Fix base register coalescing in side trace.

Thanks to Sergey Kaplun, NiLuJe and Peter Cawley. #1031 #1016

diff --git a/src/lj_asm.c b/src/lj_asm.c
index cfdfa99f5ccd65121b76349698bf714decd219dd..1708c360a03656b1db332f55013c0d383f236dd5 100644 (file)
--- a/src/lj_asm.c
+++ b/src/lj_asm.c
@@ -1366,6 +1366,7 @@ static void asm_head_side(ASMState *as)
   RegSet allow = RSET_ALL;  /* Inverse of all coalesced registers. */
   RegSet live = RSET_EMPTY;  /* Live parent registers. */
   RegSet pallow = RSET_GPR;  /* Registers needed by the parent stack check. */
+  Reg pbase;
   IRIns *irp = &as->parent->ir[REF_BASE];  /* Parent base. */
   int32_t spadj, spdelta;
   int pass2 = 0;
@@ -1377,7 +1378,11 @@ static void asm_head_side(ASMState *as)
     as->snapno = 0;
     asm_snap_alloc(as);
   }
-  allow = asm_head_side_base(as, irp, allow);
+  pbase = asm_head_side_base(as, irp);
+  if (pbase != RID_NONE) {
+    rset_clear(allow, pbase);
+    rset_clear(pallow, pbase);
+  }
 
   /* Scan all parent SLOADs and collect register dependencies. */
   for (i = as->stopins; i > REF_BASE; i--) {

diff --git a/src/lj_asm_arm.h b/src/lj_asm_arm.h
index 262fa59e79ffa30e6136ea5c7be8f862d6eea004..57575874e7176f03650d62b5e4065025558792d8 100644 (file)
--- a/src/lj_asm_arm.h
+++ b/src/lj_asm_arm.h
@@ -2114,7 +2114,7 @@ static void asm_head_root_base(ASMState *as)
 }
 
 /* Coalesce BASE register for a side trace. */
-static RegSet asm_head_side_base(ASMState *as, IRIns *irp, RegSet allow)
+static Reg asm_head_side_base(ASMState *as, IRIns *irp)
 {
   IRIns *ir;
   asm_head_lreg(as);
@@ -2122,16 +2122,15 @@ static RegSet asm_head_side_base(ASMState *as, IRIns *irp, RegSet allow)
   if (ra_hasreg(ir->r) && (rset_test(as->modset, ir->r) || irt_ismarked(ir->t)))
     ra_spill(as, ir);
   if (ra_hasspill(irp->s)) {
-    rset_clear(allow, ra_dest(as, ir, allow));
+    return ra_dest(as, ir, RSET_GPR);
   } else {
     Reg r = irp->r;
     lua_assert(ra_hasreg(r));
-    rset_clear(allow, r);
     if (r != ir->r && !rset_test(as->freeset, r))
       ra_restore(as, regcost_ref(as->cost[r]));
     ra_destreg(as, ir, r);
+    return r;
   }
-  return allow;
 }
 
 /* -- Tail of trace ------------------------------------------------------- */

diff --git a/src/lj_asm_mips.h b/src/lj_asm_mips.h
index 1d4c8a25a8af6affe0fe3d99c6490d9862432300..10a5dbe97157188672cc29ea7c79b66e93e7d78d 100644 (file)
--- a/src/lj_asm_mips.h
+++ b/src/lj_asm_mips.h
@@ -1732,7 +1732,7 @@ static void asm_head_root_base(ASMState *as)
 }
 
 /* Coalesce BASE register for a side trace. */
-static RegSet asm_head_side_base(ASMState *as, IRIns *irp, RegSet allow)
+static Reg asm_head_side_base(ASMState *as, IRIns *irp)
 {
   IRIns *ir = IR(REF_BASE);
   Reg r = ir->r;
@@ -1742,15 +1742,15 @@ static RegSet asm_head_side_base(ASMState *as, IRIns *irp, RegSet allow)
     if (rset_test(as->modset, r) || irt_ismarked(ir->t))
       ir->r = RID_INIT;  /* No inheritance for modified BASE register. */
     if (irp->r == r) {
-      rset_clear(allow, r);  /* Mark same BASE register as coalesced. */
+      return r;  /* Same BASE register already coalesced. */
     } else if (ra_hasreg(irp->r) && rset_test(as->freeset, irp->r)) {
-      rset_clear(allow, irp->r);
       emit_move(as, r, irp->r);  /* Move from coalesced parent reg. */
+      return irp->r;
     } else {
       emit_getgl(as, r, jit_base);  /* Otherwise reload BASE. */
     }
   }
-  return allow;
+  return RID_NONE;
 }
 
 /* -- Tail of trace ------------------------------------------------------- */

diff --git a/src/lj_asm_ppc.h b/src/lj_asm_ppc.h
index 5fd35d2e6dd5bac2a3d7bdbb41f6218658c0059b..d7d743a66431351c407d6450b9d494639cd9e698 100644 (file)
--- a/src/lj_asm_ppc.h
+++ b/src/lj_asm_ppc.h
@@ -1915,7 +1915,7 @@ static void asm_head_root_base(ASMState *as)
 }
 
 /* Coalesce BASE register for a side trace. */
-static RegSet asm_head_side_base(ASMState *as, IRIns *irp, RegSet allow)
+static Reg asm_head_side_base(ASMState *as, IRIns *irp)
 {
   IRIns *ir = IR(REF_BASE);
   Reg r = ir->r;
@@ -1924,15 +1924,15 @@ static RegSet asm_head_side_base(ASMState *as, IRIns *irp, RegSet allow)
     if (rset_test(as->modset, r) || irt_ismarked(ir->t))
       ir->r = RID_INIT;  /* No inheritance for modified BASE register. */
     if (irp->r == r) {
-      rset_clear(allow, r);  /* Mark same BASE register as coalesced. */
+      return r;  /* Same BASE register already coalesced. */
     } else if (ra_hasreg(irp->r) && rset_test(as->freeset, irp->r)) {
-      rset_clear(allow, irp->r);
       emit_mr(as, r, irp->r);  /* Move from coalesced parent reg. */
+      return irp->r;
     } else {
       emit_getgl(as, r, jit_base);  /* Otherwise reload BASE. */
     }
   }
-  return allow;
+  return RID_NONE;
 }
 
 /* -- Tail of trace ------------------------------------------------------- */

diff --git a/src/lj_asm_x86.h b/src/lj_asm_x86.h
index 8b529086e1c11bd5827b3d8f518ea9da3610c42f..bfbdb112aa32d2c3a114922f467fbe73e3ade7d3 100644 (file)
--- a/src/lj_asm_x86.h
+++ b/src/lj_asm_x86.h
@@ -2502,7 +2502,7 @@ static void asm_head_root_base(ASMState *as)
 }
 
 /* Coalesce or reload BASE register for a side trace. */
-static RegSet asm_head_side_base(ASMState *as, IRIns *irp, RegSet allow)
+static Reg asm_head_side_base(ASMState *as, IRIns *irp)
 {
   IRIns *ir = IR(REF_BASE);
   Reg r = ir->r;
@@ -2511,15 +2511,15 @@ static RegSet asm_head_side_base(ASMState *as, IRIns *irp, RegSet allow)
     if (rset_test(as->modset, r) || irt_ismarked(ir->t))
       ir->r = RID_INIT;  /* No inheritance for modified BASE register. */
     if (irp->r == r) {
-      rset_clear(allow, r);  /* Mark same BASE register as coalesced. */
+      return r;  /* Same BASE register already coalesced. */
     } else if (ra_hasreg(irp->r) && rset_test(as->freeset, irp->r)) {
-      rset_clear(allow, irp->r);
       emit_rr(as, XO_MOV, r, irp->r);  /* Move from coalesced parent reg. */
+      return irp->r;
     } else {
       emit_getgl(as, r, jit_base);  /* Otherwise reload BASE. */
     }
   }
-  return allow;
+  return RID_NONE;
 }
 
 /* -- Tail of trace ------------------------------------------------------- */