[rt.cpan.org #77677] x64 asm is broken for ::API, >4 param crash

Wed Jun 06 19:35:56 2012: Request 77677 was acted upon.
Transaction: Ticket created by bulk88.
       Queue: Win32-API
     Subject: x64 asm is broken for ::API, >4 param crash
   Broken in: 0.68
    Severity: Normal
       Owner: Nobody
  Requestors: [email protected]
      Status: new
 Ticket <URL: https://rt.cpan.org/Ticket/Display.html?id=77677 >


If there are over 4 parameters on x64 with GCC, there is a crash.
Remember every function on x64 has 4 parameters without exception. RSI
and R10 is filled with garbage with the 2 POPs at the end. The stack
pusher loop is broken. RSI in Call_asm is the retval struct pointer on
-O2 (strawberry perl's default). On -O0 it doesn't crash, IDK and don't
care why.
________________________

.globl Call_x64_real
Call_x64_real:

	pushq	%rbp
	movq	%rsp,%rbp
	subq	$32,%rsp	# keep space for 4 64bit params

ADD 32 to RSP A FIXED AMOUNT

	# Store register parameters 
	movq    %rcx,16(%rbp)	# ApiFunction
	movq    %rdx,24(%rbp)	# int_registers
	movq    %r8,32(%rbp)	# float_registers
	movq    %r9,40(%rbp)	# stack

	# Save regs we are gonna use
	pushq	%rsi
ADD 8 to RSP A FIXED AMOUNT
	pushq	%r10
ADD 8 to RSP A FIXED AMOUNT

	# Load up integer registers first... 
	movq    24(%rbp),%rax	# rax = int_registers
	movq    (%rax),%rcx
	movq    8(%rax),%rdx
	movq    16(%rax),%r8
	movq    24(%rax),%r9

	# Now floating-point registers 
	movq	32(%rbp),%rax	# rax = float_registers
	movsd	(%rax),%xmm0
	movsd	8(%rax),%xmm1
	movsd	16(%rax),%xmm2
	movsd	24(%rax),%xmm3

	# Now the stack 
	movq	40(%rbp),%rsi	# rsi = stack
	movq	48(%rbp),%rax	# rax = nstack
NSTACK IS NUMBER OF STACK PARAMS
FROM Call_asm
	required_stack = nparams > 4 ? nparams - 4 : 0;
NSTACK IS required_stack IN THE CALLER Call_asm
END COMMENT

	# Except not if there isn't any 
	testq	%rax,%rax
	je	docall

copystack:
	subq	$1,%rax
	movq	(%rsi,%rax,8),%r10
	pushq	%r10
ADD MANY 8s TO RSP THIS IS A LOOP VARIABLE AMOUNT
	testq	%rax,%rax
	jne	copystack

docall:
	# And call
	movq	16(%rbp),%r10   # r10 = ApiFunction
	subq	$32,%rsp	# Microsoft x64 calling convention - allocate 32 bytes of
"shadow space" on the stack

ADD 32 TO RSP, A FIXED AMOUNT

	callq	*%r10
	addq	$32,%rsp	# restore stack

REMOVE 32 FROM RSP, A FIXED AMOUNT

	# Store return value
	movq	56(%rbp),%r10	# r10 = iret
	movq	%rax,(%r10)
	movq	64(%rbp),%r10	# r10 = dret
	movsd	%xmm0,(%r10)
 
	# Restore regs
	popq	%r10
REMOVE 8 FROM RSP, A FIXED AMOUNT
	popq	%rsi
REMOVE 8 FROM RSP, A FIXED AMOUNT
	movq	%rbp,%rsp
	popq	%rbp
	retq
____________________________________________
This bug is in the public 0.68, and my personal API versions
(0.69/0.70). Its only on x64 and on GCC Perl. I'll investigate whether
the same bug is in MSVC x64 side.