[PATCH 1/2] ARM: mm: avoid setting nG bit for user mappings that aren't present

[Will Deacon]

Swap entries are encoding in ptes such that !pte_present(pte) and
pte_file(pte). The remaining bits of the descriptor are used to identify
the swapfile and offset within it to the swap entry.

When writing such a pte for a user virtual address, set_pte_at
unconditionally sets the nG bit, which (in the case of LPAE) will
corrupt the swapfile offset and lead to a BUG:

[  140.494067] swap_free: Unused swap offset entry 000763b4
[  140.509989] BUG: Bad page map in process rs:main Q:Reg  pte:0ec76800 pmd:8f92e003

This patch fixes the problem by only setting the nG bit for user
mappings that are actually present.

Signed-off-by: Will Deacon <will.deacon at arm.com>
---
 arch/arm/include/asm/pgtable.h |   34 ++++++++++++++++++----------------
 arch/arm/mm/flush.c            |    2 --
 2 files changed, 18 insertions(+), 18 deletions(-)

diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index f66626d..d88f9f0 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -195,6 +195,18 @@ static inline pte_t *pmd_page_vaddr(pmd_t pmd)
 
 #define pte_clear(mm,addr,ptep)	set_pte_ext(ptep, __pte(0), 0)
 
+#define pte_none(pte)		(!pte_val(pte))
+#define pte_present(pte)	(pte_val(pte) & L_PTE_PRESENT)
+#define pte_write(pte)		(!(pte_val(pte) & L_PTE_RDONLY))
+#define pte_dirty(pte)		(pte_val(pte) & L_PTE_DIRTY)
+#define pte_young(pte)		(pte_val(pte) & L_PTE_YOUNG)
+#define pte_exec(pte)		(!(pte_val(pte) & L_PTE_XN))
+#define pte_special(pte)	(0)
+
+#define pte_present_user(pte) \
+	((pte_val(pte) & (L_PTE_PRESENT | L_PTE_USER)) == \
+	 (L_PTE_PRESENT | L_PTE_USER))
+
 #if __LINUX_ARM_ARCH__ < 6
 static inline void __sync_icache_dcache(pte_t pteval)
 {
@@ -206,25 +218,15 @@ extern void __sync_icache_dcache(pte_t pteval);
 static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep, pte_t pteval)
 {
-	if (addr >= TASK_SIZE)
-		set_pte_ext(ptep, pteval, 0);
-	else {
+	unsigned long ext = 0;
+
+	if (addr < TASK_SIZE && pte_present_user(pteval)) {
 		__sync_icache_dcache(pteval);
-		set_pte_ext(ptep, pteval, PTE_EXT_NG);
+		ext |= PTE_EXT_NG;
 	}
-}
 
-#define pte_none(pte)		(!pte_val(pte))
-#define pte_present(pte)	(pte_val(pte) & L_PTE_PRESENT)
-#define pte_write(pte)		(!(pte_val(pte) & L_PTE_RDONLY))
-#define pte_dirty(pte)		(pte_val(pte) & L_PTE_DIRTY)
-#define pte_young(pte)		(pte_val(pte) & L_PTE_YOUNG)
-#define pte_exec(pte)		(!(pte_val(pte) & L_PTE_XN))
-#define pte_special(pte)	(0)
-
-#define pte_present_user(pte) \
-	((pte_val(pte) & (L_PTE_PRESENT | L_PTE_USER)) == \
-	 (L_PTE_PRESENT | L_PTE_USER))
+	set_pte_ext(ptep, pteval, ext);
+}
 
 #define PTE_BIT_FUNC(fn,op) \
 static inline pte_t pte_##fn(pte_t pte) { pte_val(pte) op; return pte; }
diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index 7745854..40ca11e 100644
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@@ -231,8 +231,6 @@ void __sync_icache_dcache(pte_t pteval)
 	struct page *page;
 	struct address_space *mapping;
 
-	if (!pte_present_user(pteval))
-		return;
 	if (cache_is_vipt_nonaliasing() && !pte_exec(pteval))
 		/* only flush non-aliasing VIPT caches for exec mappings */
 		return;
-- 
1.7.4.1