diff --git a/sys/amd64/amd64/pmap.c b/sys/amd64/amd64/pmap.c
index f87d3b5c599b..3cb85301e93f 100644
--- a/sys/amd64/amd64/pmap.c
+++ b/sys/amd64/amd64/pmap.c
@@ -5192,7 +5192,7 @@ pmap_zero_page_idle(vm_page_t m)
 {
 	vm_offset_t va = PHYS_TO_DMAP(VM_PAGE_TO_PHYS(m));
 
-	pagezero((void *)va);
+	sse2_pagezero((void *)va);
 }
 
 /*
diff --git a/sys/amd64/amd64/support.S b/sys/amd64/amd64/support.S
index bc07fbda739c..1a4e910ee10e 100644
--- a/sys/amd64/amd64/support.S
+++ b/sys/amd64/amd64/support.S
@@ -78,6 +78,12 @@ ENTRY(sse2_pagezero)
 	movq	$-PAGE_SIZE,%rdx
 	subq	%rdx,%rdi
 	xorl	%eax,%eax
+	jmp	1f
+	/*
+	 * The loop takes 29 bytes.  Ensure that it doesn't cross a 32-byte
+	 * cache line.
+	 */
+	.p2align 5,0x90
 1:
 	movnti	%rax,(%rdi,%rdx)
 	movnti	%rax,8(%rdi,%rdx)
@@ -88,7 +94,7 @@ ENTRY(sse2_pagezero)
 	sfence
 	POP_FRAME_POINTER
 	ret
-END(pagezero)
+END(sse2_pagezero)
 
 ENTRY(bcmp)
 	PUSH_FRAME_POINTER
diff --git a/sys/amd64/include/md_var.h b/sys/amd64/include/md_var.h
index e4c50eba7642..f161c97d8e41 100644
--- a/sys/amd64/include/md_var.h
+++ b/sys/amd64/include/md_var.h
@@ -57,6 +57,7 @@ void	gsbase_load_fault(void) __asm(__STRING(gsbase_load_fault));
 void	fpstate_drop(struct thread *td);
 void	pagezero(void *addr);
 void	setidt(int idx, alias_for_inthand_t *func, int typ, int dpl, int ist);
+void	sse2_pagezero(void *addr);
 struct savefpu *get_pcb_user_save_td(struct thread *td);
 struct savefpu *get_pcb_user_save_pcb(struct pcb *pcb);
 
diff --git a/sys/i386/i386/support.s b/sys/i386/i386/support.s
index 63912b6aba86..03d08cb52855 100644
--- a/sys/i386/i386/support.s
+++ b/sys/i386/i386/support.s
@@ -69,9 +69,16 @@ ENTRY(sse2_pagezero)
 	movl	%ecx,%eax
 	addl	$4096,%eax
 	xor	%ebx,%ebx
+	jmp	1f
+	/*
+	 * The loop takes 14 bytes.  Ensure that it doesn't cross a 16-byte
+	 * cache line.
+	 */
+	.p2align 4,0x90
 1:
 	movnti	%ebx,(%ecx)
-	addl	$4,%ecx
+	movnti	%ebx,4(%ecx)
+	addl	$8,%ecx
 	cmpl	%ecx,%eax
 	jne	1b
 	sfence