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.

[punit.agrawal@arm.com: fix arm64 ltp failure]
Link: http://lkml.kernel.org/r/20170619170145.25577-5-punit.agrawal@arm.com
Link: http://lkml.kernel.org/r/20170522133604.11392-3-punit.agrawal@arm.com
Signed-off-by: Punit Agrawal <punit.agrawal@arm.com>
Acked-by: Steve Capper <steve.capper@arm.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Hillf Danton <hillf.zj@alibaba-inc.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/gup.c b/mm/gup.c
index 1e68bf21330299cd1e04aae8e28f10d082d87115..23f01c40c88f63cc88ff62548a4d120b0c406a8e 100644 (file)
--- 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;