diff options
53 files changed, 2365 insertions, 590 deletions
diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.rst b/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.rst index 72f0f6fbd53c..6f89cf1e567d 100644 --- a/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.rst +++ b/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.rst @@ -38,7 +38,7 @@ sections. RCU-preempt Expedited Grace Periods =================================== -``CONFIG_PREEMPT=y`` kernels implement RCU-preempt. +``CONFIG_PREEMPTION=y`` kernels implement RCU-preempt. The overall flow of the handling of a given CPU by an RCU-preempt expedited grace period is shown in the following diagram: @@ -112,7 +112,7 @@ things. RCU-sched Expedited Grace Periods --------------------------------- -``CONFIG_PREEMPT=n`` kernels implement RCU-sched. The overall flow of +``CONFIG_PREEMPTION=n`` kernels implement RCU-sched. The overall flow of the handling of a given CPU by an RCU-sched expedited grace period is shown in the following diagram: diff --git a/Documentation/RCU/Design/Requirements/Requirements.rst b/Documentation/RCU/Design/Requirements/Requirements.rst index 93a189ae8592..0da9133fa13a 100644 --- a/Documentation/RCU/Design/Requirements/Requirements.rst +++ b/Documentation/RCU/Design/Requirements/Requirements.rst @@ -72,13 +72,13 @@ understanding of this guarantee. RCU's grace-period guarantee allows updaters to wait for the completion of all pre-existing RCU read-side critical sections. An RCU read-side -critical section begins with the marker ``rcu_read_lock()`` and ends -with the marker ``rcu_read_unlock()``. These markers may be nested, and +critical section begins with the marker rcu_read_lock() and ends +with the marker rcu_read_unlock(). These markers may be nested, and RCU treats a nested set as one big RCU read-side critical section. -Production-quality implementations of ``rcu_read_lock()`` and -``rcu_read_unlock()`` are extremely lightweight, and in fact have +Production-quality implementations of rcu_read_lock() and +rcu_read_unlock() are extremely lightweight, and in fact have exactly zero overhead in Linux kernels built for production use with -``CONFIG_PREEMPT=n``. +``CONFIG_PREEMPTION=n``. This guarantee allows ordering to be enforced with extremely low overhead to readers, for example: @@ -102,12 +102,12 @@ overhead to readers, for example: 15 WRITE_ONCE(y, 1); 16 } -Because the ``synchronize_rcu()`` on line 14 waits for all pre-existing -readers, any instance of ``thread0()`` that loads a value of zero from -``x`` must complete before ``thread1()`` stores to ``y``, so that +Because the synchronize_rcu() on line 14 waits for all pre-existing +readers, any instance of thread0() that loads a value of zero from +``x`` must complete before thread1() stores to ``y``, so that instance must also load a value of zero from ``y``. Similarly, any -instance of ``thread0()`` that loads a value of one from ``y`` must have -started after the ``synchronize_rcu()`` started, and must therefore also +instance of thread0() that loads a value of one from ``y`` must have +started after the synchronize_rcu() started, and must therefore also load a value of one from ``x``. Therefore, the outcome: :: @@ -121,14 +121,14 @@ cannot happen. +-----------------------------------------------------------------------+ | Wait a minute! You said that updaters can make useful forward | | progress concurrently with readers, but pre-existing readers will | -| block ``synchronize_rcu()``!!! | +| block synchronize_rcu()!!! | | Just who are you trying to fool??? | +-----------------------------------------------------------------------+ | **Answer**: | +-----------------------------------------------------------------------+ | First, if updaters do not wish to be blocked by readers, they can use | -| ``call_rcu()`` or ``kfree_rcu()``, which will be discussed later. | -| Second, even when using ``synchronize_rcu()``, the other update-side | +| call_rcu() or kfree_rcu(), which will be discussed later. | +| Second, even when using synchronize_rcu(), the other update-side | | code does run concurrently with readers, whether pre-existing or not. | +-----------------------------------------------------------------------+ @@ -170,34 +170,34 @@ recovery from node failure, more or less as follows: 29 WRITE_ONCE(state, STATE_NORMAL); 30 } -The RCU read-side critical section in ``do_something_dlm()`` works with -the ``synchronize_rcu()`` in ``start_recovery()`` to guarantee that -``do_something()`` never runs concurrently with ``recovery()``, but with -little or no synchronization overhead in ``do_something_dlm()``. +The RCU read-side critical section in do_something_dlm() works with +the synchronize_rcu() in start_recovery() to guarantee that +do_something() never runs concurrently with recovery(), but with +little or no synchronization overhead in do_something_dlm(). +-----------------------------------------------------------------------+ | **Quick Quiz**: | +-----------------------------------------------------------------------+ -| Why is the ``synchronize_rcu()`` on line 28 needed? | +| Why is the synchronize_rcu() on line 28 needed? | +-----------------------------------------------------------------------+ | **Answer**: | +-----------------------------------------------------------------------+ | Without that extra grace period, memory reordering could result in | -| ``do_something_dlm()`` executing ``do_something()`` concurrently with | -| the last bits of ``recovery()``. | +| do_something_dlm() executing do_something() concurrently with | +| the last bits of recovery(). | +-----------------------------------------------------------------------+ In order to avoid fatal problems such as deadlocks, an RCU read-side -critical section must not contain calls to ``synchronize_rcu()``. +critical section must not contain calls to synchronize_rcu(). Similarly, an RCU read-side critical section must not contain anything that waits, directly or indirectly, on completion of an invocation of -``synchronize_rcu()``. +synchronize_rcu(). Although RCU's grace-period guarantee is useful in and of itself, with `quite a few use cases <https://lwn.net/Articles/573497/>`__, it would be good to be able to use RCU to coordinate read-side access to linked data structures. For this, the grace-period guarantee is not sufficient, -as can be seen in function ``add_gp_buggy()`` below. We will look at the +as can be seen in function add_gp_buggy() below. We will look at the reader's code later, but in the meantime, just think of the reader as locklessly picking up the ``gp`` pointer, and, if the value loaded is non-\ ``NULL``, locklessly accessing the ``->a`` and ``->b`` fields. @@ -256,8 +256,8 @@ Publish/Subscribe Guarantee RCU's publish-subscribe guarantee allows data to be inserted into a linked data structure without disrupting RCU readers. The updater uses -``rcu_assign_pointer()`` to insert the new data, and readers use -``rcu_dereference()`` to access data, whether new or old. The following +rcu_assign_pointer() to insert the new data, and readers use +rcu_dereference() to access data, whether new or old. The following shows an example of insertion: :: @@ -279,7 +279,7 @@ shows an example of insertion: 15 return true; 16 } -The ``rcu_assign_pointer()`` on line 13 is conceptually equivalent to a +The rcu_assign_pointer() on line 13 is conceptually equivalent to a simple assignment statement, but also guarantees that its assignment will happen after the two assignments in lines 11 and 12, similar to the C11 ``memory_order_release`` store operation. It also prevents any @@ -289,7 +289,7 @@ number of “interesting” compiler optimizations, for example, the use of +-----------------------------------------------------------------------+ | **Quick Quiz**: | +-----------------------------------------------------------------------+ -| But ``rcu_assign_pointer()`` does nothing to prevent the two | +| But rcu_assign_pointer() does nothing to prevent the two | | assignments to ``p->a`` and ``p->b`` from being reordered. Can't that | | also cause problems? | +-----------------------------------------------------------------------+ @@ -303,7 +303,7 @@ number of “interesting” compiler optimizations, for example, the use of It is tempting to assume that the reader need not do anything special to control its accesses to the RCU-protected data, as shown in -``do_something_gp_buggy()`` below: +do_something_gp_buggy() below: :: @@ -321,11 +321,10 @@ control its accesses to the RCU-protected data, as shown in 12 } However, this temptation must be resisted because there are a -surprisingly large number of ways that the compiler (to say nothing of -`DEC Alpha CPUs <https://h71000.www7.hp.com/wizard/wiz_2637.html>`__) -can trip this code up. For but one example, if the compiler were short -of registers, it might choose to refetch from ``gp`` rather than keeping -a separate copy in ``p`` as follows: +surprisingly large number of ways that the compiler (or weak ordering +CPUs like the DEC Alpha) can trip this code up. For but one example, if +the compiler were short of registers, it might choose to refetch from +``gp`` rather than keeping a separate copy in ``p`` as follows: :: @@ -345,7 +344,7 @@ If this function ran concurrently with a series of updates that replaced the current structure with a new one, the fetches of ``gp->a`` and ``gp->b`` might well come from two different structures, which could cause serious confusion. To prevent this (and much else besides), -``do_something_gp()`` uses ``rcu_dereference()`` to fetch from ``gp``: +do_something_gp() uses rcu_dereference() to fetch from ``gp``: :: @@ -362,21 +361,21 @@ cause serious confusion. To prevent this (and much else besides), 11 return false; 12 } -The ``rcu_dereference()`` uses volatile casts and (for DEC Alpha) memory +The rcu_dereference() uses volatile casts and (for DEC Alpha) memory barriers in the Linux kernel. Should a `high-quality implementation of C11 ``memory_order_consume`` [PDF] <http://www.rdrop.com/users/paulmck/RCU/consume.2015.07.13a.pdf>`__ -ever appear, then ``rcu_dereference()`` could be implemented as a +ever appear, then rcu_dereference() could be implemented as a ``memory_order_consume`` load. Regardless of the exact implementation, a -pointer fetched by ``rcu_dereference()`` may not be used outside of the +pointer fetched by rcu_dereference() may not be used outside of the outermost RCU read-side critical section containing that -``rcu_dereference()``, unless protection of the corresponding data +rcu_dereference(), unless protection of the corresponding data element has been passed from RCU to some other synchronization mechanism, most commonly locking or `reference counting <https://www.kernel.org/doc/Documentation/RCU/rcuref.txt>`__. -In short, updaters use ``rcu_assign_pointer()`` and readers use -``rcu_dereference()``, and these two RCU API elements work together to +In short, updaters use rcu_assign_pointer() and readers use +rcu_dereference(), and these two RCU API elements work together to ensure that readers have a consistent view of newly added data elements. Of course, it is also necessary to remove elements from RCU-protected @@ -388,9 +387,9 @@ data structures, for example, using the following process: the newly removed data element). #. At this point, only the updater has a reference to the newly removed data element, so it can safely reclaim the data element, for example, - by passing it to ``kfree()``. + by passing it to kfree(). -This process is implemented by ``remove_gp_synchronous()``: +This process is implemented by remove_gp_synchronous(): :: @@ -413,16 +412,16 @@ This process is implemented by ``remove_gp_synchronous()``: This function is straightforward, with line 13 waiting for a grace period before line 14 frees the old data element. This waiting ensures -that readers will reach line 7 of ``do_something_gp()`` before the data -element referenced by ``p`` is freed. The ``rcu_access_pointer()`` on -line 6 is similar to ``rcu_dereference()``, except that: +that readers will reach line 7 of do_something_gp() before the data +element referenced by ``p`` is freed. The rcu_access_pointer() on +line 6 is similar to rcu_dereference(), except that: -#. The value returned by ``rcu_access_pointer()`` cannot be +#. The value returned by rcu_access_pointer() cannot be dereferenced. If you want to access the value pointed to as well as - the pointer itself, use ``rcu_dereference()`` instead of - ``rcu_access_pointer()``. -#. The call to ``rcu_access_pointer()`` need not be protected. In - contrast, ``rcu_dereference()`` must either be within an RCU + the pointer itself, use rcu_dereference() instead of + rcu_access_pointer(). +#. The call to rcu_access_pointer() need not be protected. In + contrast, rcu_dereference() must either be within an RCU read-side critical section or in a code segment where the pointer cannot change, for example, in code protected by the corresponding update-side lock. @@ -430,13 +429,13 @@ line 6 is similar to ``rcu_dereference()``, except that: +-----------------------------------------------------------------------+ | **Quick Quiz**: | +-----------------------------------------------------------------------+ -| Without the ``rcu_dereference()`` or the ``rcu_access_pointer()``, | +| Without the rcu_dereference() or the rcu_access_pointer(), | | what destructive optimizations might the compiler make use of? | +-----------------------------------------------------------------------+ | **Answer**: | +-----------------------------------------------------------------------+ -| Let's start with what happens to ``do_something_gp()`` if it fails to | -| use ``rcu_dereference()``. It could reuse a value formerly fetched | +| Let's start with what happens to do_something_gp() if it fails to | +| use rcu_dereference(). It could reuse a value formerly fetched | | from this same pointer. It could also fetch the pointer from ``gp`` | | in a byte-at-a-time manner, resulting in *load tearing*, in turn | | resulting a bytewise mash-up of two distinct pointer values. It might | @@ -445,15 +444,15 @@ line 6 is similar to ``rcu_dereference()``, except that: | update has changed the pointer to match the wrong guess. Too bad | | about any dereferences that returned pre-initialization garbage in | | the meantime! | -| For ``remove_gp_synchronous()``, as long as all modifications to | +| For remove_gp_synchronous(), as long as all modifications to | | ``gp`` are carried out while holding ``gp_lock``, the above | | optimizations are harmless. However, ``sparse`` will complain if you | | define ``gp`` with ``__rcu`` and then access it without using either | -| ``rcu_access_pointer()`` or ``rcu_dereference()``. | +| rcu_access_pointer() or rcu_dereference(). | +-----------------------------------------------------------------------+ In short, RCU's publish-subscribe guarantee is provided by the -combination of ``rcu_assign_pointer()`` and ``rcu_dereference()``. This +combination of rcu_assign_pointer() and rcu_dereference(). This guarantee allows data elements to be safely added to RCU-protected linked data structures without disrupting RCU readers. This guarantee can be used in combination with the grace-period guarantee to also allow @@ -462,9 +461,9 @@ again without disrupting RCU readers. This guarantee was only partially premeditated. DYNIX/ptx used an explicit memory barrier for publication, but had nothing resembling -``rcu_dereference()`` for subscription, nor did it have anything +rcu_dereference() for subscription, nor did it have anything resembling the dependency-ordering barrier that was later subsumed -into ``rcu_dereference()`` and later still into ``READ_ONCE()``. The +into rcu_dereference() and later still into READ_ONCE(). The need for these operations made itself known quite suddenly at a late-1990s meeting with the DEC Alpha architects, back in the days when DEC was still a free-standing company. It took the Alpha architects a @@ -474,7 +473,7 @@ documentation did not make this point clear. More recent work with the C and C++ standards committees have provided much education on tricks and traps from the compiler. In short, compilers were much less tricky in the early 1990s, but in 2015, don't even think about omitting -``rcu_dereference()``! +rcu_dereference()! Memory-Barrier Guarantees ~~~~~~~~~~~~~~~~~~~~~~~~~ @@ -484,31 +483,31 @@ demonstrates the need for RCU's stringent memory-ordering guarantees on systems with more than one CPU: #. Each CPU that has an RCU read-side critical section that begins - before ``synchronize_rcu()`` starts is guaranteed to execute a full + before synchronize_rcu() starts is guaranteed to execute a full memory barrier between the time that the RCU read-side critical - section ends and the time that ``synchronize_rcu()`` returns. Without + section ends and the time that synchronize_rcu() returns. Without this guarantee, a pre-existing RCU read-side critical section might hold a reference to the newly removed ``struct foo`` after the - ``kfree()`` on line 14 of ``remove_gp_synchronous()``. + kfree() on line 14 of remove_gp_synchronous(). #. Each CPU that has an RCU read-side critical section that ends after - ``synchronize_rcu()`` returns is guaranteed to execute a full memory - barrier between the time that ``synchronize_rcu()`` begins and the + synchronize_rcu() returns is guaranteed to execute a full memory + barrier between the time that synchronize_rcu() begins and the time that the RCU read-side critical section begins. Without this guarantee, a later RCU read-side critical section running after the - ``kfree()`` on line 14 of ``remove_gp_synchronous()`` might later run - ``do_something_gp()`` and find the newly deleted ``struct foo``. -#. If the task invoking ``synchronize_rcu()`` remains on a given CPU, + kfree() on line 14 of remove_gp_synchronous() might later run + do_something_gp() and find the newly deleted ``struct foo``. +#. If the task invoking synchronize_rcu() remains on a given CPU, then that CPU is guaranteed to execute a full memory barrier sometime - during the execution of ``synchronize_rcu()``. This guarantee ensures - that the ``kfree()`` on line 14 of ``remove_gp_synchronous()`` really + during the execution of synchronize_rcu(). This guarantee ensures + that the kfree() on line 14 of remove_gp_synchronous() really does execute after the removal on line 11. -#. If the task invoking ``synchronize_rcu()`` migrates among a group of +#. If the task invoking synchronize_rcu() migrates among a group of CPUs during that invocation, then each of the CPUs in that group is guaranteed to execute a full memory barrier sometime during the - execution of ``synchronize_rcu()``. This guarantee also ensures that - the ``kfree()`` on line 14 of ``remove_gp_synchronous()`` really does + execution of synchronize_rcu(). This guarantee also ensures that + the kfree() on line 14 of remove_gp_synchronous() really does execute after the removal on line 11, but also in the case where the - thread executing the ``synchronize_rcu()`` migrates in the meantime. + thread executing the synchronize_rcu() migrates in the meantime. +-----------------------------------------------------------------------+ | **Quick Quiz**: | @@ -516,19 +515,19 @@ systems with more than one CPU: | Given that multiple CPUs can start RCU read-side critical sections at | | any time without any ordering whatsoever, how can RCU possibly tell | | whether or not a given RCU read-side critical section starts before a | -| given instance of ``synchronize_rcu()``? | +| given instance of synchronize_rcu()? | +-----------------------------------------------------------------------+ | **Answer**: | +-----------------------------------------------------------------------+ | If RCU cannot tell whether or not a given RCU read-side critical | -| section starts before a given instance of ``synchronize_rcu()``, then | +| section starts before a given instance of synchronize_rcu(), then | | it must assume that the RCU read-side critical section started first. | -| In other words, a given instance of ``synchronize_rcu()`` can avoid | +| In other words, a given instance of synchronize_rcu() can avoid | | waiting on a given RCU read-side critical section only if it can | -| prove that ``synchronize_rcu()`` started first. | -| A related question is “When ``rcu_read_lock()`` doesn't generate any | +| prove that synchronize_rcu() started first. | +| A related question is “When rcu_read_lock() doesn't generate any | | code, why does it matter how it relates to a grace period?” The | -| answer is that it is not the relationship of ``rcu_read_lock()`` | +| answer is that it is not the relationship of rcu_read_lock() | | itself that is important, but rather the relationship of the code | | within the enclosed RCU read-side critical section to the code | | preceding and following the grace period. If we take this viewpoint, | @@ -556,14 +555,14 @@ systems with more than one CPU: | Yes, they really are required. To see why the first guarantee is | | required, consider the following sequence of events: | | | -| #. CPU 1: ``rcu_read_lock()`` | +| #. CPU 1: rcu_read_lock() | | #. CPU 1: ``q = rcu_dereference(gp); /* Very likely to return p. */`` | | #. CPU 0: ``list_del_rcu(p);`` | -| #. CPU 0: ``synchronize_rcu()`` starts. | +| #. CPU 0: synchronize_rcu() starts. | | #. CPU 1: ``do_something_with(q->a);`` | | ``/* No smp_mb(), so might happen after kfree(). */`` | -| #. CPU 1: ``rcu_read_unlock()`` | -| #. CPU 0: ``synchronize_rcu()`` returns. | +| #. CPU 1: rcu_read_unlock() | +| #. CPU 0: synchronize_rcu() returns. | | #. CPU 0: ``kfree(p);`` | | | | Therefore, there absolutely must be a full memory barrier between the | @@ -574,14 +573,14 @@ systems with more than one CPU: | is roughly similar: | | | | #. CPU 0: ``list_del_rcu(p);`` | -| #. CPU 0: ``synchronize_rcu()`` starts. | -| #. CPU 1: ``rcu_read_lock()`` | +| #. CPU 0: synchronize_rcu() starts. | +| #. CPU 1: rcu_read_lock() | | #. CPU 1: ``q = rcu_dereference(gp);`` | | ``/* Might return p if no memory barrier. */`` | -| #. CPU 0: ``synchronize_rcu()`` returns. | +| #. CPU 0: synchronize_rcu() returns. | | #. CPU 0: ``kfree(p);`` | | #. CPU 1: ``do_something_with(q->a); /* Boom!!! */`` | -| #. CPU 1: ``rcu_read_unlock()`` | +| #. CPU 1: rcu_read_unlock() | | | | And similarly, without a memory barrier between the beginning of the | | grace period and the beginning of the RCU read-side critical section, | @@ -597,7 +596,7 @@ systems with more than one CPU: +-----------------------------------------------------------------------+ | **Quick Quiz**: | +-----------------------------------------------------------------------+ -| You claim that ``rcu_read_lock()`` and ``rcu_read_unlock()`` generate | +| You claim that rcu_read_lock() and rcu_read_unlock() generate | | absolutely no code in some kernel builds. This means that the | | compiler might arbitrarily rearrange consecutive RCU read-side | | critical sections. Given such rearrangement, if a given RCU read-side | @@ -607,11 +606,11 @@ systems with more than one CPU: +-----------------------------------------------------------------------+ | **Answer**: | +-----------------------------------------------------------------------+ -| In cases where ``rcu_read_lock()`` and ``rcu_read_unlock()`` generate | +| In cases where rcu_read_lock() and rcu_read_unlock() generate | | absolutely no code, RCU infers quiescent states only at special | | locations, for example, within the scheduler. Because calls to | -| ``schedule()`` had better prevent calling-code accesses to shared | -| variables from being rearranged across the call to ``schedule()``, if | +| schedule() had better prevent calling-code accesses to shared | +| variables from being rearranged across the call to schedule(), if | | RCU detects the end of a given RCU read-side critical section, it | | will necessarily detect the end of all prior RCU read-side critical | | sections, no matter how aggressively the compiler scrambles the code. | @@ -655,8 +654,8 @@ read-side critical section might search for a given data element, and then might acquire the update-side spinlock in order to update that element, all while remaining in that RCU read-side critical section. Of course, it is necessary to exit the RCU read-side critical section -before invoking ``synchronize_rcu()``, however, this inconvenience can -be avoided through use of the ``call_rcu()`` and ``kfree_rcu()`` API +before invoking synchronize_rcu(), however, this inconvenience can +be avoided through use of the call_rcu() and kfree_rcu() API members described later in this document. +-----------------------------------------------------------------------+ @@ -694,10 +693,10 @@ these non-guarantees were premeditated. Readers Impose Minimal Ordering ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -Reader-side markers such as ``rcu_read_lock()`` and -``rcu_read_unlock()`` provide absolutely no ordering guarantees except +Reader-side markers such as rcu_read_lock() and +rcu_read_unlock() provide absolutely no ordering guarantees except through their interaction with the grace-period APIs such as -``synchronize_rcu()``. To see this, consider the following pair of +synchronize_rcu(). To see this, consider the following pair of threads: :: @@ -722,7 +721,7 @@ threads: 18 rcu_read_unlock(); 19 } -After ``thread0()`` and ``thread1()`` execute concurrently, it is quite +After thread0() and thread1() execute concurrently, it is quite possible to have :: @@ -730,7 +729,7 @@ possible to have (r1 == 1 && r2 == 0) (that is, ``y`` appears to have been assigned before ``x``), which would -not be possible if ``rcu_read_lock()`` and ``rcu_read_unlock()`` had +not be possible if rcu_read_lock() and rcu_read_unlock() had much in the way of ordering properties. But they do not, so the CPU is within its rights to do significant reordering. This is by design: Any significant ordering constraints would slow down these fast-path APIs. @@ -742,14 +741,14 @@ significant ordering constraints would slow down these fast-path APIs. +-----------------------------------------------------------------------+ | **Answer**: | +-----------------------------------------------------------------------+ -| No, the volatile casts in ``READ_ONCE()`` and ``WRITE_ONCE()`` | +| No, the volatile casts in READ_ONCE() and WRITE_ONCE() | | prevent the compiler from reordering in this particular case. | +-----------------------------------------------------------------------+ Readers Do Not Exclude Updaters ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -Neither ``rcu_read_lock()`` nor ``rcu_read_unlock()`` exclude updates. +Neither rcu_read_lock() nor rcu_read_unlock() exclude updates. All they do is to prevent grace periods from ending. The following example illustrates this: @@ -775,19 +774,19 @@ example illustrates this: 18 spin_unlock(&my_lock); 19 } -If the ``thread0()`` function's ``rcu_read_lock()`` excluded the -``thread1()`` function's update, the ``WARN_ON()`` could never fire. But -the fact is that ``rcu_read_lock()`` does not exclude much of anything -aside from subsequent grace periods, of which ``thread1()`` has none, so -the ``WARN_ON()`` can and does fire. +If the thread0() function's rcu_read_lock() excluded the +thread1() function's update, the WARN_ON() could never fire. But +the fact is that rcu_read_lock() does not exclude much of anything +aside from subsequent grace periods, of which thread1() has none, so +the WARN_ON() can and does fire. Updaters Only Wait For Old Readers ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -It might be tempting to assume that after ``synchronize_rcu()`` +It might be tempting to assume that after synchronize_rcu() completes, there are no readers executing. This temptation must be avoided because new readers can start immediately after -``synchronize_rcu()`` starts, and ``synchronize_rcu()`` is under no +synchronize_rcu() starts, and synchronize_rcu() is under no obligation to wait for these new readers. +-----------------------------------------------------------------------+ @@ -799,10 +798,10 @@ obligation to wait for these new readers. +-----------------------------------------------------------------------+ | **Answer**: | +-----------------------------------------------------------------------+ -| For no time at all. Even if ``synchronize_rcu()`` were to wait until | +| For no time at all. Even if synchronize_rcu() were to wait until | | all readers had completed, a new reader might start immediately after | -| ``synchronize_rcu()`` completed. Therefore, the code following | -| ``synchronize_rcu()`` can *never* rely on there being no readers. | +| synchronize_rcu() completed. Therefore, the code following | +| synchronize_rcu() can *never* rely on there being no readers. | +-----------------------------------------------------------------------+ Grace Periods Don't Partition Read-Side Critical Sections @@ -892,12 +891,12 @@ period is known to end before the second grace period starts: 28 rcu_read_unlock(); 29 } -Here, if ``(r1 == 1)``, then ``thread0()``'s write to ``b`` must happen -before the end of ``thread1()``'s grace period. If in addition -``(r4 == 1)``, then ``thread3()``'s read from ``b`` must happen after -the beginning of ``thread2()``'s grace period. If it is also the case -that ``(r2 == 1)``, then the end of ``thread1()``'s grace period must -precede the beginning of ``thread2()``'s grace period. This mean that +Here, if ``(r1 == 1)``, then thread0()'s write to ``b`` must happen +before the end of thread1()'s grace period. If in addition +``(r4 == 1)``, then thread3()'s read from ``b`` must happen after +the beginning of thread2()'s grace period. If it is also the case +that ``(r2 == 1)``, then the end of thread1()'s grace period must +precede the beginning of thread2()'s grace period. This mean that the two RCU read-side critical sections cannot overlap, guaranteeing that ``(r3 == 1)``. As a result, the outcome: @@ -1076,8 +1075,8 @@ is captured by the following list of situations: b. Wait-free read-side primitives for real-time use. This focus on read-mostly situations means that RCU must interoperate -with other synchronization primitives. For example, the ``add_gp()`` and -``remove_gp_synchronous()`` examples discussed earlier use RCU to +with other synchronization primitives. For example, the add_gp() and +remove_gp_synchronous() examples discussed earlier use RCU to protect readers and locking to coordinate updaters. However, the need extends much farther, requiring that a variety of synchronization primitives be legal within RCU read-side critical sections, including @@ -1104,11 +1103,11 @@ memory barriers. | sections. | | Note that it *is* legal for a normal RCU read-side critical section | | to conditionally acquire a sleeping locks (as in | -| ``mutex_trylock()``), but only as long as it does not loop | +| mutex_trylock()), but only as long as it does not loop | | indefinitely attempting to conditionally acquire that sleeping locks. | -| The key point is that things like ``mutex_trylock()`` either return | +| The key point is that things like mutex_trylock() either return | | with the mutex held, or return an error indication if the mutex was | -| not immediately available. Either way, ``mutex_trylock()`` returns | +| not immediately available. Either way, mutex_trylock() returns | | immediately without sleeping. | +-----------------------------------------------------------------------+ @@ -1182,8 +1181,8 @@ and has become decreasingly so as memory sizes have expanded and memory costs have plummeted. However, as I learned from Matt Mackall's `bloatwatch <http://elinux.org/Linux_Tiny-FAQ>`__ efforts, memory footprint is critically important on single-CPU systems with -non-preemptible (``CONFIG_PREEMPT=n``) kernels, and thus `tiny -RCU <https://lkml.kernel.org/g/20090113221724.GA15307@linux.vnet.ibm.com>`__ +non-preemptible (``CONFIG_PREEMPTION=n``) kernels, and thus `tiny +RCU <https://lore.kernel.org/r/20090113221724.GA15307@linux.vnet.ibm.com>`__ was born. Josh Triplett has since taken over the small-memory banner with his `Linux kernel tinification <https://tiny.wiki.kernel.org/>`__ project, which resulted in `SRCU <#Sleepable%20RCU>`__ becoming optional @@ -1191,57 +1190,57 @@ for those kernels not needing it. The remaining performance requirements are, for the most part, unsurprising. For example, in keeping with RCU's read-side -specialization, ``rcu_dereference()`` should have negligible overhead +specialization, rcu_dereference() should have negligible overhead (for example, suppression of a few minor compiler optimizations). -Similarly, in non-preemptible environments, ``rcu_read_lock()`` and -``rcu_read_unlock()`` should have exactly zero overhead. +Similarly, in non-preemptible environments, rcu_read_lock() and +rcu_read_unlock() should have exactly zero overhead. In preemptible environments, in the case where the RCU read-side critical section was not preempted (as will be the case for the -highest-priority real-time process), ``rcu_read_lock()`` and -``rcu_read_unlock()`` should have minimal overhead. In particular, they +highest-priority real-time process), rcu_read_lock() and +rcu_read_unlock() should have minimal overhead. In particular, they should not contain atomic read-modify-write operations, memory-barrier instructions, preemption disabling, interrupt disabling, or backwards branches. However, in the case where the RCU read-side critical section -was preempted, ``rcu_read_unlock()`` may acquire spinlocks and disable +was preempted, rcu_read_unlock() may acquire spinlocks and disable interrupts. This is why it is better to nest an RCU read-side critical section within a preempt-disable region than vice versa, at least in cases where that critical section is short enough to avoid unduly degrading real-time latencies. -The ``synchronize_rcu()`` grace-period-wait primitive is optimized for +The synchronize_rcu() grace-period-wait primitive is optimized for throughput. It may therefore incur several milliseconds of latency in addition to the duration of the longest RCU read-side critical section. On the other hand, multiple concurrent invocations of -``synchronize_rcu()`` are required to use batching optimizations so that +synchronize_rcu() are required to use batching optimizations so that they can be satisfied by a single underlying grace-period-wait operation. For example, in the Linux kernel, it is not unusual for a single grace-period-wait operation to serve more than `1,000 separate invocations <https://www.usenix.org/conference/2004-usenix-annual-technical-conference/making-rcu-safe-deep-sub-millisecond-response>`__ -of ``synchronize_rcu()``, thus amortizing the per-invocation overhead +of synchronize_rcu(), thus amortizing the per-invocation overhead down to nearly zero. However, the grace-period optimization is also required to avoid measurable degradation of real-time scheduling and interrupt latencies. -In some cases, the multi-millisecond ``synchronize_rcu()`` latencies are -unacceptable. In these cases, ``synchronize_rcu_expedited()`` may be +In some cases, the multi-millisecond synchronize_rcu() latencies are +unacceptable. In these cases, synchronize_rcu_expedited() may be used instead, reducing the grace-period latency down to a few tens of microseconds on small systems, at least in cases where the RCU read-side critical sections are short. There are currently no special latency -requirements for ``synchronize_rcu_expedited()`` on large systems, but, +requirements for synchronize_rcu_expedited() on large systems, but, consistent with the empirical nature of the RCU specification, that is subject to change. However, there most definitely are scalability -requirements: A storm of ``synchronize_rcu_expedited()`` invocations on +requirements: A storm of synchronize_rcu_expedited() invocations on 4096 CPUs should at least make reasonable forward progress. In return -for its shorter latencies, ``synchronize_rcu_expedited()`` is permitted +for its shorter latencies, synchronize_rcu_expedited() is permitted to impose modest degradation of real-time latency on non-idle online CPUs. Here, “modest” means roughly the same latency degradation as a scheduling-clock interrupt. There are a number of situations where even -``synchronize_rcu_expedited()``'s reduced grace-period latency is -unacceptable. In these situations, the asynchronous ``call_rcu()`` can -be used in place of ``synchronize_rcu()`` as follows: +synchronize_rcu_expedited()'s reduced grace-period latency is +unacceptable. In these situations, the asynchronous call_rcu() can +be used in place of synchronize_rcu() as follows: :: @@ -1275,19 +1274,19 @@ be used in place of ``synchronize_rcu()`` as follows: 28 } A definition of ``struct foo`` is finally needed, and appears on -lines 1-5. The function ``remove_gp_cb()`` is passed to ``call_rcu()`` +lines 1-5. The function remove_gp_cb() is passed to call_rcu() on line 25, and will be invoked after the end of a subsequent grace -period. This gets the same effect as ``remove_gp_synchronous()``, but +period. This gets the same effect as remove_gp_synchronous(), but without forcing the updater to wait for a grace period to elapse. The -``call_rcu()`` function may be used in a number of situations where -neither ``synchronize_rcu()`` nor ``synchronize_rcu_expedited()`` would -be legal, including within preempt-disable code, ``local_bh_disable()`` +call_rcu() function may be used in a number of situations where +neither synchronize_rcu() nor synchronize_rcu_expedited() would +be legal, including within preempt-disable code, local_bh_disable() code, interrupt-disable code, and interrupt handlers. However, even -``call_rcu()`` is illegal within NMI handlers and from idle and offline -CPUs. The callback function (``remove_gp_cb()`` in this case) will be +call_rcu() is illegal within NMI handlers and from idle and offline +CPUs. The callback function (remove_gp_cb() in this case) will be executed within softirq (software interrupt) environment within the Linux kernel, either within a real softirq handler or under the -protection of ``local_bh_disable()``. In both the Linux kernel and in +protection of local_bh_disable(). In both the Linux kernel and in userspace, it is bad practice to write an RCU callback function that takes too long. Long-running operations should be relegated to separate threads or (in the Linux kernel) workqueues. @@ -1295,23 +1294,23 @@ threads or (in the Linux kernel) workqueues. +-----------------------------------------------------------------------+ | **Quick Quiz**: | +-----------------------------------------------------------------------+ -| Why does line 19 use ``rcu_access_pointer()``? After all, | -| ``call_rcu()`` on line 25 stores into the structure, which would | +| Why does line 19 use rcu_access_pointer()? After all, | +| call_rcu() on line 25 stores into the structure, which would | | interact badly with concurrent insertions. Doesn't this mean that | -| ``rcu_dereference()`` is required? | +| rcu_dereference() is required? | +-----------------------------------------------------------------------+ | **Answer**: | +-----------------------------------------------------------------------+ | Presumably the ``->gp_lock`` acquired on line 18 excludes any | -| changes, including any insertions that ``rcu_dereference()`` would | +| changes, including any insertions that rcu_dereference() would | | protect against. Therefore, any insertions will be delayed until | | after ``->gp_lock`` is released on line 25, which in turn means that | -| ``rcu_access_pointer()`` suffices. | +| rcu_access_pointer() suffices. | +-----------------------------------------------------------------------+ -However, all that ``remove_gp_cb()`` is doing is invoking ``kfree()`` on +However, all that remove_gp_cb() is doing is invoking kfree() on the data element. This is a common idiom, and is supported by -``kfree_rcu()``, which allows “fire and forget” operation as shown +kfree_rcu(), which allows “fire and forget” operation as shown below: :: @@ -1338,20 +1337,20 @@ below: 20 return true; 21 } -Note that ``remove_gp_faf()`` simply invokes ``kfree_rcu()`` and +Note that remove_gp_faf() simply invokes kfree_rcu() and proceeds, without any need to pay any further attention to the -subsequent grace period and ``kfree()``. It is permissible to invoke -``kfree_rcu()`` from the same environments as for ``call_rcu()``. -Interestingly enough, DYNIX/ptx had the equivalents of ``call_rcu()`` -and ``kfree_rcu()``, but not ``synchronize_rcu()``. This was due to the +subsequent grace period and kfree(). It is permissible to invoke +kfree_rcu() from the same environments as for call_rcu(). +Interestingly enough, DYNIX/ptx had the equivalents of call_rcu() +and kfree_rcu(), but not synchronize_rcu(). This was due to the fact that RCU was not heavily used within DYNIX/ptx, so the very few -places that needed something like ``synchronize_rcu()`` simply +places that needed something like synchronize_rcu() simply open-coded it. +-----------------------------------------------------------------------+ | **Quick Quiz**: | +-----------------------------------------------------------------------+ -| Earlier it was claimed that ``call_rcu()`` and ``kfree_rcu()`` | +| Earlier it was claimed that call_rcu() and kfree_rcu() | | allowed updaters to avoid being blocked by readers. But how can that | | be correct, given that the invocation of the callback and the freeing | | of the memory (respectively) must still wait for a grace period to | @@ -1363,16 +1362,16 @@ open-coded it. | definition would say that updates in garbage-collected languages | | cannot complete until the next time the garbage collector runs, which | | does not seem at all reasonable. The key point is that in most cases, | -| an updater using either ``call_rcu()`` or ``kfree_rcu()`` can proceed | -| to the next update as soon as it has invoked ``call_rcu()`` or | -| ``kfree_rcu()``, without having to wait for a subsequent grace | +| an updater using either call_rcu() or kfree_rcu() can proceed | +| to the next update as soon as it has invoked call_rcu() or | +| kfree_rcu(), without having to wait for a subsequent grace | | period. | +-----------------------------------------------------------------------+ But what if the updater must wait for the completion of code to be executed after the end of the grace period, but has other tasks that can be carried out in the meantime? The polling-style -``get_state_synchronize_rcu()`` and ``cond_synchronize_rcu()`` functions +get_state_synchronize_rcu() and cond_synchronize_rcu() functions may be used for this purpose, as shown below: :: @@ -1397,11 +1396,11 @@ may be used for this purpose, as shown below: 18 return true; 19 } -On line 14, ``get_state_synchronize_rcu()`` obtains a “cookie” from RCU, +On line 14, get_state_synchronize_rcu() obtains a “cookie” from RCU, then line 15 carries out other tasks, and finally, line 16 returns immediately if a grace period has elapsed in the meantime, but otherwise waits as required. The need for ``get_state_synchronize_rcu`` and -``cond_synchronize_rcu()`` has appeared quite recently, so it is too +cond_synchronize_rcu() has appeared quite recently, so it is too early to tell whether they will stand the test of time. RCU thus provides a range of tools to allow updaters to strike the @@ -1421,8 +1420,8 @@ example, an infinite loop in an RCU read-side critical section must by definition prevent later grace periods from ever completing. For a more involved example, consider a 64-CPU system built with ``CONFIG_RCU_NOCB_CPU=y`` and booted with ``rcu_nocbs=1-63``, where -CPUs 1 through 63 spin in tight loops that invoke ``call_rcu()``. Even -if these tight loops also contain calls to ``cond_resched()`` (thus +CPUs 1 through 63 spin in tight loops that invoke call_rcu(). Even +if these tight loops also contain calls to cond_resched() (thus allowing grace periods to complete), CPU 0 simply will not be able to invoke callbacks as fast as the other 63 CPUs can register them, at least not until the system runs out of memory. In both of these @@ -1435,21 +1434,21 @@ RCU takes the following steps to encourage timely completion of grace periods: #. If a grace period fails to complete within 100 milliseconds, RCU - causes future invocations of ``cond_resched()`` on the holdout CPUs + causes future invocations of cond_resched() on the holdout CPUs to provide an RCU quiescent state. RCU also causes those CPUs' - ``need_resched()`` invocations to return ``true``, but only after the + need_resched() invocations to return ``true``, but only after the corresponding CPU's next scheduling-clock. #. CPUs mentioned in the ``nohz_full`` kernel boot parameter can run indefinitely in the kernel without scheduling-clock interrupts, which - defeats the above ``need_resched()`` strategem. RCU will therefore - invoke ``resched_cpu()`` on any ``nohz_full`` CPUs still holding out + defeats the above need_resched() strategem. RCU will therefore + invoke resched_cpu() on any ``nohz_full`` CPUs still holding out after 109 milliseconds. #. In kernels built with ``CONFIG_RCU_BOOST=y``, if a given task that has been preempted within an RCU read-side critical section is holding out for more than 500 milliseconds, RCU will resort to priority boosting. #. If a CPU is still holding out 10 seconds into the grace period, RCU - will invoke ``resched_cpu()`` on it regardless of its ``nohz_full`` + will invoke resched_cpu() on it regardless of its ``nohz_full`` state. The above values are defaults for systems running with ``HZ=1000``. They @@ -1460,7 +1459,7 @@ caution when changing them. Note that these forward-progress measures are provided only for RCU, not for `SRCU <#Sleepable%20RCU>`__ or `Tasks RCU <#Tasks%20RCU>`__. -RCU takes the following steps in ``call_rcu()`` to encourage timely +RCU takes the following steps in call_rcu() to encourage timely invocation of callbacks when any given non-\ ``rcu_nocbs`` CPU has 10,000 callbacks, or has 10,000 more callbacks than it had the last time encouragement was provided: @@ -1481,8 +1480,8 @@ RCU, not for `SRCU <#Sleepable%20RCU>`__ or `Tasks RCU <#Tasks%20RCU>`__. Even for RCU, callback-invocation forward progress for ``rcu_nocbs`` CPUs is much less well-developed, in part because workloads benefiting from ``rcu_nocbs`` CPUs tend to invoke -``call_rcu()`` relatively infrequently. If workloads emerge that need -both ``rcu_nocbs`` CPUs and high ``call_rcu()`` invocation rates, then +call_rcu() relatively infrequently. If workloads emerge that need +both ``rcu_nocbs`` CPUs and high call_rcu() invocation rates, then additional forward-progress work will be required. Composability @@ -1496,11 +1495,11 @@ in fact may be nested arbitrarily deeply. In practice, as with all real-world implementations of composable constructs, there are limitations. -Implementations of RCU for which ``rcu_read_lock()`` and -``rcu_read_unlock()`` generate no code, such as Linux-kernel RCU when -``CONFIG_PREEMPT=n``, can be nested arbitrarily deeply. After all, there +Implementations of RCU for which rcu_read_lock() and +rcu_read_unlock() generate no code, such as Linux-kernel RCU when +``CONFIG_PREEMPTION=n``, can be nested arbitrarily deeply. After all, there is no overhead. Except that if all these instances of -``rcu_read_lock()`` and ``rcu_read_unlock()`` are visible to the +rcu_read_lock() and rcu_read_unlock() are visible to the compiler, compilation will eventually fail due to exhausting memory, mass storage, or user patience, whichever comes first. If the nesting is not visible to the compiler, as is the case with mutually recursive @@ -1558,11 +1557,11 @@ argue that such workloads should instead use something other than RCU, the fact remains that RCU must handle such workloads gracefully. This requirement is another factor driving batching of grace periods, but it is also the driving force behind the checks for large numbers of queued -RCU callbacks in the ``call_rcu()`` code path. Finally, high update +RCU callbacks in the call_rcu() code path. Finally, high update rates should not delay RCU read-side critical sections, although some small read-side delays can occur when using -``synchronize_rcu_expedited()``, courtesy of this function's use of -``smp_call_function_single()``. +synchronize_rcu_expedited(), courtesy of this function's use of +smp_call_function_single(). Although all three of these corner cases were understood in the early 1990s, a simple user-level test consisting of ``close(open(path))`` in a @@ -1583,48 +1582,48 @@ Software-Engineering Requirements Between Murphy's Law and “To err is human”, it is necessary to guard against mishaps and misuse: -#. It is all too easy to forget to use ``rcu_read_lock()`` everywhere +#. It is all too easy to forget to use rcu_read_lock() everywhere that it is needed, so kernels built with ``CONFIG_PROVE_RCU=y`` will - splat if ``rcu_dereference()`` is used outside of an RCU read-side + splat if rcu_dereference() is used outside of an RCU read-side critical section. Update-side code can use - ``rcu_dereference_protected()``, which takes a `lockdep + rcu_dereference_protected(), which takes a `lockdep expression <https://lwn.net/Articles/371986/>`__ to indicate what is providing the protection. If the indicated protection is not provided, a lockdep splat is emitted. Code shared between readers and updaters can use - ``rcu_dereference_check()``, which also takes a lockdep expression, - and emits a lockdep splat if neither ``rcu_read_lock()`` nor the + rcu_dereference_check(), which also takes a lockdep expression, + and emits a lockdep splat if neither rcu_read_lock() nor the indicated protection is in place. In addition, - ``rcu_dereference_raw()`` is used in those (hopefully rare) cases + rcu_dereference_raw() is used in those (hopefully rare) cases where the required protection cannot be easily described. Finally, - ``rcu_read_lock_held()`` is provided to allow a function to verify + rcu_read_lock_held() is provided to allow a function to verify that it has been invoked within an RCU read-side critical section. I was made aware of this set of requirements shortly after Thomas Gleixner audited a number of RCU uses. #. A given function might wish to check for RCU-related preconditions upon entry, before using any other RCU API. The - ``rcu_lockdep_assert()`` does this job, asserting the expression in + rcu_lockdep_assert() does this job, asserting the expression in kernels having lockdep enabled and doing nothing otherwise. -#. It is also easy to forget to use ``rcu_assign_pointer()`` and - ``rcu_dereference()``, perhaps (incorrectly) substituting a simple +#. It is also easy to forget to use rcu_assign_pointer() and + rcu_dereference(), perhaps (incorrectly) substituting a simple assignment. To catch this sort of error, a given RCU-protected pointer may be tagged with ``__rcu``, after which sparse will complain about simple-assignment accesses to that pointer. Arnd Bergmann made me aware of this requirement, and also supplied the needed `patch series <https://lwn.net/Articles/376011/>`__. #. Kernels built with ``CONFIG_DEBUG_OBJECTS_RCU_HEAD=y`` will splat if - a data element is passed to ``call_rcu()`` twice in a row, without a + a data element is passed to call_rcu() twice in a row, without a grace period in between. (This error is similar to a double free.) The corresponding ``rcu_head`` structures that are dynamically allocated are automatically tracked, but ``rcu_head`` structures allocated on the stack must be initialized with - ``init_rcu_head_on_stack()`` and cleaned up with - ``destroy_rcu_head_on_stack()``. Similarly, statically allocated + init_rcu_head_on_stack() and cleaned up with + destroy_rcu_head_on_stack(). Similarly, statically allocated non-stack ``rcu_head`` structures must be initialized with - ``init_rcu_head()`` and cleaned up with ``destroy_rcu_head()``. + init_rcu_head() and cleaned up with destroy_rcu_head(). Mathieu Desnoyers made me aware of this requirement, and also supplied the needed - `patch <https://lkml.kernel.org/g/20100319013024.GA28456@Krystal>`__. + `patch <https://lore.kernel.org/r/20100319013024.GA28456@Krystal>`__. #. An infinite loop in an RCU read-side critical section will eventually trigger an RCU CPU stall warning splat, with the duration of “eventually” being controlled by the ``RCU_CPU_STALL_TIMEOUT`` @@ -1638,9 +1637,9 @@ against mishaps and misuse: ``rcupdate.rcu_cpu_stall_suppress`` to suppress the splats. This kernel parameter may also be set via ``sysfs``. Furthermore, RCU CPU stall warnings are counter-productive during sysrq dumps and during - panics. RCU therefore supplies the ``rcu_sysrq_start()`` and - ``rcu_sysrq_end()`` API members to be called before and after long - sysrq dumps. RCU also supplies the ``rcu_panic()`` notifier that is + panics. RCU therefore supplies the rcu_sysrq_start() and + rcu_sysrq_end() API members to be called before and after long + sysrq dumps. RCU also supplies the rcu_panic() notifier that is automatically invoked at the beginning of a panic to suppress further RCU CPU stall warnings. @@ -1656,7 +1655,7 @@ against mishaps and misuse: synchronization mechanism, for example, reference counting. #. In kernels built with ``CONFIG_RCU_TRACE=y``, RCU-related information is provided via event tracing. -#. Open-coded use of ``rcu_assign_pointer()`` and ``rcu_dereference()`` +#. Open-coded use of rcu_assign_pointer() and rcu_dereference() to create typical linked data structures can be surprisingly error-prone. Therefore, RCU-protected `linked lists <https://lwn.net/Articles/609973/#RCU%20List%20APIs>`__ and, @@ -1665,12 +1664,11 @@ against mishaps and misuse: other special-purpose RCU-protected data structures are available in the Linux kernel and the userspace RCU library. #. Some linked structures are created at compile time, but still require - ``__rcu`` checking. The ``RCU_POINTER_INITIALIZER()`` macro serves + ``__rcu`` checking. The RCU_POINTER_INITIALIZER() macro serves this purpose. -#. It is not necessary to use ``rcu_assign_pointer()`` when creating +#. It is not necessary to use rcu_assign_pointer() when creating linked structures that are to be published via a single external - pointer. The ``RCU_INIT_POINTER()`` macro is provided for this task - and also for assigning ``NULL`` pointers at runtime. + pointer. The RCU_INIT_POINTER() macro is provided for this task. This not a hard-and-fast list: RCU's diagnostic capabilities will continue to be guided by the number and type of usage bugs found in @@ -1716,7 +1714,7 @@ requires almost all of them be hidden behind a ``CONFIG_RCU_EXPERT`` This all should be quite obvious, but the fact remains that Linus Torvalds recently had to -`remind <https://lkml.kernel.org/g/CA+55aFy4wcCwaL4okTs8wXhGZ5h-ibecy_Meg9C4MNQrUnwMcg@mail.gmail.com>`__ +`remind <https://lore.kernel.org/r/CA+55aFy4wcCwaL4okTs8wXhGZ5h-ibecy_Meg9C4MNQrUnwMcg@mail.gmail.com>`__ me of this requirement. Firmware Interface @@ -1743,17 +1741,17 @@ Early Boot ~~~~~~~~~~ The Linux kernel's boot sequence is an interesting process, and RCU is -used early, even before ``rcu_init()`` is invoked. In fact, a number of +used early, even before rcu_init() is invoked. In fact, a number of RCU's primitives can be used as soon as the initial task's ``task_struct`` is available and the boot CPU's per-CPU variables are -set up. The read-side primitives (``rcu_read_lock()``, -``rcu_read_unlock()``, ``rcu_dereference()``, and -``rcu_access_pointer()``) will operate normally very early on, as will -``rcu_assign_pointer()``. +set up. The read-side primitives (rcu_read_lock(), +rcu_read_unlock(), rcu_dereference(), and +rcu_access_pointer()) will operate normally very early on, as will +rcu_assign_pointer(). -Although ``call_rcu()`` may be invoked at any time during boot, +Although call_rcu() may be invoked at any time during boot, callbacks are not guaranteed to be invoked until after all of RCU's -kthreads have been spawned, which occurs at ``early_initcall()`` time. +kthreads have been spawned, which occurs at early_initcall() time. This delay in callback invocation is due to the fact that RCU does not invoke callbacks until it is fully initialized, and this full initialization cannot occur until after the scheduler has initialized @@ -1762,22 +1760,22 @@ it would be possible to invoke callbacks earlier, however, this is not a panacea because there would be severe restrictions on what operations those callbacks could invoke. -Perhaps surprisingly, ``synchronize_rcu()`` and -``synchronize_rcu_expedited()``, will operate normally during very early +Perhaps surprisingly, synchronize_rcu() and +synchronize_rcu_expedited(), will operate normally during very early boot, the reason being that there is only one CPU and preemption is -disabled. This means that the call ``synchronize_rcu()`` (or friends) +disabled. This means that the call synchronize_rcu() (or friends) itself is a quiescent state and thus a grace period, so the early-boot implementation can be a no-op. However, once the scheduler has spawned its first kthread, this early -boot trick fails for ``synchronize_rcu()`` (as well as for -``synchronize_rcu_expedited()``) in ``CONFIG_PREEMPT=y`` kernels. The +boot trick fails for synchronize_rcu() (as well as for +synchronize_rcu_expedited()) in ``CONFIG_PREEMPTION=y`` kernels. The reason is that an RCU read-side critical section might be preempted, -which means that a subsequent ``synchronize_rcu()`` really does have to +which means that a subsequent synchronize_rcu() really does have to wait for something, as opposed to simply returning immediately. -Unfortunately, ``synchronize_rcu()`` can't do this until all of its +Unfortunately, synchronize_rcu() can't do this until all of its kthreads are spawned, which doesn't happen until some time during -``early_initcalls()`` time. But this is no excuse: RCU is nevertheless +early_initcalls() time. But this is no excuse: RCU is nevertheless required to correctly handle synchronous grace periods during this time period. Once all of its kthreads are up and running, RCU starts running normally. @@ -1820,7 +1818,7 @@ Interrupts and NMIs The Linux kernel has interrupts, and RCU read-side critical sections are legal within interrupt handlers and within interrupt-disabled regions of -code, as are invocations of ``call_rcu()``. +code, as are invocations of call_rcu(). Some Linux-kernel architectures can enter an interrupt handler from non-idle process context, and then just never leave it, instead @@ -1832,22 +1830,22 @@ way during a rewrite of RCU's dyntick-idle code. The Linux kernel has non-maskable interrupts (NMIs), and RCU read-side critical sections are legal within NMI handlers. Thankfully, RCU -update-side primitives, including ``call_rcu()``, are prohibited within +update-side primitives, including call_rcu(), are prohibited within NMI handlers. The name notwithstanding, some Linux-kernel architectures can have nested NMIs, which RCU must handle correctly. Andy Lutomirski `surprised -me <https://lkml.kernel.org/r/CALCETrXLq1y7e_dKFPgou-FKHB6Pu-r8+t-6Ds+8=va7anBWDA@mail.gmail.com>`__ +me <https://lore.kernel.org/r/CALCETrXLq1y7e_dKFPgou-FKHB6Pu-r8+t-6Ds+8=va7anBWDA@mail.gmail.com>`__ with this requirement; he also kindly surprised me with `an -algorithm <https://lkml.kernel.org/r/CALCETrXSY9JpW3uE6H8WYk81sg56qasA2aqmjMPsq5dOtzso=g@mail.gmail.com>`__ +algorithm <https://lore.kernel.org/r/CALCETrXSY9JpW3uE6H8WYk81sg56qasA2aqmjMPsq5dOtzso=g@mail.gmail.com>`__ that meets this requirement. Furthermore, NMI handlers can be interrupted by what appear to RCU to be normal interrupts. One way that this can happen is for code that -directly invokes ``rcu_irq_enter()`` and ``rcu_irq_exit()`` to be called +directly invokes rcu_irq_enter() and rcu_irq_exit() to be called from an NMI handler. This astonishing fact of life prompted the current -code structure, which has ``rcu_irq_enter()`` invoking -``rcu_nmi_enter()`` and ``rcu_irq_exit()`` invoking ``rcu_nmi_exit()``. +code structure, which has rcu_irq_enter() invoking +rcu_nmi_enter() and rcu_irq_exit() invoking rcu_nmi_exit(). And yes, I also learned of this requirement the hard way. Loadable Modules @@ -1857,45 +1855,45 @@ The Linux kernel has loadable modules, and these modules can also be unloaded. After a given module has been unloaded, any attempt to call one of its functions results in a segmentation fault. The module-unload functions must therefore cancel any delayed calls to loadable-module -functions, for example, any outstanding ``mod_timer()`` must be dealt -with via ``del_timer_sync()`` or similar. +functions, for example, any outstanding mod_timer() must be dealt +with via del_timer_sync() or similar. Unfortunately, there is no way to cancel an RCU callback; once you -invoke ``call_rcu()``, the callback function is eventually going to be +invoke call_rcu(), the callback function is eventually going to be invoked, unless the system goes down first. Because it is normally considered socially irresponsible to crash the system in response to a module unload request, we need some other way to deal with in-flight RCU callbacks. -RCU therefore provides ``rcu_barrier()``, which waits until all +RCU therefore provides rcu_barrier(), which waits until all in-flight RCU callbacks have been invoked. If a module uses -``call_rcu()``, its exit function should therefore prevent any future -invocation of ``call_rcu()``, then invoke ``rcu_barrier()``. In theory, -the underlying module-unload code could invoke ``rcu_barrier()`` +call_rcu(), its exit function should therefore prevent any future +invocation of call_rcu(), then invoke rcu_barrier(). In theory, +the underlying module-unload code could invoke rcu_barrier() unconditionally, but in practice this would incur unacceptable latencies. Nikita Danilov noted this requirement for an analogous filesystem-unmount situation, and Dipankar Sarma incorporated -``rcu_barrier()`` into RCU. The need for ``rcu_barrier()`` for module +rcu_barrier() into RCU. The need for rcu_barrier() for module unloading became apparent later. .. important:: - The ``rcu_barrier()`` function is not, repeat, + The rcu_barrier() function is not, repeat, *not*, obligated to wait for a grace period. It is instead only required to wait for RCU callbacks that have already been posted. Therefore, if there are no RCU callbacks posted anywhere in the system, - ``rcu_barrier()`` is within its rights to return immediately. Even if - there are callbacks posted, ``rcu_barrier()`` does not necessarily need + rcu_barrier() is within its rights to return immediately. Even if + there are callbacks posted, rcu_barrier() does not necessarily need to wait for a grace period. +-----------------------------------------------------------------------+ | **Quick Quiz**: | +-----------------------------------------------------------------------+ | Wait a minute! Each RCU callbacks must wait for a grace period to | -| complete, and ``rcu_barrier()`` must wait for each pre-existing | -| callback to be invoked. Doesn't ``rcu_barrier()`` therefore need to | +| complete, and rcu_barrier() must wait for each pre-existing | +| callback to be invoked. Doesn't rcu_barrier() therefore need to | | wait for a full grace period if there is even one callback posted | | anywhere in the system? | +-----------------------------------------------------------------------+ @@ -1904,14 +1902,14 @@ unloading became apparent later. | Absolutely not!!! | | Yes, each RCU callbacks must wait for a grace period to complete, but | | it might well be partly (or even completely) finished waiting by the | -| time ``rcu_barrier()`` is invoked. In that case, ``rcu_barrier()`` | +| time rcu_barrier() is invoked. In that case, rcu_barrier() | | need only wait for the remaining portion of the grace period to | | elapse. So even if there are quite a few callbacks posted, | -| ``rcu_barrier()`` might well return quite quickly. | +| rcu_barrier() might well return quite quickly. | | | | So if you need to wait for a grace period as well as for all | | pre-existing callbacks, you will need to invoke both | -| ``synchronize_rcu()`` and ``rcu_barrier()``. If latency is a concern, | +| synchronize_rcu() and rcu_barrier(). If latency is a concern, | | you can always use workqueues to invoke them concurrently. | +-----------------------------------------------------------------------+ @@ -1929,18 +1927,18 @@ The Linux-kernel CPU-hotplug implementation has notifiers that are used to allow the various kernel subsystems (including RCU) to respond appropriately to a given CPU-hotplug operation. Most RCU operations may be invoked from CPU-hotplug notifiers, including even synchronous -grace-period operations such as (``synchronize_rcu()`` and -``synchronize_rcu_expedited()``). However, these synchronous operations +grace-period operations such as (synchronize_rcu() and +synchronize_rcu_expedited()). However, these synchronous operations do block and therefore cannot be invoked from notifiers that execute via -``stop_machine()``, specifically those between the ``CPUHP_AP_OFFLINE`` +stop_machine(), specifically those between the ``CPUHP_AP_OFFLINE`` and ``CPUHP_AP_ONLINE`` states. -In addition, all-callback-wait operations such as ``rcu_barrier()`` may +In addition, all-callback-wait operations such as rcu_barrier() may not be invoked from any CPU-hotplug notifier. This restriction is due to the fact that there are phases of CPU-hotplug operations where the outgoing CPU's callbacks will not be invoked until after the CPU-hotplug operation ends, which could also result in deadlock. Furthermore, -``rcu_barrier()`` blocks CPU-hotplug operations during its execution, +rcu_barrier() blocks CPU-hotplug operations during its execution, which results in another type of deadlock when invoked from a CPU-hotplug notifier. @@ -1955,12 +1953,12 @@ if offline CPUs block an RCU grace period for too long. An offline CPU's quiescent state will be reported either: -1. As the CPU goes offline using RCU's hotplug notifier (``rcu_report_dead()``). -2. When grace period initialization (``rcu_gp_init()``) detects a +1. As the CPU goes offline using RCU's hotplug notifier (rcu_report_dead()). +2. When grace period initialization (rcu_gp_init()) detects a race either with CPU offlining or with a task unblocking on a leaf ``rcu_node`` structure whose CPUs are all offline. -The CPU-online path (``rcu_cpu_starting()``) should never need to report +The CPU-online path (rcu_cpu_starting()) should never need to report a quiescent state for an offline CPU. However, as a debugging measure, it does emit a warning if a quiescent state was not already reported for that CPU. @@ -1984,11 +1982,11 @@ room for further improvement. There is no longer any prohibition against holding any of scheduler's runqueue or priority-inheritance spinlocks across an -``rcu_read_unlock()``, even if interrupts and preemption were enabled +rcu_read_unlock(), even if interrupts and preemption were enabled somewhere within the corresponding RCU read-side critical section. -Therefore, it is now perfectly legal to execute ``rcu_read_lock()`` +Therefore, it is now perfectly legal to execute rcu_read_lock() with preemption enabled, acquire one of the scheduler locks, and hold -that lock across the matching ``rcu_read_unlock()``. +that lock across the matching rcu_read_unlock(). Similarly, the RCU flavor consolidation has removed the need for negative nesting. The fact that interrupt-disabled regions of code act as RCU @@ -1999,7 +1997,7 @@ Tracing and RCU ~~~~~~~~~~~~~~~ It is possible to use tracing on RCU code, but tracing itself uses RCU. -For this reason, ``rcu_dereference_raw_check()`` is provided for use +For this reason, rcu_dereference_raw_check() is provided for use by tracing, which avoids the destructive recursion that could otherwise ensue. This API is also used by virtualization in some architectures, where RCU readers execute in environments in which tracing cannot be @@ -2010,12 +2008,12 @@ Accesses to User Memory and RCU ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ The kernel needs to access user-space memory, for example, to access data -referenced by system-call parameters. The ``get_user()`` macro does this job. +referenced by system-call parameters. The get_user() macro does this job. However, user-space memory might well be paged out, which means that -``get_user()`` might well page-fault and thus block while waiting for the +get_user() might well page-fault and thus block while waiting for the resulting I/O to complete. It would be a very bad thing for the compiler to -reorder a ``get_user()`` invocation into an RCU read-side critical section. +reorder a get_user() invocation into an RCU read-side critical section. For example, suppose that the source code looked like this: @@ -2040,23 +2038,23 @@ the following: 5 rcu_read_unlock(); 6 do_something_with(v, user_v); -If the compiler did make this transformation in a ``CONFIG_PREEMPT=n`` kernel -build, and if ``get_user()`` did page fault, the result would be a quiescent +If the compiler did make this transformation in a ``CONFIG_PREEMPTION=n`` kernel +build, and if get_user() did page fault, the result would be a quiescent state in the middle of an RCU read-side critical section. This misplaced quiescent state could result in line 4 being a use-after-free access, which could be bad for your kernel's actuarial statistics. Similar examples -can be constructed with the call to ``get_user()`` preceding the -``rcu_read_lock()``. +can be constructed with the call to get_user() preceding the +rcu_read_lock(). -Unfortunately, ``get_user()`` doesn't have any particular ordering properties, +Unfortunately, get_user() doesn't have any particular ordering properties, and in some architectures the underlying ``asm`` isn't even marked ``volatile``. And even if it was marked ``volatile``, the above access to ``p->value`` is not volatile, so the compiler would not have any reason to keep those two accesses in order. -Therefore, the Linux-kernel definitions of ``rcu_read_lock()`` and -``rcu_read_unlock()`` must act as compiler barriers, at least for outermost -instances of ``rcu_read_lock()`` and ``rcu_read_unlock()`` within a nested set +Therefore, the Linux-kernel definitions of rcu_read_lock() and +rcu_read_unlock() must act as compiler barriers, at least for outermost +instances of rcu_read_lock() and rcu_read_unlock() within a nested set of RCU read-side critical sections. Energy Efficiency @@ -2071,26 +2069,26 @@ call. Because RCU avoids interrupting idle CPUs, it is illegal to execute an RCU read-side critical section on an idle CPU. (Kernels built with -``CONFIG_PROVE_RCU=y`` will splat if you try it.) The ``RCU_NONIDLE()`` +``CONFIG_PROVE_RCU=y`` will splat if you try it.) The RCU_NONIDLE() macro and ``_rcuidle`` event tracing is provided to work around this -restriction. In addition, ``rcu_is_watching()`` may be used to test +restriction. In addition, rcu_is_watching() may be used to test whether or not it is currently legal to run RCU read-side critical sections on this CPU. I learned of the need for diagnostics on the one -hand and ``RCU_NONIDLE()`` on the other while inspecting idle-loop code. +hand and RCU_NONIDLE() on the other while inspecting idle-loop code. Steven Rostedt supplied ``_rcuidle`` event tracing, which is used quite heavily in the idle loop. However, there are some restrictions on the -code placed within ``RCU_NONIDLE()``: +code placed within RCU_NONIDLE(): #. Blocking is prohibited. In practice, this is not a serious restriction given that idle tasks are prohibited from blocking to begin with. -#. Although nesting ``RCU_NONIDLE()`` is permitted, they cannot nest +#. Although nesting RCU_NONIDLE() is permitted, they cannot nest indefinitely deeply. However, given that they can be nested on the order of a million deep, even on 32-bit systems, this should not be a serious restriction. This nesting limit would probably be reached long after the compiler OOMed or the stack overflowed. -#. Any code path that enters ``RCU_NONIDLE()`` must sequence out of that - same ``RCU_NONIDLE()``. For example, the following is grossly +#. Any code path that enters RCU_NONIDLE() must sequence out of that + same RCU_NONIDLE(). For example, the following is grossly illegal: :: @@ -2103,7 +2101,7 @@ code placed within ``RCU_NONIDLE()``: It is just as illegal to transfer control into the middle of - ``RCU_NONIDLE()``'s argument. Yes, in theory, you could transfer in + RCU_NONIDLE()'s argument. Yes, in theory, you could transfer in as long as you also transferred out, but in practice you could also expect to get sharply worded review comments. @@ -2195,9 +2193,9 @@ scheduling-clock interrupt be enabled when RCU needs it to be: sections, and RCU believes this CPU to be idle, no problem. This sort of thing is used by some architectures for light-weight exception handlers, which can then avoid the overhead of - ``rcu_irq_enter()`` and ``rcu_irq_exit()`` at exception entry and + rcu_irq_enter() and rcu_irq_exit() at exception entry and exit, respectively. Some go further and avoid the entireties of - ``irq_enter()`` and ``irq_exit()``. + irq_enter() and irq_exit(). Just make very sure you are running some of your tests with ``CONFIG_PROVE_RCU=y``, just in case one of your code paths was in fact joking about not doing RCU read-side critical sections. @@ -2221,7 +2219,7 @@ scheduling-clock interrupt be enabled when RCU needs it to be: | **Quick Quiz**: | +-----------------------------------------------------------------------+ | But what if my driver has a hardware interrupt handler that can run | -| for many seconds? I cannot invoke ``schedule()`` from an hardware | +| for many seconds? I cannot invoke schedule() from an hardware | | interrupt handler, after all! | +-----------------------------------------------------------------------+ | **Answer**: | @@ -2243,8 +2241,8 @@ Memory Efficiency Although small-memory non-realtime systems can simply use Tiny RCU, code size is only one aspect of memory efficiency. Another aspect is the size -of the ``rcu_head`` structure used by ``call_rcu()`` and -``kfree_rcu()``. Although this structure contains nothing more than a +of the ``rcu_head`` structure used by call_rcu() and +kfree_rcu(). Although this structure contains nothing more than a pair of pointers, it does appear in many RCU-protected data structures, including some that are size critical. The ``page`` structure is a case in point, as evidenced by the many occurrences of the ``union`` keyword @@ -2254,7 +2252,7 @@ This need for memory efficiency is one reason that RCU uses hand-crafted singly linked lists to track the ``rcu_head`` structures that are waiting for a grace period to elapse. It is also the reason why ``rcu_head`` structures do not contain debug information, such as fields -tracking the file and line of the ``call_rcu()`` or ``kfree_rcu()`` that +tracking the file and line of the call_rcu() or kfree_rcu() that posted them. Although this information might appear in debug-only kernel builds at some point, in the meantime, the ``->func`` field will often provide the needed debug information. @@ -2264,18 +2262,18 @@ more extreme measures. Returning to the ``page`` structure, the ``rcu_head`` field shares storage with a great many other structures that are used at various points in the corresponding page's lifetime. In order to correctly resolve certain `race -conditions <https://lkml.kernel.org/g/1439976106-137226-1-git-send-email-kirill.shutemov@linux.intel.com>`__, +conditions <https://lore.kernel.org/r/1439976106-137226-1-git-send-email-kirill.shutemov@linux.intel.com>`__, the Linux kernel's memory-management subsystem needs a particular bit to remain zero during all phases of grace-period processing, and that bit happens to map to the bottom bit of the ``rcu_head`` structure's -``->next`` field. RCU makes this guarantee as long as ``call_rcu()`` is -used to post the callback, as opposed to ``kfree_rcu()`` or some future -“lazy” variant of ``call_rcu()`` that might one day be created for +``->next`` field. RCU makes this guarantee as long as call_rcu() is +used to post the callback, as opposed to kfree_rcu() or some future +“lazy” variant of call_rcu() that might one day be created for energy-efficiency purposes. That said, there are limits. RCU requires that the ``rcu_head`` structure be aligned to a two-byte boundary, and passing a misaligned -``rcu_head`` structure to one of the ``call_rcu()`` family of functions +``rcu_head`` structure to one of the call_rcu() family of functions will result in a splat. It is therefore necessary to exercise caution when packing structures containing fields of type ``rcu_head``. Why not a four-byte or even eight-byte alignment requirement? Because the m68k @@ -2299,7 +2297,7 @@ hot code paths in performance-critical portions of the Linux kernel's networking, security, virtualization, and scheduling code paths. RCU must therefore use efficient implementations, especially in its read-side primitives. To that end, it would be good if preemptible RCU's -implementation of ``rcu_read_lock()`` could be inlined, however, doing +implementation of rcu_read_lock() could be inlined, however, doing this requires resolving ``#include`` issues with the ``task_struct`` structure. @@ -2312,23 +2310,23 @@ on the ``rcu_node`` structure. RCU is required to tolerate all CPUs continuously invoking any combination of RCU's runtime primitives with minimal per-operation overhead. In fact, in many cases, increasing load must *decrease* the per-operation overhead, witness the batching -optimizations for ``synchronize_rcu()``, ``call_rcu()``, -``synchronize_rcu_expedited()``, and ``rcu_barrier()``. As a general +optimizations for synchronize_rcu(), call_rcu(), +synchronize_rcu_expedited(), and rcu_barrier(). As a general rule, RCU must cheerfully accept whatever the rest of the Linux kernel decides to throw at it. The Linux kernel is used for real-time workloads, especially in conjunction with the `-rt -patchset <https://rt.wiki.kernel.org/index.php/Main_Page>`__. The +patchset <https://wiki.linuxfoundation.org/realtime/>`__. The real-time-latency response requirements are such that the traditional approach of disabling preemption across RCU read-side critical sections -is inappropriate. Kernels built with ``CONFIG_PREEMPT=y`` therefore use +is inappropriate. Kernels built with ``CONFIG_PREEMPTION=y`` therefore use an RCU implementation that allows RCU read-side critical sections to be preempted. This requirement made its presence known after users made it clear that an earlier `real-time patch <https://lwn.net/Articles/107930/>`__ did not meet their needs, in conjunction with some `RCU -issues <https://lkml.kernel.org/g/20050318002026.GA2693@us.ibm.com>`__ +issues <https://lore.kernel.org/r/20050318002026.GA2693@us.ibm.com>`__ encountered by a very early version of the -rt patchset. In addition, RCU must make do with a sub-100-microsecond real-time @@ -2346,7 +2344,7 @@ number of race conditions. RCU must avoid degrading real-time response for CPU-bound threads, whether executing in usermode (which is one use case for ``CONFIG_NO_HZ_FULL=y``) or in the kernel. That said, CPU-bound loops in -the kernel must execute ``cond_resched()`` at least once per few tens of +the kernel must execute cond_resched() at least once per few tens of milliseconds in order to avoid receiving an IPI from RCU. Finally, RCU's status as a synchronization primitive means that any RCU @@ -2412,7 +2410,7 @@ grace periods from ever ending. The result was an out-of-memory condition and a system hang. The solution was the creation of RCU-bh, which does -``local_bh_disable()`` across its read-side critical sections, and which +local_bh_disable() across its read-side critical sections, and which uses the transition from one type of softirq processing to another as a quiescent state in addition to context switch, idle, user mode, and offline. This means that RCU-bh grace periods can complete even when @@ -2420,31 +2418,31 @@ some of the CPUs execute in softirq indefinitely, thus allowing algorithms based on RCU-bh to withstand network-based denial-of-service attacks. -Because ``rcu_read_lock_bh()`` and ``rcu_read_unlock_bh()`` disable and +Because rcu_read_lock_bh() and rcu_read_unlock_bh() disable and re-enable softirq handlers, any attempt to start a softirq handlers during the RCU-bh read-side critical section will be deferred. In this -case, ``rcu_read_unlock_bh()`` will invoke softirq processing, which can +case, rcu_read_unlock_bh() will invoke softirq processing, which can take considerable time. One can of course argue that this softirq overhead should be associated with the code following the RCU-bh -read-side critical section rather than ``rcu_read_unlock_bh()``, but the +read-side critical section rather than rcu_read_unlock_bh(), but the fact is that most profiling tools cannot be expected to make this sort of fine distinction. For example, suppose that a three-millisecond-long RCU-bh read-side critical section executes during a time of heavy networking load. There will very likely be an attempt to invoke at least one softirq handler during that three milliseconds, but any such invocation will be delayed until the time of the -``rcu_read_unlock_bh()``. This can of course make it appear at first -glance as if ``rcu_read_unlock_bh()`` was executing very slowly. +rcu_read_unlock_bh(). This can of course make it appear at first +glance as if rcu_read_unlock_bh() was executing very slowly. The `RCU-bh API <https://lwn.net/Articles/609973/#RCU%20Per-Flavor%20API%20Table>`__ -includes ``rcu_read_lock_bh()``, ``rcu_read_unlock_bh()``, -``rcu_dereference_bh()``, ``rcu_dereference_bh_check()``, -``synchronize_rcu_bh()``, ``synchronize_rcu_bh_expedited()``, -``call_rcu_bh()``, ``rcu_barrier_bh()``, and -``rcu_read_lock_bh_held()``. However, the update-side APIs are now -simple wrappers for other RCU flavors, namely RCU-sched in -CONFIG_PREEMPT=n kernels and RCU-preempt otherwise. +includes rcu_read_lock_bh(), rcu_read_unlock_bh(), rcu_dereference_bh(), +rcu_dereference_bh_check(), and rcu_read_lock_bh_held(). However, the +old RCU-bh update-side APIs are now gone, replaced by synchronize_rcu(), +synchronize_rcu_expedited(), call_rcu(), and rcu_barrier(). In addition, +anything that disables bottom halves also marks an RCU-bh read-side +critical section, including local_bh_disable() and local_bh_enable(), +local_irq_save() and local_irq_restore(), and so on. Sched Flavor (Historical) ~~~~~~~~~~~~~~~~~~~~~~~~~ @@ -2462,32 +2460,32 @@ not have this property, given that any point in the code outside of an RCU read-side critical section can be a quiescent state. Therefore, *RCU-sched* was created, which follows “classic” RCU in that an RCU-sched grace period waits for pre-existing interrupt and NMI -handlers. In kernels built with ``CONFIG_PREEMPT=n``, the RCU and +handlers. In kernels built with ``CONFIG_PREEMPTION=n``, the RCU and RCU-sched APIs have identical implementations, while kernels built with -``CONFIG_PREEMPT=y`` provide a separate implementation for each. +``CONFIG_PREEMPTION=y`` provide a separate implementation for each. -Note well that in ``CONFIG_PREEMPT=y`` kernels, -``rcu_read_lock_sched()`` and ``rcu_read_unlock_sched()`` disable and +Note well that in ``CONFIG_PREEMPTION=y`` kernels, +rcu_read_lock_sched() and rcu_read_unlock_sched() disable and re-enable preemption, respectively. This means that if there was a preemption attempt during the RCU-sched read-side critical section, -``rcu_read_unlock_sched()`` will enter the scheduler, with all the -latency and overhead entailed. Just as with ``rcu_read_unlock_bh()``, -this can make it look as if ``rcu_read_unlock_sched()`` was executing +rcu_read_unlock_sched() will enter the scheduler, with all the +latency and overhead entailed. Just as with rcu_read_unlock_bh(), +this can make it look as if rcu_read_unlock_sched() was executing very slowly. However, the highest-priority task won't be preempted, so -that task will enjoy low-overhead ``rcu_read_unlock_sched()`` +that task will enjoy low-overhead rcu_read_unlock_sched() invocations. The `RCU-sched API <https://lwn.net/Articles/609973/#RCU%20Per-Flavor%20API%20Table>`__ -includes ``rcu_read_lock_sched()``, ``rcu_read_unlock_sched()``, -``rcu_read_lock_sched_notrace()``, ``rcu_read_unlock_sched_notrace()``, -``rcu_dereference_sched()``, ``rcu_dereference_sched_check()``, -``synchronize_sched()``, ``synchronize_rcu_sched_expedited()``, -``call_rcu_sched()``, ``rcu_barrier_sched()``, and -``rcu_read_lock_sched_held()``. However, anything that disables -preemption also marks an RCU-sched read-side critical section, including -``preempt_disable()`` and ``preempt_enable()``, ``local_irq_save()`` and -``local_irq_restore()``, and so on. +includes rcu_read_lock_sched(), rcu_read_unlock_sched(), +rcu_read_lock_sched_notrace(), rcu_read_unlock_sched_notrace(), +rcu_dereference_sched(), rcu_dereference_sched_check(), and +rcu_read_lock_sched_held(). However, the old RCU-sched update-side APIs +are now gone, replaced by synchronize_rcu(), synchronize_rcu_expedited(), +call_rcu(), and rcu_barrier(). In addition, anything that disables +preemption also marks an RCU-sched read-side critical section, +including preempt_disable() and preempt_enable(), local_irq_save() +and local_irq_restore(), and so on. Sleepable RCU ~~~~~~~~~~~~~ @@ -2509,7 +2507,7 @@ this structure must be passed in to each SRCU function, for example, structure. The key benefit of these domains is that a slow SRCU reader in one domain does not delay an SRCU grace period in some other domain. That said, one consequence of these domains is that read-side code must -pass a “cookie” from ``srcu_read_lock()`` to ``srcu_read_unlock()``, for +pass a “cookie” from srcu_read_lock() to srcu_read_unlock(), for example, as follows: :: @@ -2539,24 +2537,24 @@ period to elapse. For example, this results in a self-deadlock: 6 srcu_read_unlock(&ss, idx); However, if line 5 acquired a mutex that was held across a -``synchronize_srcu()`` for domain ``ss``, deadlock would still be +synchronize_srcu() for domain ``ss``, deadlock would still be possible. Furthermore, if line 5 acquired a mutex that was held across a -``synchronize_srcu()`` for some other domain ``ss1``, and if an +synchronize_srcu() for some other domain ``ss1``, and if an ``ss1``-domain SRCU read-side critical section acquired another mutex -that was held across as ``ss``-domain ``synchronize_srcu()``, deadlock +that was held across as ``ss``-domain synchronize_srcu(), deadlock would again be possible. Such a deadlock cycle could extend across an arbitrarily large number of different SRCU domains. Again, with great power comes great responsibility. Unlike the other RCU flavors, SRCU read-side critical sections can run on idle and even offline CPUs. This ability requires that -``srcu_read_lock()`` and ``srcu_read_unlock()`` contain memory barriers, +srcu_read_lock() and srcu_read_unlock() contain memory barriers, which means that SRCU readers will run a bit slower than would RCU -readers. It also motivates the ``smp_mb__after_srcu_read_unlock()`` API, -which, in combination with ``srcu_read_unlock()``, guarantees a full +readers. It also motivates the smp_mb__after_srcu_read_unlock() API, +which, in combination with srcu_read_unlock(), guarantees a full memory barrier. -Also unlike other RCU flavors, ``synchronize_srcu()`` may **not** be +Also unlike other RCU flavors, synchronize_srcu() may **not** be invoked from CPU-hotplug notifiers, due to the fact that SRCU grace periods make use of timers and the possibility of timers being temporarily “stranded” on the outgoing CPU. This stranding of timers @@ -2565,7 +2563,7 @@ the CPU-hotplug process. The problem is that if a notifier is waiting on an SRCU grace period, that grace period is waiting on a timer, and that timer is stranded on the outgoing CPU, then the notifier will never be awakened, in other words, deadlock has occurred. This same situation of -course also prohibits ``srcu_barrier()`` from being invoked from +course also prohibits srcu_barrier() from being invoked from CPU-hotplug notifiers. SRCU also differs from other RCU flavors in that SRCU's expedited and @@ -2576,12 +2574,12 @@ have not yet completed. (But please note that this is a property of the current implementation, not necessarily of future implementations.) In addition, if SRCU has been idle for longer than the interval specified by the ``srcutree.exp_holdoff`` kernel boot parameter (25 microseconds -by default), and if a ``synchronize_srcu()`` invocation ends this idle +by default), and if a synchronize_srcu() invocation ends this idle period, that invocation will be automatically expedited. As of v4.12, SRCU's callbacks are maintained per-CPU, eliminating a locking bottleneck present in prior kernel versions. Although this will -allow users to put much heavier stress on ``call_srcu()``, it is +allow users to put much heavier stress on call_srcu(), it is important to note that SRCU does not yet take any special steps to deal with callback flooding. So if you are posting (say) 10,000 SRCU callbacks per second per CPU, you are probably totally OK, but if you @@ -2592,12 +2590,12 @@ of your CPUs and the size of your memory. The `SRCU API <https://lwn.net/Articles/609973/#RCU%20Per-Flavor%20API%20Table>`__ -includes ``srcu_read_lock()``, ``srcu_read_unlock()``, -``srcu_dereference()``, ``srcu_dereference_check()``, -``synchronize_srcu()``, ``synchronize_srcu_expedited()``, -``call_srcu()``, ``srcu_barrier()``, and ``srcu_read_lock_held()``. It -also includes ``DEFINE_SRCU()``, ``DEFINE_STATIC_SRCU()``, and -``init_srcu_struct()`` APIs for defining and initializing +includes srcu_read_lock(), srcu_read_unlock(), +srcu_dereference(), srcu_dereference_check(), +synchronize_srcu(), synchronize_srcu_expedited(), +call_srcu(), srcu_barrier(), and srcu_read_lock_held(). It +also includes DEFINE_SRCU(), DEFINE_STATIC_SRCU(), and +init_srcu_struct() APIs for defining and initializing ``srcu_struct`` structures. More recently, the SRCU API has added polling interfaces: @@ -2626,11 +2624,11 @@ required to install different types of probes. It would be good to be able to free old trampolines, which sounds like a job for some form of RCU. However, because it is necessary to be able to install a trace anywhere in the code, it is not possible to use read-side markers such -as ``rcu_read_lock()`` and ``rcu_read_unlock()``. In addition, it does +as rcu_read_lock() and rcu_read_unlock(). In addition, it does not work to have these markers in the trampoline itself, because there -would need to be instructions following ``rcu_read_unlock()``. Although -``synchronize_rcu()`` would guarantee that execution reached the -``rcu_read_unlock()``, it would not be able to guarantee that execution +would need to be instructions following rcu_read_unlock(). Although +synchronize_rcu() would guarantee that execution reached the +rcu_read_unlock(), it would not be able to guarantee that execution had completely left the trampoline. Worse yet, in some situations the trampoline's protection must extend a few instructions *prior* to execution reaching the trampoline. For example, these few instructions @@ -2641,16 +2639,16 @@ actually reached the trampoline itself. The solution, in the form of `Tasks RCU <https://lwn.net/Articles/607117/>`__, is to have implicit read-side critical sections that are delimited by voluntary context switches, that -is, calls to ``schedule()``, ``cond_resched()``, and -``synchronize_rcu_tasks()``. In addition, transitions to and from +is, calls to schedule(), cond_resched(), and +synchronize_rcu_tasks(). In addition, transitions to and from userspace execution also delimit tasks-RCU read-side critical sections. The tasks-RCU API is quite compact, consisting only of -``call_rcu_tasks()``, ``synchronize_rcu_tasks()``, and -``rcu_barrier_tasks()``. In ``CONFIG_PREEMPT=n`` kernels, trampolines -cannot be preempted, so these APIs map to ``call_rcu()``, -``synchronize_rcu()``, and ``rcu_barrier()``, respectively. In -``CONFIG_PREEMPT=y`` kernels, trampolines can be preempted, and these +call_rcu_tasks(), synchronize_rcu_tasks(), and +rcu_barrier_tasks(). In ``CONFIG_PREEMPTION=n`` kernels, trampolines +cannot be preempted, so these APIs map to call_rcu(), +synchronize_rcu(), and rcu_barrier(), respectively. In +``CONFIG_PREEMPTION=y`` kernels, trampolines can be preempted, and these three APIs are therefore implemented by separate functions that check for voluntary context switches. @@ -2664,8 +2662,8 @@ grace-period state machine so as to avoid the need for the additional latency. RCU disables CPU hotplug in a few places, perhaps most notably in the -``rcu_barrier()`` operations. If there is a strong reason to use -``rcu_barrier()`` in CPU-hotplug notifiers, it will be necessary to +rcu_barrier() operations. If there is a strong reason to use +rcu_barrier() in CPU-hotplug notifiers, it will be necessary to avoid disabling CPU hotplug. This would introduce some complexity, so there had better be a *very* good reason. @@ -2682,7 +2680,7 @@ However, this combining tree does not spread its memory across NUMA nodes nor does it align the CPU groups with hardware features such as sockets or cores. Such spreading and alignment is currently believed to be unnecessary because the hotpath read-side primitives do not access -the combining tree, nor does ``call_rcu()`` in the common case. If you +the combining tree, nor does call_rcu() in the common case. If you believe that your architecture needs such spreading and alignment, then your architecture should also benefit from the ``rcutree.rcu_fanout_leaf`` boot parameter, which can be set to the @@ -2703,7 +2701,7 @@ likely that adjustments will be required to more gracefully handle extreme loads. It might also be necessary to be able to relate CPU utilization by RCU's kthreads and softirq handlers to the code that instigated this CPU utilization. For example, RCU callback overhead -might be charged back to the originating ``call_rcu()`` instance, though +might be charged back to the originating call_rcu() instance, though probably not in production kernels. Additional work may be required to provide reasonable forward-progress diff --git a/Documentation/RCU/checklist.rst b/Documentation/RCU/checklist.rst index bb7128eb322e..1030119294d0 100644 --- a/Documentation/RCU/checklist.rst +++ b/Documentation/RCU/checklist.rst @@ -70,7 +70,7 @@ over a rather long period of time, but improvements are always welcome! is less readable and prevents lockdep from detecting locking issues. Letting RCU-protected pointers "leak" out of an RCU read-side - critical section is every bid as bad as letting them leak out + critical section is every bit as bad as letting them leak out from under a lock. Unless, of course, you have arranged some other means of protection, such as a lock or a reference count -before- letting them out of the RCU read-side critical section. @@ -129,9 +129,7 @@ over a rather long period of time, but improvements are always welcome! accesses. The rcu_dereference() primitive ensures that the CPU picks up the pointer before it picks up the data that the pointer points to. This really is necessary - on Alpha CPUs. If you don't believe me, see: - - http://www.openvms.compaq.com/wizard/wiz_2637.html + on Alpha CPUs. The rcu_dereference() primitive is also an excellent documentation aid, letting the person reading the @@ -214,9 +212,9 @@ over a rather long period of time, but improvements are always welcome! the rest of the system. 7. As of v4.20, a given kernel implements only one RCU flavor, - which is RCU-sched for PREEMPT=n and RCU-preempt for PREEMPT=y. + which is RCU-sched for PREEMPTION=n and RCU-preempt for PREEMPTION=y. If the updater uses call_rcu() or synchronize_rcu(), - then the corresponding readers my use rcu_read_lock() and + then the corresponding readers may use rcu_read_lock() and rcu_read_unlock(), rcu_read_lock_bh() and rcu_read_unlock_bh(), or any pair of primitives that disables and re-enables preemption, for example, rcu_read_lock_sched() and rcu_read_unlock_sched(). diff --git a/Documentation/RCU/rcubarrier.rst b/Documentation/RCU/rcubarrier.rst index f64f4413a47c..3b4a24877496 100644 --- a/Documentation/RCU/rcubarrier.rst +++ b/Documentation/RCU/rcubarrier.rst @@ -9,7 +9,7 @@ RCU (read-copy update) is a synchronization mechanism that can be thought of as a replacement for read-writer locking (among other things), but with very low-overhead readers that are immune to deadlock, priority inversion, and unbounded latency. RCU read-side critical sections are delimited -by rcu_read_lock() and rcu_read_unlock(), which, in non-CONFIG_PREEMPT +by rcu_read_lock() and rcu_read_unlock(), which, in non-CONFIG_PREEMPTION kernels, generate no code whatsoever. This means that RCU writers are unaware of the presence of concurrent @@ -329,10 +329,10 @@ Answer: This cannot happen. The reason is that on_each_cpu() has its last to smp_call_function() and further to smp_call_function_on_cpu(), causing this latter to spin until the cross-CPU invocation of rcu_barrier_func() has completed. This by itself would prevent - a grace period from completing on non-CONFIG_PREEMPT kernels, + a grace period from completing on non-CONFIG_PREEMPTION kernels, since each CPU must undergo a context switch (or other quiescent state) before the grace period can complete. However, this is - of no use in CONFIG_PREEMPT kernels. + of no use in CONFIG_PREEMPTION kernels. Therefore, on_each_cpu() disables preemption across its call to smp_call_function() and also across the local call to diff --git a/Documentation/RCU/stallwarn.rst b/Documentation/RCU/stallwarn.rst index c9ab6af4d3be..7148e9be08c3 100644 --- a/Documentation/RCU/stallwarn.rst +++ b/Documentation/RCU/stallwarn.rst @@ -25,7 +25,7 @@ warnings: - A CPU looping with bottom halves disabled. -- For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the kernel +- For !CONFIG_PREEMPTION kernels, a CPU looping anywhere in the kernel without invoking schedule(). If the looping in the kernel is really expected and desirable behavior, you might need to add some calls to cond_resched(). @@ -44,7 +44,7 @@ warnings: result in the ``rcu_.*kthread starved for`` console-log message, which will include additional debugging information. -- A CPU-bound real-time task in a CONFIG_PREEMPT kernel, which might +- A CPU-bound real-time task in a CONFIG_PREEMPTION kernel, which might happen to preempt a low-priority task in the middle of an RCU read-side critical section. This is especially damaging if that low-priority task is not permitted to run on any other CPU, @@ -92,7 +92,9 @@ warnings: buggy timer hardware through bugs in the interrupt or exception path (whether hardware, firmware, or software) through bugs in Linux's timer subsystem through bugs in the scheduler, and, - yes, even including bugs in RCU itself. + yes, even including bugs in RCU itself. It can also result in + the ``rcu_.*timer wakeup didn't happen for`` console-log message, + which will include additional debugging information. - A bug in the RCU implementation. @@ -292,6 +294,25 @@ kthread is waiting for a short timeout, the "state" precedes value of the task_struct ->state field, and the "cpu" indicates that the grace-period kthread last ran on CPU 5. +If the relevant grace-period kthread does not wake from FQS wait in a +reasonable time, then the following additional line is printed:: + + kthread timer wakeup didn't happen for 23804 jiffies! g7076 f0x0 RCU_GP_WAIT_FQS(5) ->state=0x402 + +The "23804" indicates that kthread's timer expired more than 23 thousand +jiffies ago. The rest of the line has meaning similar to the kthread +starvation case. + +Additionally, the following line is printed:: + + Possible timer handling issue on cpu=4 timer-softirq=11142 + +Here "cpu" indicates that the grace-period kthread last ran on CPU 4, +where it queued the fqs timer. The number following the "timer-softirq" +is the current ``TIMER_SOFTIRQ`` count on cpu 4. If this value does not +change on successive RCU CPU stall warnings, there is further reason to +suspect a timer problem. + Multiple Warnings From One Stall ================================ diff --git a/Documentation/RCU/whatisRCU.rst b/Documentation/RCU/whatisRCU.rst index 1a4723f48bd9..17e95ab2a201 100644 --- a/Documentation/RCU/whatisRCU.rst +++ b/Documentation/RCU/whatisRCU.rst @@ -683,7 +683,7 @@ Quick Quiz #1: ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ This section presents a "toy" RCU implementation that is based on "classic RCU". It is also short on performance (but only for updates) and -on features such as hotplug CPU and the ability to run in CONFIG_PREEMPT +on features such as hotplug CPU and the ability to run in CONFIG_PREEMPTION kernels. The definitions of rcu_dereference() and rcu_assign_pointer() are the same as those shown in the preceding section, so they are omitted. :: @@ -739,7 +739,7 @@ Quick Quiz #2: Quick Quiz #3: If it is illegal to block in an RCU read-side critical section, what the heck do you do in - PREEMPT_RT, where normal spinlocks can block??? + CONFIG_PREEMPT_RT, where normal spinlocks can block??? :ref:`Answers to Quick Quiz <8_whatisRCU>` @@ -1093,7 +1093,7 @@ Quick Quiz #2: overhead is **negative**. Answer: - Imagine a single-CPU system with a non-CONFIG_PREEMPT + Imagine a single-CPU system with a non-CONFIG_PREEMPTION kernel where a routing table is used by process-context code, but can be updated by irq-context code (for example, by an "ICMP REDIRECT" packet). The usual way of handling @@ -1120,10 +1120,10 @@ Answer: Quick Quiz #3: If it is illegal to block in an RCU read-side critical section, what the heck do you do in - PREEMPT_RT, where normal spinlocks can block??? + CONFIG_PREEMPT_RT, where normal spinlocks can block??? Answer: - Just as PREEMPT_RT permits preemption of spinlock + Just as CONFIG_PREEMPT_RT permits preemption of spinlock critical sections, it permits preemption of RCU read-side critical sections. It also permits spinlocks blocking while in RCU read-side critical diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 18f3aa759e54..b1d6cd58a04c 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -4092,6 +4092,10 @@ value, meaning that RCU_SOFTIRQ is used by default. Specify rcutree.use_softirq=0 to use rcuc kthreads. + But note that CONFIG_PREEMPT_RT=y kernels disable + this kernel boot parameter, forcibly setting it + to zero. + rcutree.rcu_fanout_exact= [KNL] Disable autobalancing of the rcu_node combining tree. This is used by rcutorture, and might @@ -4179,12 +4183,6 @@ Set wakeup interval for idle CPUs that have RCU callbacks (RCU_FAST_NO_HZ=y). - rcutree.rcu_idle_lazy_gp_delay= [KNL] - Set wakeup interval for idle CPUs that have - only "lazy" RCU callbacks (RCU_FAST_NO_HZ=y). - Lazy RCU callbacks are those which RCU can - prove do nothing more than free memory. - rcutree.rcu_kick_kthreads= [KNL] Cause the grace-period kthread to get an extra wake_up() if it sleeps three times longer than @@ -4338,6 +4336,14 @@ stress RCU, they don't participate in the actual test, hence the "fake". + rcutorture.nocbs_nthreads= [KNL] + Set number of RCU callback-offload togglers. + Zero (the default) disables toggling. + + rcutorture.nocbs_toggle= [KNL] + Set the delay in milliseconds between successive + callback-offload toggling attempts. + rcutorture.nreaders= [KNL] Set number of RCU readers. The value -1 selects N-1, where N is the number of CPUs. A value @@ -4470,6 +4476,13 @@ only normal grace-period primitives. No effect on CONFIG_TINY_RCU kernels. + But note that CONFIG_PREEMPT_RT=y kernels enables + this kernel boot parameter, forcibly setting + it to the value one, that is, converting any + post-boot attempt at an expedited RCU grace + period to instead use normal non-expedited + grace-period processing. + rcupdate.rcu_task_ipi_delay= [KNL] Set time in jiffies during which RCU tasks will avoid sending IPIs, starting with the beginning diff --git a/include/linux/cpu.h b/include/linux/cpu.h index d6428aaf67e7..3aaa0687e8df 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -111,6 +111,8 @@ static inline void cpu_maps_update_done(void) #endif /* CONFIG_SMP */ extern struct bus_type cpu_subsys; +extern int lockdep_is_cpus_held(void); + #ifdef CONFIG_HOTPLUG_CPU extern void cpus_write_lock(void); extern void cpus_write_unlock(void); diff --git a/include/linux/list.h b/include/linux/list.h index 89bdc92e75c3..f2af4b4aa4e9 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -901,7 +901,7 @@ static inline void hlist_add_before(struct hlist_node *n, } /** - * hlist_add_behing - add a new entry after the one specified + * hlist_add_behind - add a new entry after the one specified * @n: new entry to be added * @prev: hlist node to add it after, which must be non-NULL */ diff --git a/include/linux/mm.h b/include/linux/mm.h index 5299b90a6c40..af7d050900e7 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3169,5 +3169,7 @@ unsigned long wp_shared_mapping_range(struct address_space *mapping, extern int sysctl_nr_trim_pages; +void mem_dump_obj(void *object); + #endif /* __KERNEL__ */ #endif /* _LINUX_MM_H */ diff --git a/include/linux/rcu_segcblist.h b/include/linux/rcu_segcblist.h index b36afe7b22c9..8afe886e85f1 100644 --- a/include/linux/rcu_segcblist.h +++ b/include/linux/rcu_segcblist.h @@ -63,6 +63,122 @@ struct rcu_cblist { #define RCU_NEXT_TAIL 3 #define RCU_CBLIST_NSEGS 4 + +/* + * ==NOCB Offloading state machine== + * + * + * ---------------------------------------------------------------------------- + * | SEGCBLIST_SOFTIRQ_ONLY | + * | | + * | Callbacks processed by rcu_core() from softirqs or local | + * | rcuc kthread, without holding nocb_lock. | + * ---------------------------------------------------------------------------- + * | + * v + * ---------------------------------------------------------------------------- + * | SEGCBLIST_OFFLOADED | + * | | + * | Callbacks processed by rcu_core() from softirqs or local | + * | rcuc kthread, while holding nocb_lock. Waking up CB and GP kthreads, | + * | allowing nocb_timer to be armed. | + * ---------------------------------------------------------------------------- + * | + * v + * ----------------------------------- + * | | + * v v + * --------------------------------------- ----------------------------------| + * | SEGCBLIST_OFFLOADED | | | SEGCBLIST_OFFLOADED | | + * | SEGCBLIST_KTHREAD_CB | | SEGCBLIST_KTHREAD_GP | + * | | | | + * | | | | + * | CB kthread woke up and | | GP kthread woke up and | + * | acknowledged SEGCBLIST_OFFLOADED. | | acknowledged SEGCBLIST_OFFLOADED| + * | Processes callbacks concurrently | | | + * | with rcu_core(), holding | | | + * | nocb_lock. | | | + * --------------------------------------- ----------------------------------- + * | | + * ----------------------------------- + * | + * v + * |--------------------------------------------------------------------------| + * | SEGCBLIST_OFFLOADED | | + * | SEGCBLIST_KTHREAD_CB | | + * | SEGCBLIST_KTHREAD_GP | + * | | + * | Kthreads handle callbacks holding nocb_lock, local rcu_core() stops | + * | handling callbacks. | + * ---------------------------------------------------------------------------- + */ + + + +/* + * ==NOCB De-Offloading state machine== + * + * + * |--------------------------------------------------------------------------| + * | SEGCBLIST_OFFLOADED | | + * | SEGCBLIST_KTHREAD_CB | | + * | SEGCBLIST_KTHREAD_GP | + * | | + * | CB/GP kthreads handle callbacks holding nocb_lock, local rcu_core() | + * | ignores callbacks. | + * ---------------------------------------------------------------------------- + * | + * v + * |--------------------------------------------------------------------------| + * | SEGCBLIST_KTHREAD_CB | | + * | SEGCBLIST_KTHREAD_GP | + * | | + * | CB/GP kthreads and local rcu_core() handle callbacks concurrently | + * | holding nocb_lock. Wake up CB and GP kthreads if necessary. | + * ---------------------------------------------------------------------------- + * | + * v + * ----------------------------------- + * | | + * v v + * ---------------------------------------------------------------------------| + * | | + * | SEGCBLIST_KTHREAD_CB | SEGCBLIST_KTHREAD_GP | + * | | | + * | GP kthread woke up and | CB kthread woke up and | + * | acknowledged the fact that | acknowledged the fact that | + * | SEGCBLIST_OFFLOADED got cleared. | SEGCBLIST_OFFLOADED got cleared. | + * | | The CB kthread goes to sleep | + * | The callbacks from the target CPU | until it ever gets re-offloaded. | + * | will be ignored from the GP kthread | | + * | loop. | | + * ---------------------------------------------------------------------------- + * | | + * ----------------------------------- + * | + * v + * ---------------------------------------------------------------------------- + * | 0 | + * | | + * | Callbacks processed by rcu_core() from softirqs or local | + * | rcuc kthread, while holding nocb_lock. Forbid nocb_timer to be armed. | + * | Flush pending nocb_timer. Flush nocb bypass callbacks. | + * ---------------------------------------------------------------------------- + * | + * v + * ---------------------------------------------------------------------------- + * | SEGCBLIST_SOFTIRQ_ONLY | + * | | + * | Callbacks processed by rcu_core() from softirqs or local | + * | rcuc kthread, without holding nocb_lock. | + * ---------------------------------------------------------------------------- + */ +#define SEGCBLIST_ENABLED BIT(0) +#define SEGCBLIST_SOFTIRQ_ONLY BIT(1) +#define SEGCBLIST_KTHREAD_CB BIT(2) +#define SEGCBLIST_KTHREAD_GP BIT(3) +#define SEGCBLIST_OFFLOADED BIT(4) + struct rcu_segcblist { struct rcu_head *head; struct rcu_head **tails[RCU_CBLIST_NSEGS]; @@ -72,8 +188,8 @@ struct rcu_segcblist { #else long len; #endif - u8 enabled; - u8 offloaded; + long seglen[RCU_CBLIST_NSEGS]; + u8 flags; }; #define RCU_SEGCBLIST_INITIALIZER(n) \ diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h index e09c0d87b3c3..ebd8dcca4997 100644 --- a/include/linux/rcupdate.h +++ b/include/linux/rcupdate.h @@ -88,6 +88,12 @@ void rcu_sched_clock_irq(int user); void rcu_report_dead(unsigned int cpu); void rcutree_migrate_callbacks(int cpu); +#ifdef CONFIG_TASKS_RCU_GENERIC +void rcu_init_tasks_generic(void); +#else +static inline void rcu_init_tasks_generic(void) { } +#endif + #ifdef CONFIG_RCU_STALL_COMMON void rcu_sysrq_start(void); void rcu_sysrq_end(void); @@ -106,8 +112,12 @@ static inline void rcu_user_exit(void) { } #ifdef CONFIG_RCU_NOCB_CPU void rcu_init_nohz(void); +int rcu_nocb_cpu_offload(int cpu); +int rcu_nocb_cpu_deoffload(int cpu); #else /* #ifdef CONFIG_RCU_NOCB_CPU */ static inline void rcu_init_nohz(void) { } +static inline int rcu_nocb_cpu_offload(int cpu) { return -EINVAL; } +static inline int rcu_nocb_cpu_deoffload(int cpu) { return 0; } #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ /** @@ -842,19 +852,11 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) */ #define __is_kvfree_rcu_offset(offset) ((offset) < 4096) -/* - * Helper macro for kfree_rcu() to prevent argument-expansion eyestrain. - */ -#define __kvfree_rcu(head, offset) \ - do { \ - BUILD_BUG_ON(!__is_kvfree_rcu_offset(offset)); \ - kvfree_call_rcu(head, (rcu_callback_t)(unsigned long)(offset)); \ - } while (0) - /** * kfree_rcu() - kfree an object after a grace period. - * @ptr: pointer to kfree - * @rhf: the name of the struct rcu_head within the type of @ptr. + * @ptr: pointer to kfree for both single- and double-argument invocations. + * @rhf: the name of the struct rcu_head within the type of @ptr, + * but only for double-argument invocations. * * Many rcu callbacks functions just call kfree() on the base structure. * These functions are trivial, but their size adds up, and furthermore @@ -867,7 +869,7 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) * Because the functions are not allowed in the low-order 4096 bytes of * kernel virtual memory, offsets up to 4095 bytes can be accommodated. * If the offset is larger than 4095 bytes, a compile-time error will - * be generated in __kvfree_rcu(). If this error is triggered, you can + * be generated in kvfree_rcu_arg_2(). If this error is triggered, you can * either fall back to use of call_rcu() or rearrange the structure to * position the rcu_head structure into the first 4096 bytes. * @@ -877,13 +879,7 @@ static inline notrace void rcu_read_unlock_sched_notrace(void) * The BUILD_BUG_ON check must not involve any function calls, hence the * checks are done in macros here. */ -#define kfree_rcu(ptr, rhf) \ -do { \ - typeof (ptr) ___p = (ptr); \ - \ - if (___p) \ - __kvfree_rcu(&((___p)->rhf), offsetof(typeof(*(ptr)), rhf)); \ -} while (0) +#define kfree_rcu kvfree_rcu /** * kvfree_rcu() - kvfree an object after a grace period. @@ -915,7 +911,17 @@ do { \ kvfree_rcu_arg_2, kvfree_rcu_arg_1)(__VA_ARGS__) #define KVFREE_GET_MACRO(_1, _2, NAME, ...) NAME -#define kvfree_rcu_arg_2(ptr, rhf) kfree_rcu(ptr, rhf) +#define kvfree_rcu_arg_2(ptr, rhf) \ +do { \ + typeof (ptr) ___p = (ptr); \ + \ + if (___p) { \ + BUILD_BUG_ON(!__is_kvfree_rcu_offset(offsetof(typeof(*(ptr)), rhf))); \ + kvfree_call_rcu(&((___p)->rhf), (rcu_callback_t)(unsigned long) \ + (offsetof(typeof(*(ptr)), rhf))); \ + } \ +} while (0) + #define kvfree_rcu_arg_1(ptr) \ do { \ typeof(ptr) ___p = (ptr); \ diff --git a/include/linux/slab.h b/include/linux/slab.h index be4ba5867ac5..7ae604076767 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -186,6 +186,8 @@ void kfree(const void *); void kfree_sensitive(const void *); size_t __ksize(const void *); size_t ksize(const void *); +bool kmem_valid_obj(void *object); +void kmem_dump_obj(void *object); #ifdef CONFIG_HAVE_HARDENED_USERCOPY_ALLOCATOR void __check_heap_object(const void *ptr, unsigned long n, struct page *page, diff --git a/include/linux/timer.h b/include/linux/timer.h index fda13c9d1256..4118a97e62fb 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -192,6 +192,8 @@ extern int try_to_del_timer_sync(struct timer_list *timer); #define del_singleshot_timer_sync(t) del_timer_sync(t) +extern bool timer_curr_running(struct timer_list *timer); + extern void init_timers(void); struct hrtimer; extern enum hrtimer_restart it_real_fn(struct hrtimer *); diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 80c0181c411d..c18f4751a704 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -246,4 +246,10 @@ pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms) int register_vmap_purge_notifier(struct notifier_block *nb); int unregister_vmap_purge_notifier(struct notifier_block *nb); +#ifdef CONFIG_MMU +bool vmalloc_dump_obj(void *object); +#else +static inline bool vmalloc_dump_obj(void *object) { return false; } +#endif + #endif /* _LINUX_VMALLOC_H */ diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h index 155b5cb43cfd..5fc29400e1a2 100644 --- a/include/trace/events/rcu.h +++ b/include/trace/events/rcu.h @@ -505,6 +505,32 @@ TRACE_EVENT_RCU(rcu_callback, __entry->qlen) ); +TRACE_EVENT_RCU(rcu_segcb_stats, + + TP_PROTO(struct rcu_segcblist *rs, const char *ctx), + + TP_ARGS(rs, ctx), + + TP_STRUCT__entry( + __field(const char *, ctx) + __array(unsigned long, gp_seq, RCU_CBLIST_NSEGS) + __array(long, seglen, RCU_CBLIST_NSEGS) + ), + + TP_fast_assign( + __entry->ctx = ctx; + memcpy(__entry->seglen, rs->seglen, RCU_CBLIST_NSEGS * sizeof(long)); + memcpy(__entry->gp_seq, rs->gp_seq, RCU_CBLIST_NSEGS * sizeof(unsigned long)); + + ), + + TP_printk("%s seglen: (DONE=%ld, WAIT=%ld, NEXT_READY=%ld, NEXT=%ld) " + "gp_seq: (DONE=%lu, WAIT=%lu, NEXT_READY=%lu, NEXT=%lu)", __entry->ctx, + __entry->seglen[0], __entry->seglen[1], __entry->seglen[2], __entry->seglen[3], + __entry->gp_seq[0], __entry->gp_seq[1], __entry->gp_seq[2], __entry->gp_seq[3]) + +); + /* * Tracepoint for the registration of a single RCU callback of the special * kvfree() form. The first argument is the RCU type, the second argument diff --git a/init/main.c b/init/main.c index 6feee7f11eaf..421640fca375 100644 --- a/init/main.c +++ b/init/main.c @@ -1518,6 +1518,7 @@ static noinline void __init kernel_init_freeable(void) init_mm_internals(); + rcu_init_tasks_generic(); do_pre_smp_initcalls(); lockup_detector_init(); diff --git a/kernel/cpu.c b/kernel/cpu.c index 4e11e91010e1..1b6302ecbabe 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -330,6 +330,13 @@ void lockdep_assert_cpus_held(void) percpu_rwsem_assert_held(&cpu_hotplug_lock); } +#ifdef CONFIG_LOCKDEP +int lockdep_is_cpus_held(void) +{ + return percpu_rwsem_is_held(&cpu_hotplug_lock); +} +#endif + static void lockdep_acquire_cpus_lock(void) { rwsem_acquire(&cpu_hotplug_lock.dep_map, 0, 0, _THIS_IP_); diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c index fd838cea3934..0ab94e1f1276 100644 --- a/kernel/locking/locktorture.c +++ b/kernel/locking/locktorture.c @@ -27,7 +27,6 @@ #include <linux/moduleparam.h> #include <linux/delay.h> #include <linux/slab.h> -#include <linux/percpu-rwsem.h> #include <linux/torture.h> #include <linux/reboot.h> diff --git a/kernel/rcu/Kconfig b/kernel/rcu/Kconfig index cdc57b4f6d48..3128b7cf8e1f 100644 --- a/kernel/rcu/Kconfig +++ b/kernel/rcu/Kconfig @@ -95,6 +95,7 @@ config TASKS_RUDE_RCU config TASKS_TRACE_RCU def_bool 0 + select IRQ_WORK help This option enables a task-based RCU implementation that uses explicit rcu_read_lock_trace() read-side markers, and allows @@ -188,8 +189,8 @@ config RCU_FAST_NO_HZ config RCU_BOOST bool "Enable RCU priority boosting" - depends on RT_MUTEXES && PREEMPT_RCU && RCU_EXPERT - default n + depends on (RT_MUTEXES && PREEMPT_RCU && RCU_EXPERT) || PREEMPT_RT + default y if PREEMPT_RT help This option boosts the priority of preempted RCU readers that block the current preemptible RCU grace period for too long. diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h index 59ef1ae6dc37..bf0827d4b659 100644 --- a/kernel/rcu/rcu.h +++ b/kernel/rcu/rcu.h @@ -378,7 +378,11 @@ do { \ smp_mb__after_unlock_lock(); \ } while (0) -#define raw_spin_unlock_rcu_node(p) raw_spin_unlock(&ACCESS_PRIVATE(p, lock)) +#define raw_spin_unlock_rcu_node(p) \ +do { \ + lockdep_assert_irqs_disabled(); \ + raw_spin_unlock(&ACCESS_PRIVATE(p, lock)); \ +} while (0) #define raw_spin_lock_irq_rcu_node(p) \ do { \ @@ -387,7 +391,10 @@ do { \ } while (0) #define raw_spin_unlock_irq_rcu_node(p) \ - raw_spin_unlock_irq(&ACCESS_PRIVATE(p, lock)) +do { \ + lockdep_assert_irqs_disabled(); \ + raw_spin_unlock_irq(&ACCESS_PRIVATE(p, lock)); \ +} while (0) #define raw_spin_lock_irqsave_rcu_node(p, flags) \ do { \ @@ -396,7 +403,10 @@ do { \ } while (0) #define raw_spin_unlock_irqrestore_rcu_node(p, flags) \ - raw_spin_unlock_irqrestore(&ACCESS_PRIVATE(p, lock), flags) +do { \ + lockdep_assert_irqs_disabled(); \ + raw_spin_unlock_irqrestore(&ACCESS_PRIVATE(p, lock), flags); \ +} while (0) #define raw_spin_trylock_rcu_node(p) \ ({ \ diff --git a/kernel/rcu/rcu_segcblist.c b/kernel/rcu/rcu_segcblist.c index 2d2a6b6b9dfb..7f181c9675f7 100644 --- a/kernel/rcu/rcu_segcblist.c +++ b/kernel/rcu/rcu_segcblist.c @@ -7,10 +7,10 @@ * Authors: Paul E. McKenney <paulmck@linux.ibm.com> */ -#include <linux/types.h> -#include <linux/kernel.h> +#include <linux/cpu.h> #include <linux/interrupt.h> -#include <linux/rcupdate.h> +#include <linux/kernel.h> +#include <linux/types.h> #include "rcu_segcblist.h" @@ -88,23 +88,135 @@ static void rcu_segcblist_set_len(struct rcu_segcblist *rsclp, long v) #endif } +/* Get the length of a segment of the rcu_segcblist structure. */ +static long rcu_segcblist_get_seglen(struct rcu_segcblist *rsclp, int seg) +{ + return READ_ONCE(rsclp->seglen[seg]); +} + +/* Return number of callbacks in segmented callback list by summing seglen. */ +long rcu_segcblist_n_segment_cbs(struct rcu_segcblist *rsclp) +{ + long len = 0; + int i; + + for (i = RCU_DONE_TAIL; i < RCU_CBLIST_NSEGS; i++) + len += rcu_segcblist_get_seglen(rsclp, i); + + return len; +} + +/* Set the length of a segment of the rcu_segcblist structure. */ +static void rcu_segcblist_set_seglen(struct rcu_segcblist *rsclp, int seg, long v) +{ + WRITE_ONCE(rsclp->seglen[seg], v); +} + +/* Increase the numeric length of a segment by a specified amount. */ +static void rcu_segcblist_add_seglen(struct rcu_segcblist *rsclp, int seg, long v) +{ + WRITE_ONCE(rsclp->seglen[seg], rsclp->seglen[seg] + v); +} + +/* Move from's segment length to to's segment. */ +static void rcu_segcblist_move_seglen(struct rcu_segcblist *rsclp, int from, int to) +{ + long len; + + if (from == to) + return; + + len = rcu_segcblist_get_seglen(rsclp, from); + if (!len) + return; + + rcu_segcblist_add_seglen(rsclp, to, len); + rcu_segcblist_set_seglen(rsclp, from, 0); +} + +/* Increment segment's length. */ +static void rcu_segcblist_inc_seglen(struct rcu_segcblist *rsclp, int seg) +{ + rcu_segcblist_add_seglen(rsclp, seg, 1); +} + /* * Increase the numeric length of an rcu_segcblist structure by the * specified amount, which can be negative. This can cause the ->len * field to disagree with the actual number of callbacks on the structure. * This increase is fully ordered with respect to the callers accesses * both before and after. + * + * So why on earth is a memory barrier required both before and after + * the update to the ->len field??? + * + * The reason is that rcu_barrier() locklessly samples each CPU's ->len + * field, and if a given CPU's field is zero, avoids IPIing that CPU. + * This can of course race with both queuing and invoking of callbacks. + * Failing to correctly handle either of these races could result in + * rcu_barrier() failing to IPI a CPU that actually had callbacks queued + * which rcu_barrier() was obligated to wait on. And if rcu_barrier() + * failed to wait on such a callback, unloading certain kernel modules + * would result in calls to functions whose code was no longer present in + * the kernel, for but one example. + * + * Therefore, ->len transitions from 1->0 and 0->1 have to be carefully + * ordered with respect with both list modifications and the rcu_barrier(). + * + * The queuing case is CASE 1 and the invoking case is CASE 2. + * + * CASE 1: Suppose that CPU 0 has no callbacks queued, but invokes + * call_rcu() just as CPU 1 invokes rcu_barrier(). CPU 0's ->len field + * will transition from 0->1, which is one of the transitions that must + * be handled carefully. Without the full memory barriers after the ->len + * update and at the beginning of rcu_barrier(), the following could happen: + * + * CPU 0 CPU 1 + * + * call_rcu(). + * rcu_barrier() sees ->len as 0. + * set ->len = 1. + * rcu_barrier() does nothing. + * module is unloaded. + * callback invokes unloaded function! + * + * With the full barriers, any case where rcu_barrier() sees ->len as 0 will + * have unambiguously preceded the return from the racing call_rcu(), which + * means that this call_rcu() invocation is OK to not wait on. After all, + * you are supposed to make sure that any problematic call_rcu() invocations + * happen before the rcu_barrier(). + * + * + * CASE 2: Suppose that CPU 0 is invoking its last callback just as + * CPU 1 invokes rcu_barrier(). CPU 0's ->len field will transition from + * 1->0, which is one of the transitions that must be handled carefully. + * Without the full memory barriers before the ->len update and at the + * end of rcu_barrier(), the following could happen: + * + * CPU 0 CPU 1 + * + * start invoking last callback + * set ->len = 0 (reordered) + * rcu_barrier() sees ->len as 0 + * rcu_barrier() does nothing. + * module is unloaded + * callback executing after unloaded! + * + * With the full barriers, any case where rcu_barrier() sees ->len as 0 + * will be fully ordered after the completion of the callback function, + * so that the module unloading operation is completely safe. + * */ -static void rcu_segcblist_add_len(struct rcu_segcblist *rsclp, long v) +void rcu_segcblist_add_len(struct rcu_segcblist *rsclp, long v) { #ifdef CONFIG_RCU_NOCB_CPU - smp_mb__before_atomic(); /* Up to the caller! */ + smp_mb__before_atomic(); // Read header comment above. atomic_long_add(v, &rsclp->len); - smp_mb__after_atomic(); /* Up to the caller! */ + smp_mb__after_atomic(); // Read header comment above. #else - smp_mb(); /* Up to the caller! */ + smp_mb(); // Read header comment above. WRITE_ONCE(rsclp->len, rsclp->len + v); - smp_mb(); /* Up to the caller! */ + smp_mb(); // Read header comment above. #endif } @@ -120,26 +232,6 @@ void rcu_segcblist_inc_len(struct rcu_segcblist *rsclp) } /* - * Exchange the numeric length of the specified rcu_segcblist structure - * with the specified value. This can cause the ->len field to disagree - * with the actual number of callbacks on the structure. This exchange is - * fully ordered with respect to the callers accesses both before and after. - */ -static long rcu_segcblist_xchg_len(struct rcu_segcblist *rsclp, long v) -{ -#ifdef CONFIG_RCU_NOCB_CPU - return atomic_long_xchg(&rsclp->len, v); -#else - long ret = rsclp->len; - - smp_mb(); /* Up to the caller! */ - WRITE_ONCE(rsclp->len, v); - smp_mb(); /* Up to the caller! */ - return ret; -#endif -} - -/* * Initialize an rcu_segcblist structure. */ void rcu_segcblist_init(struct rcu_segcblist *rsclp) @@ -149,10 +241,12 @@ void rcu_segcblist_init(struct rcu_segcblist *rsclp) BUILD_BUG_ON(RCU_NEXT_TAIL + 1 != ARRAY_SIZE(rsclp->gp_seq)); BUILD_BUG_ON(ARRAY_SIZE(rsclp->tails) != ARRAY_SIZE(rsclp->gp_seq)); rsclp->head = NULL; - for (i = 0; i < RCU_CBLIST_NSEGS; i++) + for (i = 0; i < RCU_CBLIST_NSEGS; i++) { rsclp->tails[i] = &rsclp->head; + rcu_segcblist_set_seglen(rsclp, i, 0); + } rcu_segcblist_set_len(rsclp, 0); - rsclp->enabled = 1; + rcu_segcblist_set_flags(rsclp, SEGCBLIST_ENABLED); } /* @@ -163,16 +257,21 @@ void rcu_segcblist_disable(struct rcu_segcblist *rsclp) { WARN_ON_ONCE(!rcu_segcblist_empty(rsclp)); WARN_ON_ONCE(rcu_segcblist_n_cbs(rsclp)); - rsclp->enabled = 0; + rcu_segcblist_clear_flags(rsclp, SEGCBLIST_ENABLED); } /* * Mark the specified rcu_segcblist structure as offloaded. This * structure must be empty. */ -void rcu_segcblist_offload(struct rcu_segcblist *rsclp) +void rcu_segcblist_offload(struct rcu_segcblist *rsclp, bool offload) { - rsclp->offloaded = 1; + if (offload) { + rcu_segcblist_clear_flags(rsclp, SEGCBLIST_SOFTIRQ_ONLY); + rcu_segcblist_set_flags(rsclp, SEGCBLIST_OFFLOADED); + } else { + rcu_segcblist_clear_flags(rsclp, SEGCBLIST_OFFLOADED); + } } /* @@ -245,7 +344,7 @@ void rcu_segcblist_enqueue(struct rcu_segcblist *rsclp, struct rcu_head *rhp) { rcu_segcblist_inc_len(rsclp); - smp_mb(); /* Ensure counts are updated before callback is enqueued. */ + rcu_segcblist_inc_seglen(rsclp, RCU_NEXT_TAIL); rhp->next = NULL; WRITE_ONCE(*rsclp->tails[RCU_NEXT_TAIL], rhp); WRITE_ONCE(rsclp->tails[RCU_NEXT_TAIL], &rhp->next); @@ -274,6 +373,7 @@ bool rcu_segcblist_entrain(struct rcu_segcblist *rsclp, for (i = RCU_NEXT_TAIL; i > RCU_DONE_TAIL; i--) if (rsclp->tails[i] != rsclp->tails[i - 1]) break; + rcu_segcblist_inc_seglen(rsclp, i); WRITE_ONCE(*rsclp->tails[i], rhp); for (; i <= RCU_NEXT_TAIL; i++) WRITE_ONCE(rsclp->tails[i], &rhp->next); @@ -281,21 +381,6 @@ bool rcu_segcblist_entrain(struct rcu_segcblist *rsclp, } /* - * Extract only the counts from the specified rcu_segcblist structure, - * and place them in the specified rcu_cblist structure. This function - * supports both callback orphaning and invocation, hence the separation - * of counts and callbacks. (Callbacks ready for invocation must be - * orphaned and adopted separately from pending callbacks, but counts - * apply to all callbacks. Locking must be used to make sure that - * both orphaned-callbacks lists are consistent.) - */ -void rcu_segcblist_extract_count(struct rcu_segcblist *rsclp, - struct rcu_cblist *rclp) -{ - rclp->len = rcu_segcblist_xchg_len(rsclp, 0); -} - -/* * Extract only those callbacks ready to be invoked from the specified * rcu_segcblist structure and place them in the specified rcu_cblist * structure. @@ -307,6 +392,7 @@ void rcu_segcblist_extract_done_cbs(struct rcu_segcblist *rsclp, if (!rcu_segcblist_ready_cbs(rsclp)) return; /* Nothing to do. */ + rclp->len = rcu_segcblist_get_seglen(rsclp, RCU_DONE_TAIL); *rclp->tail = rsclp->head; WRITE_ONCE(rsclp->head, *rsclp->tails[RCU_DONE_TAIL]); WRITE_ONCE(*rsclp->tails[RCU_DONE_TAIL], NULL); @@ -314,6 +400,7 @@ void rcu_segcblist_extract_done_cbs(struct rcu_segcblist *rsclp, for (i = RCU_CBLIST_NSEGS - 1; i >= RCU_DONE_TAIL; i--) if (rsclp->tails[i] == rsclp->tails[RCU_DONE_TAIL]) WRITE_ONCE(rsclp->tails[i], &rsclp->head); + rcu_segcblist_set_seglen(rsclp, RCU_DONE_TAIL, 0); } /* @@ -330,11 +417,15 @@ void rcu_segcblist_extract_pend_cbs(struct rcu_segcblist *rsclp, if (!rcu_segcblist_pend_cbs(rsclp)) return; /* Nothing to do. */ + rclp->len = 0; *rclp->tail = *rsclp->tails[RCU_DONE_TAIL]; rclp->tail = rsclp->tails[RCU_NEXT_TAIL]; WRITE_ONCE(*rsclp->tails[RCU_DONE_TAIL], NULL); - for (i = RCU_DONE_TAIL + 1; i < RCU_CBLIST_NSEGS; i++) + for (i = RCU_DONE_TAIL + 1; i < RCU_CBLIST_NSEGS; i++) { + rclp->len += rcu_segcblist_get_seglen(rsclp, i); WRITE_ONCE(rsclp->tails[i], rsclp->tails[RCU_DONE_TAIL]); + rcu_segcblist_set_seglen(rsclp, i, 0); + } } /* @@ -345,7 +436,6 @@ void rcu_segcblist_insert_count(struct rcu_segcblist *rsclp, struct rcu_cblist *rclp) { rcu_segcblist_add_len(rsclp, rclp->len); - rclp->len = 0; } /* @@ -359,6 +449,7 @@ void rcu_segcblist_insert_done_cbs(struct rcu_segcblist *rsclp, if (!rclp->head) return; /* No callbacks to move. */ + rcu_segcblist_add_seglen(rsclp, RCU_DONE_TAIL, rclp->len); *rclp->tail = rsclp->head; WRITE_ONCE(rsclp->head, rclp->head); for (i = RCU_DONE_TAIL; i < RCU_CBLIST_NSEGS; i++) @@ -379,6 +470,8 @@ void rcu_segcblist_insert_pend_cbs(struct rcu_segcblist *rsclp, { if (!rclp->head) return; /* Nothing to do. */ + + rcu_segcblist_add_seglen(rsclp, RCU_NEXT_TAIL, rclp->len); WRITE_ONCE(*rsclp->tails[RCU_NEXT_TAIL], rclp->head); WRITE_ONCE(rsclp->tails[RCU_NEXT_TAIL], rclp->tail); } @@ -403,6 +496,7 @@ void rcu_segcblist_advance(struct rcu_segcblist *rsclp, unsigned long seq) if (ULONG_CMP_LT(seq, rsclp->gp_seq[i])) break; WRITE_ONCE(rsclp->tails[RCU_DONE_TAIL], rsclp->tails[i]); + rcu_segcblist_move_seglen(rsclp, i, RCU_DONE_TAIL); } /* If no callbacks moved, nothing more need be done. */ @@ -423,6 +517,7 @@ void rcu_segcblist_advance(struct rcu_segcblist *rsclp, unsigned long seq) if (rsclp->tails[j] == rsclp->tails[RCU_NEXT_TAIL]) break; /* No more callbacks. */ WRITE_ONCE(rsclp->tails[j], rsclp->tails[i]); + rcu_segcblist_move_seglen(rsclp, i, j); rsclp->gp_seq[j] = rsclp->gp_seq[i]; } } @@ -444,7 +539,7 @@ void rcu_segcblist_advance(struct rcu_segcblist *rsclp, unsigned long seq) */ bool rcu_segcblist_accelerate(struct rcu_segcblist *rsclp, unsigned long seq) { - int i; + int i, j; WARN_ON_ONCE(!rcu_segcblist_is_enabled(rsclp)); if (rcu_segcblist_restempty(rsclp, RCU_DONE_TAIL)) @@ -487,6 +582,10 @@ bool rcu_segcblist_accelerate(struct rcu_segcblist *rsclp, unsigned long seq) if (rcu_segcblist_restempty(rsclp, i) || ++i >= RCU_NEXT_TAIL) return false; + /* Accounting: everything below i is about to get merged into i. */ + for (j = i + 1; j <= RCU_NEXT_TAIL; j++) + rcu_segcblist_move_seglen(rsclp, j, i); + /* * Merge all later callbacks, including newly arrived callbacks, * into the segment located by the for-loop above. Assign "seq" @@ -514,13 +613,24 @@ void rcu_segcblist_merge(struct rcu_segcblist *dst_rsclp, struct rcu_cblist donecbs; struct rcu_cblist pendcbs; + lockdep_assert_cpus_held(); + rcu_cblist_init(&donecbs); rcu_cblist_init(&pendcbs); - rcu_segcblist_extract_count(src_rsclp, &donecbs); + rcu_segcblist_extract_done_cbs(src_rsclp, &donecbs); rcu_segcblist_extract_pend_cbs(src_rsclp, &pendcbs); + + /* + * No need smp_mb() before setting length to 0, because CPU hotplug + * lock excludes rcu_barrier. + */ + rcu_segcblist_set_len(src_rsclp, 0); + rcu_segcblist_insert_count(dst_rsclp, &donecbs); + rcu_segcblist_insert_count(dst_rsclp, &pendcbs); rcu_segcblist_insert_done_cbs(dst_rsclp, &donecbs); rcu_segcblist_insert_pend_cbs(dst_rsclp, &pendcbs); + rcu_segcblist_init(src_rsclp); } diff --git a/kernel/rcu/rcu_segcblist.h b/kernel/rcu/rcu_segcblist.h index 492262bcb591..9a19328ff251 100644 --- a/kernel/rcu/rcu_segcblist.h +++ b/kernel/rcu/rcu_segcblist.h @@ -15,6 +15,9 @@ static inline long rcu_cblist_n_cbs(struct rcu_cblist *rclp) return READ_ONCE(rclp->len); } +/* Return number of callbacks in segmented callback list by summing seglen. */ +long rcu_segcblist_n_segment_cbs(struct rcu_segcblist *rsclp); + void rcu_cblist_init(struct rcu_cblist *rclp); void rcu_cblist_enqueue(struct rcu_cblist *rclp, struct rcu_head *rhp); void rcu_cblist_flush_enqueue(struct rcu_cblist *drclp, @@ -50,19 +53,51 @@ static inline long rcu_segcblist_n_cbs(struct rcu_segcblist *rsclp) #endif } +static inline void rcu_segcblist_set_flags(struct rcu_segcblist *rsclp, + int flags) +{ + rsclp->flags |= flags; +} + +static inline void rcu_segcblist_clear_flags(struct rcu_segcblist *rsclp, + int flags) +{ + rsclp->flags &= ~flags; +} + +static inline bool rcu_segcblist_test_flags(struct rcu_segcblist *rsclp, + int flags) +{ + return READ_ONCE(rsclp->flags) & flags; +} + /* * Is the specified rcu_segcblist enabled, for example, not corresponding * to an offline CPU? */ static inline bool rcu_segcblist_is_enabled(struct rcu_segcblist *rsclp) { - return rsclp->enabled; + return rcu_segcblist_test_flags(rsclp, SEGCBLIST_ENABLED); } -/* Is the specified rcu_segcblist offloaded? */ +/* Is the specified rcu_segcblist offloaded, or is SEGCBLIST_SOFTIRQ_ONLY set? */ static inline bool rcu_segcblist_is_offloaded(struct rcu_segcblist *rsclp) { - return IS_ENABLED(CONFIG_RCU_NOCB_CPU) && rsclp->offloaded; + if (IS_ENABLED(CONFIG_RCU_NOCB_CPU) && + !rcu_segcblist_test_flags(rsclp, SEGCBLIST_SOFTIRQ_ONLY)) + return true; + + return false; +} + +static inline bool rcu_segcblist_completely_offloaded(struct rcu_segcblist *rsclp) +{ + int flags = SEGCBLIST_KTHREAD_CB | SEGCBLIST_KTHREAD_GP | SEGCBLIST_OFFLOADED; + + if (IS_ENABLED(CONFIG_RCU_NOCB_CPU) && (rsclp->flags & flags) == flags) + return true; + + return false; } /* @@ -75,10 +110,22 @@ static inline bool rcu_segcblist_restempty(struct rcu_segcblist *rsclp, int seg) return !READ_ONCE(*READ_ONCE(rsclp->tails[seg])); } +/* + * Is the specified segment of the specified rcu_segcblist structure + * empty of callbacks? + */ +static inline bool rcu_segcblist_segempty(struct rcu_segcblist *rsclp, int seg) +{ + if (seg == RCU_DONE_TAIL) + return &rsclp->head == rsclp->tails[RCU_DONE_TAIL]; + return rsclp->tails[seg - 1] == rsclp->tails[seg]; +} + void rcu_segcblist_inc_len(struct rcu_segcblist *rsclp); +void rcu_segcblist_add_len(struct rcu_segcblist *rsclp, long v); void rcu_segcblist_init(struct rcu_segcblist *rsclp); void rcu_segcblist_disable(struct rcu_segcblist *rsclp); -void rcu_segcblist_offload(struct rcu_segcblist *rsclp); +void rcu_segcblist_offload(struct rcu_segcblist *rsclp, bool offload); bool rcu_segcblist_ready_cbs(struct rcu_segcblist *rsclp); bool rcu_segcblist_pend_cbs(struct rcu_segcblist *rsclp); struct rcu_head *rcu_segcblist_first_cb(struct rcu_segcblist *rsclp); @@ -88,8 +135,6 @@ void rcu_segcblist_enqueue(struct rcu_segcblist *rsclp, struct rcu_head *rhp); bool rcu_segcblist_entrain(struct rcu_segcblist *rsclp, struct rcu_head *rhp); -void rcu_segcblist_extract_count(struct rcu_segcblist *rsclp, - struct rcu_cblist *rclp); void rcu_segcblist_extract_done_cbs(struct rcu_segcblist *rsclp, struct rcu_cblist *rclp); void rcu_segcblist_extract_pend_cbs(struct rcu_segcblist *rsclp, diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index a816df4e86e0..99657ffa6688 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -98,6 +98,8 @@ torture_param(int, object_debug, 0, torture_param(int, onoff_holdoff, 0, "Time after boot before CPU hotplugs (s)"); torture_param(int, onoff_interval, 0, "Time between CPU hotplugs (jiffies), 0=disable"); +torture_param(int, nocbs_nthreads, 0, "Number of NOCB toggle threads, 0 to disable"); +torture_param(int, nocbs_toggle, 1000, "Time between toggling nocb state (ms)"); torture_param(int, read_exit_delay, 13, "Delay between read-then-exit episodes (s)"); torture_param(int, read_exit_burst, 16, @@ -128,10 +130,12 @@ static char *torture_type = "rcu"; module_param(torture_type, charp, 0444); MODULE_PARM_DESC(torture_type, "Type of RCU to torture (rcu, srcu, ...)"); +static int nrealnocbers; static int nrealreaders; static struct task_struct *writer_task; static struct task_struct **fakewriter_tasks; static struct task_struct **reader_tasks; +static struct task_struct **nocb_tasks; static struct task_struct *stats_task; static struct task_struct *fqs_task; static struct task_struct *boost_tasks[NR_CPUS]; @@ -189,6 +193,8 @@ static unsigned long n_read_exits; static struct list_head rcu_torture_removed; static unsigned long shutdown_jiffies; static unsigned long start_gp_seq; +static atomic_long_t n_nocb_offload; +static atomic_long_t n_nocb_deoffload; static int rcu_torture_writer_state; #define RTWS_FIXED_DELAY 0 @@ -1672,6 +1678,53 @@ rcu_torture_reader(void *arg) } /* + * Randomly Toggle CPUs' callback-offload state. This uses hrtimers to + * increase race probabilities and fuzzes the interval between toggling. + */ +static int rcu_nocb_toggle(void *arg) +{ + int cpu; + int maxcpu = -1; + int oldnice = task_nice(current); + long r; + DEFINE_TORTURE_RANDOM(rand); + ktime_t toggle_delay; + unsigned long toggle_fuzz; + ktime_t toggle_interval = ms_to_ktime(nocbs_toggle); + + VERBOSE_TOROUT_STRING("rcu_nocb_toggle task started"); + while (!rcu_inkernel_boot_has_ended()) + schedule_timeout_interruptible(HZ / 10); + for_each_online_cpu(cpu) + maxcpu = cpu; + WARN_ON(maxcpu < 0); + if (toggle_interval > ULONG_MAX) + toggle_fuzz = ULONG_MAX >> 3; + else + toggle_fuzz = toggle_interval >> 3; + if (toggle_fuzz <= 0) + toggle_fuzz = NSEC_PER_USEC; + do { + r = torture_random(&rand); + cpu = (r >> 4) % (maxcpu + 1); + if (r & 0x1) { + rcu_nocb_cpu_offload(cpu); + atomic_long_inc(&n_nocb_offload); + } else { + rcu_nocb_cpu_deoffload(cpu); + atomic_long_inc(&n_nocb_deoffload); + } + toggle_delay = torture_random(&rand) % toggle_fuzz + toggle_interval; + set_current_state(TASK_INTERRUPTIBLE); + schedule_hrtimeout(&toggle_delay, HRTIMER_MODE_REL); + if (stutter_wait("rcu_nocb_toggle")) + sched_set_normal(current, oldnice); + } while (!torture_must_stop()); + torture_kthread_stopping("rcu_nocb_toggle"); + return 0; +} + +/* * Print torture statistics. Caller must ensure that there is only * one call to this function at a given time!!! This is normally * accomplished by relying on the module system to only have one copy @@ -1727,7 +1780,9 @@ rcu_torture_stats_print(void) data_race(n_barrier_successes), data_race(n_barrier_attempts), data_race(n_rcu_torture_barrier_error)); - pr_cont("read-exits: %ld\n", data_race(n_read_exits)); + pr_cont("read-exits: %ld ", data_race(n_read_exits)); // Statistic. + pr_cont("nocb-toggles: %ld:%ld\n", + atomic_long_read(&n_nocb_offload), atomic_long_read(&n_nocb_deoffload)); pr_alert("%s%s ", torture_type, TORTURE_FLAG); if (atomic_read(&n_rcu_torture_mberror) || @@ -1823,7 +1878,8 @@ rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag) "stall_cpu_block=%d " "n_barrier_cbs=%d " "onoff_interval=%d onoff_holdoff=%d " - "read_exit_delay=%d read_exit_burst=%d\n", + "read_exit_delay=%d read_exit_burst=%d " + "nocbs_nthreads=%d nocbs_toggle=%d\n", torture_type, tag, nrealreaders, nfakewriters, stat_interval, verbose, test_no_idle_hz, shuffle_interval, stutter, irqreader, fqs_duration, fqs_holdoff, fqs_stutter, @@ -1833,7 +1889,8 @@ rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag) stall_cpu_block, n_barrier_cbs, onoff_interval, onoff_holdoff, - read_exit_delay, read_exit_burst); + read_exit_delay, read_exit_burst, + nocbs_nthreads, nocbs_toggle); } static int rcutorture_booster_cleanup(unsigned int cpu) @@ -2676,6 +2733,13 @@ rcu_torture_cleanup(void) torture_stop_kthread(rcu_torture_stall, stall_task); torture_stop_kthread(rcu_torture_writer, writer_task); + if (nocb_tasks) { + for (i = 0; i < nrealnocbers; i++) + torture_stop_kthread(rcu_nocb_toggle, nocb_tasks[i]); + kfree(nocb_tasks); + nocb_tasks = NULL; + } + if (reader_tasks) { for (i = 0; i < nrealreaders; i++) torture_stop_kthread(rcu_torture_reader, @@ -2951,6 +3015,26 @@ rcu_torture_init(void) if (firsterr) goto unwind; } + nrealnocbers = nocbs_nthreads; + if (WARN_ON(nrealnocbers < 0)) + nrealnocbers = 1; + if (WARN_ON(nocbs_toggle < 0)) + nocbs_toggle = HZ; + if (nrealnocbers > 0) { + nocb_tasks = kcalloc(nrealnocbers, sizeof(nocb_tasks[0]), GFP_KERNEL); + if (nocb_tasks == NULL) { + VERBOSE_TOROUT_ERRSTRING("out of memory"); + firsterr = -ENOMEM; + goto unwind; + } + } else { + nocb_tasks = NULL; + } + for (i = 0; i < nrealnocbers; i++) { + firsterr = torture_create_kthread(rcu_nocb_toggle, NULL, nocb_tasks[i]); + if (firsterr) + goto unwind; + } if (stat_interval > 0) { firsterr = torture_create_kthread(rcu_torture_stats, NULL, stats_task); diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c index 119938d381e2..e26547b34ad3 100644 --- a/kernel/rcu/srcutree.c +++ b/kernel/rcu/srcutree.c @@ -1242,6 +1242,7 @@ static void srcu_advance_state(struct srcu_struct *ssp) */ static void srcu_invoke_callbacks(struct work_struct *work) { + long len; bool more; struct rcu_cblist ready_cbs; struct rcu_head *rhp; @@ -1264,6 +1265,7 @@ static void srcu_invoke_callbacks(struct work_struct *work) /* We are on the job! Extract and invoke ready callbacks. */ sdp->srcu_cblist_invoking = true; rcu_segcblist_extract_done_cbs(&sdp->srcu_cblist, &ready_cbs); + len = ready_cbs.len; spin_unlock_irq_rcu_node(sdp); rhp = rcu_cblist_dequeue(&ready_cbs); for (; rhp != NULL; rhp = rcu_cblist_dequeue(&ready_cbs)) { @@ -1272,13 +1274,14 @@ static void srcu_invoke_callbacks(struct work_struct *work) rhp->func(rhp); local_bh_enable(); } + WARN_ON_ONCE(ready_cbs.len); /* * Update counts, accelerate new callbacks, and if needed, * schedule another round of callback invocation. */ spin_lock_irq_rcu_node(sdp); - rcu_segcblist_insert_count(&sdp->srcu_cblist, &ready_cbs); + rcu_segcblist_add_len(&sdp->srcu_cblist, -len); (void)rcu_segcblist_accelerate(&sdp->srcu_cblist, rcu_seq_snap(&ssp->srcu_gp_seq)); sdp->srcu_cblist_invoking = false; diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index 35bdcfd84d42..af7c19439f4e 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -241,7 +241,7 @@ static int __noreturn rcu_tasks_kthread(void *arg) } } -/* Spawn RCU-tasks grace-period kthread, e.g., at core_initcall() time. */ +/* Spawn RCU-tasks grace-period kthread. */ static void __init rcu_spawn_tasks_kthread_generic(struct rcu_tasks *rtp) { struct task_struct *t; @@ -564,7 +564,6 @@ static int __init rcu_spawn_tasks_kthread(void) rcu_spawn_tasks_kthread_generic(&rcu_tasks); return 0; } -core_initcall(rcu_spawn_tasks_kthread); #if !defined(CONFIG_TINY_RCU) void show_rcu_tasks_classic_gp_kthread(void) @@ -692,7 +691,6 @@ static int __init rcu_spawn_tasks_rude_kthread(void) rcu_spawn_tasks_kthread_generic(&rcu_tasks_rude); return 0; } -core_initcall(rcu_spawn_tasks_rude_kthread); #if !defined(CONFIG_TINY_RCU) void show_rcu_tasks_rude_gp_kthread(void) @@ -968,6 +966,11 @@ static void rcu_tasks_trace_pregp_step(void) static void rcu_tasks_trace_pertask(struct task_struct *t, struct list_head *hop) { + // During early boot when there is only the one boot CPU, there + // is no idle task for the other CPUs. Just return. + if (unlikely(t == NULL)) + return; + WRITE_ONCE(t->trc_reader_special.b.need_qs, false); WRITE_ONCE(t->trc_reader_checked, false); t->trc_ipi_to_cpu = -1; @@ -1193,7 +1196,6 @@ static int __init rcu_spawn_tasks_trace_kthread(void) rcu_spawn_tasks_kthread_generic(&rcu_tasks_trace); return 0; } -core_initcall(rcu_spawn_tasks_trace_kthread); #if !defined(CONFIG_TINY_RCU) void show_rcu_tasks_trace_gp_kthread(void) @@ -1222,6 +1224,100 @@ void show_rcu_tasks_gp_kthreads(void) } #endif /* #ifndef CONFIG_TINY_RCU */ +#ifdef CONFIG_PROVE_RCU +struct rcu_tasks_test_desc { + struct rcu_head rh; + const char *name; + bool notrun; +}; + +static struct rcu_tasks_test_desc tests[] = { + { + .name = "call_rcu_tasks()", + /* If not defined, the test is skipped. */ + .notrun = !IS_ENABLED(CONFIG_TASKS_RCU), + }, + { + .name = "call_rcu_tasks_rude()", + /* If not defined, the test is skipped. */ + .notrun = !IS_ENABLED(CONFIG_TASKS_RUDE_RCU), + }, + { + .name = "call_rcu_tasks_trace()", + /* If not defined, the test is skipped. */ + .notrun = !IS_ENABLED(CONFIG_TASKS_TRACE_RCU) + } +}; + +static void test_rcu_tasks_callback(struct rcu_head *rhp) +{ + struct rcu_tasks_test_desc *rttd = + container_of(rhp, struct rcu_tasks_test_desc, rh); + + pr_info("Callback from %s invoked.\n", rttd->name); + + rttd->notrun = true; +} + +static void rcu_tasks_initiate_self_tests(void) +{ + pr_info("Running RCU-tasks wait API self tests\n"); +#ifdef CONFIG_TASKS_RCU + synchronize_rcu_tasks(); + call_rcu_tasks(&tests[0].rh, test_rcu_tasks_callback); +#endif + +#ifdef CONFIG_TASKS_RUDE_RCU + synchronize_rcu_tasks_rude(); + call_rcu_tasks_rude(&tests[1].rh, test_rcu_tasks_callback); +#endif + +#ifdef CONFIG_TASKS_TRACE_RCU + synchronize_rcu_tasks_trace(); + call_rcu_tasks_trace(&tests[2].rh, test_rcu_tasks_callback); +#endif +} + +static int rcu_tasks_verify_self_tests(void) +{ + int ret = 0; + int i; + + for (i = 0; i < ARRAY_SIZE(tests); i++) { + if (!tests[i].notrun) { // still hanging. + pr_err("%s has been failed.\n", tests[i].name); + ret = -1; + } + } + + if (ret) + WARN_ON(1); + + return ret; +} +late_initcall(rcu_tasks_verify_self_tests); +#else /* #ifdef CONFIG_PROVE_RCU */ +static void rcu_tasks_initiate_self_tests(void) { } +#endif /* #else #ifdef CONFIG_PROVE_RCU */ + +void __init rcu_init_tasks_generic(void) +{ +#ifdef CONFIG_TASKS_RCU + rcu_spawn_tasks_kthread(); +#endif + +#ifdef CONFIG_TASKS_RUDE_RCU + rcu_spawn_tasks_rude_kthread(); +#endif + +#ifdef CONFIG_TASKS_TRACE_RCU + rcu_spawn_tasks_trace_kthread(); +#endif + + // Run the self-tests. + rcu_tasks_initiate_self_tests(); +} + #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */ static inline void rcu_tasks_bootup_oddness(void) {} void show_rcu_tasks_gp_kthreads(void) {} diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 40e5e3dd253e..0f4a6a3c057b 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -83,6 +83,9 @@ static DEFINE_PER_CPU_SHARED_ALIGNED(struct rcu_data, rcu_data) = { .dynticks_nesting = 1, .dynticks_nmi_nesting = DYNTICK_IRQ_NONIDLE, .dynticks = ATOMIC_INIT(RCU_DYNTICK_CTRL_CTR), +#ifdef CONFIG_RCU_NOCB_CPU + .cblist.flags = SEGCBLIST_SOFTIRQ_ONLY, +#endif }; static struct rcu_state rcu_state = { .level = { &rcu_state.node[0] }, @@ -100,8 +103,10 @@ static struct rcu_state rcu_state = { static bool dump_tree; module_param(dump_tree, bool, 0444); /* By default, use RCU_SOFTIRQ instead of rcuc kthreads. */ -static bool use_softirq = true; +static bool use_softirq = !IS_ENABLED(CONFIG_PREEMPT_RT); +#ifndef CONFIG_PREEMPT_RT module_param(use_softirq, bool, 0444); +#endif /* Control rcu_node-tree auto-balancing at boot time. */ static bool rcu_fanout_exact; module_param(rcu_fanout_exact, bool, 0444); @@ -1495,6 +1500,8 @@ static bool rcu_accelerate_cbs(struct rcu_node *rnp, struct rcu_data *rdp) if (!rcu_segcblist_pend_cbs(&rdp->cblist)) return false; + trace_rcu_segcb_stats(&rdp->cblist, TPS("SegCbPreAcc")); + /* * Callbacks are often registered with incomplete grace-period * information. Something about the fact that getting exact @@ -1515,6 +1522,8 @@ static bool rcu_accelerate_cbs(struct rcu_node *rnp, struct rcu_data *rdp) else trace_rcu_grace_period(rcu_state.name, gp_seq_req, TPS("AccReadyCB")); + trace_rcu_segcb_stats(&rdp->cblist, TPS("SegCbPostAcc")); + return ret; } @@ -1765,7 +1774,7 @@ static bool rcu_gp_init(void) * go offline later. Please also refer to "Hotplug CPU" section * of RCU's Requirements documentation. */ - rcu_state.gp_state = RCU_GP_ONOFF; + WRITE_ONCE(rcu_state.gp_state, RCU_GP_ONOFF); rcu_for_each_leaf_node(rnp) { smp_mb(); // Pair with barriers used when updating ->ofl_seq to odd values. firstseq = READ_ONCE(rnp->ofl_seq); @@ -1831,7 +1840,7 @@ static bool rcu_gp_init(void) * The grace period cannot complete until the initialization * process finishes, because this kthread handles both. */ - rcu_state.gp_state = RCU_GP_INIT; + WRITE_ONCE(rcu_state.gp_state, RCU_GP_INIT); rcu_for_each_node_breadth_first(rnp) { rcu_gp_slow(gp_init_delay); raw_spin_lock_irqsave_rcu_node(rnp, flags); @@ -1930,17 +1939,22 @@ static void rcu_gp_fqs_loop(void) ret = 0; for (;;) { if (!ret) { - rcu_state.jiffies_force_qs = jiffies + j; + WRITE_ONCE(rcu_state.jiffies_force_qs, jiffies + j); + /* + * jiffies_force_qs before RCU_GP_WAIT_FQS state + * update; required for stall checks. + */ + smp_wmb(); WRITE_ONCE(rcu_state.jiffies_kick_kthreads, jiffies + (j ? 3 * j : 2)); } trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("fqswait")); - rcu_state.gp_state = RCU_GP_WAIT_FQS; + WRITE_ONCE(rcu_state.gp_state, RCU_GP_WAIT_FQS); ret = swait_event_idle_timeout_exclusive( rcu_state.gp_wq, rcu_gp_fqs_check_wake(&gf), j); rcu_gp_torture_wait(); - rcu_state.gp_state = RCU_GP_DOING_FQS; + WRITE_ONCE(rcu_state.gp_state, RCU_GP_DOING_FQS); /* Locking provides needed memory barriers. */ /* If grace period done, leave loop. */ if (!READ_ONCE(rnp->qsmask) && @@ -2054,7 +2068,7 @@ static void rcu_gp_cleanup(void) trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("end")); rcu_seq_end(&rcu_state.gp_seq); ASSERT_EXCLUSIVE_WRITER(rcu_state.gp_seq); - rcu_state.gp_state = RCU_GP_IDLE; + WRITE_ONCE(rcu_state.gp_state, RCU_GP_IDLE); /* Check for GP requests since above loop. */ rdp = this_cpu_ptr(&rcu_data); if (!needgp && ULONG_CMP_LT(rnp->gp_seq, rnp->gp_seq_needed)) { @@ -2093,12 +2107,12 @@ static int __noreturn rcu_gp_kthread(void *unused) for (;;) { trace_rcu_grace_period(rcu_state.name, rcu_state.gp_seq, TPS("reqwait")); - rcu_state.gp_state = RCU_GP_WAIT_GPS; + WRITE_ONCE(rcu_state.gp_state, RCU_GP_WAIT_GPS); swait_event_idle_exclusive(rcu_state.gp_wq, READ_ONCE(rcu_state.gp_flags) & RCU_GP_FLAG_INIT); rcu_gp_torture_wait(); - rcu_state.gp_state = RCU_GP_DONE_GPS; + WRITE_ONCE(rcu_state.gp_state, RCU_GP_DONE_GPS); /* Locking provides needed memory barrier. */ if (rcu_gp_init()) break; @@ -2113,9 +2127,9 @@ static int __noreturn rcu_gp_kthread(void *unused) rcu_gp_fqs_loop(); /* Handle grace-period end. */ - rcu_state.gp_state = RCU_GP_CLEANUP; + WRITE_ONCE(rcu_state.gp_state, RCU_GP_CLEANUP); rcu_gp_cleanup(); - rcu_state.gp_state = RCU_GP_CLEANED; + WRITE_ONCE(rcu_state.gp_state, RCU_GP_CLEANED); } } @@ -2430,11 +2444,12 @@ int rcutree_dead_cpu(unsigned int cpu) static void rcu_do_batch(struct rcu_data *rdp) { int div; + bool __maybe_unused empty; unsigned long flags; const bool offloaded = rcu_segcblist_is_offloaded(&rdp->cblist); struct rcu_head *rhp; struct rcu_cblist rcl = RCU_CBLIST_INITIALIZER(rcl); - long bl, count; + long bl, count = 0; long pending, tlimit = 0; /* If no callbacks are ready, just return. */ @@ -2471,14 +2486,18 @@ static void rcu_do_batch(struct rcu_data *rdp) rcu_segcblist_extract_done_cbs(&rdp->cblist, &rcl); if (offloaded) rdp->qlen_last_fqs_check = rcu_segcblist_n_cbs(&rdp->cblist); + + trace_rcu_segcb_stats(&rdp->cblist, TPS("SegCbDequeued")); rcu_nocb_unlock_irqrestore(rdp, flags); /* Invoke callbacks. */ tick_dep_set_task(current, TICK_DEP_BIT_RCU); rhp = rcu_cblist_dequeue(&rcl); + for (; rhp; rhp = rcu_cblist_dequeue(&rcl)) { rcu_callback_t f; + count++; debug_rcu_head_unqueue(rhp); rcu_lock_acquire(&rcu_callback_map); @@ -2492,21 +2511,19 @@ static void rcu_do_batch(struct rcu_data *rdp) /* * Stop only if limit reached and CPU has something to do. - * Note: The rcl structure counts down from zero. */ - if (-rcl.len >= bl && !offloaded && + if (count >= bl && !offloaded && (need_resched() || (!is_idle_task(current) && !rcu_is_callbacks_kthread()))) break; if (unlikely(tlimit)) { /* only call local_clock() every 32 callbacks */ - if (likely((-rcl.len & 31) || local_clock() < tlimit)) + if (likely((count & 31) || local_clock() < tlimit)) continue; /* Exceeded the time limit, so leave. */ break; } - if (offloaded) { - WARN_ON_ONCE(in_serving_softirq()); + if (!in_serving_softirq()) { local_bh_enable(); lockdep_assert_irqs_enabled(); cond_resched_tasks_rcu_qs(); @@ -2517,15 +2534,13 @@ static void rcu_do_batch(struct rcu_data *rdp) local_irq_save(flags); rcu_nocb_lock(rdp); - count = -rcl.len; rdp->n_cbs_invoked += count; trace_rcu_batch_end(rcu_state.name, count, !!rcl.head, need_resched(), is_idle_task(current), rcu_is_callbacks_kthread()); /* Update counts and requeue any remaining callbacks. */ rcu_segcblist_insert_done_cbs(&rdp->cblist, &rcl); - smp_mb(); /* List handling before counting for rcu_barrier(). */ - rcu_segcblist_insert_count(&rdp->cblist, &rcl); + rcu_segcblist_add_len(&rdp->cblist, -count); /* Reinstate batch limit if we have worked down the excess. */ count = rcu_segcblist_n_cbs(&rdp->cblist); @@ -2543,9 +2558,12 @@ static void rcu_do_batch(struct rcu_data *rdp) * The following usually indicates a double call_rcu(). To track * this down, try building with CONFIG_DEBUG_OBJECTS_RCU_HEAD=y. */ - WARN_ON_ONCE(count == 0 && !rcu_segcblist_empty(&rdp->cblist)); + empty = rcu_segcblist_empty(&rdp->cblist); + WARN_ON_ONCE(count == 0 && !empty); WARN_ON_ONCE(!IS_ENABLED(CONFIG_RCU_NOCB_CPU) && - count != 0 && rcu_segcblist_empty(&rdp->cblist)); + count != 0 && empty); + WARN_ON_ONCE(count == 0 && rcu_segcblist_n_segment_cbs(&rdp->cblist) != 0); + WARN_ON_ONCE(!empty && rcu_segcblist_n_segment_cbs(&rdp->cblist) == 0); rcu_nocb_unlock_irqrestore(rdp, flags); @@ -2566,6 +2584,7 @@ static void rcu_do_batch(struct rcu_data *rdp) void rcu_sched_clock_irq(int user) { trace_rcu_utilization(TPS("Start scheduler-tick")); + lockdep_assert_irqs_disabled(); raw_cpu_inc(rcu_data.ticks_this_gp); /* The load-acquire pairs with the store-release setting to true. */ if (smp_load_acquire(this_cpu_ptr(&rcu_data.rcu_urgent_qs))) { @@ -2579,6 +2598,7 @@ void rcu_sched_clock_irq(int user) rcu_flavor_sched_clock_irq(user); if (rcu_pending(user)) invoke_rcu_core(); + lockdep_assert_irqs_disabled(); trace_rcu_utilization(TPS("End scheduler-tick")); } @@ -2688,7 +2708,7 @@ static __latent_entropy void rcu_core(void) unsigned long flags; struct rcu_data *rdp = raw_cpu_ptr(&rcu_data); struct rcu_node *rnp = rdp->mynode; - const bool offloaded = rcu_segcblist_is_offloaded(&rdp->cblist); + const bool do_batch = !rcu_segcblist_completely_offloaded(&rdp->cblist); if (cpu_is_offline(smp_processor_id())) return; @@ -2708,17 +2728,17 @@ static __latent_entropy void rcu_core(void) /* No grace period and unregistered callbacks? */ if (!rcu_gp_in_progress() && - rcu_segcblist_is_enabled(&rdp->cblist) && !offloaded) { - local_irq_save(flags); + rcu_segcblist_is_enabled(&rdp->cblist) && do_batch) { + rcu_nocb_lock_irqsave(rdp, flags); if (!rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL)) rcu_accelerate_cbs_unlocked(rnp, rdp); - local_irq_restore(flags); + rcu_nocb_unlock_irqrestore(rdp, flags); } rcu_check_gp_start_stall(rnp, rdp, rcu_jiffies_till_stall_check()); /* If there are callbacks ready, invoke them. */ - if (!offloaded && rcu_segcblist_ready_cbs(&rdp->cblist) && + if (do_batch && rcu_segcblist_ready_cbs(&rdp->cblist) && likely(READ_ONCE(rcu_scheduler_fully_active))) rcu_do_batch(rdp); @@ -2941,6 +2961,7 @@ static void check_cb_ovld(struct rcu_data *rdp) static void __call_rcu(struct rcu_head *head, rcu_callback_t func) { + static atomic_t doublefrees; unsigned long flags; struct rcu_data *rdp; bool was_alldone; @@ -2954,8 +2975,10 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func) * Use rcu:rcu_callback trace event to find the previous * time callback was passed to __call_rcu(). */ - WARN_ONCE(1, "__call_rcu(): Double-freed CB %p->%pS()!!!\n", - head, head->func); + if (atomic_inc_return(&doublefrees) < 4) { + pr_err("%s(): Double-freed CB %p->%pS()!!! ", __func__, head, head->func); + mem_dump_obj(head); + } WRITE_ONCE(head->func, rcu_leak_callback); return; } @@ -2989,6 +3012,8 @@ __call_rcu(struct rcu_head *head, rcu_callback_t func) trace_rcu_callback(rcu_state.name, head, rcu_segcblist_n_cbs(&rdp->cblist)); + trace_rcu_segcb_stats(&rdp->cblist, TPS("SegCBQueued")); + /* Go handle any RCU core processing required. */ if (unlikely(rcu_segcblist_is_offloaded(&rdp->cblist))) { __call_rcu_nocb_wake(rdp, was_alldone, flags); /* unlocks */ @@ -3498,6 +3523,7 @@ void kvfree_call_rcu(struct rcu_head *head, rcu_callback_t func) goto unlock_return; } + kasan_record_aux_stack(ptr); success = kvfree_call_rcu_add_ptr_to_bulk(krcp, ptr); if (!success) { run_page_cache_worker(krcp); @@ -3747,6 +3773,8 @@ static int rcu_pending(int user) struct rcu_data *rdp = this_cpu_ptr(&rcu_data); struct rcu_node *rnp = rdp->mynode; + lockdep_assert_irqs_disabled(); + /* Check for CPU stalls, if enabled. */ check_cpu_stall(rdp); @@ -4001,12 +4029,18 @@ int rcutree_prepare_cpu(unsigned int cpu) rdp->qlen_last_fqs_check = 0; rdp->n_force_qs_snap = rcu_state.n_force_qs; rdp->blimit = blimit; - if (rcu_segcblist_empty(&rdp->cblist) && /* No early-boot CBs? */ - !rcu_segcblist_is_offloaded(&rdp->cblist)) - rcu_segcblist_init(&rdp->cblist); /* Re-enable callbacks. */ rdp->dynticks_nesting = 1; /* CPU not up, no tearing. */ rcu_dynticks_eqs_online(); raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */ + /* + * Lock in case the CB/GP kthreads are still around handling + * old callbacks (longer term we should flush all callbacks + * before completing CPU offline) + */ + rcu_nocb_lock(rdp); + if (rcu_segcblist_empty(&rdp->cblist)) /* No early-boot CBs? */ + rcu_segcblist_init(&rdp->cblist); /* Re-enable callbacks. */ + rcu_nocb_unlock(rdp); /* * Add CPU to leaf rcu_node pending-online bitmask. Any needed @@ -4159,6 +4193,9 @@ void rcu_report_dead(unsigned int cpu) struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); struct rcu_node *rnp = rdp->mynode; /* Outgoing CPU's rdp & rnp. */ + // Do any dangling deferred wakeups. + do_nocb_deferred_wakeup(rdp); + /* QS for any half-done expedited grace period. */ preempt_disable(); rcu_report_exp_rdp(this_cpu_ptr(&rcu_data)); diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index 7708ed161f4a..5d359b9f9fec 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -201,6 +201,7 @@ struct rcu_data { /* 5) Callback offloading. */ #ifdef CONFIG_RCU_NOCB_CPU struct swait_queue_head nocb_cb_wq; /* For nocb kthreads to sleep on. */ + struct swait_queue_head nocb_state_wq; /* For offloading state changes */ struct task_struct *nocb_gp_kthread; raw_spinlock_t nocb_lock; /* Guard following pair of fields. */ atomic_t nocb_lock_contended; /* Contention experienced. */ @@ -256,6 +257,7 @@ struct rcu_data { }; /* Values for nocb_defer_wakeup field in struct rcu_data. */ +#define RCU_NOCB_WAKE_OFF -1 #define RCU_NOCB_WAKE_NOT 0 #define RCU_NOCB_WAKE 1 #define RCU_NOCB_WAKE_FORCE 2 diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index 8760b6ead770..6c6ff06d4ae6 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -545,7 +545,7 @@ static void synchronize_rcu_expedited_wait(void) data_race(rnp_root->expmask), ".T"[!!data_race(rnp_root->exp_tasks)]); if (ndetected) { - pr_err("blocking rcu_node structures:"); + pr_err("blocking rcu_node structures (internal RCU debug):"); rcu_for_each_node_breadth_first(rnp) { if (rnp == rnp_root) continue; /* printed unconditionally */ diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 7e291ce0a1d6..231a0c6cf03c 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -682,6 +682,7 @@ static void rcu_flavor_sched_clock_irq(int user) { struct task_struct *t = current; + lockdep_assert_irqs_disabled(); if (user || rcu_is_cpu_rrupt_from_idle()) { rcu_note_voluntary_context_switch(current); } @@ -1665,6 +1666,8 @@ static void wake_nocb_gp(struct rcu_data *rdp, bool force, static void wake_nocb_gp_defer(struct rcu_data *rdp, int waketype, const char *reason) { + if (rdp->nocb_defer_wakeup == RCU_NOCB_WAKE_OFF) + return; if (rdp->nocb_defer_wakeup == RCU_NOCB_WAKE_NOT) mod_timer(&rdp->nocb_timer, jiffies + 1); if (rdp->nocb_defer_wakeup < waketype) @@ -1929,6 +1932,52 @@ static void do_nocb_bypass_wakeup_timer(struct timer_list *t) } /* + * Check if we ignore this rdp. + * + * We check that without holding the nocb lock but + * we make sure not to miss a freshly offloaded rdp + * with the current ordering: + * + * rdp_offload_toggle() nocb_gp_enabled_cb() + * ------------------------- ---------------------------- + * WRITE flags LOCK nocb_gp_lock + * LOCK nocb_gp_lock READ/WRITE nocb_gp_sleep + * READ/WRITE nocb_gp_sleep UNLOCK nocb_gp_lock + * UNLOCK nocb_gp_lock READ flags + */ +static inline bool nocb_gp_enabled_cb(struct rcu_data *rdp) +{ + u8 flags = SEGCBLIST_OFFLOADED | SEGCBLIST_KTHREAD_GP; + + return rcu_segcblist_test_flags(&rdp->cblist, flags); +} + +static inline bool nocb_gp_update_state(struct rcu_data *rdp, bool *needwake_state) +{ + struct rcu_segcblist *cblist = &rdp->cblist; + + if (rcu_segcblist_test_flags(cblist, SEGCBLIST_OFFLOADED)) { + if (!rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_GP)) { + rcu_segcblist_set_flags(cblist, SEGCBLIST_KTHREAD_GP); + if (rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_CB)) + *needwake_state = true; + } + return true; + } + + /* + * De-offloading. Clear our flag and notify the de-offload worker. + * We will ignore this rdp until it ever gets re-offloaded. + */ + WARN_ON_ONCE(!rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_GP)); + rcu_segcblist_clear_flags(cblist, SEGCBLIST_KTHREAD_GP); + if (!rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_CB)) + *needwake_state = true; + return false; +} + + +/* * No-CBs GP kthreads come here to wait for additional callbacks to show up * or for grace periods to end. */ @@ -1956,8 +2005,18 @@ static void nocb_gp_wait(struct rcu_data *my_rdp) */ WARN_ON_ONCE(my_rdp->nocb_gp_rdp != my_rdp); for (rdp = my_rdp; rdp; rdp = rdp->nocb_next_cb_rdp) { + bool needwake_state = false; + + if (!nocb_gp_enabled_cb(rdp)) + continue; trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("Check")); rcu_nocb_lock_irqsave(rdp, flags); + if (!nocb_gp_update_state(rdp, &needwake_state)) { + rcu_nocb_unlock_irqrestore(rdp, flags); + if (needwake_state) + swake_up_one(&rdp->nocb_state_wq); + continue; + } bypass_ncbs = rcu_cblist_n_cbs(&rdp->nocb_bypass); if (bypass_ncbs && (time_after(j, READ_ONCE(rdp->nocb_bypass_first) + 1) || @@ -1967,6 +2026,8 @@ static void nocb_gp_wait(struct rcu_data *my_rdp) bypass_ncbs = rcu_cblist_n_cbs(&rdp->nocb_bypass); } else if (!bypass_ncbs && rcu_segcblist_empty(&rdp->cblist)) { rcu_nocb_unlock_irqrestore(rdp, flags); + if (needwake_state) + swake_up_one(&rdp->nocb_state_wq); continue; /* No callbacks here, try next. */ } if (bypass_ncbs) { @@ -2018,6 +2079,8 @@ static void nocb_gp_wait(struct rcu_data *my_rdp) } if (needwake_gp) rcu_gp_kthread_wake(); + if (needwake_state) + swake_up_one(&rdp->nocb_state_wq); } my_rdp->nocb_gp_bypass = bypass; @@ -2081,14 +2144,27 @@ static int rcu_nocb_gp_kthread(void *arg) return 0; } +static inline bool nocb_cb_can_run(struct rcu_data *rdp) +{ + u8 flags = SEGCBLIST_OFFLOADED | SEGCBLIST_KTHREAD_CB; + return rcu_segcblist_test_flags(&rdp->cblist, flags); +} + +static inline bool nocb_cb_wait_cond(struct rcu_data *rdp) +{ + return nocb_cb_can_run(rdp) && !READ_ONCE(rdp->nocb_cb_sleep); +} + /* * Invoke any ready callbacks from the corresponding no-CBs CPU, * then, if there are no more, wait for more to appear. */ static void nocb_cb_wait(struct rcu_data *rdp) { + struct rcu_segcblist *cblist = &rdp->cblist; unsigned long cur_gp_seq; unsigned long flags; + bool needwake_state = false; bool needwake_gp = false; struct rcu_node *rnp = rdp->mynode; @@ -2100,32 +2176,55 @@ static void nocb_cb_wait(struct rcu_data *rdp) local_bh_enable(); lockdep_assert_irqs_enabled(); rcu_nocb_lock_irqsave(rdp, flags); - if (rcu_segcblist_nextgp(&rdp->cblist, &cur_gp_seq) && + if (rcu_segcblist_nextgp(cblist, &cur_gp_seq) && rcu_seq_done(&rnp->gp_seq, cur_gp_seq) && raw_spin_trylock_rcu_node(rnp)) { /* irqs already disabled. */ needwake_gp = rcu_advance_cbs(rdp->mynode, rdp); raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */ } - if (rcu_segcblist_ready_cbs(&rdp->cblist)) { - rcu_nocb_unlock_irqrestore(rdp, flags); - if (needwake_gp) - rcu_gp_kthread_wake(); - return; - } - trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("CBSleep")); WRITE_ONCE(rdp->nocb_cb_sleep, true); + + if (rcu_segcblist_test_flags(cblist, SEGCBLIST_OFFLOADED)) { + if (!rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_CB)) { + rcu_segcblist_set_flags(cblist, SEGCBLIST_KTHREAD_CB); + if (rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_GP)) + needwake_state = true; + } + if (rcu_segcblist_ready_cbs(cblist)) + WRITE_ONCE(rdp->nocb_cb_sleep, false); + } else { + /* + * De-offloading. Clear our flag and notify the de-offload worker. + * We won't touch the callbacks and keep sleeping until we ever + * get re-offloaded. + */ + WARN_ON_ONCE(!rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_CB)); + rcu_segcblist_clear_flags(cblist, SEGCBLIST_KTHREAD_CB); + if (!rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_GP)) + needwake_state = true; + } + + if (rdp->nocb_cb_sleep) + trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("CBSleep")); + rcu_nocb_unlock_irqrestore(rdp, flags); if (needwake_gp) rcu_gp_kthread_wake(); - swait_event_interruptible_exclusive(rdp->nocb_cb_wq, - !READ_ONCE(rdp->nocb_cb_sleep)); - if (!smp_load_acquire(&rdp->nocb_cb_sleep)) { /* VVV */ - /* ^^^ Ensure CB invocation follows _sleep test. */ - return; - } - WARN_ON(signal_pending(current)); - trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WokeEmpty")); + + if (needwake_state) + swake_up_one(&rdp->nocb_state_wq); + + do { + swait_event_interruptible_exclusive(rdp->nocb_cb_wq, + nocb_cb_wait_cond(rdp)); + + // VVV Ensure CB invocation follows _sleep test. + if (smp_load_acquire(&rdp->nocb_cb_sleep)) { // ^^^ + WARN_ON(signal_pending(current)); + trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WokeEmpty")); + } + } while (!nocb_cb_can_run(rdp)); } /* @@ -2148,7 +2247,7 @@ static int rcu_nocb_cb_kthread(void *arg) /* Is a deferred wakeup of rcu_nocb_kthread() required? */ static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp) { - return READ_ONCE(rdp->nocb_defer_wakeup); + return READ_ONCE(rdp->nocb_defer_wakeup) > RCU_NOCB_WAKE_NOT; } /* Do a deferred wakeup of rcu_nocb_kthread(). */ @@ -2187,6 +2286,195 @@ static void do_nocb_deferred_wakeup(struct rcu_data *rdp) do_nocb_deferred_wakeup_common(rdp); } +static int rdp_offload_toggle(struct rcu_data *rdp, + bool offload, unsigned long flags) + __releases(rdp->nocb_lock) +{ + struct rcu_segcblist *cblist = &rdp->cblist; + struct rcu_data *rdp_gp = rdp->nocb_gp_rdp; + bool wake_gp = false; + + rcu_segcblist_offload(cblist, offload); + + if (rdp->nocb_cb_sleep) + rdp->nocb_cb_sleep = false; + rcu_nocb_unlock_irqrestore(rdp, flags); + + /* + * Ignore former value of nocb_cb_sleep and force wake up as it could + * have been spuriously set to false already. + */ + swake_up_one(&rdp->nocb_cb_wq); + + raw_spin_lock_irqsave(&rdp_gp->nocb_gp_lock, flags); + if (rdp_gp->nocb_gp_sleep) { + rdp_gp->nocb_gp_sleep = false; + wake_gp = true; + } + raw_spin_unlock_irqrestore(&rdp_gp->nocb_gp_lock, flags); + + if (wake_gp) + wake_up_process(rdp_gp->nocb_gp_kthread); + + return 0; +} + +static int __rcu_nocb_rdp_deoffload(struct rcu_data *rdp) +{ + struct rcu_segcblist *cblist = &rdp->cblist; + unsigned long flags; + int ret; + + pr_info("De-offloading %d\n", rdp->cpu); + + rcu_nocb_lock_irqsave(rdp, flags); + /* + * If there are still pending work offloaded, the offline + * CPU won't help much handling them. + */ + if (cpu_is_offline(rdp->cpu) && !rcu_segcblist_empty(&rdp->cblist)) { + rcu_nocb_unlock_irqrestore(rdp, flags); + return -EBUSY; + } + + ret = rdp_offload_toggle(rdp, false, flags); + swait_event_exclusive(rdp->nocb_state_wq, + !rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_CB | + SEGCBLIST_KTHREAD_GP)); + rcu_nocb_lock_irqsave(rdp, flags); + /* Make sure nocb timer won't stay around */ + WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOCB_WAKE_OFF); + rcu_nocb_unlock_irqrestore(rdp, flags); + del_timer_sync(&rdp->nocb_timer); + + /* + * Flush bypass. While IRQs are disabled and once we set + * SEGCBLIST_SOFTIRQ_ONLY, no callback is supposed to be + * enqueued on bypass. + */ + rcu_nocb_lock_irqsave(rdp, flags); + rcu_nocb_flush_bypass(rdp, NULL, jiffies); + rcu_segcblist_set_flags(cblist, SEGCBLIST_SOFTIRQ_ONLY); + /* + * With SEGCBLIST_SOFTIRQ_ONLY, we can't use + * rcu_nocb_unlock_irqrestore() anymore. Theoretically we + * could set SEGCBLIST_SOFTIRQ_ONLY with cb unlocked and IRQs + * disabled now, but let's be paranoid. + */ + raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags); + + return ret; +} + +static long rcu_nocb_rdp_deoffload(void *arg) +{ + struct rcu_data *rdp = arg; + + WARN_ON_ONCE(rdp->cpu != raw_smp_processor_id()); + return __rcu_nocb_rdp_deoffload(rdp); +} + +int rcu_nocb_cpu_deoffload(int cpu) +{ + struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); + int ret = 0; + + if (rdp == rdp->nocb_gp_rdp) { + pr_info("Can't deoffload an rdp GP leader (yet)\n"); + return -EINVAL; + } + mutex_lock(&rcu_state.barrier_mutex); + cpus_read_lock(); + if (rcu_segcblist_is_offloaded(&rdp->cblist)) { + if (cpu_online(cpu)) + ret = work_on_cpu(cpu, rcu_nocb_rdp_deoffload, rdp); + else + ret = __rcu_nocb_rdp_deoffload(rdp); + if (!ret) + cpumask_clear_cpu(cpu, rcu_nocb_mask); + } + cpus_read_unlock(); + mutex_unlock(&rcu_state.barrier_mutex); + + return ret; +} +EXPORT_SYMBOL_GPL(rcu_nocb_cpu_deoffload); + +static int __rcu_nocb_rdp_offload(struct rcu_data *rdp) +{ + struct rcu_segcblist *cblist = &rdp->cblist; + unsigned long flags; + int ret; + + /* + * For now we only support re-offload, ie: the rdp must have been + * offloaded on boot first. + */ + if (!rdp->nocb_gp_rdp) + return -EINVAL; + + pr_info("Offloading %d\n", rdp->cpu); + /* + * Can't use rcu_nocb_lock_irqsave() while we are in + * SEGCBLIST_SOFTIRQ_ONLY mode. + */ + raw_spin_lock_irqsave(&rdp->nocb_lock, flags); + /* Re-enable nocb timer */ + WRITE_ONCE(rdp->nocb_defer_wakeup, RCU_NOCB_WAKE_NOT); + /* + * We didn't take the nocb lock while working on the + * rdp->cblist in SEGCBLIST_SOFTIRQ_ONLY mode. + * Every modifications that have been done previously on + * rdp->cblist must be visible remotely by the nocb kthreads + * upon wake up after reading the cblist flags. + * + * The layout against nocb_lock enforces that ordering: + * + * __rcu_nocb_rdp_offload() nocb_cb_wait()/nocb_gp_wait() + * ------------------------- ---------------------------- + * WRITE callbacks rcu_nocb_lock() + * rcu_nocb_lock() READ flags + * WRITE flags READ callbacks + * rcu_nocb_unlock() rcu_nocb_unlock() + */ + ret = rdp_offload_toggle(rdp, true, flags); + swait_event_exclusive(rdp->nocb_state_wq, + rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_CB) && + rcu_segcblist_test_flags(cblist, SEGCBLIST_KTHREAD_GP)); + + return ret; +} + +static long rcu_nocb_rdp_offload(void *arg) +{ + struct rcu_data *rdp = arg; + + WARN_ON_ONCE(rdp->cpu != raw_smp_processor_id()); + return __rcu_nocb_rdp_offload(rdp); +} + +int rcu_nocb_cpu_offload(int cpu) +{ + struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); + int ret = 0; + + mutex_lock(&rcu_state.barrier_mutex); + cpus_read_lock(); + if (!rcu_segcblist_is_offloaded(&rdp->cblist)) { + if (cpu_online(cpu)) + ret = work_on_cpu(cpu, rcu_nocb_rdp_offload, rdp); + else + ret = __rcu_nocb_rdp_offload(rdp); + if (!ret) + cpumask_set_cpu(cpu, rcu_nocb_mask); + } + cpus_read_unlock(); + mutex_unlock(&rcu_state.barrier_mutex); + + return ret; +} +EXPORT_SYMBOL_GPL(rcu_nocb_cpu_offload); + void __init rcu_init_nohz(void) { int cpu; @@ -2229,7 +2517,9 @@ void __init rcu_init_nohz(void) rdp = per_cpu_ptr(&rcu_data, cpu); if (rcu_segcblist_empty(&rdp->cblist)) rcu_segcblist_init(&rdp->cblist); - rcu_segcblist_offload(&rdp->cblist); + rcu_segcblist_offload(&rdp->cblist, true); + rcu_segcblist_set_flags(&rdp->cblist, SEGCBLIST_KTHREAD_CB); + rcu_segcblist_set_flags(&rdp->cblist, SEGCBLIST_KTHREAD_GP); } rcu_organize_nocb_kthreads(); } @@ -2239,6 +2529,7 @@ static void __init rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp) { init_swait_queue_head(&rdp->nocb_cb_wq); init_swait_queue_head(&rdp->nocb_gp_wq); + init_swait_queue_head(&rdp->nocb_state_wq); raw_spin_lock_init(&rdp->nocb_lock); raw_spin_lock_init(&rdp->nocb_bypass_lock); raw_spin_lock_init(&rdp->nocb_gp_lock); @@ -2381,6 +2672,19 @@ void rcu_bind_current_to_nocb(void) } EXPORT_SYMBOL_GPL(rcu_bind_current_to_nocb); +// The ->on_cpu field is available only in CONFIG_SMP=y, so... +#ifdef CONFIG_SMP +static char *show_rcu_should_be_on_cpu(struct task_struct *tsp) +{ + return tsp && tsp->state == TASK_RUNNING && !tsp->on_cpu ? "!" : ""; +} +#else // #ifdef CONFIG_SMP +static char *show_rcu_should_be_on_cpu(struct task_struct *tsp) +{ + return ""; +} +#endif // #else #ifdef CONFIG_SMP + /* * Dump out nocb grace-period kthread state for the specified rcu_data * structure. @@ -2389,7 +2693,7 @@ static void show_rcu_nocb_gp_state(struct rcu_data *rdp) { struct rcu_node *rnp = rdp->mynode; - pr_info("nocb GP %d %c%c%c%c%c%c %c[%c%c] %c%c:%ld rnp %d:%d %lu\n", + pr_info("nocb GP %d %c%c%c%c%c%c %c[%c%c] %c%c:%ld rnp %d:%d %lu %c CPU %d%s\n", rdp->cpu, "kK"[!!rdp->nocb_gp_kthread], "lL"[raw_spin_is_locked(&rdp->nocb_gp_lock)], @@ -2403,12 +2707,17 @@ static void show_rcu_nocb_gp_state(struct rcu_data *rdp) ".B"[!!rdp->nocb_gp_bypass], ".G"[!!rdp->nocb_gp_gp], (long)rdp->nocb_gp_seq, - rnp->grplo, rnp->grphi, READ_ONCE(rdp->nocb_gp_loops)); + rnp->grplo, rnp->grphi, READ_ONCE(rdp->nocb_gp_loops), + rdp->nocb_gp_kthread ? task_state_to_char(rdp->nocb_gp_kthread) : '.', + rdp->nocb_cb_kthread ? (int)task_cpu(rdp->nocb_gp_kthread) : -1, + show_rcu_should_be_on_cpu(rdp->nocb_cb_kthread)); } /* Dump out nocb kthread state for the specified rcu_data structure. */ static void show_rcu_nocb_state(struct rcu_data *rdp) { + char bufw[20]; + char bufr[20]; struct rcu_segcblist *rsclp = &rdp->cblist; bool waslocked; bool wastimer; @@ -2417,8 +2726,11 @@ static void show_rcu_nocb_state(struct rcu_data *rdp) if (rdp->nocb_gp_rdp == rdp) show_rcu_nocb_gp_state(rdp); - pr_info(" CB %d->%d %c%c%c%c%c%c F%ld L%ld C%d %c%c%c%c%c q%ld\n", + sprintf(bufw, "%ld", rsclp->gp_seq[RCU_WAIT_TAIL]); + sprintf(bufr, "%ld", rsclp->gp_seq[RCU_NEXT_READY_TAIL]); + pr_info(" CB %d^%d->%d %c%c%c%c%c%c F%ld L%ld C%d %c%c%s%c%s%c%c q%ld %c CPU %d%s\n", rdp->cpu, rdp->nocb_gp_rdp->cpu, + rdp->nocb_next_cb_rdp ? rdp->nocb_next_cb_rdp->cpu : -1, "kK"[!!rdp->nocb_cb_kthread], "bB"[raw_spin_is_locked(&rdp->nocb_bypass_lock)], "cC"[!!atomic_read(&rdp->nocb_lock_contended)], @@ -2429,11 +2741,16 @@ static void show_rcu_nocb_state(struct rcu_data *rdp) jiffies - rdp->nocb_nobypass_last, rdp->nocb_nobypass_count, ".D"[rcu_segcblist_ready_cbs(rsclp)], - ".W"[!rcu_segcblist_restempty(rsclp, RCU_DONE_TAIL)], - ".R"[!rcu_segcblist_restempty(rsclp, RCU_WAIT_TAIL)], - ".N"[!rcu_segcblist_restempty(rsclp, RCU_NEXT_READY_TAIL)], + ".W"[!rcu_segcblist_segempty(rsclp, RCU_WAIT_TAIL)], + rcu_segcblist_segempty(rsclp, RCU_WAIT_TAIL) ? "" : bufw, + ".R"[!rcu_segcblist_segempty(rsclp, RCU_NEXT_READY_TAIL)], + rcu_segcblist_segempty(rsclp, RCU_NEXT_READY_TAIL) ? "" : bufr, + ".N"[!rcu_segcblist_segempty(rsclp, RCU_NEXT_TAIL)], ".B"[!!rcu_cblist_n_cbs(&rdp->nocb_bypass)], - rcu_segcblist_n_cbs(&rdp->cblist)); + rcu_segcblist_n_cbs(&rdp->cblist), + rdp->nocb_cb_kthread ? task_state_to_char(rdp->nocb_cb_kthread) : '.', + rdp->nocb_cb_kthread ? (int)task_cpu(rdp->nocb_gp_kthread) : -1, + show_rcu_should_be_on_cpu(rdp->nocb_cb_kthread)); /* It is OK for GP kthreads to have GP state. */ if (rdp->nocb_gp_rdp == rdp) diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h index 70d48c52fabc..475b26171b20 100644 --- a/kernel/rcu/tree_stall.h +++ b/kernel/rcu/tree_stall.h @@ -266,6 +266,7 @@ static int rcu_print_task_stall(struct rcu_node *rnp, unsigned long flags) struct task_struct *t; struct task_struct *ts[8]; + lockdep_assert_irqs_disabled(); if (!rcu_preempt_blocked_readers_cgp(rnp)) return 0; pr_err("\tTasks blocked on level-%d rcu_node (CPUs %d-%d):", @@ -290,6 +291,7 @@ static int rcu_print_task_stall(struct rcu_node *rnp, unsigned long flags) ".q"[rscr.rs.b.need_qs], ".e"[rscr.rs.b.exp_hint], ".l"[rscr.on_blkd_list]); + lockdep_assert_irqs_disabled(); put_task_struct(t); ndetected++; } @@ -333,9 +335,12 @@ static void rcu_dump_cpu_stacks(void) rcu_for_each_leaf_node(rnp) { raw_spin_lock_irqsave_rcu_node(rnp, flags); for_each_leaf_node_possible_cpu(rnp, cpu) - if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu)) - if (!trigger_single_cpu_backtrace(cpu)) + if (rnp->qsmask & leaf_node_cpu_bit(rnp, cpu)) { + if (cpu_is_offline(cpu)) + pr_err("Offline CPU %d blocking current GP.\n", cpu); + else if (!trigger_single_cpu_backtrace(cpu)) dump_cpu_task(cpu); + } raw_spin_unlock_irqrestore_rcu_node(rnp, flags); } } @@ -449,25 +454,66 @@ static void print_cpu_stall_info(int cpu) /* Complain about starvation of grace-period kthread. */ static void rcu_check_gp_kthread_starvation(void) { + int cpu; struct task_struct *gpk = rcu_state.gp_kthread; unsigned long j; if (rcu_is_gp_kthread_starving(&j)) { + cpu = gpk ? task_cpu(gpk) : -1; pr_err("%s kthread starved for %ld jiffies! g%ld f%#x %s(%d) ->state=%#lx ->cpu=%d\n", rcu_state.name, j, (long)rcu_seq_current(&rcu_state.gp_seq), data_race(rcu_state.gp_flags), gp_state_getname(rcu_state.gp_state), rcu_state.gp_state, - gpk ? gpk->state : ~0, gpk ? task_cpu(gpk) : -1); + gpk ? gpk->state : ~0, cpu); if (gpk) { pr_err("\tUnless %s kthread gets sufficient CPU time, OOM is now expected behavior.\n", rcu_state.name); pr_err("RCU grace-period kthread stack dump:\n"); sched_show_task(gpk); + if (cpu >= 0) { + if (cpu_is_offline(cpu)) { + pr_err("RCU GP kthread last ran on offline CPU %d.\n", cpu); + } else { + pr_err("Stack dump where RCU GP kthread last ran:\n"); + if (!trigger_single_cpu_backtrace(cpu)) + dump_cpu_task(cpu); + } + } wake_up_process(gpk); } } } +/* Complain about missing wakeups from expired fqs wait timer */ +static void rcu_check_gp_kthread_expired_fqs_timer(void) +{ + struct task_struct *gpk = rcu_state.gp_kthread; + short gp_state; + unsigned long jiffies_fqs; + int cpu; + + /* + * Order reads of .gp_state and .jiffies_force_qs. + * Matching smp_wmb() is present in rcu_gp_fqs_loop(). + */ + gp_state = smp_load_acquire(&rcu_state.gp_state); + jiffies_fqs = READ_ONCE(rcu_state.jiffies_force_qs); + + if (gp_state == RCU_GP_WAIT_FQS && + time_after(jiffies, jiffies_fqs + RCU_STALL_MIGHT_MIN) && + gpk && !READ_ONCE(gpk->on_rq)) { + cpu = task_cpu(gpk); + pr_err("%s kthread timer wakeup didn't happen for %ld jiffies! g%ld f%#x %s(%d) ->state=%#lx\n", + rcu_state.name, (jiffies - jiffies_fqs), + (long)rcu_seq_current(&rcu_state.gp_seq), + data_race(rcu_state.gp_flags), + gp_state_getname(RCU_GP_WAIT_FQS), RCU_GP_WAIT_FQS, + gpk->state); + pr_err("\tPossible timer handling issue on cpu=%d timer-softirq=%u\n", + cpu, kstat_softirqs_cpu(TIMER_SOFTIRQ, cpu)); + } +} + static void print_other_cpu_stall(unsigned long gp_seq, unsigned long gps) { int cpu; @@ -478,6 +524,8 @@ static void print_other_cpu_stall(unsigned long gp_seq, unsigned long gps) struct rcu_node *rnp; long totqlen = 0; + lockdep_assert_irqs_disabled(); + /* Kick and suppress, if so configured. */ rcu_stall_kick_kthreads(); if (rcu_stall_is_suppressed()) @@ -499,6 +547,7 @@ static void print_other_cpu_stall(unsigned long gp_seq, unsigned long gps) } } ndetected += rcu_print_task_stall(rnp, flags); // Releases rnp->lock. + lockdep_assert_irqs_disabled(); } for_each_possible_cpu(cpu) @@ -529,6 +578,7 @@ static void print_other_cpu_stall(unsigned long gp_seq, unsigned long gps) WRITE_ONCE(rcu_state.jiffies_stall, jiffies + 3 * rcu_jiffies_till_stall_check() + 3); + rcu_check_gp_kthread_expired_fqs_timer(); rcu_check_gp_kthread_starvation(); panic_on_rcu_stall(); @@ -544,6 +594,8 @@ static void print_cpu_stall(unsigned long gps) struct rcu_node *rnp = rcu_get_root(); long totqlen = 0; + lockdep_assert_irqs_disabled(); + /* Kick and suppress, if so configured. */ rcu_stall_kick_kthreads(); if (rcu_stall_is_suppressed()) @@ -564,6 +616,7 @@ static void print_cpu_stall(unsigned long gps) jiffies - gps, (long)rcu_seq_current(&rcu_state.gp_seq), totqlen); + rcu_check_gp_kthread_expired_fqs_timer(); rcu_check_gp_kthread_starvation(); rcu_dump_cpu_stacks(); @@ -598,6 +651,7 @@ static void check_cpu_stall(struct rcu_data *rdp) unsigned long js; struct rcu_node *rnp; + lockdep_assert_irqs_disabled(); if ((rcu_stall_is_suppressed() && !READ_ONCE(rcu_kick_kthreads)) || !rcu_gp_in_progress()) return; diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c index 39334d2d2b37..b95ae86c40a7 100644 --- a/kernel/rcu/update.c +++ b/kernel/rcu/update.c @@ -56,8 +56,10 @@ #ifndef CONFIG_TINY_RCU module_param(rcu_expedited, int, 0); module_param(rcu_normal, int, 0); -static int rcu_normal_after_boot; +static int rcu_normal_after_boot = IS_ENABLED(CONFIG_PREEMPT_RT); +#ifndef CONFIG_PREEMPT_RT module_param(rcu_normal_after_boot, int, 0); +#endif #endif /* #ifndef CONFIG_TINY_RCU */ #ifdef CONFIG_DEBUG_LOCK_ALLOC diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 15d2562118d1..a75c608839c4 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3464,7 +3464,7 @@ out: /** * try_invoke_on_locked_down_task - Invoke a function on task in fixed state - * @p: Process for which the function is to be invoked. + * @p: Process for which the function is to be invoked, can be @current. * @func: Function to invoke. * @arg: Argument to function. * @@ -3482,12 +3482,11 @@ out: */ bool try_invoke_on_locked_down_task(struct task_struct *p, bool (*func)(struct task_struct *t, void *arg), void *arg) { - bool ret = false; struct rq_flags rf; + bool ret = false; struct rq *rq; - lockdep_assert_irqs_enabled(); - raw_spin_lock_irq(&p->pi_lock); + raw_spin_lock_irqsave(&p->pi_lock, rf.flags); if (p->on_rq) { rq = __task_rq_lock(p, &rf); if (task_rq(p) == rq) @@ -3504,7 +3503,7 @@ bool try_invoke_on_locked_down_task(struct task_struct *p, bool (*func)(struct t ret = func(p, arg); } } - raw_spin_unlock_irq(&p->pi_lock); + raw_spin_unlock_irqrestore(&p->pi_lock, rf.flags); return ret; } diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 8dbc008f8942..f475f1a027c8 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -1237,6 +1237,20 @@ int try_to_del_timer_sync(struct timer_list *timer) } EXPORT_SYMBOL(try_to_del_timer_sync); +bool timer_curr_running(struct timer_list *timer) +{ + int i; + + for (i = 0; i < NR_BASES; i++) { + struct timer_base *base = this_cpu_ptr(&timer_bases[i]); + + if (base->running_timer == timer) + return true; + } + + return false; +} + #ifdef CONFIG_PREEMPT_RT static __init void timer_base_init_expiry_lock(struct timer_base *base) { diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c index e59eda07305e..a1071cdefb5a 100644 --- a/lib/percpu-refcount.c +++ b/lib/percpu-refcount.c @@ -5,6 +5,7 @@ #include <linux/sched.h> #include <linux/wait.h> #include <linux/slab.h> +#include <linux/mm.h> #include <linux/percpu-refcount.h> /* @@ -168,6 +169,7 @@ static void percpu_ref_switch_to_atomic_rcu(struct rcu_head *rcu) struct percpu_ref_data, rcu); struct percpu_ref *ref = data->ref; unsigned long __percpu *percpu_count = percpu_count_ptr(ref); + static atomic_t underflows; unsigned long count = 0; int cpu; @@ -191,9 +193,13 @@ static void percpu_ref_switch_to_atomic_rcu(struct rcu_head *rcu) */ atomic_long_add((long)count - PERCPU_COUNT_BIAS, &data->count); - WARN_ONCE(atomic_long_read(&data->count) <= 0, - "percpu ref (%ps) <= 0 (%ld) after switching to atomic", - data->release, atomic_long_read(&data->count)); + if (WARN_ONCE(atomic_long_read(&data->count) <= 0, + "percpu ref (%ps) <= 0 (%ld) after switching to atomic", + data->release, atomic_long_read(&data->count)) && + atomic_inc_return(&underflows) < 4) { + pr_err("%s(): percpu_ref underflow", __func__); + mem_dump_obj(data); + } /* @ref is viewed as dead on all CPUs, send out switch confirmation */ percpu_ref_call_confirm_rcu(rcu); diff --git a/mm/slab.c b/mm/slab.c index d7c8da9319c7..dcc55e78f353 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -3635,6 +3635,26 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t flags, EXPORT_SYMBOL(__kmalloc_node_track_caller); #endif /* CONFIG_NUMA */ +void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct page *page) +{ + struct kmem_cache *cachep; + unsigned int objnr; + void *objp; + + kpp->kp_ptr = object; + kpp->kp_page = page; + cachep = page->slab_cache; + kpp->kp_slab_cache = cachep; + objp = object - obj_offset(cachep); + kpp->kp_data_offset = obj_offset(cachep); + page = virt_to_head_page(objp); + objnr = obj_to_index(cachep, page, objp); + objp = index_to_obj(cachep, page, objnr); + kpp->kp_objp = objp; + if (DEBUG && cachep->flags & SLAB_STORE_USER) + kpp->kp_ret = *dbg_userword(cachep, objp); +} + /** * __do_kmalloc - allocate memory * @size: how many bytes of memory are required. diff --git a/mm/slab.h b/mm/slab.h index 1a756a359fa8..ecad9b57bc44 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -615,4 +615,16 @@ static inline bool slab_want_init_on_free(struct kmem_cache *c) return false; } +#define KS_ADDRS_COUNT 16 +struct kmem_obj_info { + void *kp_ptr; + struct page *kp_page; + void *kp_objp; + unsigned long kp_data_offset; + struct kmem_cache *kp_slab_cache; + void *kp_ret; + void *kp_stack[KS_ADDRS_COUNT]; +}; +void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct page *page); + #endif /* MM_SLAB_H */ diff --git a/mm/slab_common.c b/mm/slab_common.c index e981c80d216c..adbace4256ef 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -537,6 +537,81 @@ bool slab_is_available(void) return slab_state >= UP; } +/** + * kmem_valid_obj - does the pointer reference a valid slab object? + * @object: pointer to query. + * + * Return: %true if the pointer is to a not-yet-freed object from + * kmalloc() or kmem_cache_alloc(), either %true or %false if the pointer + * is to an already-freed object, and %false otherwise. + */ +bool kmem_valid_obj(void *object) +{ + struct page *page; + + /* Some arches consider ZERO_SIZE_PTR to be a valid address. */ + if (object < (void *)PAGE_SIZE || !virt_addr_valid(object)) + return false; + page = virt_to_head_page(object); + return PageSlab(page); +} + +/** + * kmem_dump_obj - Print available slab provenance information + * @object: slab object for which to find provenance information. + * + * This function uses pr_cont(), so that the caller is expected to have + * printed out whatever preamble is appropriate. The provenance information + * depends on the type of object and on how much debugging is enabled. + * For a slab-cache object, the fact that it is a slab object is printed, + * and, if available, the slab name, return address, and stack trace from + * the allocation of that object. + * + * This function will splat if passed a pointer to a non-slab object. + * If you are not sure what type of object you have, you should instead + * use mem_dump_obj(). + */ +void kmem_dump_obj(void *object) +{ + char *cp = IS_ENABLED(CONFIG_MMU) ? "" : "/vmalloc"; + int i; + struct page *page; + unsigned long ptroffset; + struct kmem_obj_info kp = { }; + + if (WARN_ON_ONCE(!virt_addr_valid(object))) + return; + page = virt_to_head_page(object); + if (WARN_ON_ONCE(!PageSlab(page))) { + pr_cont(" non-slab memory.\n"); + return; + } + kmem_obj_info(&kp, object, page); + if (kp.kp_slab_cache) + pr_cont(" slab%s %s", cp, kp.kp_slab_cache->name); + else + pr_cont(" slab%s", cp); + if (kp.kp_objp) + pr_cont(" start %px", kp.kp_objp); + if (kp.kp_data_offset) + pr_cont(" data offset %lu", kp.kp_data_offset); + if (kp.kp_objp) { + ptroffset = ((char *)object - (char *)kp.kp_objp) - kp.kp_data_offset; + pr_cont(" pointer offset %lu", ptroffset); + } + if (kp.kp_slab_cache && kp.kp_slab_cache->usersize) + pr_cont(" size %u", kp.kp_slab_cache->usersize); + if (kp.kp_ret) + pr_cont(" allocated at %pS\n", kp.kp_ret); + else + pr_cont("\n"); + for (i = 0; i < ARRAY_SIZE(kp.kp_stack); i++) { + if (!kp.kp_stack[i]) + break; + pr_info(" %pS\n", kp.kp_stack[i]); + } +} + #ifndef CONFIG_SLOB /* Create a cache during boot when no slab services are available yet */ void __init create_boot_cache(struct kmem_cache *s, const char *name, diff --git a/mm/slob.c b/mm/slob.c index 8d4bfa46247f..ef87ada8705d 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -461,6 +461,12 @@ out: spin_unlock_irqrestore(&slob_lock, flags); } +void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct page *page) +{ + kpp->kp_ptr = object; + kpp->kp_page = page; +} + /* * End of slob allocator proper. Begin kmem_cache_alloc and kmalloc frontend. */ diff --git a/mm/slub.c b/mm/slub.c index 0c8b43a5b3b0..3c1a84316fd7 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -3919,6 +3919,46 @@ int __kmem_cache_shutdown(struct kmem_cache *s) return 0; } +void kmem_obj_info(struct kmem_obj_info *kpp, void *object, struct page *page) +{ + void *base; + int __maybe_unused i; + unsigned int objnr; + void *objp; + void *objp0; + struct kmem_cache *s = page->slab_cache; + struct track __maybe_unused *trackp; + + kpp->kp_ptr = object; + kpp->kp_page = page; + kpp->kp_slab_cache = s; + base = page_address(page); + objp0 = kasan_reset_tag(object); +#ifdef CONFIG_SLUB_DEBUG + objp = restore_red_left(s, objp0); +#else + objp = objp0; +#endif + objnr = obj_to_index(s, page, objp); + kpp->kp_data_offset = (unsigned long)((char *)objp0 - (char *)objp); + objp = base + s->size * objnr; + kpp->kp_objp = objp; + if (WARN_ON_ONCE(objp < base || objp >= base + page->objects * s->size || (objp - base) % s->size) || + !(s->flags & SLAB_STORE_USER)) + return; +#ifdef CONFIG_SLUB_DEBUG + trackp = get_track(s, objp, TRACK_ALLOC); + kpp->kp_ret = (void *)trackp->addr; +#ifdef CONFIG_STACKTRACE + for (i = 0; i < KS_ADDRS_COUNT && i < TRACK_ADDRS_COUNT; i++) { + kpp->kp_stack[i] = (void *)trackp->addrs[i]; + if (!kpp->kp_stack[i]) + break; + } +#endif +#endif +} + /******************************************************************** * Kmalloc subsystem *******************************************************************/ diff --git a/mm/util.c b/mm/util.c index 8c9b7d1e7c49..54870226cea6 100644 --- a/mm/util.c +++ b/mm/util.c @@ -982,3 +982,34 @@ int __weak memcmp_pages(struct page *page1, struct page *page2) kunmap_atomic(addr1); return ret; } + +/** + * mem_dump_obj - Print available provenance information + * @object: object for which to find provenance information. + * + * This function uses pr_cont(), so that the caller is expected to have + * printed out whatever preamble is appropriate. The provenance information + * depends on the type of object and on how much debugging is enabled. + * For example, for a slab-cache object, the slab name is printed, and, + * if available, the return address and stack trace from the allocation + * of that object. + */ +void mem_dump_obj(void *object) +{ + if (kmem_valid_obj(object)) { + kmem_dump_obj(object); + return; + } + if (vmalloc_dump_obj(object)) + return; + if (!virt_addr_valid(object)) { + if (object == NULL) + pr_cont(" NULL pointer.\n"); + else if (object == ZERO_SIZE_PTR) + pr_cont(" zero-size pointer.\n"); + else + pr_cont(" non-paged memory.\n"); + return; + } + pr_cont(" non-slab/vmalloc memory.\n"); +} diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 4d88fe5a277a..e3229ff627ea 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -3448,6 +3448,19 @@ void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms) } #endif /* CONFIG_SMP */ +bool vmalloc_dump_obj(void *object) +{ + struct vm_struct *vm; + void *objp = (void *)PAGE_ALIGN((unsigned long)object); + + vm = find_vm_area(objp); + if (!vm) + return false; + pr_cont(" %u-page vmalloc region starting at %#lx allocated at %pS\n", + vm->nr_pages, (unsigned long)vm->addr, vm->caller); + return true; +} + #ifdef CONFIG_PROC_FS static void *s_start(struct seq_file *m, loff_t *pos) __acquires(&vmap_purge_lock) diff --git a/tools/testing/selftests/rcutorture/bin/config2csv.sh b/tools/testing/selftests/rcutorture/bin/config2csv.sh new file mode 100755 index 000000000000..d5a16631b16e --- /dev/null +++ b/tools/testing/selftests/rcutorture/bin/config2csv.sh @@ -0,0 +1,67 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0+ +# +# Create a spreadsheet from torture-test Kconfig options and kernel boot +# parameters. Run this in the directory containing the scenario files. +# +# Usage: config2csv path.csv [ "scenario1 scenario2 ..." ] +# +# By default, this script will take the list of scenarios from the CFLIST +# file in that directory, otherwise it will consider only the scenarios +# specified on the command line. It will examine each scenario's file +# and also its .boot file, if present, and create a column in the .csv +# output file. Note that "CFLIST" is a synonym for all the scenarios in the +# CFLIST file, which allows easy comparison of those scenarios with selected +# scenarios such as BUSTED that are normally omitted from CFLIST files. + +csvout=${1} +if test -z "$csvout" +then + echo "Need .csv output file as first argument." + exit 1 +fi +shift +defaultconfigs="`tr '\012' ' ' < CFLIST`" +if test "$#" -eq 0 +then + scenariosarg=$defaultconfigs +else + scenariosarg=$* +fi +scenarios="`echo $scenariosarg | sed -e "s/\<CFLIST\>/$defaultconfigs/g"`" + +T=/tmp/config2latex.sh.$$ +trap 'rm -rf $T' 0 +mkdir $T + +cat << '---EOF---' >> $T/p.awk +END { +---EOF--- +for i in $scenarios +do + echo ' s["'$i'"] = 1;' >> $T/p.awk + grep -v '^#' < $i | grep -v '^ *$' > $T/p + if test -r $i.boot + then + tr -s ' ' '\012' < $i.boot | grep -v '^#' >> $T/p + fi + sed -e 's/^[^=]*$/&=?/' < $T/p | + sed -e 's/^\([^=]*\)=\(.*\)$/\tp["\1:'"$i"'"] = "\2";\n\tc["\1"] = 1;/' >> $T/p.awk +done +cat << '---EOF---' >> $T/p.awk + ns = asorti(s, ss); + nc = asorti(c, cs); + for (j = 1; j <= ns; j++) + printf ",\"%s\"", ss[j]; + printf "\n"; + for (i = 1; i <= nc; i++) { + printf "\"%s\"", cs[i]; + for (j = 1; j <= ns; j++) { + printf ",\"%s\"", p[cs[i] ":" ss[j]]; + } + printf "\n"; + } +} +---EOF--- +awk -f $T/p.awk < /dev/null > $T/p.csv +cp $T/p.csv $csvout diff --git a/tools/testing/selftests/rcutorture/bin/console-badness.sh b/tools/testing/selftests/rcutorture/bin/console-badness.sh index 80ae7f08b363..e6a132df6172 100755 --- a/tools/testing/selftests/rcutorture/bin/console-badness.sh +++ b/tools/testing/selftests/rcutorture/bin/console-badness.sh @@ -14,4 +14,5 @@ egrep 'Badness|WARNING:|Warn|BUG|===========|Call Trace:|Oops:|detected stalls o grep -v 'ODEBUG: ' | grep -v 'This means that this is a DEBUG kernel and it is' | grep -v 'Warning: unable to open an initial console' | +grep -v 'Warning: Failed to add ttynull console. No stdin, stdout, and stderr.*the init process!' | grep -v 'NOHZ tick-stop error: Non-RCU local softirq work is pending, handler' diff --git a/tools/testing/selftests/rcutorture/bin/functions.sh b/tools/testing/selftests/rcutorture/bin/functions.sh index 82663495fb38..c35ba24f994c 100644 --- a/tools/testing/selftests/rcutorture/bin/functions.sh +++ b/tools/testing/selftests/rcutorture/bin/functions.sh @@ -108,6 +108,39 @@ configfrag_hotplug_cpu () { grep -q '^CONFIG_HOTPLUG_CPU=y$' "$1" } +# get_starttime +# +# Returns a cookie identifying the current time. +get_starttime () { + awk 'BEGIN { print systime() }' < /dev/null +} + +# get_starttime_duration starttime +# +# Given the return value from get_starttime, compute a human-readable +# string denoting the time since get_starttime. +get_starttime_duration () { + awk -v starttime=$1 ' + BEGIN { + ts = systime() - starttime; + tm = int(ts / 60); + th = int(ts / 3600); + td = int(ts / 86400); + d = td; + h = th - td * 24; + m = tm - th * 60; + s = ts - tm * 60; + if (d >= 1) + printf "%dd %d:%02d:%02d\n", d, h, m, s + else if (h >= 1) + printf "%d:%02d:%02d\n", h, m, s + else if (m >= 1) + printf "%d:%02d.0\n", m, s + else + print s " seconds" + }' < /dev/null +} + # identify_boot_image qemu-cmd # # Returns the relative path to the kernel build image. This will be @@ -170,6 +203,7 @@ identify_qemu () { # and the TORTURE_QEMU_INTERACTIVE environment variable. identify_qemu_append () { echo debug_boot_weak_hash + echo panic=-1 local console=ttyS0 case "$1" in qemu-system-x86_64|qemu-system-i386) @@ -232,7 +266,7 @@ identify_qemu_args () { # Returns the number of virtual CPUs available to the aggregate of the # guest OSes. identify_qemu_vcpus () { - lscpu | grep '^CPU(s):' | sed -e 's/CPU(s)://' -e 's/[ ]*//g' + getconf _NPROCESSORS_ONLN } # print_bug diff --git a/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh b/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh index 6f50722f251f..0670841122d8 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-find-errors.sh @@ -39,12 +39,14 @@ done if test -n "$files" then $editor $files + editorret=1 else echo No build errors. fi if grep -q -e "--buildonly" < ${rundir}/log then echo Build-only run, no console logs to check. + exit $editorret fi # Find console logs with errors @@ -62,5 +64,10 @@ then exit 1 else echo No errors in console logs. - exit 0 + if test -n "$editorret" + then + exit $editorret + else + exit 0 + fi fi diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh index 840a4679a0d7..47cf4db10896 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh @@ -87,15 +87,16 @@ do fi done EDITOR=echo kvm-find-errors.sh "${@: -1}" > $T 2>&1 -ret=$? builderrors="`tr ' ' '\012' < $T | grep -c '/Make.out.diags'`" if test "$builderrors" -gt 0 then echo $builderrors runs with build errors. + ret=1 fi runerrors="`tr ' ' '\012' < $T | grep -c '/console.log.diags'`" if test "$runerrors" -gt 0 then echo $runerrors runs with runtime errors. + ret=2 fi exit $ret diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh index 3cd03d01857c..536d103ef166 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh @@ -125,7 +125,6 @@ seconds=$4 qemu_args=$5 boot_args=$6 -kstarttime=`gawk 'BEGIN { print systime() }' < /dev/null` if test -z "$TORTURE_BUILDONLY" then echo ' ---' `date`: Starting kernel @@ -158,6 +157,8 @@ then boot_args="$boot_args $TORTURE_BOOT_GDB_ARG" fi echo $QEMU $qemu_args -m $TORTURE_QEMU_MEM -kernel $KERNEL -append \"$qemu_append $boot_args\" $TORTURE_QEMU_GDB_ARG > $resdir/qemu-cmd +echo "# TORTURE_SHUTDOWN_GRACE=$TORTURE_SHUTDOWN_GRACE" >> $resdir/qemu-cmd +echo "# seconds=$seconds" >> $resdir/qemu-cmd if test -n "$TORTURE_BUILDONLY" then @@ -174,6 +175,7 @@ echo 'echo $! > $resdir/qemu_pid' >> $T/qemu-cmd echo "NOTE: $QEMU either did not run or was interactive" > $resdir/console.log # Attempt to run qemu +kstarttime=`gawk 'BEGIN { print systime() }' < /dev/null` ( . $T/qemu-cmd; wait `cat $resdir/qemu_pid`; echo $? > $resdir/qemu-retval ) & commandcompleted=0 if test -z "$TORTURE_KCONFIG_GDB_ARG" @@ -209,7 +211,7 @@ do if test -n "$TORTURE_KCONFIG_GDB_ARG" then : - elif test $kruntime -ge $seconds || test -f "$TORTURE_STOPFILE" + elif test $kruntime -ge $seconds || test -f "$resdir/../STOP.1" then break; fi @@ -252,16 +254,16 @@ then fi if test $commandcompleted -eq 0 -a -n "$qemu_pid" then - if ! test -f "$TORTURE_STOPFILE" + if ! test -f "$resdir/../STOP.1" then echo Grace period for qemu job at pid $qemu_pid fi oldline="`tail $resdir/console.log`" while : do - if test -f "$TORTURE_STOPFILE" + if test -f "$resdir/../STOP.1" then - echo "PID $qemu_pid killed due to run STOP request" >> $resdir/Warnings 2>&1 + echo "PID $qemu_pid killed due to run STOP.1 request" >> $resdir/Warnings 2>&1 kill -KILL $qemu_pid break fi diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh index 45d07b7b69f5..8d3c99b35e06 100755 --- a/tools/testing/selftests/rcutorture/bin/kvm.sh +++ b/tools/testing/selftests/rcutorture/bin/kvm.sh @@ -47,6 +47,9 @@ cpus=0 ds=`date +%Y.%m.%d-%H.%M.%S` jitter="-1" +startdate="`date`" +starttime="`get_starttime`" + usage () { echo "Usage: $scriptname optional arguments:" echo " --allcpus" @@ -57,7 +60,7 @@ usage () { echo " --cpus N" echo " --datestamp string" echo " --defconfig string" - echo " --dryrun sched|script" + echo " --dryrun batches|sched|script" echo " --duration minutes | <seconds>s | <hours>h | <days>d" echo " --gdb" echo " --help" @@ -85,7 +88,7 @@ do ;; --bootargs|--bootarg) checkarg --bootargs "(list of kernel boot arguments)" "$#" "$2" '.*' '^--' - TORTURE_BOOTARGS="$2" + TORTURE_BOOTARGS="$TORTURE_BOOTARGS $2" shift ;; --bootimage) @@ -97,8 +100,8 @@ do TORTURE_BUILDONLY=1 ;; --configs|--config) - checkarg --configs "(list of config files)" "$#" "$2" '^[^/]*$' '^--' - configs="$2" + checkarg --configs "(list of config files)" "$#" "$2" '^[^/]\+$' '^--' + configs="$configs $2" shift ;; --cpus) @@ -113,7 +116,7 @@ do shift ;; --datestamp) - checkarg --datestamp "(relative pathname)" "$#" "$2" '^[^/]*$' '^--' + checkarg --datestamp "(relative pathname)" "$#" "$2" '^[a-zA-Z0-9._-/]*$' '^--' ds=$2 shift ;; @@ -123,7 +126,7 @@ do shift ;; --dryrun) - checkarg --dryrun "sched|script" $# "$2" 'sched\|script' '^--' + checkarg --dryrun "batches|sched|script" $# "$2" 'batches\|sched\|script' '^--' dryrun=$2 shift ;; @@ -162,18 +165,18 @@ do ;; --kconfig|--kconfigs) checkarg --kconfig "(Kconfig options)" $# "$2" '^CONFIG_[A-Z0-9_]\+=\([ynm]\|[0-9]\+\)\( CONFIG_[A-Z0-9_]\+=\([ynm]\|[0-9]\+\)\)*$' '^error$' - TORTURE_KCONFIG_ARG="$2" + TORTURE_KCONFIG_ARG="`echo "$TORTURE_KCONFIG_ARG $2" | sed -e 's/^ *//' -e 's/ *$//'`" shift ;; --kasan) TORTURE_KCONFIG_KASAN_ARG="CONFIG_DEBUG_INFO=y CONFIG_KASAN=y"; export TORTURE_KCONFIG_KASAN_ARG ;; --kcsan) - TORTURE_KCONFIG_KCSAN_ARG="CONFIG_DEBUG_INFO=y CONFIG_KCSAN=y CONFIG_KCSAN_ASSUME_PLAIN_WRITES_ATOMIC=n CONFIG_KCSAN_REPORT_VALUE_CHANGE_ONLY=n CONFIG_KCSAN_REPORT_ONCE_IN_MS=100000 CONFIG_KCSAN_VERBOSE=y CONFIG_KCSAN_INTERRUPT_WATCHER=y"; export TORTURE_KCONFIG_KCSAN_ARG + TORTURE_KCONFIG_KCSAN_ARG="CONFIG_DEBUG_INFO=y CONFIG_KCSAN=y CONFIG_KCSAN_ASSUME_PLAIN_WRITES_ATOMIC=n CONFIG_KCSAN_REPORT_VALUE_CHANGE_ONLY=n CONFIG_KCSAN_REPORT_ONCE_IN_MS=100000 CONFIG_KCSAN_INTERRUPT_WATCHER=y CONFIG_KCSAN_VERBOSE=y CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=y"; export TORTURE_KCONFIG_KCSAN_ARG ;; --kmake-arg|--kmake-args) checkarg --kmake-arg "(kernel make arguments)" $# "$2" '.*' '^error$' - TORTURE_KMAKE_ARG="$2" + TORTURE_KMAKE_ARG="`echo "$TORTURE_KMAKE_ARG $2" | sed -e 's/^ *//' -e 's/ *$//'`" shift ;; --mac) @@ -191,7 +194,7 @@ do ;; --qemu-args|--qemu-arg) checkarg --qemu-args "(qemu arguments)" $# "$2" '^-' '^error' - TORTURE_QEMU_ARG="$2" + TORTURE_QEMU_ARG="`echo "$TORTURE_QEMU_ARG $2" | sed -e 's/^ *//' -e 's/ *$//'`" shift ;; --qemu-cmd) @@ -232,7 +235,7 @@ do shift done -if test -z "$TORTURE_INITRD" || tools/testing/selftests/rcutorture/bin/mkinitrd.sh +if test -n "$dryrun" || test -z "$TORTURE_INITRD" || tools/testing/selftests/rcutorture/bin/mkinitrd.sh then : else @@ -283,19 +286,34 @@ then exit 1 fi fi -for CF1 in $configs_derep +echo 'BEGIN {' > $T/cfgcpu.awk +for CF1 in `echo $configs_derep | tr -s ' ' '\012' | sort -u` do if test -f "$CONFIGFRAG/$CF1" then - cpu_count=`configNR_CPUS.sh $CONFIGFRAG/$CF1` + if echo "$TORTURE_KCONFIG_ARG" | grep -q '\<CONFIG_NR_CPUS=' + then + echo "$TORTURE_KCONFIG_ARG" | tr -s ' ' | tr ' ' '\012' > $T/KCONFIG_ARG + cpu_count=`configNR_CPUS.sh $T/KCONFIG_ARG` + else + cpu_count=`configNR_CPUS.sh $CONFIGFRAG/$CF1` + fi cpu_count=`configfrag_boot_cpus "$TORTURE_BOOTARGS" "$CONFIGFRAG/$CF1" "$cpu_count"` cpu_count=`configfrag_boot_maxcpus "$TORTURE_BOOTARGS" "$CONFIGFRAG/$CF1" "$cpu_count"` - echo $CF1 $cpu_count >> $T/cfgcpu + echo 'scenariocpu["'"$CF1"'"] = '"$cpu_count"';' >> $T/cfgcpu.awk else echo "The --configs file $CF1 does not exist, terminating." exit 1 fi done +cat << '___EOF___' >> $T/cfgcpu.awk +} +{ + for (i = 1; i <= NF; i++) + print $i, scenariocpu[$i]; +} +___EOF___ +echo $configs_derep | awk -f $T/cfgcpu.awk > $T/cfgcpu sort -k2nr $T/cfgcpu -T="$T" > $T/cfgcpu.sort # Use a greedy bin-packing algorithm, sorting the list accordingly. @@ -315,11 +333,10 @@ END { batch = 0; nc = -1; - # Each pass through the following loop creates on test batch - # that can be executed concurrently given ncpus. Note that a - # given test that requires more than the available CPUs will run in - # their own batch. Such tests just have to make do with what - # is available. + # Each pass through the following loop creates on test batch that + # can be executed concurrently given ncpus. Note that a given test + # that requires more than the available CPUs will run in its own + # batch. Such tests just have to make do with what is available. while (nc != ncpus) { batch++; nc = ncpus; @@ -375,9 +392,9 @@ if ! test -e $resdir then mkdir -p "$resdir" || : fi -mkdir $resdir/$ds +mkdir -p $resdir/$ds TORTURE_RESDIR="$resdir/$ds"; export TORTURE_RESDIR -TORTURE_STOPFILE="$resdir/$ds/STOP"; export TORTURE_STOPFILE +TORTURE_STOPFILE="$resdir/$ds/STOP.1"; export TORTURE_STOPFILE echo Results directory: $resdir/$ds echo $scriptname $args touch $resdir/$ds/log @@ -517,14 +534,19 @@ END { dump(first, i, batchnum); }' >> $T/script +cat << '___EOF___' >> $T/script +echo | tee -a $TORTURE_RESDIR/log +echo | tee -a $TORTURE_RESDIR/log +echo " --- `date` Test summary:" | tee -a $TORTURE_RESDIR/log +___EOF___ cat << ___EOF___ >> $T/script -echo -echo -echo " --- `date` Test summary:" -echo Results directory: $resdir/$ds -kcsan-collapse.sh $resdir/$ds -kvm-recheck.sh $resdir/$ds +echo Results directory: $resdir/$ds | tee -a $resdir/$ds/log +kcsan-collapse.sh $resdir/$ds | tee -a $resdir/$ds/log +kvm-recheck.sh $resdir/$ds > $T/kvm-recheck.sh.out 2>&1 ___EOF___ +echo 'ret=$?' >> $T/script +echo "cat $T/kvm-recheck.sh.out | tee -a $resdir/$ds/log" >> $T/script +echo 'exit $ret' >> $T/script if test "$dryrun" = script then @@ -533,13 +555,34 @@ then elif test "$dryrun" = sched then # Extract the test run schedule from the script. - egrep 'Start batch|Starting build\.' $T/script | - grep -v ">>" | + egrep 'Start batch|Starting build\.' $T/script | grep -v ">>" | sed -e 's/:.*$//' -e 's/^echo //' + nbuilds="`grep 'Starting build\.' $T/script | + grep -v ">>" | sed -e 's/:.*$//' -e 's/^echo //' | + awk '{ print $1 }' | grep -v '\.' | wc -l`" + echo Total number of builds: $nbuilds + nbatches="`grep 'Start batch' $T/script | grep -v ">>" | wc -l`" + echo Total number of batches: $nbatches exit 0 +elif test "$dryrun" = batches +then + # Extract the tests and their batches from the script. + egrep 'Start batch|Starting build\.' $T/script | grep -v ">>" | + sed -e 's/:.*$//' -e 's/^echo //' -e 's/-ovf//' | + awk ' + /^----Start/ { + batchno = $3; + next; + } + { + print batchno, $1, $2 + }' else # Not a dryrun, so run the script. - sh $T/script + bash $T/script + ret=$? + echo " --- Done at `date` (`get_starttime_duration $starttime`) exitcode $ret" | tee -a $resdir/$ds/log + exit $ret fi # Tracing: trace_event=rcu:rcu_grace_period,rcu:rcu_future_grace_period,rcu:rcu_grace_period_init,rcu:rcu_nocb_wake,rcu:rcu_preempt_task,rcu:rcu_unlock_preempted_task,rcu:rcu_quiescent_state_report,rcu:rcu_fqs,rcu:rcu_callback,rcu:rcu_kfree_callback,rcu:rcu_batch_start,rcu:rcu_invoke_callback,rcu:rcu_invoke_kfree_callback,rcu:rcu_batch_end,rcu:rcu_torture_read,rcu:rcu_barrier diff --git a/tools/testing/selftests/rcutorture/bin/parse-build.sh b/tools/testing/selftests/rcutorture/bin/parse-build.sh index 09155c15ea65..9313e5065ae9 100755 --- a/tools/testing/selftests/rcutorture/bin/parse-build.sh +++ b/tools/testing/selftests/rcutorture/bin/parse-build.sh @@ -21,7 +21,7 @@ mkdir $T . functions.sh -if grep -q CC < $F || test -n "$TORTURE_TRUST_MAKE" +if grep -q CC < $F || test -n "$TORTURE_TRUST_MAKE" || grep -qe --trust-make < `dirname $F`/../log then : else diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh index 263b1be50008..9f624bd53c27 100755 --- a/tools/testing/selftests/rcutorture/bin/parse-console.sh +++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh @@ -128,7 +128,7 @@ then then summary="$summary Badness: $n_badness" fi - n_warn=`grep -v 'Warning: unable to open an initial console' $file | egrep -c 'WARNING:|Warn'` + n_warn=`grep -v 'Warning: unable to open an initial console' $file | grep -v 'Warning: Failed to add ttynull console. No stdin, stdout, and stderr for the init process' | egrep -c 'WARNING:|Warn'` if test "$n_warn" -ne 0 then summary="$summary Warnings: $n_warn" diff --git a/tools/testing/selftests/rcutorture/bin/torture.sh b/tools/testing/selftests/rcutorture/bin/torture.sh new file mode 100755 index 000000000000..ad7525b7ac29 --- /dev/null +++ b/tools/testing/selftests/rcutorture/bin/torture.sh @@ -0,0 +1,442 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0+ +# +# Run a series of torture tests, intended for overnight or +# longer timeframes, and also for large systems. +# +# Usage: torture.sh [ options ] +# +# Copyright (C) 2020 Facebook, Inc. +# +# Authors: Paul E. McKenney <paulmck@kernel.org> + +scriptname=$0 +args="$*" + +KVM="`pwd`/tools/testing/selftests/rcutorture"; export KVM +PATH=${KVM}/bin:$PATH; export PATH +. functions.sh + +TORTURE_ALLOTED_CPUS="`identify_qemu_vcpus`" +MAKE_ALLOTED_CPUS=$((TORTURE_ALLOTED_CPUS*2)) +HALF_ALLOTED_CPUS=$((TORTURE_ALLOTED_CPUS/2)) +if test "$HALF_ALLOTED_CPUS" -lt 1 +then + HALF_ALLOTED_CPUS=1 +fi +VERBOSE_BATCH_CPUS=$((TORTURE_ALLOTED_CPUS/16)) +if test "$VERBOSE_BATCH_CPUS" -lt 2 +then + VERBOSE_BATCH_CPUS=0 +fi + +# Configurations/scenarios. +configs_rcutorture= +configs_locktorture= +configs_scftorture= +kcsan_kmake_args= + +# Default compression, duration, and apportionment. +compress_kasan_vmlinux="`identify_qemu_vcpus`" +duration_base=10 +duration_rcutorture_frac=7 +duration_locktorture_frac=1 +duration_scftorture_frac=2 + +# "yes" or "no" parameters +do_allmodconfig=yes +do_rcutorture=yes +do_locktorture=yes +do_scftorture=yes +do_rcuscale=yes +do_refscale=yes +do_kvfree=yes +do_kasan=yes +do_kcsan=no + +# doyesno - Helper function for yes/no arguments +function doyesno () { + if test "$1" = "$2" + then + echo yes + else + echo no + fi +} + +usage () { + echo "Usage: $scriptname optional arguments:" + echo " --compress-kasan-vmlinux concurrency" + echo " --configs-rcutorture \"config-file list w/ repeat factor (3*TINY01)\"" + echo " --configs-locktorture \"config-file list w/ repeat factor (10*LOCK01)\"" + echo " --configs-scftorture \"config-file list w/ repeat factor (2*CFLIST)\"" + echo " --doall" + echo " --doallmodconfig / --do-no-allmodconfig" + echo " --do-kasan / --do-no-kasan" + echo " --do-kcsan / --do-no-kcsan" + echo " --do-kvfree / --do-no-kvfree" + echo " --do-locktorture / --do-no-locktorture" + echo " --do-none" + echo " --do-rcuscale / --do-no-rcuscale" + echo " --do-rcutorture / --do-no-rcutorture" + echo " --do-refscale / --do-no-refscale" + echo " --do-scftorture / --do-no-scftorture" + echo " --duration [ <minutes> | <hours>h | <days>d ]" + echo " --kcsan-kmake-arg kernel-make-arguments" + exit 1 +} + +while test $# -gt 0 +do + case "$1" in + --compress-kasan-vmlinux) + checkarg --compress-kasan-vmlinux "(concurrency level)" $# "$2" '^[0-9][0-9]*$' '^error' + compress_kasan_vmlinux=$2 + shift + ;; + --config-rcutorture|--configs-rcutorture) + checkarg --configs-rcutorture "(list of config files)" "$#" "$2" '^[^/]\+$' '^--' + configs_rcutorture="$configs_rcutorture $2" + shift + ;; + --config-locktorture|--configs-locktorture) + checkarg --configs-locktorture "(list of config files)" "$#" "$2" '^[^/]\+$' '^--' + configs_locktorture="$configs_locktorture $2" + shift + ;; + --config-scftorture|--configs-scftorture) + checkarg --configs-scftorture "(list of config files)" "$#" "$2" '^[^/]\+$' '^--' + configs_scftorture="$configs_scftorture $2" + shift + ;; + --doall) + do_allmodconfig=yes + do_rcutorture=yes + do_locktorture=yes + do_scftorture=yes + do_rcuscale=yes + do_refscale=yes + do_kvfree=yes + do_kasan=yes + do_kcsan=yes + ;; + --do-allmodconfig|--do-no-allmodconfig) + do_allmodconfig=`doyesno "$1" --do-allmodconfig` + ;; + --do-kasan|--do-no-kasan) + do_kasan=`doyesno "$1" --do-kasan` + ;; + --do-kcsan|--do-no-kcsan) + do_kcsan=`doyesno "$1" --do-kcsan` + ;; + --do-kvfree|--do-no-kvfree) + do_kvfree=`doyesno "$1" --do-kvfree` + ;; + --do-locktorture|--do-no-locktorture) + do_locktorture=`doyesno "$1" --do-locktorture` + ;; + --do-none) + do_allmodconfig=no + do_rcutorture=no + do_locktorture=no + do_scftorture=no + do_rcuscale=no + do_refscale=no + do_kvfree=no + do_kasan=no + do_kcsan=no + ;; + --do-rcuscale|--do-no-rcuscale) + do_rcuscale=`doyesno "$1" --do-rcuscale` + ;; + --do-rcutorture|--do-no-rcutorture) + do_rcutorture=`doyesno "$1" --do-rcutorture` + ;; + --do-refscale|--do-no-refscale) + do_refscale=`doyesno "$1" --do-refscale` + ;; + --do-scftorture|--do-no-scftorture) + do_scftorture=`doyesno "$1" --do-scftorture` + ;; + --duration) + checkarg --duration "(minutes)" $# "$2" '^[0-9][0-9]*\(m\|h\|d\|\)$' '^error' + mult=1 + if echo "$2" | grep -q 'm$' + then + mult=1 + elif echo "$2" | grep -q 'h$' + then + mult=60 + elif echo "$2" | grep -q 'd$' + then + mult=1440 + fi + ts=`echo $2 | sed -e 's/[smhd]$//'` + duration_base=$(($ts*mult)) + shift + ;; + --kcsan-kmake-arg|--kcsan-kmake-args) + checkarg --kcsan-kmake-arg "(kernel make arguments)" $# "$2" '.*' '^error$' + kcsan_kmake_args="`echo "$kcsan_kmake_args $2" | sed -e 's/^ *//' -e 's/ *$//'`" + shift + ;; + *) + echo Unknown argument $1 + usage + ;; + esac + shift +done + +ds="`date +%Y.%m.%d-%H.%M.%S`-torture" +startdate="`date`" +starttime="`get_starttime`" + +T=/tmp/torture.sh.$$ +trap 'rm -rf $T' 0 2 +mkdir $T + +echo " --- " $scriptname $args | tee -a $T/log +echo " --- Results directory: " $ds | tee -a $T/log + +# Calculate rcutorture defaults and apportion time +if test -z "$configs_rcutorture" +then + configs_rcutorture=CFLIST +fi +duration_rcutorture=$((duration_base*duration_rcutorture_frac/10)) +if test "$duration_rcutorture" -eq 0 +then + echo " --- Zero time for rcutorture, disabling" | tee -a $T/log + do_rcutorture=no +fi + +# Calculate locktorture defaults and apportion time +if test -z "$configs_locktorture" +then + configs_locktorture=CFLIST +fi +duration_locktorture=$((duration_base*duration_locktorture_frac/10)) +if test "$duration_locktorture" -eq 0 +then + echo " --- Zero time for locktorture, disabling" | tee -a $T/log + do_locktorture=no +fi + +# Calculate scftorture defaults and apportion time +if test -z "$configs_scftorture" +then + configs_scftorture=CFLIST +fi +duration_scftorture=$((duration_base*duration_scftorture_frac/10)) +if test "$duration_scftorture" -eq 0 +then + echo " --- Zero time for scftorture, disabling" | tee -a $T/log + do_scftorture=no +fi + +touch $T/failures +touch $T/successes + +# torture_one - Does a single kvm.sh run. +# +# Usage: +# torture_bootargs="[ kernel boot arguments ]" +# torture_one flavor [ kvm.sh arguments ] +# +# Note that "flavor" is an arbitrary string. Supply --torture if needed. +# Note that quoting is problematic. So on the command line, pass multiple +# values with multiple kvm.sh argument instances. +function torture_one { + local cur_bootargs= + local boottag= + + echo " --- $curflavor:" Start `date` | tee -a $T/log + if test -n "$torture_bootargs" + then + boottag="--bootargs" + cur_bootargs="$torture_bootargs" + fi + "$@" $boottag "$cur_bootargs" --datestamp "$ds/results-$curflavor" > $T/$curflavor.out 2>&1 + retcode=$? + resdir="`grep '^Results directory: ' $T/$curflavor.out | tail -1 | sed -e 's/^Results directory: //'`" + if test -z "$resdir" + then + cat $T/$curflavor.out | tee -a $T/log + echo retcode=$retcode | tee -a $T/log + fi + if test "$retcode" == 0 + then + echo "$curflavor($retcode)" $resdir >> $T/successes + else + echo "$curflavor($retcode)" $resdir >> $T/failures + fi +} + +# torture_set - Does a set of tortures with and without KASAN and KCSAN. +# +# Usage: +# torture_bootargs="[ kernel boot arguments ]" +# torture_set flavor [ kvm.sh arguments ] +# +# Note that "flavor" is an arbitrary string. Supply --torture if needed. +# Note that quoting is problematic. So on the command line, pass multiple +# values with multiple kvm.sh argument instances. +function torture_set { + local cur_kcsan_kmake_args= + local kcsan_kmake_tag= + local flavor=$1 + shift + curflavor=$flavor + torture_one "$@" + if test "$do_kasan" = "yes" + then + curflavor=${flavor}-kasan + torture_one "$@" --kasan + fi + if test "$do_kcsan" = "yes" + then + curflavor=${flavor}-kcsan + if test -n "$kcsan_kmake_args" + then + kcsan_kmake_tag="--kmake-args" + cur_kcsan_kmake_args="$kcsan_kmake_args" + fi + torture_one $* --kconfig "CONFIG_DEBUG_LOCK_ALLOC=y CONFIG_PROVE_LOCKING=y" $kcsan_kmake_tag $cur_kcsan_kmake_args --kcsan + fi +} + +# make allmodconfig +if test "$do_allmodconfig" = "yes" +then + echo " --- allmodconfig:" Start `date` | tee -a $T/log + amcdir="tools/testing/selftests/rcutorture/res/$ds/allmodconfig" + mkdir -p "$amcdir" + echo " --- make clean" > "$amcdir/Make.out" 2>&1 + make -j$MAKE_ALLOTED_CPUS clean >> "$amcdir/Make.out" 2>&1 + echo " --- make allmodconfig" >> "$amcdir/Make.out" 2>&1 + make -j$MAKE_ALLOTED_CPUS allmodconfig >> "$amcdir/Make.out" 2>&1 + echo " --- make " >> "$amcdir/Make.out" 2>&1 + make -j$MAKE_ALLOTED_CPUS >> "$amcdir/Make.out" 2>&1 + retcode="$?" + echo $retcode > "$amcdir/Make.exitcode" + if test "$retcode" == 0 + then + echo "allmodconfig($retcode)" $amcdir >> $T/successes + else + echo "allmodconfig($retcode)" $amcdir >> $T/failures + fi +fi + +# --torture rcu +if test "$do_rcutorture" = "yes" +then + torture_bootargs="rcupdate.rcu_cpu_stall_suppress_at_boot=1 torture.disable_onoff_at_boot rcupdate.rcu_task_stall_timeout=30000" + torture_set "rcutorture" tools/testing/selftests/rcutorture/bin/kvm.sh --allcpus --duration "$duration_rcutorture" --configs "$configs_rcutorture" --trust-make +fi + +if test "$do_locktorture" = "yes" +then + torture_bootargs="torture.disable_onoff_at_boot" + torture_set "locktorture" tools/testing/selftests/rcutorture/bin/kvm.sh --torture lock --allcpus --duration "$duration_locktorture" --configs "$configs_locktorture" --trust-make +fi + +if test "$do_scftorture" = "yes" +then + torture_bootargs="scftorture.nthreads=$HALF_ALLOTED_CPUS torture.disable_onoff_at_boot" + torture_set "scftorture" tools/testing/selftests/rcutorture/bin/kvm.sh --torture scf --allcpus --duration "$duration_scftorture" --configs "$configs_scftorture" --kconfig "CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --trust-make +fi + +if test "$do_refscale" = yes +then + primlist="`grep '\.name[ ]*=' kernel/rcu/refscale.c | sed -e 's/^[^"]*"//' -e 's/".*$//'`" +else + primlist= +fi +for prim in $primlist +do + torture_bootargs="refscale.scale_type="$prim" refscale.nreaders=$HALF_ALLOTED_CPUS refscale.loops=10000 refscale.holdoff=20 torture.disable_onoff_at_boot" + torture_set "refscale-$prim" tools/testing/selftests/rcutorture/bin/kvm.sh --torture refscale --allcpus --duration 5 --kconfig "CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --bootargs "verbose_batched=$VERBOSE_BATCH_CPUS torture.verbose_sleep_frequency=8 torture.verbose_sleep_duration=$VERBOSE_BATCH_CPUS" --trust-make +done + +if test "$do_rcuscale" = yes +then + primlist="`grep '\.name[ ]*=' kernel/rcu/rcuscale.c | sed -e 's/^[^"]*"//' -e 's/".*$//'`" +else + primlist= +fi +for prim in $primlist +do + torture_bootargs="rcuscale.scale_type="$prim" rcuscale.nwriters=$HALF_ALLOTED_CPUS rcuscale.holdoff=20 torture.disable_onoff_at_boot" + torture_set "rcuscale-$prim" tools/testing/selftests/rcutorture/bin/kvm.sh --torture rcuscale --allcpus --duration 5 --kconfig "CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --trust-make +done + +if test "$do_kvfree" = "yes" +then + torture_bootargs="rcuscale.kfree_rcu_test=1 rcuscale.kfree_nthreads=16 rcuscale.holdoff=20 rcuscale.kfree_loops=10000 torture.disable_onoff_at_boot" + torture_set "rcuscale-kvfree" tools/testing/selftests/rcutorture/bin/kvm.sh --torture rcuscale --allcpus --duration 10 --kconfig "CONFIG_NR_CPUS=$HALF_ALLOTED_CPUS" --trust-make +fi + +echo " --- " $scriptname $args +echo " --- " Done `date` | tee -a $T/log +ret=0 +nsuccesses=0 +echo SUCCESSES: | tee -a $T/log +if test -s "$T/successes" +then + cat "$T/successes" | tee -a $T/log + nsuccesses="`wc -l "$T/successes" | awk '{ print $1 }'`" +fi +nfailures=0 +echo FAILURES: | tee -a $T/log +if test -s "$T/failures" +then + cat "$T/failures" | tee -a $T/log + nfailures="`wc -l "$T/failures" | awk '{ print $1 }'`" + ret=2 +fi +echo Started at $startdate, ended at `date`, duration `get_starttime_duration $starttime`. | tee -a $T/log +echo Summary: Successes: $nsuccesses Failures: $nfailures. | tee -a $T/log +tdir="`cat $T/successes $T/failures | head -1 | awk '{ print $NF }' | sed -e 's,/[^/]\+/*$,,'`" +if test -n "$tdir" && test $compress_kasan_vmlinux -gt 0 +then + # KASAN vmlinux files can approach 1GB in size, so compress them. + echo Looking for KASAN files to compress: `date` > "$tdir/log-xz" 2>&1 + find "$tdir" -type d -name '*-kasan' -print > $T/xz-todo + ncompresses=0 + batchno=1 + if test -s $T/xz-todo + then + echo Size before compressing: `du -sh $tdir | awk '{ print $1 }'` `date` 2>&1 | tee -a "$tdir/log-xz" | tee -a $T/log + for i in `cat $T/xz-todo` + do + echo Compressing vmlinux files in ${i}: `date` >> "$tdir/log-xz" 2>&1 + for j in $i/*/vmlinux + do + xz "$j" >> "$tdir/log-xz" 2>&1 & + ncompresses=$((ncompresses+1)) + if test $ncompresses -ge $compress_kasan_vmlinux + then + echo Waiting for batch $batchno of $ncompresses compressions `date` | tee -a "$tdir/log-xz" | tee -a $T/log + wait + ncompresses=0 + batchno=$((batchno+1)) + fi + done + done + if test $ncompresses -gt 0 + then + echo Waiting for final batch $batchno of $ncompresses compressions `date` | tee -a "$tdir/log-xz" | tee -a $T/log + fi + wait + echo Size after compressing: `du -sh $tdir | awk '{ print $1 }'` `date` 2>&1 | tee -a "$tdir/log-xz" | tee -a $T/log + echo Total duration `get_starttime_duration $starttime`. | tee -a $T/log + else + echo No compression needed: `date` >> "$tdir/log-xz" 2>&1 + fi +fi +if test -n "$tdir" +then + cp $T/log "$tdir" +fi +exit $ret diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot index d6da9a61d44a..40af3df0f397 100644 --- a/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot +++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE01.boot @@ -2,5 +2,7 @@ maxcpus=8 nr_cpus=43 rcutree.gp_preinit_delay=3 rcutree.gp_init_delay=3 rcutree.gp_cleanup_delay=3 -rcu_nocbs=0 +rcu_nocbs=0-1,3-7 +rcutorture.nocbs_nthreads=8 +rcutorture.nocbs_toggle=1000 rcutorture.fwd_progress=0 |