diff --git a/target/arm/translate-vfp.inc.c b/target/arm/translate-vfp.inc.c
index 00f64401dd..1d7100debe 100644
--- a/target/arm/translate-vfp.inc.c
+++ b/target/arm/translate-vfp.inc.c
@@ -1341,3 +1341,45 @@ static bool trans_VMLS_dp(DisasContext *s, arg_VMLS_sp *a)
 {
     return do_vfp_3op_dp(s, gen_VMLS_dp, a->vd, a->vn, a->vm, true);
 }
+
+static void gen_VNMLS_sp(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm, TCGv_ptr fpst)
+{
+    /*
+     * VNMLS: -fd + (fn * fm)
+     * Note that it isn't valid to replace (-A + B) with (B - A) or similar
+     * plausible looking simplifications because this will give wrong results
+     * for NaNs.
+     */
+    TCGv_i32 tmp = tcg_temp_new_i32();
+
+    gen_helper_vfp_muls(tmp, vn, vm, fpst);
+    gen_helper_vfp_negs(vd, vd);
+    gen_helper_vfp_adds(vd, vd, tmp, fpst);
+    tcg_temp_free_i32(tmp);
+}
+
+static bool trans_VNMLS_sp(DisasContext *s, arg_VNMLS_sp *a)
+{
+    return do_vfp_3op_sp(s, gen_VNMLS_sp, a->vd, a->vn, a->vm, true);
+}
+
+static void gen_VNMLS_dp(TCGv_i64 vd, TCGv_i64 vn, TCGv_i64 vm, TCGv_ptr fpst)
+{
+    /*
+     * VNMLS: -fd + (fn * fm)
+     * Note that it isn't valid to replace (-A + B) with (B - A) or similar
+     * plausible looking simplifications because this will give wrong results
+     * for NaNs.
+     */
+    TCGv_i64 tmp = tcg_temp_new_i64();
+
+    gen_helper_vfp_muld(tmp, vn, vm, fpst);
+    gen_helper_vfp_negd(vd, vd);
+    gen_helper_vfp_addd(vd, vd, tmp, fpst);
+    tcg_temp_free_i64(tmp);
+}
+
+static bool trans_VNMLS_dp(DisasContext *s, arg_VNMLS_sp *a)
+{
+    return do_vfp_3op_dp(s, gen_VNMLS_dp, a->vd, a->vn, a->vm, true);
+}
diff --git a/target/arm/translate.c b/target/arm/translate.c
index 4e9cabc865..b85baec0de 100644
--- a/target/arm/translate.c
+++ b/target/arm/translate.c
@@ -1393,18 +1393,6 @@ VFP_OP2(div)
 
 #undef VFP_OP2
 
-static inline void gen_vfp_F1_mul(int dp)
-{
-    /* Like gen_vfp_mul() but put result in F1 */
-    TCGv_ptr fpst = get_fpstatus_ptr(0);
-    if (dp) {
-        gen_helper_vfp_muld(cpu_F1d, cpu_F0d, cpu_F1d, fpst);
-    } else {
-        gen_helper_vfp_muls(cpu_F1s, cpu_F0s, cpu_F1s, fpst);
-    }
-    tcg_temp_free_ptr(fpst);
-}
-
 static inline void gen_vfp_F1_neg(int dp)
 {
     /* Like gen_vfp_neg() but put result in F1 */
@@ -3134,7 +3122,7 @@ static int disas_vfp_insn(DisasContext *s, uint32_t insn)
             rn = VFP_SREG_N(insn);
 
             switch (op) {
-            case 0 ... 1:
+            case 0 ... 2:
                 /* Already handled by decodetree */
                 return 1;
             default:
@@ -3320,16 +3308,6 @@ static int disas_vfp_insn(DisasContext *s, uint32_t insn)
             for (;;) {
                 /* Perform the calculation.  */
                 switch (op) {
-                case 2: /* VNMLS: -fd + (fn * fm) */
-                    /* Note that it isn't valid to replace (-A + B) with (B - A)
-                     * or similar plausible looking simplifications
-                     * because this will give wrong results for NaNs.
-                     */
-                    gen_vfp_F1_mul(dp);
-                    gen_mov_F0_vreg(dp, rd);
-                    gen_vfp_neg(dp);
-                    gen_vfp_add(dp);
-                    break;
                 case 3: /* VNMLA: -fd + -(fn * fm) */
                     gen_vfp_mul(dp);
                     gen_vfp_F1_neg(dp);
diff --git a/target/arm/vfp.decode b/target/arm/vfp.decode
index 7bcf2260ee..08e4f42740 100644
--- a/target/arm/vfp.decode
+++ b/target/arm/vfp.decode
@@ -107,3 +107,8 @@ VMLS_sp      ---- 1110 0.00 .... .... 1010 .1.0 .... \
              vm=%vm_sp vn=%vn_sp vd=%vd_sp
 VMLS_dp      ---- 1110 0.00 .... .... 1011 .1.0 .... \
              vm=%vm_dp vn=%vn_dp vd=%vd_dp
+
+VNMLS_sp     ---- 1110 0.01 .... .... 1010 .0.0 .... \
+             vm=%vm_sp vn=%vn_sp vd=%vd_sp
+VNMLS_dp     ---- 1110 0.01 .... .... 1011 .0.0 .... \
+             vm=%vm_dp vn=%vn_dp vd=%vd_dp