filemap: add filemap_map_folio_range()

filemap_map_folio_range() maps partial/full folio.  Comparing to original
filemap_map_pages(), it updates refcount once per folio instead of per
page and gets minor performance improvement for large folio.

With a will-it-scale.page_fault3 like app (change file write fault testing
to read fault testing.  Trying to upstream it to will-it-scale at [1]),
got 2% performance gain on a 48C/96T Cascade Lake test box with 96
processes running against xfs.

[1]: https://github.com/antonblanchard/will-it-scale/pull/37

Link: https://lkml.kernel.org/r/20230802151406.3735276-35-willy@infradead.org
Signed-off-by: Yin Fengwei <fengwei.yin@intel.com>
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 55 insertions, 54 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 8040545954bc..bdc1e0b811bf 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2168,16 +2168,6 @@ out:
 }
 EXPORT_SYMBOL(filemap_get_folios);
 
-static inline
-bool folio_more_pages(struct folio *folio, pgoff_t index, pgoff_t max)
-{
-	if (!folio_test_large(folio) || folio_test_hugetlb(folio))
-		return false;
-	if (index >= max)
-		return false;
-	return index < folio_next_index(folio) - 1;
-}
-
 /**
  * filemap_get_folios_contig - Get a batch of contiguous folios
  * @mapping:	The address_space to search
@@ -3436,10 +3426,10 @@ static bool filemap_map_pmd(struct vm_fault *vmf, struct folio *folio,
 	return false;
 }
 
-static struct folio *next_uptodate_page(struct folio *folio,
-				       struct address_space *mapping,
-				       struct xa_state *xas, pgoff_t end_pgoff)
+static struct folio *next_uptodate_folio(struct xa_state *xas,
+		struct address_space *mapping, pgoff_t end_pgoff)
 {
+	struct folio *folio = xas_next_entry(xas, end_pgoff);
 	unsigned long max_idx;
 
 	do {
@@ -3477,20 +3467,51 @@ skip:
 	return NULL;
 }
 
-static inline struct folio *first_map_page(struct address_space *mapping,
-					  struct xa_state *xas,
-					  pgoff_t end_pgoff)
+/*
+ * Map page range [start_page, start_page + nr_pages) of folio.
+ * start_page is gotten from start by folio_page(folio, start)
+ */
+static vm_fault_t filemap_map_folio_range(struct vm_fault *vmf,
+			struct folio *folio, unsigned long start,
+			unsigned long addr, unsigned int nr_pages)
 {
-	return next_uptodate_page(xas_find(xas, end_pgoff),
-				  mapping, xas, end_pgoff);
-}
+	vm_fault_t ret = 0;
+	struct vm_area_struct *vma = vmf->vma;
+	struct file *file = vma->vm_file;
+	struct page *page = folio_page(folio, start);
+	unsigned int mmap_miss = READ_ONCE(file->f_ra.mmap_miss);
+	unsigned int ref_count = 0, count = 0;
 
-static inline struct folio *next_map_page(struct address_space *mapping,
-					 struct xa_state *xas,
-					 pgoff_t end_pgoff)
-{
-	return next_uptodate_page(xas_next_entry(xas, end_pgoff),
-				  mapping, xas, end_pgoff);
+	do {
+		if (PageHWPoison(page))
+			continue;
+
+		if (mmap_miss > 0)
+			mmap_miss--;
+
+		/*
+		 * NOTE: If there're PTE markers, we'll leave them to be
+		 * handled in the specific fault path, and it'll prohibit the
+		 * fault-around logic.
+		 */
+		if (!pte_none(*vmf->pte))
+			continue;
+
+		if (vmf->address == addr)
+			ret = VM_FAULT_NOPAGE;
+
+		ref_count++;
+		do_set_pte(vmf, page, addr);
+		update_mmu_cache(vma, addr, vmf->pte);
+	} while (vmf->pte++, page++, addr += PAGE_SIZE, ++count < nr_pages);
+
+	/* Restore the vmf->pte */
+	vmf->pte -= nr_pages;
+
+	folio_ref_add(folio, ref_count);
+	WRITE_ONCE(file->f_ra.mmap_miss, mmap_miss);
+
+	return ret;
 }
 
 vm_fault_t filemap_map_pages(struct vm_fault *vmf,
@@ -3503,12 +3524,11 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf,
 	unsigned long addr;
 	XA_STATE(xas, &mapping->i_pages, start_pgoff);
 	struct folio *folio;
-	struct page *page;
-	unsigned int mmap_miss = READ_ONCE(file->f_ra.mmap_miss);
 	vm_fault_t ret = 0;
+	int nr_pages = 0;
 
 	rcu_read_lock();
-	folio = first_map_page(mapping, &xas, end_pgoff);
+	folio = next_uptodate_folio(&xas, mapping, end_pgoff);
 	if (!folio)
 		goto out;
 
@@ -3525,17 +3545,13 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf,
 		goto out;
 	}
 	do {
-again:
-		page = folio_file_page(folio, xas.xa_index);
-		if (PageHWPoison(page))
-			goto unlock;
-
-		if (mmap_miss > 0)
-			mmap_miss--;
+		unsigned long end;
 
 		addr += (xas.xa_index - last_pgoff) << PAGE_SHIFT;
 		vmf->pte += xas.xa_index - last_pgoff;
 		last_pgoff = xas.xa_index;
+		end = folio->index + folio_nr_pages(folio) - 1;
+		nr_pages = min(end, end_pgoff) - xas.xa_index + 1;
 
 		/*
 		 * NOTE: If there're PTE markers, we'll leave them to be
@@ -3545,32 +3561,17 @@ again:
 		if (!pte_none(ptep_get(vmf->pte)))
 			goto unlock;
 
-		/* We're about to handle the fault */
-		if (vmf->address == addr)
-			ret = VM_FAULT_NOPAGE;
+		ret |= filemap_map_folio_range(vmf, folio,
+				xas.xa_index - folio->index, addr, nr_pages);
 
-		do_set_pte(vmf, page, addr);
-		/* no need to invalidate: a not-present page won't be cached */
-		update_mmu_cache(vma, addr, vmf->pte);
-		if (folio_more_pages(folio, xas.xa_index, end_pgoff)) {
-			xas.xa_index++;
-			folio_ref_inc(folio);
-			goto again;
-		}
-		folio_unlock(folio);
-		continue;
 unlock:
-		if (folio_more_pages(folio, xas.xa_index, end_pgoff)) {
-			xas.xa_index++;
-			goto again;
-		}
 		folio_unlock(folio);
 		folio_put(folio);
-	} while ((folio = next_map_page(mapping, &xas, end_pgoff)) != NULL);
+		folio = next_uptodate_folio(&xas, mapping, end_pgoff);
+	} while (folio);
 	pte_unmap_unlock(vmf->pte, vmf->ptl);
 out:
 	rcu_read_unlock();
-	WRITE_ONCE(file->f_ra.mmap_miss, mmap_miss);
 	return ret;
 }
 EXPORT_SYMBOL(filemap_map_pages);