The Intel SDM section 10.2.3.3 on the MXCSR.FTZ bit says that we
flush outputs to zero when we detect underflow, which is after
rounding.  Set the detect_ftz flag accordingly.

This allows us to enable the test in fma.c which checks this
behaviour.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/i386/tcg/fpu_helper.c | 8 ++++----
 tests/tcg/x86_64/fma.c       | 5 -----
 2 files changed, 4 insertions(+), 9 deletions(-)

diff --git a/target/i386/tcg/fpu_helper.c b/target/i386/tcg/fpu_helper.c
index f112c6c6737..87fbc149d84 100644
--- a/target/i386/tcg/fpu_helper.c
+++ b/target/i386/tcg/fpu_helper.c
@@ -189,13 +189,13 @@ void cpu_init_fp_statuses(CPUX86State *env)
     set_float_default_nan_pattern(0b11000000, &env->mmx_status);
     set_float_default_nan_pattern(0b11000000, &env->sse_status);
     /*
-     * TODO: x86 does flush-to-zero detection after rounding (the SDM
+     * x86 does flush-to-zero detection after rounding (the SDM
      * section 10.2.3.3 on the FTZ bit of MXCSR says that we flush
      * when we detect underflow, which x86 does after rounding).
      */
-    set_float_ftz_detection(float_ftz_before_rounding, &env->fp_status);
-    set_float_ftz_detection(float_ftz_before_rounding, &env->mmx_status);
-    set_float_ftz_detection(float_ftz_before_rounding, &env->sse_status);
+    set_float_ftz_detection(float_ftz_after_rounding, &env->fp_status);
+    set_float_ftz_detection(float_ftz_after_rounding, &env->mmx_status);
+    set_float_ftz_detection(float_ftz_after_rounding, &env->sse_status);
 }
 
 static inline uint8_t save_exception_flags(CPUX86State *env)
diff --git a/tests/tcg/x86_64/fma.c b/tests/tcg/x86_64/fma.c
index 09c622ebc00..46f863005ed 100644
--- a/tests/tcg/x86_64/fma.c
+++ b/tests/tcg/x86_64/fma.c
@@ -79,14 +79,9 @@ static testdata tests[] = {
     /*
      * Flushing of denormal outputs to zero should also happen after
      * rounding, so setting FTZ should not affect the result or the flags.
-     * QEMU currently does not emulate this correctly because we do the
-     * flush-to-zero check before rounding, so we incorrectly produce a
-     * zero result and set Underflow as well as Precision.
      */
-#ifdef ENABLE_FAILING_TESTS
     { 0x3fdfffffffffffff, 0x001fffffffffffff, 0x801fffffffffffff, true,
       0x8010000000000000, 0x20 }, /* Enabling FTZ shouldn't change flags */
-#endif
 };
 
 int main(void)
-- 
2.43.0