ffi 1.9.18 → 1.9.23

data/ext/ffi_c/libffi/src/powerpc/linux64_closure.S

@@ -30,68 +30,135 @@
 
 	.file	"linux64_closure.S"
 
-#ifdef __powerpc64__
+#ifdef POWERPC64
 	FFI_HIDDEN (ffi_closure_LINUX64)
-	FFI_HIDDEN (.ffi_closure_LINUX64)
-	.globl  ffi_closure_LINUX64, .ffi_closure_LINUX64
+	.globl  ffi_closure_LINUX64
+	.text
+	.cfi_startproc
+# if _CALL_ELF == 2
+ffi_closure_LINUX64:
+	addis	%r2, %r12, .TOC.-ffi_closure_LINUX64@ha
+	addi	%r2, %r2, .TOC.-ffi_closure_LINUX64@l
+	.localentry ffi_closure_LINUX64, . - ffi_closure_LINUX64
+# else
 	.section        ".opd","aw"
 	.align  3
 ffi_closure_LINUX64:
+#  ifdef _CALL_LINUX
+	.quad   .L.ffi_closure_LINUX64,.TOC.@tocbase,0
+	.type   ffi_closure_LINUX64,@function
+	.text
+.L.ffi_closure_LINUX64:
+#  else
+	FFI_HIDDEN (.ffi_closure_LINUX64)
+	.globl  .ffi_closure_LINUX64
 	.quad   .ffi_closure_LINUX64,.TOC.@tocbase,0
 	.size   ffi_closure_LINUX64,24
 	.type   .ffi_closure_LINUX64,@function
 	.text
 .ffi_closure_LINUX64:
-.LFB1:
-	# save general regs into parm save area
-	std	%r3, 48(%r1)
-	std	%r4, 56(%r1)
-	std	%r5, 64(%r1)
-	std	%r6, 72(%r1)
+#  endif
+# endif
+
+# if _CALL_ELF == 2
+#  32 byte special reg save area + 64 byte parm save area
+#  + 64 byte retval area + 13*8 fpr save area + round to 16
+#  define STACKFRAME 272
+#  define PARMSAVE 32
+#  define RETVAL PARMSAVE+64
+# else
+#  48 bytes special reg save area + 64 bytes parm save area
+#  + 16 bytes retval area + 13*8 bytes fpr save area + round to 16
+#  define STACKFRAME 240
+#  define PARMSAVE 48
+#  define RETVAL PARMSAVE+64
+# endif
+
+# if _CALL_ELF == 2
+	ld	%r12, FFI_TRAMPOLINE_SIZE(%r11)		# closure->cif
+	mflr	%r0
+	lwz	%r12, 28(%r12)				# cif->flags
+	mtcrf	0x40, %r12
+	addi	%r12, %r1, PARMSAVE
+	bt	7, 0f
+	# Our caller has not allocated a parameter save area.
+	# We need to allocate one here and use it to pass gprs to
+	# ffi_closure_helper_LINUX64.
+	addi	%r12, %r1, -STACKFRAME+PARMSAVE
+0:
+	# Save general regs into parm save area
+	std	%r3, 0(%r12)
+	std	%r4, 8(%r12)
+	std	%r5, 16(%r12)
+	std	%r6, 24(%r12)
+	std	%r7, 32(%r12)
+	std	%r8, 40(%r12)
+	std	%r9, 48(%r12)
+	std	%r10, 56(%r12)
+
+	# load up the pointer to the parm save area
+	mr	%r7, %r12
+# else
+	# copy r2 to r11 and load TOC into r2
+	mr	%r11, %r2
+	ld	%r2, 16(%r2)
+
 	mflr	%r0
+	# Save general regs into parm save area
+	# This is the parameter save area set up by our caller.
+	std	%r3, PARMSAVE+0(%r1)
+	std	%r4, PARMSAVE+8(%r1)
+	std	%r5, PARMSAVE+16(%r1)
+	std	%r6, PARMSAVE+24(%r1)
+	std	%r7, PARMSAVE+32(%r1)
+	std	%r8, PARMSAVE+40(%r1)
+	std	%r9, PARMSAVE+48(%r1)
+	std	%r10, PARMSAVE+56(%r1)
 
-	std	%r7, 80(%r1)
-	std	%r8, 88(%r1)
-	std	%r9, 96(%r1)
-	std	%r10, 104(%r1)
+	# load up the pointer to the parm save area
+	addi	%r7, %r1, PARMSAVE
+# endif
 	std	%r0, 16(%r1)
 
-	# mandatory 48 bytes special reg save area + 64 bytes parm save area
-	# + 16 bytes retval area + 13*8 bytes fpr save area + round to 16
-	stdu	%r1, -240(%r1)
-.LCFI0:
+	# closure->cif
+	ld	%r3, FFI_TRAMPOLINE_SIZE(%r11)
+	# closure->fun
+	ld	%r4, FFI_TRAMPOLINE_SIZE+8(%r11)
+	# closure->user_data
+	ld	%r5, FFI_TRAMPOLINE_SIZE+16(%r11)
 
+.Ldoclosure:
 	# next save fpr 1 to fpr 13
-	stfd  %f1, 128+(0*8)(%r1)
-	stfd  %f2, 128+(1*8)(%r1)
-	stfd  %f3, 128+(2*8)(%r1)
-	stfd  %f4, 128+(3*8)(%r1)
-	stfd  %f5, 128+(4*8)(%r1)
-	stfd  %f6, 128+(5*8)(%r1)
-	stfd  %f7, 128+(6*8)(%r1)
-	stfd  %f8, 128+(7*8)(%r1)
-	stfd  %f9, 128+(8*8)(%r1)
-	stfd  %f10, 128+(9*8)(%r1)
-	stfd  %f11, 128+(10*8)(%r1)
-	stfd  %f12, 128+(11*8)(%r1)
-	stfd  %f13, 128+(12*8)(%r1)
-
-	# set up registers for the routine that actually does the work
-	# get the context pointer from the trampoline
-	mr %r3, %r11
-
-	# now load up the pointer to the result storage
-	addi %r4, %r1, 112
-
-	# now load up the pointer to the parameter save area
-	# in the previous frame
-	addi %r5, %r1, 240 + 48
-
-	# now load up the pointer to the saved fpr registers */
-	addi %r6, %r1, 128
+	stfd	%f1, -104+(0*8)(%r1)
+	stfd	%f2, -104+(1*8)(%r1)
+	stfd	%f3, -104+(2*8)(%r1)
+	stfd	%f4, -104+(3*8)(%r1)
+	stfd	%f5, -104+(4*8)(%r1)
+	stfd	%f6, -104+(5*8)(%r1)
+	stfd	%f7, -104+(6*8)(%r1)
+	stfd	%f8, -104+(7*8)(%r1)
+	stfd	%f9, -104+(8*8)(%r1)
+	stfd	%f10, -104+(9*8)(%r1)
+	stfd	%f11, -104+(10*8)(%r1)
+	stfd	%f12, -104+(11*8)(%r1)
+	stfd	%f13, -104+(12*8)(%r1)
+
+	# load up the pointer to the saved fpr registers */
+	addi	%r8, %r1, -104
+
+	# load up the pointer to the result storage
+	addi	%r6, %r1, -STACKFRAME+RETVAL
+
+	stdu	%r1, -STACKFRAME(%r1)
+	.cfi_def_cfa_offset STACKFRAME
+	.cfi_offset 65, 16
 
 	# make the call
+# if defined _CALL_LINUX || _CALL_ELF == 2
+	bl ffi_closure_helper_LINUX64
+# else
 	bl .ffi_closure_helper_LINUX64
+# endif
 .Lret:
 
 	# now r3 contains the return type
@@ -100,10 +167,12 @@ ffi_closure_LINUX64:
 
 	# look up the proper starting point in table
 	# by using return type as offset
+	ld %r0, STACKFRAME+16(%r1)
+	cmpldi %r3, FFI_V2_TYPE_SMALL_STRUCT
+	bge .Lsmall
 	mflr %r4		# move address of .Lret to r4
 	sldi %r3, %r3, 4	# now multiply return type by 16
 	addi %r4, %r4, .Lret_type0 - .Lret
-	ld %r0, 240+16(%r1)
 	add %r3, %r3, %r4	# add contents of table to table address
 	mtctr %r3
 	bctr			# jump to it
@@ -116,121 +185,304 @@ ffi_closure_LINUX64:
 .Lret_type0:
 # case FFI_TYPE_VOID
 	mtlr %r0
-	addi %r1, %r1, 240
+	addi %r1, %r1, STACKFRAME
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset STACKFRAME
 	nop
 # case FFI_TYPE_INT
-	lwa %r3, 112+4(%r1)
+# ifdef __LITTLE_ENDIAN__
+	lwa %r3, RETVAL+0(%r1)
+# else
+	lwa %r3, RETVAL+4(%r1)
+# endif
 	mtlr %r0
-	addi %r1, %r1, 240
+	addi %r1, %r1, STACKFRAME
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset STACKFRAME
 # case FFI_TYPE_FLOAT
-	lfs %f1, 112+0(%r1)
+	lfs %f1, RETVAL+0(%r1)
 	mtlr %r0
-	addi %r1, %r1, 240
+	addi %r1, %r1, STACKFRAME
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset STACKFRAME
 # case FFI_TYPE_DOUBLE
-	lfd %f1, 112+0(%r1)
+	lfd %f1, RETVAL+0(%r1)
 	mtlr %r0
-	addi %r1, %r1, 240
+	addi %r1, %r1, STACKFRAME
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset STACKFRAME
 # case FFI_TYPE_LONGDOUBLE
-	lfd %f1, 112+0(%r1)
+	lfd %f1, RETVAL+0(%r1)
 	mtlr %r0
-	lfd %f2, 112+8(%r1)
+	lfd %f2, RETVAL+8(%r1)
 	b .Lfinish
 # case FFI_TYPE_UINT8
-	lbz %r3, 112+7(%r1)
+# ifdef __LITTLE_ENDIAN__
+	lbz %r3, RETVAL+0(%r1)
+# else
+	lbz %r3, RETVAL+7(%r1)
+# endif
 	mtlr %r0
-	addi %r1, %r1, 240
+	addi %r1, %r1, STACKFRAME
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset STACKFRAME
 # case FFI_TYPE_SINT8
-	lbz %r3, 112+7(%r1)
+# ifdef __LITTLE_ENDIAN__
+	lbz %r3, RETVAL+0(%r1)
+# else
+	lbz %r3, RETVAL+7(%r1)
+# endif
 	extsb %r3,%r3
 	mtlr %r0
 	b .Lfinish
 # case FFI_TYPE_UINT16
-	lhz %r3, 112+6(%r1)
+# ifdef __LITTLE_ENDIAN__
+	lhz %r3, RETVAL+0(%r1)
+# else
+	lhz %r3, RETVAL+6(%r1)
+# endif
 	mtlr %r0
 .Lfinish:
-	addi %r1, %r1, 240
+	addi %r1, %r1, STACKFRAME
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset STACKFRAME
 # case FFI_TYPE_SINT16
-	lha %r3, 112+6(%r1)
+# ifdef __LITTLE_ENDIAN__
+	lha %r3, RETVAL+0(%r1)
+# else
+	lha %r3, RETVAL+6(%r1)
+# endif
 	mtlr %r0
-	addi %r1, %r1, 240
+	addi %r1, %r1, STACKFRAME
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset STACKFRAME
 # case FFI_TYPE_UINT32
-	lwz %r3, 112+4(%r1)
+# ifdef __LITTLE_ENDIAN__
+	lwz %r3, RETVAL+0(%r1)
+# else
+	lwz %r3, RETVAL+4(%r1)
+# endif
 	mtlr %r0
-	addi %r1, %r1, 240
+	addi %r1, %r1, STACKFRAME
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset STACKFRAME
 # case FFI_TYPE_SINT32
-	lwa %r3, 112+4(%r1)
+# ifdef __LITTLE_ENDIAN__
+	lwa %r3, RETVAL+0(%r1)
+# else
+	lwa %r3, RETVAL+4(%r1)
+# endif
 	mtlr %r0
-	addi %r1, %r1, 240
+	addi %r1, %r1, STACKFRAME
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset STACKFRAME
 # case FFI_TYPE_UINT64
-	ld %r3, 112+0(%r1)
+	ld %r3, RETVAL+0(%r1)
 	mtlr %r0
-	addi %r1, %r1, 240
+	addi %r1, %r1, STACKFRAME
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset STACKFRAME
 # case FFI_TYPE_SINT64
-	ld %r3, 112+0(%r1)
+	ld %r3, RETVAL+0(%r1)
 	mtlr %r0
-	addi %r1, %r1, 240
+	addi %r1, %r1, STACKFRAME
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset STACKFRAME
 # case FFI_TYPE_STRUCT
 	mtlr %r0
-	addi %r1, %r1, 240
+	addi %r1, %r1, STACKFRAME
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset STACKFRAME
 	nop
 # case FFI_TYPE_POINTER
-	ld %r3, 112+0(%r1)
+	ld %r3, RETVAL+0(%r1)
+	mtlr %r0
+	addi %r1, %r1, STACKFRAME
+	.cfi_def_cfa_offset 0
+	blr
+	.cfi_def_cfa_offset STACKFRAME
+# case FFI_V2_TYPE_FLOAT_HOMOG
+	lfs %f1, RETVAL+0(%r1)
+	lfs %f2, RETVAL+4(%r1)
+	lfs %f3, RETVAL+8(%r1)
+	b .Lmorefloat
+# case FFI_V2_TYPE_DOUBLE_HOMOG
+	lfd %f1, RETVAL+0(%r1)
+	lfd %f2, RETVAL+8(%r1)
+	lfd %f3, RETVAL+16(%r1)
+	lfd %f4, RETVAL+24(%r1)
+	mtlr %r0
+	lfd %f5, RETVAL+32(%r1)
+	lfd %f6, RETVAL+40(%r1)
+	lfd %f7, RETVAL+48(%r1)
+	lfd %f8, RETVAL+56(%r1)
+	addi %r1, %r1, STACKFRAME
+	.cfi_def_cfa_offset 0
+	blr
+	.cfi_def_cfa_offset STACKFRAME
+.Lmorefloat:
+	lfs %f4, RETVAL+12(%r1)
+	mtlr %r0
+	lfs %f5, RETVAL+16(%r1)
+	lfs %f6, RETVAL+20(%r1)
+	lfs %f7, RETVAL+24(%r1)
+	lfs %f8, RETVAL+28(%r1)
+	addi %r1, %r1, STACKFRAME
+	.cfi_def_cfa_offset 0
+	blr
+	.cfi_def_cfa_offset STACKFRAME
+.Lsmall:
+# ifdef __LITTLE_ENDIAN__
+	ld %r3,RETVAL+0(%r1)
+	mtlr %r0
+	ld %r4,RETVAL+8(%r1)
+	addi %r1, %r1, STACKFRAME
+	.cfi_def_cfa_offset 0
+	blr
+# else
+	# A struct smaller than a dword is returned in the low bits of r3
+	# ie. right justified.  Larger structs are passed left justified
+	# in r3 and r4.  The return value area on the stack will have
+	# the structs as they are usually stored in memory.
+	cmpldi %r3, FFI_V2_TYPE_SMALL_STRUCT + 7 # size 8 bytes?
+	neg %r5, %r3
+	ld %r3,RETVAL+0(%r1)
+	blt .Lsmalldown
+	mtlr %r0
+	ld %r4,RETVAL+8(%r1)
+	addi %r1, %r1, STACKFRAME
+	.cfi_def_cfa_offset 0
+	blr
+	.cfi_def_cfa_offset STACKFRAME
+.Lsmalldown:
+	addi %r5, %r5, FFI_V2_TYPE_SMALL_STRUCT + 7
 	mtlr %r0
-	addi %r1, %r1, 240
+	sldi %r5, %r5, 3
+	addi %r1, %r1, STACKFRAME
+	.cfi_def_cfa_offset 0
+	srd %r3, %r3, %r5
 	blr
-# esac
-.LFE1:
+# endif
+
+	.cfi_endproc
+# if _CALL_ELF == 2
+	.size	ffi_closure_LINUX64,.-ffi_closure_LINUX64
+# else
+#  ifdef _CALL_LINUX
+	.size	ffi_closure_LINUX64,.-.L.ffi_closure_LINUX64
+#  else
 	.long	0
 	.byte	0,12,0,1,128,0,0,0
 	.size	.ffi_closure_LINUX64,.-.ffi_closure_LINUX64
+#  endif
+# endif
+
+
+	FFI_HIDDEN (ffi_go_closure_linux64)
+	.globl  ffi_go_closure_linux64
+	.text
+	.cfi_startproc
+# if _CALL_ELF == 2
+ffi_go_closure_linux64:
+	addis	%r2, %r12, .TOC.-ffi_go_closure_linux64@ha
+	addi	%r2, %r2, .TOC.-ffi_go_closure_linux64@l
+	.localentry ffi_go_closure_linux64, . - ffi_go_closure_linux64
+# else
+	.section        ".opd","aw"
+	.align  3
+ffi_go_closure_linux64:
+#  ifdef _CALL_LINUX
+	.quad   .L.ffi_go_closure_linux64,.TOC.@tocbase,0
+	.type   ffi_go_closure_linux64,@function
+	.text
+.L.ffi_go_closure_linux64:
+#  else
+	FFI_HIDDEN (.ffi_go_closure_linux64)
+	.globl  .ffi_go_closure_linux64
+	.quad   .ffi_go_closure_linux64,.TOC.@tocbase,0
+	.size   ffi_go_closure_linux64,24
+	.type   .ffi_go_closure_linux64,@function
+	.text
+.ffi_go_closure_linux64:
+#  endif
+# endif
+
+# if _CALL_ELF == 2
+	ld	%r12, 8(%r11)				# closure->cif
+	mflr	%r0
+	lwz	%r12, 28(%r12)				# cif->flags
+	mtcrf	0x40, %r12
+	addi	%r12, %r1, PARMSAVE
+	bt	7, 0f
+	# Our caller has not allocated a parameter save area.
+	# We need to allocate one here and use it to pass gprs to
+	# ffi_closure_helper_LINUX64.
+	addi	%r12, %r1, -STACKFRAME+PARMSAVE
+0:
+	# Save general regs into parm save area
+	std	%r3, 0(%r12)
+	std	%r4, 8(%r12)
+	std	%r5, 16(%r12)
+	std	%r6, 24(%r12)
+	std	%r7, 32(%r12)
+	std	%r8, 40(%r12)
+	std	%r9, 48(%r12)
+	std	%r10, 56(%r12)
+
+	# load up the pointer to the parm save area
+	mr	%r7, %r12
+# else
+	mflr	%r0
+	# Save general regs into parm save area
+	# This is the parameter save area set up by our caller.
+	std	%r3, PARMSAVE+0(%r1)
+	std	%r4, PARMSAVE+8(%r1)
+	std	%r5, PARMSAVE+16(%r1)
+	std	%r6, PARMSAVE+24(%r1)
+	std	%r7, PARMSAVE+32(%r1)
+	std	%r8, PARMSAVE+40(%r1)
+	std	%r9, PARMSAVE+48(%r1)
+	std	%r10, PARMSAVE+56(%r1)
 
-	.section	.eh_frame,EH_FRAME_FLAGS,@progbits
-.Lframe1:
-	.4byte	.LECIE1-.LSCIE1	 # Length of Common Information Entry
-.LSCIE1:
-	.4byte	0x0	 # CIE Identifier Tag
-	.byte	0x1	 # CIE Version
-	.ascii "zR\0"	 # CIE Augmentation
-	.uleb128 0x1	 # CIE Code Alignment Factor
-	.sleb128 -8	 # CIE Data Alignment Factor
-	.byte	0x41	 # CIE RA Column
-	.uleb128 0x1	 # Augmentation size
-	.byte	0x14	 # FDE Encoding (pcrel udata8)
-	.byte	0xc	 # DW_CFA_def_cfa
-	.uleb128 0x1
-	.uleb128 0x0
-	.align 3
-.LECIE1:
-.LSFDE1:
-	.4byte	.LEFDE1-.LASFDE1	 # FDE Length
-.LASFDE1:
-	.4byte	.LASFDE1-.Lframe1	 # FDE CIE offset
-	.8byte	.LFB1-.	 # FDE initial location
-	.8byte	.LFE1-.LFB1	 # FDE address range
-	.uleb128 0x0	 # Augmentation size
-	.byte	0x2	 # DW_CFA_advance_loc1
-	.byte	.LCFI0-.LFB1
-	.byte	0xe	 # DW_CFA_def_cfa_offset
-	.uleb128 240
-	.byte	0x11	 # DW_CFA_offset_extended_sf
-	.uleb128 0x41
-	.sleb128 -2
-	.align 3
-.LEFDE1:
+	# load up the pointer to the parm save area
+	addi	%r7, %r1, PARMSAVE
+# endif
+	std	%r0, 16(%r1)
+
+	# closure->cif
+	ld	%r3, 8(%r11)
+	# closure->fun
+	ld	%r4, 16(%r11)
+	# user_data
+	mr	%r5, %r11
+	b	.Ldoclosure
+
+	.cfi_endproc
+# if _CALL_ELF == 2
+	.size	ffi_go_closure_linux64,.-ffi_go_closure_linux64
+# else
+#  ifdef _CALL_LINUX
+	.size	ffi_go_closure_linux64,.-.L.ffi_go_closure_linux64
+#  else
+	.long	0
+	.byte	0,12,0,1,128,0,0,0
+	.size	.ffi_go_closure_linux64,.-.ffi_go_closure_linux64
+#  endif
+# endif
 #endif
 
-#if defined __ELF__ && defined __linux__
+#if (defined __ELF__ && defined __linux__) || _CALL_ELF == 2
 	.section	.note.GNU-stack,"",@progbits
 #endif