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
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
|
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Performance counter support for e500 family processors.
*
* Copyright 2008-2009 Paul Mackerras, IBM Corporation.
* Copyright 2010 Freescale Semiconductor, Inc.
*/
#include <linux/string.h>
#include <linux/perf_event.h>
#include <asm/reg.h>
#include <asm/cputable.h>
/*
* Map of generic hardware event types to hardware events
* Zero if unsupported
*/
static int e500_generic_events[] = {
[PERF_COUNT_HW_CPU_CYCLES] = 1,
[PERF_COUNT_HW_INSTRUCTIONS] = 2,
[PERF_COUNT_HW_CACHE_MISSES] = 41, /* Data L1 cache reloads */
[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 12,
[PERF_COUNT_HW_BRANCH_MISSES] = 15,
[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 18,
[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 19,
};
#define C(x) PERF_COUNT_HW_CACHE_##x
/*
* Table of generalized cache-related events.
* 0 means not supported, -1 means nonsensical, other values
* are event codes.
*/
static int e500_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
/*
* D-cache misses are not split into read/write/prefetch;
* use raw event 41.
*/
[C(L1D)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 27, 0 },
[C(OP_WRITE)] = { 28, 0 },
[C(OP_PREFETCH)] = { 29, 0 },
},
[C(L1I)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 2, 60 },
[C(OP_WRITE)] = { -1, -1 },
[C(OP_PREFETCH)] = { 0, 0 },
},
/*
* Assuming LL means L2, it's not a good match for this model.
* It allocates only on L1 castout or explicit prefetch, and
* does not have separate read/write events (but it does have
* separate instruction/data events).
*/
[C(LL)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 0, 0 },
[C(OP_WRITE)] = { 0, 0 },
[C(OP_PREFETCH)] = { 0, 0 },
},
/*
* There are data/instruction MMU misses, but that's a miss on
* the chip's internal level-one TLB which is probably not
* what the user wants. Instead, unified level-two TLB misses
* are reported here.
*/
[C(DTLB)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 26, 66 },
[C(OP_WRITE)] = { -1, -1 },
[C(OP_PREFETCH)] = { -1, -1 },
},
[C(BPU)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { 12, 15 },
[C(OP_WRITE)] = { -1, -1 },
[C(OP_PREFETCH)] = { -1, -1 },
},
[C(NODE)] = { /* RESULT_ACCESS RESULT_MISS */
[C(OP_READ)] = { -1, -1 },
[C(OP_WRITE)] = { -1, -1 },
[C(OP_PREFETCH)] = { -1, -1 },
},
};
static int num_events = 128;
/* Upper half of event id is PMLCb, for threshold events */
static u64 e500_xlate_event(u64 event_id)
{
u32 event_low = (u32)event_id;
u64 ret;
if (event_low >= num_events)
return 0;
ret = FSL_EMB_EVENT_VALID;
if (event_low >= 76 && event_low <= 81) {
ret |= FSL_EMB_EVENT_RESTRICTED;
ret |= event_id &
(FSL_EMB_EVENT_THRESHMUL | FSL_EMB_EVENT_THRESH);
} else if (event_id &
(FSL_EMB_EVENT_THRESHMUL | FSL_EMB_EVENT_THRESH)) {
/* Threshold requested on non-threshold event */
return 0;
}
return ret;
}
static struct fsl_emb_pmu e500_pmu = {
.name = "e500 family",
.n_counter = 4,
.n_restricted = 2,
.xlate_event = e500_xlate_event,
.n_generic = ARRAY_SIZE(e500_generic_events),
.generic_events = e500_generic_events,
.cache_events = &e500_cache_events,
};
static int init_e500_pmu(void)
{
unsigned int pvr = mfspr(SPRN_PVR);
/* ec500mc */
if (PVR_VER(pvr) == PVR_VER_E500MC || PVR_VER(pvr) == PVR_VER_E5500)
num_events = 256;
/* e500 */
else if (PVR_VER(pvr) != PVR_VER_E500V1 && PVR_VER(pvr) != PVR_VER_E500V2)
return -ENODEV;
return register_fsl_emb_pmu(&e500_pmu);
}
early_initcall(init_e500_pmu);
|
