Rework ptep_set_access_flags and fix sun4c

Some changes done a while ago to avoid pounding on ptep_set_access_flags and
update_mmu_cache in some race situations break sun4c which requires
update_mmu_cache() to always be called on minor faults.

This patch reworks ptep_set_access_flags() semantics, implementations and
callers so that it's now responsible for returning whether an update is
necessary or not (basically whether the PTE actually changed).  This allow
fixing the sparc implementation to always return 1 on sun4c.

[akpm@linux-foundation.org: fixes, cleanups]
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: David Miller <davem@davemloft.net>
Cc: Mark Fortescue <mark@mtfhpc.demon.co.uk>
Acked-by: William Lee Irwin III <wli@holomorphy.com>
Cc: "Luck, Tony" <tony.luck@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

11 files changed, 92 insertions, 46 deletions

diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index dc8f99ee305f..7d7bcf990e99 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -27,13 +27,20 @@ do {				  					\
  * Largely same as above, but only sets the access flags (dirty,
  * accessed, and writable). Furthermore, we know it always gets set
  * to a "more permissive" setting, which allows most architectures
- * to optimize this.
+ * to optimize this. We return whether the PTE actually changed, which
+ * in turn instructs the caller to do things like update__mmu_cache.
+ * This used to be done in the caller, but sparc needs minor faults to
+ * force that call on sun4c so we changed this macro slightly
  */
 #define ptep_set_access_flags(__vma, __address, __ptep, __entry, __dirty) \
-do {				  					  \
-	set_pte_at((__vma)->vm_mm, (__address), __ptep, __entry);	  \
-	flush_tlb_page(__vma, __address);				  \
-} while (0)
+({									  \
+	int __changed = !pte_same(*(__ptep), __entry);			  \
+	if (__changed) {						  \
+		set_pte_at((__vma)->vm_mm, (__address), __ptep, __entry); \
+		flush_tlb_page(__vma, __address);			  \
+	}								  \
+	__changed;							  \
+})
 #endif
 
 #ifndef __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
diff --git a/include/asm-i386/pgtable.h b/include/asm-i386/pgtable.h
index d62bdb029efa..628fa7747d0c 100644
--- a/include/asm-i386/pgtable.h
+++ b/include/asm-i386/pgtable.h
@@ -285,13 +285,15 @@ static inline pte_t native_local_ptep_get_and_clear(pte_t *ptep)
  */
 #define  __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
 #define ptep_set_access_flags(vma, address, ptep, entry, dirty)		\
-do {									\
-	if (dirty) {							\
+({									\
+	int __changed = !pte_same(*(ptep), entry);			\
+	if (__changed && dirty) {					\
 		(ptep)->pte_low = (entry).pte_low;			\
 		pte_update_defer((vma)->vm_mm, (address), (ptep));	\
 		flush_tlb_page(vma, address);				\
 	}								\
-} while (0)
+	__changed;							\
+})
 
 #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_DIRTY
 #define ptep_test_and_clear_dirty(vma, addr, ptep) ({			\
diff --git a/include/asm-ia64/pgtable.h b/include/asm-ia64/pgtable.h
index 670b706411b8..6580f31b3135 100644
--- a/include/asm-ia64/pgtable.h
+++ b/include/asm-ia64/pgtable.h
@@ -533,16 +533,23 @@ extern void lazy_mmu_prot_update (pte_t pte);
  * daccess_bit in ivt.S).
  */
 #ifdef CONFIG_SMP
-# define ptep_set_access_flags(__vma, __addr, __ptep, __entry, __safely_writable)	\
-do {											\
-	if (__safely_writable) {							\
-		set_pte(__ptep, __entry);						\
-		flush_tlb_page(__vma, __addr);						\
-	}										\
-} while (0)
+# define ptep_set_access_flags(__vma, __addr, __ptep, __entry, __safely_writable) \
+({									\
+	int __changed = !pte_same(*(__ptep), __entry);			\
+	if (__changed && __safely_writable) {				\
+		set_pte(__ptep, __entry);				\
+		flush_tlb_page(__vma, __addr);				\
+	}								\
+	__changed;							\
+})
 #else
-# define ptep_set_access_flags(__vma, __addr, __ptep, __entry, __safely_writable)	\
-	ptep_establish(__vma, __addr, __ptep, __entry)
+# define ptep_set_access_flags(__vma, __addr, __ptep, __entry, __safely_writable) \
+({									\
+	int __changed = !pte_same(*(__ptep), __entry);			\
+	if (__changed)							\
+		ptep_establish(__vma, __addr, __ptep, __entry);		\
+	__changed;							\
+})
 #endif
 
 #  ifdef CONFIG_VIRTUAL_MEM_MAP
diff --git a/include/asm-powerpc/pgtable-ppc32.h b/include/asm-powerpc/pgtable-ppc32.h
index c863bdb2889c..7fb730c62f83 100644
--- a/include/asm-powerpc/pgtable-ppc32.h
+++ b/include/asm-powerpc/pgtable-ppc32.h
@@ -673,10 +673,14 @@ static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry, int dirty)
 }
 
 #define  ptep_set_access_flags(__vma, __address, __ptep, __entry, __dirty) \
-	do {								   \
-		__ptep_set_access_flags(__ptep, __entry, __dirty);	   \
-		flush_tlb_page_nohash(__vma, __address);	       	   \
-	} while(0)
+({									   \
+	int __changed = !pte_same(*(__ptep), __entry);			   \
+	if (__changed) {						   \
+		__ptep_set_access_flags(__ptep, __entry, __dirty);    	   \
+		flush_tlb_page_nohash(__vma, __address);		   \
+	}								   \
+	__changed;							   \
+})
 
 /*
  * Macro to mark a page protection value as "uncacheable".
diff --git a/include/asm-powerpc/pgtable-ppc64.h b/include/asm-powerpc/pgtable-ppc64.h
index 704c4e669fe0..3cfd98f44bfe 100644
--- a/include/asm-powerpc/pgtable-ppc64.h
+++ b/include/asm-powerpc/pgtable-ppc64.h
@@ -413,10 +413,14 @@ static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry, int dirty)
 	:"cc");
 }
 #define  ptep_set_access_flags(__vma, __address, __ptep, __entry, __dirty) \
-	do {								   \
-		__ptep_set_access_flags(__ptep, __entry, __dirty);	   \
-		flush_tlb_page_nohash(__vma, __address);	       	   \
-	} while(0)
+({									   \
+	int __changed = !pte_same(*(__ptep), __entry);			   \
+	if (__changed) {						   \
+		__ptep_set_access_flags(__ptep, __entry, __dirty);    	   \
+		flush_tlb_page_nohash(__vma, __address);		   \
+	}								   \
+	__changed;							   \
+})
 
 /*
  * Macro to mark a page protection value as "uncacheable".
diff --git a/include/asm-ppc/pgtable.h b/include/asm-ppc/pgtable.h
index bed452d4a5f0..9d0ce9ff5840 100644
--- a/include/asm-ppc/pgtable.h
+++ b/include/asm-ppc/pgtable.h
@@ -694,10 +694,14 @@ static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry, int dirty)
 }
 
 #define  ptep_set_access_flags(__vma, __address, __ptep, __entry, __dirty) \
-	do {								   \
-		__ptep_set_access_flags(__ptep, __entry, __dirty);	   \
-		flush_tlb_page_nohash(__vma, __address);	       	   \
-	} while(0)
+({									   \
+	int __changed = !pte_same(*(__ptep), __entry);			   \
+	if (__changed) {						   \
+		__ptep_set_access_flags(__ptep, __entry, __dirty);    	   \
+		flush_tlb_page_nohash(__vma, __address);		   \
+	}								   \
+	__changed;							   \
+})
 
 /*
  * Macro to mark a page protection value as "uncacheable".
diff --git a/include/asm-s390/pgtable.h b/include/asm-s390/pgtable.h
index 8fe8d42e64c3..0a307bb2f353 100644
--- a/include/asm-s390/pgtable.h
+++ b/include/asm-s390/pgtable.h
@@ -744,7 +744,12 @@ ptep_establish(struct vm_area_struct *vma,
 }
 
 #define ptep_set_access_flags(__vma, __address, __ptep, __entry, __dirty) \
-	ptep_establish(__vma, __address, __ptep, __entry)
+({									  \
+	int __changed = !pte_same(*(__ptep), __entry);			  \
+	if (__changed)							  \
+		ptep_establish(__vma, __address, __ptep, __entry);	  \
+	__changed;							  \
+})
 
 /*
  * Test and clear dirty bit in storage key.
diff --git a/include/asm-sparc/pgtable.h b/include/asm-sparc/pgtable.h
index 4f0a5ba0d6a0..59229aeba27b 100644
--- a/include/asm-sparc/pgtable.h
+++ b/include/asm-sparc/pgtable.h
@@ -446,6 +446,17 @@ extern int io_remap_pfn_range(struct vm_area_struct *vma,
 #define GET_IOSPACE(pfn)		(pfn >> (BITS_PER_LONG - 4))
 #define GET_PFN(pfn)			(pfn & 0x0fffffffUL)
 
+#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
+#define ptep_set_access_flags(__vma, __address, __ptep, __entry, __dirty) \
+({									  \
+	int __changed = !pte_same(*(__ptep), __entry);			  \
+	if (__changed) {						  \
+		set_pte_at((__vma)->vm_mm, (__address), __ptep, __entry); \
+		flush_tlb_page(__vma, __address);			  \
+	}								  \
+	(sparc_cpu_model == sun4c) || __changed;			  \
+})
+
 #include <asm-generic/pgtable.h>
 
 #endif /* !(__ASSEMBLY__) */
diff --git a/include/asm-x86_64/pgtable.h b/include/asm-x86_64/pgtable.h
index 08b9831f2e14..0a71e0b9a619 100644
--- a/include/asm-x86_64/pgtable.h
+++ b/include/asm-x86_64/pgtable.h
@@ -395,12 +395,14 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
  * bit at the same time. */
 #define  __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
 #define ptep_set_access_flags(__vma, __address, __ptep, __entry, __dirty) \
-	do {								  \
-		if (__dirty) {						  \
-			set_pte(__ptep, __entry);			  \
-			flush_tlb_page(__vma, __address);		  \
-		}							  \
-	} while (0)
+({									  \
+	int __changed = !pte_same(*(__ptep), __entry);			  \
+	if (__changed && __dirty) {					  \
+		set_pte(__ptep, __entry);			  	  \
+		flush_tlb_page(__vma, __address);		  	  \
+	}								  \
+	__changed;							  \
+})
 
 /* Encode and de-code a swap entry */
 #define __swp_type(x)			(((x).val >> 1) & 0x3f)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index eb7180db3033..a45d1f0691ce 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -326,9 +326,10 @@ static void set_huge_ptep_writable(struct vm_area_struct *vma,
 	pte_t entry;
 
 	entry = pte_mkwrite(pte_mkdirty(*ptep));
-	ptep_set_access_flags(vma, address, ptep, entry, 1);
-	update_mmu_cache(vma, address, entry);
-	lazy_mmu_prot_update(entry);
+	if (ptep_set_access_flags(vma, address, ptep, entry, 1)) {
+		update_mmu_cache(vma, address, entry);
+		lazy_mmu_prot_update(entry);
+	}
 }
 
 
diff --git a/mm/memory.c b/mm/memory.c
index cb94488ab96d..f64cbf9baa36 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1691,9 +1691,10 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		flush_cache_page(vma, address, pte_pfn(orig_pte));
 		entry = pte_mkyoung(orig_pte);
 		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
-		ptep_set_access_flags(vma, address, page_table, entry, 1);
-		update_mmu_cache(vma, address, entry);
-		lazy_mmu_prot_update(entry);
+		if (ptep_set_access_flags(vma, address, page_table, entry,1)) {
+			update_mmu_cache(vma, address, entry);
+			lazy_mmu_prot_update(entry);
+		}
 		ret |= VM_FAULT_WRITE;
 		goto unlock;
 	}
@@ -2525,10 +2526,9 @@ static inline int handle_pte_fault(struct mm_struct *mm,
 		pte_t *pte, pmd_t *pmd, int write_access)
 {
 	pte_t entry;
-	pte_t old_entry;
 	spinlock_t *ptl;
 
-	old_entry = entry = *pte;
+	entry = *pte;
 	if (!pte_present(entry)) {
 		if (pte_none(entry)) {
 			if (vma->vm_ops) {
@@ -2561,8 +2561,7 @@ static inline int handle_pte_fault(struct mm_struct *mm,
 		entry = pte_mkdirty(entry);
 	}
 	entry = pte_mkyoung(entry);
-	if (!pte_same(old_entry, entry)) {
-		ptep_set_access_flags(vma, address, pte, entry, write_access);
+	if (ptep_set_access_flags(vma, address, pte, entry, write_access)) {
 		update_mmu_cache(vma, address, entry);
 		lazy_mmu_prot_update(entry);
 	} else {