Merge remote-tracking branch 'remotes/rth/tags/pull-axp-201508018' into staging

Alpha shadow register optimization

# gpg: Signature made Tue 18 Aug 2015 19:09:41 BST using RSA key ID 4DD0279B
# gpg: Good signature from "Richard Henderson <rth7680@gmail.com>"
# gpg:                 aka "Richard Henderson <rth@redhat.com>"
# gpg:                 aka "Richard Henderson <rth@twiddle.net>"

* remotes/rth/tags/pull-axp-201508018:
  target-alpha: Inline hw_ret
  target-alpha: Inline call_pal
  target-alpha: Use separate TCGv temporaries for the shadow registers

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

7 files changed, 166 insertions, 134 deletions

diff --git a/target-alpha/cpu.h b/target-alpha/cpu.h
index 91c56d6bcf..3f1ece30ee 100644
--- a/target-alpha/cpu.h
+++ b/target-alpha/cpu.h
@@ -445,8 +445,9 @@ void QEMU_NORETURN arith_excp(CPUAlphaState *, uintptr_t, int, uint64_t);
 
 uint64_t cpu_alpha_load_fpcr (CPUAlphaState *env);
 void cpu_alpha_store_fpcr (CPUAlphaState *env, uint64_t val);
+uint64_t cpu_alpha_load_gr(CPUAlphaState *env, unsigned reg);
+void cpu_alpha_store_gr(CPUAlphaState *env, unsigned reg, uint64_t val);
 #ifndef CONFIG_USER_ONLY
-void swap_shadow_regs(CPUAlphaState *env);
 QEMU_NORETURN void alpha_cpu_unassigned_access(CPUState *cpu, hwaddr addr,
                                                bool is_write, bool is_exec,
                                                int unused, unsigned size);
diff --git a/target-alpha/gdbstub.c b/target-alpha/gdbstub.c
index 980f140e72..99a4051b35 100644
--- a/target-alpha/gdbstub.c
+++ b/target-alpha/gdbstub.c
@@ -30,7 +30,7 @@ int alpha_cpu_gdb_read_register(CPUState *cs, uint8_t *mem_buf, int n)
 
     switch (n) {
     case 0 ... 30:
-        val = env->ir[n];
+        val = cpu_alpha_load_gr(env, n);
         break;
     case 32 ... 62:
         d.d = env->fir[n - 32];
@@ -66,7 +66,7 @@ int alpha_cpu_gdb_write_register(CPUState *cs, uint8_t *mem_buf, int n)
 
     switch (n) {
     case 0 ... 30:
-        env->ir[n] = tmp;
+        cpu_alpha_store_gr(env, n, tmp);
         break;
     case 32 ... 62:
         d.ll = tmp;
diff --git a/target-alpha/helper.c b/target-alpha/helper.c
index 46b8ef9141..5a85335838 100644
--- a/target-alpha/helper.c
+++ b/target-alpha/helper.c
@@ -79,6 +79,30 @@ void helper_store_fpcr(CPUAlphaState *env, uint64_t val)
     cpu_alpha_store_fpcr(env, val);
 }
 
+static uint64_t *cpu_alpha_addr_gr(CPUAlphaState *env, unsigned reg)
+{
+#ifndef CONFIG_USER_ONLY
+    if (env->pal_mode) {
+        if (reg >= 8 && reg <= 14) {
+            return &env->shadow[reg - 8];
+        } else if (reg == 25) {
+            return &env->shadow[7];
+        }
+    }
+#endif
+    return &env->ir[reg];
+}
+
+uint64_t cpu_alpha_load_gr(CPUAlphaState *env, unsigned reg)
+{
+    return *cpu_alpha_addr_gr(env, reg);
+}
+
+void cpu_alpha_store_gr(CPUAlphaState *env, unsigned reg, uint64_t val)
+{
+    *cpu_alpha_addr_gr(env, reg) = val;
+}
+
 #if defined(CONFIG_USER_ONLY)
 int alpha_cpu_handle_mmu_fault(CPUState *cs, vaddr address,
                                int rw, int mmu_idx)
@@ -90,38 +114,6 @@ int alpha_cpu_handle_mmu_fault(CPUState *cs, vaddr address,
     return 1;
 }
 #else
-void swap_shadow_regs(CPUAlphaState *env)
-{
-    uint64_t i0, i1, i2, i3, i4, i5, i6, i7;
-
-    i0 = env->ir[8];
-    i1 = env->ir[9];
-    i2 = env->ir[10];
-    i3 = env->ir[11];
-    i4 = env->ir[12];
-    i5 = env->ir[13];
-    i6 = env->ir[14];
-    i7 = env->ir[25];
-
-    env->ir[8]  = env->shadow[0];
-    env->ir[9]  = env->shadow[1];
-    env->ir[10] = env->shadow[2];
-    env->ir[11] = env->shadow[3];
-    env->ir[12] = env->shadow[4];
-    env->ir[13] = env->shadow[5];
-    env->ir[14] = env->shadow[6];
-    env->ir[25] = env->shadow[7];
-
-    env->shadow[0] = i0;
-    env->shadow[1] = i1;
-    env->shadow[2] = i2;
-    env->shadow[3] = i3;
-    env->shadow[4] = i4;
-    env->shadow[5] = i5;
-    env->shadow[6] = i6;
-    env->shadow[7] = i7;
-}
-
 /* Returns the OSF/1 entMM failure indication, or -1 on success.  */
 static int get_physical_address(CPUAlphaState *env, target_ulong addr,
                                 int prot_need, int mmu_idx,
@@ -375,10 +367,7 @@ void alpha_cpu_do_interrupt(CPUState *cs)
     env->pc = env->palbr + i;
 
     /* Switch to PALmode.  */
-    if (!env->pal_mode) {
-        env->pal_mode = 1;
-        swap_shadow_regs(env);
-    }
+    env->pal_mode = 1;
 #endif /* !USER_ONLY */
 }
 
@@ -443,7 +432,7 @@ void alpha_cpu_dump_state(CPUState *cs, FILE *f, fprintf_function cpu_fprintf,
                 env->pc, env->ps);
     for (i = 0; i < 31; i++) {
         cpu_fprintf(f, "IR%02d %s " TARGET_FMT_lx " ", i,
-                    linux_reg_names[i], env->ir[i]);
+                    linux_reg_names[i], cpu_alpha_load_gr(env, i));
         if ((i % 3) == 2)
             cpu_fprintf(f, "\n");
     }
diff --git a/target-alpha/helper.h b/target-alpha/helper.h
index d221f0d7d6..42bb247e32 100644
--- a/target-alpha/helper.h
+++ b/target-alpha/helper.h
@@ -91,9 +91,6 @@ DEF_HELPER_FLAGS_2(ieee_input_cmp, TCG_CALL_NO_WG, void, env, i64)
 DEF_HELPER_FLAGS_2(ieee_input_s, TCG_CALL_NO_WG, void, env, i64)
 
 #if !defined (CONFIG_USER_ONLY)
-DEF_HELPER_2(hw_ret, void, env, i64)
-DEF_HELPER_3(call_pal, void, env, i64, i64)
-
 DEF_HELPER_2(ldl_phys, i64, env, i64)
 DEF_HELPER_2(ldq_phys, i64, env, i64)
 DEF_HELPER_2(ldl_l_phys, i64, env, i64)
diff --git a/target-alpha/machine.c b/target-alpha/machine.c
index e796bbe27d..d9bf977fc6 100644
--- a/target-alpha/machine.c
+++ b/target-alpha/machine.c
@@ -70,8 +70,8 @@ static VMStateField vmstate_env_fields[] = {
 
 static const VMStateDescription vmstate_env = {
     .name = "env",
-    .version_id = 1,
-    .minimum_version_id = 1,
+    .version_id = 2,
+    .minimum_version_id = 2,
     .fields = vmstate_env_fields,
 };
 
diff --git a/target-alpha/sys_helper.c b/target-alpha/sys_helper.c
index 1c59e108b9..1f0e1a9671 100644
--- a/target-alpha/sys_helper.c
+++ b/target-alpha/sys_helper.c
@@ -40,28 +40,6 @@ uint64_t helper_load_pcc(CPUAlphaState *env)
 
 /* PALcode support special instructions */
 #ifndef CONFIG_USER_ONLY
-void helper_hw_ret(CPUAlphaState *env, uint64_t a)
-{
-    env->pc = a & ~3;
-    env->intr_flag = 0;
-    env->lock_addr = -1;
-    if ((a & 1) == 0) {
-        env->pal_mode = 0;
-        swap_shadow_regs(env);
-    }
-}
-
-void helper_call_pal(CPUAlphaState *env, uint64_t pc, uint64_t entry_ofs)
-{
-    int pal_mode = env->pal_mode;
-    env->exc_addr = pc | pal_mode;
-    env->pc = env->palbr + entry_ofs;
-    if (!pal_mode) {
-        env->pal_mode = 1;
-        swap_shadow_regs(env);
-    }
-}
-
 void helper_tbia(CPUAlphaState *env)
 {
     tlb_flush(CPU(alpha_env_get_cpu(env)), 1);
diff --git a/target-alpha/translate.c b/target-alpha/translate.c
index 81d4ff827c..2849ede85c 100644
--- a/target-alpha/translate.c
+++ b/target-alpha/translate.c
@@ -42,6 +42,9 @@ typedef struct DisasContext DisasContext;
 struct DisasContext {
     struct TranslationBlock *tb;
     uint64_t pc;
+#ifndef CONFIG_USER_ONLY
+    uint64_t palbr;
+#endif
     int mem_idx;
 
     /* Current rounding mode for this TB.  */
@@ -52,6 +55,9 @@ struct DisasContext {
     /* implver value for this CPU.  */
     int implver;
 
+    /* The set of registers active in the current context.  */
+    TCGv *ir;
+
     /* Temporaries for $31 and $f31 as source and destination.  */
     TCGv zero;
     TCGv sink;
@@ -86,13 +92,17 @@ typedef enum {
 
 /* global register indexes */
 static TCGv_ptr cpu_env;
-static TCGv cpu_ir[31];
+static TCGv cpu_std_ir[31];
 static TCGv cpu_fir[31];
 static TCGv cpu_pc;
 static TCGv cpu_lock_addr;
 static TCGv cpu_lock_st_addr;
 static TCGv cpu_lock_value;
 
+#ifndef CONFIG_USER_ONLY
+static TCGv cpu_pal_ir[31];
+#endif
+
 #include "exec/gen-icount.h"
 
 void alpha_translate_init(void)
@@ -122,6 +132,12 @@ void alpha_translate_init(void)
         "f16", "f17", "f18", "f19", "f20", "f21", "f22", "f23",
         "f24", "f25", "f26", "f27", "f28", "f29", "f30"
     };
+#ifndef CONFIG_USER_ONLY
+    static const char shadow_names[8][8] = {
+        "pal_t7", "pal_s0", "pal_s1", "pal_s2",
+        "pal_s3", "pal_s4", "pal_s5", "pal_t11"
+    };
+#endif
 
     static bool done_init = 0;
     int i;
@@ -134,9 +150,9 @@ void alpha_translate_init(void)
     cpu_env = tcg_global_reg_new_ptr(TCG_AREG0, "env");
 
     for (i = 0; i < 31; i++) {
-        cpu_ir[i] = tcg_global_mem_new_i64(TCG_AREG0,
-                                           offsetof(CPUAlphaState, ir[i]),
-                                           greg_names[i]);
+        cpu_std_ir[i] = tcg_global_mem_new_i64(TCG_AREG0,
+                                               offsetof(CPUAlphaState, ir[i]),
+                                               greg_names[i]);
     }
 
     for (i = 0; i < 31; i++) {
@@ -145,6 +161,17 @@ void alpha_translate_init(void)
                                             freg_names[i]);
     }
 
+#ifndef CONFIG_USER_ONLY
+    memcpy(cpu_pal_ir, cpu_std_ir, sizeof(cpu_pal_ir));
+    for (i = 0; i < 8; i++) {
+        int r = (i == 7 ? 25 : i + 8);
+        cpu_pal_ir[r] = tcg_global_mem_new_i64(TCG_AREG0,
+                                               offsetof(CPUAlphaState,
+                                                        shadow[i]),
+                                               shadow_names[i]);
+    }
+#endif
+
     for (i = 0; i < ARRAY_SIZE(vars); ++i) {
         const GlobalVar *v = &vars[i];
         *v->var = tcg_global_mem_new_i64(TCG_AREG0, v->ofs, v->name);
@@ -170,7 +197,7 @@ static TCGv dest_sink(DisasContext *ctx)
 static TCGv load_gpr(DisasContext *ctx, unsigned reg)
 {
     if (likely(reg < 31)) {
-        return cpu_ir[reg];
+        return ctx->ir[reg];
     } else {
         return load_zero(ctx);
     }
@@ -183,7 +210,7 @@ static TCGv load_gpr_lit(DisasContext *ctx, unsigned reg,
         ctx->lit = tcg_const_i64(lit);
         return ctx->lit;
     } else if (likely(reg < 31)) {
-        return cpu_ir[reg];
+        return ctx->ir[reg];
     } else {
         return load_zero(ctx);
     }
@@ -192,7 +219,7 @@ static TCGv load_gpr_lit(DisasContext *ctx, unsigned reg,
 static TCGv dest_gpr(DisasContext *ctx, unsigned reg)
 {
     if (likely(reg < 31)) {
-        return cpu_ir[reg];
+        return ctx->ir[reg];
     } else {
         return dest_sink(ctx);
     }
@@ -304,7 +331,7 @@ static inline void gen_load_mem(DisasContext *ctx,
         addr = tmp;
     }
 
-    va = (fp ? cpu_fir[ra] : cpu_ir[ra]);
+    va = (fp ? cpu_fir[ra] : ctx->ir[ra]);
     tcg_gen_qemu_load(va, addr, ctx->mem_idx);
 
     tcg_temp_free(tmp);
@@ -399,13 +426,13 @@ static ExitStatus gen_store_conditional(DisasContext *ctx, int ra, int rb,
         tcg_gen_qemu_ld_i64(val, addr, ctx->mem_idx, quad ? MO_LEQ : MO_LESL);
         tcg_gen_brcond_i64(TCG_COND_NE, val, cpu_lock_value, lab_fail);
 
-        tcg_gen_qemu_st_i64(cpu_ir[ra], addr, ctx->mem_idx,
+        tcg_gen_qemu_st_i64(ctx->ir[ra], addr, ctx->mem_idx,
                             quad ? MO_LEQ : MO_LEUL);
-        tcg_gen_movi_i64(cpu_ir[ra], 1);
+        tcg_gen_movi_i64(ctx->ir[ra], 1);
         tcg_gen_br(lab_done);
 
         gen_set_label(lab_fail);
-        tcg_gen_movi_i64(cpu_ir[ra], 0);
+        tcg_gen_movi_i64(ctx->ir[ra], 0);
 
         gen_set_label(lab_done);
         tcg_gen_movi_i64(cpu_lock_addr, -1);
@@ -444,7 +471,7 @@ static ExitStatus gen_bdirect(DisasContext *ctx, int ra, int32_t disp)
     uint64_t dest = ctx->pc + (disp << 2);
 
     if (ra != 31) {
-        tcg_gen_movi_i64(cpu_ir[ra], ctx->pc);
+        tcg_gen_movi_i64(ctx->ir[ra], ctx->pc);
     }
 
     /* Notice branch-to-next; used to initialize RA with the PC.  */
@@ -1059,12 +1086,13 @@ static void gen_msk_l(DisasContext *ctx, TCGv vc, TCGv va, int rb, bool islit,
     }
 }
 
-static void gen_rx(int ra, int set)
+static void gen_rx(DisasContext *ctx, int ra, int set)
 {
     TCGv_i32 tmp;
 
     if (ra != 31) {
-        tcg_gen_ld8u_i64(cpu_ir[ra], cpu_env, offsetof(CPUAlphaState, intr_flag));
+        tcg_gen_ld8u_i64(ctx->ir[ra], cpu_env,
+                         offsetof(CPUAlphaState, intr_flag));
     }
 
     tmp = tcg_const_i32(set);
@@ -1086,12 +1114,12 @@ static ExitStatus gen_call_pal(DisasContext *ctx, int palcode)
             break;
         case 0x9E:
             /* RDUNIQUE */
-            tcg_gen_ld_i64(cpu_ir[IR_V0], cpu_env,
+            tcg_gen_ld_i64(ctx->ir[IR_V0], cpu_env,
                            offsetof(CPUAlphaState, unique));
             break;
         case 0x9F:
             /* WRUNIQUE */
-            tcg_gen_st_i64(cpu_ir[IR_A0], cpu_env,
+            tcg_gen_st_i64(ctx->ir[IR_A0], cpu_env,
                            offsetof(CPUAlphaState, unique));
             break;
         default:
@@ -1115,17 +1143,17 @@ static ExitStatus gen_call_pal(DisasContext *ctx, int palcode)
             break;
         case 0x2D:
             /* WRVPTPTR */
-            tcg_gen_st_i64(cpu_ir[IR_A0], cpu_env,
+            tcg_gen_st_i64(ctx->ir[IR_A0], cpu_env,
                            offsetof(CPUAlphaState, vptptr));
             break;
         case 0x31:
             /* WRVAL */
-            tcg_gen_st_i64(cpu_ir[IR_A0], cpu_env,
+            tcg_gen_st_i64(ctx->ir[IR_A0], cpu_env,
                            offsetof(CPUAlphaState, sysval));
             break;
         case 0x32:
             /* RDVAL */
-            tcg_gen_ld_i64(cpu_ir[IR_V0], cpu_env,
+            tcg_gen_ld_i64(ctx->ir[IR_V0], cpu_env,
                            offsetof(CPUAlphaState, sysval));
             break;
 
@@ -1135,12 +1163,12 @@ static ExitStatus gen_call_pal(DisasContext *ctx, int palcode)
 
             /* Note that we already know we're in kernel mode, so we know
                that PS only contains the 3 IPL bits.  */
-            tcg_gen_ld8u_i64(cpu_ir[IR_V0], cpu_env,
+            tcg_gen_ld8u_i64(ctx->ir[IR_V0], cpu_env,
                              offsetof(CPUAlphaState, ps));
 
             /* But make sure and store only the 3 IPL bits from the user.  */
             tmp = tcg_temp_new();
-            tcg_gen_andi_i64(tmp, cpu_ir[IR_A0], PS_INT_MASK);
+            tcg_gen_andi_i64(tmp, ctx->ir[IR_A0], PS_INT_MASK);
             tcg_gen_st8_i64(tmp, cpu_env, offsetof(CPUAlphaState, ps));
             tcg_temp_free(tmp);
             break;
@@ -1148,22 +1176,22 @@ static ExitStatus gen_call_pal(DisasContext *ctx, int palcode)
 
         case 0x36:
             /* RDPS */
-            tcg_gen_ld8u_i64(cpu_ir[IR_V0], cpu_env,
+            tcg_gen_ld8u_i64(ctx->ir[IR_V0], cpu_env,
                              offsetof(CPUAlphaState, ps));
             break;
         case 0x38:
             /* WRUSP */
-            tcg_gen_st_i64(cpu_ir[IR_A0], cpu_env,
+            tcg_gen_st_i64(ctx->ir[IR_A0], cpu_env,
                            offsetof(CPUAlphaState, usp));
             break;
         case 0x3A:
             /* RDUSP */
-            tcg_gen_ld_i64(cpu_ir[IR_V0], cpu_env,
+            tcg_gen_ld_i64(ctx->ir[IR_V0], cpu_env,
                            offsetof(CPUAlphaState, usp));
             break;
         case 0x3C:
             /* WHAMI */
-            tcg_gen_ld32s_i64(cpu_ir[IR_V0], cpu_env,
+            tcg_gen_ld32s_i64(ctx->ir[IR_V0], cpu_env,
                 -offsetof(AlphaCPU, env) + offsetof(CPUState, cpu_index));
             break;
 
@@ -1181,15 +1209,24 @@ static ExitStatus gen_call_pal(DisasContext *ctx, int palcode)
     return gen_excp(ctx, EXCP_CALL_PAL, palcode);
 #else
     {
-        TCGv pc = tcg_const_i64(ctx->pc);
-        TCGv entry = tcg_const_i64(palcode & 0x80
-                                   ? 0x2000 + (palcode - 0x80) * 64
-                                   : 0x1000 + palcode * 64);
+        TCGv tmp = tcg_temp_new();
+        uint64_t exc_addr = ctx->pc;
+        uint64_t entry = ctx->palbr;
+
+        if (ctx->tb->flags & TB_FLAGS_PAL_MODE) {
+            exc_addr |= 1;
+        } else {
+            tcg_gen_movi_i64(tmp, 1);
+            tcg_gen_st8_i64(tmp, cpu_env, offsetof(CPUAlphaState, pal_mode));
+        }
 
-        gen_helper_call_pal(cpu_env, pc, entry);
+        tcg_gen_movi_i64(tmp, exc_addr);
+        tcg_gen_st_i64(tmp, cpu_env, offsetof(CPUAlphaState, exc_addr));
+        tcg_temp_free(tmp);
 
-        tcg_temp_free(entry);
-        tcg_temp_free(pc);
+        entry += (palcode & 0x80
+                  ? 0x2000 + (palcode - 0x80) * 64
+                  : 0x1000 + palcode * 64);
 
         /* Since the destination is running in PALmode, we don't really
            need the page permissions check.  We'll see the existence of
@@ -1197,11 +1234,13 @@ static ExitStatus gen_call_pal(DisasContext *ctx, int palcode)
            we change the PAL base register.  */
         if (!ctx->singlestep_enabled && !(ctx->tb->cflags & CF_LAST_IO)) {
             tcg_gen_goto_tb(0);
+            tcg_gen_movi_i64(cpu_pc, entry);
             tcg_gen_exit_tb((uintptr_t)ctx->tb);
             return EXIT_GOTO_TB;
+        } else {
+            tcg_gen_movi_i64(cpu_pc, entry);
+            return EXIT_PC_UPDATED;
         }
-
-        return EXIT_PC_UPDATED;
     }
 #endif
 }
@@ -1228,8 +1267,6 @@ static int cpu_pr_data(int pr)
     case 11: return offsetof(CPUAlphaState, sysval);
     case 12: return offsetof(CPUAlphaState, usp);
 
-    case 32 ... 39:
-        return offsetof(CPUAlphaState, shadow[pr - 32]);
     case 40 ... 63:
         return offsetof(CPUAlphaState, scratch[pr - 40]);
 
@@ -1241,36 +1278,48 @@ static int cpu_pr_data(int pr)
 
 static ExitStatus gen_mfpr(DisasContext *ctx, TCGv va, int regno)
 {
-    int data = cpu_pr_data(regno);
-
-    /* Special help for VMTIME and WALLTIME.  */
-    if (regno == 250 || regno == 249) {
-	void (*helper)(TCGv) = gen_helper_get_walltime;
-	if (regno == 249) {
-		helper = gen_helper_get_vmtime;
-	}
-        if (ctx->tb->cflags & CF_USE_ICOUNT) {
+    void (*helper)(TCGv);
+    int data;
+
+    switch (regno) {
+    case 32 ... 39:
+        /* Accessing the "non-shadow" general registers.  */
+        regno = regno == 39 ? 25 : regno - 32 + 8;
+        tcg_gen_mov_i64(va, cpu_std_ir[regno]);
+        break;
+
+    case 250: /* WALLTIME */
+        helper = gen_helper_get_walltime;
+        goto do_helper;
+    case 249: /* VMTIME */
+        helper = gen_helper_get_vmtime;
+    do_helper:
+        if (use_icount) {
             gen_io_start();
             helper(va);
             gen_io_end();
             return EXIT_PC_STALE;
         } else {
             helper(va);
-            return NO_EXIT;
         }
-    }
+        break;
 
-    /* The basic registers are data only, and unknown registers
-       are read-zero, write-ignore.  */
-    if (data == 0) {
-        tcg_gen_movi_i64(va, 0);
-    } else if (data & PR_BYTE) {
-        tcg_gen_ld8u_i64(va, cpu_env, data & ~PR_BYTE);
-    } else if (data & PR_LONG) {
-        tcg_gen_ld32s_i64(va, cpu_env, data & ~PR_LONG);
-    } else {
-        tcg_gen_ld_i64(va, cpu_env, data);
+    default:
+        /* The basic registers are data only, and unknown registers
+           are read-zero, write-ignore.  */
+        data = cpu_pr_data(regno);
+        if (data == 0) {
+            tcg_gen_movi_i64(va, 0);
+        } else if (data & PR_BYTE) {
+            tcg_gen_ld8u_i64(va, cpu_env, data & ~PR_BYTE);
+        } else if (data & PR_LONG) {
+            tcg_gen_ld32s_i64(va, cpu_env, data & ~PR_LONG);
+        } else {
+            tcg_gen_ld_i64(va, cpu_env, data);
+        }
+        break;
     }
+
     return NO_EXIT;
 }
 
@@ -1316,6 +1365,12 @@ static ExitStatus gen_mtpr(DisasContext *ctx, TCGv vb, int regno)
         gen_helper_tb_flush(cpu_env);
         return EXIT_PC_STALE;
 
+    case 32 ... 39:
+        /* Accessing the "non-shadow" general registers.  */
+        regno = regno == 39 ? 25 : regno - 32 + 8;
+        tcg_gen_mov_i64(cpu_std_ir[regno], vb);
+        break;
+
     default:
         /* The basic registers are data only, and unknown registers
            are read-zero, write-ignore.  */
@@ -2295,14 +2350,14 @@ static ExitStatus translate_one(DisasContext *ctx, uint32_t insn)
             break;
         case 0xE000:
             /* RC */
-            gen_rx(ra, 0);
+            gen_rx(ctx, ra, 0);
             break;
         case 0xE800:
             /* ECB */
             break;
         case 0xF000:
             /* RS */
-            gen_rx(ra, 1);
+            gen_rx(ctx, ra, 1);
             break;
         case 0xF800:
             /* WH64 */
@@ -2334,7 +2389,7 @@ static ExitStatus translate_one(DisasContext *ctx, uint32_t insn)
         vb = load_gpr(ctx, rb);
         tcg_gen_andi_i64(cpu_pc, vb, ~3);
         if (ra != 31) {
-            tcg_gen_movi_i64(cpu_ir[ra], ctx->pc);
+            tcg_gen_movi_i64(ctx->ir[ra], ctx->pc);
         }
         ret = EXIT_PC_UPDATED;
         break;
@@ -2374,10 +2429,10 @@ static ExitStatus translate_one(DisasContext *ctx, uint32_t insn)
                 goto invalid_opc;
                 break;
             case 0x6:
-                /* Incpu_ir[ra]id */
+                /* Invalid */
                 goto invalid_opc;
             case 0x7:
-                /* Incpu_ir[ra]id */
+                /* Invaliid */
                 goto invalid_opc;
             case 0x8:
                 /* Longword virtual access (hw_ldl) */
@@ -2580,13 +2635,18 @@ static ExitStatus translate_one(DisasContext *ctx, uint32_t insn)
             /* Pre-EV6 CPUs interpreted this as HW_REI, loading the return
                address from EXC_ADDR.  This turns out to be useful for our
                emulation PALcode, so continue to accept it.  */
-            tmp = tcg_temp_new();
-            tcg_gen_ld_i64(tmp, cpu_env, offsetof(CPUAlphaState, exc_addr));
-            gen_helper_hw_ret(cpu_env, tmp);
-            tcg_temp_free(tmp);
+            ctx->lit = vb = tcg_temp_new();
+            tcg_gen_ld_i64(vb, cpu_env, offsetof(CPUAlphaState, exc_addr));
         } else {
-            gen_helper_hw_ret(cpu_env, load_gpr(ctx, rb));
+            vb = load_gpr(ctx, rb);
         }
+        tmp = tcg_temp_new();
+        tcg_gen_movi_i64(tmp, 0);
+        tcg_gen_st8_i64(tmp, cpu_env, offsetof(CPUAlphaState, intr_flag));
+        tcg_gen_movi_i64(cpu_lock_addr, -1);
+        tcg_gen_andi_i64(tmp, vb, 1);
+        tcg_gen_st8_i64(tmp, cpu_env, offsetof(CPUAlphaState, pal_mode));
+        tcg_gen_andi_i64(cpu_pc, vb, ~3);
         ret = EXIT_PC_UPDATED;
         break;
 #else
@@ -2817,6 +2877,13 @@ static inline void gen_intermediate_code_internal(AlphaCPU *cpu,
     ctx.implver = env->implver;
     ctx.singlestep_enabled = cs->singlestep_enabled;
 
+#ifdef CONFIG_USER_ONLY
+    ctx.ir = cpu_std_ir;
+#else
+    ctx.palbr = env->palbr;
+    ctx.ir = (tb->flags & TB_FLAGS_PAL_MODE ? cpu_pal_ir : cpu_std_ir);
+#endif
+
     /* ??? Every TB begins with unset rounding mode, to be initialized on
        the first fp insn of the TB.  Alternately we could define a proper
        default for every TB (e.g. QUAL_RM_N or QUAL_RM_D) and make sure