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
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
|
From e387d228099075ac3f762ccfbbe29f9ee59678c8 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <frederic@kernel.org>
Date: Wed, 2 Dec 2020 12:57:31 +0100
Subject: [PATCH 129/323] irqtime: Move irqtime entry accounting after irq
offset incrementation
Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/5.10/older/patches-5.10.204-rt100.tar.xz
IRQ time entry is currently accounted before HARDIRQ_OFFSET or
SOFTIRQ_OFFSET are incremented. This is convenient to decide to which
index the cputime to account is dispatched.
Unfortunately it prevents tick_irq_enter() from being called under
HARDIRQ_OFFSET because tick_irq_enter() has to be called before the IRQ
entry accounting due to the necessary clock catch up. As a result we
don't benefit from appropriate lockdep coverage on tick_irq_enter().
To prepare for fixing this, move the IRQ entry cputime accounting after
the preempt offset is incremented. This requires the cputime dispatch
code to handle the extra offset.
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20201202115732.27827-5-frederic@kernel.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
---
include/linux/hardirq.h | 4 ++--
include/linux/vtime.h | 34 ++++++++++++++++++++++++----------
kernel/sched/cputime.c | 18 +++++++++++-------
kernel/softirq.c | 6 +++---
4 files changed, 40 insertions(+), 22 deletions(-)
diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index c35b71f8644a..0926e9ca4d85 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -32,9 +32,9 @@ static __always_inline void rcu_irq_enter_check_tick(void)
*/
#define __irq_enter() \
do { \
- account_irq_enter_time(current); \
preempt_count_add(HARDIRQ_OFFSET); \
lockdep_hardirq_enter(); \
+ account_hardirq_enter(current); \
} while (0)
/*
@@ -62,8 +62,8 @@ void irq_enter_rcu(void);
*/
#define __irq_exit() \
do { \
+ account_hardirq_exit(current); \
lockdep_hardirq_exit(); \
- account_irq_exit_time(current); \
preempt_count_sub(HARDIRQ_OFFSET); \
} while (0)
diff --git a/include/linux/vtime.h b/include/linux/vtime.h
index 6c9867419615..041d6524d144 100644
--- a/include/linux/vtime.h
+++ b/include/linux/vtime.h
@@ -83,32 +83,46 @@ static inline void vtime_init_idle(struct task_struct *tsk, int cpu) { }
#endif
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
-extern void vtime_account_irq(struct task_struct *tsk);
+extern void vtime_account_irq(struct task_struct *tsk, unsigned int offset);
extern void vtime_account_softirq(struct task_struct *tsk);
extern void vtime_account_hardirq(struct task_struct *tsk);
extern void vtime_flush(struct task_struct *tsk);
#else /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
-static inline void vtime_account_irq(struct task_struct *tsk) { }
+static inline void vtime_account_irq(struct task_struct *tsk, unsigned int offset) { }
+static inline void vtime_account_softirq(struct task_struct *tsk) { }
+static inline void vtime_account_hardirq(struct task_struct *tsk) { }
static inline void vtime_flush(struct task_struct *tsk) { }
#endif
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
-extern void irqtime_account_irq(struct task_struct *tsk);
+extern void irqtime_account_irq(struct task_struct *tsk, unsigned int offset);
#else
-static inline void irqtime_account_irq(struct task_struct *tsk) { }
+static inline void irqtime_account_irq(struct task_struct *tsk, unsigned int offset) { }
#endif
-static inline void account_irq_enter_time(struct task_struct *tsk)
+static inline void account_softirq_enter(struct task_struct *tsk)
{
- vtime_account_irq(tsk);
- irqtime_account_irq(tsk);
+ vtime_account_irq(tsk, SOFTIRQ_OFFSET);
+ irqtime_account_irq(tsk, SOFTIRQ_OFFSET);
}
-static inline void account_irq_exit_time(struct task_struct *tsk)
+static inline void account_softirq_exit(struct task_struct *tsk)
{
- vtime_account_irq(tsk);
- irqtime_account_irq(tsk);
+ vtime_account_softirq(tsk);
+ irqtime_account_irq(tsk, 0);
+}
+
+static inline void account_hardirq_enter(struct task_struct *tsk)
+{
+ vtime_account_irq(tsk, HARDIRQ_OFFSET);
+ irqtime_account_irq(tsk, HARDIRQ_OFFSET);
+}
+
+static inline void account_hardirq_exit(struct task_struct *tsk)
+{
+ vtime_account_hardirq(tsk);
+ irqtime_account_irq(tsk, 0);
}
#endif /* _LINUX_KERNEL_VTIME_H */
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 60129af16ed6..02a7932c7383 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -44,12 +44,13 @@ static void irqtime_account_delta(struct irqtime *irqtime, u64 delta,
}
/*
- * Called before incrementing preempt_count on {soft,}irq_enter
+ * Called after incrementing preempt_count on {soft,}irq_enter
* and before decrementing preempt_count on {soft,}irq_exit.
*/
-void irqtime_account_irq(struct task_struct *curr)
+void irqtime_account_irq(struct task_struct *curr, unsigned int offset)
{
struct irqtime *irqtime = this_cpu_ptr(&cpu_irqtime);
+ unsigned int pc;
s64 delta;
int cpu;
@@ -59,6 +60,7 @@ void irqtime_account_irq(struct task_struct *curr)
cpu = smp_processor_id();
delta = sched_clock_cpu(cpu) - irqtime->irq_start_time;
irqtime->irq_start_time += delta;
+ pc = preempt_count() - offset;
/*
* We do not account for softirq time from ksoftirqd here.
@@ -66,9 +68,9 @@ void irqtime_account_irq(struct task_struct *curr)
* in that case, so as not to confuse scheduler with a special task
* that do not consume any time, but still wants to run.
*/
- if (hardirq_count())
+ if (pc & HARDIRQ_MASK)
irqtime_account_delta(irqtime, delta, CPUTIME_IRQ);
- else if (in_serving_softirq() && curr != this_cpu_ksoftirqd())
+ else if ((pc & SOFTIRQ_OFFSET) && curr != this_cpu_ksoftirqd())
irqtime_account_delta(irqtime, delta, CPUTIME_SOFTIRQ);
}
@@ -417,11 +419,13 @@ void vtime_task_switch(struct task_struct *prev)
}
# endif
-void vtime_account_irq(struct task_struct *tsk)
+void vtime_account_irq(struct task_struct *tsk, unsigned int offset)
{
- if (hardirq_count()) {
+ unsigned int pc = preempt_count() - offset;
+
+ if (pc & HARDIRQ_OFFSET) {
vtime_account_hardirq(tsk);
- } else if (in_serving_softirq()) {
+ } else if (pc & SOFTIRQ_OFFSET) {
vtime_account_softirq(tsk);
} else if (!IS_ENABLED(CONFIG_HAVE_VIRT_CPU_ACCOUNTING_IDLE) &&
is_idle_task(tsk)) {
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 617009ccd82c..b8f42b3ba8ca 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -315,10 +315,10 @@ asmlinkage __visible void __softirq_entry __do_softirq(void)
current->flags &= ~PF_MEMALLOC;
pending = local_softirq_pending();
- account_irq_enter_time(current);
__local_bh_disable_ip(_RET_IP_, SOFTIRQ_OFFSET);
in_hardirq = lockdep_softirq_start();
+ account_softirq_enter(current);
restart:
/* Reset the pending bitmask before enabling irqs */
@@ -365,8 +365,8 @@ asmlinkage __visible void __softirq_entry __do_softirq(void)
wakeup_softirqd();
}
+ account_softirq_exit(current);
lockdep_softirq_end(in_hardirq);
- account_irq_exit_time(current);
__local_bh_enable(SOFTIRQ_OFFSET);
WARN_ON_ONCE(in_interrupt());
current_restore_flags(old_flags, PF_MEMALLOC);
@@ -418,7 +418,7 @@ static inline void __irq_exit_rcu(void)
#else
lockdep_assert_irqs_disabled();
#endif
- account_irq_exit_time(current);
+ account_hardirq_exit(current);
preempt_count_sub(HARDIRQ_OFFSET);
if (!in_interrupt() && local_softirq_pending())
invoke_softirq();
--
2.43.0
|
