[PATCH 5/5] target/i386: fix fscale handling of rounding precision

[Joseph Myers]

The fscale implementation uses floatx80_scalbn for the final scaling
operation.  floatx80_scalbn ends up rounding the result using the
dynamic rounding precision configured for the FPU.  But only a limited
set of x87 floating-point instructions are supposed to respect the
dynamic rounding precision, and fscale is not in that set.  Fix the
implementation to save and restore the rounding precision around the
call to floatx80_scalbn.

Signed-off-by: Joseph Myers <address@hidden>
---
 target/i386/fpu_helper.c          |  3 +++
 tests/tcg/i386/test-i386-fscale.c | 13 +++++++++++++
 2 files changed, 16 insertions(+)

diff --git a/target/i386/fpu_helper.c b/target/i386/fpu_helper.c
index d4c15728e1..0c3fce933c 100644
--- a/target/i386/fpu_helper.c
+++ b/target/i386/fpu_helper.c
@@ -1001,7 +1001,10 @@ void helper_fscale(CPUX86State *env)
         }
     } else {
         int n = floatx80_to_int32_round_to_zero(ST1, &env->fp_status);
+        signed char save = env->fp_status.floatx80_rounding_precision;
+        env->fp_status.floatx80_rounding_precision = 80;
         ST0 = floatx80_scalbn(ST0, n, &env->fp_status);
+        env->fp_status.floatx80_rounding_precision = save;
     }
 }
 
diff --git a/tests/tcg/i386/test-i386-fscale.c 
b/tests/tcg/i386/test-i386-fscale.c
index b953e7c563..d23b3cfeec 100644
--- a/tests/tcg/i386/test-i386-fscale.c
+++ b/tests/tcg/i386/test-i386-fscale.c
@@ -8,6 +8,8 @@ union u {
     long double ld;
 };
 
+volatile long double ld_third = 1.0L / 3.0L;
+volatile long double ld_four_thirds = 4.0L / 3.0L;
 volatile union u ld_invalid_1 = { .s = { 1, 1234 } };
 volatile union u ld_invalid_2 = { .s = { 0, 1234 } };
 volatile union u ld_invalid_3 = { .s = { 0, 0x7fff } };
@@ -91,5 +93,16 @@ int main(void)
         printf("FAIL: fscale finite down inf\n");
         ret = 1;
     }
+    /* Set round-to-nearest with single-precision rounding.  */
+    cw = cw & ~0xf00;
+    __asm__ volatile ("fldcw %0" : : "m" (cw));
+    __asm__ volatile ("fscale" : "=t" (ld_res) :
+                      "0" (ld_third), "u" (2.0L));
+    cw = cw | 0x300;
+    __asm__ volatile ("fldcw %0" : : "m" (cw));
+    if (ld_res != ld_four_thirds) {
+        printf("FAIL: fscale single-precision\n");
+        ret = 1;
+    }
     return ret;
 }
-- 
2.17.1


-- 
Joseph S. Myers
address@hidden