[PATCH] tcg/ppc: Use new registers for LQ destination

[Richard Henderson]

LQ has a constraint that RTp != RA, else SIGILL.
Therefore, force the destination of INDEX_op_qemu_*_ld128 to be a
new register pair, so that it cannot overlap the input address.

This requires new support in process_op_defs and tcg_reg_alloc_op.

Cc: qemu-stable@nongnu.org
Fixes: 526cd4ec01f ("tcg/ppc: Support 128-bit load/store")
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---

This bug may be triggered with qemu-aarch64 and
tests/tcg/multiarch/linux-test.c.

r~

---
 tcg/ppc/tcg-target-con-set.h |  2 +-
 tcg/tcg.c                    | 21 ++++++++++++++++-----
 tcg/ppc/tcg-target.c.inc     |  3 ++-
 3 files changed, 19 insertions(+), 7 deletions(-)

diff --git a/tcg/ppc/tcg-target-con-set.h b/tcg/ppc/tcg-target-con-set.h
index bbd7b21247..cb47b29452 100644
--- a/tcg/ppc/tcg-target-con-set.h
+++ b/tcg/ppc/tcg-target-con-set.h
@@ -35,7 +35,7 @@ C_O1_I3(v, v, v, v)
 C_O1_I4(r, r, ri, rZ, rZ)
 C_O1_I4(r, r, r, ri, ri)
 C_O2_I1(r, r, r)
-C_O2_I1(o, m, r)
+C_N1O1_I1(o, m, r)
 C_O2_I2(r, r, r, r)
 C_O2_I4(r, r, rI, rZM, r, r)
 C_O2_I4(r, r, r, r, rI, rZM)
diff --git a/tcg/tcg.c b/tcg/tcg.c
index 896a36caeb..e2c38f6d11 100644
--- a/tcg/tcg.c
+++ b/tcg/tcg.c
@@ -653,6 +653,7 @@ static void tcg_out_movext3(TCGContext *s, const 
TCGMovExtend *i1,
 #define C_O1_I4(O1, I1, I2, I3, I4)     C_PFX5(c_o1_i4_, O1, I1, I2, I3, I4),
 
 #define C_N1_I2(O1, I1, I2)             C_PFX3(c_n1_i2_, O1, I1, I2),
+#define C_N1O1_I1(O1, O2, I1)           C_PFX3(c_n1o1_i1_, O1, O2, I1),
 #define C_N2_I1(O1, O2, I1)             C_PFX3(c_n2_i1_, O1, O2, I1),
 
 #define C_O2_I1(O1, O2, I1)             C_PFX3(c_o2_i1_, O1, O2, I1),
@@ -676,6 +677,7 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode);
 #undef C_O1_I3
 #undef C_O1_I4
 #undef C_N1_I2
+#undef C_N1O1_I1
 #undef C_N2_I1
 #undef C_O2_I1
 #undef C_O2_I2
@@ -696,6 +698,7 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode);
 #define C_O1_I4(O1, I1, I2, I3, I4)     { .args_ct_str = { #O1, #I1, #I2, #I3, 
#I4 } },
 
 #define C_N1_I2(O1, I1, I2)             { .args_ct_str = { "&" #O1, #I1, #I2 } 
},
+#define C_N1O1_I1(O1, O2, I1)           { .args_ct_str = { "&" #O1, #O2, #I1 } 
},
 #define C_N2_I1(O1, O2, I1)             { .args_ct_str = { "&" #O1, "&" #O2, 
#I1 } },
 
 #define C_O2_I1(O1, O2, I1)             { .args_ct_str = { #O1, #O2, #I1 } },
@@ -718,6 +721,7 @@ static const TCGTargetOpDef constraint_sets[] = {
 #undef C_O1_I3
 #undef C_O1_I4
 #undef C_N1_I2
+#undef C_N1O1_I1
 #undef C_N2_I1
 #undef C_O2_I1
 #undef C_O2_I2
@@ -738,6 +742,7 @@ static const TCGTargetOpDef constraint_sets[] = {
 #define C_O1_I4(O1, I1, I2, I3, I4)     C_PFX5(c_o1_i4_, O1, I1, I2, I3, I4)
 
 #define C_N1_I2(O1, I1, I2)             C_PFX3(c_n1_i2_, O1, I1, I2)
+#define C_N1O1_I1(O1, O2, I1)           C_PFX3(c_n1o1_i1_, O1, O2, I1)
 #define C_N2_I1(O1, O2, I1)             C_PFX3(c_n2_i1_, O1, O2, I1)
 
 #define C_O2_I1(O1, O2, I1)             C_PFX3(c_o2_i1_, O1, O2, I1)
@@ -2988,6 +2993,7 @@ static void process_op_defs(TCGContext *s)
                     .pair = 2,
                     .pair_index = o,
                     .regs = def->args_ct[o].regs << 1,
+                    .newreg = def->args_ct[o].newreg,
                 };
                 def->args_ct[o].pair = 1;
                 def->args_ct[o].pair_index = i;
@@ -3004,6 +3010,7 @@ static void process_op_defs(TCGContext *s)
                     .pair = 1,
                     .pair_index = o,
                     .regs = def->args_ct[o].regs >> 1,
+                    .newreg = def->args_ct[o].newreg,
                 };
                 def->args_ct[o].pair = 2;
                 def->args_ct[o].pair_index = i;
@@ -5036,17 +5043,21 @@ static void tcg_reg_alloc_op(TCGContext *s, const TCGOp 
*op)
                 break;
 
             case 1: /* first of pair */
-                tcg_debug_assert(!arg_ct->newreg);
                 if (arg_ct->oalias) {
                     reg = new_args[arg_ct->alias_index];
-                    break;
+                } else if (arg_ct->newreg) {
+                    reg = tcg_reg_alloc_pair(s, arg_ct->regs,
+                                             i_allocated_regs | 
o_allocated_regs,
+                                             output_pref(op, k),
+                                             ts->indirect_base);
+                } else {
+                    reg = tcg_reg_alloc_pair(s, arg_ct->regs, o_allocated_regs,
+                                             output_pref(op, k),
+                                             ts->indirect_base);
                 }
-                reg = tcg_reg_alloc_pair(s, arg_ct->regs, o_allocated_regs,
-                                         output_pref(op, k), 
ts->indirect_base);
                 break;
 
             case 2: /* second of pair */
-                tcg_debug_assert(!arg_ct->newreg);
                 if (arg_ct->oalias) {
                     reg = new_args[arg_ct->alias_index];
                 } else {
diff --git a/tcg/ppc/tcg-target.c.inc b/tcg/ppc/tcg-target.c.inc
index 856c3b18f5..54816967bc 100644
--- a/tcg/ppc/tcg-target.c.inc
+++ b/tcg/ppc/tcg-target.c.inc
@@ -2595,6 +2595,7 @@ static void tcg_out_qemu_ldst_i128(TCGContext *s, TCGReg 
datalo, TCGReg datahi,
         tcg_debug_assert(!need_bswap);
         tcg_debug_assert(datalo & 1);
         tcg_debug_assert(datahi == datalo - 1);
+        tcg_debug_assert(!is_ld || datahi != index);
         insn = is_ld ? LQ : STQ;
         tcg_out32(s, insn | TAI(datahi, index, 0));
     } else {
@@ -4071,7 +4072,7 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode 
op)
 
     case INDEX_op_qemu_ld_a32_i128:
     case INDEX_op_qemu_ld_a64_i128:
-        return C_O2_I1(o, m, r);
+        return C_N1O1_I1(o, m, r);
     case INDEX_op_qemu_st_a32_i128:
     case INDEX_op_qemu_st_a64_i128:
         return C_O0_I3(o, m, r);
-- 
2.34.1