summary refs log tree commit diff stats
path: root/target
diff options
context:
space:
mode:
Diffstat (limited to 'target')
-rw-r--r--target/arm/tcg/translate-a64.c2
-rw-r--r--target/arm/tcg/translate.c2
-rw-r--r--target/arm/tcg/translate.h12
-rw-r--r--target/hppa/int_helper.c20
-rw-r--r--target/hppa/sys_helper.c18
-rw-r--r--target/hppa/translate.c10
-rw-r--r--target/i386/tcg/translate.c3
-rw-r--r--target/m68k/cpu.c12
-rw-r--r--target/m68k/cpu.h3
-rw-r--r--target/m68k/fpu_helper.c72
-rw-r--r--target/m68k/helper.c4
-rw-r--r--target/m68k/helper.h2
-rw-r--r--target/m68k/translate.c4
-rw-r--r--target/microblaze/translate.c8
-rw-r--r--target/riscv/translate.c11
-rw-r--r--target/s390x/tcg/translate.c4
-rw-r--r--target/sh4/cpu.h14
-rw-r--r--target/sh4/helper.h4
-rw-r--r--target/sh4/op_helper.c51
-rw-r--r--target/sh4/translate.c7
20 files changed, 183 insertions, 80 deletions
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
index 340265beb0..2666d52711 100644
--- a/target/arm/tcg/translate-a64.c
+++ b/target/arm/tcg/translate-a64.c
@@ -14179,7 +14179,7 @@ static void aarch64_tr_insn_start(DisasContextBase *dcbase, CPUState *cpu)
         pc_arg &= ~TARGET_PAGE_MASK;
     }
     tcg_gen_insn_start(pc_arg, 0, 0);
-    dc->insn_start = tcg_last_op();
+    dc->insn_start_updated = false;
 }
 
 static void aarch64_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu)
diff --git a/target/arm/tcg/translate.c b/target/arm/tcg/translate.c
index 69585e6003..dc49a8d806 100644
--- a/target/arm/tcg/translate.c
+++ b/target/arm/tcg/translate.c
@@ -9273,7 +9273,7 @@ static void arm_tr_insn_start(DisasContextBase *dcbase, CPUState *cpu)
         condexec_bits = (dc->condexec_cond << 4) | (dc->condexec_mask >> 1);
     }
     tcg_gen_insn_start(pc_arg, condexec_bits, 0);
-    dc->insn_start = tcg_last_op();
+    dc->insn_start_updated = false;
 }
 
 static bool arm_check_kernelpage(DisasContext *dc)
diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h
index 93be745cf3..dc66ff2190 100644
--- a/target/arm/tcg/translate.h
+++ b/target/arm/tcg/translate.h
@@ -165,10 +165,10 @@ typedef struct DisasContext {
     uint8_t gm_blocksize;
     /* True if this page is guarded.  */
     bool guarded_page;
+    /* True if the current insn_start has been updated. */
+    bool insn_start_updated;
     /* Bottom two bits of XScale c15_cpar coprocessor access control reg */
     int c15_cpar;
-    /* TCG op of the current insn_start.  */
-    TCGOp *insn_start;
     /* Offset from VNCR_EL2 when FEAT_NV2 redirects this reg to memory */
     uint32_t nv2_redirect_offset;
 } DisasContext;
@@ -276,10 +276,10 @@ static inline void disas_set_insn_syndrome(DisasContext *s, uint32_t syn)
     syn &= ARM_INSN_START_WORD2_MASK;
     syn >>= ARM_INSN_START_WORD2_SHIFT;
 
-    /* We check and clear insn_start_idx to catch multiple updates.  */
-    assert(s->insn_start != NULL);
-    tcg_set_insn_start_param(s->insn_start, 2, syn);
-    s->insn_start = NULL;
+    /* Check for multiple updates.  */
+    assert(!s->insn_start_updated);
+    s->insn_start_updated = true;
+    tcg_set_insn_start_param(s->base.insn_start, 2, syn);
 }
 
 static inline int curr_insn_len(DisasContext *s)
diff --git a/target/hppa/int_helper.c b/target/hppa/int_helper.c
index 90437a92cd..a667ee380d 100644
--- a/target/hppa/int_helper.c
+++ b/target/hppa/int_helper.c
@@ -107,14 +107,10 @@ void hppa_cpu_do_interrupt(CPUState *cs)
 
     /* step 3 */
     /*
-     * For pa1.x, IIASQ is simply a copy of IASQ.
-     * For pa2.0, IIASQ is the top bits of the virtual address,
-     *            or zero if translation is disabled.
+     * IIASQ is the top bits of the virtual address, or zero if translation
+     * is disabled -- with PSW_W == 0, this will reduce to the space.
      */
-    if (!hppa_is_pa20(env)) {
-        env->cr[CR_IIASQ] = env->iasq_f >> 32;
-        env->cr_back[0] = env->iasq_b >> 32;
-    } else if (old_psw & PSW_C) {
+    if (old_psw & PSW_C) {
         env->cr[CR_IIASQ] =
             hppa_form_gva_psw(old_psw, env->iasq_f, env->iaoq_f) >> 32;
         env->cr_back[0] =
@@ -123,8 +119,14 @@ void hppa_cpu_do_interrupt(CPUState *cs)
         env->cr[CR_IIASQ] = 0;
         env->cr_back[0] = 0;
     }
-    env->cr[CR_IIAOQ] = env->iaoq_f;
-    env->cr_back[1] = env->iaoq_b;
+    /* IIAOQ is the full offset for wide mode, or 32 bits for narrow mode. */
+    if (old_psw & PSW_W) {
+        env->cr[CR_IIAOQ] = env->iaoq_f;
+        env->cr_back[1] = env->iaoq_b;
+    } else {
+        env->cr[CR_IIAOQ] = (uint32_t)env->iaoq_f;
+        env->cr_back[1] = (uint32_t)env->iaoq_b;
+    }
 
     if (old_psw & PSW_Q) {
         /* step 5 */
diff --git a/target/hppa/sys_helper.c b/target/hppa/sys_helper.c
index 208e51c086..22d6c89964 100644
--- a/target/hppa/sys_helper.c
+++ b/target/hppa/sys_helper.c
@@ -78,21 +78,21 @@ target_ulong HELPER(swap_system_mask)(CPUHPPAState *env, target_ulong nsm)
 
 void HELPER(rfi)(CPUHPPAState *env)
 {
-    env->iasq_f = (uint64_t)env->cr[CR_IIASQ] << 32;
-    env->iasq_b = (uint64_t)env->cr_back[0] << 32;
-    env->iaoq_f = env->cr[CR_IIAOQ];
-    env->iaoq_b = env->cr_back[1];
+    uint64_t mask;
+
+    cpu_hppa_put_psw(env, env->cr[CR_IPSW]);
 
     /*
      * For pa2.0, IIASQ is the top bits of the virtual address.
      * To recreate the space identifier, remove the offset bits.
+     * For pa1.x, the mask reduces to no change to space.
      */
-    if (hppa_is_pa20(env)) {
-        env->iasq_f &= ~env->iaoq_f;
-        env->iasq_b &= ~env->iaoq_b;
-    }
+    mask = gva_offset_mask(env->psw);
 
-    cpu_hppa_put_psw(env, env->cr[CR_IPSW]);
+    env->iaoq_f = env->cr[CR_IIAOQ];
+    env->iaoq_b = env->cr_back[1];
+    env->iasq_f = (env->cr[CR_IIASQ] << 32) & ~(env->iaoq_f & mask);
+    env->iasq_b = (env->cr_back[0] << 32) & ~(env->iaoq_b & mask);
 }
 
 static void getshadowregs(CPUHPPAState *env)
diff --git a/target/hppa/translate.c b/target/hppa/translate.c
index 8a1a8bc3aa..42fa480950 100644
--- a/target/hppa/translate.c
+++ b/target/hppa/translate.c
@@ -44,7 +44,6 @@ typedef struct DisasCond {
 typedef struct DisasContext {
     DisasContextBase base;
     CPUState *cs;
-    TCGOp *insn_start;
 
     uint64_t iaoq_f;
     uint64_t iaoq_b;
@@ -62,6 +61,7 @@ typedef struct DisasContext {
     int privilege;
     bool psw_n_nonzero;
     bool is_pa20;
+    bool insn_start_updated;
 
 #ifdef CONFIG_USER_ONLY
     MemOp unalign;
@@ -300,9 +300,9 @@ void hppa_translate_init(void)
 
 static void set_insn_breg(DisasContext *ctx, int breg)
 {
-    assert(ctx->insn_start != NULL);
-    tcg_set_insn_start_param(ctx->insn_start, 2, breg);
-    ctx->insn_start = NULL;
+    assert(!ctx->insn_start_updated);
+    ctx->insn_start_updated = true;
+    tcg_set_insn_start_param(ctx->base.insn_start, 2, breg);
 }
 
 static DisasCond cond_make_f(void)
@@ -4694,7 +4694,7 @@ static void hppa_tr_insn_start(DisasContextBase *dcbase, CPUState *cs)
     DisasContext *ctx = container_of(dcbase, DisasContext, base);
 
     tcg_gen_insn_start(ctx->iaoq_f, ctx->iaoq_b, 0);
-    ctx->insn_start = tcg_last_op();
+    ctx->insn_start_updated = false;
 }
 
 static void hppa_tr_translate_insn(DisasContextBase *dcbase, CPUState *cs)
diff --git a/target/i386/tcg/translate.c b/target/i386/tcg/translate.c
index 07f642dc9e..76a42c679c 100644
--- a/target/i386/tcg/translate.c
+++ b/target/i386/tcg/translate.c
@@ -139,6 +139,7 @@ typedef struct DisasContext {
     TCGv_i64 tmp1_i64;
 
     sigjmp_buf jmpbuf;
+    TCGOp *prev_insn_start;
     TCGOp *prev_insn_end;
 } DisasContext;
 
@@ -3123,6 +3124,7 @@ static bool disas_insn(DisasContext *s, CPUState *cpu)
         /* END TODO */
         s->base.num_insns--;
         tcg_remove_ops_after(s->prev_insn_end);
+        s->base.insn_start = s->prev_insn_start;
         s->base.is_jmp = DISAS_TOO_MANY;
         return false;
     default:
@@ -6995,6 +6997,7 @@ static void i386_tr_insn_start(DisasContextBase *dcbase, CPUState *cpu)
     DisasContext *dc = container_of(dcbase, DisasContext, base);
     target_ulong pc_arg = dc->base.pc_next;
 
+    dc->prev_insn_start = dc->base.insn_start;
     dc->prev_insn_end = tcg_last_op();
     if (tb_cflags(dcbase->tb) & CF_PCREL) {
         pc_arg &= ~TARGET_PAGE_MASK;
diff --git a/target/m68k/cpu.c b/target/m68k/cpu.c
index 7c8efbb42c..df49ff1880 100644
--- a/target/m68k/cpu.c
+++ b/target/m68k/cpu.c
@@ -390,12 +390,19 @@ static const VMStateDescription vmstate_freg = {
     }
 };
 
-static int fpu_post_load(void *opaque, int version)
+static int fpu_pre_save(void *opaque)
 {
     M68kCPU *s = opaque;
 
-    cpu_m68k_restore_fp_status(&s->env);
+    s->env.fpsr = cpu_m68k_get_fpsr(&s->env);
+    return 0;
+}
+
+static int fpu_post_load(void *opaque, int version)
+{
+    M68kCPU *s = opaque;
 
+    cpu_m68k_set_fpsr(&s->env, s->env.fpsr);
     return 0;
 }
 
@@ -404,6 +411,7 @@ const VMStateDescription vmmstate_fpu = {
     .version_id = 1,
     .minimum_version_id = 1,
     .needed = fpu_needed,
+    .pre_save = fpu_pre_save,
     .post_load = fpu_post_load,
     .fields = (const VMStateField[]) {
         VMSTATE_UINT32(env.fpcr, M68kCPU),
diff --git a/target/m68k/cpu.h b/target/m68k/cpu.h
index 346427e144..e184239a81 100644
--- a/target/m68k/cpu.h
+++ b/target/m68k/cpu.h
@@ -199,7 +199,8 @@ void cpu_m68k_set_ccr(CPUM68KState *env, uint32_t);
 void cpu_m68k_set_sr(CPUM68KState *env, uint32_t);
 void cpu_m68k_restore_fp_status(CPUM68KState *env);
 void cpu_m68k_set_fpcr(CPUM68KState *env, uint32_t val);
-
+uint32_t cpu_m68k_get_fpsr(CPUM68KState *env);
+void cpu_m68k_set_fpsr(CPUM68KState *env, uint32_t val);
 
 /*
  * Instead of computing the condition codes after each m68k instruction,
diff --git a/target/m68k/fpu_helper.c b/target/m68k/fpu_helper.c
index ab120b5f59..8314791f50 100644
--- a/target/m68k/fpu_helper.c
+++ b/target/m68k/fpu_helper.c
@@ -164,6 +164,78 @@ void HELPER(set_fpcr)(CPUM68KState *env, uint32_t val)
     cpu_m68k_set_fpcr(env, val);
 }
 
+/* Convert host exception flags to cpu_m68k form.  */
+static int cpu_m68k_exceptbits_from_host(int host_bits)
+{
+    int target_bits = 0;
+
+    if (host_bits & float_flag_invalid) {
+        target_bits |= 0x80;
+    }
+    if (host_bits & float_flag_overflow) {
+        target_bits |= 0x40;
+    }
+    if (host_bits & (float_flag_underflow | float_flag_output_denormal)) {
+        target_bits |= 0x20;
+    }
+    if (host_bits & float_flag_divbyzero) {
+        target_bits |= 0x10;
+    }
+    if (host_bits & float_flag_inexact) {
+        target_bits |= 0x08;
+    }
+    return target_bits;
+}
+
+/* Convert cpu_m68k exception flags to target form.  */
+static int cpu_m68k_exceptbits_to_host(int target_bits)
+{
+    int host_bits = 0;
+
+    if (target_bits & 0x80) {
+        host_bits |= float_flag_invalid;
+    }
+    if (target_bits & 0x40) {
+        host_bits |= float_flag_overflow;
+    }
+    if (target_bits & 0x20) {
+        host_bits |= float_flag_underflow;
+    }
+    if (target_bits & 0x10) {
+        host_bits |= float_flag_divbyzero;
+    }
+    if (target_bits & 0x08) {
+        host_bits |= float_flag_inexact;
+    }
+    return host_bits;
+}
+
+uint32_t cpu_m68k_get_fpsr(CPUM68KState *env)
+{
+    int host_flags = get_float_exception_flags(&env->fp_status);
+    int target_flags = cpu_m68k_exceptbits_from_host(host_flags);
+    int except = (env->fpsr & ~(0xf8)) | target_flags;
+    return except;
+}
+
+uint32_t HELPER(get_fpsr)(CPUM68KState *env)
+{
+    return cpu_m68k_get_fpsr(env);
+}
+
+void cpu_m68k_set_fpsr(CPUM68KState *env, uint32_t val)
+{
+    env->fpsr = val;
+
+    int host_flags = cpu_m68k_exceptbits_to_host((int) env->fpsr);
+    set_float_exception_flags(host_flags, &env->fp_status);
+}
+
+void HELPER(set_fpsr)(CPUM68KState *env, uint32_t val)
+{
+    cpu_m68k_set_fpsr(env, val);
+}
+
 #define PREC_BEGIN(prec)                                        \
     do {                                                        \
         FloatX80RoundPrec old =                                 \
diff --git a/target/m68k/helper.c b/target/m68k/helper.c
index 1a475f082a..7a91f33b17 100644
--- a/target/m68k/helper.c
+++ b/target/m68k/helper.c
@@ -87,7 +87,7 @@ static int m68k_fpu_gdb_get_reg(CPUState *cs, GByteArray *mem_buf, int n)
     case 8: /* fpcontrol */
         return gdb_get_reg32(mem_buf, env->fpcr);
     case 9: /* fpstatus */
-        return gdb_get_reg32(mem_buf, env->fpsr);
+        return gdb_get_reg32(mem_buf, cpu_m68k_get_fpsr(env));
     case 10: /* fpiar, not implemented */
         return gdb_get_reg32(mem_buf, 0);
     }
@@ -109,7 +109,7 @@ static int m68k_fpu_gdb_set_reg(CPUState *cs, uint8_t *mem_buf, int n)
         cpu_m68k_set_fpcr(env, ldl_p(mem_buf));
         return 4;
     case 9: /* fpstatus */
-        env->fpsr = ldl_p(mem_buf);
+        cpu_m68k_set_fpsr(env, ldl_p(mem_buf));
         return 4;
     case 10: /* fpiar, not implemented */
         return 4;
diff --git a/target/m68k/helper.h b/target/m68k/helper.h
index 2bbe0dc032..95aa5e53bb 100644
--- a/target/m68k/helper.h
+++ b/target/m68k/helper.h
@@ -54,6 +54,8 @@ DEF_HELPER_4(fsdiv, void, env, fp, fp, fp)
 DEF_HELPER_4(fddiv, void, env, fp, fp, fp)
 DEF_HELPER_4(fsgldiv, void, env, fp, fp, fp)
 DEF_HELPER_FLAGS_3(fcmp, TCG_CALL_NO_RWG, void, env, fp, fp)
+DEF_HELPER_2(set_fpsr, void, env, i32)
+DEF_HELPER_1(get_fpsr, i32, env)
 DEF_HELPER_FLAGS_2(set_fpcr, TCG_CALL_NO_RWG, void, env, i32)
 DEF_HELPER_FLAGS_2(ftst, TCG_CALL_NO_RWG, void, env, fp)
 DEF_HELPER_3(fconst, void, env, fp, i32)
diff --git a/target/m68k/translate.c b/target/m68k/translate.c
index 6ae3df43bc..8a194f2f21 100644
--- a/target/m68k/translate.c
+++ b/target/m68k/translate.c
@@ -4686,7 +4686,7 @@ static void gen_load_fcr(DisasContext *s, TCGv res, int reg)
         tcg_gen_movi_i32(res, 0);
         break;
     case M68K_FPSR:
-        tcg_gen_ld_i32(res, tcg_env, offsetof(CPUM68KState, fpsr));
+        gen_helper_get_fpsr(res, tcg_env);
         break;
     case M68K_FPCR:
         tcg_gen_ld_i32(res, tcg_env, offsetof(CPUM68KState, fpcr));
@@ -4700,7 +4700,7 @@ static void gen_store_fcr(DisasContext *s, TCGv val, int reg)
     case M68K_FPIAR:
         break;
     case M68K_FPSR:
-        tcg_gen_st_i32(val, tcg_env, offsetof(CPUM68KState, fpsr));
+        gen_helper_set_fpsr(tcg_env, val);
         break;
     case M68K_FPCR:
         gen_helper_set_fpcr(tcg_env, val);
diff --git a/target/microblaze/translate.c b/target/microblaze/translate.c
index 4e52ef32db..fc451befae 100644
--- a/target/microblaze/translate.c
+++ b/target/microblaze/translate.c
@@ -62,9 +62,6 @@ typedef struct DisasContext {
     DisasContextBase base;
     const MicroBlazeCPUConfig *cfg;
 
-    /* TCG op of the current insn_start.  */
-    TCGOp *insn_start;
-
     TCGv_i32 r0;
     bool r0_set;
 
@@ -699,14 +696,14 @@ static TCGv compute_ldst_addr_ea(DisasContext *dc, int ra, int rb)
 static void record_unaligned_ess(DisasContext *dc, int rd,
                                  MemOp size, bool store)
 {
-    uint32_t iflags = tcg_get_insn_start_param(dc->insn_start, 1);
+    uint32_t iflags = tcg_get_insn_start_param(dc->base.insn_start, 1);
 
     iflags |= ESR_ESS_FLAG;
     iflags |= rd << 5;
     iflags |= store * ESR_S;
     iflags |= (size == MO_32) * ESR_W;
 
-    tcg_set_insn_start_param(dc->insn_start, 1, iflags);
+    tcg_set_insn_start_param(dc->base.insn_start, 1, iflags);
 }
 #endif
 
@@ -1624,7 +1621,6 @@ static void mb_tr_insn_start(DisasContextBase *dcb, CPUState *cs)
     DisasContext *dc = container_of(dcb, DisasContext, base);
 
     tcg_gen_insn_start(dc->base.pc_next, dc->tb_flags & ~MSR_TB_MASK);
-    dc->insn_start = tcg_last_op();
 }
 
 static void mb_tr_translate_insn(DisasContextBase *dcb, CPUState *cs)
diff --git a/target/riscv/translate.c b/target/riscv/translate.c
index 9d57089fcc..9ff09ebdb6 100644
--- a/target/riscv/translate.c
+++ b/target/riscv/translate.c
@@ -115,8 +115,7 @@ typedef struct DisasContext {
     bool itrigger;
     /* FRM is known to contain a valid value. */
     bool frm_valid;
-    /* TCG of the current insn_start */
-    TCGOp *insn_start;
+    bool insn_start_updated;
 } DisasContext;
 
 static inline bool has_ext(DisasContext *ctx, uint32_t ext)
@@ -207,9 +206,9 @@ static void gen_check_nanbox_s(TCGv_i64 out, TCGv_i64 in)
 
 static void decode_save_opc(DisasContext *ctx)
 {
-    assert(ctx->insn_start != NULL);
-    tcg_set_insn_start_param(ctx->insn_start, 1, ctx->opcode);
-    ctx->insn_start = NULL;
+    assert(!ctx->insn_start_updated);
+    ctx->insn_start_updated = true;
+    tcg_set_insn_start_param(ctx->base.insn_start, 1, ctx->opcode);
 }
 
 static void gen_pc_plus_diff(TCGv target, DisasContext *ctx,
@@ -1224,7 +1223,7 @@ static void riscv_tr_insn_start(DisasContextBase *dcbase, CPUState *cpu)
     }
 
     tcg_gen_insn_start(pc_next, 0);
-    ctx->insn_start = tcg_last_op();
+    ctx->insn_start_updated = false;
 }
 
 static void riscv_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu)
diff --git a/target/s390x/tcg/translate.c b/target/s390x/tcg/translate.c
index 57b7db1ee9..90a74ee795 100644
--- a/target/s390x/tcg/translate.c
+++ b/target/s390x/tcg/translate.c
@@ -141,7 +141,6 @@ struct DisasFields {
 struct DisasContext {
     DisasContextBase base;
     const DisasInsn *insn;
-    TCGOp *insn_start;
     DisasFields fields;
     uint64_t ex_value;
     /*
@@ -6314,7 +6313,7 @@ static DisasJumpType translate_one(CPUS390XState *env, DisasContext *s)
     insn = extract_insn(env, s);
 
     /* Update insn_start now that we know the ILEN.  */
-    tcg_set_insn_start_param(s->insn_start, 2, s->ilen);
+    tcg_set_insn_start_param(s->base.insn_start, 2, s->ilen);
 
     /* Not found means unimplemented/illegal opcode.  */
     if (insn == NULL) {
@@ -6468,7 +6467,6 @@ static void s390x_tr_insn_start(DisasContextBase *dcbase, CPUState *cs)
 
     /* Delay the set of ilen until we've read the insn. */
     tcg_gen_insn_start(dc->base.pc_next, dc->cc_op, 0);
-    dc->insn_start = tcg_last_op();
 }
 
 static target_ulong get_next_pc(CPUS390XState *env, DisasContext *s,
diff --git a/target/sh4/cpu.h b/target/sh4/cpu.h
index 9211da6bde..d928bcf006 100644
--- a/target/sh4/cpu.h
+++ b/target/sh4/cpu.h
@@ -155,12 +155,22 @@ typedef struct CPUArchState {
     uint32_t pc;                /* program counter */
     uint32_t delayed_pc;        /* target of delayed branch */
     uint32_t delayed_cond;      /* condition of delayed branch */
-    uint32_t mach;              /* multiply and accumulate high */
-    uint32_t macl;              /* multiply and accumulate low */
     uint32_t pr;                /* procedure register */
     uint32_t fpscr;             /* floating point status/control register */
     uint32_t fpul;              /* floating point communication register */
 
+    /* multiply and accumulate: high, low and combined. */
+    union {
+        uint64_t mac;
+        struct {
+#if HOST_BIG_ENDIAN
+            uint32_t mach, macl;
+#else
+            uint32_t macl, mach;
+#endif
+        };
+    };
+
     /* float point status register */
     float_status fp_status;
 
diff --git a/target/sh4/helper.h b/target/sh4/helper.h
index 8d792f6b55..29011d3dbb 100644
--- a/target/sh4/helper.h
+++ b/target/sh4/helper.h
@@ -11,8 +11,8 @@ DEF_HELPER_3(movcal, void, env, i32, i32)
 DEF_HELPER_1(discard_movcal_backup, void, env)
 DEF_HELPER_2(ocbi, void, env, i32)
 
-DEF_HELPER_3(macl, void, env, i32, i32)
-DEF_HELPER_3(macw, void, env, i32, i32)
+DEF_HELPER_3(macl, void, env, s32, s32)
+DEF_HELPER_3(macw, void, env, s32, s32)
 
 DEF_HELPER_2(ld_fpscr, void, env, i32)
 
diff --git a/target/sh4/op_helper.c b/target/sh4/op_helper.c
index 4559d0d376..99394b714c 100644
--- a/target/sh4/op_helper.c
+++ b/target/sh4/op_helper.c
@@ -158,38 +158,47 @@ void helper_ocbi(CPUSH4State *env, uint32_t address)
     }
 }
 
-void helper_macl(CPUSH4State *env, uint32_t arg0, uint32_t arg1)
+void helper_macl(CPUSH4State *env, int32_t arg0, int32_t arg1)
 {
+    const int64_t min = -(1ll << 47);
+    const int64_t max = (1ll << 47) - 1;
+    int64_t mul = (int64_t)arg0 * arg1;
+    int64_t mac = env->mac;
     int64_t res;
 
-    res = ((uint64_t) env->mach << 32) | env->macl;
-    res += (int64_t) (int32_t) arg0 *(int64_t) (int32_t) arg1;
-    env->mach = (res >> 32) & 0xffffffff;
-    env->macl = res & 0xffffffff;
-    if (env->sr & (1u << SR_S)) {
-        if (res < 0)
-            env->mach |= 0xffff0000;
-        else
-            env->mach &= 0x00007fff;
+    if (!(env->sr & (1u << SR_S))) {
+        res = mac + mul;
+    } else if (sadd64_overflow(mac, mul, &res)) {
+        res = mac < 0 ? min : max;
+    } else {
+        res = MIN(MAX(res, min), max);
     }
+
+    env->mac = res;
 }
 
-void helper_macw(CPUSH4State *env, uint32_t arg0, uint32_t arg1)
+void helper_macw(CPUSH4State *env, int32_t arg0, int32_t arg1)
 {
-    int64_t res;
+    /* Inputs are already sign-extended from 16 bits. */
+    int32_t mul = arg0 * arg1;
 
-    res = ((uint64_t) env->mach << 32) | env->macl;
-    res += (int64_t) (int16_t) arg0 *(int64_t) (int16_t) arg1;
-    env->mach = (res >> 32) & 0xffffffff;
-    env->macl = res & 0xffffffff;
     if (env->sr & (1u << SR_S)) {
-        if (res < -0x80000000) {
-            env->mach = 1;
-            env->macl = 0x80000000;
-        } else if (res > 0x000000007fffffff) {
+        /*
+         * In saturation arithmetic mode, the accumulator is 32-bit
+         * with carry. MACH is not considered during the addition
+         * operation nor the 32-bit saturation logic.
+         */
+        int32_t res, macl = env->macl;
+
+        if (sadd32_overflow(macl, mul, &res)) {
+            res = macl < 0 ? INT32_MIN : INT32_MAX;
+            /* If overflow occurs, the MACH register is set to 1. */
             env->mach = 1;
-            env->macl = 0x7fffffff;
         }
+        env->macl = res;
+    } else {
+        /* In non-saturation arithmetic mode, the accumulator is 64-bit */
+        env->mac += mul;
     }
 }
 
diff --git a/target/sh4/translate.c b/target/sh4/translate.c
index a9b1bc7524..ebb6c901bf 100644
--- a/target/sh4/translate.c
+++ b/target/sh4/translate.c
@@ -523,6 +523,7 @@ static void _decode_opc(DisasContext * ctx)
         tcg_gen_movi_i32(REG(B11_8), B7_0s);
         return;
     case 0x9000: /* mov.w @(disp,PC),Rn */
+        CHECK_NOT_DELAY_SLOT
         {
             TCGv addr = tcg_constant_i32(ctx->base.pc_next + 4 + B7_0 * 2);
             tcg_gen_qemu_ld_i32(REG(B11_8), addr, ctx->memidx,
@@ -530,6 +531,7 @@ static void _decode_opc(DisasContext * ctx)
         }
         return;
     case 0xd000: /* mov.l @(disp,PC),Rn */
+        CHECK_NOT_DELAY_SLOT
         {
             TCGv addr = tcg_constant_i32((ctx->base.pc_next + 4 + B7_0 * 4) & ~3);
             tcg_gen_qemu_ld_i32(REG(B11_8), addr, ctx->memidx,
@@ -816,10 +818,10 @@ static void _decode_opc(DisasContext * ctx)
             TCGv arg0, arg1;
             arg0 = tcg_temp_new();
             tcg_gen_qemu_ld_i32(arg0, REG(B7_4), ctx->memidx,
-                                MO_TESL | MO_ALIGN);
+                                MO_TESW | MO_ALIGN);
             arg1 = tcg_temp_new();
             tcg_gen_qemu_ld_i32(arg1, REG(B11_8), ctx->memidx,
-                                MO_TESL | MO_ALIGN);
+                                MO_TESW | MO_ALIGN);
             gen_helper_macw(tcg_env, arg0, arg1);
             tcg_gen_addi_i32(REG(B11_8), REG(B11_8), 2);
             tcg_gen_addi_i32(REG(B7_4), REG(B7_4), 2);
@@ -1236,6 +1238,7 @@ static void _decode_opc(DisasContext * ctx)
         }
         return;
     case 0xc700: /* mova @(disp,PC),R0 */
+        CHECK_NOT_DELAY_SLOT
         tcg_gen_movi_i32(REG(0), ((ctx->base.pc_next & 0xfffffffc) +
                                   4 + B7_0 * 4) & ~3);
         return;