From: David Hildenbrand david@redhat.com
mainline inclusion from mainline-6.8-rc1 commit b06dc281aa9901076898d4d0a7bde588f11bc204 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I9CESE CVE: NA
-------------------------------------------------
Let's mimic what we did with folio_add_file_rmap_*() and folio_add_anon_rmap_*() so we can similarly replace page_remove_rmap() next.
Make the compiler always special-case on the granularity by using __always_inline.
We're adding folio_remove_rmap_ptes() handling right away, as we want to use that soon for batching rmap operations when unmapping PTE-mapped large folios.
Link: https://lkml.kernel.org/r/20231220224504.646757-24-david@redhat.com Signed-off-by: David Hildenbrand david@redhat.com Cc: Hugh Dickins hughd@google.com Cc: Matthew Wilcox (Oracle) willy@infradead.org Cc: Muchun Song muchun.song@linux.dev Cc: Muchun Song songmuchun@bytedance.com Cc: Peter Xu peterx@redhat.com Cc: Ryan Roberts ryan.roberts@arm.com Cc: Yin Fengwei fengwei.yin@intel.com Signed-off-by: Andrew Morton akpm@linux-foundation.org (cherry picked from commit b06dc281aa9901076898d4d0a7bde588f11bc204) Signed-off-by: Kefeng Wang wangkefeng.wang@huawei.com --- include/linux/rmap.h | 6 ++++ mm/rmap.c | 82 +++++++++++++++++++++++++++++++++++--------- 2 files changed, 72 insertions(+), 16 deletions(-)
diff --git a/include/linux/rmap.h b/include/linux/rmap.h index 9075ac964c7e..179772439145 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -240,6 +240,12 @@ void folio_add_file_rmap_pmd(struct folio *, struct page *, struct vm_area_struct *); void page_remove_rmap(struct page *, struct vm_area_struct *, bool compound); +void folio_remove_rmap_ptes(struct folio *, struct page *, int nr_pages, + struct vm_area_struct *); +#define folio_remove_rmap_pte(folio, page, vma) \ + folio_remove_rmap_ptes(folio, page, 1, vma) +void folio_remove_rmap_pmd(struct folio *, struct page *, + struct vm_area_struct *);
void hugetlb_add_anon_rmap(struct folio *, struct vm_area_struct *, unsigned long address, rmap_t flags); diff --git a/mm/rmap.c b/mm/rmap.c index 4ae00c8560c6..d3b4259cb9b3 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1480,25 +1480,37 @@ void page_remove_rmap(struct page *page, struct vm_area_struct *vma, bool compound) { struct folio *folio = page_folio(page); + + if (likely(!compound)) + folio_remove_rmap_pte(folio, page, vma); + else + folio_remove_rmap_pmd(folio, page, vma); +} + +static __always_inline void __folio_remove_rmap(struct folio *folio, + struct page *page, int nr_pages, struct vm_area_struct *vma, + enum rmap_level level) +{ atomic_t *mapped = &folio->_nr_pages_mapped; - int nr = 0, nr_pmdmapped = 0; - bool last; + int last, nr = 0, nr_pmdmapped = 0; enum node_stat_item idx;
- VM_WARN_ON_FOLIO(folio_test_hugetlb(folio), folio); - VM_BUG_ON_PAGE(compound && !PageHead(page), page); - - /* Is page being unmapped by PTE? Is this its last map to be removed? */ - if (likely(!compound)) { - last = atomic_add_negative(-1, &page->_mapcount); - nr = last; - if (last && folio_test_large(folio)) { - nr = atomic_dec_return_relaxed(mapped); - nr = (nr < COMPOUND_MAPPED); - } - } else if (folio_test_pmd_mappable(folio)) { - /* That test is redundant: it's for safety or to optimize out */ + __folio_rmap_sanity_checks(folio, page, nr_pages, level); + + switch (level) { + case RMAP_LEVEL_PTE: + do { + last = atomic_add_negative(-1, &page->_mapcount); + if (last && folio_test_large(folio)) { + last = atomic_dec_return_relaxed(mapped); + last = (last < COMPOUND_MAPPED); + }
+ if (last) + nr++; + } while (page++, --nr_pages > 0); + break; + case RMAP_LEVEL_PMD: last = atomic_add_negative(-1, &folio->_entire_mapcount); if (last) { nr = atomic_sub_return_relaxed(COMPOUND_MAPPED, mapped); @@ -1513,6 +1525,7 @@ void page_remove_rmap(struct page *page, struct vm_area_struct *vma, nr = 0; } } + break; }
if (nr_pmdmapped) { @@ -1534,7 +1547,7 @@ void page_remove_rmap(struct page *page, struct vm_area_struct *vma, * is still mapped. */ if (folio_test_large(folio) && folio_test_anon(folio)) - if (!compound || nr < nr_pmdmapped) + if (level == RMAP_LEVEL_PTE || nr < nr_pmdmapped) deferred_split_folio(folio); }
@@ -1549,6 +1562,43 @@ void page_remove_rmap(struct page *page, struct vm_area_struct *vma, munlock_vma_folio(folio, vma); }
+/** + * folio_remove_rmap_ptes - remove PTE mappings from a page range of a folio + * @folio: The folio to remove the mappings from + * @page: The first page to remove + * @nr_pages: The number of pages that will be removed from the mapping + * @vma: The vm area from which the mappings are removed + * + * The page range of the folio is defined by [page, page + nr_pages) + * + * The caller needs to hold the page table lock. + */ +void folio_remove_rmap_ptes(struct folio *folio, struct page *page, + int nr_pages, struct vm_area_struct *vma) +{ + __folio_remove_rmap(folio, page, nr_pages, vma, RMAP_LEVEL_PTE); +} + +/** + * folio_remove_rmap_pmd - remove a PMD mapping from a page range of a folio + * @folio: The folio to remove the mapping from + * @page: The first page to remove + * @vma: The vm area from which the mapping is removed + * + * The page range of the folio is defined by [page, page + HPAGE_PMD_NR) + * + * The caller needs to hold the page table lock. + */ +void folio_remove_rmap_pmd(struct folio *folio, struct page *page, + struct vm_area_struct *vma) +{ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + __folio_remove_rmap(folio, page, HPAGE_PMD_NR, vma, RMAP_LEVEL_PMD); +#else + WARN_ON_ONCE(true); +#endif +} + /* * @arg: enum ttu_flags will be passed to this argument */