4 files changed, 98 insertions, 21 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);
 }
 
diff --git a/src/lj_ccall.c b/src/lj_ccall.c
index 9001cb5a..00e753b9 100644
--- a/src/lj_ccall.c
+++ b/src/lj_ccall.c
@@ -348,7 +348,6 @@
       goto done; \
     } else { \
       nfpr = CCALL_NARG_FPR;  /* Prevent reordering. */ \
-      if (LJ_TARGET_OSX && d->size < 8) goto err_nyi; \
     } \
   } else {  /* Try to pass argument in GPRs. */ \
     if (!LJ_TARGET_OSX && (d->info & CTF_ALIGN) > CTALIGN_PTR) \
@@ -359,7 +358,6 @@
       goto done; \
     } else { \
       ngpr = maxgpr;  /* Prevent reordering. */ \
-      if (LJ_TARGET_OSX && d->size < 8) goto err_nyi; \
     } \
   }
 
@@ -1023,7 +1021,7 @@ static int ccall_set_args(lua_State *L, CTState *cts, CType *ct,
       CCALL_HANDLE_STRUCTARG
     } else if (ctype_iscomplex(d->info)) {
       CCALL_HANDLE_COMPLEXARG
-    } else {
+    } else if (!(CCALL_PACK_STACKARG && ctype_isenum(d->info))) {
       sz = CTSIZE_PTR;
     }
     n = (sz + CTSIZE_PTR-1) / CTSIZE_PTR;  /* Number of GPRs or stack slots needed. */
@@ -1033,12 +1031,12 @@ static int ccall_set_args(lua_State *L, CTState *cts, CType *ct,
     /* Otherwise pass argument on stack. */
     if (CCALL_ALIGN_STACKARG) {  /* Align argument on stack. */
       MSize align = (1u << ctype_align(d->info)) - 1;
-      if (rp)
+      if (rp || (CCALL_PACK_STACKARG && isva && align < CTSIZE_PTR-1))
         align = CTSIZE_PTR-1;
       nsp = (nsp + align) & ~align;
     }
     dp = ((uint8_t *)cc->stack) + nsp;
-    nsp += n * CTSIZE_PTR;
+    nsp += CCALL_PACK_STACKARG ? sz : n * CTSIZE_PTR;
     if (nsp > CCALL_SIZE_STACK) {  /* Too many arguments. */
     err_nyi:
       lj_err_caller(L, LJ_ERR_FFI_NYICALL);
@@ -1053,7 +1051,8 @@ static int ccall_set_args(lua_State *L, CTState *cts, CType *ct,
     }
     lj_cconv_ct_tv(cts, d, (uint8_t *)dp, o, CCF_ARG(narg));
     /* Extend passed integers to 32 bits at least. */
-    if (ctype_isinteger_or_bool(d->info) && d->size < 4) {
+    if (ctype_isinteger_or_bool(d->info) && d->size < 4 &&
+        (!CCALL_PACK_STACKARG || !((uintptr_t)dp & 3))) {  /* Assumes LJ_LE. */
       if (d->info & CTF_UNSIGNED)
         *(uint32_t *)dp = d->size == 1 ? (uint32_t)*(uint8_t *)dp :
                                          (uint32_t)*(uint16_t *)dp;
diff --git a/src/lj_ccall.h b/src/lj_ccall.h
index 57300817..24646d90 100644
--- a/src/lj_ccall.h
+++ b/src/lj_ccall.h
@@ -75,6 +75,9 @@ typedef union FPRArg {
 #define CCALL_NARG_FPR          8
 #define CCALL_NRET_FPR          4
 #define CCALL_SPS_FREE          0
+#if LJ_TARGET_OSX
+#define CCALL_PACK_STACKARG     1
+#endif
 
 typedef intptr_t GPRArg;
 typedef union FPRArg {
@@ -139,6 +142,9 @@ typedef union FPRArg {
 #ifndef CCALL_ALIGN_STACKARG
 #define CCALL_ALIGN_STACKARG    1
 #endif
+#ifndef CCALL_PACK_STACKARG
+#define CCALL_PACK_STACKARG     0
+#endif
 #ifndef CCALL_ALIGN_CALLSTATE
 #define CCALL_ALIGN_CALLSTATE   8
 #endif
diff --git a/src/lj_crecord.c b/src/lj_crecord.c
index 04bc895d..d7a522fb 100644
--- a/src/lj_crecord.c
+++ b/src/lj_crecord.c
@@ -1118,6 +1118,12 @@ static TRef crec_call_args(jit_State *J, RecordFFData *rd,
     ngpr = 1;
   else if (ctype_cconv(ct->info) == CTCC_FASTCALL)
     ngpr = 2;
+#elif LJ_TARGET_ARM64
+#if LJ_ABI_WIN
+#error "NYI: ARM64 Windows ABI calling conventions"
+#elif LJ_TARGET_OSX
+  int ngpr = CCALL_NARG_GPR;
+#endif
 #endif
 
   /* Skip initial attributes. */
@@ -1143,6 +1149,14 @@ static TRef crec_call_args(jit_State *J, RecordFFData *rd,
     } else {
       if (!(ct->info & CTF_VARARG))
         lj_trace_err(J, LJ_TRERR_NYICALL);  /* Too many arguments. */
+#if LJ_TARGET_ARM64 && LJ_TARGET_OSX
+      if (ngpr >= 0) {
+        ngpr = -1;
+        args[n++] = TREF_NIL;  /* Marker for start of varargs. */
+        if (n >= CCI_NARGS_MAX)
+          lj_trace_err(J, LJ_TRERR_NYICALL);
+      }
+#endif
       did = lj_ccall_ctid_vararg(cts, o);  /* Infer vararg type. */
     }
     d = ctype_raw(cts, did);
@@ -1151,6 +1165,15 @@ static TRef crec_call_args(jit_State *J, RecordFFData *rd,
       lj_trace_err(J, LJ_TRERR_NYICALL);
     tr = crec_ct_tv(J, d, 0, *base, o);
     if (ctype_isinteger_or_bool(d->info)) {
+#if LJ_TARGET_ARM64 && LJ_TARGET_OSX
+      if (!ngpr) {
+        /* Fixed args passed on the stack use their unpromoted size. */
+        if (d->size != lj_ir_type_size[tref_type(tr)]) {
+          lj_assertJ(d->size == 1 || d->size==2, "unexpected size %d", d->size);
+          tr = emitconv(tr, d->size==1 ? IRT_U8 : IRT_U16, tref_type(tr), 0);
+        }
+      } else
+#endif
       if (d->size < 4) {
         if ((d->info & CTF_UNSIGNED))
           tr = emitconv(tr, IRT_INT, d->size==1 ? IRT_U8 : IRT_U16, 0);
@@ -1188,6 +1211,10 @@ static TRef crec_call_args(jit_State *J, RecordFFData *rd,
       }
     }
 #endif
+#elif LJ_TARGET_ARM64 && LJ_TARGET_OSX
+    if (!ctype_isfp(d->info) && ngpr) {
+      ngpr--;
+    }
 #endif
     args[n] = tr;
   }