diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h
index 01f6c2ca7ecd..9c567d243f61 100644
--- a/arch/powerpc/include/asm/book3s/64/radix.h
+++ b/arch/powerpc/include/asm/book3s/64/radix.h
@@ -202,7 +202,24 @@ static inline void radix__set_pte_at(struct mm_struct *mm, unsigned long addr,
 				 pte_t *ptep, pte_t pte, int percpu)
 {
 	*ptep = pte;
-	asm volatile("ptesync" : : : "memory");
+
+	/*
+	 * The architecture suggests a ptesync after setting the pte, which
+	 * orders the store that updates the pte with subsequent page table
+	 * walk accesses which may load the pte. Without this it may be
+	 * possible for a subsequent access to result in spurious fault.
+	 *
+	 * This is not necessary for correctness, because a spurious fault
+	 * is tolerated by the page fault handler, and this store will
+	 * eventually be seen. In testing, there was no noticable increase
+	 * in user faults on POWER9. Avoiding ptesync here is a significant
+	 * win for things like fork. If a future microarchitecture benefits
+	 * from ptesync, it should probably go into update_mmu_cache, rather
+	 * than set_pte_at (which is used to set ptes unrelated to faults).
+	 *
+	 * Spurious faults to vmalloc region are not tolerated, so there is
+	 * a ptesync in flush_cache_vmap.
+	 */
 }
 
 static inline int radix__pmd_bad(pmd_t pmd)
diff --git a/arch/powerpc/include/asm/cacheflush.h b/arch/powerpc/include/asm/cacheflush.h
index 11843e37d9cf..e9662648e72d 100644
--- a/arch/powerpc/include/asm/cacheflush.h
+++ b/arch/powerpc/include/asm/cacheflush.h
@@ -26,6 +26,19 @@
 #define flush_cache_vmap(start, end)		do { } while (0)
 #define flush_cache_vunmap(start, end)		do { } while (0)
 
+#ifdef CONFIG_BOOK3S_64
+/*
+ * Book3s has no ptesync after setting a pte, so without this ptesync it's
+ * possible for a kernel virtual mapping access to return a spurious fault
+ * if it's accessed right after the pte is set. The page fault handler does
+ * not expect this type of fault. flush_cache_vmap is not exactly the right
+ * place to put this, but it seems to work well enough.
+ */
+#define flush_cache_vmap(start, end)		do { asm volatile("ptesync"); } while (0)
+#else
+#define flush_cache_vmap(start, end)		do { } while (0)
+#endif
+
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 extern void flush_dcache_page(struct page *page);
 #define flush_dcache_mmap_lock(mapping)		do { } while (0)
diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c
index d6f74cbf0fed..96f68c5aa1f5 100644
--- a/arch/powerpc/mm/pgtable-radix.c
+++ b/arch/powerpc/mm/pgtable-radix.c
@@ -1115,5 +1115,5 @@ void radix__ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep,
 		 * an access fault, which is defined by the architectue.
 		 */
 	}
-	asm volatile("ptesync" : : : "memory");
+	/* See ptesync comment in radix__set_pte_at */
 }