blob: cf0d5416a4c39271aa572188647a7d30de93806a [file] [log] [blame]
David Howells108b42b2006-03-31 16:00:29 +01001 ============================
2 LINUX KERNEL MEMORY BARRIERS
3 ============================
4
5By: David Howells <dhowells@redhat.com>
6
7Contents:
8
9 (*) Abstract memory access model.
10
11 - Device operations.
12 - Guarantees.
13
14 (*) What are memory barriers?
15
16 - Varieties of memory barrier.
17 - What may not be assumed about memory barriers?
18 - Data dependency barriers.
19 - Control dependencies.
20 - SMP barrier pairing.
21 - Examples of memory barrier sequences.
David Howells670bd952006-06-10 09:54:12 -070022 - Read memory barriers vs load speculation.
David Howells108b42b2006-03-31 16:00:29 +010023
24 (*) Explicit kernel barriers.
25
26 - Compiler barrier.
27 - The CPU memory barriers.
28 - MMIO write barrier.
29
30 (*) Implicit kernel memory barriers.
31
32 - Locking functions.
33 - Interrupt disabling functions.
34 - Miscellaneous functions.
35
36 (*) Inter-CPU locking barrier effects.
37
38 - Locks vs memory accesses.
39 - Locks vs I/O accesses.
40
41 (*) Where are memory barriers needed?
42
43 - Interprocessor interaction.
44 - Atomic operations.
45 - Accessing devices.
46 - Interrupts.
47
48 (*) Kernel I/O barrier effects.
49
50 (*) Assumed minimum execution ordering model.
51
52 (*) The effects of the cpu cache.
53
54 - Cache coherency.
55 - Cache coherency vs DMA.
56 - Cache coherency vs MMIO.
57
58 (*) The things CPUs get up to.
59
60 - And then there's the Alpha.
61
62 (*) References.
63
64
65============================
66ABSTRACT MEMORY ACCESS MODEL
67============================
68
69Consider the following abstract model of the system:
70
71 : :
72 : :
73 : :
74 +-------+ : +--------+ : +-------+
75 | | : | | : | |
76 | | : | | : | |
77 | CPU 1 |<----->| Memory |<----->| CPU 2 |
78 | | : | | : | |
79 | | : | | : | |
80 +-------+ : +--------+ : +-------+
81 ^ : ^ : ^
82 | : | : |
83 | : | : |
84 | : v : |
85 | : +--------+ : |
86 | : | | : |
87 | : | | : |
88 +---------->| Device |<----------+
89 : | | :
90 : | | :
91 : +--------+ :
92 : :
93
94Each CPU executes a program that generates memory access operations. In the
95abstract CPU, memory operation ordering is very relaxed, and a CPU may actually
96perform the memory operations in any order it likes, provided program causality
97appears to be maintained. Similarly, the compiler may also arrange the
98instructions it emits in any order it likes, provided it doesn't affect the
99apparent operation of the program.
100
101So in the above diagram, the effects of the memory operations performed by a
102CPU are perceived by the rest of the system as the operations cross the
103interface between the CPU and rest of the system (the dotted lines).
104
105
106For example, consider the following sequence of events:
107
108 CPU 1 CPU 2
109 =============== ===============
110 { A == 1; B == 2 }
111 A = 3; x = A;
112 B = 4; y = B;
113
114The set of accesses as seen by the memory system in the middle can be arranged
115in 24 different combinations:
116
117 STORE A=3, STORE B=4, x=LOAD A->3, y=LOAD B->4
118 STORE A=3, STORE B=4, y=LOAD B->4, x=LOAD A->3
119 STORE A=3, x=LOAD A->3, STORE B=4, y=LOAD B->4
120 STORE A=3, x=LOAD A->3, y=LOAD B->2, STORE B=4
121 STORE A=3, y=LOAD B->2, STORE B=4, x=LOAD A->3
122 STORE A=3, y=LOAD B->2, x=LOAD A->3, STORE B=4
123 STORE B=4, STORE A=3, x=LOAD A->3, y=LOAD B->4
124 STORE B=4, ...
125 ...
126
127and can thus result in four different combinations of values:
128
129 x == 1, y == 2
130 x == 1, y == 4
131 x == 3, y == 2
132 x == 3, y == 4
133
134
135Furthermore, the stores committed by a CPU to the memory system may not be
136perceived by the loads made by another CPU in the same order as the stores were
137committed.
138
139
140As a further example, consider this sequence of events:
141
142 CPU 1 CPU 2
143 =============== ===============
144 { A == 1, B == 2, C = 3, P == &A, Q == &C }
145 B = 4; Q = P;
146 P = &B D = *Q;
147
148There is an obvious data dependency here, as the value loaded into D depends on
149the address retrieved from P by CPU 2. At the end of the sequence, any of the
150following results are possible:
151
152 (Q == &A) and (D == 1)
153 (Q == &B) and (D == 2)
154 (Q == &B) and (D == 4)
155
156Note that CPU 2 will never try and load C into D because the CPU will load P
157into Q before issuing the load of *Q.
158
159
160DEVICE OPERATIONS
161-----------------
162
163Some devices present their control interfaces as collections of memory
164locations, but the order in which the control registers are accessed is very
165important. For instance, imagine an ethernet card with a set of internal
166registers that are accessed through an address port register (A) and a data
167port register (D). To read internal register 5, the following code might then
168be used:
169
170 *A = 5;
171 x = *D;
172
173but this might show up as either of the following two sequences:
174
175 STORE *A = 5, x = LOAD *D
176 x = LOAD *D, STORE *A = 5
177
178the second of which will almost certainly result in a malfunction, since it set
179the address _after_ attempting to read the register.
180
181
182GUARANTEES
183----------
184
185There are some minimal guarantees that may be expected of a CPU:
186
187 (*) On any given CPU, dependent memory accesses will be issued in order, with
188 respect to itself. This means that for:
189
190 Q = P; D = *Q;
191
192 the CPU will issue the following memory operations:
193
194 Q = LOAD P, D = LOAD *Q
195
196 and always in that order.
197
198 (*) Overlapping loads and stores within a particular CPU will appear to be
199 ordered within that CPU. This means that for:
200
201 a = *X; *X = b;
202
203 the CPU will only issue the following sequence of memory operations:
204
205 a = LOAD *X, STORE *X = b
206
207 And for:
208
209 *X = c; d = *X;
210
211 the CPU will only issue:
212
213 STORE *X = c, d = LOAD *X
214
215 (Loads and stores overlap if they are targetted at overlapping pieces of
216 memory).
217
218And there are a number of things that _must_ or _must_not_ be assumed:
219
220 (*) It _must_not_ be assumed that independent loads and stores will be issued
221 in the order given. This means that for:
222
223 X = *A; Y = *B; *D = Z;
224
225 we may get any of the following sequences:
226
227 X = LOAD *A, Y = LOAD *B, STORE *D = Z
228 X = LOAD *A, STORE *D = Z, Y = LOAD *B
229 Y = LOAD *B, X = LOAD *A, STORE *D = Z
230 Y = LOAD *B, STORE *D = Z, X = LOAD *A
231 STORE *D = Z, X = LOAD *A, Y = LOAD *B
232 STORE *D = Z, Y = LOAD *B, X = LOAD *A
233
234 (*) It _must_ be assumed that overlapping memory accesses may be merged or
235 discarded. This means that for:
236
237 X = *A; Y = *(A + 4);
238
239 we may get any one of the following sequences:
240
241 X = LOAD *A; Y = LOAD *(A + 4);
242 Y = LOAD *(A + 4); X = LOAD *A;
243 {X, Y} = LOAD {*A, *(A + 4) };
244
245 And for:
246
247 *A = X; Y = *A;
248
249 we may get either of:
250
251 STORE *A = X; Y = LOAD *A;
David Howells670bd952006-06-10 09:54:12 -0700252 STORE *A = Y = X;
David Howells108b42b2006-03-31 16:00:29 +0100253
254
255=========================
256WHAT ARE MEMORY BARRIERS?
257=========================
258
259As can be seen above, independent memory operations are effectively performed
260in random order, but this can be a problem for CPU-CPU interaction and for I/O.
261What is required is some way of intervening to instruct the compiler and the
262CPU to restrict the order.
263
264Memory barriers are such interventions. They impose a perceived partial
David Howells2b948952006-06-25 05:48:49 -0700265ordering over the memory operations on either side of the barrier.
266
267Such enforcement is important because the CPUs and other devices in a system
268can use a variety of tricks to improve performance - including reordering,
269deferral and combination of memory operations; speculative loads; speculative
270branch prediction and various types of caching. Memory barriers are used to
271override or suppress these tricks, allowing the code to sanely control the
272interaction of multiple CPUs and/or devices.
David Howells108b42b2006-03-31 16:00:29 +0100273
274
275VARIETIES OF MEMORY BARRIER
276---------------------------
277
278Memory barriers come in four basic varieties:
279
280 (1) Write (or store) memory barriers.
281
282 A write memory barrier gives a guarantee that all the STORE operations
283 specified before the barrier will appear to happen before all the STORE
284 operations specified after the barrier with respect to the other
285 components of the system.
286
287 A write barrier is a partial ordering on stores only; it is not required
288 to have any effect on loads.
289
David Howells6bc39272006-06-25 05:49:22 -0700290 A CPU can be viewed as committing a sequence of store operations to the
David Howells108b42b2006-03-31 16:00:29 +0100291 memory system as time progresses. All stores before a write barrier will
292 occur in the sequence _before_ all the stores after the write barrier.
293
294 [!] Note that write barriers should normally be paired with read or data
295 dependency barriers; see the "SMP barrier pairing" subsection.
296
297
298 (2) Data dependency barriers.
299
300 A data dependency barrier is a weaker form of read barrier. In the case
301 where two loads are performed such that the second depends on the result
302 of the first (eg: the first load retrieves the address to which the second
303 load will be directed), a data dependency barrier would be required to
304 make sure that the target of the second load is updated before the address
305 obtained by the first load is accessed.
306
307 A data dependency barrier is a partial ordering on interdependent loads
308 only; it is not required to have any effect on stores, independent loads
309 or overlapping loads.
310
311 As mentioned in (1), the other CPUs in the system can be viewed as
312 committing sequences of stores to the memory system that the CPU being
313 considered can then perceive. A data dependency barrier issued by the CPU
314 under consideration guarantees that for any load preceding it, if that
315 load touches one of a sequence of stores from another CPU, then by the
316 time the barrier completes, the effects of all the stores prior to that
317 touched by the load will be perceptible to any loads issued after the data
318 dependency barrier.
319
320 See the "Examples of memory barrier sequences" subsection for diagrams
321 showing the ordering constraints.
322
323 [!] Note that the first load really has to have a _data_ dependency and
324 not a control dependency. If the address for the second load is dependent
325 on the first load, but the dependency is through a conditional rather than
326 actually loading the address itself, then it's a _control_ dependency and
327 a full read barrier or better is required. See the "Control dependencies"
328 subsection for more information.
329
330 [!] Note that data dependency barriers should normally be paired with
331 write barriers; see the "SMP barrier pairing" subsection.
332
333
334 (3) Read (or load) memory barriers.
335
336 A read barrier is a data dependency barrier plus a guarantee that all the
337 LOAD operations specified before the barrier will appear to happen before
338 all the LOAD operations specified after the barrier with respect to the
339 other components of the system.
340
341 A read barrier is a partial ordering on loads only; it is not required to
342 have any effect on stores.
343
344 Read memory barriers imply data dependency barriers, and so can substitute
345 for them.
346
347 [!] Note that read barriers should normally be paired with write barriers;
348 see the "SMP barrier pairing" subsection.
349
350
351 (4) General memory barriers.
352
David Howells670bd952006-06-10 09:54:12 -0700353 A general memory barrier gives a guarantee that all the LOAD and STORE
354 operations specified before the barrier will appear to happen before all
355 the LOAD and STORE operations specified after the barrier with respect to
356 the other components of the system.
357
358 A general memory barrier is a partial ordering over both loads and stores.
David Howells108b42b2006-03-31 16:00:29 +0100359
360 General memory barriers imply both read and write memory barriers, and so
361 can substitute for either.
362
363
364And a couple of implicit varieties:
365
366 (5) LOCK operations.
367
368 This acts as a one-way permeable barrier. It guarantees that all memory
369 operations after the LOCK operation will appear to happen after the LOCK
370 operation with respect to the other components of the system.
371
372 Memory operations that occur before a LOCK operation may appear to happen
373 after it completes.
374
375 A LOCK operation should almost always be paired with an UNLOCK operation.
376
377
378 (6) UNLOCK operations.
379
380 This also acts as a one-way permeable barrier. It guarantees that all
381 memory operations before the UNLOCK operation will appear to happen before
382 the UNLOCK operation with respect to the other components of the system.
383
384 Memory operations that occur after an UNLOCK operation may appear to
385 happen before it completes.
386
387 LOCK and UNLOCK operations are guaranteed to appear with respect to each
388 other strictly in the order specified.
389
390 The use of LOCK and UNLOCK operations generally precludes the need for
391 other sorts of memory barrier (but note the exceptions mentioned in the
392 subsection "MMIO write barrier").
393
394
395Memory barriers are only required where there's a possibility of interaction
396between two CPUs or between a CPU and a device. If it can be guaranteed that
397there won't be any such interaction in any particular piece of code, then
398memory barriers are unnecessary in that piece of code.
399
400
401Note that these are the _minimum_ guarantees. Different architectures may give
402more substantial guarantees, but they may _not_ be relied upon outside of arch
403specific code.
404
405
406WHAT MAY NOT BE ASSUMED ABOUT MEMORY BARRIERS?
407----------------------------------------------
408
409There are certain things that the Linux kernel memory barriers do not guarantee:
410
411 (*) There is no guarantee that any of the memory accesses specified before a
412 memory barrier will be _complete_ by the completion of a memory barrier
413 instruction; the barrier can be considered to draw a line in that CPU's
414 access queue that accesses of the appropriate type may not cross.
415
416 (*) There is no guarantee that issuing a memory barrier on one CPU will have
417 any direct effect on another CPU or any other hardware in the system. The
418 indirect effect will be the order in which the second CPU sees the effects
419 of the first CPU's accesses occur, but see the next point:
420
David Howells6bc39272006-06-25 05:49:22 -0700421 (*) There is no guarantee that a CPU will see the correct order of effects
David Howells108b42b2006-03-31 16:00:29 +0100422 from a second CPU's accesses, even _if_ the second CPU uses a memory
423 barrier, unless the first CPU _also_ uses a matching memory barrier (see
424 the subsection on "SMP Barrier Pairing").
425
426 (*) There is no guarantee that some intervening piece of off-the-CPU
427 hardware[*] will not reorder the memory accesses. CPU cache coherency
428 mechanisms should propagate the indirect effects of a memory barrier
429 between CPUs, but might not do so in order.
430
431 [*] For information on bus mastering DMA and coherency please read:
432
433 Documentation/pci.txt
434 Documentation/DMA-mapping.txt
435 Documentation/DMA-API.txt
436
437
438DATA DEPENDENCY BARRIERS
439------------------------
440
441The usage requirements of data dependency barriers are a little subtle, and
442it's not always obvious that they're needed. To illustrate, consider the
443following sequence of events:
444
445 CPU 1 CPU 2
446 =============== ===============
447 { A == 1, B == 2, C = 3, P == &A, Q == &C }
448 B = 4;
449 <write barrier>
450 P = &B
451 Q = P;
452 D = *Q;
453
454There's a clear data dependency here, and it would seem that by the end of the
455sequence, Q must be either &A or &B, and that:
456
457 (Q == &A) implies (D == 1)
458 (Q == &B) implies (D == 4)
459
460But! CPU 2's perception of P may be updated _before_ its perception of B, thus
461leading to the following situation:
462
463 (Q == &B) and (D == 2) ????
464
465Whilst this may seem like a failure of coherency or causality maintenance, it
466isn't, and this behaviour can be observed on certain real CPUs (such as the DEC
467Alpha).
468
David Howells2b948952006-06-25 05:48:49 -0700469To deal with this, a data dependency barrier or better must be inserted
470between the address load and the data load:
David Howells108b42b2006-03-31 16:00:29 +0100471
472 CPU 1 CPU 2
473 =============== ===============
474 { A == 1, B == 2, C = 3, P == &A, Q == &C }
475 B = 4;
476 <write barrier>
477 P = &B
478 Q = P;
479 <data dependency barrier>
480 D = *Q;
481
482This enforces the occurrence of one of the two implications, and prevents the
483third possibility from arising.
484
485[!] Note that this extremely counterintuitive situation arises most easily on
486machines with split caches, so that, for example, one cache bank processes
487even-numbered cache lines and the other bank processes odd-numbered cache
488lines. The pointer P might be stored in an odd-numbered cache line, and the
489variable B might be stored in an even-numbered cache line. Then, if the
490even-numbered bank of the reading CPU's cache is extremely busy while the
491odd-numbered bank is idle, one can see the new value of the pointer P (&B),
David Howells6bc39272006-06-25 05:49:22 -0700492but the old value of the variable B (2).
David Howells108b42b2006-03-31 16:00:29 +0100493
494
495Another example of where data dependency barriers might by required is where a
496number is read from memory and then used to calculate the index for an array
497access:
498
499 CPU 1 CPU 2
500 =============== ===============
501 { M[0] == 1, M[1] == 2, M[3] = 3, P == 0, Q == 3 }
502 M[1] = 4;
503 <write barrier>
504 P = 1
505 Q = P;
506 <data dependency barrier>
507 D = M[Q];
508
509
510The data dependency barrier is very important to the RCU system, for example.
511See rcu_dereference() in include/linux/rcupdate.h. This permits the current
512target of an RCU'd pointer to be replaced with a new modified target, without
513the replacement target appearing to be incompletely initialised.
514
515See also the subsection on "Cache Coherency" for a more thorough example.
516
517
518CONTROL DEPENDENCIES
519--------------------
520
521A control dependency requires a full read memory barrier, not simply a data
522dependency barrier to make it work correctly. Consider the following bit of
523code:
524
525 q = &a;
526 if (p)
527 q = &b;
528 <data dependency barrier>
529 x = *q;
530
531This will not have the desired effect because there is no actual data
532dependency, but rather a control dependency that the CPU may short-circuit by
533attempting to predict the outcome in advance. In such a case what's actually
534required is:
535
536 q = &a;
537 if (p)
538 q = &b;
539 <read barrier>
540 x = *q;
541
542
543SMP BARRIER PAIRING
544-------------------
545
546When dealing with CPU-CPU interactions, certain types of memory barrier should
547always be paired. A lack of appropriate pairing is almost certainly an error.
548
549A write barrier should always be paired with a data dependency barrier or read
550barrier, though a general barrier would also be viable. Similarly a read
551barrier or a data dependency barrier should always be paired with at least an
552write barrier, though, again, a general barrier is viable:
553
554 CPU 1 CPU 2
555 =============== ===============
556 a = 1;
557 <write barrier>
David Howells670bd952006-06-10 09:54:12 -0700558 b = 2; x = b;
David Howells108b42b2006-03-31 16:00:29 +0100559 <read barrier>
David Howells670bd952006-06-10 09:54:12 -0700560 y = a;
David Howells108b42b2006-03-31 16:00:29 +0100561
562Or:
563
564 CPU 1 CPU 2
565 =============== ===============================
566 a = 1;
567 <write barrier>
568 b = &a; x = b;
569 <data dependency barrier>
570 y = *x;
571
572Basically, the read barrier always has to be there, even though it can be of
573the "weaker" type.
574
David Howells670bd952006-06-10 09:54:12 -0700575[!] Note that the stores before the write barrier would normally be expected to
576match the loads after the read barrier or data dependency barrier, and vice
577versa:
578
579 CPU 1 CPU 2
580 =============== ===============
581 a = 1; }---- --->{ v = c
582 b = 2; } \ / { w = d
583 <write barrier> \ <read barrier>
584 c = 3; } / \ { x = a;
585 d = 4; }---- --->{ y = b;
586
David Howells108b42b2006-03-31 16:00:29 +0100587
588EXAMPLES OF MEMORY BARRIER SEQUENCES
589------------------------------------
590
591Firstly, write barriers act as a partial orderings on store operations.
592Consider the following sequence of events:
593
594 CPU 1
595 =======================
596 STORE A = 1
597 STORE B = 2
598 STORE C = 3
599 <write barrier>
600 STORE D = 4
601 STORE E = 5
602
603This sequence of events is committed to the memory coherence system in an order
604that the rest of the system might perceive as the unordered set of { STORE A,
605STORE B, STORE C } all occuring before the unordered set of { STORE D, STORE E
606}:
607
608 +-------+ : :
609 | | +------+
610 | |------>| C=3 | } /\
611 | | : +------+ }----- \ -----> Events perceptible
612 | | : | A=1 | } \/ to rest of system
613 | | : +------+ }
614 | CPU 1 | : | B=2 | }
615 | | +------+ }
616 | | wwwwwwwwwwwwwwww } <--- At this point the write barrier
617 | | +------+ } requires all stores prior to the
618 | | : | E=5 | } barrier to be committed before
619 | | : +------+ } further stores may be take place.
620 | |------>| D=4 | }
621 | | +------+
622 +-------+ : :
623 |
David Howells670bd952006-06-10 09:54:12 -0700624 | Sequence in which stores are committed to the
625 | memory system by CPU 1
David Howells108b42b2006-03-31 16:00:29 +0100626 V
627
628
629Secondly, data dependency barriers act as a partial orderings on data-dependent
630loads. Consider the following sequence of events:
631
632 CPU 1 CPU 2
633 ======================= =======================
David Howellsc14038c2006-04-10 22:54:24 -0700634 { B = 7; X = 9; Y = 8; C = &Y }
David Howells108b42b2006-03-31 16:00:29 +0100635 STORE A = 1
636 STORE B = 2
637 <write barrier>
638 STORE C = &B LOAD X
639 STORE D = 4 LOAD C (gets &B)
640 LOAD *C (reads B)
641
642Without intervention, CPU 2 may perceive the events on CPU 1 in some
643effectively random order, despite the write barrier issued by CPU 1:
644
645 +-------+ : : : :
646 | | +------+ +-------+ | Sequence of update
647 | |------>| B=2 |----- --->| Y->8 | | of perception on
648 | | : +------+ \ +-------+ | CPU 2
649 | CPU 1 | : | A=1 | \ --->| C->&Y | V
650 | | +------+ | +-------+
651 | | wwwwwwwwwwwwwwww | : :
652 | | +------+ | : :
653 | | : | C=&B |--- | : : +-------+
654 | | : +------+ \ | +-------+ | |
655 | |------>| D=4 | ----------->| C->&B |------>| |
656 | | +------+ | +-------+ | |
657 +-------+ : : | : : | |
658 | : : | |
659 | : : | CPU 2 |
660 | +-------+ | |
661 Apparently incorrect ---> | | B->7 |------>| |
662 perception of B (!) | +-------+ | |
663 | : : | |
664 | +-------+ | |
665 The load of X holds ---> \ | X->9 |------>| |
666 up the maintenance \ +-------+ | |
667 of coherence of B ----->| B->2 | +-------+
668 +-------+
669 : :
670
671
672In the above example, CPU 2 perceives that B is 7, despite the load of *C
673(which would be B) coming after the the LOAD of C.
674
675If, however, a data dependency barrier were to be placed between the load of C
David Howellsc14038c2006-04-10 22:54:24 -0700676and the load of *C (ie: B) on CPU 2:
677
678 CPU 1 CPU 2
679 ======================= =======================
680 { B = 7; X = 9; Y = 8; C = &Y }
681 STORE A = 1
682 STORE B = 2
683 <write barrier>
684 STORE C = &B LOAD X
685 STORE D = 4 LOAD C (gets &B)
686 <data dependency barrier>
687 LOAD *C (reads B)
688
689then the following will occur:
David Howells108b42b2006-03-31 16:00:29 +0100690
691 +-------+ : : : :
692 | | +------+ +-------+
693 | |------>| B=2 |----- --->| Y->8 |
694 | | : +------+ \ +-------+
695 | CPU 1 | : | A=1 | \ --->| C->&Y |
696 | | +------+ | +-------+
697 | | wwwwwwwwwwwwwwww | : :
698 | | +------+ | : :
699 | | : | C=&B |--- | : : +-------+
700 | | : +------+ \ | +-------+ | |
701 | |------>| D=4 | ----------->| C->&B |------>| |
702 | | +------+ | +-------+ | |
703 +-------+ : : | : : | |
704 | : : | |
705 | : : | CPU 2 |
706 | +-------+ | |
David Howells670bd952006-06-10 09:54:12 -0700707 | | X->9 |------>| |
708 | +-------+ | |
709 Makes sure all effects ---> \ ddddddddddddddddd | |
710 prior to the store of C \ +-------+ | |
711 are perceptible to ----->| B->2 |------>| |
712 subsequent loads +-------+ | |
David Howells108b42b2006-03-31 16:00:29 +0100713 : : +-------+
714
715
716And thirdly, a read barrier acts as a partial order on loads. Consider the
717following sequence of events:
718
719 CPU 1 CPU 2
720 ======================= =======================
David Howells670bd952006-06-10 09:54:12 -0700721 { A = 0, B = 9 }
David Howells108b42b2006-03-31 16:00:29 +0100722 STORE A=1
David Howells108b42b2006-03-31 16:00:29 +0100723 <write barrier>
David Howells670bd952006-06-10 09:54:12 -0700724 STORE B=2
David Howells108b42b2006-03-31 16:00:29 +0100725 LOAD B
David Howells670bd952006-06-10 09:54:12 -0700726 LOAD A
David Howells108b42b2006-03-31 16:00:29 +0100727
728Without intervention, CPU 2 may then choose to perceive the events on CPU 1 in
729some effectively random order, despite the write barrier issued by CPU 1:
730
David Howells670bd952006-06-10 09:54:12 -0700731 +-------+ : : : :
732 | | +------+ +-------+
733 | |------>| A=1 |------ --->| A->0 |
734 | | +------+ \ +-------+
735 | CPU 1 | wwwwwwwwwwwwwwww \ --->| B->9 |
736 | | +------+ | +-------+
737 | |------>| B=2 |--- | : :
738 | | +------+ \ | : : +-------+
739 +-------+ : : \ | +-------+ | |
740 ---------->| B->2 |------>| |
741 | +-------+ | CPU 2 |
742 | | A->0 |------>| |
743 | +-------+ | |
744 | : : +-------+
745 \ : :
746 \ +-------+
747 ---->| A->1 |
748 +-------+
749 : :
David Howells108b42b2006-03-31 16:00:29 +0100750
751
David Howells6bc39272006-06-25 05:49:22 -0700752If, however, a read barrier were to be placed between the load of B and the
David Howells670bd952006-06-10 09:54:12 -0700753load of A on CPU 2:
David Howells108b42b2006-03-31 16:00:29 +0100754
David Howells670bd952006-06-10 09:54:12 -0700755 CPU 1 CPU 2
756 ======================= =======================
757 { A = 0, B = 9 }
758 STORE A=1
759 <write barrier>
760 STORE B=2
761 LOAD B
762 <read barrier>
763 LOAD A
764
765then the partial ordering imposed by CPU 1 will be perceived correctly by CPU
7662:
767
768 +-------+ : : : :
769 | | +------+ +-------+
770 | |------>| A=1 |------ --->| A->0 |
771 | | +------+ \ +-------+
772 | CPU 1 | wwwwwwwwwwwwwwww \ --->| B->9 |
773 | | +------+ | +-------+
774 | |------>| B=2 |--- | : :
775 | | +------+ \ | : : +-------+
776 +-------+ : : \ | +-------+ | |
777 ---------->| B->2 |------>| |
778 | +-------+ | CPU 2 |
779 | : : | |
780 | : : | |
781 At this point the read ----> \ rrrrrrrrrrrrrrrrr | |
782 barrier causes all effects \ +-------+ | |
783 prior to the storage of B ---->| A->1 |------>| |
784 to be perceptible to CPU 2 +-------+ | |
785 : : +-------+
786
787
788To illustrate this more completely, consider what could happen if the code
789contained a load of A either side of the read barrier:
790
791 CPU 1 CPU 2
792 ======================= =======================
793 { A = 0, B = 9 }
794 STORE A=1
795 <write barrier>
796 STORE B=2
797 LOAD B
798 LOAD A [first load of A]
799 <read barrier>
800 LOAD A [second load of A]
801
802Even though the two loads of A both occur after the load of B, they may both
803come up with different values:
804
805 +-------+ : : : :
806 | | +------+ +-------+
807 | |------>| A=1 |------ --->| A->0 |
808 | | +------+ \ +-------+
809 | CPU 1 | wwwwwwwwwwwwwwww \ --->| B->9 |
810 | | +------+ | +-------+
811 | |------>| B=2 |--- | : :
812 | | +------+ \ | : : +-------+
813 +-------+ : : \ | +-------+ | |
814 ---------->| B->2 |------>| |
815 | +-------+ | CPU 2 |
816 | : : | |
817 | : : | |
818 | +-------+ | |
819 | | A->0 |------>| 1st |
820 | +-------+ | |
821 At this point the read ----> \ rrrrrrrrrrrrrrrrr | |
822 barrier causes all effects \ +-------+ | |
823 prior to the storage of B ---->| A->1 |------>| 2nd |
824 to be perceptible to CPU 2 +-------+ | |
825 : : +-------+
826
827
828But it may be that the update to A from CPU 1 becomes perceptible to CPU 2
829before the read barrier completes anyway:
830
831 +-------+ : : : :
832 | | +------+ +-------+
833 | |------>| A=1 |------ --->| A->0 |
834 | | +------+ \ +-------+
835 | CPU 1 | wwwwwwwwwwwwwwww \ --->| B->9 |
836 | | +------+ | +-------+
837 | |------>| B=2 |--- | : :
838 | | +------+ \ | : : +-------+
839 +-------+ : : \ | +-------+ | |
840 ---------->| B->2 |------>| |
841 | +-------+ | CPU 2 |
842 | : : | |
843 \ : : | |
844 \ +-------+ | |
845 ---->| A->1 |------>| 1st |
846 +-------+ | |
847 rrrrrrrrrrrrrrrrr | |
848 +-------+ | |
849 | A->1 |------>| 2nd |
850 +-------+ | |
851 : : +-------+
852
853
854The guarantee is that the second load will always come up with A == 1 if the
855load of B came up with B == 2. No such guarantee exists for the first load of
856A; that may come up with either A == 0 or A == 1.
857
858
859READ MEMORY BARRIERS VS LOAD SPECULATION
860----------------------------------------
861
862Many CPUs speculate with loads: that is they see that they will need to load an
863item from memory, and they find a time where they're not using the bus for any
864other loads, and so do the load in advance - even though they haven't actually
865got to that point in the instruction execution flow yet. This permits the
866actual load instruction to potentially complete immediately because the CPU
867already has the value to hand.
868
869It may turn out that the CPU didn't actually need the value - perhaps because a
870branch circumvented the load - in which case it can discard the value or just
871cache it for later use.
872
873Consider:
874
875 CPU 1 CPU 2
876 ======================= =======================
877 LOAD B
878 DIVIDE } Divide instructions generally
879 DIVIDE } take a long time to perform
880 LOAD A
881
882Which might appear as this:
883
884 : : +-------+
885 +-------+ | |
886 --->| B->2 |------>| |
887 +-------+ | CPU 2 |
888 : :DIVIDE | |
889 +-------+ | |
890 The CPU being busy doing a ---> --->| A->0 |~~~~ | |
891 division speculates on the +-------+ ~ | |
892 LOAD of A : : ~ | |
893 : :DIVIDE | |
894 : : ~ | |
895 Once the divisions are complete --> : : ~-->| |
896 the CPU can then perform the : : | |
897 LOAD with immediate effect : : +-------+
898
899
900Placing a read barrier or a data dependency barrier just before the second
901load:
902
903 CPU 1 CPU 2
904 ======================= =======================
905 LOAD B
906 DIVIDE
907 DIVIDE
908 <read barrier>
909 LOAD A
910
911will force any value speculatively obtained to be reconsidered to an extent
912dependent on the type of barrier used. If there was no change made to the
913speculated memory location, then the speculated value will just be used:
914
915 : : +-------+
916 +-------+ | |
917 --->| B->2 |------>| |
918 +-------+ | CPU 2 |
919 : :DIVIDE | |
920 +-------+ | |
921 The CPU being busy doing a ---> --->| A->0 |~~~~ | |
922 division speculates on the +-------+ ~ | |
923 LOAD of A : : ~ | |
924 : :DIVIDE | |
925 : : ~ | |
926 : : ~ | |
927 rrrrrrrrrrrrrrrr~ | |
928 : : ~ | |
929 : : ~-->| |
930 : : | |
931 : : +-------+
932
933
934but if there was an update or an invalidation from another CPU pending, then
935the speculation will be cancelled and the value reloaded:
936
937 : : +-------+
938 +-------+ | |
939 --->| B->2 |------>| |
940 +-------+ | CPU 2 |
941 : :DIVIDE | |
942 +-------+ | |
943 The CPU being busy doing a ---> --->| A->0 |~~~~ | |
944 division speculates on the +-------+ ~ | |
945 LOAD of A : : ~ | |
946 : :DIVIDE | |
947 : : ~ | |
948 : : ~ | |
949 rrrrrrrrrrrrrrrrr | |
950 +-------+ | |
951 The speculation is discarded ---> --->| A->1 |------>| |
952 and an updated value is +-------+ | |
953 retrieved : : +-------+
David Howells108b42b2006-03-31 16:00:29 +0100954
955
956========================
957EXPLICIT KERNEL BARRIERS
958========================
959
960The Linux kernel has a variety of different barriers that act at different
961levels:
962
963 (*) Compiler barrier.
964
965 (*) CPU memory barriers.
966
967 (*) MMIO write barrier.
968
969
970COMPILER BARRIER
971----------------
972
973The Linux kernel has an explicit compiler barrier function that prevents the
974compiler from moving the memory accesses either side of it to the other side:
975
976 barrier();
977
978This a general barrier - lesser varieties of compiler barrier do not exist.
979
980The compiler barrier has no direct effect on the CPU, which may then reorder
981things however it wishes.
982
983
984CPU MEMORY BARRIERS
985-------------------
986
987The Linux kernel has eight basic CPU memory barriers:
988
989 TYPE MANDATORY SMP CONDITIONAL
990 =============== ======================= ===========================
991 GENERAL mb() smp_mb()
992 WRITE wmb() smp_wmb()
993 READ rmb() smp_rmb()
994 DATA DEPENDENCY read_barrier_depends() smp_read_barrier_depends()
995
996
997All CPU memory barriers unconditionally imply compiler barriers.
998
999SMP memory barriers are reduced to compiler barriers on uniprocessor compiled
1000systems because it is assumed that a CPU will be appear to be self-consistent,
1001and will order overlapping accesses correctly with respect to itself.
1002
1003[!] Note that SMP memory barriers _must_ be used to control the ordering of
1004references to shared memory on SMP systems, though the use of locking instead
1005is sufficient.
1006
1007Mandatory barriers should not be used to control SMP effects, since mandatory
1008barriers unnecessarily impose overhead on UP systems. They may, however, be
1009used to control MMIO effects on accesses through relaxed memory I/O windows.
1010These are required even on non-SMP systems as they affect the order in which
1011memory operations appear to a device by prohibiting both the compiler and the
1012CPU from reordering them.
1013
1014
1015There are some more advanced barrier functions:
1016
1017 (*) set_mb(var, value)
1018 (*) set_wmb(var, value)
1019
1020 These assign the value to the variable and then insert at least a write
1021 barrier after it, depending on the function. They aren't guaranteed to
1022 insert anything more than a compiler barrier in a UP compilation.
1023
1024
1025 (*) smp_mb__before_atomic_dec();
1026 (*) smp_mb__after_atomic_dec();
1027 (*) smp_mb__before_atomic_inc();
1028 (*) smp_mb__after_atomic_inc();
1029
1030 These are for use with atomic add, subtract, increment and decrement
David Howellsdbc87002006-04-10 22:54:23 -07001031 functions that don't return a value, especially when used for reference
1032 counting. These functions do not imply memory barriers.
David Howells108b42b2006-03-31 16:00:29 +01001033
1034 As an example, consider a piece of code that marks an object as being dead
1035 and then decrements the object's reference count:
1036
1037 obj->dead = 1;
1038 smp_mb__before_atomic_dec();
1039 atomic_dec(&obj->ref_count);
1040
1041 This makes sure that the death mark on the object is perceived to be set
1042 *before* the reference counter is decremented.
1043
1044 See Documentation/atomic_ops.txt for more information. See the "Atomic
1045 operations" subsection for information on where to use these.
1046
1047
1048 (*) smp_mb__before_clear_bit(void);
1049 (*) smp_mb__after_clear_bit(void);
1050
1051 These are for use similar to the atomic inc/dec barriers. These are
1052 typically used for bitwise unlocking operations, so care must be taken as
1053 there are no implicit memory barriers here either.
1054
1055 Consider implementing an unlock operation of some nature by clearing a
1056 locking bit. The clear_bit() would then need to be barriered like this:
1057
1058 smp_mb__before_clear_bit();
1059 clear_bit( ... );
1060
1061 This prevents memory operations before the clear leaking to after it. See
1062 the subsection on "Locking Functions" with reference to UNLOCK operation
1063 implications.
1064
1065 See Documentation/atomic_ops.txt for more information. See the "Atomic
1066 operations" subsection for information on where to use these.
1067
1068
1069MMIO WRITE BARRIER
1070------------------
1071
1072The Linux kernel also has a special barrier for use with memory-mapped I/O
1073writes:
1074
1075 mmiowb();
1076
1077This is a variation on the mandatory write barrier that causes writes to weakly
1078ordered I/O regions to be partially ordered. Its effects may go beyond the
1079CPU->Hardware interface and actually affect the hardware at some level.
1080
1081See the subsection "Locks vs I/O accesses" for more information.
1082
1083
1084===============================
1085IMPLICIT KERNEL MEMORY BARRIERS
1086===============================
1087
1088Some of the other functions in the linux kernel imply memory barriers, amongst
David Howells670bd952006-06-10 09:54:12 -07001089which are locking and scheduling functions.
David Howells108b42b2006-03-31 16:00:29 +01001090
1091This specification is a _minimum_ guarantee; any particular architecture may
1092provide more substantial guarantees, but these may not be relied upon outside
1093of arch specific code.
1094
1095
1096LOCKING FUNCTIONS
1097-----------------
1098
1099The Linux kernel has a number of locking constructs:
1100
1101 (*) spin locks
1102 (*) R/W spin locks
1103 (*) mutexes
1104 (*) semaphores
1105 (*) R/W semaphores
1106 (*) RCU
1107
1108In all cases there are variants on "LOCK" operations and "UNLOCK" operations
1109for each construct. These operations all imply certain barriers:
1110
1111 (1) LOCK operation implication:
1112
1113 Memory operations issued after the LOCK will be completed after the LOCK
1114 operation has completed.
1115
1116 Memory operations issued before the LOCK may be completed after the LOCK
1117 operation has completed.
1118
1119 (2) UNLOCK operation implication:
1120
1121 Memory operations issued before the UNLOCK will be completed before the
1122 UNLOCK operation has completed.
1123
1124 Memory operations issued after the UNLOCK may be completed before the
1125 UNLOCK operation has completed.
1126
1127 (3) LOCK vs LOCK implication:
1128
1129 All LOCK operations issued before another LOCK operation will be completed
1130 before that LOCK operation.
1131
1132 (4) LOCK vs UNLOCK implication:
1133
1134 All LOCK operations issued before an UNLOCK operation will be completed
1135 before the UNLOCK operation.
1136
1137 All UNLOCK operations issued before a LOCK operation will be completed
1138 before the LOCK operation.
1139
1140 (5) Failed conditional LOCK implication:
1141
1142 Certain variants of the LOCK operation may fail, either due to being
1143 unable to get the lock immediately, or due to receiving an unblocked
1144 signal whilst asleep waiting for the lock to become available. Failed
1145 locks do not imply any sort of barrier.
1146
1147Therefore, from (1), (2) and (4) an UNLOCK followed by an unconditional LOCK is
1148equivalent to a full barrier, but a LOCK followed by an UNLOCK is not.
1149
1150[!] Note: one of the consequence of LOCKs and UNLOCKs being only one-way
1151 barriers is that the effects instructions outside of a critical section may
1152 seep into the inside of the critical section.
1153
David Howells670bd952006-06-10 09:54:12 -07001154A LOCK followed by an UNLOCK may not be assumed to be full memory barrier
1155because it is possible for an access preceding the LOCK to happen after the
1156LOCK, and an access following the UNLOCK to happen before the UNLOCK, and the
1157two accesses can themselves then cross:
1158
1159 *A = a;
1160 LOCK
1161 UNLOCK
1162 *B = b;
1163
1164may occur as:
1165
1166 LOCK, STORE *B, STORE *A, UNLOCK
1167
David Howells108b42b2006-03-31 16:00:29 +01001168Locks and semaphores may not provide any guarantee of ordering on UP compiled
1169systems, and so cannot be counted on in such a situation to actually achieve
1170anything at all - especially with respect to I/O accesses - unless combined
1171with interrupt disabling operations.
1172
1173See also the section on "Inter-CPU locking barrier effects".
1174
1175
1176As an example, consider the following:
1177
1178 *A = a;
1179 *B = b;
1180 LOCK
1181 *C = c;
1182 *D = d;
1183 UNLOCK
1184 *E = e;
1185 *F = f;
1186
1187The following sequence of events is acceptable:
1188
1189 LOCK, {*F,*A}, *E, {*C,*D}, *B, UNLOCK
1190
1191 [+] Note that {*F,*A} indicates a combined access.
1192
1193But none of the following are:
1194
1195 {*F,*A}, *B, LOCK, *C, *D, UNLOCK, *E
1196 *A, *B, *C, LOCK, *D, UNLOCK, *E, *F
1197 *A, *B, LOCK, *C, UNLOCK, *D, *E, *F
1198 *B, LOCK, *C, *D, UNLOCK, {*F,*A}, *E
1199
1200
1201
1202INTERRUPT DISABLING FUNCTIONS
1203-----------------------------
1204
1205Functions that disable interrupts (LOCK equivalent) and enable interrupts
1206(UNLOCK equivalent) will act as compiler barriers only. So if memory or I/O
1207barriers are required in such a situation, they must be provided from some
1208other means.
1209
1210
1211MISCELLANEOUS FUNCTIONS
1212-----------------------
1213
1214Other functions that imply barriers:
1215
1216 (*) schedule() and similar imply full memory barriers.
1217
David Howells108b42b2006-03-31 16:00:29 +01001218
1219=================================
1220INTER-CPU LOCKING BARRIER EFFECTS
1221=================================
1222
1223On SMP systems locking primitives give a more substantial form of barrier: one
1224that does affect memory access ordering on other CPUs, within the context of
1225conflict on any particular lock.
1226
1227
1228LOCKS VS MEMORY ACCESSES
1229------------------------
1230
Aneesh Kumar79afecf2006-05-15 09:44:36 -07001231Consider the following: the system has a pair of spinlocks (M) and (Q), and
David Howells108b42b2006-03-31 16:00:29 +01001232three CPUs; then should the following sequence of events occur:
1233
1234 CPU 1 CPU 2
1235 =============================== ===============================
1236 *A = a; *E = e;
1237 LOCK M LOCK Q
1238 *B = b; *F = f;
1239 *C = c; *G = g;
1240 UNLOCK M UNLOCK Q
1241 *D = d; *H = h;
1242
1243Then there is no guarantee as to what order CPU #3 will see the accesses to *A
1244through *H occur in, other than the constraints imposed by the separate locks
1245on the separate CPUs. It might, for example, see:
1246
1247 *E, LOCK M, LOCK Q, *G, *C, *F, *A, *B, UNLOCK Q, *D, *H, UNLOCK M
1248
1249But it won't see any of:
1250
1251 *B, *C or *D preceding LOCK M
1252 *A, *B or *C following UNLOCK M
1253 *F, *G or *H preceding LOCK Q
1254 *E, *F or *G following UNLOCK Q
1255
1256
1257However, if the following occurs:
1258
1259 CPU 1 CPU 2
1260 =============================== ===============================
1261 *A = a;
1262 LOCK M [1]
1263 *B = b;
1264 *C = c;
1265 UNLOCK M [1]
1266 *D = d; *E = e;
1267 LOCK M [2]
1268 *F = f;
1269 *G = g;
1270 UNLOCK M [2]
1271 *H = h;
1272
1273CPU #3 might see:
1274
1275 *E, LOCK M [1], *C, *B, *A, UNLOCK M [1],
1276 LOCK M [2], *H, *F, *G, UNLOCK M [2], *D
1277
1278But assuming CPU #1 gets the lock first, it won't see any of:
1279
1280 *B, *C, *D, *F, *G or *H preceding LOCK M [1]
1281 *A, *B or *C following UNLOCK M [1]
1282 *F, *G or *H preceding LOCK M [2]
1283 *A, *B, *C, *E, *F or *G following UNLOCK M [2]
1284
1285
1286LOCKS VS I/O ACCESSES
1287---------------------
1288
1289Under certain circumstances (especially involving NUMA), I/O accesses within
1290two spinlocked sections on two different CPUs may be seen as interleaved by the
1291PCI bridge, because the PCI bridge does not necessarily participate in the
1292cache-coherence protocol, and is therefore incapable of issuing the required
1293read memory barriers.
1294
1295For example:
1296
1297 CPU 1 CPU 2
1298 =============================== ===============================
1299 spin_lock(Q)
1300 writel(0, ADDR)
1301 writel(1, DATA);
1302 spin_unlock(Q);
1303 spin_lock(Q);
1304 writel(4, ADDR);
1305 writel(5, DATA);
1306 spin_unlock(Q);
1307
1308may be seen by the PCI bridge as follows:
1309
1310 STORE *ADDR = 0, STORE *ADDR = 4, STORE *DATA = 1, STORE *DATA = 5
1311
1312which would probably cause the hardware to malfunction.
1313
1314
1315What is necessary here is to intervene with an mmiowb() before dropping the
1316spinlock, for example:
1317
1318 CPU 1 CPU 2
1319 =============================== ===============================
1320 spin_lock(Q)
1321 writel(0, ADDR)
1322 writel(1, DATA);
1323 mmiowb();
1324 spin_unlock(Q);
1325 spin_lock(Q);
1326 writel(4, ADDR);
1327 writel(5, DATA);
1328 mmiowb();
1329 spin_unlock(Q);
1330
1331this will ensure that the two stores issued on CPU #1 appear at the PCI bridge
1332before either of the stores issued on CPU #2.
1333
1334
1335Furthermore, following a store by a load to the same device obviates the need
1336for an mmiowb(), because the load forces the store to complete before the load
1337is performed:
1338
1339 CPU 1 CPU 2
1340 =============================== ===============================
1341 spin_lock(Q)
1342 writel(0, ADDR)
1343 a = readl(DATA);
1344 spin_unlock(Q);
1345 spin_lock(Q);
1346 writel(4, ADDR);
1347 b = readl(DATA);
1348 spin_unlock(Q);
1349
1350
1351See Documentation/DocBook/deviceiobook.tmpl for more information.
1352
1353
1354=================================
1355WHERE ARE MEMORY BARRIERS NEEDED?
1356=================================
1357
1358Under normal operation, memory operation reordering is generally not going to
1359be a problem as a single-threaded linear piece of code will still appear to
1360work correctly, even if it's in an SMP kernel. There are, however, three
1361circumstances in which reordering definitely _could_ be a problem:
1362
1363 (*) Interprocessor interaction.
1364
1365 (*) Atomic operations.
1366
1367 (*) Accessing devices (I/O).
1368
1369 (*) Interrupts.
1370
1371
1372INTERPROCESSOR INTERACTION
1373--------------------------
1374
1375When there's a system with more than one processor, more than one CPU in the
1376system may be working on the same data set at the same time. This can cause
1377synchronisation problems, and the usual way of dealing with them is to use
1378locks. Locks, however, are quite expensive, and so it may be preferable to
1379operate without the use of a lock if at all possible. In such a case
1380operations that affect both CPUs may have to be carefully ordered to prevent
1381a malfunction.
1382
1383Consider, for example, the R/W semaphore slow path. Here a waiting process is
1384queued on the semaphore, by virtue of it having a piece of its stack linked to
1385the semaphore's list of waiting processes:
1386
1387 struct rw_semaphore {
1388 ...
1389 spinlock_t lock;
1390 struct list_head waiters;
1391 };
1392
1393 struct rwsem_waiter {
1394 struct list_head list;
1395 struct task_struct *task;
1396 };
1397
1398To wake up a particular waiter, the up_read() or up_write() functions have to:
1399
1400 (1) read the next pointer from this waiter's record to know as to where the
1401 next waiter record is;
1402
1403 (4) read the pointer to the waiter's task structure;
1404
1405 (3) clear the task pointer to tell the waiter it has been given the semaphore;
1406
1407 (4) call wake_up_process() on the task; and
1408
1409 (5) release the reference held on the waiter's task struct.
1410
1411In otherwords, it has to perform this sequence of events:
1412
1413 LOAD waiter->list.next;
1414 LOAD waiter->task;
1415 STORE waiter->task;
1416 CALL wakeup
1417 RELEASE task
1418
1419and if any of these steps occur out of order, then the whole thing may
1420malfunction.
1421
1422Once it has queued itself and dropped the semaphore lock, the waiter does not
1423get the lock again; it instead just waits for its task pointer to be cleared
1424before proceeding. Since the record is on the waiter's stack, this means that
1425if the task pointer is cleared _before_ the next pointer in the list is read,
1426another CPU might start processing the waiter and might clobber the waiter's
1427stack before the up*() function has a chance to read the next pointer.
1428
1429Consider then what might happen to the above sequence of events:
1430
1431 CPU 1 CPU 2
1432 =============================== ===============================
1433 down_xxx()
1434 Queue waiter
1435 Sleep
1436 up_yyy()
1437 LOAD waiter->task;
1438 STORE waiter->task;
1439 Woken up by other event
1440 <preempt>
1441 Resume processing
1442 down_xxx() returns
1443 call foo()
1444 foo() clobbers *waiter
1445 </preempt>
1446 LOAD waiter->list.next;
1447 --- OOPS ---
1448
1449This could be dealt with using the semaphore lock, but then the down_xxx()
1450function has to needlessly get the spinlock again after being woken up.
1451
1452The way to deal with this is to insert a general SMP memory barrier:
1453
1454 LOAD waiter->list.next;
1455 LOAD waiter->task;
1456 smp_mb();
1457 STORE waiter->task;
1458 CALL wakeup
1459 RELEASE task
1460
1461In this case, the barrier makes a guarantee that all memory accesses before the
1462barrier will appear to happen before all the memory accesses after the barrier
1463with respect to the other CPUs on the system. It does _not_ guarantee that all
1464the memory accesses before the barrier will be complete by the time the barrier
1465instruction itself is complete.
1466
1467On a UP system - where this wouldn't be a problem - the smp_mb() is just a
1468compiler barrier, thus making sure the compiler emits the instructions in the
David Howells6bc39272006-06-25 05:49:22 -07001469right order without actually intervening in the CPU. Since there's only one
1470CPU, that CPU's dependency ordering logic will take care of everything else.
David Howells108b42b2006-03-31 16:00:29 +01001471
1472
1473ATOMIC OPERATIONS
1474-----------------
1475
David Howellsdbc87002006-04-10 22:54:23 -07001476Whilst they are technically interprocessor interaction considerations, atomic
1477operations are noted specially as some of them imply full memory barriers and
1478some don't, but they're very heavily relied on as a group throughout the
1479kernel.
1480
1481Any atomic operation that modifies some state in memory and returns information
1482about the state (old or new) implies an SMP-conditional general memory barrier
1483(smp_mb()) on each side of the actual operation. These include:
David Howells108b42b2006-03-31 16:00:29 +01001484
1485 xchg();
1486 cmpxchg();
David Howells108b42b2006-03-31 16:00:29 +01001487 atomic_cmpxchg();
1488 atomic_inc_return();
1489 atomic_dec_return();
1490 atomic_add_return();
1491 atomic_sub_return();
1492 atomic_inc_and_test();
1493 atomic_dec_and_test();
1494 atomic_sub_and_test();
1495 atomic_add_negative();
1496 atomic_add_unless();
David Howellsdbc87002006-04-10 22:54:23 -07001497 test_and_set_bit();
1498 test_and_clear_bit();
1499 test_and_change_bit();
David Howells108b42b2006-03-31 16:00:29 +01001500
David Howellsdbc87002006-04-10 22:54:23 -07001501These are used for such things as implementing LOCK-class and UNLOCK-class
1502operations and adjusting reference counters towards object destruction, and as
1503such the implicit memory barrier effects are necessary.
David Howells108b42b2006-03-31 16:00:29 +01001504
David Howells108b42b2006-03-31 16:00:29 +01001505
David Howellsdbc87002006-04-10 22:54:23 -07001506The following operation are potential problems as they do _not_ imply memory
1507barriers, but might be used for implementing such things as UNLOCK-class
1508operations:
1509
1510 atomic_set();
David Howells108b42b2006-03-31 16:00:29 +01001511 set_bit();
1512 clear_bit();
1513 change_bit();
David Howellsdbc87002006-04-10 22:54:23 -07001514
1515With these the appropriate explicit memory barrier should be used if necessary
1516(smp_mb__before_clear_bit() for instance).
David Howells108b42b2006-03-31 16:00:29 +01001517
1518
David Howellsdbc87002006-04-10 22:54:23 -07001519The following also do _not_ imply memory barriers, and so may require explicit
1520memory barriers under some circumstances (smp_mb__before_atomic_dec() for
1521instance)):
David Howells108b42b2006-03-31 16:00:29 +01001522
1523 atomic_add();
1524 atomic_sub();
1525 atomic_inc();
1526 atomic_dec();
1527
1528If they're used for statistics generation, then they probably don't need memory
1529barriers, unless there's a coupling between statistical data.
1530
1531If they're used for reference counting on an object to control its lifetime,
1532they probably don't need memory barriers because either the reference count
1533will be adjusted inside a locked section, or the caller will already hold
1534sufficient references to make the lock, and thus a memory barrier unnecessary.
1535
1536If they're used for constructing a lock of some description, then they probably
1537do need memory barriers as a lock primitive generally has to do things in a
1538specific order.
1539
1540
1541Basically, each usage case has to be carefully considered as to whether memory
David Howellsdbc87002006-04-10 22:54:23 -07001542barriers are needed or not.
1543
1544[!] Note that special memory barrier primitives are available for these
1545situations because on some CPUs the atomic instructions used imply full memory
1546barriers, and so barrier instructions are superfluous in conjunction with them,
1547and in such cases the special barrier primitives will be no-ops.
David Howells108b42b2006-03-31 16:00:29 +01001548
1549See Documentation/atomic_ops.txt for more information.
1550
1551
1552ACCESSING DEVICES
1553-----------------
1554
1555Many devices can be memory mapped, and so appear to the CPU as if they're just
1556a set of memory locations. To control such a device, the driver usually has to
1557make the right memory accesses in exactly the right order.
1558
1559However, having a clever CPU or a clever compiler creates a potential problem
1560in that the carefully sequenced accesses in the driver code won't reach the
1561device in the requisite order if the CPU or the compiler thinks it is more
1562efficient to reorder, combine or merge accesses - something that would cause
1563the device to malfunction.
1564
1565Inside of the Linux kernel, I/O should be done through the appropriate accessor
1566routines - such as inb() or writel() - which know how to make such accesses
1567appropriately sequential. Whilst this, for the most part, renders the explicit
1568use of memory barriers unnecessary, there are a couple of situations where they
1569might be needed:
1570
1571 (1) On some systems, I/O stores are not strongly ordered across all CPUs, and
1572 so for _all_ general drivers locks should be used and mmiowb() must be
1573 issued prior to unlocking the critical section.
1574
1575 (2) If the accessor functions are used to refer to an I/O memory window with
1576 relaxed memory access properties, then _mandatory_ memory barriers are
1577 required to enforce ordering.
1578
1579See Documentation/DocBook/deviceiobook.tmpl for more information.
1580
1581
1582INTERRUPTS
1583----------
1584
1585A driver may be interrupted by its own interrupt service routine, and thus the
1586two parts of the driver may interfere with each other's attempts to control or
1587access the device.
1588
1589This may be alleviated - at least in part - by disabling local interrupts (a
1590form of locking), such that the critical operations are all contained within
1591the interrupt-disabled section in the driver. Whilst the driver's interrupt
1592routine is executing, the driver's core may not run on the same CPU, and its
1593interrupt is not permitted to happen again until the current interrupt has been
1594handled, thus the interrupt handler does not need to lock against that.
1595
1596However, consider a driver that was talking to an ethernet card that sports an
1597address register and a data register. If that driver's core talks to the card
1598under interrupt-disablement and then the driver's interrupt handler is invoked:
1599
1600 LOCAL IRQ DISABLE
1601 writew(ADDR, 3);
1602 writew(DATA, y);
1603 LOCAL IRQ ENABLE
1604 <interrupt>
1605 writew(ADDR, 4);
1606 q = readw(DATA);
1607 </interrupt>
1608
1609The store to the data register might happen after the second store to the
1610address register if ordering rules are sufficiently relaxed:
1611
1612 STORE *ADDR = 3, STORE *ADDR = 4, STORE *DATA = y, q = LOAD *DATA
1613
1614
1615If ordering rules are relaxed, it must be assumed that accesses done inside an
1616interrupt disabled section may leak outside of it and may interleave with
1617accesses performed in an interrupt - and vice versa - unless implicit or
1618explicit barriers are used.
1619
1620Normally this won't be a problem because the I/O accesses done inside such
1621sections will include synchronous load operations on strictly ordered I/O
1622registers that form implicit I/O barriers. If this isn't sufficient then an
1623mmiowb() may need to be used explicitly.
1624
1625
1626A similar situation may occur between an interrupt routine and two routines
1627running on separate CPUs that communicate with each other. If such a case is
1628likely, then interrupt-disabling locks should be used to guarantee ordering.
1629
1630
1631==========================
1632KERNEL I/O BARRIER EFFECTS
1633==========================
1634
1635When accessing I/O memory, drivers should use the appropriate accessor
1636functions:
1637
1638 (*) inX(), outX():
1639
1640 These are intended to talk to I/O space rather than memory space, but
1641 that's primarily a CPU-specific concept. The i386 and x86_64 processors do
1642 indeed have special I/O space access cycles and instructions, but many
1643 CPUs don't have such a concept.
1644
1645 The PCI bus, amongst others, defines an I/O space concept - which on such
1646 CPUs as i386 and x86_64 cpus readily maps to the CPU's concept of I/O
David Howells6bc39272006-06-25 05:49:22 -07001647 space. However, it may also be mapped as a virtual I/O space in the CPU's
1648 memory map, particularly on those CPUs that don't support alternate I/O
1649 spaces.
David Howells108b42b2006-03-31 16:00:29 +01001650
1651 Accesses to this space may be fully synchronous (as on i386), but
1652 intermediary bridges (such as the PCI host bridge) may not fully honour
1653 that.
1654
1655 They are guaranteed to be fully ordered with respect to each other.
1656
1657 They are not guaranteed to be fully ordered with respect to other types of
1658 memory and I/O operation.
1659
1660 (*) readX(), writeX():
1661
1662 Whether these are guaranteed to be fully ordered and uncombined with
1663 respect to each other on the issuing CPU depends on the characteristics
1664 defined for the memory window through which they're accessing. On later
1665 i386 architecture machines, for example, this is controlled by way of the
1666 MTRR registers.
1667
1668 Ordinarily, these will be guaranteed to be fully ordered and uncombined,,
1669 provided they're not accessing a prefetchable device.
1670
1671 However, intermediary hardware (such as a PCI bridge) may indulge in
1672 deferral if it so wishes; to flush a store, a load from the same location
1673 is preferred[*], but a load from the same device or from configuration
1674 space should suffice for PCI.
1675
1676 [*] NOTE! attempting to load from the same location as was written to may
1677 cause a malfunction - consider the 16550 Rx/Tx serial registers for
1678 example.
1679
1680 Used with prefetchable I/O memory, an mmiowb() barrier may be required to
1681 force stores to be ordered.
1682
1683 Please refer to the PCI specification for more information on interactions
1684 between PCI transactions.
1685
1686 (*) readX_relaxed()
1687
1688 These are similar to readX(), but are not guaranteed to be ordered in any
1689 way. Be aware that there is no I/O read barrier available.
1690
1691 (*) ioreadX(), iowriteX()
1692
1693 These will perform as appropriate for the type of access they're actually
1694 doing, be it inX()/outX() or readX()/writeX().
1695
1696
1697========================================
1698ASSUMED MINIMUM EXECUTION ORDERING MODEL
1699========================================
1700
1701It has to be assumed that the conceptual CPU is weakly-ordered but that it will
1702maintain the appearance of program causality with respect to itself. Some CPUs
1703(such as i386 or x86_64) are more constrained than others (such as powerpc or
1704frv), and so the most relaxed case (namely DEC Alpha) must be assumed outside
1705of arch-specific code.
1706
1707This means that it must be considered that the CPU will execute its instruction
1708stream in any order it feels like - or even in parallel - provided that if an
1709instruction in the stream depends on the an earlier instruction, then that
1710earlier instruction must be sufficiently complete[*] before the later
1711instruction may proceed; in other words: provided that the appearance of
1712causality is maintained.
1713
1714 [*] Some instructions have more than one effect - such as changing the
1715 condition codes, changing registers or changing memory - and different
1716 instructions may depend on different effects.
1717
1718A CPU may also discard any instruction sequence that winds up having no
1719ultimate effect. For example, if two adjacent instructions both load an
1720immediate value into the same register, the first may be discarded.
1721
1722
1723Similarly, it has to be assumed that compiler might reorder the instruction
1724stream in any way it sees fit, again provided the appearance of causality is
1725maintained.
1726
1727
1728============================
1729THE EFFECTS OF THE CPU CACHE
1730============================
1731
1732The way cached memory operations are perceived across the system is affected to
1733a certain extent by the caches that lie between CPUs and memory, and by the
1734memory coherence system that maintains the consistency of state in the system.
1735
1736As far as the way a CPU interacts with another part of the system through the
1737caches goes, the memory system has to include the CPU's caches, and memory
1738barriers for the most part act at the interface between the CPU and its cache
1739(memory barriers logically act on the dotted line in the following diagram):
1740
1741 <--- CPU ---> : <----------- Memory ----------->
1742 :
1743 +--------+ +--------+ : +--------+ +-----------+
1744 | | | | : | | | | +--------+
1745 | CPU | | Memory | : | CPU | | | | |
1746 | Core |--->| Access |----->| Cache |<-->| | | |
1747 | | | Queue | : | | | |--->| Memory |
1748 | | | | : | | | | | |
1749 +--------+ +--------+ : +--------+ | | | |
1750 : | Cache | +--------+
1751 : | Coherency |
1752 : | Mechanism | +--------+
1753 +--------+ +--------+ : +--------+ | | | |
1754 | | | | : | | | | | |
1755 | CPU | | Memory | : | CPU | | |--->| Device |
1756 | Core |--->| Access |----->| Cache |<-->| | | |
1757 | | | Queue | : | | | | | |
1758 | | | | : | | | | +--------+
1759 +--------+ +--------+ : +--------+ +-----------+
1760 :
1761 :
1762
1763Although any particular load or store may not actually appear outside of the
1764CPU that issued it since it may have been satisfied within the CPU's own cache,
1765it will still appear as if the full memory access had taken place as far as the
1766other CPUs are concerned since the cache coherency mechanisms will migrate the
1767cacheline over to the accessing CPU and propagate the effects upon conflict.
1768
1769The CPU core may execute instructions in any order it deems fit, provided the
1770expected program causality appears to be maintained. Some of the instructions
1771generate load and store operations which then go into the queue of memory
1772accesses to be performed. The core may place these in the queue in any order
1773it wishes, and continue execution until it is forced to wait for an instruction
1774to complete.
1775
1776What memory barriers are concerned with is controlling the order in which
1777accesses cross from the CPU side of things to the memory side of things, and
1778the order in which the effects are perceived to happen by the other observers
1779in the system.
1780
1781[!] Memory barriers are _not_ needed within a given CPU, as CPUs always see
1782their own loads and stores as if they had happened in program order.
1783
1784[!] MMIO or other device accesses may bypass the cache system. This depends on
1785the properties of the memory window through which devices are accessed and/or
1786the use of any special device communication instructions the CPU may have.
1787
1788
1789CACHE COHERENCY
1790---------------
1791
1792Life isn't quite as simple as it may appear above, however: for while the
1793caches are expected to be coherent, there's no guarantee that that coherency
1794will be ordered. This means that whilst changes made on one CPU will
1795eventually become visible on all CPUs, there's no guarantee that they will
1796become apparent in the same order on those other CPUs.
1797
1798
1799Consider dealing with a system that has pair of CPUs (1 & 2), each of which has
1800a pair of parallel data caches (CPU 1 has A/B, and CPU 2 has C/D):
1801
1802 :
1803 : +--------+
1804 : +---------+ | |
1805 +--------+ : +--->| Cache A |<------->| |
1806 | | : | +---------+ | |
1807 | CPU 1 |<---+ | |
1808 | | : | +---------+ | |
1809 +--------+ : +--->| Cache B |<------->| |
1810 : +---------+ | |
1811 : | Memory |
1812 : +---------+ | System |
1813 +--------+ : +--->| Cache C |<------->| |
1814 | | : | +---------+ | |
1815 | CPU 2 |<---+ | |
1816 | | : | +---------+ | |
1817 +--------+ : +--->| Cache D |<------->| |
1818 : +---------+ | |
1819 : +--------+
1820 :
1821
1822Imagine the system has the following properties:
1823
1824 (*) an odd-numbered cache line may be in cache A, cache C or it may still be
1825 resident in memory;
1826
1827 (*) an even-numbered cache line may be in cache B, cache D or it may still be
1828 resident in memory;
1829
1830 (*) whilst the CPU core is interrogating one cache, the other cache may be
1831 making use of the bus to access the rest of the system - perhaps to
1832 displace a dirty cacheline or to do a speculative load;
1833
1834 (*) each cache has a queue of operations that need to be applied to that cache
1835 to maintain coherency with the rest of the system;
1836
1837 (*) the coherency queue is not flushed by normal loads to lines already
1838 present in the cache, even though the contents of the queue may
1839 potentially effect those loads.
1840
1841Imagine, then, that two writes are made on the first CPU, with a write barrier
1842between them to guarantee that they will appear to reach that CPU's caches in
1843the requisite order:
1844
1845 CPU 1 CPU 2 COMMENT
1846 =============== =============== =======================================
1847 u == 0, v == 1 and p == &u, q == &u
1848 v = 2;
1849 smp_wmb(); Make sure change to v visible before
1850 change to p
1851 <A:modify v=2> v is now in cache A exclusively
1852 p = &v;
1853 <B:modify p=&v> p is now in cache B exclusively
1854
1855The write memory barrier forces the other CPUs in the system to perceive that
1856the local CPU's caches have apparently been updated in the correct order. But
1857now imagine that the second CPU that wants to read those values:
1858
1859 CPU 1 CPU 2 COMMENT
1860 =============== =============== =======================================
1861 ...
1862 q = p;
1863 x = *q;
1864
1865The above pair of reads may then fail to happen in expected order, as the
1866cacheline holding p may get updated in one of the second CPU's caches whilst
1867the update to the cacheline holding v is delayed in the other of the second
1868CPU's caches by some other cache event:
1869
1870 CPU 1 CPU 2 COMMENT
1871 =============== =============== =======================================
1872 u == 0, v == 1 and p == &u, q == &u
1873 v = 2;
1874 smp_wmb();
1875 <A:modify v=2> <C:busy>
1876 <C:queue v=2>
Aneesh Kumar79afecf2006-05-15 09:44:36 -07001877 p = &v; q = p;
David Howells108b42b2006-03-31 16:00:29 +01001878 <D:request p>
1879 <B:modify p=&v> <D:commit p=&v>
1880 <D:read p>
1881 x = *q;
1882 <C:read *q> Reads from v before v updated in cache
1883 <C:unbusy>
1884 <C:commit v=2>
1885
1886Basically, whilst both cachelines will be updated on CPU 2 eventually, there's
1887no guarantee that, without intervention, the order of update will be the same
1888as that committed on CPU 1.
1889
1890
1891To intervene, we need to interpolate a data dependency barrier or a read
1892barrier between the loads. This will force the cache to commit its coherency
1893queue before processing any further requests:
1894
1895 CPU 1 CPU 2 COMMENT
1896 =============== =============== =======================================
1897 u == 0, v == 1 and p == &u, q == &u
1898 v = 2;
1899 smp_wmb();
1900 <A:modify v=2> <C:busy>
1901 <C:queue v=2>
1902 p = &b; q = p;
1903 <D:request p>
1904 <B:modify p=&v> <D:commit p=&v>
1905 <D:read p>
1906 smp_read_barrier_depends()
1907 <C:unbusy>
1908 <C:commit v=2>
1909 x = *q;
1910 <C:read *q> Reads from v after v updated in cache
1911
1912
1913This sort of problem can be encountered on DEC Alpha processors as they have a
1914split cache that improves performance by making better use of the data bus.
1915Whilst most CPUs do imply a data dependency barrier on the read when a memory
1916access depends on a read, not all do, so it may not be relied on.
1917
1918Other CPUs may also have split caches, but must coordinate between the various
1919cachelets for normal memory accesss. The semantics of the Alpha removes the
1920need for coordination in absence of memory barriers.
1921
1922
1923CACHE COHERENCY VS DMA
1924----------------------
1925
1926Not all systems maintain cache coherency with respect to devices doing DMA. In
1927such cases, a device attempting DMA may obtain stale data from RAM because
1928dirty cache lines may be resident in the caches of various CPUs, and may not
1929have been written back to RAM yet. To deal with this, the appropriate part of
1930the kernel must flush the overlapping bits of cache on each CPU (and maybe
1931invalidate them as well).
1932
1933In addition, the data DMA'd to RAM by a device may be overwritten by dirty
1934cache lines being written back to RAM from a CPU's cache after the device has
1935installed its own data, or cache lines simply present in a CPUs cache may
1936simply obscure the fact that RAM has been updated, until at such time as the
1937cacheline is discarded from the CPU's cache and reloaded. To deal with this,
1938the appropriate part of the kernel must invalidate the overlapping bits of the
1939cache on each CPU.
1940
1941See Documentation/cachetlb.txt for more information on cache management.
1942
1943
1944CACHE COHERENCY VS MMIO
1945-----------------------
1946
1947Memory mapped I/O usually takes place through memory locations that are part of
1948a window in the CPU's memory space that have different properties assigned than
1949the usual RAM directed window.
1950
1951Amongst these properties is usually the fact that such accesses bypass the
1952caching entirely and go directly to the device buses. This means MMIO accesses
1953may, in effect, overtake accesses to cached memory that were emitted earlier.
1954A memory barrier isn't sufficient in such a case, but rather the cache must be
1955flushed between the cached memory write and the MMIO access if the two are in
1956any way dependent.
1957
1958
1959=========================
1960THE THINGS CPUS GET UP TO
1961=========================
1962
1963A programmer might take it for granted that the CPU will perform memory
1964operations in exactly the order specified, so that if a CPU is, for example,
1965given the following piece of code to execute:
1966
1967 a = *A;
1968 *B = b;
1969 c = *C;
1970 d = *D;
1971 *E = e;
1972
1973They would then expect that the CPU will complete the memory operation for each
1974instruction before moving on to the next one, leading to a definite sequence of
1975operations as seen by external observers in the system:
1976
1977 LOAD *A, STORE *B, LOAD *C, LOAD *D, STORE *E.
1978
1979
1980Reality is, of course, much messier. With many CPUs and compilers, the above
1981assumption doesn't hold because:
1982
1983 (*) loads are more likely to need to be completed immediately to permit
1984 execution progress, whereas stores can often be deferred without a
1985 problem;
1986
1987 (*) loads may be done speculatively, and the result discarded should it prove
1988 to have been unnecessary;
1989
1990 (*) loads may be done speculatively, leading to the result having being
1991 fetched at the wrong time in the expected sequence of events;
1992
1993 (*) the order of the memory accesses may be rearranged to promote better use
1994 of the CPU buses and caches;
1995
1996 (*) loads and stores may be combined to improve performance when talking to
1997 memory or I/O hardware that can do batched accesses of adjacent locations,
1998 thus cutting down on transaction setup costs (memory and PCI devices may
1999 both be able to do this); and
2000
2001 (*) the CPU's data cache may affect the ordering, and whilst cache-coherency
2002 mechanisms may alleviate this - once the store has actually hit the cache
2003 - there's no guarantee that the coherency management will be propagated in
2004 order to other CPUs.
2005
2006So what another CPU, say, might actually observe from the above piece of code
2007is:
2008
2009 LOAD *A, ..., LOAD {*C,*D}, STORE *E, STORE *B
2010
2011 (Where "LOAD {*C,*D}" is a combined load)
2012
2013
2014However, it is guaranteed that a CPU will be self-consistent: it will see its
2015_own_ accesses appear to be correctly ordered, without the need for a memory
2016barrier. For instance with the following code:
2017
2018 U = *A;
2019 *A = V;
2020 *A = W;
2021 X = *A;
2022 *A = Y;
2023 Z = *A;
2024
2025and assuming no intervention by an external influence, it can be assumed that
2026the final result will appear to be:
2027
2028 U == the original value of *A
2029 X == W
2030 Z == Y
2031 *A == Y
2032
2033The code above may cause the CPU to generate the full sequence of memory
2034accesses:
2035
2036 U=LOAD *A, STORE *A=V, STORE *A=W, X=LOAD *A, STORE *A=Y, Z=LOAD *A
2037
2038in that order, but, without intervention, the sequence may have almost any
2039combination of elements combined or discarded, provided the program's view of
2040the world remains consistent.
2041
2042The compiler may also combine, discard or defer elements of the sequence before
2043the CPU even sees them.
2044
2045For instance:
2046
2047 *A = V;
2048 *A = W;
2049
2050may be reduced to:
2051
2052 *A = W;
2053
2054since, without a write barrier, it can be assumed that the effect of the
2055storage of V to *A is lost. Similarly:
2056
2057 *A = Y;
2058 Z = *A;
2059
2060may, without a memory barrier, be reduced to:
2061
2062 *A = Y;
2063 Z = Y;
2064
2065and the LOAD operation never appear outside of the CPU.
2066
2067
2068AND THEN THERE'S THE ALPHA
2069--------------------------
2070
2071The DEC Alpha CPU is one of the most relaxed CPUs there is. Not only that,
2072some versions of the Alpha CPU have a split data cache, permitting them to have
2073two semantically related cache lines updating at separate times. This is where
2074the data dependency barrier really becomes necessary as this synchronises both
2075caches with the memory coherence system, thus making it seem like pointer
2076changes vs new data occur in the right order.
2077
2078The Alpha defines the Linux's kernel's memory barrier model.
2079
2080See the subsection on "Cache Coherency" above.
2081
2082
2083==========
2084REFERENCES
2085==========
2086
2087Alpha AXP Architecture Reference Manual, Second Edition (Sites & Witek,
2088Digital Press)
2089 Chapter 5.2: Physical Address Space Characteristics
2090 Chapter 5.4: Caches and Write Buffers
2091 Chapter 5.5: Data Sharing
2092 Chapter 5.6: Read/Write Ordering
2093
2094AMD64 Architecture Programmer's Manual Volume 2: System Programming
2095 Chapter 7.1: Memory-Access Ordering
2096 Chapter 7.4: Buffering and Combining Memory Writes
2097
2098IA-32 Intel Architecture Software Developer's Manual, Volume 3:
2099System Programming Guide
2100 Chapter 7.1: Locked Atomic Operations
2101 Chapter 7.2: Memory Ordering
2102 Chapter 7.4: Serializing Instructions
2103
2104The SPARC Architecture Manual, Version 9
2105 Chapter 8: Memory Models
2106 Appendix D: Formal Specification of the Memory Models
2107 Appendix J: Programming with the Memory Models
2108
2109UltraSPARC Programmer Reference Manual
2110 Chapter 5: Memory Accesses and Cacheability
2111 Chapter 15: Sparc-V9 Memory Models
2112
2113UltraSPARC III Cu User's Manual
2114 Chapter 9: Memory Models
2115
2116UltraSPARC IIIi Processor User's Manual
2117 Chapter 8: Memory Models
2118
2119UltraSPARC Architecture 2005
2120 Chapter 9: Memory
2121 Appendix D: Formal Specifications of the Memory Models
2122
2123UltraSPARC T1 Supplement to the UltraSPARC Architecture 2005
2124 Chapter 8: Memory Models
2125 Appendix F: Caches and Cache Coherency
2126
2127Solaris Internals, Core Kernel Architecture, p63-68:
2128 Chapter 3.3: Hardware Considerations for Locks and
2129 Synchronization
2130
2131Unix Systems for Modern Architectures, Symmetric Multiprocessing and Caching
2132for Kernel Programmers:
2133 Chapter 13: Other Memory Models
2134
2135Intel Itanium Architecture Software Developer's Manual: Volume 1:
2136 Section 2.6: Speculation
2137 Section 4.4: Memory Access