tcg: Add guest load/store primitives for TCGv_i128

These are not yet considering atomicity of the 16-byte value;
this is a direct replacement for the current target code which
uses a pair of 8-byte operations.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

1 files changed, 134 insertions, 0 deletions

diff --git a/tcg/tcg-op.c b/tcg/tcg-op.c
index cb83d23..33ef325 100644
--- a/tcg/tcg-op.c
+++ b/tcg/tcg-op.c
@@ -3109,6 +3109,140 @@ void tcg_gen_qemu_st_i64(TCGv_i64 val, TCGv addr, TCGArg idx, MemOp memop)
     }
 }
 
+static void canonicalize_memop_i128_as_i64(MemOp ret[2], MemOp orig)
+{
+    MemOp mop_1 = orig, mop_2;
+
+    tcg_debug_assert((orig & MO_SIZE) == MO_128);
+    tcg_debug_assert((orig & MO_SIGN) == 0);
+
+    /* Use a memory ordering implemented by the host. */
+    if (!TCG_TARGET_HAS_MEMORY_BSWAP && (orig & MO_BSWAP)) {
+        mop_1 &= ~MO_BSWAP;
+    }
+
+    /* Reduce the size to 64-bit. */
+    mop_1 = (mop_1 & ~MO_SIZE) | MO_64;
+
+    /* Retain the alignment constraints of the original. */
+    switch (orig & MO_AMASK) {
+    case MO_UNALN:
+    case MO_ALIGN_2:
+    case MO_ALIGN_4:
+        mop_2 = mop_1;
+        break;
+    case MO_ALIGN_8:
+        /* Prefer MO_ALIGN+MO_64 to MO_ALIGN_8+MO_64. */
+        mop_1 = (mop_1 & ~MO_AMASK) | MO_ALIGN;
+        mop_2 = mop_1;
+        break;
+    case MO_ALIGN:
+        /* Second has 8-byte alignment; first has 16-byte alignment. */
+        mop_2 = mop_1;
+        mop_1 = (mop_1 & ~MO_AMASK) | MO_ALIGN_16;
+        break;
+    case MO_ALIGN_16:
+    case MO_ALIGN_32:
+    case MO_ALIGN_64:
+        /* Second has 8-byte alignment; first retains original. */
+        mop_2 = (mop_1 & ~MO_AMASK) | MO_ALIGN;
+        break;
+    default:
+        g_assert_not_reached();
+    }
+    ret[0] = mop_1;
+    ret[1] = mop_2;
+}
+
+void tcg_gen_qemu_ld_i128(TCGv_i128 val, TCGv addr, TCGArg idx, MemOp memop)
+{
+    MemOp mop[2];
+    TCGv addr_p8;
+    TCGv_i64 x, y;
+
+    canonicalize_memop_i128_as_i64(mop, memop);
+
+    tcg_gen_req_mo(TCG_MO_LD_LD | TCG_MO_ST_LD);
+    addr = plugin_prep_mem_callbacks(addr);
+
+    /* TODO: respect atomicity of the operation. */
+    /* TODO: allow the tcg backend to see the whole operation. */
+
+    /*
+     * Since there are no global TCGv_i128, there is no visible state
+     * changed if the second load faults.  Load directly into the two
+     * subwords.
+     */
+    if ((memop & MO_BSWAP) == MO_LE) {
+        x = TCGV128_LOW(val);
+        y = TCGV128_HIGH(val);
+    } else {
+        x = TCGV128_HIGH(val);
+        y = TCGV128_LOW(val);
+    }
+
+    gen_ldst_i64(INDEX_op_qemu_ld_i64, x, addr, mop[0], idx);
+
+    if ((mop[0] ^ memop) & MO_BSWAP) {
+        tcg_gen_bswap64_i64(x, x);
+    }
+
+    addr_p8 = tcg_temp_new();
+    tcg_gen_addi_tl(addr_p8, addr, 8);
+    gen_ldst_i64(INDEX_op_qemu_ld_i64, y, addr_p8, mop[1], idx);
+    tcg_temp_free(addr_p8);
+
+    if ((mop[0] ^ memop) & MO_BSWAP) {
+        tcg_gen_bswap64_i64(y, y);
+    }
+
+    plugin_gen_mem_callbacks(addr, make_memop_idx(memop, idx),
+                             QEMU_PLUGIN_MEM_R);
+}
+
+void tcg_gen_qemu_st_i128(TCGv_i128 val, TCGv addr, TCGArg idx, MemOp memop)
+{
+    MemOp mop[2];
+    TCGv addr_p8;
+    TCGv_i64 x, y;
+
+    canonicalize_memop_i128_as_i64(mop, memop);
+
+    tcg_gen_req_mo(TCG_MO_ST_LD | TCG_MO_ST_ST);
+    addr = plugin_prep_mem_callbacks(addr);
+
+    /* TODO: respect atomicity of the operation. */
+    /* TODO: allow the tcg backend to see the whole operation. */
+
+    if ((memop & MO_BSWAP) == MO_LE) {
+        x = TCGV128_LOW(val);
+        y = TCGV128_HIGH(val);
+    } else {
+        x = TCGV128_HIGH(val);
+        y = TCGV128_LOW(val);
+    }
+
+    addr_p8 = tcg_temp_new();
+    if ((mop[0] ^ memop) & MO_BSWAP) {
+        TCGv_i64 t = tcg_temp_new_i64();
+
+        tcg_gen_bswap64_i64(t, x);
+        gen_ldst_i64(INDEX_op_qemu_st_i64, t, addr, mop[0], idx);
+        tcg_gen_bswap64_i64(t, y);
+        tcg_gen_addi_tl(addr_p8, addr, 8);
+        gen_ldst_i64(INDEX_op_qemu_st_i64, t, addr_p8, mop[1], idx);
+        tcg_temp_free_i64(t);
+    } else {
+        gen_ldst_i64(INDEX_op_qemu_st_i64, x, addr, mop[0], idx);
+        tcg_gen_addi_tl(addr_p8, addr, 8);
+        gen_ldst_i64(INDEX_op_qemu_st_i64, y, addr_p8, mop[1], idx);
+    }
+    tcg_temp_free(addr_p8);
+
+    plugin_gen_mem_callbacks(addr, make_memop_idx(memop, idx),
+                             QEMU_PLUGIN_MEM_W);
+}
+
 static void tcg_gen_ext_i32(TCGv_i32 ret, TCGv_i32 val, MemOp opc)
 {
     switch (opc & MO_SSIZE) {