_flags, NULL, &any_young); + if (any_young) + ptent = pte_mkyoung(ptent); + + if (nr < folio_nr_pages(folio)) { + int err; + + if (folio_likely_mapped_shared(folio)) + continue; + if (pageout_anon_only_filter && !folio_test_anon(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); + start_pte = pte = + pte_offset_map_lock(mm, pmd, addr, &ptl); + if (!start_pte) + break; + arch_enter_lazy_mmu_mode(); + if (!err) + nr = 0; + continue; + } }
/* * Do not interfere with other mappings of this folio and - * non-LRU folio. + * non-LRU folio. 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_test_lru(folio) || folio_mapcount(folio) != 1) + if (!folio_test_lru(folio) || + folio_mapcount(folio) != folio_nr_pages(folio)) continue;
if (pageout_anon_only_filter && !folio_test_anon(folio)) continue;
- VM_BUG_ON_FOLIO(folio_test_large(folio), folio); - if (!pageout && pte_young(ptent)) { - ptent = ptep_get_and_clear_full(mm, addr, pte, - tlb->fullmm); - ptent = pte_mkold(ptent); - set_pte_at(mm, addr, pte, ptent); - tlb_remove_tlb_entry(tlb, pte, addr); + mkold_ptes(vma, addr, pte, nr); + tlb_remove_tlb_entries(tlb, pte, nr, addr); }
/* diff --git a/mm/memory.c b/mm/memory.c index 11d97d28aa37..64e1fd144d93 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -996,7 +996,7 @@ copy_present_ptes(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma flags |= FPB_IGNORE_SOFT_DIRTY;
nr = folio_pte_batch(folio, addr, src_pte, pte, max_nr, flags, - &any_writable); + &any_writable, NULL); folio_ref_add(folio, nr); if (folio_test_anon(folio)) { if (unlikely(folio_try_dup_anon_rmap_ptes(folio, page, @@ -1563,7 +1563,7 @@ static inline int zap_present_ptes(struct mmu_gather *tlb, */ if (unlikely(folio_test_large(folio) && max_nr != 1)) { nr = folio_pte_batch(folio, addr, pte, ptent, max_nr, fpb_flags, - NULL); + NULL, NULL);
zap_present_folio_ptes(tlb, vma, folio, page, pte, ptent, nr, addr, details, rss, force_flush,