This patch reverts commit 75437bb304 (locking/pvqspinlock: Don't
wait if vCPU is preempted). A large performance regression was caused
by this commit. on over-subscription scenarios.
The test was run on a Xeon Skylake box, 2 sockets, 40 cores, 80 threads,
with three VMs of 80 vCPUs each. The score of ebizzy -M is reduced from
13000-14000 records/s to 1700-1800 records/s:
Host Guest score
vanilla w/o kvm optimizations upstream 1700-1800 records/s
vanilla w/o kvm optimizations revert 13000-14000 records/s
vanilla w/ kvm optimizations upstream 4500-5000 records/s
vanilla w/ kvm optimizations revert 14000-15500 records/s
Exit from aggressive wait-early mechanism can result in premature yield
and extra scheduling latency.
Actually, only 6% of wait_early events are caused by vcpu_is_preempted()
being true. However, when one vCPU voluntarily releases its vCPU, all
the subsequently waiters in the queue will do the same and the cascading
effect leads to bad performance.
kvm optimizations:
[1] commit d73eb57b80 (KVM: Boost vCPUs that are delivering interrupts)
[2] commit 266e85a5ec (KVM: X86: Boost queue head vCPU to mitigate lock waiter preemption)
Tested-by: loobinliu@tencent.com
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Waiman Long <longman@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: loobinliu@tencent.com
Cc: stable@vger.kernel.org
Fixes: 75437bb304 (locking/pvqspinlock: Don't wait if vCPU is preempted)
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Pull scheduler updates from Ingo Molnar:
- MAINTAINERS: Add Mark Rutland as perf submaintainer, Juri Lelli and
Vincent Guittot as scheduler submaintainers. Add Dietmar Eggemann,
Steven Rostedt, Ben Segall and Mel Gorman as scheduler reviewers.
As perf and the scheduler is getting bigger and more complex,
document the status quo of current responsibilities and interests,
and spread the review pain^H^H^H^H fun via an increase in the Cc:
linecount generated by scripts/get_maintainer.pl. :-)
- Add another series of patches that brings the -rt (PREEMPT_RT) tree
closer to mainline: split the monolithic CONFIG_PREEMPT dependencies
into a new CONFIG_PREEMPTION category that will allow the eventual
introduction of CONFIG_PREEMPT_RT. Still a few more hundred patches
to go though.
- Extend the CPU cgroup controller with uclamp.min and uclamp.max to
allow the finer shaping of CPU bandwidth usage.
- Micro-optimize energy-aware wake-ups from O(CPUS^2) to O(CPUS).
- Improve the behavior of high CPU count, high thread count
applications running under cpu.cfs_quota_us constraints.
- Improve balancing with SCHED_IDLE (SCHED_BATCH) tasks present.
- Improve CPU isolation housekeeping CPU allocation NUMA locality.
- Fix deadline scheduler bandwidth calculations and logic when cpusets
rebuilds the topology, or when it gets deadline-throttled while it's
being offlined.
- Convert the cpuset_mutex to percpu_rwsem, to allow it to be used from
setscheduler() system calls without creating global serialization.
Add new synchronization between cpuset topology-changing events and
the deadline acceptance tests in setscheduler(), which were broken
before.
- Rework the active_mm state machine to be less confusing and more
optimal.
- Rework (simplify) the pick_next_task() slowpath.
- Improve load-balancing on AMD EPYC systems.
- ... and misc cleanups, smaller fixes and improvements - please see
the Git log for more details.
* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (53 commits)
sched/psi: Correct overly pessimistic size calculation
sched/fair: Speed-up energy-aware wake-ups
sched/uclamp: Always use 'enum uclamp_id' for clamp_id values
sched/uclamp: Update CPU's refcount on TG's clamp changes
sched/uclamp: Use TG's clamps to restrict TASK's clamps
sched/uclamp: Propagate system defaults to the root group
sched/uclamp: Propagate parent clamps
sched/uclamp: Extend CPU's cgroup controller
sched/topology: Improve load balancing on AMD EPYC systems
arch, ia64: Make NUMA select SMP
sched, perf: MAINTAINERS update, add submaintainers and reviewers
sched/fair: Use rq_lock/unlock in online_fair_sched_group
cpufreq: schedutil: fix equation in comment
sched: Rework pick_next_task() slow-path
sched: Allow put_prev_task() to drop rq->lock
sched/fair: Expose newidle_balance()
sched: Add task_struct pointer to sched_class::set_curr_task
sched: Rework CPU hotplug task selection
sched/{rt,deadline}: Fix set_next_task vs pick_next_task
sched: Fix kerneldoc comment for ia64_set_curr_task
...
Pull locking updates from Ingo Molnar:
- improve rwsem scalability
- add uninitialized rwsem debugging check
- reduce lockdep's stacktrace memory usage and add diagnostics
- misc cleanups, code consolidation and constification
* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
mutex: Fix up mutex_waiter usage
locking/mutex: Use mutex flags macro instead of hard code
locking/mutex: Make __mutex_owner static to mutex.c
locking/qspinlock,x86: Clarify virt_spin_lock_key
locking/rwsem: Check for operations on an uninitialized rwsem
locking/rwsem: Make handoff writer optimistically spin on owner
locking/lockdep: Report more stack trace statistics
locking/lockdep: Reduce space occupied by stack traces
stacktrace: Constify 'entries' arguments
locking/lockdep: Make it clear that what lock_class::key points at is not modified
The patch moving bits into mutex.c was a little too much; by also
moving struct mutex_waiter a few less common CONFIGs would no longer
build.
Fixes: 5f35d5a66b ("locking/mutex: Make __mutex_owner static to mutex.c")
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
__mutex_owner() should only be used by the mutex api's.
So, to put this restiction let's move the __mutex_owner()
function definition from linux/mutex.h to mutex.c file.
There exist functions that uses __mutex_owner() like
mutex_is_locked() and mutex_trylock_recursive(), So
to keep legacy thing intact move them as well and
export them.
Move mutex_waiter structure also to keep it private to the
file.
Signed-off-by: Mukesh Ojha <mojha@codeaurora.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: mingo@redhat.com
Cc: will@kernel.org
Link: https://lkml.kernel.org/r/1564585504-3543-1-git-send-email-mojha@codeaurora.org
When the handoff bit is set by a writer, no other tasks other than
the setting writer itself is allowed to acquire the lock. If the
to-be-handoff'ed writer goes to sleep, there will be a wakeup latency
period where the lock is free, but no one can acquire it. That is less
than ideal.
To reduce that latency, the handoff writer will now optimistically spin
on the owner if it happens to be a on-cpu writer. It will spin until
it releases the lock and the to-be-handoff'ed writer can then acquire
the lock immediately without any delay. Of course, if the owner is not
a on-cpu writer, the to-be-handoff'ed writer will have to sleep anyway.
The optimistic spinning code is also modified to not stop spinning
when the handoff bit is set. This will prevent an occasional setting of
handoff bit from causing a bunch of optimistic spinners from entering
into the wait queue causing significant reduction in throughput.
On a 1-socket 22-core 44-thread Skylake system, the AIM7 shared_memory
workload was run with 7000 users. The throughput (jobs/min) of the
following kernels were as follows:
1) 5.2-rc6
- 8,092,486
2) 5.2-rc6 + tip's rwsem patches
- 7,567,568
3) 5.2-rc6 + tip's rwsem patches + this patch
- 7,954,545
Using perf-record(1), the %cpu time used by rwsem_down_write_slowpath(),
rwsem_down_write_failed() and their callees for the 3 kernels were 1.70%,
5.46% and 2.08% respectively.
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: x86@kernel.org
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: huang ying <huang.ying.caritas@gmail.com>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Link: https://lkml.kernel.org/r/20190625143913.24154-1-longman@redhat.com
Security is a wonderful thing, but so is the ability to debug based on
lockdep warnings. This commit therefore makes lockdep lock addresses
visible in the clear.
Signed-off-by: Paul E. McKenney <paulmck@linux.ibm.com>
Although commit 669de8bda8 ("kernel/workqueue: Use dynamic lockdep keys
for workqueues") unregisters dynamic lockdep keys when a workqueue is
destroyed, a side effect of that commit is that all stack traces
associated with the lockdep key are leaked when a workqueue is destroyed.
Fix this by storing each unique stack trace once. Other changes in this
patch are:
- Use NULL instead of { .nr_entries = 0 } to represent 'no trace'.
- Store a pointer to a stack trace in struct lock_class and struct
lock_list instead of storing 'nr_entries' and 'offset'.
This patch avoids that the following program triggers the "BUG:
MAX_STACK_TRACE_ENTRIES too low!" complaint:
#include <fcntl.h>
#include <unistd.h>
int main()
{
for (;;) {
int fd = open("/dev/infiniband/rdma_cm", O_RDWR);
close(fd);
}
}
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Reported-by: Eric Biggers <ebiggers@kernel.org>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Waiman Long <longman@redhat.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Yuyang Du <duyuyang@gmail.com>
Link: https://lkml.kernel.org/r/20190722182443.216015-4-bvanassche@acm.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
While reviewing another read_slowpath patch, both Will and I noticed
another missing ACQUIRE, namely:
X = 0;
CPU0 CPU1
rwsem_down_read()
for (;;) {
set_current_state(TASK_UNINTERRUPTIBLE);
X = 1;
rwsem_up_write();
rwsem_mark_wake()
atomic_long_add(adjustment, &sem->count);
smp_store_release(&waiter->task, NULL);
if (!waiter.task)
break;
...
}
r = X;
Allows 'r == 0'.
Reported-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reported-by: Will Deacon <will@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Will Deacon <will@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: 1da177e4c3 ("Linux-2.6.12-rc2")
Signed-off-by: Ingo Molnar <mingo@kernel.org>
LTP mtest06 has been observed to occasionally hit "still mapped when
deleted" and following BUG_ON on arm64.
The extra mapcount originated from pagefault handler, which handled
pagefault for vma that has already been detached. vma is detached
under mmap_sem write lock by detach_vmas_to_be_unmapped(), which
also invalidates vmacache.
When the pagefault handler (under mmap_sem read lock) calls
find_vma(), vmacache_valid() wrongly reports vmacache as valid.
After rwsem down_read() returns via 'queue empty' path (as of v5.2),
it does so without an ACQUIRE on sem->count:
down_read()
__down_read()
rwsem_down_read_failed()
__rwsem_down_read_failed_common()
raw_spin_lock_irq(&sem->wait_lock);
if (list_empty(&sem->wait_list)) {
if (atomic_long_read(&sem->count) >= 0) {
raw_spin_unlock_irq(&sem->wait_lock);
return sem;
The problem can be reproduced by running LTP mtest06 in a loop and
building the kernel (-j $NCPUS) in parallel. It does reproduces since
v4.20 on arm64 HPE Apollo 70 (224 CPUs, 256GB RAM, 2 nodes). It
triggers reliably in about an hour.
The patched kernel ran fine for 10+ hours.
Signed-off-by: Jan Stancek <jstancek@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Will Deacon <will@kernel.org>
Acked-by: Waiman Long <longman@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: dbueso@suse.de
Fixes: 4b486b535c ("locking/rwsem: Exit read lock slowpath if queue empty & no writer")
Link: https://lkml.kernel.org/r/50b8914e20d1d62bb2dee42d342836c2c16ebee7.1563438048.git.jstancek@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
For writer, the owner value is cleared on unlock. For reader, it is
left intact on unlock for providing better debugging aid on crash dump
and the unlock of one reader may not mean the lock is free.
As a result, the owner_on_cpu() shouldn't be used on read-owner
as the task pointer value may not be valid and it might have
been freed. That is the case in rwsem_spin_on_owner(), but not in
rwsem_can_spin_on_owner(). This can lead to use-after-free error from
KASAN. For example,
BUG: KASAN: use-after-free in rwsem_down_write_slowpath
(/home/miguel/kernel/linux/kernel/locking/rwsem.c:669
/home/miguel/kernel/linux/kernel/locking/rwsem.c:1125)
Fix this by checking for RWSEM_READER_OWNED flag before calling
owner_on_cpu().
Reported-by: Luis Henriques <lhenriques@suse.com>
Tested-by: Luis Henriques <lhenriques@suse.com>
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Jeff Layton <jlayton@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: huang ying <huang.ying.caritas@gmail.com>
Fixes: 94a9717b3c ("locking/rwsem: Make rwsem->owner an atomic_long_t")
Link: https://lkml.kernel.org/r/81e82d5b-5074-77e8-7204-28479bbe0df0@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Convert the locking documents to ReST and add them to the
kernel development book where it belongs.
Most of the stuff here is just to make Sphinx to properly
parse the text file, as they're already in good shape,
not requiring massive changes in order to be parsed.
The conversion is actually:
- add blank lines and identation in order to identify paragraphs;
- fix tables markups;
- add some lists markups;
- mark literal blocks;
- adjust title markups.
At its new index.rst, let's add a :orphan: while this is not linked to
the main index.rst file, in order to avoid build warnings.
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Acked-by: Federico Vaga <federico.vaga@vaga.pv.it>
The stats variable nr_unused_locks is incremented every time a new lock
class is register and decremented when the lock is first used in
__lock_acquire(). And after all, it is shown and checked in lockdep_stats.
However, under configurations that either CONFIG_TRACE_IRQFLAGS or
CONFIG_PROVE_LOCKING is not defined:
The commit:
0918065151 ("locking/lockdep: Consolidate lock usage bit initialization")
missed marking the LOCK_USED flag at IRQ usage initialization because
as mark_usage() is not called. And the commit:
886532aee3 ("locking/lockdep: Move mark_lock() inside CONFIG_TRACE_IRQFLAGS && CONFIG_PROVE_LOCKING")
further made mark_lock() not defined such that the LOCK_USED cannot be
marked at all when the lock is first acquired.
As a result, we fix this by not showing and checking the stats under such
configurations for lockdep_stats.
Reported-by: Qian Cai <cai@lca.pw>
Signed-off-by: Yuyang Du <duyuyang@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will.deacon@arm.com>
Cc: arnd@arndb.de
Cc: frederic@kernel.org
Link: https://lkml.kernel.org/r/20190709101522.9117-1-duyuyang@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Pull locking updates from Ingo Molnar:
"The main changes in this cycle are:
- rwsem scalability improvements, phase #2, by Waiman Long, which are
rather impressive:
"On a 2-socket 40-core 80-thread Skylake system with 40 reader
and writer locking threads, the min/mean/max locking operations
done in a 5-second testing window before the patchset were:
40 readers, Iterations Min/Mean/Max = 1,807/1,808/1,810
40 writers, Iterations Min/Mean/Max = 1,807/50,344/151,255
After the patchset, they became:
40 readers, Iterations Min/Mean/Max = 30,057/31,359/32,741
40 writers, Iterations Min/Mean/Max = 94,466/95,845/97,098"
There's a lot of changes to the locking implementation that makes
it similar to qrwlock, including owner handoff for more fair
locking.
Another microbenchmark shows how across the spectrum the
improvements are:
"With a locking microbenchmark running on 5.1 based kernel, the
total locking rates (in kops/s) on a 2-socket Skylake system
with equal numbers of readers and writers (mixed) before and
after this patchset were:
# of Threads Before Patch After Patch
------------ ------------ -----------
2 2,618 4,193
4 1,202 3,726
8 802 3,622
16 729 3,359
32 319 2,826
64 102 2,744"
The changes are extensive and the patch-set has been through
several iterations addressing various locking workloads. There
might be more regressions, but unless they are pathological I
believe we want to use this new implementation as the baseline
going forward.
- jump-label optimizations by Daniel Bristot de Oliveira: the primary
motivation was to remove IPI disturbance of isolated RT-workload
CPUs, which resulted in the implementation of batched jump-label
updates. Beyond the improvement of the real-time characteristics
kernel, in one test this patchset improved static key update
overhead from 57 msecs to just 1.4 msecs - which is a nice speedup
as well.
- atomic64_t cross-arch type cleanups by Mark Rutland: over the last
~10 years of atomic64_t existence the various types used by the
APIs only had to be self-consistent within each architecture -
which means they became wildly inconsistent across architectures.
Mark puts and end to this by reworking all the atomic64
implementations to use 's64' as the base type for atomic64_t, and
to ensure that this type is consistently used for parameters and
return values in the API, avoiding further problems in this area.
- A large set of small improvements to lockdep by Yuyang Du: type
cleanups, output cleanups, function return type and othr cleanups
all around the place.
- A set of percpu ops cleanups and fixes by Peter Zijlstra.
- Misc other changes - please see the Git log for more details"
* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (82 commits)
locking/lockdep: increase size of counters for lockdep statistics
locking/atomics: Use sed(1) instead of non-standard head(1) option
locking/lockdep: Move mark_lock() inside CONFIG_TRACE_IRQFLAGS && CONFIG_PROVE_LOCKING
x86/jump_label: Make tp_vec_nr static
x86/percpu: Optimize raw_cpu_xchg()
x86/percpu, sched/fair: Avoid local_clock()
x86/percpu, x86/irq: Relax {set,get}_irq_regs()
x86/percpu: Relax smp_processor_id()
x86/percpu: Differentiate this_cpu_{}() and __this_cpu_{}()
locking/rwsem: Guard against making count negative
locking/rwsem: Adaptive disabling of reader optimistic spinning
locking/rwsem: Enable time-based spinning on reader-owned rwsem
locking/rwsem: Make rwsem->owner an atomic_long_t
locking/rwsem: Enable readers spinning on writer
locking/rwsem: Clarify usage of owner's nonspinaable bit
locking/rwsem: Wake up almost all readers in wait queue
locking/rwsem: More optimal RT task handling of null owner
locking/rwsem: Always release wait_lock before waking up tasks
locking/rwsem: Implement lock handoff to prevent lock starvation
locking/rwsem: Make rwsem_spin_on_owner() return owner state
...
