1 .\" Copyright (c) 2000-2001 John H. Baldwin <jhb@FreeBSD.org>
2 .\" All rights reserved.
4 .\" Redistribution and use in source and binary forms, with or without
5 .\" modification, are permitted provided that the following conditions
7 .\" 1. Redistributions of source code must retain the above copyright
8 .\" notice, this list of conditions and the following disclaimer.
9 .\" 2. Redistributions in binary form must reproduce the above copyright
10 .\" notice, this list of conditions and the following disclaimer in the
11 .\" documentation and/or other materials provided with the distribution.
13 .\" THIS SOFTWARE IS PROVIDED BY THE DEVELOPERS ``AS IS'' AND ANY EXPRESS OR
14 .\" IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
15 .\" OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
16 .\" IN NO EVENT SHALL THE DEVELOPERS BE LIABLE FOR ANY DIRECT, INDIRECT,
17 .\" INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
18 .\" NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
19 .\" DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
20 .\" THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
21 .\" (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
22 .\" THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
35 .Nm atomic_readandclear ,
44 .Fn atomic_add_[acq_|rel_]<type> "volatile <type> *p" "<type> v"
46 .Fn atomic_clear_[acq_|rel_]<type> "volatile <type> *p" "<type> v"
48 .Fo atomic_cmpset_[acq_|rel_]<type>
49 .Fa "volatile <type> *dst"
54 .Fn atomic_fetchadd_<type> "volatile <type> *p" "<type> v"
56 .Fn atomic_load_acq_<type> "volatile <type> *p"
58 .Fn atomic_readandclear_<type> "volatile <type> *p"
60 .Fn atomic_set_[acq_|rel_]<type> "volatile <type> *p" "<type> v"
62 .Fn atomic_subtract_[acq_|rel_]<type> "volatile <type> *p" "<type> v"
64 .Fn atomic_store_rel_<type> "volatile <type> *p" "<type> v"
66 .Fn atomic_swap_<type> "volatile <type> *p" "<type> v"
68 .Fn atomic_testandset_<type> "volatile <type> *p" "u_int v"
70 Each of the atomic operations is guaranteed to be atomic in the presence of
72 They can be used to implement reference counts or as building blocks for more
73 advanced synchronization primitives such as mutexes.
75 Each atomic operation operates on a specific
77 The type to use is indicated in the function name.
78 The available types that can be used are:
80 .Bl -tag -offset indent -width short -compact
86 unsigned integer the size of a pointer
88 unsigned 32-bit integer
90 unsigned 64-bit integer
93 For example, the function to atomically add two integers is called
96 Certain architectures also provide operations for types smaller than
99 .Bl -tag -offset indent -width short -compact
103 unsigned short integer
105 unsigned 8-bit integer
107 unsigned 16-bit integer
110 These must not be used in MI code because the instructions to implement them
111 efficiently may not be available.
113 Memory barriers are used to guarantee the order of data accesses in
115 First, they specify hints to the compiler to not re-order or optimize the
117 Second, on architectures that do not guarantee ordered data accesses,
118 special instructions or special variants of instructions are used to indicate
119 to the processor that data accesses need to occur in a certain order.
120 As a result, most of the atomic operations have three variants in order to
121 include optional memory barriers.
122 The first form just performs the operation without any explicit barriers.
123 The second form uses a read memory barrier, and the third variant uses a write
126 The second variant of each operation includes a read memory barrier.
127 This barrier ensures that the effects of this operation are completed before the
128 effects of any later data accesses.
129 As a result, the operation is said to have acquire semantics as it acquires a
130 pseudo-lock requiring further operations to wait until it has completed.
131 To denote this, the suffix
133 is inserted into the function name immediately prior to the
134 .Dq Li _ Ns Aq Fa type
136 For example, to subtract two integers ensuring that any later writes will
137 happen after the subtraction is performed, use
138 .Fn atomic_subtract_acq_int .
140 The third variant of each operation includes a write memory barrier.
141 This ensures that all effects of all previous data accesses are completed
142 before this operation takes place.
143 As a result, the operation is said to have release semantics as it releases
144 any pending data accesses to be completed before its operation is performed.
145 To denote this, the suffix
147 is inserted into the function name immediately prior to the
148 .Dq Li _ Ns Aq Fa type
150 For example, to add two long integers ensuring that all previous
151 writes will happen first, use
152 .Fn atomic_add_rel_long .
154 A practical example of using memory barriers is to ensure that data accesses
155 that are protected by a lock are all performed while the lock is held.
156 To achieve this, one would use a read barrier when acquiring the lock to
157 guarantee that the lock is held before any protected operations are performed.
158 Finally, one would use a write barrier when releasing the lock to ensure that
159 all of the protected operations are completed before the lock is released.
160 .Ss Multiple Processors
161 The current set of atomic operations do not necessarily guarantee atomicity
162 across multiple processors.
163 To guarantee atomicity across processors, not only does the individual
164 operation need to be atomic on the processor performing the operation, but
165 the result of the operation needs to be pushed out to stable storage and the
166 caches of all other processors on the system need to invalidate any cache
167 lines that include the affected memory region.
170 architecture, the cache coherency model requires that the hardware perform
171 this task, thus the atomic operations are atomic across multiple processors.
173 This section describes the semantics of each operation using a C like notation.
175 .It Fn atomic_add p v
176 .Bd -literal -compact
179 .It Fn atomic_clear p v
180 .Bd -literal -compact
183 .It Fn atomic_cmpset dst old new
184 .Bd -literal -compact
195 functions are not implemented for the types
202 .It Fn atomic_fetchadd p v
203 .Bd -literal -compact
212 functions are only implemented for the types
217 and do not have any variants with memory barriers at this time.
220 .Bd -literal -compact
227 functions are only provided with acquire memory barriers.
229 .It Fn atomic_readandclear p
230 .Bd -literal -compact
238 .Fn atomic_readandclear
239 functions are not implemented for the types
246 and do not have any variants with memory barriers at this time.
248 .It Fn atomic_set p v
249 .Bd -literal -compact
252 .It Fn atomic_subtract p v
253 .Bd -literal -compact
256 .It Fn atomic_store p v
257 .Bd -literal -compact
264 functions are only provided with release memory barriers.
266 .It Fn atomic_swap p v
267 .Bd -literal -compact
276 functions are not implemented for the types
283 and do not have any variants with memory barriers at this time.
285 .It Fn atomic_testandset p v
286 .Bd -literal -compact
287 bit = 1 << (v % (sizeof(*p) * NBBY));
288 tmp = (*p & bit) != 0;
295 .Fn atomic_testandset
296 functions are only implemented for the types
301 and do not have any variants with memory barriers at this time.
305 is currently not implemented for any of the atomic operations on the
314 function returns the result of the compare operation.
316 .Fn atomic_fetchadd ,
318 .Fn atomic_readandclear ,
321 functions return the value at the specified address.
323 .Fn atomic_testandset
324 function returns the result of the test operation.
326 This example uses the
327 .Fn atomic_cmpset_acq_ptr
330 functions to obtain a sleep mutex and handle recursion.
339 /* Try to obtain mtx_lock once. */
340 #define _obtain_lock(mp, tid) \\
341 atomic_cmpset_acq_ptr(&(mp)->mtx_lock, MTX_UNOWNED, (tid))
343 /* Get a sleep lock, deal with recursion inline. */
344 #define _get_sleep_lock(mp, tid, opts, file, line) do { \\
345 uintptr_t _tid = (uintptr_t)(tid); \\
347 if (!_obtain_lock(mp, tid)) { \\
348 if (((mp)->mtx_lock & MTX_FLAGMASK) != _tid) \\
349 _mtx_lock_sleep((mp), _tid, (opts), (file), (line));\\
351 atomic_set_ptr(&(mp)->mtx_lock, MTX_RECURSE); \\
352 (mp)->mtx_recurse++; \\
364 operations were first introduced in
366 This first set only supported the types
375 .Fn atomic_readandclear ,
378 operations were added in
387 and all of the acquire and release variants
393 operations were added in
398 .Fn atomic_testandset
399 operations were added in