1 files changed, 27 insertions, 34 deletions

diff --git a/mm/memory.c b/mm/memory.c
index 42ebdc33268e..83aef222f11b 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -238,23 +238,13 @@ void arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
 	__tlb_reset_range(tlb);
 }
 
-static void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
+static void tlb_flush_mmu_free(struct mmu_gather *tlb)
 {
-	if (!tlb->end)
-		return;
+	struct mmu_gather_batch *batch;
 
-	tlb_flush(tlb);
-	mmu_notifier_invalidate_range(tlb->mm, tlb->start, tlb->end);
 #ifdef CONFIG_HAVE_RCU_TABLE_FREE
 	tlb_table_flush(tlb);
 #endif
-	__tlb_reset_range(tlb);
-}
-
-static void tlb_flush_mmu_free(struct mmu_gather *tlb)
-{
-	struct mmu_gather_batch *batch;
-
 	for (batch = &tlb->local; batch && batch->nr; batch = batch->next) {
 		free_pages_and_swap_cache(batch->pages, batch->nr);
 		batch->nr = 0;
@@ -326,20 +316,31 @@ bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_
 
 #ifdef CONFIG_HAVE_RCU_TABLE_FREE
 
-static void tlb_remove_table_smp_sync(void *arg)
+/*
+ * See the comment near struct mmu_table_batch.
+ */
+
+/*
+ * If we want tlb_remove_table() to imply TLB invalidates.
+ */
+static inline void tlb_table_invalidate(struct mmu_gather *tlb)
 {
-	struct mm_struct __maybe_unused *mm = arg;
+#ifdef CONFIG_HAVE_RCU_TABLE_INVALIDATE
 	/*
-	 * On most architectures this does nothing. Simply delivering the
-	 * interrupt is enough to prevent races with software page table
-	 * walking like that done in get_user_pages_fast.
-	 *
-	 * See the comment near struct mmu_table_batch.
+	 * Invalidate page-table caches used by hardware walkers. Then we still
+	 * need to RCU-sched wait while freeing the pages because software
+	 * walkers can still be in-flight.
 	 */
-	tlb_flush_remove_tables_local(mm);
+	tlb_flush_mmu_tlbonly(tlb);
+#endif
+}
+
+static void tlb_remove_table_smp_sync(void *arg)
+{
+	/* Simply deliver the interrupt */
 }
 
-static void tlb_remove_table_one(void *table, struct mmu_gather *tlb)
+static void tlb_remove_table_one(void *table)
 {
 	/*
 	 * This isn't an RCU grace period and hence the page-tables cannot be
@@ -348,7 +349,7 @@ static void tlb_remove_table_one(void *table, struct mmu_gather *tlb)
 	 * It is however sufficient for software page-table walkers that rely on
 	 * IRQ disabling. See the comment near struct mmu_table_batch.
 	 */
-	smp_call_function(tlb_remove_table_smp_sync, tlb->mm, 1);
+	smp_call_function(tlb_remove_table_smp_sync, NULL, 1);
 	__tlb_remove_table(table);
 }
 
@@ -369,9 +370,8 @@ void tlb_table_flush(struct mmu_gather *tlb)
 {
 	struct mmu_table_batch **batch = &tlb->batch;
 
-	tlb_flush_remove_tables(tlb->mm);
-
 	if (*batch) {
+		tlb_table_invalidate(tlb);
 		call_rcu_sched(&(*batch)->rcu, tlb_remove_table_rcu);
 		*batch = NULL;
 	}
@@ -381,23 +381,16 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table)
 {
 	struct mmu_table_batch **batch = &tlb->batch;
 
-	/*
-	 * When there's less then two users of this mm there cannot be a
-	 * concurrent page-table walk.
-	 */
-	if (atomic_read(&tlb->mm->mm_users) < 2) {
-		__tlb_remove_table(table);
-		return;
-	}
-
 	if (*batch == NULL) {
 		*batch = (struct mmu_table_batch *)__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
 		if (*batch == NULL) {
-			tlb_remove_table_one(table, tlb);
+			tlb_table_invalidate(tlb);
+			tlb_remove_table_one(table);
 			return;
 		}
 		(*batch)->nr = 0;
 	}
+
 	(*batch)->tables[(*batch)->nr++] = table;
 	if ((*batch)->nr == MAX_TABLE_BATCH)
 		tlb_table_flush(tlb);