On Thu, 19 Nov 2009, Andrew Haley wrote:
> Thomas Gleixner wrote:
> > On Thu, 19 Nov 2009, Andrew Haley wrote:
> >> Thomas Gleixner wrote:
> >>> There is no real obvious reason why the edi magic needs to be done
> >>> _before_
> >>>
> >>> push %ebp
> >>> mov %esp,%ebp
> >> Sure there is: unless you do the adjustment first %ebp won't be 16-aligned.
> >
> > And why is this not done in 99% of the functions in the kernel, just
> > in this one and some random others ?
>
> If I could see the function I might be able to tell you. It's either a
> performance enhancement, something to do with SSE, or it's a bug.
kernel/time/timer_stats.c timer_stats_update_stats()
Here is the disassembly:
8107ad50 <timer_stats_update_stats>:
8107ad50: 57 push %edi
8107ad51: 8d 7c 24 08 lea 0x8(%esp),%edi
8107ad55: 83 e4 f0 and $0xfffffff0,%esp
8107ad58: ff 77 fc pushl -0x4(%edi)
8107ad5b: 55 push %ebp
8107ad5c: 89 e5 mov %esp,%ebp
8107ad5e: 57 push %edi
8107ad5f: 56 push %esi
8107ad60: 53 push %ebx
8107ad61: 83 ec 6c sub $0x6c,%esp
8107ad64: e8 47 92 f8 ff call 81003fb0 <mcount>
8107ad69: 8b 77 04 mov 0x4(%edi),%esi
8107ad6c: 89 75 a4 mov %esi,-0x5c(%ebp)
8107ad6f: 65 8b 35 14 00 00 00 mov %gs:0x14,%esi
8107ad76: 89 75 e4 mov %esi,-0x1c(%ebp)
8107ad79: 31 f6 xor %esi,%esi
8107ad7b: 8b 35 60 5a cd 81 mov 0x81cd5a60,%esi
8107ad81: 8b 1f mov (%edi),%ebx
8107ad83: 85 f6 test %esi,%esi
8107ad85: 8b 7f 08 mov 0x8(%edi),%edi
8107ad88: 75 18 jne 8107ada2
<timer_stats_update_stats+0x52>
8107ad8a: 8b 45 e4 mov -0x1c(%ebp),%eax
8107ad8d: 65 33 05 14 00 00 00 xor %gs:0x14,%eax
8107ad94: 75 53 jne 8107ade9
<timer_stats_update_stats+0x99>
8107ad96: 83 c4 6c add $0x6c,%esp
8107ad99: 5b pop %ebx
8107ad9a: 5e pop %esi
8107ad9b: 5f pop %edi
8107ad9c: 5d pop %ebp
8107ad9d: 8d 67 f8 lea -0x8(%edi),%esp
8107ada0: 5f pop %edi
8107ada1: c3 ret
8107ada2: be 00 7a d6 81 mov $0x81d67a00,%esi
8107ada7: 89 45 ac mov %eax,-0x54(%ebp)
8107adaa: 89 75 a0 mov %esi,-0x60(%ebp)
8107adad: 89 5d b4 mov %ebx,-0x4c(%ebp)
8107adb0: 64 8b 35 78 6a d6 81 mov %fs:0x81d66a78,%esi
8107adb7: 8b 34 b5 20 50 cd 81 mov -0x7e32afe0(,%esi,4),%esi
8107adbe: 89 4d b0 mov %ecx,-0x50(%ebp)
8107adc1: 01 75 a0 add %esi,-0x60(%ebp)
8107adc4: 89 55 b8 mov %edx,-0x48(%ebp)
8107adc7: 8b 45 a0 mov -0x60(%ebp),%eax
8107adca: 89 7d c0 mov %edi,-0x40(%ebp)
8107adcd: e8 de f7 76 00 call 817ea5b0 <_spin_lock_irqsave>
8107add2: 83 3d 60 5a cd 81 00 cmpl $0x0,0x81cd5a60
8107add9: 89 c3 mov %eax,%ebx
8107addb: 75 11 jne 8107adee
<timer_stats_update_stats+0x9e>
8107addd: 89 da mov %ebx,%edx
8107addf: 8b 45 a0 mov -0x60(%ebp),%eax
8107ade2: e8 79 fc 76 00 call 817eaa60
<_spin_unlock_irqrestore>
8107ade7: eb a1 jmp 8107ad8a
<timer_stats_update_stats+0x3a>
8107ade9: e8 52 e4 fc ff call 81049240 <__stack_chk_fail>
8107adee: 8d 45 a8 lea -0x58(%ebp),%eax
8107adf1: 8b 55 a4 mov -0x5c(%ebp),%edx
8107adf4: e8 f7 fd ff ff call 8107abf0 <tstat_lookup>
8107adf9: 85 c0 test %eax,%eax
8107adfb: 74 05 je 8107ae02
<timer_stats_update_stats+0xb2>
8107adfd: ff 40 14 incl 0x14(%eax)
8107ae00: eb db jmp 8107addd
<timer_stats_update_stats+0x8d>
8107ae02: f0 ff 05 00 67 fd 81 lock incl 0x81fd6700
8107ae09: eb d2 jmp 8107addd
<timer_stats_update_stats+0x8d>
8107ae0b: 90 nop
8107ae0c: 90 nop
8107ae0d: 90 nop
8107ae0e: 90 nop
8107ae0f: 90 nop
There is a dozen more of those.
Thanks,
tglx
