xref: /linux-6.15/kernel/rcu/Kconfig (revision 3b6e1dd4)
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	help
12	  This option selects the RCU implementation that is
13	  designed for very large SMP system with hundreds or
14	  thousands of CPUs.  It also scales down nicely to
15	  smaller systems.
16
17config PREEMPT_RCU
18	bool
19	default y if PREEMPTION
20	select TREE_RCU
21	help
22	  This option selects the RCU implementation that is
23	  designed for very large SMP systems with hundreds or
24	  thousands of CPUs, but for which real-time response
25	  is also required.  It also scales down nicely to
26	  smaller systems.
27
28	  Select this option if you are unsure.
29
30config TINY_RCU
31	bool
32	default y if !PREEMPTION && !SMP
33	help
34	  This option selects the RCU implementation that is
35	  designed for UP systems from which real-time response
36	  is not required.  This option greatly reduces the
37	  memory footprint of RCU.
38
39config RCU_EXPERT
40	bool "Make expert-level adjustments to RCU configuration"
41	default n
42	help
43	  This option needs to be enabled if you wish to make
44	  expert-level adjustments to RCU configuration.  By default,
45	  no such adjustments can be made, which has the often-beneficial
46	  side-effect of preventing "make oldconfig" from asking you all
47	  sorts of detailed questions about how you would like numerous
48	  obscure RCU options to be set up.
49
50	  Say Y if you need to make expert-level adjustments to RCU.
51
52	  Say N if you are unsure.
53
54config SRCU
55	bool
56	help
57	  This option selects the sleepable version of RCU. This version
58	  permits arbitrary sleeping or blocking within RCU read-side critical
59	  sections.
60
61config TINY_SRCU
62	bool
63	default y if SRCU && TINY_RCU
64	help
65	  This option selects the single-CPU non-preemptible version of SRCU.
66
67config TREE_SRCU
68	bool
69	default y if SRCU && !TINY_RCU
70	help
71	  This option selects the full-fledged version of SRCU.
72
73config TASKS_RCU_GENERIC
74	def_bool TASKS_RCU || TASKS_RUDE_RCU || TASKS_TRACE_RCU
75	select SRCU
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 TASKS_RUDE_RCU
97	def_bool 0
98	select IRQ_WORK
99	help
100	  This option enables a task-based RCU implementation that uses
101	  only context switch (including preemption) and user-mode
102	  execution as quiescent states.  It forces IPIs and context
103	  switches on all online CPUs, including idle ones, so use
104	  with caution.
105
106config FORCE_TASKS_TRACE_RCU
107	bool "Force selection of Tasks Trace RCU"
108	depends on RCU_EXPERT
109	select TASKS_TRACE_RCU
110	default n
111	help
112	  This option enables a task-based RCU implementation that uses
113	  explicit rcu_read_lock_trace() read-side markers, and allows
114	  these readers to appear in the idle loop as well as on the
115	  CPU hotplug code paths.  It can force IPIs on online CPUs,
116	  including idle ones, so use with caution.  Not for manual
117	  selection in most cases.
118
119config TASKS_TRACE_RCU
120	bool
121	default n
122	select IRQ_WORK
123
124config RCU_STALL_COMMON
125	def_bool TREE_RCU
126	help
127	  This option enables RCU CPU stall code that is common between
128	  the TINY and TREE variants of RCU.  The purpose is to allow
129	  the tiny variants to disable RCU CPU stall warnings, while
130	  making these warnings mandatory for the tree variants.
131
132config RCU_NEED_SEGCBLIST
133	def_bool ( TREE_RCU || TREE_SRCU || TASKS_RCU_GENERIC )
134
135config RCU_FANOUT
136	int "Tree-based hierarchical RCU fanout value"
137	range 2 64 if 64BIT
138	range 2 32 if !64BIT
139	depends on TREE_RCU && RCU_EXPERT
140	default 64 if 64BIT
141	default 32 if !64BIT
142	help
143	  This option controls the fanout of hierarchical implementations
144	  of RCU, allowing RCU to work efficiently on machines with
145	  large numbers of CPUs.  This value must be at least the fourth
146	  root of NR_CPUS, which allows NR_CPUS to be insanely large.
147	  The default value of RCU_FANOUT should be used for production
148	  systems, but if you are stress-testing the RCU implementation
149	  itself, small RCU_FANOUT values allow you to test large-system
150	  code paths on small(er) systems.
151
152	  Select a specific number if testing RCU itself.
153	  Take the default if unsure.
154
155config RCU_FANOUT_LEAF
156	int "Tree-based hierarchical RCU leaf-level fanout value"
157	range 2 64 if 64BIT && !RCU_STRICT_GRACE_PERIOD
158	range 2 32 if !64BIT && !RCU_STRICT_GRACE_PERIOD
159	range 2 3 if RCU_STRICT_GRACE_PERIOD
160	depends on TREE_RCU && RCU_EXPERT
161	default 16 if !RCU_STRICT_GRACE_PERIOD
162	default 2 if RCU_STRICT_GRACE_PERIOD
163	help
164	  This option controls the leaf-level fanout of hierarchical
165	  implementations of RCU, and allows trading off cache misses
166	  against lock contention.  Systems that synchronize their
167	  scheduling-clock interrupts for energy-efficiency reasons will
168	  want the default because the smaller leaf-level fanout keeps
169	  lock contention levels acceptably low.  Very large systems
170	  (hundreds or thousands of CPUs) will instead want to set this
171	  value to the maximum value possible in order to reduce the
172	  number of cache misses incurred during RCU's grace-period
173	  initialization.  These systems tend to run CPU-bound, and thus
174	  are not helped by synchronized interrupts, and thus tend to
175	  skew them, which reduces lock contention enough that large
176	  leaf-level fanouts work well.  That said, setting leaf-level
177	  fanout to a large number will likely cause problematic
178	  lock contention on the leaf-level rcu_node structures unless
179	  you boot with the skew_tick kernel parameter.
180
181	  Select a specific number if testing RCU itself.
182
183	  Select the maximum permissible value for large systems, but
184	  please understand that you may also need to set the skew_tick
185	  kernel boot parameter to avoid contention on the rcu_node
186	  structure's locks.
187
188	  Take the default if unsure.
189
190config RCU_BOOST
191	bool "Enable RCU priority boosting"
192	depends on (RT_MUTEXES && PREEMPT_RCU && RCU_EXPERT) || PREEMPT_RT
193	default y if PREEMPT_RT
194	help
195	  This option boosts the priority of preempted RCU readers that
196	  block the current preemptible RCU grace period for too long.
197	  This option also prevents heavy loads from blocking RCU
198	  callback invocation.
199
200	  Say Y here if you are working with real-time apps or heavy loads
201	  Say N here if you are unsure.
202
203config RCU_BOOST_DELAY
204	int "Milliseconds to delay boosting after RCU grace-period start"
205	range 0 3000
206	depends on RCU_BOOST
207	default 500
208	help
209	  This option specifies the time to wait after the beginning of
210	  a given grace period before priority-boosting preempted RCU
211	  readers blocking that grace period.  Note that any RCU reader
212	  blocking an expedited RCU grace period is boosted immediately.
213
214	  Accept the default if unsure.
215
216config RCU_NOCB_CPU
217	bool "Offload RCU callback processing from boot-selected CPUs"
218	depends on TREE_RCU
219	depends on RCU_EXPERT || NO_HZ_FULL
220	default n
221	help
222	  Use this option to reduce OS jitter for aggressive HPC or
223	  real-time workloads.	It can also be used to offload RCU
224	  callback invocation to energy-efficient CPUs in battery-powered
225	  asymmetric multiprocessors.  The price of this reduced jitter
226	  is that the overhead of call_rcu() increases and that some
227	  workloads will incur significant increases in context-switch
228	  rates.
229
230	  This option offloads callback invocation from the set of CPUs
231	  specified at boot time by the rcu_nocbs parameter.  For each
232	  such CPU, a kthread ("rcuox/N") will be created to invoke
233	  callbacks, where the "N" is the CPU being offloaded, and where
234	  the "x" is "p" for RCU-preempt (PREEMPTION kernels) and "s" for
235	  RCU-sched (!PREEMPTION kernels).  Nothing prevents this kthread
236	  from running on the specified CPUs, but (1) the kthreads may be
237	  preempted between each callback, and (2) affinity or cgroups can
238	  be used to force the kthreads to run on whatever set of CPUs is
239	  desired.
240
241	  Say Y here if you need reduced OS jitter, despite added overhead.
242	  Say N here if you are unsure.
243
244config TASKS_TRACE_RCU_READ_MB
245	bool "Tasks Trace RCU readers use memory barriers in user and idle"
246	depends on RCU_EXPERT && TASKS_TRACE_RCU
247	default PREEMPT_RT || NR_CPUS < 8
248	help
249	  Use this option to further reduce the number of IPIs sent
250	  to CPUs executing in userspace or idle during tasks trace
251	  RCU grace periods.  Given that a reasonable setting of
252	  the rcupdate.rcu_task_ipi_delay kernel boot parameter
253	  eliminates such IPIs for many workloads, proper setting
254	  of this Kconfig option is important mostly for aggressive
255	  real-time installations and for battery-powered devices,
256	  hence the default chosen above.
257
258	  Say Y here if you hate IPIs.
259	  Say N here if you hate read-side memory barriers.
260	  Take the default if you are unsure.
261
262endmenu # "RCU Subsystem"
263