Commit Graph

3086 Commits

Author SHA1 Message Date
3b80dee70e Merge tag 'sched-urgent-2020-12-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler fix from Ingo Molnar:
 "Fix a context switch performance regression"

* tag 'sched-urgent-2020-12-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched: Optimize finish_lock_switch()
2020-12-27 09:00:47 -08:00
4960821a4d Merge tag 'pm-5.11-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm
Pull more power management updates from Rafael Wysocki:
 "These update the CPPC cpufreq driver and intel_pstate (which involves
  updating the cpufreq core and the schedutil governor) and make
  janitorial changes in the ACPI code handling processor objects.

  Specifics:

   - Rework the passive-mode "fast switch" path in the intel_pstate
     driver to allow it receive the minimum (required) and target
     (desired) performance information from the schedutil governor so as
     to avoid running some workloads too fast (Rafael Wysocki).

   - Make the intel_pstate driver allow the policy max limit to be
     increased after the guaranteed performance value for the given CPU
     has increased (Rafael Wysocki).

   - Clean up the handling of CPU coordination types in the CPPC cpufreq
     driver and make it export frequency domains information to user
     space via sysfs (Ionela Voinescu).

   - Fix the ACPI code handling processor objects to use a correct
     coordination type when it fails to map frequency domains and drop a
     redundant CPU map initialization from it (Ionela Voinescu, Punit
     Agrawal)"

* tag 'pm-5.11-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  cpufreq: intel_pstate: Use most recent guaranteed performance values
  cpufreq: intel_pstate: Implement the ->adjust_perf() callback
  cpufreq: Add special-purpose fast-switching callback for drivers
  cpufreq: schedutil: Add util to struct sg_cpu
  cppc_cpufreq: replace per-cpu data array with a list
  cppc_cpufreq: expose information on frequency domains
  cppc_cpufreq: clarify support for coordination types
  cppc_cpufreq: use policy->cpu as driver of frequency setting
  ACPI: processor: fix NONE coordination for domain mapping failure
2020-12-22 14:12:10 -08:00
c3a74f8e25 Merge branch 'pm-cpufreq'
* pm-cpufreq:
  cpufreq: intel_pstate: Use most recent guaranteed performance values
  cpufreq: intel_pstate: Implement the ->adjust_perf() callback
  cpufreq: Add special-purpose fast-switching callback for drivers
  cpufreq: schedutil: Add util to struct sg_cpu
  cppc_cpufreq: replace per-cpu data array with a list
  cppc_cpufreq: expose information on frequency domains
  cppc_cpufreq: clarify support for coordination types
  cppc_cpufreq: use policy->cpu as driver of frequency setting
  ACPI: processor: fix NONE coordination for domain mapping failure
  ACPI: processor: Drop duplicate setting of shared_cpu_map
2020-12-22 17:59:11 +01:00
6a447b0e31 Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull KVM updates from Paolo Bonzini:
 "Much x86 work was pushed out to 5.12, but ARM more than made up for it.

  ARM:
   - PSCI relay at EL2 when "protected KVM" is enabled
   - New exception injection code
   - Simplification of AArch32 system register handling
   - Fix PMU accesses when no PMU is enabled
   - Expose CSV3 on non-Meltdown hosts
   - Cache hierarchy discovery fixes
   - PV steal-time cleanups
   - Allow function pointers at EL2
   - Various host EL2 entry cleanups
   - Simplification of the EL2 vector allocation

  s390:
   - memcg accouting for s390 specific parts of kvm and gmap
   - selftest for diag318
   - new kvm_stat for when async_pf falls back to sync

  x86:
   - Tracepoints for the new pagetable code from 5.10
   - Catch VFIO and KVM irqfd events before userspace
   - Reporting dirty pages to userspace with a ring buffer
   - SEV-ES host support
   - Nested VMX support for wait-for-SIPI activity state
   - New feature flag (AVX512 FP16)
   - New system ioctl to report Hyper-V-compatible paravirtualization features

  Generic:
   - Selftest improvements"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (171 commits)
  KVM: SVM: fix 32-bit compilation
  KVM: SVM: Add AP_JUMP_TABLE support in prep for AP booting
  KVM: SVM: Provide support to launch and run an SEV-ES guest
  KVM: SVM: Provide an updated VMRUN invocation for SEV-ES guests
  KVM: SVM: Provide support for SEV-ES vCPU loading
  KVM: SVM: Provide support for SEV-ES vCPU creation/loading
  KVM: SVM: Update ASID allocation to support SEV-ES guests
  KVM: SVM: Set the encryption mask for the SVM host save area
  KVM: SVM: Add NMI support for an SEV-ES guest
  KVM: SVM: Guest FPU state save/restore not needed for SEV-ES guest
  KVM: SVM: Do not report support for SMM for an SEV-ES guest
  KVM: x86: Update __get_sregs() / __set_sregs() to support SEV-ES
  KVM: SVM: Add support for CR8 write traps for an SEV-ES guest
  KVM: SVM: Add support for CR4 write traps for an SEV-ES guest
  KVM: SVM: Add support for CR0 write traps for an SEV-ES guest
  KVM: SVM: Add support for EFER write traps for an SEV-ES guest
  KVM: SVM: Support string IO operations for an SEV-ES guest
  KVM: SVM: Support MMIO for an SEV-ES guest
  KVM: SVM: Create trace events for VMGEXIT MSR protocol processing
  KVM: SVM: Create trace events for VMGEXIT processing
  ...
2020-12-20 10:44:05 -08:00
b4ec805464 Merge tag 'pm-5.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm
Pull power management updates from Rafael Wysocki:
 "These update cpufreq (core and drivers), cpuidle (polling state
  implementation and the PSCI driver), the OPP (operating performance
  points) framework, devfreq (core and drivers), the power capping RAPL
  (Running Average Power Limit) driver, the Energy Model support, the
  generic power domains (genpd) framework, the ACPI device power
  management, the core system-wide suspend code and power management
  utilities.

  Specifics:

   - Use local_clock() instead of jiffies in the cpufreq statistics to
     improve accuracy (Viresh Kumar).

   - Fix up OPP usage in the cpufreq-dt and qcom-cpufreq-nvmem cpufreq
     drivers (Viresh Kumar).

   - Clean up the cpufreq core, the intel_pstate driver and the
     schedutil cpufreq governor (Rafael Wysocki).

   - Fix up error code paths in the sti-cpufreq and mediatek cpufreq
     drivers (Yangtao Li, Qinglang Miao).

   - Fix cpufreq_online() to return error codes instead of success (0)
     in all cases when it fails (Wang ShaoBo).

   - Add mt8167 support to the mediatek cpufreq driver and blacklist
     mt8516 in the cpufreq-dt-platdev driver (Fabien Parent).

   - Modify the tegra194 cpufreq driver to always return values from the
     frequency table as the current frequency and clean up that driver
     (Sumit Gupta, Jon Hunter).

   - Modify the arm_scmi cpufreq driver to allow it to discover the
     power scale present in the performance protocol and provide this
     information to the Energy Model (Lukasz Luba).

   - Add missing MODULE_DEVICE_TABLE to several cpufreq drivers (Pali
     Rohár).

   - Clean up the CPPC cpufreq driver (Ionela Voinescu).

   - Fix NVMEM_IMX_OCOTP dependency in the imx cpufreq driver (Arnd
     Bergmann).

   - Rework the poling interval selection for the polling state in
     cpuidle (Mel Gorman).

   - Enable suspend-to-idle for PSCI OSI mode in the PSCI cpuidle driver
     (Ulf Hansson).

   - Modify the OPP framework to support empty (node-less) OPP tables in
     DT for passing dependency information (Nicola Mazzucato).

   - Fix potential lockdep issue in the OPP core and clean up the OPP
     core (Viresh Kumar).

   - Modify dev_pm_opp_put_regulators() to accept a NULL argument and
     update its users accordingly (Viresh Kumar).

   - Add frequency changes tracepoint to devfreq (Matthias Kaehlcke).

   - Add support for governor feature flags to devfreq, make devfreq
     sysfs file permissions depend on the governor and clean up the
     devfreq core (Chanwoo Choi).

   - Clean up the tegra20 devfreq driver and deprecate it to allow
     another driver based on EMC_STAT to be used instead of it (Dmitry
     Osipenko).

   - Add interconnect support to the tegra30 devfreq driver, allow it to
     take the interconnect and OPP information from DT and clean it up
     (Dmitry Osipenko).

   - Add interconnect support to the exynos-bus devfreq driver along
     with interconnect properties documentation (Sylwester Nawrocki).

   - Add suport for AMD Fam17h and Fam19h processors to the RAPL power
     capping driver (Victor Ding, Kim Phillips).

   - Fix handling of overly long constraint names in the powercap
     framework (Lukasz Luba).

   - Fix the wakeup configuration handling for bridges in the ACPI
     device power management core (Rafael Wysocki).

   - Add support for using an abstract scale for power units in the
     Energy Model (EM) and document it (Lukasz Luba).

   - Add em_cpu_energy() micro-optimization to the EM (Pavankumar
     Kondeti).

   - Modify the generic power domains (genpd) framwework to support
     suspend-to-idle (Ulf Hansson).

   - Fix creation of debugfs nodes in genpd (Thierry Strudel).

   - Clean up genpd (Lina Iyer).

   - Clean up the core system-wide suspend code and make it print driver
     flags for devices with debug enabled (Alex Shi, Patrice Chotard,
     Chen Yu).

   - Modify the ACPI system reboot code to make it prepare for system
     power off to avoid confusing the platform firmware (Kai-Heng Feng).

   - Update the pm-graph (multiple changes, mostly usability-related)
     and cpupower (online and offline CPU information support) PM
     utilities (Todd Brandt, Brahadambal Srinivasan)"

* tag 'pm-5.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (86 commits)
  cpufreq: Fix cpufreq_online() return value on errors
  cpufreq: Fix up several kerneldoc comments
  cpufreq: stats: Use local_clock() instead of jiffies
  cpufreq: schedutil: Simplify sugov_update_next_freq()
  cpufreq: intel_pstate: Simplify intel_cpufreq_update_pstate()
  PM: domains: create debugfs nodes when adding power domains
  opp: of: Allow empty opp-table with opp-shared
  dt-bindings: opp: Allow empty OPP tables
  media: venus: dev_pm_opp_put_*() accepts NULL argument
  drm/panfrost: dev_pm_opp_put_*() accepts NULL argument
  drm/lima: dev_pm_opp_put_*() accepts NULL argument
  PM / devfreq: exynos: dev_pm_opp_put_*() accepts NULL argument
  cpufreq: qcom-cpufreq-nvmem: dev_pm_opp_put_*() accepts NULL argument
  cpufreq: dt: dev_pm_opp_put_regulators() accepts NULL argument
  opp: Allow dev_pm_opp_put_*() APIs to accept NULL opp_table
  opp: Don't create an OPP table from dev_pm_opp_get_opp_table()
  cpufreq: dt: Don't (ab)use dev_pm_opp_get_opp_table() to create OPP table
  opp: Reduce the size of critical section in _opp_kref_release()
  PM / EM: Micro optimization in em_cpu_energy
  cpufreq: arm_scmi: Discover the power scale in performance protocol
  ...
2020-12-15 16:30:31 -08:00
2cffa11e2a Merge tag 'irq-core-2020-12-15' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull irq updates from Thomas Gleixner:
 "Generic interrupt and irqchips subsystem updates. Unusually, there is
  not a single completely new irq chip driver, just new DT bindings and
  extensions of existing drivers to accomodate new variants!

  Core:

   - Consolidation and robustness changes for irq time accounting

   - Cleanup and consolidation of irq stats

   - Remove the fasteoi IPI flow which has been proved useless

   - Provide an interface for converting legacy interrupt mechanism into
     irqdomains

  Drivers:

   - Preliminary support for managed interrupts on platform devices

   - Correctly identify allocation of MSIs proxyied by another device

   - Generalise the Ocelot support to new SoCs

   - Improve GICv4.1 vcpu entry, matching the corresponding KVM
     optimisation

   - Work around spurious interrupts on Qualcomm PDC

   - Random fixes and cleanups"

* tag 'irq-core-2020-12-15' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (54 commits)
  irqchip/qcom-pdc: Fix phantom irq when changing between rising/falling
  driver core: platform: Add devm_platform_get_irqs_affinity()
  ACPI: Drop acpi_dev_irqresource_disabled()
  resource: Add irqresource_disabled()
  genirq/affinity: Add irq_update_affinity_desc()
  irqchip/gic-v3-its: Flag device allocation as proxied if behind a PCI bridge
  irqchip/gic-v3-its: Tag ITS device as shared if allocating for a proxy device
  platform-msi: Track shared domain allocation
  irqchip/ti-sci-intr: Fix freeing of irqs
  irqchip/ti-sci-inta: Fix printing of inta id on probe success
  drivers/irqchip: Remove EZChip NPS interrupt controller
  Revert "genirq: Add fasteoi IPI flow"
  irqchip/hip04: Make IPIs use handle_percpu_devid_irq()
  irqchip/bcm2836: Make IPIs use handle_percpu_devid_irq()
  irqchip/armada-370-xp: Make IPIs use handle_percpu_devid_irq()
  irqchip/gic, gic-v3: Make SGIs use handle_percpu_devid_irq()
  irqchip/ocelot: Add support for Jaguar2 platforms
  irqchip/ocelot: Add support for Serval platforms
  irqchip/ocelot: Add support for Luton platforms
  irqchip/ocelot: prepare to support more SoC
  ...
2020-12-15 15:03:31 -08:00
ee2cc4276b cpufreq: Add special-purpose fast-switching callback for drivers
First off, some cpufreq drivers (eg. intel_pstate) can pass hints
beyond the current target frequency to the hardware and there are no
provisions for doing that in the cpufreq framework.  In particular,
today the driver has to assume that it should not allow the frequency
to fall below the one requested by the governor (or the required
capacity may not be provided) which may not be the case and which may
lead to excessive energy usage in some scenarios.

Second, the hints passed by these drivers to the hardware need not be
in terms of the frequency, so representing the utilization numbers
coming from the scheduler as frequency before passing them to those
drivers is not really useful.

Address the two points above by adding a special-purpose replacement
for the ->fast_switch callback, called ->adjust_perf, allowing the
governor to pass abstract performance level (rather than frequency)
values for the minimum (required) and target (desired) performance
along with the CPU capacity to compare them to.

Also update the schedutil governor to use the new callback instead
of ->fast_switch if present and if the utilization mertics are
frequency-invariant (that is requisite for the direct mapping
between the utilization and the CPU performance levels to be a
reasonable approximation).

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
2020-12-15 19:24:18 +01:00
ca6827de4b cpufreq: schedutil: Add util to struct sg_cpu
Instead of passing util and max between functions while computing the
utilization and capacity, store the former in struct sg_cpu (along
with the latter and bw_dl).

This will allow the current utilization value to be compared with the
one obtained previously (which is requisite for some code changes to
follow this one), but also it causes the code to look slightly more
consistent and cleaner.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
2020-12-15 19:24:18 +01:00
722e039d9a Merge tag 'kvmarm-5.11' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into HEAD
KVM/arm64 updates for Linux 5.11

- PSCI relay at EL2 when "protected KVM" is enabled
- New exception injection code
- Simplification of AArch32 system register handling
- Fix PMU accesses when no PMU is enabled
- Expose CSV3 on non-Meltdown hosts
- Cache hierarchy discovery fixes
- PV steal-time cleanups
- Allow function pointers at EL2
- Various host EL2 entry cleanups
- Simplification of the EL2 vector allocation
2020-12-15 12:48:24 -05:00
e1f1320fc0 Merge branch 'pm-cpufreq'
* pm-cpufreq: (31 commits)
  cpufreq: Fix cpufreq_online() return value on errors
  cpufreq: Fix up several kerneldoc comments
  cpufreq: stats: Use local_clock() instead of jiffies
  cpufreq: schedutil: Simplify sugov_update_next_freq()
  cpufreq: intel_pstate: Simplify intel_cpufreq_update_pstate()
  cpufreq: arm_scmi: Discover the power scale in performance protocol
  firmware: arm_scmi: Add power_scale_mw_get() interface
  cpufreq: tegra194: Rename tegra194_get_speed_common function
  cpufreq: tegra194: Remove unnecessary frequency calculation
  cpufreq: tegra186: Simplify cluster information lookup
  cpufreq: tegra186: Fix sparse 'incorrect type in assignment' warning
  cpufreq: imx: fix NVMEM_IMX_OCOTP dependency
  cpufreq: vexpress-spc: Add missing MODULE_ALIAS
  cpufreq: scpi: Add missing MODULE_ALIAS
  cpufreq: loongson1: Add missing MODULE_ALIAS
  cpufreq: sun50i: Add missing MODULE_DEVICE_TABLE
  cpufreq: st: Add missing MODULE_DEVICE_TABLE
  cpufreq: qcom: Add missing MODULE_DEVICE_TABLE
  cpufreq: mediatek: Add missing MODULE_DEVICE_TABLE
  cpufreq: highbank: Add missing MODULE_DEVICE_TABLE
  ...
2020-12-15 15:24:52 +01:00
ae79270232 sched: Optimize finish_lock_switch()
The kernel test robot measured a -1.6% performance regression on
will-it-scale/sched_yield due to commit:

  2558aacff8 ("sched/hotplug: Ensure only per-cpu kthreads run during hotplug")

Even though we were careful to replace a single load with another
single load from the same cacheline.

Restore finish_lock_switch() to the exact state before the offending
patch and solve the problem differently.

Fixes: 2558aacff8 ("sched/hotplug: Ensure only per-cpu kthreads run during hotplug")
Reported-by: kernel test robot <oliver.sang@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20201210161408.GX3021@hirez.programming.kicks-ass.net
2020-12-15 11:27:53 +01:00
3c41e57a1e Merge tag 'irqchip-5.11' of git://git.kernel.org/pub/scm/linux/kernel/git/maz/arm-platforms into irq/core
Pull irqchip updates for 5.11 from Marc Zyngier:

  - Preliminary support for managed interrupts on platform devices
  - Correctly identify allocation of MSIs proxyied by another device
  - Remove the fasteoi IPI flow which has been proved useless
  - Generalise the Ocelot support to new SoCs
  - Improve GICv4.1 vcpu entry, matching the corresponding KVM optimisation
  - Work around spurious interrupts on Qualcomm PDC
  - Random fixes and cleanups

Link: https://lore.kernel.org/r/20201212135626.1479884-1-maz@kernel.org
2020-12-15 10:48:07 +01:00
edd7ab7684 Merge tag 'core-mm-2020-12-14' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull kmap updates from Thomas Gleixner:
 "The new preemtible kmap_local() implementation:

   - Consolidate all kmap_atomic() internals into a generic
     implementation which builds the base for the kmap_local() API and
     make the kmap_atomic() interface wrappers which handle the
     disabling/enabling of preemption and pagefaults.

   - Switch the storage from per-CPU to per task and provide scheduler
     support for clearing mapping when scheduling out and restoring them
     when scheduling back in.

   - Merge the migrate_disable/enable() code, which is also part of the
     scheduler pull request. This was required to make the kmap_local()
     interface available which does not disable preemption when a
     mapping is established. It has to disable migration instead to
     guarantee that the virtual address of the mapped slot is the same
     across preemption.

   - Provide better debug facilities: guard pages and enforced
     utilization of the mapping mechanics on 64bit systems when the
     architecture allows it.

   - Provide the new kmap_local() API which can now be used to cleanup
     the kmap_atomic() usage sites all over the place. Most of the usage
     sites do not require the implicit disabling of preemption and
     pagefaults so the penalty on 64bit and 32bit non-highmem systems is
     removed and quite some of the code can be simplified. A wholesale
     conversion is not possible because some usage depends on the
     implicit side effects and some need to be cleaned up because they
     work around these side effects.

     The migrate disable side effect is only effective on highmem
     systems and when enforced debugging is enabled. On 64bit and 32bit
     non-highmem systems the overhead is completely avoided"

* tag 'core-mm-2020-12-14' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (33 commits)
  ARM: highmem: Fix cache_is_vivt() reference
  x86/crashdump/32: Simplify copy_oldmem_page()
  io-mapping: Provide iomap_local variant
  mm/highmem: Provide kmap_local*
  sched: highmem: Store local kmaps in task struct
  x86: Support kmap_local() forced debugging
  mm/highmem: Provide CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP
  mm/highmem: Provide and use CONFIG_DEBUG_KMAP_LOCAL
  microblaze/mm/highmem: Add dropped #ifdef back
  xtensa/mm/highmem: Make generic kmap_atomic() work correctly
  mm/highmem: Take kmap_high_get() properly into account
  highmem: High implementation details and document API
  Documentation/io-mapping: Remove outdated blurb
  io-mapping: Cleanup atomic iomap
  mm/highmem: Remove the old kmap_atomic cruft
  highmem: Get rid of kmap_types.h
  xtensa/mm/highmem: Switch to generic kmap atomic
  sparc/mm/highmem: Switch to generic kmap atomic
  powerpc/mm/highmem: Switch to generic kmap atomic
  nds32/mm/highmem: Switch to generic kmap atomic
  ...
2020-12-14 18:35:53 -08:00
adb35e8dc9 Merge tag 'sched-core-2020-12-14' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler updates from Thomas Gleixner:

 - migrate_disable/enable() support which originates from the RT tree
   and is now a prerequisite for the new preemptible kmap_local() API
   which aims to replace kmap_atomic().

 - A fair amount of topology and NUMA related improvements

 - Improvements for the frequency invariant calculations

 - Enhanced robustness for the global CPU priority tracking and decision
   making

 - The usual small fixes and enhancements all over the place

* tag 'sched-core-2020-12-14' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (61 commits)
  sched/fair: Trivial correction of the newidle_balance() comment
  sched/fair: Clear SMT siblings after determining the core is not idle
  sched: Fix kernel-doc markup
  x86: Print ratio freq_max/freq_base used in frequency invariance calculations
  x86, sched: Use midpoint of max_boost and max_P for frequency invariance on AMD EPYC
  x86, sched: Calculate frequency invariance for AMD systems
  irq_work: Optimize irq_work_single()
  smp: Cleanup smp_call_function*()
  irq_work: Cleanup
  sched: Limit the amount of NUMA imbalance that can exist at fork time
  sched/numa: Allow a floating imbalance between NUMA nodes
  sched: Avoid unnecessary calculation of load imbalance at clone time
  sched/numa: Rename nr_running and break out the magic number
  sched: Make migrate_disable/enable() independent of RT
  sched/topology: Condition EAS enablement on FIE support
  arm64: Rebuild sched domains on invariance status changes
  sched/topology,schedutil: Wrap sched domains rebuild
  sched/uclamp: Allow to reset a task uclamp constraint value
  sched/core: Fix typos in comments
  Documentation: scheduler: fix information on arch SD flags, sched_domain and sched_debug
  ...
2020-12-14 18:29:11 -08:00
1ac0884d54 Merge tag 'core-entry-2020-12-14' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull core entry/exit updates from Thomas Gleixner:
 "A set of updates for entry/exit handling:

   - More generalization of entry/exit functionality

   - The consolidation work to reclaim TIF flags on x86 and also for
     non-x86 specific TIF flags which are solely relevant for syscall
     related work and have been moved into their own storage space. The
     x86 specific part had to be merged in to avoid a major conflict.

   - The TIF_NOTIFY_SIGNAL work which replaces the inefficient signal
     delivery mode of task work and results in an impressive performance
     improvement for io_uring. The non-x86 consolidation of this is
     going to come seperate via Jens.

   - The selective syscall redirection facility which provides a clean
     and efficient way to support the non-Linux syscalls of WINE by
     catching them at syscall entry and redirecting them to the user
     space emulation. This can be utilized for other purposes as well
     and has been designed carefully to avoid overhead for the regular
     fastpath. This includes the core changes and the x86 support code.

   - Simplification of the context tracking entry/exit handling for the
     users of the generic entry code which guarantee the proper ordering
     and protection.

   - Preparatory changes to make the generic entry code accomodate S390
     specific requirements which are mostly related to their syscall
     restart mechanism"

* tag 'core-entry-2020-12-14' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (36 commits)
  entry: Add syscall_exit_to_user_mode_work()
  entry: Add exit_to_user_mode() wrapper
  entry_Add_enter_from_user_mode_wrapper
  entry: Rename exit_to_user_mode()
  entry: Rename enter_from_user_mode()
  docs: Document Syscall User Dispatch
  selftests: Add benchmark for syscall user dispatch
  selftests: Add kselftest for syscall user dispatch
  entry: Support Syscall User Dispatch on common syscall entry
  kernel: Implement selective syscall userspace redirection
  signal: Expose SYS_USER_DISPATCH si_code type
  x86: vdso: Expose sigreturn address on vdso to the kernel
  MAINTAINERS: Add entry for common entry code
  entry: Fix boot for !CONFIG_GENERIC_ENTRY
  x86: Support HAVE_CONTEXT_TRACKING_OFFSTACK
  context_tracking: Only define schedule_user() on !HAVE_CONTEXT_TRACKING_OFFSTACK archs
  sched: Detect call to schedule from critical entry code
  context_tracking: Don't implement exception_enter/exit() on CONFIG_HAVE_CONTEXT_TRACKING_OFFSTACK
  context_tracking: Introduce HAVE_CONTEXT_TRACKING_OFFSTACK
  x86: Reclaim unused x86 TI flags
  ...
2020-12-14 17:13:53 -08:00
90ac908a41 cpufreq: schedutil: Simplify sugov_update_next_freq()
Rearrange a conditional to make it more straightforward.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
2020-12-11 19:53:58 +01:00
5b78f2dc31 sched/fair: Trivial correction of the newidle_balance() comment
idle_balance() has been renamed to newidle_balance(). To differentiate
with nohz_idle_balance, it seems refining the comment will be helpful
for the readers of the code.

Signed-off-by: Barry Song <song.bao.hua@hisilicon.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lkml.kernel.org/r/20201202220641.22752-1-song.bao.hua@hisilicon.com
2020-12-11 10:30:44 +01:00
13d5a5e9f9 sched/fair: Clear SMT siblings after determining the core is not idle
The clearing of SMT siblings from the SIS mask before checking for an idle
core is a small but unnecessary cost. Defer the clearing of the siblings
until the scan moves to the next potential target. The cost of this was
not measured as it is borderline noise but it should be self-evident.

Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/20201130144020.GS3371@techsingularity.net
2020-12-11 10:30:38 +01:00
59a74b1544 sched: Fix kernel-doc markup
Kernel-doc requires that a kernel-doc markup to be immediately
below the function prototype, as otherwise it will rename it.
So, move sys_sched_yield() markup to the right place.

Also fix the cpu_util() markup: Kernel-doc markups
should use this format:
        identifier - description

Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/50cd6f460aeb872ebe518a8e9cfffda2df8bdb0a.1606823973.git.mchehab+huawei@kernel.org
2020-12-11 10:30:31 +01:00
e45cdc71d1 membarrier: Execute SYNC_CORE on the calling thread
membarrier()'s MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE is documented as
syncing the core on all sibling threads but not necessarily the calling
thread.  This behavior is fundamentally buggy and cannot be used safely.

Suppose a user program has two threads.  Thread A is on CPU 0 and thread B
is on CPU 1.  Thread A modifies some text and calls
membarrier(MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE).

Then thread B executes the modified code.  If, at any point after
membarrier() decides which CPUs to target, thread A could be preempted and
replaced by thread B on CPU 0.  This could even happen on exit from the
membarrier() syscall.  If this happens, thread B will end up running on CPU
0 without having synced.

In principle, this could be fixed by arranging for the scheduler to issue
sync_core_before_usermode() whenever switching between two threads in the
same mm if there is any possibility of a concurrent membarrier() call, but
this would have considerable overhead.  Instead, make membarrier() sync the
calling CPU as well.

As an optimization, this avoids an extra smp_mb() in the default
barrier-only mode and an extra rseq preempt on the caller.

Fixes: 70216e18e5 ("membarrier: Provide core serializing command, *_SYNC_CORE")
Signed-off-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://lore.kernel.org/r/250ded637696d490c69bef1877148db86066881c.1607058304.git.luto@kernel.org
2020-12-09 09:37:43 +01:00
758c9373d8 membarrier: Explicitly sync remote cores when SYNC_CORE is requested
membarrier() does not explicitly sync_core() remote CPUs; instead, it
relies on the assumption that an IPI will result in a core sync.  On x86,
this may be true in practice, but it's not architecturally reliable.  In
particular, the SDM and APM do not appear to guarantee that interrupt
delivery is serializing.  While IRET does serialize, IPI return can
schedule, thereby switching to another task in the same mm that was
sleeping in a syscall.  The new task could then SYSRET back to usermode
without ever executing IRET.

Make this more robust by explicitly calling sync_core_before_usermode()
on remote cores.  (This also helps people who search the kernel tree for
instances of sync_core() and sync_core_before_usermode() -- one might be
surprised that the core membarrier code doesn't currently show up in a
such a search.)

Fixes: 70216e18e5 ("membarrier: Provide core serializing command, *_SYNC_CORE")
Signed-off-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/776b448d5f7bd6b12690707f5ed67bcda7f1d427.1607058304.git.luto@kernel.org
2020-12-09 09:37:43 +01:00
2ecedd7569 membarrier: Add an actual barrier before rseq_preempt()
It seems that most RSEQ membarrier users will expect any stores done before
the membarrier() syscall to be visible to the target task(s).  While this
is extremely likely to be true in practice, nothing actually guarantees it
by a strict reading of the x86 manuals.  Rather than providing this
guarantee by accident and potentially causing a problem down the road, just
add an explicit barrier.

Fixes: 70216e18e5 ("membarrier: Provide core serializing command, *_SYNC_CORE")
Signed-off-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/d3e7197e034fa4852afcf370ca49c30496e58e40.1607058304.git.luto@kernel.org
2020-12-09 09:37:43 +01:00
d3759e7184 irqtime: Move irqtime entry accounting after irq offset incrementation
IRQ time entry is currently accounted before HARDIRQ_OFFSET or
SOFTIRQ_OFFSET are incremented. This is convenient to decide to which
index the cputime to account is dispatched.

Unfortunately it prevents tick_irq_enter() from being called under
HARDIRQ_OFFSET because tick_irq_enter() has to be called before the IRQ
entry accounting due to the necessary clock catch up. As a result we
don't benefit from appropriate lockdep coverage on tick_irq_enter().

To prepare for fixing this, move the IRQ entry cputime accounting after
the preempt offset is incremented. This requires the cputime dispatch
code to handle the extra offset.

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20201202115732.27827-5-frederic@kernel.org
2020-12-02 20:20:05 +01:00
8a6a5920d3 sched/vtime: Consolidate IRQ time accounting
The 3 architectures implementing CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
all have their own version of irq time accounting that dispatch the
cputime to the appropriate index: hardirq, softirq, system, idle,
guest... from an all-in-one function.

Instead of having these ad-hoc versions, move the cputime destination
dispatch decision to the core code and leave only the actual per-index
cputime accounting to the architecture.

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20201202115732.27827-4-frederic@kernel.org
2020-12-02 20:20:05 +01:00
2b91ec9f55 s390/vtime: Use the generic IRQ entry accounting
s390 has its own version of IRQ entry accounting because it doesn't
account the idle time the same way the other architectures do. Only
the actual idle sleep time is accounted as idle time, the rest of the
idle task execution is accounted as system time.

Make the generic IRQ entry accounting aware of architectures that have
their own way of accounting idle time and convert s390 to use it.

This prepares s390 to get involved in further consolidations of IRQ
time accounting.

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20201202115732.27827-3-frederic@kernel.org
2020-12-02 20:20:04 +01:00
7197688b20 sched/cputime: Remove symbol exports from IRQ time accounting
account_irq_enter_time() and account_irq_exit_time() are not called
from modules. EXPORT_SYMBOL_GPL() can be safely removed from the IRQ
cputime accounting functions called from there.

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20201202115732.27827-2-frederic@kernel.org
2020-12-02 20:20:04 +01:00
f91a3aa6bc Merge tag 'locking-urgent-2020-11-29' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull locking fixes from Thomas Gleixner:
 "Two more places which invoke tracing from RCU disabled regions in the
  idle path.

  Similar to the entry path the low level idle functions have to be
  non-instrumentable"

* tag 'locking-urgent-2020-11-29' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  intel_idle: Fix intel_idle() vs tracing
  sched/idle: Fix arch_cpu_idle() vs tracing
2020-11-29 11:19:26 -08:00
a787bdaff8 Merge branch 'linus' into sched/core, to resolve semantic conflict
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2020-11-27 11:10:50 +01:00
545b8c8df4 smp: Cleanup smp_call_function*()
Get rid of the __call_single_node union and cleanup the API a little
to avoid external code relying on the structure layout as much.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
2020-11-24 16:47:49 +01:00
23e6082a52 sched: Limit the amount of NUMA imbalance that can exist at fork time
At fork time currently, a local node can be allowed to fill completely
and allow the periodic load balancer to fix the problem. This can be
problematic in cases where a task creates lots of threads that idle until
woken as part of a worker poll causing a memory bandwidth problem.

However, a "real" workload suffers badly from this behaviour. The workload
in question is mostly NUMA aware but spawns large numbers of threads
that act as a worker pool that can be called from anywhere. These need
to spread early to get reasonable behaviour.

This patch limits how much a local node can fill before spilling over
to another node and it will not be a universal win. Specifically,
very short-lived workloads that fit within a NUMA node would prefer
the memory bandwidth.

As I cannot describe the "real" workload, the best proxy measure I found
for illustration was a page fault microbenchmark. It's not representative
of the workload but demonstrates the hazard of the current behaviour.

pft timings
                                 5.10.0-rc2             5.10.0-rc2
                          imbalancefloat-v2          forkspread-v2
Amean     elapsed-1        46.37 (   0.00%)       46.05 *   0.69%*
Amean     elapsed-4        12.43 (   0.00%)       12.49 *  -0.47%*
Amean     elapsed-7         7.61 (   0.00%)        7.55 *   0.81%*
Amean     elapsed-12        4.79 (   0.00%)        4.80 (  -0.17%)
Amean     elapsed-21        3.13 (   0.00%)        2.89 *   7.74%*
Amean     elapsed-30        3.65 (   0.00%)        2.27 *  37.62%*
Amean     elapsed-48        3.08 (   0.00%)        2.13 *  30.69%*
Amean     elapsed-79        2.00 (   0.00%)        1.90 *   4.95%*
Amean     elapsed-80        2.00 (   0.00%)        1.90 *   4.70%*

This is showing the time to fault regions belonging to threads. The target
machine has 80 logical CPUs and two nodes. Note the ~30% gain when the
machine is approximately the point where one node becomes fully utilised.
The slower results are borderline noise.

Kernel building shows similar benefits around the same balance point.
Generally performance was either neutral or better in the tests conducted.
The main consideration with this patch is the point where fork stops
spreading a task so some workloads may benefit from different balance
points but it would be a risky tuning parameter.

Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/20201120090630.3286-5-mgorman@techsingularity.net
2020-11-24 16:47:48 +01:00
7d2b5dd0bc sched/numa: Allow a floating imbalance between NUMA nodes
Currently, an imbalance is only allowed when a destination node
is almost completely idle. This solved one basic class of problems
and was the cautious approach.

This patch revisits the possibility that NUMA nodes can be imbalanced
until 25% of the CPUs are occupied. The reasoning behind 25% is somewhat
superficial -- it's half the cores when HT is enabled.  At higher
utilisations, balancing should continue as normal and keep things even
until scheduler domains are fully busy or over utilised.

Note that this is not expected to be a universal win. Any benchmark
that prefers spreading as wide as possible with limited communication
will favour the old behaviour as there is more memory bandwidth.
Workloads that communicate heavily in pairs such as netperf or tbench
benefit. For the tests I ran, the vast majority of workloads saw
a benefit so it seems to be a worthwhile trade-off.

Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/20201120090630.3286-4-mgorman@techsingularity.net
2020-11-24 16:47:47 +01:00
5c339005f8 sched: Avoid unnecessary calculation of load imbalance at clone time
In find_idlest_group(), the load imbalance is only relevant when the group
is either overloaded or fully busy but it is calculated unconditionally.
This patch moves the imbalance calculation to the context it is required.
Technically, it is a micro-optimisation but really the benefit is avoiding
confusing one type of imbalance with another depending on the group_type
in the next patch.

No functional change.

Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/20201120090630.3286-3-mgorman@techsingularity.net
2020-11-24 16:47:47 +01:00
abeae76a47 sched/numa: Rename nr_running and break out the magic number
This is simply a preparation patch to make the following patches easier
to read. No functional change.

Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/20201120090630.3286-2-mgorman@techsingularity.net
2020-11-24 16:47:47 +01:00
58c644ba51 sched/idle: Fix arch_cpu_idle() vs tracing
We call arch_cpu_idle() with RCU disabled, but then use
local_irq_{en,dis}able(), which invokes tracing, which relies on RCU.

Switch all arch_cpu_idle() implementations to use
raw_local_irq_{en,dis}able() and carefully manage the
lockdep,rcu,tracing state like we do in entry.

(XXX: we really should change arch_cpu_idle() to not return with
interrupts enabled)

Reported-by: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Mark Rutland <mark.rutland@arm.com>
Link: https://lkml.kernel.org/r/20201120114925.594122626@infradead.org
2020-11-24 16:47:35 +01:00
5fbda3ecd1 sched: highmem: Store local kmaps in task struct
Instead of storing the map per CPU provide and use per task storage. That
prepares for local kmaps which are preemptible.

The context switch code is preparatory and not yet in use because
kmap_atomic() runs with preemption disabled. Will be made usable in the
next step.

The context switch logic is safe even when an interrupt happens after
clearing or before restoring the kmaps. The kmap index in task struct is
not modified so any nesting kmap in an interrupt will use unused indices
and on return the counter is the same as before.

Also add an assert into the return to user space code. Going back to user
space with an active kmap local is a nono.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20201118204007.372935758@linutronix.de
2020-11-24 14:42:09 +01:00
13c8da5db4 Merge branch 'sched/core' into core/mm
Pull the migrate disable mechanics which is a prerequisite for preemptible
kmap_local().
2020-11-24 11:26:11 +01:00
74d862b682 sched: Make migrate_disable/enable() independent of RT
Now that the scheduler can deal with migrate disable properly, there is no
real compelling reason to make it only available for RT.

There are quite some code pathes which needlessly disable preemption in
order to prevent migration and some constructs like kmap_atomic() enforce
it implicitly.

Making it available independent of RT allows to provide a preemptible
variant of kmap_atomic() and makes the code more consistent in general.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Grudgingly-Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20201118204007.269943012@linutronix.de
2020-11-24 11:25:44 +01:00
f4b936f5d6 Merge tag 'sched-urgent-2020-11-22' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler fixes from Thomas Gleixner:
 "A couple of scheduler fixes:

   - Make the conditional update of the overutilized state work
     correctly by caching the relevant flags state before overwriting
     them and checking them afterwards.

   - Fix a data race in the wakeup path which caused loadavg on ARM64
     platforms to become a random number generator.

   - Fix the ordering of the iowaiter accounting operations so it can't
     be decremented before it is incremented.

   - Fix a bug in the deadline scheduler vs. priority inheritance when a
     non-deadline task A has inherited the parameters of a deadline task
     B and then blocks on a non-deadline task C.

     The second inheritance step used the static deadline parameters of
     task A, which are usually 0, instead of further propagating task
     B's parameters. The zero initialized parameters trigger a bug in
     the deadline scheduler"

* tag 'sched-urgent-2020-11-22' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/deadline: Fix priority inheritance with multiple scheduling classes
  sched: Fix rq->nr_iowait ordering
  sched: Fix data-race in wakeup
  sched/fair: Fix overutilized update in enqueue_task_fair()
2020-11-22 13:26:07 -08:00
fa50e2b452 sched/topology: Condition EAS enablement on FIE support
In order to make accurate predictions across CPUs and for all performance
states, Energy Aware Scheduling (EAS) needs frequency-invariant load
tracking signals.

EAS task placement aims to minimize energy consumption, and does so in
part by limiting the search space to only CPUs with the highest spare
capacity (CPU capacity - CPU utilization) in their performance domain.
Those candidates are the placement choices that will keep frequency at
its lowest possible and therefore save the most energy.

But without frequency invariance, a CPU's utilization is relative to the
CPU's current performance level, and not relative to its maximum
performance level, which determines its capacity. As a result, it will
fail to correctly indicate any potential spare capacity obtained by an
increase in a CPU's performance level. Therefore, a non-invariant
utilization signal would render the EAS task placement logic invalid.

Now that we properly report support for the Frequency Invariance Engine
(FIE) through arch_scale_freq_invariant() for arm and arm64 systems,
while also ensuring a re-evaluation of the EAS use conditions for
possible invariance status change, we can assert this is the case when
initializing EAS. Warn and bail out otherwise.

Suggested-by: Quentin Perret <qperret@google.com>
Signed-off-by: Ionela Voinescu <ionela.voinescu@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20201027180713.7642-4-ionela.voinescu@arm.com
2020-11-19 11:25:47 +01:00
31f6a8c0a4 sched/topology,schedutil: Wrap sched domains rebuild
Add the rebuild_sched_domains_energy() function to wrap the functionality
that rebuilds the scheduling domains if any of the Energy Aware Scheduling
(EAS) initialisation conditions change. This functionality is used when
schedutil is added or removed or when EAS is enabled or disabled
through the sched_energy_aware sysctl.

Therefore, create a single function that is used in both these cases and
that can be later reused.

Signed-off-by: Ionela Voinescu <ionela.voinescu@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Quentin Perret <qperret@google.com>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://lkml.kernel.org/r/20201027180713.7642-2-ionela.voinescu@arm.com
2020-11-19 11:25:47 +01:00
480a6ca2dc sched/uclamp: Allow to reset a task uclamp constraint value
In case the user wants to stop controlling a uclamp constraint value
for a task, use the magic value -1 in sched_util_{min,max} with the
appropriate sched_flags (SCHED_FLAG_UTIL_CLAMP_{MIN,MAX}) to indicate
the reset.

The advantage over the 'additional flag' approach (i.e. introducing
SCHED_FLAG_UTIL_CLAMP_RESET) is that no additional flag has to be
exported via uapi. This avoids the need to document how this new flag
has be used in conjunction with the existing uclamp related flags.

The following subtle issue is fixed as well. When a uclamp constraint
value is set on a !user_defined uclamp_se it is currently first reset
and then set.
Fix this by AND'ing !user_defined with !SCHED_FLAG_UTIL_CLAMP which
stands for the 'sched class change' case.
The related condition 'if (uc_se->user_defined)' moved from
__setscheduler_uclamp() into uclamp_reset().

Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Yun Hsiang <hsiang023167@gmail.com>
Link: https://lkml.kernel.org/r/20201113113454.25868-1-dietmar.eggemann@arm.com
2020-11-19 11:25:47 +01:00
b19a888c1e sched/core: Fix typos in comments
Signed-off-by: Tal Zussman <tz2294@columbia.edu>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20201113005156.GA8408@charmander
2020-11-19 11:25:46 +01:00
b5b217346d sched/topology: Warn when NUMA diameter > 2
NUMA topologies where the shortest path between some two nodes requires
three or more hops (i.e. diameter > 2) end up being misrepresented in the
scheduler topology structures.

This is currently detected when booting a kernel with CONFIG_SCHED_DEBUG=y
+ sched_debug on the cmdline, although this will only yield a warning about
sched_group spans not matching sched_domain spans:

  ERROR: groups don't span domain->span

Add an explicit warning for that case, triggered regardless of
CONFIG_SCHED_DEBUG, and decorate it with an appropriate comment.

The topology described in the comment can be booted up on QEMU by appending
the following to your usual QEMU incantation:

    -smp cores=4 \
    -numa node,cpus=0,nodeid=0 -numa node,cpus=1,nodeid=1, \
    -numa node,cpus=2,nodeid=2, -numa node,cpus=3,nodeid=3, \
    -numa dist,src=0,dst=1,val=20, -numa dist,src=0,dst=2,val=30, \
    -numa dist,src=0,dst=3,val=40, -numa dist,src=1,dst=2,val=20, \
    -numa dist,src=1,dst=3,val=30, -numa dist,src=2,dst=3,val=20

A somewhat more realistic topology (6-node mesh) with the same affliction
can be conjured with:

    -smp cores=6 \
    -numa node,cpus=0,nodeid=0 -numa node,cpus=1,nodeid=1, \
    -numa node,cpus=2,nodeid=2, -numa node,cpus=3,nodeid=3, \
    -numa node,cpus=4,nodeid=4, -numa node,cpus=5,nodeid=5, \
    -numa dist,src=0,dst=1,val=20, -numa dist,src=0,dst=2,val=30, \
    -numa dist,src=0,dst=3,val=40, -numa dist,src=0,dst=4,val=30, \
    -numa dist,src=0,dst=5,val=20, \
    -numa dist,src=1,dst=2,val=20, -numa dist,src=1,dst=3,val=30, \
    -numa dist,src=1,dst=4,val=20, -numa dist,src=1,dst=5,val=30, \
    -numa dist,src=2,dst=3,val=20, -numa dist,src=2,dst=4,val=30, \
    -numa dist,src=2,dst=5,val=40, \
    -numa dist,src=3,dst=4,val=20, -numa dist,src=3,dst=5,val=30, \
    -numa dist,src=4,dst=5,val=20

Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Link: https://lore.kernel.org/lkml/jhjtux5edo2.mognet@arm.com
2020-11-19 11:25:46 +01:00
1293771e43 sched: Fix migration_cpu_stop() WARN
Oleksandr reported hitting the WARN in the 'task_rq(p) != rq' branch
of migration_cpu_stop(). Valentin noted that using cpu_of(rq) in that
case is just plain wrong to begin with, since per the earlier branch
that isn't the actual CPU of the task.

Replace both instances of is_cpu_allowed() by a direct p->cpus_mask
test using task_cpu().

Reported-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Debugged-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
2020-11-19 11:25:45 +01:00
d707faa64d sched/core: Add missing completion for affine_move_task() waiters
Qian reported that some fuzzer issuing sched_setaffinity() ends up stuck on
a wait_for_completion(). The problematic pattern seems to be:

  affine_move_task()
      // task_running() case
      stop_one_cpu();
      wait_for_completion(&pending->done);

Combined with, on the stopper side:

  migration_cpu_stop()
    // Task moved between unlocks and scheduling the stopper
    task_rq(p) != rq &&
    // task_running() case
    dest_cpu >= 0

    => no complete_all()

This can happen with both PREEMPT and !PREEMPT, although !PREEMPT should
be more likely to see this given the targeted task has a much bigger window
to block and be woken up elsewhere before the stopper runs.

Make migration_cpu_stop() always look at pending affinity requests; signal
their completion if the stopper hits a rq mismatch but the task is
still within its allowed mask. When Migrate-Disable isn't involved, this
matches the previous set_cpus_allowed_ptr() vs migration_cpu_stop()
behaviour.

Fixes: 6d337eab04 ("sched: Fix migrate_disable() vs set_cpus_allowed_ptr()")
Reported-by: Qian Cai <cai@redhat.com>
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/lkml/8b62fd1ad1b18def27f18e2ee2df3ff5b36d0762.camel@redhat.com
2020-11-19 11:25:45 +01:00
6775de4984 context_tracking: Only define schedule_user() on !HAVE_CONTEXT_TRACKING_OFFSTACK archs
schedule_user() was traditionally used by the entry code's tail to
preempt userspace after the call to user_enter(). Indeed the call to
user_enter() used to be performed upon syscall exit slow path which was
right before the last opportunity to schedule() while resuming to
userspace. The context tracking state had to be saved on the task stack
and set back to CONTEXT_KERNEL temporarily in order to safely switch to
another task.

Only a few archs use it now (namely sparc64 and powerpc64) and those
implementing HAVE_CONTEXT_TRACKING_OFFSTACK definetly can't rely on it.

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20201117151637.259084-5-frederic@kernel.org
2020-11-19 11:25:42 +01:00
9f68b5b74c sched: Detect call to schedule from critical entry code
Detect calls to schedule() between user_enter() and user_exit(). Those
are symptoms of early entry code that either forgot to protect a call
to schedule() inside exception_enter()/exception_exit() or, in the case
of HAVE_CONTEXT_TRACKING_OFFSTACK, enabled interrupts or preemption in
a wrong spot.

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20201117151637.259084-4-frederic@kernel.org
2020-11-19 11:25:42 +01:00
2279f540ea sched/deadline: Fix priority inheritance with multiple scheduling classes
Glenn reported that "an application [he developed produces] a BUG in
deadline.c when a SCHED_DEADLINE task contends with CFS tasks on nested
PTHREAD_PRIO_INHERIT mutexes.  I believe the bug is triggered when a CFS
task that was boosted by a SCHED_DEADLINE task boosts another CFS task
(nested priority inheritance).

 ------------[ cut here ]------------
 kernel BUG at kernel/sched/deadline.c:1462!
 invalid opcode: 0000 [#1] PREEMPT SMP
 CPU: 12 PID: 19171 Comm: dl_boost_bug Tainted: ...
 Hardware name: ...
 RIP: 0010:enqueue_task_dl+0x335/0x910
 Code: ...
 RSP: 0018:ffffc9000c2bbc68 EFLAGS: 00010002
 RAX: 0000000000000009 RBX: ffff888c0af94c00 RCX: ffffffff81e12500
 RDX: 000000000000002e RSI: ffff888c0af94c00 RDI: ffff888c10b22600
 RBP: ffffc9000c2bbd08 R08: 0000000000000009 R09: 0000000000000078
 R10: ffffffff81e12440 R11: ffffffff81e1236c R12: ffff888bc8932600
 R13: ffff888c0af94eb8 R14: ffff888c10b22600 R15: ffff888bc8932600
 FS:  00007fa58ac55700(0000) GS:ffff888c10b00000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 00007fa58b523230 CR3: 0000000bf44ab003 CR4: 00000000007606e0
 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
 PKRU: 55555554
 Call Trace:
  ? intel_pstate_update_util_hwp+0x13/0x170
  rt_mutex_setprio+0x1cc/0x4b0
  task_blocks_on_rt_mutex+0x225/0x260
  rt_spin_lock_slowlock_locked+0xab/0x2d0
  rt_spin_lock_slowlock+0x50/0x80
  hrtimer_grab_expiry_lock+0x20/0x30
  hrtimer_cancel+0x13/0x30
  do_nanosleep+0xa0/0x150
  hrtimer_nanosleep+0xe1/0x230
  ? __hrtimer_init_sleeper+0x60/0x60
  __x64_sys_nanosleep+0x8d/0xa0
  do_syscall_64+0x4a/0x100
  entry_SYSCALL_64_after_hwframe+0x49/0xbe
 RIP: 0033:0x7fa58b52330d
 ...
 ---[ end trace 0000000000000002 ]—

He also provided a simple reproducer creating the situation below:

 So the execution order of locking steps are the following
 (N1 and N2 are non-deadline tasks. D1 is a deadline task. M1 and M2
 are mutexes that are enabled * with priority inheritance.)

 Time moves forward as this timeline goes down:

 N1              N2               D1
 |               |                |
 |               |                |
 Lock(M1)        |                |
 |               |                |
 |             Lock(M2)           |
 |               |                |
 |               |              Lock(M2)
 |               |                |
 |             Lock(M1)           |
 |             (!!bug triggered!) |

Daniel reported a similar situation as well, by just letting ksoftirqd
run with DEADLINE (and eventually block on a mutex).

Problem is that boosted entities (Priority Inheritance) use static
DEADLINE parameters of the top priority waiter. However, there might be
cases where top waiter could be a non-DEADLINE entity that is currently
boosted by a DEADLINE entity from a different lock chain (i.e., nested
priority chains involving entities of non-DEADLINE classes). In this
case, top waiter static DEADLINE parameters could be null (initialized
to 0 at fork()) and replenish_dl_entity() would hit a BUG().

Fix this by keeping track of the original donor and using its parameters
when a task is boosted.

Reported-by: Glenn Elliott <glenn@aurora.tech>
Reported-by: Daniel Bristot de Oliveira <bristot@redhat.com>
Signed-off-by: Juri Lelli <juri.lelli@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Daniel Bristot de Oliveira <bristot@redhat.com>
Link: https://lkml.kernel.org/r/20201117061432.517340-1-juri.lelli@redhat.com
2020-11-17 13:15:28 +01:00
ec618b84f6 sched: Fix rq->nr_iowait ordering
schedule()				ttwu()
    deactivate_task();			  if (p->on_rq && ...) // false
					    atomic_dec(&task_rq(p)->nr_iowait);
    if (prev->in_iowait)
      atomic_inc(&rq->nr_iowait);

Allows nr_iowait to be decremented before it gets incremented,
resulting in more dodgy IO-wait numbers than usual.

Note that because we can now do ttwu_queue_wakelist() before
p->on_cpu==0, we lose the natural ordering and have to further delay
the decrement.

Fixes: c6e7bd7afa ("sched/core: Optimize ttwu() spinning on p->on_cpu")
Reported-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Link: https://lkml.kernel.org/r/20201117093829.GD3121429@hirez.programming.kicks-ass.net
2020-11-17 13:15:28 +01:00
8e1ac4299a sched/fair: Fix overutilized update in enqueue_task_fair()
enqueue_task_fair() attempts to skip the overutilized update for new
tasks as their util_avg is not accurate yet. However, the flag we check
to do so is overwritten earlier on in the function, which makes the
condition pretty much a nop.

Fix this by saving the flag early on.

Fixes: 2802bf3cd9 ("sched/fair: Add over-utilization/tipping point indicator")
Reported-by: Rick Yiu <rickyiu@google.com>
Signed-off-by: Quentin Perret <qperret@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
Link: https://lkml.kernel.org/r/20201112111201.2081902-1-qperret@google.com
2020-11-17 13:15:27 +01:00