Hello everyone, I am getting an exception when I enable the -O2 optimization. More precisaily, the line that stars with write_portd.... is corrupting the data section. This is the pascal code:
function PciReadDword(const bus, device, func, regnum: UInt32): UInt32; var Send: DWORD; begin Send := $80000000 or (bus shl 16) or (device shl 11) or (func shl 8) or (regnum shl 2); write_portd(@Send, PCI_CONF_PORT_INDEX); read_portd(@Send, PCI_CONF_PORT_DATA); Result := Send; end; *which generates (without -02):* .section .text.n_arch_$$_pcireaddword$longword$longword$longword$longword$$longword,"x" .balign 16,0x90 .globl ARCH_$$_PCIREADDWORD$LONGWORD$LONGWORD$LONGWORD$LONGWORD$$LONGWORD ARCH_$$_PCIREADDWORD$LONGWORD$LONGWORD$LONGWORD$LONGWORD$$LONGWORD: .Lc207: .seh_proc ARCH_$$_PCIREADDWORD$LONGWORD$LONGWORD$LONGWORD$LONGWORD$$LONGWORD .Ll464: # [992] begin pushq %rbp .seh_pushreg %rbp .Lc209: .Lc210: movq %rsp,%rbp .Lc211: leaq -80(%rsp),%rsp .seh_stackalloc 80 .seh_endprologue # Var bus located at rbp-8, size=OS_32 # Var device located at rbp-16, size=OS_32 # Var func located at rbp-24, size=OS_32 # Var regnum located at rbp-32, size=OS_32 # Var $result located at rbp-40, size=OS_32 # Var Send located at rbp-48, size=OS_32 movl %ecx,-8(%rbp) movl %edx,-16(%rbp) movl %r8d,-24(%rbp) movl %r9d,-32(%rbp) .Ll465: # [993] Send := $80000000 or (bus shl 16) or (device shl 11) or (func shl 8) or (regnum shl 2); movl -8(%rbp),%eax shll $16,%eax orl $2147483648,%eax movl -16(%rbp),%edx shll $11,%edx orl %eax,%edx movl -24(%rbp),%eax shll $8,%eax orl %edx,%eax movl -32(%rbp),%edx shll $2,%edx orl %eax,%edx movl %edx,-48(%rbp) .Ll466: # [995] write_portd(@Send, PCI_CONF_PORT_INDEX); leaq -48(%rbp),%rcx movl $3320,%edx call ARCH_$$_WRITE_PORTD$POINTER$WORD .Ll467: # [996] read_portd(@Send, PCI_CONF_PORT_DATA); leaq -48(%rbp),%rcx movl $3324,%edx call ARCH_$$_READ_PORTD$POINTER$WORD .Ll468: # [997] Result := Send; movl -48(%rbp),%eax movl %eax,-40(%rbp) .Ll469: # [998] end; movl -40(%rbp),%eax nop leaq (%rbp),%rsp popq %rbp ret .seh_endproc .Lc208: .Lt28: .Ll470: *and with -O2:* .section .text.n_arch_$$_pciwriteword$word$word$word$word$word,"x" .balign 16,0x90 .globl ARCH_$$_PCIWRITEWORD$WORD$WORD$WORD$WORD$WORD ARCH_$$_PCIWRITEWORD$WORD$WORD$WORD$WORD$WORD: .Lc148: # Temps allocated between rbp-16 and rbp-8 .seh_proc ARCH_$$_PCIWRITEWORD$WORD$WORD$WORD$WORD$WORD .Ll471: # [1014] begin pushq %rbp .seh_pushreg %rbp .Lc150: .Lc151: movq %rsp,%rbp .Lc152: leaq -48(%rsp),%rsp .seh_stackalloc 48 # Var bus located in register ax # Var device located in register dx # Var func located in register r8w # Var regnum located in register r9w # Var value located in register cx movq %rbx,-16(%rbp) .seh_savereg %rbx, 32 .seh_endprologue # Var Send located at rbp-8, size=OS_32 movw %cx,%ax movw 48(%rbp),%bx # PeepHole Optimization,var11 .Ll472: # [1015] Send := $80000000 or (bus shl 16) or (device shl 11) or (func shl 8) or (regnum and $fc); andl $65535,%eax shll $16,%eax orl $2147483648,%eax # PeepHole Optimization,var11 andl $65535,%edx shll $11,%edx orl %eax,%edx # PeepHole Optimization,var11 andl $65535,%r8d shll $8,%r8d orl %edx,%r8d # PeepHole Optimization,var1 # PeepHole Optimization,var11 andl $252,%r9d orl %r8d,%r9d movl %r9d,-8(%rbp) .Ll473: # [1016] write_portd(@Send, PCI_CONF_PORT_INDEX); leaq -8(%rbp),%rcx movl $3320,%edx call ARCH_$$_WRITE_PORTD$POINTER$WORD .Ll474: # [1017] write_portw(value, PCI_CONF_PORT_DATA); movw %bx,%cx # Var value located in register cx # PeepHole Optimization,var11 andl $65535,%ecx movl $3324,%edx call ARCH_$$_WRITE_PORTW$WORD$WORD .Ll475: # [1018] end; movq -16(%rbp),%rbx leaq (%rbp),%rsp popq %rbp ret .seh_endproc The first thing that I realize was the the optimized version is not generating the correct source when is exiting since it should return "Send", but am I right? The assembler code of write_portd remains the same, Am I missing something? Regards, Matias.
_______________________________________________ fpc-pascal maillist - fpc-pascal@lists.freepascal.org http://lists.freepascal.org/cgi-bin/mailman/listinfo/fpc-pascal
