The RDHWR instruction is used to support TLS on Linux/MIPS. For now
it is always emulated by kernel (on Reserved Instruction exception
handler), the instruction will be quite expensive.
If I compile this code with gcc 4.1.1 (-O2),
extern __thread int x;
int foo(int arg)
{
if (arg)
return x;
return 0;
}
I got this output.
foo:
.frame $sp,0,$31 # vars= 0, regs= 0/0, args= 0, gp= 0
.mask 0x00000000,0
.fmask 0x00000000,0
.set noreorder
.cpload $25
.set nomacro
lw $2,%gottprel(x)($28)
.set push
.set mips32r2
rdhwr $3,$29
.set pop
addu $2,$2,$3
beq $4,$0,$L4
move $3,$0
lw $3,0($2)
$L4:
j $31
move $2,$3
The RDHWR is executed _before_ evaluating the "arg" value. For arg ==
0 case, the RDHWR has no point but just a overhead. Without -O2, the
RDHWR is executed _after_ the evaluation, so gcc's optimizer reorder
the RDHWR instruction.
I want to make the RDHWR called only if really required. Is it
possible to prevent such a reording for RDHWR ?
This is very common case in libc. On returning from system call, libc
checks the result and write to the "errno" which is thread-local. On
successful syscall, we do not need to access "errno" at all, but gcc
sometimes put RDHWR _before_ checking the result of the syscall. This
add an additional exception for the syscall for usual case.
I do not know much about gcc's internal. Any help are welcome. Thank
you.
---
Atsushi Nemoto
