mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-17 09:57:46 +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>
123 lines
2.3 KiB
ArmAsm
123 lines
2.3 KiB
ArmAsm
/*
|
|
* Copyright (C) 2014-15 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>
|
|
|
|
#undef PREALLOC_NOT_AVAIL
|
|
|
|
ENTRY_CFI(memset)
|
|
prefetchw [r0] ; Prefetch the write location
|
|
mov.f 0, r2
|
|
;;; if size is zero
|
|
jz.d [blink]
|
|
mov r3, r0 ; don't clobber ret val
|
|
|
|
;;; if length < 8
|
|
brls.d.nt r2, 8, .Lsmallchunk
|
|
mov.f lp_count,r2
|
|
|
|
and.f r4, r0, 0x03
|
|
rsub lp_count, r4, 4
|
|
lpnz @.Laligndestination
|
|
;; LOOP BEGIN
|
|
stb.ab r1, [r3,1]
|
|
sub r2, r2, 1
|
|
.Laligndestination:
|
|
|
|
;;; Destination is aligned
|
|
and r1, r1, 0xFF
|
|
asl r4, r1, 8
|
|
or r4, r4, r1
|
|
asl r5, r4, 16
|
|
or r5, r5, r4
|
|
mov r4, r5
|
|
|
|
sub3 lp_count, r2, 8
|
|
cmp r2, 64
|
|
bmsk.hi r2, r2, 5
|
|
mov.ls lp_count, 0
|
|
add3.hi r2, r2, 8
|
|
|
|
;;; Convert len to Dwords, unfold x8
|
|
lsr.f lp_count, lp_count, 6
|
|
|
|
lpnz @.Lset64bytes
|
|
;; LOOP START
|
|
#ifdef PREALLOC_NOT_AVAIL
|
|
prefetchw [r3, 64] ;Prefetch the next write location
|
|
#else
|
|
prealloc [r3, 64]
|
|
#endif
|
|
#ifdef CONFIG_ARC_HAS_LL64
|
|
std.ab r4, [r3, 8]
|
|
std.ab r4, [r3, 8]
|
|
std.ab r4, [r3, 8]
|
|
std.ab r4, [r3, 8]
|
|
std.ab r4, [r3, 8]
|
|
std.ab r4, [r3, 8]
|
|
std.ab r4, [r3, 8]
|
|
std.ab r4, [r3, 8]
|
|
#else
|
|
st.ab r4, [r3, 4]
|
|
st.ab r4, [r3, 4]
|
|
st.ab r4, [r3, 4]
|
|
st.ab r4, [r3, 4]
|
|
st.ab r4, [r3, 4]
|
|
st.ab r4, [r3, 4]
|
|
st.ab r4, [r3, 4]
|
|
st.ab r4, [r3, 4]
|
|
st.ab r4, [r3, 4]
|
|
st.ab r4, [r3, 4]
|
|
st.ab r4, [r3, 4]
|
|
st.ab r4, [r3, 4]
|
|
st.ab r4, [r3, 4]
|
|
st.ab r4, [r3, 4]
|
|
st.ab r4, [r3, 4]
|
|
st.ab r4, [r3, 4]
|
|
#endif
|
|
.Lset64bytes:
|
|
|
|
lsr.f lp_count, r2, 5 ;Last remaining max 124 bytes
|
|
lpnz .Lset32bytes
|
|
;; LOOP START
|
|
prefetchw [r3, 32] ;Prefetch the next write location
|
|
#ifdef CONFIG_ARC_HAS_LL64
|
|
std.ab r4, [r3, 8]
|
|
std.ab r4, [r3, 8]
|
|
std.ab r4, [r3, 8]
|
|
std.ab r4, [r3, 8]
|
|
#else
|
|
st.ab r4, [r3, 4]
|
|
st.ab r4, [r3, 4]
|
|
st.ab r4, [r3, 4]
|
|
st.ab r4, [r3, 4]
|
|
st.ab r4, [r3, 4]
|
|
st.ab r4, [r3, 4]
|
|
st.ab r4, [r3, 4]
|
|
st.ab r4, [r3, 4]
|
|
#endif
|
|
.Lset32bytes:
|
|
|
|
and.f lp_count, r2, 0x1F ;Last remaining 31 bytes
|
|
.Lsmallchunk:
|
|
lpnz .Lcopy3bytes
|
|
;; LOOP START
|
|
stb.ab r1, [r3, 1]
|
|
.Lcopy3bytes:
|
|
|
|
j [blink]
|
|
|
|
END_CFI(memset)
|
|
|
|
ENTRY_CFI(memzero)
|
|
; adjust bzero args to memset args
|
|
mov r2, r1
|
|
b.d memset ;tail call so need to tinker with blink
|
|
mov r1, 0
|
|
END_CFI(memzero)
|