]>
Commit | Line | Data |
---|---|---|
c232694e SF |
1 | |
2 | .. _local_ops: | |
3 | ||
4 | ================================================= | |
5 | Semantics and Behavior of Local Atomic Operations | |
6 | ================================================= | |
7 | ||
8 | :Author: Mathieu Desnoyers | |
9 | ||
10 | ||
11 | This document explains the purpose of the local atomic operations, how | |
12 | to implement them for any given architecture and shows how they can be used | |
13 | properly. It also stresses on the precautions that must be taken when reading | |
14 | those local variables across CPUs when the order of memory writes matters. | |
15 | ||
16 | .. note:: | |
17 | ||
18 | Note that ``local_t`` based operations are not recommended for general | |
19 | kernel use. Please use the ``this_cpu`` operations instead unless there is | |
20 | really a special purpose. Most uses of ``local_t`` in the kernel have been | |
21 | replaced by ``this_cpu`` operations. ``this_cpu`` operations combine the | |
22 | relocation with the ``local_t`` like semantics in a single instruction and | |
23 | yield more compact and faster executing code. | |
24 | ||
25 | ||
26 | Purpose of local atomic operations | |
27 | ================================== | |
28 | ||
29 | Local atomic operations are meant to provide fast and highly reentrant per CPU | |
30 | counters. They minimize the performance cost of standard atomic operations by | |
31 | removing the LOCK prefix and memory barriers normally required to synchronize | |
32 | across CPUs. | |
33 | ||
34 | Having fast per CPU atomic counters is interesting in many cases: it does not | |
35 | require disabling interrupts to protect from interrupt handlers and it permits | |
36 | coherent counters in NMI handlers. It is especially useful for tracing purposes | |
37 | and for various performance monitoring counters. | |
38 | ||
39 | Local atomic operations only guarantee variable modification atomicity wrt the | |
40 | CPU which owns the data. Therefore, care must taken to make sure that only one | |
41 | CPU writes to the ``local_t`` data. This is done by using per cpu data and | |
42 | making sure that we modify it from within a preemption safe context. It is | |
43 | however permitted to read ``local_t`` data from any CPU: it will then appear to | |
44 | be written out of order wrt other memory writes by the owner CPU. | |
45 | ||
46 | ||
47 | Implementation for a given architecture | |
48 | ======================================= | |
49 | ||
50 | It can be done by slightly modifying the standard atomic operations: only | |
51 | their UP variant must be kept. It typically means removing LOCK prefix (on | |
52 | i386 and x86_64) and any SMP synchronization barrier. If the architecture does | |
53 | not have a different behavior between SMP and UP, including | |
54 | ``asm-generic/local.h`` in your architecture's ``local.h`` is sufficient. | |
55 | ||
56 | The ``local_t`` type is defined as an opaque ``signed long`` by embedding an | |
57 | ``atomic_long_t`` inside a structure. This is made so a cast from this type to | |
58 | a ``long`` fails. The definition looks like:: | |
59 | ||
60 | typedef struct { atomic_long_t a; } local_t; | |
61 | ||
62 | ||
63 | Rules to follow when using local atomic operations | |
64 | ================================================== | |
65 | ||
66 | * Variables touched by local ops must be per cpu variables. | |
67 | * *Only* the CPU owner of these variables must write to them. | |
68 | * This CPU can use local ops from any context (process, irq, softirq, nmi, ...) | |
69 | to update its ``local_t`` variables. | |
70 | * Preemption (or interrupts) must be disabled when using local ops in | |
71 | process context to make sure the process won't be migrated to a | |
72 | different CPU between getting the per-cpu variable and doing the | |
73 | actual local op. | |
74 | * When using local ops in interrupt context, no special care must be | |
75 | taken on a mainline kernel, since they will run on the local CPU with | |
76 | preemption already disabled. I suggest, however, to explicitly | |
77 | disable preemption anyway to make sure it will still work correctly on | |
78 | -rt kernels. | |
79 | * Reading the local cpu variable will provide the current copy of the | |
80 | variable. | |
81 | * Reads of these variables can be done from any CPU, because updates to | |
82 | "``long``", aligned, variables are always atomic. Since no memory | |
83 | synchronization is done by the writer CPU, an outdated copy of the | |
84 | variable can be read when reading some *other* cpu's variables. | |
85 | ||
86 | ||
87 | How to use local atomic operations | |
88 | ================================== | |
89 | ||
90 | :: | |
91 | ||
92 | #include <linux/percpu.h> | |
93 | #include <asm/local.h> | |
94 | ||
95 | static DEFINE_PER_CPU(local_t, counters) = LOCAL_INIT(0); | |
96 | ||
97 | ||
98 | Counting | |
99 | ======== | |
100 | ||
101 | Counting is done on all the bits of a signed long. | |
102 | ||
103 | In preemptible context, use ``get_cpu_var()`` and ``put_cpu_var()`` around | |
104 | local atomic operations: it makes sure that preemption is disabled around write | |
105 | access to the per cpu variable. For instance:: | |
106 | ||
107 | local_inc(&get_cpu_var(counters)); | |
108 | put_cpu_var(counters); | |
109 | ||
110 | If you are already in a preemption-safe context, you can use | |
111 | ``this_cpu_ptr()`` instead:: | |
112 | ||
113 | local_inc(this_cpu_ptr(&counters)); | |
114 | ||
115 | ||
116 | ||
117 | Reading the counters | |
118 | ==================== | |
119 | ||
120 | Those local counters can be read from foreign CPUs to sum the count. Note that | |
121 | the data seen by local_read across CPUs must be considered to be out of order | |
122 | relatively to other memory writes happening on the CPU that owns the data:: | |
123 | ||
124 | long sum = 0; | |
125 | for_each_online_cpu(cpu) | |
126 | sum += local_read(&per_cpu(counters, cpu)); | |
127 | ||
128 | If you want to use a remote local_read to synchronize access to a resource | |
129 | between CPUs, explicit ``smp_wmb()`` and ``smp_rmb()`` memory barriers must be used | |
130 | respectively on the writer and the reader CPUs. It would be the case if you use | |
131 | the ``local_t`` variable as a counter of bytes written in a buffer: there should | |
132 | be a ``smp_wmb()`` between the buffer write and the counter increment and also a | |
133 | ``smp_rmb()`` between the counter read and the buffer read. | |
134 | ||
135 | ||
136 | Here is a sample module which implements a basic per cpu counter using | |
137 | ``local.h``:: | |
138 | ||
139 | /* test-local.c | |
140 | * | |
141 | * Sample module for local.h usage. | |
142 | */ | |
143 | ||
144 | ||
145 | #include <asm/local.h> | |
146 | #include <linux/module.h> | |
147 | #include <linux/timer.h> | |
148 | ||
149 | static DEFINE_PER_CPU(local_t, counters) = LOCAL_INIT(0); | |
150 | ||
151 | static struct timer_list test_timer; | |
152 | ||
153 | /* IPI called on each CPU. */ | |
154 | static void test_each(void *info) | |
155 | { | |
156 | /* Increment the counter from a non preemptible context */ | |
157 | printk("Increment on cpu %d\n", smp_processor_id()); | |
158 | local_inc(this_cpu_ptr(&counters)); | |
159 | ||
160 | /* This is what incrementing the variable would look like within a | |
161 | * preemptible context (it disables preemption) : | |
162 | * | |
163 | * local_inc(&get_cpu_var(counters)); | |
164 | * put_cpu_var(counters); | |
165 | */ | |
166 | } | |
167 | ||
168 | static void do_test_timer(unsigned long data) | |
169 | { | |
170 | int cpu; | |
171 | ||
172 | /* Increment the counters */ | |
173 | on_each_cpu(test_each, NULL, 1); | |
174 | /* Read all the counters */ | |
175 | printk("Counters read from CPU %d\n", smp_processor_id()); | |
176 | for_each_online_cpu(cpu) { | |
177 | printk("Read : CPU %d, count %ld\n", cpu, | |
178 | local_read(&per_cpu(counters, cpu))); | |
179 | } | |
7eeb6b89 | 180 | mod_timer(&test_timer, jiffies + 1000); |
c232694e SF |
181 | } |
182 | ||
183 | static int __init test_init(void) | |
184 | { | |
185 | /* initialize the timer that will increment the counter */ | |
7eeb6b89 KC |
186 | timer_setup(&test_timer, do_test_timer, 0); |
187 | mod_timer(&test_timer, jiffies + 1); | |
c232694e SF |
188 | |
189 | return 0; | |
190 | } | |
191 | ||
192 | static void __exit test_exit(void) | |
193 | { | |
194 | del_timer_sync(&test_timer); | |
195 | } | |
196 | ||
197 | module_init(test_init); | |
198 | module_exit(test_exit); | |
199 | ||
200 | MODULE_LICENSE("GPL"); | |
201 | MODULE_AUTHOR("Mathieu Desnoyers"); | |
202 | MODULE_DESCRIPTION("Local Atomic Ops"); |