target/i386: fix PHSUB* instructions with dest=src

The computation must not overwrite neither the destination
nor the source before the last element has been computed.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

1 files changed, 29 insertions, 20 deletions

diff --git a/target/i386/ops_sse.h b/target/i386/ops_sse.h
index 535440f..2524db4 100644
--- a/target/i386/ops_sse.h
+++ b/target/i386/ops_sse.h
@@ -1528,34 +1528,43 @@ void glue(helper_pmaddubsw, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
 
 void glue(helper_phsubw, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
 {
-    d->W(0) = (int16_t)d->W(0) - (int16_t)d->W(1);
-    d->W(1) = (int16_t)d->W(2) - (int16_t)d->W(3);
-    XMM_ONLY(d->W(2) = (int16_t)d->W(4) - (int16_t)d->W(5));
-    XMM_ONLY(d->W(3) = (int16_t)d->W(6) - (int16_t)d->W(7));
-    d->W((2 << SHIFT) + 0) = (int16_t)s->W(0) - (int16_t)s->W(1);
-    d->W((2 << SHIFT) + 1) = (int16_t)s->W(2) - (int16_t)s->W(3);
-    XMM_ONLY(d->W(6) = (int16_t)s->W(4) - (int16_t)s->W(5));
-    XMM_ONLY(d->W(7) = (int16_t)s->W(6) - (int16_t)s->W(7));
+    Reg r;
+
+    r.W(0) = (int16_t)d->W(0) - (int16_t)d->W(1);
+    r.W(1) = (int16_t)d->W(2) - (int16_t)d->W(3);
+    XMM_ONLY(r.W(2) = (int16_t)d->W(4) - (int16_t)d->W(5));
+    XMM_ONLY(r.W(3) = (int16_t)d->W(6) - (int16_t)d->W(7));
+    r.W((2 << SHIFT) + 0) = (int16_t)s->W(0) - (int16_t)s->W(1);
+    r.W((2 << SHIFT) + 1) = (int16_t)s->W(2) - (int16_t)s->W(3);
+    XMM_ONLY(r.W(6) = (int16_t)s->W(4) - (int16_t)s->W(5));
+    XMM_ONLY(r.W(7) = (int16_t)s->W(6) - (int16_t)s->W(7));
+    MOVE(*d, r);
 }
 
 void glue(helper_phsubd, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
 {
-    d->L(0) = (int32_t)d->L(0) - (int32_t)d->L(1);
-    XMM_ONLY(d->L(1) = (int32_t)d->L(2) - (int32_t)d->L(3));
-    d->L((1 << SHIFT) + 0) = (int32_t)s->L(0) - (int32_t)s->L(1);
-    XMM_ONLY(d->L(3) = (int32_t)s->L(2) - (int32_t)s->L(3));
+    Reg r;
+
+    r.L(0) = (int32_t)d->L(0) - (int32_t)d->L(1);
+    XMM_ONLY(r.L(1) = (int32_t)d->L(2) - (int32_t)d->L(3));
+    r.L((1 << SHIFT) + 0) = (int32_t)s->L(0) - (int32_t)s->L(1);
+    XMM_ONLY(r.L(3) = (int32_t)s->L(2) - (int32_t)s->L(3));
+    MOVE(*d, r);
 }
 
 void glue(helper_phsubsw, SUFFIX)(CPUX86State *env, Reg *d, Reg *s)
 {
-    d->W(0) = satsw((int16_t)d->W(0) - (int16_t)d->W(1));
-    d->W(1) = satsw((int16_t)d->W(2) - (int16_t)d->W(3));
-    XMM_ONLY(d->W(2) = satsw((int16_t)d->W(4) - (int16_t)d->W(5)));
-    XMM_ONLY(d->W(3) = satsw((int16_t)d->W(6) - (int16_t)d->W(7)));
-    d->W((2 << SHIFT) + 0) = satsw((int16_t)s->W(0) - (int16_t)s->W(1));
-    d->W((2 << SHIFT) + 1) = satsw((int16_t)s->W(2) - (int16_t)s->W(3));
-    XMM_ONLY(d->W(6) = satsw((int16_t)s->W(4) - (int16_t)s->W(5)));
-    XMM_ONLY(d->W(7) = satsw((int16_t)s->W(6) - (int16_t)s->W(7)));
+    Reg r;
+
+    r.W(0) = satsw((int16_t)d->W(0) - (int16_t)d->W(1));
+    r.W(1) = satsw((int16_t)d->W(2) - (int16_t)d->W(3));
+    XMM_ONLY(r.W(2) = satsw((int16_t)d->W(4) - (int16_t)d->W(5)));
+    XMM_ONLY(r.W(3) = satsw((int16_t)d->W(6) - (int16_t)d->W(7)));
+    r.W((2 << SHIFT) + 0) = satsw((int16_t)s->W(0) - (int16_t)s->W(1));
+    r.W((2 << SHIFT) + 1) = satsw((int16_t)s->W(2) - (int16_t)s->W(3));
+    XMM_ONLY(r.W(6) = satsw((int16_t)s->W(4) - (int16_t)s->W(5)));
+    XMM_ONLY(r.W(7) = satsw((int16_t)s->W(6) - (int16_t)s->W(7)));
+    MOVE(*d, r);
 }
 
 #define FABSB(_, x) (x > INT8_MAX  ? -(int8_t)x : x)