Merge remote-tracking branch 'remotes/pmaydell/tags/pull-target-arm-20180515' into staging

target-arm queue:
 * Fix coverity nit in int_to_float code
 * Don't set Invalid for float-to-int(MAXINT)
 * Fix fp_status_f16 tininess before rounding
 * Add various missing insns from the v8.2-FP16 extension
 * Fix sqrt_f16 exception raising
 * sdcard: Correct CRC16 offset in sd_function_switch()
 * tcg: Optionally log FPU state in TCG -d cpu logging

# gpg: Signature made Tue 15 May 2018 15:06:09 BST
# gpg:                using RSA key 3C2525ED14360CDE
# gpg: Good signature from "Peter Maydell <peter.maydell@linaro.org>"
# gpg:                 aka "Peter Maydell <pmaydell@gmail.com>"
# gpg:                 aka "Peter Maydell <pmaydell@chiark.greenend.org.uk>"
# Primary key fingerprint: E1A5 C593 CD41 9DE2 8E83  15CF 3C25 25ED 1436 0CDE

* remotes/pmaydell/tags/pull-target-arm-20180515:
  tcg: Optionally log FPU state in TCG -d cpu logging
  sdcard: Correct CRC16 offset in sd_function_switch()
  target/arm: Fix sqrt_f16 exception raising
  target/arm: Implement FMOV (immediate) for fp16
  target/arm: Implement FCSEL for fp16
  target/arm: Implement FCMP for fp16
  target/arm: Implement FP data-processing (3 source) for fp16
  target/arm: Implement FP data-processing (2 source) for fp16
  target/arm: Introduce and use read_fp_hreg
  target/arm: Implement FCVT (scalar, fixed-point) for fp16
  target/arm: Implement FCVT (scalar, integer) for fp16
  target/arm: Early exit after unallocated_encoding in disas_fp_int_conv
  target/arm: Implement FMOV (general) for fp16
  target/arm: Fix fp_status_f16 tininess before rounding
  fpu/softfloat: Don't set Invalid for float-to-int(MAXINT)
  fpu/softfloat: int_to_float ensure r fully initialised

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

accel/tcg/cpu-exec.c

@@ -156,11 +156,14 @@ static inline tcg_target_ulong cpu_tb_exec(CPUState *cpu, TranslationBlock *itb)
     if (qemu_loglevel_mask(CPU_LOG_TB_CPU)
         && qemu_log_in_addr_range(itb->pc)) {
         qemu_log_lock();
+        int flags = 0;
+        if (qemu_loglevel_mask(CPU_LOG_TB_FPU)) {
+            flags |= CPU_DUMP_FPU;
+        }
 #if defined(TARGET_I386)
-        log_cpu_state(cpu, CPU_DUMP_CCOP);
-#else
-        log_cpu_state(cpu, 0);
+        flags |= CPU_DUMP_CCOP;
 #endif
+        log_cpu_state(cpu, flags);
         qemu_log_unlock();
     }
 #endif /* DEBUG_DISAS */

fpu/softfloat.c

@@ -1368,14 +1368,14 @@ static int64_t round_to_int_and_pack(FloatParts in, int rmode,
             r = UINT64_MAX;
         }
         if (p.sign) {
-            if (r < -(uint64_t) min) {
+            if (r <= -(uint64_t) min) {
                 return -r;
             } else {
                 s->float_exception_flags = orig_flags | float_flag_invalid;
                 return min;
             }
         } else {
-            if (r < max) {
+            if (r <= max) {
                 return r;
             } else {
                 s->float_exception_flags = orig_flags | float_flag_invalid;
@@ -1525,7 +1525,7 @@ FLOAT_TO_UINT(64, 64)
 
 static FloatParts int_to_float(int64_t a, float_status *status)
 {
-    FloatParts r;
+    FloatParts r = {};
     if (a == 0) {
         r.cls = float_class_zero;
         r.sign = false;

hw/sd/sd.c

@@ -787,7 +787,7 @@ static void sd_function_switch(SDState *sd, uint32_t arg)
         sd->data[14 + (i >> 1)] = new_func << ((i * 4) & 4);
     }
     memset(&sd->data[17], 0, 47);
-    stw_be_p(sd->data + 65, sd_crc16(sd->data, 64));
+    stw_be_p(sd->data + 64, sd_crc16(sd->data, 64));
 }
 
 static inline bool sd_wp_addr(SDState *sd, uint64_t addr)

include/qemu/log.h

@@ -44,6 +44,7 @@ static inline bool qemu_log_separate(void)
 #define CPU_LOG_PAGE       (1 << 14)
 /* LOG_TRACE (1 << 15) is defined in log-for-trace.h */
 #define CPU_LOG_TB_OP_IND  (1 << 16)
+#define CPU_LOG_TB_FPU     (1 << 17)
 
 /* Lock output for a series of related logs.  Since this is not needed
  * for a single qemu_log / qemu_log_mask / qemu_log_mask_and_addr, we

target/arm/cpu.c

@@ -324,6 +324,8 @@ static void arm_cpu_reset(CPUState *s)
                               &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);
 #ifndef CONFIG_USER_ONLY
     if (kvm_enabled()) {
         kvm_arm_reset_vcpu(cpu);

target/arm/helper-a64.c

@@ -85,6 +85,16 @@ static inline uint32_t float_rel_to_flags(int res)
     return flags;
 }
 
+uint64_t HELPER(vfp_cmph_a64)(float16 x, float16 y, void *fp_status)
+{
+    return float_rel_to_flags(float16_compare_quiet(x, y, fp_status));
+}
+
+uint64_t HELPER(vfp_cmpeh_a64)(float16 x, float16 y, void *fp_status)
+{
+    return float_rel_to_flags(float16_compare(x, y, fp_status));
+}
+
 uint64_t HELPER(vfp_cmps_a64)(float32 x, float32 y, void *fp_status)
 {
     return float_rel_to_flags(float32_compare_quiet(x, y, fp_status));

target/arm/helper-a64.h

@@ -19,6 +19,8 @@
 DEF_HELPER_FLAGS_2(udiv64, TCG_CALL_NO_RWG_SE, i64, i64, i64)
 DEF_HELPER_FLAGS_2(sdiv64, TCG_CALL_NO_RWG_SE, s64, s64, s64)
 DEF_HELPER_FLAGS_1(rbit64, TCG_CALL_NO_RWG_SE, i64, i64)
+DEF_HELPER_3(vfp_cmph_a64, i64, f16, f16, ptr)
+DEF_HELPER_3(vfp_cmpeh_a64, i64, f16, f16, ptr)
 DEF_HELPER_3(vfp_cmps_a64, i64, f32, f32, ptr)
 DEF_HELPER_3(vfp_cmpes_a64, i64, f32, f32, ptr)
 DEF_HELPER_3(vfp_cmpd_a64, i64, f64, f64, ptr)

target/arm/helper.c

@@ -11427,8 +11427,12 @@ VFP_CONV_FIX_A64(uq, s, 32, 64, uint64)
 #undef VFP_CONV_FIX_A64
 
 /* Conversion to/from f16 can overflow to infinity before/after scaling.
- * Therefore we convert to f64 (which does not round), scale,
- * and then convert f64 to f16 (which may round).
+ * Therefore we convert to f64, scale, and then convert f64 to f16; or
+ * vice versa for conversion to integer.
+ *
+ * For 16- and 32-bit integers, the conversion to f64 never rounds.
+ * For 64-bit integers, any integer that would cause rounding will also
+ * overflow to f16 infinity, so there is no double rounding problem.
  */
 
 static float16 do_postscale_fp16(float64 f, int shift, float_status *fpst)
@@ -11446,6 +11450,16 @@ float16 HELPER(vfp_ultoh)(uint32_t x, uint32_t shift, void *fpst)
     return do_postscale_fp16(uint32_to_float64(x, fpst), shift, fpst);
 }
 
+float16 HELPER(vfp_sqtoh)(uint64_t x, uint32_t shift, void *fpst)
+{
+    return do_postscale_fp16(int64_to_float64(x, fpst), shift, fpst);
+}
+
+float16 HELPER(vfp_uqtoh)(uint64_t x, uint32_t shift, void *fpst)
+{
+    return do_postscale_fp16(uint64_to_float64(x, fpst), shift, fpst);
+}
+
 static float64 do_prescale_fp16(float16 f, int shift, float_status *fpst)
 {
     if (unlikely(float16_is_any_nan(f))) {
@@ -11475,6 +11489,26 @@ uint32_t HELPER(vfp_touhh)(float16 x, uint32_t shift, void *fpst)
     return float64_to_uint16(do_prescale_fp16(x, shift, fpst), fpst);
 }
 
+uint32_t HELPER(vfp_toslh)(float16 x, uint32_t shift, void *fpst)
+{
+    return float64_to_int32(do_prescale_fp16(x, shift, fpst), fpst);
+}
+
+uint32_t HELPER(vfp_toulh)(float16 x, uint32_t shift, void *fpst)
+{
+    return float64_to_uint32(do_prescale_fp16(x, shift, fpst), fpst);
+}
+
+uint64_t HELPER(vfp_tosqh)(float16 x, uint32_t shift, void *fpst)
+{
+    return float64_to_int64(do_prescale_fp16(x, shift, fpst), fpst);
+}
+
+uint64_t HELPER(vfp_touqh)(float16 x, uint32_t shift, void *fpst)
+{
+    return float64_to_uint64(do_prescale_fp16(x, shift, fpst), fpst);
+}
+
 /* Set the current fp rounding mode and return the old one.
  * The argument is a softfloat float_round_ value.
  */

target/arm/helper.h

@@ -151,6 +151,10 @@ DEF_HELPER_3(vfp_touhd_round_to_zero, i64, f64, i32, ptr)
 DEF_HELPER_3(vfp_tould_round_to_zero, i64, f64, i32, ptr)
 DEF_HELPER_3(vfp_touhh, i32, f16, i32, ptr)
 DEF_HELPER_3(vfp_toshh, i32, f16, i32, ptr)
+DEF_HELPER_3(vfp_toulh, i32, f16, i32, ptr)
+DEF_HELPER_3(vfp_toslh, i32, f16, i32, ptr)
+DEF_HELPER_3(vfp_touqh, i64, f16, i32, ptr)
+DEF_HELPER_3(vfp_tosqh, i64, f16, i32, ptr)
 DEF_HELPER_3(vfp_toshs, i32, f32, i32, ptr)
 DEF_HELPER_3(vfp_tosls, i32, f32, i32, ptr)
 DEF_HELPER_3(vfp_tosqs, i64, f32, i32, ptr)
@@ -177,6 +181,8 @@ DEF_HELPER_3(vfp_ultod, f64, i64, i32, ptr)
 DEF_HELPER_3(vfp_uqtod, f64, i64, i32, ptr)
 DEF_HELPER_3(vfp_sltoh, f16, i32, i32, ptr)
 DEF_HELPER_3(vfp_ultoh, f16, i32, i32, ptr)
+DEF_HELPER_3(vfp_sqtoh, f16, i64, i32, ptr)
+DEF_HELPER_3(vfp_uqtoh, f16, i64, i32, ptr)
 
 DEF_HELPER_FLAGS_2(set_rmode, TCG_CALL_NO_RWG, i32, i32, ptr)
 DEF_HELPER_FLAGS_2(set_neon_rmode, TCG_CALL_NO_RWG, i32, i32, env)

util/log.c

@@ -256,6 +256,8 @@ const QEMULogItem qemu_log_items[] = {
       "show trace before each executed TB (lots of logs)" },
     { CPU_LOG_TB_CPU, "cpu",
       "show CPU registers before entering a TB (lots of logs)" },
+    { CPU_LOG_TB_FPU, "fpu",
+      "include FPU registers in the 'cpu' logging" },
     { CPU_LOG_MMU, "mmu",
       "log MMU-related activities" },
     { CPU_LOG_PCALL, "pcall",