diff --git a/dynasm/dasm_ppc.lua b/dynasm/dasm_ppc.lua
index e2f704ec..1b0f9add 100644
--- a/dynasm/dasm_ppc.lua
+++ b/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),
diff --git a/src/host/buildvm_asm.c b/src/host/buildvm_asm.c
index 28419c07..5e5025e6 100644
--- a/src/host/buildvm_asm.c
+++ b/src/host/buildvm_asm.c
@@ -136,18 +136,14 @@ 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) {
-#if LJ_ARCH_PPC64
-    const char *suffix = strchr(sym, '@');
-    if (suffix && suffix[1] == 'h') {
-      fprintf(ctx->fp, "\taddis 11, 2, %s\n", sym);
-    } else if (suffix && suffix[1] == 'l') {
-      fprintf(ctx->fp, "\tld 12, %s\n", sym);
-    } else
-#endif
     fprintf(ctx->fp, "\t%s " TOCPREFIX "%s\n", (ins & 1) ? "bl" : "b", sym);
   } else {
     fprintf(stderr,
@@ -245,7 +241,7 @@ void emit_asm(BuildCtx *ctx)
   int i, rel;
 
   fprintf(ctx->fp, "\t.file \"buildvm_%s.dasc\"\n", ctx->dasm_arch);
-#if LJ_ARCH_PPC64
+#if LJ_ARCH_PPC_ELFV2
   fprintf(ctx->fp, "\t.abiversion 2\n");
 #endif
   fprintf(ctx->fp, "\t.text\n");
diff --git a/src/lj_arch.h b/src/lj_arch.h
index 159fd45d..12080e22 100644
--- a/src/lj_arch.h
+++ b/src/lj_arch.h
@@ -269,7 +269,6 @@
 #elif LJ_ARCH_BITS == 64
 #define LJ_ARCH_PPC32ON64	1
 #define LJ_ARCH_NOJIT		1	/* NYI */
-#define LJ_ARCH_NOFFI		1	/* NYI */
 #if _CALL_ELF == 2
 #define LJ_ARCH_PPC_ELFV2	1
 #else
diff --git a/src/lj_ccall.c b/src/lj_ccall.c
index b599be33..ee34b52f 100644
--- a/src/lj_ccall.c
+++ b/src/lj_ccall.c
@@ -362,6 +362,82 @@
 #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 \
+  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;
@@ -370,13 +446,13 @@
   /* Complex values are returned in 2 or 4 GPRs. */ \
   cc->retref = 0;
 
-#define CCALL_HANDLE_COMPLEXRET2 \
-  memcpy(dp, sp, ctr->size);  /* Copy complex from GPRs. */
-
 #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. */
 
@@ -403,6 +479,8 @@
     } \
   }
 
+#endif
+
 #define CCALL_HANDLE_RET \
   if (ctype_isfp(ctr->info) && ctr->size == sizeof(float)) \
     ctr = ctype_get(cts, CTID_DOUBLE);  /* FPRs always hold doubles. */
@@ -794,6 +872,50 @@ noth:  /* Not a homogeneous float/double aggregate. */
 
 #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
@@ -967,6 +1089,9 @@ 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 (fid) {  /* Get argument type from field. */
       CType *ctf = ctype_get(cts, fid);
@@ -1023,7 +1148,37 @@ 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)
@@ -1033,6 +1188,15 @@ static int ccall_set_args(lua_State *L, CTState *cts, CType *ct,
 	*(int32_t *)dp = d->size == 1 ? (int32_t)*(int8_t *)dp :
 					(int32_t)*(int16_t *)dp;
     }
+#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
     if ((ctype_isinteger_or_bool(d->info) || ctype_isenum(d->info) ||
 	 (isfp && nsp == 0)) && d->size <= 4) {
diff --git a/src/lj_ccall.h b/src/lj_ccall.h
index d97227a6..fcce7792 100644
--- a/src/lj_ccall.h
+++ b/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		8
 #define CCALL_NRET_GPR		4	/* For complex double. */
 #define CCALL_NRET_FPR		1
 #define CCALL_SPS_EXTRA		4
+#endif
 #define CCALL_SPS_FREE		0
 
 typedef intptr_t GPRArg;
diff --git a/src/lj_ccallback.c b/src/lj_ccallback.c
index 2ca6406c..c2a55c02 100644
--- a/src/lj_ccallback.c
+++ b/src/lj_ccallback.c
@@ -61,8 +61,24 @@ static MSize CALLBACK_OFS2SLOT(MSize ofs)
 
 #elif LJ_TARGET_PPC
 
+#if LJ_ARCH_PPC_OPD
+
+#define CALLBACK_SLOT2OFS(slot)		(24*(slot))
+#define CALLBACK_OFS2SLOT(ofs)		((ofs)/24)
+#define CALLBACK_MAX_SLOT		(CALLBACK_OFS2SLOT(CALLBACK_MCODE_SIZE))
+
+#elif LJ_ARCH_PPC_ELFV2
+
+#define CALLBACK_SLOT2OFS(slot)		(4*(slot))
+#define CALLBACK_OFS2SLOT(ofs)		((ofs)/4)
+#define CALLBACK_MAX_SLOT		(CALLBACK_MCODE_SIZE/4 - 10)
+
+#else
+
 #define CALLBACK_MCODE_HEAD		24
 
+#endif
+
 #elif LJ_TARGET_MIPS32
 
 #define CALLBACK_MCODE_HEAD		20
@@ -188,24 +204,59 @@ static void callback_mcode_init(global_State *g, uint32_t *page)
   lua_assert(p - page <= CALLBACK_MCODE_SIZE);
 }
 #elif LJ_TARGET_PPC
+#if LJ_ARCH_PPC_OPD
+register void *vm_toc __asm__("r2");
+static void callback_mcode_init(global_State *g, uint64_t *page)
+{
+  uint64_t *p = page;
+  void *target = (void *)lj_vm_ffi_callback;
+  MSize slot;
+  for (slot = 0; slot < CALLBACK_MAX_SLOT; slot++) {
+    *p++ = (uint64_t)target;
+    *p++ = (uint64_t)vm_toc;
+    *p++ = (uint64_t)g | ((uint64_t)slot << 47);
+  }
+  lua_assert(p - page <= CALLBACK_MCODE_SIZE / 8);
+}
+#else
 static void callback_mcode_init(global_State *g, uint32_t *page)
 {
   uint32_t *p = page;
   void *target = (void *)lj_vm_ffi_callback;
   MSize slot;
+#if LJ_ARCH_PPC_ELFV2
+  // Needs to be in sync with lj_vm_ffi_callback.
+  lua_assert(CALLBACK_MCODE_SIZE == 4096);
+  for (slot = 0; slot < CALLBACK_MAX_SLOT; slot++) {
+    *p = PPCI_B | (((page+CALLBACK_MAX_SLOT-p) & 0x00ffffffu) << 2);
+    p++;
+  }
+  *p++ = PPCI_LI | PPCF_T(RID_SYS1) | ((((intptr_t)target) >> 32) & 0xffff);
+  *p++ = PPCI_LI | PPCF_T(RID_R11) | ((((intptr_t)g) >> 32) & 0xffff);
+  *p++ = PPCI_RLDICR | PPCF_T(RID_SYS1) | PPCF_A(RID_SYS1) | PPCF_SH(32) | PPCF_M6(63-32);  /* sldi */
+  *p++ = PPCI_RLDICR | PPCF_T(RID_R11) | PPCF_A(RID_R11) | PPCF_SH(32) | PPCF_M6(63-32);  /* sldi */
+  *p++ = PPCI_ORIS | PPCF_A(RID_SYS1) | PPCF_T(RID_SYS1) | ((((intptr_t)target) >> 16) & 0xffff);
+  *p++ = PPCI_ORIS | PPCF_A(RID_R11) | PPCF_T(RID_R11) | ((((intptr_t)g) >> 16) & 0xffff);
+  *p++ = PPCI_ORI | PPCF_A(RID_SYS1) | PPCF_T(RID_SYS1) | (((intptr_t)target) & 0xffff);
+  *p++ = PPCI_ORI | PPCF_A(RID_R11) | PPCF_T(RID_R11) | (((intptr_t)g) & 0xffff);
+  *p++ = PPCI_MTCTR | PPCF_T(RID_SYS1);
+  *p++ = PPCI_BCTR;
+#else
   *p++ = PPCI_LIS | PPCF_T(RID_TMP) | (u32ptr(target) >> 16);
-  *p++ = PPCI_LIS | PPCF_T(RID_R12) | (u32ptr(g) >> 16);
+  *p++ = PPCI_LIS | PPCF_T(RID_R11) | (u32ptr(g) >> 16);
   *p++ = PPCI_ORI | PPCF_A(RID_TMP)|PPCF_T(RID_TMP) | (u32ptr(target) & 0xffff);
-  *p++ = PPCI_ORI | PPCF_A(RID_R12)|PPCF_T(RID_R12) | (u32ptr(g) & 0xffff);
+  *p++ = PPCI_ORI | PPCF_A(RID_R11)|PPCF_T(RID_R11) | (u32ptr(g) & 0xffff);
   *p++ = PPCI_MTCTR | PPCF_T(RID_TMP);
   *p++ = PPCI_BCTR;
   for (slot = 0; slot < CALLBACK_MAX_SLOT; slot++) {
-    *p++ = PPCI_LI | PPCF_T(RID_R11) | slot;
+    *p++ = PPCI_LI | PPCF_T(RID_R12) | slot;
     *p = PPCI_B | (((page-p) & 0x00ffffffu) << 2);
     p++;
   }
-  lua_assert(p - page <= CALLBACK_MCODE_SIZE);
+#endif
+  lua_assert(p - page <= CALLBACK_MCODE_SIZE / 4);
 }
+#endif
 #elif LJ_TARGET_MIPS
 static void callback_mcode_init(global_State *g, uint32_t *page)
 {
@@ -637,6 +688,15 @@ static void callback_conv_result(CTState *cts, lua_State *L, TValue *o)
 	*(int32_t *)dp = ctr->size == 1 ? (int32_t)*(int8_t *)dp :
 					  (int32_t)*(int16_t *)dp;
     }
+#if LJ_TARGET_PPC && LJ_ARCH_BITS == 64
+    if (ctr->size <= 4 &&
+	(ctype_isinteger_or_bool(ctr->info) || ctype_isenum(ctr->info))) {
+      if (ctr->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
     /* Always sign-extend results to 64 bits. Even a soft-fp 'float'. */
     if (ctr->size <= 4 &&
diff --git a/src/lj_ctype.h b/src/lj_ctype.h
index e9b426f0..9bba59e6 100644
--- a/src/lj_ctype.h
+++ b/src/lj_ctype.h
@@ -153,7 +153,7 @@ typedef struct CType {
 
 /* Simplify target-specific configuration. Checked in lj_ccall.h. */
 #define CCALL_MAX_GPR		8
-#define CCALL_MAX_FPR		8
+#define CCALL_MAX_FPR		14
 
 typedef LJ_ALIGN(8) union FPRCBArg { double d; float f[2]; } FPRCBArg;
 
diff --git a/src/lj_def.h b/src/lj_def.h
index 9413399d..a22eb048 100644
--- a/src/lj_def.h
+++ b/src/lj_def.h
@@ -71,7 +71,11 @@ typedef unsigned int uintptr_t;
 #define LJ_MAX_IDXCHAIN	100		/* __index/__newindex chain limit. */
 #define LJ_STACK_EXTRA	(5+2*LJ_FR2)	/* Extra stack space (metamethods). */
 
+#if defined(__powerpc64__) && _CALL_ELF != 2
+#define LJ_NUM_CBPAGE	4		/* Number of FFI callback pages. */
+#else
 #define LJ_NUM_CBPAGE	1		/* Number of FFI callback pages. */
+#endif
 
 /* Minimum table/buffer sizes. */
 #define LJ_MIN_GLOBAL	6		/* Min. global table size (hbits). */
diff --git a/src/lj_target_ppc.h b/src/lj_target_ppc.h
index bbf22390..794d29e6 100644
--- a/src/lj_target_ppc.h
+++ b/src/lj_target_ppc.h
@@ -131,6 +131,8 @@ static LJ_AINLINE uint32_t *exitstub_trace_addr_(uint32_t *p, uint32_t exitno)
 #define PPCF_C(r)	((r) << 6)
 #define PPCF_MB(n)	((n) << 6)
 #define PPCF_ME(n)	((n) << 1)
+#define PPCF_SH(n)	((((n) & 31) << (11+1)) | (((n) & 32) >> (5-1)))
+#define PPCF_M6(n)	((((n) & 31) << (5+1)) | (((n) & 32) << (11-5)))
 #define PPCF_Y		0x00200000
 #define PPCF_DOT	0x00000001
 
@@ -200,6 +202,13 @@ typedef enum PPCIns {
   PPCI_RLWINM = 0x54000000,
   PPCI_RLWIMI = 0x50000000,
 
+  PPCI_RLDICL = 0x78000000,
+  PPCI_RLDICR = 0x78000004,
+  PPCI_RLDIC = 0x78000008,
+  PPCI_RLDIMI = 0x7800000c,
+  PPCI_RLDCL = 0x78000010,
+  PPCI_RLDCR = 0x78000012,
+
   PPCI_B = 0x48000000,
   PPCI_BL = 0x48000001,
   PPCI_BC = 0x40800000,
diff --git a/src/vm_ppc.dasc b/src/vm_ppc.dasc
index a9c5e602..a5866e6b 100644
--- a/src/vm_ppc.dasc
+++ b/src/vm_ppc.dasc
@@ -33,16 +33,16 @@
 |.macro lpx, a, b, c; ldx a, b, c; .endmacro
 |.macro lp, a, b; ld a, b; .endmacro
 |.macro stp, a, b; std a, b; .endmacro
+|.macro stpx, a, b, c; stdx a, b, c; .endmacro
 |.define decode_OPP, decode_OP8
-|.if FFI
-|// Missing: Calling conventions, 64 bit regs, TOC.
-|.error lib_ffi not yet implemented for PPC64
-|.endif
+|.define WORD_SIZE, 8
 |.else
 |.macro lpx, a, b, c; lwzx a, b, c; .endmacro
 |.macro lp, a, b; lwz a, b; .endmacro
 |.macro stp, a, b; stw a, b; .endmacro
+|.macro stpx, a, b, c; stwx a, b, c; .endmacro
 |.define decode_OPP, decode_OP4
+|.define WORD_SIZE, 4
 |.endif
 |
 |// Convenience macros for TOC handling.
@@ -2525,9 +2525,9 @@ static void build_subroutines(BuildCtx *ctx)
   |  bgt >5				// Need to grow stack.
   |  mtctr FUNCREG
   |  bctrl				// (lua_State *L)
+  |  .toc lp TOCREG, SAVE_TOC
   |  // Either throws an error, or recovers and returns -1, 0 or nresults+1.
   |  lp BASE, L->base
-  |  .toc lp TOCREG, SAVE_TOC
   |  cmpwi CRET1, 0
   |   slwi RD, CRET1, 3
   |   la RA, -8(BASE)
@@ -2928,10 +2928,18 @@ static void build_subroutines(BuildCtx *ctx)
   |->vm_cachesync:
   |.if JIT or FFI
   |  // Compute start of first cache line and number of cache lines.
+  |  .if GPR64
+  |  rldicr CARG1, CARG1, 0, 58
+  |  .else
   |  rlwinm CARG1, CARG1, 0, 0, 26
+  |  .endif
   |  sub CARG2, CARG2, CARG1
   |  addi CARG2, CARG2, 31
+  |  .if GPR64
+  |  srdi. CARG2, CARG2, 5
+  |  .else
   |  rlwinm. CARG2, CARG2, 27, 5, 31
+  |  .endif
   |  beqlr
   |  mtctr CARG2
   |  mr CARG3, CARG1
@@ -2953,32 +2961,54 @@ static void build_subroutines(BuildCtx *ctx)
   |//-- FFI helper functions -----------------------------------------------
   |//-----------------------------------------------------------------------
   |
-  |// Handler for callback functions. Callback slot number in r11, g in r12.
+  |// Handler for callback functions. Callback slot number in r12, g in r11.
   |->vm_ffi_callback:
   |.if FFI
   |.type CTSTATE, CTState, PC
+  |  .if OPD
+  |   rldicl r12, r11, 17, 47
+  |   rldicl r11, r11, 0, 17
+  |  .endif
+  |  .if ELFV2
+  |   rlwinm r12, r12, 30, 22, 31
+  |   addisl TOCREG, TOCREG, extern .TOC.-lj_vm_ffi_callback@ha
+  |   addil TOCREG, TOCREG, extern .TOC.-lj_vm_ffi_callback@l
+  |  .endif
   |  saveregs
-  |  lwz CTSTATE, GL:r12->ctype_state
-  |   addi DISPATCH, r12, GG_G2DISP
-  |  stw r11, CTSTATE->cb.slot
-  |  stw r3, CTSTATE->cb.gpr[0]
+  |  lwz CTSTATE, GL:r11->ctype_state
+  |   addi DISPATCH, r11, GG_G2DISP
+  |  stw r12, CTSTATE->cb.slot
+  |  stp r3, CTSTATE->cb.gpr[0]
   |   stfd f1, CTSTATE->cb.fpr[0]
-  |  stw r4, CTSTATE->cb.gpr[1]
+  |  stp r4, CTSTATE->cb.gpr[1]
   |   stfd f2, CTSTATE->cb.fpr[1]
-  |  stw r5, CTSTATE->cb.gpr[2]
+  |  stp r5, CTSTATE->cb.gpr[2]
   |   stfd f3, CTSTATE->cb.fpr[2]
-  |  stw r6, CTSTATE->cb.gpr[3]
+  |  stp r6, CTSTATE->cb.gpr[3]
   |   stfd f4, CTSTATE->cb.fpr[3]
-  |  stw r7, CTSTATE->cb.gpr[4]
+  |  stp r7, CTSTATE->cb.gpr[4]
   |   stfd f5, CTSTATE->cb.fpr[4]
-  |  stw r8, CTSTATE->cb.gpr[5]
+  |  stp r8, CTSTATE->cb.gpr[5]
   |   stfd f6, CTSTATE->cb.fpr[5]
-  |  stw r9, CTSTATE->cb.gpr[6]
+  |  stp r9, CTSTATE->cb.gpr[6]
   |   stfd f7, CTSTATE->cb.fpr[6]
-  |  stw r10, CTSTATE->cb.gpr[7]
+  |  stp r10, CTSTATE->cb.gpr[7]
   |   stfd f8, CTSTATE->cb.fpr[7]
+  |  .if GPR64
+  |   stfd f9, CTSTATE->cb.fpr[8]
+  |   stfd f10, CTSTATE->cb.fpr[9]
+  |   stfd f11, CTSTATE->cb.fpr[10]
+  |   stfd f12, CTSTATE->cb.fpr[11]
+  |   stfd f13, CTSTATE->cb.fpr[12]
+  |  .endif
+  |  .if ELFV2
+  |  addi TMP0, sp, CFRAME_SPACE+96
+  |  .elif GPR64
+  |  addi TMP0, sp, CFRAME_SPACE+112
+  |  .else
   |  addi TMP0, sp, CFRAME_SPACE+8
-  |  stw TMP0, CTSTATE->cb.stack
+  |  .endif
+  |  stp TMP0, CTSTATE->cb.stack
   |   mr CARG1, CTSTATE
   |  stw CTSTATE, SAVE_PC		// Any value outside of bytecode is ok.
   |   mr CARG2, sp
@@ -3019,9 +3049,21 @@ static void build_subroutines(BuildCtx *ctx)
   |  mr CARG1, CTSTATE
   |  mr CARG2, RA
   |  bl extern lj_ccallback_leave	// (CTState *cts, TValue *o)
-  |  lwz CRET1, CTSTATE->cb.gpr[0]
+  |  lp CRET1, CTSTATE->cb.gpr[0]
   |  lfd FARG1, CTSTATE->cb.fpr[0]
-  |  lwz CRET2, CTSTATE->cb.gpr[1]
+  |  lp CRET2, CTSTATE->cb.gpr[1]
+  |  .if GPR64
+  |    lfd FARG2, CTSTATE->cb.fpr[1]
+  |  .else
+  |    lp CARG3, CTSTATE->cb.gpr[2]
+  |    lp CARG4, CTSTATE->cb.gpr[3]
+  |  .endif
+  |  .elfv2 lfd f3, CTSTATE->cb.fpr[2]
+  |  .elfv2 lfd f4, CTSTATE->cb.fpr[3]
+  |  .elfv2 lfd f5, CTSTATE->cb.fpr[4]
+  |  .elfv2 lfd f6, CTSTATE->cb.fpr[5]
+  |  .elfv2 lfd f7, CTSTATE->cb.fpr[6]
+  |  .elfv2 lfd f8, CTSTATE->cb.fpr[7]
   |  b ->vm_leave_unw
   |.endif
   |
@@ -3034,23 +3076,46 @@ static void build_subroutines(BuildCtx *ctx)
   |   lbz CARG2, CCSTATE->nsp
   |   lbz CARG3, CCSTATE->nfpr
   |  neg TMP1, TMP1
+  |  .if GPR64
+  |    std TMP0, 16(sp)
+  |  .else
   |    stw TMP0, 4(sp)
+  |  .endif
   |   cmpwi cr1, CARG3, 0
   |  mr TMP2, sp
   |   addic. CARG2, CARG2, -1
+  |  .if GPR64
+  |  stdux sp, sp, TMP1
+  |  .else
   |  stwux sp, sp, TMP1
+  |  .endif
   |   crnot 4*cr1+eq, 4*cr1+eq		// For vararg calls.
-  |  stw r14, -4(TMP2)
-  |  stw CCSTATE, -8(TMP2)
+  |  .if GPR64
+  |    std r14, -8(TMP2)
+  |    std CCSTATE, -16(TMP2)
+  |  .else
+  |    stw r14, -4(TMP2)
+  |    stw CCSTATE, -8(TMP2)
+  |  .endif
   |  mr r14, TMP2
   |  la TMP1, CCSTATE->stack
+  |  .if GPR64
+  |   sldi CARG2, CARG2, 3
+  |  .else
   |   slwi CARG2, CARG2, 2
+  |  .endif
   |   blty >2
-  |  la TMP2, 8(sp)
+  |  .if ELFV2
+  |    la TMP2, 96(sp)
+  |  .elif GPR64
+  |    la TMP2, 112(sp)
+  |  .else
+  |    la TMP2, 8(sp)
+  |  .endif
   |1:
-  |  lwzx TMP0, TMP1, CARG2
-  |  stwx TMP0, TMP2, CARG2
-  |   addic. CARG2, CARG2, -4
+  |  lpx TMP0, TMP1, CARG2
+  |  stpx TMP0, TMP2, CARG2
+  |   addic. CARG2, CARG2, -WORD_SIZE
   |  bge <1
   |2:
   |  bney cr1, >3
@@ -3062,28 +3127,49 @@ static void build_subroutines(BuildCtx *ctx)
   |  lfd f6, CCSTATE->fpr[5]
   |  lfd f7, CCSTATE->fpr[6]
   |  lfd f8, CCSTATE->fpr[7]
+  |  .if GPR64
+  |  lfd f9, CCSTATE->fpr[8]
+  |  lfd f10, CCSTATE->fpr[9]
+  |  lfd f11, CCSTATE->fpr[10]
+  |  lfd f12, CCSTATE->fpr[11]
+  |  lfd f13, CCSTATE->fpr[12]
+  |  .endif
   |3:
-  |   lp TMP0, CCSTATE->func
-  |  lwz CARG2, CCSTATE->gpr[1]
-  |  lwz CARG3, CCSTATE->gpr[2]
-  |  lwz CARG4, CCSTATE->gpr[3]
-  |  lwz CARG5, CCSTATE->gpr[4]
-  |   mtctr TMP0
-  |  lwz r8, CCSTATE->gpr[5]
-  |  lwz r9, CCSTATE->gpr[6]
-  |  lwz r10, CCSTATE->gpr[7]
-  |  lwz CARG1, CCSTATE->gpr[0]		// Do this last, since CCSTATE is CARG1.
+  |  .toc std TOCREG, SAVE_TOC
+  |   lp FUNCREG, CCSTATE->func
+  |  lp CARG2, CCSTATE->gpr[1]
+  |  lp CARG3, CCSTATE->gpr[2]
+  |  .opd lp TOCREG, TOC_OFS(FUNCREG)
+  |  .opdenv lp ENVREG, ENV_OFS(FUNCREG)
+  |  .opd lp FUNCREG, 0(FUNCREG)
+  |  lp CARG4, CCSTATE->gpr[3]
+  |  lp CARG5, CCSTATE->gpr[4]
+  |   mtctr FUNCREG
+  |  lp r8, CCSTATE->gpr[5]
+  |  lp r9, CCSTATE->gpr[6]
+  |  lp r10, CCSTATE->gpr[7]
+  |  lp CARG1, CCSTATE->gpr[0]		// Do this last, since CCSTATE is CARG1.
   |   bctrl
-  |  lwz CCSTATE:TMP1, -8(r14)
-  |  lwz TMP2, -4(r14)
+  |   .toc lp TOCREG, SAVE_TOC
+  |  .if GPR64
+  |   ld CCSTATE:TMP1, -16(r14)
+  |   ld TMP2, -8(r14)
+  |   ld TMP0, 16(r14)
+  |  .else
+  |   lwz CCSTATE:TMP1, -8(r14)
+  |   lwz TMP2, -4(r14)
   |   lwz TMP0, 4(r14)
-  |  stw CARG1, CCSTATE:TMP1->gpr[0]
+  |  .endif
+  |  stp CARG1, CCSTATE:TMP1->gpr[0]
   |  stfd FARG1, CCSTATE:TMP1->fpr[0]
-  |  stw CARG2, CCSTATE:TMP1->gpr[1]
+  |  stp CARG2, CCSTATE:TMP1->gpr[1]
+  |  .if GPR64
+  |   stfd FARG2, CCSTATE:TMP1->fpr[1]
+  |  .endif
   |   mtlr TMP0
-  |  stw CARG3, CCSTATE:TMP1->gpr[2]
+  |  stp CARG3, CCSTATE:TMP1->gpr[2]
   |   mr sp, r14
-  |  stw CARG4, CCSTATE:TMP1->gpr[3]
+  |  stp CARG4, CCSTATE:TMP1->gpr[3]
   |   mr r14, TMP2
   |  blr
   |.endif
@@ -5333,9 +5419,9 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
     |  .opdenv lp ENVREG, ENV_OFS(FUNCREG)
     |     st_vmstate
     |  bctrl				// (lua_State *L [, lua_CFunction f])
+    |  .toc lp TOCREG, SAVE_TOC
     |  // Returns nresults.
     |  lp BASE, L->base
-    |  .toc lp TOCREG, SAVE_TOC
     |   slwi RD, CRET1, 3
     |  lp TMP1, L->top
     |    li_vmstate INTERP
@@ -5436,8 +5522,12 @@ static void emit_asm_debug(BuildCtx *ctx)
 	"\t.long lj_vm_ffi_call\n"
 #endif
 	"\t.long %d\n"
+#if LJ_ARCH_PPC32ON64
+	"\t.byte 0x11\n\t.uleb128 65\n\t.sleb128 -2\n"
+#else
 	"\t.byte 0x11\n\t.uleb128 65\n\t.sleb128 -1\n"
-	"\t.byte 0x8e\n\t.uleb128 2\n"
+#endif
+	"\t.byte 0x8e\n\t.uleb128 1\n"
 	"\t.byte 0xd\n\t.uleb128 0xe\n"
 	"\t.align 2\n"
 	".LEFDE1:\n\n", (int)ctx->codesz - fcofs);
@@ -5519,8 +5609,12 @@ static void emit_asm_debug(BuildCtx *ctx)
 	"\t.long lj_vm_ffi_call-.\n"
 	"\t.long %d\n"
 	"\t.uleb128 0\n"			/* augmentation length */
+#if LJ_ARCH_PPC32ON64
+	"\t.byte 0x11\n\t.uleb128 65\n\t.sleb128 -2\n"
+#else
 	"\t.byte 0x11\n\t.uleb128 65\n\t.sleb128 -1\n"
-	"\t.byte 0x8e\n\t.uleb128 2\n"
+#endif
+	"\t.byte 0x8e\n\t.uleb128 1\n"
 	"\t.byte 0xd\n\t.uleb128 0xe\n"
 	"\t.align 2\n"
 	".LEFDE3:\n\n", (int)ctx->codesz - fcofs);