target/arm: Convert VFP two-register transfer insns to decodetree

Convert the VFP two-register transfer instructions to decodetree
(in the v8 Arm ARM these are the "Advanced SIMD and floating-point
64-bit move" encoding group).

Again, we expand out the sequences involving gen_vfp_msr() and
gen_msr_vfp().

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>

3 files changed, 77 insertions, 44 deletions

diff --git a/target/arm/translate-vfp.inc.c b/target/arm/translate-vfp.inc.c
index 74c10f9024..5f081221b8 100644
--- a/target/arm/translate-vfp.inc.c
+++ b/target/arm/translate-vfp.inc.c
@@ -783,3 +783,73 @@ static bool trans_VMOV_single(DisasContext *s, arg_VMOV_single *a)
 
     return true;
 }
+
+static bool trans_VMOV_64_sp(DisasContext *s, arg_VMOV_64_sp *a)
+{
+    TCGv_i32 tmp;
+
+    /*
+     * VMOV between two general-purpose registers and two single precision
+     * floating point registers
+     */
+    if (!vfp_access_check(s)) {
+        return true;
+    }
+
+    if (a->op) {
+        /* fpreg to gpreg */
+        tmp = tcg_temp_new_i32();
+        neon_load_reg32(tmp, a->vm);
+        store_reg(s, a->rt, tmp);
+        tmp = tcg_temp_new_i32();
+        neon_load_reg32(tmp, a->vm + 1);
+        store_reg(s, a->rt2, tmp);
+    } else {
+        /* gpreg to fpreg */
+        tmp = load_reg(s, a->rt);
+        neon_store_reg32(tmp, a->vm);
+        tmp = load_reg(s, a->rt2);
+        neon_store_reg32(tmp, a->vm + 1);
+    }
+
+    return true;
+}
+
+static bool trans_VMOV_64_dp(DisasContext *s, arg_VMOV_64_sp *a)
+{
+    TCGv_i32 tmp;
+
+    /*
+     * VMOV between two general-purpose registers and one double precision
+     * floating point register
+     */
+
+    /* UNDEF accesses to D16-D31 if they don't exist */
+    if (!dc_isar_feature(aa32_fp_d32, s) && (a->vm & 0x10)) {
+        return false;
+    }
+
+    if (!vfp_access_check(s)) {
+        return true;
+    }
+
+    if (a->op) {
+        /* fpreg to gpreg */
+        tmp = tcg_temp_new_i32();
+        neon_load_reg32(tmp, a->vm * 2);
+        store_reg(s, a->rt, tmp);
+        tmp = tcg_temp_new_i32();
+        neon_load_reg32(tmp, a->vm * 2 + 1);
+        store_reg(s, a->rt2, tmp);
+    } else {
+        /* gpreg to fpreg */
+        tmp = load_reg(s, a->rt);
+        neon_store_reg32(tmp, a->vm * 2);
+        tcg_temp_free_i32(tmp);
+        tmp = load_reg(s, a->rt2);
+        neon_store_reg32(tmp, a->vm * 2 + 1);
+        tcg_temp_free_i32(tmp);
+    }
+
+    return true;
+}
diff --git a/target/arm/translate.c b/target/arm/translate.c
index 5b614e7211..0607625d0f 100644
--- a/target/arm/translate.c
+++ b/target/arm/translate.c
@@ -3703,50 +3703,8 @@ static int disas_vfp_insn(DisasContext *s, uint32_t insn)
     case 0xc:
     case 0xd:
         if ((insn & 0x03e00000) == 0x00400000) {
-            /* two-register transfer */
-            rn = (insn >> 16) & 0xf;
-            rd = (insn >> 12) & 0xf;
-            if (dp) {
-                VFP_DREG_M(rm, insn);
-            } else {
-                rm = VFP_SREG_M(insn);
-            }
-
-            if (insn & ARM_CP_RW_BIT) {
-                /* vfp->arm */
-                if (dp) {
-                    gen_mov_F0_vreg(0, rm * 2);
-                    tmp = gen_vfp_mrs();
-                    store_reg(s, rd, tmp);
-                    gen_mov_F0_vreg(0, rm * 2 + 1);
-                    tmp = gen_vfp_mrs();
-                    store_reg(s, rn, tmp);
-                } else {
-                    gen_mov_F0_vreg(0, rm);
-                    tmp = gen_vfp_mrs();
-                    store_reg(s, rd, tmp);
-                    gen_mov_F0_vreg(0, rm + 1);
-                    tmp = gen_vfp_mrs();
-                    store_reg(s, rn, tmp);
-                }
-            } else {
-                /* arm->vfp */
-                if (dp) {
-                    tmp = load_reg(s, rd);
-                    gen_vfp_msr(tmp);
-                    gen_mov_vreg_F0(0, rm * 2);
-                    tmp = load_reg(s, rn);
-                    gen_vfp_msr(tmp);
-                    gen_mov_vreg_F0(0, rm * 2 + 1);
-                } else {
-                    tmp = load_reg(s, rd);
-                    gen_vfp_msr(tmp);
-                    gen_mov_vreg_F0(0, rm);
-                    tmp = load_reg(s, rn);
-                    gen_vfp_msr(tmp);
-                    gen_mov_vreg_F0(0, rm + 1);
-                }
-            }
+            /* Already handled by decodetree */
+            return 1;
         } else {
             /* Load/store */
             rn = (insn >> 16) & 0xf;
diff --git a/target/arm/vfp.decode b/target/arm/vfp.decode
index bb7de403df..134f1c9ef5 100644
--- a/target/arm/vfp.decode
+++ b/target/arm/vfp.decode
@@ -66,3 +66,8 @@ VDUP         ---- 1110 1 b:1 q:1 0 .... rt:4 1011 . 0 e:1 1 0000 \
 VMSR_VMRS    ---- 1110 111 l:1 reg:4 rt:4 1010 0001 0000
 VMOV_single  ---- 1110 000 l:1 .... rt:4 1010 . 001 0000 \
              vn=%vn_sp
+
+VMOV_64_sp   ---- 1100 010 op:1 rt2:4 rt:4 1010 00.1 .... \
+             vm=%vm_sp
+VMOV_64_dp   ---- 1100 010 op:1 rt2:4 rt:4 1011 00.1 .... \
+             vm=%vm_dp