powerpc/mm: handle protnone ptes on fork

We need to mark pages of parent process read only on fork.  Numa fault
pte needs a protnone ptes variant with saved write flag set.  On fork we
need to make sure we remove the saved write bit.  Instead of adding the
protnone check in the caller update ptep_set_wrprotect variants to clear
savedwrite bit.

Without this we see random segfaults in application on fork.

Fixes: c137a2757b886 ("powerpc/mm/autonuma: switch ppc64 to its own implementation of saved write")
Link: http://lkml.kernel.org/r/1488203787-17849-1-git-send-email-aneesh.kumar@linux.vnet.ibm.com
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Paul Mackerras <paulus@ozlabs.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 1eeeb72..f0b08ac 100644 (file)
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -347,23 +347,53 @@ static inline int __ptep_test_and_clear_young(struct mm_struct *mm,
        __r;                                                    \
 })
 
+static inline int pte_write(pte_t pte)
+{
+       return !!(pte_raw(pte) & cpu_to_be64(_PAGE_WRITE));
+}
+
+#ifdef CONFIG_NUMA_BALANCING
+#define pte_savedwrite pte_savedwrite
+static inline bool pte_savedwrite(pte_t pte)
+{
+       /*
+        * Saved write ptes are prot none ptes that doesn't have
+        * privileged bit sit. We mark prot none as one which has
+        * present and pviliged bit set and RWX cleared. To mark
+        * protnone which used to have _PAGE_WRITE set we clear
+        * the privileged bit.
+        */
+       return !(pte_raw(pte) & cpu_to_be64(_PAGE_RWX | _PAGE_PRIVILEGED));
+}
+#else
+#define pte_savedwrite pte_savedwrite
+static inline bool pte_savedwrite(pte_t pte)
+{
+       return false;
+}
+#endif
+
 #define __HAVE_ARCH_PTEP_SET_WRPROTECT
 static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
                                      pte_t *ptep)
 {
-       if ((pte_raw(*ptep) & cpu_to_be64(_PAGE_WRITE)) == 0)
-               return;
-
-       pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 0);
+       if (pte_write(*ptep))
+               pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 0);
+       else if (unlikely(pte_savedwrite(*ptep)))
+               pte_update(mm, addr, ptep, 0, _PAGE_PRIVILEGED, 0);
 }
 
 static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
                                           unsigned long addr, pte_t *ptep)
 {
-       if ((pte_raw(*ptep) & cpu_to_be64(_PAGE_WRITE)) == 0)
-               return;
-
-       pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 1);
+       /*
+        * We should not find protnone for hugetlb, but this complete the
+        * interface.
+        */
+       if (pte_write(*ptep))
+               pte_update(mm, addr, ptep, _PAGE_WRITE, 0, 1);
+       else if (unlikely(pte_savedwrite(*ptep)))
+               pte_update(mm, addr, ptep, 0, _PAGE_PRIVILEGED, 1);
 }
 
 #define __HAVE_ARCH_PTEP_GET_AND_CLEAR
@@ -397,11 +427,6 @@ static inline void pte_clear(struct mm_struct *mm, unsigned long addr,
        pte_update(mm, addr, ptep, ~0UL, 0, 0);
 }
 
-static inline int pte_write(pte_t pte)
-{
-       return !!(pte_raw(pte) & cpu_to_be64(_PAGE_WRITE));
-}
-
 static inline int pte_dirty(pte_t pte)
 {
        return !!(pte_raw(pte) & cpu_to_be64(_PAGE_DIRTY));
@@ -466,19 +491,6 @@ static inline pte_t pte_clear_savedwrite(pte_t pte)
        return __pte(pte_val(pte) | _PAGE_PRIVILEGED);
 }
 
-#define pte_savedwrite pte_savedwrite
-static inline bool pte_savedwrite(pte_t pte)
-{
-       /*
-        * Saved write ptes are prot none ptes that doesn't have
-        * privileged bit sit. We mark prot none as one which has
-        * present and pviliged bit set and RWX cleared. To mark
-        * protnone which used to have _PAGE_WRITE set we clear
-        * the privileged bit.
-        */
-       VM_BUG_ON(!pte_protnone(pte));
-       return !(pte_raw(pte) & cpu_to_be64(_PAGE_RWX | _PAGE_PRIVILEGED));
-}
 #endif /* CONFIG_NUMA_BALANCING */
 
 static inline int pte_present(pte_t pte)
@@ -982,11 +994,10 @@ static inline int __pmdp_test_and_clear_young(struct mm_struct *mm,
 static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long addr,
                                      pmd_t *pmdp)
 {
-
-       if ((pmd_raw(*pmdp) & cpu_to_be64(_PAGE_WRITE)) == 0)
-               return;
-
-       pmd_hugepage_update(mm, addr, pmdp, _PAGE_WRITE, 0);
+       if (pmd_write((*pmdp)))
+               pmd_hugepage_update(mm, addr, pmdp, _PAGE_WRITE, 0);
+       else if (unlikely(pmd_savedwrite(*pmdp)))
+               pmd_hugepage_update(mm, addr, pmdp, 0, _PAGE_PRIVILEGED);
 }
 
 static inline int pmd_trans_huge(pmd_t pmd)