--- zzzz-none-000/linux-3.10.107/arch/parisc/include/asm/tlbflush.h	2017-06-27 09:49:32.000000000 +0000
+++ scorpion-7490-727/linux-3.10.107/arch/parisc/include/asm/tlbflush.h	2021-02-04 17:41:59.000000000 +0000
@@ -13,6 +13,9 @@
  * active at any one time on the Merced bus.  This tlb purge
  * synchronisation is fairly lightweight and harmless so we activate
  * it on all systems not just the N class.
+
+ * It is also used to ensure PTE updates are atomic and consistent
+ * with the TLB.
  */
 extern spinlock_t pa_tlb_lock;
 
@@ -24,20 +27,24 @@
 
 #define smp_flush_tlb_all()	flush_tlb_all()
 
+int __flush_tlb_range(unsigned long sid,
+	unsigned long start, unsigned long end);
+
+#define flush_tlb_range(vma, start, end) \
+	__flush_tlb_range((vma)->vm_mm->context, start, end)
+
+#define flush_tlb_kernel_range(start, end) \
+	__flush_tlb_range(0, start, end)
+
 /*
  * flush_tlb_mm()
  *
- * XXX This code is NOT valid for HP-UX compatibility processes,
- * (although it will probably work 99% of the time). HP-UX
- * processes are free to play with the space id's and save them
- * over long periods of time, etc. so we have to preserve the
- * space and just flush the entire tlb. We need to check the
- * personality in order to do that, but the personality is not
- * currently being set correctly.
- *
- * Of course, Linux processes could do the same thing, but
- * we don't support that (and the compilers, dynamic linker,
- * etc. do not do that).
+ * The code to switch to a new context is NOT valid for processes
+ * which play with the space id's.  Thus, we have to preserve the
+ * space and just flush the entire tlb.  However, the compilers,
+ * dynamic linker, etc, do not manipulate space id's, so there
+ * could be a significant performance benefit in switching contexts
+ * and not flushing the whole tlb.
  */
 
 static inline void flush_tlb_mm(struct mm_struct *mm)
@@ -45,10 +52,18 @@
 	BUG_ON(mm == &init_mm); /* Should never happen */
 
 #if 1 || defined(CONFIG_SMP)
+	/* Except for very small threads, flushing the whole TLB is
+	 * faster than using __flush_tlb_range.  The pdtlb and pitlb
+	 * instructions are very slow because of the TLB broadcast.
+	 * It might be faster to do local range flushes on all CPUs
+	 * on PA 2.0 systems.
+	 */
 	flush_tlb_all();
 #else
 	/* FIXME: currently broken, causing space id and protection ids
-	 *  to go out of sync, resulting in faults on userspace accesses.
+	 * to go out of sync, resulting in faults on userspace accesses.
+	 * This approach needs further investigation since running many
+	 * small applications (e.g., GCC testsuite) is faster on HP-UX.
 	 */
 	if (mm) {
 		if (mm->context != 0)
@@ -65,22 +80,12 @@
 {
 	unsigned long flags, sid;
 
-	/* For one page, it's not worth testing the split_tlb variable */
-
-	mb();
 	sid = vma->vm_mm->context;
 	purge_tlb_start(flags);
 	mtsp(sid, 1);
 	pdtlb(addr);
-	pitlb(addr);
+	if (unlikely(split_tlb))
+		pitlb(addr);
 	purge_tlb_end(flags);
 }
-
-void __flush_tlb_range(unsigned long sid,
-	unsigned long start, unsigned long end);
-
-#define flush_tlb_range(vma,start,end) __flush_tlb_range((vma)->vm_mm->context,start,end)
-
-#define flush_tlb_kernel_range(start, end) __flush_tlb_range(0,start,end)
-
 #endif