mm: swap: entirely map large folios found in swapcache

When a large folio is found in the swapcache, the current implementation
requires calling do_swap_page() nr_pages times, resulting in nr_pages page
faults.  This patch opts to map the entire large folio at once to minimize
page faults.  Additionally, redundant checks and early exits for ARM64 MTE
restoring are removed.

Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Chuanhua Han <[email protected]>
Co-developed-by: Barry Song <[email protected]>
Signed-off-by: Barry Song <[email protected]>
Reviewed-by: Ryan Roberts <[email protected]>
Reviewed-by: "Huang, Ying" <[email protected]>
Cc: Andreas Larsson <[email protected]>
Cc: Baolin Wang <[email protected]>
Cc: Chris Li <[email protected]>
Cc: Christoph Hellwig <[email protected]>
Cc: David Hildenbrand <[email protected]>
Cc: "David S. Miller" <[email protected]>
Cc: Gao Xiang <[email protected]>
Cc: Hugh Dickins <[email protected]>
Cc: Johannes Weiner <[email protected]>
Cc: Kairui Song <[email protected]>
Cc: Khalid Aziz <[email protected]>
Cc: Len Brown <[email protected]>
Cc: Matthew Wilcox (Oracle) <[email protected]>
Cc: Pavel Machek <[email protected]>
Cc: "Rafael J. Wysocki" <[email protected]>
Cc: Suren Baghdasaryan <[email protected]>
Cc: Yosry Ahmed <[email protected]>
Cc: Yu Zhao <[email protected]>
Cc: Zi Yan <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>

1 files changed, 48 insertions, 11 deletions

diff --git a/mm/memory.c b/mm/memory.c
index 2aac2000f0de..70d42483cd46 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4010,6 +4010,10 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 	pte_t pte;
 	vm_fault_t ret = 0;
 	void *shadow = NULL;
+	int nr_pages;
+	unsigned long page_idx;
+	unsigned long address;
+	pte_t *ptep;
 
 	if (!pte_unmap_same(vmf))
 		goto out;
@@ -4208,6 +4212,38 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 		goto out_nomap;
 	}
 
+	nr_pages = 1;
+	page_idx = 0;
+	address = vmf->address;
+	ptep = vmf->pte;
+	if (folio_test_large(folio) && folio_test_swapcache(folio)) {
+		int nr = folio_nr_pages(folio);
+		unsigned long idx = folio_page_idx(folio, page);
+		unsigned long folio_start = address - idx * PAGE_SIZE;
+		unsigned long folio_end = folio_start + nr * PAGE_SIZE;
+		pte_t *folio_ptep;
+		pte_t folio_pte;
+
+		if (unlikely(folio_start < max(address & PMD_MASK, vma->vm_start)))
+			goto check_folio;
+		if (unlikely(folio_end > pmd_addr_end(address, vma->vm_end)))
+			goto check_folio;
+
+		folio_ptep = vmf->pte - idx;
+		folio_pte = ptep_get(folio_ptep);
+		if (!pte_same(folio_pte, pte_move_swp_offset(vmf->orig_pte, -idx)) ||
+		    swap_pte_batch(folio_ptep, nr, folio_pte) != nr)
+			goto check_folio;
+
+		page_idx = idx;
+		address = folio_start;
+		ptep = folio_ptep;
+		nr_pages = nr;
+		entry = folio->swap;
+		page = &folio->page;
+	}
+
+check_folio:
 	/*
 	 * PG_anon_exclusive reuses PG_mappedtodisk for anon pages. A swap pte
 	 * must never point at an anonymous page in the swapcache that is
@@ -4267,12 +4303,12 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 	 * We're already holding a reference on the page but haven't mapped it
 	 * yet.
 	 */
-	swap_free(entry);
+	swap_free_nr(entry, nr_pages);
 	if (should_try_to_free_swap(folio, vma, vmf->flags))
 		folio_free_swap(folio);
 
-	inc_mm_counter(vma->vm_mm, MM_ANONPAGES);
-	dec_mm_counter(vma->vm_mm, MM_SWAPENTS);
+	add_mm_counter(vma->vm_mm, MM_ANONPAGES, nr_pages);
+	add_mm_counter(vma->vm_mm, MM_SWAPENTS, -nr_pages);
 	pte = mk_pte(page, vma->vm_page_prot);
 
 	/*
@@ -4289,27 +4325,28 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 		}
 		rmap_flags |= RMAP_EXCLUSIVE;
 	}
-	flush_icache_page(vma, page);
+	folio_ref_add(folio, nr_pages - 1);
+	flush_icache_pages(vma, page, nr_pages);
 	if (pte_swp_soft_dirty(vmf->orig_pte))
 		pte = pte_mksoft_dirty(pte);
 	if (pte_swp_uffd_wp(vmf->orig_pte))
 		pte = pte_mkuffd_wp(pte);
-	vmf->orig_pte = pte;
+	vmf->orig_pte = pte_advance_pfn(pte, page_idx);
 
 	/* ksm created a completely new copy */
 	if (unlikely(folio != swapcache && swapcache)) {
-		folio_add_new_anon_rmap(folio, vma, vmf->address);
+		folio_add_new_anon_rmap(folio, vma, address);
 		folio_add_lru_vma(folio, vma);
 	} else {
-		folio_add_anon_rmap_pte(folio, page, vma, vmf->address,
+		folio_add_anon_rmap_ptes(folio, page, nr_pages, vma, address,
 					rmap_flags);
 	}
 
 	VM_BUG_ON(!folio_test_anon(folio) ||
 			(pte_write(pte) && !PageAnonExclusive(page)));
-	set_pte_at(vma->vm_mm, vmf->address, vmf->pte, pte);
-	arch_do_swap_page_nr(vma->vm_mm, vma, vmf->address,
-			pte, vmf->orig_pte, 1);
+	set_ptes(vma->vm_mm, address, ptep, pte, nr_pages);
+	arch_do_swap_page_nr(vma->vm_mm, vma, address,
+			pte, pte, nr_pages);
 
 	folio_unlock(folio);
 	if (folio != swapcache && swapcache) {
@@ -4333,7 +4370,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
 	}
 
 	/* No need to invalidate - it was non-present before */
-	update_mmu_cache_range(vmf, vma, vmf->address, vmf->pte, 1);
+	update_mmu_cache_range(vmf, vma, address, ptep, nr_pages);
 unlock:
 	if (vmf->pte)
 		pte_unmap_unlock(vmf->pte, vmf->ptl);