powerpc/mm/autonuma: switch ppc64 to its own implementation of saved write

With this our protnone becomes a present pte with READ/WRITE/EXEC bit
cleared.  By default we also set _PAGE_PRIVILEGED on such pte.  This is
now used to help us identify a protnone pte that as saved write bit.
For such pte, we will clear the _PAGE_PRIVILEGED bit.  The pte still
remain non-accessible from both user and kernel.

[aneesh.kumar@linux.vnet.ibm.com: v3]
  Link: http://lkml.kernel.org/r/1487498625-10891-4-git-send-email-aneesh.kumar@linux.vnet.ibm.com
Link: http://lkml.kernel.org/r/1487050314-3892-3-git-send-email-aneesh.kumar@linux.vnet.ibm.com
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Acked-by: Michael Neuling <mikey@neuling.org>
Cc: Rik van Riel <riel@surriel.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Michael Ellerman <michaele@au1.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

arch/powerpc/include/asm/book3s/64/pgtable.h

@@ -1,6 +1,9 @@
 #ifndef _ASM_POWERPC_BOOK3S_64_PGTABLE_H_
 #define _ASM_POWERPC_BOOK3S_64_PGTABLE_H_
 
+#ifndef __ASSEMBLY__
+#include <linux/mmdebug.h>
+#endif
 /*
  * Common bits between hash and Radix page table
  */
@@ -434,15 +437,47 @@ static inline pte_t pte_clear_soft_dirty(pte_t pte)
 #endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */
 
 #ifdef CONFIG_NUMA_BALANCING
-/*
- * These work without NUMA balancing but the kernel does not care. See the
- * comment in include/asm-generic/pgtable.h . On powerpc, this will only
- * work for user pages and always return true for kernel pages.
- */
 static inline int pte_protnone(pte_t pte)
 {
-	return (pte_raw(pte) & cpu_to_be64(_PAGE_PRESENT | _PAGE_PRIVILEGED)) ==
+	return (pte_raw(pte) & cpu_to_be64(_PAGE_PRESENT | _PAGE_PTE | _PAGE_RWX)) ==
-		cpu_to_be64(_PAGE_PRESENT | _PAGE_PRIVILEGED);
+		cpu_to_be64(_PAGE_PRESENT | _PAGE_PTE);
+}
+
+#define pte_mk_savedwrite pte_mk_savedwrite
+static inline pte_t pte_mk_savedwrite(pte_t pte)
+{
+	/*
+	 * Used by Autonuma subsystem to preserve the write bit
+	 * while marking the pte PROT_NONE. Only allow this
+	 * on PROT_NONE pte
+	 */
+	VM_BUG_ON((pte_raw(pte) & cpu_to_be64(_PAGE_PRESENT | _PAGE_RWX | _PAGE_PRIVILEGED)) !=
+		  cpu_to_be64(_PAGE_PRESENT | _PAGE_PRIVILEGED));
+	return __pte(pte_val(pte) & ~_PAGE_PRIVILEGED);
+}
+
+#define pte_clear_savedwrite pte_clear_savedwrite
+static inline pte_t pte_clear_savedwrite(pte_t pte)
+{
+	/*
+	 * Used by KSM subsystem to make a protnone pte readonly.
+	 */
+	VM_BUG_ON(!pte_protnone(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 */
 
@@ -873,6 +908,8 @@ static inline pte_t *pmdp_ptep(pmd_t *pmd)
 #define pmd_mkclean(pmd)	pte_pmd(pte_mkclean(pmd_pte(pmd)))
 #define pmd_mkyoung(pmd)	pte_pmd(pte_mkyoung(pmd_pte(pmd)))
 #define pmd_mkwrite(pmd)	pte_pmd(pte_mkwrite(pmd_pte(pmd)))
+#define pmd_mk_savedwrite(pmd)	pte_pmd(pte_mk_savedwrite(pmd_pte(pmd)))
+#define pmd_clear_savedwrite(pmd)	pte_pmd(pte_clear_savedwrite(pmd_pte(pmd)))
 
 #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
 #define pmd_soft_dirty(pmd)    pte_soft_dirty(pmd_pte(pmd))
@@ -889,6 +926,7 @@ static inline int pmd_protnone(pmd_t pmd)
 
 #define __HAVE_ARCH_PMD_WRITE
 #define pmd_write(pmd)		pte_write(pmd_pte(pmd))
+#define pmd_savedwrite(pmd)	pte_savedwrite(pmd_pte(pmd))
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 extern pmd_t pfn_pmd(unsigned long pfn, pgprot_t pgprot);