target-arm: add support for v8 VMULL.P64 instruction

Add support for the VMULL.P64 polynomial 64x64 to 128 bit multiplication
instruction in the A32/T32 instruction sets; this is part of the v8
Crypto Extensions.

To do this we have to move the neon_pmull_64_{lo,hi} helpers from
helper-a64.c into neon_helper.c so they can be used by the AArch32
translator.

Inspired-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 1401386724-26529-4-git-send-email-peter.maydell@linaro.org

1 files changed, 30 insertions, 0 deletions

diff --git a/target-arm/neon_helper.c b/target-arm/neon_helper.c
index 492e500..47d13e9 100644
--- a/target-arm/neon_helper.c
+++ b/target-arm/neon_helper.c
@@ -2211,3 +2211,33 @@ void HELPER(neon_zip16)(CPUARMState *env, uint32_t rd, uint32_t rm)
     env->vfp.regs[rm] = make_float64(m0);
     env->vfp.regs[rd] = make_float64(d0);
 }
+
+/* Helper function for 64 bit polynomial multiply case:
+ * perform PolynomialMult(op1, op2) and return either the top or
+ * bottom half of the 128 bit result.
+ */
+uint64_t HELPER(neon_pmull_64_lo)(uint64_t op1, uint64_t op2)
+{
+    int bitnum;
+    uint64_t res = 0;
+
+    for (bitnum = 0; bitnum < 64; bitnum++) {
+        if (op1 & (1ULL << bitnum)) {
+            res ^= op2 << bitnum;
+        }
+    }
+    return res;
+}
+uint64_t HELPER(neon_pmull_64_hi)(uint64_t op1, uint64_t op2)
+{
+    int bitnum;
+    uint64_t res = 0;
+
+    /* bit 0 of op1 can't influence the high 64 bits at all */
+    for (bitnum = 1; bitnum < 64; bitnum++) {
+        if (op1 & (1ULL << bitnum)) {
+            res ^= op2 >> (64 - bitnum);
+        }
+    }
+    return res;
+}