mirror of
https://github.com/torvalds/linux
synced 2024-11-05 18:23:50 +00:00
a7c8655b07
Commit6f1982fedd("sched/isolation: Handle the nohz_full= parameter") broke CONFIG_NO_HZ_FULL_ALL=y kernels. This breakage is due to the code under CONFIG_NO_HZ_FULL_ALL failing to invoke the shiny new housekeeping functions. This means that rcutorture scenario TREE04 now emits RCU CPU stall warnings due to the RCU grace-period kthreads not being awakened at a time of their choosing, or perhaps even not at all: [ 27.731422] rcu_bh kthread starved for 21001 jiffies! g18446744073709551369 c18446744073709551368 f0x0 RCU_GP_WAIT_FQS(3) ->state=0x402 ->cpu=3 [ 27.731423] rcu_bh I14936 9 2 0x80080000 [ 27.731435] Call Trace: [ 27.731440] __schedule+0x31a/0x6d0 [ 27.731442] schedule+0x31/0x80 [ 27.731446] schedule_timeout+0x15a/0x320 [ 27.731453] ? call_timer_fn+0x130/0x130 [ 27.731457] rcu_gp_kthread+0x66c/0xea0 [ 27.731458] ? rcu_gp_kthread+0x66c/0xea0 Because no one has complained about CONFIG_NO_HZ_FULL_ALL=y being broken, I hypothesize that no one is in fact using it, other than rcutorture. This commit therefore eliminates CONFIG_NO_HZ_FULL_ALL and updates rcutorture's config files to instead use the nohz_full= kernel parameter to put the desired CPUs into nohz_full mode. Fixes:6f1982fedd("sched/isolation: Handle the nohz_full= parameter") Reported-by: kernel test robot <xiaolong.ye@intel.com> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Frederic Weisbecker <frederic@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Chris Metcalf <cmetcalf@mellanox.com> Cc: Christoph Lameter <cl@linux.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Luiz Capitulino <lcapitulino@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@redhat.com> Cc: Wanpeng Li <kernellwp@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: John Stultz <john.stultz@linaro.org> Cc: Jonathan Corbet <corbet@lwn.net>
134 lines
3.5 KiB
Text
134 lines
3.5 KiB
Text
#
|
|
# Timer subsystem related configuration options
|
|
#
|
|
|
|
# Options selectable by arch Kconfig
|
|
|
|
# Watchdog function for clocksources to detect instabilities
|
|
config CLOCKSOURCE_WATCHDOG
|
|
bool
|
|
|
|
# Architecture has extra clocksource data
|
|
config ARCH_CLOCKSOURCE_DATA
|
|
bool
|
|
|
|
# Clocksources require validation of the clocksource against the last
|
|
# cycle update - x86/TSC misfeature
|
|
config CLOCKSOURCE_VALIDATE_LAST_CYCLE
|
|
bool
|
|
|
|
# Timekeeping vsyscall support
|
|
config GENERIC_TIME_VSYSCALL
|
|
bool
|
|
|
|
# Old style timekeeping
|
|
config ARCH_USES_GETTIMEOFFSET
|
|
bool
|
|
|
|
# The generic clock events infrastructure
|
|
config GENERIC_CLOCKEVENTS
|
|
bool
|
|
|
|
# Architecture can handle broadcast in a driver-agnostic way
|
|
config ARCH_HAS_TICK_BROADCAST
|
|
bool
|
|
|
|
# Clockevents broadcasting infrastructure
|
|
config GENERIC_CLOCKEVENTS_BROADCAST
|
|
bool
|
|
depends on GENERIC_CLOCKEVENTS
|
|
|
|
# Automatically adjust the min. reprogramming time for
|
|
# clock event device
|
|
config GENERIC_CLOCKEVENTS_MIN_ADJUST
|
|
bool
|
|
|
|
# Generic update of CMOS clock
|
|
config GENERIC_CMOS_UPDATE
|
|
bool
|
|
|
|
if GENERIC_CLOCKEVENTS
|
|
menu "Timers subsystem"
|
|
|
|
# Core internal switch. Selected by NO_HZ_COMMON / HIGH_RES_TIMERS. This is
|
|
# only related to the tick functionality. Oneshot clockevent devices
|
|
# are supported independent of this.
|
|
config TICK_ONESHOT
|
|
bool
|
|
|
|
config NO_HZ_COMMON
|
|
bool
|
|
depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS
|
|
select TICK_ONESHOT
|
|
|
|
choice
|
|
prompt "Timer tick handling"
|
|
default NO_HZ_IDLE if NO_HZ
|
|
|
|
config HZ_PERIODIC
|
|
bool "Periodic timer ticks (constant rate, no dynticks)"
|
|
help
|
|
This option keeps the tick running periodically at a constant
|
|
rate, even when the CPU doesn't need it.
|
|
|
|
config NO_HZ_IDLE
|
|
bool "Idle dynticks system (tickless idle)"
|
|
depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS
|
|
select NO_HZ_COMMON
|
|
help
|
|
This option enables a tickless idle system: timer interrupts
|
|
will only trigger on an as-needed basis when the system is idle.
|
|
This is usually interesting for energy saving.
|
|
|
|
Most of the time you want to say Y here.
|
|
|
|
config NO_HZ_FULL
|
|
bool "Full dynticks system (tickless)"
|
|
# NO_HZ_COMMON dependency
|
|
depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS
|
|
# We need at least one periodic CPU for timekeeping
|
|
depends on SMP
|
|
depends on HAVE_CONTEXT_TRACKING
|
|
# VIRT_CPU_ACCOUNTING_GEN dependency
|
|
depends on HAVE_VIRT_CPU_ACCOUNTING_GEN
|
|
select NO_HZ_COMMON
|
|
select RCU_NOCB_CPU
|
|
select VIRT_CPU_ACCOUNTING_GEN
|
|
select IRQ_WORK
|
|
select CPU_ISOLATION
|
|
help
|
|
Adaptively try to shutdown the tick whenever possible, even when
|
|
the CPU is running tasks. Typically this requires running a single
|
|
task on the CPU. Chances for running tickless are maximized when
|
|
the task mostly runs in userspace and has few kernel activity.
|
|
|
|
You need to fill up the nohz_full boot parameter with the
|
|
desired range of dynticks CPUs.
|
|
|
|
This is implemented at the expense of some overhead in user <-> kernel
|
|
transitions: syscalls, exceptions and interrupts. Even when it's
|
|
dynamically off.
|
|
|
|
Say N.
|
|
|
|
endchoice
|
|
|
|
config NO_HZ
|
|
bool "Old Idle dynticks config"
|
|
depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS
|
|
help
|
|
This is the old config entry that enables dynticks idle.
|
|
We keep it around for a little while to enforce backward
|
|
compatibility with older config files.
|
|
|
|
config HIGH_RES_TIMERS
|
|
bool "High Resolution Timer Support"
|
|
depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS
|
|
select TICK_ONESHOT
|
|
help
|
|
This option enables high resolution timer support. If your
|
|
hardware is not capable then this option only increases
|
|
the size of the kernel image.
|
|
|
|
endmenu
|
|
endif
|