[PATCH 1/2] mm: Allow architectures to request 'old' entries when prefaulting

[Kirill A. Shutemov]

On Sat, Dec 26, 2020 at 01:16:09PM -0800, Linus Torvalds wrote:
> On Sat, Dec 26, 2020 at 1:04 PM Hugh Dickins <hughd at google.com> wrote:
> >
> >
> > Hold on. I guess this one will suffer from the same bug as the previous.
> > I was about to report back, after satisfactory overnight testing of that
> > version - provided that one big little bug is fixed:
> >
> > --- a/mm/filemap.c
> > +++ b/mm/filemap.c
> > @@ -2919,7 +2919,7 @@ static bool filemap_map_pmd(struct vm_fa
> >
> >         if (pmd_none(*vmf->pmd) &&
> >             PageTransHuge(page) &&
> > -           do_set_pmd(vmf, page)) {
> > +           do_set_pmd(vmf, page) == 0) {
> >                 unlock_page(page);
> >                 return true;
> >         }
> 
> I missed that entirely, because when just reading the patch it looks
> fine and I didn't look at what do_set_pmd() function returns outside
> the patch.
> 
> And maybe it would be better to write it as
> 
>         if (pmd_none(*vmf->pmd) && PageTransHuge(page)) {
>                 vm_fault_t ret = do_set_pmd(vmf, page);
>                 if (!ret) {
>                         ...
> 
> instead to make it a bit more explicit about how that return value is
> a vm_fault_t there...
> 
> And see my other email about how I suspect there is still a leak in
> that patch for the previous test-case.

Ughh...

Here's the fixup I have so far. It doesn't blow up immediately, but please
take a closer look. Who knows what stupid mistake I did this time. :/

diff --git a/mm/filemap.c b/mm/filemap.c
index 3a92aaa59b9b..c4b374678e7d 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2837,16 +2837,21 @@ static bool filemap_map_pmd(struct vm_fault *vmf, struct page *page)
 	struct mm_struct *mm = vmf->vma->vm_mm;
 
 	/* Huge page is mapped? No need to proceed. */
-	if (pmd_trans_huge(*vmf->pmd))
-		return true;
-
-	if (pmd_none(*vmf->pmd) &&
-	    PageTransHuge(page) &&
-	    do_set_pmd(vmf, page)) {
+	if (pmd_trans_huge(*vmf->pmd)) {
 		unlock_page(page);
+		put_page(page);
 		return true;
 	}
 
+	if (pmd_none(*vmf->pmd) && PageTransHuge(page)) {
+	    vm_fault_t ret = do_set_pmd(vmf, page);
+	    if (!ret) {
+		    /* The page is mapped successfully, reference consumed. */
+		    unlock_page(page);
+		    return true;
+	    }
+	}
+
 	if (pmd_none(*vmf->pmd)) {
 		vmf->ptl = pmd_lock(mm, vmf->pmd);
 		if (likely(pmd_none(*vmf->pmd))) {
@@ -2867,7 +2872,7 @@ static bool filemap_map_pmd(struct vm_fault *vmf, struct page *page)
 	return false;
 }
 
-static struct page *next_stable_page(struct page *page, struct vm_fault *vmf,
+static struct page *next_uptodate_page(struct page *page, struct vm_fault *vmf,
 				     struct xa_state *xas, pgoff_t end_pgoff)
 {
 	struct address_space *mapping = vmf->vma->vm_file->f_mapping;
@@ -2914,15 +2919,16 @@ static inline struct page *first_map_page(struct vm_fault *vmf,
 					  struct xa_state *xas,
 					  pgoff_t end_pgoff)
 {
-	return next_stable_page(xas_find(xas, end_pgoff), vmf, xas, end_pgoff);
+	return next_uptodate_page(xas_find(xas, end_pgoff),
+				  vmf, xas, end_pgoff);
 }
 
 static inline struct page *next_map_page(struct vm_fault *vmf,
 					  struct xa_state *xas,
 					  pgoff_t end_pgoff)
 {
-	return next_stable_page(xas_next_entry(xas, end_pgoff),
-				vmf, xas, end_pgoff);
+	return next_uptodate_page(xas_next_entry(xas, end_pgoff),
+				  vmf, xas, end_pgoff);
 }
 
 void filemap_map_pages(struct vm_fault *vmf,
-- 
 Kirill A. Shutemov