target/i386: fix floating-point load-constant rounding

The implementations of the fldl2t, fldl2e, fldpi, fldlg2 and fldln2
instructions load fixed constants independent of the rounding mode.
Fix them to load a value correctly rounded for the current rounding
mode (but always rounded to 64-bit precision independent of the
precision control, and without setting "inexact") as specified.

Signed-off-by: Joseph Myers <joseph@codesourcery.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <alpine.DEB.2.21.2005132348310.11687@digraph.polyomino.org.uk>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

2 files changed, 248 insertions, 5 deletions

diff --git a/target/i386/fpu_helper.c b/target/i386/fpu_helper.c
index 4d14c1ca24..f0b9cb5de8 100644
--- a/target/i386/fpu_helper.c
+++ b/target/i386/fpu_helper.c
@@ -59,8 +59,13 @@
 #define FPUC_EM 0x3f
 
 #define floatx80_lg2 make_floatx80(0x3ffd, 0x9a209a84fbcff799LL)
+#define floatx80_lg2_d make_floatx80(0x3ffd, 0x9a209a84fbcff798LL)
 #define floatx80_l2e make_floatx80(0x3fff, 0xb8aa3b295c17f0bcLL)
+#define floatx80_l2e_d make_floatx80(0x3fff, 0xb8aa3b295c17f0bbLL)
 #define floatx80_l2t make_floatx80(0x4000, 0xd49a784bcd1b8afeLL)
+#define floatx80_l2t_u make_floatx80(0x4000, 0xd49a784bcd1b8affLL)
+#define floatx80_ln2_d make_floatx80(0x3ffe, 0xb17217f7d1cf79abLL)
+#define floatx80_pi_d make_floatx80(0x4000, 0xc90fdaa22168c234LL)
 
 #if !defined(CONFIG_USER_ONLY)
 static qemu_irq ferr_irq;
@@ -544,27 +549,66 @@ void helper_fld1_ST0(CPUX86State *env)
 
 void helper_fldl2t_ST0(CPUX86State *env)
 {
-    ST0 = floatx80_l2t;
+    switch (env->fpuc & FPU_RC_MASK) {
+    case FPU_RC_UP:
+        ST0 = floatx80_l2t_u;
+        break;
+    default:
+        ST0 = floatx80_l2t;
+        break;
+    }
 }
 
 void helper_fldl2e_ST0(CPUX86State *env)
 {
-    ST0 = floatx80_l2e;
+    switch (env->fpuc & FPU_RC_MASK) {
+    case FPU_RC_DOWN:
+    case FPU_RC_CHOP:
+        ST0 = floatx80_l2e_d;
+        break;
+    default:
+        ST0 = floatx80_l2e;
+        break;
+    }
 }
 
 void helper_fldpi_ST0(CPUX86State *env)
 {
-    ST0 = floatx80_pi;
+    switch (env->fpuc & FPU_RC_MASK) {
+    case FPU_RC_DOWN:
+    case FPU_RC_CHOP:
+        ST0 = floatx80_pi_d;
+        break;
+    default:
+        ST0 = floatx80_pi;
+        break;
+    }
 }
 
 void helper_fldlg2_ST0(CPUX86State *env)
 {
-    ST0 = floatx80_lg2;
+    switch (env->fpuc & FPU_RC_MASK) {
+    case FPU_RC_DOWN:
+    case FPU_RC_CHOP:
+        ST0 = floatx80_lg2_d;
+        break;
+    default:
+        ST0 = floatx80_lg2;
+        break;
+    }
 }
 
 void helper_fldln2_ST0(CPUX86State *env)
 {
-    ST0 = floatx80_ln2;
+    switch (env->fpuc & FPU_RC_MASK) {
+    case FPU_RC_DOWN:
+    case FPU_RC_CHOP:
+        ST0 = floatx80_ln2_d;
+        break;
+    default:
+        ST0 = floatx80_ln2;
+        break;
+    }
 }
 
 void helper_fldz_ST0(CPUX86State *env)
diff --git a/tests/tcg/i386/test-i386-fldcst.c b/tests/tcg/i386/test-i386-fldcst.c
new file mode 100644
index 0000000000..e635432ccf
--- /dev/null
+++ b/tests/tcg/i386/test-i386-fldcst.c
@@ -0,0 +1,199 @@
+/* Test instructions loading floating-point constants.  */
+
+#include <stdint.h>
+#include <stdio.h>
+
+volatile long double ld_res;
+
+int main(void)
+{
+    short cw;
+    int ret = 0;
+
+    /* Round to nearest.  */
+    __asm__ volatile ("fnstcw %0" : "=m" (cw));
+    cw = (cw & ~0xc00) | 0x000;
+    __asm__ volatile ("fldcw %0" : : "m" (cw));
+    __asm__ volatile ("fldl2t" : "=t" (ld_res));
+    if (ld_res != 0x3.5269e12f346e2bf8p+0L) {
+        printf("FAIL: fldl2t N\n");
+        ret = 1;
+    }
+    /* Round downward.  */
+    __asm__ volatile ("fnstcw %0" : "=m" (cw));
+    cw = (cw & ~0xc00) | 0x400;
+    __asm__ volatile ("fldcw %0" : : "m" (cw));
+    __asm__ volatile ("fldl2t" : "=t" (ld_res));
+    if (ld_res != 0x3.5269e12f346e2bf8p+0L) {
+        printf("FAIL: fldl2t D\n");
+        ret = 1;
+    }
+    /* Round toward zero.  */
+    __asm__ volatile ("fnstcw %0" : "=m" (cw));
+    cw = (cw & ~0xc00) | 0xc00;
+    __asm__ volatile ("fldcw %0" : : "m" (cw));
+    __asm__ volatile ("fldl2t" : "=t" (ld_res));
+    if (ld_res != 0x3.5269e12f346e2bf8p+0L) {
+        printf("FAIL: fldl2t Z\n");
+        ret = 1;
+    }
+    /* Round upward.  */
+    __asm__ volatile ("fnstcw %0" : "=m" (cw));
+    cw = (cw & ~0xc00) | 0x800;
+    __asm__ volatile ("fldcw %0" : : "m" (cw));
+    __asm__ volatile ("fldl2t" : "=t" (ld_res));
+    if (ld_res != 0x3.5269e12f346e2bfcp+0L) {
+        printf("FAIL: fldl2t U\n");
+        ret = 1;
+    }
+
+    /* Round to nearest.  */
+    __asm__ volatile ("fnstcw %0" : "=m" (cw));
+    cw = (cw & ~0xc00) | 0x000;
+    __asm__ volatile ("fldcw %0" : : "m" (cw));
+    __asm__ volatile ("fldl2e" : "=t" (ld_res));
+    if (ld_res != 0x1.71547652b82fe178p+0L) {
+        printf("FAIL: fldl2e N\n");
+        ret = 1;
+    }
+    /* Round downward.  */
+    __asm__ volatile ("fnstcw %0" : "=m" (cw));
+    cw = (cw & ~0xc00) | 0x400;
+    __asm__ volatile ("fldcw %0" : : "m" (cw));
+    __asm__ volatile ("fldl2e" : "=t" (ld_res));
+    if (ld_res != 0x1.71547652b82fe176p+0L) {
+        printf("FAIL: fldl2e D\n");
+        ret = 1;
+    }
+    /* Round toward zero.  */
+    __asm__ volatile ("fnstcw %0" : "=m" (cw));
+    cw = (cw & ~0xc00) | 0xc00;
+    __asm__ volatile ("fldcw %0" : : "m" (cw));
+    __asm__ volatile ("fldl2e" : "=t" (ld_res));
+    if (ld_res != 0x1.71547652b82fe176p+0L) {
+        printf("FAIL: fldl2e Z\n");
+        ret = 1;
+    }
+    /* Round upward.  */
+    __asm__ volatile ("fnstcw %0" : "=m" (cw));
+    cw = (cw & ~0xc00) | 0x800;
+    __asm__ volatile ("fldcw %0" : : "m" (cw));
+    __asm__ volatile ("fldl2e" : "=t" (ld_res));
+    if (ld_res != 0x1.71547652b82fe178p+0L) {
+        printf("FAIL: fldl2e U\n");
+        ret = 1;
+    }
+
+    /* Round to nearest.  */
+    __asm__ volatile ("fnstcw %0" : "=m" (cw));
+    cw = (cw & ~0xc00) | 0x000;
+    __asm__ volatile ("fldcw %0" : : "m" (cw));
+    __asm__ volatile ("fldpi" : "=t" (ld_res));
+    if (ld_res != 0x3.243f6a8885a308d4p+0L) {
+        printf("FAIL: fldpi N\n");
+        ret = 1;
+    }
+    /* Round downward.  */
+    __asm__ volatile ("fnstcw %0" : "=m" (cw));
+    cw = (cw & ~0xc00) | 0x400;
+    __asm__ volatile ("fldcw %0" : : "m" (cw));
+    __asm__ volatile ("fldpi" : "=t" (ld_res));
+    if (ld_res != 0x3.243f6a8885a308dp+0L) {
+        printf("FAIL: fldpi D\n");
+        ret = 1;
+    }
+    /* Round toward zero.  */
+    __asm__ volatile ("fnstcw %0" : "=m" (cw));
+    cw = (cw & ~0xc00) | 0xc00;
+    __asm__ volatile ("fldcw %0" : : "m" (cw));
+    __asm__ volatile ("fldpi" : "=t" (ld_res));
+    if (ld_res != 0x3.243f6a8885a308dp+0L) {
+        printf("FAIL: fldpi Z\n");
+        ret = 1;
+    }
+    /* Round upward.  */
+    __asm__ volatile ("fnstcw %0" : "=m" (cw));
+    cw = (cw & ~0xc00) | 0x800;
+    __asm__ volatile ("fldcw %0" : : "m" (cw));
+    __asm__ volatile ("fldpi" : "=t" (ld_res));
+    if (ld_res != 0x3.243f6a8885a308d4p+0L) {
+        printf("FAIL: fldpi U\n");
+        ret = 1;
+    }
+
+    /* Round to nearest.  */
+    __asm__ volatile ("fnstcw %0" : "=m" (cw));
+    cw = (cw & ~0xc00) | 0x000;
+    __asm__ volatile ("fldcw %0" : : "m" (cw));
+    __asm__ volatile ("fldlg2" : "=t" (ld_res));
+    if (ld_res != 0x4.d104d427de7fbcc8p-4L) {
+        printf("FAIL: fldlg2 N\n");
+        ret = 1;
+    }
+    /* Round downward.  */
+    __asm__ volatile ("fnstcw %0" : "=m" (cw));
+    cw = (cw & ~0xc00) | 0x400;
+    __asm__ volatile ("fldcw %0" : : "m" (cw));
+    __asm__ volatile ("fldlg2" : "=t" (ld_res));
+    if (ld_res != 0x4.d104d427de7fbccp-4L) {
+        printf("FAIL: fldlg2 D\n");
+        ret = 1;
+    }
+    /* Round toward zero.  */
+    __asm__ volatile ("fnstcw %0" : "=m" (cw));
+    cw = (cw & ~0xc00) | 0xc00;
+    __asm__ volatile ("fldcw %0" : : "m" (cw));
+    __asm__ volatile ("fldlg2" : "=t" (ld_res));
+    if (ld_res != 0x4.d104d427de7fbccp-4L) {
+        printf("FAIL: fldlg2 Z\n");
+        ret = 1;
+    }
+    /* Round upward.  */
+    __asm__ volatile ("fnstcw %0" : "=m" (cw));
+    cw = (cw & ~0xc00) | 0x800;
+    __asm__ volatile ("fldcw %0" : : "m" (cw));
+    __asm__ volatile ("fldlg2" : "=t" (ld_res));
+    if (ld_res != 0x4.d104d427de7fbcc8p-4L) {
+        printf("FAIL: fldlg2 U\n");
+        ret = 1;
+    }
+
+    /* Round to nearest.  */
+    __asm__ volatile ("fnstcw %0" : "=m" (cw));
+    cw = (cw & ~0xc00) | 0x000;
+    __asm__ volatile ("fldcw %0" : : "m" (cw));
+    __asm__ volatile ("fldln2" : "=t" (ld_res));
+    if (ld_res != 0xb.17217f7d1cf79acp-4L) {
+        printf("FAIL: fldln2 N\n");
+        ret = 1;
+    }
+    /* Round downward.  */
+    __asm__ volatile ("fnstcw %0" : "=m" (cw));
+    cw = (cw & ~0xc00) | 0x400;
+    __asm__ volatile ("fldcw %0" : : "m" (cw));
+    __asm__ volatile ("fldln2" : "=t" (ld_res));
+    if (ld_res != 0xb.17217f7d1cf79abp-4L) {
+        printf("FAIL: fldln2 D\n");
+        ret = 1;
+    }
+    /* Round toward zero.  */
+    __asm__ volatile ("fnstcw %0" : "=m" (cw));
+    cw = (cw & ~0xc00) | 0xc00;
+    __asm__ volatile ("fldcw %0" : : "m" (cw));
+    __asm__ volatile ("fldln2" : "=t" (ld_res));
+    if (ld_res != 0xb.17217f7d1cf79abp-4L) {
+        printf("FAIL: fldln2 Z\n");
+        ret = 1;
+    }
+    /* Round upward.  */
+    __asm__ volatile ("fnstcw %0" : "=m" (cw));
+    cw = (cw & ~0xc00) | 0x800;
+    __asm__ volatile ("fldcw %0" : : "m" (cw));
+    __asm__ volatile ("fldln2" : "=t" (ld_res));
+    if (ld_res != 0xb.17217f7d1cf79acp-4L) {
+        printf("FAIL: fldln2 U\n");
+        ret = 1;
+    }
+
+    return ret;
+}