This is a partial forward-port of Peter Ziljstra's work first posted
at:
https://lore.kernel.org/lkml/20180530142236.667774973@infradead.org/
Currently select_idle_cpu()'s proportional scheme uses the average idle
time *for when we are idle*, that is temporally challenged. When a CPU
is not at all idle, we'll happily continue using whatever value we did
see when the CPU goes idle. To fix this, introduce a separate average
idle and age it (the existing value still makes sense for things like
new-idle balancing, which happens when we do go idle).
The overall goal is to not spend more time scanning for idle CPUs than
we're idle for. Otherwise we're inhibiting work. This means that we need to
consider the cost over all the wake-ups between consecutive idle periods.
To track this, the scan cost is subtracted from the estimated average
idle time.
The impact of this patch is related to workloads that have domains that
are fully busy or overloaded. Without the patch, the scan depth may be
too high because a CPU is not reaching idle.
Due to the nature of the patch, this is a regression magnet. It
potentially wins when domains are almost fully busy or overloaded --
at that point searches are likely to fail but idle is not being aged
as CPUs are active so search depth is too large and useless. It will
potentially show regressions when there are idle CPUs and a deep search is
beneficial. This tbench result on a 2-socket broadwell machine partially
illustates the problem
5.13.0-rc2 5.13.0-rc2
vanilla sched-avgidle-v1r5
Hmean 1 445.02 ( 0.00%) 451.36 * 1.42%*
Hmean 2 830.69 ( 0.00%) 846.03 * 1.85%*
Hmean 4 1350.80 ( 0.00%) 1505.56 * 11.46%*
Hmean 8 2888.88 ( 0.00%) 2586.40 * -10.47%*
Hmean 16 5248.18 ( 0.00%) 5305.26 * 1.09%*
Hmean 32 8914.03 ( 0.00%) 9191.35 * 3.11%*
Hmean 64 10663.10 ( 0.00%) 10192.65 * -4.41%*
Hmean 128 18043.89 ( 0.00%) 18478.92 * 2.41%*
Hmean 256 16530.89 ( 0.00%) 17637.16 * 6.69%*
Hmean 320 16451.13 ( 0.00%) 17270.97 * 4.98%*
Note that 8 was a regression point where a deeper search would have helped
but it gains for high thread counts when searches are useless. Hackbench
is a more extreme example although not perfect as the tasks idle rapidly
hackbench-process-pipes
5.13.0-rc2 5.13.0-rc2
vanilla sched-avgidle-v1r5
Amean 1 0.3950 ( 0.00%) 0.3887 ( 1.60%)
Amean 4 0.9450 ( 0.00%) 0.9677 ( -2.40%)
Amean 7 1.4737 ( 0.00%) 1.4890 ( -1.04%)
Amean 12 2.3507 ( 0.00%) 2.3360 * 0.62%*
Amean 21 4.0807 ( 0.00%) 4.0993 * -0.46%*
Amean 30 5.6820 ( 0.00%) 5.7510 * -1.21%*
Amean 48 8.7913 ( 0.00%) 8.7383 ( 0.60%)
Amean 79 14.3880 ( 0.00%) 13.9343 * 3.15%*
Amean 110 21.2233 ( 0.00%) 19.4263 * 8.47%*
Amean 141 28.2930 ( 0.00%) 25.1003 * 11.28%*
Amean 172 34.7570 ( 0.00%) 30.7527 * 11.52%*
Amean 203 41.0083 ( 0.00%) 36.4267 * 11.17%*
Amean 234 47.7133 ( 0.00%) 42.0623 * 11.84%*
Amean 265 53.0353 ( 0.00%) 47.7720 * 9.92%*
Amean 296 60.0170 ( 0.00%) 53.4273 * 10.98%*
Stddev 1 0.0052 ( 0.00%) 0.0025 ( 51.57%)
Stddev 4 0.0357 ( 0.00%) 0.0370 ( -3.75%)
Stddev 7 0.0190 ( 0.00%) 0.0298 ( -56.64%)
Stddev 12 0.0064 ( 0.00%) 0.0095 ( -48.38%)
Stddev 21 0.0065 ( 0.00%) 0.0097 ( -49.28%)
Stddev 30 0.0185 ( 0.00%) 0.0295 ( -59.54%)
Stddev 48 0.0559 ( 0.00%) 0.0168 ( 69.92%)
Stddev 79 0.1559 ( 0.00%) 0.0278 ( 82.17%)
Stddev 110 1.1728 ( 0.00%) 0.0532 ( 95.47%)
Stddev 141 0.7867 ( 0.00%) 0.0968 ( 87.69%)
Stddev 172 1.0255 ( 0.00%) 0.0420 ( 95.91%)
Stddev 203 0.8106 ( 0.00%) 0.1384 ( 82.92%)
Stddev 234 1.1949 ( 0.00%) 0.1328 ( 88.89%)
Stddev 265 0.9231 ( 0.00%) 0.0820 ( 91.11%)
Stddev 296 1.0456 ( 0.00%) 0.1327 ( 87.31%)
Again, higher thread counts benefit and the standard deviation
shows that results are also a lot more stable when the idle
time is aged.
The patch potentially matters when a socket was multiple LLCs as the
maximum search depth is lower. However, some of the test results were
suspiciously good (e.g. specjbb2005 gaining 50% on a Zen1 machine) and
other results were not dramatically different to other mcahines.
Given the nature of the patch, Peter's full series is not being forward
ported as each part should stand on its own. Preferably they would be
merged at different times to reduce the risk of false bisections.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210615111611.GH30378@techsingularity.net
Energy Aware Scheduling (EAS) needs to predict the decisions made by
SchedUtil. The map_util_freq() exists to do that.
There are corner cases where the max allowed frequency might be reduced
(due to thermal). SchedUtil as a CPUFreq governor, is aware of that
but EAS is not. This patch aims to address it.
SchedUtil stores the maximum allowed frequency in
'sugov_policy::next_freq' field. EAS has to predict that value, which is
the real used frequency. That value is made after a call to
cpufreq_driver_resolve_freq() which clamps to the CPUFreq policy limits.
In the existing code EAS is not able to predict that real frequency.
This leads to energy estimation errors.
To avoid wrong energy estimation in EAS (due to frequency miss prediction)
make sure that the step which calculates Performance Domain frequency,
is also aware of the allowed CPU capacity.
Furthermore, modify map_util_freq() to not extend the frequency value.
Instead, use map_util_perf() to extend the util value in both places:
SchedUtil and EAS, but for EAS clamp it to max allowed CPU capacity.
In the end, we achieve the same desirable behavior for both subsystems
and alignment in regards to the real CPU frequency.
Signed-off-by: Lukasz Luba <lukasz.luba@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> (For the schedutil part)
Link: https://lore.kernel.org/r/20210614191238.23224-1-lukasz.luba@arm.com
Energy Aware Scheduling (EAS) needs to be able to predict the frequency
requests made by the SchedUtil governor to properly estimate energy used
in the future. It has to take into account CPUs utilization and forecast
Performance Domain (PD) frequency. There is a corner case when the max
allowed frequency might be reduced due to thermal. SchedUtil is aware of
that reduced frequency, so it should be taken into account also in EAS
estimations.
SchedUtil, as a CPUFreq governor, knows the maximum allowed frequency of
a CPU, thanks to cpufreq_driver_resolve_freq() and internal clamping
to 'policy::max'. SchedUtil is responsible to respect that upper limit
while setting the frequency through CPUFreq drivers. This effective
frequency is stored internally in 'sugov_policy::next_freq' and EAS has
to predict that value.
In the existing code the raw value of arch_scale_cpu_capacity() is used
for clamping the returned CPU utilization from effective_cpu_util().
This patch fixes issue with too big single CPU utilization, by introducing
clamping to the allowed CPU capacity. The allowed CPU capacity is a CPU
capacity reduced by thermal pressure raw value.
Thanks to knowledge about allowed CPU capacity, we don't get too big value
for a single CPU utilization, which is then added to the util sum. The
util sum is used as a source of information for estimating whole PD energy.
To avoid wrong energy estimation in EAS (due to capped frequency), make
sure that the calculation of util sum is aware of allowed CPU capacity.
This thermal pressure might be visible in scenarios where the CPUs are not
heavily loaded, but some other component (like GPU) drastically reduced
available power budget and increased the SoC temperature. Thus, we still
use EAS for task placement and CPUs are not over-utilized.
Signed-off-by: Lukasz Luba <lukasz.luba@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Link: https://lore.kernel.org/r/20210614191128.22735-1-lukasz.luba@arm.com
Rounding in PELT calculation happening when entities are attached/detached
of a cfs_rq can result into situations where util/runnable_avg is not null
but util/runnable_sum is. This is normally not possible so we need to
ensure that util/runnable_sum stays synced with util/runnable_avg.
detach_entity_load_avg() is the last place where we don't sync
util/runnable_sum with util/runnbale_avg when moving some sched_entities
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210601085832.12626-1-vincent.guittot@linaro.org
Will reported that the 'XXX __migrate_task() can fail' in migration_cpu_stop()
can happen, and it *is* sort of a big deal. Looking at it some more, one
will note there is a glaring hole in the deferred CPU selection:
(w/ CONFIG_CPUSET=n, so that the affinity mask passed via taskset doesn't
get AND'd with cpu_online_mask)
$ taskset -pc 0-2 $PID
# offline CPUs 3-4
$ taskset -pc 3-5 $PID
`\
$PID may stay on 0-2 due to the cpumask_any_distribute() picking an
offline CPU and __migrate_task() refusing to do anything due to
cpu_is_allowed().
set_cpus_allowed_ptr() goes to some length to pick a dest_cpu that matches
the right constraints vs affinity and the online/active state of the
CPUs. Reuse that instead of discarding it in the affine_move_task() case.
Fixes: 6d337eab04 ("sched: Fix migrate_disable() vs set_cpus_allowed_ptr()")
Reported-by: Will Deacon <will@kernel.org>
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210526205751.842360-2-valentin.schneider@arm.com
Checking for and processing RCU-nocb deferred wakeup upon user/guest
entry is only relevant when nohz_full runs on the local CPU, otherwise
the periodic tick should take care of it.
Make sure we don't needlessly pollute these fast-paths as a -3%
performance regression on a will-it-scale.per_process_ops has been
reported so far.
Fixes: 47b8ff194c (entry: Explicitly flush pending rcuog wakeup before last rescheduling point)
Fixes: 4ae7dc97f7 (entry/kvm: Explicitly flush pending rcuog wakeup before last rescheduling point)
Reported-by: kernel test robot <oliver.sang@intel.com>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Paul E. McKenney <paulmck@kernel.org>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20210527113441.465489-1-frederic@kernel.org
During the update of fair blocked load (__update_blocked_fair()), we
update the contribution of the cfs in tg->load_avg if cfs_rq's pelt
has decayed. Nevertheless, the pelt values of a cfs_rq could have
been recently updated while propagating the change of a child. In this
case, cfs_rq's pelt will not decayed because it has already been
updated and we don't update tg->load_avg.
__update_blocked_fair
...
for_each_leaf_cfs_rq_safe: child cfs_rq
update cfs_rq_load_avg() for child cfs_rq
...
update_load_avg(cfs_rq_of(se), se, 0)
...
update cfs_rq_load_avg() for parent cfs_rq
-propagation of child's load makes parent cfs_rq->load_sum
becoming null
-UPDATE_TG is not set so it doesn't update parent
cfs_rq->tg_load_avg_contrib
..
for_each_leaf_cfs_rq_safe: parent cfs_rq
update cfs_rq_load_avg() for parent cfs_rq
- nothing to do because parent cfs_rq has already been updated
recently so cfs_rq->tg_load_avg_contrib is not updated
...
parent cfs_rq is decayed
list_del_leaf_cfs_rq parent cfs_rq
- but it still contibutes to tg->load_avg
we must set UPDATE_TG flags when propagting pending load to the parent
Fixes: 039ae8bcf7 ("sched/fair: Fix O(nr_cgroups) in the load balancing path")
Reported-by: Odin Ugedal <odin@uged.al>
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Odin Ugedal <odin@uged.al>
Link: https://lkml.kernel.org/r/20210527122916.27683-3-vincent.guittot@linaro.org
when removing a cfs_rq from the list we only check _sum value so we must
ensure that _avg and _sum stay synced so load_sum can't be null whereas
load_avg is not after propagating load in the cgroup hierarchy.
Use load_avg to compute load_sum similarly to what is done for util_sum
and runnable_sum.
Fixes: 0e2d2aaaae ("sched/fair: Rewrite PELT migration propagation")
Reported-by: Odin Ugedal <odin@uged.al>
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Odin Ugedal <odin@uged.al>
Link: https://lkml.kernel.org/r/20210527122916.27683-2-vincent.guittot@linaro.org
Pull seccomp fixes from Kees Cook:
"This fixes a hard-to-hit race condition in the addfd user_notif
feature of seccomp, visible since v5.9.
And a small documentation fix"
* tag 'seccomp-fixes-v5.13-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux:
seccomp: Refactor notification handler to prepare for new semantics
Documentation: seccomp: Fix user notification documentation
Pull networking fixes from Jakub Kicinski:
"Networking fixes for 5.13-rc4, including fixes from bpf, netfilter,
can and wireless trees. Notably including fixes for the recently
announced "FragAttacks" WiFi vulnerabilities. Rather large batch,
touching some core parts of the stack, too, but nothing hair-raising.
Current release - regressions:
- tipc: make node link identity publish thread safe
- dsa: felix: re-enable TAS guard band mode
- stmmac: correct clocks enabled in stmmac_vlan_rx_kill_vid()
- stmmac: fix system hang if change mac address after interface
ifdown
Current release - new code bugs:
- mptcp: avoid OOB access in setsockopt()
- bpf: Fix nested bpf_bprintf_prepare with more per-cpu buffers
- ethtool: stats: fix a copy-paste error - init correct array size
Previous releases - regressions:
- sched: fix packet stuck problem for lockless qdisc
- net: really orphan skbs tied to closing sk
- mlx4: fix EEPROM dump support
- bpf: fix alu32 const subreg bound tracking on bitwise operations
- bpf: fix mask direction swap upon off reg sign change
- bpf, offload: reorder offload callback 'prepare' in verifier
- stmmac: Fix MAC WoL not working if PHY does not support WoL
- packetmmap: fix only tx timestamp on request
- tipc: skb_linearize the head skb when reassembling msgs
Previous releases - always broken:
- mac80211: address recent "FragAttacks" vulnerabilities
- mac80211: do not accept/forward invalid EAPOL frames
- mptcp: avoid potential error message floods
- bpf, ringbuf: deny reserve of buffers larger than ringbuf to
prevent out of buffer writes
- bpf: forbid trampoline attach for functions with variable arguments
- bpf: add deny list of functions to prevent inf recursion of tracing
programs
- tls splice: check SPLICE_F_NONBLOCK instead of MSG_DONTWAIT
- can: isotp: prevent race between isotp_bind() and
isotp_setsockopt()
- netfilter: nft_set_pipapo_avx2: Add irq_fpu_usable() check,
fallback to non-AVX2 version
Misc:
- bpf: add kconfig knob for disabling unpriv bpf by default"
* tag 'net-5.13-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (172 commits)
net: phy: Document phydev::dev_flags bits allocation
mptcp: validate 'id' when stopping the ADD_ADDR retransmit timer
mptcp: avoid error message on infinite mapping
mptcp: drop unconditional pr_warn on bad opt
mptcp: avoid OOB access in setsockopt()
nfp: update maintainer and mailing list addresses
net: mvpp2: add buffer header handling in RX
bnx2x: Fix missing error code in bnx2x_iov_init_one()
net: zero-initialize tc skb extension on allocation
net: hns: Fix kernel-doc
sctp: fix the proc_handler for sysctl encap_port
sctp: add the missing setting for asoc encap_port
bpf, selftests: Adjust few selftest result_unpriv outcomes
bpf: No need to simulate speculative domain for immediates
bpf: Fix mask direction swap upon off reg sign change
bpf: Wrap aux data inside bpf_sanitize_info container
bpf: Fix BPF_LSM kconfig symbol dependency
selftests/bpf: Add test for l3 use of bpf_redirect_peer
bpftool: Add sock_release help info for cgroup attach/prog load command
net: dsa: microchip: enable phy errata workaround on 9567
...
Commit:
00b89fe019 ("sched: Make the idle task quack like a per-CPU kthread")
... added PF_KTHREAD | PF_NO_SETAFFINITY to the idle kernel threads.
Unfortunately these properties are inherited to the init/0 children
through kernel_thread() calls: init/1 and kthreadd. There are several
side effects to that:
1) kthreadd affinity can not be reset anymore from userspace. Also
PF_NO_SETAFFINITY propagates to all kthreadd children, including
the unbound kthreads Therefore it's not possible anymore to overwrite
the affinity of any of them. Here is an example of warning reported
by rcutorture:
WARNING: CPU: 0 PID: 116 at kernel/rcu/tree_nocb.h:1306 rcu_bind_current_to_nocb+0x31/0x40
Call Trace:
rcu_torture_fwd_prog+0x62/0x730
kthread+0x122/0x140
ret_from_fork+0x22/0x30
2) init/1 does an exec() in the end which clears both
PF_KTHREAD and PF_NO_SETAFFINITY so we are fine once kernel_init()
escapes to userspace. But until then, no initcall or init code can
successfully call sched_setaffinity() to init/1.
Also PF_KTHREAD looks legit on init/1 before it calls exec() but
we better be careful with unknown introduced side effects.
One way to solve the PF_NO_SETAFFINITY issue is to not inherit this flag
on copy_process() at all. The cases where it matters are:
* fork_idle(): explicitly set the flag already.
* fork() syscalls: userspace tasks that shouldn't be concerned by that.
* create_io_thread(): the callers explicitly attribute the flag to the
newly created tasks.
* kernel_thread():
- Fix the issues on init/1 and kthreadd
- Fix the issues on kthreadd children.
- Usermode helper created by an unbound workqueue. This shouldn't
matter. In the worst case it gives more control to userspace
on setting affinity to these short living tasks although this can
be tuned with inherited unbound workqueues affinity already.
Fixes: 00b89fe019 ("sched: Make the idle task quack like a per-CPU kthread")
Reported-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Paul E. McKenney <paulmck@kernel.org>
Link: https://lore.kernel.org/r/20210525235849.441842-1-frederic@kernel.org
In 801c6058d1 ("bpf: Fix leakage of uninitialized bpf stack under
speculation") we replaced masking logic with direct loads of immediates
if the register is a known constant. Given in this case we do not apply
any masking, there is also no reason for the operation to be truncated
under the speculative domain.
Therefore, there is also zero reason for the verifier to branch-off and
simulate this case, it only needs to do it for unknown but bounded scalars.
As a side-effect, this also enables few test cases that were previously
rejected due to simulation under zero truncation.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Piotr Krysiuk <piotras@gmail.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Masking direction as indicated via mask_to_left is considered to be
calculated once and then used to derive pointer limits. Thus, this
needs to be placed into bpf_sanitize_info instead so we can pass it
to sanitize_ptr_alu() call after the pointer move. Piotr noticed a
corner case where the off reg causes masking direction change which
then results in an incorrect final aux->alu_limit.
Fixes: 7fedb63a83 ("bpf: Tighten speculative pointer arithmetic mask")
Reported-by: Piotr Krysiuk <piotras@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Piotr Krysiuk <piotras@gmail.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Add a container structure struct bpf_sanitize_info which holds
the current aux info, and update call-sites to sanitize_ptr_alu()
to pass it in. This is needed for passing in additional state
later on.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Piotr Krysiuk <piotras@gmail.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Similarly as 6bdacdb48e ("bpf: Fix BPF_JIT kconfig symbol dependency") we
need to detangle the hard BPF_LSM dependency on NET. This was previously
implicit by its dependency on BPF_JIT which itself was dependent on NET (but
without any actual/real hard dependency code-wise). Given the latter was
lifted, so should be the former as BPF_LSMs could well exist on net-less
systems. This therefore also fixes a randconfig build error recently reported
by Randy:
ld: kernel/bpf/bpf_lsm.o: in function `bpf_lsm_func_proto':
bpf_lsm.c:(.text+0x1a0): undefined reference to `bpf_sk_storage_get_proto'
ld: bpf_lsm.c:(.text+0x1b8): undefined reference to `bpf_sk_storage_delete_proto'
[...]
Fixes: b24abcff91 ("bpf, kconfig: Add consolidated menu entry for bpf with core options")
Reported-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Tested-by: Randy Dunlap <rdunlap@infradead.org>
Pull cgroup fixes from Tejun Heo:
- "cgroup_disable=" boot param was being applied too late confusing
some subsystems. Fix it by moving application to __setup() time.
- Comment spelling fixes. Included here to lower the chance of trivial
future merge conflicts.
* 'for-5.13-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
cgroup: fix spelling mistakes
cgroup: disable controllers at parse time
Pull workqueue fix from Tejun Heo:
"One commit to fix spurious workqueue stall warnings across VM
suspensions"
* 'for-5.13-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/wq:
wq: handle VM suspension in stall detection
Fix some spelling mistakes in comments:
hierarhcy ==> hierarchy
automtically ==> automatically
overriden ==> overridden
In absense of .. or ==> In absence of .. and
assocaited ==> associated
taget ==> target
initate ==> initiate
succeded ==> succeeded
curremt ==> current
udpated ==> updated
Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Pull locking fixes from Thomas Gleixner:
"Two locking fixes:
- Invoke the lockdep tracepoints in the correct place so the ordering
is correct again
- Don't leave the mutex WAITER bit stale when the last waiter is
dropping out early due to a signal as that forces all subsequent
lock operations needlessly into the slowpath until it's cleaned up
again"
* tag 'locking-urgent-2021-05-23' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
locking/mutex: clear MUTEX_FLAGS if wait_list is empty due to signal
locking/lockdep: Correct calling tracepoints
Commit 9bf3bc949f ("watchdog: cleanup handling of false positives")
tried to handle a virtual host stopped by the host a more
straightforward and cleaner way.
But it introduced a risk of false softlockup reports. The virtual host
might be stopped at any time, for example between
kvm_check_and_clear_guest_paused() and is_softlockup(). As a result,
is_softlockup() might read the updated jiffies and detects a softlockup.
A solution might be to put back kvm_check_and_clear_guest_paused() after
is_softlockup() and detect it. But it would put back the cycle that
complicates the logic.
In fact, the handling of all the timestamps is not reliable. The code
does not guarantee when and how many times the timestamps are read. For
example, "period_ts" might be touched anytime also from NMI and re-read in
is_softlockup(). It works just by chance.
Fix all the problems by making the code even more explicit.
1. Make sure that "now" and "period_ts" timestamps are read only once.
They might be changed at anytime by NMI or when the virtual guest is
stopped by the host. Note that "now" timestamp does this implicitly
because "jiffies" is marked volatile.
2. "now" time must be read first. The state of "period_ts" will
decide whether it will be used or the period will get restarted.
3. kvm_check_and_clear_guest_paused() must be called before reading
"period_ts". It touches the variable when the guest was stopped.
As a result, "now" timestamp is used only when the watchdog was not
touched and the guest not stopped in the meantime. "period_ts" is
restarted in all other situations.
Link: https://lkml.kernel.org/r/YKT55gw+RZfyoFf7@alley
Fixes: 9bf3bc949f ("watchdog: cleanup handling of false positives")
Signed-off-by: Petr Mladek <pmladek@suse.com>
Reported-by: Sergey Senozhatsky <senozhatsky@chromium.org>
Reviewed-by: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Pull siginfo fix from Eric Biederman:
"During the merge window an issue with si_perf and the siginfo ABI came
up. The alpha and sparc siginfo structure layout had changed with the
addition of SIGTRAP TRAP_PERF and the new field si_perf.
The reason only alpha and sparc were affected is that they are the
only architectures that use si_trapno.
Looking deeper it was discovered that si_trapno is used for only a few
select signals on alpha and sparc, and that none of the other
_sigfault fields past si_addr are used at all. Which means technically
no regression on alpha and sparc.
While the alignment concerns might be dismissed the abuse of si_errno
by SIGTRAP TRAP_PERF does have the potential to cause regressions in
existing userspace.
While we still have time before userspace starts using and depending
on the new definition siginfo for SIGTRAP TRAP_PERF this set of
changes cleans up siginfo_t.
- The si_trapno field is demoted from magic alpha and sparc status
and made an ordinary union member of the _sigfault member of
siginfo_t. Without moving it of course.
- si_perf is replaced with si_perf_data and si_perf_type ending the
abuse of si_errno.
- Unnecessary additions to signalfd_siginfo are removed"
* 'for-v5.13-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace:
signalfd: Remove SIL_PERF_EVENT fields from signalfd_siginfo
signal: Deliver all of the siginfo perf data in _perf
signal: Factor force_sig_perf out of perf_sigtrap
signal: Implement SIL_FAULT_TRAPNO
siginfo: Move si_trapno inside the union inside _si_fault
Pull module fix from Jessica Yu:
"When CONFIG_MODULE_UNLOAD=n, module exit sections get sorted into the
init region of the module in order to satisfy the requirements of
jump_labels and static_calls.
Previously, the exit section check was done in module_init_section(),
but the solution there is not completely arch-indepedent as ARM is a
special case and supplies its own module_init_section() function.
Instead of pushing this logic further to the arch-specific code,
switch to an arch-independent solution to check for module exit
sections in the core module loader code in layout_sections() instead"
* tag 'modules-for-v5.13-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/jeyu/linux:
module: check for exit sections in layout_sections() instead of module_init_section()
Pull kcsan fix from Paul McKenney:
"Fix for a regression introduced in this merge window by commit
e36299efe7 ("kcsan, debugfs: Move debugfs file creation out of early
init").
The regression is not easy to trigger, requiring a KCSAN build using
clang with CONFIG_LTO_CLANG=y. The fix is to simply make the
kcsan_debugfs_init() function's type initcall-compatible. This has
been posted to the relevant mailing lists:"
* 'urgent.2021.05.20a' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu:
kcsan: Fix debugfs initcall return type
The cppcheck static code analysis reported the following error:
if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(bufs->tmp_bufs))) {
^
ARRAY_SIZE is a macro that expands to sizeofs, so bufs is not actually
dereferenced at runtime, and the code is actually safe. But to keep
things tidy, this patch removes the need for a call to ARRAY_SIZE by
extracting the size of the array into a macro. Cppcheck should no longer
be confused and the code ends up being a bit cleaner.
Fixes: e2d5b2bb76 ("bpf: Fix nested bpf_bprintf_prepare with more per-cpu buffers")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Florent Revest <revest@chromium.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/bpf/20210517092830.1026418-2-revest@chromium.org
Randy reported a randconfig build error recently on i386:
ld: arch/x86/net/bpf_jit_comp32.o: in function `do_jit':
bpf_jit_comp32.c:(.text+0x28c9): undefined reference to `__bpf_call_base'
ld: arch/x86/net/bpf_jit_comp32.o: in function `bpf_int_jit_compile':
bpf_jit_comp32.c:(.text+0x3694): undefined reference to `bpf_jit_blind_constants'
ld: bpf_jit_comp32.c:(.text+0x3719): undefined reference to `bpf_jit_binary_free'
ld: bpf_jit_comp32.c:(.text+0x3745): undefined reference to `bpf_jit_binary_alloc'
ld: bpf_jit_comp32.c:(.text+0x37d3): undefined reference to `bpf_jit_prog_release_other'
[...]
The cause was that b24abcff91 ("bpf, kconfig: Add consolidated menu entry for
bpf with core options") moved BPF_JIT from net/Kconfig into kernel/bpf/Kconfig
and previously BPF_JIT was guarded by a 'if NET'. However, there is no actual
dependency on NET, it's just that menuconfig NET selects BPF. And the latter in
turn causes kernel/bpf/core.o to be built which contains above symbols. Randy's
randconfig didn't have NET set, and BPF wasn't either, but BPF_JIT otoh was.
Detangle this by making BPF_JIT depend on BPF instead. arm64 was the only arch
that pulled in its JIT in net/ via obj-$(CONFIG_NET), all others unconditionally
pull this dir in via obj-y. Do the same since CONFIG_NET guard there is really
useless as we compiled the JIT via obj-$(CONFIG_BPF_JIT) += bpf_jit_comp.o anyway.
Fixes: b24abcff91 ("bpf, kconfig: Add consolidated menu entry for bpf with core options")
Reported-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Tested-by: Randy Dunlap <rdunlap@infradead.org>
If VCPU is suspended (VM suspend) in wq_watchdog_timer_fn() then
once this VCPU resumes it will see the new jiffies value, while it
may take a while before IRQ detects PVCLOCK_GUEST_STOPPED on this
VCPU and updates all the watchdogs via pvclock_touch_watchdogs().
There is a small chance of misreported WQ stalls in the meantime,
because new jiffies is time_after() old 'ts + thresh'.
wq_watchdog_timer_fn()
{
for_each_pool(pool, pi) {
if (time_after(jiffies, ts + thresh)) {
pr_emerg("BUG: workqueue lockup - pool");
}
}
}
Save jiffies at the beginning of this function and use that value
for stall detection. If VM gets suspended then we continue using
"old" jiffies value and old WQ touch timestamps. If IRQ at some
point restarts the stall detection cycle (pvclock_touch_watchdogs())
then old jiffies will always be before new 'ts + thresh'.
Signed-off-by: Sergey Senozhatsky <senozhatsky@chromium.org>
Signed-off-by: Tejun Heo <tj@kernel.org>
This patch effectively reverts the commit a3e72739b7 ("cgroup: fix
too early usage of static_branch_disable()"). The commit 6041186a32
("init: initialize jump labels before command line option parsing") has
moved the jump_label_init() before parse_args() which has made the
commit a3e72739b7 unnecessary. On the other hand there are
consequences of disabling the controllers later as there are subsystems
doing the controller checks for different decisions. One such incident
is reported [1] regarding the memory controller and its impact on memory
reclaim code.
[1] https://lore.kernel.org/linux-mm/921e53f3-4b13-aab8-4a9e-e83ff15371e4@nec.com
Signed-off-by: Shakeel Butt <shakeelb@google.com>
Reported-by: NOMURA JUNICHI(野村 淳一) <junichi.nomura@nec.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Tested-by: Jun'ichi Nomura <junichi.nomura@nec.com>
cpu_cgroup_css_online() calls cpu_util_update_eff() without holding the
uclamp_mutex or rcu_read_lock() like other call sites, which is
a mistake.
The uclamp_mutex is required to protect against concurrent reads and
writes that could update the cgroup hierarchy.
The rcu_read_lock() is required to traverse the cgroup data structures
in cpu_util_update_eff().
Surround the caller with the required locks and add some asserts to
better document the dependency in cpu_util_update_eff().
Fixes: 7226017ad3 ("sched/uclamp: Fix a bug in propagating uclamp value in new cgroups")
Reported-by: Quentin Perret <qperret@google.com>
Signed-off-by: Qais Yousef <qais.yousef@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210510145032.1934078-3-qais.yousef@arm.com
cpu.uclamp.min is a protection as described in cgroup-v2 Resource
Distribution Model
Documentation/admin-guide/cgroup-v2.rst
which means we try our best to preserve the minimum performance point of
tasks in this group. See full description of cpu.uclamp.min in the
cgroup-v2.rst.
But the current implementation makes it a limit, which is not what was
intended.
For example:
tg->cpu.uclamp.min = 20%
p0->uclamp[UCLAMP_MIN] = 0
p1->uclamp[UCLAMP_MIN] = 50%
Previous Behavior (limit):
p0->effective_uclamp = 0
p1->effective_uclamp = 20%
New Behavior (Protection):
p0->effective_uclamp = 20%
p1->effective_uclamp = 50%
Which is inline with how protections should work.
With this change the cgroup and per-task behaviors are the same, as
expected.
Additionally, we remove the confusing relationship between cgroup and
!user_defined flag.
We don't want for example RT tasks that are boosted by default to max to
change their boost value when they attach to a cgroup. If a cgroup wants
to limit the max performance point of tasks attached to it, then
cpu.uclamp.max must be set accordingly.
Or if they want to set different boost value based on cgroup, then
sysctl_sched_util_clamp_min_rt_default must be used to NOT boost to max
and set the right cpu.uclamp.min for each group to let the RT tasks
obtain the desired boost value when attached to that group.
As it stands the dependency on !user_defined flag adds an extra layer of
complexity that is not required now cpu.uclamp.min behaves properly as
a protection.
The propagation model of effective cpu.uclamp.min in child cgroups as
implemented by cpu_util_update_eff() is still correct. The parent
protection sets an upper limit of what the child cgroups will
effectively get.
Fixes: 3eac870a32 (sched/uclamp: Use TG's clamps to restrict TASK's clamps)
Signed-off-by: Qais Yousef <qais.yousef@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210510145032.1934078-2-qais.yousef@arm.com
It turns out that linux uses si_trapno very sparingly, and as such it
can be considered extra information for a very narrow selection of
signals, rather than information that is present with every fault
reported in siginfo.
As such move si_trapno inside the union inside of _si_fault. This
results in no change in placement, and makes it eaiser
to extend _si_fault in the future as this reduces the number of
special cases. In particular with si_trapno included in the union it
is no longer a concern that the union must be pointer aligned on most
architectures because the union follows immediately after si_addr
which is a pointer.
This change results in a difference in siginfo field placement on
sparc and alpha for the fields si_addr_lsb, si_lower, si_upper,
si_pkey, and si_perf. These architectures do not implement the
signals that would use si_addr_lsb, si_lower, si_upper, si_pkey, and
si_perf. Further these architecture have not yet implemented the
userspace that would use si_perf.
The point of this change is in fact to correct these placement issues
before sparc or alpha grow userspace that cares. This change was
discussed[1] and the agreement is that this change is currently safe.
[1]: https://lkml.kernel.org/r/CAK8P3a0+uKYwL1NhY6Hvtieghba2hKYGD6hcKx5n8=4Gtt+pHA@mail.gmail.com
Acked-by: Marco Elver <elver@google.com>
v1: https://lkml.kernel.org/r/m1tunns7yf.fsf_-_@fess.ebiederm.org
v2: https://lkml.kernel.org/r/20210505141101.11519-5-ebiederm@xmission.com
Link: https://lkml.kernel.org/r/20210517195748.8880-1-ebiederm@xmission.com
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
clang with CONFIG_LTO_CLANG points out that an initcall function should
return an 'int' due to the changes made to the initcall macros in commit
3578ad11f3 ("init: lto: fix PREL32 relocations"):
kernel/kcsan/debugfs.c:274:15: error: returning 'void' from a function with incompatible result type 'int'
late_initcall(kcsan_debugfs_init);
~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~
include/linux/init.h:292:46: note: expanded from macro 'late_initcall'
#define late_initcall(fn) __define_initcall(fn, 7)
Fixes: e36299efe7 ("kcsan, debugfs: Move debugfs file creation out of early init")
Cc: stable <stable@vger.kernel.org>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Marco Elver <elver@google.com>
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
Reviewed-by: Miguel Ojeda <ojeda@kernel.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
For all intents and purposes, the idle task is a per-CPU kthread. It isn't
created via the same route as other pcpu kthreads however, and as a result
it is missing a few bells and whistles: it fails kthread_is_per_cpu() and
it doesn't have PF_NO_SETAFFINITY set.
Fix the former by giving the idle task a kthread struct along with the
KTHREAD_IS_PER_CPU flag. This requires some extra iffery as init_idle()
call be called more than once on the same idle task.
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210510151024.2448573-2-valentin.schneider@arm.com
When a interruptible mutex locker is interrupted by a signal
without acquiring this lock and removed from the wait queue.
if the mutex isn't contended enough to have a waiter
put into the wait queue again, the setting of the WAITER
bit will force mutex locker to go into the slowpath to
acquire the lock every time, so if the wait queue is empty,
the WAITER bit need to be clear.
Fixes: 040a0a3710 ("mutex: Add support for wound/wait style locks")
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Zqiang <qiang.zhang@windriver.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20210517034005.30828-1-qiang.zhang@windriver.com
Previously, when CONFIG_MODULE_UNLOAD=n, the module loader just does not
attempt to load exit sections since it never expects that any code in those
sections will ever execute. However, dynamic code patching (alternatives,
jump_label and static_call) can have sites in __exit code, even if __exit is
never executed. Therefore __exit must be present at runtime, at least for as
long as __init code is.
Commit 33121347fb ("module: treat exit sections the same as init
sections when !CONFIG_MODULE_UNLOAD") solves the requirements of
jump_labels and static_calls by putting the exit sections in the init
region of the module so that they are at least present at init, and
discarded afterwards. It does this by including a check for exit
sections in module_init_section(), so that it also returns true for exit
sections, and the module loader will automatically sort them in the init
region of the module.
However, the solution there was not completely arch-independent. ARM is
a special case where it supplies its own module_{init, exit}_section()
functions. Instead of pushing the exit section checks into
module_init_section(), just implement the exit section check in
layout_sections(), so that we don't have to touch arch-dependent code.
Fixes: 33121347fb ("module: treat exit sections the same as init sections when !CONFIG_MODULE_UNLOAD")
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: Jessica Yu <jeyu@kernel.org>
