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 TINY_SRCU
 57	bool
 58	default y if TINY_RCU
 59	help
 60	  This option selects the single-CPU non-preemptible version of SRCU.
 61
 62config TREE_SRCU
 63	bool
 64	default y if !TINY_RCU
 65	help
 66	  This option selects the full-fledged version of SRCU.
 67
 68config NEED_SRCU_NMI_SAFE
 69	def_bool HAVE_NMI && !ARCH_HAS_NMI_SAFE_THIS_CPU_OPS && !TINY_SRCU
 70
 71config TASKS_RCU_GENERIC
 72	def_bool TASKS_RCU || TASKS_RUDE_RCU || TASKS_TRACE_RCU
 73	help
 74	  This option enables generic infrastructure code supporting
 75	  task-based RCU implementations.  Not for manual selection.
 76
 77config FORCE_TASKS_RCU
 78	bool "Force selection of TASKS_RCU"
 79	depends on RCU_EXPERT
 80	select TASKS_RCU
 81	default n
 82	help
 83	  This option force-enables a task-based RCU implementation
 84	  that uses only voluntary context switch (not preemption!),
 85	  idle, and user-mode execution as quiescent states.  Not for
 86	  manual selection in most cases.
 87
 88config TASKS_RCU
 89	bool
 90	default n
 91	select IRQ_WORK
 92
 93config FORCE_TASKS_RUDE_RCU
 94	bool "Force selection of Tasks Rude RCU"
 95	depends on RCU_EXPERT
 96	select TASKS_RUDE_RCU
 97	default n
 98	help
 99	  This option force-enables a task-based RCU implementation
100	  that uses only context switch (including preemption) and
101	  user-mode execution as quiescent states.  It forces IPIs and
102	  context switches on all online CPUs, including idle ones,
103	  so use with caution.	Not for manual selection in most cases.
104
105config TASKS_RUDE_RCU
106	bool
107	default n
108	select IRQ_WORK
109
110config FORCE_TASKS_TRACE_RCU
111	bool "Force selection of Tasks Trace RCU"
112	depends on RCU_EXPERT
113	select TASKS_TRACE_RCU
114	default n
115	help
116	  This option enables a task-based RCU implementation that uses
117	  explicit rcu_read_lock_trace() read-side markers, and allows
118	  these readers to appear in the idle loop as well as on the
119	  CPU hotplug code paths.  It can force IPIs on online CPUs,
120	  including idle ones, so use with caution.  Not for manual
121	  selection in most cases.
122
123config TASKS_TRACE_RCU
124	bool
125	default n
126	select IRQ_WORK
127
128config RCU_STALL_COMMON
129	def_bool TREE_RCU
130	help
131	  This option enables RCU CPU stall code that is common between
132	  the TINY and TREE variants of RCU.  The purpose is to allow
133	  the tiny variants to disable RCU CPU stall warnings, while
134	  making these warnings mandatory for the tree variants.
135
136config RCU_NEED_SEGCBLIST
137	def_bool ( TREE_RCU || TREE_SRCU || TASKS_RCU_GENERIC )
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
138
139config RCU_FANOUT
140	int "Tree-based hierarchical RCU fanout value"
141	range 2 64 if 64BIT
142	range 2 32 if !64BIT
143	depends on TREE_RCU && RCU_EXPERT
144	default 64 if 64BIT
145	default 32 if !64BIT
146	help
147	  This option controls the fanout of hierarchical implementations
148	  of RCU, allowing RCU to work efficiently on machines with
149	  large numbers of CPUs.  This value must be at least the fourth
150	  root of NR_CPUS, which allows NR_CPUS to be insanely large.
151	  The default value of RCU_FANOUT should be used for production
152	  systems, but if you are stress-testing the RCU implementation
153	  itself, small RCU_FANOUT values allow you to test large-system
154	  code paths on small(er) systems.
155
156	  Select a specific number if testing RCU itself.
157	  Take the default if unsure.
158
159config RCU_FANOUT_LEAF
160	int "Tree-based hierarchical RCU leaf-level fanout value"
161	range 2 64 if 64BIT && !RCU_STRICT_GRACE_PERIOD
162	range 2 32 if !64BIT && !RCU_STRICT_GRACE_PERIOD
163	range 2 3 if RCU_STRICT_GRACE_PERIOD
164	depends on TREE_RCU && RCU_EXPERT
165	default 16 if !RCU_STRICT_GRACE_PERIOD
166	default 2 if RCU_STRICT_GRACE_PERIOD
167	help
168	  This option controls the leaf-level fanout of hierarchical
169	  implementations of RCU, and allows trading off cache misses
170	  against lock contention.  Systems that synchronize their
171	  scheduling-clock interrupts for energy-efficiency reasons will
172	  want the default because the smaller leaf-level fanout keeps
173	  lock contention levels acceptably low.  Very large systems
174	  (hundreds or thousands of CPUs) will instead want to set this
175	  value to the maximum value possible in order to reduce the
176	  number of cache misses incurred during RCU's grace-period
177	  initialization.  These systems tend to run CPU-bound, and thus
178	  are not helped by synchronized interrupts, and thus tend to
179	  skew them, which reduces lock contention enough that large
180	  leaf-level fanouts work well.  That said, setting leaf-level
181	  fanout to a large number will likely cause problematic
182	  lock contention on the leaf-level rcu_node structures unless
183	  you boot with the skew_tick kernel parameter.
184
185	  Select a specific number if testing RCU itself.
186
187	  Select the maximum permissible value for large systems, but
188	  please understand that you may also need to set the skew_tick
189	  kernel boot parameter to avoid contention on the rcu_node
190	  structure's locks.
191
192	  Take the default if unsure.
193
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
194config RCU_BOOST
195	bool "Enable RCU priority boosting"
196	depends on (RT_MUTEXES && PREEMPT_RCU && RCU_EXPERT) || PREEMPT_RT
197	default y if PREEMPT_RT
198	help
199	  This option boosts the priority of preempted RCU readers that
200	  block the current preemptible RCU grace period for too long.
201	  This option also prevents heavy loads from blocking RCU
202	  callback invocation.
203
204	  Say Y here if you are working with real-time apps or heavy loads
205	  Say N here if you are unsure.
206
207config RCU_BOOST_DELAY
208	int "Milliseconds to delay boosting after RCU grace-period start"
209	range 0 3000
210	depends on RCU_BOOST
211	default 500
212	help
213	  This option specifies the time to wait after the beginning of
214	  a given grace period before priority-boosting preempted RCU
215	  readers blocking that grace period.  Note that any RCU reader
216	  blocking an expedited RCU grace period is boosted immediately.
217
218	  Accept the default if unsure.
219
220config RCU_EXP_KTHREAD
221	bool "Perform RCU expedited work in a real-time kthread"
222	depends on RCU_BOOST && RCU_EXPERT
223	default !PREEMPT_RT && NR_CPUS <= 32
224	help
225	  Use this option to further reduce the latencies of expedited
226	  grace periods at the expense of being more disruptive.
227
228	  This option is disabled by default on PREEMPT_RT=y kernels which
229	  disable expedited grace periods after boot by unconditionally
230	  setting rcupdate.rcu_normal_after_boot=1.
231
232	  Accept the default if unsure.
233
234config RCU_NOCB_CPU
235	bool "Offload RCU callback processing from boot-selected CPUs"
236	depends on TREE_RCU
237	depends on RCU_EXPERT || NO_HZ_FULL
238	default n
239	help
240	  Use this option to reduce OS jitter for aggressive HPC or
241	  real-time workloads.	It can also be used to offload RCU
242	  callback invocation to energy-efficient CPUs in battery-powered
243	  asymmetric multiprocessors.  The price of this reduced jitter
244	  is that the overhead of call_rcu() increases and that some
245	  workloads will incur significant increases in context-switch
246	  rates.
247
248	  This option offloads callback invocation from the set of CPUs
249	  specified at boot time by the rcu_nocbs parameter.  For each
250	  such CPU, a kthread ("rcuox/N") will be created to invoke
251	  callbacks, where the "N" is the CPU being offloaded, and where
252	  the "x" is "p" for RCU-preempt (PREEMPTION kernels) and "s" for
253	  RCU-sched (!PREEMPTION kernels).  Nothing prevents this kthread
254	  from running on the specified CPUs, but (1) the kthreads may be
255	  preempted between each callback, and (2) affinity or cgroups can
256	  be used to force the kthreads to run on whatever set of CPUs is
257	  desired.
258
259	  Say Y here if you need reduced OS jitter, despite added overhead.
260	  Say N here if you are unsure.
261
262config RCU_NOCB_CPU_DEFAULT_ALL
263	bool "Offload RCU callback processing from all CPUs by default"
264	depends on RCU_NOCB_CPU
265	default n
266	help
267	  Use this option to offload callback processing from all CPUs
268	  by default, in the absence of the rcu_nocbs or nohz_full boot
269	  parameter. This also avoids the need to use any boot parameters
270	  to achieve the effect of offloading all CPUs on boot.
271
272	  Say Y here if you want offload all CPUs by default on boot.
273	  Say N here if you are unsure.
274
275config RCU_NOCB_CPU_CB_BOOST
276	bool "Offload RCU callback from real-time kthread"
277	depends on RCU_NOCB_CPU && RCU_BOOST
278	default y if PREEMPT_RT
279	help
280	  Use this option to invoke offloaded callbacks as SCHED_FIFO
281	  to avoid starvation by heavy SCHED_OTHER background load.
282	  Of course, running as SCHED_FIFO during callback floods will
283	  cause the rcuo[ps] kthreads to monopolize the CPU for hundreds
284	  of milliseconds or more.  Therefore, when enabling this option,
285	  it is your responsibility to ensure that latency-sensitive
286	  tasks either run with higher priority or run on some other CPU.
287
288	  Say Y here if you want to set RT priority for offloading kthreads.
289	  Say N here if you are building a !PREEMPT_RT kernel and are unsure.
290
291config TASKS_TRACE_RCU_READ_MB
292	bool "Tasks Trace RCU readers use memory barriers in user and idle"
293	depends on RCU_EXPERT && TASKS_TRACE_RCU
294	default PREEMPT_RT || NR_CPUS < 8
295	help
296	  Use this option to further reduce the number of IPIs sent
297	  to CPUs executing in userspace or idle during tasks trace
298	  RCU grace periods.  Given that a reasonable setting of
299	  the rcupdate.rcu_task_ipi_delay kernel boot parameter
300	  eliminates such IPIs for many workloads, proper setting
301	  of this Kconfig option is important mostly for aggressive
302	  real-time installations and for battery-powered devices,
303	  hence the default chosen above.
304
305	  Say Y here if you hate IPIs.
306	  Say N here if you hate read-side memory barriers.
307	  Take the default if you are unsure.
308
309config RCU_LAZY
310	bool "RCU callback lazy invocation functionality"
311	depends on RCU_NOCB_CPU
312	default n
313	help
314	  To save power, batch RCU callbacks and flush after delay, memory
315	  pressure, or callback list growing too big.
316
317	  Requires rcu_nocbs=all to be set.
318
319	  Use rcutree.enable_rcu_lazy=0 to turn it off at boot time.
320
321config RCU_LAZY_DEFAULT_OFF
322	bool "Turn RCU lazy invocation off by default"
323	depends on RCU_LAZY
324	default n
325	help
326	  Allows building the kernel with CONFIG_RCU_LAZY=y yet keep it default
327	  off. Boot time param rcutree.enable_rcu_lazy=1 can be used to switch
328	  it back on.
329
330config RCU_DOUBLE_CHECK_CB_TIME
331	bool "RCU callback-batch backup time check"
332	depends on RCU_EXPERT
333	default n
334	help
335	  Use this option to provide more precise enforcement of the
336	  rcutree.rcu_resched_ns module parameter in situations where
337	  a single RCU callback might run for hundreds of microseconds,
338	  thus defeating the 32-callback batching used to amortize the
339	  cost of the fine-grained but expensive local_clock() function.
340
341	  This option rounds rcutree.rcu_resched_ns up to the next
342	  jiffy, and overrides the 32-callback batching if this limit
343	  is exceeded.
344
345	  Say Y here if you need tighter callback-limit enforcement.
346	  Say N here if you are unsure.
347
348endmenu # "RCU Subsystem"

 
  1#
  2# RCU-related configuration options
  3#
  4
  5menu "RCU Subsystem"
  6
  7config TREE_RCU
  8	bool
  9	default y if !PREEMPT && SMP
 
 
 10	help
 11	  This option selects the RCU implementation that is
 12	  designed for very large SMP system with hundreds or
 13	  thousands of CPUs.  It also scales down nicely to
 14	  smaller systems.
 15
 16config PREEMPT_RCU
 17	bool
 18	default y if PREEMPT
 
 19	help
 20	  This option selects the RCU implementation that is
 21	  designed for very large SMP systems with hundreds or
 22	  thousands of CPUs, but for which real-time response
 23	  is also required.  It also scales down nicely to
 24	  smaller systems.
 25
 26	  Select this option if you are unsure.
 27
 28config TINY_RCU
 29	bool
 30	default y if !PREEMPT && !SMP
 31	help
 32	  This option selects the RCU implementation that is
 33	  designed for UP systems from which real-time response
 34	  is not required.  This option greatly reduces the
 35	  memory footprint of RCU.
 36
 37config RCU_EXPERT
 38	bool "Make expert-level adjustments to RCU configuration"
 39	default n
 40	help
 41	  This option needs to be enabled if you wish to make
 42	  expert-level adjustments to RCU configuration.  By default,
 43	  no such adjustments can be made, which has the often-beneficial
 44	  side-effect of preventing "make oldconfig" from asking you all
 45	  sorts of detailed questions about how you would like numerous
 46	  obscure RCU options to be set up.
 47
 48	  Say Y if you need to make expert-level adjustments to RCU.
 49
 50	  Say N if you are unsure.
 51
 52config SRCU
 53	bool
 54	help
 55	  This option selects the sleepable version of RCU. This version
 56	  permits arbitrary sleeping or blocking within RCU read-side critical
 57	  sections.
 58
 59config TINY_SRCU
 60	bool
 61	default y if SRCU && 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 SRCU && !TINY_RCU
 68	help
 69	  This option selects the full-fledged version of SRCU.
 70
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 71config TASKS_RCU
 72	def_bool PREEMPT
 73	select SRCU
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 74	help
 75	  This option enables a task-based RCU implementation that uses
 76	  only voluntary context switch (not preemption!), idle, and
 77	  user-mode execution as quiescent states.
 
 
 
 
 
 
 
 
 78
 79config RCU_STALL_COMMON
 80	def_bool ( TREE_RCU || PREEMPT_RCU )
 81	help
 82	  This option enables RCU CPU stall code that is common between
 83	  the TINY and TREE variants of RCU.  The purpose is to allow
 84	  the tiny variants to disable RCU CPU stall warnings, while
 85	  making these warnings mandatory for the tree variants.
 86
 87config RCU_NEED_SEGCBLIST
 88	def_bool ( TREE_RCU || PREEMPT_RCU || TREE_SRCU )
 89
 90config CONTEXT_TRACKING
 91       bool
 92
 93config CONTEXT_TRACKING_FORCE
 94	bool "Force context tracking"
 95	depends on CONTEXT_TRACKING
 96	default y if !NO_HZ_FULL
 97	help
 98	  The major pre-requirement for full dynticks to work is to
 99	  support the context tracking subsystem. But there are also
100	  other dependencies to provide in order to make the full
101	  dynticks working.
102
103	  This option stands for testing when an arch implements the
104	  context tracking backend but doesn't yet fullfill all the
105	  requirements to make the full dynticks feature working.
106	  Without the full dynticks, there is no way to test the support
107	  for context tracking and the subsystems that rely on it: RCU
108	  userspace extended quiescent state and tickless cputime
109	  accounting. This option copes with the absence of the full
110	  dynticks subsystem by forcing the context tracking on all
111	  CPUs in the system.
112
113	  Say Y only if you're working on the development of an
114	  architecture backend for the context tracking.
115
116	  Say N otherwise, this option brings an overhead that you
117	  don't want in production.
118
119
120config RCU_FANOUT
121	int "Tree-based hierarchical RCU fanout value"
122	range 2 64 if 64BIT
123	range 2 32 if !64BIT
124	depends on (TREE_RCU || PREEMPT_RCU) && RCU_EXPERT
125	default 64 if 64BIT
126	default 32 if !64BIT
127	help
128	  This option controls the fanout of hierarchical implementations
129	  of RCU, allowing RCU to work efficiently on machines with
130	  large numbers of CPUs.  This value must be at least the fourth
131	  root of NR_CPUS, which allows NR_CPUS to be insanely large.
132	  The default value of RCU_FANOUT should be used for production
133	  systems, but if you are stress-testing the RCU implementation
134	  itself, small RCU_FANOUT values allow you to test large-system
135	  code paths on small(er) systems.
136
137	  Select a specific number if testing RCU itself.
138	  Take the default if unsure.
139
140config RCU_FANOUT_LEAF
141	int "Tree-based hierarchical RCU leaf-level fanout value"
142	range 2 64 if 64BIT
143	range 2 32 if !64BIT
144	depends on (TREE_RCU || PREEMPT_RCU) && RCU_EXPERT
145	default 16
 
 
146	help
147	  This option controls the leaf-level fanout of hierarchical
148	  implementations of RCU, and allows trading off cache misses
149	  against lock contention.  Systems that synchronize their
150	  scheduling-clock interrupts for energy-efficiency reasons will
151	  want the default because the smaller leaf-level fanout keeps
152	  lock contention levels acceptably low.  Very large systems
153	  (hundreds or thousands of CPUs) will instead want to set this
154	  value to the maximum value possible in order to reduce the
155	  number of cache misses incurred during RCU's grace-period
156	  initialization.  These systems tend to run CPU-bound, and thus
157	  are not helped by synchronized interrupts, and thus tend to
158	  skew them, which reduces lock contention enough that large
159	  leaf-level fanouts work well.  That said, setting leaf-level
160	  fanout to a large number will likely cause problematic
161	  lock contention on the leaf-level rcu_node structures unless
162	  you boot with the skew_tick kernel parameter.
163
164	  Select a specific number if testing RCU itself.
165
166	  Select the maximum permissible value for large systems, but
167	  please understand that you may also need to set the skew_tick
168	  kernel boot parameter to avoid contention on the rcu_node
169	  structure's locks.
170
171	  Take the default if unsure.
172
173config RCU_FAST_NO_HZ
174	bool "Accelerate last non-dyntick-idle CPU's grace periods"
175	depends on NO_HZ_COMMON && SMP && RCU_EXPERT
176	default n
177	help
178	  This option permits CPUs to enter dynticks-idle state even if
179	  they have RCU callbacks queued, and prevents RCU from waking
180	  these CPUs up more than roughly once every four jiffies (by
181	  default, you can adjust this using the rcutree.rcu_idle_gp_delay
182	  parameter), thus improving energy efficiency.  On the other
183	  hand, this option increases the duration of RCU grace periods,
184	  for example, slowing down synchronize_rcu().
185
186	  Say Y if energy efficiency is critically important, and you
187	  	don't care about increased grace-period durations.
188
189	  Say N if you are unsure.
190
191config RCU_BOOST
192	bool "Enable RCU priority boosting"
193	depends on RT_MUTEXES && PREEMPT_RCU && RCU_EXPERT
194	default n
195	help
196	  This option boosts the priority of preempted RCU readers that
197	  block the current preemptible RCU grace period for too long.
198	  This option also prevents heavy loads from blocking RCU
199	  callback invocation for all flavors of RCU.
200
201	  Say Y here if you are working with real-time apps or heavy loads
202	  Say N here if you are unsure.
203
204config RCU_BOOST_DELAY
205	int "Milliseconds to delay boosting after RCU grace-period start"
206	range 0 3000
207	depends on RCU_BOOST
208	default 500
209	help
210	  This option specifies the time to wait after the beginning of
211	  a given grace period before priority-boosting preempted RCU
212	  readers blocking that grace period.  Note that any RCU reader
213	  blocking an expedited RCU grace period is boosted immediately.
214
215	  Accept the default if unsure.
216
 
 
 
 
 
 
 
 
 
 
 
 
 
 
217config RCU_NOCB_CPU
218	bool "Offload RCU callback processing from boot-selected CPUs"
219	depends on TREE_RCU || PREEMPT_RCU
220	depends on RCU_EXPERT || NO_HZ_FULL
221	default n
222	help
223	  Use this option to reduce OS jitter for aggressive HPC or
224	  real-time workloads.	It can also be used to offload RCU
225	  callback invocation to energy-efficient CPUs in battery-powered
226	  asymmetric multiprocessors.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
227
228	  This option offloads callback invocation from the set of
229	  CPUs specified at boot time by the rcu_nocbs parameter.
230	  For each such CPU, a kthread ("rcuox/N") will be created to
231	  invoke callbacks, where the "N" is the CPU being offloaded,
232	  and where the "x" is "b" for RCU-bh, "p" for RCU-preempt, and
233	  "s" for RCU-sched.  Nothing prevents this kthread from running
234	  on the specified CPUs, but (1) the kthreads may be preempted
235	  between each callback, and (2) affinity or cgroups can be used
236	  to force the kthreads to run on whatever set of CPUs is desired.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
237
238	  Say Y here if you want to help to debug reduced OS jitter.
239	  Say N here if you are unsure.
240
241endmenu # "RCU Subsystem"