target/arm: Fix sve_zip_p vs odd vector lengths

Wrote too much with low-half zip (zip1) with vl % 512 != 0.

Adjust all of the x + (y << s) to x | (y << s) as a style fix.

We only ever have exact overlap between D, M, and N.  Therefore
we only need a single temporary, and we do not need to check for
partial overlap.

Reported-by: Laurent Desnogues <laurent.desnogues@gmail.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210309155305.11301-3-richard.henderson@linaro.org
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

1 files changed, 14 insertions, 11 deletions

diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index 11c9397dbb..2fb4b2c1ea 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -1871,6 +1871,7 @@ void HELPER(sve_zip_p)(void *vd, void *vn, void *vm, uint32_t pred_desc)
     intptr_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ);
     int esz = FIELD_EX32(pred_desc, PREDDESC, ESZ);
     intptr_t high = FIELD_EX32(pred_desc, PREDDESC, DATA);
+    int esize = 1 << esz;
     uint64_t *d = vd;
     intptr_t i;
 
@@ -1883,33 +1884,35 @@ void HELPER(sve_zip_p)(void *vd, void *vn, void *vm, uint32_t pred_desc)
         mm = extract64(mm, high * half, half);
         nn = expand_bits(nn, esz);
         mm = expand_bits(mm, esz);
-        d[0] = nn + (mm << (1 << esz));
+        d[0] = nn | (mm << esize);
     } else {
-        ARMPredicateReg tmp_n, tmp_m;
+        ARMPredicateReg tmp;
 
         /* We produce output faster than we consume input.
            Therefore we must be mindful of possible overlap.  */
-        if ((vn - vd) < (uintptr_t)oprsz) {
-            vn = memcpy(&tmp_n, vn, oprsz);
-        }
-        if ((vm - vd) < (uintptr_t)oprsz) {
-            vm = memcpy(&tmp_m, vm, oprsz);
+        if (vd == vn) {
+            vn = memcpy(&tmp, vn, oprsz);
+            if (vd == vm) {
+                vm = vn;
+            }
+        } else if (vd == vm) {
+            vm = memcpy(&tmp, vm, oprsz);
         }
         if (high) {
             high = oprsz >> 1;
         }
 
-        if ((high & 3) == 0) {
+        if ((oprsz & 7) == 0) {
             uint32_t *n = vn, *m = vm;
             high >>= 2;
 
-            for (i = 0; i < DIV_ROUND_UP(oprsz, 8); i++) {
+            for (i = 0; i < oprsz / 8; i++) {
                 uint64_t nn = n[H4(high + i)];
                 uint64_t mm = m[H4(high + i)];
 
                 nn = expand_bits(nn, esz);
                 mm = expand_bits(mm, esz);
-                d[i] = nn + (mm << (1 << esz));
+                d[i] = nn | (mm << esize);
             }
         } else {
             uint8_t *n = vn, *m = vm;
@@ -1921,7 +1924,7 @@ void HELPER(sve_zip_p)(void *vd, void *vn, void *vm, uint32_t pred_desc)
 
                 nn = expand_bits(nn, esz);
                 mm = expand_bits(mm, esz);
-                d16[H2(i)] = nn + (mm << (1 << esz));
+                d16[H2(i)] = nn | (mm << esize);
             }
         }
     }