1 files changed, 31 insertions, 26 deletions

diff --git a/src/lj_ccall.c b/src/lj_ccall.c
index 04e306eb..9001cb5a 100644
--- a/src/lj_ccall.c
+++ b/src/lj_ccall.c
@@ -20,12 +20,15 @@
 #if LJ_TARGET_X86
 /* -- x86 calling conventions --------------------------------------------- */
 
+#define CCALL_PUSH(arg) \
+  *(GPRArg *)((uint8_t *)cc->stack + nsp) = (GPRArg)(arg), nsp += CTSIZE_PTR
+
 #if LJ_ABI_WIN
 
 #define CCALL_HANDLE_STRUCTRET \
   /* Return structs bigger than 8 by reference (on stack only). */ \
   cc->retref = (sz > 8); \
-  if (cc->retref) cc->stack[nsp++] = (GPRArg)dp;
+  if (cc->retref) CCALL_PUSH(dp);
 
 #define CCALL_HANDLE_COMPLEXRET CCALL_HANDLE_STRUCTRET
 
@@ -40,7 +43,7 @@
     if (ngpr < maxgpr) \
       cc->gpr[ngpr++] = (GPRArg)dp; \
     else \
-      cc->stack[nsp++] = (GPRArg)dp; \
+      CCALL_PUSH(dp); \
   } else {  /* Struct with single FP field ends up in FPR. */ \
     cc->resx87 = ccall_classify_struct(cts, ctr); \
   }
@@ -56,7 +59,7 @@
   if (ngpr < maxgpr) \
     cc->gpr[ngpr++] = (GPRArg)dp; \
   else \
-    cc->stack[nsp++] = (GPRArg)dp;
+    CCALL_PUSH(dp);
 
 #endif
 
@@ -67,7 +70,7 @@
     if (ngpr < maxgpr) \
       cc->gpr[ngpr++] = (GPRArg)dp; \
     else \
-      cc->stack[nsp++] = (GPRArg)dp; \
+      CCALL_PUSH(dp); \
   }
 
 #endif
@@ -278,8 +281,8 @@
   if (ngpr < maxgpr) { \
     dp = &cc->gpr[ngpr]; \
     if (ngpr + n > maxgpr) { \
-      nsp += ngpr + n - maxgpr;  /* Assumes contiguous gpr/stack fields. */ \
-      if (nsp > CCALL_MAXSTACK) goto err_nyi;  /* Too many arguments. */ \
+      nsp += (ngpr + n - maxgpr) * CTSIZE_PTR;  /* Assumes contiguous gpr/stack fields. */ \
+      if (nsp > CCALL_SIZE_STACK) goto err_nyi;  /* Too many arguments. */ \
       ngpr = maxgpr; \
     } else { \
       ngpr += n; \
@@ -471,8 +474,8 @@
   if (ngpr < maxgpr) { \
     dp = &cc->gpr[ngpr]; \
     if (ngpr + n > maxgpr) { \
-     nsp += ngpr + n - maxgpr;  /* Assumes contiguous gpr/stack fields. */ \
-     if (nsp > CCALL_MAXSTACK) goto err_nyi;  /* Too many arguments. */ \
+     nsp += (ngpr + n - maxgpr) * CTSIZE_PTR;  /* Assumes contiguous gpr/stack fields. */ \
+     if (nsp > CCALL_SIZE_STACK) goto err_nyi;  /* Too many arguments. */ \
      ngpr = maxgpr; \
     } else { \
      ngpr += n; \
@@ -565,8 +568,8 @@
   if (ngpr < maxgpr) { \
     dp = &cc->gpr[ngpr]; \
     if (ngpr + n > maxgpr) { \
-      nsp += ngpr + n - maxgpr;  /* Assumes contiguous gpr/stack fields. */ \
-      if (nsp > CCALL_MAXSTACK) goto err_nyi;  /* Too many arguments. */ \
+      nsp += (ngpr + n - maxgpr) * CTSIZE_PTR;  /* Assumes contiguous gpr/stack fields. */ \
+      if (nsp > CCALL_SIZE_STACK) goto err_nyi;  /* Too many arguments. */ \
       ngpr = maxgpr; \
     } else { \
       ngpr += n; \
@@ -698,10 +701,11 @@ static int ccall_struct_arg(CCallState *cc, CTState *cts, CType *d, int *rcl,
   lj_cconv_ct_tv(cts, d, (uint8_t *)dp, o, CCF_ARG(narg));
   if (ccall_struct_reg(cc, cts, dp, rcl)) {
     /* Register overflow? Pass on stack. */
-    MSize nsp = cc->nsp, n = rcl[1] ? 2 : 1;
-    if (nsp + n > CCALL_MAXSTACK) return 1;  /* Too many arguments. */
-    cc->nsp = nsp + n;
-    memcpy(&cc->stack[nsp], dp, n*CTSIZE_PTR);
+    MSize nsp = cc->nsp, sz = rcl[1] ? 2*CTSIZE_PTR : CTSIZE_PTR;
+    if (nsp + sz > CCALL_SIZE_STACK)
+      return 1;  /* Too many arguments. */
+    cc->nsp = nsp + sz;
+    memcpy((uint8_t *)cc->stack + nsp, dp, sz);
   }
   return 0;  /* Ok. */
 }
@@ -1022,22 +1026,23 @@ static int ccall_set_args(lua_State *L, CTState *cts, CType *ct,
     } else {
       sz = CTSIZE_PTR;
     }
-    sz = (sz + CTSIZE_PTR-1) & ~(CTSIZE_PTR-1);
-    n = sz / CTSIZE_PTR;  /* Number of GPRs or stack slots needed. */
+    n = (sz + CTSIZE_PTR-1) / CTSIZE_PTR;  /* Number of GPRs or stack slots needed. */
 
     CCALL_HANDLE_REGARG  /* Handle register arguments. */
 
     /* Otherwise pass argument on stack. */
-    if (CCALL_ALIGN_STACKARG && !rp && (d->info & CTF_ALIGN) > CTALIGN_PTR) {
-      MSize align = (1u << ctype_align(d->info-CTALIGN_PTR)) -1;
-      nsp = (nsp + align) & ~align;  /* Align argument on stack. */
+    if (CCALL_ALIGN_STACKARG) {  /* Align argument on stack. */
+      MSize align = (1u << ctype_align(d->info)) - 1;
+      if (rp)
+        align = CTSIZE_PTR-1;
+      nsp = (nsp + align) & ~align;
     }
-    if (nsp + n > CCALL_MAXSTACK) {  /* Too many arguments. */
+    dp = ((uint8_t *)cc->stack) + nsp;
+    nsp += n * CTSIZE_PTR;
+    if (nsp > CCALL_SIZE_STACK) {  /* Too many arguments. */
     err_nyi:
       lj_err_caller(L, LJ_ERR_FFI_NYICALL);
     }
-    dp = &cc->stack[nsp];
-    nsp += n;
     isva = 0;
 
   done:
@@ -1099,10 +1104,10 @@ static int ccall_set_args(lua_State *L, CTState *cts, CType *ct,
 #if LJ_TARGET_X64 || (LJ_TARGET_PPC && !LJ_ABI_SOFTFP)
   cc->nfpr = nfpr;  /* Required for vararg functions. */
 #endif
-  cc->nsp = nsp;
-  cc->spadj = (CCALL_SPS_FREE + CCALL_SPS_EXTRA)*CTSIZE_PTR;
-  if (nsp > CCALL_SPS_FREE)
-    cc->spadj += (((nsp-CCALL_SPS_FREE)*CTSIZE_PTR + 15u) & ~15u);
+  cc->nsp = (nsp + CTSIZE_PTR-1) & ~(CTSIZE_PTR-1);
+  cc->spadj = (CCALL_SPS_FREE + CCALL_SPS_EXTRA) * CTSIZE_PTR;
+  if (cc->nsp > CCALL_SPS_FREE * CTSIZE_PTR)
+    cc->spadj += (((cc->nsp - CCALL_SPS_FREE * CTSIZE_PTR) + 15u) & ~15u);
   return gcsteps;
 }