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
134
135
136
137
138
|
From 21ca98c4c18bf0b0c13e77180a713a33401d539d Mon Sep 17 00:00:00 2001
From: Sandipan Das <sandipan.das@amd.com>
Date: Thu, 21 Apr 2022 11:16:57 +0530
Subject: [PATCH 73/86] perf/x86/amd/core: Add PerfMonV2 counter control
commit 9622e67e3980c01872490de0925e5c6c23247c94 upstream
If AMD Performance Monitoring Version 2 (PerfMonV2) is
supported, use a new scheme to manage the Core PMCs using
the new global control and status registers. This will be
bypassed on unsupported hardware (x86_pmu.version < 2).
Currently, all PMCs have dedicated control (PERF_CTL) and
counter (PERF_CTR) registers. For a given PMC, the enable
(En) bit of its PERF_CTL register is used to start or stop
counting.
The Performance Counter Global Control (PerfCntrGlobalCtl)
register has enable (PerfCntrEn) bits for each PMC. For a
PMC to start counting, both PERF_CTL and PerfCntrGlobalCtl
enable bits must be set. If either of those are cleared,
the PMC stops counting.
In x86_pmu_{en,dis}able_all(), the PERF_CTL registers of
all active PMCs are written to in a loop. Ideally, PMCs
counting the same event that were started and stopped at
the same time should record the same counts. Due to delays
in between writes to the PERF_CTL registers across loop
iterations, the PMCs cannot be enabled or disabled at the
same instant and hence, record slightly different counts.
This is fixed by enabling or disabling all active PMCs at
the same time with a single write to the PerfCntrGlobalCtl
register.
Signed-off-by: Sandipan Das <sandipan.das@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/dfe8e934074aaabc6ba748dfaccd0a77c974bb82.1650515382.git.sandipan.das@amd.com
Signed-off-by: Zhaolong Zhang <zhaolong.zhang@windriver.com>
---
arch/x86/events/amd/core.c | 50 ++++++++++++++++++++++++++++++++++----
1 file changed, 45 insertions(+), 5 deletions(-)
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index 52fd7941a724..a339c3e0be33 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -664,6 +664,11 @@ static void amd_pmu_cpu_dead(int cpu)
amd_pmu_cpu_reset(cpu);
}
+static inline void amd_pmu_set_global_ctl(u64 ctl)
+{
+ wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_CTL, ctl);
+}
+
/*
* When a PMC counter overflows, an NMI is used to process the event and
* reset the counter. NMI latency can result in the counter being updated
@@ -693,15 +698,11 @@ static void amd_pmu_wait_on_overflow(int idx)
}
}
-static void amd_pmu_disable_all(void)
+static void amd_pmu_check_overflow(void)
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
int idx;
- amd_brs_disable_all();
-
- x86_pmu_disable_all();
-
/*
* This shouldn't be called from NMI context, but add a safeguard here
* to return, since if we're in NMI context we can't wait for an NMI
@@ -748,6 +749,26 @@ static void amd_pmu_enable_all(int added)
}
}
+static void amd_pmu_v2_enable_event(struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ /*
+ * Testing cpu_hw_events.enabled should be skipped in this case unlike
+ * in x86_pmu_enable_event().
+ *
+ * Since cpu_hw_events.enabled is set only after returning from
+ * x86_pmu_start(), the PMCs must be programmed and kept ready.
+ * Counting starts only after x86_pmu_enable_all() is called.
+ */
+ __x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
+}
+
+static void amd_pmu_v2_enable_all(int added)
+{
+ amd_pmu_set_global_ctl(amd_pmu_global_cntr_mask);
+}
+
static void amd_pmu_disable_event(struct perf_event *event)
{
x86_pmu_disable_event(event);
@@ -765,6 +786,20 @@ static void amd_pmu_disable_event(struct perf_event *event)
amd_pmu_wait_on_overflow(event->hw.idx);
}
+static void amd_pmu_disable_all(void)
+{
+ amd_brs_disable_all();
+ x86_pmu_disable_all();
+ amd_pmu_check_overflow();
+}
+
+static void amd_pmu_v2_disable_all(void)
+{
+ /* Disable all PMCs */
+ amd_pmu_set_global_ctl(0);
+ amd_pmu_check_overflow();
+}
+
static void amd_pmu_add_event(struct perf_event *event)
{
if (needs_branch_stack(event))
@@ -1216,6 +1251,11 @@ static int __init amd_core_pmu_init(void)
x86_pmu.num_counters = ebx.split.num_core_pmc;
amd_pmu_global_cntr_mask = (1ULL << x86_pmu.num_counters) - 1;
+
+ /* Update PMC handling functions */
+ x86_pmu.enable_all = amd_pmu_v2_enable_all;
+ x86_pmu.disable_all = amd_pmu_v2_disable_all;
+ x86_pmu.enable = amd_pmu_v2_enable_event;
}
/*
--
2.37.3
|
