[Qemu-devel] [PATCH v4 0/2] target-m68k: add movem, BCD and CAS instructions

[Qemu-devel] [PATCH v4 0/2] target-m68k: add movem, BCD and CAS instructions

[Laurent Vivier]

This series is another subset of the series I sent in May:
https://lists.gnu.org/archive/html/qemu-devel/2016-05/msg00501.html

This subset contains reworked patches for:
- abcd/nbcd/sbcd: remove inline, delay write back to memory and
  use only 3 digits (and extract it from the bifield patch as
  it was squashed into it)
- movem: delay the update of the registers to the end of the load
  sequence to be able to restart the operation in case of page
  fault, and manage the 68020+ <-> 68000/68010 special case
- cas/cas2: rewrite according Richard's comments,
  and use cmpxchg() in cas.

I've checked it doesn't break coldfire support:
http://wiki.qemu.org/download/coldfire-test-0.1.tar.bz2
but it can't boot a 680x0 processor kernel.

v4:
- bcd: simplify bcd_flags
- cas: use cpu_ldX_data_ra()/cpu_stX_data_ra()
           helper_atomic_cmpxchgq_be()
       fix address of second cmpxchgq() (use a2 instead of a1)
       manage invalid size in opcode_table

v3:
- This series must be applied on top of m68k-for-2.9 branch
- remove movem as it has been applied from another series
- bcd: use less bits, use 8bit immediate
- cas2: use CC_OP_CMPW  in cas2w,
        check CONFIG_ATOMIC64,
        call HELPER(cas2l) from INSN(cas2l)
v2:
- movem: don't use temp variable mask2
- bcd: delay register write back
       fix bcd_add() to add X
       define bcd_sub() instead of bsd_neg()
- cas2: make it atomic with "parallel_cpus" and
        cpu_loop_exit_atomic() (and 64bit cmpxchg()
        if possible)

Thanks,
Laurent

Laurent Vivier (2):
  target-m68k: add abcd/sbcd/nbcd
  target-m68k: add cas/cas2 ops

 target-m68k/helper.h    |   2 +
 target-m68k/op_helper.c | 109 ++++++++++++++
 target-m68k/translate.c | 369 ++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 480 insertions(+)

-- 
2.7.4

[Qemu-devel] [PATCH v4 1/2] target-m68k: add abcd/sbcd/nbcd

[Laurent Vivier]

Signed-off-by: Laurent Vivier <laurent@vivier.eu>
Reviewed-by: Richard Henderson <rth@twiddle.net>
---
 target-m68k/translate.c | 216 ++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 216 insertions(+)

diff --git a/target-m68k/translate.c b/target-m68k/translate.c
index b538d74..f4eba90 100644
--- a/target-m68k/translate.c
+++ b/target-m68k/translate.c
@@ -1315,6 +1315,217 @@ DISAS_INSN(divl)
     set_cc_op(s, CC_OP_FLAGS);
 }
 
+static void bcd_add(TCGv dest, TCGv src)
+{
+    TCGv t0, t1;
+
+    /*  dest10 = dest10 + src10 + X
+     *
+     *        t1 = src
+     *        t2 = t1 + 0x066
+     *        t3 = t2 + dest + X
+     *        t4 = t2 ^ dest
+     *        t5 = t3 ^ t4
+     *        t6 = ~t5 & 0x110
+     *        t7 = (t6 >> 2) | (t6 >> 3)
+     *        return t3 - t7
+     */
+
+    /* t1 = (src + 0x066) + dest + X
+     *    = result with some possible exceding 0x6
+     */
+
+    t0 = tcg_const_i32(0x066);
+    tcg_gen_add_i32(t0, t0, src);
+
+    t1 = tcg_temp_new();
+    tcg_gen_add_i32(t1, t0, dest);
+    tcg_gen_add_i32(t1, t1, QREG_CC_X);
+
+    /* we will remove exceding 0x6 where there is no carry */
+
+    /* t0 = (src + 0x0066) ^ dest
+     *    = t1 without carries
+     */
+
+    tcg_gen_xor_i32(t0, t0, dest);
+
+    /* extract the carries
+     * t0 = t0 ^ t1
+     *    = only the carries
+     */
+
+    tcg_gen_xor_i32(t0, t0, t1);
+
+    /* generate 0x1 where there is no carry
+     * and for each 0x10, generate a 0x6
+     */
+
+    tcg_gen_shri_i32(t0, t0, 3);
+    tcg_gen_not_i32(t0, t0);
+    tcg_gen_andi_i32(t0, t0, 0x22);
+    tcg_gen_add_i32(dest, t0, t0);
+    tcg_gen_add_i32(dest, dest, t0);
+
+    /* remove the exceding 0x6
+     * for digits that have not generated a carry
+     */
+
+    tcg_gen_sub_i32(dest, t1, dest);
+    tcg_temp_free(t1);
+}
+
+static void bcd_sub(TCGv dest, TCGv src)
+{
+    TCGv t0, t1, t2;
+
+    /*  dest10 = dest10 - src10 - X
+     *         = bcd_add(dest + 1 - X, 0x199 - src)
+     */
+
+    /* t0 = 0x066 + (0x199 - src) */
+
+    t0 = tcg_temp_new();
+    tcg_gen_subfi_i32(t0, 0x1ff, src);
+
+    /* t1 = t0 + dest + 1 - X*/
+
+    t1 = tcg_temp_new();
+    tcg_gen_add_i32(t1, t0, dest);
+    tcg_gen_addi_i32(t1, t1, 1);
+    tcg_gen_sub_i32(t1, t1, QREG_CC_X);
+
+    /* t2 = t0 ^ dest */
+
+    t2 = tcg_temp_new();
+    tcg_gen_xor_i32(t2, t0, dest);
+
+    /* t0 = t1 ^ t2 */
+
+    tcg_gen_xor_i32(t0, t1, t2);
+
+    /* t2 = ~t0 & 0x110
+     * t0 = (t2 >> 2) | (t2 >> 3)
+     *
+     * to fit on 8bit operands, changed in:
+     *
+     * t2 = ~(t0 >> 3) & 0x22
+     * t0 = t2 + t2
+     * t0 = t0 + t2
+     */
+
+    tcg_gen_shri_i32(t2, t0, 3);
+    tcg_gen_not_i32(t2, t2);
+    tcg_gen_andi_i32(t2, t2, 0x22);
+    tcg_gen_add_i32(t0, t2, t2);
+    tcg_gen_add_i32(t0, t0, t2);
+
+    /* return t1 - t0 */
+
+    tcg_gen_sub_i32(dest, t1, t0);
+}
+
+static void bcd_flags(TCGv val)
+{
+    tcg_gen_andi_i32(QREG_CC_C, val, 0x0ff);
+    tcg_gen_or_i32(QREG_CC_Z, QREG_CC_Z, QREG_CC_C);
+
+    tcg_gen_shri_i32(QREG_CC_C, val, 8);
+    tcg_gen_andi_i32(QREG_CC_C, QREG_CC_C, 1);
+
+    tcg_gen_mov_i32(QREG_CC_X, QREG_CC_C);
+}
+
+DISAS_INSN(abcd_reg)
+{
+    TCGv src;
+    TCGv dest;
+
+    gen_flush_flags(s); /* !Z is sticky */
+
+    src = gen_extend(DREG(insn, 0), OS_BYTE, 0);
+    dest = gen_extend(DREG(insn, 9), OS_BYTE, 0);
+    bcd_add(dest, src);
+    gen_partset_reg(OS_BYTE, DREG(insn, 9), dest);
+
+    bcd_flags(dest);
+}
+
+DISAS_INSN(abcd_mem)
+{
+    TCGv src, dest, addr;
+
+    gen_flush_flags(s); /* !Z is sticky */
+
+    /* Indirect pre-decrement load (mode 4) */
+
+    src = gen_ea_mode(env, s, 4, REG(insn, 0), OS_BYTE,
+                      NULL_QREG, NULL, EA_LOADU);
+    dest = gen_ea_mode(env, s, 4, REG(insn, 9), OS_BYTE,
+                       NULL_QREG, &addr, EA_LOADU);
+
+    bcd_add(dest, src);
+
+    gen_ea_mode(env, s, 4, REG(insn, 9), OS_BYTE, dest, &addr, EA_STORE);
+
+    bcd_flags(dest);
+}
+
+DISAS_INSN(sbcd_reg)
+{
+    TCGv src, dest;
+
+    gen_flush_flags(s); /* !Z is sticky */
+
+    src = gen_extend(DREG(insn, 0), OS_BYTE, 0);
+    dest = gen_extend(DREG(insn, 9), OS_BYTE, 0);
+
+    bcd_sub(dest, src);
+
+    gen_partset_reg(OS_BYTE, DREG(insn, 9), dest);
+
+    bcd_flags(dest);
+}
+
+DISAS_INSN(sbcd_mem)
+{
+    TCGv src, dest, addr;
+
+    gen_flush_flags(s); /* !Z is sticky */
+
+    /* Indirect pre-decrement load (mode 4) */
+
+    src = gen_ea_mode(env, s, 4, REG(insn, 0), OS_BYTE,
+                      NULL_QREG, NULL, EA_LOADU);
+    dest = gen_ea_mode(env, s, 4, REG(insn, 9), OS_BYTE,
+                       NULL_QREG, &addr, EA_LOADU);
+
+    bcd_sub(dest, src);
+
+    gen_ea_mode(env, s, 4, REG(insn, 9), OS_BYTE, dest, &addr, EA_STORE);
+
+    bcd_flags(dest);
+}
+
+DISAS_INSN(nbcd)
+{
+    TCGv src, dest;
+    TCGv addr;
+
+    gen_flush_flags(s); /* !Z is sticky */
+
+    SRC_EA(env, src, OS_BYTE, 0, &addr);
+
+    dest = tcg_const_i32(0);
+    bcd_sub(dest, src);
+
+    DEST_EA(env, insn, OS_BYTE, dest, &addr);
+
+    bcd_flags(dest);
+
+    tcg_temp_free(dest);
+}
+
 DISAS_INSN(addsub)
 {
     TCGv reg;
@@ -3689,6 +3900,7 @@ void register_m68k_insns (CPUM68KState *env)
     INSN(not,       4600, ff00, M68000);
     INSN(undef,     46c0, ffc0, M68000);
     INSN(move_to_sr, 46c0, ffc0, CF_ISA_A);
+    INSN(nbcd,      4800, ffc0, M68000);
     INSN(linkl,     4808, fff8, M68000);
     BASE(pea,       4840, ffc0);
     BASE(swap,      4840, fff8);
@@ -3742,6 +3954,8 @@ void register_m68k_insns (CPUM68KState *env)
     INSN(mvzs,      7100, f100, CF_ISA_B);
     BASE(or,        8000, f000);
     BASE(divw,      80c0, f0c0);
+    INSN(sbcd_reg,  8100, f1f8, M68000);
+    INSN(sbcd_mem,  8108, f1f8, M68000);
     BASE(addsub,    9000, f000);
     INSN(undef,     90c0, f0c0, CF_ISA_A);
     INSN(subx_reg,  9180, f1f8, CF_ISA_A);
@@ -3779,6 +3993,8 @@ void register_m68k_insns (CPUM68KState *env)
     INSN(exg_aa,    c148, f1f8, M68000);
     INSN(exg_da,    c188, f1f8, M68000);
     BASE(mulw,      c0c0, f0c0);
+    INSN(abcd_reg,  c100, f1f8, M68000);
+    INSN(abcd_mem,  c108, f1f8, M68000);
     BASE(addsub,    d000, f000);
     INSN(undef,     d0c0, f0c0, CF_ISA_A);
     INSN(addx_reg,      d180, f1f8, CF_ISA_A);
-- 
2.7.4

[Qemu-devel] [PATCH v4 2/2] target-m68k: add cas/cas2 ops

[Laurent Vivier]

Implement CAS using cmpxchg.
Implement CAS2 using helper and either cmpxchg when
the 32bit addresses are consecutive, or with
parallel_cpus+cpu_loop_exit_atomic() otherwise.

Suggested-by: Richard Henderson <rth@twiddle.net>
Signed-off-by: Laurent Vivier <laurent@vivier.eu>
---
 target-m68k/helper.h    |   2 +
 target-m68k/op_helper.c | 109 ++++++++++++++++++++++++++++++++++
 target-m68k/translate.c | 153 ++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 264 insertions(+)

diff --git a/target-m68k/helper.h b/target-m68k/helper.h
index d863e55..17ec342 100644
--- a/target-m68k/helper.h
+++ b/target-m68k/helper.h
@@ -9,6 +9,8 @@ DEF_HELPER_4(divull, void, env, int, int, i32)
 DEF_HELPER_4(divsll, void, env, int, int, s32)
 DEF_HELPER_2(set_sr, void, env, i32)
 DEF_HELPER_3(movec, void, env, i32, i32)
+DEF_HELPER_4(cas2w, void, env, i32, i32, i32)
+DEF_HELPER_4(cas2l, void, env, i32, i32, i32)
 
 DEF_HELPER_2(f64_to_i32, f32, env, f64)
 DEF_HELPER_2(f64_to_f32, f32, env, f64)
diff --git a/target-m68k/op_helper.c b/target-m68k/op_helper.c
index a4bfa4e..52edd42 100644
--- a/target-m68k/op_helper.c
+++ b/target-m68k/op_helper.c
@@ -359,3 +359,112 @@ void HELPER(divsll)(CPUM68KState *env, int numr, int regr, int32_t den)
     env->dregs[regr] = rem;
     env->dregs[numr] = quot;
 }
+
+void HELPER(cas2w)(CPUM68KState *env, uint32_t regs, uint32_t a1, uint32_t a2)
+{
+    uint32_t Dc1 = extract32(regs, 9, 3);
+    uint32_t Dc2 = extract32(regs, 6, 3);
+    uint32_t Du1 = extract32(regs, 3, 3);
+    uint32_t Du2 = extract32(regs, 0, 3);
+    int16_t c1 = env->dregs[Dc1];
+    int16_t c2 = env->dregs[Dc2];
+    int16_t u1 = env->dregs[Du1];
+    int16_t u2 = env->dregs[Du2];
+    int16_t l1, l2;
+    uintptr_t ra = GETPC();
+
+    if (parallel_cpus) {
+        /* Tell the main loop we need to serialize this insn.  */
+        cpu_loop_exit_atomic(ENV_GET_CPU(env), ra);
+    } else {
+        /* We're executing in a serial context -- no need to be atomic.  */
+        l1 = cpu_lduw_data_ra(env, a1, ra);
+        l2 = cpu_lduw_data_ra(env, a2, ra);
+        if (l1 == c1 && l2 == c2) {
+            cpu_stw_data_ra(env, a1, u1, ra);
+            cpu_stw_data_ra(env, a2, u2, ra);
+        }
+    }
+
+    if (c1 != l1) {
+        env->cc_n = l1;
+        env->cc_v = c1;
+    } else {
+        env->cc_n = l2;
+        env->cc_v = c2;
+    }
+    env->cc_op = CC_OP_CMPW;
+    env->dregs[Dc1] = deposit32(env->dregs[Dc1], 0, 16, l1);
+    env->dregs[Dc2] = deposit32(env->dregs[Dc2], 0, 16, l2);
+}
+
+void HELPER(cas2l)(CPUM68KState *env, uint32_t regs, uint32_t a1, uint32_t a2)
+{
+    uint32_t Dc1 = extract32(regs, 9, 3);
+    uint32_t Dc2 = extract32(regs, 6, 3);
+    uint32_t Du1 = extract32(regs, 3, 3);
+    uint32_t Du2 = extract32(regs, 0, 3);
+    uint32_t c1 = env->dregs[Dc1];
+    uint32_t c2 = env->dregs[Dc2];
+    uint32_t u1 = env->dregs[Du1];
+    uint32_t u2 = env->dregs[Du2];
+    uint32_t l1, l2;
+    uint64_t c, u, l;
+    uintptr_t ra = GETPC();
+#if defined(CONFIG_ATOMIC64) && !defined(CONFIG_USER_ONLY)
+    int mmu_idx = cpu_mmu_index(env, 0);
+    TCGMemOpIdx oi;
+#endif
+
+    if (parallel_cpus) {
+        /* We're executing in a parallel context -- must be atomic.  */
+#ifdef CONFIG_ATOMIC64
+        if ((a1 & 7) == 0 && a2 == a1 + 4) {
+            c = deposit64(c2, 32, 32, c1);
+            u = deposit64(u2, 32, 32, u1);
+#ifdef CONFIG_USER_ONLY
+            l = helper_atomic_cmpxchgq_be(env, a1, c, u);
+#else
+            oi = make_memop_idx(MO_BEQ, mmu_idx);
+            l = helper_atomic_cmpxchgq_be_mmu(env, a1, c, u, oi, ra);
+#endif
+            l1 = l >> 32;
+            l2 = l;
+        } else if ((a2 & 7) == 0 && a1 == a2 + 4) {
+            c = deposit64(c1, 32, 32, c2);
+            u = deposit64(u1, 32, 32, u2);
+#ifdef CONFIG_USER_ONLY
+            l = helper_atomic_cmpxchgq_be(env, a2, c, u);
+#else
+            oi = make_memop_idx(MO_BEQ, mmu_idx);
+            l = helper_atomic_cmpxchgq_be_mmu(env, a2, c, u, oi, ra);
+#endif
+            l2 = l >> 32;
+            l1 = l;
+        } else
+#endif
+        {
+            /* Tell the main loop we need to serialize this insn.  */
+            cpu_loop_exit_atomic(ENV_GET_CPU(env), ra);
+        }
+    } else {
+        /* We're executing in a serial context -- no need to be atomic.  */
+        l1 = cpu_ldl_data_ra(env, a1, ra);
+        l2 = cpu_ldl_data_ra(env, a2, ra);
+        if (l1 == c1 && l2 == c2) {
+            cpu_stl_data_ra(env, a1, u1, ra);
+            cpu_stl_data_ra(env, a2, u2, ra);
+        }
+    }
+
+    if (c1 != l1) {
+        env->cc_n = l1;
+        env->cc_v = c1;
+    } else {
+        env->cc_n = l2;
+        env->cc_v = c2;
+    }
+    env->cc_op = CC_OP_CMPL;
+    env->dregs[Dc1] = l1;
+    env->dregs[Dc2] = l2;
+}
diff --git a/target-m68k/translate.c b/target-m68k/translate.c
index f4eba90..5bd6d9e 100644
--- a/target-m68k/translate.c
+++ b/target-m68k/translate.c
@@ -1878,6 +1878,154 @@ DISAS_INSN(arith_im)
     tcg_temp_free(dest);
 }
 
+DISAS_INSN(cas)
+{
+    int opsize;
+    TCGv addr;
+    uint16_t ext;
+    TCGv load;
+    TCGv cmp;
+    TCGMemOp opc;
+
+    switch ((insn >> 9) & 3) {
+    case 1:
+        opsize = OS_BYTE;
+        opc = MO_UB;
+        break;
+    case 2:
+        opsize = OS_WORD;
+        opc = MO_TEUW;
+        break;
+    case 3:
+        opsize = OS_LONG;
+        opc = MO_TEUL;
+        break;
+    default:
+        g_assert_not_reached();
+    }
+    opc |= MO_ALIGN;
+
+    ext = read_im16(env, s);
+
+    /* cas Dc,Du,<EA> */
+
+    addr = gen_lea(env, s, insn, opsize);
+    if (IS_NULL_QREG(addr)) {
+        gen_addr_fault(s);
+        return;
+    }
+
+    cmp = gen_extend(DREG(ext, 0), opsize, 0);
+
+    /* if  <EA> == Dc then
+     *     <EA> = Du
+     *     Dc = <EA> (because <EA> == Dc)
+     * else
+     *     Dc = <EA>
+     */
+
+    load = tcg_temp_new();
+    tcg_gen_atomic_cmpxchg_i32(load, addr, cmp, DREG(ext, 6),
+                               IS_USER(s), opc);
+    gen_partset_reg(opsize, DREG(ext, 0), load);
+
+    gen_update_cc_cmp(s, load, cmp, opsize);
+    tcg_temp_free(load);
+}
+
+DISAS_INSN(cas2w)
+{
+    uint16_t ext1, ext2;
+    TCGv addr1, addr2;
+    TCGv regs;
+
+    /* cas2 Dc1:Dc2,Du1:Du2,(Rn1):(Rn2) */
+
+    ext1 = read_im16(env, s);
+
+    if (ext1 & 0x8000) {
+        /* Address Register */
+        addr1 = AREG(ext1, 12);
+    } else {
+        /* Data Register */
+        addr1 = DREG(ext1, 12);
+    }
+
+    ext2 = read_im16(env, s);
+    if (ext2 & 0x8000) {
+        /* Address Register */
+        addr2 = AREG(ext2, 12);
+    } else {
+        /* Data Register */
+        addr2 = DREG(ext2, 12);
+    }
+
+    /* if (R1) == Dc1 && (R2) == Dc2 then
+     *     (R1) = Du1
+     *     (R2) = Du2
+     * else
+     *     Dc1 = (R1)
+     *     Dc2 = (R2)
+     */
+
+    regs = tcg_const_i32(REG(ext2, 6) |
+                         (REG(ext1, 6) << 3) |
+                         (REG(ext2, 0) << 6) |
+                         (REG(ext1, 0) << 9));
+    gen_helper_cas2w(cpu_env, regs, addr1, addr2);
+    tcg_temp_free(regs);
+
+    /* Note that cas2w also assigned to env->cc_op.  */
+    s->cc_op = CC_OP_CMPW;
+    s->cc_op_synced = 1;
+}
+
+DISAS_INSN(cas2l)
+{
+    uint16_t ext1, ext2;
+    TCGv addr1, addr2, regs;
+
+    /* cas2 Dc1:Dc2,Du1:Du2,(Rn1):(Rn2) */
+
+    ext1 = read_im16(env, s);
+
+    if (ext1 & 0x8000) {
+        /* Address Register */
+        addr1 = AREG(ext1, 12);
+    } else {
+        /* Data Register */
+        addr1 = DREG(ext1, 12);
+    }
+
+    ext2 = read_im16(env, s);
+    if (ext2 & 0x8000) {
+        /* Address Register */
+        addr2 = AREG(ext2, 12);
+    } else {
+        /* Data Register */
+        addr2 = DREG(ext2, 12);
+    }
+
+    /* if (R1) == Dc1 && (R2) == Dc2 then
+     *     (R1) = Du1
+     *     (R2) = Du2
+     * else
+     *     Dc1 = (R1)
+     *     Dc2 = (R2)
+     */
+
+    regs = tcg_const_i32(REG(ext2, 6) |
+                         (REG(ext1, 6) << 3) |
+                         (REG(ext2, 0) << 6) |
+                         (REG(ext1, 0) << 9));
+    gen_helper_cas2l(cpu_env, regs, addr1, addr2);
+    tcg_temp_free(regs);
+
+    /* Note that cas2l also assigned to env->cc_op.  */
+    s->cc_op = CC_OP_CMPL;
+    s->cc_op_synced = 1;
+}
+
 DISAS_INSN(byterev)
 {
     TCGv reg;
@@ -3872,6 +4020,11 @@ void register_m68k_insns (CPUM68KState *env)
     INSN(arith_im,  0680, fff8, CF_ISA_A);
     INSN(arith_im,  0c00, ff38, CF_ISA_A);
     INSN(arith_im,  0c00, ff00, M68000);
+    INSN(cas,       0ac0, ffc0, CAS);
+    INSN(cas,       0cc0, ffc0, CAS);
+    INSN(cas,       0ec0, ffc0, CAS);
+    INSN(cas2w,     0cfc, ffff, CAS);
+    INSN(cas2l,     0efc, ffff, CAS);
     BASE(bitop_im,  0800, ffc0);
     BASE(bitop_im,  0840, ffc0);
     BASE(bitop_im,  0880, ffc0);
-- 
2.7.4

Re: [Qemu-devel] [PATCH v4 1/2] target-m68k: add abcd/sbcd/nbcd

[Richard Henderson]

On 11/08/2016 02:25 PM, Laurent Vivier wrote:
> Signed-off-by: Laurent Vivier <laurent@vivier.eu>
> Reviewed-by: Richard Henderson <rth@twiddle.net>
> ---
>  target-m68k/translate.c | 216 ++++++++++++++++++++++++++++++++++++++++++++++++
>  1 file changed, 216 insertions(+)

Reviewed-by: Richard Henderson <rth@twiddle.net>


r~

Re: [Qemu-devel] [PATCH v4 2/2] target-m68k: add cas/cas2 ops

[Richard Henderson]

On 11/08/2016 02:25 PM, Laurent Vivier wrote:
> Implement CAS using cmpxchg.
> Implement CAS2 using helper and either cmpxchg when
> the 32bit addresses are consecutive, or with
> parallel_cpus+cpu_loop_exit_atomic() otherwise.
>
> Suggested-by: Richard Henderson <rth@twiddle.net>
> Signed-off-by: Laurent Vivier <laurent@vivier.eu>
> ---
>  target-m68k/helper.h    |   2 +
>  target-m68k/op_helper.c | 109 ++++++++++++++++++++++++++++++++++
>  target-m68k/translate.c | 153 ++++++++++++++++++++++++++++++++++++++++++++++++
>  3 files changed, 264 insertions(+)

Reviewed-by: Richard Henderson <rth@twiddle.net>


r~