diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h
index 0baf7f0..f1a0dac 100644
--- a/arch/arm/include/asm/tlb.h
+++ b/arch/arm/include/asm/tlb.h
@@ -98,15 +98,25 @@
 	}
 }
 
-static inline void tlb_flush_mmu(struct mmu_gather *tlb)
+static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
 {
 	tlb_flush(tlb);
+}
+
+static inline void tlb_flush_mmu_free(struct mmu_gather *tlb)
+{
 	free_pages_and_swap_cache(tlb->pages, tlb->nr);
 	tlb->nr = 0;
 	if (tlb->pages == tlb->local)
 		__tlb_alloc_page(tlb);
 }
 
+static inline void tlb_flush_mmu(struct mmu_gather *tlb)
+{
+	tlb_flush_mmu_tlbonly(tlb);
+	tlb_flush_mmu_free(tlb);
+}
+
 static inline void
 tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
 {
diff --git a/arch/ia64/include/asm/tlb.h b/arch/ia64/include/asm/tlb.h
index bc5efc7..39d64e0 100644
--- a/arch/ia64/include/asm/tlb.h
+++ b/arch/ia64/include/asm/tlb.h
@@ -91,18 +91,9 @@
 #define RR_RID_MASK	0x00000000ffffff00L
 #define RR_TO_RID(val) 	((val >> 8) & 0xffffff)
 
-/*
- * Flush the TLB for address range START to END and, if not in fast mode, release the
- * freed pages that where gathered up to this point.
- */
 static inline void
-ia64_tlb_flush_mmu (struct mmu_gather *tlb, unsigned long start, unsigned long end)
+ia64_tlb_flush_mmu_tlbonly(struct mmu_gather *tlb, unsigned long start, unsigned long end)
 {
-	unsigned long i;
-	unsigned int nr;
-
-	if (!tlb->need_flush)
-		return;
 	tlb->need_flush = 0;
 
 	if (tlb->fullmm) {
@@ -135,6 +126,14 @@
 		flush_tlb_range(&vma, ia64_thash(start), ia64_thash(end));
 	}
 
+}
+
+static inline void
+ia64_tlb_flush_mmu_free(struct mmu_gather *tlb)
+{
+	unsigned long i;
+	unsigned int nr;
+
 	/* lastly, release the freed pages */
 	nr = tlb->nr;
 
@@ -144,6 +143,19 @@
 		free_page_and_swap_cache(tlb->pages[i]);
 }
 
+/*
+ * Flush the TLB for address range START to END and, if not in fast mode, release the
+ * freed pages that where gathered up to this point.
+ */
+static inline void
+ia64_tlb_flush_mmu (struct mmu_gather *tlb, unsigned long start, unsigned long end)
+{
+	if (!tlb->need_flush)
+		return;
+	ia64_tlb_flush_mmu_tlbonly(tlb, start, end);
+	ia64_tlb_flush_mmu_free(tlb);
+}
+
 static inline void __tlb_alloc_page(struct mmu_gather *tlb)
 {
 	unsigned long addr = __get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0);
@@ -206,6 +218,16 @@
 	return tlb->max - tlb->nr;
 }
 
+static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
+{
+	ia64_tlb_flush_mmu_tlbonly(tlb, tlb->start_addr, tlb->end_addr);
+}
+
+static inline void tlb_flush_mmu_free(struct mmu_gather *tlb)
+{
+	ia64_tlb_flush_mmu_free(tlb);
+}
+
 static inline void tlb_flush_mmu(struct mmu_gather *tlb)
 {
 	ia64_tlb_flush_mmu(tlb, tlb->start_addr, tlb->end_addr);
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index c544b6f..a25f09f 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -59,12 +59,23 @@
 	tlb->batch = NULL;
 }
 
-static inline void tlb_flush_mmu(struct mmu_gather *tlb)
+static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
 {
 	__tlb_flush_mm_lazy(tlb->mm);
+}
+
+static inline void tlb_flush_mmu_free(struct mmu_gather *tlb)
+{
 	tlb_table_flush(tlb);
 }
 
+
+static inline void tlb_flush_mmu(struct mmu_gather *tlb)
+{
+	tlb_flush_mmu_tlbonly(tlb);
+	tlb_flush_mmu_free(tlb);
+}
+
 static inline void tlb_finish_mmu(struct mmu_gather *tlb,
 				  unsigned long start, unsigned long end)
 {
diff --git a/arch/sh/include/asm/tlb.h b/arch/sh/include/asm/tlb.h
index 362192e..62f80d2 100644
--- a/arch/sh/include/asm/tlb.h
+++ b/arch/sh/include/asm/tlb.h
@@ -86,6 +86,14 @@
 	}
 }
 
+static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
+{
+}
+
+static inline void tlb_flush_mmu_free(struct mmu_gather *tlb)
+{
+}
+
 static inline void tlb_flush_mmu(struct mmu_gather *tlb)
 {
 }
diff --git a/arch/um/include/asm/tlb.h b/arch/um/include/asm/tlb.h
index 29b0301..16eb63f 100644
--- a/arch/um/include/asm/tlb.h
+++ b/arch/um/include/asm/tlb.h
@@ -59,13 +59,25 @@
 			       unsigned long end);
 
 static inline void
+tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
+{
+	flush_tlb_mm_range(tlb->mm, tlb->start, tlb->end);
+}
+
+static inline void
+tlb_flush_mmu_free(struct mmu_gather *tlb)
+{
+	init_tlb_gather(tlb);
+}
+
+static inline void
 tlb_flush_mmu(struct mmu_gather *tlb)
 {
 	if (!tlb->need_flush)
 		return;
 
-	flush_tlb_mm_range(tlb->mm, tlb->start, tlb->end);
-	init_tlb_gather(tlb);
+	tlb_flush_mmu_tlbonly(tlb);
+	tlb_flush_mmu_free(tlb);
 }
 
 /* tlb_finish_mmu