FFI/ARM64/OSX: Handle non-standard OSX C calling conventions.

Contributed by Peter Cawley. #205

1 files changed, 60 insertions, 15 deletions

diff --git a/src/lj_asm_arm64.h b/src/lj_asm_arm64.h
index 1d5cca4f..3889883d 100644
--- a/src/lj_asm_arm64.h
+++ b/src/lj_asm_arm64.h
@@ -419,7 +419,7 @@ static int asm_fuseorshift(ASMState *as, IRIns *ir)
 static void asm_gencall(ASMState *as, const CCallInfo *ci, IRRef *args)
 {
   uint32_t n, nargs = CCI_XNARGS(ci);
-  int32_t ofs = 0;
+  int32_t spofs = 0, spalign = LJ_HASFFI && LJ_TARGET_OSX ? 0 : 7;
   Reg gpr, fpr = REGARG_FIRSTFPR;
   if (ci->func)
     emit_call(as, ci->func);
@@ -438,8 +438,14 @@ static void asm_gencall(ASMState *as, const CCallInfo *ci, IRRef *args)
           fpr++;
         } else {
           Reg r = ra_alloc1(as, ref, RSET_FPR);
-          emit_spstore(as, ir, r, ofs + ((LJ_BE && !irt_isnum(ir->t)) ? 4 : 0));
-          ofs += 8;
+          int32_t al = spalign;
+#if LJ_HASFFI && LJ_TARGET_OSX
+          al |= irt_isnum(ir->t) ? 7 : 3;
+#endif
+          spofs = (spofs + al) & ~al;
+          if (LJ_BE && al >= 7 && !irt_isnum(ir->t)) spofs += 4, al -= 4;
+          emit_spstore(as, ir, r, spofs);
+          spofs += al + 1;
         }
       } else {
         if (gpr <= REGARG_LASTGPR) {
@@ -449,10 +455,27 @@ static void asm_gencall(ASMState *as, const CCallInfo *ci, IRRef *args)
           gpr++;
         } else {
           Reg r = ra_alloc1(as, ref, RSET_GPR);
-          emit_spstore(as, ir, r, ofs + ((LJ_BE && !irt_is64(ir->t)) ? 4 : 0));
-          ofs += 8;
+          int32_t al = spalign;
+#if LJ_HASFFI && LJ_TARGET_OSX
+          al |= irt_size(ir->t) - 1;
+#endif
+          spofs = (spofs + al) & ~al;
+          if (al >= 3) {
+            if (LJ_BE && al >= 7 && !irt_is64(ir->t)) spofs += 4, al -= 4;
+            emit_spstore(as, ir, r, spofs);
+          } else {
+            lj_assertA(al == 0 || al == 1, "size %d unexpected", al + 1);
+            emit_lso(as, al ? A64I_STRH : A64I_STRB, r, RID_SP, spofs);
+          }
+          spofs += al + 1;
         }
       }
+#if LJ_HASFFI && LJ_TARGET_OSX
+    } else {  /* Marker for start of varargs. */
+      gpr = REGARG_LASTGPR+1;
+      fpr = REGARG_LASTFPR+1;
+      spalign = 7;
+#endif
     }
   }
 }
@@ -1976,19 +1999,41 @@ static void asm_tail_prep(ASMState *as)
 /* Ensure there are enough stack slots for call arguments. */
 static Reg asm_setup_call_slots(ASMState *as, IRIns *ir, const CCallInfo *ci)
 {
-  IRRef args[CCI_NARGS_MAX*2];
+#if LJ_HASFFI
   uint32_t i, nargs = CCI_XNARGS(ci);
-  int nslots = 0, ngpr = REGARG_NUMGPR, nfpr = REGARG_NUMFPR;
-  asm_collectargs(as, ir, ci, args);
-  for (i = 0; i < nargs; i++) {
-    if (args[i] && irt_isfp(IR(args[i])->t)) {
-      if (nfpr > 0) nfpr--; else nslots += 2;
-    } else {
-      if (ngpr > 0) ngpr--; else nslots += 2;
+  if (nargs > (REGARG_NUMGPR < REGARG_NUMFPR ? REGARG_NUMGPR : REGARG_NUMFPR) ||
+      (LJ_TARGET_OSX && (ci->flags & CCI_VARARG))) {
+    IRRef args[CCI_NARGS_MAX*2];
+    int ngpr = REGARG_NUMGPR, nfpr = REGARG_NUMFPR;
+    int spofs = 0, spalign = LJ_TARGET_OSX ? 0 : 7, nslots;
+    asm_collectargs(as, ir, ci, args);
+    for (i = 0; i < nargs; i++) {
+      int al = spalign;
+      if (!args[i]) {
+#if LJ_TARGET_OSX
+        /* Marker for start of varaargs. */
+        nfpr = 0;
+        ngpr = 0;
+        spalign = 7;
+#endif
+      } else if (irt_isfp(IR(args[i])->t)) {
+        if (nfpr > 0) { nfpr--; continue; }
+#if LJ_TARGET_OSX
+        al |= irt_isnum(IR(args[i])->t) ? 7 : 3;
+#endif
+      } else {
+        if (ngpr > 0) { ngpr--; continue; }
+#if LJ_TARGET_OSX
+        al |= irt_size(IR(args[i])->t) - 1;
+#endif
+      }
+      spofs = (spofs + 2*al+1) & ~al;  /* Align and bump stack pointer. */
     }
+    nslots = (spofs + 3) >> 2;
+    if (nslots > as->evenspill)  /* Leave room for args in stack slots. */
+      as->evenspill = nslots;
   }
-  if (nslots > as->evenspill)  /* Leave room for args in stack slots. */
-    as->evenspill = nslots;
+#endif
   return REGSP_HINT(RID_RET);
 }