ffi 1.1.5 → 1.15.5

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

@@ -31,15 +31,16 @@
 
 	.file   "ppc_closure.S"
 
-#ifndef __powerpc64__
+#ifndef POWERPC64
 
+FFI_HIDDEN(ffi_closure_SYSV)
 ENTRY(ffi_closure_SYSV)
-.LFB1:
+	.cfi_startproc
 	stwu %r1,-144(%r1)
-.LCFI0:
+	.cfi_def_cfa_offset 144
 	mflr %r0
-.LCFI1:
 	stw %r0,148(%r1)
+	.cfi_offset 65, 4
 
 # we want to build up an areas for the parameters passed
 # in registers (both floating point and integer)
@@ -48,6 +49,17 @@ ENTRY(ffi_closure_SYSV)
 	stw   %r3, 16(%r1)
 	stw   %r4, 20(%r1)
 	stw   %r5, 24(%r1)
+
+	# set up registers for the routine that does the work
+
+	# closure->cif
+	lwz %r3,FFI_TRAMPOLINE_SIZE(%r11)
+	# closure->fun
+	lwz %r4,FFI_TRAMPOLINE_SIZE+4(%r11)
+	# closure->user_data
+	lwz %r5,FFI_TRAMPOLINE_SIZE+8(%r11)
+
+.Ldoclosure:
 	stw   %r6, 28(%r1)
 	stw   %r7, 32(%r1)
 	stw   %r8, 36(%r1)
@@ -66,23 +78,18 @@ ENTRY(ffi_closure_SYSV)
 	stfd  %f8, 104(%r1)
 #endif
 
-	# set up registers for the routine that actually does the work
-	# get the context pointer from the trampoline
-	mr %r3,%r11
+	# pointer to the result storage
+	addi %r6,%r1,112
 
-	# now load up the pointer to the result storage
-	addi %r4,%r1,112
+	# pointer to the saved gpr registers
+	addi %r7,%r1,16
 
-	# now load up the pointer to the saved gpr registers
-	addi %r5,%r1,16
+	# pointer to the saved fpr registers
+	addi %r8,%r1,48
 
-	# now load up the pointer to the saved fpr registers */
-	addi %r6,%r1,48
-
-	# now load up the pointer to the outgoing parameter
-	# stack in the previous frame
+	# pointer to the outgoing parameter save area in the previous frame
 	# i.e. the previous frame pointer + 8
-	addi %r7,%r1,152
+	addi %r9,%r1,152
 
 	# make the call
 	bl ffi_closure_helper_SYSV@local
@@ -101,7 +108,6 @@ ENTRY(ffi_closure_SYSV)
 	add %r3,%r3,%r4		# add contents of table to table address
 	mtctr %r3
 	bctr			# jump to it
-.LFE1:
 
 # Each of the ret_typeX code fragments has to be exactly 16 bytes long
 # (4 instructions). For cache effectiveness we align to a 16 byte boundary
@@ -111,7 +117,9 @@ ENTRY(ffi_closure_SYSV)
 .Lret_type0:
 	mtlr %r0
 	addi %r1,%r1,144
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset 144
 	nop
 
 # case FFI_TYPE_INT
@@ -119,61 +127,110 @@ ENTRY(ffi_closure_SYSV)
 	mtlr %r0
 .Lfinish:
 	addi %r1,%r1,144
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset 144
 
 # case FFI_TYPE_FLOAT
+#ifndef __NO_FPRS__
 	lfs %f1,112+0(%r1)
+#else
+	nop
+#endif
 	mtlr %r0
 	addi %r1,%r1,144
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset 144
 
 # case FFI_TYPE_DOUBLE
+#ifndef __NO_FPRS__
 	lfd %f1,112+0(%r1)
+#else
+	nop
+#endif
 	mtlr %r0
 	addi %r1,%r1,144
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset 144
 
 # case FFI_TYPE_LONGDOUBLE
+#ifndef __NO_FPRS__
 	lfd %f1,112+0(%r1)
 	lfd %f2,112+8(%r1)
 	mtlr %r0
 	b .Lfinish
+#else
+	mtlr %r0
+	addi %r1,%r1,144
+	.cfi_def_cfa_offset 0
+	blr
+	.cfi_def_cfa_offset 144
+	nop
+#endif
 
 # case FFI_TYPE_UINT8
+#ifdef __LITTLE_ENDIAN__
+	lbz %r3,112+0(%r1)
+#else
 	lbz %r3,112+3(%r1)
+#endif
 	mtlr %r0
 	addi %r1,%r1,144
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset 144
 
 # case FFI_TYPE_SINT8
+#ifdef __LITTLE_ENDIAN__
+	lbz %r3,112+0(%r1)
+#else
 	lbz %r3,112+3(%r1)
+#endif
 	extsb %r3,%r3
 	mtlr %r0
 	b .Lfinish
 
 # case FFI_TYPE_UINT16
+#ifdef __LITTLE_ENDIAN__
+	lhz %r3,112+0(%r1)
+#else
 	lhz %r3,112+2(%r1)
+#endif
 	mtlr %r0
 	addi %r1,%r1,144
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset 144
 
 # case FFI_TYPE_SINT16
+#ifdef __LITTLE_ENDIAN__
+	lha %r3,112+0(%r1)
+#else
 	lha %r3,112+2(%r1)
+#endif
 	mtlr %r0
 	addi %r1,%r1,144
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset 144
 
 # case FFI_TYPE_UINT32
 	lwz %r3,112+0(%r1)
 	mtlr %r0
 	addi %r1,%r1,144
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset 144
 
 # case FFI_TYPE_SINT32
 	lwz %r3,112+0(%r1)
 	mtlr %r0
 	addi %r1,%r1,144
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset 144
 
 # case FFI_TYPE_UINT64
 	lwz %r3,112+0(%r1)
@@ -190,63 +247,96 @@ ENTRY(ffi_closure_SYSV)
 # case FFI_TYPE_STRUCT
 	mtlr %r0
 	addi %r1,%r1,144
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset 144
 	nop
 
 # case FFI_TYPE_POINTER
 	lwz %r3,112+0(%r1)
 	mtlr %r0
 	addi %r1,%r1,144
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset 144
 
 # case FFI_TYPE_UINT128
 	lwz %r3,112+0(%r1)
 	lwz %r4,112+4(%r1)
 	lwz %r5,112+8(%r1)
-	bl .Luint128
+	b .Luint128
 
 # The return types below are only used when the ABI type is FFI_SYSV.
 # case FFI_SYSV_TYPE_SMALL_STRUCT + 1. One byte struct.
 	lbz %r3,112+0(%r1)
 	mtlr %r0
 	addi %r1,%r1,144
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset 144
 
 # case FFI_SYSV_TYPE_SMALL_STRUCT + 2. Two byte struct.
 	lhz %r3,112+0(%r1)
 	mtlr %r0
 	addi %r1,%r1,144
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset 144
 
 # case FFI_SYSV_TYPE_SMALL_STRUCT + 3. Three byte struct.
 	lwz %r3,112+0(%r1)
+#ifdef __LITTLE_ENDIAN__
+	mtlr %r0
+	addi %r1,%r1,144
+	.cfi_def_cfa_offset 0
+	blr
+	.cfi_def_cfa_offset 144
+#else
 	srwi %r3,%r3,8
 	mtlr %r0
 	b .Lfinish
+#endif
 
 # case FFI_SYSV_TYPE_SMALL_STRUCT + 4. Four byte struct.
 	lwz %r3,112+0(%r1)
 	mtlr %r0
 	addi %r1,%r1,144
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset 144
 
 # case FFI_SYSV_TYPE_SMALL_STRUCT + 5. Five byte struct.
 	lwz %r3,112+0(%r1)
 	lwz %r4,112+4(%r1)
+#ifdef __LITTLE_ENDIAN__
+	mtlr %r0
+	b .Lfinish
+#else
 	li %r5,24
 	b .Lstruct567
+#endif
 
 # case FFI_SYSV_TYPE_SMALL_STRUCT + 6. Six byte struct.
 	lwz %r3,112+0(%r1)
 	lwz %r4,112+4(%r1)
+#ifdef __LITTLE_ENDIAN__
+	mtlr %r0
+	b .Lfinish
+#else
 	li %r5,16
 	b .Lstruct567
+#endif
 
 # case FFI_SYSV_TYPE_SMALL_STRUCT + 7. Seven byte struct.
 	lwz %r3,112+0(%r1)
 	lwz %r4,112+4(%r1)
+#ifdef __LITTLE_ENDIAN__
+	mtlr %r0
+	b .Lfinish
+#else
 	li %r5,8
 	b .Lstruct567
+#endif
 
 # case FFI_SYSV_TYPE_SMALL_STRUCT + 8. Eight byte struct.
 	lwz %r3,112+0(%r1)
@@ -254,6 +344,7 @@ ENTRY(ffi_closure_SYSV)
 	mtlr %r0
 	b .Lfinish
 
+#ifndef __LITTLE_ENDIAN__
 .Lstruct567:
 	subfic %r6,%r5,32
 	srw %r4,%r4,%r5
@@ -262,66 +353,45 @@ ENTRY(ffi_closure_SYSV)
 	or %r4,%r6,%r4
 	mtlr %r0
 	addi %r1,%r1,144
+	.cfi_def_cfa_offset 0
 	blr
+	.cfi_def_cfa_offset 144
+#endif
 
 .Luint128:
 	lwz %r6,112+12(%r1)
 	mtlr %r0
 	addi %r1,%r1,144
+	.cfi_def_cfa_offset 0
 	blr
-
+	.cfi_endproc
 END(ffi_closure_SYSV)
 
-	.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
-#if defined _RELOCATABLE || defined __PIC__
-	.ascii "zR\0"	 # CIE Augmentation
-#else
-	.ascii "\0"	 # CIE Augmentation
-#endif
-	.uleb128 0x1	 # CIE Code Alignment Factor
-	.sleb128 -4	 # CIE Data Alignment Factor
-	.byte	0x41	 # CIE RA Column
-#if defined _RELOCATABLE || defined __PIC__
-	.uleb128 0x1	 # Augmentation size
-	.byte	0x1b	 # FDE Encoding (pcrel sdata4)
-#endif
-	.byte	0xc	 # DW_CFA_def_cfa
-	.uleb128 0x1
-	.uleb128 0x0
-	.align 2
-.LECIE1:
-.LSFDE1:
-	.4byte	.LEFDE1-.LASFDE1	 # FDE Length
-.LASFDE1:
-	.4byte	.LASFDE1-.Lframe1	 # FDE CIE offset
-#if defined _RELOCATABLE || defined __PIC__
-	.4byte	.LFB1-.	 # FDE initial location
-#else
-	.4byte	.LFB1	 # FDE initial location
-#endif
-	.4byte	.LFE1-.LFB1	 # FDE address range
-#if defined _RELOCATABLE || defined __PIC__
-	.uleb128 0x0	 # Augmentation size
-#endif
-	.byte	0x4	 # DW_CFA_advance_loc4
-	.4byte	.LCFI0-.LFB1
-	.byte	0xe	 # DW_CFA_def_cfa_offset
-	.uleb128 144
-	.byte	0x4	 # DW_CFA_advance_loc4
-	.4byte	.LCFI1-.LCFI0
-	.byte	0x11	 # DW_CFA_offset_extended_sf
-	.uleb128 0x41
-	.sleb128 -1
-	.align 2
-.LEFDE1:
 
-#endif
+FFI_HIDDEN(ffi_go_closure_sysv)
+ENTRY(ffi_go_closure_sysv)
+	.cfi_startproc
+	stwu %r1,-144(%r1)
+	.cfi_def_cfa_offset 144
+	mflr %r0
+	stw %r0,148(%r1)
+	.cfi_offset 65, 4
+
+	stw   %r3, 16(%r1)
+	stw   %r4, 20(%r1)
+	stw   %r5, 24(%r1)
+
+	# closure->cif
+	lwz %r3,4(%r11)
+	# closure->fun
+	lwz %r4,8(%r11)
+	# user_data
+	mr %r5,%r11
+	b .Ldoclosure
+	.cfi_endproc
+END(ffi_go_closure_sysv)
 
 #if defined __ELF__ && defined __linux__
 	.section	.note.GNU-stack,"",@progbits
 #endif
+#endif

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

@@ -30,35 +30,36 @@
 #include <ffi.h>
 #include <powerpc/asm.h>
 
-#ifndef __powerpc64__
-	.globl ffi_prep_args_SYSV
+#ifndef POWERPC64
+FFI_HIDDEN(ffi_call_SYSV)
 ENTRY(ffi_call_SYSV)
-.LFB1:
+	.cfi_startproc
 	/* Save the old stack pointer as AP.  */
-	mr	%r8,%r1
+	mr	%r10,%r1
+	.cfi_def_cfa_register 10
 
-.LCFI0:
 	/* Allocate the stack space we need.  */
-	stwux	%r1,%r1,%r4
+	stwux	%r1,%r1,%r8
 	/* Save registers we use.  */
 	mflr	%r9
-	stw	%r28,-16(%r8)
-.LCFI1:
-	stw	%r29,-12(%r8)
-.LCFI2:
-	stw	%r30, -8(%r8)
-.LCFI3:
-	stw	%r31, -4(%r8)
-.LCFI4:
-	stw	%r9,   4(%r8)
-.LCFI5:
+	stw	%r28,-16(%r10)
+	stw	%r29,-12(%r10)
+	stw	%r30, -8(%r10)
+	stw	%r31, -4(%r10)
+	stw	%r9,   4(%r10)
+	.cfi_offset 65, 4
+	.cfi_offset 31, -4
+	.cfi_offset 30, -8
+	.cfi_offset 29, -12
+	.cfi_offset 28, -16
 
 	/* Save arguments over call...  */
-	mr	%r31,%r5	/* flags, */
-	mr	%r30,%r6	/* rvalue, */
-	mr	%r29,%r7	/* function address, */
-	mr	%r28,%r8	/* our AP. */
-.LCFI6:
+	stw	%r7,   -20(%r10)	/* closure, */
+	mr	%r31,%r6		/* flags, */
+	mr	%r30,%r5		/* rvalue, */
+	mr	%r29,%r4		/* function address, */
+	mr	%r28,%r10		/* our AP. */
+	.cfi_def_cfa_register 28
 
 	/* Call ffi_prep_args_SYSV.  */
 	mr	%r4,%r1
@@ -70,45 +71,49 @@ ENTRY(ffi_call_SYSV)
 	/* Get the address to call into CTR.  */
 	mtctr	%r29
 	/* Load all those argument registers.  */
-	lwz	%r3,-16-(8*4)(%r28)
-	lwz	%r4,-16-(7*4)(%r28)
-	lwz	%r5,-16-(6*4)(%r28)
-	lwz	%r6,-16-(5*4)(%r28)
+	lwz	%r3,-24-(8*4)(%r28)
+	lwz	%r4,-24-(7*4)(%r28)
+	lwz	%r5,-24-(6*4)(%r28)
+	lwz	%r6,-24-(5*4)(%r28)
 	bf-	5,1f
 	nop
-	lwz	%r7,-16-(4*4)(%r28)
-	lwz	%r8,-16-(3*4)(%r28)
-	lwz	%r9,-16-(2*4)(%r28)
-	lwz	%r10,-16-(1*4)(%r28)
+	lwz	%r7,-24-(4*4)(%r28)
+	lwz	%r8,-24-(3*4)(%r28)
+	lwz	%r9,-24-(2*4)(%r28)
+	lwz	%r10,-24-(1*4)(%r28)
 	nop
 1:
 
+#ifndef __NO_FPRS__
 	/* Load all the FP registers.  */
 	bf-	6,2f
-	lfd	%f1,-16-(8*4)-(8*8)(%r28)
-	lfd	%f2,-16-(8*4)-(7*8)(%r28)
-	lfd	%f3,-16-(8*4)-(6*8)(%r28)
-	lfd	%f4,-16-(8*4)-(5*8)(%r28)
+	lfd	%f1,-24-(8*4)-(8*8)(%r28)
+	lfd	%f2,-24-(8*4)-(7*8)(%r28)
+	lfd	%f3,-24-(8*4)-(6*8)(%r28)
+	lfd	%f4,-24-(8*4)-(5*8)(%r28)
 	nop
-	lfd	%f5,-16-(8*4)-(4*8)(%r28)
-	lfd	%f6,-16-(8*4)-(3*8)(%r28)
-	lfd	%f7,-16-(8*4)-(2*8)(%r28)
-	lfd	%f8,-16-(8*4)-(1*8)(%r28)
+	lfd	%f5,-24-(8*4)-(4*8)(%r28)
+	lfd	%f6,-24-(8*4)-(3*8)(%r28)
+	lfd	%f7,-24-(8*4)-(2*8)(%r28)
+	lfd	%f8,-24-(8*4)-(1*8)(%r28)
+#endif
 2:
 
 	/* Make the call.  */
+	lwz	%r11, -20(%r28)
 	bctrl
 
 	/* Now, deal with the return value.  */
-	mtcrf	0x01,%r31 /* cr7  */
+	mtcrf	0x03,%r31 /* cr6-cr7  */
 	bt-	31,L(small_struct_return_value)
 	bt-	30,L(done_return_value)
+#ifndef __NO_FPRS__
 	bt-	29,L(fp_return_value)
+#endif
 	stw	%r3,0(%r30)
-	bf+	28,L(done_return_value)
+	bf+	27,L(done_return_value)
 	stw	%r4,4(%r30)
-	mtcrf	0x02,%r31 /* cr6  */
-	bf	27,L(done_return_value)
+	bf	26,L(done_return_value)
 	stw     %r5,8(%r30)
 	stw	%r6,12(%r30)
 	/* Fall through...  */
@@ -121,99 +126,48 @@ L(done_return_value):
 	lwz	%r30, -8(%r28)
 	lwz	%r29,-12(%r28)
 	lwz	%r28,-16(%r28)
+	.cfi_remember_state
+	/* At this point we don't have a cfa register.  Say all our
+	   saved regs have been restored.  */
+	.cfi_same_value 65
+	.cfi_same_value 31
+	.cfi_same_value 30
+	.cfi_same_value 29
+	.cfi_same_value 28
+	/* Hopefully this works..  */
+	.cfi_def_cfa_register 1
+	.cfi_offset 1, 0
 	lwz	%r1,0(%r1)
+	.cfi_same_value 1
 	blr
 
+#ifndef __NO_FPRS__
 L(fp_return_value):
-	bf	28,L(float_return_value)
+	.cfi_restore_state
+	bf	27,L(float_return_value)
 	stfd	%f1,0(%r30)
-	mtcrf   0x02,%r31 /* cr6  */
-	bf	27,L(done_return_value)
+	bf	26,L(done_return_value)
 	stfd	%f2,8(%r30)
 	b	L(done_return_value)
 L(float_return_value):
 	stfs	%f1,0(%r30)
 	b	L(done_return_value)
+#endif
 
 L(small_struct_return_value):
-	extrwi	%r6,%r31,2,19         /* number of bytes padding = shift/8 */
-	mtcrf	0x02,%r31	      /* copy flags to cr[24:27] (cr6) */
-	extrwi	%r5,%r31,5,19         /* r5 <- number of bits of padding */
-	subfic  %r6,%r6,4             /* r6 <- number of useful bytes in r3 */
-	bf-	25,L(done_return_value) /* struct in r3 ? if not, done. */
-/* smst_one_register: */
-	slw	%r3,%r3,%r5           /* Left-justify value in r3 */
-	mtxer	%r6                   /* move byte count to XER ... */
-	stswx	%r3,0,%r30            /* ... and store that many bytes */
-	bf+	26,L(done_return_value)  /* struct in r3:r4 ? */
-	add	%r6,%r6,%r30          /* adjust pointer */
-	stswi	%r4,%r6,4             /* store last four bytes */
-	b	L(done_return_value)
+	/*
+	 * The C code always allocates a properly-aligned 8-byte bounce
+	 * buffer to make this assembly code very simple.  Just write out
+	 * r3 and r4 to the buffer to allow the C code to handle the rest.
+	 */
+	stw %r3, 0(%r30)
+	stw %r4, 4(%r30)
+	b L(done_return_value)
+	.cfi_endproc
 
-.LFE1:
 END(ffi_call_SYSV)
 
-      .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 */
-#if defined _RELOCATABLE || defined __PIC__
-      .ascii	"zR\0"   /*  CIE Augmentation */
-#else
-      .ascii	"\0"	 /*  CIE Augmentation */
-#endif
-      .uleb128  0x1      /*  CIE Code Alignment Factor */
-      .sleb128  -4	 /*  CIE Data Alignment Factor */
-      .byte     0x41     /*  CIE RA Column */
-#if defined _RELOCATABLE || defined __PIC__
-      .uleb128  0x1      /*  Augmentation size */
-      .byte	0x1b	 /*  FDE Encoding (pcrel sdata4) */
-#endif
-      .byte     0xc      /*  DW_CFA_def_cfa */
-      .uleb128  0x1
-      .uleb128  0x0
-      .align 2
-.LECIE1:
-.LSFDE1:
-      .4byte    .LEFDE1-.LASFDE1         /*  FDE Length */
-.LASFDE1:
-      .4byte    .LASFDE1-.Lframe1         /*  FDE CIE offset */
-#if defined _RELOCATABLE || defined __PIC__
-      .4byte    .LFB1-.  /*  FDE initial location */
-#else
-      .4byte    .LFB1    /*  FDE initial location */
-#endif
-      .4byte    .LFE1-.LFB1      /*  FDE address range */
-#if defined _RELOCATABLE || defined __PIC__
-      .uleb128  0x0	 /*  Augmentation size */
-#endif
-      .byte     0x4      /*  DW_CFA_advance_loc4 */
-      .4byte    .LCFI0-.LFB1
-      .byte     0xd      /*  DW_CFA_def_cfa_register */
-      .uleb128  0x08
-      .byte     0x4      /*  DW_CFA_advance_loc4 */
-      .4byte    .LCFI5-.LCFI0
-      .byte     0x11     /*  DW_CFA_offset_extended_sf */
-      .uleb128  0x41
-      .sleb128  -1
-      .byte     0x9f     /*  DW_CFA_offset, column 0x1f */
-      .uleb128  0x1
-      .byte     0x9e     /*  DW_CFA_offset, column 0x1e */
-      .uleb128  0x2
-      .byte     0x9d     /*  DW_CFA_offset, column 0x1d */
-      .uleb128  0x3
-      .byte     0x9c     /*  DW_CFA_offset, column 0x1c */
-      .uleb128  0x4
-      .byte     0x4      /*  DW_CFA_advance_loc4 */
-      .4byte    .LCFI6-.LCFI5
-      .byte     0xd      /*  DW_CFA_def_cfa_register */
-      .uleb128  0x1c
-      .align 2
-.LEFDE1:
-#endif
-
 #if defined __ELF__ && defined __linux__
 	.section	.note.GNU-stack,"",@progbits
 #endif
+#endif