[RFC v2 10/76] target/riscv: rvv-0.9: add translation-time vector context status

[frank.chang@sifive.com]

From: LIU Zhiwei <zhiwei_liu@c-sky.com>

Signed-off-by: LIU Zhiwei <zhiwei_liu@c-sky.com>
Signed-off-by: Frank Chang <frank.chang@sifive.com>
---
 target/riscv/insn_trans/trans_rvv.inc.c | 69 ++++++++++++++++++++-----
 target/riscv/translate.c                | 33 ++++++++++++
 2 files changed, 90 insertions(+), 12 deletions(-)

diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_trans/trans_rvv.inc.c
index c0b7375927..e537e80550 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -48,6 +48,7 @@ static bool trans_vsetvl(DisasContext *ctx, arg_vsetvl *a)
     tcg_temp_free(s1);
     tcg_temp_free(s2);
     tcg_temp_free(dst);
+    mark_vs_dirty(ctx);
     return true;
 }
 
@@ -78,6 +79,7 @@ static bool trans_vsetvli(DisasContext *ctx, arg_vsetvli *a)
     tcg_temp_free(s1);
     tcg_temp_free(s2);
     tcg_temp_free(dst);
+    mark_vs_dirty(ctx);
     return true;
 }
 
@@ -163,7 +165,8 @@ typedef void gen_helper_ldst_us(TCGv_ptr, TCGv_ptr, TCGv,
                                 TCGv_env, TCGv_i32);
 
 static bool ldst_us_trans(uint32_t vd, uint32_t rs1, uint32_t data,
-                          gen_helper_ldst_us *fn, DisasContext *s)
+                          gen_helper_ldst_us *fn, DisasContext *s,
+                          bool is_store)
 {
     TCGv_ptr dest, mask;
     TCGv base;
@@ -195,6 +198,9 @@ static bool ldst_us_trans(uint32_t vd, uint32_t rs1, uint32_t data,
     tcg_temp_free_ptr(mask);
     tcg_temp_free(base);
     tcg_temp_free_i32(desc);
+    if (!is_store) {
+        mark_vs_dirty(s);
+    }
     gen_set_label(over);
     return true;
 }
@@ -245,7 +251,7 @@ static bool ld_us_op(DisasContext *s, arg_r2nfvm *a, uint8_t seq)
     data = FIELD_DP32(data, VDATA, VM, a->vm);
     data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
     data = FIELD_DP32(data, VDATA, NF, a->nf);
-    return ldst_us_trans(a->rd, a->rs1, data, fn, s);
+    return ldst_us_trans(a->rd, a->rs1, data, fn, s, false);
 }
 
 static bool ld_us_check(DisasContext *s, arg_r2nfvm* a)
@@ -298,7 +304,7 @@ static bool st_us_op(DisasContext *s, arg_r2nfvm *a, uint8_t seq)
     data = FIELD_DP32(data, VDATA, VM, a->vm);
     data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
     data = FIELD_DP32(data, VDATA, NF, a->nf);
-    return ldst_us_trans(a->rd, a->rs1, data, fn, s);
+    return ldst_us_trans(a->rd, a->rs1, data, fn, s, true);
 }
 
 static bool st_us_check(DisasContext *s, arg_r2nfvm* a)
@@ -321,7 +327,7 @@ typedef void gen_helper_ldst_stride(TCGv_ptr, TCGv_ptr, TCGv,
 
 static bool ldst_stride_trans(uint32_t vd, uint32_t rs1, uint32_t rs2,
                               uint32_t data, gen_helper_ldst_stride *fn,
-                              DisasContext *s)
+                              DisasContext *s, bool is_store)
 {
     TCGv_ptr dest, mask;
     TCGv base, stride;
@@ -348,6 +354,9 @@ static bool ldst_stride_trans(uint32_t vd, uint32_t rs1, uint32_t rs2,
     tcg_temp_free(base);
     tcg_temp_free(stride);
     tcg_temp_free_i32(desc);
+    if (!is_store) {
+        mark_vs_dirty(s);
+    }
     gen_set_label(over);
     return true;
 }
@@ -382,7 +391,7 @@ static bool ld_stride_op(DisasContext *s, arg_rnfvm *a, uint8_t seq)
     data = FIELD_DP32(data, VDATA, VM, a->vm);
     data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
     data = FIELD_DP32(data, VDATA, NF, a->nf);
-    return ldst_stride_trans(a->rd, a->rs1, a->rs2, data, fn, s);
+    return ldst_stride_trans(a->rd, a->rs1, a->rs2, data, fn, s, false);
 }
 
 static bool ld_stride_check(DisasContext *s, arg_rnfvm* a)
@@ -426,7 +435,7 @@ static bool st_stride_op(DisasContext *s, arg_rnfvm *a, uint8_t seq)
         return false;
     }
 
-    return ldst_stride_trans(a->rd, a->rs1, a->rs2, data, fn, s);
+    return ldst_stride_trans(a->rd, a->rs1, a->rs2, data, fn, s, true);
 }
 
 static bool st_stride_check(DisasContext *s, arg_rnfvm* a)
@@ -449,7 +458,7 @@ typedef void gen_helper_ldst_index(TCGv_ptr, TCGv_ptr, TCGv,
 
 static bool ldst_index_trans(uint32_t vd, uint32_t rs1, uint32_t vs2,
                              uint32_t data, gen_helper_ldst_index *fn,
-                             DisasContext *s)
+                             DisasContext *s, bool is_store)
 {
     TCGv_ptr dest, mask, index;
     TCGv base;
@@ -476,6 +485,9 @@ static bool ldst_index_trans(uint32_t vd, uint32_t rs1, uint32_t vs2,
     tcg_temp_free_ptr(index);
     tcg_temp_free(base);
     tcg_temp_free_i32(desc);
+    if (!is_store) {
+        mark_vs_dirty(s);
+    }
     gen_set_label(over);
     return true;
 }
@@ -510,7 +522,7 @@ static bool ld_index_op(DisasContext *s, arg_rnfvm *a, uint8_t seq)
     data = FIELD_DP32(data, VDATA, VM, a->vm);
     data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
     data = FIELD_DP32(data, VDATA, NF, a->nf);
-    return ldst_index_trans(a->rd, a->rs1, a->rs2, data, fn, s);
+    return ldst_index_trans(a->rd, a->rs1, a->rs2, data, fn, s, false);
 }
 
 static bool ld_index_check(DisasContext *s, arg_rnfvm* a)
@@ -554,7 +566,7 @@ static bool st_index_op(DisasContext *s, arg_rnfvm *a, uint8_t seq)
     data = FIELD_DP32(data, VDATA, VM, a->vm);
     data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
     data = FIELD_DP32(data, VDATA, NF, a->nf);
-    return ldst_index_trans(a->rd, a->rs1, a->rs2, data, fn, s);
+    return ldst_index_trans(a->rd, a->rs1, a->rs2, data, fn, s, true);
 }
 
 static bool st_index_check(DisasContext *s, arg_rnfvm* a)
@@ -598,6 +610,7 @@ static bool ldff_trans(uint32_t vd, uint32_t rs1, uint32_t data,
     tcg_temp_free_ptr(mask);
     tcg_temp_free(base);
     tcg_temp_free_i32(desc);
+    mark_vs_dirty(s);
     gen_set_label(over);
     return true;
 }
@@ -677,6 +690,7 @@ static bool amo_trans(uint32_t vd, uint32_t rs1, uint32_t vs2,
     tcg_temp_free_ptr(index);
     tcg_temp_free(base);
     tcg_temp_free_i32(desc);
+    mark_vs_dirty(s);
     gen_set_label(over);
     return true;
 }
@@ -823,6 +837,7 @@ do_opivv_gvec(DisasContext *s, arg_rmrr *a, GVecGen3Fn *gvec_fn,
                            vreg_ofs(s, a->rs1), vreg_ofs(s, a->rs2),
                            cpu_env, 0, s->vlen / 8, data, fn);
     }
+    mark_vs_dirty(s);
     gen_set_label(over);
     return true;
 }
@@ -877,6 +892,7 @@ static bool opivx_trans(uint32_t vd, uint32_t rs1, uint32_t vs2, uint32_t vm,
     tcg_temp_free_ptr(src2);
     tcg_temp_free(src1);
     tcg_temp_free_i32(desc);
+    mark_vs_dirty(s);
     gen_set_label(over);
     return true;
 }
@@ -911,6 +927,7 @@ do_opivx_gvec(DisasContext *s, arg_rmrr *a, GVecGen2sFn *gvec_fn,
 
         tcg_temp_free_i64(src1);
         tcg_temp_free(tmp);
+        mark_vs_dirty(s);
         return true;
     }
     return opivx_trans(a->rd, a->rs1, a->rs2, a->vm, fn, s);
@@ -1024,6 +1041,7 @@ static bool opivi_trans(uint32_t vd, uint32_t imm, uint32_t vs2, uint32_t vm,
     tcg_temp_free_ptr(src2);
     tcg_temp_free(src1);
     tcg_temp_free_i32(desc);
+    mark_vs_dirty(s);
     gen_set_label(over);
     return true;
 }
@@ -1047,10 +1065,10 @@ do_opivi_gvec(DisasContext *s, arg_rmrr *a, GVecGen2iFn *gvec_fn,
             gvec_fn(s->sew, vreg_ofs(s, a->rd), vreg_ofs(s, a->rs2),
                     sextract64(a->rs1, 0, 5), MAXSZ(s), MAXSZ(s));
         }
-    } else {
-        return opivi_trans(a->rd, a->rs1, a->rs2, a->vm, fn, s, zx);
+        mark_vs_dirty(s);
+        return true;
     }
-    return true;
+    return opivi_trans(a->rd, a->rs1, a->rs2, a->vm, fn, s, zx);
 }
 
 /* OPIVI with GVEC IR */
@@ -1111,6 +1129,7 @@ static bool do_opivv_widen(DisasContext *s, arg_rmrr *a,
                            vreg_ofs(s, a->rs2),
                            cpu_env, 0, s->vlen / 8,
                            data, fn);
+        mark_vs_dirty(s);
         gen_set_label(over);
         return true;
     }
@@ -1198,6 +1217,7 @@ static bool do_opiwv_widen(DisasContext *s, arg_rmrr *a,
                            vreg_ofs(s, a->rs1),
                            vreg_ofs(s, a->rs2),
                            cpu_env, 0, s->vlen / 8, data, fn);
+        mark_vs_dirty(s);
         gen_set_label(over);
         return true;
     }
@@ -1276,6 +1296,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a)             \
                            vreg_ofs(s, a->rs1),                    \
                            vreg_ofs(s, a->rs2), cpu_env, 0,        \
                            s->vlen / 8, data, fns[s->sew]);        \
+        mark_vs_dirty(s);                                          \
         gen_set_label(over);                                       \
         return true;                                               \
     }                                                              \
@@ -1407,6 +1428,7 @@ do_opivx_gvec_shift(DisasContext *s, arg_rmrr *a, GVecGen2sFn32 *gvec_fn,
 
         tcg_temp_free_i32(src1);
         tcg_temp_free(tmp);
+        mark_vs_dirty(s);
         return true;
     }
     return opivx_trans(a->rd, a->rs1, a->rs2, a->vm, fn, s);
@@ -1465,6 +1487,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a)             \
                            vreg_ofs(s, a->rs1),                    \
                            vreg_ofs(s, a->rs2), cpu_env, 0,        \
                            s->vlen / 8, data, fns[s->sew]);        \
+        mark_vs_dirty(s);                                          \
         gen_set_label(over);                                       \
         return true;                                               \
     }                                                              \
@@ -1648,6 +1671,7 @@ static bool trans_vmv_v_v(DisasContext *s, arg_vmv_v_v *a)
                                cpu_env, 0, s->vlen / 8, data, fns[s->sew]);
             gen_set_label(over);
         }
+        mark_vs_dirty(s);
         return true;
     }
     return false;
@@ -1690,6 +1714,7 @@ static bool trans_vmv_v_x(DisasContext *s, arg_vmv_v_x *a)
         }
 
         tcg_temp_free(s1);
+        mark_vs_dirty(s);
         gen_set_label(over);
         return true;
     }
@@ -1705,6 +1730,7 @@ static bool trans_vmv_v_i(DisasContext *s, arg_vmv_v_i *a)
         if (s->vl_eq_vlmax) {
             tcg_gen_gvec_dup_imm(s->sew, vreg_ofs(s, a->rd),
                                  MAXSZ(s), MAXSZ(s), simm);
+            mark_vs_dirty(s);
         } else {
             TCGv_i32 desc;
             TCGv_i64 s1;
@@ -1726,6 +1752,7 @@ static bool trans_vmv_v_i(DisasContext *s, arg_vmv_v_i *a)
             tcg_temp_free_ptr(dest);
             tcg_temp_free_i32(desc);
             tcg_temp_free_i64(s1);
+            mark_vs_dirty(s);
             gen_set_label(over);
         }
         return true;
@@ -1830,6 +1857,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a)             \
                            vreg_ofs(s, a->rs1),                    \
                            vreg_ofs(s, a->rs2), cpu_env, 0,        \
                            s->vlen / 8, data, fns[s->sew - 1]);    \
+        mark_vs_dirty(s);                                          \
         gen_set_label(over);                                       \
         return true;                                               \
     }                                                              \
@@ -1865,6 +1893,7 @@ static bool opfvf_trans(uint32_t vd, uint32_t rs1, uint32_t vs2,
     tcg_temp_free_ptr(mask);
     tcg_temp_free_ptr(src2);
     tcg_temp_free_i32(desc);
+    mark_vs_dirty(s);
     gen_set_label(over);
     return true;
 }
@@ -1942,6 +1971,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a)           \
                            vreg_ofs(s, a->rs1),                  \
                            vreg_ofs(s, a->rs2), cpu_env, 0,      \
                            s->vlen / 8, data, fns[s->sew - 1]);  \
+        mark_vs_dirty(s);                                        \
         gen_set_label(over);                                     \
         return true;                                             \
     }                                                            \
@@ -2016,6 +2046,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmrr *a)             \
                            vreg_ofs(s, a->rs1),                    \
                            vreg_ofs(s, a->rs2), cpu_env, 0,        \
                            s->vlen / 8, data, fns[s->sew - 1]);    \
+        mark_vs_dirty(s);                                          \
         gen_set_label(over);                                       \
         return true;                                               \
     }                                                              \
@@ -2130,6 +2161,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a)              \
         tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0),     \
                            vreg_ofs(s, a->rs2), cpu_env, 0,        \
                            s->vlen / 8, data, fns[s->sew - 1]);    \
+        mark_vs_dirty(s);                                          \
         gen_set_label(over);                                       \
         return true;                                               \
     }                                                              \
@@ -2202,6 +2234,7 @@ static bool trans_vfmv_v_f(DisasContext *s, arg_vfmv_v_f *a)
         if (s->vl_eq_vlmax) {
             tcg_gen_gvec_dup_i64(s->sew, vreg_ofs(s, a->rd),
                                  MAXSZ(s), MAXSZ(s), cpu_fpr[a->rs1]);
+            mark_vs_dirty(s);
         } else {
             TCGv_ptr dest;
             TCGv_i32 desc;
@@ -2221,6 +2254,7 @@ static bool trans_vfmv_v_f(DisasContext *s, arg_vfmv_v_f *a)
 
             tcg_temp_free_ptr(dest);
             tcg_temp_free_i32(desc);
+            mark_vs_dirty(s);
             gen_set_label(over);
         }
         return true;
@@ -2270,6 +2304,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a)              \
         tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0),     \
                            vreg_ofs(s, a->rs2), cpu_env, 0,        \
                            s->vlen / 8, data, fns[s->sew - 1]);    \
+        mark_vs_dirty(s);                                          \
         gen_set_label(over);                                       \
         return true;                                               \
     }                                                              \
@@ -2318,6 +2353,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a)              \
         tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0),     \
                            vreg_ofs(s, a->rs2), cpu_env, 0,        \
                            s->vlen / 8, data, fns[s->sew - 1]);    \
+        mark_vs_dirty(s);                                          \
         gen_set_label(over);                                       \
         return true;                                               \
     }                                                              \
@@ -2380,6 +2416,7 @@ static bool trans_##NAME(DisasContext *s, arg_r *a)                \
                            vreg_ofs(s, a->rs1),                    \
                            vreg_ofs(s, a->rs2), cpu_env, 0,        \
                            s->vlen / 8, data, fn);                 \
+        mark_vs_dirty(s);                                          \
         gen_set_label(over);                                       \
         return true;                                               \
     }                                                              \
@@ -2477,6 +2514,7 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a)              \
         tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd),                     \
                            vreg_ofs(s, 0), vreg_ofs(s, a->rs2),    \
                            cpu_env, 0, s->vlen / 8, data, fn);     \
+        mark_vs_dirty(s);                                          \
         gen_set_label(over);                                       \
         return true;                                               \
     }                                                              \
@@ -2508,6 +2546,7 @@ static bool trans_viota_m(DisasContext *s, arg_viota_m *a)
         tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0),
                            vreg_ofs(s, a->rs2), cpu_env, 0,
                            s->vlen / 8, data, fns[s->sew]);
+        mark_vs_dirty(s);
         gen_set_label(over);
         return true;
     }
@@ -2533,6 +2572,7 @@ static bool trans_vid_v(DisasContext *s, arg_vid_v *a)
         };
         tcg_gen_gvec_2_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0),
                            cpu_env, 0, s->vlen / 8, data, fns[s->sew]);
+        mark_vs_dirty(s);
         gen_set_label(over);
         return true;
     }
@@ -2708,6 +2748,7 @@ static bool trans_vmv_s_x(DisasContext *s, arg_vmv_s_x *a)
         tcg_gen_extu_tl_i64(t1, cpu_gpr[a->rs1]);
         vec_element_storei(s, a->rd, 0, t1);
         tcg_temp_free_i64(t1);
+        mark_vs_dirty(s);
     done:
         gen_set_label(over);
         return true;
@@ -2758,6 +2799,7 @@ static bool trans_vfmv_s_f(DisasContext *s, arg_vfmv_s_f *a)
         }
         vec_element_storei(s, a->rd, 0, t1);
         tcg_temp_free_i64(t1);
+        mark_vs_dirty(s);
         gen_set_label(over);
         return true;
     }
@@ -2824,6 +2866,7 @@ static bool trans_vrgather_vx(DisasContext *s, arg_rmrr *a)
         tcg_gen_gvec_dup_i64(s->sew, vreg_ofs(s, a->rd),
                              MAXSZ(s), MAXSZ(s), dest);
         tcg_temp_free_i64(dest);
+        mark_vs_dirty(s);
     } else {
         static gen_helper_opivx * const fns[4] = {
             gen_helper_vrgather_vx_b, gen_helper_vrgather_vx_h,
@@ -2850,6 +2893,7 @@ static bool trans_vrgather_vi(DisasContext *s, arg_rmrr *a)
                                  endian_ofs(s, a->rs2, a->rs1),
                                  MAXSZ(s), MAXSZ(s));
         }
+        mark_vs_dirty(s);
     } else {
         static gen_helper_opivx * const fns[4] = {
             gen_helper_vrgather_vx_b, gen_helper_vrgather_vx_h,
@@ -2886,6 +2930,7 @@ static bool trans_vcompress_vm(DisasContext *s, arg_r *a)
         tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0),
                            vreg_ofs(s, a->rs1), vreg_ofs(s, a->rs2),
                            cpu_env, 0, s->vlen / 8, data, fns[s->sew]);
+        mark_vs_dirty(s);
         gen_set_label(over);
         return true;
     }
diff --git a/target/riscv/translate.c b/target/riscv/translate.c
index 9632e79cf3..02b4204584 100644
--- a/target/riscv/translate.c
+++ b/target/riscv/translate.c
@@ -47,6 +47,7 @@ typedef struct DisasContext {
     bool virt_enabled;
     uint32_t opcode;
     uint32_t mstatus_fs;
+    uint32_t mstatus_vs;
     uint32_t misa;
     uint32_t mem_idx;
     /* Remember the rounding mode encoded in the previous fp instruction,
@@ -416,6 +417,37 @@ static void mark_fs_dirty(DisasContext *ctx)
 static inline void mark_fs_dirty(DisasContext *ctx) { }
 #endif
 
+#ifndef CONFIG_USER_ONLY
+/* The states of mstatus_vs are:
+ * 0 = disabled, 1 = initial, 2 = clean, 3 = dirty
+ * We will have already diagnosed disabled state,
+ * and need to turn initial/clean into dirty.
+ */
+static void mark_vs_dirty(DisasContext *ctx)
+{
+    TCGv tmp;
+    if (ctx->mstatus_vs == MSTATUS_VS) {
+        return;
+    }
+    /* Remember the state change for the rest of the TB.  */
+    ctx->mstatus_vs = MSTATUS_VS;
+
+    tmp = tcg_temp_new();
+    tcg_gen_ld_tl(tmp, cpu_env, offsetof(CPURISCVState, mstatus));
+    tcg_gen_ori_tl(tmp, tmp, MSTATUS_VS | MSTATUS_SD);
+    tcg_gen_st_tl(tmp, cpu_env, offsetof(CPURISCVState, mstatus));
+
+    if (ctx->virt_enabled) {
+        tcg_gen_ld_tl(tmp, cpu_env, offsetof(CPURISCVState, mstatus_hs));
+        tcg_gen_ori_tl(tmp, tmp, MSTATUS_VS | MSTATUS_SD);
+        tcg_gen_st_tl(tmp, cpu_env, offsetof(CPURISCVState, mstatus_hs));
+    }
+    tcg_temp_free(tmp);
+}
+#else
+static inline void mark_vs_dirty(DisasContext *ctx) { }
+#endif
+
 #if !defined(TARGET_RISCV64)
 static void gen_fp_load(DisasContext *ctx, uint32_t opc, int rd,
         int rs1, target_long imm)
@@ -764,6 +796,7 @@ static void riscv_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs)
     ctx->pc_succ_insn = ctx->base.pc_first;
     ctx->mem_idx = tb_flags & TB_FLAGS_MMU_MASK;
     ctx->mstatus_fs = tb_flags & TB_FLAGS_MSTATUS_FS;
+    ctx->mstatus_vs = tb_flags & TB_FLAGS_MSTATUS_VS;
     ctx->priv_ver = env->priv_ver;
 #if !defined(CONFIG_USER_ONLY)
     if (riscv_has_ext(env, RVH)) {
-- 
2.17.1