xref: /linux-6.15/kernel/rcu/Kconfig (revision 9621fbee)
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 TASKS_RCU
81	def_bool PREEMPTION
82	help
83	  This option enables a task-based RCU implementation that uses
84	  only voluntary context switch (not preemption!), idle, and
85	  user-mode execution as quiescent states.  Not for manual selection.
86
87config TASKS_RUDE_RCU
88	def_bool 0
89	help
90	  This option enables a task-based RCU implementation that uses
91	  only context switch (including preemption) and user-mode
92	  execution as quiescent states.  It forces IPIs and context
93	  switches on all online CPUs, including idle ones, so use
94	  with caution.
95
96config TASKS_TRACE_RCU
97	def_bool 0
98	select IRQ_WORK
99	help
100	  This option enables a task-based RCU implementation that uses
101	  explicit rcu_read_lock_trace() read-side markers, and allows
102	  these readers to appear in the idle loop as well as on the CPU
103	  hotplug code paths.  It can force IPIs on online CPUs, including
104	  idle ones, so use with caution.
105
106config RCU_STALL_COMMON
107	def_bool TREE_RCU
108	help
109	  This option enables RCU CPU stall code that is common between
110	  the TINY and TREE variants of RCU.  The purpose is to allow
111	  the tiny variants to disable RCU CPU stall warnings, while
112	  making these warnings mandatory for the tree variants.
113
114config RCU_NEED_SEGCBLIST
115	def_bool ( TREE_RCU || TREE_SRCU || TASKS_RCU_GENERIC )
116
117config RCU_FANOUT
118	int "Tree-based hierarchical RCU fanout value"
119	range 2 64 if 64BIT
120	range 2 32 if !64BIT
121	depends on TREE_RCU && RCU_EXPERT
122	default 64 if 64BIT
123	default 32 if !64BIT
124	help
125	  This option controls the fanout of hierarchical implementations
126	  of RCU, allowing RCU to work efficiently on machines with
127	  large numbers of CPUs.  This value must be at least the fourth
128	  root of NR_CPUS, which allows NR_CPUS to be insanely large.
129	  The default value of RCU_FANOUT should be used for production
130	  systems, but if you are stress-testing the RCU implementation
131	  itself, small RCU_FANOUT values allow you to test large-system
132	  code paths on small(er) systems.
133
134	  Select a specific number if testing RCU itself.
135	  Take the default if unsure.
136
137config RCU_FANOUT_LEAF
138	int "Tree-based hierarchical RCU leaf-level fanout value"
139	range 2 64 if 64BIT && !RCU_STRICT_GRACE_PERIOD
140	range 2 32 if !64BIT && !RCU_STRICT_GRACE_PERIOD
141	range 2 3 if RCU_STRICT_GRACE_PERIOD
142	depends on TREE_RCU && RCU_EXPERT
143	default 16 if !RCU_STRICT_GRACE_PERIOD
144	default 2 if RCU_STRICT_GRACE_PERIOD
145	help
146	  This option controls the leaf-level fanout of hierarchical
147	  implementations of RCU, and allows trading off cache misses
148	  against lock contention.  Systems that synchronize their
149	  scheduling-clock interrupts for energy-efficiency reasons will
150	  want the default because the smaller leaf-level fanout keeps
151	  lock contention levels acceptably low.  Very large systems
152	  (hundreds or thousands of CPUs) will instead want to set this
153	  value to the maximum value possible in order to reduce the
154	  number of cache misses incurred during RCU's grace-period
155	  initialization.  These systems tend to run CPU-bound, and thus
156	  are not helped by synchronized interrupts, and thus tend to
157	  skew them, which reduces lock contention enough that large
158	  leaf-level fanouts work well.  That said, setting leaf-level
159	  fanout to a large number will likely cause problematic
160	  lock contention on the leaf-level rcu_node structures unless
161	  you boot with the skew_tick kernel parameter.
162
163	  Select a specific number if testing RCU itself.
164
165	  Select the maximum permissible value for large systems, but
166	  please understand that you may also need to set the skew_tick
167	  kernel boot parameter to avoid contention on the rcu_node
168	  structure's locks.
169
170	  Take the default if unsure.
171
172config RCU_BOOST
173	bool "Enable RCU priority boosting"
174	depends on (RT_MUTEXES && PREEMPT_RCU && RCU_EXPERT) || PREEMPT_RT
175	default y if PREEMPT_RT
176	help
177	  This option boosts the priority of preempted RCU readers that
178	  block the current preemptible RCU grace period for too long.
179	  This option also prevents heavy loads from blocking RCU
180	  callback invocation.
181
182	  Say Y here if you are working with real-time apps or heavy loads
183	  Say N here if you are unsure.
184
185config RCU_BOOST_DELAY
186	int "Milliseconds to delay boosting after RCU grace-period start"
187	range 0 3000
188	depends on RCU_BOOST
189	default 500
190	help
191	  This option specifies the time to wait after the beginning of
192	  a given grace period before priority-boosting preempted RCU
193	  readers blocking that grace period.  Note that any RCU reader
194	  blocking an expedited RCU grace period is boosted immediately.
195
196	  Accept the default if unsure.
197
198config RCU_EXP_KTHREAD
199	bool "Perform RCU expedited work in a real-time kthread"
200	depends on RCU_BOOST && RCU_EXPERT
201	default !PREEMPT_RT && NR_CPUS <= 32
202	help
203	  Use this option to further reduce the latencies of expedited
204	  grace periods at the expense of being more disruptive.
205
206	  This option is disabled by default on PREEMPT_RT=y kernels which
207	  disable expedited grace periods after boot by unconditionally
208	  setting rcupdate.rcu_normal_after_boot=1.
209
210	  Accept the default if unsure.
211
212config RCU_NOCB_CPU
213	bool "Offload RCU callback processing from boot-selected CPUs"
214	depends on TREE_RCU
215	depends on RCU_EXPERT || NO_HZ_FULL
216	default n
217	help
218	  Use this option to reduce OS jitter for aggressive HPC or
219	  real-time workloads.	It can also be used to offload RCU
220	  callback invocation to energy-efficient CPUs in battery-powered
221	  asymmetric multiprocessors.  The price of this reduced jitter
222	  is that the overhead of call_rcu() increases and that some
223	  workloads will incur significant increases in context-switch
224	  rates.
225
226	  This option offloads callback invocation from the set of CPUs
227	  specified at boot time by the rcu_nocbs parameter.  For each
228	  such CPU, a kthread ("rcuox/N") will be created to invoke
229	  callbacks, where the "N" is the CPU being offloaded, and where
230	  the "x" is "p" for RCU-preempt (PREEMPTION kernels) and "s" for
231	  RCU-sched (!PREEMPTION kernels).  Nothing prevents this kthread
232	  from running on the specified CPUs, but (1) the kthreads may be
233	  preempted between each callback, and (2) affinity or cgroups can
234	  be used to force the kthreads to run on whatever set of CPUs is
235	  desired.
236
237	  Say Y here if you need reduced OS jitter, despite added overhead.
238	  Say N here if you are unsure.
239
240config TASKS_TRACE_RCU_READ_MB
241	bool "Tasks Trace RCU readers use memory barriers in user and idle"
242	depends on RCU_EXPERT
243	default PREEMPT_RT || NR_CPUS < 8
244	help
245	  Use this option to further reduce the number of IPIs sent
246	  to CPUs executing in userspace or idle during tasks trace
247	  RCU grace periods.  Given that a reasonable setting of
248	  the rcupdate.rcu_task_ipi_delay kernel boot parameter
249	  eliminates such IPIs for many workloads, proper setting
250	  of this Kconfig option is important mostly for aggressive
251	  real-time installations and for battery-powered devices,
252	  hence the default chosen above.
253
254	  Say Y here if you hate IPIs.
255	  Say N here if you hate read-side memory barriers.
256	  Take the default if you are unsure.
257
258endmenu # "RCU Subsystem"
259