target/loongarch: Add floating point load/store instruction translation

This includes:
- FLD.{S/D}, FST.{S/D}
- FLDX.{S/D}, FSTX.{S/D}
- FLD{GT/LE}.{S/D}, FST{GT/LE}.{S/D}

Signed-off-by: Song Gao <gaosong@loongson.cn>
Signed-off-by: Xiaojuan Yang <yangxiaojuan@loongson.cn>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20220606124333.2060567-15-yangxiaojuan@loongson.cn>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

3 files changed, 178 insertions, 0 deletions

diff --git a/target/loongarch/insn_trans/trans_fmemory.c.inc b/target/loongarch/insn_trans/trans_fmemory.c.inc
new file mode 100644
index 0000000000..74ee98f63a
--- /dev/null
+++ b/target/loongarch/insn_trans/trans_fmemory.c.inc
@@ -0,0 +1,153 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (c) 2021 Loongson Technology Corporation Limited
+ */
+
+static void maybe_nanbox_load(TCGv freg, MemOp mop)
+{
+    if ((mop & MO_SIZE) == MO_32) {
+        gen_nanbox_s(freg, freg);
+    }
+}
+
+static bool gen_fload_i(DisasContext *ctx, arg_fr_i *a, MemOp mop)
+{
+    TCGv addr = gpr_src(ctx, a->rj, EXT_NONE);
+    TCGv temp = NULL;
+
+    if (a->imm) {
+        temp = tcg_temp_new();
+        tcg_gen_addi_tl(temp, addr, a->imm);
+        addr = temp;
+    }
+
+    tcg_gen_qemu_ld_tl(cpu_fpr[a->fd], addr, ctx->mem_idx, mop);
+    maybe_nanbox_load(cpu_fpr[a->fd], mop);
+
+    if (temp) {
+        tcg_temp_free(temp);
+    }
+
+    return true;
+}
+
+static bool gen_fstore_i(DisasContext *ctx, arg_fr_i *a, MemOp mop)
+{
+    TCGv addr = gpr_src(ctx, a->rj, EXT_NONE);
+    TCGv temp = NULL;
+
+    if (a->imm) {
+        temp = tcg_temp_new();
+        tcg_gen_addi_tl(temp, addr, a->imm);
+        addr = temp;
+    }
+
+    tcg_gen_qemu_st_tl(cpu_fpr[a->fd], addr, ctx->mem_idx, mop);
+
+    if (temp) {
+        tcg_temp_free(temp);
+    }
+    return true;
+}
+
+static bool gen_floadx(DisasContext *ctx, arg_frr *a, MemOp mop)
+{
+    TCGv src1 = gpr_src(ctx, a->rj, EXT_NONE);
+    TCGv src2 = gpr_src(ctx, a->rk, EXT_NONE);
+    TCGv addr = tcg_temp_new();
+
+    tcg_gen_add_tl(addr, src1, src2);
+    tcg_gen_qemu_ld_tl(cpu_fpr[a->fd], addr, ctx->mem_idx, mop);
+    maybe_nanbox_load(cpu_fpr[a->fd], mop);
+    tcg_temp_free(addr);
+
+    return true;
+}
+
+static bool gen_fstorex(DisasContext *ctx, arg_frr *a, MemOp mop)
+{
+    TCGv src1 = gpr_src(ctx, a->rj, EXT_NONE);
+    TCGv src2 = gpr_src(ctx, a->rk, EXT_NONE);
+    TCGv addr = tcg_temp_new();
+
+    tcg_gen_add_tl(addr, src1, src2);
+    tcg_gen_qemu_st_tl(cpu_fpr[a->fd], addr, ctx->mem_idx, mop);
+    tcg_temp_free(addr);
+
+    return true;
+}
+
+static bool gen_fload_gt(DisasContext *ctx, arg_frr *a, MemOp mop)
+{
+    TCGv src1 = gpr_src(ctx, a->rj, EXT_NONE);
+    TCGv src2 = gpr_src(ctx, a->rk, EXT_NONE);
+    TCGv addr = tcg_temp_new();
+
+    gen_helper_asrtgt_d(cpu_env, src1, src2);
+    tcg_gen_add_tl(addr, src1, src2);
+    tcg_gen_qemu_ld_tl(cpu_fpr[a->fd], addr, ctx->mem_idx, mop);
+    maybe_nanbox_load(cpu_fpr[a->fd], mop);
+    tcg_temp_free(addr);
+
+    return true;
+}
+
+static bool gen_fstore_gt(DisasContext *ctx, arg_frr *a, MemOp mop)
+{
+    TCGv src1 = gpr_src(ctx, a->rj, EXT_NONE);
+    TCGv src2 = gpr_src(ctx, a->rk, EXT_NONE);
+    TCGv addr = tcg_temp_new();
+
+    gen_helper_asrtgt_d(cpu_env, src1, src2);
+    tcg_gen_add_tl(addr, src1, src2);
+    tcg_gen_qemu_st_tl(cpu_fpr[a->fd], addr, ctx->mem_idx, mop);
+    tcg_temp_free(addr);
+
+    return true;
+}
+
+static bool gen_fload_le(DisasContext *ctx, arg_frr *a, MemOp mop)
+{
+    TCGv src1 = gpr_src(ctx, a->rj, EXT_NONE);
+    TCGv src2 = gpr_src(ctx, a->rk, EXT_NONE);
+    TCGv addr = tcg_temp_new();
+
+    gen_helper_asrtle_d(cpu_env, src1, src2);
+    tcg_gen_add_tl(addr, src1, src2);
+    tcg_gen_qemu_ld_tl(cpu_fpr[a->fd], addr, ctx->mem_idx, mop);
+    maybe_nanbox_load(cpu_fpr[a->fd], mop);
+    tcg_temp_free(addr);
+
+    return true;
+}
+
+static bool gen_fstore_le(DisasContext *ctx, arg_frr *a, MemOp mop)
+{
+    TCGv src1 = gpr_src(ctx, a->rj, EXT_NONE);
+    TCGv src2 = gpr_src(ctx, a->rk, EXT_NONE);
+    TCGv addr = tcg_temp_new();
+
+    gen_helper_asrtle_d(cpu_env, src1, src2);
+    tcg_gen_add_tl(addr, src1, src2);
+    tcg_gen_qemu_st_tl(cpu_fpr[a->fd], addr, ctx->mem_idx, mop);
+    tcg_temp_free(addr);
+
+    return true;
+}
+
+TRANS(fld_s, gen_fload_i, MO_TEUL)
+TRANS(fst_s, gen_fstore_i, MO_TEUL)
+TRANS(fld_d, gen_fload_i, MO_TEUQ)
+TRANS(fst_d, gen_fstore_i, MO_TEUQ)
+TRANS(fldx_s, gen_floadx, MO_TEUL)
+TRANS(fldx_d, gen_floadx, MO_TEUQ)
+TRANS(fstx_s, gen_fstorex, MO_TEUL)
+TRANS(fstx_d, gen_fstorex, MO_TEUQ)
+TRANS(fldgt_s, gen_fload_gt, MO_TEUL)
+TRANS(fldgt_d, gen_fload_gt, MO_TEUQ)
+TRANS(fldle_s, gen_fload_le, MO_TEUL)
+TRANS(fldle_d, gen_fload_le, MO_TEUQ)
+TRANS(fstgt_s, gen_fstore_gt, MO_TEUL)
+TRANS(fstgt_d, gen_fstore_gt, MO_TEUQ)
+TRANS(fstle_s, gen_fstore_le, MO_TEUL)
+TRANS(fstle_d, gen_fstore_le, MO_TEUQ)
diff --git a/target/loongarch/insns.decode b/target/loongarch/insns.decode
index c62a4f6dcd..8f286e7233 100644
--- a/target/loongarch/insns.decode
+++ b/target/loongarch/insns.decode
@@ -36,6 +36,8 @@
 &fc           fd cj
 &cr           cd rj
 &rc           rd cj
+&frr          fd rj rk
+&fr_i         fd rj imm
 
 #
 # Formats
@@ -70,6 +72,8 @@
 @fc            .... ........ ..... ..... .. cj:3 fd:5    &fc
 @cr            .... ........ ..... ..... rj:5 .. cd:3    &cr
 @rc            .... ........ ..... ..... .. cj:3 rd:5    &rc
+@frr               .... ........ ..... rk:5 rj:5 fd:5    &frr
+@fr_i12                 .... ...... imm:s12 rj:5 fd:5    &fr_i
 
 #
 # Fixed point arithmetic operation instruction
@@ -385,3 +389,23 @@ movfr2cf        0000 00010001 01001 10100 ..... 00 ...   @cf
 movcf2fr        0000 00010001 01001 10101 00 ... .....   @fc
 movgr2cf        0000 00010001 01001 10110 ..... 00 ...   @cr
 movcf2gr        0000 00010001 01001 10111 00 ... .....   @rc
+
+#
+# Floating point load/store instruction
+#
+fld_s           0010 101100 ............ ..... .....     @fr_i12
+fst_s           0010 101101 ............ ..... .....     @fr_i12
+fld_d           0010 101110 ............ ..... .....     @fr_i12
+fst_d           0010 101111 ............ ..... .....     @fr_i12
+fldx_s          0011 10000011 00000 ..... ..... .....    @frr
+fldx_d          0011 10000011 01000 ..... ..... .....    @frr
+fstx_s          0011 10000011 10000 ..... ..... .....    @frr
+fstx_d          0011 10000011 11000 ..... ..... .....    @frr
+fldgt_s         0011 10000111 01000 ..... ..... .....    @frr
+fldgt_d         0011 10000111 01001 ..... ..... .....    @frr
+fldle_s         0011 10000111 01010 ..... ..... .....    @frr
+fldle_d         0011 10000111 01011 ..... ..... .....    @frr
+fstgt_s         0011 10000111 01100 ..... ..... .....    @frr
+fstgt_d         0011 10000111 01101 ..... ..... .....    @frr
+fstle_s         0011 10000111 01110 ..... ..... .....    @frr
+fstle_d         0011 10000111 01111 ..... ..... .....    @frr
diff --git a/target/loongarch/translate.c b/target/loongarch/translate.c
index 26d60b50fd..daa77ade33 100644
--- a/target/loongarch/translate.c
+++ b/target/loongarch/translate.c
@@ -170,6 +170,7 @@ static void gen_set_gpr(int reg_num, TCGv t, DisasExtend dst_ext)
 #include "insn_trans/trans_fcmp.c.inc"
 #include "insn_trans/trans_fcnv.c.inc"
 #include "insn_trans/trans_fmov.c.inc"
+#include "insn_trans/trans_fmemory.c.inc"
 
 static void loongarch_tr_translate_insn(DisasContextBase *dcbase, CPUState *cs)
 {