Merge remote-tracking branch 'remotes/stsquad/tags/pull-fpu-next-230119-2' into staging

Some more softfloat/fpu fixes

   - make check-softfloat
   - fixes for fp-bench
   - workaround broken host fma
   - compile fix for s390x/clang
   - fixed for bigendian (v2)
   - minor makefile tweaks (v2)

# gpg: Signature made Wed 23 Jan 2019 11:37:53 GMT
# gpg:                using RSA key FBD0DB095A9E2A44
# gpg: Good signature from "Alex Bennée (Master Work Key) <alex.bennee@linaro.org>"
# Primary key fingerprint: 6685 AE99 E751 67BC AFC8  DF35 FBD0 DB09 5A9E 2A44

* remotes/stsquad/tags/pull-fpu-next-230119-2:
  tests/Makefile: add check-softfloat rule
  scripts/archive-source: include softfloat tests
  tests/Makefile: add floating point tests
  include/fpu/softfloat: Fix compilation with Clang on s390x
  softfloat: enforce softfloat if the host's FMA is broken
  tests/fp/platform.h: include config-host.h
  fp-test: fix signature of slow_clear_flags and qemu_clear_flags
  tests/fp/Makefile: do not use gcc-only -W flags
  berkeley-testfloat-3: pull changes
  fp-bench: remove wrong exponent raise in fill_random
  fp-bench: fix update_random_ops

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

9 files changed, 182 insertions, 15 deletions

diff --git a/fpu/softfloat.c b/fpu/softfloat.c
index 59eac97d10..9132d7a0b0 100644
--- a/fpu/softfloat.c
+++ b/fpu/softfloat.c
@@ -1542,6 +1542,8 @@ soft_f64_muladd(float64 a, float64 b, float64 c, int flags,
     return float64_round_pack_canonical(pr, status);
 }
 
+static bool force_soft_fma;
+
 float32 QEMU_FLATTEN
 float32_muladd(float32 xa, float32 xb, float32 xc, int flags, float_status *s)
 {
@@ -1562,6 +1564,11 @@ float32_muladd(float32 xa, float32 xb, float32 xc, int flags, float_status *s)
     if (unlikely(!f32_is_zon3(ua, ub, uc))) {
         goto soft;
     }
+
+    if (unlikely(force_soft_fma)) {
+        goto soft;
+    }
+
     /*
      * When (a || b) == 0, there's no need to check for under/over flow,
      * since we know the addend is (normal || 0) and the product is 0.
@@ -1623,6 +1630,11 @@ float64_muladd(float64 xa, float64 xb, float64 xc, int flags, float_status *s)
     if (unlikely(!f64_is_zon3(ua, ub, uc))) {
         goto soft;
     }
+
+    if (unlikely(force_soft_fma)) {
+        goto soft;
+    }
+
     /*
      * When (a || b) == 0, there's no need to check for under/over flow,
      * since we know the addend is (normal || 0) and the product is 0.
@@ -7974,3 +7986,24 @@ float128 float128_scalbn(float128 a, int n, float_status *status)
                                          , status);
 
 }
+
+static void __attribute__((constructor)) softfloat_init(void)
+{
+    union_float64 ua, ub, uc, ur;
+
+    if (QEMU_NO_HARDFLOAT) {
+        return;
+    }
+    /*
+     * Test that the host's FMA is not obviously broken. For example,
+     * glibc < 2.23 can perform an incorrect FMA on certain hosts; see
+     *   https://sourceware.org/bugzilla/show_bug.cgi?id=13304
+     */
+    ua.s = 0x0020000000000001ULL;
+    ub.s = 0x3ca0000000000000ULL;
+    uc.s = 0x0020000000000000ULL;
+    ur.h = fma(ua.h, ub.h, uc.h);
+    if (ur.s != 0x0020000000000001ULL) {
+        force_soft_fma = true;
+    }
+}
diff --git a/include/fpu/softfloat-macros.h b/include/fpu/softfloat-macros.h
index b1d772e6d4..bd5b6418e3 100644
--- a/include/fpu/softfloat-macros.h
+++ b/include/fpu/softfloat-macros.h
@@ -641,7 +641,7 @@ static inline uint64_t udiv_qrnnd(uint64_t *r, uint64_t n1,
     uint64_t q;
     asm("divq %4" : "=a"(q), "=d"(*r) : "0"(n0), "1"(n1), "rm"(d));
     return q;
-#elif defined(__s390x__)
+#elif defined(__s390x__) && !defined(__clang__)
     /* Need to use a TImode type to get an even register pair for DLGR.  */
     unsigned __int128 n = (unsigned __int128)n1 << 64 | n0;
     asm("dlgr %0, %1" : "+r"(n) : "r"(d));
diff --git a/scripts/archive-source.sh b/scripts/archive-source.sh
index 62bd22578b..6eed2a29bd 100755
--- a/scripts/archive-source.sh
+++ b/scripts/archive-source.sh
@@ -26,7 +26,7 @@ vroot_dir="${tar_file}.vroot"
 # independent of what the developer currently has initialized
 # in their checkout, because the build environment is completely
 # different to the host OS.
-submodules="dtc ui/keycodemapdb"
+submodules="dtc ui/keycodemapdb tests/fp/berkeley-softfloat-3 tests/fp/berkeley-testfloat-3"
 
 trap "status=$?; rm -rf \"$list_file\" \"$vroot_dir\"; exit \$status" 0 1 2 3 15
 
diff --git a/tests/Makefile.include b/tests/Makefile.include
index 4eea38ae99..f5e6eb5152 100644
--- a/tests/Makefile.include
+++ b/tests/Makefile.include
@@ -12,6 +12,7 @@ check-help:
 	@echo " $(MAKE) check-qapi-schema    Run QAPI schema tests"
 	@echo " $(MAKE) check-block          Run block tests"
 	@echo " $(MAKE) check-tcg            Run TCG tests"
+	@echo " $(MAKE) check-softfloat      Run FPU emulation tests"
 	@echo " $(MAKE) check-acceptance     Run all acceptance (functional) tests"
 	@echo
 	@echo " $(MAKE) check-report.html    Generates an HTML test report"
@@ -880,6 +881,138 @@ check-report-unit.tap: $(check-unit-y)
 check-report.tap: $(patsubst %,check-report-qtest-%.tap, $(QTEST_TARGETS)) check-report-unit.tap
 	$(call quiet-command,./scripts/tap-merge.py $^ > $@,"GEN","$@")
 
+# FPU Emulation tests (aka softfloat)
+#
+# As we still have some places that need fixing the rules are a little
+# more complex than they need to be and have to override some of the
+# generic Makefile expansions. Once we are cleanly passing all
+# the tests we can simplify the make syntax.
+
+FP_TEST_BIN=$(BUILD_DIR)/tests/fp/fp-test
+
+# the build dir is created by configure
+.PHONY: $(FP_TEST_BIN)
+$(FP_TEST_BIN):
+	$(call quiet-command, \
+	 	$(MAKE) $(SUBDIR_MAKEFLAGS) -C $(dir $@) V="$(V)" $(notdir $@), \
+	         "BUILD", "$(notdir $@)")
+
+# The full test suite can take a bit of time, default to a quick run
+ifeq ($(SPEED), quick)
+FP_TL=-l 1
+else
+FP_TL=-l 2 -r all
+endif
+
+# $1 = tests, $2 = description
+test-softfloat = $(call quiet-command, \
+			cd $(BUILD_DIR)/tests/fp && \
+			./fp-test -s $(FP_TL) $1 > $2.out 2>&1 || \
+			(cat $2.out && exit 1;), \
+			"FLOAT TEST", $2)
+
+# Conversion Routines:
+# FIXME: i32_to_extF80 (broken), i64_to_extF80 (broken)
+#        ui32_to_f128 (not implemented), f128_to_ui32 (not implemented)
+#        extF80_roundToInt (broken)
+#
+check-softfloat-conv: $(FP_TEST_BIN)
+	$(call test-softfloat, \
+		i32_to_f16 i64_to_f16 \
+		i32_to_f32 i64_to_f32 \
+		i32_to_f64 i64_to_f64 \
+		i32_to_f128 i64_to_f128, int-to-float)
+	$(call test-softfloat, \
+		ui32_to_f16 ui64_to_f16 \
+		ui32_to_f32 ui64_to_f32 \
+		ui32_to_f64 ui64_to_f64 \
+		ui64_to_f128, uint-to-float)
+	$(call test-softfloat, \
+		f16_to_i32 f16_to_i32_r_minMag \
+		f32_to_i32 f32_to_i32_r_minMag \
+		f64_to_i32 f64_to_i32_r_minMag \
+		extF80_to_i32 extF80_to_i32_r_minMag \
+		f128_to_i32 f128_to_i32_r_minMag \
+		f16_to_i64 f16_to_i64_r_minMag \
+		f32_to_i64 f32_to_i64_r_minMag \
+		f64_to_i64 f64_to_i64_r_minMag \
+		extF80_to_i64 extF80_to_i64_r_minMag \
+		f128_to_i64 f128_to_i64_r_minMag, \
+		float-to-int)
+	$(call test-softfloat, \
+		f16_to_ui32 f16_to_ui32_r_minMag \
+		f32_to_ui32 f32_to_ui32_r_minMag \
+		f64_to_ui32 f64_to_ui32_r_minMag \
+		f16_to_ui64 f16_to_ui64_r_minMag \
+		f32_to_ui64 f32_to_ui64_r_minMag \
+		f64_to_ui64 f64_to_ui64_r_minMag, \
+		float-to-uint)
+	$(call test-softfloat, \
+		f16_roundToInt f32_roundToInt \
+		f64_roundToInt f128_roundToInt, \
+		round-to-integer)
+
+# Generic rule for all float operations
+#
+# Some patterns are overidden due to broken or missing tests.
+# Hopefully these can be removed over time.
+
+check-softfloat-%: $(FP_TEST_BIN)
+	$(call test-softfloat, f16_$* f32_$* f64_$* extF80_$* f128_$*, $*)
+
+# Float Compare routines
+SF_COMPARE_OPS=eq eq_signaling le le_quiet lt_quiet
+SF_COMPARE_RULES=$(patsubst %,check-softfloat-%, $(SF_COMPARE_OPS))
+
+# FIXME: extF80_le_quiet (broken)
+check-softfloat-le_quiet: $(FP_TEST_BIN)
+	$(call test-softfloat, 				\
+		f16_le_quiet f32_le_quiet f64_le_quiet  \
+		f128_le_quiet, 				\
+		le_quiet)
+
+# FIXME: extF80_lt_quiet (broken)
+check-softfloat-lt_quiet: $(FP_TEST_BIN)
+	$(call test-softfloat, 				\
+		f16_lt_quiet f32_lt_quiet f64_lt_quiet  \
+		f128_lt_quiet, 				\
+		lt_quiet)
+
+.PHONY: check-softfloat-compare
+check-softfloat-compare: $(SF_COMPARE_RULES)
+
+# Math Operations
+
+# FIXME: extF80_mulAdd (missing)
+check-softfloat-mulAdd: $(FP_TEST_BIN)
+	$(call test-softfloat, \
+		f16_mulAdd f32_mulAdd f64_mulAdd f128_mulAdd, \
+		mulAdd)
+
+# FIXME: extF80_rem (broken)
+check-softfloat-rem: $(FP_TEST_BIN)
+	$(call test-softfloat, \
+		f16_rem f32_rem f64_rem f128_rem, \
+		rem)
+
+SF_MATH_OPS=add sub mul mulAdd div rem sqrt
+SF_MATH_RULES=$(patsubst %,check-softfloat-%, $(SF_MATH_OPS))
+
+.PHONY: check-softfloat-ops
+check-softfloat-ops: $(SF_MATH_RULES)
+
+# Finally a generic rule to test all of softfoat. If TCG isnt't
+# enabled we define a null operation which skips the tests.
+
+.PHONY: check-softfloat
+ifeq ($(CONFIG_TCG),y)
+check-softfloat: check-softfloat-conv check-softfloat-compare check-softfloat-ops
+else
+check-softfloat:
+	$(call quiet-command, /bin/true, "FLOAT TEST", \
+		"SKIPPED for non-TCG builds")
+endif
+
 # Per guest TCG tests
 
 LINUX_USER_TARGETS=$(filter %-linux-user,$(TARGET_DIRS))
@@ -912,7 +1045,7 @@ clean-tcg-tests-%:
 build-tcg: $(BUILD_TCG_TARGET_RULES)
 
 .PHONY: check-tcg
-check-tcg: $(RUN_TCG_TARGET_RULES)
+check-tcg: check-softfloat $(RUN_TCG_TARGET_RULES)
 
 .PHONY: clean-tcg
 clean-tcg: $(CLEAN_TCG_TARGET_RULES)
@@ -993,7 +1126,7 @@ check-acceptance: check-venv $(TESTS_RESULTS_DIR)
 check-qapi-schema: $(patsubst %,check-%, $(check-qapi-schema-y)) check-tests/qapi-schema/doc-good.texi
 check-qtest: $(patsubst %,check-qtest-%, $(QTEST_TARGETS))
 check-block: $(patsubst %,check-%, $(check-block-y))
-check: check-qapi-schema check-unit check-qtest check-decodetree
+check: check-qapi-schema check-unit check-softfloat check-qtest check-decodetree
 check-clean:
 	rm -rf $(check-unit-y) tests/*.o $(QEMU_IOTESTS_HELPERS-y)
 	rm -rf $(sort $(foreach target,$(SYSEMU_TARGET_LIST), $(check-qtest-$(target)-y)) $(check-qtest-generic-y))
diff --git a/tests/fp/Makefile b/tests/fp/Makefile
index 5019dcdca0..5a35e7c210 100644
--- a/tests/fp/Makefile
+++ b/tests/fp/Makefile
@@ -65,8 +65,7 @@ QEMU_CFLAGS += $(TF_OPTS)
 TF_CFLAGS :=
 TF_CFLAGS += -Wno-strict-prototypes
 TF_CFLAGS += -Wno-unknown-pragmas
-TF_CFLAGS += -Wno-discarded-qualifiers
-TF_CFLAGS += -Wno-maybe-uninitialized
+TF_CFLAGS += -Wno-uninitialized
 TF_CFLAGS += -Wno-missing-prototypes
 TF_CFLAGS += -Wno-return-type
 TF_CFLAGS += -Wno-unused-function
diff --git a/tests/fp/berkeley-testfloat-3 b/tests/fp/berkeley-testfloat-3
-Subproject ca9fa2ba05625ba929958f163b01747e07dd39c
+Subproject 5a59dcec19327396a011a17fd924aed4fec416b
diff --git a/tests/fp/fp-bench.c b/tests/fp/fp-bench.c
index f5bc5edebf..4ba5e1d2d4 100644
--- a/tests/fp/fp-bench.c
+++ b/tests/fp/fp-bench.c
@@ -143,15 +143,20 @@ static void update_random_ops(int n_ops, enum precision prec)
     for (i = 0; i < n_ops; i++) {
         uint64_t r = random_ops[i];
 
-        if (prec == PREC_SINGLE || PREC_FLOAT32) {
+        switch (prec) {
+        case PREC_SINGLE:
+        case PREC_FLOAT32:
             do {
                 r = xorshift64star(r);
             } while (!float32_is_normal(r));
-        } else if (prec == PREC_DOUBLE || PREC_FLOAT64) {
+            break;
+        case PREC_DOUBLE:
+        case PREC_FLOAT64:
             do {
                 r = xorshift64star(r);
             } while (!float64_is_normal(r));
-        } else {
+            break;
+        default:
             g_assert_not_reached();
         }
         random_ops[i] = r;
@@ -171,8 +176,6 @@ static void fill_random(union fp *ops, int n_ops, enum precision prec,
             if (no_neg && float32_is_neg(ops[i].f32)) {
                 ops[i].f32 = float32_chs(ops[i].f32);
             }
-            /* raise the exponent to limit the frequency of denormal results */
-            ops[i].f32 |= 0x40000000;
             break;
         case PREC_DOUBLE:
         case PREC_FLOAT64:
@@ -180,8 +183,6 @@ static void fill_random(union fp *ops, int n_ops, enum precision prec,
             if (no_neg && float64_is_neg(ops[i].f64)) {
                 ops[i].f64 = float64_chs(ops[i].f64);
             }
-            /* raise the exponent to limit the frequency of denormal results */
-            ops[i].f64 |= LIT64(0x4000000000000000);
             break;
         default:
             g_assert_not_reached();
diff --git a/tests/fp/fp-test.c b/tests/fp/fp-test.c
index fca576309c..2a35ef601d 100644
--- a/tests/fp/fp-test.c
+++ b/tests/fp/fp-test.c
@@ -789,7 +789,7 @@ static int set_init_flags(const char *flags)
     return 0;
 }
 
-static uint8_t slow_clear_flags(void)
+static uint_fast8_t slow_clear_flags(void)
 {
     uint8_t prev = slowfloat_exceptionFlags;
 
@@ -797,7 +797,7 @@ static uint8_t slow_clear_flags(void)
     return prev;
 }
 
-static uint8_t qemu_clear_flags(void)
+static uint_fast8_t qemu_clear_flags(void)
 {
     uint8_t prev = qemu_flags_to_sf(qsf.float_exception_flags);
 
diff --git a/tests/fp/platform.h b/tests/fp/platform.h
index f8c423dde3..c20ba70baa 100644
--- a/tests/fp/platform.h
+++ b/tests/fp/platform.h
@@ -29,6 +29,7 @@
  * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
  * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  */
+#include "config-host.h"
 
 #ifndef HOST_WORDS_BIGENDIAN
 #define LITTLEENDIAN 1