[v2,12/20] target-mips: add MSA BIT format instructions

diff --git a/target-mips/helper.h b/target-mips/helper.h
index 585eaa9..b5f171c 100644
--- a/target-mips/helper.h
+++ b/target-mips/helper.h
@@ -771,3 +771,16 @@  DEF_HELPER_5(msa_maxi_u_df, void, env, i32, i32, i32, s64)
 DEF_HELPER_5(msa_mini_s_df, void, env, i32, i32, i32, s64)
 DEF_HELPER_5(msa_mini_u_df, void, env, i32, i32, i32, s64)
 DEF_HELPER_5(msa_subvi_df, void, env, i32, i32, i32, s64)
+
+DEF_HELPER_5(msa_slli_df, void, env, i32, i32, i32, i32)
+DEF_HELPER_5(msa_srai_df, void, env, i32, i32, i32, i32)
+DEF_HELPER_5(msa_srli_df, void, env, i32, i32, i32, i32)
+DEF_HELPER_5(msa_bclri_df, void, env, i32, i32, i32, i32)
+DEF_HELPER_5(msa_bseti_df, void, env, i32, i32, i32, i32)
+DEF_HELPER_5(msa_bnegi_df, void, env, i32, i32, i32, i32)
+DEF_HELPER_5(msa_binsli_df, void, env, i32, i32, i32, i32)
+DEF_HELPER_5(msa_binsri_df, void, env, i32, i32, i32, i32)
+DEF_HELPER_5(msa_sat_s_df, void, env, i32, i32, i32, i32)
+DEF_HELPER_5(msa_sat_u_df, void, env, i32, i32, i32, i32)
+DEF_HELPER_5(msa_srari_df, void, env, i32, i32, i32, i32)
+DEF_HELPER_5(msa_srlri_df, void, env, i32, i32, i32, i32)
diff --git a/target-mips/msa_helper.c b/target-mips/msa_helper.c
index ffdde07..da43439 100644
--- a/target-mips/msa_helper.c
+++ b/target-mips/msa_helper.c
@@ -256,3 +256,200 @@  void helper_msa_ldi_df(CPUMIPSState *env, uint32_t df, uint32_t wd,
         assert(0);
     }
 }
+
+/* Data format bit position and unsigned values */
+#define BIT_POSITION(x, df) ((uint64_t)(x) % DF_BITS(df))
+
+static inline int64_t msa_sll_df(uint32_t df, int64_t arg1, int64_t arg2)
+{
+    int32_t b_arg2 = BIT_POSITION(arg2, df);
+    return arg1 << b_arg2;
+}
+
+static inline int64_t msa_sra_df(uint32_t df, int64_t arg1, int64_t arg2)
+{
+    int32_t b_arg2 = BIT_POSITION(arg2, df);
+    return arg1 >> b_arg2;
+}
+
+static inline int64_t msa_srl_df(uint32_t df, int64_t arg1, int64_t arg2)
+{
+    uint64_t u_arg1 = UNSIGNED(arg1, df);
+    int32_t b_arg2 = BIT_POSITION(arg2, df);
+    return u_arg1 >> b_arg2;
+}
+
+static inline int64_t msa_bclr_df(uint32_t df, int64_t arg1, int64_t arg2)
+{
+    int32_t b_arg2 = BIT_POSITION(arg2, df);
+    return UNSIGNED(arg1 & (~(1LL << b_arg2)), df);
+}
+
+static inline int64_t msa_bset_df(uint32_t df, int64_t arg1,
+        int64_t arg2)
+{
+    int32_t b_arg2 = BIT_POSITION(arg2, df);
+    return UNSIGNED(arg1 | (1LL << b_arg2), df);
+}
+
+static inline int64_t msa_bneg_df(uint32_t df, int64_t arg1, int64_t arg2)
+{
+    int32_t b_arg2 = BIT_POSITION(arg2, df);
+    return UNSIGNED(arg1 ^ (1LL << b_arg2), df);
+}
+
+static inline int64_t msa_binsl_df(uint32_t df, int64_t dest, int64_t arg1,
+                                   int64_t arg2)
+{
+    uint64_t u_arg1 = UNSIGNED(arg1, df);
+    uint64_t u_dest = UNSIGNED(dest, df);
+    int32_t sh_d = BIT_POSITION(arg2, df) + 1;
+    int32_t sh_a = DF_BITS(df) - sh_d;
+    if (sh_d == DF_BITS(df)) {
+        return u_arg1;
+    } else {
+        return UNSIGNED(UNSIGNED(u_dest << sh_d, df) >> sh_d, df) |
+               UNSIGNED(UNSIGNED(u_arg1 >> sh_a, df) << sh_a, df);
+    }
+}
+
+static inline int64_t msa_binsr_df(uint32_t df, int64_t dest, int64_t arg1,
+                                   int64_t arg2)
+{
+    uint64_t u_arg1 = UNSIGNED(arg1, df);
+    uint64_t u_dest = UNSIGNED(dest, df);
+    int32_t sh_d = BIT_POSITION(arg2, df) + 1;
+    int32_t sh_a = DF_BITS(df) - sh_d;
+    if (sh_d == DF_BITS(df)) {
+        return u_arg1;
+    } else {
+        return UNSIGNED(UNSIGNED(u_dest >> sh_d, df) << sh_d, df) |
+               UNSIGNED(UNSIGNED(u_arg1 << sh_a, df) >> sh_a, df);
+    }
+}
+
+static inline int64_t msa_sat_s_df(uint32_t df, int64_t arg, uint32_t m)
+{
+    return arg < M_MIN_INT(m+1) ? M_MIN_INT(m+1) :
+                                  arg > M_MAX_INT(m+1) ? M_MAX_INT(m+1) :
+                                                         arg;
+}
+
+static inline int64_t msa_sat_u_df(uint32_t df, int64_t arg, uint32_t m)
+{
+    uint64_t u_arg = UNSIGNED(arg, df);
+    return  u_arg < M_MAX_UINT(m+1) ? u_arg :
+                                      M_MAX_UINT(m+1);
+}
+
+static inline int64_t msa_srar_df(uint32_t df, int64_t arg1, int64_t arg2)
+{
+    int32_t b_arg2 = BIT_POSITION(arg2, df);
+    if (b_arg2 == 0) {
+        return arg1;
+    } else {
+        int64_t r_bit = (arg1 >> (b_arg2 - 1)) & 1;
+        return (arg1 >> b_arg2) + r_bit;
+    }
+}
+
+static inline int64_t msa_srlr_df(uint32_t df, int64_t arg1, int64_t arg2)
+{
+    uint64_t u_arg1 = UNSIGNED(arg1, df);
+    int32_t b_arg2 = BIT_POSITION(arg2, df);
+    if (b_arg2 == 0) {
+        return u_arg1;
+    } else {
+        uint64_t r_bit = (u_arg1 >> (b_arg2 - 1)) & 1;
+        return (u_arg1 >> b_arg2) + r_bit;
+    }
+}
+
+#define MSA_BINOP_IMMU_DF(helper, func)                                  \
+void helper_msa_ ## helper ## _df(CPUMIPSState *env, uint32_t df, uint32_t wd, \
+                       uint32_t ws, uint32_t u5)                        \
+{                                                                       \
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);                          \
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);                          \
+    uint32_t i;                                                         \
+                                                                        \
+    switch (df) {                                                       \
+    case DF_BYTE:                                                       \
+        for (i = 0; i < DF_ELEMENTS(DF_BYTE); i++) {                    \
+            pwd->b[i] = msa_ ## func ## _df(df, pws->b[i], u5);         \
+        }                                                               \
+        break;                                                          \
+    case DF_HALF:                                                       \
+        for (i = 0; i < DF_ELEMENTS(DF_HALF); i++) {                    \
+            pwd->h[i] = msa_ ## func ## _df(df, pws->h[i], u5);         \
+        }                                                               \
+        break;                                                          \
+    case DF_WORD:                                                       \
+        for (i = 0; i < DF_ELEMENTS(DF_WORD); i++) {                    \
+            pwd->w[i] = msa_ ## func ## _df(df, pws->w[i], u5);         \
+        }                                                               \
+        break;                                                          \
+    case DF_DOUBLE:                                                     \
+        for (i = 0; i < DF_ELEMENTS(DF_DOUBLE); i++) {                  \
+            pwd->d[i] = msa_ ## func ## _df(df, pws->d[i], u5);         \
+        }                                                               \
+        break;                                                          \
+    default:                                                            \
+        assert(0);                                                      \
+    }                                                                   \
+}
+
+MSA_BINOP_IMMU_DF(slli, sll)
+MSA_BINOP_IMMU_DF(srai, sra)
+MSA_BINOP_IMMU_DF(srli, srl)
+MSA_BINOP_IMMU_DF(bclri, bclr)
+MSA_BINOP_IMMU_DF(bseti, bset)
+MSA_BINOP_IMMU_DF(bnegi, bneg)
+MSA_BINOP_IMMU_DF(sat_s, sat_s)
+MSA_BINOP_IMMU_DF(sat_u, sat_u)
+MSA_BINOP_IMMU_DF(srari, srar)
+MSA_BINOP_IMMU_DF(srlri, srlr)
+#undef MSA_BINOP_IMMU_DF
+
+#define MSA_TEROP_IMMU_DF(helper, func)                                  \
+void helper_msa_ ## helper ## _df(CPUMIPSState *env, uint32_t df,       \
+                                  uint32_t wd, uint32_t ws, uint32_t u5) \
+{                                                                       \
+    wr_t *pwd = &(env->active_fpu.fpr[wd].wr);                          \
+    wr_t *pws = &(env->active_fpu.fpr[ws].wr);                          \
+    uint32_t i;                                                         \
+                                                                        \
+    switch (df) {                                                       \
+    case DF_BYTE:                                                       \
+        for (i = 0; i < DF_ELEMENTS(DF_BYTE); i++) {                    \
+            pwd->b[i] = msa_ ## func ## _df(df, pwd->b[i], pws->b[i],   \
+                                            u5);                        \
+        }                                                               \
+        break;                                                          \
+    case DF_HALF:                                                       \
+        for (i = 0; i < DF_ELEMENTS(DF_HALF); i++) {                    \
+            pwd->h[i] = msa_ ## func ## _df(df, pwd->h[i], pws->h[i],   \
+                                            u5);                        \
+        }                                                               \
+        break;                                                          \
+    case DF_WORD:                                                       \
+        for (i = 0; i < DF_ELEMENTS(DF_WORD); i++) {                    \
+            pwd->w[i] = msa_ ## func ## _df(df, pwd->w[i], pws->w[i],   \
+                                            u5);                        \
+        }                                                               \
+        break;                                                          \
+    case DF_DOUBLE:                                                     \
+        for (i = 0; i < DF_ELEMENTS(DF_DOUBLE); i++) {                  \
+            pwd->d[i] = msa_ ## func ## _df(df, pwd->d[i], pws->d[i],   \
+                                            u5);                        \
+        }                                                               \
+        break;                                                          \
+    default:                                                            \
+        assert(0);                                                      \
+    }                                                                   \
+}
+
+MSA_TEROP_IMMU_DF(binsli, binsl)
+MSA_TEROP_IMMU_DF(binsri, binsr)
+#undef MSA_TEROP_IMMU_DF
+
diff --git a/target-mips/translate.c b/target-mips/translate.c
index 62dd0b9..f304c82 100644
--- a/target-mips/translate.c
+++ b/target-mips/translate.c
@@ -17470,6 +17470,87 @@  static void gen_msa_i5(CPUMIPSState *env, DisasContext *ctx)
     tcg_temp_free_i64(ts5);
 }
 
+static void gen_msa_bit(CPUMIPSState *env, DisasContext *ctx)
+{
+#define MASK_MSA_BIT(op)    (MASK_MSA_MINOR(op) | (op & (0x7 << 23)))
+    uint32_t opcode = ctx->opcode;
+
+    uint8_t dfm = (ctx->opcode >> 16) & 0x7f;
+    uint32_t df = 0, m = 0;
+    uint8_t ws = (ctx->opcode >> 11) & 0x1f;
+    uint8_t wd = (ctx->opcode >> 6) & 0x1f;
+
+    if ((dfm & 0x40) == 0x00) {
+        m = dfm & 0x3f;
+        df = DF_DOUBLE;
+    } else if ((dfm & 0x60) == 0x40) {
+        m = dfm & 0x1f;
+        df = DF_WORD;
+    } else if ((dfm & 0x70) == 0x60) {
+        m = dfm & 0x0f;
+        df = DF_HALF;
+    } else if ((dfm & 0x78) == 0x70) {
+        m = dfm & 0x7;
+        df = DF_BYTE;
+    } else {
+        generate_exception(ctx, EXCP_RI);
+        return;
+    }
+
+    TCGv_i32 tdf = tcg_const_i32(df);
+    TCGv_i32 tm  = tcg_const_i32(m);
+    TCGv_i32 twd = tcg_const_i32(wd);
+    TCGv_i32 tws = tcg_const_i32(ws);
+
+    switch (MASK_MSA_BIT(opcode)) {
+    case OPC_SLLI_df:
+        gen_helper_msa_slli_df(cpu_env, tdf, twd, tws, tm);
+        break;
+    case OPC_SRAI_df:
+        gen_helper_msa_srai_df(cpu_env, tdf, twd, tws, tm);
+        break;
+    case OPC_SRLI_df:
+        gen_helper_msa_srli_df(cpu_env, tdf, twd, tws, tm);
+        break;
+    case OPC_BCLRI_df:
+        gen_helper_msa_bclri_df(cpu_env, tdf, twd, tws, tm);
+        break;
+    case OPC_BSETI_df:
+        gen_helper_msa_bseti_df(cpu_env, tdf, twd, tws, tm);
+        break;
+    case OPC_BNEGI_df:
+        gen_helper_msa_bnegi_df(cpu_env, tdf, twd, tws, tm);
+        break;
+    case OPC_BINSLI_df:
+        gen_helper_msa_binsli_df(cpu_env, tdf, twd, tws, tm);
+        break;
+    case OPC_BINSRI_df:
+        gen_helper_msa_binsri_df(cpu_env, tdf, twd, tws, tm);
+        break;
+    case OPC_SAT_S_df:
+        gen_helper_msa_sat_s_df(cpu_env, tdf, twd, tws, tm);
+        break;
+    case OPC_SAT_U_df:
+        gen_helper_msa_sat_u_df(cpu_env, tdf, twd, tws, tm);
+        break;
+    case OPC_SRARI_df:
+        gen_helper_msa_srari_df(cpu_env, tdf, twd, tws, tm);
+        break;
+    case OPC_SRLRI_df:
+        gen_helper_msa_srlri_df(cpu_env, tdf, twd, tws, tm);
+        break;
+    default:
+        MIPS_INVAL("MSA instruction");
+        generate_exception(ctx, EXCP_RI);
+        break;
+    }
+
+    tcg_temp_free_i32(tdf);
+    tcg_temp_free_i32(tm);
+    tcg_temp_free_i32(twd);
+    tcg_temp_free_i32(tws);
+}
+
 static void gen_msa(CPUMIPSState *env, DisasContext *ctx)
 {
     uint32_t opcode = ctx->opcode;
@@ -17486,6 +17567,10 @@  static void gen_msa(CPUMIPSState *env, DisasContext *ctx)
     case OPC_MSA_I5_07:
         gen_msa_i5(env, ctx);
         break;
+    case OPC_MSA_BIT_09:
+    case OPC_MSA_BIT_0A:
+        gen_msa_bit(env, ctx);
+        break;
     default:
         MIPS_INVAL("MSA instruction");
         generate_exception(ctx, EXCP_RI);