mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-28 11:18:45 +07:00
86effd0dc6
This uses a new set of annoations viz. ENTRY_CFI/END_CFI to enabel cfi
ops generation.
Note that we didn't change the normal ENTRY/EXIT as we don't actually
want unwind info in the trap/exception/interrutp handlers which use
these, as unwinder then gets confused (it keeps recursing vs. stopping).
Semantically these are leaf routines and unwinding should stop when it
hits those routines.
Before
------
28.52% 1.19% 9929 hackbench libuClibc-1.0.17.so [.] __write_nocancel
|
---__write_nocancel
|--8.95%--EV_Trap
| --8.25%--sys_write
| |--3.93%--sock_write_iter
...
|--2.62%--memset <==== [LEAF entry as no unwind info]
^^^^^^
After
-----
29.46% 1.24% 13622 hackbench libuClibc-1.0.17.so [.] __write_nocancel
|
---__write_nocancel
|--9.31%--EV_Trap
| --8.62%--sys_write
| |--4.17%--sock_write_iter
...
|--6.19%--sys_write
| --6.19%--sock_write_iter
| unix_stream_sendmsg
| |--1.62%--sock_alloc_send_pskb
| |--0.89%--sock_def_readable
| |--0.88%--_raw_spin_unlock_irqrestore
| |--0.69%--memset
| | ^^^^^^ <==== [now in proper callframe]
| |
| --0.52%--skb_copy_datagram_from_iter
Signed-off-by: Vineet Gupta <vgupta@synopsys.com>
60 lines
1.2 KiB
ArmAsm
60 lines
1.2 KiB
ArmAsm
/*
|
|
* Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify
|
|
* it under the terms of the GNU General Public License version 2 as
|
|
* published by the Free Software Foundation.
|
|
*/
|
|
|
|
#include <linux/linkage.h>
|
|
|
|
#define SMALL 7 /* Must be at least 6 to deal with alignment/loop issues. */
|
|
|
|
ENTRY_CFI(memset)
|
|
mov_s r4,r0
|
|
or r12,r0,r2
|
|
bmsk.f r12,r12,1
|
|
extb_s r1,r1
|
|
asl r3,r1,8
|
|
beq.d .Laligned
|
|
or_s r1,r1,r3
|
|
brls r2,SMALL,.Ltiny
|
|
add r3,r2,r0
|
|
stb r1,[r3,-1]
|
|
bclr_s r3,r3,0
|
|
stw r1,[r3,-2]
|
|
bmsk.f r12,r0,1
|
|
add_s r2,r2,r12
|
|
sub.ne r2,r2,4
|
|
stb.ab r1,[r4,1]
|
|
and r4,r4,-2
|
|
stw.ab r1,[r4,2]
|
|
and r4,r4,-4
|
|
.Laligned: ; This code address should be aligned for speed.
|
|
asl r3,r1,16
|
|
lsr.f lp_count,r2,2
|
|
or_s r1,r1,r3
|
|
lpne .Loop_end
|
|
st.ab r1,[r4,4]
|
|
.Loop_end:
|
|
j_s [blink]
|
|
|
|
.balign 4
|
|
.Ltiny:
|
|
mov.f lp_count,r2
|
|
lpne .Ltiny_end
|
|
stb.ab r1,[r4,1]
|
|
.Ltiny_end:
|
|
j_s [blink]
|
|
END_CFI(memset)
|
|
|
|
; memzero: @r0 = mem, @r1 = size_t
|
|
; memset: @r0 = mem, @r1 = char, @r2 = size_t
|
|
|
|
ENTRY_CFI(memzero)
|
|
; adjust bzero args to memset args
|
|
mov r2, r1
|
|
mov r1, 0
|
|
b memset ;tail call so need to tinker with blink
|
|
END_CFI(memzero)
|