Add ppc64 little-endian support for luajit2

dynasm/dasm_ppc.lua

@@ -257,9 +257,11 @@ map_op = {
   addic_3 =	"30000000RRI",
   ["addic._3"] = "34000000RRI",
   addi_3 =	"38000000RR0I",
+  addil_3 =	"38000000RR0J",
   li_2 =	"38000000RI",
   la_2 =	"38000000RD",
   addis_3 =	"3c000000RR0I",
+  addisl_3 =	"3c000000RR0J",
   lis_2 =	"3c000000RI",
   lus_2 =	"3c000000RU",
   bc_3 =	"40000000AAK",
@@ -842,6 +844,9 @@ map_op = {
   srdi_3 =	op_alias("rldicl_4", function(p)
     p[4] = p[3]; p[3] = "64-("..p[3]..")"
   end),
+  ["srdi._3"] =	op_alias("rldicl._4", function(p)
+    p[4] = p[3]; p[3] = "64-("..p[3]..")"
+  end),
   clrldi_3 =	op_alias("rldicl_4", function(p)
     p[4] = p[3]; p[3] = "0"
   end),

src/Makefile

@@ -463,7 +463,16 @@ ifeq (ppc,$(TARGET_LJARCH))
     DASM_AFLAGS+= -D GPR64
   endif
   ifeq (PS3,$(TARGET_SYS))
-    DASM_AFLAGS+= -D PPE -D TOC
+    DASM_AFLAGS+= -D PPE
+  endif
+  ifneq (,$(findstring LJ_ARCH_PPC_OPD 1,$(TARGET_TESTARCH)))
+    DASM_AFLAGS+= -D OPD
+  endif
+  ifneq (,$(findstring LJ_ARCH_PPC_OPDENV 1,$(TARGET_TESTARCH)))
+    DASM_AFLAGS+= -D OPDENV
+  endif
+  ifneq (,$(findstring LJ_ARCH_PPC_ELFV2 1,$(TARGET_TESTARCH)))
+    DASM_AFLAGS+= -D ELFV2
   endif
 endif
 endif

src/host/buildvm_asm.c

@@ -188,7 +188,11 @@ static void emit_asm_wordreloc(BuildCtx *ctx, uint8_t *p, int n,
 #else
 #define TOCPREFIX ""
 #endif
-  if ((ins >> 26) == 16) {
+  if ((ins >> 26) == 14) {
+    fprintf(ctx->fp, "\taddi %d,%d,%s\n", (ins >> 21) & 31, (ins >> 16) & 31, sym);
+  } else if ((ins >> 26) == 15) {
+    fprintf(ctx->fp, "\taddis %d,%d,%s\n", (ins >> 21) & 31, (ins >> 16) & 31, sym);
+  } else if ((ins >> 26) == 16) {
     fprintf(ctx->fp, "\t%s %d, %d, " TOCPREFIX "%s\n",
 	    (ins & 1) ? "bcl" : "bc", (ins >> 21) & 31, (ins >> 16) & 31, sym);
   } else if ((ins >> 26) == 18) {
@@ -290,6 +294,9 @@ void emit_asm(BuildCtx *ctx)
   int i, rel;
 
   fprintf(ctx->fp, "\t.file \"buildvm_%s.dasc\"\n", ctx->dasm_arch);
+#if LJ_ARCH_PPC_ELFV2
+  fprintf(ctx->fp, "\t.abiversion 2\n");
+#endif
   fprintf(ctx->fp, "\t.text\n");
   emit_asm_align(ctx, 4);
 

src/lj_arch.h

@@ -299,8 +299,18 @@
 #if LJ_TARGET_CONSOLE
 #define LJ_ARCH_PPC32ON64	1
 #define LJ_ARCH_NOFFI		1
+#if LJ_TARGET_PS3
+#define LJ_ARCH_PPC_OPD		1
+#endif
 #elif LJ_ARCH_BITS == 64
-#error "No support for PPC64"
+#define LJ_ARCH_PPC32ON64	1
+#define LJ_ARCH_NOJIT		1	/* NYI */
+#if _CALL_ELF == 2
+#define LJ_ARCH_PPC_ELFV2	1
+#else
+#define LJ_ARCH_PPC_OPD		1
+#define LJ_ARCH_PPC_OPDENV	1
+#endif
 #endif
 
 #if _ARCH_PWR7
@@ -482,9 +492,6 @@
 #error "No support for ILP32 model on ARM64"
 #endif
 #elif LJ_TARGET_PPC
-#if defined(_LITTLE_ENDIAN) && (!defined(_BYTE_ORDER) || (_BYTE_ORDER == _LITTLE_ENDIAN))
-#error "No support for little-endian PPC32"
-#endif
 #if defined(__NO_FPRS__) && !defined(_SOFT_FLOAT)
 #error "No support for PPC/e500 anymore (use LuaJIT 2.0)"
 #endif

src/lj_ccall.c

@@ -370,21 +370,97 @@
 #elif LJ_TARGET_PPC
 /* -- PPC calling conventions --------------------------------------------- */
 
+#if LJ_ARCH_BITS == 64
+
+#if LJ_ARCH_PPC_ELFV2
+
+#define CCALL_HANDLE_STRUCTRET \
+  if (sz > 16 && ccall_classify_fp(cts, ctr) <= 0) { \
+    cc->retref = 1;  /* Return by reference. */ \
+    cc->gpr[ngpr++] = (GPRArg)dp; \
+  }
+
+#define CCALL_HANDLE_STRUCTRET2 \
+  int isfp = ccall_classify_fp(cts, ctr); \
+  int i; \
+  if (isfp == FTYPE_FLOAT) { \
+    for (i = 0; i < ctr->size / 4; i++) \
+      ((float *)dp)[i] = cc->fpr[i]; \
+  } else if (isfp == FTYPE_DOUBLE) { \
+    for (i = 0; i < ctr->size / 8; i++) \
+      ((double *)dp)[i] = cc->fpr[i]; \
+  } else { \
+    if (ctr->size < 8 && LJ_BE) { \
+      sp += 8 - ctr->size; \
+    } \
+    memcpy(dp, sp, ctr->size); \
+  }
+
+#else
+
 #define CCALL_HANDLE_STRUCTRET \
   cc->retref = 1;  /* Return all structs by reference. */ \
   cc->gpr[ngpr++] = (GPRArg)dp;
 
+#endif
+
 #define CCALL_HANDLE_COMPLEXRET \
   /* Complex values are returned in 2 or 4 GPRs. */ \
   cc->retref = 0;
 
+#define CCALL_HANDLE_STRUCTARG
+
 #define CCALL_HANDLE_COMPLEXRET2 \
-  memcpy(dp, sp, ctr->size);  /* Copy complex from GPRs. */
+  if (ctr->size == 2*sizeof(float)) {  /* Copy complex float from FPRs. */ \
+    ((float *)dp)[0] = cc->fpr[0]; \
+    ((float *)dp)[1] = cc->fpr[1]; \
+  } else {  /* Copy complex double from FPRs. */ \
+    ((double *)dp)[0] = cc->fpr[0]; \
+    ((double *)dp)[1] = cc->fpr[1]; \
+  }
+
+#define CCALL_HANDLE_COMPLEXARG \
+  isfp = 1; \
+  if (d->size == sizeof(float) * 2) { \
+    d = ctype_get(cts, CTID_COMPLEX_DOUBLE); \
+    isf32 = 1; \
+  }
+
+#define CCALL_HANDLE_REGARG \
+  if (isfp && d->size == sizeof(float)) { \
+    d = ctype_get(cts, CTID_DOUBLE); \
+    isf32 = 1; \
+  } \
+  if (ngpr < maxgpr) { \
+   dp = &cc->gpr[ngpr]; \
+   ngpr += n; \
+   if (ngpr > maxgpr) { \
+     nsp += ngpr - 8; \
+     ngpr = 8; \
+     if (nsp > CCALL_MAXSTACK) { \
+       goto err_nyi; \
+     } \
+   } \
+   goto done; \
+  }
+
+#else
+
+#define CCALL_HANDLE_STRUCTRET \
+  cc->retref = 1;  /* Return all structs by reference. */ \
+  cc->gpr[ngpr++] = (GPRArg)dp;
+
+#define CCALL_HANDLE_COMPLEXRET \
+  /* Complex values are returned in 2 or 4 GPRs. */ \
+  cc->retref = 0;
 
 #define CCALL_HANDLE_STRUCTARG \
   rp = cdataptr(lj_cdata_new(cts, did, sz)); \
   sz = CTSIZE_PTR;  /* Pass all structs by reference. */
 
+#define CCALL_HANDLE_COMPLEXRET2 \
+  memcpy(dp, sp, ctr->size);  /* Copy complex from GPRs. */
+
 #define CCALL_HANDLE_COMPLEXARG \
   /* Pass complex by value in 2 or 4 GPRs. */
 
@@ -419,6 +495,8 @@
   }
 #endif
 
+#endif
+
 #if !LJ_ABI_SOFTFP
 #define CCALL_HANDLE_RET \
   if (ctype_isfp(ctr->info) && ctr->size == sizeof(float)) \
@@ -846,6 +924,50 @@ static unsigned int ccall_classify_struct(CTState *cts, CType *ct)
 
 #endif
 
+/* -- PowerPC64 ELFv2 ABI struct classification ------------------- */
+
+#if LJ_ARCH_PPC_ELFV2
+
+#define FTYPE_FLOAT	1
+#define FTYPE_DOUBLE	2
+
+static unsigned int ccall_classify_fp(CTState *cts, CType *ct) {
+  if (ctype_isfp(ct->info)) {
+    if (ct->size == sizeof(float))
+      return FTYPE_FLOAT;
+    else
+      return FTYPE_DOUBLE;
+  } else if (ctype_iscomplex(ct->info)) {
+    if (ct->size == sizeof(float) * 2)
+      return FTYPE_FLOAT;
+    else
+      return FTYPE_DOUBLE;
+  } else if (ctype_isstruct(ct->info)) {
+    int res = -1;
+    int sz = ct->size;
+    while (ct->sib) {
+      ct = ctype_get(cts, ct->sib);
+      if (ctype_isfield(ct->info)) {
+        int sub = ccall_classify_fp(cts, ctype_rawchild(cts, ct));
+        if (res == -1)
+          res = sub;
+        if (sub != -1 && sub != res)
+          return 0;
+      } else if (ctype_isbitfield(ct->info) ||
+        ctype_isxattrib(ct->info, CTA_SUBTYPE)) {
+        return 0;
+      }
+    }
+    if (res > 0 && sz > res * 4 * 8)
+      return 0;
+    return res;
+  } else {
+    return 0;
+  }
+}
+
+#endif
+
 /* -- MIPS64 ABI struct classification ---------------------------- */
 
 #if LJ_TARGET_MIPS64
@@ -1020,6 +1142,9 @@ static int ccall_set_args(lua_State *L, CTState *cts, CType *ct,
     CTSize sz;
     MSize n, isfp = 0, isva = 0;
     void *dp, *rp = NULL;
+#if LJ_TARGET_PPC && LJ_ARCH_BITS == 64
+    int isf32 = 0;
+#endif
 
 #if LJ_TARGET_S390X
     uint32_t onstack = 0;
@@ -1083,7 +1208,37 @@ static int ccall_set_args(lua_State *L, CTState *cts, CType *ct,
       *(void **)dp = rp;
       dp = rp;
     }
+#if LJ_TARGET_PPC && LJ_ARCH_BITS == 64 && LJ_BE
+    if (ctype_isstruct(d->info) && sz < CTSIZE_PTR) {
+      dp = (char *)dp + (CTSIZE_PTR - sz);
+    }
+#endif
     lj_cconv_ct_tv(cts, d, (uint8_t *)dp, o, CCF_ARG(narg));
+#if LJ_TARGET_PPC && LJ_ARCH_BITS == 64
+    if (isfp) {
+      int i;
+      for (i = 0; i < d->size / 8 && nfpr < CCALL_NARG_FPR; i++)
+        cc->fpr[nfpr++] = ((double *)dp)[i];
+    }
+    if (isf32) {
+      int i;
+      for (i = 0; i < d->size / 8; i++)
+        ((float *)dp)[i*2] = ((double *)dp)[i];
+    }
+#endif
+#if LJ_ARCH_PPC_ELFV2
+    if (ctype_isstruct(d->info)) {
+      isfp = ccall_classify_fp(cts, d);
+      int i;
+      if (isfp == FTYPE_FLOAT) {
+        for (i = 0; i < d->size / 4 && nfpr < CCALL_NARG_FPR; i++)
+          cc->fpr[nfpr++] = ((float *)dp)[i];
+      } else if (isfp == FTYPE_DOUBLE) {
+        for (i = 0; i < d->size / 8 && nfpr < CCALL_NARG_FPR; i++)
+          cc->fpr[nfpr++] = ((double *)dp)[i];
+      }
+    }
+#endif
     /* Extend passed integers to 32 bits at least. */
     if (ctype_isinteger_or_bool(d->info) && d->size < 4) {
       if (d->info & CTF_UNSIGNED)
@@ -1097,6 +1252,15 @@ static int ccall_set_args(lua_State *L, CTState *cts, CType *ct,
     if (isfp && d->size == sizeof(float))
       ((float *)dp)[1] = ((float *)dp)[0];  /* Floats occupy high slot. */
 #endif
+#if LJ_TARGET_PPC && LJ_ARCH_BITS == 64
+    if ((ctype_isinteger_or_bool(d->info) || ctype_isenum(d->info))
+	&& d->size <= 4) {
+      if (d->info & CTF_UNSIGNED)
+	*(uint64_t *)dp = (uint64_t)*(uint32_t *)dp;
+      else
+        *(int64_t *)dp = (int64_t)*(int32_t *)dp;
+    }
+#endif
 #if LJ_TARGET_MIPS64 || (LJ_TARGET_ARM64 && LJ_BE)
     if ((ctype_isinteger_or_bool(d->info) || ctype_isenum(d->info)
 #if LJ_TARGET_MIPS64

src/lj_ccall.h

@@ -86,10 +86,23 @@ typedef union FPRArg {
 #elif LJ_TARGET_PPC
 
 #define CCALL_NARG_GPR		8
+#if LJ_ARCH_BITS == 64
+#define CCALL_NARG_FPR		13
+#if LJ_ARCH_PPC_ELFV2
+#define CCALL_NRET_GPR		2
+#define CCALL_NRET_FPR		8
+#define CCALL_SPS_EXTRA		14
+#else
+#define CCALL_NRET_GPR		1
+#define CCALL_NRET_FPR		2
+#define CCALL_SPS_EXTRA		16
+#endif
+#else
 #define CCALL_NARG_FPR		(LJ_ABI_SOFTFP ? 0 : 8)
 #define CCALL_NRET_GPR		4	/* For complex double. */
 #define CCALL_NRET_FPR		(LJ_ABI_SOFTFP ? 0 : 1)
 #define CCALL_SPS_EXTRA		4
+#endif
 #define CCALL_SPS_FREE		0
 
 typedef intptr_t GPRArg;