mm, gup: ensure real head page is ref-counted when using hugepages

When speculatively taking references to a hugepage using
page_cache_add_speculative() in gup_huge_pmd(), it is assumed that the
page returned by pmd_page() is the head page.  Although normally true,
this assumption doesn't hold when the hugepage comprises of successive
page table entries such as when using contiguous bit on arm64 at PTE or
PMD levels.

This can be addressed by ensuring that the page passed to
page_cache_add_speculative() is the real head or by de-referencing the
head page within the function.

We take the first approach to keep the usage pattern aligned with
page_cache_get_speculative() where users already pass the appropriate
page, i.e., the de-referenced head.

Apply the same logic to fix gup_huge_[pud|pgd]() as well.

[[email protected]: fix arm64 ltp failure]
  Link: http://lkml.kernel.org/r/[email protected]
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Punit Agrawal <[email protected]>
Acked-by: Steve Capper <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: "Kirill A. Shutemov" <[email protected]>
Cc: Aneesh Kumar K.V <[email protected]>
Cc: Catalin Marinas <[email protected]>
Cc: Will Deacon <[email protected]>
Cc: Naoya Horiguchi <[email protected]>
Cc: Mark Rutland <[email protected]>
Cc: Hillf Danton <[email protected]>
Cc: Mike Kravetz <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

1 files changed, 6 insertions, 6 deletions

diff --git a/mm/gup.c b/mm/gup.c
index 1e68bf213302..23f01c40c88f 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1423,8 +1423,7 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 		return __gup_device_huge_pmd(orig, addr, end, pages, nr);
 
 	refs = 0;
-	head = pmd_page(orig);
-	page = head + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
+	page = pmd_page(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
 	do {
 		pages[*nr] = page;
 		(*nr)++;
@@ -1432,6 +1431,7 @@ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 		refs++;
 	} while (addr += PAGE_SIZE, addr != end);
 
+	head = compound_head(pmd_page(orig));
 	if (!page_cache_add_speculative(head, refs)) {
 		*nr -= refs;
 		return 0;
@@ -1461,8 +1461,7 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
 		return __gup_device_huge_pud(orig, addr, end, pages, nr);
 
 	refs = 0;
-	head = pud_page(orig);
-	page = head + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
+	page = pud_page(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
 	do {
 		pages[*nr] = page;
 		(*nr)++;
@@ -1470,6 +1469,7 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
 		refs++;
 	} while (addr += PAGE_SIZE, addr != end);
 
+	head = compound_head(pud_page(orig));
 	if (!page_cache_add_speculative(head, refs)) {
 		*nr -= refs;
 		return 0;
@@ -1498,8 +1498,7 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr,
 
 	BUILD_BUG_ON(pgd_devmap(orig));
 	refs = 0;
-	head = pgd_page(orig);
-	page = head + ((addr & ~PGDIR_MASK) >> PAGE_SHIFT);
+	page = pgd_page(orig) + ((addr & ~PGDIR_MASK) >> PAGE_SHIFT);
 	do {
 		pages[*nr] = page;
 		(*nr)++;
@@ -1507,6 +1506,7 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr,
 		refs++;
 	} while (addr += PAGE_SIZE, addr != end);
 
+	head = compound_head(pgd_page(orig));
 	if (!page_cache_add_speculative(head, refs)) {
 		*nr -= refs;
 		return 0;