1 files changed, 34 insertions, 21 deletions

diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index ac80f57..dbf4759 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -433,12 +433,6 @@ static void gen_rebuild_hflags(DisasContext *s)
     gen_helper_rebuild_hflags_a64(tcg_env, tcg_constant_i32(s->current_el));
 }
 
-static void gen_exception_internal(int excp)
-{
-    assert(excp_is_internal(excp));
-    gen_helper_exception_internal(tcg_env, tcg_constant_i32(excp));
-}
-
 static void gen_exception_internal_insn(DisasContext *s, int excp)
 {
     gen_a64_update_pc(s, 0);
@@ -1387,11 +1381,8 @@ static bool fp_access_check_only(DisasContext *s)
     return true;
 }
 
-static bool fp_access_check(DisasContext *s)
+static bool nonstreaming_check(DisasContext *s)
 {
-    if (!fp_access_check_only(s)) {
-        return false;
-    }
     if (s->sme_trap_nonstreaming && s->is_nonstreaming) {
         gen_exception_insn(s, 0, EXCP_UDEF,
                            syn_smetrap(SME_ET_Streaming, false));
@@ -1400,6 +1391,11 @@ static bool fp_access_check(DisasContext *s)
     return true;
 }
 
+static bool fp_access_check(DisasContext *s)
+{
+    return fp_access_check_only(s) && nonstreaming_check(s);
+}
+
 /*
  * Return <0 for non-supported element sizes, with MO_16 controlled by
  * FEAT_FP16; return 0 for fp disabled; otherwise return >0 for success.
@@ -1450,14 +1446,24 @@ static int fp_access_check_vector_hsd(DisasContext *s, bool is_q, MemOp esz)
  */
 bool sve_access_check(DisasContext *s)
 {
-    if (s->pstate_sm || !dc_isar_feature(aa64_sve, s)) {
+    if (dc_isar_feature(aa64_sme, s)) {
         bool ret;
 
-        assert(dc_isar_feature(aa64_sme, s));
-        ret = sme_sm_enabled_check(s);
+        if (s->pstate_sm) {
+            ret = sme_enabled_check(s);
+        } else if (dc_isar_feature(aa64_sve, s)) {
+            goto continue_sve;
+        } else {
+            ret = sme_sm_enabled_check(s);
+        }
+        if (ret) {
+            ret = nonstreaming_check(s);
+        }
         s->sve_access_checked = (ret ? 1 : -1);
         return ret;
     }
+
+ continue_sve:
     if (s->sve_excp_el) {
         /* Assert that we only raise one exception per instruction. */
         assert(!s->sve_access_checked);
@@ -1494,7 +1500,8 @@ bool sme_enabled_check(DisasContext *s)
      * to be zero when fp_excp_el has priority.  This is because we need
      * sme_excp_el by itself for cpregs access checks.
      */
-    if (!s->fp_excp_el || s->sme_excp_el < s->fp_excp_el) {
+    if (s->sme_excp_el
+        && (!s->fp_excp_el || s->sme_excp_el <= s->fp_excp_el)) {
         bool ret = sme_access_check(s);
         s->fp_access_checked = (ret ? 1 : -1);
         return ret;
@@ -1816,6 +1823,10 @@ static bool trans_RETA(DisasContext *s, arg_reta *a)
 {
     TCGv_i64 dst;
 
+    if (!dc_isar_feature(aa64_pauth, s)) {
+        return false;
+    }
+
     dst = auth_branch_target(s, cpu_reg(s, 30), cpu_X[31], !a->m);
     gen_a64_set_pc(s, dst);
     s->base.is_jmp = DISAS_JUMP;
@@ -6103,9 +6114,9 @@ static bool do_dot_vector_env(DisasContext *s, arg_qrrr_e *a,
     return true;
 }
 
-TRANS_FEAT(SDOT_v, aa64_dp, do_dot_vector, a, gen_helper_gvec_sdot_b)
-TRANS_FEAT(UDOT_v, aa64_dp, do_dot_vector, a, gen_helper_gvec_udot_b)
-TRANS_FEAT(USDOT_v, aa64_i8mm, do_dot_vector, a, gen_helper_gvec_usdot_b)
+TRANS_FEAT(SDOT_v, aa64_dp, do_dot_vector, a, gen_helper_gvec_sdot_4b)
+TRANS_FEAT(UDOT_v, aa64_dp, do_dot_vector, a, gen_helper_gvec_udot_4b)
+TRANS_FEAT(USDOT_v, aa64_i8mm, do_dot_vector, a, gen_helper_gvec_usdot_4b)
 TRANS_FEAT(BFDOT_v, aa64_bf16, do_dot_vector_env, a, gen_helper_gvec_bfdot)
 TRANS_FEAT(BFMMLA, aa64_bf16, do_dot_vector_env, a, gen_helper_gvec_bfmmla)
 TRANS_FEAT(SMMLA, aa64_i8mm, do_dot_vector, a, gen_helper_gvec_smmla_b)
@@ -6865,12 +6876,12 @@ static bool do_dot_vector_idx_env(DisasContext *s, arg_qrrx_e *a,
     return true;
 }
 
-TRANS_FEAT(SDOT_vi, aa64_dp, do_dot_vector_idx, a, gen_helper_gvec_sdot_idx_b)
-TRANS_FEAT(UDOT_vi, aa64_dp, do_dot_vector_idx, a, gen_helper_gvec_udot_idx_b)
+TRANS_FEAT(SDOT_vi, aa64_dp, do_dot_vector_idx, a, gen_helper_gvec_sdot_idx_4b)
+TRANS_FEAT(UDOT_vi, aa64_dp, do_dot_vector_idx, a, gen_helper_gvec_udot_idx_4b)
 TRANS_FEAT(SUDOT_vi, aa64_i8mm, do_dot_vector_idx, a,
-           gen_helper_gvec_sudot_idx_b)
+           gen_helper_gvec_sudot_idx_4b)
 TRANS_FEAT(USDOT_vi, aa64_i8mm, do_dot_vector_idx, a,
-           gen_helper_gvec_usdot_idx_b)
+           gen_helper_gvec_usdot_idx_4b)
 TRANS_FEAT(BFDOT_vi, aa64_bf16, do_dot_vector_idx_env, a,
            gen_helper_gvec_bfdot_idx)
 
@@ -10128,8 +10139,10 @@ static void aarch64_tr_init_disas_context(DisasContextBase *dcbase,
     dc->trap_eret = EX_TBFLAG_A64(tb_flags, TRAP_ERET);
     dc->sve_excp_el = EX_TBFLAG_A64(tb_flags, SVEEXC_EL);
     dc->sme_excp_el = EX_TBFLAG_A64(tb_flags, SMEEXC_EL);
+    dc->zt0_excp_el = EX_TBFLAG_A64(tb_flags, ZT0EXC_EL);
     dc->vl = (EX_TBFLAG_A64(tb_flags, VL) + 1) * 16;
     dc->svl = (EX_TBFLAG_A64(tb_flags, SVL) + 1) * 16;
+    dc->max_svl = arm_cpu->sme_max_vq * 16;
     dc->pauth_active = EX_TBFLAG_A64(tb_flags, PAUTH_ACTIVE);
     dc->bt = EX_TBFLAG_A64(tb_flags, BT);
     dc->btype = EX_TBFLAG_A64(tb_flags, BTYPE);