blob: 154accc7a543c4d1a5f90980496c3471e48ff34e (
plain)
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
|
/* SPDX-License-Identifier: GPL-2.0-only */
#ifndef _KERNEL_TIME_MIGRATION_H
#define _KERNEL_TIME_MIGRATION_H
/* Per group capacity. Must be a power of 2! */
#define TMIGR_CHILDREN_PER_GROUP 8
/**
* struct tmigr_event - a timer event associated to a CPU
* @nextevt: The node to enqueue an event in the parent group queue
* @cpu: The CPU to which this event belongs
* @ignore: Hint whether the event could be ignored; it is set when
* CPU or group is active;
*/
struct tmigr_event {
struct timerqueue_node nextevt;
unsigned int cpu;
bool ignore;
};
/**
* struct tmigr_group - timer migration hierarchy group
* @lock: Lock protecting the event information and group hierarchy
* information during setup
* @parent: Pointer to the parent group. Pointer is updated when a
* new hierarchy level is added because of a CPU coming
* online the first time. Once it is set, the pointer will
* not be removed or updated. When accessing parent pointer
* lock less to decide whether to abort a propagation or
* not, it is not a problem. The worst outcome is an
* unnecessary/early CPU wake up. But do not access parent
* pointer several times in the same 'action' (like
* activation, deactivation, check for remote expiry,...)
* without holding the lock as it is not ensured that value
* will not change.
* @groupevt: Next event of the group which is only used when the
* group is !active. The group event is then queued into
* the parent timer queue.
* Ignore bit of @groupevt is set when the group is active.
* @next_expiry: Base monotonic expiry time of the next event of the
* group; It is used for the racy lockless check whether a
* remote expiry is required; it is always reliable
* @events: Timer queue for child events queued in the group
* @migr_state: State of the group (see union tmigr_state)
* @level: Hierarchy level of the group; Required during setup
* @numa_node: Required for setup only to make sure CPU and low level
* group information is NUMA local. It is set to NUMA node
* as long as the group level is per NUMA node (level <
* tmigr_crossnode_level); otherwise it is set to
* NUMA_NO_NODE
* @num_children: Counter of group children to make sure the group is only
* filled with TMIGR_CHILDREN_PER_GROUP; Required for setup
* only
* @groupmask: mask of the group in the parent group; is set during
* setup and will never change; can be read lockless
* @list: List head that is added to the per level
* tmigr_level_list; is required during setup when a
* new group needs to be connected to the existing
* hierarchy groups
*/
struct tmigr_group {
raw_spinlock_t lock;
struct tmigr_group *parent;
struct tmigr_event groupevt;
u64 next_expiry;
struct timerqueue_head events;
atomic_t migr_state;
unsigned int level;
int numa_node;
unsigned int num_children;
u8 groupmask;
struct list_head list;
};
/**
* struct tmigr_cpu - timer migration per CPU group
* @lock: Lock protecting the tmigr_cpu group information
* @online: Indicates whether the CPU is online; In deactivate path
* it is required to know whether the migrator in the top
* level group is to be set offline, while a timer is
* pending. Then another online CPU needs to be notified to
* take over the migrator role. Furthermore the information
* is required in CPU hotplug path as the CPU is able to go
* idle before the timer migration hierarchy hotplug AP is
* reached. During this phase, the CPU has to handle the
* global timers on its own and must not act as a migrator.
* @idle: Indicates whether the CPU is idle in the timer migration
* hierarchy
* @remote: Is set when timers of the CPU are expired remotely
* @tmgroup: Pointer to the parent group
* @groupmask: mask of tmigr_cpu in the parent group
* @wakeup: Stores the first timer when the timer migration
* hierarchy is completely idle and remote expiry was done;
* is returned to timer code in the idle path and is only
* used in idle path.
* @cpuevt: CPU event which could be enqueued into the parent group
*/
struct tmigr_cpu {
raw_spinlock_t lock;
bool online;
bool idle;
bool remote;
struct tmigr_group *tmgroup;
u8 groupmask;
u64 wakeup;
struct tmigr_event cpuevt;
};
/**
* union tmigr_state - state of tmigr_group
* @state: Combined version of the state - only used for atomic
* read/cmpxchg function
* @struct: Split version of the state - only use the struct members to
* update information to stay independent of endianness
*/
union tmigr_state {
u32 state;
/**
* struct - split state of tmigr_group
* @active: Contains each mask bit of the active children
* @migrator: Contains mask of the child which is migrator
* @seq: Sequence counter needs to be increased when an update
* to the tmigr_state is done. It prevents a race when
* updates in the child groups are propagated in changed
* order. Detailed information about the scenario is
* given in the documentation at the begin of
* timer_migration.c.
*/
struct {
u8 active;
u8 migrator;
u16 seq;
} __packed;
};
#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
extern void tmigr_handle_remote(void);
extern bool tmigr_requires_handle_remote(void);
extern void tmigr_cpu_activate(void);
extern u64 tmigr_cpu_deactivate(u64 nextevt);
extern u64 tmigr_cpu_new_timer(u64 nextevt);
extern u64 tmigr_quick_check(u64 nextevt);
#else
static inline void tmigr_handle_remote(void) { }
static inline bool tmigr_requires_handle_remote(void) { return false; }
static inline void tmigr_cpu_activate(void) { }
#endif
#endif
|