target-alpha improvements, version 4

index a508077..8e11304 100644
@@ -77,10 +77,6 @@ DEF_HELPER_FLAGS_2(cmpgeq, TCG_CALL_CONST | TCG_CALL_PURE, i64, i64, i64)
 DEF_HELPER_FLAGS_2(cmpgle, TCG_CALL_CONST | TCG_CALL_PURE, i64, i64, i64)
 DEF_HELPER_FLAGS_2(cmpglt, TCG_CALL_CONST | TCG_CALL_PURE, i64, i64, i64)
 
-DEF_HELPER_FLAGS_2(cpys, TCG_CALL_CONST | TCG_CALL_PURE, i64, i64, i64)
-DEF_HELPER_FLAGS_2(cpysn, TCG_CALL_CONST | TCG_CALL_PURE, i64, i64, i64)
-DEF_HELPER_FLAGS_2(cpyse, TCG_CALL_CONST | TCG_CALL_PURE, i64, i64, i64)
-
 DEF_HELPER_FLAGS_1(cvtts, TCG_CALL_CONST, i64, i64)
 DEF_HELPER_FLAGS_1(cvtst, TCG_CALL_CONST, i64, i64)
 DEF_HELPER_FLAGS_1(cvtqs, TCG_CALL_CONST, i64, i64)

index 4d2c2ee..2419dc4 100644
@@ -921,24 +921,6 @@ uint64_t helper_sqrtt (uint64_t a)
     return float64_to_t(fr);
 }
 
-
-/* Sign copy */
-uint64_t helper_cpys(uint64_t a, uint64_t b)
-{
-    return (a & 0x8000000000000000ULL) | (b & ~0x8000000000000000ULL);
-}
-
-uint64_t helper_cpysn(uint64_t a, uint64_t b)
-{
-    return ((~a) & 0x8000000000000000ULL) | (b & ~0x8000000000000000ULL);
-}
-
-uint64_t helper_cpyse(uint64_t a, uint64_t b)
-{
-    return (a & 0xFFF0000000000000ULL) | (b & ~0xFFF0000000000000ULL);
-}
-
-
 /* Comparisons */
 uint64_t helper_cmptun (uint64_t a, uint64_t b)
 {

90 lines not on this page · raw message

index c378195..10c78d0 100644
@@ -89,10 +89,6 @@ DEF_HELPER_FLAGS_1(cvttq, TCG_CALL_CONST, i64, i64)
 DEF_HELPER_FLAGS_1(cvttq_c, TCG_CALL_CONST, i64, i64)
 DEF_HELPER_FLAGS_1(cvttq_svic, TCG_CALL_CONST, i64, i64)
 
-DEF_HELPER_FLAGS_1(cvtql, TCG_CALL_CONST | TCG_CALL_PURE, i64, i64)
-DEF_HELPER_1(cvtql_v, i64, i64)
-DEF_HELPER_1(cvtql_sv, i64, i64)
-
 DEF_HELPER_FLAGS_1(setroundmode, TCG_CALL_CONST, void, i32)
 DEF_HELPER_FLAGS_1(setflushzero, TCG_CALL_CONST, void, i32)
 DEF_HELPER_FLAGS_0(fp_exc_clear, TCG_CALL_CONST, void)

index 84867b8..f9cd07a 100644
@@ -1159,26 +1159,6 @@ uint64_t helper_cvtlq (uint64_t a)
     return (lo & 0x3FFFFFFF) | (hi & 0xc0000000);
 }
 
-uint64_t helper_cvtql (uint64_t a)
-{
-    return ((a & 0xC0000000) << 32) | ((a & 0x7FFFFFFF) << 29);
-}
-
-uint64_t helper_cvtql_v (uint64_t a)
-{
-    if ((int32_t)a != (int64_t)a)
-        helper_excp(EXCP_ARITH, EXC_M_IOV);
-    return helper_cvtql(a);
-}
-
-uint64_t helper_cvtql_sv (uint64_t a)
-{
-    /* ??? I'm pretty sure there's nothing that /sv needs to do that /v
-       doesn't do.  The only thing I can think is that /sv is a valid
-       instruction merely for completeness in the ISA.  */
-    return helper_cvtql_v(a);
-}
-
 /* PALcode support special instructions */
 #if !defined (CONFIG_USER_ONLY)
 void helper_hw_rei (void)

65 lines not on this page · raw message

index 10c78d0..ccf6a2a 100644
@@ -83,7 +83,6 @@ DEF_HELPER_FLAGS_1(cvtqf, TCG_CALL_CONST, i64, i64)
 DEF_HELPER_FLAGS_1(cvtgf, TCG_CALL_CONST, i64, i64)
 DEF_HELPER_FLAGS_1(cvtgq, TCG_CALL_CONST, i64, i64)
 DEF_HELPER_FLAGS_1(cvtqg, TCG_CALL_CONST, i64, i64)
-DEF_HELPER_FLAGS_1(cvtlq, TCG_CALL_CONST | TCG_CALL_PURE, i64, i64)
 
 DEF_HELPER_FLAGS_1(cvttq, TCG_CALL_CONST, i64, i64)
 DEF_HELPER_FLAGS_1(cvttq_c, TCG_CALL_CONST, i64, i64)

index f9cd07a..a209130 100644
@@ -1152,13 +1152,6 @@ uint64_t helper_cvtqg (uint64_t a)
     return float64_to_g(fr);
 }
 
-uint64_t helper_cvtlq (uint64_t a)
-{
-    int32_t lo = a >> 29;
-    int32_t hi = a >> 32;
-    return (lo & 0x3FFFFFFF) | (hi & 0xc0000000);
-}
-
 /* PALcode support special instructions */
 #if !defined (CONFIG_USER_ONLY)
 void helper_hw_rei (void)

index 44ce830..dff03ef 100644
@@ -597,6 +597,28 @@ static inline void gen_fp_exc_raise(int rc, int fn11)
     gen_fp_exc_raise_ignore(rc, fn11, fn11 & QUAL_I ? 0 : float_flag_inexact);
 }
 
+static void gen_fcvtlq(int rb, int rc)
+{
+    if (unlikely(rc == 31)) {
+        return;
+    }
+    if (unlikely(rb == 31)) {
+        tcg_gen_movi_i64(cpu_fir[rc], 0);
+    } else {
+        TCGv tmp = tcg_temp_new();
+
+        /* The arithmetic right shift here, plus the sign-extended mask below
+           yields a sign-extended result without an explicit ext32s_i64.  */
+        tcg_gen_sari_i64(tmp, cpu_fir[rb], 32);
+        tcg_gen_shri_i64(cpu_fir[rc], cpu_fir[rb], 29);
+        tcg_gen_andi_i64(tmp, tmp, (int32_t)0xc0000000);
+        tcg_gen_andi_i64(cpu_fir[rc], cpu_fir[rc], 0x3fffffff);
+        tcg_gen_or_i64(cpu_fir[rc], cpu_fir[rc], tmp);
+
+        tcg_temp_free(tmp);
+    }
+}
+
 static void gen_fcvtql(int rb, int rc)
 {
     if (unlikely(rc == 31)) {

@@ -646,7 +668,6 @@ static inline void glue(gen_f, name)(int rb, int rc)    \
         tcg_temp_free(tmp);                             \
     }                                                   \
 }
-FARITH2(cvtlq)
 
 /* ??? VAX instruction qualifiers ignored.  */
 FARITH2(sqrtf)

index dff03ef..adeff0a 100644
@@ -1290,33 +1290,34 @@ MVIOP2(pkwb)
 MVIOP2(unpkbl)
 MVIOP2(unpkbw)
 
-static inline void gen_cmp(TCGCond cond, int ra, int rb, int rc, int islit,
-                           uint8_t lit)
+static void gen_cmp(TCGCond cond, int ra, int rb, int rc,
+                    int islit, uint8_t lit)
 {
-    int l1, l2;
-    TCGv tmp;
+    TCGv va, vb;
 
-    if (unlikely(rc == 31))
+    if (unlikely(rc == 31)) {
         return;
+    }
 
-    l1 = gen_new_label();
-    l2 = gen_new_label();
+    if (ra == 31) {
+        va = tcg_const_i64(0);
+    } else {
+        va = cpu_ir[ra];
+    }
+    if (islit) {
+        vb = tcg_const_i64(lit);
+    } else {
+        vb = cpu_ir[rb];
+    }
 
-    if (ra != 31) {
-        tmp = tcg_temp_new();
-        tcg_gen_mov_i64(tmp, cpu_ir[ra]);
-    } else
-        tmp = tcg_const_i64(0);
-    if (islit)
-        tcg_gen_brcondi_i64(cond, tmp, lit, l1);
-    else
-        tcg_gen_brcond_i64(cond, tmp, cpu_ir[rb], l1);
+    tcg_gen_setcond_i64(cond, cpu_ir[rc], va, vb);
 
-    tcg_gen_movi_i64(cpu_ir[rc], 0);
-    tcg_gen_br(l2);
-    gen_set_label(l1);
-    tcg_gen_movi_i64(cpu_ir[rc], 1);
-    gen_set_label(l2);
+    if (ra == 31) {
+        tcg_temp_free(va);
+    }
+    if (islit) {
+        tcg_temp_free(vb);
+    }
 }
 
 static void gen_rx(int ra, int set)

index dfe55c3..2360a0e 100644
@@ -2534,13 +2534,16 @@ static ExitStatus translate_one(DisasContext *ctx, uint32_t insn)
         break;
 #endif
     case 0x1A:
-        if (rb != 31)
+        /* JMP, JSR, RET, JSR_COROUTINE.  These only differ by the branch
+           prediction stack action, which of course we don't implement.  */
+        if (rb != 31) {
             tcg_gen_andi_i64(cpu_pc, cpu_ir[rb], ~3);
-        else
+        } else {
             tcg_gen_movi_i64(cpu_pc, 0);
-        if (ra != 31)
+        }
+        if (ra != 31) {
             tcg_gen_movi_i64(cpu_ir[ra], ctx->pc);
-        /* Those four jumps only differ by the branch prediction hint */
+        }
         ret = EXIT_PC_UPDATED;
         break;
     case 0x1B:

index 79cf375..a508077 100644
@@ -1,9 +1,9 @@
 #include "def-helper.h"
 
 DEF_HELPER_2(excp, void, int, int)
-DEF_HELPER_0(load_pcc, i64)
-DEF_HELPER_0(rc, i64)
-DEF_HELPER_0(rs, i64)
+DEF_HELPER_FLAGS_0(load_pcc, TCG_CALL_CONST | TCG_CALL_PURE, i64)
+DEF_HELPER_FLAGS_0(rc, TCG_CALL_CONST, i64)
+DEF_HELPER_FLAGS_0(rs, TCG_CALL_CONST, i64)
 
 DEF_HELPER_2(addqv, i64, i64, i64)
 DEF_HELPER_2(addlv, i64, i64, i64)

@@ -11,98 +11,98 @@ DEF_HELPER_2(subqv, i64, i64, i64)
 DEF_HELPER_2(sublv, i64, i64, i64)
 DEF_HELPER_2(mullv, i64, i64, i64)
 DEF_HELPER_2(mulqv, i64, i64, i64)
-DEF_HELPER_2(umulh, i64, i64, i64)
-
-DEF_HELPER_1(ctpop, i64, i64)
-DEF_HELPER_1(ctlz, i64, i64)
-DEF_HELPER_1(cttz, i64, i64)
-
-DEF_HELPER_2(zap, i64, i64, i64)
-DEF_HELPER_2(zapnot, i64, i64, i64)
-
-DEF_HELPER_2(cmpbge, i64, i64, i64)
-
-DEF_HELPER_2(minub8, i64, i64, i64)
-DEF_HELPER_2(minsb8, i64, i64, i64)
-DEF_HELPER_2(minuw4, i64, i64, i64)
-DEF_HELPER_2(minsw4, i64, i64, i64)
-DEF_HELPER_2(maxub8, i64, i64, i64)
-DEF_HELPER_2(maxsb8, i64, i64, i64)
-DEF_HELPER_2(maxuw4, i64, i64, i64)
-DEF_HELPER_2(maxsw4, i64, i64, i64)
-DEF_HELPER_2(perr, i64, i64, i64)
-DEF_HELPER_1(pklb, i64, i64)
-DEF_HELPER_1(pkwb, i64, i64)
-DEF_HELPER_1(unpkbl, i64, i64)
-DEF_HELPER_1(unpkbw, i64, i64)
-
-DEF_HELPER_0(load_fpcr, i64)
-DEF_HELPER_1(store_fpcr, void, i64)
-
-DEF_HELPER_1(f_to_memory, i32, i64)
-DEF_HELPER_1(memory_to_f, i64, i32)
-DEF_HELPER_2(addf, i64, i64, i64)
-DEF_HELPER_2(subf, i64, i64, i64)
-DEF_HELPER_2(mulf, i64, i64, i64)
-DEF_HELPER_2(divf, i64, i64, i64)
-DEF_HELPER_1(sqrtf, i64, i64)
-
-DEF_HELPER_1(g_to_memory, i64, i64)
-DEF_HELPER_1(memory_to_g, i64, i64)
-DEF_HELPER_2(addg, i64, i64, i64)
-DEF_HELPER_2(subg, i64, i64, i64)
-DEF_HELPER_2(mulg, i64, i64, i64)
-DEF_HELPER_2(divg, i64, i64, i64)
-DEF_HELPER_1(sqrtg, i64, i64)
-
-DEF_HELPER_1(s_to_memory, i32, i64)
-DEF_HELPER_1(memory_to_s, i64, i32)
-DEF_HELPER_2(adds, i64, i64, i64)
-DEF_HELPER_2(subs, i64, i64, i64)
-DEF_HELPER_2(muls, i64, i64, i64)
-DEF_HELPER_2(divs, i64, i64, i64)
-DEF_HELPER_1(sqrts, i64, i64)
-
-DEF_HELPER_2(addt, i64, i64, i64)
-DEF_HELPER_2(subt, i64, i64, i64)
-DEF_HELPER_2(mult, i64, i64, i64)
-DEF_HELPER_2(divt, i64, i64, i64)
-DEF_HELPER_1(sqrtt, i64, i64)
-
-DEF_HELPER_2(cmptun, i64, i64, i64)
-DEF_HELPER_2(cmpteq, i64, i64, i64)
-DEF_HELPER_2(cmptle, i64, i64, i64)
-DEF_HELPER_2(cmptlt, i64, i64, i64)
-DEF_HELPER_2(cmpgeq, i64, i64, i64)
-DEF_HELPER_2(cmpgle, i64, i64, i64)
-DEF_HELPER_2(cmpglt, i64, i64, i64)
-
-DEF_HELPER_2(cpys, i64, i64, i64)
-DEF_HELPER_2(cpysn, i64, i64, i64)
-DEF_HELPER_2(cpyse, i64, i64, i64)
-
-DEF_HELPER_1(cvtts, i64, i64)
-DEF_HELPER_1(cvtst, i64, i64)
-DEF_HELPER_1(cvtqs, i64, i64)
-DEF_HELPER_1(cvtqt, i64, i64)
-DEF_HELPER_1(cvtqf, i64, i64)
-DEF_HELPER_1(cvtgf, i64, i64)
-DEF_HELPER_1(cvtgq, i64, i64)
-DEF_HELPER_1(cvtqg, i64, i64)
-DEF_HELPER_1(cvtlq, i64, i64)
-
-DEF_HELPER_1(cvttq, i64, i64)
-DEF_HELPER_1(cvttq_c, i64, i64)
-DEF_HELPER_1(cvttq_svic, i64, i64)
-
-DEF_HELPER_1(cvtql, i64, i64)
+DEF_HELPER_FLAGS_2(umulh, TCG_CALL_CONST | TCG_CALL_PURE, i64, i64, i64)
+
+DEF_HELPER_FLAGS_1(ctpop, TCG_CALL_CONST | TCG_CALL_PURE, i64, i64)
+DEF_HELPER_FLAGS_1(ctlz, TCG_CALL_CONST | TCG_CALL_PURE, i64, i64)
+DEF_HELPER_FLAGS_1(cttz, TCG_CALL_CONST | TCG_CALL_PURE, i64, i64)
+
+DEF_HELPER_FLAGS_2(zap, TCG_CALL_CONST | TCG_CALL_PURE, i64, i64, i64)
+DEF_HELPER_FLAGS_2(zapnot, TCG_CALL_CONST | TCG_CALL_PURE, i64, i64, i64)
+
+DEF_HELPER_FLAGS_2(cmpbge, TCG_CALL_CONST | TCG_CALL_PURE, i64, i64, i64)
+
+DEF_HELPER_FLAGS_2(minub8, TCG_CALL_CONST | TCG_CALL_PURE, i64, i64, i64)
+DEF_HELPER_FLAGS_2(minsb8, TCG_CALL_CONST | TCG_CALL_PURE, i64, i64, i64)
+DEF_HELPER_FLAGS_2(minuw4, TCG_CALL_CONST | TCG_CALL_PURE, i64, i64, i64)
+DEF_HELPER_FLAGS_2(minsw4, TCG_CALL_CONST | TCG_CALL_PURE, i64, i64, i64)
+DEF_HELPER_FLAGS_2(maxub8, TCG_CALL_CONST | TCG_CALL_PURE, i64, i64, i64)
+DEF_HELPER_FLAGS_2(maxsb8, TCG_CALL_CONST | TCG_CALL_PURE, i64, i64, i64)
+DEF_HELPER_FLAGS_2(maxuw4, TCG_CALL_CONST | TCG_CALL_PURE, i64, i64, i64)
+DEF_HELPER_FLAGS_2(maxsw4, TCG_CALL_CONST | TCG_CALL_PURE, i64, i64, i64)
+DEF_HELPER_FLAGS_2(perr, TCG_CALL_CONST | TCG_CALL_PURE, i64, i64, i64)
+DEF_HELPER_FLAGS_1(pklb, TCG_CALL_CONST | TCG_CALL_PURE, i64, i64)
+DEF_HELPER_FLAGS_1(pkwb, TCG_CALL_CONST | TCG_CALL_PURE, i64, i64)
+DEF_HELPER_FLAGS_1(unpkbl, TCG_CALL_CONST | TCG_CALL_PURE, i64, i64)
+DEF_HELPER_FLAGS_1(unpkbw, TCG_CALL_CONST | TCG_CALL_PURE, i64, i64)
+
+DEF_HELPER_FLAGS_0(load_fpcr, TCG_CALL_CONST | TCG_CALL_PURE, i64)
+DEF_HELPER_FLAGS_1(store_fpcr, TCG_CALL_CONST, void, i64)
+
+DEF_HELPER_FLAGS_1(f_to_memory, TCG_CALL_CONST | TCG_CALL_PURE, i32, i64)
+DEF_HELPER_FLAGS_1(memory_to_f, TCG_CALL_CONST | TCG_CALL_PURE, i64, i32)
+DEF_HELPER_FLAGS_2(addf, TCG_CALL_CONST, i64, i64, i64)
+DEF_HELPER_FLAGS_2(subf, TCG_CALL_CONST, i64, i64, i64)
+DEF_HELPER_FLAGS_2(mulf, TCG_CALL_CONST, i64, i64, i64)
+DEF_HELPER_FLAGS_2(divf, TCG_CALL_CONST, i64, i64, i64)
+DEF_HELPER_FLAGS_1(sqrtf, TCG_CALL_CONST, i64, i64)
+
+DEF_HELPER_FLAGS_1(g_to_memory, TCG_CALL_CONST | TCG_CALL_PURE, i64, i64)
+DEF_HELPER_FLAGS_1(memory_to_g, TCG_CALL_CONST | TCG_CALL_PURE, i64, i64)
+DEF_HELPER_FLAGS_2(addg, TCG_CALL_CONST, i64, i64, i64)
+DEF_HELPER_FLAGS_2(subg, TCG_CALL_CONST, i64, i64, i64)
+DEF_HELPER_FLAGS_2(mulg, TCG_CALL_CONST, i64, i64, i64)
+DEF_HELPER_FLAGS_2(divg, TCG_CALL_CONST, i64, i64, i64)
+DEF_HELPER_FLAGS_1(sqrtg, TCG_CALL_CONST, i64, i64)
+
+DEF_HELPER_FLAGS_1(s_to_memory, TCG_CALL_CONST | TCG_CALL_PURE, i32, i64)
+DEF_HELPER_FLAGS_1(memory_to_s, TCG_CALL_CONST | TCG_CALL_PURE, i64, i32)
+DEF_HELPER_FLAGS_2(adds, TCG_CALL_CONST, i64, i64, i64)
+DEF_HELPER_FLAGS_2(subs, TCG_CALL_CONST, i64, i64, i64)
+DEF_HELPER_FLAGS_2(muls, TCG_CALL_CONST, i64, i64, i64)
+DEF_HELPER_FLAGS_2(divs, TCG_CALL_CONST, i64, i64, i64)
+DEF_HELPER_FLAGS_1(sqrts, TCG_CALL_CONST, i64, i64)
+
+DEF_HELPER_FLAGS_2(addt, TCG_CALL_CONST, i64, i64, i64)
+DEF_HELPER_FLAGS_2(subt, TCG_CALL_CONST, i64, i64, i64)
+DEF_HELPER_FLAGS_2(mult, TCG_CALL_CONST, i64, i64, i64)
+DEF_HELPER_FLAGS_2(divt, TCG_CALL_CONST, i64, i64, i64)
+DEF_HELPER_FLAGS_1(sqrtt, TCG_CALL_CONST, i64, i64)
+
+DEF_HELPER_FLAGS_2(cmptun, TCG_CALL_CONST | TCG_CALL_PURE, i64, i64, i64)
+DEF_HELPER_FLAGS_2(cmpteq, TCG_CALL_CONST | TCG_CALL_PURE, i64, i64, i64)
+DEF_HELPER_FLAGS_2(cmptle, TCG_CALL_CONST | TCG_CALL_PURE, i64, i64, i64)
+DEF_HELPER_FLAGS_2(cmptlt, TCG_CALL_CONST | TCG_CALL_PURE, i64, i64, i64)
+DEF_HELPER_FLAGS_2(cmpgeq, TCG_CALL_CONST | TCG_CALL_PURE, i64, i64, i64)
+DEF_HELPER_FLAGS_2(cmpgle, TCG_CALL_CONST | TCG_CALL_PURE, i64, i64, i64)
+DEF_HELPER_FLAGS_2(cmpglt, TCG_CALL_CONST | TCG_CALL_PURE, i64, i64, i64)
+
+DEF_HELPER_FLAGS_2(cpys, TCG_CALL_CONST | TCG_CALL_PURE, i64, i64, i64)
+DEF_HELPER_FLAGS_2(cpysn, TCG_CALL_CONST | TCG_CALL_PURE, i64, i64, i64)
+DEF_HELPER_FLAGS_2(cpyse, TCG_CALL_CONST | TCG_CALL_PURE, i64, i64, i64)
+
+DEF_HELPER_FLAGS_1(cvtts, TCG_CALL_CONST, i64, i64)
+DEF_HELPER_FLAGS_1(cvtst, TCG_CALL_CONST, i64, i64)
+DEF_HELPER_FLAGS_1(cvtqs, TCG_CALL_CONST, i64, i64)
+DEF_HELPER_FLAGS_1(cvtqt, TCG_CALL_CONST, i64, i64)
+DEF_HELPER_FLAGS_1(cvtqf, TCG_CALL_CONST, i64, i64)
+DEF_HELPER_FLAGS_1(cvtgf, TCG_CALL_CONST, i64, i64)
+DEF_HELPER_FLAGS_1(cvtgq, TCG_CALL_CONST, i64, i64)
+DEF_HELPER_FLAGS_1(cvtqg, TCG_CALL_CONST, i64, i64)
+DEF_HELPER_FLAGS_1(cvtlq, TCG_CALL_CONST | TCG_CALL_PURE, i64, i64)
+
+DEF_HELPER_FLAGS_1(cvttq, TCG_CALL_CONST, i64, i64)
+DEF_HELPER_FLAGS_1(cvttq_c, TCG_CALL_CONST, i64, i64)
+DEF_HELPER_FLAGS_1(cvttq_svic, TCG_CALL_CONST, i64, i64)
+
+DEF_HELPER_FLAGS_1(cvtql, TCG_CALL_CONST | TCG_CALL_PURE, i64, i64)
 DEF_HELPER_1(cvtql_v, i64, i64)
 DEF_HELPER_1(cvtql_sv, i64, i64)
 
-DEF_HELPER_1(setroundmode, void, i32)
-DEF_HELPER_1(setflushzero, void, i32)
-DEF_HELPER_0(fp_exc_clear, void)
-DEF_HELPER_0(fp_exc_get, i32)
+DEF_HELPER_FLAGS_1(setroundmode, TCG_CALL_CONST, void, i32)
+DEF_HELPER_FLAGS_1(setflushzero, TCG_CALL_CONST, void, i32)
+DEF_HELPER_FLAGS_0(fp_exc_clear, TCG_CALL_CONST, void)
+DEF_HELPER_FLAGS_0(fp_exc_get, TCG_CALL_CONST | TCG_CALL_PURE, i32)
 DEF_HELPER_2(fp_exc_raise, void, i32, i32)
 DEF_HELPER_2(fp_exc_raise_s, void, i32, i32)
 

index a03e432..050a418 100644
@@ -5768,7 +5768,7 @@ abi_long do_syscall(void *cpu_env, int num, abi_long arg1,
         ret = get_errno(fsync(arg1));
         break;
     case TARGET_NR_clone:
-#if defined(TARGET_SH4)
+#if defined(TARGET_SH4) || defined(TARGET_ALPHA)
         ret = get_errno(do_fork(cpu_env, arg1, arg2, arg3, arg5, arg4));
 #elif defined(TARGET_CRIS)
         ret = get_errno(do_fork(cpu_env, arg2, arg1, arg3, arg4, arg5));

index 8afe16d..3dd9888 100644
@@ -411,15 +411,6 @@ static inline int cpu_mmu_index (CPUState *env)
     return (env->ps >> 3) & 3;
 }
 
-#if defined(CONFIG_USER_ONLY)
-static inline void cpu_clone_regs(CPUState *env, target_ulong newsp)
-{
-    if (newsp)
-        env->ir[30] = newsp;
-    /* FIXME: Zero syscall return value.  */
-}
-#endif
-
 #include "cpu-all.h"
 #include "exec-all.h"
 

@@ -477,7 +468,7 @@ enum {
     IR_S4   = 13,
     IR_S5   = 14,
     IR_S6   = 15,
-#define IR_FP IR_S6
+    IR_FP   = IR_S6,
     IR_A0   = 16,
     IR_A1   = 17,
     IR_A2   = 18,

@@ -490,7 +481,7 @@ enum {
     IR_T11  = 25,
     IR_RA   = 26,
     IR_T12  = 27,
-#define IR_PV IR_T12
+    IR_PV   = IR_T12,
     IR_AT   = 28,
     IR_GP   = 29,
     IR_SP   = 30,

@@ -531,4 +522,19 @@ static inline void cpu_get_tb_cpu_state(CPUState *env, target_ulong *pc,
     *flags = env->ps;
 }
 
+#if defined(CONFIG_USER_ONLY)
+static inline void cpu_clone_regs(CPUState *env, target_ulong newsp)
+{
+    if (newsp)
+        env->ir[IR_SP] = newsp;
+    env->ir[IR_V0] = 0;
+    env->ir[IR_A3] = 0;
+}
+
+static inline void cpu_set_tls(CPUState *env, target_ulong newtls)
+{
+    env->unique = newtls;
+}
+#endif
+
 #endif /* !defined (__CPU_ALPHA_H__) */

index ca49cc4..5252881 100644
@@ -2357,6 +2357,11 @@ void cpu_loop (CPUState *env)
     while (1) {
         trapnr = cpu_alpha_exec (env);
 
+	/* All of the traps imply a transition through PALcode, which
+	   implies an REI instruction has been executed.  Which means
+	   that the intr_flag should be cleared.  */
+	env->intr_flag = 0;
+
         switch (trapnr) {
         case EXCP_RESET:
             fprintf(stderr, "Reset requested. Exit\n");

index 8e11304..c378195 100644
@@ -2,8 +2,6 @@
 
 DEF_HELPER_2(excp, void, int, int)
 DEF_HELPER_FLAGS_0(load_pcc, TCG_CALL_CONST | TCG_CALL_PURE, i64)
-DEF_HELPER_FLAGS_0(rc, TCG_CALL_CONST, i64)
-DEF_HELPER_FLAGS_0(rs, TCG_CALL_CONST, i64)
 
 DEF_HELPER_2(addqv, i64, i64, i64)
 DEF_HELPER_2(addlv, i64, i64, i64)

index 2419dc4..84867b8 100644
@@ -47,32 +47,6 @@ void helper_store_fpcr (uint64_t val)
     cpu_alpha_store_fpcr (env, val);
 }
 
-static spinlock_t intr_cpu_lock = SPIN_LOCK_UNLOCKED;
-
-uint64_t helper_rs(void)
-{
-    uint64_t tmp;
-
-    spin_lock(&intr_cpu_lock);
-    tmp = env->intr_flag;
-    env->intr_flag = 1;
-    spin_unlock(&intr_cpu_lock);
-
-    return tmp;
-}
-
-uint64_t helper_rc(void)
-{
-    uint64_t tmp;
-
-    spin_lock(&intr_cpu_lock);
-    tmp = env->intr_flag;
-    env->intr_flag = 0;
-    spin_unlock(&intr_cpu_lock);
-
-    return tmp;
-}
-
 uint64_t helper_addqv (uint64_t op1, uint64_t op2)
 {
     uint64_t tmp = op1;

@@ -1211,6 +1185,7 @@ void helper_hw_rei (void)
 {
     env->pc = env->ipr[IPR_EXC_ADDR] & ~3;
     env->ipr[IPR_EXC_ADDR] = env->ipr[IPR_EXC_ADDR] & 1;
+    env->intr_flag = 0;
     /* XXX: re-enable interrupts and memory mapping */
 }
 

@@ -1218,6 +1193,7 @@ void helper_hw_ret (uint64_t a)
 {
     env->pc = a & ~3;
     env->ipr[IPR_EXC_ADDR] = a & 1;
+    env->intr_flag = 0;
     /* XXX: re-enable interrupts and memory mapping */
 }
 

index b677378..188e76c 100644
@@ -1266,6 +1266,19 @@ static inline void gen_cmp(TCGCond cond, int ra, int rb, int rc, int islit,
     gen_set_label(l2);
 }
 
+static void gen_rx(int ra, int set)
+{
+    TCGv_i32 tmp;
+
+    if (ra != 31) {
+        tcg_gen_ld8u_i64(cpu_ir[ra], cpu_env, offsetof(CPUState, intr_flag));
+    }
+
+    tmp = tcg_const_i32(set);
+    tcg_gen_st8_i32(tmp, cpu_env, offsetof(CPUState, intr_flag));
+    tcg_temp_free_i32(tmp);
+}
+
 static inline int translate_one(DisasContext *ctx, uint32_t insn)
 {
     uint32_t palcode;

@@ -2359,16 +2372,14 @@ static inline int translate_one(DisasContext *ctx, uint32_t insn)
             break;
         case 0xE000:
             /* RC */
-            if (ra != 31)
-                gen_helper_rc(cpu_ir[ra]);
+            gen_rx(ra, 0);
             break;
         case 0xE800:
             /* ECB */
             break;
         case 0xF000:
             /* RS */
-            if (ra != 31)
-                gen_helper_rs(cpu_ir[ra]);
+            gen_rx(ra, 1);
             break;
         case 0xF800:
             /* WH64 */

index adeff0a..ea651c4 100644
@@ -394,9 +394,10 @@ static void gen_fbcond(DisasContext *ctx, TCGCond cond, int ra, int32_t disp)
     gen_bcond_pcload(ctx, disp, lab_true);
 }
 
-static inline void gen_cmov(TCGCond inv_cond, int ra, int rb, int rc,
-                            int islit, uint8_t lit, int mask)
+static void gen_cmov(TCGCond cond, int ra, int rb, int rc,
+		     int islit, uint8_t lit, int mask)
 {
+    TCGCond inv_cond = tcg_invert_cond(cond);
     int l1;
 
     if (unlikely(rc == 31))

@@ -426,7 +427,7 @@ static inline void gen_cmov(TCGCond inv_cond, int ra, int rb, int rc,
     gen_set_label(l1);
 }
 
-static void gen_fcmov(TCGCond inv_cond, int ra, int rb, int rc)
+static void gen_fcmov(TCGCond cond, int ra, int rb, int rc)
 {
     TCGv va = cpu_fir[ra];
     int l1;

@@ -439,7 +440,7 @@ static void gen_fcmov(TCGCond inv_cond, int ra, int rb, int rc)
     }
 
     l1 = gen_new_label();
-    gen_fbcond_internal(inv_cond, va, l1);
+    gen_fbcond_internal(tcg_invert_cond(cond), va, l1);
 
     if (rb != 31)
         tcg_gen_mov_i64(cpu_fir[rc], cpu_fir[rb]);

@@ -1767,11 +1768,11 @@ static inline int translate_one(DisasContext *ctx, uint32_t insn)
             break;
         case 0x14:
             /* CMOVLBS */
-            gen_cmov(TCG_COND_EQ, ra, rb, rc, islit, lit, 1);
+            gen_cmov(TCG_COND_NE, ra, rb, rc, islit, lit, 1);
             break;
         case 0x16:
             /* CMOVLBC */
-            gen_cmov(TCG_COND_NE, ra, rb, rc, islit, lit, 1);
+            gen_cmov(TCG_COND_EQ, ra, rb, rc, islit, lit, 1);
             break;
         case 0x20:
             /* BIS */

@@ -1791,11 +1792,11 @@ static inline int translate_one(DisasContext *ctx, uint32_t insn)
             break;
         case 0x24:
             /* CMOVEQ */
-            gen_cmov(TCG_COND_NE, ra, rb, rc, islit, lit, 0);
+            gen_cmov(TCG_COND_EQ, ra, rb, rc, islit, lit, 0);
             break;
         case 0x26:
             /* CMOVNE */
-            gen_cmov(TCG_COND_EQ, ra, rb, rc, islit, lit, 0);
+            gen_cmov(TCG_COND_NE, ra, rb, rc, islit, lit, 0);
             break;
         case 0x28:
             /* ORNOT */

@@ -1831,11 +1832,11 @@ static inline int translate_one(DisasContext *ctx, uint32_t insn)
             break;
         case 0x44:
             /* CMOVLT */
-            gen_cmov(TCG_COND_GE, ra, rb, rc, islit, lit, 0);
+            gen_cmov(TCG_COND_LT, ra, rb, rc, islit, lit, 0);
             break;
         case 0x46:
             /* CMOVGE */
-            gen_cmov(TCG_COND_LT, ra, rb, rc, islit, lit, 0);
+            gen_cmov(TCG_COND_GE, ra, rb, rc, islit, lit, 0);
             break;
         case 0x48:
             /* EQV */

@@ -1875,11 +1876,11 @@ static inline int translate_one(DisasContext *ctx, uint32_t insn)
             break;
         case 0x64:
             /* CMOVLE */
-            gen_cmov(TCG_COND_GT, ra, rb, rc, islit, lit, 0);
+            gen_cmov(TCG_COND_LE, ra, rb, rc, islit, lit, 0);
             break;
         case 0x66:
             /* CMOVGT */
-            gen_cmov(TCG_COND_LE, ra, rb, rc, islit, lit, 0);
+            gen_cmov(TCG_COND_GT, ra, rb, rc, islit, lit, 0);
             break;
         case 0x6C:
             /* IMPLVER */

@@ -2353,27 +2354,27 @@ static inline int translate_one(DisasContext *ctx, uint32_t insn)
             break;
         case 0x02A:
             /* FCMOVEQ */
-            gen_fcmov(TCG_COND_NE, ra, rb, rc);
+            gen_fcmov(TCG_COND_EQ, ra, rb, rc);
             break;
         case 0x02B:
             /* FCMOVNE */
-            gen_fcmov(TCG_COND_EQ, ra, rb, rc);
+            gen_fcmov(TCG_COND_NE, ra, rb, rc);
             break;
         case 0x02C:
             /* FCMOVLT */
-            gen_fcmov(TCG_COND_GE, ra, rb, rc);
+            gen_fcmov(TCG_COND_LT, ra, rb, rc);
             break;
         case 0x02D:
             /* FCMOVGE */
-            gen_fcmov(TCG_COND_LT, ra, rb, rc);
+            gen_fcmov(TCG_COND_GE, ra, rb, rc);
             break;
         case 0x02E:
             /* FCMOVLE */
-            gen_fcmov(TCG_COND_GT, ra, rb, rc);
+            gen_fcmov(TCG_COND_LE, ra, rb, rc);
             break;
         case 0x02F:
             /* FCMOVGT */
-            gen_fcmov(TCG_COND_LE, ra, rb, rc);
+            gen_fcmov(TCG_COND_GT, ra, rb, rc);
             break;
         case 0x030:
             /* CVTQL */

index 2360a0e..5636f60 100644
@@ -74,7 +74,11 @@ typedef enum {
 
     /* We are exiting the TB, but have neither emitted a goto_tb, nor
        updated the PC for the next instruction to be executed.  */
-    EXIT_PC_STALE
+    EXIT_PC_STALE,
+
+    /* We are ending the TB with a noreturn function call, e.g. longjmp.
+       No following code will be executed.  */
+    EXIT_NORETURN,
 } ExitStatus;
 
 /* global register indexes */

@@ -134,7 +138,7 @@ static void alpha_translate_init(void)
     done_init = 1;
 }
 
-static inline void gen_excp(DisasContext *ctx, int exception, int error_code)
+static ExitStatus gen_excp(DisasContext *ctx, int exception, int error_code)
 {
     TCGv_i32 tmp1, tmp2;
 

@@ -144,11 +148,13 @@ static inline void gen_excp(DisasContext *ctx, int exception, int error_code)
     gen_helper_excp(tmp1, tmp2);
     tcg_temp_free_i32(tmp2);
     tcg_temp_free_i32(tmp1);
+
+    return EXIT_NORETURN;
 }
 
-static inline void gen_invalid(DisasContext *ctx)
+static inline ExitStatus gen_invalid(DisasContext *ctx)
 {
-    gen_excp(ctx, EXCP_OPCDEC, 0);
+    return gen_excp(ctx, EXCP_OPCDEC, 0);
 }
 
 static inline void gen_qemu_ldf(TCGv t0, TCGv t1, int flags)

@@ -1458,9 +1464,7 @@ static ExitStatus translate_one(DisasContext *ctx, uint32_t insn)
 #endif
         if (palcode >= 0x80 && palcode < 0xC0) {
             /* Unprivileged PAL call */
-            gen_excp(ctx, EXCP_CALL_PAL + ((palcode & 0x3F) << 6), 0);
-            /* PC updated by gen_excp.  */
-            ret = EXIT_PC_UPDATED;
+            ret = gen_excp(ctx, EXCP_CALL_PAL + ((palcode & 0x3F) << 6), 0);
             break;
         }
 #ifndef CONFIG_USER_ONLY

@@ -1468,9 +1472,7 @@ static ExitStatus translate_one(DisasContext *ctx, uint32_t insn)
             /* Privileged PAL code */
             if (ctx->mem_idx & 1)
                 goto invalid_opc;
-            gen_excp(ctx, EXCP_CALL_PALP + ((palcode & 0x3F) << 6), 0);
-            /* PC updated by gen_excp.  */
-            ret = EXIT_PC_UPDATED;
+            ret = gen_excp(ctx, EXCP_CALL_PALP + ((palcode & 0x3F) << 6), 0);
         }
 #endif
         /* Invalid PAL call */

@@ -3078,9 +3080,7 @@ static ExitStatus translate_one(DisasContext *ctx, uint32_t insn)
         ret = gen_bcond(ctx, TCG_COND_GT, ra, disp21, 0);
         break;
     invalid_opc:
-        gen_invalid(ctx);
-        /* PC updated by gen_excp.  */
-        ret = EXIT_PC_UPDATED;
+        ret = gen_invalid(ctx);
         break;
     }
 

@@ -3184,6 +3184,7 @@ static inline void gen_intermediate_code_internal(CPUState *env,
 
     switch (ret) {
     case EXIT_GOTO_TB:
+    case EXIT_NORETURN:
         break;
     case EXIT_PC_STALE:
         tcg_gen_movi_i64(cpu_pc, ctx.pc);

index ea651c4..dfe55c3 100644
@@ -43,12 +43,13 @@
 
 typedef struct DisasContext DisasContext;
 struct DisasContext {
+    struct TranslationBlock *tb;
+    CPUAlphaState *env;
     uint64_t pc;
     int mem_idx;
 #if !defined (CONFIG_USER_ONLY)
     int pal_mode;
 #endif
-    CPUAlphaState *env;
     uint32_t amask;
 
     /* Current rounding mode for this TB.  */

@@ -57,6 +58,25 @@ struct DisasContext {
     int tb_ftz;
 };
 
+/* Return values from translate_one, indicating the state of the TB.
+   Note that zero indicates that we are not exiting the TB.  */
+
+typedef enum {
+    NO_EXIT,
+
+    /* We have emitted one or more goto_tb.  No fixup required.  */
+    EXIT_GOTO_TB,
+
+    /* We are not using a goto_tb (for whatever reason), but have updated
+       the PC (for whatever reason), so there's no need to do it again on
+       exiting the TB.  */
+    EXIT_PC_UPDATED,
+
+    /* We are exiting the TB, but have neither emitted a goto_tb, nor
+       updated the PC for the next instruction to be executed.  */
+    EXIT_PC_STALE
+} ExitStatus;
+
 /* global register indexes */
 static TCGv_ptr cpu_env;
 static TCGv cpu_ir[31];

@@ -300,77 +320,126 @@ static inline void gen_store_mem(DisasContext *ctx,
     tcg_temp_free(addr);
 }
 
-static void gen_bcond_pcload(DisasContext *ctx, int32_t disp, int lab_true)
+static int use_goto_tb(DisasContext *ctx, uint64_t dest)
 {
-    int lab_over = gen_new_label();
+    /* Check for the dest on the same page as the start of the TB.  We
+       also want to suppress goto_tb in the case of single-steping and IO.  */
+    return (((ctx->tb->pc ^ dest) & TARGET_PAGE_MASK) == 0
+            && !ctx->env->singlestep_enabled
+            && !(ctx->tb->cflags & CF_LAST_IO));
+}
 
-    tcg_gen_movi_i64(cpu_pc, ctx->pc);
-    tcg_gen_br(lab_over);
-    gen_set_label(lab_true);
-    tcg_gen_movi_i64(cpu_pc, ctx->pc + (int64_t)(disp << 2));
-    gen_set_label(lab_over);
+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);
+    }
+
+    /* Notice branch-to-next; used to initialize RA with the PC.  */
+    if (disp == 0) {
+        return 0;
+    } else if (use_goto_tb(ctx, dest)) {
+        tcg_gen_goto_tb(0);
+        tcg_gen_movi_i64(cpu_pc, dest);
+        tcg_gen_exit_tb((long)ctx->tb);
+        return EXIT_GOTO_TB;
+    } else {
+        tcg_gen_movi_i64(cpu_pc, dest);
+        return EXIT_PC_UPDATED;
+    }
 }
 
-static void gen_bcond(DisasContext *ctx, TCGCond cond, int ra,
-                      int32_t disp, int mask)
+static ExitStatus gen_bcond_internal(DisasContext *ctx, TCGCond cond,
+                                     TCGv cmp, int32_t disp)
 {
+    uint64_t dest = ctx->pc + (disp << 2);
     int lab_true = gen_new_label();
 
-    if (likely(ra != 31)) {
+    if (use_goto_tb(ctx, dest)) {
+        tcg_gen_brcondi_i64(cond, cmp, 0, lab_true);
+
+        tcg_gen_goto_tb(0);
+        tcg_gen_movi_i64(cpu_pc, ctx->pc);
+        tcg_gen_exit_tb((long)ctx->tb);
+
+        gen_set_label(lab_true);
+        tcg_gen_goto_tb(1);
+        tcg_gen_movi_i64(cpu_pc, dest);
+        tcg_gen_exit_tb((long)ctx->tb + 1);
+
+        return EXIT_GOTO_TB;
+    } else {
+        int lab_over = gen_new_label();
+
+        /* ??? Consider using either
+             movi pc, next
+             addi tmp, pc, disp
+             movcond pc, cond, 0, tmp, pc
+           or
+             setcond tmp, cond, 0
+             movi pc, next
+             neg tmp, tmp
+             andi tmp, tmp, disp
+             add pc, pc, tmp
+           The current diamond subgraph surely isn't efficient.  */
+
+        tcg_gen_brcondi_i64(cond, cmp, 0, lab_true);
+        tcg_gen_movi_i64(cpu_pc, ctx->pc);
+        tcg_gen_br(lab_over);
+        gen_set_label(lab_true);
+        tcg_gen_movi_i64(cpu_pc, dest);
+        gen_set_label(lab_over);
+
+        return EXIT_PC_UPDATED;
+    }
+}
+
+static ExitStatus gen_bcond(DisasContext *ctx, TCGCond cond, int ra,
+                            int32_t disp, int mask)
+{
+    TCGv cmp_tmp;
+
+    if (unlikely(ra == 31)) {
+        cmp_tmp = tcg_const_i64(0);
+    } else {
+        cmp_tmp = tcg_temp_new();
         if (mask) {
-            TCGv tmp = tcg_temp_new();
-            tcg_gen_andi_i64(tmp, cpu_ir[ra], 1);
-            tcg_gen_brcondi_i64(cond, tmp, 0, lab_true);
-            tcg_temp_free(tmp);
+            tcg_gen_andi_i64(cmp_tmp, cpu_ir[ra], 1);
         } else {
-            tcg_gen_brcondi_i64(cond, cpu_ir[ra], 0, lab_true);
+            tcg_gen_mov_i64(cmp_tmp, cpu_ir[ra]);
         }
-    } else {
-        /* Very uncommon case - Do not bother to optimize.  */
-        TCGv tmp = tcg_const_i64(0);
-        tcg_gen_brcondi_i64(cond, tmp, 0, lab_true);
-        tcg_temp_free(tmp);
     }
-    gen_bcond_pcload(ctx, disp, lab_true);
+
+    return gen_bcond_internal(ctx, cond, cmp_tmp, disp);
 }
 
-/* Generate a forward TCG branch to LAB_TRUE if RA cmp 0.0.
-   This is complicated by the fact that -0.0 compares the same as +0.0.  */
+/* Fold -0.0 for comparison with COND.  */
 
-static void gen_fbcond_internal(TCGCond cond, TCGv src, int lab_true)
+static void gen_fold_mzero(TCGCond cond, TCGv dest, TCGv src)
 {
-    int lab_false = -1;
     uint64_t mzero = 1ull << 63;
-    TCGv tmp;
 
     switch (cond) {
     case TCG_COND_LE:
     case TCG_COND_GT:
         /* For <= or >, the -0.0 value directly compares the way we want.  */
-        tcg_gen_brcondi_i64(cond, src, 0, lab_true);
+        tcg_gen_mov_i64(dest, src);
         break;
 
     case TCG_COND_EQ:
     case TCG_COND_NE:
         /* For == or !=, we can simply mask off the sign bit and compare.  */
-        /* ??? Assume that the temporary is reclaimed at the branch.  */
-        tmp = tcg_temp_new();
-        tcg_gen_andi_i64(tmp, src, mzero - 1);
-        tcg_gen_brcondi_i64(cond, tmp, 0, lab_true);
+        tcg_gen_andi_i64(dest, src, mzero - 1);
         break;
 
     case TCG_COND_GE:
-        /* For >=, emit two branches to the destination.  */
-        tcg_gen_brcondi_i64(cond, src, 0, lab_true);
-        tcg_gen_brcondi_i64(TCG_COND_EQ, src, mzero, lab_true);
-        break;
-
     case TCG_COND_LT:
-        /* For <, first filter out -0.0 to what will be the fallthru.  */
-        lab_false = gen_new_label();
-        tcg_gen_brcondi_i64(TCG_COND_EQ, src, mzero, lab_false);
-        tcg_gen_brcondi_i64(cond, src, 0, lab_true);
-        gen_set_label(lab_false);
+        /* For >= or <, map -0.0 to +0.0 via comparison and mask.  */
+        tcg_gen_setcondi_i64(TCG_COND_NE, dest, src, mzero);
+        tcg_gen_neg_i64(dest, dest);
+        tcg_gen_and_i64(dest, dest, src);
         break;
 
     default:

@@ -378,24 +447,24 @@ static void gen_fbcond_internal(TCGCond cond, TCGv src, int lab_true)
     }
 }
 
-static void gen_fbcond(DisasContext *ctx, TCGCond cond, int ra, int32_t disp)
+static ExitStatus gen_fbcond(DisasContext *ctx, TCGCond cond, int ra,
+                             int32_t disp)
 {
-    int lab_true;
+    TCGv cmp_tmp;
 
     if (unlikely(ra == 31)) {
         /* Very uncommon case, but easier to optimize it to an integer
            comparison than continuing with the floating point comparison.  */
-        gen_bcond(ctx, cond, ra, disp, 0);
-        return;
+        return gen_bcond(ctx, cond, ra, disp, 0);
     }
 
-    lab_true = gen_new_label();
-    gen_fbcond_internal(cond, cpu_fir[ra], lab_true);
-    gen_bcond_pcload(ctx, disp, lab_true);
+    cmp_tmp = tcg_temp_new();
+    gen_fold_mzero(cond, cmp_tmp, cpu_fir[ra]);
+    return gen_bcond_internal(ctx, cond, cmp_tmp, disp);
 }
 
 static void gen_cmov(TCGCond cond, int ra, int rb, int rc,
-		     int islit, uint8_t lit, int mask)
+                     int islit, uint8_t lit, int mask)
 {
     TCGCond inv_cond = tcg_invert_cond(cond);
     int l1;

@@ -429,18 +498,23 @@ static void gen_cmov(TCGCond cond, int ra, int rb, int rc,
 
 static void gen_fcmov(TCGCond cond, int ra, int rb, int rc)
 {
-    TCGv va = cpu_fir[ra];
+    TCGv cmp_tmp;
     int l1;
 
-    if (unlikely(rc == 31))
+    if (unlikely(rc == 31)) {
         return;
+    }
+
+    cmp_tmp = tcg_temp_new();
     if (unlikely(ra == 31)) {
-        /* ??? Assume that the temporary is reclaimed at the branch.  */
-        va = tcg_const_i64(0);
+        tcg_gen_movi_i64(cmp_tmp, 0);
+    } else {
+        gen_fold_mzero(cond, cmp_tmp, cpu_fir[ra]);
     }
 
     l1 = gen_new_label();
-    gen_fbcond_internal(tcg_invert_cond(cond), va, l1);
+    tcg_gen_brcondi_i64(tcg_invert_cond(cond), cmp_tmp, 0, l1);
+    tcg_temp_free(cmp_tmp);
 
     if (rb != 31)
         tcg_gen_mov_i64(cpu_fir[rc], cpu_fir[rb]);

@@ -1334,14 +1408,14 @@ static void gen_rx(int ra, int set)
     tcg_temp_free_i32(tmp);
 }
 
-static inline int translate_one(DisasContext *ctx, uint32_t insn)
+static ExitStatus translate_one(DisasContext *ctx, uint32_t insn)
 {
     uint32_t palcode;
     int32_t disp21, disp16, disp12;
     uint16_t fn11, fn16;
     uint8_t opc, ra, rb, rc, sbz, fpfn, fn7, fn2, islit, real_islit;
     uint8_t lit;
-    int ret;
+    ExitStatus ret;
 
     /* Decode all instruction fields */
     opc = insn >> 26;

@@ -1364,10 +1438,10 @@ static inline int translate_one(DisasContext *ctx, uint32_t insn)
     fpfn = fn11 & 0x3F;
     fn7 = (insn >> 5) & 0x0000007F;
     fn2 = (insn >> 5) & 0x00000003;
-    ret = 0;
     LOG_DISAS("opc %02x ra %2d rb %2d rc %2d disp16 %6d\n",
               opc, ra, rb, rc, disp16);
 
+    ret = NO_EXIT;
     switch (opc) {
     case 0x00:
         /* CALL_PAL */

@@ -1385,7 +1459,8 @@ static inline int translate_one(DisasContext *ctx, uint32_t insn)
         if (palcode >= 0x80 && palcode < 0xC0) {
             /* Unprivileged PAL call */
             gen_excp(ctx, EXCP_CALL_PAL + ((palcode & 0x3F) << 6), 0);
-            ret = 3;
+            /* PC updated by gen_excp.  */
+            ret = EXIT_PC_UPDATED;
             break;
         }
 #ifndef CONFIG_USER_ONLY

@@ -1394,7 +1469,8 @@ static inline int translate_one(DisasContext *ctx, uint32_t insn)
             if (ctx->mem_idx & 1)
                 goto invalid_opc;
             gen_excp(ctx, EXCP_CALL_PALP + ((palcode & 0x3F) << 6), 0);
-            ret = 3;
+            /* PC updated by gen_excp.  */
+            ret = EXIT_PC_UPDATED;
         }
 #endif
         /* Invalid PAL call */

@@ -2397,13 +2473,11 @@ static inline int translate_one(DisasContext *ctx, uint32_t insn)
         switch ((uint16_t)disp16) {
         case 0x0000:
             /* TRAPB */
-            /* No-op. Just exit from the current tb */
-            ret = 2;
+            /* No-op.  */
             break;
         case 0x0400:
             /* EXCB */
-            /* No-op. Just exit from the current tb */
-            ret = 2;
+            /* No-op.  */
             break;
         case 0x4000:
             /* MB */

@@ -2467,21 +2541,7 @@ static inline int translate_one(DisasContext *ctx, uint32_t insn)
         if (ra != 31)
             tcg_gen_movi_i64(cpu_ir[ra], ctx->pc);
         /* Those four jumps only differ by the branch prediction hint */
-        switch (fn2) {
-        case 0x0:
-            /* JMP */
-            break;
-        case 0x1:
-            /* JSR */
-            break;
-        case 0x2:
-            /* RET */
-            break;
-        case 0x3:
-            /* JSR_COROUTINE */
-            break;
-        }
-        ret = 1;
+        ret = EXIT_PC_UPDATED;
         break;
     case 0x1B:
         /* HW_LD (PALcode) */

@@ -2772,7 +2832,7 @@ static inline int translate_one(DisasContext *ctx, uint32_t insn)
                 tcg_temp_free(tmp2);
             }
             tcg_temp_free(tmp1);
-            ret = 2;
+            ret = EXIT_PC_STALE;
         }
         break;
 #endif

@@ -2797,7 +2857,7 @@ static inline int translate_one(DisasContext *ctx, uint32_t insn)
             gen_helper_hw_ret(tmp);
             tcg_temp_free(tmp);
         }
-        ret = 2;
+        ret = EXIT_PC_UPDATED;
         break;
 #endif
     case 0x1F:

@@ -2958,85 +3018,66 @@ static inline int translate_one(DisasContext *ctx, uint32_t insn)
         break;
     case 0x30:
         /* BR */
-        if (ra != 31)
-            tcg_gen_movi_i64(cpu_ir[ra], ctx->pc);
-        tcg_gen_movi_i64(cpu_pc, ctx->pc + (int64_t)(disp21 << 2));
-        ret = 1;
+        ret = gen_bdirect(ctx, ra, disp21);
         break;
     case 0x31: /* FBEQ */
-        gen_fbcond(ctx, TCG_COND_EQ, ra, disp21);
-        ret = 1;
+        ret = gen_fbcond(ctx, TCG_COND_EQ, ra, disp21);
         break;
     case 0x32: /* FBLT */
-        gen_fbcond(ctx, TCG_COND_LT, ra, disp21);
-        ret = 1;
+        ret = gen_fbcond(ctx, TCG_COND_LT, ra, disp21);
         break;
     case 0x33: /* FBLE */
-        gen_fbcond(ctx, TCG_COND_LE, ra, disp21);
-        ret = 1;
+        ret = gen_fbcond(ctx, TCG_COND_LE, ra, disp21);
         break;
     case 0x34:
         /* BSR */
-        if (ra != 31)
-            tcg_gen_movi_i64(cpu_ir[ra], ctx->pc);
-        tcg_gen_movi_i64(cpu_pc, ctx->pc + (int64_t)(disp21 << 2));
-        ret = 1;
+        ret = gen_bdirect(ctx, ra, disp21);
         break;
     case 0x35: /* FBNE */
-        gen_fbcond(ctx, TCG_COND_NE, ra, disp21);
-        ret = 1;
+        ret = gen_fbcond(ctx, TCG_COND_NE, ra, disp21);
         break;
     case 0x36: /* FBGE */
-        gen_fbcond(ctx, TCG_COND_GE, ra, disp21);
-        ret = 1;
+        ret = gen_fbcond(ctx, TCG_COND_GE, ra, disp21);
         break;
     case 0x37: /* FBGT */
-        gen_fbcond(ctx, TCG_COND_GT, ra, disp21);
-        ret = 1;
+        ret = gen_fbcond(ctx, TCG_COND_GT, ra, disp21);
         break;
     case 0x38:
         /* BLBC */
-        gen_bcond(ctx, TCG_COND_EQ, ra, disp21, 1);
-        ret = 1;
+        ret = gen_bcond(ctx, TCG_COND_EQ, ra, disp21, 1);
         break;
     case 0x39:
         /* BEQ */
-        gen_bcond(ctx, TCG_COND_EQ, ra, disp21, 0);
-        ret = 1;
+        ret = gen_bcond(ctx, TCG_COND_EQ, ra, disp21, 0);
         break;
     case 0x3A:
         /* BLT */
-        gen_bcond(ctx, TCG_COND_LT, ra, disp21, 0);
-        ret = 1;
+        ret = gen_bcond(ctx, TCG_COND_LT, ra, disp21, 0);
         break;
     case 0x3B:
         /* BLE */
-        gen_bcond(ctx, TCG_COND_LE, ra, disp21, 0);
-        ret = 1;
+        ret = gen_bcond(ctx, TCG_COND_LE, ra, disp21, 0);
         break;
     case 0x3C:
         /* BLBS */
-        gen_bcond(ctx, TCG_COND_NE, ra, disp21, 1);
-        ret = 1;
+        ret = gen_bcond(ctx, TCG_COND_NE, ra, disp21, 1);
         break;
     case 0x3D:
         /* BNE */
-        gen_bcond(ctx, TCG_COND_NE, ra, disp21, 0);
-        ret = 1;
+        ret = gen_bcond(ctx, TCG_COND_NE, ra, disp21, 0);
         break;
     case 0x3E:
         /* BGE */
-        gen_bcond(ctx, TCG_COND_GE, ra, disp21, 0);
-        ret = 1;
+        ret = gen_bcond(ctx, TCG_COND_GE, ra, disp21, 0);
         break;
     case 0x3F:
         /* BGT */
-        gen_bcond(ctx, TCG_COND_GT, ra, disp21, 0);
-        ret = 1;
+        ret = gen_bcond(ctx, TCG_COND_GT, ra, disp21, 0);
         break;
     invalid_opc:
         gen_invalid(ctx);
-        ret = 3;
+        /* PC updated by gen_excp.  */
+        ret = EXIT_PC_UPDATED;
         break;
     }
 

@@ -3053,15 +3094,17 @@ static inline void gen_intermediate_code_internal(CPUState *env,
     uint16_t *gen_opc_end;
     CPUBreakpoint *bp;
     int j, lj = -1;
-    int ret;
+    ExitStatus ret;
     int num_insns;
     int max_insns;
 
     pc_start = tb->pc;
     gen_opc_end = gen_opc_buf + OPC_MAX_SIZE;
+
+    ctx.tb = tb;
+    ctx.env = env;
     ctx.pc = pc_start;
     ctx.amask = env->amask;
-    ctx.env = env;
 #if defined (CONFIG_USER_ONLY)
     ctx.mem_idx = 0;
 #else

@@ -3085,7 +3128,7 @@ static inline void gen_intermediate_code_internal(CPUState *env,
         max_insns = CF_COUNT_MASK;
 
     gen_icount_start();
-    for (ret = 0; ret == 0;) {
+    do {
         if (unlikely(!QTAILQ_EMPTY(&env->breakpoints))) {
             QTAILQ_FOREACH(bp, &env->breakpoints, entry) {
                 if (bp->pc == ctx.pc) {

@@ -3116,36 +3159,39 @@ static inline void gen_intermediate_code_internal(CPUState *env,
 
         ctx.pc += 4;
         ret = translate_one(ctxp, insn);
-        if (ret != 0)
-            break;
-        /* if we reach a page boundary or are single stepping, stop
-         * generation
-         */
-        if (env->singlestep_enabled) {
-            gen_excp(&ctx, EXCP_DEBUG, 0);
-            break;
-        }
 
-        if ((ctx.pc & (TARGET_PAGE_SIZE - 1)) == 0)
-            break;
-
-        if (gen_opc_ptr >= gen_opc_end)
-            break;
-
-        if (num_insns >= max_insns)
-            break;
-
-        if (singlestep) {
-            break;
+        if (ret == NO_EXIT) {
+            /* If we reach a page boundary, are single stepping,
+               or exhaust instruction count, stop generation.  */
+            if (env->singlestep_enabled) {
+                gen_excp(&ctx, EXCP_DEBUG, 0);
+                ret = EXIT_PC_UPDATED;
+            } else if ((ctx.pc & (TARGET_PAGE_SIZE - 1)) == 0
+                       || gen_opc_ptr >= gen_opc_end
+                       || num_insns >= max_insns
+                       || singlestep) {
+                ret = EXIT_PC_STALE;
+            }
         }
+    } while (ret == NO_EXIT);
+
+    if (tb->cflags & CF_LAST_IO) {
+        gen_io_end();
     }
-    if (ret != 1 && ret != 3) {
+
+    switch (ret) {
+    case EXIT_GOTO_TB:
+        break;
+    case EXIT_PC_STALE:
         tcg_gen_movi_i64(cpu_pc, ctx.pc);
+        /* FALLTHRU */
+    case EXIT_PC_UPDATED:
+        tcg_gen_exit_tb(0);
+        break;
+    default:
+        abort();
     }
-    if (tb->cflags & CF_LAST_IO)
-        gen_io_end();
-    /* Generate the return instruction */
-    tcg_gen_exit_tb(0);
+
     gen_icount_end(tb, num_insns);
     *gen_opc_ptr = INDEX_op_end;
     if (search_pc) {

@@ -3157,6 +3203,7 @@ static inline void gen_intermediate_code_internal(CPUState *env,
         tb->size = ctx.pc - pc_start;
         tb->icount = num_insns;
     }
+
 #ifdef DEBUG_DISAS
     if (qemu_loglevel_mask(CPU_LOG_TB_IN_ASM)) {
         qemu_log("IN: %s\n", lookup_symbol(pc_start));

index d2e15f4..6e2d2e1 100644
@@ -209,6 +209,19 @@ static inline int64_t cpu_get_real_ticks(void)
     return (int64_t)(count * cyc_per_count);
 }
 
+#elif defined(__alpha__)
+
+static inline int64_t cpu_get_real_ticks(void)
+{
+    uint64_t cc;
+    uint32_t cur, ofs;
+
+    asm volatile("rpcc %0" : "=r"(cc));
+    cur = cc;
+    ofs = cc >> 32;
+    return cur - ofs;
+}
+
 #else
 /* The host CPU doesn't have an easily accessible cycle counter.
    Just return a monotonically increasing value.  This will be

index dae23e2..c2f6a50 100644
@@ -355,7 +355,6 @@ struct CPUAlphaState {
     uint64_t ir[31];
     float64 fir[31];
     uint64_t pc;
-    uint32_t pcc[2];
     uint64_t ipr[IPR_LAST];
     uint64_t ps;
     uint64_t unique;

index bfc095c..ff5ae26 100644
@@ -21,6 +21,7 @@
 #include "host-utils.h"
 #include "softfloat.h"
 #include "helper.h"
+#include "qemu-timer.h"
 
 /*****************************************************************************/
 /* Exceptions processing helpers */

@@ -33,8 +34,8 @@ void QEMU_NORETURN helper_excp (int excp, int error)
 
 uint64_t helper_load_pcc (void)
 {
-    /* XXX: TODO */
-    return 0;
+    /* ??? This isn't a timer for which we have any rate info.  */
+    return (uint32_t)cpu_get_real_ticks();
 }
 
 uint64_t helper_load_fpcr (void)

index 5252881..61c3ed9 100644
@@ -2348,6 +2348,51 @@ void cpu_loop(CPUM68KState *env)
 #endif /* TARGET_M68K */
 
 #ifdef TARGET_ALPHA
+static void do_store_exclusive(CPUAlphaState *env, int reg, int quad)
+{
+    target_ulong addr, val, tmp;
+    target_siginfo_t info;
+    int ret = 0;
+
+    addr = env->lock_addr;
+    tmp = env->lock_st_addr;
+    env->lock_addr = -1;
+    env->lock_st_addr = 0;
+
+    start_exclusive();
+    mmap_lock();
+
+    if (addr == tmp) {
+        if (quad ? get_user_s64(val, addr) : get_user_s32(val, addr)) {
+            goto do_sigsegv;
+        }
+
+        if (val == env->lock_value) {
+            tmp = env->ir[reg];
+            if (quad ? put_user_u64(tmp, addr) : put_user_u32(tmp, addr)) {
+                goto do_sigsegv;
+            }
+            ret = 1;
+        }
+    }
+    env->ir[reg] = ret;
+    env->pc += 4;
+
+    mmap_unlock();
+    end_exclusive();
+    return;
+
+ do_sigsegv:
+    mmap_unlock();
+    end_exclusive();
+
+    info.si_signo = TARGET_SIGSEGV;
+    info.si_errno = 0;
+    info.si_code = TARGET_SEGV_MAPERR;
+    info._sifields._sigfault._addr = addr;
+    queue_signal(env, TARGET_SIGSEGV, &info);
+}
+
 void cpu_loop (CPUState *env)
 {
     int trapnr;

@@ -2372,6 +2417,7 @@ void cpu_loop (CPUState *env)
             exit(1);
             break;
         case EXCP_ARITH:
+            env->lock_addr = -1;
             info.si_signo = TARGET_SIGFPE;
             info.si_errno = 0;
             info.si_code = TARGET_FPE_FLTINV;

@@ -2383,6 +2429,7 @@ void cpu_loop (CPUState *env)
             exit(1);
             break;
         case EXCP_DFAULT:
+            env->lock_addr = -1;
             info.si_signo = TARGET_SIGSEGV;
             info.si_errno = 0;
             info.si_code = 0;  /* ??? SEGV_MAPERR vs SEGV_ACCERR.  */

@@ -2406,6 +2453,7 @@ void cpu_loop (CPUState *env)
             exit(1);
             break;
         case EXCP_UNALIGN:
+            env->lock_addr = -1;
             info.si_signo = TARGET_SIGBUS;
             info.si_errno = 0;
             info.si_code = TARGET_BUS_ADRALN;

@@ -2414,6 +2462,7 @@ void cpu_loop (CPUState *env)
             break;
         case EXCP_OPCDEC:
         do_sigill:
+            env->lock_addr = -1;
             info.si_signo = TARGET_SIGILL;
             info.si_errno = 0;
             info.si_code = TARGET_ILL_ILLOPC;

@@ -2424,6 +2473,7 @@ void cpu_loop (CPUState *env)
             /* No-op.  Linux simply re-enables the FPU.  */
             break;
         case EXCP_CALL_PAL ... (EXCP_CALL_PALP - 1):
+            env->lock_addr = -1;
             switch ((trapnr >> 6) | 0x80) {
             case 0x80:
                 /* BPT */

@@ -2513,11 +2563,16 @@ void cpu_loop (CPUState *env)
         case EXCP_DEBUG:
             info.si_signo = gdb_handlesig (env, TARGET_SIGTRAP);
             if (info.si_signo) {
+                env->lock_addr = -1;
                 info.si_errno = 0;
                 info.si_code = TARGET_TRAP_BRKPT;
                 queue_signal(env, info.si_signo, &info);
             }
             break;
+        case EXCP_STL_C:
+        case EXCP_STQ_C:
+            do_store_exclusive(env, env->error_code, trapnr - EXCP_STL_C);
+            break;
         default:
             printf ("Unhandled trap: 0x%x\n", trapnr);
             cpu_dump_state(env, stderr, fprintf, 0);

index 3dd9888..dae23e2 100644
@@ -355,11 +355,13 @@ struct CPUAlphaState {
     uint64_t ir[31];
     float64 fir[31];
     uint64_t pc;
-    uint64_t lock;
     uint32_t pcc[2];
     uint64_t ipr[IPR_LAST];
     uint64_t ps;
     uint64_t unique;
+    uint64_t lock_addr;
+    uint64_t lock_st_addr;
+    uint64_t lock_value;
     float_status fp_status;
     /* The following fields make up the FPCR, but in FP_STATUS format.  */
     uint8_t fpcr_exc_status;

@@ -440,6 +442,8 @@ enum {
     /* Pseudo exception for console */
     EXCP_CONSOLE_DISPATCH = 0x4001,
     EXCP_CONSOLE_FIXUP    = 0x4002,
+    EXCP_STL_C            = 0x4003,
+    EXCP_STQ_C            = 0x4004,
 };
 
 /* Arithmetic exception */

index 46335cd..1ed7ea3 100644
@@ -556,12 +556,15 @@ void cpu_dump_state (CPUState *env, FILE *f,
         if ((i % 3) == 2)
             cpu_fprintf(f, "\n");
     }
-    cpu_fprintf(f, "\n");
+
+    cpu_fprintf(f, "lock_a   " TARGET_FMT_lx " lock_v   " TARGET_FMT_lx "\n",
+                env->lock_addr, env->lock_value);
+
     for (i = 0; i < 31; i++) {
         cpu_fprintf(f, "FIR%02d    " TARGET_FMT_lx " ", i,
                     *((uint64_t *)(&env->fir[i])));
         if ((i % 3) == 2)
             cpu_fprintf(f, "\n");
     }
-    cpu_fprintf(f, "\nlock     " TARGET_FMT_lx "\n", env->lock);
+    cpu_fprintf(f, "\n");
 }

index a209130..bfc095c 100644
@@ -1159,6 +1159,7 @@ void helper_hw_rei (void)
     env->pc = env->ipr[IPR_EXC_ADDR] & ~3;
     env->ipr[IPR_EXC_ADDR] = env->ipr[IPR_EXC_ADDR] & 1;
     env->intr_flag = 0;
+    env->lock_addr = -1;
     /* XXX: re-enable interrupts and memory mapping */
 }
 

@@ -1167,6 +1168,7 @@ void helper_hw_ret (uint64_t a)
     env->pc = a & ~3;
     env->ipr[IPR_EXC_ADDR] = a & 1;
     env->intr_flag = 0;
+    env->lock_addr = -1;
     /* XXX: re-enable interrupts and memory mapping */
 }
 

312 lines not on this page · raw message

index 10c78d0..ccf6a2a 100644
@@ -83,7 +83,6 @@ DEF_HELPER_FLAGS_1(cvtqf, TCG_CALL_CONST, i64, i64)
 DEF_HELPER_FLAGS_1(cvtgf, TCG_CALL_CONST, i64, i64)
 DEF_HELPER_FLAGS_1(cvtgq, TCG_CALL_CONST, i64, i64)
 DEF_HELPER_FLAGS_1(cvtqg, TCG_CALL_CONST, i64, i64)
-DEF_HELPER_FLAGS_1(cvtlq, TCG_CALL_CONST | TCG_CALL_PURE, i64, i64)
 
 DEF_HELPER_FLAGS_1(cvttq, TCG_CALL_CONST, i64, i64)
 DEF_HELPER_FLAGS_1(cvttq_c, TCG_CALL_CONST, i64, i64)

index f9cd07a..a209130 100644
@@ -1152,13 +1152,6 @@ uint64_t helper_cvtqg (uint64_t a)
     return float64_to_g(fr);
 }
 
-uint64_t helper_cvtlq (uint64_t a)
-{
-    int32_t lo = a >> 29;
-    int32_t hi = a >> 32;
-    return (lo & 0x3FFFFFFF) | (hi & 0xc0000000);
-}
-
 /* PALcode support special instructions */
 #if !defined (CONFIG_USER_ONLY)
 void helper_hw_rei (void)

index 939496c..00f070d 100644
@@ -598,6 +598,28 @@ static inline void gen_fp_exc_raise(int rc, int fn11)
     gen_fp_exc_raise_ignore(rc, fn11, fn11 & QUAL_I ? 0 : float_flag_inexact);
 }
 
+static void gen_fcvtlq(int rb, int rc)
+{
+    if (unlikely(rc == 31)) {
+        return;
+    }
+    if (unlikely(rb == 31)) {
+        tcg_gen_movi_i64(cpu_fir[rc], 0);
+    } else {
+        TCGv tmp = tcg_temp_new();
+
+        /* The arithmetic right shift here, plus the sign-extended mask below
+           yields a sign-extended result without an explicit ext32s_i64.  */
+        tcg_gen_sari_i64(tmp, cpu_fir[rb], 32);
+        tcg_gen_shri_i64(cpu_fir[rc], cpu_fir[rb], 29);
+        tcg_gen_andi_i64(tmp, tmp, (int32_t)0xc0000000);
+        tcg_gen_andi_i64(cpu_fir[rc], cpu_fir[rc], 0x3fffffff);
+        tcg_gen_or_i64(cpu_fir[rc], cpu_fir[rc], tmp);
+
+        tcg_temp_free(tmp);
+    }
+}
+
 static void gen_fcvtql(int rb, int rc)
 {
     if (unlikely(rc == 31)) {

@@ -647,7 +669,6 @@ static inline void glue(gen_f, name)(int rb, int rc)    \
         tcg_temp_free(tmp);                             \
     }                                                   \
 }
-FARITH2(cvtlq)
 
 /* ??? VAX instruction qualifiers ignored.  */
 FARITH2(sqrtf)

index 29152fa..2c29337 100644
@@ -2535,13 +2535,16 @@ static ExitStatus translate_one(DisasContext *ctx, uint32_t insn)
         break;
 #endif
     case 0x1A:
-        if (rb != 31)
+        /* JMP, JSR, RET, JSR_COROUTINE.  These only differ by the branch
+           prediction stack action, which of course we don't implement.  */
+        if (rb != 31) {
             tcg_gen_andi_i64(cpu_pc, cpu_ir[rb], ~3);
-        else
+        } else {
             tcg_gen_movi_i64(cpu_pc, 0);
-        if (ra != 31)
+        }
+        if (ra != 31) {
             tcg_gen_movi_i64(cpu_ir[ra], ctx->pc);
-        /* Those four jumps only differ by the branch prediction hint */
+        }
         ret = EXIT_PC_UPDATED;
         break;
     case 0x1B:

index 00f070d..29152fa 100644
@@ -43,12 +43,13 @@
 
 typedef struct DisasContext DisasContext;
 struct DisasContext {
+    struct TranslationBlock *tb;
+    CPUAlphaState *env;
     uint64_t pc;
     int mem_idx;
 #if !defined (CONFIG_USER_ONLY)
     int pal_mode;
 #endif
-    CPUAlphaState *env;
     uint32_t amask;
 
     /* Current rounding mode for this TB.  */

@@ -57,6 +58,25 @@ struct DisasContext {
     int tb_ftz;
 };
 
+/* Return values from translate_one, indicating the state of the TB.
+   Note that zero indicates that we are not exiting the TB.  */
+
+typedef enum {
+    NO_EXIT,
+
+    /* We have emitted one or more goto_tb.  No fixup required.  */
+    EXIT_GOTO_TB,
+
+    /* We are not using a goto_tb (for whatever reason), but have updated
+       the PC (for whatever reason), so there's no need to do it again on
+       exiting the TB.  */
+    EXIT_PC_UPDATED,
+
+    /* We are exiting the TB, but have neither emitted a goto_tb, nor
+       updated the PC for the next instruction to be executed.  */
+    EXIT_PC_STALE
+} ExitStatus;
+
 /* global register indexes */
 static TCGv_ptr cpu_env;
 static TCGv cpu_ir[31];

@@ -300,77 +320,126 @@ static inline void gen_store_mem(DisasContext *ctx,
     tcg_temp_free(addr);
 }
 
-static void gen_bcond_pcload(DisasContext *ctx, int32_t disp, int lab_true)
+static int use_goto_tb(DisasContext *ctx, uint64_t dest)
 {
-    int lab_over = gen_new_label();
+    /* Check for the dest on the same page as the start of the TB.  We
+       also want to suppress goto_tb in the case of single-steping and IO.  */
+    return (((ctx->tb->pc ^ dest) & TARGET_PAGE_MASK) == 0
+            && !ctx->env->singlestep_enabled
+            && !(ctx->tb->cflags & CF_LAST_IO));
+}
 
-    tcg_gen_movi_i64(cpu_pc, ctx->pc);
-    tcg_gen_br(lab_over);
-    gen_set_label(lab_true);
-    tcg_gen_movi_i64(cpu_pc, ctx->pc + (int64_t)(disp << 2));
-    gen_set_label(lab_over);
+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);
+    }
+
+    /* Notice branch-to-next; used to initialize RA with the PC.  */
+    if (disp == 0) {
+        return 0;
+    } else if (use_goto_tb(ctx, dest)) {
+        tcg_gen_goto_tb(0);
+        tcg_gen_movi_i64(cpu_pc, dest);
+        tcg_gen_exit_tb((long)ctx->tb);
+        return EXIT_GOTO_TB;
+    } else {
+        tcg_gen_movi_i64(cpu_pc, dest);
+        return EXIT_PC_UPDATED;
+    }
 }
 
-static void gen_bcond(DisasContext *ctx, TCGCond cond, int ra,
-                      int32_t disp, int mask)
+static ExitStatus gen_bcond_internal(DisasContext *ctx, TCGCond cond,
+                                     TCGv cmp, int32_t disp)
 {
+    uint64_t dest = ctx->pc + (disp << 2);
     int lab_true = gen_new_label();
 
-    if (likely(ra != 31)) {
+    if (use_goto_tb(ctx, dest)) {
+        tcg_gen_brcondi_i64(cond, cmp, 0, lab_true);
+
+        tcg_gen_goto_tb(0);
+        tcg_gen_movi_i64(cpu_pc, ctx->pc);
+        tcg_gen_exit_tb((long)ctx->tb);
+
+        gen_set_label(lab_true);
+        tcg_gen_goto_tb(1);
+        tcg_gen_movi_i64(cpu_pc, dest);
+        tcg_gen_exit_tb((long)ctx->tb + 1);
+
+        return EXIT_GOTO_TB;
+    } else {
+        int lab_over = gen_new_label();
+
+        /* ??? Consider using either
+             movi pc, next
+             addi tmp, pc, disp
+             movcond pc, cond, 0, tmp, pc
+           or
+             setcond tmp, cond, 0
+             movi pc, next
+             neg tmp, tmp
+             andi tmp, tmp, disp
+             add pc, pc, tmp
+           The current diamond subgraph surely isn't efficient.  */
+
+        tcg_gen_brcondi_i64(cond, cmp, 0, lab_true);
+        tcg_gen_movi_i64(cpu_pc, ctx->pc);
+        tcg_gen_br(lab_over);
+        gen_set_label(lab_true);
+        tcg_gen_movi_i64(cpu_pc, dest);
+        gen_set_label(lab_over);
+
+        return EXIT_PC_UPDATED;
+    }
+}
+
+static ExitStatus gen_bcond(DisasContext *ctx, TCGCond cond, int ra,
+                            int32_t disp, int mask)
+{
+    TCGv cmp_tmp;
+
+    if (unlikely(ra == 31)) {
+        cmp_tmp = tcg_const_i64(0);
+    } else {
+        cmp_tmp = tcg_temp_new();
         if (mask) {
-            TCGv tmp = tcg_temp_new();
-            tcg_gen_andi_i64(tmp, cpu_ir[ra], 1);
-            tcg_gen_brcondi_i64(cond, tmp, 0, lab_true);
-            tcg_temp_free(tmp);
+            tcg_gen_andi_i64(cmp_tmp, cpu_ir[ra], 1);
         } else {
-            tcg_gen_brcondi_i64(cond, cpu_ir[ra], 0, lab_true);
+            tcg_gen_mov_i64(cmp_tmp, cpu_ir[ra]);
         }
-    } else {
-        /* Very uncommon case - Do not bother to optimize.  */
-        TCGv tmp = tcg_const_i64(0);
-        tcg_gen_brcondi_i64(cond, tmp, 0, lab_true);
-        tcg_temp_free(tmp);
     }
-    gen_bcond_pcload(ctx, disp, lab_true);
+
+    return gen_bcond_internal(ctx, cond, cmp_tmp, disp);
 }
 
-/* Generate a forward TCG branch to LAB_TRUE if RA cmp 0.0.
-   This is complicated by the fact that -0.0 compares the same as +0.0.  */
+/* Fold -0.0 for comparison with COND.  */
 
-static void gen_fbcond_internal(TCGCond cond, TCGv src, int lab_true)
+static void gen_fold_mzero(TCGCond cond, TCGv dest, TCGv src)
 {
-    int lab_false = -1;
     uint64_t mzero = 1ull << 63;
-    TCGv tmp;
 
     switch (cond) {
     case TCG_COND_LE:
     case TCG_COND_GT:
         /* For <= or >, the -0.0 value directly compares the way we want.  */
-        tcg_gen_brcondi_i64(cond, src, 0, lab_true);
+        tcg_gen_mov_i64(dest, src);
         break;
 
     case TCG_COND_EQ:
     case TCG_COND_NE:
         /* For == or !=, we can simply mask off the sign bit and compare.  */
-        /* ??? Assume that the temporary is reclaimed at the branch.  */
-        tmp = tcg_temp_new();
-        tcg_gen_andi_i64(tmp, src, mzero - 1);
-        tcg_gen_brcondi_i64(cond, tmp, 0, lab_true);
+        tcg_gen_andi_i64(dest, src, mzero - 1);
         break;
 
     case TCG_COND_GE:
-        /* For >=, emit two branches to the destination.  */
-        tcg_gen_brcondi_i64(cond, src, 0, lab_true);
-        tcg_gen_brcondi_i64(TCG_COND_EQ, src, mzero, lab_true);
-        break;
-
     case TCG_COND_LT:
-        /* For <, first filter out -0.0 to what will be the fallthru.  */
-        lab_false = gen_new_label();
-        tcg_gen_brcondi_i64(TCG_COND_EQ, src, mzero, lab_false);
-        tcg_gen_brcondi_i64(cond, src, 0, lab_true);
-        gen_set_label(lab_false);
+        /* For >= or <, map -0.0 to +0.0 via comparison and mask.  */
+        tcg_gen_setcondi_i64(TCG_COND_NE, dest, src, mzero);
+        tcg_gen_neg_i64(dest, dest);
+        tcg_gen_and_i64(dest, dest, src);
         break;
 
     default:

@@ -378,24 +447,24 @@ static void gen_fbcond_internal(TCGCond cond, TCGv src, int lab_true)
     }
 }
 
-static void gen_fbcond(DisasContext *ctx, TCGCond cond, int ra, int32_t disp)
+static ExitStatus gen_fbcond(DisasContext *ctx, TCGCond cond, int ra,
+                             int32_t disp)
 {
-    int lab_true;
+    TCGv cmp_tmp;
 
     if (unlikely(ra == 31)) {
         /* Very uncommon case, but easier to optimize it to an integer
            comparison than continuing with the floating point comparison.  */
-        gen_bcond(ctx, cond, ra, disp, 0);
-        return;
+        return gen_bcond(ctx, cond, ra, disp, 0);
     }
 
-    lab_true = gen_new_label();
-    gen_fbcond_internal(cond, cpu_fir[ra], lab_true);
-    gen_bcond_pcload(ctx, disp, lab_true);
+    cmp_tmp = tcg_temp_new();
+    gen_fold_mzero(cond, cmp_tmp, cpu_fir[ra]);
+    return gen_bcond_internal(ctx, cond, cmp_tmp, disp);
 }
 
 static void gen_cmov(TCGCond cond, int ra, int rb, int rc,
-		     int islit, uint8_t lit, int mask)
+                     int islit, uint8_t lit, int mask)
 {
     TCGCond inv_cond = tcg_invert_cond(cond);
     int l1;

@@ -429,18 +498,23 @@ static void gen_cmov(TCGCond cond, int ra, int rb, int rc,
 
 static void gen_fcmov(TCGCond cond, int ra, int rb, int rc)
 {
-    TCGv va = cpu_fir[ra];
+    TCGv cmp_tmp;
     int l1;
 
-    if (unlikely(rc == 31))
+    if (unlikely(rc == 31)) {
         return;
+    }
+
+    cmp_tmp = tcg_temp_new();
     if (unlikely(ra == 31)) {
-        /* ??? Assume that the temporary is reclaimed at the branch.  */
-        va = tcg_const_i64(0);
+        tcg_gen_movi_i64(cmp_tmp, 0);
+    } else {
+        gen_fold_mzero(cond, cmp_tmp, cpu_fir[ra]);
     }
 
     l1 = gen_new_label();
-    gen_fbcond_internal(tcg_invert_cond(cond), va, l1);
+    tcg_gen_brcondi_i64(tcg_invert_cond(cond), cmp_tmp, 0, l1);
+    tcg_temp_free(cmp_tmp);
 
     if (rb != 31)
         tcg_gen_mov_i64(cpu_fir[rc], cpu_fir[rb]);

@@ -1335,14 +1409,14 @@ static void gen_rx(int ra, int set)
     tcg_temp_free_i32(tmp);
 }
 
-static inline int translate_one(DisasContext *ctx, uint32_t insn)
+static ExitStatus translate_one(DisasContext *ctx, uint32_t insn)
 {
     uint32_t palcode;
     int32_t disp21, disp16, disp12;
     uint16_t fn11, fn16;
     uint8_t opc, ra, rb, rc, sbz, fpfn, fn7, fn2, islit, real_islit;
     uint8_t lit;
-    int ret;
+    ExitStatus ret;
 
     /* Decode all instruction fields */
     opc = insn >> 26;

@@ -1365,10 +1439,10 @@ static inline int translate_one(DisasContext *ctx, uint32_t insn)
     fpfn = fn11 & 0x3F;
     fn7 = (insn >> 5) & 0x0000007F;
     fn2 = (insn >> 5) & 0x00000003;
-    ret = 0;
     LOG_DISAS("opc %02x ra %2d rb %2d rc %2d disp16 %6d\n",
               opc, ra, rb, rc, disp16);
 
+    ret = NO_EXIT;
     switch (opc) {
     case 0x00:
         /* CALL_PAL */

@@ -1386,7 +1460,8 @@ static inline int translate_one(DisasContext *ctx, uint32_t insn)
         if (palcode >= 0x80 && palcode < 0xC0) {
             /* Unprivileged PAL call */
             gen_excp(ctx, EXCP_CALL_PAL + ((palcode & 0x3F) << 6), 0);
-            ret = 3;
+            /* PC updated by gen_excp.  */
+            ret = EXIT_PC_UPDATED;
             break;
         }
 #ifndef CONFIG_USER_ONLY

@@ -1395,7 +1470,8 @@ static inline int translate_one(DisasContext *ctx, uint32_t insn)
             if (ctx->mem_idx & 1)
                 goto invalid_opc;
             gen_excp(ctx, EXCP_CALL_PALP + ((palcode & 0x3F) << 6), 0);
-            ret = 3;
+            /* PC updated by gen_excp.  */
+            ret = EXIT_PC_UPDATED;
         }
 #endif
         /* Invalid PAL call */

@@ -2398,13 +2474,11 @@ static inline int translate_one(DisasContext *ctx, uint32_t insn)
         switch ((uint16_t)disp16) {
         case 0x0000:
             /* TRAPB */
-            /* No-op. Just exit from the current tb */
-            ret = 2;
+            /* No-op.  */
             break;
         case 0x0400:
             /* EXCB */
-            /* No-op. Just exit from the current tb */
-            ret = 2;
+            /* No-op.  */
             break;
         case 0x4000:
             /* MB */

@@ -2468,21 +2542,7 @@ static inline int translate_one(DisasContext *ctx, uint32_t insn)
         if (ra != 31)
             tcg_gen_movi_i64(cpu_ir[ra], ctx->pc);
         /* Those four jumps only differ by the branch prediction hint */
-        switch (fn2) {
-        case 0x0:
-            /* JMP */
-            break;
-        case 0x1:
-            /* JSR */
-            break;
-        case 0x2:
-            /* RET */
-            break;
-        case 0x3:
-            /* JSR_COROUTINE */
-            break;
-        }
-        ret = 1;
+        ret = EXIT_PC_UPDATED;
         break;
     case 0x1B:
         /* HW_LD (PALcode) */

@@ -2773,7 +2833,7 @@ static inline int translate_one(DisasContext *ctx, uint32_t insn)
                 tcg_temp_free(tmp2);
             }
             tcg_temp_free(tmp1);
-            ret = 2;
+            ret = EXIT_PC_STALE;
         }
         break;
 #endif

@@ -2798,7 +2858,7 @@ static inline int translate_one(DisasContext *ctx, uint32_t insn)
             gen_helper_hw_ret(tmp);
             tcg_temp_free(tmp);
         }
-        ret = 2;
+        ret = EXIT_PC_UPDATED;
         break;
 #endif
     case 0x1F:

@@ -2959,85 +3019,66 @@ static inline int translate_one(DisasContext *ctx, uint32_t insn)
         break;
     case 0x30:
         /* BR */
-        if (ra != 31)
-            tcg_gen_movi_i64(cpu_ir[ra], ctx->pc);
-        tcg_gen_movi_i64(cpu_pc, ctx->pc + (int64_t)(disp21 << 2));
-        ret = 1;
+        ret = gen_bdirect(ctx, ra, disp21);
         break;
     case 0x31: /* FBEQ */
-        gen_fbcond(ctx, TCG_COND_EQ, ra, disp21);
-        ret = 1;
+        ret = gen_fbcond(ctx, TCG_COND_EQ, ra, disp21);
         break;
     case 0x32: /* FBLT */
-        gen_fbcond(ctx, TCG_COND_LT, ra, disp21);
-        ret = 1;
+        ret = gen_fbcond(ctx, TCG_COND_LT, ra, disp21);
         break;
     case 0x33: /* FBLE */
-        gen_fbcond(ctx, TCG_COND_LE, ra, disp21);
-        ret = 1;
+        ret = gen_fbcond(ctx, TCG_COND_LE, ra, disp21);
         break;
     case 0x34:
         /* BSR */
-        if (ra != 31)
-            tcg_gen_movi_i64(cpu_ir[ra], ctx->pc);
-        tcg_gen_movi_i64(cpu_pc, ctx->pc + (int64_t)(disp21 << 2));
-        ret = 1;
+        ret = gen_bdirect(ctx, ra, disp21);
         break;
     case 0x35: /* FBNE */
-        gen_fbcond(ctx, TCG_COND_NE, ra, disp21);
-        ret = 1;
+        ret = gen_fbcond(ctx, TCG_COND_NE, ra, disp21);
         break;
     case 0x36: /* FBGE */
-        gen_fbcond(ctx, TCG_COND_GE, ra, disp21);
-        ret = 1;
+        ret = gen_fbcond(ctx, TCG_COND_GE, ra, disp21);
         break;
     case 0x37: /* FBGT */
-        gen_fbcond(ctx, TCG_COND_GT, ra, disp21);
-        ret = 1;
+        ret = gen_fbcond(ctx, TCG_COND_GT, ra, disp21);
         break;
     case 0x38:
         /* BLBC */
-        gen_bcond(ctx, TCG_COND_EQ, ra, disp21, 1);
-        ret = 1;
+        ret = gen_bcond(ctx, TCG_COND_EQ, ra, disp21, 1);
         break;
     case 0x39:
         /* BEQ */
-        gen_bcond(ctx, TCG_COND_EQ, ra, disp21, 0);
-        ret = 1;
+        ret = gen_bcond(ctx, TCG_COND_EQ, ra, disp21, 0);
         break;
     case 0x3A:
         /* BLT */
-        gen_bcond(ctx, TCG_COND_LT, ra, disp21, 0);
-        ret = 1;
+        ret = gen_bcond(ctx, TCG_COND_LT, ra, disp21, 0);
         break;
     case 0x3B:
         /* BLE */
-        gen_bcond(ctx, TCG_COND_LE, ra, disp21, 0);
-        ret = 1;
+        ret = gen_bcond(ctx, TCG_COND_LE, ra, disp21, 0);
         break;
     case 0x3C:
         /* BLBS */
-        gen_bcond(ctx, TCG_COND_NE, ra, disp21, 1);
-        ret = 1;
+        ret = gen_bcond(ctx, TCG_COND_NE, ra, disp21, 1);
         break;
     case 0x3D:
         /* BNE */
-        gen_bcond(ctx, TCG_COND_NE, ra, disp21, 0);
-        ret = 1;
+        ret = gen_bcond(ctx, TCG_COND_NE, ra, disp21, 0);
         break;
     case 0x3E:
         /* BGE */
-        gen_bcond(ctx, TCG_COND_GE, ra, disp21, 0);
-        ret = 1;
+        ret = gen_bcond(ctx, TCG_COND_GE, ra, disp21, 0);
         break;
     case 0x3F:
         /* BGT */
-        gen_bcond(ctx, TCG_COND_GT, ra, disp21, 0);
-        ret = 1;
+        ret = gen_bcond(ctx, TCG_COND_GT, ra, disp21, 0);
         break;
     invalid_opc:
         gen_invalid(ctx);
-        ret = 3;
+        /* PC updated by gen_excp.  */
+        ret = EXIT_PC_UPDATED;
         break;
     }
 

@@ -3054,15 +3095,17 @@ static inline void gen_intermediate_code_internal(CPUState *env,
     uint16_t *gen_opc_end;
     CPUBreakpoint *bp;
     int j, lj = -1;
-    int ret;
+    ExitStatus ret;
     int num_insns;
     int max_insns;
 
     pc_start = tb->pc;
     gen_opc_end = gen_opc_buf + OPC_MAX_SIZE;
+
+    ctx.tb = tb;
+    ctx.env = env;
     ctx.pc = pc_start;
     ctx.amask = env->amask;
-    ctx.env = env;
 #if defined (CONFIG_USER_ONLY)
     ctx.mem_idx = 0;
 #else

@@ -3086,7 +3129,7 @@ static inline void gen_intermediate_code_internal(CPUState *env,
         max_insns = CF_COUNT_MASK;
 
     gen_icount_start();
-    for (ret = 0; ret == 0;) {
+    do {
         if (unlikely(!QTAILQ_EMPTY(&env->breakpoints))) {
             QTAILQ_FOREACH(bp, &env->breakpoints, entry) {
                 if (bp->pc == ctx.pc) {

@@ -3117,36 +3160,39 @@ static inline void gen_intermediate_code_internal(CPUState *env,
 
         ctx.pc += 4;
         ret = translate_one(ctxp, insn);
-        if (ret != 0)
-            break;
-        /* if we reach a page boundary or are single stepping, stop
-         * generation
-         */
-        if (env->singlestep_enabled) {
-            gen_excp(&ctx, EXCP_DEBUG, 0);
-            break;
-        }
 
-        if ((ctx.pc & (TARGET_PAGE_SIZE - 1)) == 0)
-            break;
-
-        if (gen_opc_ptr >= gen_opc_end)
-            break;
-
-        if (num_insns >= max_insns)
-            break;
-
-        if (singlestep) {
-            break;
+        if (ret == NO_EXIT) {
+            /* If we reach a page boundary, are single stepping,
+               or exhaust instruction count, stop generation.  */
+            if (env->singlestep_enabled) {
+                gen_excp(&ctx, EXCP_DEBUG, 0);
+                ret = EXIT_PC_UPDATED;
+            } else if ((ctx.pc & (TARGET_PAGE_SIZE - 1)) == 0
+                       || gen_opc_ptr >= gen_opc_end
+                       || num_insns >= max_insns
+                       || singlestep) {
+                ret = EXIT_PC_STALE;
+            }
         }
+    } while (ret == NO_EXIT);
+
+    if (tb->cflags & CF_LAST_IO) {
+        gen_io_end();
     }
-    if (ret != 1 && ret != 3) {
+
+    switch (ret) {
+    case EXIT_GOTO_TB:
+        break;
+    case EXIT_PC_STALE:
         tcg_gen_movi_i64(cpu_pc, ctx.pc);
+        /* FALLTHRU */
+    case EXIT_PC_UPDATED:
+        tcg_gen_exit_tb(0);
+        break;
+    default:
+        abort();
     }
-    if (tb->cflags & CF_LAST_IO)
-        gen_io_end();
-    /* Generate the return instruction */
-    tcg_gen_exit_tb(0);
+
     gen_icount_end(tb, num_insns);
     *gen_opc_ptr = INDEX_op_end;
     if (search_pc) {

@@ -3158,6 +3204,7 @@ static inline void gen_intermediate_code_internal(CPUState *env,
         tb->size = ctx.pc - pc_start;
         tb->icount = num_insns;
     }
+
 #ifdef DEBUG_DISAS
     if (qemu_loglevel_mask(CPU_LOG_TB_IN_ASM)) {
         qemu_log("IN: %s\n", lookup_symbol(pc_start));

index 2c29337..9ada94e 100644
@@ -74,7 +74,11 @@ typedef enum {
 
     /* We are exiting the TB, but have neither emitted a goto_tb, nor
        updated the PC for the next instruction to be executed.  */
-    EXIT_PC_STALE
+    EXIT_PC_STALE,
+
+    /* We are ending the TB with a noreturn function call, e.g. longjmp.
+       No following code will be executed.  */
+    EXIT_NORETURN,
 } ExitStatus;
 
 /* global register indexes */

@@ -134,7 +138,7 @@ static void alpha_translate_init(void)
     done_init = 1;
 }
 
-static inline void gen_excp(DisasContext *ctx, int exception, int error_code)
+static ExitStatus gen_excp(DisasContext *ctx, int exception, int error_code)
 {
     TCGv_i32 tmp1, tmp2;
 

@@ -144,11 +148,13 @@ static inline void gen_excp(DisasContext *ctx, int exception, int error_code)
     gen_helper_excp(tmp1, tmp2);
     tcg_temp_free_i32(tmp2);
     tcg_temp_free_i32(tmp1);
+
+    return EXIT_NORETURN;
 }
 
-static inline void gen_invalid(DisasContext *ctx)
+static inline ExitStatus gen_invalid(DisasContext *ctx)
 {
-    gen_excp(ctx, EXCP_OPCDEC, 0);
+    return gen_excp(ctx, EXCP_OPCDEC, 0);
 }
 
 static inline void gen_qemu_ldf(TCGv t0, TCGv t1, int flags)

@@ -1459,9 +1465,7 @@ static ExitStatus translate_one(DisasContext *ctx, uint32_t insn)
 #endif
         if (palcode >= 0x80 && palcode < 0xC0) {
             /* Unprivileged PAL call */
-            gen_excp(ctx, EXCP_CALL_PAL + ((palcode & 0x3F) << 6), 0);
-            /* PC updated by gen_excp.  */
-            ret = EXIT_PC_UPDATED;
+            ret = gen_excp(ctx, EXCP_CALL_PAL + ((palcode & 0x3F) << 6), 0);
             break;
         }
 #ifndef CONFIG_USER_ONLY

@@ -1469,9 +1473,7 @@ static ExitStatus translate_one(DisasContext *ctx, uint32_t insn)
             /* Privileged PAL code */
             if (ctx->mem_idx & 1)
                 goto invalid_opc;
-            gen_excp(ctx, EXCP_CALL_PALP + ((palcode & 0x3F) << 6), 0);
-            /* PC updated by gen_excp.  */
-            ret = EXIT_PC_UPDATED;
+            ret = gen_excp(ctx, EXCP_CALL_PALP + ((palcode & 0x3F) << 6), 0);
         }
 #endif
         /* Invalid PAL call */

@@ -3079,9 +3081,7 @@ static ExitStatus translate_one(DisasContext *ctx, uint32_t insn)
         ret = gen_bcond(ctx, TCG_COND_GT, ra, disp21, 0);
         break;
     invalid_opc:
-        gen_invalid(ctx);
-        /* PC updated by gen_excp.  */
-        ret = EXIT_PC_UPDATED;
+        ret = gen_invalid(ctx);
         break;
     }
 

@@ -3185,6 +3185,7 @@ static inline void gen_intermediate_code_internal(CPUState *env,
 
     switch (ret) {
     case EXIT_GOTO_TB:
+    case EXIT_NORETURN:
         break;
     case EXIT_PC_STALE:
         tcg_gen_movi_i64(cpu_pc, ctx.pc);

index c0cc261..1fdcdc1 100644
@@ -2348,6 +2348,51 @@ void cpu_loop(CPUM68KState *env)
 #endif /* TARGET_M68K */
 
 #ifdef TARGET_ALPHA
+static void do_store_exclusive(CPUAlphaState *env, int reg, int quad)
+{
+    target_ulong addr, val, tmp;
+    target_siginfo_t info;
+    int ret = 0;
+
+    addr = env->lock_addr;
+    tmp = env->lock_st_addr;
+    env->lock_addr = -1;
+    env->lock_st_addr = 0;
+
+    start_exclusive();
+    mmap_lock();
+
+    if (addr == tmp) {
+        if (quad ? get_user_s64(val, addr) : get_user_s32(val, addr)) {
+            goto do_sigsegv;
+        }
+
+        if (val == env->lock_value) {
+            tmp = env->ir[reg];
+            if (quad ? put_user_u64(tmp, addr) : put_user_u32(tmp, addr)) {
+                goto do_sigsegv;
+            }
+            ret = 1;
+        }
+    }
+    env->ir[reg] = ret;
+    env->pc += 4;
+
+    mmap_unlock();
+    end_exclusive();
+    return;
+
+ do_sigsegv:
+    mmap_unlock();
+    end_exclusive();
+
+    info.si_signo = TARGET_SIGSEGV;
+    info.si_errno = 0;
+    info.si_code = TARGET_SEGV_MAPERR;
+    info._sifields._sigfault._addr = addr;
+    queue_signal(env, TARGET_SIGSEGV, &info);
+}
+
 void cpu_loop (CPUState *env)
 {
     int trapnr;

@@ -2372,6 +2417,7 @@ void cpu_loop (CPUState *env)
             exit(1);
             break;
         case EXCP_ARITH:
+            env->lock_addr = -1;
             info.si_signo = TARGET_SIGFPE;
             info.si_errno = 0;
             info.si_code = TARGET_FPE_FLTINV;

@@ -2383,6 +2429,7 @@ void cpu_loop (CPUState *env)
             exit(1);
             break;
         case EXCP_DFAULT:
+            env->lock_addr = -1;
             info.si_signo = TARGET_SIGSEGV;
             info.si_errno = 0;
             info.si_code = 0;  /* ??? SEGV_MAPERR vs SEGV_ACCERR.  */

@@ -2406,6 +2453,7 @@ void cpu_loop (CPUState *env)
             exit(1);
             break;
         case EXCP_UNALIGN:
+            env->lock_addr = -1;
             info.si_signo = TARGET_SIGBUS;
             info.si_errno = 0;
             info.si_code = TARGET_BUS_ADRALN;

@@ -2414,6 +2462,7 @@ void cpu_loop (CPUState *env)
             break;
         case EXCP_OPCDEC:
         do_sigill:
+            env->lock_addr = -1;
             info.si_signo = TARGET_SIGILL;
             info.si_errno = 0;
             info.si_code = TARGET_ILL_ILLOPC;

@@ -2424,6 +2473,7 @@ void cpu_loop (CPUState *env)
             /* No-op.  Linux simply re-enables the FPU.  */
             break;
         case EXCP_CALL_PAL ... (EXCP_CALL_PALP - 1):
+            env->lock_addr = -1;
             switch ((trapnr >> 6) | 0x80) {
             case 0x80:
                 /* BPT */

@@ -2513,11 +2563,16 @@ void cpu_loop (CPUState *env)
         case EXCP_DEBUG:
             info.si_signo = gdb_handlesig (env, TARGET_SIGTRAP);
             if (info.si_signo) {
+                env->lock_addr = -1;
                 info.si_errno = 0;
                 info.si_code = TARGET_TRAP_BRKPT;
                 queue_signal(env, info.si_signo, &info);
             }
             break;
+        case EXCP_STL_C:
+        case EXCP_STQ_C:
+            do_store_exclusive(env, env->error_code, trapnr - EXCP_STL_C);
+            break;
         default:
             printf ("Unhandled trap: 0x%x\n", trapnr);
             cpu_dump_state(env, stderr, fprintf, 0);

index c397930..817504b 100644
@@ -355,11 +355,13 @@ struct CPUAlphaState {
     uint64_t ir[31];
     float64 fir[31];
     uint64_t pc;
-    uint64_t lock;
     uint32_t pcc[2];
     uint64_t ipr[IPR_LAST];
     uint64_t ps;
     uint64_t unique;
+    uint64_t lock_addr;
+    uint64_t lock_st_addr;
+    uint64_t lock_value;
     float_status fp_status;
     /* The following fields make up the FPCR, but in FP_STATUS format.  */
     uint8_t fpcr_exc_status;