target/arm: Implement MVE VMOV to/from 2 general-purpose registers

Implement the MVE VMOV forms that move data between 2 general-purpose
registers and 2 32-bit lanes in a vector register.

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

target/arm/mve.decode

@@ -136,6 +136,10 @@ VLDR_VSTR        1110110 1 a:1 . w:1 . .... ... 111101 .......   @vldr_vstr \
 VLDR_VSTR        1110110 1 a:1 . w:1 . .... ... 111110 .......   @vldr_vstr \
                  size=2 p=1
 
+# Moves between 2 32-bit vector lanes and 2 general purpose registers
+VMOV_to_2gp      1110 1100 0 . 00 rt2:4 ... 0 1111 000 idx:1 rt:4 qd=%qd
+VMOV_from_2gp    1110 1100 0 . 01 rt2:4 ... 0 1111 000 idx:1 rt:4 qd=%qd
+
 # Vector 2-op
 VAND             1110 1111 0 . 00 ... 0 ... 0 0001 . 1 . 1 ... 0 @2op_nosz
 VBIC             1110 1111 0 . 01 ... 0 ... 0 0001 . 1 . 1 ... 0 @2op_nosz

target/arm/translate-a32.h

@@ -49,6 +49,7 @@ void gen_rev16(TCGv_i32 dest, TCGv_i32 var);
 void clear_eci_state(DisasContext *s);
 bool mve_eci_check(DisasContext *s);
 void mve_update_and_store_eci(DisasContext *s);
+bool mve_skip_vmov(DisasContext *s, int vn, int index, int size);
 
 static inline TCGv_i32 load_cpu_offset(int offset)
 {

target/arm/translate-mve.c

@@ -1507,3 +1507,88 @@ static bool do_vabav(DisasContext *s, arg_vabav *a, MVEGenVABAVFn *fn)
 
 DO_VABAV(VABAV_S, vabavs)
 DO_VABAV(VABAV_U, vabavu)
+
+static bool trans_VMOV_to_2gp(DisasContext *s, arg_VMOV_to_2gp *a)
+{
+    /*
+     * VMOV two 32-bit vector lanes to two general-purpose registers.
+     * This insn is not predicated but it is subject to beat-wise
+     * execution if it is not in an IT block. For us this means
+     * only that if PSR.ECI says we should not be executing the beat
+     * corresponding to the lane of the vector register being accessed
+     * then we should skip perfoming the move, and that we need to do
+     * the usual check for bad ECI state and advance of ECI state.
+     * (If PSR.ECI is non-zero then we cannot be in an IT block.)
+     */
+    TCGv_i32 tmp;
+    int vd;
+
+    if (!dc_isar_feature(aa32_mve, s) || !mve_check_qreg_bank(s, a->qd) ||
+        a->rt == 13 || a->rt == 15 || a->rt2 == 13 || a->rt2 == 15 ||
+        a->rt == a->rt2) {
+        /* Rt/Rt2 cases are UNPREDICTABLE */
+        return false;
+    }
+    if (!mve_eci_check(s) || !vfp_access_check(s)) {
+        return true;
+    }
+
+    /* Convert Qreg index to Dreg for read_neon_element32() etc */
+    vd = a->qd * 2;
+
+    if (!mve_skip_vmov(s, vd, a->idx, MO_32)) {
+        tmp = tcg_temp_new_i32();
+        read_neon_element32(tmp, vd, a->idx, MO_32);
+        store_reg(s, a->rt, tmp);
+    }
+    if (!mve_skip_vmov(s, vd + 1, a->idx, MO_32)) {
+        tmp = tcg_temp_new_i32();
+        read_neon_element32(tmp, vd + 1, a->idx, MO_32);
+        store_reg(s, a->rt2, tmp);
+    }
+
+    mve_update_and_store_eci(s);
+    return true;
+}
+
+static bool trans_VMOV_from_2gp(DisasContext *s, arg_VMOV_to_2gp *a)
+{
+    /*
+     * VMOV two general-purpose registers to two 32-bit vector lanes.
+     * This insn is not predicated but it is subject to beat-wise
+     * execution if it is not in an IT block. For us this means
+     * only that if PSR.ECI says we should not be executing the beat
+     * corresponding to the lane of the vector register being accessed
+     * then we should skip perfoming the move, and that we need to do
+     * the usual check for bad ECI state and advance of ECI state.
+     * (If PSR.ECI is non-zero then we cannot be in an IT block.)
+     */
+    TCGv_i32 tmp;
+    int vd;
+
+    if (!dc_isar_feature(aa32_mve, s) || !mve_check_qreg_bank(s, a->qd) ||
+        a->rt == 13 || a->rt == 15 || a->rt2 == 13 || a->rt2 == 15) {
+        /* Rt/Rt2 cases are UNPREDICTABLE */
+        return false;
+    }
+    if (!mve_eci_check(s) || !vfp_access_check(s)) {
+        return true;
+    }
+
+    /* Convert Qreg idx to Dreg for read_neon_element32() etc */
+    vd = a->qd * 2;
+
+    if (!mve_skip_vmov(s, vd, a->idx, MO_32)) {
+        tmp = load_reg(s, a->rt);
+        write_neon_element32(tmp, vd, a->idx, MO_32);
+        tcg_temp_free_i32(tmp);
+    }
+    if (!mve_skip_vmov(s, vd + 1, a->idx, MO_32)) {
+        tmp = load_reg(s, a->rt2);
+        write_neon_element32(tmp, vd + 1, a->idx, MO_32);
+        tcg_temp_free_i32(tmp);
+    }
+
+    mve_update_and_store_eci(s);
+    return true;
+}

target/arm/translate-vfp.c

@@ -581,7 +581,7 @@ static bool trans_VCVT(DisasContext *s, arg_VCVT *a)
     return true;
 }
 
-static bool mve_skip_vmov(DisasContext *s, int vn, int index, int size)
+bool mve_skip_vmov(DisasContext *s, int vn, int index, int size)
 {
     /*
      * In a CPU with MVE, the VMOV (vector lane to general-purpose register)