[PATCH 06/37] target/i386: add ALU load/writeback core

[Paolo Bonzini <pbonzini@redhat.com>]

Add generic code generation that takes care of preparing operands
around calls to decode.e.gen in a table-driven manner, so that ALU
operations need not take care of that.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 target/i386/tcg/decode-new.c.inc |  20 +++-
 target/i386/tcg/decode-new.h     |   1 +
 target/i386/tcg/emit.c.inc       | 152 +++++++++++++++++++++++++++++++
 target/i386/tcg/translate.c      |  24 +++++
 4 files changed, 195 insertions(+), 2 deletions(-)

diff --git a/target/i386/tcg/decode-new.c.inc b/target/i386/tcg/decode-new.c.inc
index de8ef51a2d..7f76051b2d 100644
--- a/target/i386/tcg/decode-new.c.inc
+++ b/target/i386/tcg/decode-new.c.inc
@@ -228,7 +228,7 @@ static bool decode_op_size(DisasContext *s, X86OpEntry *e, X86OpSize size, MemOp
             *ot = MO_64;
             return true;
         }
-        if (s->vex_l && e->s0 != X86_SIZE_qq) {
+        if (s->vex_l && e->s0 != X86_SIZE_qq && e->s1 != X86_SIZE_qq) {
             return false;
         }
         *ot = MO_128;
@@ -741,7 +741,23 @@ static target_ulong disas_insn_new(DisasContext *s, CPUState *cpu, int b)
     if (decode.op[0].has_ea || decode.op[1].has_ea || decode.op[2].has_ea) {
         gen_load_ea(s, &decode.mem);
     }
-    decode.e.gen(s, env, &decode);
+    if (s->prefix & PREFIX_LOCK) {
+        if (decode.op[0].unit != X86_OP_INT || !decode.op[0].has_ea) {
+            goto illegal_op;
+        }
+        gen_load(s, s->T1, NULL, &decode.op[2], decode.immediate);
+        decode.e.gen(s, env, &decode);
+    } else {
+        if (decode.op[0].unit == X86_OP_MMX) {
+            gen_mmx_offset(s->ptr0, &decode.op[0]);
+        } else if (decode.op[0].unit == X86_OP_SSE) {
+            gen_xmm_offset(s->ptr0, &decode.op[0]);
+        }
+        gen_load(s, s->T0, s->ptr1, &decode.op[1], decode.immediate);
+        gen_load(s, s->T1, s->ptr2, &decode.op[2], decode.immediate);
+        decode.e.gen(s, env, &decode);
+        gen_writeback(s, &decode.op[0]);
+    }
     return s->pc;
  illegal_op:
     gen_illegal_opcode(s);
diff --git a/target/i386/tcg/decode-new.h b/target/i386/tcg/decode-new.h
index fb44560aae..a2d3c3867f 100644
--- a/target/i386/tcg/decode-new.h
+++ b/target/i386/tcg/decode-new.h
@@ -168,6 +168,7 @@ typedef struct X86DecodedOp {
     MemOp ot;     /* For b/c/d/p/s/q/v/w/y/z */
     X86OpUnit unit;
     bool has_ea;
+    int offset;   /* For MMX and SSE */
 } X86DecodedOp;
 
 struct X86DecodedInsn {
diff --git a/target/i386/tcg/emit.c.inc b/target/i386/tcg/emit.c.inc
index e86364ffc1..6fa0062d6a 100644
--- a/target/i386/tcg/emit.c.inc
+++ b/target/i386/tcg/emit.c.inc
@@ -29,3 +29,155 @@ static void gen_load_ea(DisasContext *s, AddressParts *mem)
     TCGv ea = gen_lea_modrm_1(s, *mem);
     gen_lea_v_seg(s, s->aflag, ea, mem->def_seg, s->override);
 }
+
+static void gen_mmx_offset(TCGv_ptr ptr, X86DecodedOp *op)
+{
+    if (!op->has_ea) {
+        op->offset = offsetof(CPUX86State, fpregs[op->n].mmx);
+    } else {
+        op->offset = offsetof(CPUX86State, mmx_t0);
+    }
+    tcg_gen_addi_ptr(ptr, cpu_env, op->offset);
+
+    /*
+     * ptr is for passing to helpers, and points to the MMXReg; op->offset
+     * is for TCG ops and points to the operand.
+     */
+    if (op->ot == MO_32) {
+        op->offset += offsetof(MMXReg, MMX_L(0));
+    }
+}
+
+static int xmm_offset(MemOp ot)
+{
+    if (ot == MO_8) {
+        return offsetof(ZMMReg, ZMM_B(0));
+    } else if (ot == MO_16) {
+        return offsetof(ZMMReg, ZMM_W(0));
+    } else if (ot == MO_32) {
+        return offsetof(ZMMReg, ZMM_L(0));
+    } else if (ot == MO_64) {
+        return offsetof(ZMMReg, ZMM_Q(0));
+    } else if (ot == MO_128) {
+        return offsetof(ZMMReg, ZMM_X(0));
+    } else if (ot == MO_256) {
+        return offsetof(ZMMReg, ZMM_Y(0));
+    } else {
+       abort();
+    }
+}
+
+static void gen_xmm_offset(TCGv_ptr ptr, X86DecodedOp *op)
+{
+    if (!op->has_ea) {
+        op->offset = ZMM_OFFSET(op->n);
+    } else {
+        op->offset = offsetof(CPUX86State, xmm_t0);
+    }
+    /*
+     * ptr is for passing to helpers, and points to the ZMMReg; op->offset
+     * is for TCG ops (especially gvec) and points to the base of the vector.
+     */
+    tcg_gen_addi_ptr(ptr, cpu_env, op->offset);
+    op->offset += xmm_offset(op->ot);
+}
+
+static void gen_load_sse(DisasContext *s, TCGv temp, MemOp ot, int dest_ofs)
+{
+    if (ot == MO_8) {
+        gen_op_ld_v(s, MO_8, temp, s->A0);
+        tcg_gen_st8_tl(temp, cpu_env, dest_ofs);
+    } else if (ot == MO_16) {
+        gen_op_ld_v(s, MO_16, temp, s->A0);
+        tcg_gen_st16_tl(temp, cpu_env, dest_ofs);
+    } else if (ot == MO_32) {
+        gen_op_ld_v(s, MO_32, temp, s->A0);
+        tcg_gen_st32_tl(temp, cpu_env, dest_ofs);
+    } else if (ot == MO_64) {
+        gen_ldq_env_A0(s, dest_ofs);
+    } else if (ot == MO_128) {
+        gen_ldo_env_A0(s, dest_ofs);
+    } else if (ot == MO_256) {
+        gen_ldy_env_A0(s, dest_ofs);
+    }
+}
+
+static void gen_load(DisasContext *s, TCGv v, TCGv_ptr ptr, X86DecodedOp *op, uint64_t imm)
+{
+    switch (op->unit) {
+    case X86_OP_SKIP:
+        return;
+    case X86_OP_SEG:
+        tcg_gen_ld32u_tl(v, cpu_env,
+                         offsetof(CPUX86State,segs[op->n].selector));
+        break;
+    case X86_OP_CR:
+        tcg_gen_ld_tl(v, cpu_env, offsetof(CPUX86State, cr[op->n]));
+        break;
+    case X86_OP_DR:
+        tcg_gen_ld_tl(v, cpu_env, offsetof(CPUX86State, dr[op->n]));
+        break;
+    case X86_OP_INT:
+        if (op->has_ea) {
+            gen_op_ld_v(s, op->ot, v, s->A0);
+        } else {
+            gen_op_mov_v_reg(s, op->ot, v, op->n);
+        }
+        break;
+    case X86_OP_IMM:
+        tcg_gen_movi_tl(v, imm);
+        break;
+
+    case X86_OP_MMX:
+        gen_mmx_offset(ptr, op);
+        goto load_vector;
+
+    case X86_OP_SSE:
+        gen_xmm_offset(ptr, op);
+    load_vector:
+        if (op->has_ea) {
+            gen_load_sse(s, v, op->ot, op->offset);
+        }
+        break;
+
+    default:
+        abort();
+    }
+}
+
+static void gen_writeback(DisasContext *s, X86DecodedOp *op)
+{
+    switch (op->unit) {
+    case X86_OP_SKIP:
+        break;
+    case X86_OP_SEG:
+        /* Note that reg == R_SS in gen_movl_seg_T0 always sets is_jmp.  */
+        gen_movl_seg_T0(s, op->n);
+        if (s->base.is_jmp) {
+            gen_jmp_im(s, s->pc - s->cs_base);
+            if (op->n == R_SS) {
+                s->flags &= ~HF_TF_MASK;
+                gen_eob_inhibit_irq(s, true);
+            } else {
+                gen_eob(s);
+            }
+        }
+        break;
+    case X86_OP_CR:
+    case X86_OP_DR:
+        /* TBD */
+        break;
+    case X86_OP_INT:
+        if (op->has_ea) {
+            gen_op_st_v(s, op->ot, s->T0, s->A0);
+        } else {
+            gen_op_mov_reg_v(s, op->ot, op->n, s->T0);
+        }
+        break;
+    case X86_OP_MMX:
+    case X86_OP_SSE:
+        break;
+    default:
+        abort();
+    }
+}
diff --git a/target/i386/tcg/translate.c b/target/i386/tcg/translate.c
index f66bf2ac79..7e9920e29c 100644
--- a/target/i386/tcg/translate.c
+++ b/target/i386/tcg/translate.c
@@ -2831,6 +2831,30 @@ static inline void gen_sto_env_A0(DisasContext *s, int offset)
     tcg_gen_qemu_st_i64(s->tmp1_i64, s->tmp0, mem_index, MO_LEUQ);
 }
 
+static inline void gen_ldy_env_A0(DisasContext *s, int offset)
+{
+    int mem_index = s->mem_index;
+    gen_ldo_env_A0(s, offset);
+    tcg_gen_addi_tl(s->tmp0, s->A0, 16);
+    tcg_gen_qemu_ld_i64(s->tmp1_i64, s->tmp0, mem_index, MO_LEUQ);
+    tcg_gen_st_i64(s->tmp1_i64, cpu_env, offset + offsetof(ZMMReg, ZMM_Q(2)));
+    tcg_gen_addi_tl(s->tmp0, s->A0, 24);
+    tcg_gen_qemu_ld_i64(s->tmp1_i64, s->tmp0, mem_index, MO_LEUQ);
+    tcg_gen_st_i64(s->tmp1_i64, cpu_env, offset + offsetof(ZMMReg, ZMM_Q(3)));
+}
+
+static inline void gen_sty_env_A0(DisasContext *s, int offset)
+{
+    int mem_index = s->mem_index;
+    gen_sto_env_A0(s, offset);
+    tcg_gen_addi_tl(s->tmp0, s->A0, 16);
+    tcg_gen_ld_i64(s->tmp1_i64, cpu_env, offset + offsetof(ZMMReg, ZMM_Q(2)));
+    tcg_gen_qemu_st_i64(s->tmp1_i64, s->tmp0, mem_index, MO_LEUQ);
+    tcg_gen_addi_tl(s->tmp0, s->A0, 24);
+    tcg_gen_ld_i64(s->tmp1_i64, cpu_env, offset + offsetof(ZMMReg, ZMM_Q(3)));
+    tcg_gen_qemu_st_i64(s->tmp1_i64, s->tmp0, mem_index, MO_LEUQ);
+}
+
 static inline void gen_op_movo(DisasContext *s, int d_offset, int s_offset)
 {
     tcg_gen_ld_i64(s->tmp1_i64, cpu_env, s_offset + offsetof(XMMReg, XMM_Q(0)));
-- 
2.37.2