target/arm: Implement FPST_STD_F16 fpstatus

Architecturally, Neon FP16 operations use the "standard FPSCR" like
all other Neon operations.  However, this is defined in the Arm ARM
pseudocode as "a fixed value, except that FZ16 (and AHP) follow the
FPSCR bits". In QEMU, the softfloat float_status doesn't include
separate flush-to-zero for FP16 operations, so we must keep separate
fp_status for "Neon non-FP16" and "Neon fp16" operations, in the
same way we do already for the non-Neon "fp_status" vs "fp_status_f16".

Add the extra float_status field to the CPU state structure,
ensure it is correctly initialized and updated on FPSCR writes,
and make fpstatus_ptr(FPST_STD_F16) return a pointer to it.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20200806104453.30393-4-peter.maydell@linaro.org

4 files changed, 18 insertions, 2 deletions

diff --git a/target/arm/cpu.c b/target/arm/cpu.c
index 111579554f..6b382fcd60 100644
--- a/target/arm/cpu.c
+++ b/target/arm/cpu.c
@@ -391,12 +391,15 @@ static void arm_cpu_reset(DeviceState *dev)
     set_flush_to_zero(1, &env->vfp.standard_fp_status);
     set_flush_inputs_to_zero(1, &env->vfp.standard_fp_status);
     set_default_nan_mode(1, &env->vfp.standard_fp_status);
+    set_default_nan_mode(1, &env->vfp.standard_fp_status_f16);
     set_float_detect_tininess(float_tininess_before_rounding,
                               &env->vfp.fp_status);
     set_float_detect_tininess(float_tininess_before_rounding,
                               &env->vfp.standard_fp_status);
     set_float_detect_tininess(float_tininess_before_rounding,
                               &env->vfp.fp_status_f16);
+    set_float_detect_tininess(float_tininess_before_rounding,
+                              &env->vfp.standard_fp_status_f16);
 #ifndef CONFIG_USER_ONLY
     if (kvm_enabled()) {
         kvm_arm_reset_vcpu(cpu);
diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index 9d2845c179..ac857bdc2c 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -609,6 +609,8 @@ typedef struct CPUARMState {
          *  fp_status: is the "normal" fp status.
          *  fp_status_fp16: used for half-precision calculations
          *  standard_fp_status : the ARM "Standard FPSCR Value"
+         *  standard_fp_status_fp16 : used for half-precision
+         *       calculations with the ARM "Standard FPSCR Value"
          *
          * Half-precision operations are governed by a separate
          * flush-to-zero control bit in FPSCR:FZ16. We pass a separate
@@ -619,15 +621,20 @@ typedef struct CPUARMState {
          * Neon) which the architecture defines as controlled by the
          * standard FPSCR value rather than the FPSCR.
          *
+         * The "standard FPSCR but for fp16 ops" is needed because
+         * the "standard FPSCR" tracks the FPSCR.FZ16 bit rather than
+         * using a fixed value for it.
+         *
          * To avoid having to transfer exception bits around, we simply
          * say that the FPSCR cumulative exception flags are the logical
-         * OR of the flags in the three fp statuses. This relies on the
+         * OR of the flags in the four fp statuses. This relies on the
          * only thing which needs to read the exception flags being
          * an explicit FPSCR read.
          */
         float_status fp_status;
         float_status fp_status_f16;
         float_status standard_fp_status;
+        float_status standard_fp_status_f16;
 
         /* ZCR_EL[1-3] */
         uint64_t zcr_el[4];
diff --git a/target/arm/translate.h b/target/arm/translate.h
index e3680e6547..6d6d4c0f42 100644
--- a/target/arm/translate.h
+++ b/target/arm/translate.h
@@ -436,7 +436,8 @@ static inline TCGv_ptr fpstatus_ptr(ARMFPStatusFlavour flavour)
         offset = offsetof(CPUARMState, vfp.standard_fp_status);
         break;
     case FPST_STD_F16:
-        /* Not yet used or implemented: fall through to assert */
+        offset = offsetof(CPUARMState, vfp.standard_fp_status_f16);
+        break;
     default:
         g_assert_not_reached();
     }
diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c
index 60dcd4bf14..64266ece62 100644
--- a/target/arm/vfp_helper.c
+++ b/target/arm/vfp_helper.c
@@ -93,6 +93,8 @@ static uint32_t vfp_get_fpscr_from_host(CPUARMState *env)
     /* FZ16 does not generate an input denormal exception.  */
     i |= (get_float_exception_flags(&env->vfp.fp_status_f16)
           & ~float_flag_input_denormal);
+    i |= (get_float_exception_flags(&env->vfp.standard_fp_status_f16)
+          & ~float_flag_input_denormal);
     return vfp_exceptbits_from_host(i);
 }
 
@@ -124,7 +126,9 @@ static void vfp_set_fpscr_to_host(CPUARMState *env, uint32_t val)
     if (changed & FPCR_FZ16) {
         bool ftz_enabled = val & FPCR_FZ16;
         set_flush_to_zero(ftz_enabled, &env->vfp.fp_status_f16);
+        set_flush_to_zero(ftz_enabled, &env->vfp.standard_fp_status_f16);
         set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status_f16);
+        set_flush_inputs_to_zero(ftz_enabled, &env->vfp.standard_fp_status_f16);
     }
     if (changed & FPCR_FZ) {
         bool ftz_enabled = val & FPCR_FZ;
@@ -146,6 +150,7 @@ static void vfp_set_fpscr_to_host(CPUARMState *env, uint32_t val)
     set_float_exception_flags(i, &env->vfp.fp_status);
     set_float_exception_flags(0, &env->vfp.fp_status_f16);
     set_float_exception_flags(0, &env->vfp.standard_fp_status);
+    set_float_exception_flags(0, &env->vfp.standard_fp_status_f16);
 }
 
 #else