[Qemu-devel] [PATCH v2 15/42] target/arm: Convert VFP VLDR and VSTR to decodetree

[Peter Maydell <peter.maydell@linaro.org>]

Convert the VFP single load/store insns VLDR and VSTR to decodetree.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/translate-vfp.inc.c | 73 ++++++++++++++++++++++++++++++++++
 target/arm/translate.c         | 22 +---------
 target/arm/vfp.decode          |  7 ++++
 3 files changed, 82 insertions(+), 20 deletions(-)

diff --git a/target/arm/translate-vfp.inc.c b/target/arm/translate-vfp.inc.c
index 5f081221b83..40f2cac3e2e 100644
--- a/target/arm/translate-vfp.inc.c
+++ b/target/arm/translate-vfp.inc.c
@@ -853,3 +853,76 @@ static bool trans_VMOV_64_dp(DisasContext *s, arg_VMOV_64_sp *a)
 
     return true;
 }
+
+static bool trans_VLDR_VSTR_sp(DisasContext *s, arg_VLDR_VSTR_sp *a)
+{
+    uint32_t offset;
+    TCGv_i32 addr;
+
+    if (!vfp_access_check(s)) {
+        return true;
+    }
+
+    offset = a->imm << 2;
+    if (!a->u) {
+        offset = -offset;
+    }
+
+    if (s->thumb && a->rn == 15) {
+        /* This is actually UNPREDICTABLE */
+        addr = tcg_temp_new_i32();
+        tcg_gen_movi_i32(addr, s->pc & ~2);
+    } else {
+        addr = load_reg(s, a->rn);
+    }
+    tcg_gen_addi_i32(addr, addr, offset);
+    if (a->l) {
+        gen_vfp_ld(s, false, addr);
+        gen_mov_vreg_F0(false, a->vd);
+    } else {
+        gen_mov_F0_vreg(false, a->vd);
+        gen_vfp_st(s, false, addr);
+    }
+    tcg_temp_free_i32(addr);
+
+    return true;
+}
+
+static bool trans_VLDR_VSTR_dp(DisasContext *s, arg_VLDR_VSTR_sp *a)
+{
+    uint32_t offset;
+    TCGv_i32 addr;
+
+    /* UNDEF accesses to D16-D31 if they don't exist */
+    if (!dc_isar_feature(aa32_fp_d32, s) && (a->vd & 0x10)) {
+        return false;
+    }
+
+    if (!vfp_access_check(s)) {
+        return true;
+    }
+
+    offset = a->imm << 2;
+    if (!a->u) {
+        offset = -offset;
+    }
+
+    if (s->thumb && a->rn == 15) {
+        /* This is actually UNPREDICTABLE */
+        addr = tcg_temp_new_i32();
+        tcg_gen_movi_i32(addr, s->pc & ~2);
+    } else {
+        addr = load_reg(s, a->rn);
+    }
+    tcg_gen_addi_i32(addr, addr, offset);
+    if (a->l) {
+        gen_vfp_ld(s, true, addr);
+        gen_mov_vreg_F0(true, a->vd);
+    } else {
+        gen_mov_F0_vreg(true, a->vd);
+        gen_vfp_st(s, true, addr);
+    }
+    tcg_temp_free_i32(addr);
+
+    return true;
+}
diff --git a/target/arm/translate.c b/target/arm/translate.c
index d2dced7c45a..d954e8de1eb 100644
--- a/target/arm/translate.c
+++ b/target/arm/translate.c
@@ -3713,26 +3713,8 @@ static int disas_vfp_insn(DisasContext *s, uint32_t insn)
             else
                 rd = VFP_SREG_D(insn);
             if ((insn & 0x01200000) == 0x01000000) {
-                /* Single load/store */
-                offset = (insn & 0xff) << 2;
-                if ((insn & (1 << 23)) == 0)
-                    offset = -offset;
-                if (s->thumb && rn == 15) {
-                    /* This is actually UNPREDICTABLE */
-                    addr = tcg_temp_new_i32();
-                    tcg_gen_movi_i32(addr, s->pc & ~2);
-                } else {
-                    addr = load_reg(s, rn);
-                }
-                tcg_gen_addi_i32(addr, addr, offset);
-                if (insn & (1 << 20)) {
-                    gen_vfp_ld(s, dp, addr);
-                    gen_mov_vreg_F0(dp, rd);
-                } else {
-                    gen_mov_F0_vreg(dp, rd);
-                    gen_vfp_st(s, dp, addr);
-                }
-                tcg_temp_free_i32(addr);
+                /* Already handled by decodetree */
+                return 1;
             } else {
                 /* load/store multiple */
                 int w = insn & (1 << 21);
diff --git a/target/arm/vfp.decode b/target/arm/vfp.decode
index 134f1c9ef58..8fa7fa0bead 100644
--- a/target/arm/vfp.decode
+++ b/target/arm/vfp.decode
@@ -71,3 +71,10 @@ 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
+
+# Note that the half-precision variants of VLDR and VSTR are
+# not part of this decodetree at all because they have bits [9:8] == 0b01
+VLDR_VSTR_sp ---- 1101 u:1 .0 l:1 rn:4 .... 1010 imm:8 \
+             vd=%vd_sp
+VLDR_VSTR_dp ---- 1101 u:1 .0 l:1 rn:4 .... 1011 imm:8 \
+             vd=%vd_dp
-- 
2.20.1