tcg/s390x: Implement tcg_out_ld/st for vector types

Reviewed-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

tcg/s390x/tcg-target.c.inc

@@ -265,6 +265,12 @@ typedef enum S390Opcode {
     RX_STC      = 0x42,
     RX_STH      = 0x40,
 
+    VRX_VL      = 0xe706,
+    VRX_VLLEZ   = 0xe704,
+    VRX_VST     = 0xe70e,
+    VRX_VSTEF   = 0xe70b,
+    VRX_VSTEG   = 0xe70a,
+
     NOP         = 0x0707,
 } S390Opcode;
 
@@ -412,6 +418,16 @@ static void * const qemu_st_helpers[(MO_SIZE | MO_BSWAP) + 1] = {
 static const tcg_insn_unit *tb_ret_addr;
 uint64_t s390_facilities[3];
 
+static inline bool is_general_reg(TCGReg r)
+{
+    return r <= TCG_REG_R15;
+}
+
+static inline bool is_vector_reg(TCGReg r)
+{
+    return r >= TCG_REG_V0 && r <= TCG_REG_V31;
+}
+
 static bool patch_reloc(tcg_insn_unit *src_rw, int type,
                         intptr_t value, intptr_t addend)
 {
@@ -529,6 +545,31 @@ static void tcg_out_insn_RSY(TCGContext *s, S390Opcode op, TCGReg r1,
 #define tcg_out_insn_RX   tcg_out_insn_RS
 #define tcg_out_insn_RXY  tcg_out_insn_RSY
 
+static int RXB(TCGReg v1, TCGReg v2, TCGReg v3, TCGReg v4)
+{
+    /*
+     * Shift bit 4 of each regno to its corresponding bit of RXB.
+     * RXB itself begins at bit 8 of the instruction so 8 - 4 = 4
+     * is the left-shift of the 4th operand.
+     */
+    return ((v1 & 0x10) << (4 + 3))
+         | ((v2 & 0x10) << (4 + 2))
+         | ((v3 & 0x10) << (4 + 1))
+         | ((v4 & 0x10) << (4 + 0));
+}
+
+static void tcg_out_insn_VRX(TCGContext *s, S390Opcode op, TCGReg v1,
+                             TCGReg b2, TCGReg x2, intptr_t d2, int m3)
+{
+    tcg_debug_assert(is_vector_reg(v1));
+    tcg_debug_assert(d2 >= 0 && d2 <= 0xfff);
+    tcg_debug_assert(is_general_reg(x2));
+    tcg_debug_assert(is_general_reg(b2));
+    tcg_out16(s, (op & 0xff00) | ((v1 & 0xf) << 4) | x2);
+    tcg_out16(s, (b2 << 12) | d2);
+    tcg_out16(s, (op & 0x00ff) | RXB(v1, 0, 0, 0) | (m3 << 12));
+}
+
 /* Emit an opcode with "type-checking" of the format.  */
 #define tcg_out_insn(S, FMT, OP, ...) \
     glue(tcg_out_insn_,FMT)(S, glue(glue(FMT,_),OP), ## __VA_ARGS__)
@@ -705,25 +746,92 @@ static void tcg_out_mem(TCGContext *s, S390Opcode opc_rx, S390Opcode opc_rxy,
     }
 }
 
+static void tcg_out_vrx_mem(TCGContext *s, S390Opcode opc_vrx,
+                            TCGReg data, TCGReg base, TCGReg index,
+                            tcg_target_long ofs, int m3)
+{
+    if (ofs < 0 || ofs >= 0x1000) {
+        if (ofs >= -0x80000 && ofs < 0x80000) {
+            tcg_out_insn(s, RXY, LAY, TCG_TMP0, base, index, ofs);
+            base = TCG_TMP0;
+            index = TCG_REG_NONE;
+            ofs = 0;
+        } else {
+            tcg_out_movi(s, TCG_TYPE_PTR, TCG_TMP0, ofs);
+            if (index != TCG_REG_NONE) {
+                tcg_out_insn(s, RRE, AGR, TCG_TMP0, index);
+            }
+            index = TCG_TMP0;
+            ofs = 0;
+        }
+    }
+    tcg_out_insn_VRX(s, opc_vrx, data, base, index, ofs, m3);
+}
 
 /* load data without address translation or endianness conversion */
-static inline void tcg_out_ld(TCGContext *s, TCGType type, TCGReg data,
+static void tcg_out_ld(TCGContext *s, TCGType type, TCGReg data,
                        TCGReg base, intptr_t ofs)
 {
-    if (type == TCG_TYPE_I32) {
+    switch (type) {
+    case TCG_TYPE_I32:
+        if (likely(is_general_reg(data))) {
             tcg_out_mem(s, RX_L, RXY_LY, data, base, TCG_REG_NONE, ofs);
-    } else {
+            break;
+        }
+        tcg_out_vrx_mem(s, VRX_VLLEZ, data, base, TCG_REG_NONE, ofs, MO_32);
+        break;
+
+    case TCG_TYPE_I64:
+        if (likely(is_general_reg(data))) {
             tcg_out_mem(s, 0, RXY_LG, data, base, TCG_REG_NONE, ofs);
+            break;
+        }
+        /* fallthru */
+
+    case TCG_TYPE_V64:
+        tcg_out_vrx_mem(s, VRX_VLLEZ, data, base, TCG_REG_NONE, ofs, MO_64);
+        break;
+
+    case TCG_TYPE_V128:
+        /* Hint quadword aligned.  */
+        tcg_out_vrx_mem(s, VRX_VL, data, base, TCG_REG_NONE, ofs, 4);
+        break;
+
+    default:
+        g_assert_not_reached();
     }
 }
 
-static inline void tcg_out_st(TCGContext *s, TCGType type, TCGReg data,
+static void tcg_out_st(TCGContext *s, TCGType type, TCGReg data,
                        TCGReg base, intptr_t ofs)
 {
-    if (type == TCG_TYPE_I32) {
+    switch (type) {
+    case TCG_TYPE_I32:
+        if (likely(is_general_reg(data))) {
             tcg_out_mem(s, RX_ST, RXY_STY, data, base, TCG_REG_NONE, ofs);
         } else {
+            tcg_out_vrx_mem(s, VRX_VSTEF, data, base, TCG_REG_NONE, ofs, 1);
+        }
+        break;
+
+    case TCG_TYPE_I64:
+        if (likely(is_general_reg(data))) {
             tcg_out_mem(s, 0, RXY_STG, data, base, TCG_REG_NONE, ofs);
+            break;
+        }
+        /* fallthru */
+
+    case TCG_TYPE_V64:
+        tcg_out_vrx_mem(s, VRX_VSTEG, data, base, TCG_REG_NONE, ofs, 0);
+        break;
+
+    case TCG_TYPE_V128:
+        /* Hint quadword aligned.  */
+        tcg_out_vrx_mem(s, VRX_VST, data, base, TCG_REG_NONE, ofs, 4);
+        break;
+
+    default:
+        g_assert_not_reached();
     }
 }