@@ -176,6 +176,7 @@ enum {
#define FSR_DZM (1ULL << 24)
#define FSR_NXM (1ULL << 23)
#define FSR_TEM_MASK (FSR_NVM | FSR_OFM | FSR_UFM | FSR_DZM | FSR_NXM)
+#define FSR_TEM_SHIFT 23
#define FSR_NVA (1ULL << 9)
#define FSR_OFA (1ULL << 8)
@@ -183,6 +184,7 @@ enum {
#define FSR_DZA (1ULL << 6)
#define FSR_NXA (1ULL << 5)
#define FSR_AEXC_MASK (FSR_NVA | FSR_OFA | FSR_UFA | FSR_DZA | FSR_NXA)
+#define FSR_AEXC_SHIFT 5
#define FSR_NVC (1ULL << 4)
#define FSR_OFC (1ULL << 3)
@@ -464,7 +466,10 @@ struct CPUArchState {
target_ulong cond; /* conditional branch result (XXX: save it in a
temporary register when possible) */
- target_ulong fsr; /* FPU state register */
+ /* FPU State Register, in parts */
+ target_ulong fsr; /* rm, tem, aexc, fcc* */
+ uint32_t fsr_cexc_ftt; /* cexc, ftt */
+
CPU_DoubleU fpr[TARGET_DPREGS]; /* floating point registers */
uint32_t cwp; /* index of current register window (extracted
from PSR) */
@@ -36,7 +36,7 @@ DEF_HELPER_FLAGS_4(ld_asi, TCG_CALL_NO_WG, i64, env, tl, int, i32)
DEF_HELPER_FLAGS_5(st_asi, TCG_CALL_NO_WG, void, env, tl, i64, int, i32)
#endif
DEF_HELPER_FLAGS_1(get_fsr, TCG_CALL_NO_WG_SE, tl, env)
-DEF_HELPER_FLAGS_2(set_fsr, TCG_CALL_NO_RWG, void, env, tl)
+DEF_HELPER_FLAGS_2(set_fsr_noftt, 0, void, env, tl)
DEF_HELPER_FLAGS_2(fsqrts, 0, f32, env, f32)
DEF_HELPER_FLAGS_2(fsqrtd, 0, f64, env, f64)
DEF_HELPER_FLAGS_2(fsqrtq, 0, i128, env, i128)
@@ -48,9 +48,7 @@ static inline Int128 f128_ret(float128 f)
static void check_ieee_exceptions(CPUSPARCState *env, uintptr_t ra)
{
target_ulong status = get_float_exception_flags(&env->fp_status);
- target_ulong fsr = env->fsr;
-
- fsr &= FSR_FTT_CEXC_NMASK;
+ uint32_t cexc = 0;
if (unlikely(status)) {
/* Keep exception flags clear for next time. */
@@ -58,38 +56,33 @@ static void check_ieee_exceptions(CPUSPARCState *env, uintptr_t ra)
/* Copy IEEE 754 flags into FSR */
if (status & float_flag_invalid) {
- fsr |= FSR_NVC;
+ cexc |= FSR_NVC;
}
if (status & float_flag_overflow) {
- fsr |= FSR_OFC;
+ cexc |= FSR_OFC;
}
if (status & float_flag_underflow) {
- fsr |= FSR_UFC;
+ cexc |= FSR_UFC;
}
if (status & float_flag_divbyzero) {
- fsr |= FSR_DZC;
+ cexc |= FSR_DZC;
}
if (status & float_flag_inexact) {
- fsr |= FSR_NXC;
+ cexc |= FSR_NXC;
}
- if ((fsr & FSR_CEXC_MASK) & ((fsr & FSR_TEM_MASK) >> 23)) {
- CPUState *cs = env_cpu(env);
-
- /* Unmasked exception, generate a trap. Note that while
- the helper is marked as NO_WG, we can get away with
- writing to cpu state along the exception path, since
- TCG generated code will never see the write. */
- env->fsr = fsr | FSR_FTT_IEEE_EXCP;
- cs->exception_index = TT_FP_EXCP;
- cpu_loop_exit_restore(cs, ra);
- } else {
- /* Accumulate exceptions */
- fsr |= (fsr & FSR_CEXC_MASK) << 5;
+ if (cexc & (env->fsr >> FSR_TEM_SHIFT)) {
+ /* Unmasked exception, generate an IEEE trap. */
+ env->fsr_cexc_ftt = cexc | FSR_FTT_IEEE_EXCP;
+ cpu_raise_exception_ra(env, TT_FP_EXCP, ra);
}
+
+ /* Accumulate exceptions */
+ env->fsr |= cexc << FSR_AEXC_SHIFT;
}
- env->fsr = fsr;
+ /* No trap, so FTT is cleared. */
+ env->fsr_cexc_ftt = cexc;
}
float32 helper_fadds(CPUSPARCState *env, float32 src1, float32 src2)
@@ -456,7 +449,7 @@ GEN_FCMP(fcmpeq_fcc3, float128, 26, 1);
target_ulong cpu_get_fsr(CPUSPARCState *env)
{
- target_ulong fsr = env->fsr;
+ target_ulong fsr = env->fsr | env->fsr_cexc_ftt;
/* VER is kept completely separate until re-assembly. */
fsr |= env->def.fpu_version;
@@ -473,7 +466,7 @@ static void set_fsr_nonsplit(CPUSPARCState *env, target_ulong fsr)
{
int rnd_mode;
- env->fsr = fsr & ~FSR_VER_MASK;
+ env->fsr = fsr & ~(FSR_VER_MASK | FSR_CEXC_MASK | FSR_FTT_MASK);
switch (fsr & FSR_RD_MASK) {
case FSR_RD_NEAREST:
@@ -495,10 +488,13 @@ static void set_fsr_nonsplit(CPUSPARCState *env, target_ulong fsr)
void cpu_put_fsr(CPUSPARCState *env, target_ulong fsr)
{
+ env->fsr_cexc_ftt = fsr & (FSR_CEXC_MASK | FSR_FTT_MASK);
set_fsr_nonsplit(env, fsr);
}
-void helper_set_fsr(CPUSPARCState *env, target_ulong fsr)
+void helper_set_fsr_noftt(CPUSPARCState *env, target_ulong fsr)
{
+ env->fsr_cexc_ftt &= FSR_FTT_MASK;
+ env->fsr_cexc_ftt |= fsr & FSR_CEXC_MASK;
set_fsr_nonsplit(env, fsr);
}
@@ -1199,7 +1199,8 @@ static bool gen_compare_reg(DisasCompare *cmp, int cond, TCGv r_src)
static void gen_op_clear_ieee_excp_and_FTT(void)
{
- tcg_gen_andi_tl(cpu_fsr, cpu_fsr, FSR_FTT_CEXC_NMASK);
+ tcg_gen_st_i32(tcg_constant_i32(0), tcg_env,
+ offsetof(CPUSPARCState, fsr_cexc_ftt));
}
static void gen_op_fmovs(TCGv_i32 dst, TCGv_i32 src)
@@ -1400,10 +1401,15 @@ static void gen_op_fcmpeq(int fccno, TCGv_i128 r_rs1, TCGv_i128 r_rs2)
}
#endif
-static void gen_op_fpexception_im(DisasContext *dc, int fsr_flags)
+static void gen_op_fpexception_im(DisasContext *dc, int ftt)
{
- tcg_gen_andi_tl(cpu_fsr, cpu_fsr, FSR_FTT_NMASK);
- tcg_gen_ori_tl(cpu_fsr, cpu_fsr, fsr_flags);
+ /*
+ * CEXC is only set when succesfully completing an FPop,
+ * or when raising FSR_FTT_IEEE_EXCP, i.e. check_ieee_exception.
+ * Thus we can simply store FTT into this field.
+ */
+ tcg_gen_st_i32(tcg_constant_i32(ftt), tcg_env,
+ offsetof(CPUSPARCState, fsr_cexc_ftt));
gen_exception(dc, TT_FP_EXCP);
}
@@ -4395,19 +4401,22 @@ static bool trans_STDFQ(DisasContext *dc, arg_STDFQ *a)
static bool do_ldfsr(DisasContext *dc, arg_r_r_ri *a, MemOp mop,
target_ulong new_mask, target_ulong old_mask)
{
- TCGv tmp, addr = gen_ldst_addr(dc, a->rs1, a->imm, a->rs2_or_imm);
+ TCGv addr = gen_ldst_addr(dc, a->rs1, a->imm, a->rs2_or_imm);
+ TCGv tnew, told;
+
if (addr == NULL) {
return false;
}
if (gen_trap_ifnofpu(dc)) {
return true;
}
- tmp = tcg_temp_new();
- tcg_gen_qemu_ld_tl(tmp, addr, dc->mem_idx, mop | MO_ALIGN);
- tcg_gen_andi_tl(tmp, tmp, new_mask);
- tcg_gen_andi_tl(cpu_fsr, cpu_fsr, old_mask);
- tcg_gen_or_tl(cpu_fsr, cpu_fsr, tmp);
- gen_helper_set_fsr(tcg_env, cpu_fsr);
+ tnew = tcg_temp_new();
+ told = tcg_temp_new();
+ tcg_gen_qemu_ld_tl(tnew, addr, dc->mem_idx, mop | MO_ALIGN);
+ tcg_gen_andi_tl(tnew, tnew, new_mask);
+ tcg_gen_andi_tl(told, cpu_fsr, old_mask);
+ tcg_gen_or_tl(tnew, tnew, told);
+ gen_helper_set_fsr_noftt(tcg_env, tnew);
return advance_pc(dc);
}
These two fields are adjusted by all FPop insns. Having them separate makes it easier to set without masking. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/sparc/cpu.h | 7 +++++- target/sparc/helper.h | 2 +- target/sparc/fop_helper.c | 46 ++++++++++++++++++--------------------- target/sparc/translate.c | 31 ++++++++++++++++---------- 4 files changed, 48 insertions(+), 38 deletions(-)