1# SPDX-License-Identifier: GPL-2.0-only
  2#
  3# RCU-related configuration options
  4#
  5
  6menu "RCU Subsystem"
  7
  8config TREE_RCU
  9	bool
 10	default y if SMP
 11	# Dynticks-idle tracking
 12	select CONTEXT_TRACKING_IDLE
 13	help
 14	  This option selects the RCU implementation that is
 15	  designed for very large SMP system with hundreds or
 16	  thousands of CPUs.  It also scales down nicely to
 17	  smaller systems.
 18
 19config PREEMPT_RCU
 20	bool
 21	default y if PREEMPTION
 22	select TREE_RCU
 23	help
 24	  This option selects the RCU implementation that is
 25	  designed for very large SMP systems with hundreds or
 26	  thousands of CPUs, but for which real-time response
 27	  is also required.  It also scales down nicely to
 28	  smaller systems.
 29
 30	  Select this option if you are unsure.
 31
 32config TINY_RCU
 33	bool
 34	default y if !PREEMPTION && !SMP
 35	help
 36	  This option selects the RCU implementation that is
 37	  designed for UP systems from which real-time response
 38	  is not required.  This option greatly reduces the
 39	  memory footprint of RCU.
 40
 41config RCU_EXPERT
 42	bool "Make expert-level adjustments to RCU configuration"
 43	default n
 44	help
 45	  This option needs to be enabled if you wish to make
 46	  expert-level adjustments to RCU configuration.  By default,
 47	  no such adjustments can be made, which has the often-beneficial
 48	  side-effect of preventing "make oldconfig" from asking you all
 49	  sorts of detailed questions about how you would like numerous
 50	  obscure RCU options to be set up.
 51
 52	  Say Y if you need to make expert-level adjustments to RCU.
 53
 54	  Say N if you are unsure.
 55
 56config SRCU
 57	def_bool y
 58
 59config TINY_SRCU
 60	bool
 61	default y if TINY_RCU
 62	help
 63	  This option selects the single-CPU non-preemptible version of SRCU.
 64
 65config TREE_SRCU
 66	bool
 67	default y if !TINY_RCU
 68	help
 69	  This option selects the full-fledged version of SRCU.
 70
 71config NEED_SRCU_NMI_SAFE
 72	def_bool HAVE_NMI && !ARCH_HAS_NMI_SAFE_THIS_CPU_OPS && !TINY_SRCU
 73
 74config TASKS_RCU_GENERIC
 75	def_bool TASKS_RCU || TASKS_RUDE_RCU || TASKS_TRACE_RCU
 76	help
 77	  This option enables generic infrastructure code supporting
 78	  task-based RCU implementations.  Not for manual selection.
 79
 80config FORCE_TASKS_RCU
 81	bool "Force selection of TASKS_RCU"
 82	depends on RCU_EXPERT
 83	select TASKS_RCU
 84	default n
 85	help
 86	  This option force-enables a task-based RCU implementation
 87	  that uses only voluntary context switch (not preemption!),
 88	  idle, and user-mode execution as quiescent states.  Not for
 89	  manual selection in most cases.
 90
 91config TASKS_RCU
 92	bool
 93	default n
 94	select IRQ_WORK
 95
 96config FORCE_TASKS_RUDE_RCU
 97	bool "Force selection of Tasks Rude RCU"
 98	depends on RCU_EXPERT
 99	select TASKS_RUDE_RCU
100	default n
101	help
102	  This option force-enables a task-based RCU implementation
103	  that uses only context switch (including preemption) and
104	  user-mode execution as quiescent states.  It forces IPIs and
105	  context switches on all online CPUs, including idle ones,
106	  so use with caution.	Not for manual selection in most cases.
107
108config TASKS_RUDE_RCU
109	bool
110	default n
111	select IRQ_WORK
112
113config FORCE_TASKS_TRACE_RCU
114	bool "Force selection of Tasks Trace RCU"
115	depends on RCU_EXPERT
116	select TASKS_TRACE_RCU
117	default n
118	help
119	  This option enables a task-based RCU implementation that uses
120	  explicit rcu_read_lock_trace() read-side markers, and allows
121	  these readers to appear in the idle loop as well as on the
122	  CPU hotplug code paths.  It can force IPIs on online CPUs,
123	  including idle ones, so use with caution.  Not for manual
124	  selection in most cases.
125
126config TASKS_TRACE_RCU
127	bool
128	default n
129	select IRQ_WORK
130
131config RCU_STALL_COMMON
132	def_bool TREE_RCU
133	help
134	  This option enables RCU CPU stall code that is common between
135	  the TINY and TREE variants of RCU.  The purpose is to allow
136	  the tiny variants to disable RCU CPU stall warnings, while
137	  making these warnings mandatory for the tree variants.
138
139config RCU_NEED_SEGCBLIST
140	def_bool ( TREE_RCU || TREE_SRCU || TASKS_RCU_GENERIC )
141
142config RCU_FANOUT
143	int "Tree-based hierarchical RCU fanout value"
144	range 2 64 if 64BIT
145	range 2 32 if !64BIT
146	depends on TREE_RCU && RCU_EXPERT
147	default 64 if 64BIT
148	default 32 if !64BIT
149	help
150	  This option controls the fanout of hierarchical implementations
151	  of RCU, allowing RCU to work efficiently on machines with
152	  large numbers of CPUs.  This value must be at least the fourth
153	  root of NR_CPUS, which allows NR_CPUS to be insanely large.
154	  The default value of RCU_FANOUT should be used for production
155	  systems, but if you are stress-testing the RCU implementation
156	  itself, small RCU_FANOUT values allow you to test large-system
157	  code paths on small(er) systems.
158
159	  Select a specific number if testing RCU itself.
160	  Take the default if unsure.
161
162config RCU_FANOUT_LEAF
163	int "Tree-based hierarchical RCU leaf-level fanout value"
164	range 2 64 if 64BIT && !RCU_STRICT_GRACE_PERIOD
165	range 2 32 if !64BIT && !RCU_STRICT_GRACE_PERIOD
166	range 2 3 if RCU_STRICT_GRACE_PERIOD
167	depends on TREE_RCU && RCU_EXPERT
168	default 16 if !RCU_STRICT_GRACE_PERIOD
169	default 2 if RCU_STRICT_GRACE_PERIOD
170	help
171	  This option controls the leaf-level fanout of hierarchical
172	  implementations of RCU, and allows trading off cache misses
173	  against lock contention.  Systems that synchronize their
174	  scheduling-clock interrupts for energy-efficiency reasons will
175	  want the default because the smaller leaf-level fanout keeps
176	  lock contention levels acceptably low.  Very large systems
177	  (hundreds or thousands of CPUs) will instead want to set this
178	  value to the maximum value possible in order to reduce the
179	  number of cache misses incurred during RCU's grace-period
180	  initialization.  These systems tend to run CPU-bound, and thus
181	  are not helped by synchronized interrupts, and thus tend to
182	  skew them, which reduces lock contention enough that large
183	  leaf-level fanouts work well.  That said, setting leaf-level
184	  fanout to a large number will likely cause problematic
185	  lock contention on the leaf-level rcu_node structures unless
186	  you boot with the skew_tick kernel parameter.
187
188	  Select a specific number if testing RCU itself.
189
190	  Select the maximum permissible value for large systems, but
191	  please understand that you may also need to set the skew_tick
192	  kernel boot parameter to avoid contention on the rcu_node
193	  structure's locks.
194
195	  Take the default if unsure.
196
197config RCU_BOOST
198	bool "Enable RCU priority boosting"
199	depends on (RT_MUTEXES && PREEMPT_RCU && RCU_EXPERT) || PREEMPT_RT
200	default y if PREEMPT_RT
201	help
202	  This option boosts the priority of preempted RCU readers that
203	  block the current preemptible RCU grace period for too long.
204	  This option also prevents heavy loads from blocking RCU
205	  callback invocation.
206
207	  Say Y here if you are working with real-time apps or heavy loads
208	  Say N here if you are unsure.
209
210config RCU_BOOST_DELAY
211	int "Milliseconds to delay boosting after RCU grace-period start"
212	range 0 3000
213	depends on RCU_BOOST
214	default 500
215	help
216	  This option specifies the time to wait after the beginning of
217	  a given grace period before priority-boosting preempted RCU
218	  readers blocking that grace period.  Note that any RCU reader
219	  blocking an expedited RCU grace period is boosted immediately.
220
221	  Accept the default if unsure.
222
223config RCU_EXP_KTHREAD
224	bool "Perform RCU expedited work in a real-time kthread"
225	depends on RCU_BOOST && RCU_EXPERT
226	default !PREEMPT_RT && NR_CPUS <= 32
227	help
228	  Use this option to further reduce the latencies of expedited
229	  grace periods at the expense of being more disruptive.
230
231	  This option is disabled by default on PREEMPT_RT=y kernels which
232	  disable expedited grace periods after boot by unconditionally
233	  setting rcupdate.rcu_normal_after_boot=1.
234
235	  Accept the default if unsure.
236
237config RCU_NOCB_CPU
238	bool "Offload RCU callback processing from boot-selected CPUs"
239	depends on TREE_RCU
240	depends on RCU_EXPERT || NO_HZ_FULL
241	default n
242	help
243	  Use this option to reduce OS jitter for aggressive HPC or
244	  real-time workloads.	It can also be used to offload RCU
245	  callback invocation to energy-efficient CPUs in battery-powered
246	  asymmetric multiprocessors.  The price of this reduced jitter
247	  is that the overhead of call_rcu() increases and that some
248	  workloads will incur significant increases in context-switch
249	  rates.
250
251	  This option offloads callback invocation from the set of CPUs
252	  specified at boot time by the rcu_nocbs parameter.  For each
253	  such CPU, a kthread ("rcuox/N") will be created to invoke
254	  callbacks, where the "N" is the CPU being offloaded, and where
255	  the "x" is "p" for RCU-preempt (PREEMPTION kernels) and "s" for
256	  RCU-sched (!PREEMPTION kernels).  Nothing prevents this kthread
257	  from running on the specified CPUs, but (1) the kthreads may be
258	  preempted between each callback, and (2) affinity or cgroups can
259	  be used to force the kthreads to run on whatever set of CPUs is
260	  desired.
261
262	  Say Y here if you need reduced OS jitter, despite added overhead.
263	  Say N here if you are unsure.
264
265config RCU_NOCB_CPU_DEFAULT_ALL
266	bool "Offload RCU callback processing from all CPUs by default"
267	depends on RCU_NOCB_CPU
268	default n
269	help
270	  Use this option to offload callback processing from all CPUs
271	  by default, in the absence of the rcu_nocbs or nohz_full boot
272	  parameter. This also avoids the need to use any boot parameters
273	  to achieve the effect of offloading all CPUs on boot.
274
275	  Say Y here if you want offload all CPUs by default on boot.
276	  Say N here if you are unsure.
277
278config RCU_NOCB_CPU_CB_BOOST
279	bool "Offload RCU callback from real-time kthread"
280	depends on RCU_NOCB_CPU && RCU_BOOST
281	default y if PREEMPT_RT
282	help
283	  Use this option to invoke offloaded callbacks as SCHED_FIFO
284	  to avoid starvation by heavy SCHED_OTHER background load.
285	  Of course, running as SCHED_FIFO during callback floods will
286	  cause the rcuo[ps] kthreads to monopolize the CPU for hundreds
287	  of milliseconds or more.  Therefore, when enabling this option,
288	  it is your responsibility to ensure that latency-sensitive
289	  tasks either run with higher priority or run on some other CPU.
290
291	  Say Y here if you want to set RT priority for offloading kthreads.
292	  Say N here if you are building a !PREEMPT_RT kernel and are unsure.
293
294config TASKS_TRACE_RCU_READ_MB
295	bool "Tasks Trace RCU readers use memory barriers in user and idle"
296	depends on RCU_EXPERT && TASKS_TRACE_RCU
297	default PREEMPT_RT || NR_CPUS < 8
298	help
299	  Use this option to further reduce the number of IPIs sent
300	  to CPUs executing in userspace or idle during tasks trace
301	  RCU grace periods.  Given that a reasonable setting of
302	  the rcupdate.rcu_task_ipi_delay kernel boot parameter
303	  eliminates such IPIs for many workloads, proper setting
304	  of this Kconfig option is important mostly for aggressive
305	  real-time installations and for battery-powered devices,
306	  hence the default chosen above.
307
308	  Say Y here if you hate IPIs.
309	  Say N here if you hate read-side memory barriers.
310	  Take the default if you are unsure.
311
312config RCU_LAZY
313	bool "RCU callback lazy invocation functionality"
314	depends on RCU_NOCB_CPU
315	default n
316	help
317	  To save power, batch RCU callbacks and flush after delay, memory
318	  pressure, or callback list growing too big.
319
320endmenu # "RCU Subsystem"