SH4: Implement FD bit

SH4 manual say that if a floating point instruction is executed while
FD bit in the status register is 1, an exception should be raised. QEMU
presently does not do that, so the kernel does not initialize FP state
for any thread, nor does it save/restore FP state. The most apparent
consequence is that while recent gcc/libc expect double-precision mode
to be set by kernel, they run in single-precision mode, and all FP code
produces wrong values.

This patch fixes this. It also fixes a couple of places where PC was
not updated before handling an exception, although both those places
deal with invalid instruction and don't lead to any user-visible bugs.

(Vladimir Prus)

git-svn-id: svn://svn.savannah.nongnu.org/qemu/trunk@5937 c046a42c-6fe2-441c-8c8c-71466251a162

target-sh4/cpu.h

@@ -279,7 +279,8 @@ static inline void cpu_get_tb_cpu_state(CPUState *env, target_ulong *pc,
     *flags = (env->flags & (DELAY_SLOT | DELAY_SLOT_CONDITIONAL
                     | DELAY_SLOT_TRUE | DELAY_SLOT_CLEARME))   /* Bits  0- 3 */
             | (env->fpscr & (FPSCR_FR | FPSCR_SZ | FPSCR_PR))  /* Bits 19-21 */
-            | (env->sr & (SR_MD | SR_RB));                     /* Bits 29-30 */
+            | (env->sr & (SR_MD | SR_RB))                      /* Bits 29-30 */
+            | (env->sr & SR_FD);                               /* Bit 15 */
 }
 
 #endif				/* _CPU_SH4_H */

target-sh4/helper.h

@@ -3,6 +3,8 @@
 DEF_HELPER_0(ldtlb, void)
 DEF_HELPER_0(raise_illegal_instruction, void)
 DEF_HELPER_0(raise_slot_illegal_instruction, void)
+DEF_HELPER_0(raise_fpu_disable, void)
+DEF_HELPER_0(raise_slot_fpu_disable, void)
 DEF_HELPER_0(debug, void)
 DEF_HELPER_1(sleep, void, i32)
 DEF_HELPER_1(trapa, void, i32)

target-sh4/op_helper.c

@@ -89,6 +89,18 @@ void helper_raise_slot_illegal_instruction(void)
     cpu_loop_exit();
 }
 
+void helper_raise_fpu_disable(void)
+{
+  env->exception_index = 0x800;
+  cpu_loop_exit();
+}
+
+void helper_raise_slot_fpu_disable(void)
+{
+  env->exception_index = 0x820;
+  cpu_loop_exit();
+}
+
 void helper_debug(void)
 {
     env->exception_index = EXCP_DEBUG;

target-sh4/translate.c

@@ -447,17 +447,35 @@ static inline void gen_store_fpr64 (TCGv_i64 t, int reg)
 #define DREG(x) FREG(x) /* Assumes lsb of (x) is always 0 */
 
 #define CHECK_NOT_DELAY_SLOT \
-  if (ctx->flags & (DELAY_SLOT | DELAY_SLOT_CONDITIONAL)) \
-  {gen_helper_raise_slot_illegal_instruction(); ctx->bstate = BS_EXCP; \
-   return;}
+  if (ctx->flags & (DELAY_SLOT | DELAY_SLOT_CONDITIONAL))     \
+  {                                                           \
+      tcg_gen_movi_i32(cpu_pc, ctx->pc-2);                    \
+      gen_helper_raise_slot_illegal_instruction();            \
+      ctx->bstate = BS_EXCP;                                  \
+      return;                                                 \
+  }
 
 #define CHECK_PRIVILEGED                                      \
   if (IS_USER(ctx)) {                                         \
+      tcg_gen_movi_i32(cpu_pc, ctx->pc);                      \
       gen_helper_raise_illegal_instruction();                 \
       ctx->bstate = BS_EXCP;                                  \
       return;                                                 \
   }
 
+#define CHECK_FPU_ENABLED                                       \
+  if (ctx->flags & SR_FD) {                                     \
+      if (ctx->flags & (DELAY_SLOT | DELAY_SLOT_CONDITIONAL)) { \
+          tcg_gen_movi_i32(cpu_pc, ctx->pc-2);                  \
+          gen_helper_raise_slot_fpu_disable();                  \
+      } else {                                                  \
+          tcg_gen_movi_i32(cpu_pc, ctx->pc);                    \
+          gen_helper_raise_fpu_disable();                       \
+      }                                                         \
+      ctx->bstate = BS_EXCP;                                    \
+      return;                                                   \
+  }
+
 static void _decode_opc(DisasContext * ctx)
 {
 #if 0
@@ -1454,12 +1472,14 @@ static void _decode_opc(DisasContext * ctx)
 	LDST(mach, 0x400a, 0x4006, 0x000a, 0x4002, {})
 	LDST(macl, 0x401a, 0x4016, 0x001a, 0x4012, {})
 	LDST(pr,   0x402a, 0x4026, 0x002a, 0x4022, {})
-	LDST(fpul, 0x405a, 0x4056, 0x005a, 0x4052, {})
+	LDST(fpul, 0x405a, 0x4056, 0x005a, 0x4052, {CHECK_FPU_ENABLED})
     case 0x406a:		/* lds Rm,FPSCR */
+	CHECK_FPU_ENABLED
 	gen_helper_ld_fpscr(REG(B11_8));
 	ctx->bstate = BS_STOP;
 	return;
     case 0x4066:		/* lds.l @Rm+,FPSCR */
+	CHECK_FPU_ENABLED
 	{
 	    TCGv addr = tcg_temp_new();
 	    tcg_gen_qemu_ld32s(addr, REG(B11_8), ctx->memidx);
@@ -1470,9 +1490,11 @@ static void _decode_opc(DisasContext * ctx)
 	}
 	return;
     case 0x006a:		/* sts FPSCR,Rn */
+	CHECK_FPU_ENABLED
 	tcg_gen_andi_i32(REG(B11_8), cpu_fpscr, 0x003fffff);
 	return;
     case 0x4062:		/* sts FPSCR,@-Rn */
+	CHECK_FPU_ENABLED
 	{
 	    TCGv addr, val;
 	    val = tcg_temp_new();