[merged mm-stable] filemap-optimize-folio-refount-update-in-filemap_map_pages.patch removed from -mm tree

[merged mm-stable] filemap-optimize-folio-refount-update-in-filemap_map_pages.patch removed from -mm tree

[Andrew Morton]

The quilt patch titled
     Subject: filemap: optimize folio refount update in filemap_map_pages
has been removed from the -mm tree.  Its filename was
     filemap-optimize-folio-refount-update-in-filemap_map_pages.patch

This patch was dropped because it was merged into the mm-stable branch
of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

------------------------------------------------------
From: Jinjiang Tu <tujinjiang@huawei.com>
Subject: filemap: optimize folio refount update in filemap_map_pages
Date: Thu, 4 Sep 2025 21:27:37 +0800

There are two meaningless folio refcount update for order0 folio in
filemap_map_pages().  First, filemap_map_order0_folio() adds folio
refcount after the folio is mapped to pte.  And then, filemap_map_pages()
drops a refcount grabbed by next_uptodate_folio().  We could remain the
refcount unchanged in this case.

As Matthew metenioned in [1], it is safe to call folio_unlock() before
calling folio_put() here, because the folio is in page cache with refcount
held, and truncation will wait for the unlock.

Optimize filemap_map_folio_range() with the same method too.

With this patch, we can get 8% performance gain for lmbench testcase
'lat_pagefault -P 1 file' in order0 folio case, the size of file is 512M.


Link: https://lkml.kernel.org/r/20250904132737.1250368-1-tujinjiang@huawei.com
Link: https://lore.kernel.org/all/aKcU-fzxeW3xT5Wv@casper.infradead.org/ [1]
Signed-off-by: Jinjiang Tu <tujinjiang@huawei.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/filemap.c |   20 ++++++++++++++------
 1 file changed, 14 insertions(+), 6 deletions(-)

--- a/mm/filemap.c~filemap-optimize-folio-refount-update-in-filemap_map_pages
+++ a/mm/filemap.c
@@ -3665,6 +3665,7 @@ static vm_fault_t filemap_map_folio_rang
 			unsigned long addr, unsigned int nr_pages,
 			unsigned long *rss, unsigned short *mmap_miss)
 {
+	unsigned int ref_from_caller = 1;
 	vm_fault_t ret = 0;
 	struct page *page = folio_page(folio, start);
 	unsigned int count = 0;
@@ -3698,7 +3699,8 @@ skip:
 		if (count) {
 			set_pte_range(vmf, folio, page, count, addr);
 			*rss += count;
-			folio_ref_add(folio, count);
+			folio_ref_add(folio, count - ref_from_caller);
+			ref_from_caller = 0;
 			if (in_range(vmf->address, addr, count * PAGE_SIZE))
 				ret = VM_FAULT_NOPAGE;
 		}
@@ -3713,12 +3715,16 @@ skip:
 	if (count) {
 		set_pte_range(vmf, folio, page, count, addr);
 		*rss += count;
-		folio_ref_add(folio, count);
+		folio_ref_add(folio, count - ref_from_caller);
+		ref_from_caller = 0;
 		if (in_range(vmf->address, addr, count * PAGE_SIZE))
 			ret = VM_FAULT_NOPAGE;
 	}
 
 	vmf->pte = old_ptep;
+	if (ref_from_caller)
+		/* Locked folios cannot get truncated. */
+		folio_ref_dec(folio);
 
 	return ret;
 }
@@ -3731,7 +3737,7 @@ static vm_fault_t filemap_map_order0_fol
 	struct page *page = &folio->page;
 
 	if (PageHWPoison(page))
-		return ret;
+		goto out;
 
 	/* See comment of filemap_map_folio_range() */
 	if (!folio_test_workingset(folio))
@@ -3743,15 +3749,18 @@ static vm_fault_t filemap_map_order0_fol
 	 * the fault-around logic.
 	 */
 	if (!pte_none(ptep_get(vmf->pte)))
-		return ret;
+		goto out;
 
 	if (vmf->address == addr)
 		ret = VM_FAULT_NOPAGE;
 
 	set_pte_range(vmf, folio, page, 1, addr);
 	(*rss)++;
-	folio_ref_inc(folio);
+	return ret;
 
+out:
+	/* Locked folios cannot get truncated. */
+	folio_ref_dec(folio);
 	return ret;
 }
 
@@ -3811,7 +3820,6 @@ vm_fault_t filemap_map_pages(struct vm_f
 					nr_pages, &rss, &mmap_miss);
 
 		folio_unlock(folio);
-		folio_put(folio);
 	} while ((folio = next_uptodate_folio(&xas, mapping, end_pgoff)) != NULL);
 	add_mm_counter(vma->vm_mm, folio_type, rss);
 	pte_unmap_unlock(vmf->pte, vmf->ptl);
_

Patches currently in -mm which might be from tujinjiang@huawei.com are

mm-hugetlb-fix-folio-is-still-mapped-when-deleted.patch