[PATCH 4.9 154/157] mm: add follow_pte_pmd()

[Greg Kroah-Hartman]

From: Ross Zwisler <ross.zwisler@xxxxxxxxxxxxxxx>

commit 097963959594c5eccaba42510f7033f703211bda upstream.

Patch series "Write protect DAX PMDs in *sync path".

Currently dax_mapping_entry_mkclean() fails to clean and write protect
the pmd_t of a DAX PMD entry during an *sync operation.  This can result
in data loss, as detailed in patch 2.

This series is based on Dan's "libnvdimm-pending" branch, which is the
current home for Jan's "dax: Page invalidation fixes" series.  You can
find a working tree here:

  https://git.kernel.org/cgit/linux/kernel/git/zwisler/linux.git/log/?h=dax_pmd_clean

This patch (of 2):

Similar to follow_pte(), follow_pte_pmd() allows either a PTE leaf or a
huge page PMD leaf to be found and returned.

Link: http://lkml.kernel.org/r/1482272586-21177-2-git-send-email-ross.zwisler@xxxxxxxxxxxxxxx
Signed-off-by: Ross Zwisler <ross.zwisler@xxxxxxxxxxxxxxx>
Suggested-by: Dave Hansen <dave.hansen@xxxxxxxxx>
Cc: Alexander Viro <viro@xxxxxxxxxxxxxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxx>
Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
Cc: Dave Chinner <david@xxxxxxxxxxxxx>
Cc: Jan Kara <jack@xxxxxxx>
Cc: Matthew Wilcox <mawilcox@xxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
[bwh: Backported to 4.9: adjust context]
Signed-off-by: Ben Hutchings <ben@xxxxxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
 include/linux/mm.h |    2 ++
 mm/memory.c        |   37 ++++++++++++++++++++++++++++++-------
 2 files changed, 32 insertions(+), 7 deletions(-)

--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1269,6 +1269,8 @@ int copy_page_range(struct mm_struct *ds
 			struct vm_area_struct *vma);
 void unmap_mapping_range(struct address_space *mapping,
 		loff_t const holebegin, loff_t const holelen, int even_cows);
+int follow_pte_pmd(struct mm_struct *mm, unsigned long address,
+			     pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp);
 int follow_pfn(struct vm_area_struct *vma, unsigned long address,
 	unsigned long *pfn);
 int follow_phys(struct vm_area_struct *vma, unsigned long address,
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3780,8 +3780,8 @@ int __pmd_alloc(struct mm_struct *mm, pu
 }
 #endif /* __PAGETABLE_PMD_FOLDED */
 
-static int __follow_pte(struct mm_struct *mm, unsigned long address,
-		pte_t **ptepp, spinlock_t **ptlp)
+static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address,
+		pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp)
 {
 	pgd_t *pgd;
 	pud_t *pud;
@@ -3798,11 +3798,20 @@ static int __follow_pte(struct mm_struct
 
 	pmd = pmd_offset(pud, address);
 	VM_BUG_ON(pmd_trans_huge(*pmd));
-	if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
-		goto out;
 
-	/* We cannot handle huge page PFN maps. Luckily they don't exist. */
-	if (pmd_huge(*pmd))
+	if (pmd_huge(*pmd)) {
+		if (!pmdpp)
+			goto out;
+
+		*ptlp = pmd_lock(mm, pmd);
+		if (pmd_huge(*pmd)) {
+			*pmdpp = pmd;
+			return 0;
+		}
+		spin_unlock(*ptlp);
+	}
+
+	if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
 		goto out;
 
 	ptep = pte_offset_map_lock(mm, pmd, address, ptlp);
@@ -3825,9 +3834,23 @@ static inline int follow_pte(struct mm_s
 
 	/* (void) is needed to make gcc happy */
 	(void) __cond_lock(*ptlp,
-			   !(res = __follow_pte(mm, address, ptepp, ptlp)));
+			   !(res = __follow_pte_pmd(mm, address, ptepp, NULL,
+					   ptlp)));
+	return res;
+}
+
+int follow_pte_pmd(struct mm_struct *mm, unsigned long address,
+			     pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp)
+{
+	int res;
+
+	/* (void) is needed to make gcc happy */
+	(void) __cond_lock(*ptlp,
+			   !(res = __follow_pte_pmd(mm, address, ptepp, pmdpp,
+					   ptlp)));
 	return res;
 }
+EXPORT_SYMBOL(follow_pte_pmd);
 
 /**
  * follow_pfn - look up PFN at a user virtual address