Attachment 1451879 Details for Bug 1591701 – patch6

[patch] patch6

ppc64le_270bfa6.patch (text/plain), 59.60 KB, created by Menanteau Guy on 2018-06-15 10:20:19 UTC

(hide)

Description:

Filename:

MIME Type:

Creator: Menanteau Guy

Created: 2018-06-15 10:20:19 UTC

Size: 59.60 KB

patch

obsolete

>From 270bfa6a083685a7cfec0f190f8b6a3f05a94945 Mon Sep 17 00:00:00 2001
>From: =?UTF-8?q?Marcin=20Ko=C5=9Bcielnicki?= <koriakin@0x04.net>
>Date: Sat, 9 Jul 2016 10:17:09 +0200
>Subject: [PATCH] ppc: Add little-endian support.
>
>---
> src/lj_arch.h   |   3 -
> src/vm_ppc.dasc | 728 +++++++++++++++++++++++++++++++++-----------------------
> 2 files changed, 428 insertions(+), 303 deletions(-)
>
>diff --git a/src/lj_arch.h b/src/lj_arch.h
>index 238178777..5193b3697 100644
>--- a/src/lj_arch.h
>+++ b/src/lj_arch.h
>@@ -427,9 +427,6 @@
> #if defined(_SOFT_FLOAT) || defined(_SOFT_DOUBLE)
> #error "No support for PowerPC CPUs without double-precision FPU"
> #endif
>-#if LJ_ARCH_ENDIAN == LUAJIT_LE
>-#error "No support for little-endian PPC"
>-#endif
> #if LJ_ARCH_PPC_ELFV2
> #error "No support for PPC ELFv2"
> #endif
>diff --git a/src/vm_ppc.dasc b/src/vm_ppc.dasc
>index e8e0dfdd6..56a8e5a80 100644
>--- a/src/vm_ppc.dasc
>+++ b/src/vm_ppc.dasc
>@@ -110,6 +110,7 @@
> |.define LREG,		r18	// Register holding lua_State (also in SAVE_L).
> |.define MULTRES,	r19	// Size of multi-result: (nresults+1)*8.
> |.define JGL,		r31	// On-trace: global_State + 32768.
>+|.define BASEP4,	r25	// Equal to BASE + 4
> |
> |// Constants for type-comparisons, stores and conversions. C callee-save.
> |.define TISNUM,	r22
>@@ -198,17 +199,30 @@
> |.define SAVE_GPR_,	112     // .. 112+18*8: 64 bit GPR saves.
> |//			48(sp)  // Callee parameter save area (ABI mandated).
> |.define SAVE_TOC,	40(sp)  // TOC save area.
>+|.if ENDIAN_LE
>+|.define TMPD_HI,	36(sp)  // \ Link editor temp (ABI mandated).
>+|.define TMPD_LO,	32(sp)  // /
>+|.define TONUM_HI,	28(sp)  // \ Compiler temp (ABI mandated).
>+|.define TONUM_LO,	24(sp)  // /
>+|.else
> |.define TMPD_LO,	36(sp)  // \ Link editor temp (ABI mandated).
> |.define TMPD_HI,	32(sp)  // /
> |.define TONUM_LO,	28(sp)  // \ Compiler temp (ABI mandated).
> |.define TONUM_HI,	24(sp)  // /
>+|.endif
> |// Next frame lr:	16(sp)
> |// Next frame cr:	8(sp)
> |// Back chain for sp:	0(sp)	<-- sp while in interpreter
> |
>+|.if ENDIAN_LE
>+|.define TMPD_BLO,	32(sp)
>+|.define TMPD,		TMPD_LO
>+|.define TONUM_D,	TONUM_LO
>+|.else
> |.define TMPD_BLO,	39(sp)
> |.define TMPD,		TMPD_HI
> |.define TONUM_D,	TONUM_HI
>+|.endif
> |
> |.endif
> |.else
>@@ -226,16 +240,29 @@
> |.define SAVE_PC,	32(sp)
> |.define SAVE_MULTRES,	28(sp)
> |.define UNUSED1,	24(sp)
>+|.if ENDIAN_LE
>+|.define TMPD_HI,	20(sp)
>+|.define TMPD_LO,	16(sp)
>+|.define TONUM_HI,	12(sp)
>+|.define TONUM_LO,	8(sp)
>+|.else
> |.define TMPD_LO,	20(sp)
> |.define TMPD_HI,	16(sp)
> |.define TONUM_LO,	12(sp)
> |.define TONUM_HI,	8(sp)
>+|.endif
> |// Next frame lr:	4(sp)
> |// Back chain for sp:	0(sp)	<-- sp while in interpreter
> |
>+|.if ENDIAN_LE
>+|.define TMPD_BLO,	16(sp)
>+|.define TMPD,		TMPD_LO
>+|.define TONUM_D,	TONUM_LO
>+|.else
> |.define TMPD_BLO,	23(sp)
> |.define TMPD,		TMPD_HI
> |.define TONUM_D,	TONUM_HI
>+|.endif
> |
> |.endif
> |
>@@ -350,8 +377,35 @@
> |//-----------------------------------------------------------------------
> |
> |// Access to frame relative to BASE.
>+|.if ENDIAN_LE
>+|.define FRAME_PC,	-4
>+|.define FRAME_FUNC,	-8
>+|.define FRAME_CONTPC,	-12
>+|.define FRAME_CONTRET,	-16
>+|.define WORD_LO,	0
>+|.define WORD_HI,	4
>+|.define WORD_BLO,	0
>+|.define BASE_LO,	BASE
>+|.define BASE_HI,	BASEP4
>+|.macro lwzux2, hi, lo, base, idx
>+|  lwzux lo, base, idx
>+|  lwz hi, 4(base)
>+|.endmacro
>+|.else
> |.define FRAME_PC,	-8
> |.define FRAME_FUNC,	-4
>+|.define FRAME_CONTPC,	-16
>+|.define FRAME_CONTRET,	-12
>+|.define WORD_LO,	4
>+|.define WORD_HI,	0
>+|.define WORD_BLO,	7
>+|.define BASE_LO,	BASEP4
>+|.define BASE_HI,	BASE
>+|.macro lwzux2, hi, lo, base, idx
>+|  lwzux hi, base, idx
>+|  lwz lo, 4(base)
>+|.endmacro
>+|.endif
> |
> |// Instruction decode.
> |.macro decode_OP4, dst, ins; rlwinm dst, ins, 2, 22, 29; .endmacro
>@@ -412,6 +466,7 @@
> |// Call decode and dispatch.
> |.macro ins_callt
> |  // BASE = new base, RB = LFUNC/CFUNC, RC = nargs*8, FRAME_PC(BASE) = PC
>+|  addi BASEP4, BASE, 4
> |  lwz PC, LFUNC:RB->pc
> |  lwz INS, 0(PC)
> |   addi PC, PC, 4
>@@ -504,7 +559,12 @@ static void build_subroutines(BuildCtx *ctx)
>   |  lwz PC, FRAME_PC(TMP2)		// Fetch PC of previous frame.
>   |  mr BASE, TMP2			// Restore caller base.
>   |  // Prepending may overwrite the pcall frame, so do it at the end.
>-  |   stwu TMP1, FRAME_PC(RA)		// Prepend true to results.
>+  |  .if ENDIAN_LE
>+  |    addi RA, RA, -8
>+  |    stw TMP1, WORD_HI(RA)		// Prepend true to results.
>+  |  .else
>+  |    stwu TMP1, -8(RA)		// Prepend true to results.
>+  |  .endif
>   |
>   |->vm_returnc:
>   |  addi RD, RD, 8			// RD = (nresults+1)*8.
>@@ -560,7 +620,7 @@ static void build_subroutines(BuildCtx *ctx)
>   |  lwz TMP1, L->maxstack
>   |  cmplw BASE, TMP1
>   |  bge >8
>-  |  stw TISNIL, 0(BASE)
>+  |  stw TISNIL, WORD_HI(BASE)
>   |  addi RD, RD, 8
>   |  addi BASE, BASE, 8
>   |  b <2
>@@ -631,7 +691,7 @@ static void build_subroutines(BuildCtx *ctx)
>   |  la RA, -8(BASE)			// Results start at BASE-8.
>   |     stw TMP3, TMPD
>   |   addi DISPATCH, DISPATCH, GG_G2DISP
>-  |  stw TMP1, 0(RA)			// Prepend false to error message.
>+  |  stw TMP1, WORD_HI(RA)		// Prepend false to error message.
>   |  li RD, 16				// 2 results: false + error message.
>   |    st_vmstate
>   |     lfs TONUM, TMPD
>@@ -772,8 +832,8 @@ static void build_subroutines(BuildCtx *ctx)
>   |
>   |->vm_call_dispatch:
>   |  // TMP2 = old base, BASE = new base, RC = nargs*8, PC = caller PC
>-  |  lwz TMP0, FRAME_PC(BASE)
>-  |   lwz LFUNC:RB, FRAME_FUNC(BASE)
>+  |  lwz TMP0, WORD_HI-8(BASE)
>+  |   lwz LFUNC:RB, WORD_LO-8(BASE)
>   |  checkfunc TMP0; bne ->vmeta_call
>   |
>   |->vm_call_dispatch_f:
>@@ -825,15 +885,16 @@ static void build_subroutines(BuildCtx *ctx)
>   |
>   |->cont_dispatch:
>   |  // BASE = meta base, RA = resultptr, RD = (nresults+1)*8
>-  |  lwz TMP0, -12(BASE)		// Continuation.
>+  |  lwz TMP0, FRAME_CONTRET(BASE)	// Continuation.
>   |   mr RB, BASE
>   |   mr BASE, TMP2			// Restore caller BASE.
>   |    lwz LFUNC:TMP1, FRAME_FUNC(TMP2)
>   |.if FFI
>   |  cmplwi TMP0, 1
>   |.endif
>-  |     lwz PC, -16(RB)			// Restore PC from [cont|PC].
>-  |   subi TMP2, RD, 8
>+  |     lwz PC, FRAME_CONTPC(RB)	// Restore PC from [cont|PC].
>+  |  addi BASEP4, BASE, 4
>+  |   addi TMP2, RD, WORD_HI-8
>   |    lwz TMP1, LFUNC:TMP1->pc
>   |   stwx TISNIL, RA, TMP2		// Ensure one valid arg.
>   |.if P64
>@@ -880,20 +941,20 @@ static void build_subroutines(BuildCtx *ctx)
>   |  la CARG3, DISPATCH_GL(tmptv)(DISPATCH)
>   |  li TMP0, LJ_TSTR
>   |   decode_RB8 RB, INS
>-  |  stw STR:RC, 4(CARG3)
>+  |  stw STR:RC, WORD_LO(CARG3)
>   |   add CARG2, BASE, RB
>-  |  stw TMP0, 0(CARG3)
>+  |  stw TMP0, WORD_HI(CARG3)
>   |  b >1
>   |
>   |->vmeta_tgets:
>   |  la CARG2, DISPATCH_GL(tmptv)(DISPATCH)
>   |  li TMP0, LJ_TTAB
>-  |  stw TAB:RB, 4(CARG2)
>+  |  stw TAB:RB, WORD_LO(CARG2)
>   |   la CARG3, DISPATCH_GL(tmptv2)(DISPATCH)
>-  |  stw TMP0, 0(CARG2)
>+  |  stw TMP0, WORD_HI(CARG2)
>   |   li TMP1, LJ_TSTR
>-  |   stw STR:RC, 4(CARG3)
>-  |   stw TMP1, 0(CARG3)
>+  |   stw STR:RC, WORD_LO(CARG3)
>+  |   stw TMP1, WORD_HI(CARG3)
>   |  b >1
>   |
>   |->vmeta_tgetb:			// TMP0 = index
>@@ -904,8 +965,8 @@ static void build_subroutines(BuildCtx *ctx)
>   |  la CARG3, DISPATCH_GL(tmptv)(DISPATCH)
>   |   add CARG2, BASE, RB
>   |.if DUALNUM
>-  |  stw TISNUM, 0(CARG3)
>-  |  stw TMP0, 4(CARG3)
>+  |  stw TISNUM, WORD_HI(CARG3)
>+  |  stw TMP0, WORD_LO(CARG3)
>   |.else
>   |  stfd f0, 0(CARG3)
>   |.endif
>@@ -933,7 +994,7 @@ static void build_subroutines(BuildCtx *ctx)
>   |  // BASE = base, L->top = new base, stack = cont/func/t/k
>   |  subfic TMP1, BASE, FRAME_CONT
>   |  lp BASE, L->top
>-  |  stw PC, -16(BASE)			// [cont|PC]
>+  |  stw PC, FRAME_CONTPC(BASE)		// [cont|PC]
>   |   add PC, TMP1, BASE
>   |  lwz LFUNC:RB, FRAME_FUNC(BASE)	// Guaranteed to be a function here.
>   |   li NARGS8:RC, 16			// 2 args for func(t, k).
>@@ -947,7 +1008,7 @@ static void build_subroutines(BuildCtx *ctx)
>   |  lfd f14, 0(CRET1)
>   |  b ->BC_TGETR_Z
>   |1:
>-  |  stwx TISNIL, BASE, RA
>+  |  stwx TISNIL, BASE_HI, RA
>   |  b ->cont_nop
>   |
>   |//-----------------------------------------------------------------------
>@@ -956,20 +1017,20 @@ static void build_subroutines(BuildCtx *ctx)
>   |  la CARG3, DISPATCH_GL(tmptv)(DISPATCH)
>   |  li TMP0, LJ_TSTR
>   |   decode_RB8 RB, INS
>-  |  stw STR:RC, 4(CARG3)
>+  |  stw STR:RC, WORD_LO(CARG3)
>   |   add CARG2, BASE, RB
>-  |  stw TMP0, 0(CARG3)
>+  |  stw TMP0, WORD_HI(CARG3)
>   |  b >1
>   |
>   |->vmeta_tsets:
>   |  la CARG2, DISPATCH_GL(tmptv)(DISPATCH)
>   |  li TMP0, LJ_TTAB
>-  |  stw TAB:RB, 4(CARG2)
>+  |  stw TAB:RB, WORD_LO(CARG2)
>   |   la CARG3, DISPATCH_GL(tmptv2)(DISPATCH)
>-  |  stw TMP0, 0(CARG2)
>+  |  stw TMP0, WORD_HI(CARG2)
>   |   li TMP1, LJ_TSTR
>-  |   stw STR:RC, 4(CARG3)
>-  |   stw TMP1, 0(CARG3)
>+  |   stw STR:RC, WORD_LO(CARG3)
>+  |   stw TMP1, WORD_HI(CARG3)
>   |  b >1
>   |
>   |->vmeta_tsetb:			// TMP0 = index
>@@ -980,8 +1041,8 @@ static void build_subroutines(BuildCtx *ctx)
>   |  la CARG3, DISPATCH_GL(tmptv)(DISPATCH)
>   |   add CARG2, BASE, RB
>   |.if DUALNUM
>-  |  stw TISNUM, 0(CARG3)
>-  |  stw TMP0, 4(CARG3)
>+  |  stw TISNUM, WORD_HI(CARG3)
>+  |  stw TMP0, WORD_LO(CARG3)
>   |.else
>   |  stfd f0, 0(CARG3)
>   |.endif
>@@ -1010,7 +1071,7 @@ static void build_subroutines(BuildCtx *ctx)
>   |  // BASE = base, L->top = new base, stack = cont/func/t/k/(v)
>   |  subfic TMP1, BASE, FRAME_CONT
>   |  lp BASE, L->top
>-  |  stw PC, -16(BASE)			// [cont|PC]
>+  |  stw PC, FRAME_CONTPC(BASE)		// [cont|PC]
>   |   add PC, TMP1, BASE
>   |  lwz LFUNC:RB, FRAME_FUNC(BASE)	// Guaranteed to be a function here.
>   |   li NARGS8:RC, 24			// 3 args for func(t, k, v)
>@@ -1030,17 +1091,9 @@ static void build_subroutines(BuildCtx *ctx)
>   |->vmeta_comp:
>   |  mr CARG1, L
>   |   subi PC, PC, 4
>-  |.if DUALNUM
>-  |  mr CARG2, RA
>-  |.else
>   |  add CARG2, BASE, RA
>-  |.endif
>   |   stw PC, SAVE_PC
>-  |.if DUALNUM
>-  |  mr CARG3, RD
>-  |.else
>   |  add CARG3, BASE, RD
>-  |.endif
>   |   stp BASE, L->base
>   |  decode_OP1 CARG4, INS
>   |  bl extern lj_meta_comp  // (lua_State *L, TValue *o1, *o2, int op)
>@@ -1067,7 +1120,7 @@ static void build_subroutines(BuildCtx *ctx)
>   |  b ->cont_nop
>   |
>   |->cont_condt:			// RA = resultptr
>-  |  lwz TMP0, 0(RA)
>+  |  lwz TMP0, WORD_HI(RA)
>   |  .gpr64 extsw TMP0, TMP0
>   |  subfic TMP0, TMP0, LJ_TTRUE	// Branch if result is true.
>   |  subfe CRET1, CRET1, CRET1
>@@ -1075,7 +1128,7 @@ static void build_subroutines(BuildCtx *ctx)
>   |  b <4
>   |
>   |->cont_condf:			// RA = resultptr
>-  |  lwz TMP0, 0(RA)
>+  |  lwz TMP0, WORD_HI(RA)
>   |  .gpr64 extsw TMP0, TMP0
>   |  subfic TMP0, TMP0, LJ_TTRUE	// Branch if result is false.
>   |  subfe CRET1, CRET1, CRET1
>@@ -1127,8 +1180,8 @@ static void build_subroutines(BuildCtx *ctx)
>   |.endif
>   |
>   |->vmeta_unm:
>-  |  mr CARG3, RD
>-  |  mr CARG4, RD
>+  |  add CARG3, BASE, RD
>+  |  add CARG4, BASE, RD
>   |  b >1
>   |
>   |->vmeta_arith_vn:
>@@ -1163,7 +1216,7 @@ static void build_subroutines(BuildCtx *ctx)
>   |->vmeta_binop:
>   |  // BASE = old base, CRET1 = new base, stack = cont/func/o1/o2
>   |  sub TMP1, CRET1, BASE
>-  |   stw PC, -16(CRET1)		// [cont|PC]
>+  |   stw PC, FRAME_CONTPC(CRET1)	// [cont|PC]
>   |   mr TMP2, BASE
>   |  addi PC, TMP1, FRAME_CONT
>   |   mr BASE, CRET1
>@@ -1174,7 +1227,7 @@ static void build_subroutines(BuildCtx *ctx)
> #if LJ_52
>   |  mr SAVE0, CARG1
> #endif
>-  |  mr CARG2, RD
>+  |  add CARG2, BASE, RD
>   |   stp BASE, L->base
>   |  mr CARG1, L
>   |   stw PC, SAVE_PC
>@@ -1251,25 +1304,25 @@ static void build_subroutines(BuildCtx *ctx)
>   |.macro .ffunc_1, name
>   |->ff_ .. name:
>   |  cmplwi NARGS8:RC, 8
>-  |   lwz CARG3, 0(BASE)
>-  |    lwz CARG1, 4(BASE)
>+  |   lwz CARG3, WORD_HI(BASE)
>+  |    lwz CARG1, WORD_LO(BASE)
>   |  blt ->fff_fallback
>   |.endmacro
>   |
>   |.macro .ffunc_2, name
>   |->ff_ .. name:
>   |  cmplwi NARGS8:RC, 16
>-  |   lwz CARG3, 0(BASE)
>-  |    lwz CARG4, 8(BASE)
>-  |   lwz CARG1, 4(BASE)
>-  |    lwz CARG2, 12(BASE)
>+  |   lwz CARG3, WORD_HI(BASE)
>+  |    lwz CARG4, WORD_HI+8(BASE)
>+  |   lwz CARG1, WORD_LO(BASE)
>+  |    lwz CARG2, WORD_LO+8(BASE)
>   |  blt ->fff_fallback
>   |.endmacro
>   |
>   |.macro .ffunc_n, name
>   |->ff_ .. name:
>   |  cmplwi NARGS8:RC, 8
>-  |   lwz CARG3, 0(BASE)
>+  |   lwz CARG3, WORD_HI(BASE)
>   |    lfd FARG1, 0(BASE)
>   |  blt ->fff_fallback
>   |  checknum CARG3; bge ->fff_fallback
>@@ -1278,9 +1331,9 @@ static void build_subroutines(BuildCtx *ctx)
>   |.macro .ffunc_nn, name
>   |->ff_ .. name:
>   |  cmplwi NARGS8:RC, 16
>-  |   lwz CARG3, 0(BASE)
>+  |   lwz CARG3, WORD_HI(BASE)
>   |    lfd FARG1, 0(BASE)
>-  |   lwz CARG4, 8(BASE)
>+  |   lwz CARG4, WORD_HI+8(BASE)
>   |    lfd FARG2, 8(BASE)
>   |  blt ->fff_fallback
>   |  checknum CARG3; bge ->fff_fallback
>@@ -1303,9 +1356,9 @@ static void build_subroutines(BuildCtx *ctx)
>   |  cmplw cr1, CARG3, TMP1
>   |    lwz PC, FRAME_PC(BASE)
>   |  bge cr1, ->fff_fallback
>-  |   stw CARG3, 0(RA)
>+  |   stw CARG3, WORD_HI(RA)
>   |  addi RD, NARGS8:RC, 8		// Compute (nresults+1)*8.
>-  |   stw CARG1, 4(RA)
>+  |   stw CARG1, WORD_LO(RA)
>   |  beq ->fff_res			// Done if exactly 1 argument.
>   |  li TMP1, 8
>   |  subi RC, RC, 8
>@@ -1319,7 +1372,7 @@ static void build_subroutines(BuildCtx *ctx)
>   |
>   |.ffunc type
>   |  cmplwi NARGS8:RC, 8
>-  |   lwz CARG1, 0(BASE)
>+  |   lwz CARG1, WORD_HI(BASE)
>   |  blt ->fff_fallback
>   |  .gpr64 extsw CARG1, CARG1
>   |.if P64
>@@ -1371,10 +1424,10 @@ static void build_subroutines(BuildCtx *ctx)
>   |  sub TMP1, TMP0, TMP1
>   |  add NODE:TMP2, NODE:TMP2, TMP1	// node = tab->node + (idx*32-idx*8)
>   |3:  // Rearranged logic, because we expect _not_ to find the key.
>-  |  lwz CARG4, NODE:TMP2->key
>-  |   lwz TMP0, 4+offsetof(Node, key)(NODE:TMP2)
>-  |    lwz CARG2, NODE:TMP2->val
>-  |     lwz TMP1, 4+offsetof(Node, val)(NODE:TMP2)
>+  |  lwz CARG4, WORD_HI+offsetof(Node, key)(NODE:TMP2)
>+  |   lwz TMP0, WORD_LO+offsetof(Node, key)(NODE:TMP2)
>+  |    lwz CARG2, WORD_HI+offsetof(Node, val)(NODE:TMP2)
>+  |     lwz TMP1, WORD_LO+offsetof(Node, val)(NODE:TMP2)
>   |  checkstr CARG4; bne >4
>   |   cmpw TMP0, STR:RC; beq >5
>   |4:
>@@ -1436,8 +1489,8 @@ static void build_subroutines(BuildCtx *ctx)
>   |
>   |.ffunc rawget
>   |  cmplwi NARGS8:RC, 16
>-  |   lwz CARG4, 0(BASE)
>-  |    lwz TAB:CARG2, 4(BASE)
>+  |   lwz CARG4, WORD_HI(BASE)
>+  |    lwz TAB:CARG2, WORD_LO(BASE)
>   |  blt ->fff_fallback
>   |  checktab CARG4; bne ->fff_fallback
>   |   la CARG3, 8(BASE)
>@@ -1452,7 +1505,7 @@ static void build_subroutines(BuildCtx *ctx)
>   |.ffunc tonumber
>   |  // Only handles the number case inline (without a base argument).
>   |  cmplwi NARGS8:RC, 8
>-  |   lwz CARG1, 0(BASE)
>+  |   lwz CARG1, WORD_HI(BASE)
>   |    lfd FARG1, 0(BASE)
>   |  bne ->fff_fallback			// Exactly one argument.
>   |   checknum CARG1; bgt ->fff_fallback
>@@ -1487,10 +1540,10 @@ static void build_subroutines(BuildCtx *ctx)
>   |
>   |.ffunc next
>   |  cmplwi NARGS8:RC, 8
>-  |   lwz CARG1, 0(BASE)
>-  |    lwz TAB:CARG2, 4(BASE)
>+  |   lwz CARG1, WORD_HI(BASE)
>+  |    lwz TAB:CARG2, WORD_LO(BASE)
>   |  blt ->fff_fallback
>-  |   stwx TISNIL, BASE, NARGS8:RC	// Set missing 2nd arg to nil.
>+  |   stwx TISNIL, BASE_HI, NARGS8:RC	// Set missing 2nd arg to nil.
>   |  checktab CARG1
>   |   lwz PC, FRAME_PC(BASE)
>   |  bne ->fff_fallback
>@@ -1526,18 +1579,18 @@ static void build_subroutines(BuildCtx *ctx)
>   |  lfd f0, CFUNC:RB->upvalue[0]
>   |  la RA, -8(BASE)
> #endif
>-  |   stw TISNIL, 8(BASE)
>+  |   stw TISNIL, 8+WORD_HI(BASE)
>   |  li RD, (3+1)*8
>   |  stfd f0, 0(RA)
>   |  b ->fff_res
>   |
>   |.ffunc ipairs_aux
>   |  cmplwi NARGS8:RC, 16
>-  |   lwz CARG3, 0(BASE)
>-  |    lwz TAB:CARG1, 4(BASE)
>-  |   lwz CARG4, 8(BASE)
>+  |   lwz CARG3, WORD_HI(BASE)
>+  |    lwz TAB:CARG1, WORD_LO(BASE)
>+  |   lwz CARG4, 8+WORD_HI(BASE)
>   |.if DUALNUM
>-  |    lwz TMP2, 12(BASE)
>+  |    lwz TMP2, 8+WORD_LO(BASE)
>   |.else
>   |    lfd FARG2, 8(BASE)
>   |.endif
>@@ -1566,16 +1619,16 @@ static void build_subroutines(BuildCtx *ctx)
>   |   la RA, -8(BASE)
>   |  cmplw TMP0, TMP2
>   |.if DUALNUM
>-  |  stw TISNUM, 0(RA)
>+  |  stw TISNUM, WORD_HI(RA)
>   |   slwi TMP3, TMP2, 3
>-  |  stw TMP2, 4(RA)
>+  |  stw TMP2, WORD_LO(RA)
>   |.else
>   |   slwi TMP3, TMP2, 3
>   |  stfd FARG2, 0(RA)
>   |.endif
>   |  ble >2				// Not in array part?
>-  |  lwzx TMP2, TMP1, TMP3
>-  |  lfdx f0, TMP1, TMP3
>+  |  lfdux f0, TMP1, TMP3
>+  |  lwz TMP2, WORD_HI(TMP1)
>   |1:
>   |  checknil TMP2
>   |   li RD, (0+1)*8
>@@ -1594,7 +1647,7 @@ static void build_subroutines(BuildCtx *ctx)
>   |  cmplwi CRET1, 0
>   |   li RD, (0+1)*8
>   |  beq ->fff_res
>-  |  lwz TMP2, 0(CRET1)
>+  |  lwz TMP2, WORD_HI(CRET1)
>   |  lfd f0, 0(CRET1)
>   |  b <1
>   |
>@@ -1613,11 +1666,11 @@ static void build_subroutines(BuildCtx *ctx)
>   |  la RA, -8(BASE)
> #endif
>   |.if DUALNUM
>-  |  stw TISNUM, 8(BASE)
>+  |  stw TISNUM, 8+WORD_HI(BASE)
>   |.else
>-  |  stw ZERO, 8(BASE)
>+  |  stw ZERO, 8+WORD_HI(BASE)
>   |.endif
>-  |   stw ZERO, 12(BASE)
>+  |   stw ZERO, 8+WORD_LO(BASE)
>   |  li RD, (3+1)*8
>   |  stfd f0, 0(RA)
>   |  b ->fff_res
>@@ -1638,7 +1691,7 @@ static void build_subroutines(BuildCtx *ctx)
>   |
>   |.ffunc xpcall
>   |  cmplwi NARGS8:RC, 16
>-  |   lwz CARG4, 8(BASE)
>+  |   lwz CARG4, 8+WORD_HI(BASE)
>   |    lfd FARG2, 8(BASE)
>   |    lfd FARG1, 0(BASE)
>   |  blt ->fff_fallback
>@@ -1735,7 +1788,7 @@ static void build_subroutines(BuildCtx *ctx)
>   |.if resume
>   |  li TMP1, LJ_TTRUE
>   |   la RA, -8(BASE)
>-  |  stw TMP1, -8(BASE)			// Prepend true to results.
>+  |  stw TMP1, WORD_HI-8(BASE)		// Prepend true to results.
>   |  addi RD, RD, 16
>   |.else
>   |  mr RA, BASE
>@@ -1755,7 +1808,7 @@ static void build_subroutines(BuildCtx *ctx)
>   |  lfd f0, 0(TMP3)
>   |   stp TMP3, L:SAVE0->top		// Remove error from coroutine stack.
>   |    li RD, (2+1)*8
>-  |   stw TMP1, -8(BASE)		// Prepend false to results.
>+  |   stw TMP1, WORD_HI-8(BASE)		// Prepend false to results.
>   |    la RA, -8(BASE)
>   |  stfd f0, 0(BASE)			// Copy error message.
>   |  b <7
>@@ -1808,8 +1861,8 @@ static void build_subroutines(BuildCtx *ctx)
>   |->fff_resi:
>   |  lwz PC, FRAME_PC(BASE)
>   |  la RA, -8(BASE)
>-  |  stw TISNUM, -8(BASE)
>-  |  stw CRET1, -4(BASE)
>+  |  stw TISNUM, WORD_HI-8(BASE)
>+  |  stw CRET1, WORD_LO-8(BASE)
>   |  b ->fff_res1
>   |1:
>   |  lus CARG3, 0x41e0	// 2^31.
>@@ -1824,9 +1877,9 @@ static void build_subroutines(BuildCtx *ctx)
>   |->fff_restv:
>   |  // CARG3/CARG1 = TValue result.
>   |  lwz PC, FRAME_PC(BASE)
>-  |   stw CARG3, -8(BASE)
>+  |   stw CARG3, WORD_HI-8(BASE)
>   |  la RA, -8(BASE)
>-  |   stw CARG1, -4(BASE)
>+  |   stw CARG1, WORD_LO-8(BASE)
>   |->fff_res1:
>   |  // RA = results, PC = return.
>   |  li RD, (1+1)*8
>@@ -1844,10 +1897,11 @@ static void build_subroutines(BuildCtx *ctx)
>   |  ins_next1
>   |  // Adjust BASE. KBASE is assumed to be set for the calling frame.
>   |   sub BASE, RA, TMP0
>+  |   addi BASEP4, BASE, 4
>   |  ins_next2
>   |
>   |6:  // Fill up results with nil.
>-  |  subi TMP1, RD, 8
>+  |  addi TMP1, RD, WORD_HI-8
>   |   addi RD, RD, 8
>   |  stwx TISNIL, RA, TMP1
>   |  b <5
>@@ -1960,7 +2014,7 @@ static void build_subroutines(BuildCtx *ctx)
>   |
>   |.ffunc math_log
>   |  cmplwi NARGS8:RC, 8
>-  |   lwz CARG3, 0(BASE)
>+  |   lwz CARG3, WORD_HI(BASE)
>   |    lfd FARG1, 0(BASE)
>   |  bne ->fff_fallback			// Need exactly 1 argument.
>   |  checknum CARG3; bge ->fff_fallback
>@@ -1985,13 +2039,13 @@ static void build_subroutines(BuildCtx *ctx)
>   |.if DUALNUM
>   |.ffunc math_ldexp
>   |  cmplwi NARGS8:RC, 16
>-  |   lwz CARG3, 0(BASE)
>+  |   lwz CARG3, WORD_HI(BASE)
>   |    lfd FARG1, 0(BASE)
>-  |   lwz CARG4, 8(BASE)
>+  |   lwz CARG4, WORD_HI+8(BASE)
>   |.if GPR64
>-  |    lwz CARG2, 12(BASE)
>+  |    lwz CARG2, WORD_LO+8(BASE)
>   |.else
>-  |    lwz CARG1, 12(BASE)
>+  |    lwz CARG1, WORD_LO+8(BASE)
>   |.endif
>   |  blt ->fff_fallback
>   |  checknum CARG3; bge ->fff_fallback
>@@ -2023,8 +2077,8 @@ static void build_subroutines(BuildCtx *ctx)
>   |  stfd FARG1, 0(RA)
>   |  li RD, (2+1)*8
>   |.if DUALNUM
>-  |   stw TISNUM, 8(RA)
>-  |   stw TMP1, 12(RA)
>+  |   stw TISNUM, WORD_HI+8(RA)
>+  |   stw TMP1, WORD_LO+8(RA)
>   |.else
>   |   stfd FARG2, 8(RA)
>   |.endif
>@@ -2051,9 +2105,9 @@ static void build_subroutines(BuildCtx *ctx)
>   |   add TMP2, BASE, NARGS8:RC
>   |  bne >4
>   |1:  // Handle integers.
>-  |  lwz CARG4, 0(TMP1)
>+  |  lwz CARG4, WORD_HI(TMP1)
>   |   cmplw cr1, TMP1, TMP2
>-  |  lwz CARG2, 4(TMP1)
>+  |  lwz CARG2, WORD_LO(TMP1)
>   |   bge cr1, ->fff_resi
>   |  checknum CARG4
>   |   xoris TMP0, CARG1, 0x8000
>@@ -2082,7 +2136,7 @@ static void build_subroutines(BuildCtx *ctx)
>   |   lfd FARG1, 0(BASE)
>   |  bge ->fff_fallback
>   |5:  // Handle numbers.
>-  |  lwz CARG4, 0(TMP1)
>+  |  lwz CARG4, WORD_HI(TMP1)
>   |   cmplw cr1, TMP1, TMP2
>   |  lfd FARG2, 0(TMP1)
>   |   bge cr1, ->fff_resn
>@@ -2097,7 +2151,7 @@ static void build_subroutines(BuildCtx *ctx)
>   |.endif
>   |  b <5
>   |7:  // Convert integer to number and continue above.
>-  |   lwz CARG2, 4(TMP1)
>+  |   lwz CARG2, WORD_LO(TMP1)
>   |  bne ->fff_fallback
>   |  tonum_i FARG2, CARG2
>   |  b <6
>@@ -2105,7 +2159,7 @@ static void build_subroutines(BuildCtx *ctx)
>   |  .ffunc_n name
>   |  li TMP1, 8
>   |1:
>-  |   lwzx CARG2, BASE, TMP1
>+  |   lwzx CARG2, BASE_HI, TMP1
>   |   lfdx FARG2, BASE, TMP1
>   |  cmplw cr1, TMP1, NARGS8:RC
>   |   checknum CARG2
>@@ -2129,8 +2183,8 @@ static void build_subroutines(BuildCtx *ctx)
>   |
>   |.ffunc string_byte			// Only handle the 1-arg case here.
>   |  cmplwi NARGS8:RC, 8
>-  |   lwz CARG3, 0(BASE)
>-  |    lwz STR:CARG1, 4(BASE)
>+  |   lwz CARG3, WORD_HI(BASE)
>+  |    lwz STR:CARG1, WORD_LO(BASE)
>   |  bne ->fff_fallback			// Need exactly 1 argument.
>   |   checkstr CARG3
>   |   bne ->fff_fallback
>@@ -2161,12 +2215,12 @@ static void build_subroutines(BuildCtx *ctx)
>   |.ffunc string_char			// Only handle the 1-arg case here.
>   |  ffgccheck
>   |  cmplwi NARGS8:RC, 8
>-  |   lwz CARG3, 0(BASE)
>+  |   lwz CARG3, WORD_HI(BASE)
>   |.if DUALNUM
>-  |    lwz TMP0, 4(BASE)
>+  |    lwz TMP0, WORD_LO(BASE)
>   |  bne ->fff_fallback			// Exactly 1 argument.
>   |  checknum CARG3; bne ->fff_fallback
>-  |   la CARG2, 7(BASE)
>+  |   la CARG2, WORD_BLO(BASE)
>   |.else
>   |    lfd FARG1, 0(BASE)
>   |  bne ->fff_fallback			// Exactly 1 argument.
>@@ -2190,16 +2244,16 @@ static void build_subroutines(BuildCtx *ctx)
>   |.ffunc string_sub
>   |  ffgccheck
>   |  cmplwi NARGS8:RC, 16
>-  |   lwz CARG3, 16(BASE)
>+  |   lwz CARG3, WORD_HI+16(BASE)
>   |.if not DUALNUM
>   |    lfd f0, 16(BASE)
>   |.endif
>-  |   lwz TMP0, 0(BASE)
>-  |    lwz STR:CARG1, 4(BASE)
>+  |   lwz TMP0, WORD_HI(BASE)
>+  |    lwz STR:CARG1, WORD_LO(BASE)
>   |  blt ->fff_fallback
>-  |   lwz CARG2, 8(BASE)
>+  |   lwz CARG2, WORD_HI+8(BASE)
>   |.if DUALNUM
>-  |    lwz TMP1, 12(BASE)
>+  |    lwz TMP1, WORD_LO+8(BASE)
>   |.else
>   |    lfd f1, 8(BASE)
>   |.endif
>@@ -2207,7 +2261,7 @@ static void build_subroutines(BuildCtx *ctx)
>   |  beq >1
>   |.if DUALNUM
>   |  checknum CARG3
>-  |   lwz TMP2, 20(BASE)
>+  |   lwz TMP2, WORD_LO+16(BASE)
>   |  bne ->fff_fallback
>   |1:
>   |  checknum CARG2; bne ->fff_fallback
>@@ -2263,8 +2317,8 @@ static void build_subroutines(BuildCtx *ctx)
>   |  .ffunc string_ .. name
>   |  ffgccheck
>   |  cmplwi NARGS8:RC, 8
>-  |   lwz CARG3, 0(BASE)
>-  |    lwz STR:CARG2, 4(BASE)
>+  |   lwz CARG3, WORD_HI(BASE)
>+  |    lwz STR:CARG2, WORD_LO(BASE)
>   |  blt ->fff_fallback
>   |  checkstr CARG3
>   |   la SBUF:CARG1, DISPATCH_GL(tmpbuf)(DISPATCH)
>@@ -2302,10 +2356,10 @@ static void build_subroutines(BuildCtx *ctx)
>   |  addi TMP1, BASE, 8
>   |  add TMP2, BASE, NARGS8:RC
>   |1:
>-  |  lwz CARG4, 0(TMP1)
>+  |  lwz CARG4, WORD_HI(TMP1)
>   |   cmplw cr1, TMP1, TMP2
>   |.if DUALNUM
>-  |  lwz CARG2, 4(TMP1)
>+  |  lwz CARG2, WORD_LO(TMP1)
>   |.else
>   |  lfd FARG1, 0(TMP1)
>   |.endif
>@@ -2524,6 +2578,7 @@ static void build_subroutines(BuildCtx *ctx)
>   |3:
>   |  lp BASE, L->base
>   |4:  // Re-dispatch to static ins.
>+  |  addi BASEP4, BASE, 4
>   |  lwz INS, -4(PC)
>   |  decode_OPP TMP1, INS
>   |   decode_RB8 RB, INS
>@@ -2537,7 +2592,7 @@ static void build_subroutines(BuildCtx *ctx)
>   |
>   |->cont_hook:				// Continue from hook yield.
>   |  addi PC, PC, 4
>-  |  lwz MULTRES, -20(RB)		// Restore MULTRES for *M ins.
>+  |  lwz MULTRES, WORD_LO-24(RB)		// Restore MULTRES for *M ins.
>   |  b <4
>   |
>   |->vm_hotloop:			// Hot loop counter underflow.
>@@ -2579,6 +2634,7 @@ static void build_subroutines(BuildCtx *ctx)
>   |  lp BASE, L->base
>   |   lp TMP0, L->top
>   |   stw ZERO, SAVE_PC			// Invalidate for subsequent line hook.
>+  |  addi BASEP4, BASE, 4
>   |  sub NARGS8:RC, TMP0, BASE
>   |  add RA, BASE, RA
>   |  lwz LFUNC:RB, FRAME_FUNC(BASE)
>@@ -2590,7 +2646,7 @@ static void build_subroutines(BuildCtx *ctx)
>   |.if JIT
>   |  // RA = resultptr, RB = meta base
>   |  lwz INS, -4(PC)
>-  |    lwz TRACE:TMP2, -20(RB)		// Save previous trace.
>+  |    lwz TRACE:TMP2, WORD_LO-24(RB)	// Save previous trace.
>   |   addic. TMP1, MULTRES, -8
>   |  decode_RA8 RC, INS			// Call base.
>   |   beq >2
>@@ -2625,10 +2681,11 @@ static void build_subroutines(BuildCtx *ctx)
>   |  mr CARG2, PC
>   |  bl extern lj_dispatch_stitch	// (jit_State *J, const BCIns *pc)
>   |  lp BASE, L->base
>+  |  addi BASEP4, BASE, 4
>   |  b ->cont_nop
>   |
>   |9:
>-  |  stwx TISNIL, BASE, RC
>+  |  stwx TISNIL, BASE_HI, RC
>   |  addi RC, RC, 8
>   |  b <3
>   |.endif
>@@ -2643,6 +2700,7 @@ static void build_subroutines(BuildCtx *ctx)
>   |  // HOOK_PROFILE is off again, so re-dispatch to dynamic instruction.
>   |  lp BASE, L->base
>   |  subi PC, PC, 4
>+  |  addi BASEP4, BASE, 4
>   |  b ->cont_nop
> #endif
>   |
>@@ -2659,6 +2717,7 @@ static void build_subroutines(BuildCtx *ctx)
>   |
>   |->vm_exit_handler:
>   |.if JIT
>+  // XXX: endian
>   |  addi sp, sp, -(16+32*8+32*4)
>   |  stmw r2, 16+32*8+2*4(sp)
>   |    addi DISPATCH, JGL, -GG_DISP2G-32768
>@@ -2710,6 +2769,7 @@ static void build_subroutines(BuildCtx *ctx)
>   |.endif
>   |->vm_exit_interp:
>   |.if JIT
>+  // XXX: endian
>   |  // CARG1 = MULTRES or negated error code, BASE, PC and JGL set.
>   |  lwz L, SAVE_L
>   |  addi DISPATCH, JGL, -GG_DISP2G-32768
>@@ -2767,7 +2827,7 @@ static void build_subroutines(BuildCtx *ctx)
>   |  lwz TMP2, -4(TMP1)
>   |  decode_RA8 TMP0, TMP2
>   |  sub TMP1, BASE, TMP0
>-  |  lwz LFUNC:TMP2, -12(TMP1)
>+  |  lwz LFUNC:TMP2, WORD_LO-16(TMP1)
>   |  lwz TMP1, LFUNC:TMP2->pc
>   |  lwz KBASE, PC2PROTO(k)(TMP1)
>   |3:
>@@ -2998,13 +3058,13 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>   case BC_ISLT: case BC_ISGE: case BC_ISLE: case BC_ISGT:
>     |  // RA = src1*8, RD = src2*8, JMP with RD = target
>     |.if DUALNUM
>-    |  lwzux TMP0, RA, BASE
>+    |  lwzx TMP0, BASE_HI, RA
>     |    addi PC, PC, 4
>-    |   lwz CARG2, 4(RA)
>-    |  lwzux TMP1, RD, BASE
>+    |   lwzx CARG2, BASE_LO, RA
>+    |  lwzx TMP1, BASE_HI, RD
>     |    lwz TMP2, -4(PC)
>     |  checknum cr0, TMP0
>-    |   lwz CARG3, 4(RD)
>+    |   lwzx CARG3, BASE_LO, RD
>     |    decode_RD4 TMP2, TMP2
>     |  checknum cr1, TMP1
>     |    addis TMP2, TMP2, -(BCBIAS_J*4 >> 16)
>@@ -3028,7 +3088,7 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     |7:  // RA is not an integer.
>     |  bgt cr0, ->vmeta_comp
>     |  // RA is a number.
>-    |   lfd f0, 0(RA)
>+    |   lfdx f0, BASE, RA
>     |  bgt cr1, ->vmeta_comp
>     |  blt cr1, >4
>     |  // RA is a number, RD is an integer.
>@@ -3040,7 +3100,7 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     |  // RA is an integer, RD is a number.
>     |  tonum_i f0, CARG2
>     |4:
>-    |  lfd f1, 0(RD)
>+    |  lfdx f1, BASE, RD
>     |5:
>     |  fcmpu cr0, f0, f1
>     if (op == BC_ISLT) {
>@@ -3056,10 +3116,10 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     }
>     |  b <1
>     |.else
>-    |  lwzx TMP0, BASE, RA
>+    |  lwzx TMP0, BASE_HI, RA
>     |    addi PC, PC, 4
>     |   lfdx f0, BASE, RA
>-    |  lwzx TMP1, BASE, RD
>+    |  lwzx TMP1, BASE_HI, RD
>     |  checknum cr0, TMP0
>     |    lwz TMP2, -4(PC)
>     |   lfdx f1, BASE, RD
>@@ -3090,15 +3150,23 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     vk = op == BC_ISEQV;
>     |  // RA = src1*8, RD = src2*8, JMP with RD = target
>     |.if DUALNUM
>-    |  lwzux TMP0, RA, BASE
>+    |  lwzx TMP0, BASE_HI, RA
>     |    addi PC, PC, 4
>-    |   lwz CARG2, 4(RA)
>-    |  lwzux TMP1, RD, BASE
>+    |   lwzx CARG2, BASE_LO, RA
>+    |  .if ENDIAN_LE
>+    |    lwzx TMP1, BASE_HI, RD
>+    |  .else
>+    |    lwzux TMP1, RD, BASE_HI
>+    |  .endif
>     |  checknum cr0, TMP0
>     |    lwz TMP2, -4(PC)
>     |  checknum cr1, TMP1
>     |    decode_RD4 TMP2, TMP2
>-    |   lwz CARG3, 4(RD)
>+    |  .if ENDIAN_LE
>+    |   lwzux CARG3, RD, BASE_LO
>+    |  .else
>+    |   lwz CARG3, WORD_LO(RD)
>+    |  .endif
>     |  cror 4*cr7+gt, 4*cr0+gt, 4*cr1+gt
>     |    addis TMP2, TMP2, -(BCBIAS_J*4 >> 16)
>     if (vk) {
>@@ -3107,14 +3175,14 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>       |  ble cr7, ->BC_ISNEN_Z
>     }
>     |.else
>-    |  lwzux TMP0, RA, BASE
>+    |  lwzx TMP0, BASE_HI, RA
>     |   lwz TMP2, 0(PC)
>-    |    lfd f0, 0(RA)
>+    |    lfdx f0, BASE, RA
>     |   addi PC, PC, 4
>-    |  lwzux TMP1, RD, BASE
>+    |  lwzx TMP1, BASE_HI, RD
>     |  checknum cr0, TMP0
>     |   decode_RD4 TMP2, TMP2
>-    |    lfd f1, 0(RD)
>+    |    lfdx f1, BASE, RD
>     |  checknum cr1, TMP1
>     |   addis TMP2, TMP2, -(BCBIAS_J*4 >> 16)
>     |  bge cr0, >5
>@@ -3132,8 +3200,8 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     |.endif
>     |5:  // Either or both types are not numbers.
>     |.if not DUALNUM
>-    |    lwz CARG2, 4(RA)
>-    |    lwz CARG3, 4(RD)
>+    |    lwzx CARG2, BASE_LO, RA
>+    |    lwzx CARG3, BASE_LO, RD
>     |.endif
>     |.if FFI
>     |  cmpwi cr7, TMP0, LJ_TCDATA
>@@ -3197,9 +3265,9 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>   case BC_ISEQS: case BC_ISNES:
>     vk = op == BC_ISEQS;
>     |  // RA = src*8, RD = str_const*8 (~), JMP with RD = target
>-    |  lwzux TMP0, RA, BASE
>+    |  lwzx TMP0, BASE_HI, RA
>     |   srwi RD, RD, 1
>-    |  lwz STR:TMP3, 4(RA)
>+    |  lwzx STR:TMP3, BASE_LO, RA
>     |    lwz TMP2, 0(PC)
>     |   subfic RD, RD, -4
>     |    addi PC, PC, 4
>@@ -3231,15 +3299,14 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     vk = op == BC_ISEQN;
>     |  // RA = src*8, RD = num_const*8, JMP with RD = target
>     |.if DUALNUM
>-    |  lwzux TMP0, RA, BASE
>+    |  lwzx TMP0, BASE_HI, RA
>     |    addi PC, PC, 4
>-    |   lwz CARG2, 4(RA)
>-    |  lwzux TMP1, RD, KBASE
>+    |   lwzx CARG2, BASE_LO, RA
>+    |  lwzux2 TMP1, CARG3, RD, KBASE
>     |  checknum cr0, TMP0
>     |    lwz TMP2, -4(PC)
>     |  checknum cr1, TMP1
>     |    decode_RD4 TMP2, TMP2
>-    |   lwz CARG3, 4(RD)
>     |    addis TMP2, TMP2, -(BCBIAS_J*4 >> 16)
>     if (vk) {
>       |->BC_ISEQN_Z:
>@@ -3256,7 +3323,7 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     } else {
>       |->BC_ISNEN_Z:  // Dummy label.
>     }
>-    |  lwzx TMP0, BASE, RA
>+    |  lwzx TMP0, BASE_HI, RA
>     |    addi PC, PC, 4
>     |   lfdx f0, BASE, RA
>     |    lwz TMP2, -4(PC)
>@@ -3294,7 +3361,7 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     |7:  // RA is not an integer.
>     |  bge cr0, <3
>     |  // RA is a number.
>-    |   lfd f0, 0(RA)
>+    |   lfdx f0, BASE, RA
>     |  blt cr1, >1
>     |  // RA is a number, RD is an integer.
>     |  tonum_i f1, CARG3
>@@ -3313,7 +3380,7 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>   case BC_ISEQP: case BC_ISNEP:
>     vk = op == BC_ISEQP;
>     |  // RA = src*8, RD = primitive_type*8 (~), JMP with RD = target
>-    |  lwzx TMP0, BASE, RA
>+    |  lwzx TMP0, BASE_HI, RA
>     |   srwi TMP1, RD, 3
>     |    lwz TMP2, 0(PC)
>     |   not TMP1, TMP1
>@@ -3343,7 +3410,7 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
> 
>   case BC_ISTC: case BC_ISFC: case BC_IST: case BC_ISF:
>     |  // RA = dst*8 or unused, RD = src*8, JMP with RD = target
>-    |  lwzx TMP0, BASE, RD
>+    |  lwzx TMP0, BASE_HI, RD
>     |   lwz INS, 0(PC)
>     |   addi PC, PC, 4
>     if (op == BC_IST || op == BC_ISF) {
>@@ -3378,7 +3445,7 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
> 
>   case BC_ISTYPE:
>     |  // RA = src*8, RD = -type*8
>-    |  lwzx TMP0, BASE, RA
>+    |  lwzx TMP0, BASE_HI, RA
>     |  srwi TMP1, RD, 3
>     |  ins_next1
>     |.if not PPE and not GPR64
>@@ -3392,7 +3459,7 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     break;
>   case BC_ISNUM:
>     |  // RA = src*8, RD = -(TISNUM-1)*8
>-    |  lwzx TMP0, BASE, RA
>+    |  lwzx TMP0, BASE_HI, RA
>     |  ins_next1
>     |  checknum TMP0
>     |  bge ->vmeta_istype
>@@ -3411,17 +3478,17 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>   case BC_NOT:
>     |  // RA = dst*8, RD = src*8
>     |  ins_next1
>-    |  lwzx TMP0, BASE, RD
>+    |  lwzx TMP0, BASE_HI, RD
>     |  .gpr64 extsw TMP0, TMP0
>     |  subfic TMP1, TMP0, LJ_TTRUE
>     |  adde TMP0, TMP0, TMP1
>-    |  stwx TMP0, BASE, RA
>+    |  stwx TMP0, BASE_HI, RA
>     |  ins_next2
>     break;
>   case BC_UNM:
>     |  // RA = dst*8, RD = src*8
>-    |  lwzux TMP1, RD, BASE
>-    |   lwz TMP0, 4(RD)
>+    |  lwzx TMP1, BASE_HI, RD
>+    |   lwzx TMP0, BASE_LO, RD
>     |  checknum TMP1
>     |.if DUALNUM
>     |  bne >5
>@@ -3436,8 +3503,8 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     |1:
>     |.endif
>     |  ins_next1
>-    |  stwux TISNUM, RA, BASE
>-    |   stw TMP0, 4(RA)
>+    |  stwx TISNUM, BASE_HI, RA
>+    |   stwx TMP0, BASE_LO, RA
>     |3:
>     |  ins_next2
>     |4:
>@@ -3454,8 +3521,8 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     |  xoris TMP1, TMP1, 0x8000
>     |7:
>     |  ins_next1
>-    |  stwux TMP1, RA, BASE
>-    |   stw TMP0, 4(RA)
>+    |  stwx TMP1, BASE_HI, RA
>+    |   stwx TMP0, BASE_LO, RA
>     |.if DUALNUM
>     |  b <3
>     |.else
>@@ -3464,15 +3531,15 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     break;
>   case BC_LEN:
>     |  // RA = dst*8, RD = src*8
>-    |  lwzux TMP0, RD, BASE
>-    |   lwz CARG1, 4(RD)
>+    |  lwzx TMP0, BASE_HI, RD
>+    |   lwzx CARG1, BASE_LO, RD
>     |  checkstr TMP0; bne >2
>     |  lwz CRET1, STR:CARG1->len
>     |1:
>     |.if DUALNUM
>     |  ins_next1
>-    |  stwux TISNUM, RA, BASE
>-    |   stw CRET1, 4(RA)
>+    |  stwx TISNUM, BASE_HI, RA
>+    |   stwx CRET1, BASE_LO, RA
>     |.else
>     |  tonum_u f0, CRET1		// Result is a non-negative integer.
>     |  ins_next1
>@@ -3507,9 +3574,16 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     ||vk = ((int)op - BC_ADDVN) / (BC_ADDNV-BC_ADDVN);
>     ||switch (vk) {
>     ||case 0:
>-    |   lwzx TMP1, BASE, RB
>+    |   .if ENDIAN_LE and DUALNUM
>+    |     addi TMP2, RC, 4
>+    |   .endif
>+    |   lwzx TMP1, BASE_HI, RB
>     |   .if DUALNUM
>-    |     lwzx TMP2, KBASE, RC
>+    |     .if ENDIAN_LE
>+    |       lwzx TMP2, KBASE, TMP2
>+    |     .else
>+    |       lwzx TMP2, KBASE, RC
>+    |     .endif
>     |   .endif
>     |    lfdx f14, BASE, RB
>     |    lfdx f15, KBASE, RC
>@@ -3523,9 +3597,16 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     |   .endif
>     ||  break;
>     ||case 1:
>-    |   lwzx TMP1, BASE, RB
>+    |   .if ENDIAN_LE and DUALNUM
>+    |     addi TMP2, RC, 4
>+    |   .endif
>+    |   lwzx TMP1, BASE_HI, RB
>     |   .if DUALNUM
>-    |     lwzx TMP2, KBASE, RC
>+    |     .if ENDIAN_LE
>+    |       lwzx TMP2, KBASE, TMP2
>+    |     .else
>+    |       lwzx TMP2, KBASE, RC
>+    |     .endif
>     |   .endif
>     |    lfdx f15, BASE, RB
>     |    lfdx f14, KBASE, RC
>@@ -3539,8 +3620,8 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     |   .endif
>     ||  break;
>     ||default:
>-    |   lwzx TMP1, BASE, RB
>-    |   lwzx TMP2, BASE, RC
>+    |   lwzx TMP1, BASE_HI, RB
>+    |   lwzx TMP2, BASE_HI, RC
>     |    lfdx f14, BASE, RB
>     |    lfdx f15, BASE, RC
>     |   checknum cr0, TMP1
>@@ -3595,25 +3676,49 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     ||vk = ((int)op - BC_ADDVN) / (BC_ADDNV-BC_ADDVN);
>     ||switch (vk) {
>     ||case 0:
>-    |   lwzux TMP1, RB, BASE
>-    |   lwzux TMP2, RC, KBASE
>-    |    lwz CARG1, 4(RB)
>-    |   checknum cr0, TMP1
>-    |    lwz CARG2, 4(RC)
>+    |   .if ENDIAN_LE
>+    |     lwzux CARG2, RC, KBASE
>+    |     lwzx TMP1, RB, BASE_HI
>+    |      lwz TMP2, 4(RC)
>+    |     checknum cr0, TMP1
>+    |      lwzux CARG1, RB, BASE
>+    |   .else
>+    |     lwzux TMP1, RB, BASE
>+    |     lwzux TMP2, RC, KBASE
>+    |      lwz CARG1, 4(RB)
>+    |     checknum cr0, TMP1
>+    |      lwz CARG2, 4(RC)
>+    |   .endif
>     ||  break;
>     ||case 1:
>-    |   lwzux TMP1, RB, BASE
>-    |   lwzux TMP2, RC, KBASE
>-    |    lwz CARG2, 4(RB)
>-    |   checknum cr0, TMP1
>-    |    lwz CARG1, 4(RC)
>+    |   .if ENDIAN_LE
>+    |     lwzux CARG1, RC, KBASE
>+    |     lwzx TMP1, RB, BASE_HI
>+    |      lwz TMP2, 4(RC)
>+    |     checknum cr0, TMP1
>+    |      lwzux CARG2, RB, BASE
>+    |   .else
>+    |     lwzux TMP1, RB, BASE
>+    |     lwzux TMP2, RC, KBASE
>+    |      lwz CARG2, 4(RB)
>+    |     checknum cr0, TMP1
>+    |      lwz CARG1, 4(RC)
>+    |   .endif
>     ||  break;
>     ||default:
>-    |   lwzux TMP1, RB, BASE
>-    |   lwzux TMP2, RC, BASE
>-    |    lwz CARG1, 4(RB)
>-    |   checknum cr0, TMP1
>-    |    lwz CARG2, 4(RC)
>+    |   .if ENDIAN_LE
>+    |     lwzx TMP1, RB, BASE_HI
>+    |     lwzx TMP2, RC, BASE_HI
>+    |      lwzux CARG1, RB, BASE
>+    |     checknum cr0, TMP1
>+    |      lwzux CARG2, RC, BASE
>+    |   .else
>+    |     lwzux TMP1, RB, BASE
>+    |     lwzux TMP2, RC, BASE
>+    |      lwz CARG1, 4(RB)
>+    |     checknum cr0, TMP1
>+    |      lwz CARG2, 4(RC)
>+    |   .endif
>     ||  break;
>     ||}
>     |  checknum cr1, TMP2
>@@ -3623,8 +3728,8 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     |  bso >4
>     |1:
>     |  ins_next1
>-    |  stwux TISNUM, RA, BASE
>-    |  stw CARG1, 4(RA)
>+    |  stwx TISNUM, BASE_HI, RA
>+    |  stwx CARG1, BASE_LO, RA
>     |2:
>     |  ins_next2
>     |4:  // Overflow.
>@@ -3701,9 +3806,9 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     break;
>   case BC_POW:
>     |  // NYI: (partial) integer arithmetic.
>-    |  lwzx TMP1, BASE, RB
>+    |  lwzx TMP1, BASE_HI, RB
>     |   lfdx FARG1, BASE, RB
>-    |  lwzx TMP2, BASE, RC
>+    |  lwzx TMP2, BASE_HI, RC
>     |   lfdx FARG2, BASE, RC
>     |  checknum cr0, TMP1
>     |  checknum cr1, TMP2
>@@ -3729,6 +3834,7 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     |  // Returns NULL (finished) or TValue * (metamethod).
>     |  cmplwi CRET1, 0
>     |   lp BASE, L->base
>+    |   addi BASEP4, BASE, 4
>     |  bne ->vmeta_binop
>     |  ins_next1
>     |  lfdx f0, BASE, SAVE0		// Copy result from RB to RA.
>@@ -3745,8 +3851,8 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     |  ins_next1
>     |  lwzx TMP0, KBASE, TMP1		// KBASE-4-str_const*4
>     |  li TMP2, LJ_TSTR
>-    |  stwux TMP2, RA, BASE
>-    |  stw TMP0, 4(RA)
>+    |  stwx TMP2, BASE_HI, RA
>+    |  stwx TMP0, BASE_LO, RA
>     |  ins_next2
>     break;
>   case BC_KCDATA:
>@@ -3757,8 +3863,8 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     |  ins_next1
>     |  lwzx TMP0, KBASE, TMP1		// KBASE-4-cdata_const*4
>     |  li TMP2, LJ_TCDATA
>-    |  stwux TMP2, RA, BASE
>-    |  stw TMP0, 4(RA)
>+    |  stwx TMP2, BASE_HI, RA
>+    |  stwx TMP0, BASE_LO, RA
>     |  ins_next2
>     |.endif
>     break;
>@@ -3768,8 +3874,8 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     |  slwi RD, RD, 13
>     |  srawi RD, RD, 16
>     |  ins_next1
>-    |   stwux TISNUM, RA, BASE
>-    |   stw RD, 4(RA)
>+    |   stwx TISNUM, BASE_HI, RA
>+    |   stwx RD, BASE_LO, RA
>     |  ins_next2
>     |.else
>     |  // The soft-float approach is faster.
>@@ -3787,8 +3893,8 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     |   add RD, RD, TMP1		// hi = hi + exponent-1
>     |    and RD, RD, TMP0		// hi = x == 0 ? 0 : hi
>     |  ins_next1
>-    |    stwux RD, RA, BASE
>-    |    stw ZERO, 4(RA)
>+    |    stwx RD, BASE_HI, RA
>+    |    stwx ZERO, BASE_LO, RA
>     |  ins_next2
>     |.endif
>     break;
>@@ -3804,15 +3910,15 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     |  srwi TMP1, RD, 3
>     |  not TMP0, TMP1
>     |  ins_next1
>-    |  stwx TMP0, BASE, RA
>+    |  stwx TMP0, BASE_HI, RA
>     |  ins_next2
>     break;
>   case BC_KNIL:
>     |  // RA = base*8, RD = end*8
>-    |  stwx TISNIL, BASE, RA
>+    |  stwx TISNIL, BASE_HI, RA
>     |   addi RA, RA, 8
>     |1:
>-    |  stwx TISNIL, BASE, RA
>+    |  stwx TISNIL, BASE_HI, RA
>     |  cmpw RA, RD
>     |   addi RA, RA, 8
>     |  blt <1
>@@ -3844,10 +3950,10 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     |   lwz CARG2, UPVAL:RB->v
>     |  andix. TMP3, TMP3, LJ_GC_BLACK	// isblack(uv)
>     |    lbz TMP0, UPVAL:RB->closed
>-    |   lwz TMP2, 0(RD)
>+    |   lwz TMP2, WORD_HI(RD)
>     |   stfd f0, 0(CARG2)
>     |    cmplwi cr1, TMP0, 0
>-    |   lwz TMP1, 4(RD)
>+    |   lwz TMP1, WORD_LO(RD)
>     |  cror 4*cr0+eq, 4*cr0+eq, 4*cr1+eq
>     |   subi TMP2, TMP2, (LJ_TNUMX+1)
>     |  bne >2				// Upvalue is closed and black?
>@@ -3880,8 +3986,8 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     |   lbz TMP3, STR:TMP1->marked
>     |   lbz TMP2, UPVAL:RB->closed
>     |   li TMP0, LJ_TSTR
>-    |   stw STR:TMP1, 4(CARG2)
>-    |   stw TMP0, 0(CARG2)
>+    |   stw STR:TMP1, WORD_LO(CARG2)
>+    |   stw TMP0, WORD_HI(CARG2)
>     |  bne >2
>     |1:
>     |  ins_next
>@@ -3918,7 +4024,7 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     |  lwzx UPVAL:RB, LFUNC:RB, RA
>     |  ins_next1
>     |  lwz TMP1, UPVAL:RB->v
>-    |  stw TMP0, 0(TMP1)
>+    |  stw TMP0, WORD_HI(TMP1)
>     |  ins_next2
>     break;
> 
>@@ -3951,8 +4057,8 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     |  // Returns GCfuncL *.
>     |  lp BASE, L->base
>     |   li TMP0, LJ_TFUNC
>-    |  stwux TMP0, RA, BASE
>-    |  stw LFUNC:CRET1, 4(RA)
>+    |  stwx TMP0, BASE_HI, RA
>+    |  stwx LFUNC:CRET1, BASE_LO, RA
>     |  ins_next
>     break;
> 
>@@ -3985,8 +4091,9 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     }
>     |  lp BASE, L->base
>     |   li TMP0, LJ_TTAB
>-    |  stwux TMP0, RA, BASE
>-    |  stw TAB:CRET1, 4(RA)
>+    |  addi BASEP4, BASE, 4
>+    |  stwx TMP0, BASE_HI, RA
>+    |  stwx TAB:CRET1, BASE_LO, RA
>     |  ins_next
>     if (op == BC_TNEW) {
>       |3:
>@@ -4019,13 +4126,13 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
> 
>   case BC_TGETV:
>     |  // RA = dst*8, RB = table*8, RC = key*8
>-    |  lwzux CARG1, RB, BASE
>-    |  lwzux CARG2, RC, BASE
>-    |   lwz TAB:RB, 4(RB)
>+    |  lwzx CARG1, BASE_HI, RB
>+    |  lwzx CARG2, BASE_HI, RC
>+    |   lwzx TAB:RB, BASE_LO, RB
>     |.if DUALNUM
>-    |   lwz RC, 4(RC)
>+    |   lwzx RC, BASE_LO, RC
>     |.else
>-    |   lfd f0, 0(RC)
>+    |   lfdx f0, BASE, RC
>     |.endif
>     |  checktab CARG1
>     |   checknum cr1, CARG2
>@@ -4052,7 +4159,12 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     |   slwi TMP2, TMP2, 3
>     |.endif
>     |  ble ->vmeta_tgetv		// Integer key and in array part?
>-    |  lwzx TMP0, TMP1, TMP2
>+    |  .if ENDIAN_LE
>+    |    addi TMP3, TMP1, 4
>+    |    lwzx TMP0, TMP3, TMP2
>+    |  .else
>+    |    lwzx TMP0, TMP1, TMP2
>+    |  .endif
>     |   lfdx f14, TMP1, TMP2
>     |  checknil TMP0; beq >2
>     |1:
>@@ -4072,15 +4184,15 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     |5:
>     |  checkstr CARG2; bne ->vmeta_tgetv
>     |.if not DUALNUM
>-    |  lwz STR:RC, 4(RC)
>+    |  lwzx STR:RC, BASE_LO, RC
>     |.endif
>     |  b ->BC_TGETS_Z			// String key?
>     break;
>   case BC_TGETS:
>     |  // RA = dst*8, RB = table*8, RC = str_const*8 (~)
>-    |  lwzux CARG1, RB, BASE
>+    |  lwzx CARG1, BASE_HI, RB
>     |   srwi TMP1, RC, 1
>-    |    lwz TAB:RB, 4(RB)
>+    |    lwzx TAB:RB, BASE_LO, RB
>     |   subfic TMP1, TMP1, -4
>     |  checktab CARG1
>     |   lwzx STR:RC, KBASE, TMP1	// KBASE-4-str_const*4
>@@ -4096,16 +4208,16 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     |  sub TMP1, TMP0, TMP1
>     |  add NODE:TMP2, NODE:TMP2, TMP1	// node = tab->node + (idx*32-idx*8)
>     |1:
>-    |  lwz CARG1, NODE:TMP2->key
>-    |   lwz TMP0, 4+offsetof(Node, key)(NODE:TMP2)
>-    |    lwz CARG2, NODE:TMP2->val
>-    |     lwz TMP1, 4+offsetof(Node, val)(NODE:TMP2)
>+    |  lwz CARG1, WORD_HI+offsetof(Node, key)(NODE:TMP2)
>+    |   lwz TMP0, WORD_LO+offsetof(Node, key)(NODE:TMP2)
>+    |    lwz CARG2, WORD_HI+offsetof(Node, val)(NODE:TMP2)
>+    |     lwz TMP1, WORD_LO+offsetof(Node, val)(NODE:TMP2)
>     |  checkstr CARG1; bne >4
>     |   cmpw TMP0, STR:RC; bne >4
>     |    checknil CARG2; beq >5		// Key found, but nil value?
>     |3:
>-    |    stwux CARG2, RA, BASE
>-    |     stw TMP1, 4(RA)
>+    |    stwx CARG2, BASE_HI, RA
>+    |     stwx TMP1, BASE_LO, RA
>     |  ins_next
>     |
>     |4:  // Follow hash chain.
>@@ -4126,14 +4238,19 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     break;
>   case BC_TGETB:
>     |  // RA = dst*8, RB = table*8, RC = index*8
>-    |  lwzux CARG1, RB, BASE
>+    |  lwzx CARG1, BASE_HI, RB
>     |   srwi TMP0, RC, 3
>-    |   lwz TAB:RB, 4(RB)
>+    |   lwzx TAB:RB, BASE_LO, RB
>     |  checktab CARG1; bne ->vmeta_tgetb
>     |  lwz TMP1, TAB:RB->asize
>     |   lwz TMP2, TAB:RB->array
>     |  cmplw TMP0, TMP1; bge ->vmeta_tgetb
>-    |  lwzx TMP1, TMP2, RC
>+    |  .if ENDIAN_LE
>+    |    addi TMP1, TMP2, 4
>+    |    lwzx TMP1, TMP1, RC
>+    |  .else
>+    |    lwzx TMP1, TMP2, RC
>+    |  .endif
>     |   lfdx f0, TMP2, RC
>     |  checknil TMP1; beq >5
>     |1:
>@@ -4152,12 +4269,10 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     break;
>   case BC_TGETR:
>     |  // RA = dst*8, RB = table*8, RC = key*8
>-    |  add RB, BASE, RB
>-    |  lwz TAB:CARG1, 4(RB)
>+    |  lwzx TAB:CARG1, BASE_LO, RB
>     |.if DUALNUM
>-    |  add RC, BASE, RC
>     |  lwz TMP0, TAB:CARG1->asize
>-    |  lwz CARG2, 4(RC)
>+    |  lwzx CARG2, BASE_LO, RC
>     |   lwz TMP1, TAB:CARG1->array
>     |.else
>     |  lfdx f0, BASE, RC
>@@ -4177,13 +4292,13 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
> 
>   case BC_TSETV:
>     |  // RA = src*8, RB = table*8, RC = key*8
>-    |  lwzux CARG1, RB, BASE
>-    |  lwzux CARG2, RC, BASE
>-    |   lwz TAB:RB, 4(RB)
>+    |  lwzx CARG1, BASE_HI, RB
>+    |  lwzx CARG2, BASE_HI, RC
>+    |   lwzx TAB:RB, BASE_LO, RB
>     |.if DUALNUM
>-    |   lwz RC, 4(RC)
>+    |   lwzx RC, BASE_LO, RC
>     |.else
>-    |   lfd f0, 0(RC)
>+    |   lfdx f0, BASE, RC
>     |.endif
>     |  checktab CARG1
>     |   checknum cr1, CARG2
>@@ -4210,7 +4325,12 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     |   slwi TMP0, TMP2, 3
>     |.endif
>     |  ble ->vmeta_tsetv		// Integer key and in array part?
>+    |  .if ENDIAN_LE
>+    |   addi TMP2, TMP1, 4
>+    |   lwzx TMP2, TMP2, TMP0
>+    |  .else
>     |   lwzx TMP2, TMP1, TMP0
>+    |  .endif
>     |  lbz TMP3, TAB:RB->marked
>     |    lfdx f14, BASE, RA
>     |   checknil TMP2; beq >3
>@@ -4233,7 +4353,7 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     |5:
>     |  checkstr CARG2; bne ->vmeta_tsetv
>     |.if not DUALNUM
>-    |  lwz STR:RC, 4(RC)
>+    |  lwzx STR:RC, BASE_LO, RC
>     |.endif
>     |  b ->BC_TSETS_Z			// String key?
>     |
>@@ -4243,9 +4363,9 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     break;
>   case BC_TSETS:
>     |  // RA = src*8, RB = table*8, RC = str_const*8 (~)
>-    |  lwzux CARG1, RB, BASE
>+    |  lwzx CARG1, BASE_HI, RB
>     |   srwi TMP1, RC, 1
>-    |    lwz TAB:RB, 4(RB)
>+    |    lwzx TAB:RB, BASE_LO, RB
>     |   subfic TMP1, TMP1, -4
>     |  checktab CARG1
>     |   lwzx STR:RC, KBASE, TMP1	// KBASE-4-str_const*4
>@@ -4264,9 +4384,9 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     |    lbz TMP3, TAB:RB->marked
>     |  add NODE:TMP2, NODE:TMP2, TMP1	// node = tab->node + (idx*32-idx*8)
>     |1:
>-    |  lwz CARG1, NODE:TMP2->key
>-    |   lwz TMP0, 4+offsetof(Node, key)(NODE:TMP2)
>-    |    lwz CARG2, NODE:TMP2->val
>+    |  lwz CARG1, WORD_HI+offsetof(Node, key)(NODE:TMP2)
>+    |   lwz TMP0, WORD_LO+offsetof(Node, key)(NODE:TMP2)
>+    |    lwz CARG2, WORD_HI+offsetof(Node, val)(NODE:TMP2)
>     |     lwz NODE:TMP1, NODE:TMP2->next
>     |  checkstr CARG1; bne >5
>     |   cmpw TMP0, STR:RC; bne >5
>@@ -4306,13 +4426,14 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     |  beq ->vmeta_tsets		// 'no __newindex' flag NOT set: check.
>     |6:
>     |  li TMP0, LJ_TSTR
>-    |   stw STR:RC, 4(CARG3)
>+    |   stw STR:RC, WORD_LO(CARG3)
>     |   mr CARG2, TAB:RB
>-    |  stw TMP0, 0(CARG3)
>+    |  stw TMP0, WORD_HI(CARG3)
>     |  bl extern lj_tab_newkey		// (lua_State *L, GCtab *t, TValue *k)
>     |  // Returns TValue *.
>     |  lp BASE, L->base
>     |  stfd f14, 0(CRET1)
>+    |   addi BASEP4, BASE, 4
>     |  b <3				// No 2nd write barrier needed.
>     |
>     |7:  // Possible table write barrier for the value. Skip valiswhite check.
>@@ -4321,9 +4442,9 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     break;
>   case BC_TSETB:
>     |  // RA = src*8, RB = table*8, RC = index*8
>-    |  lwzux CARG1, RB, BASE
>+    |  lwzx CARG1, BASE_HI, RB
>     |   srwi TMP0, RC, 3
>-    |   lwz TAB:RB, 4(RB)
>+    |   lwzx TAB:RB, BASE_LO, RB
>     |  checktab CARG1; bne ->vmeta_tsetb
>     |  lwz TMP1, TAB:RB->asize
>     |   lwz TMP2, TAB:RB->array
>@@ -4331,7 +4452,12 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     |  cmplw TMP0, TMP1
>     |   lfdx f14, BASE, RA
>     |  bge ->vmeta_tsetb
>-    |  lwzx TMP1, TMP2, RC
>+    |  .if ENDIAN_LE
>+    |    addi TMP1, TMP2, 4
>+    |    lwzx TMP1, TMP1, RC
>+    |  .else
>+    |    lwzx TMP1, TMP2, RC
>+    |  .endif
>     |  checknil TMP1; beq >5
>     |1:
>     |  andix. TMP0, TMP3, LJ_GC_BLACK	// isblack(table)
>@@ -4355,13 +4481,11 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     break;
>   case BC_TSETR:
>     |  // RA = dst*8, RB = table*8, RC = key*8
>-    |  add RB, BASE, RB
>-    |  lwz TAB:CARG2, 4(RB)
>+    |  lwzx TAB:CARG2, BASE_LO, RB
>     |.if DUALNUM
>-    |  add RC, BASE, RC
>     |    lbz TMP3, TAB:CARG2->marked
>     |  lwz TMP0, TAB:CARG2->asize
>-    |  lwz CARG3, 4(RC)
>+    |  lwzx CARG3, BASE_LO, RC
>     |   lwz TMP1, TAB:CARG2->array
>     |.else
>     |  lfdx f0, BASE, RC
>@@ -4392,9 +4516,9 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     |  add RA, BASE, RA
>     |1:
>     |   add TMP3, KBASE, RD
>-    |  lwz TAB:CARG2, -4(RA)		// Guaranteed to be a table.
>+    |  lwz TAB:CARG2, WORD_LO-8(RA)	// Guaranteed to be a table.
>     |    addic. TMP0, MULTRES, -8
>-    |   lwz TMP3, 4(TMP3)		// Integer constant is in lo-word.
>+    |   lwz TMP3, WORD_LO(TMP3)		// Integer constant is in lo-word.
>     |    srwi CARG3, TMP0, 3
>     |    beq >4				// Nothing to copy?
>     |  add CARG3, CARG3, TMP3
>@@ -4443,8 +4567,7 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>   case BC_CALL:
>     |  // RA = base*8, (RB = (nresults+1)*8,) RC = (nargs+1)*8
>     |  mr TMP2, BASE
>-    |  lwzux TMP0, BASE, RA
>-    |   lwz LFUNC:RB, 4(BASE)
>+    |  lwzux2 TMP0, LFUNC:RB, BASE, RA
>     |    subi NARGS8:RC, NARGS8:RC, 8
>     |   addi BASE, BASE, 8
>     |  checkfunc TMP0; bne ->vmeta_call
>@@ -4458,8 +4581,7 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     break;
>   case BC_CALLT:
>     |  // RA = base*8, (RB = 0,) RC = (nargs+1)*8
>-    |  lwzux TMP0, RA, BASE
>-    |   lwz LFUNC:RB, 4(RA)
>+    |  lwzux2 TMP0, LFUNC:RB, RA, BASE
>     |    subi NARGS8:RC, NARGS8:RC, 8
>     |    lwz TMP1, FRAME_PC(BASE)
>     |  checkfunc TMP0
>@@ -4511,12 +4633,12 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     |  // RA = base*8, (RB = (nresults+1)*8, RC = (nargs+1)*8 ((2+1)*8))
>     |  mr TMP2, BASE
>     |  add BASE, BASE, RA
>-    |  lwz TMP1, -24(BASE)
>-    |   lwz LFUNC:RB, -20(BASE)
>+    |  lwz TMP1, WORD_HI-24(BASE)
>+    |   lwz LFUNC:RB, WORD_LO-24(BASE)
>     |    lfd f1, -8(BASE)
>     |    lfd f0, -16(BASE)
>-    |  stw TMP1, 0(BASE)		// Copy callable.
>-    |   stw LFUNC:RB, 4(BASE)
>+    |  stw TMP1, WORD_HI(BASE)		// Copy callable.
>+    |   stw LFUNC:RB, WORD_LO(BASE)
>     |  checkfunc TMP1
>     |    stfd f1, 16(BASE)		// Copy control var.
>     |     li NARGS8:RC, 16		// Iterators get 2 arguments.
>@@ -4531,8 +4653,8 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     |  // NYI: add hotloop, record BC_ITERN.
>     |.endif
>     |  add RA, BASE, RA
>-    |  lwz TAB:RB, -12(RA)
>-    |  lwz RC, -4(RA)			// Get index from control var.
>+    |  lwz TAB:RB, WORD_LO-16(RA)
>+    |  lwz RC, WORD_LO-8(RA)		// Get index from control var.
>     |  lwz TMP0, TAB:RB->asize
>     |  lwz TMP1, TAB:RB->array
>     |   addi PC, PC, 4
>@@ -4540,14 +4662,14 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     |  cmplw RC, TMP0
>     |   slwi TMP3, RC, 3
>     |  bge >5				// Index points after array part?
>-    |  lwzx TMP2, TMP1, TMP3
>-    |   lfdx f0, TMP1, TMP3
>+    |  lfdux f0, TMP3, TMP1
>+    |   lwz TMP2, WORD_HI(TMP3)
>     |  checknil TMP2
>     |     lwz INS, -4(PC)
>     |  beq >4
>     |.if DUALNUM
>-    |   stw RC, 4(RA)
>-    |   stw TISNUM, 0(RA)
>+    |   stw RC, WORD_LO(RA)
>+    |   stw TISNUM, WORD_HI(RA)
>     |.else
>     |   tonum_u f1, RC
>     |.endif
>@@ -4555,7 +4677,7 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     |     addis TMP3, PC, -(BCBIAS_J*4 >> 16)
>     |  stfd f0, 8(RA)
>     |     decode_RD4 TMP1, INS
>-    |    stw RC, -4(RA)			// Update control var.
>+    |    stw RC, WORD_LO-8(RA)		// Update control var.
>     |     add PC, TMP1, TMP3
>     |.if not DUALNUM
>     |   stfd f1, 0(RA)
>@@ -4577,9 +4699,8 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     |  bgty <3
>     |   slwi RB, RC, 3
>     |   sub TMP3, TMP3, RB
>-    |  lwzx RB, TMP2, TMP3
>-    |  lfdx f0, TMP2, TMP3
>-    |   add NODE:TMP3, TMP2, TMP3
>+    |  lfdux f0, TMP3, TMP2
>+    |  lwz RB, WORD_HI(TMP3)
>     |  checknil RB
>     |     lwz INS, -4(PC)
>     |  beq >7
>@@ -4591,7 +4712,7 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     |   stfd f1, 0(RA)
>     |    addi RC, RC, 1
>     |     add PC, TMP1, TMP2
>-    |    stw RC, -4(RA)			// Update control var.
>+    |    stw RC, WORD_LO-8(RA)		// Update control var.
>     |  b <3
>     |
>     |7:  // Skip holes in hash part.
>@@ -4602,10 +4723,10 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>   case BC_ISNEXT:
>     |  // RA = base*8, RD = target (points to ITERN)
>     |  add RA, BASE, RA
>-    |  lwz TMP0, -24(RA)
>-    |  lwz CFUNC:TMP1, -20(RA)
>-    |   lwz TMP2, -16(RA)
>-    |    lwz TMP3, -8(RA)
>+    |  lwz TMP0, WORD_HI-24(RA)
>+    |  lwz CFUNC:TMP1, WORD_LO-24(RA)
>+    |   lwz TMP2, WORD_HI-16(RA)
>+    |    lwz TMP3, WORD_HI-8(RA)
>     |   cmpwi cr0, TMP2, LJ_TTAB
>     |  cmpwi cr1, TMP0, LJ_TFUNC
>     |    cmpwi cr6, TMP3, LJ_TNIL
>@@ -4619,8 +4740,8 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     |  bne cr0, >5
>     |  lus TMP1, 0xfffe
>     |  ori TMP1, TMP1, 0x7fff
>-    |  stw ZERO, -4(RA)			// Initialize control var.
>-    |  stw TMP1, -8(RA)
>+    |  stw ZERO, WORD_LO-8(RA)		// Initialize control var.
>+    |  stw TMP1, WORD_HI-8(RA)
>     |    addis PC, TMP3, -(BCBIAS_J*4 >> 16)
>     |1:
>     |  ins_next
>@@ -4663,11 +4784,12 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     |    addi RA, RA, 8
>     |   blt cr1, <1			// More vararg slots?
>     |2:  // Fill up remainder with nil.
>-    |  stw TISNIL, 0(RA)
>+    |  stw TISNIL, WORD_HI(RA)
>     |  cmplw RA, TMP2
>     |   addi RA, RA, 8
>     |  blt <2
>     |3:
>+    |  addi BASEP4, BASE, 4
>     |  ins_next
>     |
>     |5:  // Copy all varargs.
>@@ -4748,13 +4870,14 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     |  bgt >6
>     |   sub BASE, TMP2, RA
>     |  lwz LFUNC:TMP1, FRAME_FUNC(BASE)
>+    |  addi BASEP4, BASE, 4
>     |  ins_next1
>     |  lwz TMP1, LFUNC:TMP1->pc
>     |  lwz KBASE, PC2PROTO(k)(TMP1)
>     |  ins_next2
>     |
>     |6:  // Fill up results with nil.
>-    |  subi TMP1, RD, 8
>+    |  addi TMP1, RD, WORD_HI-8
>     |   addi RD, RD, 8
>     |  stwx TISNIL, TMP2, TMP1
>     |  b <5
>@@ -4790,13 +4913,14 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     |  bgt >6
>     |   sub BASE, TMP2, RA
>     |  lwz LFUNC:TMP1, FRAME_FUNC(BASE)
>+    |  addi BASEP4, BASE, 4
>     |  ins_next1
>     |  lwz TMP1, LFUNC:TMP1->pc
>     |  lwz KBASE, PC2PROTO(k)(TMP1)
>     |  ins_next2
>     |
>     |6:  // Fill up results with nil.
>-    |  subi TMP1, RD, 8
>+    |  addi TMP1, RD, WORD_HI-8
>     |   addi RD, RD, 8
>     |  stwx TISNIL, TMP2, TMP1
>     |  b <5
>@@ -4822,11 +4946,10 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     vk = (op == BC_IFORL || op == BC_JFORL);
>     |.if DUALNUM
>     |  // Integer loop.
>-    |  lwzux TMP1, RA, BASE
>-    |   lwz CARG1, FORL_IDX*8+4(RA)
>+    |  lwzux2 TMP1, CARG1, RA, BASE
>     |  cmplw cr0, TMP1, TISNUM
>     if (vk) {
>-      |   lwz CARG3, FORL_STEP*8+4(RA)
>+      |   lwz CARG3, FORL_STEP*8+WORD_LO(RA)
>       |  bne >9
>       |.if GPR64
>       |  // Need to check overflow for (a<<32) + (b<<32).
>@@ -4838,15 +4961,15 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>       |  addo. CARG1, CARG1, CARG3
>       |.endif
>       |    cmpwi cr6, CARG3, 0
>-      |   lwz CARG2, FORL_STOP*8+4(RA)
>+      |   lwz CARG2, FORL_STOP*8+WORD_LO(RA)
>       |  bso >6
>       |4:
>-      |  stw CARG1, FORL_IDX*8+4(RA)
>+      |  stw CARG1, FORL_IDX*8+WORD_LO(RA)
>     } else {
>-      |  lwz TMP3, FORL_STEP*8(RA)
>-      |   lwz CARG3, FORL_STEP*8+4(RA)
>-      |  lwz TMP2, FORL_STOP*8(RA)
>-      |   lwz CARG2, FORL_STOP*8+4(RA)
>+      |  lwz TMP3, FORL_STEP*8+WORD_HI(RA)
>+      |   lwz CARG3, FORL_STEP*8+WORD_LO(RA)
>+      |  lwz TMP2, FORL_STOP*8+WORD_HI(RA)
>+      |   lwz CARG2, FORL_STOP*8+WORD_LO(RA)
>       |  cmplw cr7, TMP3, TISNUM
>       |  cmplw cr1, TMP2, TISNUM
>       |  crand 4*cr0+eq, 4*cr0+eq, 4*cr7+eq
>@@ -4857,11 +4980,11 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     |    blt cr6, >5
>     |  cmpw CARG1, CARG2
>     |1:
>-    |   stw TISNUM, FORL_EXT*8(RA)
>+    |   stw TISNUM, FORL_EXT*8+WORD_HI(RA)
>     if (op != BC_JFORL) {
>       |  srwi RD, RD, 1
>     }
>-    |   stw CARG1, FORL_EXT*8+4(RA)
>+    |   stw CARG1, FORL_EXT*8+WORD_LO(RA)
>     if (op != BC_JFORL) {
>       |  add RD, PC, RD
>     }
>@@ -4896,14 +5019,19 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>       |.endif
>       |  lfd f3, FORL_STEP*8(RA)
>       |  lfd f2, FORL_STOP*8(RA)
>-      |   lwz TMP3, FORL_STEP*8(RA)
>+      |   lwz TMP3, FORL_STEP*8+WORD_HI(RA)
>       |  fadd f1, f1, f3
>       |  stfd f1, FORL_IDX*8(RA)
>     } else {
>       |.if DUALNUM
>       |9:  // FP loop.
>       |.else
>+      |.if ENDIAN_LE
>+      |  lwzx TMP1, RA, BASE_LO
>+      |  add RA, RA, BASE
>+      |.else
>       |  lwzux TMP1, RA, BASE
>+      |.endif
>       |  lwz TMP3, FORL_STEP*8(RA)
>       |  lwz TMP2, FORL_STOP*8(RA)
>       |  cmplw cr0, TMP1, TISNUM
>@@ -4984,17 +5112,16 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
> #endif
>   case BC_IITERL:
>     |  // RA = base*8, RD = target
>-    |  lwzux TMP1, RA, BASE
>-    |   lwz TMP2, 4(RA)
>+    |  lwzux2 TMP1, TMP2, RA, BASE
>     |  checknil TMP1; beq >1		// Stop if iterator returned nil.
>     if (op == BC_JITERL) {
>-      |  stw TMP1, -8(RA)
>-      |   stw TMP2, -4(RA)
>+      |  stw TMP1, WORD_HI-8(RA)
>+      |   stw TMP2, WORD_LO-8(RA)
>       |  b =>BC_JLOOP
>     } else {
>       |  branch_RD			// Otherwise save control var + branch.
>-      |  stw TMP1, -8(RA)
>-      |   stw TMP2, -4(RA)
>+      |  stw TMP1, WORD_HI-8(RA)
>+      |   stw TMP2, WORD_LO-8(RA)
>     }
>     |1:
>     |  ins_next
>@@ -5075,7 +5202,7 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     }
>     |
>     |3:  // Clear missing parameters.
>-    |  stwx TISNIL, BASE, NARGS8:RC
>+    |  stwx TISNIL, BASE_HI, NARGS8:RC
>     |  addi NARGS8:RC, NARGS8:RC, 8
>     |  b <2
>     break;
>@@ -5092,11 +5219,11 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     |  lwz TMP2, L->maxstack
>     |   add TMP1, BASE, RC
>     |  add TMP0, RA, RC
>-    |   stw LFUNC:RB, 4(TMP1)		// Store copy of LFUNC.
>+    |   stw LFUNC:RB, WORD_LO(TMP1)	// Store copy of LFUNC.
>     |   addi TMP3, RC, 8+FRAME_VARG
>     |    lwz KBASE, -4+PC2PROTO(k)(PC)
>     |  cmplw TMP0, TMP2
>-    |   stw TMP3, 0(TMP1)		// Store delta + FRAME_VARG.
>+    |   stw TMP3, WORD_HI(TMP1)		// Store delta + FRAME_VARG.
>     |  bge ->vm_growstack_l
>     |  lbz TMP2, -4+PC2PROTO(numparams)(PC)
>     |   mr RA, BASE
>@@ -5107,18 +5234,19 @@ static void build_ins(BuildCtx *ctx, BCOp op, int defop)
>     |  beq >3
>     |1:
>     |  cmplw RA, RC			// Less args than parameters?
>-    |   lwz TMP0, 0(RA)
>-    |   lwz TMP3, 4(RA)
>+    |   lwz TMP0, WORD_HI(RA)
>+    |   lwz TMP3, WORD_LO(RA)
>     |  bge >4
>-    |    stw TISNIL, 0(RA)		// Clear old fixarg slot (help the GC).
>+    |    stw TISNIL, WORD_HI(RA)	// Clear old fixarg slot (help the GC).
>     |    addi RA, RA, 8
>     |2:
>     |  addic. TMP2, TMP2, -1
>-    |   stw TMP0, 8(TMP1)
>-    |   stw TMP3, 12(TMP1)
>+    |   stw TMP0, WORD_HI+8(TMP1)
>+    |   stw TMP3, WORD_LO+8(TMP1)
>     |    addi TMP1, TMP1, 8
>     |  bne <1
>     |3:
>+    |  addi BASEP4, BASE, 4
>     |  ins_next2
>     |
>     |4:  // Clear missing parameters.

Actions: View | Diff

Attachments on bug 1591701: 1451874 | 1451875 | 1451876 | 1451877 | 1451878 | 1451879 | 1451880 | 1451881 | 1451882 | 1579425