Linus Torvalds 1d6d399223 Kthreads affinity follow either of 4 existing different patterns: ... 1) Per-CPU kthreads must stay affine to a single CPU and never execute relevant code on any other CPU. This is currently handled by smpboot code which takes care of CPU-hotplug operations. Affinity here is a correctness constraint. 2) Some kthreads _have_ to be affine to a specific set of CPUs and can't run anywhere else. The affinity is set through kthread_bind_mask() and the subsystem takes care by itself to handle CPU-hotplug operations. Affinity here is assumed to be a correctness constraint. 3) Per-node kthreads _prefer_ to be affine to a specific NUMA node. This is not a correctness constraint but merely a preference in terms of memory locality. kswapd and kcompactd both fall into this category. The affinity is set manually like for any other task and CPU-hotplug is supposed to be handled by the relevant subsystem so that the task is properly reaffined whenever a given CPU from the node comes up. Also care should be taken so that the node affinity doesn't cross isolated (nohz_full) cpumask boundaries. 4) Similar to the previous point except kthreads have a _preferred_ affinity different than a node. Both RCU boost kthreads and RCU exp kworkers fall into this category as they refer to "RCU nodes" from a distinctly distributed tree. Currently the preferred affinity patterns (3 and 4) have at least 4 identified users, with more or less success when it comes to handle CPU-hotplug operations and CPU isolation. Each of which do it in its own ad-hoc way. This is an infrastructure proposal to handle this with the following API changes: _ kthread_create_on_node() automatically affines the created kthread to its target node unless it has been set as per-cpu or bound with kthread_bind[_mask]() before the first wake-up. - kthread_affine_preferred() is a new function that can be called right after kthread_create_on_node() to specify a preferred affinity different than the specified node. When the preferred affinity can't be applied because the possible targets are offline or isolated (nohz_full), the kthread is affine to the housekeeping CPUs (which means to all online CPUs most of the time or only the non-nohz_full CPUs when nohz_full= is set). kswapd, kcompactd, RCU boost kthreads and RCU exp kworkers have been converted, along with a few old drivers. Summary of the changes: * Consolidate a bunch of ad-hoc implementations of kthread_run_on_cpu() * Introduce task_cpu_fallback_mask() that defines the default last resort affinity of a task to become nohz_full aware * Add some correctness check to ensure kthread_bind() is always called before the first kthread wake up. * Default affine kthread to its preferred node. * Convert kswapd / kcompactd and remove their halfway working ad-hoc affinity implementation * Implement kthreads preferred affinity * Unify kthread worker and kthread API's style * Convert RCU kthreads to the new API and remove the ad-hoc affinity implementation. -----BEGIN PGP SIGNATURE----- iQIzBAABCAAdFiEEd76+gtGM8MbftQlOhSRUR1COjHcFAmeNf8gACgkQhSRUR1CO jHedQQ/+IxTjjqQiItzrq41TES2S0desHDq8lNJFb7rsR/DtKFyLx3s67cOYV+cM Yx54QHg2m/Fz4nXMQ7Po5ygOtJGCKBc5C5QQy7y0lVKeTQK+daDfEtBSa3oG7j3C u+E3tTY6qxkbCzymUyaKkHN4/ay2vLvjFS50luV7KMyI3x47Aji+t7VdCX4LCPP2 eAwOALWD0+7qLJ/VF6gsmQLKA4Qx7PQAzBa3KSBmUN9UcN8Gk1bQHCTIQKDHP9LQ v8BXrNZtYX1o2+snNYpX2z6/ECjxkdwriOgqqZY5306hd9RAQ1u46Dx3byrIqjGn ULG/XQ2istPyhTqb/h+RbrobdOcwEUIeqk8hRRbBXE8bPpqUz9EMuaCMxWDbQjgH NTuKG4ifKJ/IqstkkuDkdOiByE/ysMmwqrTXgSnu2ITNL9yY3BEgFbvA95hgo42s f7QCxEfZb1MHcNEMENSMwM3xw5lLMGMpxVZcMQ3gLwyotMBRrhFZm1qZJG7TITYW IDIeCbH4JOMdQwLs3CcWTXio0N5/85NhRNFV+IDn96OrgxObgnMtV8QwNgjXBAJ5 wGeJWt8s34W1Zo3qS9gEuVzEhW4XaxISQQMkHe8faKkK6iHmIB/VjSQikDwwUNQ/ AspYj82RyWBCDZsqhiYh71kpxjvS6Xp0bj39Ce1sNsOnuksxKkQ= =g8In -----END PGP SIGNATURE----- Merge tag 'kthread-for-6.14-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/frederic/linux-dynticks Pull kthread updates from Frederic Weisbecker: "Kthreads affinity follow either of 4 existing different patterns: 1) Per-CPU kthreads must stay affine to a single CPU and never execute relevant code on any other CPU. This is currently handled by smpboot code which takes care of CPU-hotplug operations. Affinity here is a correctness constraint. 2) Some kthreads _have_ to be affine to a specific set of CPUs and can't run anywhere else. The affinity is set through kthread_bind_mask() and the subsystem takes care by itself to handle CPU-hotplug operations. Affinity here is assumed to be a correctness constraint. 3) Per-node kthreads _prefer_ to be affine to a specific NUMA node. This is not a correctness constraint but merely a preference in terms of memory locality. kswapd and kcompactd both fall into this category. The affinity is set manually like for any other task and CPU-hotplug is supposed to be handled by the relevant subsystem so that the task is properly reaffined whenever a given CPU from the node comes up. Also care should be taken so that the node affinity doesn't cross isolated (nohz_full) cpumask boundaries. 4) Similar to the previous point except kthreads have a _preferred_ affinity different than a node. Both RCU boost kthreads and RCU exp kworkers fall into this category as they refer to "RCU nodes" from a distinctly distributed tree. Currently the preferred affinity patterns (3 and 4) have at least 4 identified users, with more or less success when it comes to handle CPU-hotplug operations and CPU isolation. Each of which do it in its own ad-hoc way. This is an infrastructure proposal to handle this with the following API changes: - kthread_create_on_node() automatically affines the created kthread to its target node unless it has been set as per-cpu or bound with kthread_bind[_mask]() before the first wake-up. - kthread_affine_preferred() is a new function that can be called right after kthread_create_on_node() to specify a preferred affinity different than the specified node. When the preferred affinity can't be applied because the possible targets are offline or isolated (nohz_full), the kthread is affine to the housekeeping CPUs (which means to all online CPUs most of the time or only the non-nohz_full CPUs when nohz_full= is set). kswapd, kcompactd, RCU boost kthreads and RCU exp kworkers have been converted, along with a few old drivers. Summary of the changes: - Consolidate a bunch of ad-hoc implementations of kthread_run_on_cpu() - Introduce task_cpu_fallback_mask() that defines the default last resort affinity of a task to become nohz_full aware - Add some correctness check to ensure kthread_bind() is always called before the first kthread wake up. - Default affine kthread to its preferred node. - Convert kswapd / kcompactd and remove their halfway working ad-hoc affinity implementation - Implement kthreads preferred affinity - Unify kthread worker and kthread API's style - Convert RCU kthreads to the new API and remove the ad-hoc affinity implementation" * tag 'kthread-for-6.14-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/frederic/linux-dynticks: kthread: modify kernel-doc function name to match code rcu: Use kthread preferred affinity for RCU exp kworkers treewide: Introduce kthread_run_worker[_on_cpu]() kthread: Unify kthread_create_on_cpu() and kthread_create_worker_on_cpu() automatic format rcu: Use kthread preferred affinity for RCU boost kthread: Implement preferred affinity mm: Create/affine kswapd to its preferred node mm: Create/affine kcompactd to its preferred node kthread: Default affine kthread to its preferred NUMA node kthread: Make sure kthread hasn't started while binding it sched,arm64: Handle CPU isolation on last resort fallback rq selection arm64: Exclude nohz_full CPUs from 32bits el0 support lib: test_objpool: Use kthread_run_on_cpu() kallsyms: Use kthread_run_on_cpu() soc/qman: test: Use kthread_run_on_cpu() arm/bL_switcher: Use kthread_run_on_cpu()		2025-01-21 17:10:05 -08:00
..
bpf
cgroup	drm next for 6.14-rc1	2025-01-21 16:09:47 -08:00
configs
debug
dma
entry
events
futex
gcov
irq	Updates for the interrupt subsystem:	2025-01-21 13:51:07 -08:00
kcsan
livepatch
locking	RCU pull request for v6.14	2025-01-21 14:39:21 -08:00
module
power
printk
rcu	Kthreads affinity follow either of 4 existing different patterns:	2025-01-21 17:10:05 -08:00
sched	Kthreads affinity follow either of 4 existing different patterns:	2025-01-21 17:10:05 -08:00
time	Updates for timers and timekeeping:	2025-01-21 13:16:00 -08:00
trace	ftrace updates for v6.14:	2025-01-21 15:15:28 -08:00
.gitignore
acct.c
async.c
audit.c
audit.h
audit_fsnotify.c
audit_tree.c
audit_watch.c
auditfilter.c
auditsc.c
backtracetest.c
bounds.c
capability.c
cfi.c
compat.c
configs.c
context_tracking.c
cpu.c
cpu_pm.c
crash_core.c
crash_reserve.c
cred.c
delayacct.c
dma.c
elfcorehdr.c
exec_domain.c
exit.c
exit.h
extable.c
fail_function.c
fork.c
freezer.c
gen_kheaders.sh
groups.c
hung_task.c
iomem.c
irq_work.c
jump_label.c
kallsyms.c
kallsyms_internal.h
kallsyms_selftest.c
kallsyms_selftest.h
kcmp.c
Kconfig.freezer
Kconfig.hz
Kconfig.kexec
Kconfig.locks
Kconfig.preempt
kcov.c
kexec.c
kexec_core.c
kexec_elf.c
kexec_file.c
kexec_internal.h
kheaders.c
kprobes.c
ksyms_common.c
ksysfs.c
kthread.c	Kthreads affinity follow either of 4 existing different patterns:	2025-01-21 17:10:05 -08:00
latencytop.c
Makefile
module_signature.c
notifier.c
nsproxy.c
padata.c
panic.c
params.c
pid.c
pid_namespace.c
pid_sysctl.h
profile.c
ptrace.c
range.c
reboot.c
regset.c
relay.c
resource.c
resource_kunit.c
rseq.c
scftorture.c
scs.c
seccomp.c
signal.c
smp.c
smpboot.c
smpboot.h
softirq.c
stackleak.c
stacktrace.c
static_call.c
static_call_inline.c
stop_machine.c
sys.c
sys_ni.c
sysctl-test.c
sysctl.c
task_work.c
taskstats.c
torture.c
tracepoint.c
tsacct.c
ucount.c
uid16.c
uid16.h
umh.c
up.c
user-return-notifier.c
user.c
user_namespace.c
usermode_driver.c
utsname.c
utsname_sysctl.c
vhost_task.c
vmcore_info.c
watch_queue.c
watchdog.c
watchdog_buddy.c
watchdog_perf.c
workqueue.c	Kthreads affinity follow either of 4 existing different patterns:	2025-01-21 17:10:05 -08:00
workqueue_internal.h