Pull timer updates from Thomas Gleixner:
"A large set of updates and features for timers and timekeeping:
- The hierarchical timer pull model
When timer wheel timers are armed they are placed into the timer
wheel of a CPU which is likely to be busy at the time of expiry.
This is done to avoid wakeups on potentially idle CPUs.
This is wrong in several aspects:
1) The heuristics to select the target CPU are wrong by
definition as the chance to get the prediction right is
close to zero.
2) Due to #1 it is possible that timers are accumulated on
a single target CPU
3) The required computation in the enqueue path is just overhead
for dubious value especially under the consideration that the
vast majority of timer wheel timers are either canceled or
rearmed before they expire.
The timer pull model avoids the above by removing the target
computation on enqueue and queueing timers always on the CPU on
which they get armed.
This is achieved by having separate wheels for CPU pinned timers
and global timers which do not care about where they expire.
As long as a CPU is busy it handles both the pinned and the global
timers which are queued on the CPU local timer wheels.
When a CPU goes idle it evaluates its own timer wheels:
- If the first expiring timer is a pinned timer, then the global
timers can be ignored as the CPU will wake up before they
expire.
- If the first expiring timer is a global timer, then the expiry
time is propagated into the timer pull hierarchy and the CPU
makes sure to wake up for the first pinned timer.
The timer pull hierarchy organizes CPUs in groups of eight at the
lowest level and at the next levels groups of eight groups up to
the point where no further aggregation of groups is required, i.e.
the number of levels is log8(NR_CPUS). The magic number of eight
has been established by experimention, but can be adjusted if
needed.
In each group one busy CPU acts as the migrator. It's only one CPU
to avoid lock contention on remote timer wheels.
The migrator CPU checks in its own timer wheel handling whether
there are other CPUs in the group which have gone idle and have
global timers to expire. If there are global timers to expire, the
migrator locks the remote CPU timer wheel and handles the expiry.
Depending on the group level in the hierarchy this handling can
require to walk the hierarchy downwards to the CPU level.
Special care is taken when the last CPU goes idle. At this point
the CPU is the systemwide migrator at the top of the hierarchy and
it therefore cannot delegate to the hierarchy. It needs to arm its
own timer device to expire either at the first expiring timer in
the hierarchy or at the first CPU local timer, which ever expires
first.
This completely removes the overhead from the enqueue path, which
is e.g. for networking a true hotpath and trades it for a slightly
more complex idle path.
This has been in development for a couple of years and the final
series has been extensively tested by various teams from silicon
vendors and ran through extensive CI.
There have been slight performance improvements observed on network
centric workloads and an Intel team confirmed that this allows them
to power down a die completely on a mult-die socket for the first
time in a mostly idle scenario.
There is only one outstanding ~1.5% regression on a specific
overloaded netperf test which is currently investigated, but the
rest is either positive or neutral performance wise and positive on
the power management side.
- Fixes for the timekeeping interpolation code for cross-timestamps:
cross-timestamps are used for PTP to get snapshots from hardware
timers and interpolated them back to clock MONOTONIC. The changes
address a few corner cases in the interpolation code which got the
math and logic wrong.
- Simplifcation of the clocksource watchdog retry logic to
automatically adjust to handle larger systems correctly instead of
having more incomprehensible command line parameters.
- Treewide consolidation of the VDSO data structures.
- The usual small improvements and cleanups all over the place"
* tag 'timers-core-2024-03-10' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (62 commits)
timer/migration: Fix quick check reporting late expiry
tick/sched: Fix build failure for CONFIG_NO_HZ_COMMON=n
vdso/datapage: Quick fix - use asm/page-def.h for ARM64
timers: Assert no next dyntick timer look-up while CPU is offline
tick: Assume timekeeping is correctly handed over upon last offline idle call
tick: Shut down low-res tick from dying CPU
tick: Split nohz and highres features from nohz_mode
tick: Move individual bit features to debuggable mask accesses
tick: Move got_idle_tick away from common flags
tick: Assume the tick can't be stopped in NOHZ_MODE_INACTIVE mode
tick: Move broadcast cancellation up to CPUHP_AP_TICK_DYING
tick: Move tick cancellation up to CPUHP_AP_TICK_DYING
tick: Start centralizing tick related CPU hotplug operations
tick/sched: Don't clear ts::next_tick again in can_stop_idle_tick()
tick/sched: Rename tick_nohz_stop_sched_tick() to tick_nohz_full_stop_tick()
tick: Use IS_ENABLED() whenever possible
tick/sched: Remove useless oneshot ifdeffery
tick/nohz: Remove duplicate between lowres and highres handlers
tick/nohz: Remove duplicate between tick_nohz_switch_to_nohz() and tick_setup_sched_timer()
hrtimer: Select housekeeping CPU during migration
...
Boqun pointed out that workqueues aren't handling BH work items on offlined
CPUs. Unlike tasklet which transfers out the pending tasks from
CPUHP_SOFTIRQ_DEAD, BH workqueue would just leave them pending which is
problematic. Note that this behavior is specific to BH workqueues as the
non-BH per-CPU workers just become unbound when the CPU goes offline.
This patch fixes the issue by draining the pending BH work items from an
offlined CPU from CPUHP_SOFTIRQ_DEAD. Because work items carry more context,
it's not as easy to transfer the pending work items from one pool to
another. Instead, run BH work items which execute the offlined pools on an
online CPU.
Note that this assumes that no further BH work items will be queued on the
offlined CPUs. This assumption is shared with tasklet and should be fine for
conversions. However, this issue also exists for per-CPU workqueues which
will just keep executing work items queued after CPU offline on unbound
workers and workqueue should reject per-CPU and BH work items queued on
offline CPUs. This will be addressed separately later.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-and-reviewed-by: Boqun Feng <boqun.feng@gmail.com>
Link: http://lkml.kernel.org/r/Zdvw0HdSXcU3JZ4g@boqun-archlinux
When CONFIG_WQ_CPU_INTENSIVE_REPORT is set, the kernel will report
the work functions which violate the intensive_threshold_us repeatedly.
And now, only when the violate times exceed 4 and is a power of 2,
the kernel warning could be triggered.
However, sometimes, even if a long work execution time occurs only once,
it may cause other work to be delayed for a long time. This may also
cause some problems sometimes.
In order to freely control the threshold of warninging, a boot argument
is added so that the user can control the warning threshold to be printed.
At the same time, keep the exponential backoff to prevent reporting too much.
By default, the warning threshold is 4.
tj: Updated kernel-parameters.txt description.
Signed-off-by: Xuewen Yan <xuewen.yan@unisoc.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
The implementation of the NOHZ pull at expiry model will change the timer
bases per CPU. Timers, that have to expire on a specific CPU, require the
TIMER_PINNED flag. If the CPU doesn't matter, the TIMER_PINNED flag must be
dropped. This is required for call sites which use the timer alternately as
pinned and not pinned timer like workqueues do.
Therefore use add_timer_global() in __queue_delayed_work() for non-bound
delayed work to make sure the TIMER_PINNED flag is dropped.
Signed-off-by: Anna-Maria Behnsen <anna-maria@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Acked-by: Tejun Heo <tj@kernel.org>
Link: https://lore.kernel.org/r/20240221090548.36600-7-anna-maria@linutronix.de
- set_work_data() takes a separate @flags argument but just ORs it to @data.
This is more confusing than helpful. Just take @data.
- Use the name @flags consistently and add the parameter to
set_work_pool_and_{keep|clear}_pending(). This will be used by the planned
disable/enable support.
No functional changes.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Lai Jiangshan <jiangshanlai@gmail.com>
clear_work_data() is only used in one place and immediately followed by
smp_mb(), making it equivalent to set_work_pool_and_clear_pending() w/
WORK_OFFQ_POOL_NONE for @pool_id. Drop it. No functional changes.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Lai Jiangshan <jiangshanlai@gmail.com>
The planned disable/enable support will need the same logic. Let's factor it
out. No functional changes.
v2: Update function comment to include @irq_flags.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Lai Jiangshan <jiangshanlai@gmail.com>
The bits of work->data are used for a few different purposes. How the bits
are used is determined by enum work_bits. The planned disable/enable support
will add another use, so let's clean it up a bit in preparation.
- Let WORK_STRUCT_*_BIT's values be determined by enum definition order.
- Deliminate different bit sections the same way using SHIFT and BITS
values.
- Rename __WORK_OFFQ_CANCELING to WORK_OFFQ_CANCELING_BIT for consistency.
- Introduce WORK_STRUCT_PWQ_SHIFT and replace WORK_STRUCT_FLAG_MASK and
WORK_STRUCT_WQ_DATA_MASK with WQ_STRUCT_PWQ_MASK for clarity.
- Improve documentation.
No functional changes.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Lai Jiangshan <jiangshanlai@gmail.com>
The cancel path used bool @is_dwork to distinguish canceling a regular work
and a delayed one. The planned disable/enable support will need passing
around another flag in the code path. As passing them around with bools will
be confusing, let's introduce named flags to pass around in the cancel path.
WORK_CANCEL_DELAYED replaces @is_dwork. No functional changes.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Lai Jiangshan <jiangshanlai@gmail.com>
Using the generic term `flags` for irq flags is conventional but can be
confusing as there's quite a bit of code dealing with work flags which
involves some subtleties. Let's use a more explicit name `irq_flags` for
local irq flags. No functional changes.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Lai Jiangshan <jiangshanlai@gmail.com>
They are currently a bit disorganized with flush and cancel functions mixed.
Reoranize them so that flush functions come first, cancel next and
cancel_sync last. This way, we won't have to add prototypes for internal
functions for the planned disable/enable support.
This is pure code reorganization. No functional changes.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Lai Jiangshan <jiangshanlai@gmail.com>
__cancel_work_timer() is used to implement cancel_work_sync() and
cancel_delayed_work_sync(), similarly to how __cancel_work() is used to
implement cancel_work() and cancel_delayed_work(). ie. The _timer part of
the name is a complete misnomer. The difference from __cancel_work() is the
fact that it syncs against work item execution not whether it handles timers
or not.
Let's rename it to less confusing __cancel_work_sync(). No functional
change.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Lai Jiangshan <jiangshanlai@gmail.com>
The different flavors of RCU read critical sections have been unified. Let's
update the locking assertion macros accordingly to avoid requiring
unnecessary explicit rcu_read_[un]lock() calls.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Lai Jiangshan <jiangshanlai@gmail.com>
Reorder some global declarations and adjust comments and whitespaces for
clarity and consistency. No functional changes.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Lai Jiangshan <jiangshanlai@gmail.com>
2f34d7337d ("workqueue: Fix queue_work_on() with BH workqueues") added
irq_work usage to workqueue; however, it turns out irq_work is actually
optional and the change breaks build on configuration which doesn't have
CONFIG_IRQ_WORK enabled.
Fix build by making workqueue use irq_work only when CONFIG_SMP and enabling
CONFIG_IRQ_WORK when CONFIG_SMP is set. It's reasonable to argue that it may
be better to just always enable it. However, this still saves a small bit of
memory for tiny UP configs and also the least amount of change, so, for now,
let's keep it conditional.
Verified to do the right thing for x86_64 allnoconfig and defconfig, and
aarch64 allnoconfig, allnoconfig + prink disable (SMP but nothing selects
IRQ_WORK) and a modified aarch64 Kconfig where !SMP and nothing selects
IRQ_WORK.
v2: `depends on SMP` leads to Kconfig warnings when CONFIG_IRQ_WORK is
selected by something else when !CONFIG_SMP. Use `def_bool y if SMP`
instead.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Naresh Kamboju <naresh.kamboju@linaro.org>
Tested-by: Anders Roxell <anders.roxell@linaro.org>
Fixes: 2f34d7337d ("workqueue: Fix queue_work_on() with BH workqueues")
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
When queue_work_on() is used to queue a BH work item on a remote CPU, the
work item is queued on that CPU but kick_pool() raises softirq on the local
CPU. This leads to stalls as the work item won't be executed until something
else on the remote CPU schedules a BH work item or tasklet locally.
Fix it by bouncing raising softirq to the target CPU using per-cpu irq_work.
Signed-off-by: Tejun Heo <tj@kernel.org>
Fixes: 4cb1ef6460 ("workqueue: Implement BH workqueues to eventually replace tasklets")
Since 5797b1c189 ("workqueue: Implement system-wide nr_active enforcement
for unbound workqueues"), unbound workqueues have separate min_active which
sets the number of interdependent work items that can be handled. This value
is currently initialized to WQ_DFL_MIN_ACTIVE which is 8. This isn't high
enough for some users, let's add an interface to adjust the setting.
Signed-off-by: Tejun Heo <tj@kernel.org>
Fix the kernel-doc comment of the unplug_oldest_pwq() function to enable
proper processing and formatting of the embedded ASCII diagram.
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Commit 85f0ab43f9 ("kernel/workqueue: Bind rescuer to unbound
cpumask for WQ_UNBOUND") modified init_rescuer() to bind rescuer of
an unbound workqueue to the cpumask in wq->unbound_attrs. However
unbound_attrs->cpumask's of all workqueues are initialized to
cpu_possible_mask and will only be changed if it has the WQ_SYSFS flag
to expose a cpumask sysfs file to be written by users. So this patch
doesn't achieve what it is intended to do.
If an unbound workqueue is created after wq_unbound_cpumask is modified
and there is no more unbound cpumask update after that, the unbound
rescuer will be bound to all CPUs unless the workqueue is created
with the WQ_SYSFS flag and a user explicitly modified its cpumask
sysfs file. Fix this problem by binding directly to wq_unbound_cpumask
in init_rescuer().
Fixes: 85f0ab43f9 ("kernel/workqueue: Bind rescuer to unbound cpumask for WQ_UNBOUND")
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
When workqueue cpumask changes are committed the associated rescuer (if
one exists) affinity is not touched and this might be a problem down the
line for isolated setups.
Make sure rescuers affinity is updated every time a workqueue cpumask
changes, so that rescuers can't break isolation.
[longman: set_cpus_allowed_ptr() will block until the designated task
is enqueued on an allowed CPU, no wake_up_process() needed. Also use
the unbound_effective_cpumask() helper as suggested by Tejun.]
Signed-off-by: Juri Lelli <juri.lelli@redhat.com>
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Ordered workqueues does not currently follow changes made to the
global unbound cpumask because per-pool workqueue changes may break
the ordering guarantee. IOW, a work function in an ordered workqueue
may run on an isolated CPU.
This patch enables ordered workqueues to follow changes made to the
global unbound cpumask by temporaily plug or suspend the newly allocated
pool_workqueue from executing newly queued work items until the old
pwq has been properly drained. For ordered workqueues, there should
only be one pwq that is unplugged, the rests should be plugged.
This enables ordered workqueues to follow the unbound cpumask changes
like other unbound workqueues at the expense of some delay in execution
of work functions during the transition period.
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Add a new pwq into the tail of wq->pwqs so that pwq iteration will
start from the oldest pwq to the newest. This ordering will facilitate
the inclusion of ordered workqueues in a wq_unbound_cpumask update.
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
The for-6.8-fixes commit ae9cc8956944 ("Revert "workqueue: Override implicit
ordered attribute in workqueue_apply_unbound_cpumask()") also fixes build for
Signed-off-by: Tejun Heo <tj@kernel.org>
This reverts commit ca10d851b9.
The commit allowed workqueue_apply_unbound_cpumask() to clear __WQ_ORDERED
on now removed implicitly ordered workqueues. This was incorrect in that
system-wide config change shouldn't break ordering properties of all
workqueues. The reason why apply_workqueue_attrs() path was allowed to do so
was because it was targeting the specific workqueue - either the workqueue
had WQ_SYSFS set or the workqueue user specifically tried to change
max_active, both of which indicate that the workqueue doesn't need to be
ordered.
The implicitly ordered workqueue promotion was removed by the previous
commit 3bc1e711c2 ("workqueue: Don't implicitly make UNBOUND workqueues w/
@max_active==1 ordered"). However, it didn't update this path and broke
build. Let's revert the commit which was incorrect in the first place which
also fixes build.
Signed-off-by: Tejun Heo <tj@kernel.org>
Fixes: 3bc1e711c2 ("workqueue: Don't implicitly make UNBOUND workqueues w/ @max_active==1 ordered")
Fixes: ca10d851b9 ("workqueue: Override implicit ordered attribute in workqueue_apply_unbound_cpumask()")
Cc: stable@vger.kernel.org # v6.6+
Signed-off-by: Tejun Heo <tj@kernel.org>
5c0338c687 ("workqueue: restore WQ_UNBOUND/max_active==1 to be ordered")
automoatically promoted UNBOUND workqueues w/ @max_active==1 to ordered
workqueues because UNBOUND workqueues w/ @max_active==1 used to be the way
to create ordered workqueues and the new NUMA support broke it. These
problems can be subtle and the fact that they can only trigger on NUMA
machines made them even more difficult to debug.
However, overloading the UNBOUND allocation interface this way creates other
issues. It's difficult to tell whether a given workqueue actually needs to
be ordered and users that legitimately want a min concurrency level wq
unexpectedly gets an ordered one instead. With planned UNBOUND workqueue
udpates to improve execution locality and more prevalence of chiplet designs
which can benefit from such improvements, this isn't a state we wanna be in
forever.
There aren't that many UNBOUND w/ @max_active==1 users in the tree and the
preceding patches audited all and converted them to
alloc_ordered_workqueue() as appropriate. This patch removes the implicit
promotion of UNBOUND w/ @max_active==1 workqueues to ordered ones.
v2: v1 patch incorrectly dropped !list_empty(&wq->pwqs) condition in
apply_workqueue_attrs_locked() which spuriously triggers WARNING and
fails workqueue creation. Fix it.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: kernel test robot <oliver.sang@intel.com>
Link: https://lore.kernel.org/oe-lkp/202304251050.45a5df1f-oliver.sang@intel.com
