1<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" 2 "http://www.w3.org/TR/html4/loose.dtd"> 3 <html> 4 <head><title>A Tour Through RCU's Requirements [LWN.net]</title> 5 <meta HTTP-EQUIV="Content-Type" CONTENT="text/html; charset=utf-8"> 6 7<h1>A Tour Through RCU's Requirements</h1> 8 9<p>Copyright IBM Corporation, 2015</p> 10<p>Author: Paul E. McKenney</p> 11<p><i>The initial version of this document appeared in the 12<a href="https://lwn.net/">LWN</a> articles 13<a href="https://lwn.net/Articles/652156/">here</a>, 14<a href="https://lwn.net/Articles/652677/">here</a>, and 15<a href="https://lwn.net/Articles/653326/">here</a>.</i></p> 16 17<h2>Introduction</h2> 18 19<p> 20Read-copy update (RCU) is a synchronization mechanism that is often 21used as a replacement for reader-writer locking. 22RCU is unusual in that updaters do not block readers, 23which means that RCU's read-side primitives can be exceedingly fast 24and scalable. 25In addition, updaters can make useful forward progress concurrently 26with readers. 27However, all this concurrency between RCU readers and updaters does raise 28the question of exactly what RCU readers are doing, which in turn 29raises the question of exactly what RCU's requirements are. 30 31<p> 32This document therefore summarizes RCU's requirements, and can be thought 33of as an informal, high-level specification for RCU. 34It is important to understand that RCU's specification is primarily 35empirical in nature; 36in fact, I learned about many of these requirements the hard way. 37This situation might cause some consternation, however, not only 38has this learning process been a lot of fun, but it has also been 39a great privilege to work with so many people willing to apply 40technologies in interesting new ways. 41 42<p> 43All that aside, here are the categories of currently known RCU requirements: 44</p> 45 46<ol> 47<li> <a href="#Fundamental Requirements"> 48 Fundamental Requirements</a> 49<li> <a href="#Fundamental Non-Requirements">Fundamental Non-Requirements</a> 50<li> <a href="#Parallelism Facts of Life"> 51 Parallelism Facts of Life</a> 52<li> <a href="#Quality-of-Implementation Requirements"> 53 Quality-of-Implementation Requirements</a> 54<li> <a href="#Linux Kernel Complications"> 55 Linux Kernel Complications</a> 56<li> <a href="#Software-Engineering Requirements"> 57 Software-Engineering Requirements</a> 58<li> <a href="#Other RCU Flavors"> 59 Other RCU Flavors</a> 60<li> <a href="#Possible Future Changes"> 61 Possible Future Changes</a> 62</ol> 63 64<p> 65This is followed by a <a href="#Summary">summary</a>, 66however, the answers to each quick quiz immediately follows the quiz. 67Select the big white space with your mouse to see the answer. 68 69<h2><a name="Fundamental Requirements">Fundamental Requirements</a></h2> 70 71<p> 72RCU's fundamental requirements are the closest thing RCU has to hard 73mathematical requirements. 74These are: 75 76<ol> 77<li> <a href="#Grace-Period Guarantee"> 78 Grace-Period Guarantee</a> 79<li> <a href="#Publish-Subscribe Guarantee"> 80 Publish-Subscribe Guarantee</a> 81<li> <a href="#Memory-Barrier Guarantees"> 82 Memory-Barrier Guarantees</a> 83<li> <a href="#RCU Primitives Guaranteed to Execute Unconditionally"> 84 RCU Primitives Guaranteed to Execute Unconditionally</a> 85<li> <a href="#Guaranteed Read-to-Write Upgrade"> 86 Guaranteed Read-to-Write Upgrade</a> 87</ol> 88 89<h3><a name="Grace-Period Guarantee">Grace-Period Guarantee</a></h3> 90 91<p> 92RCU's grace-period guarantee is unusual in being premeditated: 93Jack Slingwine and I had this guarantee firmly in mind when we started 94work on RCU (then called “rclock”) in the early 1990s. 95That said, the past two decades of experience with RCU have produced 96a much more detailed understanding of this guarantee. 97 98<p> 99RCU's grace-period guarantee allows updaters to wait for the completion 100of all pre-existing RCU read-side critical sections. 101An RCU read-side critical section 102begins with the marker <tt>rcu_read_lock()</tt> and ends with 103the marker <tt>rcu_read_unlock()</tt>. 104These markers may be nested, and RCU treats a nested set as one 105big RCU read-side critical section. 106Production-quality implementations of <tt>rcu_read_lock()</tt> and 107<tt>rcu_read_unlock()</tt> are extremely lightweight, and in 108fact have exactly zero overhead in Linux kernels built for production 109use with <tt>CONFIG_PREEMPT=n</tt>. 110 111<p> 112This guarantee allows ordering to be enforced with extremely low 113overhead to readers, for example: 114 115<blockquote> 116<pre> 117 1 int x, y; 118 2 119 3 void thread0(void) 120 4 { 121 5 rcu_read_lock(); 122 6 r1 = READ_ONCE(x); 123 7 r2 = READ_ONCE(y); 124 8 rcu_read_unlock(); 125 9 } 12610 12711 void thread1(void) 12812 { 12913 WRITE_ONCE(x, 1); 13014 synchronize_rcu(); 13115 WRITE_ONCE(y, 1); 13216 } 133</pre> 134</blockquote> 135 136<p> 137Because the <tt>synchronize_rcu()</tt> on line 14 waits for 138all pre-existing readers, any instance of <tt>thread0()</tt> that 139loads a value of zero from <tt>x</tt> must complete before 140<tt>thread1()</tt> stores to <tt>y</tt>, so that instance must 141also load a value of zero from <tt>y</tt>. 142Similarly, any instance of <tt>thread0()</tt> that loads a value of 143one from <tt>y</tt> must have started after the 144<tt>synchronize_rcu()</tt> started, and must therefore also load 145a value of one from <tt>x</tt>. 146Therefore, the outcome: 147<blockquote> 148<pre> 149(r1 == 0 && r2 == 1) 150</pre> 151</blockquote> 152cannot happen. 153 154<table> 155<tr><th> </th></tr> 156<tr><th align="left">Quick Quiz:</th></tr> 157<tr><td> 158 Wait a minute! 159 You said that updaters can make useful forward progress concurrently 160 with readers, but pre-existing readers will block 161 <tt>synchronize_rcu()</tt>!!! 162 Just who are you trying to fool??? 163</td></tr> 164<tr><th align="left">Answer:</th></tr> 165<tr><td bgcolor="#ffffff"><font color="ffffff"> 166 First, if updaters do not wish to be blocked by readers, they can use 167 <tt>call_rcu()</tt> or <tt>kfree_rcu()</tt>, which will 168 be discussed later. 169 Second, even when using <tt>synchronize_rcu()</tt>, the other 170 update-side code does run concurrently with readers, whether 171 pre-existing or not. 172</font></td></tr> 173<tr><td> </td></tr> 174</table> 175 176<p> 177This scenario resembles one of the first uses of RCU in 178<a href="https://en.wikipedia.org/wiki/DYNIX">DYNIX/ptx</a>, 179which managed a distributed lock manager's transition into 180a state suitable for handling recovery from node failure, 181more or less as follows: 182 183<blockquote> 184<pre> 185 1 #define STATE_NORMAL 0 186 2 #define STATE_WANT_RECOVERY 1 187 3 #define STATE_RECOVERING 2 188 4 #define STATE_WANT_NORMAL 3 189 5 190 6 int state = STATE_NORMAL; 191 7 192 8 void do_something_dlm(void) 193 9 { 19410 int state_snap; 19511 19612 rcu_read_lock(); 19713 state_snap = READ_ONCE(state); 19814 if (state_snap == STATE_NORMAL) 19915 do_something(); 20016 else 20117 do_something_carefully(); 20218 rcu_read_unlock(); 20319 } 20420 20521 void start_recovery(void) 20622 { 20723 WRITE_ONCE(state, STATE_WANT_RECOVERY); 20824 synchronize_rcu(); 20925 WRITE_ONCE(state, STATE_RECOVERING); 21026 recovery(); 21127 WRITE_ONCE(state, STATE_WANT_NORMAL); 21228 synchronize_rcu(); 21329 WRITE_ONCE(state, STATE_NORMAL); 21430 } 215</pre> 216</blockquote> 217 218<p> 219The RCU read-side critical section in <tt>do_something_dlm()</tt> 220works with the <tt>synchronize_rcu()</tt> in <tt>start_recovery()</tt> 221to guarantee that <tt>do_something()</tt> never runs concurrently 222with <tt>recovery()</tt>, but with little or no synchronization 223overhead in <tt>do_something_dlm()</tt>. 224 225<table> 226<tr><th> </th></tr> 227<tr><th align="left">Quick Quiz:</th></tr> 228<tr><td> 229 Why is the <tt>synchronize_rcu()</tt> on line 28 needed? 230</td></tr> 231<tr><th align="left">Answer:</th></tr> 232<tr><td bgcolor="#ffffff"><font color="ffffff"> 233 Without that extra grace period, memory reordering could result in 234 <tt>do_something_dlm()</tt> executing <tt>do_something()</tt> 235 concurrently with the last bits of <tt>recovery()</tt>. 236</font></td></tr> 237<tr><td> </td></tr> 238</table> 239 240<p> 241In order to avoid fatal problems such as deadlocks, 242an RCU read-side critical section must not contain calls to 243<tt>synchronize_rcu()</tt>. 244Similarly, an RCU read-side critical section must not 245contain anything that waits, directly or indirectly, on completion of 246an invocation of <tt>synchronize_rcu()</tt>. 247 248<p> 249Although RCU's grace-period guarantee is useful in and of itself, with 250<a href="https://lwn.net/Articles/573497/">quite a few use cases</a>, 251it would be good to be able to use RCU to coordinate read-side 252access to linked data structures. 253For this, the grace-period guarantee is not sufficient, as can 254be seen in function <tt>add_gp_buggy()</tt> below. 255We will look at the reader's code later, but in the meantime, just think of 256the reader as locklessly picking up the <tt>gp</tt> pointer, 257and, if the value loaded is non-<tt>NULL</tt>, locklessly accessing the 258<tt>->a</tt> and <tt>->b</tt> fields. 259 260<blockquote> 261<pre> 262 1 bool add_gp_buggy(int a, int b) 263 2 { 264 3 p = kmalloc(sizeof(*p), GFP_KERNEL); 265 4 if (!p) 266 5 return -ENOMEM; 267 6 spin_lock(&gp_lock); 268 7 if (rcu_access_pointer(gp)) { 269 8 spin_unlock(&gp_lock); 270 9 return false; 27110 } 27211 p->a = a; 27312 p->b = a; 27413 gp = p; /* ORDERING BUG */ 27514 spin_unlock(&gp_lock); 27615 return true; 27716 } 278</pre> 279</blockquote> 280 281<p> 282The problem is that both the compiler and weakly ordered CPUs are within 283their rights to reorder this code as follows: 284 285<blockquote> 286<pre> 287 1 bool add_gp_buggy_optimized(int a, int b) 288 2 { 289 3 p = kmalloc(sizeof(*p), GFP_KERNEL); 290 4 if (!p) 291 5 return -ENOMEM; 292 6 spin_lock(&gp_lock); 293 7 if (rcu_access_pointer(gp)) { 294 8 spin_unlock(&gp_lock); 295 9 return false; 29610 } 297<b>11 gp = p; /* ORDERING BUG */ 29812 p->a = a; 29913 p->b = a;</b> 30014 spin_unlock(&gp_lock); 30115 return true; 30216 } 303</pre> 304</blockquote> 305 306<p> 307If an RCU reader fetches <tt>gp</tt> just after 308<tt>add_gp_buggy_optimized</tt> executes line 11, 309it will see garbage in the <tt>->a</tt> and <tt>->b</tt> 310fields. 311And this is but one of many ways in which compiler and hardware optimizations 312could cause trouble. 313Therefore, we clearly need some way to prevent the compiler and the CPU from 314reordering in this manner, which brings us to the publish-subscribe 315guarantee discussed in the next section. 316 317<h3><a name="Publish-Subscribe Guarantee">Publish/Subscribe Guarantee</a></h3> 318 319<p> 320RCU's publish-subscribe guarantee allows data to be inserted 321into a linked data structure without disrupting RCU readers. 322The updater uses <tt>rcu_assign_pointer()</tt> to insert the 323new data, and readers use <tt>rcu_dereference()</tt> to 324access data, whether new or old. 325The following shows an example of insertion: 326 327<blockquote> 328<pre> 329 1 bool add_gp(int a, int b) 330 2 { 331 3 p = kmalloc(sizeof(*p), GFP_KERNEL); 332 4 if (!p) 333 5 return -ENOMEM; 334 6 spin_lock(&gp_lock); 335 7 if (rcu_access_pointer(gp)) { 336 8 spin_unlock(&gp_lock); 337 9 return false; 33810 } 33911 p->a = a; 34012 p->b = a; 34113 rcu_assign_pointer(gp, p); 34214 spin_unlock(&gp_lock); 34315 return true; 34416 } 345</pre> 346</blockquote> 347 348<p> 349The <tt>rcu_assign_pointer()</tt> on line 13 is conceptually 350equivalent to a simple assignment statement, but also guarantees 351that its assignment will 352happen after the two assignments in lines 11 and 12, 353similar to the C11 <tt>memory_order_release</tt> store operation. 354It also prevents any number of “interesting” compiler 355optimizations, for example, the use of <tt>gp</tt> as a scratch 356location immediately preceding the assignment. 357 358<table> 359<tr><th> </th></tr> 360<tr><th align="left">Quick Quiz:</th></tr> 361<tr><td> 362 But <tt>rcu_assign_pointer()</tt> does nothing to prevent the 363 two assignments to <tt>p->a</tt> and <tt>p->b</tt> 364 from being reordered. 365 Can't that also cause problems? 366</td></tr> 367<tr><th align="left">Answer:</th></tr> 368<tr><td bgcolor="#ffffff"><font color="ffffff"> 369 No, it cannot. 370 The readers cannot see either of these two fields until 371 the assignment to <tt>gp</tt>, by which time both fields are 372 fully initialized. 373 So reordering the assignments 374 to <tt>p->a</tt> and <tt>p->b</tt> cannot possibly 375 cause any problems. 376</font></td></tr> 377<tr><td> </td></tr> 378</table> 379 380<p> 381It is tempting to assume that the reader need not do anything special 382to control its accesses to the RCU-protected data, 383as shown in <tt>do_something_gp_buggy()</tt> below: 384 385<blockquote> 386<pre> 387 1 bool do_something_gp_buggy(void) 388 2 { 389 3 rcu_read_lock(); 390 4 p = gp; /* OPTIMIZATIONS GALORE!!! */ 391 5 if (p) { 392 6 do_something(p->a, p->b); 393 7 rcu_read_unlock(); 394 8 return true; 395 9 } 39610 rcu_read_unlock(); 39711 return false; 39812 } 399</pre> 400</blockquote> 401 402<p> 403However, this temptation must be resisted because there are a 404surprisingly large number of ways that the compiler 405(to say nothing of 406<a href="https://h71000.www7.hp.com/wizard/wiz_2637.html">DEC Alpha CPUs</a>) 407can trip this code up. 408For but one example, if the compiler were short of registers, it 409might choose to refetch from <tt>gp</tt> rather than keeping 410a separate copy in <tt>p</tt> as follows: 411 412<blockquote> 413<pre> 414 1 bool do_something_gp_buggy_optimized(void) 415 2 { 416 3 rcu_read_lock(); 417 4 if (gp) { /* OPTIMIZATIONS GALORE!!! */ 418<b> 5 do_something(gp->a, gp->b);</b> 419 6 rcu_read_unlock(); 420 7 return true; 421 8 } 422 9 rcu_read_unlock(); 42310 return false; 42411 } 425</pre> 426</blockquote> 427 428<p> 429If this function ran concurrently with a series of updates that 430replaced the current structure with a new one, 431the fetches of <tt>gp->a</tt> 432and <tt>gp->b</tt> might well come from two different structures, 433which could cause serious confusion. 434To prevent this (and much else besides), <tt>do_something_gp()</tt> uses 435<tt>rcu_dereference()</tt> to fetch from <tt>gp</tt>: 436 437<blockquote> 438<pre> 439 1 bool do_something_gp(void) 440 2 { 441 3 rcu_read_lock(); 442 4 p = rcu_dereference(gp); 443 5 if (p) { 444 6 do_something(p->a, p->b); 445 7 rcu_read_unlock(); 446 8 return true; 447 9 } 44810 rcu_read_unlock(); 44911 return false; 45012 } 451</pre> 452</blockquote> 453 454<p> 455The <tt>rcu_dereference()</tt> uses volatile casts and (for DEC Alpha) 456memory barriers in the Linux kernel. 457Should a 458<a href="http://www.rdrop.com/users/paulmck/RCU/consume.2015.07.13a.pdf">high-quality implementation of C11 <tt>memory_order_consume</tt> [PDF]</a> 459ever appear, then <tt>rcu_dereference()</tt> could be implemented 460as a <tt>memory_order_consume</tt> load. 461Regardless of the exact implementation, a pointer fetched by 462<tt>rcu_dereference()</tt> may not be used outside of the 463outermost RCU read-side critical section containing that 464<tt>rcu_dereference()</tt>, unless protection of 465the corresponding data element has been passed from RCU to some 466other synchronization mechanism, most commonly locking or 467<a href="https://www.kernel.org/doc/Documentation/RCU/rcuref.txt">reference counting</a>. 468 469<p> 470In short, updaters use <tt>rcu_assign_pointer()</tt> and readers 471use <tt>rcu_dereference()</tt>, and these two RCU API elements 472work together to ensure that readers have a consistent view of 473newly added data elements. 474 475<p> 476Of course, it is also necessary to remove elements from RCU-protected 477data structures, for example, using the following process: 478 479<ol> 480<li> Remove the data element from the enclosing structure. 481<li> Wait for all pre-existing RCU read-side critical sections 482 to complete (because only pre-existing readers can possibly have 483 a reference to the newly removed data element). 484<li> At this point, only the updater has a reference to the 485 newly removed data element, so it can safely reclaim 486 the data element, for example, by passing it to <tt>kfree()</tt>. 487</ol> 488 489This process is implemented by <tt>remove_gp_synchronous()</tt>: 490 491<blockquote> 492<pre> 493 1 bool remove_gp_synchronous(void) 494 2 { 495 3 struct foo *p; 496 4 497 5 spin_lock(&gp_lock); 498 6 p = rcu_access_pointer(gp); 499 7 if (!p) { 500 8 spin_unlock(&gp_lock); 501 9 return false; 50210 } 50311 rcu_assign_pointer(gp, NULL); 50412 spin_unlock(&gp_lock); 50513 synchronize_rcu(); 50614 kfree(p); 50715 return true; 50816 } 509</pre> 510</blockquote> 511 512<p> 513This function is straightforward, with line 13 waiting for a grace 514period before line 14 frees the old data element. 515This waiting ensures that readers will reach line 7 of 516<tt>do_something_gp()</tt> before the data element referenced by 517<tt>p</tt> is freed. 518The <tt>rcu_access_pointer()</tt> on line 6 is similar to 519<tt>rcu_dereference()</tt>, except that: 520 521<ol> 522<li> The value returned by <tt>rcu_access_pointer()</tt> 523 cannot be dereferenced. 524 If you want to access the value pointed to as well as 525 the pointer itself, use <tt>rcu_dereference()</tt> 526 instead of <tt>rcu_access_pointer()</tt>. 527<li> The call to <tt>rcu_access_pointer()</tt> need not be 528 protected. 529 In contrast, <tt>rcu_dereference()</tt> must either be 530 within an RCU read-side critical section or in a code 531 segment where the pointer cannot change, for example, in 532 code protected by the corresponding update-side lock. 533</ol> 534 535<table> 536<tr><th> </th></tr> 537<tr><th align="left">Quick Quiz:</th></tr> 538<tr><td> 539 Without the <tt>rcu_dereference()</tt> or the 540 <tt>rcu_access_pointer()</tt>, what destructive optimizations 541 might the compiler make use of? 542</td></tr> 543<tr><th align="left">Answer:</th></tr> 544<tr><td bgcolor="#ffffff"><font color="ffffff"> 545 Let's start with what happens to <tt>do_something_gp()</tt> 546 if it fails to use <tt>rcu_dereference()</tt>. 547 It could reuse a value formerly fetched from this same pointer. 548 It could also fetch the pointer from <tt>gp</tt> in a byte-at-a-time 549 manner, resulting in <i>load tearing</i>, in turn resulting a bytewise 550 mash-up of two distinct pointer values. 551 It might even use value-speculation optimizations, where it makes 552 a wrong guess, but by the time it gets around to checking the 553 value, an update has changed the pointer to match the wrong guess. 554 Too bad about any dereferences that returned pre-initialization garbage 555 in the meantime! 556 </font> 557 558 <p><font color="ffffff"> 559 For <tt>remove_gp_synchronous()</tt>, as long as all modifications 560 to <tt>gp</tt> are carried out while holding <tt>gp_lock</tt>, 561 the above optimizations are harmless. 562 However, <tt>sparse</tt> will complain if you 563 define <tt>gp</tt> with <tt>__rcu</tt> and then 564 access it without using 565 either <tt>rcu_access_pointer()</tt> or <tt>rcu_dereference()</tt>. 566</font></td></tr> 567<tr><td> </td></tr> 568</table> 569 570<p> 571In short, RCU's publish-subscribe guarantee is provided by the combination 572of <tt>rcu_assign_pointer()</tt> and <tt>rcu_dereference()</tt>. 573This guarantee allows data elements to be safely added to RCU-protected 574linked data structures without disrupting RCU readers. 575This guarantee can be used in combination with the grace-period 576guarantee to also allow data elements to be removed from RCU-protected 577linked data structures, again without disrupting RCU readers. 578 579<p> 580This guarantee was only partially premeditated. 581DYNIX/ptx used an explicit memory barrier for publication, but had nothing 582resembling <tt>rcu_dereference()</tt> for subscription, nor did it 583have anything resembling the <tt>smp_read_barrier_depends()</tt> 584that was later subsumed into <tt>rcu_dereference()</tt>. 585The need for these operations made itself known quite suddenly at a 586late-1990s meeting with the DEC Alpha architects, back in the days when 587DEC was still a free-standing company. 588It took the Alpha architects a good hour to convince me that any sort 589of barrier would ever be needed, and it then took me a good <i>two</i> hours 590to convince them that their documentation did not make this point clear. 591More recent work with the C and C++ standards committees have provided 592much education on tricks and traps from the compiler. 593In short, compilers were much less tricky in the early 1990s, but in 5942015, don't even think about omitting <tt>rcu_dereference()</tt>! 595 596<h3><a name="Memory-Barrier Guarantees">Memory-Barrier Guarantees</a></h3> 597 598<p> 599The previous section's simple linked-data-structure scenario clearly 600demonstrates the need for RCU's stringent memory-ordering guarantees on 601systems with more than one CPU: 602 603<ol> 604<li> Each CPU that has an RCU read-side critical section that 605 begins before <tt>synchronize_rcu()</tt> starts is 606 guaranteed to execute a full memory barrier between the time 607 that the RCU read-side critical section ends and the time that 608 <tt>synchronize_rcu()</tt> returns. 609 Without this guarantee, a pre-existing RCU read-side critical section 610 might hold a reference to the newly removed <tt>struct foo</tt> 611 after the <tt>kfree()</tt> on line 14 of 612 <tt>remove_gp_synchronous()</tt>. 613<li> Each CPU that has an RCU read-side critical section that ends 614 after <tt>synchronize_rcu()</tt> returns is guaranteed 615 to execute a full memory barrier between the time that 616 <tt>synchronize_rcu()</tt> begins and the time that the RCU 617 read-side critical section begins. 618 Without this guarantee, a later RCU read-side critical section 619 running after the <tt>kfree()</tt> on line 14 of 620 <tt>remove_gp_synchronous()</tt> might 621 later run <tt>do_something_gp()</tt> and find the 622 newly deleted <tt>struct foo</tt>. 623<li> If the task invoking <tt>synchronize_rcu()</tt> remains 624 on a given CPU, then that CPU is guaranteed to execute a full 625 memory barrier sometime during the execution of 626 <tt>synchronize_rcu()</tt>. 627 This guarantee ensures that the <tt>kfree()</tt> on 628 line 14 of <tt>remove_gp_synchronous()</tt> really does 629 execute after the removal on line 11. 630<li> If the task invoking <tt>synchronize_rcu()</tt> migrates 631 among a group of CPUs during that invocation, then each of the 632 CPUs in that group is guaranteed to execute a full memory barrier 633 sometime during the execution of <tt>synchronize_rcu()</tt>. 634 This guarantee also ensures that the <tt>kfree()</tt> on 635 line 14 of <tt>remove_gp_synchronous()</tt> really does 636 execute after the removal on 637 line 11, but also in the case where the thread executing the 638 <tt>synchronize_rcu()</tt> migrates in the meantime. 639</ol> 640 641<table> 642<tr><th> </th></tr> 643<tr><th align="left">Quick Quiz:</th></tr> 644<tr><td> 645 Given that multiple CPUs can start RCU read-side critical sections 646 at any time without any ordering whatsoever, how can RCU possibly 647 tell whether or not a given RCU read-side critical section starts 648 before a given instance of <tt>synchronize_rcu()</tt>? 649</td></tr> 650<tr><th align="left">Answer:</th></tr> 651<tr><td bgcolor="#ffffff"><font color="ffffff"> 652 If RCU cannot tell whether or not a given 653 RCU read-side critical section starts before a 654 given instance of <tt>synchronize_rcu()</tt>, 655 then it must assume that the RCU read-side critical section 656 started first. 657 In other words, a given instance of <tt>synchronize_rcu()</tt> 658 can avoid waiting on a given RCU read-side critical section only 659 if it can prove that <tt>synchronize_rcu()</tt> started first. 660 </font> 661 662 <p><font color="ffffff"> 663 A related question is “When <tt>rcu_read_lock()</tt> 664 doesn't generate any code, why does it matter how it relates 665 to a grace period?” 666 The answer is that it is not the relationship of 667 <tt>rcu_read_lock()</tt> itself that is important, but rather 668 the relationship of the code within the enclosed RCU read-side 669 critical section to the code preceding and following the 670 grace period. 671 If we take this viewpoint, then a given RCU read-side critical 672 section begins before a given grace period when some access 673 preceding the grace period observes the effect of some access 674 within the critical section, in which case none of the accesses 675 within the critical section may observe the effects of any 676 access following the grace period. 677 </font> 678 679 <p><font color="ffffff"> 680 As of late 2016, mathematical models of RCU take this 681 viewpoint, for example, see slides 62 and 63 682 of the 683 <a href="http://www2.rdrop.com/users/paulmck/scalability/paper/LinuxMM.2016.10.04c.LCE.pdf">2016 LinuxCon EU</a> 684 presentation. 685</font></td></tr> 686<tr><td> </td></tr> 687</table> 688 689<table> 690<tr><th> </th></tr> 691<tr><th align="left">Quick Quiz:</th></tr> 692<tr><td> 693 The first and second guarantees require unbelievably strict ordering! 694 Are all these memory barriers <i> really</i> required? 695</td></tr> 696<tr><th align="left">Answer:</th></tr> 697<tr><td bgcolor="#ffffff"><font color="ffffff"> 698 Yes, they really are required. 699 To see why the first guarantee is required, consider the following 700 sequence of events: 701 </font> 702 703 <ol> 704 <li> <font color="ffffff"> 705 CPU 1: <tt>rcu_read_lock()</tt> 706 </font> 707 <li> <font color="ffffff"> 708 CPU 1: <tt>q = rcu_dereference(gp); 709 /* Very likely to return p. */</tt> 710 </font> 711 <li> <font color="ffffff"> 712 CPU 0: <tt>list_del_rcu(p);</tt> 713 </font> 714 <li> <font color="ffffff"> 715 CPU 0: <tt>synchronize_rcu()</tt> starts. 716 </font> 717 <li> <font color="ffffff"> 718 CPU 1: <tt>do_something_with(q->a); 719 /* No smp_mb(), so might happen after kfree(). */</tt> 720 </font> 721 <li> <font color="ffffff"> 722 CPU 1: <tt>rcu_read_unlock()</tt> 723 </font> 724 <li> <font color="ffffff"> 725 CPU 0: <tt>synchronize_rcu()</tt> returns. 726 </font> 727 <li> <font color="ffffff"> 728 CPU 0: <tt>kfree(p);</tt> 729 </font> 730 </ol> 731 732 <p><font color="ffffff"> 733 Therefore, there absolutely must be a full memory barrier between the 734 end of the RCU read-side critical section and the end of the 735 grace period. 736 </font> 737 738 <p><font color="ffffff"> 739 The sequence of events demonstrating the necessity of the second rule 740 is roughly similar: 741 </font> 742 743 <ol> 744 <li> <font color="ffffff">CPU 0: <tt>list_del_rcu(p);</tt> 745 </font> 746 <li> <font color="ffffff">CPU 0: <tt>synchronize_rcu()</tt> starts. 747 </font> 748 <li> <font color="ffffff">CPU 1: <tt>rcu_read_lock()</tt> 749 </font> 750 <li> <font color="ffffff">CPU 1: <tt>q = rcu_dereference(gp); 751 /* Might return p if no memory barrier. */</tt> 752 </font> 753 <li> <font color="ffffff">CPU 0: <tt>synchronize_rcu()</tt> returns. 754 </font> 755 <li> <font color="ffffff">CPU 0: <tt>kfree(p);</tt> 756 </font> 757 <li> <font color="ffffff"> 758 CPU 1: <tt>do_something_with(q->a); /* Boom!!! */</tt> 759 </font> 760 <li> <font color="ffffff">CPU 1: <tt>rcu_read_unlock()</tt> 761 </font> 762 </ol> 763 764 <p><font color="ffffff"> 765 And similarly, without a memory barrier between the beginning of the 766 grace period and the beginning of the RCU read-side critical section, 767 CPU 1 might end up accessing the freelist. 768 </font> 769 770 <p><font color="ffffff"> 771 The “as if” rule of course applies, so that any 772 implementation that acts as if the appropriate memory barriers 773 were in place is a correct implementation. 774 That said, it is much easier to fool yourself into believing 775 that you have adhered to the as-if rule than it is to actually 776 adhere to it! 777</font></td></tr> 778<tr><td> </td></tr> 779</table> 780 781<table> 782<tr><th> </th></tr> 783<tr><th align="left">Quick Quiz:</th></tr> 784<tr><td> 785 You claim that <tt>rcu_read_lock()</tt> and <tt>rcu_read_unlock()</tt> 786 generate absolutely no code in some kernel builds. 787 This means that the compiler might arbitrarily rearrange consecutive 788 RCU read-side critical sections. 789 Given such rearrangement, if a given RCU read-side critical section 790 is done, how can you be sure that all prior RCU read-side critical 791 sections are done? 792 Won't the compiler rearrangements make that impossible to determine? 793</td></tr> 794<tr><th align="left">Answer:</th></tr> 795<tr><td bgcolor="#ffffff"><font color="ffffff"> 796 In cases where <tt>rcu_read_lock()</tt> and <tt>rcu_read_unlock()</tt> 797 generate absolutely no code, RCU infers quiescent states only at 798 special locations, for example, within the scheduler. 799 Because calls to <tt>schedule()</tt> had better prevent calling-code 800 accesses to shared variables from being rearranged across the call to 801 <tt>schedule()</tt>, if RCU detects the end of a given RCU read-side 802 critical section, it will necessarily detect the end of all prior 803 RCU read-side critical sections, no matter how aggressively the 804 compiler scrambles the code. 805 </font> 806 807 <p><font color="ffffff"> 808 Again, this all assumes that the compiler cannot scramble code across 809 calls to the scheduler, out of interrupt handlers, into the idle loop, 810 into user-mode code, and so on. 811 But if your kernel build allows that sort of scrambling, you have broken 812 far more than just RCU! 813</font></td></tr> 814<tr><td> </td></tr> 815</table> 816 817<p> 818Note that these memory-barrier requirements do not replace the fundamental 819RCU requirement that a grace period wait for all pre-existing readers. 820On the contrary, the memory barriers called out in this section must operate in 821such a way as to <i>enforce</i> this fundamental requirement. 822Of course, different implementations enforce this requirement in different 823ways, but enforce it they must. 824 825<h3><a name="RCU Primitives Guaranteed to Execute Unconditionally">RCU Primitives Guaranteed to Execute Unconditionally</a></h3> 826 827<p> 828The common-case RCU primitives are unconditional. 829They are invoked, they do their job, and they return, with no possibility 830of error, and no need to retry. 831This is a key RCU design philosophy. 832 833<p> 834However, this philosophy is pragmatic rather than pigheaded. 835If someone comes up with a good justification for a particular conditional 836RCU primitive, it might well be implemented and added. 837After all, this guarantee was reverse-engineered, not premeditated. 838The unconditional nature of the RCU primitives was initially an 839accident of implementation, and later experience with synchronization 840primitives with conditional primitives caused me to elevate this 841accident to a guarantee. 842Therefore, the justification for adding a conditional primitive to 843RCU would need to be based on detailed and compelling use cases. 844 845<h3><a name="Guaranteed Read-to-Write Upgrade">Guaranteed Read-to-Write Upgrade</a></h3> 846 847<p> 848As far as RCU is concerned, it is always possible to carry out an 849update within an RCU read-side critical section. 850For example, that RCU read-side critical section might search for 851a given data element, and then might acquire the update-side 852spinlock in order to update that element, all while remaining 853in that RCU read-side critical section. 854Of course, it is necessary to exit the RCU read-side critical section 855before invoking <tt>synchronize_rcu()</tt>, however, this 856inconvenience can be avoided through use of the 857<tt>call_rcu()</tt> and <tt>kfree_rcu()</tt> API members 858described later in this document. 859 860<table> 861<tr><th> </th></tr> 862<tr><th align="left">Quick Quiz:</th></tr> 863<tr><td> 864 But how does the upgrade-to-write operation exclude other readers? 865</td></tr> 866<tr><th align="left">Answer:</th></tr> 867<tr><td bgcolor="#ffffff"><font color="ffffff"> 868 It doesn't, just like normal RCU updates, which also do not exclude 869 RCU readers. 870</font></td></tr> 871<tr><td> </td></tr> 872</table> 873 874<p> 875This guarantee allows lookup code to be shared between read-side 876and update-side code, and was premeditated, appearing in the earliest 877DYNIX/ptx RCU documentation. 878 879<h2><a name="Fundamental Non-Requirements">Fundamental Non-Requirements</a></h2> 880 881<p> 882RCU provides extremely lightweight readers, and its read-side guarantees, 883though quite useful, are correspondingly lightweight. 884It is therefore all too easy to assume that RCU is guaranteeing more 885than it really is. 886Of course, the list of things that RCU does not guarantee is infinitely 887long, however, the following sections list a few non-guarantees that 888have caused confusion. 889Except where otherwise noted, these non-guarantees were premeditated. 890 891<ol> 892<li> <a href="#Readers Impose Minimal Ordering"> 893 Readers Impose Minimal Ordering</a> 894<li> <a href="#Readers Do Not Exclude Updaters"> 895 Readers Do Not Exclude Updaters</a> 896<li> <a href="#Updaters Only Wait For Old Readers"> 897 Updaters Only Wait For Old Readers</a> 898<li> <a href="#Grace Periods Don't Partition Read-Side Critical Sections"> 899 Grace Periods Don't Partition Read-Side Critical Sections</a> 900<li> <a href="#Read-Side Critical Sections Don't Partition Grace Periods"> 901 Read-Side Critical Sections Don't Partition Grace Periods</a> 902<li> <a href="#Disabling Preemption Does Not Block Grace Periods"> 903 Disabling Preemption Does Not Block Grace Periods</a> 904</ol> 905 906<h3><a name="Readers Impose Minimal Ordering">Readers Impose Minimal Ordering</a></h3> 907 908<p> 909Reader-side markers such as <tt>rcu_read_lock()</tt> and 910<tt>rcu_read_unlock()</tt> provide absolutely no ordering guarantees 911except through their interaction with the grace-period APIs such as 912<tt>synchronize_rcu()</tt>. 913To see this, consider the following pair of threads: 914 915<blockquote> 916<pre> 917 1 void thread0(void) 918 2 { 919 3 rcu_read_lock(); 920 4 WRITE_ONCE(x, 1); 921 5 rcu_read_unlock(); 922 6 rcu_read_lock(); 923 7 WRITE_ONCE(y, 1); 924 8 rcu_read_unlock(); 925 9 } 92610 92711 void thread1(void) 92812 { 92913 rcu_read_lock(); 93014 r1 = READ_ONCE(y); 93115 rcu_read_unlock(); 93216 rcu_read_lock(); 93317 r2 = READ_ONCE(x); 93418 rcu_read_unlock(); 93519 } 936</pre> 937</blockquote> 938 939<p> 940After <tt>thread0()</tt> and <tt>thread1()</tt> execute 941concurrently, it is quite possible to have 942 943<blockquote> 944<pre> 945(r1 == 1 && r2 == 0) 946</pre> 947</blockquote> 948 949(that is, <tt>y</tt> appears to have been assigned before <tt>x</tt>), 950which would not be possible if <tt>rcu_read_lock()</tt> and 951<tt>rcu_read_unlock()</tt> had much in the way of ordering 952properties. 953But they do not, so the CPU is within its rights 954to do significant reordering. 955This is by design: Any significant ordering constraints would slow down 956these fast-path APIs. 957 958<table> 959<tr><th> </th></tr> 960<tr><th align="left">Quick Quiz:</th></tr> 961<tr><td> 962 Can't the compiler also reorder this code? 963</td></tr> 964<tr><th align="left">Answer:</th></tr> 965<tr><td bgcolor="#ffffff"><font color="ffffff"> 966 No, the volatile casts in <tt>READ_ONCE()</tt> and 967 <tt>WRITE_ONCE()</tt> prevent the compiler from reordering in 968 this particular case. 969</font></td></tr> 970<tr><td> </td></tr> 971</table> 972 973<h3><a name="Readers Do Not Exclude Updaters">Readers Do Not Exclude Updaters</a></h3> 974 975<p> 976Neither <tt>rcu_read_lock()</tt> nor <tt>rcu_read_unlock()</tt> 977exclude updates. 978All they do is to prevent grace periods from ending. 979The following example illustrates this: 980 981<blockquote> 982<pre> 983 1 void thread0(void) 984 2 { 985 3 rcu_read_lock(); 986 4 r1 = READ_ONCE(y); 987 5 if (r1) { 988 6 do_something_with_nonzero_x(); 989 7 r2 = READ_ONCE(x); 990 8 WARN_ON(!r2); /* BUG!!! */ 991 9 } 99210 rcu_read_unlock(); 99311 } 99412 99513 void thread1(void) 99614 { 99715 spin_lock(&my_lock); 99816 WRITE_ONCE(x, 1); 99917 WRITE_ONCE(y, 1); 100018 spin_unlock(&my_lock); 100119 } 1002</pre> 1003</blockquote> 1004 1005<p> 1006If the <tt>thread0()</tt> function's <tt>rcu_read_lock()</tt> 1007excluded the <tt>thread1()</tt> function's update, 1008the <tt>WARN_ON()</tt> could never fire. 1009But the fact is that <tt>rcu_read_lock()</tt> does not exclude 1010much of anything aside from subsequent grace periods, of which 1011<tt>thread1()</tt> has none, so the 1012<tt>WARN_ON()</tt> can and does fire. 1013 1014<h3><a name="Updaters Only Wait For Old Readers">Updaters Only Wait For Old Readers</a></h3> 1015 1016<p> 1017It might be tempting to assume that after <tt>synchronize_rcu()</tt> 1018completes, there are no readers executing. 1019This temptation must be avoided because 1020new readers can start immediately after <tt>synchronize_rcu()</tt> 1021starts, and <tt>synchronize_rcu()</tt> is under no 1022obligation to wait for these new readers. 1023 1024<table> 1025<tr><th> </th></tr> 1026<tr><th align="left">Quick Quiz:</th></tr> 1027<tr><td> 1028 Suppose that synchronize_rcu() did wait until <i>all</i> 1029 readers had completed instead of waiting only on 1030 pre-existing readers. 1031 For how long would the updater be able to rely on there 1032 being no readers? 1033</td></tr> 1034<tr><th align="left">Answer:</th></tr> 1035<tr><td bgcolor="#ffffff"><font color="ffffff"> 1036 For no time at all. 1037 Even if <tt>synchronize_rcu()</tt> were to wait until 1038 all readers had completed, a new reader might start immediately after 1039 <tt>synchronize_rcu()</tt> completed. 1040 Therefore, the code following 1041 <tt>synchronize_rcu()</tt> can <i>never</i> rely on there being 1042 no readers. 1043</font></td></tr> 1044<tr><td> </td></tr> 1045</table> 1046 1047<h3><a name="Grace Periods Don't Partition Read-Side Critical Sections"> 1048Grace Periods Don't Partition Read-Side Critical Sections</a></h3> 1049 1050<p> 1051It is tempting to assume that if any part of one RCU read-side critical 1052section precedes a given grace period, and if any part of another RCU 1053read-side critical section follows that same grace period, then all of 1054the first RCU read-side critical section must precede all of the second. 1055However, this just isn't the case: A single grace period does not 1056partition the set of RCU read-side critical sections. 1057An example of this situation can be illustrated as follows, where 1058<tt>x</tt>, <tt>y</tt>, and <tt>z</tt> are initially all zero: 1059 1060<blockquote> 1061<pre> 1062 1 void thread0(void) 1063 2 { 1064 3 rcu_read_lock(); 1065 4 WRITE_ONCE(a, 1); 1066 5 WRITE_ONCE(b, 1); 1067 6 rcu_read_unlock(); 1068 7 } 1069 8 1070 9 void thread1(void) 107110 { 107211 r1 = READ_ONCE(a); 107312 synchronize_rcu(); 107413 WRITE_ONCE(c, 1); 107514 } 107615 107716 void thread2(void) 107817 { 107918 rcu_read_lock(); 108019 r2 = READ_ONCE(b); 108120 r3 = READ_ONCE(c); 108221 rcu_read_unlock(); 108322 } 1084</pre> 1085</blockquote> 1086 1087<p> 1088It turns out that the outcome: 1089 1090<blockquote> 1091<pre> 1092(r1 == 1 && r2 == 0 && r3 == 1) 1093</pre> 1094</blockquote> 1095 1096is entirely possible. 1097The following figure show how this can happen, with each circled 1098<tt>QS</tt> indicating the point at which RCU recorded a 1099<i>quiescent state</i> for each thread, that is, a state in which 1100RCU knows that the thread cannot be in the midst of an RCU read-side 1101critical section that started before the current grace period: 1102 1103<p><img src="GPpartitionReaders1.svg" alt="GPpartitionReaders1.svg" width="60%"></p> 1104 1105<p> 1106If it is necessary to partition RCU read-side critical sections in this 1107manner, it is necessary to use two grace periods, where the first 1108grace period is known to end before the second grace period starts: 1109 1110<blockquote> 1111<pre> 1112 1 void thread0(void) 1113 2 { 1114 3 rcu_read_lock(); 1115 4 WRITE_ONCE(a, 1); 1116 5 WRITE_ONCE(b, 1); 1117 6 rcu_read_unlock(); 1118 7 } 1119 8 1120 9 void thread1(void) 112110 { 112211 r1 = READ_ONCE(a); 112312 synchronize_rcu(); 112413 WRITE_ONCE(c, 1); 112514 } 112615 112716 void thread2(void) 112817 { 112918 r2 = READ_ONCE(c); 113019 synchronize_rcu(); 113120 WRITE_ONCE(d, 1); 113221 } 113322 113423 void thread3(void) 113524 { 113625 rcu_read_lock(); 113726 r3 = READ_ONCE(b); 113827 r4 = READ_ONCE(d); 113928 rcu_read_unlock(); 114029 } 1141</pre> 1142</blockquote> 1143 1144<p> 1145Here, if <tt>(r1 == 1)</tt>, then 1146<tt>thread0()</tt>'s write to <tt>b</tt> must happen 1147before the end of <tt>thread1()</tt>'s grace period. 1148If in addition <tt>(r4 == 1)</tt>, then 1149<tt>thread3()</tt>'s read from <tt>b</tt> must happen 1150after the beginning of <tt>thread2()</tt>'s grace period. 1151If it is also the case that <tt>(r2 == 1)</tt>, then the 1152end of <tt>thread1()</tt>'s grace period must precede the 1153beginning of <tt>thread2()</tt>'s grace period. 1154This mean that the two RCU read-side critical sections cannot overlap, 1155guaranteeing that <tt>(r3 == 1)</tt>. 1156As a result, the outcome: 1157 1158<blockquote> 1159<pre> 1160(r1 == 1 && r2 == 1 && r3 == 0 && r4 == 1) 1161</pre> 1162</blockquote> 1163 1164cannot happen. 1165 1166<p> 1167This non-requirement was also non-premeditated, but became apparent 1168when studying RCU's interaction with memory ordering. 1169 1170<h3><a name="Read-Side Critical Sections Don't Partition Grace Periods"> 1171Read-Side Critical Sections Don't Partition Grace Periods</a></h3> 1172 1173<p> 1174It is also tempting to assume that if an RCU read-side critical section 1175happens between a pair of grace periods, then those grace periods cannot 1176overlap. 1177However, this temptation leads nowhere good, as can be illustrated by 1178the following, with all variables initially zero: 1179 1180<blockquote> 1181<pre> 1182 1 void thread0(void) 1183 2 { 1184 3 rcu_read_lock(); 1185 4 WRITE_ONCE(a, 1); 1186 5 WRITE_ONCE(b, 1); 1187 6 rcu_read_unlock(); 1188 7 } 1189 8 1190 9 void thread1(void) 119110 { 119211 r1 = READ_ONCE(a); 119312 synchronize_rcu(); 119413 WRITE_ONCE(c, 1); 119514 } 119615 119716 void thread2(void) 119817 { 119918 rcu_read_lock(); 120019 WRITE_ONCE(d, 1); 120120 r2 = READ_ONCE(c); 120221 rcu_read_unlock(); 120322 } 120423 120524 void thread3(void) 120625 { 120726 r3 = READ_ONCE(d); 120827 synchronize_rcu(); 120928 WRITE_ONCE(e, 1); 121029 } 121130 121231 void thread4(void) 121332 { 121433 rcu_read_lock(); 121534 r4 = READ_ONCE(b); 121635 r5 = READ_ONCE(e); 121736 rcu_read_unlock(); 121837 } 1219</pre> 1220</blockquote> 1221 1222<p> 1223In this case, the outcome: 1224 1225<blockquote> 1226<pre> 1227(r1 == 1 && r2 == 1 && r3 == 1 && r4 == 0 && r5 == 1) 1228</pre> 1229</blockquote> 1230 1231is entirely possible, as illustrated below: 1232 1233<p><img src="ReadersPartitionGP1.svg" alt="ReadersPartitionGP1.svg" width="100%"></p> 1234 1235<p> 1236Again, an RCU read-side critical section can overlap almost all of a 1237given grace period, just so long as it does not overlap the entire 1238grace period. 1239As a result, an RCU read-side critical section cannot partition a pair 1240of RCU grace periods. 1241 1242<table> 1243<tr><th> </th></tr> 1244<tr><th align="left">Quick Quiz:</th></tr> 1245<tr><td> 1246 How long a sequence of grace periods, each separated by an RCU 1247 read-side critical section, would be required to partition the RCU 1248 read-side critical sections at the beginning and end of the chain? 1249</td></tr> 1250<tr><th align="left">Answer:</th></tr> 1251<tr><td bgcolor="#ffffff"><font color="ffffff"> 1252 In theory, an infinite number. 1253 In practice, an unknown number that is sensitive to both implementation 1254 details and timing considerations. 1255 Therefore, even in practice, RCU users must abide by the 1256 theoretical rather than the practical answer. 1257</font></td></tr> 1258<tr><td> </td></tr> 1259</table> 1260 1261<h3><a name="Disabling Preemption Does Not Block Grace Periods"> 1262Disabling Preemption Does Not Block Grace Periods</a></h3> 1263 1264<p> 1265There was a time when disabling preemption on any given CPU would block 1266subsequent grace periods. 1267However, this was an accident of implementation and is not a requirement. 1268And in the current Linux-kernel implementation, disabling preemption 1269on a given CPU in fact does not block grace periods, as Oleg Nesterov 1270<a href="https://lkml.kernel.org/g/20150614193825.GA19582@redhat.com">demonstrated</a>. 1271 1272<p> 1273If you need a preempt-disable region to block grace periods, you need to add 1274<tt>rcu_read_lock()</tt> and <tt>rcu_read_unlock()</tt>, for example 1275as follows: 1276 1277<blockquote> 1278<pre> 1279 1 preempt_disable(); 1280 2 rcu_read_lock(); 1281 3 do_something(); 1282 4 rcu_read_unlock(); 1283 5 preempt_enable(); 1284 6 1285 7 /* Spinlocks implicitly disable preemption. */ 1286 8 spin_lock(&mylock); 1287 9 rcu_read_lock(); 128810 do_something(); 128911 rcu_read_unlock(); 129012 spin_unlock(&mylock); 1291</pre> 1292</blockquote> 1293 1294<p> 1295In theory, you could enter the RCU read-side critical section first, 1296but it is more efficient to keep the entire RCU read-side critical 1297section contained in the preempt-disable region as shown above. 1298Of course, RCU read-side critical sections that extend outside of 1299preempt-disable regions will work correctly, but such critical sections 1300can be preempted, which forces <tt>rcu_read_unlock()</tt> to do 1301more work. 1302And no, this is <i>not</i> an invitation to enclose all of your RCU 1303read-side critical sections within preempt-disable regions, because 1304doing so would degrade real-time response. 1305 1306<p> 1307This non-requirement appeared with preemptible RCU. 1308If you need a grace period that waits on non-preemptible code regions, use 1309<a href="#Sched Flavor">RCU-sched</a>. 1310 1311<h2><a name="Parallelism Facts of Life">Parallelism Facts of Life</a></h2> 1312 1313<p> 1314These parallelism facts of life are by no means specific to RCU, but 1315the RCU implementation must abide by them. 1316They therefore bear repeating: 1317 1318<ol> 1319<li> Any CPU or task may be delayed at any time, 1320 and any attempts to avoid these delays by disabling 1321 preemption, interrupts, or whatever are completely futile. 1322 This is most obvious in preemptible user-level 1323 environments and in virtualized environments (where 1324 a given guest OS's VCPUs can be preempted at any time by 1325 the underlying hypervisor), but can also happen in bare-metal 1326 environments due to ECC errors, NMIs, and other hardware 1327 events. 1328 Although a delay of more than about 20 seconds can result 1329 in splats, the RCU implementation is obligated to use 1330 algorithms that can tolerate extremely long delays, but where 1331 “extremely long” is not long enough to allow 1332 wrap-around when incrementing a 64-bit counter. 1333<li> Both the compiler and the CPU can reorder memory accesses. 1334 Where it matters, RCU must use compiler directives and 1335 memory-barrier instructions to preserve ordering. 1336<li> Conflicting writes to memory locations in any given cache line 1337 will result in expensive cache misses. 1338 Greater numbers of concurrent writes and more-frequent 1339 concurrent writes will result in more dramatic slowdowns. 1340 RCU is therefore obligated to use algorithms that have 1341 sufficient locality to avoid significant performance and 1342 scalability problems. 1343<li> As a rough rule of thumb, only one CPU's worth of processing 1344 may be carried out under the protection of any given exclusive 1345 lock. 1346 RCU must therefore use scalable locking designs. 1347<li> Counters are finite, especially on 32-bit systems. 1348 RCU's use of counters must therefore tolerate counter wrap, 1349 or be designed such that counter wrap would take way more 1350 time than a single system is likely to run. 1351 An uptime of ten years is quite possible, a runtime 1352 of a century much less so. 1353 As an example of the latter, RCU's dyntick-idle nesting counter 1354 allows 54 bits for interrupt nesting level (this counter 1355 is 64 bits even on a 32-bit system). 1356 Overflowing this counter requires 2<sup>54</sup> 1357 half-interrupts on a given CPU without that CPU ever going idle. 1358 If a half-interrupt happened every microsecond, it would take 1359 570 years of runtime to overflow this counter, which is currently 1360 believed to be an acceptably long time. 1361<li> Linux systems can have thousands of CPUs running a single 1362 Linux kernel in a single shared-memory environment. 1363 RCU must therefore pay close attention to high-end scalability. 1364</ol> 1365 1366<p> 1367This last parallelism fact of life means that RCU must pay special 1368attention to the preceding facts of life. 1369The idea that Linux might scale to systems with thousands of CPUs would 1370have been met with some skepticism in the 1990s, but these requirements 1371would have otherwise have been unsurprising, even in the early 1990s. 1372 1373<h2><a name="Quality-of-Implementation Requirements">Quality-of-Implementation Requirements</a></h2> 1374 1375<p> 1376These sections list quality-of-implementation requirements. 1377Although an RCU implementation that ignores these requirements could 1378still be used, it would likely be subject to limitations that would 1379make it inappropriate for industrial-strength production use. 1380Classes of quality-of-implementation requirements are as follows: 1381 1382<ol> 1383<li> <a href="#Specialization">Specialization</a> 1384<li> <a href="#Performance and Scalability">Performance and Scalability</a> 1385<li> <a href="#Composability">Composability</a> 1386<li> <a href="#Corner Cases">Corner Cases</a> 1387</ol> 1388 1389<p> 1390These classes is covered in the following sections. 1391 1392<h3><a name="Specialization">Specialization</a></h3> 1393 1394<p> 1395RCU is and always has been intended primarily for read-mostly situations, 1396which means that RCU's read-side primitives are optimized, often at the 1397expense of its update-side primitives. 1398Experience thus far is captured by the following list of situations: 1399 1400<ol> 1401<li> Read-mostly data, where stale and inconsistent data is not 1402 a problem: RCU works great! 1403<li> Read-mostly data, where data must be consistent: 1404 RCU works well. 1405<li> Read-write data, where data must be consistent: 1406 RCU <i>might</i> work OK. 1407 Or not. 1408<li> Write-mostly data, where data must be consistent: 1409 RCU is very unlikely to be the right tool for the job, 1410 with the following exceptions, where RCU can provide: 1411 <ol type=a> 1412 <li> Existence guarantees for update-friendly mechanisms. 1413 <li> Wait-free read-side primitives for real-time use. 1414 </ol> 1415</ol> 1416 1417<p> 1418This focus on read-mostly situations means that RCU must interoperate 1419with other synchronization primitives. 1420For example, the <tt>add_gp()</tt> and <tt>remove_gp_synchronous()</tt> 1421examples discussed earlier use RCU to protect readers and locking to 1422coordinate updaters. 1423However, the need extends much farther, requiring that a variety of 1424synchronization primitives be legal within RCU read-side critical sections, 1425including spinlocks, sequence locks, atomic operations, reference 1426counters, and memory barriers. 1427 1428<table> 1429<tr><th> </th></tr> 1430<tr><th align="left">Quick Quiz:</th></tr> 1431<tr><td> 1432 What about sleeping locks? 1433</td></tr> 1434<tr><th align="left">Answer:</th></tr> 1435<tr><td bgcolor="#ffffff"><font color="ffffff"> 1436 These are forbidden within Linux-kernel RCU read-side critical 1437 sections because it is not legal to place a quiescent state 1438 (in this case, voluntary context switch) within an RCU read-side 1439 critical section. 1440 However, sleeping locks may be used within userspace RCU read-side 1441 critical sections, and also within Linux-kernel sleepable RCU 1442 <a href="#Sleepable RCU"><font color="ffffff">(SRCU)</font></a> 1443 read-side critical sections. 1444 In addition, the -rt patchset turns spinlocks into a 1445 sleeping locks so that the corresponding critical sections 1446 can be preempted, which also means that these sleeplockified 1447 spinlocks (but not other sleeping locks!) may be acquire within 1448 -rt-Linux-kernel RCU read-side critical sections. 1449 </font> 1450 1451 <p><font color="ffffff"> 1452 Note that it <i>is</i> legal for a normal RCU read-side 1453 critical section to conditionally acquire a sleeping locks 1454 (as in <tt>mutex_trylock()</tt>), but only as long as it does 1455 not loop indefinitely attempting to conditionally acquire that 1456 sleeping locks. 1457 The key point is that things like <tt>mutex_trylock()</tt> 1458 either return with the mutex held, or return an error indication if 1459 the mutex was not immediately available. 1460 Either way, <tt>mutex_trylock()</tt> returns immediately without 1461 sleeping. 1462</font></td></tr> 1463<tr><td> </td></tr> 1464</table> 1465 1466<p> 1467It often comes as a surprise that many algorithms do not require a 1468consistent view of data, but many can function in that mode, 1469with network routing being the poster child. 1470Internet routing algorithms take significant time to propagate 1471updates, so that by the time an update arrives at a given system, 1472that system has been sending network traffic the wrong way for 1473a considerable length of time. 1474Having a few threads continue to send traffic the wrong way for a 1475few more milliseconds is clearly not a problem: In the worst case, 1476TCP retransmissions will eventually get the data where it needs to go. 1477In general, when tracking the state of the universe outside of the 1478computer, some level of inconsistency must be tolerated due to 1479speed-of-light delays if nothing else. 1480 1481<p> 1482Furthermore, uncertainty about external state is inherent in many cases. 1483For example, a pair of veterinarians might use heartbeat to determine 1484whether or not a given cat was alive. 1485But how long should they wait after the last heartbeat to decide that 1486the cat is in fact dead? 1487Waiting less than 400 milliseconds makes no sense because this would 1488mean that a relaxed cat would be considered to cycle between death 1489and life more than 100 times per minute. 1490Moreover, just as with human beings, a cat's heart might stop for 1491some period of time, so the exact wait period is a judgment call. 1492One of our pair of veterinarians might wait 30 seconds before pronouncing 1493the cat dead, while the other might insist on waiting a full minute. 1494The two veterinarians would then disagree on the state of the cat during 1495the final 30 seconds of the minute following the last heartbeat. 1496 1497<p> 1498Interestingly enough, this same situation applies to hardware. 1499When push comes to shove, how do we tell whether or not some 1500external server has failed? 1501We send messages to it periodically, and declare it failed if we 1502don't receive a response within a given period of time. 1503Policy decisions can usually tolerate short 1504periods of inconsistency. 1505The policy was decided some time ago, and is only now being put into 1506effect, so a few milliseconds of delay is normally inconsequential. 1507 1508<p> 1509However, there are algorithms that absolutely must see consistent data. 1510For example, the translation between a user-level SystemV semaphore 1511ID to the corresponding in-kernel data structure is protected by RCU, 1512but it is absolutely forbidden to update a semaphore that has just been 1513removed. 1514In the Linux kernel, this need for consistency is accommodated by acquiring 1515spinlocks located in the in-kernel data structure from within 1516the RCU read-side critical section, and this is indicated by the 1517green box in the figure above. 1518Many other techniques may be used, and are in fact used within the 1519Linux kernel. 1520 1521<p> 1522In short, RCU is not required to maintain consistency, and other 1523mechanisms may be used in concert with RCU when consistency is required. 1524RCU's specialization allows it to do its job extremely well, and its 1525ability to interoperate with other synchronization mechanisms allows 1526the right mix of synchronization tools to be used for a given job. 1527 1528<h3><a name="Performance and Scalability">Performance and Scalability</a></h3> 1529 1530<p> 1531Energy efficiency is a critical component of performance today, 1532and Linux-kernel RCU implementations must therefore avoid unnecessarily 1533awakening idle CPUs. 1534I cannot claim that this requirement was premeditated. 1535In fact, I learned of it during a telephone conversation in which I 1536was given “frank and open” feedback on the importance 1537of energy efficiency in battery-powered systems and on specific 1538energy-efficiency shortcomings of the Linux-kernel RCU implementation. 1539In my experience, the battery-powered embedded community will consider 1540any unnecessary wakeups to be extremely unfriendly acts. 1541So much so that mere Linux-kernel-mailing-list posts are 1542insufficient to vent their ire. 1543 1544<p> 1545Memory consumption is not particularly important for in most 1546situations, and has become decreasingly 1547so as memory sizes have expanded and memory 1548costs have plummeted. 1549However, as I learned from Matt Mackall's 1550<a href="http://elinux.org/Linux_Tiny-FAQ">bloatwatch</a> 1551efforts, memory footprint is critically important on single-CPU systems with 1552non-preemptible (<tt>CONFIG_PREEMPT=n</tt>) kernels, and thus 1553<a href="https://lkml.kernel.org/g/20090113221724.GA15307@linux.vnet.ibm.com">tiny RCU</a> 1554was born. 1555Josh Triplett has since taken over the small-memory banner with his 1556<a href="https://tiny.wiki.kernel.org/">Linux kernel tinification</a> 1557project, which resulted in 1558<a href="#Sleepable RCU">SRCU</a> 1559becoming optional for those kernels not needing it. 1560 1561<p> 1562The remaining performance requirements are, for the most part, 1563unsurprising. 1564For example, in keeping with RCU's read-side specialization, 1565<tt>rcu_dereference()</tt> should have negligible overhead (for 1566example, suppression of a few minor compiler optimizations). 1567Similarly, in non-preemptible environments, <tt>rcu_read_lock()</tt> and 1568<tt>rcu_read_unlock()</tt> should have exactly zero overhead. 1569 1570<p> 1571In preemptible environments, in the case where the RCU read-side 1572critical section was not preempted (as will be the case for the 1573highest-priority real-time process), <tt>rcu_read_lock()</tt> and 1574<tt>rcu_read_unlock()</tt> should have minimal overhead. 1575In particular, they should not contain atomic read-modify-write 1576operations, memory-barrier instructions, preemption disabling, 1577interrupt disabling, or backwards branches. 1578However, in the case where the RCU read-side critical section was preempted, 1579<tt>rcu_read_unlock()</tt> may acquire spinlocks and disable interrupts. 1580This is why it is better to nest an RCU read-side critical section 1581within a preempt-disable region than vice versa, at least in cases 1582where that critical section is short enough to avoid unduly degrading 1583real-time latencies. 1584 1585<p> 1586The <tt>synchronize_rcu()</tt> grace-period-wait primitive is 1587optimized for throughput. 1588It may therefore incur several milliseconds of latency in addition to 1589the duration of the longest RCU read-side critical section. 1590On the other hand, multiple concurrent invocations of 1591<tt>synchronize_rcu()</tt> are required to use batching optimizations 1592so that they can be satisfied by a single underlying grace-period-wait 1593operation. 1594For example, in the Linux kernel, it is not unusual for a single 1595grace-period-wait operation to serve more than 1596<a href="https://www.usenix.org/conference/2004-usenix-annual-technical-conference/making-rcu-safe-deep-sub-millisecond-response">1,000 separate invocations</a> 1597of <tt>synchronize_rcu()</tt>, thus amortizing the per-invocation 1598overhead down to nearly zero. 1599However, the grace-period optimization is also required to avoid 1600measurable degradation of real-time scheduling and interrupt latencies. 1601 1602<p> 1603In some cases, the multi-millisecond <tt>synchronize_rcu()</tt> 1604latencies are unacceptable. 1605In these cases, <tt>synchronize_rcu_expedited()</tt> may be used 1606instead, reducing the grace-period latency down to a few tens of 1607microseconds on small systems, at least in cases where the RCU read-side 1608critical sections are short. 1609There are currently no special latency requirements for 1610<tt>synchronize_rcu_expedited()</tt> on large systems, but, 1611consistent with the empirical nature of the RCU specification, 1612that is subject to change. 1613However, there most definitely are scalability requirements: 1614A storm of <tt>synchronize_rcu_expedited()</tt> invocations on 4096 1615CPUs should at least make reasonable forward progress. 1616In return for its shorter latencies, <tt>synchronize_rcu_expedited()</tt> 1617is permitted to impose modest degradation of real-time latency 1618on non-idle online CPUs. 1619Here, “modest” means roughly the same latency 1620degradation as a scheduling-clock interrupt. 1621 1622<p> 1623There are a number of situations where even 1624<tt>synchronize_rcu_expedited()</tt>'s reduced grace-period 1625latency is unacceptable. 1626In these situations, the asynchronous <tt>call_rcu()</tt> can be 1627used in place of <tt>synchronize_rcu()</tt> as follows: 1628 1629<blockquote> 1630<pre> 1631 1 struct foo { 1632 2 int a; 1633 3 int b; 1634 4 struct rcu_head rh; 1635 5 }; 1636 6 1637 7 static void remove_gp_cb(struct rcu_head *rhp) 1638 8 { 1639 9 struct foo *p = container_of(rhp, struct foo, rh); 164010 164111 kfree(p); 164212 } 164313 164414 bool remove_gp_asynchronous(void) 164515 { 164616 struct foo *p; 164717 164818 spin_lock(&gp_lock); 164919 p = rcu_dereference(gp); 165020 if (!p) { 165121 spin_unlock(&gp_lock); 165222 return false; 165323 } 165424 rcu_assign_pointer(gp, NULL); 165525 call_rcu(&p->rh, remove_gp_cb); 165626 spin_unlock(&gp_lock); 165727 return true; 165828 } 1659</pre> 1660</blockquote> 1661 1662<p> 1663A definition of <tt>struct foo</tt> is finally needed, and appears 1664on lines 1-5. 1665The function <tt>remove_gp_cb()</tt> is passed to <tt>call_rcu()</tt> 1666on line 25, and will be invoked after the end of a subsequent 1667grace period. 1668This gets the same effect as <tt>remove_gp_synchronous()</tt>, 1669but without forcing the updater to wait for a grace period to elapse. 1670The <tt>call_rcu()</tt> function may be used in a number of 1671situations where neither <tt>synchronize_rcu()</tt> nor 1672<tt>synchronize_rcu_expedited()</tt> would be legal, 1673including within preempt-disable code, <tt>local_bh_disable()</tt> code, 1674interrupt-disable code, and interrupt handlers. 1675However, even <tt>call_rcu()</tt> is illegal within NMI handlers 1676and from idle and offline CPUs. 1677The callback function (<tt>remove_gp_cb()</tt> in this case) will be 1678executed within softirq (software interrupt) environment within the 1679Linux kernel, 1680either within a real softirq handler or under the protection 1681of <tt>local_bh_disable()</tt>. 1682In both the Linux kernel and in userspace, it is bad practice to 1683write an RCU callback function that takes too long. 1684Long-running operations should be relegated to separate threads or 1685(in the Linux kernel) workqueues. 1686 1687<table> 1688<tr><th> </th></tr> 1689<tr><th align="left">Quick Quiz:</th></tr> 1690<tr><td> 1691 Why does line 19 use <tt>rcu_access_pointer()</tt>? 1692 After all, <tt>call_rcu()</tt> on line 25 stores into the 1693 structure, which would interact badly with concurrent insertions. 1694 Doesn't this mean that <tt>rcu_dereference()</tt> is required? 1695</td></tr> 1696<tr><th align="left">Answer:</th></tr> 1697<tr><td bgcolor="#ffffff"><font color="ffffff"> 1698 Presumably the <tt>->gp_lock</tt> acquired on line 18 excludes 1699 any changes, including any insertions that <tt>rcu_dereference()</tt> 1700 would protect against. 1701 Therefore, any insertions will be delayed until after 1702 <tt>->gp_lock</tt> 1703 is released on line 25, which in turn means that 1704 <tt>rcu_access_pointer()</tt> suffices. 1705</font></td></tr> 1706<tr><td> </td></tr> 1707</table> 1708 1709<p> 1710However, all that <tt>remove_gp_cb()</tt> is doing is 1711invoking <tt>kfree()</tt> on the data element. 1712This is a common idiom, and is supported by <tt>kfree_rcu()</tt>, 1713which allows “fire and forget” operation as shown below: 1714 1715<blockquote> 1716<pre> 1717 1 struct foo { 1718 2 int a; 1719 3 int b; 1720 4 struct rcu_head rh; 1721 5 }; 1722 6 1723 7 bool remove_gp_faf(void) 1724 8 { 1725 9 struct foo *p; 172610 172711 spin_lock(&gp_lock); 172812 p = rcu_dereference(gp); 172913 if (!p) { 173014 spin_unlock(&gp_lock); 173115 return false; 173216 } 173317 rcu_assign_pointer(gp, NULL); 173418 kfree_rcu(p, rh); 173519 spin_unlock(&gp_lock); 173620 return true; 173721 } 1738</pre> 1739</blockquote> 1740 1741<p> 1742Note that <tt>remove_gp_faf()</tt> simply invokes 1743<tt>kfree_rcu()</tt> and proceeds, without any need to pay any 1744further attention to the subsequent grace period and <tt>kfree()</tt>. 1745It is permissible to invoke <tt>kfree_rcu()</tt> from the same 1746environments as for <tt>call_rcu()</tt>. 1747Interestingly enough, DYNIX/ptx had the equivalents of 1748<tt>call_rcu()</tt> and <tt>kfree_rcu()</tt>, but not 1749<tt>synchronize_rcu()</tt>. 1750This was due to the fact that RCU was not heavily used within DYNIX/ptx, 1751so the very few places that needed something like 1752<tt>synchronize_rcu()</tt> simply open-coded it. 1753 1754<table> 1755<tr><th> </th></tr> 1756<tr><th align="left">Quick Quiz:</th></tr> 1757<tr><td> 1758 Earlier it was claimed that <tt>call_rcu()</tt> and 1759 <tt>kfree_rcu()</tt> allowed updaters to avoid being blocked 1760 by readers. 1761 But how can that be correct, given that the invocation of the callback 1762 and the freeing of the memory (respectively) must still wait for 1763 a grace period to elapse? 1764</td></tr> 1765<tr><th align="left">Answer:</th></tr> 1766<tr><td bgcolor="#ffffff"><font color="ffffff"> 1767 We could define things this way, but keep in mind that this sort of 1768 definition would say that updates in garbage-collected languages 1769 cannot complete until the next time the garbage collector runs, 1770 which does not seem at all reasonable. 1771 The key point is that in most cases, an updater using either 1772 <tt>call_rcu()</tt> or <tt>kfree_rcu()</tt> can proceed to the 1773 next update as soon as it has invoked <tt>call_rcu()</tt> or 1774 <tt>kfree_rcu()</tt>, without having to wait for a subsequent 1775 grace period. 1776</font></td></tr> 1777<tr><td> </td></tr> 1778</table> 1779 1780<p> 1781But what if the updater must wait for the completion of code to be 1782executed after the end of the grace period, but has other tasks 1783that can be carried out in the meantime? 1784The polling-style <tt>get_state_synchronize_rcu()</tt> and 1785<tt>cond_synchronize_rcu()</tt> functions may be used for this 1786purpose, as shown below: 1787 1788<blockquote> 1789<pre> 1790 1 bool remove_gp_poll(void) 1791 2 { 1792 3 struct foo *p; 1793 4 unsigned long s; 1794 5 1795 6 spin_lock(&gp_lock); 1796 7 p = rcu_access_pointer(gp); 1797 8 if (!p) { 1798 9 spin_unlock(&gp_lock); 179910 return false; 180011 } 180112 rcu_assign_pointer(gp, NULL); 180213 spin_unlock(&gp_lock); 180314 s = get_state_synchronize_rcu(); 180415 do_something_while_waiting(); 180516 cond_synchronize_rcu(s); 180617 kfree(p); 180718 return true; 180819 } 1809</pre> 1810</blockquote> 1811 1812<p> 1813On line 14, <tt>get_state_synchronize_rcu()</tt> obtains a 1814“cookie” from RCU, 1815then line 15 carries out other tasks, 1816and finally, line 16 returns immediately if a grace period has 1817elapsed in the meantime, but otherwise waits as required. 1818The need for <tt>get_state_synchronize_rcu</tt> and 1819<tt>cond_synchronize_rcu()</tt> has appeared quite recently, 1820so it is too early to tell whether they will stand the test of time. 1821 1822<p> 1823RCU thus provides a range of tools to allow updaters to strike the 1824required tradeoff between latency, flexibility and CPU overhead. 1825 1826<h3><a name="Composability">Composability</a></h3> 1827 1828<p> 1829Composability has received much attention in recent years, perhaps in part 1830due to the collision of multicore hardware with object-oriented techniques 1831designed in single-threaded environments for single-threaded use. 1832And in theory, RCU read-side critical sections may be composed, and in 1833fact may be nested arbitrarily deeply. 1834In practice, as with all real-world implementations of composable 1835constructs, there are limitations. 1836 1837<p> 1838Implementations of RCU for which <tt>rcu_read_lock()</tt> 1839and <tt>rcu_read_unlock()</tt> generate no code, such as 1840Linux-kernel RCU when <tt>CONFIG_PREEMPT=n</tt>, can be 1841nested arbitrarily deeply. 1842After all, there is no overhead. 1843Except that if all these instances of <tt>rcu_read_lock()</tt> 1844and <tt>rcu_read_unlock()</tt> are visible to the compiler, 1845compilation will eventually fail due to exhausting memory, 1846mass storage, or user patience, whichever comes first. 1847If the nesting is not visible to the compiler, as is the case with 1848mutually recursive functions each in its own translation unit, 1849stack overflow will result. 1850If the nesting takes the form of loops, perhaps in the guise of tail 1851recursion, either the control variable 1852will overflow or (in the Linux kernel) you will get an RCU CPU stall warning. 1853Nevertheless, this class of RCU implementations is one 1854of the most composable constructs in existence. 1855 1856<p> 1857RCU implementations that explicitly track nesting depth 1858are limited by the nesting-depth counter. 1859For example, the Linux kernel's preemptible RCU limits nesting to 1860<tt>INT_MAX</tt>. 1861This should suffice for almost all practical purposes. 1862That said, a consecutive pair of RCU read-side critical sections 1863between which there is an operation that waits for a grace period 1864cannot be enclosed in another RCU read-side critical section. 1865This is because it is not legal to wait for a grace period within 1866an RCU read-side critical section: To do so would result either 1867in deadlock or 1868in RCU implicitly splitting the enclosing RCU read-side critical 1869section, neither of which is conducive to a long-lived and prosperous 1870kernel. 1871 1872<p> 1873It is worth noting that RCU is not alone in limiting composability. 1874For example, many transactional-memory implementations prohibit 1875composing a pair of transactions separated by an irrevocable 1876operation (for example, a network receive operation). 1877For another example, lock-based critical sections can be composed 1878surprisingly freely, but only if deadlock is avoided. 1879 1880<p> 1881In short, although RCU read-side critical sections are highly composable, 1882care is required in some situations, just as is the case for any other 1883composable synchronization mechanism. 1884 1885<h3><a name="Corner Cases">Corner Cases</a></h3> 1886 1887<p> 1888A given RCU workload might have an endless and intense stream of 1889RCU read-side critical sections, perhaps even so intense that there 1890was never a point in time during which there was not at least one 1891RCU read-side critical section in flight. 1892RCU cannot allow this situation to block grace periods: As long as 1893all the RCU read-side critical sections are finite, grace periods 1894must also be finite. 1895 1896<p> 1897That said, preemptible RCU implementations could potentially result 1898in RCU read-side critical sections being preempted for long durations, 1899which has the effect of creating a long-duration RCU read-side 1900critical section. 1901This situation can arise only in heavily loaded systems, but systems using 1902real-time priorities are of course more vulnerable. 1903Therefore, RCU priority boosting is provided to help deal with this 1904case. 1905That said, the exact requirements on RCU priority boosting will likely 1906evolve as more experience accumulates. 1907 1908<p> 1909Other workloads might have very high update rates. 1910Although one can argue that such workloads should instead use 1911something other than RCU, the fact remains that RCU must 1912handle such workloads gracefully. 1913This requirement is another factor driving batching of grace periods, 1914but it is also the driving force behind the checks for large numbers 1915of queued RCU callbacks in the <tt>call_rcu()</tt> code path. 1916Finally, high update rates should not delay RCU read-side critical 1917sections, although some small read-side delays can occur when using 1918<tt>synchronize_rcu_expedited()</tt>, courtesy of this function's use 1919of <tt>smp_call_function_single()</tt>. 1920 1921<p> 1922Although all three of these corner cases were understood in the early 19231990s, a simple user-level test consisting of <tt>close(open(path))</tt> 1924in a tight loop 1925in the early 2000s suddenly provided a much deeper appreciation of the 1926high-update-rate corner case. 1927This test also motivated addition of some RCU code to react to high update 1928rates, for example, if a given CPU finds itself with more than 10,000 1929RCU callbacks queued, it will cause RCU to take evasive action by 1930more aggressively starting grace periods and more aggressively forcing 1931completion of grace-period processing. 1932This evasive action causes the grace period to complete more quickly, 1933but at the cost of restricting RCU's batching optimizations, thus 1934increasing the CPU overhead incurred by that grace period. 1935 1936<h2><a name="Software-Engineering Requirements"> 1937Software-Engineering Requirements</a></h2> 1938 1939<p> 1940Between Murphy's Law and “To err is human”, it is necessary to 1941guard against mishaps and misuse: 1942 1943<ol> 1944<li> It is all too easy to forget to use <tt>rcu_read_lock()</tt> 1945 everywhere that it is needed, so kernels built with 1946 <tt>CONFIG_PROVE_RCU=y</tt> will splat if 1947 <tt>rcu_dereference()</tt> is used outside of an 1948 RCU read-side critical section. 1949 Update-side code can use <tt>rcu_dereference_protected()</tt>, 1950 which takes a 1951 <a href="https://lwn.net/Articles/371986/">lockdep expression</a> 1952 to indicate what is providing the protection. 1953 If the indicated protection is not provided, a lockdep splat 1954 is emitted. 1955 1956 <p> 1957 Code shared between readers and updaters can use 1958 <tt>rcu_dereference_check()</tt>, which also takes a 1959 lockdep expression, and emits a lockdep splat if neither 1960 <tt>rcu_read_lock()</tt> nor the indicated protection 1961 is in place. 1962 In addition, <tt>rcu_dereference_raw()</tt> is used in those 1963 (hopefully rare) cases where the required protection cannot 1964 be easily described. 1965 Finally, <tt>rcu_read_lock_held()</tt> is provided to 1966 allow a function to verify that it has been invoked within 1967 an RCU read-side critical section. 1968 I was made aware of this set of requirements shortly after Thomas 1969 Gleixner audited a number of RCU uses. 1970<li> A given function might wish to check for RCU-related preconditions 1971 upon entry, before using any other RCU API. 1972 The <tt>rcu_lockdep_assert()</tt> does this job, 1973 asserting the expression in kernels having lockdep enabled 1974 and doing nothing otherwise. 1975<li> It is also easy to forget to use <tt>rcu_assign_pointer()</tt> 1976 and <tt>rcu_dereference()</tt>, perhaps (incorrectly) 1977 substituting a simple assignment. 1978 To catch this sort of error, a given RCU-protected pointer may be 1979 tagged with <tt>__rcu</tt>, after which sparse 1980 will complain about simple-assignment accesses to that pointer. 1981 Arnd Bergmann made me aware of this requirement, and also 1982 supplied the needed 1983 <a href="https://lwn.net/Articles/376011/">patch series</a>. 1984<li> Kernels built with <tt>CONFIG_DEBUG_OBJECTS_RCU_HEAD=y</tt> 1985 will splat if a data element is passed to <tt>call_rcu()</tt> 1986 twice in a row, without a grace period in between. 1987 (This error is similar to a double free.) 1988 The corresponding <tt>rcu_head</tt> structures that are 1989 dynamically allocated are automatically tracked, but 1990 <tt>rcu_head</tt> structures allocated on the stack 1991 must be initialized with <tt>init_rcu_head_on_stack()</tt> 1992 and cleaned up with <tt>destroy_rcu_head_on_stack()</tt>. 1993 Similarly, statically allocated non-stack <tt>rcu_head</tt> 1994 structures must be initialized with <tt>init_rcu_head()</tt> 1995 and cleaned up with <tt>destroy_rcu_head()</tt>. 1996 Mathieu Desnoyers made me aware of this requirement, and also 1997 supplied the needed 1998 <a href="https://lkml.kernel.org/g/20100319013024.GA28456@Krystal">patch</a>. 1999<li> An infinite loop in an RCU read-side critical section will 2000 eventually trigger an RCU CPU stall warning splat, with 2001 the duration of “eventually” being controlled by the 2002 <tt>RCU_CPU_STALL_TIMEOUT</tt> <tt>Kconfig</tt> option, or, 2003 alternatively, by the 2004 <tt>rcupdate.rcu_cpu_stall_timeout</tt> boot/sysfs 2005 parameter. 2006 However, RCU is not obligated to produce this splat 2007 unless there is a grace period waiting on that particular 2008 RCU read-side critical section. 2009 <p> 2010 Some extreme workloads might intentionally delay 2011 RCU grace periods, and systems running those workloads can 2012 be booted with <tt>rcupdate.rcu_cpu_stall_suppress</tt> 2013 to suppress the splats. 2014 This kernel parameter may also be set via <tt>sysfs</tt>. 2015 Furthermore, RCU CPU stall warnings are counter-productive 2016 during sysrq dumps and during panics. 2017 RCU therefore supplies the <tt>rcu_sysrq_start()</tt> and 2018 <tt>rcu_sysrq_end()</tt> API members to be called before 2019 and after long sysrq dumps. 2020 RCU also supplies the <tt>rcu_panic()</tt> notifier that is 2021 automatically invoked at the beginning of a panic to suppress 2022 further RCU CPU stall warnings. 2023 2024 <p> 2025 This requirement made itself known in the early 1990s, pretty 2026 much the first time that it was necessary to debug a CPU stall. 2027 That said, the initial implementation in DYNIX/ptx was quite 2028 generic in comparison with that of Linux. 2029<li> Although it would be very good to detect pointers leaking out 2030 of RCU read-side critical sections, there is currently no 2031 good way of doing this. 2032 One complication is the need to distinguish between pointers 2033 leaking and pointers that have been handed off from RCU to 2034 some other synchronization mechanism, for example, reference 2035 counting. 2036<li> In kernels built with <tt>CONFIG_RCU_TRACE=y</tt>, RCU-related 2037 information is provided via event tracing. 2038<li> Open-coded use of <tt>rcu_assign_pointer()</tt> and 2039 <tt>rcu_dereference()</tt> to create typical linked 2040 data structures can be surprisingly error-prone. 2041 Therefore, RCU-protected 2042 <a href="https://lwn.net/Articles/609973/#RCU List APIs">linked lists</a> 2043 and, more recently, RCU-protected 2044 <a href="https://lwn.net/Articles/612100/">hash tables</a> 2045 are available. 2046 Many other special-purpose RCU-protected data structures are 2047 available in the Linux kernel and the userspace RCU library. 2048<li> Some linked structures are created at compile time, but still 2049 require <tt>__rcu</tt> checking. 2050 The <tt>RCU_POINTER_INITIALIZER()</tt> macro serves this 2051 purpose. 2052<li> It is not necessary to use <tt>rcu_assign_pointer()</tt> 2053 when creating linked structures that are to be published via 2054 a single external pointer. 2055 The <tt>RCU_INIT_POINTER()</tt> macro is provided for 2056 this task and also for assigning <tt>NULL</tt> pointers 2057 at runtime. 2058</ol> 2059 2060<p> 2061This not a hard-and-fast list: RCU's diagnostic capabilities will 2062continue to be guided by the number and type of usage bugs found 2063in real-world RCU usage. 2064 2065<h2><a name="Linux Kernel Complications">Linux Kernel Complications</a></h2> 2066 2067<p> 2068The Linux kernel provides an interesting environment for all kinds of 2069software, including RCU. 2070Some of the relevant points of interest are as follows: 2071 2072<ol> 2073<li> <a href="#Configuration">Configuration</a>. 2074<li> <a href="#Firmware Interface">Firmware Interface</a>. 2075<li> <a href="#Early Boot">Early Boot</a>. 2076<li> <a href="#Interrupts and NMIs"> 2077 Interrupts and non-maskable interrupts (NMIs)</a>. 2078<li> <a href="#Loadable Modules">Loadable Modules</a>. 2079<li> <a href="#Hotplug CPU">Hotplug CPU</a>. 2080<li> <a href="#Scheduler and RCU">Scheduler and RCU</a>. 2081<li> <a href="#Tracing and RCU">Tracing and RCU</a>. 2082<li> <a href="#Energy Efficiency">Energy Efficiency</a>. 2083<li> <a href="#Scheduling-Clock Interrupts and RCU"> 2084 Scheduling-Clock Interrupts and RCU</a>. 2085<li> <a href="#Memory Efficiency">Memory Efficiency</a>. 2086<li> <a href="#Performance, Scalability, Response Time, and Reliability"> 2087 Performance, Scalability, Response Time, and Reliability</a>. 2088</ol> 2089 2090<p> 2091This list is probably incomplete, but it does give a feel for the 2092most notable Linux-kernel complications. 2093Each of the following sections covers one of the above topics. 2094 2095<h3><a name="Configuration">Configuration</a></h3> 2096 2097<p> 2098RCU's goal is automatic configuration, so that almost nobody 2099needs to worry about RCU's <tt>Kconfig</tt> options. 2100And for almost all users, RCU does in fact work well 2101“out of the box.” 2102 2103<p> 2104However, there are specialized use cases that are handled by 2105kernel boot parameters and <tt>Kconfig</tt> options. 2106Unfortunately, the <tt>Kconfig</tt> system will explicitly ask users 2107about new <tt>Kconfig</tt> options, which requires almost all of them 2108be hidden behind a <tt>CONFIG_RCU_EXPERT</tt> <tt>Kconfig</tt> option. 2109 2110<p> 2111This all should be quite obvious, but the fact remains that 2112Linus Torvalds recently had to 2113<a href="https://lkml.kernel.org/g/CA+55aFy4wcCwaL4okTs8wXhGZ5h-ibecy_Meg9C4MNQrUnwMcg@mail.gmail.com">remind</a> 2114me of this requirement. 2115 2116<h3><a name="Firmware Interface">Firmware Interface</a></h3> 2117 2118<p> 2119In many cases, kernel obtains information about the system from the 2120firmware, and sometimes things are lost in translation. 2121Or the translation is accurate, but the original message is bogus. 2122 2123<p> 2124For example, some systems' firmware overreports the number of CPUs, 2125sometimes by a large factor. 2126If RCU naively believed the firmware, as it used to do, 2127it would create too many per-CPU kthreads. 2128Although the resulting system will still run correctly, the extra 2129kthreads needlessly consume memory and can cause confusion 2130when they show up in <tt>ps</tt> listings. 2131 2132<p> 2133RCU must therefore wait for a given CPU to actually come online before 2134it can allow itself to believe that the CPU actually exists. 2135The resulting “ghost CPUs” (which are never going to 2136come online) cause a number of 2137<a href="https://paulmck.livejournal.com/37494.html">interesting complications</a>. 2138 2139<h3><a name="Early Boot">Early Boot</a></h3> 2140 2141<p> 2142The Linux kernel's boot sequence is an interesting process, 2143and RCU is used early, even before <tt>rcu_init()</tt> 2144is invoked. 2145In fact, a number of RCU's primitives can be used as soon as the 2146initial task's <tt>task_struct</tt> is available and the 2147boot CPU's per-CPU variables are set up. 2148The read-side primitives (<tt>rcu_read_lock()</tt>, 2149<tt>rcu_read_unlock()</tt>, <tt>rcu_dereference()</tt>, 2150and <tt>rcu_access_pointer()</tt>) will operate normally very early on, 2151as will <tt>rcu_assign_pointer()</tt>. 2152 2153<p> 2154Although <tt>call_rcu()</tt> may be invoked at any 2155time during boot, callbacks are not guaranteed to be invoked until after 2156all of RCU's kthreads have been spawned, which occurs at 2157<tt>early_initcall()</tt> time. 2158This delay in callback invocation is due to the fact that RCU does not 2159invoke callbacks until it is fully initialized, and this full initialization 2160cannot occur until after the scheduler has initialized itself to the 2161point where RCU can spawn and run its kthreads. 2162In theory, it would be possible to invoke callbacks earlier, 2163however, this is not a panacea because there would be severe restrictions 2164on what operations those callbacks could invoke. 2165 2166<p> 2167Perhaps surprisingly, <tt>synchronize_rcu()</tt>, 2168<a href="#Bottom-Half Flavor"><tt>synchronize_rcu_bh()</tt></a> 2169(<a href="#Bottom-Half Flavor">discussed below</a>), 2170<a href="#Sched Flavor"><tt>synchronize_sched()</tt></a>, 2171<tt>synchronize_rcu_expedited()</tt>, 2172<tt>synchronize_rcu_bh_expedited()</tt>, and 2173<tt>synchronize_sched_expedited()</tt> 2174will all operate normally 2175during very early boot, the reason being that there is only one CPU 2176and preemption is disabled. 2177This means that the call <tt>synchronize_rcu()</tt> (or friends) 2178itself is a quiescent 2179state and thus a grace period, so the early-boot implementation can 2180be a no-op. 2181 2182<p> 2183However, once the scheduler has spawned its first kthread, this early 2184boot trick fails for <tt>synchronize_rcu()</tt> (as well as for 2185<tt>synchronize_rcu_expedited()</tt>) in <tt>CONFIG_PREEMPT=y</tt> 2186kernels. 2187The reason is that an RCU read-side critical section might be preempted, 2188which means that a subsequent <tt>synchronize_rcu()</tt> really does have 2189to wait for something, as opposed to simply returning immediately. 2190Unfortunately, <tt>synchronize_rcu()</tt> can't do this until all of 2191its kthreads are spawned, which doesn't happen until some time during 2192<tt>early_initcalls()</tt> time. 2193But this is no excuse: RCU is nevertheless required to correctly handle 2194synchronous grace periods during this time period. 2195Once all of its kthreads are up and running, RCU starts running 2196normally. 2197 2198<table> 2199<tr><th> </th></tr> 2200<tr><th align="left">Quick Quiz:</th></tr> 2201<tr><td> 2202 How can RCU possibly handle grace periods before all of its 2203 kthreads have been spawned??? 2204</td></tr> 2205<tr><th align="left">Answer:</th></tr> 2206<tr><td bgcolor="#ffffff"><font color="ffffff"> 2207 Very carefully! 2208 </font> 2209 2210 <p><font color="ffffff"> 2211 During the “dead zone” between the time that the 2212 scheduler spawns the first task and the time that all of RCU's 2213 kthreads have been spawned, all synchronous grace periods are 2214 handled by the expedited grace-period mechanism. 2215 At runtime, this expedited mechanism relies on workqueues, but 2216 during the dead zone the requesting task itself drives the 2217 desired expedited grace period. 2218 Because dead-zone execution takes place within task context, 2219 everything works. 2220 Once the dead zone ends, expedited grace periods go back to 2221 using workqueues, as is required to avoid problems that would 2222 otherwise occur when a user task received a POSIX signal while 2223 driving an expedited grace period. 2224 </font> 2225 2226 <p><font color="ffffff"> 2227 And yes, this does mean that it is unhelpful to send POSIX 2228 signals to random tasks between the time that the scheduler 2229 spawns its first kthread and the time that RCU's kthreads 2230 have all been spawned. 2231 If there ever turns out to be a good reason for sending POSIX 2232 signals during that time, appropriate adjustments will be made. 2233 (If it turns out that POSIX signals are sent during this time for 2234 no good reason, other adjustments will be made, appropriate 2235 or otherwise.) 2236</font></td></tr> 2237<tr><td> </td></tr> 2238</table> 2239 2240<p> 2241I learned of these boot-time requirements as a result of a series of 2242system hangs. 2243 2244<h3><a name="Interrupts and NMIs">Interrupts and NMIs</a></h3> 2245 2246<p> 2247The Linux kernel has interrupts, and RCU read-side critical sections are 2248legal within interrupt handlers and within interrupt-disabled regions 2249of code, as are invocations of <tt>call_rcu()</tt>. 2250 2251<p> 2252Some Linux-kernel architectures can enter an interrupt handler from 2253non-idle process context, and then just never leave it, instead stealthily 2254transitioning back to process context. 2255This trick is sometimes used to invoke system calls from inside the kernel. 2256These “half-interrupts” mean that RCU has to be very careful 2257about how it counts interrupt nesting levels. 2258I learned of this requirement the hard way during a rewrite 2259of RCU's dyntick-idle code. 2260 2261<p> 2262The Linux kernel has non-maskable interrupts (NMIs), and 2263RCU read-side critical sections are legal within NMI handlers. 2264Thankfully, RCU update-side primitives, including 2265<tt>call_rcu()</tt>, are prohibited within NMI handlers. 2266 2267<p> 2268The name notwithstanding, some Linux-kernel architectures 2269can have nested NMIs, which RCU must handle correctly. 2270Andy Lutomirski 2271<a href="https://lkml.kernel.org/g/CALCETrXLq1y7e_dKFPgou-FKHB6Pu-r8+t-6Ds+8=va7anBWDA@mail.gmail.com">surprised me</a> 2272with this requirement; 2273he also kindly surprised me with 2274<a href="https://lkml.kernel.org/g/CALCETrXSY9JpW3uE6H8WYk81sg56qasA2aqmjMPsq5dOtzso=g@mail.gmail.com">an algorithm</a> 2275that meets this requirement. 2276 2277<h3><a name="Loadable Modules">Loadable Modules</a></h3> 2278 2279<p> 2280The Linux kernel has loadable modules, and these modules can 2281also be unloaded. 2282After a given module has been unloaded, any attempt to call 2283one of its functions results in a segmentation fault. 2284The module-unload functions must therefore cancel any 2285delayed calls to loadable-module functions, for example, 2286any outstanding <tt>mod_timer()</tt> must be dealt with 2287via <tt>del_timer_sync()</tt> or similar. 2288 2289<p> 2290Unfortunately, there is no way to cancel an RCU callback; 2291once you invoke <tt>call_rcu()</tt>, the callback function is 2292going to eventually be invoked, unless the system goes down first. 2293Because it is normally considered socially irresponsible to crash the system 2294in response to a module unload request, we need some other way 2295to deal with in-flight RCU callbacks. 2296 2297<p> 2298RCU therefore provides 2299<tt><a href="https://lwn.net/Articles/217484/">rcu_barrier()</a></tt>, 2300which waits until all in-flight RCU callbacks have been invoked. 2301If a module uses <tt>call_rcu()</tt>, its exit function should therefore 2302prevent any future invocation of <tt>call_rcu()</tt>, then invoke 2303<tt>rcu_barrier()</tt>. 2304In theory, the underlying module-unload code could invoke 2305<tt>rcu_barrier()</tt> unconditionally, but in practice this would 2306incur unacceptable latencies. 2307 2308<p> 2309Nikita Danilov noted this requirement for an analogous filesystem-unmount 2310situation, and Dipankar Sarma incorporated <tt>rcu_barrier()</tt> into RCU. 2311The need for <tt>rcu_barrier()</tt> for module unloading became 2312apparent later. 2313 2314<p> 2315<b>Important note</b>: The <tt>rcu_barrier()</tt> function is not, 2316repeat, <i>not</i>, obligated to wait for a grace period. 2317It is instead only required to wait for RCU callbacks that have 2318already been posted. 2319Therefore, if there are no RCU callbacks posted anywhere in the system, 2320<tt>rcu_barrier()</tt> is within its rights to return immediately. 2321Even if there are callbacks posted, <tt>rcu_barrier()</tt> does not 2322necessarily need to wait for a grace period. 2323 2324<table> 2325<tr><th> </th></tr> 2326<tr><th align="left">Quick Quiz:</th></tr> 2327<tr><td> 2328 Wait a minute! 2329 Each RCU callbacks must wait for a grace period to complete, 2330 and <tt>rcu_barrier()</tt> must wait for each pre-existing 2331 callback to be invoked. 2332 Doesn't <tt>rcu_barrier()</tt> therefore need to wait for 2333 a full grace period if there is even one callback posted anywhere 2334 in the system? 2335</td></tr> 2336<tr><th align="left">Answer:</th></tr> 2337<tr><td bgcolor="#ffffff"><font color="ffffff"> 2338 Absolutely not!!! 2339 </font> 2340 2341 <p><font color="ffffff"> 2342 Yes, each RCU callbacks must wait for a grace period to complete, 2343 but it might well be partly (or even completely) finished waiting 2344 by the time <tt>rcu_barrier()</tt> is invoked. 2345 In that case, <tt>rcu_barrier()</tt> need only wait for the 2346 remaining portion of the grace period to elapse. 2347 So even if there are quite a few callbacks posted, 2348 <tt>rcu_barrier()</tt> might well return quite quickly. 2349 </font> 2350 2351 <p><font color="ffffff"> 2352 So if you need to wait for a grace period as well as for all 2353 pre-existing callbacks, you will need to invoke both 2354 <tt>synchronize_rcu()</tt> and <tt>rcu_barrier()</tt>. 2355 If latency is a concern, you can always use workqueues 2356 to invoke them concurrently. 2357</font></td></tr> 2358<tr><td> </td></tr> 2359</table> 2360 2361<h3><a name="Hotplug CPU">Hotplug CPU</a></h3> 2362 2363<p> 2364The Linux kernel supports CPU hotplug, which means that CPUs 2365can come and go. 2366It is of course illegal to use any RCU API member from an offline CPU, 2367with the exception of <a href="#Sleepable RCU">SRCU</a> read-side 2368critical sections. 2369This requirement was present from day one in DYNIX/ptx, but 2370on the other hand, the Linux kernel's CPU-hotplug implementation 2371is “interesting.” 2372 2373<p> 2374The Linux-kernel CPU-hotplug implementation has notifiers that 2375are used to allow the various kernel subsystems (including RCU) 2376to respond appropriately to a given CPU-hotplug operation. 2377Most RCU operations may be invoked from CPU-hotplug notifiers, 2378including even synchronous grace-period operations such as 2379<tt>synchronize_rcu()</tt> and <tt>synchronize_rcu_expedited()</tt>. 2380 2381<p> 2382However, all-callback-wait operations such as 2383<tt>rcu_barrier()</tt> are also not supported, due to the 2384fact that there are phases of CPU-hotplug operations where 2385the outgoing CPU's callbacks will not be invoked until after 2386the CPU-hotplug operation ends, which could also result in deadlock. 2387Furthermore, <tt>rcu_barrier()</tt> blocks CPU-hotplug operations 2388during its execution, which results in another type of deadlock 2389when invoked from a CPU-hotplug notifier. 2390 2391<h3><a name="Scheduler and RCU">Scheduler and RCU</a></h3> 2392 2393<p> 2394RCU depends on the scheduler, and the scheduler uses RCU to 2395protect some of its data structures. 2396This means the scheduler is forbidden from acquiring 2397the runqueue locks and the priority-inheritance locks 2398in the middle of an outermost RCU read-side critical section unless either 2399(1) it releases them before exiting that same 2400RCU read-side critical section, or 2401(2) interrupts are disabled across 2402that entire RCU read-side critical section. 2403This same prohibition also applies (recursively!) to any lock that is acquired 2404while holding any lock to which this prohibition applies. 2405Adhering to this rule prevents preemptible RCU from invoking 2406<tt>rcu_read_unlock_special()</tt> while either runqueue or 2407priority-inheritance locks are held, thus avoiding deadlock. 2408 2409<p> 2410Prior to v4.4, it was only necessary to disable preemption across 2411RCU read-side critical sections that acquired scheduler locks. 2412In v4.4, expedited grace periods started using IPIs, and these 2413IPIs could force a <tt>rcu_read_unlock()</tt> to take the slowpath. 2414Therefore, this expedited-grace-period change required disabling of 2415interrupts, not just preemption. 2416 2417<p> 2418For RCU's part, the preemptible-RCU <tt>rcu_read_unlock()</tt> 2419implementation must be written carefully to avoid similar deadlocks. 2420In particular, <tt>rcu_read_unlock()</tt> must tolerate an 2421interrupt where the interrupt handler invokes both 2422<tt>rcu_read_lock()</tt> and <tt>rcu_read_unlock()</tt>. 2423This possibility requires <tt>rcu_read_unlock()</tt> to use 2424negative nesting levels to avoid destructive recursion via 2425interrupt handler's use of RCU. 2426 2427<p> 2428This pair of mutual scheduler-RCU requirements came as a 2429<a href="https://lwn.net/Articles/453002/">complete surprise</a>. 2430 2431<p> 2432As noted above, RCU makes use of kthreads, and it is necessary to 2433avoid excessive CPU-time accumulation by these kthreads. 2434This requirement was no surprise, but RCU's violation of it 2435when running context-switch-heavy workloads when built with 2436<tt>CONFIG_NO_HZ_FULL=y</tt> 2437<a href="http://www.rdrop.com/users/paulmck/scalability/paper/BareMetal.2015.01.15b.pdf">did come as a surprise [PDF]</a>. 2438RCU has made good progress towards meeting this requirement, even 2439for context-switch-have <tt>CONFIG_NO_HZ_FULL=y</tt> workloads, 2440but there is room for further improvement. 2441 2442<h3><a name="Tracing and RCU">Tracing and RCU</a></h3> 2443 2444<p> 2445It is possible to use tracing on RCU code, but tracing itself 2446uses RCU. 2447For this reason, <tt>rcu_dereference_raw_notrace()</tt> 2448is provided for use by tracing, which avoids the destructive 2449recursion that could otherwise ensue. 2450This API is also used by virtualization in some architectures, 2451where RCU readers execute in environments in which tracing 2452cannot be used. 2453The tracing folks both located the requirement and provided the 2454needed fix, so this surprise requirement was relatively painless. 2455 2456<h3><a name="Energy Efficiency">Energy Efficiency</a></h3> 2457 2458<p> 2459Interrupting idle CPUs is considered socially unacceptable, 2460especially by people with battery-powered embedded systems. 2461RCU therefore conserves energy by detecting which CPUs are 2462idle, including tracking CPUs that have been interrupted from idle. 2463This is a large part of the energy-efficiency requirement, 2464so I learned of this via an irate phone call. 2465 2466<p> 2467Because RCU avoids interrupting idle CPUs, it is illegal to 2468execute an RCU read-side critical section on an idle CPU. 2469(Kernels built with <tt>CONFIG_PROVE_RCU=y</tt> will splat 2470if you try it.) 2471The <tt>RCU_NONIDLE()</tt> macro and <tt>_rcuidle</tt> 2472event tracing is provided to work around this restriction. 2473In addition, <tt>rcu_is_watching()</tt> may be used to 2474test whether or not it is currently legal to run RCU read-side 2475critical sections on this CPU. 2476I learned of the need for diagnostics on the one hand 2477and <tt>RCU_NONIDLE()</tt> on the other while inspecting 2478idle-loop code. 2479Steven Rostedt supplied <tt>_rcuidle</tt> event tracing, 2480which is used quite heavily in the idle loop. 2481However, there are some restrictions on the code placed within 2482<tt>RCU_NONIDLE()</tt>: 2483 2484<ol> 2485<li> Blocking is prohibited. 2486 In practice, this is not a serious restriction given that idle 2487 tasks are prohibited from blocking to begin with. 2488<li> Although nesting <tt>RCU_NONIDLE()</tt> is permitted, they cannot 2489 nest indefinitely deeply. 2490 However, given that they can be nested on the order of a million 2491 deep, even on 32-bit systems, this should not be a serious 2492 restriction. 2493 This nesting limit would probably be reached long after the 2494 compiler OOMed or the stack overflowed. 2495<li> Any code path that enters <tt>RCU_NONIDLE()</tt> must sequence 2496 out of that same <tt>RCU_NONIDLE()</tt>. 2497 For example, the following is grossly illegal: 2498 2499 <blockquote> 2500 <pre> 2501 1 RCU_NONIDLE({ 2502 2 do_something(); 2503 3 goto bad_idea; /* BUG!!! */ 2504 4 do_something_else();}); 2505 5 bad_idea: 2506 </pre> 2507 </blockquote> 2508 2509 <p> 2510 It is just as illegal to transfer control into the middle of 2511 <tt>RCU_NONIDLE()</tt>'s argument. 2512 Yes, in theory, you could transfer in as long as you also 2513 transferred out, but in practice you could also expect to get sharply 2514 worded review comments. 2515</ol> 2516 2517<p> 2518It is similarly socially unacceptable to interrupt an 2519<tt>nohz_full</tt> CPU running in userspace. 2520RCU must therefore track <tt>nohz_full</tt> userspace 2521execution. 2522RCU must therefore be able to sample state at two points in 2523time, and be able to determine whether or not some other CPU spent 2524any time idle and/or executing in userspace. 2525 2526<p> 2527These energy-efficiency requirements have proven quite difficult to 2528understand and to meet, for example, there have been more than five 2529clean-sheet rewrites of RCU's energy-efficiency code, the last of 2530which was finally able to demonstrate 2531<a href="http://www.rdrop.com/users/paulmck/realtime/paper/AMPenergy.2013.04.19a.pdf">real energy savings running on real hardware [PDF]</a>. 2532As noted earlier, 2533I learned of many of these requirements via angry phone calls: 2534Flaming me on the Linux-kernel mailing list was apparently not 2535sufficient to fully vent their ire at RCU's energy-efficiency bugs! 2536 2537<h3><a name="Scheduling-Clock Interrupts and RCU"> 2538Scheduling-Clock Interrupts and RCU</a></h3> 2539 2540<p> 2541The kernel transitions between in-kernel non-idle execution, userspace 2542execution, and the idle loop. 2543Depending on kernel configuration, RCU handles these states differently: 2544 2545<table border=3> 2546<tr><th><tt>HZ</tt> Kconfig</th> 2547 <th>In-Kernel</th> 2548 <th>Usermode</th> 2549 <th>Idle</th></tr> 2550<tr><th align="left"><tt>HZ_PERIODIC</tt></th> 2551 <td>Can rely on scheduling-clock interrupt.</td> 2552 <td>Can rely on scheduling-clock interrupt and its 2553 detection of interrupt from usermode.</td> 2554 <td>Can rely on RCU's dyntick-idle detection.</td></tr> 2555<tr><th align="left"><tt>NO_HZ_IDLE</tt></th> 2556 <td>Can rely on scheduling-clock interrupt.</td> 2557 <td>Can rely on scheduling-clock interrupt and its 2558 detection of interrupt from usermode.</td> 2559 <td>Can rely on RCU's dyntick-idle detection.</td></tr> 2560<tr><th align="left"><tt>NO_HZ_FULL</tt></th> 2561 <td>Can only sometimes rely on scheduling-clock interrupt. 2562 In other cases, it is necessary to bound kernel execution 2563 times and/or use IPIs.</td> 2564 <td>Can rely on RCU's dyntick-idle detection.</td> 2565 <td>Can rely on RCU's dyntick-idle detection.</td></tr> 2566</table> 2567 2568<table> 2569<tr><th> </th></tr> 2570<tr><th align="left">Quick Quiz:</th></tr> 2571<tr><td> 2572 Why can't <tt>NO_HZ_FULL</tt> in-kernel execution rely on the 2573 scheduling-clock interrupt, just like <tt>HZ_PERIODIC</tt> 2574 and <tt>NO_HZ_IDLE</tt> do? 2575</td></tr> 2576<tr><th align="left">Answer:</th></tr> 2577<tr><td bgcolor="#ffffff"><font color="ffffff"> 2578 Because, as a performance optimization, <tt>NO_HZ_FULL</tt> 2579 does not necessarily re-enable the scheduling-clock interrupt 2580 on entry to each and every system call. 2581</font></td></tr> 2582<tr><td> </td></tr> 2583</table> 2584 2585<p> 2586However, RCU must be reliably informed as to whether any given 2587CPU is currently in the idle loop, and, for <tt>NO_HZ_FULL</tt>, 2588also whether that CPU is executing in usermode, as discussed 2589<a href="#Energy Efficiency">earlier</a>. 2590It also requires that the scheduling-clock interrupt be enabled when 2591RCU needs it to be: 2592 2593<ol> 2594<li> If a CPU is either idle or executing in usermode, and RCU believes 2595 it is non-idle, the scheduling-clock tick had better be running. 2596 Otherwise, you will get RCU CPU stall warnings. Or at best, 2597 very long (11-second) grace periods, with a pointless IPI waking 2598 the CPU from time to time. 2599<li> If a CPU is in a portion of the kernel that executes RCU read-side 2600 critical sections, and RCU believes this CPU to be idle, you will get 2601 random memory corruption. <b>DON'T DO THIS!!!</b> 2602 2603 <br>This is one reason to test with lockdep, which will complain 2604 about this sort of thing. 2605<li> If a CPU is in a portion of the kernel that is absolutely 2606 positively no-joking guaranteed to never execute any RCU read-side 2607 critical sections, and RCU believes this CPU to to be idle, 2608 no problem. This sort of thing is used by some architectures 2609 for light-weight exception handlers, which can then avoid the 2610 overhead of <tt>rcu_irq_enter()</tt> and <tt>rcu_irq_exit()</tt> 2611 at exception entry and exit, respectively. 2612 Some go further and avoid the entireties of <tt>irq_enter()</tt> 2613 and <tt>irq_exit()</tt>. 2614 2615 <br>Just make very sure you are running some of your tests with 2616 <tt>CONFIG_PROVE_RCU=y</tt>, just in case one of your code paths 2617 was in fact joking about not doing RCU read-side critical sections. 2618<li> If a CPU is executing in the kernel with the scheduling-clock 2619 interrupt disabled and RCU believes this CPU to be non-idle, 2620 and if the CPU goes idle (from an RCU perspective) every few 2621 jiffies, no problem. It is usually OK for there to be the 2622 occasional gap between idle periods of up to a second or so. 2623 2624 <br>If the gap grows too long, you get RCU CPU stall warnings. 2625<li> If a CPU is either idle or executing in usermode, and RCU believes 2626 it to be idle, of course no problem. 2627<li> If a CPU is executing in the kernel, the kernel code 2628 path is passing through quiescent states at a reasonable 2629 frequency (preferably about once per few jiffies, but the 2630 occasional excursion to a second or so is usually OK) and the 2631 scheduling-clock interrupt is enabled, of course no problem. 2632 2633 <br>If the gap between a successive pair of quiescent states grows 2634 too long, you get RCU CPU stall warnings. 2635</ol> 2636 2637<table> 2638<tr><th> </th></tr> 2639<tr><th align="left">Quick Quiz:</th></tr> 2640<tr><td> 2641 But what if my driver has a hardware interrupt handler 2642 that can run for many seconds? 2643 I cannot invoke <tt>schedule()</tt> from an hardware 2644 interrupt handler, after all! 2645</td></tr> 2646<tr><th align="left">Answer:</th></tr> 2647<tr><td bgcolor="#ffffff"><font color="ffffff"> 2648 One approach is to do <tt>rcu_irq_exit();rcu_irq_enter();</tt> 2649 every so often. 2650 But given that long-running interrupt handlers can cause 2651 other problems, not least for response time, shouldn't you 2652 work to keep your interrupt handler's runtime within reasonable 2653 bounds? 2654</font></td></tr> 2655<tr><td> </td></tr> 2656</table> 2657 2658<p> 2659But as long as RCU is properly informed of kernel state transitions between 2660in-kernel execution, usermode execution, and idle, and as long as the 2661scheduling-clock interrupt is enabled when RCU needs it to be, you 2662can rest assured that the bugs you encounter will be in some other 2663part of RCU or some other part of the kernel! 2664 2665<h3><a name="Memory Efficiency">Memory Efficiency</a></h3> 2666 2667<p> 2668Although small-memory non-realtime systems can simply use Tiny RCU, 2669code size is only one aspect of memory efficiency. 2670Another aspect is the size of the <tt>rcu_head</tt> structure 2671used by <tt>call_rcu()</tt> and <tt>kfree_rcu()</tt>. 2672Although this structure contains nothing more than a pair of pointers, 2673it does appear in many RCU-protected data structures, including 2674some that are size critical. 2675The <tt>page</tt> structure is a case in point, as evidenced by 2676the many occurrences of the <tt>union</tt> keyword within that structure. 2677 2678<p> 2679This need for memory efficiency is one reason that RCU uses hand-crafted 2680singly linked lists to track the <tt>rcu_head</tt> structures that 2681are waiting for a grace period to elapse. 2682It is also the reason why <tt>rcu_head</tt> structures do not contain 2683debug information, such as fields tracking the file and line of the 2684<tt>call_rcu()</tt> or <tt>kfree_rcu()</tt> that posted them. 2685Although this information might appear in debug-only kernel builds at some 2686point, in the meantime, the <tt>->func</tt> field will often provide 2687the needed debug information. 2688 2689<p> 2690However, in some cases, the need for memory efficiency leads to even 2691more extreme measures. 2692Returning to the <tt>page</tt> structure, the <tt>rcu_head</tt> field 2693shares storage with a great many other structures that are used at 2694various points in the corresponding page's lifetime. 2695In order to correctly resolve certain 2696<a href="https://lkml.kernel.org/g/1439976106-137226-1-git-send-email-kirill.shutemov@linux.intel.com">race conditions</a>, 2697the Linux kernel's memory-management subsystem needs a particular bit 2698to remain zero during all phases of grace-period processing, 2699and that bit happens to map to the bottom bit of the 2700<tt>rcu_head</tt> structure's <tt>->next</tt> field. 2701RCU makes this guarantee as long as <tt>call_rcu()</tt> 2702is used to post the callback, as opposed to <tt>kfree_rcu()</tt> 2703or some future “lazy” 2704variant of <tt>call_rcu()</tt> that might one day be created for 2705energy-efficiency purposes. 2706 2707<p> 2708That said, there are limits. 2709RCU requires that the <tt>rcu_head</tt> structure be aligned to a 2710two-byte boundary, and passing a misaligned <tt>rcu_head</tt> 2711structure to one of the <tt>call_rcu()</tt> family of functions 2712will result in a splat. 2713It is therefore necessary to exercise caution when packing 2714structures containing fields of type <tt>rcu_head</tt>. 2715Why not a four-byte or even eight-byte alignment requirement? 2716Because the m68k architecture provides only two-byte alignment, 2717and thus acts as alignment's least common denominator. 2718 2719<p> 2720The reason for reserving the bottom bit of pointers to 2721<tt>rcu_head</tt> structures is to leave the door open to 2722“lazy” callbacks whose invocations can safely be deferred. 2723Deferring invocation could potentially have energy-efficiency 2724benefits, but only if the rate of non-lazy callbacks decreases 2725significantly for some important workload. 2726In the meantime, reserving the bottom bit keeps this option open 2727in case it one day becomes useful. 2728 2729<h3><a name="Performance, Scalability, Response Time, and Reliability"> 2730Performance, Scalability, Response Time, and Reliability</a></h3> 2731 2732<p> 2733Expanding on the 2734<a href="#Performance and Scalability">earlier discussion</a>, 2735RCU is used heavily by hot code paths in performance-critical 2736portions of the Linux kernel's networking, security, virtualization, 2737and scheduling code paths. 2738RCU must therefore use efficient implementations, especially in its 2739read-side primitives. 2740To that end, it would be good if preemptible RCU's implementation 2741of <tt>rcu_read_lock()</tt> could be inlined, however, doing 2742this requires resolving <tt>#include</tt> issues with the 2743<tt>task_struct</tt> structure. 2744 2745<p> 2746The Linux kernel supports hardware configurations with up to 27474096 CPUs, which means that RCU must be extremely scalable. 2748Algorithms that involve frequent acquisitions of global locks or 2749frequent atomic operations on global variables simply cannot be 2750tolerated within the RCU implementation. 2751RCU therefore makes heavy use of a combining tree based on the 2752<tt>rcu_node</tt> structure. 2753RCU is required to tolerate all CPUs continuously invoking any 2754combination of RCU's runtime primitives with minimal per-operation 2755overhead. 2756In fact, in many cases, increasing load must <i>decrease</i> the 2757per-operation overhead, witness the batching optimizations for 2758<tt>synchronize_rcu()</tt>, <tt>call_rcu()</tt>, 2759<tt>synchronize_rcu_expedited()</tt>, and <tt>rcu_barrier()</tt>. 2760As a general rule, RCU must cheerfully accept whatever the 2761rest of the Linux kernel decides to throw at it. 2762 2763<p> 2764The Linux kernel is used for real-time workloads, especially 2765in conjunction with the 2766<a href="https://rt.wiki.kernel.org/index.php/Main_Page">-rt patchset</a>. 2767The real-time-latency response requirements are such that the 2768traditional approach of disabling preemption across RCU 2769read-side critical sections is inappropriate. 2770Kernels built with <tt>CONFIG_PREEMPT=y</tt> therefore 2771use an RCU implementation that allows RCU read-side critical 2772sections to be preempted. 2773This requirement made its presence known after users made it 2774clear that an earlier 2775<a href="https://lwn.net/Articles/107930/">real-time patch</a> 2776did not meet their needs, in conjunction with some 2777<a href="https://lkml.kernel.org/g/20050318002026.GA2693@us.ibm.com">RCU issues</a> 2778encountered by a very early version of the -rt patchset. 2779 2780<p> 2781In addition, RCU must make do with a sub-100-microsecond real-time latency 2782budget. 2783In fact, on smaller systems with the -rt patchset, the Linux kernel 2784provides sub-20-microsecond real-time latencies for the whole kernel, 2785including RCU. 2786RCU's scalability and latency must therefore be sufficient for 2787these sorts of configurations. 2788To my surprise, the sub-100-microsecond real-time latency budget 2789<a href="http://www.rdrop.com/users/paulmck/realtime/paper/bigrt.2013.01.31a.LCA.pdf"> 2790applies to even the largest systems [PDF]</a>, 2791up to and including systems with 4096 CPUs. 2792This real-time requirement motivated the grace-period kthread, which 2793also simplified handling of a number of race conditions. 2794 2795<p> 2796RCU must avoid degrading real-time response for CPU-bound threads, whether 2797executing in usermode (which is one use case for 2798<tt>CONFIG_NO_HZ_FULL=y</tt>) or in the kernel. 2799That said, CPU-bound loops in the kernel must execute 2800<tt>cond_resched_rcu_qs()</tt> at least once per few tens of milliseconds 2801in order to avoid receiving an IPI from RCU. 2802 2803<p> 2804Finally, RCU's status as a synchronization primitive means that 2805any RCU failure can result in arbitrary memory corruption that can be 2806extremely difficult to debug. 2807This means that RCU must be extremely reliable, which in 2808practice also means that RCU must have an aggressive stress-test 2809suite. 2810This stress-test suite is called <tt>rcutorture</tt>. 2811 2812<p> 2813Although the need for <tt>rcutorture</tt> was no surprise, 2814the current immense popularity of the Linux kernel is posing 2815interesting—and perhaps unprecedented—validation 2816challenges. 2817To see this, keep in mind that there are well over one billion 2818instances of the Linux kernel running today, given Android 2819smartphones, Linux-powered televisions, and servers. 2820This number can be expected to increase sharply with the advent of 2821the celebrated Internet of Things. 2822 2823<p> 2824Suppose that RCU contains a race condition that manifests on average 2825once per million years of runtime. 2826This bug will be occurring about three times per <i>day</i> across 2827the installed base. 2828RCU could simply hide behind hardware error rates, given that no one 2829should really expect their smartphone to last for a million years. 2830However, anyone taking too much comfort from this thought should 2831consider the fact that in most jurisdictions, a successful multi-year 2832test of a given mechanism, which might include a Linux kernel, 2833suffices for a number of types of safety-critical certifications. 2834In fact, rumor has it that the Linux kernel is already being used 2835in production for safety-critical applications. 2836I don't know about you, but I would feel quite bad if a bug in RCU 2837killed someone. 2838Which might explain my recent focus on validation and verification. 2839 2840<h2><a name="Other RCU Flavors">Other RCU Flavors</a></h2> 2841 2842<p> 2843One of the more surprising things about RCU is that there are now 2844no fewer than five <i>flavors</i>, or API families. 2845In addition, the primary flavor that has been the sole focus up to 2846this point has two different implementations, non-preemptible and 2847preemptible. 2848The other four flavors are listed below, with requirements for each 2849described in a separate section. 2850 2851<ol> 2852<li> <a href="#Bottom-Half Flavor">Bottom-Half Flavor</a> 2853<li> <a href="#Sched Flavor">Sched Flavor</a> 2854<li> <a href="#Sleepable RCU">Sleepable RCU</a> 2855<li> <a href="#Tasks RCU">Tasks RCU</a> 2856<li> <a href="#Waiting for Multiple Grace Periods"> 2857 Waiting for Multiple Grace Periods</a> 2858</ol> 2859 2860<h3><a name="Bottom-Half Flavor">Bottom-Half Flavor</a></h3> 2861 2862<p> 2863The softirq-disable (AKA “bottom-half”, 2864hence the “_bh” abbreviations) 2865flavor of RCU, or <i>RCU-bh</i>, was developed by 2866Dipankar Sarma to provide a flavor of RCU that could withstand the 2867network-based denial-of-service attacks researched by Robert 2868Olsson. 2869These attacks placed so much networking load on the system 2870that some of the CPUs never exited softirq execution, 2871which in turn prevented those CPUs from ever executing a context switch, 2872which, in the RCU implementation of that time, prevented grace periods 2873from ever ending. 2874The result was an out-of-memory condition and a system hang. 2875 2876<p> 2877The solution was the creation of RCU-bh, which does 2878<tt>local_bh_disable()</tt> 2879across its read-side critical sections, and which uses the transition 2880from one type of softirq processing to another as a quiescent state 2881in addition to context switch, idle, user mode, and offline. 2882This means that RCU-bh grace periods can complete even when some of 2883the CPUs execute in softirq indefinitely, thus allowing algorithms 2884based on RCU-bh to withstand network-based denial-of-service attacks. 2885 2886<p> 2887Because 2888<tt>rcu_read_lock_bh()</tt> and <tt>rcu_read_unlock_bh()</tt> 2889disable and re-enable softirq handlers, any attempt to start a softirq 2890handlers during the 2891RCU-bh read-side critical section will be deferred. 2892In this case, <tt>rcu_read_unlock_bh()</tt> 2893will invoke softirq processing, which can take considerable time. 2894One can of course argue that this softirq overhead should be associated 2895with the code following the RCU-bh read-side critical section rather 2896than <tt>rcu_read_unlock_bh()</tt>, but the fact 2897is that most profiling tools cannot be expected to make this sort 2898of fine distinction. 2899For example, suppose that a three-millisecond-long RCU-bh read-side 2900critical section executes during a time of heavy networking load. 2901There will very likely be an attempt to invoke at least one softirq 2902handler during that three milliseconds, but any such invocation will 2903be delayed until the time of the <tt>rcu_read_unlock_bh()</tt>. 2904This can of course make it appear at first glance as if 2905<tt>rcu_read_unlock_bh()</tt> was executing very slowly. 2906 2907<p> 2908The 2909<a href="https://lwn.net/Articles/609973/#RCU Per-Flavor API Table">RCU-bh API</a> 2910includes 2911<tt>rcu_read_lock_bh()</tt>, 2912<tt>rcu_read_unlock_bh()</tt>, 2913<tt>rcu_dereference_bh()</tt>, 2914<tt>rcu_dereference_bh_check()</tt>, 2915<tt>synchronize_rcu_bh()</tt>, 2916<tt>synchronize_rcu_bh_expedited()</tt>, 2917<tt>call_rcu_bh()</tt>, 2918<tt>rcu_barrier_bh()</tt>, and 2919<tt>rcu_read_lock_bh_held()</tt>. 2920 2921<h3><a name="Sched Flavor">Sched Flavor</a></h3> 2922 2923<p> 2924Before preemptible RCU, waiting for an RCU grace period had the 2925side effect of also waiting for all pre-existing interrupt 2926and NMI handlers. 2927However, there are legitimate preemptible-RCU implementations that 2928do not have this property, given that any point in the code outside 2929of an RCU read-side critical section can be a quiescent state. 2930Therefore, <i>RCU-sched</i> was created, which follows “classic” 2931RCU in that an RCU-sched grace period waits for for pre-existing 2932interrupt and NMI handlers. 2933In kernels built with <tt>CONFIG_PREEMPT=n</tt>, the RCU and RCU-sched 2934APIs have identical implementations, while kernels built with 2935<tt>CONFIG_PREEMPT=y</tt> provide a separate implementation for each. 2936 2937<p> 2938Note well that in <tt>CONFIG_PREEMPT=y</tt> kernels, 2939<tt>rcu_read_lock_sched()</tt> and <tt>rcu_read_unlock_sched()</tt> 2940disable and re-enable preemption, respectively. 2941This means that if there was a preemption attempt during the 2942RCU-sched read-side critical section, <tt>rcu_read_unlock_sched()</tt> 2943will enter the scheduler, with all the latency and overhead entailed. 2944Just as with <tt>rcu_read_unlock_bh()</tt>, this can make it look 2945as if <tt>rcu_read_unlock_sched()</tt> was executing very slowly. 2946However, the highest-priority task won't be preempted, so that task 2947will enjoy low-overhead <tt>rcu_read_unlock_sched()</tt> invocations. 2948 2949<p> 2950The 2951<a href="https://lwn.net/Articles/609973/#RCU Per-Flavor API Table">RCU-sched API</a> 2952includes 2953<tt>rcu_read_lock_sched()</tt>, 2954<tt>rcu_read_unlock_sched()</tt>, 2955<tt>rcu_read_lock_sched_notrace()</tt>, 2956<tt>rcu_read_unlock_sched_notrace()</tt>, 2957<tt>rcu_dereference_sched()</tt>, 2958<tt>rcu_dereference_sched_check()</tt>, 2959<tt>synchronize_sched()</tt>, 2960<tt>synchronize_rcu_sched_expedited()</tt>, 2961<tt>call_rcu_sched()</tt>, 2962<tt>rcu_barrier_sched()</tt>, and 2963<tt>rcu_read_lock_sched_held()</tt>. 2964However, anything that disables preemption also marks an RCU-sched 2965read-side critical section, including 2966<tt>preempt_disable()</tt> and <tt>preempt_enable()</tt>, 2967<tt>local_irq_save()</tt> and <tt>local_irq_restore()</tt>, 2968and so on. 2969 2970<h3><a name="Sleepable RCU">Sleepable RCU</a></h3> 2971 2972<p> 2973For well over a decade, someone saying “I need to block within 2974an RCU read-side critical section” was a reliable indication 2975that this someone did not understand RCU. 2976After all, if you are always blocking in an RCU read-side critical 2977section, you can probably afford to use a higher-overhead synchronization 2978mechanism. 2979However, that changed with the advent of the Linux kernel's notifiers, 2980whose RCU read-side critical 2981sections almost never sleep, but sometimes need to. 2982This resulted in the introduction of 2983<a href="https://lwn.net/Articles/202847/">sleepable RCU</a>, 2984or <i>SRCU</i>. 2985 2986<p> 2987SRCU allows different domains to be defined, with each such domain 2988defined by an instance of an <tt>srcu_struct</tt> structure. 2989A pointer to this structure must be passed in to each SRCU function, 2990for example, <tt>synchronize_srcu(&ss)</tt>, where 2991<tt>ss</tt> is the <tt>srcu_struct</tt> structure. 2992The key benefit of these domains is that a slow SRCU reader in one 2993domain does not delay an SRCU grace period in some other domain. 2994That said, one consequence of these domains is that read-side code 2995must pass a “cookie” from <tt>srcu_read_lock()</tt> 2996to <tt>srcu_read_unlock()</tt>, for example, as follows: 2997 2998<blockquote> 2999<pre> 3000 1 int idx; 3001 2 3002 3 idx = srcu_read_lock(&ss); 3003 4 do_something(); 3004 5 srcu_read_unlock(&ss, idx); 3005</pre> 3006</blockquote> 3007 3008<p> 3009As noted above, it is legal to block within SRCU read-side critical sections, 3010however, with great power comes great responsibility. 3011If you block forever in one of a given domain's SRCU read-side critical 3012sections, then that domain's grace periods will also be blocked forever. 3013Of course, one good way to block forever is to deadlock, which can 3014happen if any operation in a given domain's SRCU read-side critical 3015section can block waiting, either directly or indirectly, for that domain's 3016grace period to elapse. 3017For example, this results in a self-deadlock: 3018 3019<blockquote> 3020<pre> 3021 1 int idx; 3022 2 3023 3 idx = srcu_read_lock(&ss); 3024 4 do_something(); 3025 5 synchronize_srcu(&ss); 3026 6 srcu_read_unlock(&ss, idx); 3027</pre> 3028</blockquote> 3029 3030<p> 3031However, if line 5 acquired a mutex that was held across 3032a <tt>synchronize_srcu()</tt> for domain <tt>ss</tt>, 3033deadlock would still be possible. 3034Furthermore, if line 5 acquired a mutex that was held across 3035a <tt>synchronize_srcu()</tt> for some other domain <tt>ss1</tt>, 3036and if an <tt>ss1</tt>-domain SRCU read-side critical section 3037acquired another mutex that was held across as <tt>ss</tt>-domain 3038<tt>synchronize_srcu()</tt>, 3039deadlock would again be possible. 3040Such a deadlock cycle could extend across an arbitrarily large number 3041of different SRCU domains. 3042Again, with great power comes great responsibility. 3043 3044<p> 3045Unlike the other RCU flavors, SRCU read-side critical sections can 3046run on idle and even offline CPUs. 3047This ability requires that <tt>srcu_read_lock()</tt> and 3048<tt>srcu_read_unlock()</tt> contain memory barriers, which means 3049that SRCU readers will run a bit slower than would RCU readers. 3050It also motivates the <tt>smp_mb__after_srcu_read_unlock()</tt> 3051API, which, in combination with <tt>srcu_read_unlock()</tt>, 3052guarantees a full memory barrier. 3053 3054<p> 3055Also unlike other RCU flavors, SRCU's callbacks-wait function 3056<tt>srcu_barrier()</tt> may be invoked from CPU-hotplug notifiers, 3057though this is not necessarily a good idea. 3058The reason that this is possible is that SRCU is insensitive 3059to whether or not a CPU is online, which means that <tt>srcu_barrier()</tt> 3060need not exclude CPU-hotplug operations. 3061 3062<p> 3063SRCU also differs from other RCU flavors in that SRCU's expedited and 3064non-expedited grace periods are implemented by the same mechanism. 3065This means that in the current SRCU implementation, expediting a 3066future grace period has the side effect of expediting all prior 3067grace periods that have not yet completed. 3068(But please note that this is a property of the current implementation, 3069not necessarily of future implementations.) 3070In addition, if SRCU has been idle for longer than the interval 3071specified by the <tt>srcutree.exp_holdoff</tt> kernel boot parameter 3072(25 microseconds by default), 3073and if a <tt>synchronize_srcu()</tt> invocation ends this idle period, 3074that invocation will be automatically expedited. 3075 3076<p> 3077As of v4.12, SRCU's callbacks are maintained per-CPU, eliminating 3078a locking bottleneck present in prior kernel versions. 3079Although this will allow users to put much heavier stress on 3080<tt>call_srcu()</tt>, it is important to note that SRCU does not 3081yet take any special steps to deal with callback flooding. 3082So if you are posting (say) 10,000 SRCU callbacks per second per CPU, 3083you are probably totally OK, but if you intend to post (say) 1,000,000 3084SRCU callbacks per second per CPU, please run some tests first. 3085SRCU just might need a few adjustment to deal with that sort of load. 3086Of course, your mileage may vary based on the speed of your CPUs and 3087the size of your memory. 3088 3089<p> 3090The 3091<a href="https://lwn.net/Articles/609973/#RCU Per-Flavor API Table">SRCU API</a> 3092includes 3093<tt>srcu_read_lock()</tt>, 3094<tt>srcu_read_unlock()</tt>, 3095<tt>srcu_dereference()</tt>, 3096<tt>srcu_dereference_check()</tt>, 3097<tt>synchronize_srcu()</tt>, 3098<tt>synchronize_srcu_expedited()</tt>, 3099<tt>call_srcu()</tt>, 3100<tt>srcu_barrier()</tt>, and 3101<tt>srcu_read_lock_held()</tt>. 3102It also includes 3103<tt>DEFINE_SRCU()</tt>, 3104<tt>DEFINE_STATIC_SRCU()</tt>, and 3105<tt>init_srcu_struct()</tt> 3106APIs for defining and initializing <tt>srcu_struct</tt> structures. 3107 3108<h3><a name="Tasks RCU">Tasks RCU</a></h3> 3109 3110<p> 3111Some forms of tracing use “trampolines” to handle the 3112binary rewriting required to install different types of probes. 3113It would be good to be able to free old trampolines, which sounds 3114like a job for some form of RCU. 3115However, because it is necessary to be able to install a trace 3116anywhere in the code, it is not possible to use read-side markers 3117such as <tt>rcu_read_lock()</tt> and <tt>rcu_read_unlock()</tt>. 3118In addition, it does not work to have these markers in the trampoline 3119itself, because there would need to be instructions following 3120<tt>rcu_read_unlock()</tt>. 3121Although <tt>synchronize_rcu()</tt> would guarantee that execution 3122reached the <tt>rcu_read_unlock()</tt>, it would not be able to 3123guarantee that execution had completely left the trampoline. 3124 3125<p> 3126The solution, in the form of 3127<a href="https://lwn.net/Articles/607117/"><i>Tasks RCU</i></a>, 3128is to have implicit 3129read-side critical sections that are delimited by voluntary context 3130switches, that is, calls to <tt>schedule()</tt>, 3131<tt>cond_resched_rcu_qs()</tt>, and 3132<tt>synchronize_rcu_tasks()</tt>. 3133In addition, transitions to and from userspace execution also delimit 3134tasks-RCU read-side critical sections. 3135 3136<p> 3137The tasks-RCU API is quite compact, consisting only of 3138<tt>call_rcu_tasks()</tt>, 3139<tt>synchronize_rcu_tasks()</tt>, and 3140<tt>rcu_barrier_tasks()</tt>. 3141 3142<h3><a name="Waiting for Multiple Grace Periods"> 3143Waiting for Multiple Grace Periods</a></h3> 3144 3145<p> 3146Perhaps you have an RCU protected data structure that is accessed from 3147RCU read-side critical sections, from softirq handlers, and from 3148hardware interrupt handlers. 3149That is three flavors of RCU, the normal flavor, the bottom-half flavor, 3150and the sched flavor. 3151How to wait for a compound grace period? 3152 3153<p> 3154The best approach is usually to “just say no!” and 3155insert <tt>rcu_read_lock()</tt> and <tt>rcu_read_unlock()</tt> 3156around each RCU read-side critical section, regardless of what 3157environment it happens to be in. 3158But suppose that some of the RCU read-side critical sections are 3159on extremely hot code paths, and that use of <tt>CONFIG_PREEMPT=n</tt> 3160is not a viable option, so that <tt>rcu_read_lock()</tt> and 3161<tt>rcu_read_unlock()</tt> are not free. 3162What then? 3163 3164<p> 3165You <i>could</i> wait on all three grace periods in succession, as follows: 3166 3167<blockquote> 3168<pre> 3169 1 synchronize_rcu(); 3170 2 synchronize_rcu_bh(); 3171 3 synchronize_sched(); 3172</pre> 3173</blockquote> 3174 3175<p> 3176This works, but triples the update-side latency penalty. 3177In cases where this is not acceptable, <tt>synchronize_rcu_mult()</tt> 3178may be used to wait on all three flavors of grace period concurrently: 3179 3180<blockquote> 3181<pre> 3182 1 synchronize_rcu_mult(call_rcu, call_rcu_bh, call_rcu_sched); 3183</pre> 3184</blockquote> 3185 3186<p> 3187But what if it is necessary to also wait on SRCU? 3188This can be done as follows: 3189 3190<blockquote> 3191<pre> 3192 1 static void call_my_srcu(struct rcu_head *head, 3193 2 void (*func)(struct rcu_head *head)) 3194 3 { 3195 4 call_srcu(&my_srcu, head, func); 3196 5 } 3197 6 3198 7 synchronize_rcu_mult(call_rcu, call_rcu_bh, call_rcu_sched, call_my_srcu); 3199</pre> 3200</blockquote> 3201 3202<p> 3203If you needed to wait on multiple different flavors of SRCU 3204(but why???), you would need to create a wrapper function resembling 3205<tt>call_my_srcu()</tt> for each SRCU flavor. 3206 3207<table> 3208<tr><th> </th></tr> 3209<tr><th align="left">Quick Quiz:</th></tr> 3210<tr><td> 3211 But what if I need to wait for multiple RCU flavors, but I also need 3212 the grace periods to be expedited? 3213</td></tr> 3214<tr><th align="left">Answer:</th></tr> 3215<tr><td bgcolor="#ffffff"><font color="ffffff"> 3216 If you are using expedited grace periods, there should be less penalty 3217 for waiting on them in succession. 3218 But if that is nevertheless a problem, you can use workqueues 3219 or multiple kthreads to wait on the various expedited grace 3220 periods concurrently. 3221</font></td></tr> 3222<tr><td> </td></tr> 3223</table> 3224 3225<p> 3226Again, it is usually better to adjust the RCU read-side critical sections 3227to use a single flavor of RCU, but when this is not feasible, you can use 3228<tt>synchronize_rcu_mult()</tt>. 3229 3230<h2><a name="Possible Future Changes">Possible Future Changes</a></h2> 3231 3232<p> 3233One of the tricks that RCU uses to attain update-side scalability is 3234to increase grace-period latency with increasing numbers of CPUs. 3235If this becomes a serious problem, it will be necessary to rework the 3236grace-period state machine so as to avoid the need for the additional 3237latency. 3238 3239<p> 3240Expedited grace periods scan the CPUs, so their latency and overhead 3241increases with increasing numbers of CPUs. 3242If this becomes a serious problem on large systems, it will be necessary 3243to do some redesign to avoid this scalability problem. 3244 3245<p> 3246RCU disables CPU hotplug in a few places, perhaps most notably in the 3247<tt>rcu_barrier()</tt> operations. 3248If there is a strong reason to use <tt>rcu_barrier()</tt> in CPU-hotplug 3249notifiers, it will be necessary to avoid disabling CPU hotplug. 3250This would introduce some complexity, so there had better be a <i>very</i> 3251good reason. 3252 3253<p> 3254The tradeoff between grace-period latency on the one hand and interruptions 3255of other CPUs on the other hand may need to be re-examined. 3256The desire is of course for zero grace-period latency as well as zero 3257interprocessor interrupts undertaken during an expedited grace period 3258operation. 3259While this ideal is unlikely to be achievable, it is quite possible that 3260further improvements can be made. 3261 3262<p> 3263The multiprocessor implementations of RCU use a combining tree that 3264groups CPUs so as to reduce lock contention and increase cache locality. 3265However, this combining tree does not spread its memory across NUMA 3266nodes nor does it align the CPU groups with hardware features such 3267as sockets or cores. 3268Such spreading and alignment is currently believed to be unnecessary 3269because the hotpath read-side primitives do not access the combining 3270tree, nor does <tt>call_rcu()</tt> in the common case. 3271If you believe that your architecture needs such spreading and alignment, 3272then your architecture should also benefit from the 3273<tt>rcutree.rcu_fanout_leaf</tt> boot parameter, which can be set 3274to the number of CPUs in a socket, NUMA node, or whatever. 3275If the number of CPUs is too large, use a fraction of the number of 3276CPUs. 3277If the number of CPUs is a large prime number, well, that certainly 3278is an “interesting” architectural choice! 3279More flexible arrangements might be considered, but only if 3280<tt>rcutree.rcu_fanout_leaf</tt> has proven inadequate, and only 3281if the inadequacy has been demonstrated by a carefully run and 3282realistic system-level workload. 3283 3284<p> 3285Please note that arrangements that require RCU to remap CPU numbers will 3286require extremely good demonstration of need and full exploration of 3287alternatives. 3288 3289<p> 3290There is an embarrassingly large number of flavors of RCU, and this 3291number has been increasing over time. 3292Perhaps it will be possible to combine some at some future date. 3293 3294<p> 3295RCU's various kthreads are reasonably recent additions. 3296It is quite likely that adjustments will be required to more gracefully 3297handle extreme loads. 3298It might also be necessary to be able to relate CPU utilization by 3299RCU's kthreads and softirq handlers to the code that instigated this 3300CPU utilization. 3301For example, RCU callback overhead might be charged back to the 3302originating <tt>call_rcu()</tt> instance, though probably not 3303in production kernels. 3304 3305<h2><a name="Summary">Summary</a></h2> 3306 3307<p> 3308This document has presented more than two decade's worth of RCU 3309requirements. 3310Given that the requirements keep changing, this will not be the last 3311word on this subject, but at least it serves to get an important 3312subset of the requirements set forth. 3313 3314<h2><a name="Acknowledgments">Acknowledgments</a></h2> 3315 3316I am grateful to Steven Rostedt, Lai Jiangshan, Ingo Molnar, 3317Oleg Nesterov, Borislav Petkov, Peter Zijlstra, Boqun Feng, and 3318Andy Lutomirski for their help in rendering 3319this article human readable, and to Michelle Rankin for her support 3320of this effort. 3321Other contributions are acknowledged in the Linux kernel's git archive. 3322 3323</body></html> 3324
