diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index ed6642ad03e073fcd5a4d35d02ba9f6bcb5221b0..25f01d0bc149cc388ce5a8e66d556669809e2b34 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -78,6 +78,14 @@ struct mmu_gather_batch {
 #define MAX_GATHER_BATCH	\
 	((PAGE_SIZE - sizeof(struct mmu_gather_batch)) / sizeof(void *))
 
+/*
+ * Limit the maximum number of mmu_gather batches to reduce a risk of soft
+ * lockups for non-preemptible kernels on huge machines when a lot of memory
+ * is zapped during unmapping.
+ * 10K pages freed at once should be safe even without a preemption point.
+ */
+#define MAX_GATHER_BATCH_COUNT	(10000UL/MAX_GATHER_BATCH)
+
 /* struct mmu_gather is an opaque type used by the mm code for passing around
  * any data needed by arch specific code for tlb_remove_page.
  */
@@ -96,6 +104,7 @@ struct mmu_gather {
 	struct mmu_gather_batch *active;
 	struct mmu_gather_batch	local;
 	struct page		*__pages[MMU_GATHER_BUNDLE];
+	unsigned int		batch_count;
 };
 
 #define HAVE_GENERIC_MMU_GATHER
diff --git a/mm/memory.c b/mm/memory.c
index e0a9b0ce4f102f8cfef2d6d7c6581d71f7595ff4..49fb1cf0861172b2860538e7c48afa0279087794 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -184,10 +184,14 @@ static int tlb_next_batch(struct mmu_gather *tlb)
 		return 1;
 	}
 
+	if (tlb->batch_count == MAX_GATHER_BATCH_COUNT)
+		return 0;
+
 	batch = (void *)__get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0);
 	if (!batch)
 		return 0;
 
+	tlb->batch_count++;
 	batch->next = NULL;
 	batch->nr   = 0;
 	batch->max  = MAX_GATHER_BATCH;
@@ -216,6 +220,7 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm)
 	tlb->local.nr   = 0;
 	tlb->local.max  = ARRAY_SIZE(tlb->__pages);
 	tlb->active     = &tlb->local;
+	tlb->batch_count = 0;
 
 #ifdef CONFIG_HAVE_RCU_TABLE_FREE
 	tlb->batch = NULL;