1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
|
/*
* Cache flushing routines.
*
* Copyright (C) 1999-2001, 2005 Hewlett-Packard Co
* David Mosberger-Tang <davidm@hpl.hp.com>
*
* 05/28/05 Zoltan Menyhart Dynamic stride size
*/
#include <asm/asmmacro.h>
/*
* flush_icache_range(start,end)
*
* Make i-cache(s) coherent with d-caches.
*
* Must deal with range from start to end-1 but nothing else (need to
* be careful not to touch addresses that may be unmapped).
*
* Note: "in0" and "in1" are preserved for debugging purposes.
*/
.section .kprobes.text,"ax"
GLOBAL_ENTRY(flush_icache_range)
.prologue
alloc r2=ar.pfs,2,0,0,0
movl r3=ia64_i_cache_stride_shift
mov r21=1
;;
ld8 r20=[r3] // r20: stride shift
sub r22=in1,r0,1 // last byte address
;;
shr.u r23=in0,r20 // start / (stride size)
shr.u r22=r22,r20 // (last byte address) / (stride size)
shl r21=r21,r20 // r21: stride size of the i-cache(s)
;;
sub r8=r22,r23 // number of strides - 1
shl r24=r23,r20 // r24: addresses for "fc.i" =
// "start" rounded down to stride boundary
.save ar.lc,r3
mov r3=ar.lc // save ar.lc
;;
.body
mov ar.lc=r8
;;
/*
* 32 byte aligned loop, even number of (actually 2) bundles
*/
.Loop: fc.i r24 // issuable on M0 only
add r24=r21,r24 // we flush "stride size" bytes per iteration
nop.i 0
br.cloop.sptk.few .Loop
;;
sync.i
;;
srlz.i
;;
mov ar.lc=r3 // restore ar.lc
br.ret.sptk.many rp
END(flush_icache_range)
/*
* clflush_cache_range(start,size)
*
* Flush cache lines from start to start+size-1.
*
* Must deal with range from start to start+size-1 but nothing else
* (need to be careful not to touch addresses that may be
* unmapped).
*
* Note: "in0" and "in1" are preserved for debugging purposes.
*/
.section .kprobes.text,"ax"
GLOBAL_ENTRY(clflush_cache_range)
.prologue
alloc r2=ar.pfs,2,0,0,0
movl r3=ia64_cache_stride_shift
mov r21=1
add r22=in1,in0
;;
ld8 r20=[r3] // r20: stride shift
sub r22=r22,r0,1 // last byte address
;;
shr.u r23=in0,r20 // start / (stride size)
shr.u r22=r22,r20 // (last byte address) / (stride size)
shl r21=r21,r20 // r21: stride size of the i-cache(s)
;;
sub r8=r22,r23 // number of strides - 1
shl r24=r23,r20 // r24: addresses for "fc" =
// "start" rounded down to stride
// boundary
.save ar.lc,r3
mov r3=ar.lc // save ar.lc
;;
.body
mov ar.lc=r8
;;
/*
* 32 byte aligned loop, even number of (actually 2) bundles
*/
.Loop_fc:
fc r24 // issuable on M0 only
add r24=r21,r24 // we flush "stride size" bytes per iteration
nop.i 0
br.cloop.sptk.few .Loop_fc
;;
sync.i
;;
srlz.i
;;
mov ar.lc=r3 // restore ar.lc
br.ret.sptk.many rp
END(clflush_cache_range)
|
