target/arm: Convert VCVT fixed-point ops to decodetree

Convert the VCVT fixed-point conversion operations in the
Neon 2-regs-and-shift group to decodetree.

Backports commit 3da26f11711caeaa18318b6afa14dfb81d7650ab from qemu

qemu/target/arm/neon-dp.decode

@@ -251,6 +251,10 @@ VMINNM_fp_3s     1111 001 1 0 . 1 . .... .... 1111 ... 1 .... @3same_fp
 @2reg_shll_b     .... ... . . . 001 shift:3  .... .... 0 . . . .... \
                  &2reg_shift vm=%vm_dp vd=%vd_dp size=0 q=0
 
+# We use size=0 for fp32 and size=1 for fp16 to match the 3-same encodings.
+@2reg_vcvt       .... ... . . . 1 ..... .... .... . q:1 . . .... \
+                 &2reg_shift vm=%vm_dp vd=%vd_dp size=0 shift=%neon_rshift_i5
+
 VSHR_S_2sh       1111 001 0 1 . ...... .... 0000 . . . 1 .... @2reg_shr_d
 VSHR_S_2sh       1111 001 0 1 . ...... .... 0000 . . . 1 .... @2reg_shr_s
 VSHR_S_2sh       1111 001 0 1 . ...... .... 0000 . . . 1 .... @2reg_shr_h
@@ -364,3 +368,10 @@ VSHLL_S_2sh      1111 001 0 1 . ...... .... 1010 . 0 . 1 .... @2reg_shll_b
 VSHLL_U_2sh      1111 001 1 1 . ...... .... 1010 . 0 . 1 .... @2reg_shll_s
 VSHLL_U_2sh      1111 001 1 1 . ...... .... 1010 . 0 . 1 .... @2reg_shll_h
 VSHLL_U_2sh      1111 001 1 1 . ...... .... 1010 . 0 . 1 .... @2reg_shll_b
+
+# VCVT fixed<->float conversions
+# TODO: FP16 fixed<->float conversions are opc==0b1100 and 0b1101
+VCVT_SF_2sh      1111 001 0 1 . ...... .... 1110 0 . . 1 .... @2reg_vcvt
+VCVT_UF_2sh      1111 001 1 1 . ...... .... 1110 0 . . 1 .... @2reg_vcvt
+VCVT_FS_2sh      1111 001 0 1 . ...... .... 1111 0 . . 1 .... @2reg_vcvt
+VCVT_FU_2sh      1111 001 1 1 . ...... .... 1111 0 . . 1 .... @2reg_vcvt

qemu/target/arm/translate-neon.inc.c

@@ -1681,3 +1681,53 @@ static bool trans_VSHLL_U_2sh(DisasContext *s, arg_2reg_shift *a)
     };
     return do_vshll_2sh(s, a, widenfn[a->size], true);
 }
+
+static bool do_fp_2sh(DisasContext *s, arg_2reg_shift *a,
+                      NeonGenTwoSingleOPFn *fn)
+{
+    /* FP operations in 2-reg-and-shift group */
+    TCGContext *tcg_ctx = s->uc->tcg_ctx;
+    TCGv_i32 tmp, shiftv;
+    TCGv_ptr fpstatus;
+    int pass;
+
+    if (!arm_dc_feature(s, ARM_FEATURE_NEON)) {
+        return false;
+    }
+
+    /* UNDEF accesses to D16-D31 if they don't exist. */
+    if (!dc_isar_feature(aa32_simd_r32, s) &&
+        ((a->vd | a->vm) & 0x10)) {
+        return false;
+    }
+
+    if ((a->vm | a->vd) & a->q) {
+        return false;
+    }
+
+    if (!vfp_access_check(s)) {
+        return true;
+    }
+
+    fpstatus = get_fpstatus_ptr(tcg_ctx, 1);
+    shiftv = tcg_const_i32(tcg_ctx, a->shift);
+    for (pass = 0; pass < (a->q ? 4 : 2); pass++) {
+        tmp = neon_load_reg(s, a->vm, pass);
+        fn(tcg_ctx, tmp, tmp, shiftv, fpstatus);
+        neon_store_reg(s, a->vd, pass, tmp);
+    }
+    tcg_temp_free_ptr(tcg_ctx, fpstatus);
+    tcg_temp_free_i32(tcg_ctx, shiftv);
+    return true;
+}
+
+#define DO_FP_2SH(INSN, FUNC)                                           \
+    static bool trans_##INSN##_2sh(DisasContext *s, arg_2reg_shift *a)  \
+    {                                                                   \
+        return do_fp_2sh(s, a, FUNC);                                   \
+    }
+
+DO_FP_2SH(VCVT_SF, gen_helper_vfp_sltos)
+DO_FP_2SH(VCVT_UF, gen_helper_vfp_ultos)
+DO_FP_2SH(VCVT_FS, gen_helper_vfp_tosls_round_to_zero)
+DO_FP_2SH(VCVT_FU, gen_helper_vfp_touls_round_to_zero)

qemu/target/arm/translate.c

@@ -5318,7 +5318,6 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
     int q;
     int rd, rn, rm, rd_ofs, rn_ofs, rm_ofs;
     int size;
-    int shift;
     int pass;
     int u;
     int vec_size;
@@ -5359,78 +5358,8 @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn)
         return 1;
     } else if (insn & (1 << 4)) {
         if ((insn & 0x00380080) != 0) {
-            /* Two registers and shift.  */
+             /* Two registers and shift: handled by decodetree */
-            op = (insn >> 8) & 0xf;
+            return 1;
-
-            switch (op) {
-            case 0: /* VSHR */
-            case 1: /* VSRA */
-            case 2: /* VRSHR */
-            case 3: /* VRSRA */
-            case 4: /* VSRI */
-            case 5: /* VSHL, VSLI */
-            case 6: /* VQSHLU */
-            case 7: /* VQSHL */
-            case 8: /* VSHRN, VRSHRN, VQSHRUN, VQRSHRUN */
-            case 9: /* VQSHRN, VQRSHRN */
-            case 10: /* VSHLL, including VMOVL */
-                return 1; /* handled by decodetree */
-            default:
-                break;
-            }
-
-            if (insn & (1 << 7)) {
-                /* 64-bit shift. */
-                if (op > 7) {
-                    return 1;
-                }
-                size = 3;
-            } else {
-                size = 2;
-                while ((insn & (1 << (size + 19))) == 0)
-                    size--;
-            }
-            shift = (insn >> 16) & ((1 << (3 + size)) - 1);
-            if (op >= 14) {
-                /* VCVT fixed-point.  */
-                TCGv_ptr fpst;
-                TCGv_i32 shiftv;
-                VFPGenFixPointFn *fn;
-
-                if (!(insn & (1 << 21)) || (q && ((rd | rm) & 1))) {
-                    return 1;
-                }
-
-                if (!(op & 1)) {
-                    if (u) {
-                        fn = gen_helper_vfp_ultos;
-                    } else {
-                        fn = gen_helper_vfp_sltos;
-                    }
-                } else {
-                    if (u) {
-                        fn = gen_helper_vfp_touls_round_to_zero;
-                    } else {
-                        fn = gen_helper_vfp_tosls_round_to_zero;
-                    }
-                }
-
-                /* We have already masked out the must-be-1 top bit of imm6,
-                 * hence this 32-shift where the ARM ARM has 64-imm6.
-                 */
-                shift = 32 - shift;
-                fpst = get_fpstatus_ptr(tcg_ctx, 1);
-                shiftv = tcg_const_i32(tcg_ctx, shift);
-                for (pass = 0; pass < (q ? 4 : 2); pass++) {
-                    TCGv_i32 tmpf = neon_load_reg(s, rm, pass);
-                    fn(tcg_ctx, tmpf, tmpf, shiftv, fpst);
-                    neon_store_reg(s, rd, pass, tmpf);
-                }
-                tcg_temp_free_ptr(tcg_ctx, fpst);
-                tcg_temp_free_i32(tcg_ctx, shiftv);
-            } else {
-                return 1;
-            }
         } else { /* (insn & 0x00380080) == 0 */
             int invert, reg_ofs, vec_size;