numa: fix /proc/<pid>/numa_maps for THP

commit 28093f9f34cedeaea0f481c58446d9dac6dd620f upstream.

In gather_pte_stats() a THP pmd is cast into a pte, which is wrong
because the layouts may differ depending on the architecture.  On s390
this will lead to inaccurate numa_maps accounting in /proc because of
misguided pte_present() and pte_dirty() checks on the fake pte.

On other architectures pte_present() and pte_dirty() may work by chance,
but there may be an issue with direct-access (dax) mappings w/o
underlying struct pages when HAVE_PTE_SPECIAL is set and THP is
available.  In vm_normal_page() the fake pte will be checked with
pte_special() and because there is no "special" bit in a pmd, this will
always return false and the VM_PFNMAP | VM_MIXEDMAP checking will be
skipped.  On dax mappings w/o struct pages, an invalid struct page
pointer would then be returned that can crash the kernel.

This patch fixes the numa_maps THP handling by introducing new "_pmd"
variants of the can_gather_numa_stats() and vm_normal_page() functions.

Signed-off-by: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Konstantin Khlebnikov <koct9i@gmail.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Jerome Marchand <jmarchan@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

1 files changed, 30 insertions, 3 deletions

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 09cd3edde08a..f6478301db00 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1435,6 +1435,32 @@ static struct page *can_gather_numa_stats(pte_t pte, struct vm_area_struct *vma,
 	return page;
 }
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static struct page *can_gather_numa_stats_pmd(pmd_t pmd,
+					      struct vm_area_struct *vma,
+					      unsigned long addr)
+{
+	struct page *page;
+	int nid;
+
+	if (!pmd_present(pmd))
+		return NULL;
+
+	page = vm_normal_page_pmd(vma, addr, pmd);
+	if (!page)
+		return NULL;
+
+	if (PageReserved(page))
+		return NULL;
+
+	nid = page_to_nid(page);
+	if (!node_isset(nid, node_states[N_MEMORY]))
+		return NULL;
+
+	return page;
+}
+#endif
+
 static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
 		unsigned long end, struct mm_walk *walk)
 {
@@ -1444,13 +1470,13 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
 	pte_t *orig_pte;
 	pte_t *pte;
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
-		pte_t huge_pte = *(pte_t *)pmd;
 		struct page *page;
 
-		page = can_gather_numa_stats(huge_pte, vma, addr);
+		page = can_gather_numa_stats_pmd(*pmd, vma, addr);
 		if (page)
-			gather_stats(page, md, pte_dirty(huge_pte),
+			gather_stats(page, md, pmd_dirty(*pmd),
 				     HPAGE_PMD_SIZE/PAGE_SIZE);
 		spin_unlock(ptl);
 		return 0;
@@ -1458,6 +1484,7 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
 
 	if (pmd_trans_unstable(pmd))
 		return 0;
+#endif
 	orig_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
 	do {
 		struct page *page = can_gather_numa_stats(*pte, vma, addr);