Re: x86_64 Compiler Output Kernel Bloat v4.4

[Jeff Merkey]

On 1/18/16, Jeff Merkey <linux.mdb@xxxxxxxxx> wrote:
> Hi,
>
> I noticed that in the assembler output for the x86_64 builds almost
> every single function originating from C code has a nop instruction
> that prefaces the function call.   I guess the concern with this is
> the wasted space issue as each one of these placeholders takes up a
> bunch of bytes at the head of each function.   Is there a reason this
> assembler header is there in the first place to anyones knowledge?
> Since every single function just about is prefaced by this inert 5
> byte instruction it adds up to quite a bit of bloat in the size of the
> linux executable.
>
> 0xffffffffa073e010 0F1F440000      nop    DWORD PTR [rax+rax]=0x0
>
> The intel assembler format shows the bytes that comprise each
> instruction.  The GDB format does not.  Both are provided.
>
> 0xffffffffa073e050 4155            push   r13
> (0)> id mdb_watchdogs
> mdb|mdb_watchdogs:
> 0xffffffffa073e010 mdb_watchdogs:         nopl   0x0(%rax,%rax,1)) <<
> 0xffffffffa073e015 mdb_watchdogs+0x5:     push   %rbp
> 0xffffffffa073e016 mdb_watchdogs+0x6:     mov    %rsp,%rbp
> 0xffffffffa073e019 mdb_watchdogs+0x9:     callq  0xffffffff811337e0
> touch_softlockup_watchdog_sync
> 0xffffffffa073e01e mdb_watchdogs+0xe:     callq  0xffffffff810f0ba0
> clocksource_touch_watchdog
> 0xffffffffa073e023 mdb_watchdogs+0x13:    callq  0xffffffff810dea20
> rcu_cpu_stall_reset
> 0xffffffffa073e028 mdb_watchdogs+0x18:    callq  0xffffffff811337c0
> touch_nmi_watchdog
> 0xffffffffa073e02d mdb_watchdogs+0x1d:    pop    %rbp
> 0xffffffffa073e02e mdb_watchdogs+0x1e:    data16
> 0xffffffffa073e030 mdb_watchdogs+0x20:    retq
> 0xffffffffa073e031 mdb_watchdogs+0x21:    nopw   %cs:0x0(%rax,%rax,1))
> mdb|mdb:
> 0xffffffffa073e040 mdb:         nopl   0x0(%rax,%rax,1))  <<
> 0xffffffffa073e045 mdb+0x5:     push   %rbp
> 0xffffffffa073e046 mdb+0x6:     mov    %rsp,%rbp
> 0xffffffffa073e049 mdb+0x9:     push   %r15
> 0xffffffffa073e04b mdb+0xb:     push   %r14
> 0xffffffffa073e04d mdb+0xd:     mov    %rdi,%r14
> 0xffffffffa073e050 mdb+0x10:    push   %r13
> (0)> u mdb_watchdogs
> mdb|mdb_watchdogs:
> 0xffffffffa073e010 0F1F440000      nop    DWORD PTR [rax+rax]=0x0 <<
> 0xffffffffa073e015 55              push   rbp
> 0xffffffffa073e016 4889E5          mov    rbp,rsp
> 0xffffffffa073e019 E8C2579FE0      call   touch_softlockup_watchdog_sync
> 0xffffffffa073e01e E87D2B9BE0      call   clocksource_touch_watchdog
> 0xffffffffa073e023 E8F8099AE0      call   rcu_cpu_stall_reset
> 0xffffffffa073e028 E893579FE0      call   touch_nmi_watchdog
> 0xffffffffa073e02d 5D              pop    rbp
> 0xffffffffa073e02e 6690            data16
> 0xffffffffa073e030 C3              ret
> 0xffffffffa073e031 6666666666662E0F1F840000000000  nop    cs:WORD PTR
> [rax+rax]=0x0000
> mdb|mdb:
> 0xffffffffa073e040 0F1F440000      nop    DWORD PTR [rax+rax]=0x0  <<
> 0xffffffffa073e045 55              push   rbp
> 0xffffffffa073e046 4889E5          mov    rbp,rsp
> 0xffffffffa073e049 4157            push   r15
> 0xffffffffa073e04b 4156            push   r14
> 0xffffffffa073e04d 4989FE          mov    r14,rdi
> 0xffffffffa073e050 4155            push   r13
> (0)> g
>
> Jeff
>

here are some examples from in-tree code:

(2)> u async_schedule
async_schedule:
0xffffffff810a0210 0F1F440000      nop    DWORD PTR [rax+rax]=0x0
0xffffffff810a0215 55              push   rbp
0xffffffff810a0216 48C7C2E0D79F81  mov    rdx,0xffffffff819fd7e0
0xffffffff810a021d 4889E5          mov    rbp,rsp
0xffffffff810a0220 E86BFEFFFF      call   __async_schedule
0xffffffff810a0225 5D              pop    rbp
0xffffffff810a0226 C3              ret
0xffffffff810a0227 660F1F840000000000  nop    WORD PTR [rax+rax]=0x0000
async_schedule_domain:
0xffffffff810a0230 0F1F440000      nop    DWORD PTR [rax+rax]=0x0
0xffffffff810a0235 55              push   rbp
0xffffffff810a0236 4889E5          mov    rbp,rsp
0xffffffff810a0239 E852FEFFFF      call   __async_schedule
0xffffffff810a023e 5D              pop    rbp
0xffffffff810a023f C3              ret
current_is_async:
0xffffffff810a0240 0F1F440000      nop    DWORD PTR [rax+rax]=0x0
0xffffffff810a0245 65488B3C2540BD0000  mov    rdi,gs:0xbd40
0xffffffff810a024e F6471420        test   BYTE PTR [rdi+20]=0x00,0x20
(2)> u schedule
schedule:
0xffffffff8167c280 0F1F440000      nop    DWORD PTR [rax+rax]=0x0
0xffffffff8167c285 55              push   rbp
0xffffffff8167c286 65488B042540BD0000  mov    rax,gs:0xbd40
0xffffffff8167c28f 4889E5          mov    rbp,rsp
0xffffffff8167c292 53              push   rbx
0xffffffff8167c293 488B10          mov    rdx,QWORD PTR [rax]=0x0
0xffffffff8167c296 4885D2          test   rdx,rdx
0xffffffff8167c299 740A            je     schedule+0x25
(0xffffffff8167c2a5) (down)
0xffffffff8167c29b 4883B8080A000000  cmp    QWORD PTR [rax+0xa08]=0x0,0x0
0xffffffff8167c2a3 741E            je     schedule+0x43
(0xffffffff8167c2c3) (down)
0xffffffff8167c2a5 65488B1C2584410100  mov    rbx,gs:0x14184
0xffffffff8167c2ae 31FF            xor    edi,edi
0xffffffff8167c2b0 E8CBF8FFFF      call   __schedule
0xffffffff8167c2b5 488B8308C0FFFF  mov    rax,QWORD PTR
[rbx-0x3ff8]=0x4B53414D5F534B41
0xffffffff8167c2bc A808            test   al,0x8
0xffffffff8167c2be 75EE            jne    schedule+0x2e
(0xffffffff8167c2ae) (up)
0xffffffff8167c2c0 5B              pop    rbx
0xffffffff8167c2c1 5D              pop    rbp
0xffffffff8167c2c2 C3              ret
(2)> g

Jeff