linux.git/kernel/cpu.c, branch v4.20-rc2

Merge branch 'x86-pti-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

2018-10-23T17:43:04+00:00

Pull x86 pti updates from Ingo Molnar:
 "The main changes:

   - Make the IBPB barrier more strict and add STIBP support (Jiri
     Kosina)

   - Micro-optimize and clean up the entry code (Andy Lutomirski)

   - ... plus misc other fixes"

* 'x86-pti-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/speculation: Propagate information about RSB filling mitigation to sysfs
  x86/speculation: Enable cross-hyperthread spectre v2 STIBP mitigation
  x86/speculation: Apply IBPB more strictly to avoid cross-process data leak
  x86/speculation: Add RETPOLINE_AMD support to the inline asm CALL_NOSPEC variant
  x86/CPU: Fix unused variable warning when !CONFIG_IA32_EMULATION
  x86/pti/64: Remove the SYSCALL64 entry trampoline
  x86/entry/64: Use the TSS sp2 slot for SYSCALL/SYSRET scratch space
  x86/entry/64: Document idtentry

Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

2018-10-23T14:00:03+00:00

Pull scheduler updates from Ingo Molnar:
 "The main changes are:

   - Migrate CPU-intense 'misfit' tasks on asymmetric capacity systems,
     to better utilize (much) faster 'big core' CPUs. (Morten Rasmussen,
     Valentin Schneider)

   - Topology handling improvements, in particular when CPU capacity
     changes and related load-balancing fixes/improvements (Morten
     Rasmussen)

   - ... plus misc other improvements, fixes and updates"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (28 commits)
  sched/completions/Documentation: Add recommendation for dynamic and ONSTACK completions
  sched/completions/Documentation: Clean up the document some more
  sched/completions/Documentation: Fix a couple of punctuation nits
  cpu/SMT: State SMT is disabled even with nosmt and without "=force"
  sched/core: Fix comment regarding nr_iowait_cpu() and get_iowait_load()
  sched/fair: Remove setting task's se->runnable_weight during PELT update
  sched/fair: Disable LB_BIAS by default
  sched/pelt: Fix warning and clean up IRQ PELT config
  sched/topology: Make local variables static
  sched/debug: Use symbolic names for task state constants
  sched/numa: Remove unused numa_stats::nr_running field
  sched/numa: Remove unused code from update_numa_stats()
  sched/debug: Explicitly cast sched_feat() to bool
  sched/core: Disable SD_PREFER_SIBLING on asymmetric CPU capacity domains
  sched/fair: Don't move tasks to lower capacity CPUs unless necessary
  sched/fair: Set rq->rd->overload when misfit
  sched/fair: Wrap rq->rd->overload accesses with READ/WRITE_ONCE()
  sched/core: Change root_domain->overload type to int
  sched/fair: Change 'prefer_sibling' type to bool
  sched/fair: Kick nohz balance if rq->misfit_task_load
  ...

cpu/SMT: State SMT is disabled even with nosmt and without "=force"

2018-10-05T08:20:31+00:00

When booting with "nosmt=force" a message is issued into dmesg to
confirm that SMT has been force-disabled but such a message is not
issued when only "nosmt" is on the kernel command line.

Fix that.

Signed-off-by: Borislav Petkov 
Cc: Linus Torvalds 
Cc: Peter Zijlstra 
Cc: Thomas Gleixner 
Link: http://lkml.kernel.org/r/20181004172227.10094-1-bp@alien8.de
Signed-off-by: Ingo Molnar

x86/speculation: Enable cross-hyperthread spectre v2 STIBP mitigation

2018-09-26T12:26:52+00:00

STIBP is a feature provided by certain Intel ucodes / CPUs. This feature
(once enabled) prevents cross-hyperthread control of decisions made by
indirect branch predictors.

Enable this feature if

- the CPU is vulnerable to spectre v2
- the CPU supports SMT and has SMT siblings online
- spectre_v2 mitigation autoselection is enabled (default)

After some previous discussion, this leaves STIBP on all the time, as wrmsr
on crossing kernel boundary is a no-no. This could perhaps later be a bit
more optimized (like disabling it in NOHZ, experiment with disabling it in
idle, etc) if needed.

Note that the synchronization of the mask manipulation via newly added
spec_ctrl_mutex is currently not strictly needed, as the only updater is
already being serialized by cpu_add_remove_lock, but let's make this a
little bit more future-proof.

Signed-off-by: Jiri Kosina 
Signed-off-by: Thomas Gleixner 
Cc: Peter Zijlstra 
Cc: Josh Poimboeuf 
Cc: Andrea Arcangeli 
Cc:  "WoodhouseDavid" 
Cc: Andi Kleen 
Cc: Tim Chen 
Cc:  "SchauflerCasey" 
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/nycvar.YFH.7.76.1809251438240.15880@cbobk.fhfr.pm

locking/lockdep, cpu/hotplug: Annotate AP thread

2018-09-11T18:01:03+00:00

Anybody trying to assert the cpu_hotplug_lock is held (lockdep_assert_cpus_held())
from AP callbacks will fail, because the lock is held by the BP.

Stick in an explicit annotation in cpuhp_thread_fun() to make this work.

Reported-by: Ingo Molnar 
Signed-off-by: Peter Zijlstra (Intel) 
Cc: Linus Torvalds 
Cc: Peter Zijlstra 
Cc: Thomas Gleixner 
Cc: linux-tip-commits@vger.kernel.org
Fixes: cb538267ea1e ("jump_label/lockdep: Assert we hold the hotplug lock for _cpuslocked() operations")
Link: http://lkml.kernel.org/r/20180911095127.GT24082@hirez.programming.kicks-ass.net
Signed-off-by: Ingo Molnar

cpu/hotplug: Prevent state corruption on error rollback

2018-09-06T13:21:38+00:00

When a teardown callback fails, the CPU hotplug code brings the CPU back to
the previous state. The previous state becomes the new target state. The
rollback happens in undo_cpu_down() which increments the state
unconditionally even if the state is already the same as the target.

As a consequence the next CPU hotplug operation will start at the wrong
state. This is easily to observe when __cpu_disable() fails.

Prevent the unconditional undo by checking the state vs. target before
incrementing state and fix up the consequently wrong conditional in the
unplug code which handles the failure of the final CPU take down on the
control CPU side.

Fixes: 4dddfb5faa61 ("smp/hotplug: Rewrite AP state machine core")
Reported-by: Neeraj Upadhyay 
Signed-off-by: Thomas Gleixner 
Tested-by: Geert Uytterhoeven 
Tested-by: Sudeep Holla 
Tested-by: Neeraj Upadhyay 
Cc: josh@joshtriplett.org
Cc: peterz@infradead.org
Cc: jiangshanlai@gmail.com
Cc: dzickus@redhat.com
Cc: brendan.jackman@arm.com
Cc: malat@debian.org
Cc: sramana@codeaurora.org
Cc: linux-arm-msm@vger.kernel.org
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/alpine.DEB.2.21.1809051419580.1416@nanos.tec.linutronix.de

----

cpu/hotplug: Adjust misplaced smb() in cpuhp_thread_fun()

2018-09-06T13:21:37+00:00

The smp_mb() in cpuhp_thread_fun() is misplaced. It needs to be after the
load of st->should_run to prevent reordering of the later load/stores
w.r.t. the load of st->should_run.

Fixes: 4dddfb5faa61 ("smp/hotplug: Rewrite AP state machine core")
Signed-off-by: Neeraj Upadhyay 
Signed-off-by: Thomas Gleixner 
Acked-by: Peter Zijlstra (Intel) 
Cc: josh@joshtriplett.org
Cc: peterz@infradead.org
Cc: jiangshanlai@gmail.com
Cc: dzickus@redhat.com
Cc: brendan.jackman@arm.com
Cc: malat@debian.org
Cc: mojha@codeaurora.org
Cc: sramana@codeaurora.org
Cc: linux-arm-msm@vger.kernel.org
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/1536126727-11629-1-git-send-email-neeraju@codeaurora.org

cpu/hotplug: Remove skip_onerr field from cpuhp_step structure

2018-08-31T12:13:03+00:00

When notifiers were there, `skip_onerr` was used to avoid calling
particular step startup/teardown callbacks in the CPU up/down rollback
path, which made the hotplug asymmetric.

As notifiers are gone now after the full state machine conversion, the
`skip_onerr` field is no longer required.

Remove it from the structure and its usage.

Signed-off-by: Mukesh Ojha 
Signed-off-by: Thomas Gleixner 
Acked-by: Peter Zijlstra (Intel) 
Link: https://lkml.kernel.org/r/1535439294-31426-1-git-send-email-mojha@codeaurora.org

cpu/hotplug: Non-SMP machines do not make use of booted_once

2018-08-14T22:00:00+00:00

Commit 0cc3cd21657b ("cpu/hotplug: Boot HT siblings at least once")
breaks non-SMP builds.

[ I suspect the 'bool' fields should just be made to be bitfields and be
  exposed regardless of configuration, but that's a separate cleanup
  that I'll leave to the owners of this file for later.   - Linus ]

Fixes: 0cc3cd21657b ("cpu/hotplug: Boot HT siblings at least once")
Cc: Dave Hansen 
Cc: Thomas Gleixner 
Cc: Tony Luck 
Signed-off-by: Abel Vesa 
Signed-off-by: Linus Torvalds

Merge tag 'pm-4.19-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

2018-08-14T20:12:24+00:00

Pull power management updates from Rafael Wysocki:
"These add a new framework for CPU idle time injection, to be used by
all of the idle injection code in the kernel in the future, fix some
issues and add a number of relatively small extensions in multiple
places.

Specifics:

- Add a new framework for CPU idle time injection (Daniel Lezcano).

- Add AVS support to the armada-37xx cpufreq driver (Gregory
CLEMENT).

- Add support for current CPU frequency reporting to the ACPI CPPC
cpufreq driver (George Cherian).

- Rework the cooling device registration in the imx6q/thermal driver
(Bastian Stender).

- Make the pcc-cpufreq driver refuse to work with dynamic scaling
governors on systems with many CPUs to avoid scalability issues
with it (Rafael Wysocki).

- Fix the intel_pstate driver to report different maximum CPU
frequencies on systems where they really are different and to
ignore the turbo active ratio if hardware-managend P-states (HWP)
are in use; make it use the match_string() helper (Xie Yisheng,
Srinivas Pandruvada).

- Fix a minor deferred probe issue in the qcom-kryo cpufreq driver
(Niklas Cassel).

- Add a tracepoint for the tracking of frequency limits changes (from
Andriod) to the cpufreq core (Ruchi Kandoi).

- Fix a circular lock dependency between CPU hotplug and sysfs
locking in the cpufreq core reported by lockdep (Waiman Long).

- Avoid excessive error reports on driver registration failures in
the ARM cpuidle driver (Sudeep Holla).

- Add a new device links flag to the driver core to make links go
away automatically on supplier driver removal (Vivek Gautam).

- Eliminate potential race condition between system-wide power
management transitions and system shutdown (Pingfan Liu).

- Add a quirk to save NVS memory on system suspend for the ASUS 1025C
laptop (Willy Tarreau).

- Make more systems use suspend-to-idle (instead of ACPI S3) by
default (Tristian Celestin).

- Get rid of stack VLA usage in the low-level hibernation code on
64-bit x86 (Kees Cook).

- Fix error handling in the hibernation core and mark an expected
fall-through switch in it (Chengguang Xu, Gustavo Silva).

- Extend the generic power domains (genpd) framework to support
attaching a device to a power domain by name (Ulf Hansson).

- Fix device reference counting and user limits initialization in the
devfreq core (Arvind Yadav, Matthias Kaehlcke).

- Fix a few issues in the rk3399_dmc devfreq driver and improve its
documentation (Enric Balletbo i Serra, Lin Huang, Nick Milner).

- Drop a redundant error message from the exynos-ppmu devfreq driver
(Markus Elfring)"

* tag 'pm-4.19-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (35 commits)
PM / reboot: Eliminate race between reboot and suspend
PM / hibernate: Mark expected switch fall-through
cpufreq: intel_pstate: Ignore turbo active ratio in HWP
cpufreq: Fix a circular lock dependency problem
cpu/hotplug: Add a cpus_read_trylock() function
x86/power/hibernate_64: Remove VLA usage
cpufreq: trace frequency limits change
cpufreq: intel_pstate: Show different max frequency with turbo 3 and HWP
cpufreq: pcc-cpufreq: Disable dynamic scaling on many-CPU systems
cpufreq: qcom-kryo: Silently error out on EPROBE_DEFER
cpufreq / CPPC: Add cpuinfo_cur_freq support for CPPC
cpufreq: armada-37xx: Add AVS support
dt-bindings: marvell: Add documentation for the Armada 3700 AVS binding
PM / devfreq: rk3399_dmc: Fix duplicated opp table on reload.
PM / devfreq: Init user limits from OPP limits, not viceversa
PM / devfreq: rk3399_dmc: fix spelling mistakes.
PM / devfreq: rk3399_dmc: do not print error when get supply and clk defer.
dt-bindings: devfreq: rk3399_dmc: move interrupts to be optional.
PM / devfreq: rk3399_dmc: remove wait for dcf irq event.
dt-bindings: clock: add rk3399 DDR3 standard speed bins.
...