Joel Fernandes (Google) 49903f70d7 sched/rt: Fix live lock between select_fallback_rq() and RT push ... commit fc09027786c900368de98d03d40af058bcb01ad9 upstream. During RCU-boost testing with the TREE03 rcutorture config, I found that after a few hours, the machine locks up. On tracing, I found that there is a live lock happening between 2 CPUs. One CPU has an RT task running, while another CPU is being offlined which also has an RT task running. During this offlining, all threads are migrated. The migration thread is repeatedly scheduled to migrate actively running tasks on the CPU being offlined. This results in a live lock because select_fallback_rq() keeps picking the CPU that an RT task is already running on only to get pushed back to the CPU being offlined. It is anyway pointless to pick CPUs for pushing tasks to if they are being offlined only to get migrated away to somewhere else. This could also add unwanted latency to this task. Fix these issues by not selecting CPUs in RT if they are not 'active' for scheduling, using the cpu_active_mask. Other parts in core.c already use cpu_active_mask to prevent tasks from being put on CPUs going offline. With this fix I ran the tests for days and could not reproduce the hang. Without the patch, I hit it in a few hours. Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org> Signed-off-by: Ingo Molnar <mingo@kernel.org> Tested-by: Paul E. McKenney <paulmck@kernel.org> Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20230923011409.3522762-1-joel@joelfernandes.org Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>		2023-10-06 14:57:02 +02:00
..
bpf	bpf: Avoid deadlock when using queue and stack maps from NMI	2023-10-06 14:56:35 +02:00
cgroup	cgroup:namespace: Remove unused cgroup_namespaces_init()	2023-09-13 09:42:56 +02:00
configs	Kbuild: add Rust support	2022-09-28 09:02:20 +02:00
debug	mm: remove vmacache	2022-09-26 19:46:18 -07:00
dma	dma-debug: don't call __dma_entry_alloc_check_leak() under free_entries_lock	2023-10-06 14:56:50 +02:00
entry	entry/rcu: Check TIF_RESCHED _after_ delayed RCU wake-up	2023-03-30 12:49:13 +02:00
events	perf: Fix function pointer case	2023-08-11 12:08:09 +02:00
futex	futex: Fix futex_waitv() hrtimer debug object leak on kcalloc error	2023-01-04 11:28:58 +01:00
gcov	gcov: add support for checksum field	2022-12-31 13:33:11 +01:00
irq	x86/pci/xen: populate MSI sysfs entries	2023-05-30 14:03:22 +01:00
kcsan	kcsan: Don't expect 64 bits atomic builtins from 32 bits architectures	2023-07-19 16:21:37 +02:00
livepatch	Livepatching changes for 6.1	2022-10-10 11:36:19 -07:00
locking	lockdep: fix static memory detection even more	2023-09-02 09:16:19 +02:00
module	modules: only allow symbol_get of EXPORT_SYMBOL_GPL modules	2023-09-06 21:27:00 +01:00
power	PM: QoS: Restore support for default value on frequency QoS	2023-07-23 13:49:45 +02:00
printk	printk: Consolidate console deferred printing	2023-09-23 11:11:07 +02:00
rcu	rcuscale: Move rcu_scale_writer() schedule_timeout_uninterruptible() to _idle()	2023-09-23 11:11:00 +02:00
sched	sched/rt: Fix live lock between select_fallback_rq() and RT push	2023-10-06 14:57:02 +02:00
time	tick/rcu: Fix false positive "softirq work is pending" messages	2023-09-13 09:42:57 +02:00
trace	ring-buffer: Do not attempt to read past "commit"	2023-10-06 14:56:53 +02:00
.gitignore
acct.c	acct: fix potential integer overflow in encode_comp_t()	2022-12-31 13:32:58 +01:00
async.c
audit.c	audit: use time_after to compare time	2022-08-29 19:47:03 -04:00
audit.h	audit: remove selinux_audit_rule_update() declaration	2022-09-07 11:30:15 -04:00
audit_fsnotify.c	audit: fix potential double free on error path from fsnotify_add_inode_mark	2022-08-22 18:50:06 -04:00
audit_tree.c
audit_watch.c	audit_init_parent(): constify path	2022-09-01 17:39:30 -04:00
auditfilter.c
auditsc.c	audit: fix possible soft lockup in __audit_inode_child()	2023-09-13 09:42:42 +02:00
backtracetest.c
bounds.c	mm: multi-gen LRU: minimal implementation	2022-09-26 19:46:09 -07:00
capability.c
cfi.c	cfi: Switch to -fsanitize=kcfi	2022-09-26 10:13:13 -07:00
compat.c	sched_getaffinity: don't assume 'cpumask_size()' is fully initialized	2023-04-06 12:10:40 +02:00
configs.c
context_tracking.c	context_tracking: Fix noinstr vs KASAN	2023-03-10 09:33:45 +01:00
cpu.c	cpu/hotplug: Prevent self deadlock on CPU hot-unplug	2023-09-13 09:43:00 +02:00
cpu_pm.c	context_tracking: Take IRQ eqs entrypoints over RCU	2022-07-05 13:32:59 -07:00
crash_core.c	vmcoreinfo: add kallsyms_num_syms symbol	2022-08-28 14:02:44 -07:00
crash_dump.c
cred.c
delayacct.c	delayacct: support re-entrance detection of thrashing accounting	2022-09-26 19:46:07 -07:00
dma.c
exec_domain.c
exit.c	exit: Detect and fix irq disabled state in oops	2023-03-10 09:33:45 +01:00
extable.c	context_tracking: Take NMI eqs entrypoints over RCU	2022-07-05 13:32:59 -07:00
fail_function.c	kernel/fail_function: fix memory leak with using debugfs_lookup()	2023-03-11 13:55:39 +01:00
fork.c	kernel/fork: beware of __put_task_struct() calling context	2023-09-23 11:11:00 +02:00
freezer.c	freezer,sched: Rewrite core freezer logic	2022-09-07 21:53:50 +02:00
gen_kheaders.sh	kbuild: build init/built-in.a just once	2022-09-29 04:40:15 +09:00
groups.c	security: Add LSM hook to setgroups() syscall	2022-07-15 18:21:49 +00:00
hung_task.c	sched: Fix more TASK_state comparisons	2022-09-30 16:50:39 +02:00
iomem.c
irq_work.c
jump_label.c	jump_label: make initial NOP patching the special case	2022-06-24 09:48:55 +02:00
kallsyms.c	kallsyms: Fix kallsyms_selftest failure	2023-09-02 09:16:19 +02:00
kallsyms_internal.h	kallsyms: Improve the performance of kallsyms_lookup_name()	2023-07-27 08:50:39 +02:00
kcmp.c
Kconfig.freezer
Kconfig.hz
Kconfig.locks
Kconfig.preempt
kcov.c	kcov: kmsan: unpoison area->list in kcov_remote_area_put()	2022-10-03 14:03:23 -07:00
kexec.c	panic, kexec: make __crash_kexec() NMI safe	2022-09-11 21:55:06 -07:00
kexec_core.c	kexec: fix a memory leak in crash_shrink_memory()	2023-07-19 16:21:08 +02:00
kexec_elf.c
kexec_file.c	kexec: support purgatories with .text.hot sections	2023-06-21 16:00:55 +02:00
kexec_internal.h	panic, kexec: make __crash_kexec() NMI safe	2022-09-11 21:55:06 -07:00
kheaders.c	kheaders: Use array declaration instead of char	2023-05-11 23:03:02 +09:00
kmod.c
kprobes.c	kprobes: Prohibit probing on CFI preamble symbol	2023-09-13 09:42:23 +02:00
ksysfs.c	kexec: turn all kexec_mutex acquisitions into trylocks	2022-09-11 21:55:06 -07:00
kthread.c	signal: break out of wait loops on kthread_stop()	2022-10-09 16:01:59 -07:00
latencytop.c	latencytop: use the last element of latency_record of system	2022-09-11 21:55:12 -07:00
Makefile	cfi: Fix CFI failure with KASAN	2022-12-31 13:33:08 +01:00
module_signature.c
notifier.c
nsproxy.c	Revert "fs/exec: allow to unshare a time namespace on vfork+exec"	2022-09-13 10:38:43 -07:00
padata.c	padata: Fix list iterator in padata_do_serial()	2022-12-31 13:32:34 +01:00
panic.c	panic: Reenable preemption in WARN slowpath	2023-09-23 11:11:09 +02:00
params.c
pid.c	gfs2: Add glockfd debugfs file	2022-06-29 13:07:16 +02:00
pid_namespace.c	rcu-tasks: Fix synchronize_rcu_tasks() VS zap_pid_ns_processes()	2023-03-10 09:32:52 +01:00
profile.c	kernel/profile.c: simplify duplicated code in profile_setup()	2022-09-11 21:55:12 -07:00
ptrace.c	freezer,sched: Rewrite core freezer logic	2022-09-07 21:53:50 +02:00
range.c
reboot.c	kernel/reboot: Add SYS_OFF_MODE_RESTART_PREPARE mode	2022-10-04 15:59:36 +02:00
regset.c
relay.c	relayfs: fix out-of-bounds access in relay_file_read	2023-05-11 23:03:03 +09:00
resource.c	PCI: Allow drivers to request exclusive config regions	2023-09-13 09:42:46 +02:00
resource_kunit.c
rseq.c	rseq: Use pr_warn_once() when deprecated/unknown ABI flags are encountered	2022-11-14 09:58:32 +01:00
scftorture.c	scftorture: Forgive memory-allocation failure if KASAN	2023-09-23 11:11:00 +02:00
scs.c
seccomp.c
signal.c	mm: suppress mm fault logging if fatal signal already pending	2023-08-03 10:24:01 +02:00
smp.c	bitmap patches for v6.1-rc1	2022-10-10 12:49:34 -07:00
smpboot.c	smpboot: use atomic_try_cmpxchg in cpu_wait_death and cpu_report_death	2022-09-11 21:55:10 -07:00
smpboot.h
softirq.c	context_tracking: Take IRQ eqs entrypoints over RCU	2022-07-05 13:32:59 -07:00
stackleak.c
stacktrace.c
static_call.c
static_call_inline.c
stop_machine.c
sys.c	kernel/sys.c: fix and improve control flow in __sys_setres[ug]id()	2023-04-26 14:28:39 +02:00
sys_ni.c	kernel/sys_ni: add compat entry for fadvise64_64	2022-08-20 15:17:45 -07:00
sysctl-test.c	kernel/sysctl-test: use SYSCTL_{ZERO/ONE_HUNDRED} instead of i_{zero/one_hundred}	2022-09-08 16:56:45 -07:00
sysctl.c	proc: proc_skip_spaces() shouldn't think it is working on C strings	2022-12-05 12:09:06 -08:00
task_work.c	task_work: use try_cmpxchg in task_work_add, task_work_cancel_match and task_work_run	2022-09-11 21:55:10 -07:00
taskstats.c	genetlink: start to validate reserved header bytes	2022-08-29 12:47:15 +01:00
torture.c	torture: Fix hang during kthread shutdown phase	2023-03-10 09:34:07 +01:00
tracepoint.c	tracepoint: Optimize the critical region of mutex_lock in tracepoint_module_coming()	2022-09-26 13:01:18 -04:00
tsacct.c
ucount.c
uid16.c
uid16.h
umh.c	freezer,umh: Fix call_usermode_helper_exec() vs SIGKILL	2023-02-22 12:59:50 +01:00
up.c
user-return-notifier.c
user.c
user_namespace.c	ucounts: Split rlimit and ucount values and max values	2022-10-09 16:24:05 -07:00
usermode_driver.c
utsname.c
utsname_sysctl.c	kernel/utsname_sysctl.c: Fix hostname polling	2022-10-23 12:01:01 -07:00
watch_queue.c	watch_queue: prevent dangling pipe pointer	2023-07-19 16:22:10 +02:00
watchdog.c	powerpc updates for 6.0	2022-08-06 16:38:17 -07:00
watchdog_hld.c	watchdog/perf: more properly prevent false positives with turbo modes	2023-07-19 16:21:08 +02:00
workqueue.c	workqueue: clean up WORK_* constant types, clarify masking	2023-07-23 13:49:19 +02:00
workqueue_internal.h