diff --git a/sys/arm/arm/vfp.c b/sys/arm/arm/vfp.c
index 2494461c115..c149aafa78d 100644
--- a/sys/arm/arm/vfp.c
+++ b/sys/arm/arm/vfp.c
@@ -38,6 +38,7 @@ __FBSDID("$FreeBSD$");
 #include <machine/armreg.h>
 #include <machine/frame.h>
 #include <machine/fp.h>
+#include <machine/md_var.h>
 #include <machine/pcb.h>
 #include <machine/undefined.h>
 #include <machine/vfp.h>
@@ -128,6 +129,15 @@ vfp_init(void)
 
 			tmp = fmrx(mvfr1);
 			PCPU_SET(vfpmvfr1, tmp);
+
+			if (PCPU_GET(cpuid) == 0) {
+				if ((tmp & VMVFR1_FZ_MASK) == 0x1) {
+					/* Denormals arithmetic support */
+					initial_fpscr &= ~VFPSCR_FZ;
+					thread0.td_pcb->pcb_vfpstate.fpscr =
+					    initial_fpscr;
+				}
+			}
 		}
 
 		/* initialize the coprocess 10 and 11 calls
diff --git a/sys/arm/arm/vm_machdep.c b/sys/arm/arm/vm_machdep.c
index 895a14ce6b5..6a70cbf403e 100644
--- a/sys/arm/arm/vm_machdep.c
+++ b/sys/arm/arm/vm_machdep.c
@@ -85,6 +85,8 @@ __FBSDID("$FreeBSD$");
 CTASSERT(sizeof(struct switchframe) == 48);
 CTASSERT(sizeof(struct trapframe) == 80);
 
+uint32_t initial_fpscr = VFPSCR_DN | VFPSCR_FZ;
+
 /*
  * Finish a fork operation, with process p2 nearly set up.
  * Copy and update the pcb, set up the stack so that the child
@@ -134,7 +136,7 @@ cpu_fork(register struct thread *td1, register struct proc *p2,
 	pcb2->pcb_regs.sf_sp = STACKALIGN(td2->td_frame);
 
 	pcb2->pcb_vfpcpu = -1;
-	pcb2->pcb_vfpstate.fpscr = VFPSCR_DN;
+	pcb2->pcb_vfpstate.fpscr = initial_fpscr;
 
 	tf = td2->td_frame;
 	tf->tf_spsr &= ~PSR_C;
diff --git a/sys/arm/include/md_var.h b/sys/arm/include/md_var.h
index 030b48bf056..642124d9d21 100644
--- a/sys/arm/include/md_var.h
+++ b/sys/arm/include/md_var.h
@@ -71,4 +71,6 @@ void dump_add_page(vm_paddr_t);
 void dump_drop_page(vm_paddr_t);
 int minidumpsys(struct dumperinfo *);
 
+extern uint32_t initial_fpscr;
+
 #endif /* !_MACHINE_MD_VAR_H_ */